Merge branch 'master' into for-5.4/logitech

Signed-off-by: Benjamin Tissoires <benjamin.tissoires@redhat.com>

231 files changed, 2626 insertions, 1627 deletions

diff --git a/net/9p/trans_virtio.c b/net/9p/trans_virtio.c
index 549938af02e7..a3cd90a74012 100644
--- a/net/9p/trans_virtio.c
+++ b/net/9p/trans_virtio.c
@@ -767,10 +767,16 @@ static struct p9_trans_module p9_virtio_trans = {
 /* The standard init function */
 static int __init p9_virtio_init(void)
 {
+	int rc;
+
 	INIT_LIST_HEAD(&virtio_chan_list);
 
 	v9fs_register_trans(&p9_virtio_trans);
-	return register_virtio_driver(&p9_virtio_drv);
+	rc = register_virtio_driver(&p9_virtio_drv);
+	if (rc)
+		v9fs_unregister_trans(&p9_virtio_trans);
+
+	return rc;
 }
 
 static void __exit p9_virtio_cleanup(void)
diff --git a/net/9p/trans_xen.c b/net/9p/trans_xen.c
index 29420ebb8f07..3963eb11c3fb 100644
--- a/net/9p/trans_xen.c
+++ b/net/9p/trans_xen.c
@@ -530,13 +530,19 @@ static struct xenbus_driver xen_9pfs_front_driver = {
 
 static int p9_trans_xen_init(void)
 {
+	int rc;
+
 	if (!xen_domain())
 		return -ENODEV;
 
 	pr_info("Initialising Xen transport for 9pfs\n");
 
 	v9fs_register_trans(&p9_xen_trans);
-	return xenbus_register_frontend(&xen_9pfs_front_driver);
+	rc = xenbus_register_frontend(&xen_9pfs_front_driver);
+	if (rc)
+		v9fs_unregister_trans(&p9_xen_trans);
+
+	return rc;
 }
 module_init(p9_trans_xen_init);
 
diff --git a/net/batman-adv/multicast.c b/net/batman-adv/multicast.c
index 67d7f83009ae..1d5bdf3a4b65 100644
--- a/net/batman-adv/multicast.c
+++ b/net/batman-adv/multicast.c
@@ -2303,7 +2303,7 @@ __batadv_mcast_flags_dump(struct sk_buff *msg, u32 portid,
 
 	while (bucket_tmp < hash->size) {
 		if (batadv_mcast_flags_dump_bucket(msg, portid, cb, hash,
-						   *bucket, &idx_tmp))
+						   bucket_tmp, &idx_tmp))
 			break;
 
 		bucket_tmp++;
@@ -2420,8 +2420,10 @@ void batadv_mcast_purge_orig(struct batadv_orig_node *orig)
 	batadv_mcast_want_unsnoop_update(bat_priv, orig, BATADV_NO_FLAGS);
 	batadv_mcast_want_ipv4_update(bat_priv, orig, BATADV_NO_FLAGS);
 	batadv_mcast_want_ipv6_update(bat_priv, orig, BATADV_NO_FLAGS);
-	batadv_mcast_want_rtr4_update(bat_priv, orig, BATADV_NO_FLAGS);
-	batadv_mcast_want_rtr6_update(bat_priv, orig, BATADV_NO_FLAGS);
+	batadv_mcast_want_rtr4_update(bat_priv, orig,
+				      BATADV_MCAST_WANT_NO_RTR4);
+	batadv_mcast_want_rtr6_update(bat_priv, orig,
+				      BATADV_MCAST_WANT_NO_RTR6);
 
 	spin_unlock_bh(&orig->mcast_handler_lock);
 }
diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c
index b9585e7d9d2e..04bc79359a17 100644
--- a/net/bluetooth/hci_core.c
+++ b/net/bluetooth/hci_core.c
@@ -3202,6 +3202,7 @@ struct hci_dev *hci_alloc_dev(void)
 	hdev->conn_info_min_age = DEFAULT_CONN_INFO_MIN_AGE;
 	hdev->conn_info_max_age = DEFAULT_CONN_INFO_MAX_AGE;
 	hdev->auth_payload_timeout = DEFAULT_AUTH_PAYLOAD_TIMEOUT;
+	hdev->min_enc_key_size = HCI_MIN_ENC_KEY_SIZE;
 
 	mutex_init(&hdev->lock);
 	mutex_init(&hdev->req_lock);
diff --git a/net/bluetooth/hci_debugfs.c b/net/bluetooth/hci_debugfs.c
index bb67f4a5479a..402e2cc54044 100644
--- a/net/bluetooth/hci_debugfs.c
+++ b/net/bluetooth/hci_debugfs.c
@@ -433,6 +433,35 @@ static int auto_accept_delay_set(void *data, u64 val)
 	return 0;
 }
 
+static int min_encrypt_key_size_set(void *data, u64 val)
+{
+	struct hci_dev *hdev = data;
+
+	if (val < 1 || val > 16)
+		return -EINVAL;
+
+	hci_dev_lock(hdev);
+	hdev->min_enc_key_size = val;
+	hci_dev_unlock(hdev);
+
+	return 0;
+}
+
+static int min_encrypt_key_size_get(void *data, u64 *val)
+{
+	struct hci_dev *hdev = data;
+
+	hci_dev_lock(hdev);
+	*val = hdev->min_enc_key_size;
+	hci_dev_unlock(hdev);
+
+	return 0;
+}
+
+DEFINE_SIMPLE_ATTRIBUTE(min_encrypt_key_size_fops,
+			min_encrypt_key_size_get,
+			min_encrypt_key_size_set, "%llu\n");
+
 static int auto_accept_delay_get(void *data, u64 *val)
 {
 	struct hci_dev *hdev = data;
@@ -545,6 +574,8 @@ void hci_debugfs_create_bredr(struct hci_dev *hdev)
 	if (lmp_ssp_capable(hdev)) {
 		debugfs_create_file("ssp_debug_mode", 0444, hdev->debugfs,
 				    hdev, &ssp_debug_mode_fops);
+		debugfs_create_file("min_encrypt_key_size", 0644, hdev->debugfs,
+				    hdev, &min_encrypt_key_size_fops);
 		debugfs_create_file("auto_accept_delay", 0644, hdev->debugfs,
 				    hdev, &auto_accept_delay_fops);
 	}
diff --git a/net/bluetooth/hidp/core.c b/net/bluetooth/hidp/core.c
index 5abd423b55fa..8d889969ae7e 100644
--- a/net/bluetooth/hidp/core.c
+++ b/net/bluetooth/hidp/core.c
@@ -101,6 +101,7 @@ static int hidp_send_message(struct hidp_session *session, struct socket *sock,
 {
 	struct sk_buff *skb;
 	struct sock *sk = sock->sk;
+	int ret;
 
 	BT_DBG("session %p data %p size %d", session, data, size);
 
@@ -114,13 +115,17 @@ static int hidp_send_message(struct hidp_session *session, struct socket *sock,
 	}
 
 	skb_put_u8(skb, hdr);
-	if (data && size > 0)
+	if (data && size > 0) {
 		skb_put_data(skb, data, size);
+		ret = size;
+	} else {
+		ret = 0;
+	}
 
 	skb_queue_tail(transmit, skb);
 	wake_up_interruptible(sk_sleep(sk));
 
-	return 0;
+	return ret;
 }
 
 static int hidp_send_ctrl_message(struct hidp_session *session,
diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c
index cc506fe99b4d..dfc1edb168b7 100644
--- a/net/bluetooth/l2cap_core.c
+++ b/net/bluetooth/l2cap_core.c
@@ -1361,7 +1361,7 @@ static bool l2cap_check_enc_key_size(struct hci_conn *hcon)
 	 * actually encrypted before enforcing a key size.
 	 */
 	return (!test_bit(HCI_CONN_ENCRYPT, &hcon->flags) ||
-		hcon->enc_key_size >= HCI_MIN_ENC_KEY_SIZE);
+		hcon->enc_key_size >= hcon->hdev->min_enc_key_size);
 }
 
 static void l2cap_do_start(struct l2cap_chan *chan)
diff --git a/net/bpfilter/Kconfig b/net/bpfilter/Kconfig
index 91f9d878165e..fed9290e3b41 100644
--- a/net/bpfilter/Kconfig
+++ b/net/bpfilter/Kconfig
@@ -9,7 +9,7 @@ menuconfig BPFILTER
 if BPFILTER
 config BPFILTER_UMH
 	tristate "bpfilter kernel module with user mode helper"
-	depends on $(success,$(srctree)/scripts/cc-can-link.sh $(CC))
+	depends on CC_CAN_LINK
 	default m
 	help
 	  This builds bpfilter kernel module with embedded user mode helper
diff --git a/net/bridge/br.c b/net/bridge/br.c
index d164f63a4345..8a8f9e5f264f 100644
--- a/net/bridge/br.c
+++ b/net/bridge/br.c
@@ -37,12 +37,15 @@ static int br_device_event(struct notifier_block *unused, unsigned long event, v
 	int err;
 
 	if (dev->priv_flags & IFF_EBRIDGE) {
+		err = br_vlan_bridge_event(dev, event, ptr);
+		if (err)
+			return notifier_from_errno(err);
+
 		if (event == NETDEV_REGISTER) {
 			/* register of bridge completed, add sysfs entries */
 			br_sysfs_addbr(dev);
 			return NOTIFY_DONE;
 		}
-		br_vlan_bridge_event(dev, event, ptr);
 	}
 
 	/* not a port of a bridge */
diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c
index 3d8deac2353d..f8cac3702712 100644
--- a/net/bridge/br_multicast.c
+++ b/net/bridge/br_multicast.c
@@ -1388,6 +1388,9 @@ br_multicast_leave_group(struct net_bridge *br,
 			if (!br_port_group_equal(p, port, src))
 				continue;
 
+			if (p->flags & MDB_PG_FLAGS_PERMANENT)
+				break;
+
 			rcu_assign_pointer(*pp, p->next);
 			hlist_del_init(&p->mglist);
 			del_timer(&p->timer);
diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h
index e8cf03b43b7d..646504db0220 100644
--- a/net/bridge/br_private.h
+++ b/net/bridge/br_private.h
@@ -894,8 +894,8 @@ int nbp_get_num_vlan_infos(struct net_bridge_port *p, u32 filter_mask);
 void br_vlan_get_stats(const struct net_bridge_vlan *v,
 		       struct br_vlan_stats *stats);
 void br_vlan_port_event(struct net_bridge_port *p, unsigned long event);
-void br_vlan_bridge_event(struct net_device *dev, unsigned long event,
-			  void *ptr);
+int br_vlan_bridge_event(struct net_device *dev, unsigned long event,
+			 void *ptr);
 
 static inline struct net_bridge_vlan_group *br_vlan_group(
 					const struct net_bridge *br)
@@ -1085,9 +1085,10 @@ static inline void br_vlan_port_event(struct net_bridge_port *p,
 {
 }
 
-static inline void br_vlan_bridge_event(struct net_device *dev,
-					unsigned long event, void *ptr)
+static inline int br_vlan_bridge_event(struct net_device *dev,
+				       unsigned long event, void *ptr)
 {
+	return 0;
 }
 #endif
 
diff --git a/net/bridge/br_vlan.c b/net/bridge/br_vlan.c
index 021cc9f66804..f5b2aeebbfe9 100644
--- a/net/bridge/br_vlan.c
+++ b/net/bridge/br_vlan.c
@@ -1053,7 +1053,6 @@ int br_vlan_init(struct net_bridge *br)
 {
 	struct net_bridge_vlan_group *vg;
 	int ret = -ENOMEM;
-	bool changed;
 
 	vg = kzalloc(sizeof(*vg), GFP_KERNEL);
 	if (!vg)
@@ -1068,17 +1067,10 @@ int br_vlan_init(struct net_bridge *br)
 	br->vlan_proto = htons(ETH_P_8021Q);
 	br->default_pvid = 1;
 	rcu_assign_pointer(br->vlgrp, vg);
-	ret = br_vlan_add(br, 1,
-			  BRIDGE_VLAN_INFO_PVID | BRIDGE_VLAN_INFO_UNTAGGED |
-			  BRIDGE_VLAN_INFO_BRENTRY, &changed, NULL);
-	if (ret)
-		goto err_vlan_add;
 
 out:
 	return ret;
 
-err_vlan_add:
-	vlan_tunnel_deinit(vg);
 err_tunnel_init:
 	rhashtable_destroy(&vg->vlan_hash);
 err_rhtbl:
@@ -1464,13 +1456,23 @@ static void nbp_vlan_set_vlan_dev_state(struct net_bridge_port *p, u16 vid)
 }
 
 /* Must be protected by RTNL. */
-void br_vlan_bridge_event(struct net_device *dev, unsigned long event,
-			  void *ptr)
+int br_vlan_bridge_event(struct net_device *dev, unsigned long event, void *ptr)
 {
 	struct netdev_notifier_changeupper_info *info;
-	struct net_bridge *br;
+	struct net_bridge *br = netdev_priv(dev);
+	bool changed;
+	int ret = 0;
 
 	switch (event) {
+	case NETDEV_REGISTER:
+		ret = br_vlan_add(br, br->default_pvid,
+				  BRIDGE_VLAN_INFO_PVID |
+				  BRIDGE_VLAN_INFO_UNTAGGED |
+				  BRIDGE_VLAN_INFO_BRENTRY, &changed, NULL);
+		break;
+	case NETDEV_UNREGISTER:
+		br_vlan_delete(br, br->default_pvid);
+		break;
 	case NETDEV_CHANGEUPPER:
 		info = ptr;
 		br_vlan_upper_change(dev, info->upper_dev, info->linking);
@@ -1478,12 +1480,13 @@ void br_vlan_bridge_event(struct net_device *dev, unsigned long event,
 
 	case NETDEV_CHANGE:
 	case NETDEV_UP:
-		br = netdev_priv(dev);
 		if (!br_opt_get(br, BROPT_VLAN_BRIDGE_BINDING))
-			return;
+			break;
 		br_vlan_link_state_change(dev, br);
 		break;
 	}
+
+	return ret;
 }
 
 /* Must be protected by RTNL. */
diff --git a/net/bridge/netfilter/Kconfig b/net/bridge/netfilter/Kconfig
index 154fa558bb90..5040fe43f4b4 100644
--- a/net/bridge/netfilter/Kconfig
+++ b/net/bridge/netfilter/Kconfig
@@ -6,7 +6,7 @@
 menuconfig NF_TABLES_BRIDGE
 	depends on BRIDGE && NETFILTER && NF_TABLES
 	select NETFILTER_FAMILY_BRIDGE
-	bool "Ethernet Bridge nf_tables support"
+	tristate "Ethernet Bridge nf_tables support"
 
 if NF_TABLES_BRIDGE
 
@@ -25,6 +25,8 @@ config NF_LOG_BRIDGE
 	tristate "Bridge packet logging"
 	select NF_LOG_COMMON
 
+endif # NF_TABLES_BRIDGE
+
 config NF_CONNTRACK_BRIDGE
 	tristate "IPv4/IPV6 bridge connection tracking support"
 	depends on NF_CONNTRACK
@@ -39,8 +41,6 @@ config NF_CONNTRACK_BRIDGE
 
 	  To compile it as a module, choose M here.  If unsure, say N.
 
-endif # NF_TABLES_BRIDGE
-
 menuconfig BRIDGE_NF_EBTABLES
 	tristate "Ethernet Bridge tables (ebtables) support"
 	depends on BRIDGE && NETFILTER && NETFILTER_XTABLES
diff --git a/net/bridge/netfilter/ebtables.c b/net/bridge/netfilter/ebtables.c
index 963dfdc14827..c8177a89f52c 100644
--- a/net/bridge/netfilter/ebtables.c
+++ b/net/bridge/netfilter/ebtables.c
@@ -1770,20 +1770,28 @@ static int compat_calc_entry(const struct ebt_entry *e,
 	return 0;
 }
 
+static int ebt_compat_init_offsets(unsigned int number)
+{
+	if (number > INT_MAX)
+		return -EINVAL;
+
+	/* also count the base chain policies */
+	number += NF_BR_NUMHOOKS;
+
+	return xt_compat_init_offsets(NFPROTO_BRIDGE, number);
+}
 
 static int compat_table_info(const struct ebt_table_info *info,
 			     struct compat_ebt_replace *newinfo)
 {
 	unsigned int size = info->entries_size;
 	const void *entries = info->entries;
+	int ret;
 
 	newinfo->entries_size = size;
-	if (info->nentries) {
-		int ret = xt_compat_init_offsets(NFPROTO_BRIDGE,
-						 info->nentries);
-		if (ret)
-			return ret;
-	}
+	ret = ebt_compat_init_offsets(info->nentries);
+	if (ret)
+		return ret;
 
 	return EBT_ENTRY_ITERATE(entries, size, compat_calc_entry, info,
 							entries, newinfo);
@@ -2234,11 +2242,9 @@ static int compat_do_replace(struct net *net, void __user *user,
 
 	xt_compat_lock(NFPROTO_BRIDGE);
 
-	if (tmp.nentries) {
-		ret = xt_compat_init_offsets(NFPROTO_BRIDGE, tmp.nentries);
-		if (ret < 0)
-			goto out_unlock;
-	}
+	ret = ebt_compat_init_offsets(tmp.nentries);
+	if (ret < 0)
+		goto out_unlock;
 
 	ret = compat_copy_entries(entries_tmp, tmp.entries_size, &state);
 	if (ret < 0)
@@ -2261,8 +2267,10 @@ static int compat_do_replace(struct net *net, void __user *user,
 	state.buf_kern_len = size64;
 
 	ret = compat_copy_entries(entries_tmp, tmp.entries_size, &state);
-	if (WARN_ON(ret < 0))
+	if (WARN_ON(ret < 0)) {
+		vfree(entries_tmp);
 		goto out_unlock;
+	}
 
 	vfree(entries_tmp);
 	tmp.entries_size = size64;
diff --git a/net/bridge/netfilter/nft_meta_bridge.c b/net/bridge/netfilter/nft_meta_bridge.c
index bed66f536b34..1804e867f715 100644
--- a/net/bridge/netfilter/nft_meta_bridge.c
+++ b/net/bridge/netfilter/nft_meta_bridge.c
@@ -30,13 +30,9 @@ static void nft_meta_bridge_get_eval(const struct nft_expr *expr,
 	switch (priv->key) {
 	case NFT_META_BRI_IIFNAME:
 		br_dev = nft_meta_get_bridge(in);
-		if (!br_dev)
-			goto err;
 		break;
 	case NFT_META_BRI_OIFNAME:
 		br_dev = nft_meta_get_bridge(out);
-		if (!br_dev)
-			goto err;
 		break;
 	case NFT_META_BRI_IIFPVID: {
 		u16 p_pvid;
@@ -61,13 +57,11 @@ static void nft_meta_bridge_get_eval(const struct nft_expr *expr,
 		return;
 	}
 	default:
-		goto out;
+		return nft_meta_get_eval(expr, regs, pkt);
 	}
 
-	strncpy((char *)dest, br_dev->name, IFNAMSIZ);
+	strncpy((char *)dest, br_dev ? br_dev->name : "", IFNAMSIZ);
 	return;
-out:
-	return nft_meta_get_eval(expr, regs, pkt);
 err:
 	regs->verdict.code = NFT_BREAK;
 }
diff --git a/net/can/gw.c b/net/can/gw.c
index 5275ddf580bc..72711053ebe6 100644
--- a/net/can/gw.c
+++ b/net/can/gw.c
@@ -1046,32 +1046,50 @@ static __init int cgw_module_init(void)
 	pr_info("can: netlink gateway (rev " CAN_GW_VERSION ") max_hops=%d\n",
 		max_hops);
 
-	register_pernet_subsys(&cangw_pernet_ops);
+	ret = register_pernet_subsys(&cangw_pernet_ops);
+	if (ret)
+		return ret;
+
+	ret = -ENOMEM;
 	cgw_cache = kmem_cache_create("can_gw", sizeof(struct cgw_job),
 				      0, 0, NULL);
-
 	if (!cgw_cache)
-		return -ENOMEM;
+		goto out_cache_create;
 
 	/* set notifier */
 	notifier.notifier_call = cgw_notifier;
-	register_netdevice_notifier(&notifier);
+	ret = register_netdevice_notifier(&notifier);
+	if (ret)
+		goto out_register_notifier;
 
 	ret = rtnl_register_module(THIS_MODULE, PF_CAN, RTM_GETROUTE,
 				   NULL, cgw_dump_jobs, 0);
-	if (ret) {
-		unregister_netdevice_notifier(&notifier);
-		kmem_cache_destroy(cgw_cache);
-		return -ENOBUFS;
-	}
-
-	/* Only the first call to rtnl_register_module can fail */
-	rtnl_register_module(THIS_MODULE, PF_CAN, RTM_NEWROUTE,
-			     cgw_create_job, NULL, 0);
-	rtnl_register_module(THIS_MODULE, PF_CAN, RTM_DELROUTE,
-			     cgw_remove_job, NULL, 0);
+	if (ret)
+		goto out_rtnl_register1;
+
+	ret = rtnl_register_module(THIS_MODULE, PF_CAN, RTM_NEWROUTE,
+				   cgw_create_job, NULL, 0);
+	if (ret)
+		goto out_rtnl_register2;
+	ret = rtnl_register_module(THIS_MODULE, PF_CAN, RTM_DELROUTE,
+				   cgw_remove_job, NULL, 0);
+	if (ret)
+		goto out_rtnl_register3;
 
 	return 0;
+
+out_rtnl_register3:
+	rtnl_unregister(PF_CAN, RTM_NEWROUTE);
+out_rtnl_register2:
+	rtnl_unregister(PF_CAN, RTM_GETROUTE);
+out_rtnl_register1:
+	unregister_netdevice_notifier(&notifier);
+out_register_notifier:
+	kmem_cache_destroy(cgw_cache);
+out_cache_create:
+	unregister_pernet_subsys(&cangw_pernet_ops);
+
+	return ret;
 }
 
 static __exit void cgw_module_exit(void)
diff --git a/net/ceph/Makefile b/net/ceph/Makefile
index db09defe27d0..59d0ba2072de 100644
--- a/net/ceph/Makefile
+++ b/net/ceph/Makefile
@@ -5,7 +5,7 @@
 obj-$(CONFIG_CEPH_LIB) += libceph.o
 
 libceph-y := ceph_common.o messenger.o msgpool.o buffer.o pagelist.o \
-	mon_client.o \
+	mon_client.o decode.o \
 	cls_lock_client.o \
 	osd_client.o osdmap.o crush/crush.o crush/mapper.o crush/hash.o \
 	striper.o \
diff --git a/net/ceph/ceph_common.c b/net/ceph/ceph_common.c
index 1c811c74bfc0..4eeea4d5c3ef 100644
--- a/net/ceph/ceph_common.c
+++ b/net/ceph/ceph_common.c
@@ -776,9 +776,7 @@ static int __init init_ceph_lib(void)
 {
 	int ret = 0;
 
-	ret = ceph_debugfs_init();
-	if (ret < 0)
-		goto out;
+	ceph_debugfs_init();
 
 	ret = ceph_crypto_init();
 	if (ret < 0)
@@ -803,7 +801,6 @@ out_crypto:
 	ceph_crypto_shutdown();
 out_debugfs:
 	ceph_debugfs_cleanup();
-out:
 	return ret;
 }
 
diff --git a/net/ceph/cls_lock_client.c b/net/ceph/cls_lock_client.c
index 4cc28541281b..17447c19d937 100644
--- a/net/ceph/cls_lock_client.c
+++ b/net/ceph/cls_lock_client.c
@@ -6,6 +6,7 @@
 
 #include <linux/ceph/cls_lock_client.h>
 #include <linux/ceph/decode.h>
+#include <linux/ceph/libceph.h>
 
 /**
  * ceph_cls_lock - grab rados lock for object
@@ -264,8 +265,11 @@ static int decode_locker(void **p, void *end, struct ceph_locker *locker)
 		return ret;
 
 	*p += sizeof(struct ceph_timespec); /* skip expiration */
-	ceph_decode_copy(p, &locker->info.addr, sizeof(locker->info.addr));
-	ceph_decode_addr(&locker->info.addr);
+
+	ret = ceph_decode_entity_addr(p, end, &locker->info.addr);
+	if (ret)
+		return ret;
+
 	len = ceph_decode_32(p);
 	*p += len; /* skip description */
 
@@ -360,7 +364,7 @@ int ceph_cls_lock_info(struct ceph_osd_client *osdc,
 	dout("%s lock_name %s\n", __func__, lock_name);
 	ret = ceph_osdc_call(osdc, oid, oloc, "lock", "get_info",
 			     CEPH_OSD_FLAG_READ, get_info_op_page,
-			     get_info_op_buf_size, reply_page, &reply_len);
+			     get_info_op_buf_size, &reply_page, &reply_len);
 
 	dout("%s: status %d\n", __func__, ret);
 	if (ret >= 0) {
@@ -375,3 +379,47 @@ int ceph_cls_lock_info(struct ceph_osd_client *osdc,
 	return ret;
 }
 EXPORT_SYMBOL(ceph_cls_lock_info);
+
+int ceph_cls_assert_locked(struct ceph_osd_request *req, int which,
+			   char *lock_name, u8 type, char *cookie, char *tag)
+{
+	int assert_op_buf_size;
+	int name_len = strlen(lock_name);
+	int cookie_len = strlen(cookie);
+	int tag_len = strlen(tag);
+	struct page **pages;
+	void *p, *end;
+	int ret;
+
+	assert_op_buf_size = name_len + sizeof(__le32) +
+			     cookie_len + sizeof(__le32) +
+			     tag_len + sizeof(__le32) +
+			     sizeof(u8) + CEPH_ENCODING_START_BLK_LEN;
+	if (assert_op_buf_size > PAGE_SIZE)
+		return -E2BIG;
+
+	ret = osd_req_op_cls_init(req, which, "lock", "assert_locked");
+	if (ret)
+		return ret;
+
+	pages = ceph_alloc_page_vector(1, GFP_NOIO);
+	if (IS_ERR(pages))
+		return PTR_ERR(pages);
+
+	p = page_address(pages[0]);
+	end = p + assert_op_buf_size;
+
+	/* encode cls_lock_assert_op struct */
+	ceph_start_encoding(&p, 1, 1,
+			    assert_op_buf_size - CEPH_ENCODING_START_BLK_LEN);
+	ceph_encode_string(&p, end, lock_name, name_len);
+	ceph_encode_8(&p, type);
+	ceph_encode_string(&p, end, cookie, cookie_len);
+	ceph_encode_string(&p, end, tag, tag_len);
+	WARN_ON(p != end);
+
+	osd_req_op_cls_request_data_pages(req, which, pages, assert_op_buf_size,
+					  0, false, true);
+	return 0;
+}
+EXPORT_SYMBOL(ceph_cls_assert_locked);
diff --git a/net/ceph/debugfs.c b/net/ceph/debugfs.c
index 63aef9915f75..7cb992e55475 100644
--- a/net/ceph/debugfs.c
+++ b/net/ceph/debugfs.c
@@ -389,12 +389,9 @@ CEPH_DEFINE_SHOW_FUNC(monc_show)
 CEPH_DEFINE_SHOW_FUNC(osdc_show)
 CEPH_DEFINE_SHOW_FUNC(client_options_show)
 
-int __init ceph_debugfs_init(void)
+void __init ceph_debugfs_init(void)
 {
 	ceph_debugfs_dir = debugfs_create_dir("ceph", NULL);
-	if (!ceph_debugfs_dir)
-		return -ENOMEM;
-	return 0;
 }
 
 void ceph_debugfs_cleanup(void)
@@ -402,9 +399,8 @@ void ceph_debugfs_cleanup(void)
 	debugfs_remove(ceph_debugfs_dir);
 }
 
-int ceph_debugfs_client_init(struct ceph_client *client)
+void ceph_debugfs_client_init(struct ceph_client *client)
 {
-	int ret = -ENOMEM;
 	char name[80];
 
 	snprintf(name, sizeof(name), "%pU.client%lld", &client->fsid,
@@ -412,56 +408,37 @@ int ceph_debugfs_client_init(struct ceph_client *client)
 
 	dout("ceph_debugfs_client_init %p %s\n", client, name);
 
-	BUG_ON(client->debugfs_dir);
 	client->debugfs_dir = debugfs_create_dir(name, ceph_debugfs_dir);
-	if (!client->debugfs_dir)
-		goto out;
 
 	client->monc.debugfs_file = debugfs_create_file("monc",
 						      0400,
 						      client->debugfs_dir,
 						      client,
 						      &monc_show_fops);
-	if (!client->monc.debugfs_file)
-		goto out;
 
 	client->osdc.debugfs_file = debugfs_create_file("osdc",
 						      0400,
 						      client->debugfs_dir,
 						      client,
 						      &osdc_show_fops);
-	if (!client->osdc.debugfs_file)
-		goto out;
 
 	client->debugfs_monmap = debugfs_create_file("monmap",
 					0400,
 					client->debugfs_dir,
 					client,
 					&monmap_show_fops);
-	if (!client->debugfs_monmap)
-		goto out;
 
 	client->debugfs_osdmap = debugfs_create_file("osdmap",
 					0400,
 					client->debugfs_dir,
 					client,
 					&osdmap_show_fops);
-	if (!client->debugfs_osdmap)
-		goto out;
 
 	client->debugfs_options = debugfs_create_file("client_options",
 					0400,
 					client->debugfs_dir,
 					client,
 					&client_options_show_fops);
-	if (!client->debugfs_options)
-		goto out;
-
-	return 0;
-
-out:
-	ceph_debugfs_client_cleanup(client);
-	return ret;
 }
 
 void ceph_debugfs_client_cleanup(struct ceph_client *client)
@@ -477,18 +454,16 @@ void ceph_debugfs_client_cleanup(struct ceph_client *client)
 
 #else  /* CONFIG_DEBUG_FS */
 
-int __init ceph_debugfs_init(void)
+void __init ceph_debugfs_init(void)
 {
-	return 0;
 }
 
 void ceph_debugfs_cleanup(void)
 {
 }
 
-int ceph_debugfs_client_init(struct ceph_client *client)
+void ceph_debugfs_client_init(struct ceph_client *client)
 {
-	return 0;
 }
 
 void ceph_debugfs_client_cleanup(struct ceph_client *client)
diff --git a/net/ceph/decode.c b/net/ceph/decode.c
new file mode 100644
index 000000000000..eea529595a7a
--- /dev/null
+++ b/net/ceph/decode.c
@@ -0,0 +1,84 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/ceph/decode.h>
+
+static int
+ceph_decode_entity_addr_versioned(void **p, void *end,
+				  struct ceph_entity_addr *addr)
+{
+	int ret;
+	u8 struct_v;
+	u32 struct_len, addr_len;
+	void *struct_end;
+
+	ret = ceph_start_decoding(p, end, 1, "entity_addr_t", &struct_v,
+				  &struct_len);
+	if (ret)
+		goto bad;
+
+	ret = -EINVAL;
+	struct_end = *p + struct_len;
+
+	ceph_decode_copy_safe(p, end, &addr->type, sizeof(addr->type), bad);
+
+	ceph_decode_copy_safe(p, end, &addr->nonce, sizeof(addr->nonce), bad);
+
+	ceph_decode_32_safe(p, end, addr_len, bad);
+	if (addr_len > sizeof(addr->in_addr))
+		goto bad;
+
+	memset(&addr->in_addr, 0, sizeof(addr->in_addr));
+	if (addr_len) {
+		ceph_decode_copy_safe(p, end, &addr->in_addr, addr_len, bad);
+
+		addr->in_addr.ss_family =
+			le16_to_cpu((__force __le16)addr->in_addr.ss_family);
+	}
+
+	/* Advance past anything the client doesn't yet understand */
+	*p = struct_end;
+	ret = 0;
+bad:
+	return ret;
+}
+
+static int
+ceph_decode_entity_addr_legacy(void **p, void *end,
+			       struct ceph_entity_addr *addr)
+{
+	int ret = -EINVAL;
+
+	/* Skip rest of type field */
+	ceph_decode_skip_n(p, end, 3, bad);
+
+	/*
+	 * Clients that don't support ADDR2 always send TYPE_NONE, change it
+	 * to TYPE_LEGACY for forward compatibility.
+	 */
+	addr->type = CEPH_ENTITY_ADDR_TYPE_LEGACY;
+	ceph_decode_copy_safe(p, end, &addr->nonce, sizeof(addr->nonce), bad);
+	memset(&addr->in_addr, 0, sizeof(addr->in_addr));
+	ceph_decode_copy_safe(p, end, &addr->in_addr,
+			      sizeof(addr->in_addr), bad);
+	addr->in_addr.ss_family =
+			be16_to_cpu((__force __be16)addr->in_addr.ss_family);
+	ret = 0;
+bad:
+	return ret;
+}
+
+int
+ceph_decode_entity_addr(void **p, void *end, struct ceph_entity_addr *addr)
+{
+	u8 marker;
+
+	ceph_decode_8_safe(p, end, marker, bad);
+	if (marker == 1)
+		return ceph_decode_entity_addr_versioned(p, end, addr);
+	else if (marker == 0)
+		return ceph_decode_entity_addr_legacy(p, end, addr);
+bad:
+	return -EINVAL;
+}
+EXPORT_SYMBOL(ceph_decode_entity_addr);
+
diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c
index a33402c99321..962f521c863e 100644
--- a/net/ceph/messenger.c
+++ b/net/ceph/messenger.c
@@ -199,12 +199,14 @@ const char *ceph_pr_addr(const struct ceph_entity_addr *addr)
 
 	switch (ss.ss_family) {
 	case AF_INET:
-		snprintf(s, MAX_ADDR_STR_LEN, "%pI4:%hu", &in4->sin_addr,
+		snprintf(s, MAX_ADDR_STR_LEN, "(%d)%pI4:%hu",
+			 le32_to_cpu(addr->type), &in4->sin_addr,
 			 ntohs(in4->sin_port));
 		break;
 
 	case AF_INET6:
-		snprintf(s, MAX_ADDR_STR_LEN, "[%pI6c]:%hu", &in6->sin6_addr,
+		snprintf(s, MAX_ADDR_STR_LEN, "(%d)[%pI6c]:%hu",
+			 le32_to_cpu(addr->type), &in6->sin6_addr,
 			 ntohs(in6->sin6_port));
 		break;
 
@@ -220,7 +222,7 @@ EXPORT_SYMBOL(ceph_pr_addr);
 static void encode_my_addr(struct ceph_messenger *msgr)
 {
 	memcpy(&msgr->my_enc_addr, &msgr->inst.addr, sizeof(msgr->my_enc_addr));
-	ceph_encode_addr(&msgr->my_enc_addr);
+	ceph_encode_banner_addr(&msgr->my_enc_addr);
 }
 
 /*
@@ -1732,12 +1734,14 @@ static int read_partial_banner(struct ceph_connection *con)
 	ret = read_partial(con, end, size, &con->actual_peer_addr);
 	if (ret <= 0)
 		goto out;
+	ceph_decode_banner_addr(&con->actual_peer_addr);
 
 	size = sizeof (con->peer_addr_for_me);
 	end += size;
 	ret = read_partial(con, end, size, &con->peer_addr_for_me);
 	if (ret <= 0)
 		goto out;
+	ceph_decode_banner_addr(&con->peer_addr_for_me);
 
 out:
 	return ret;
@@ -1981,6 +1985,7 @@ int ceph_parse_ips(const char *c, const char *end,
 		}
 
 		addr_set_port(&addr[i], port);
+		addr[i].type = CEPH_ENTITY_ADDR_TYPE_LEGACY;
 
 		dout("parse_ips got %s\n", ceph_pr_addr(&addr[i]));
 
@@ -2011,9 +2016,6 @@ static int process_banner(struct ceph_connection *con)
 	if (verify_hello(con) < 0)
 		return -1;
 
-	ceph_decode_addr(&con->actual_peer_addr);
-	ceph_decode_addr(&con->peer_addr_for_me);
-
 	/*
 	 * Make sure the other end is who we wanted.  note that the other
 	 * end may not yet know their ip address, so if it's 0.0.0.0, give
diff --git a/net/ceph/mon_client.c b/net/ceph/mon_client.c
index 895679d3529b..0520bf9825aa 100644
--- a/net/ceph/mon_client.c
+++ b/net/ceph/mon_client.c
@@ -39,7 +39,7 @@ static int __validate_auth(struct ceph_mon_client *monc);
 /*
  * Decode a monmap blob (e.g., during mount).
  */
-struct ceph_monmap *ceph_monmap_decode(void *p, void *end)
+static struct ceph_monmap *ceph_monmap_decode(void *p, void *end)
 {
 	struct ceph_monmap *m = NULL;
 	int i, err = -EINVAL;
@@ -50,7 +50,7 @@ struct ceph_monmap *ceph_monmap_decode(void *p, void *end)
 	ceph_decode_32_safe(&p, end, len, bad);
 	ceph_decode_need(&p, end, len, bad);
 
-	dout("monmap_decode %p %p len %d\n", p, end, (int)(end-p));
+	dout("monmap_decode %p %p len %d (%d)\n", p, end, len, (int)(end-p));
 	p += sizeof(u16);  /* skip version */
 
 	ceph_decode_need(&p, end, sizeof(fsid) + 2*sizeof(u32), bad);
@@ -58,7 +58,6 @@ struct ceph_monmap *ceph_monmap_decode(void *p, void *end)
 	epoch = ceph_decode_32(&p);
 
 	num_mon = ceph_decode_32(&p);
-	ceph_decode_need(&p, end, num_mon*sizeof(m->mon_inst[0]), bad);
 
 	if (num_mon > CEPH_MAX_MON)
 		goto bad;
@@ -68,17 +67,22 @@ struct ceph_monmap *ceph_monmap_decode(void *p, void *end)
 	m->fsid = fsid;
 	m->epoch = epoch;
 	m->num_mon = num_mon;
-	ceph_decode_copy(&p, m->mon_inst, num_mon*sizeof(m->mon_inst[0]));
-	for (i = 0; i < num_mon; i++)
-		ceph_decode_addr(&m->mon_inst[i].addr);
-
+	for (i = 0; i < num_mon; ++i) {
+		struct ceph_entity_inst *inst = &m->mon_inst[i];
+
+		/* copy name portion */
+		ceph_decode_copy_safe(&p, end, &inst->name,
+					sizeof(inst->name), bad);
+		err = ceph_decode_entity_addr(&p, end, &inst->addr);
+		if (err)
+			goto bad;
+	}
 	dout("monmap_decode epoch %d, num_mon %d\n", m->epoch,
 	     m->num_mon);
 	for (i = 0; i < m->num_mon; i++)
 		dout("monmap_decode  mon%d is %s\n", i,
 		     ceph_pr_addr(&m->mon_inst[i].addr));
 	return m;
-
 bad:
 	dout("monmap_decode failed with %d\n", err);
 	kfree(m);
@@ -469,6 +473,7 @@ static void ceph_monc_handle_map(struct ceph_mon_client *monc,
 	if (IS_ERR(monmap)) {
 		pr_err("problem decoding monmap, %d\n",
 		       (int)PTR_ERR(monmap));
+		ceph_msg_dump(msg);
 		goto out;
 	}
 
diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c
index 9a8eca5eda65..0b2df09b2554 100644
--- a/net/ceph/osd_client.c
+++ b/net/ceph/osd_client.c
@@ -171,14 +171,6 @@ static void ceph_osd_data_bvecs_init(struct ceph_osd_data *osd_data,
 	osd_data->num_bvecs = num_bvecs;
 }
 
-#define osd_req_op_data(oreq, whch, typ, fld)				\
-({									\
-	struct ceph_osd_request *__oreq = (oreq);			\
-	unsigned int __whch = (whch);					\
-	BUG_ON(__whch >= __oreq->r_num_ops);				\
-	&__oreq->r_ops[__whch].typ.fld;					\
-})
-
 static struct ceph_osd_data *
 osd_req_op_raw_data_in(struct ceph_osd_request *osd_req, unsigned int which)
 {
@@ -478,7 +470,7 @@ static void request_release_checks(struct ceph_osd_request *req)
 {
 	WARN_ON(!RB_EMPTY_NODE(&req->r_node));
 	WARN_ON(!RB_EMPTY_NODE(&req->r_mc_node));
-	WARN_ON(!list_empty(&req->r_unsafe_item));
+	WARN_ON(!list_empty(&req->r_private_item));
 	WARN_ON(req->r_osd);
 }
 
@@ -538,7 +530,7 @@ static void request_init(struct ceph_osd_request *req)
 	init_completion(&req->r_completion);
 	RB_CLEAR_NODE(&req->r_node);
 	RB_CLEAR_NODE(&req->r_mc_node);
-	INIT_LIST_HEAD(&req->r_unsafe_item);
+	INIT_LIST_HEAD(&req->r_private_item);
 
 	target_init(&req->r_t);
 }
@@ -4914,20 +4906,26 @@ static int decode_watcher(void **p, void *end, struct ceph_watch_item *item)
 	ret = ceph_start_decoding(p, end, 2, "watch_item_t",
 				  &struct_v, &struct_len);
 	if (ret)
-		return ret;
+		goto bad;
+
+	ret = -EINVAL;
+	ceph_decode_copy_safe(p, end, &item->name, sizeof(item->name), bad);
+	ceph_decode_64_safe(p, end, item->cookie, bad);
+	ceph_decode_skip_32(p, end, bad); /* skip timeout seconds */
 
-	ceph_decode_copy(p, &item->name, sizeof(item->name));
-	item->cookie = ceph_decode_64(p);
-	*p += 4; /* skip timeout_seconds */
 	if (struct_v >= 2) {
-		ceph_decode_copy(p, &item->addr, sizeof(item->addr));
-		ceph_decode_addr(&item->addr);
+		ret = ceph_decode_entity_addr(p, end, &item->addr);
+		if (ret)
+			goto bad;
+	} else {
+		ret = 0;
 	}
 
 	dout("%s %s%llu cookie %llu addr %s\n", __func__,
 	     ENTITY_NAME(item->name), item->cookie,
 	     ceph_pr_addr(&item->addr));
-	return 0;
+bad:
+	return ret;
 }
 
 static int decode_watchers(void **p, void *end,
@@ -5044,12 +5042,12 @@ int ceph_osdc_call(struct ceph_osd_client *osdc,
 		   const char *class, const char *method,
 		   unsigned int flags,
 		   struct page *req_page, size_t req_len,
-		   struct page *resp_page, size_t *resp_len)
+		   struct page **resp_pages, size_t *resp_len)
 {
 	struct ceph_osd_request *req;
 	int ret;
 
-	if (req_len > PAGE_SIZE || (resp_page && *resp_len > PAGE_SIZE))
+	if (req_len > PAGE_SIZE)
 		return -E2BIG;
 
 	req = ceph_osdc_alloc_request(osdc, NULL, 1, false, GFP_NOIO);
@@ -5067,8 +5065,8 @@ int ceph_osdc_call(struct ceph_osd_client *osdc,
 	if (req_page)
 		osd_req_op_cls_request_data_pages(req, 0, &req_page, req_len,
 						  0, false, false);
-	if (resp_page)
-		osd_req_op_cls_response_data_pages(req, 0, &resp_page,
+	if (resp_pages)
+		osd_req_op_cls_response_data_pages(req, 0, resp_pages,
 						   *resp_len, 0, false, false);
 
 	ret = ceph_osdc_alloc_messages(req, GFP_NOIO);
@@ -5079,7 +5077,7 @@ int ceph_osdc_call(struct ceph_osd_client *osdc,
 	ret = ceph_osdc_wait_request(osdc, req);
 	if (ret >= 0) {
 		ret = req->r_ops[0].rval;
-		if (resp_page)
+		if (resp_pages)
 			*resp_len = req->r_ops[0].outdata_len;
 	}
 
diff --git a/net/ceph/osdmap.c b/net/ceph/osdmap.c
index 48a31dc9161c..90437906b7bc 100644
--- a/net/ceph/osdmap.c
+++ b/net/ceph/osdmap.c
@@ -1489,11 +1489,9 @@ static int osdmap_decode(void **p, void *end, struct ceph_osdmap *map)
 
 	/* osd_state, osd_weight, osd_addrs->client_addr */
 	ceph_decode_need(p, end, 3*sizeof(u32) +
-			 map->max_osd*((struct_v >= 5 ? sizeof(u32) :
-							sizeof(u8)) +
-				       sizeof(*map->osd_weight) +
-				       sizeof(*map->osd_addr)), e_inval);
-
+			 map->max_osd*(struct_v >= 5 ? sizeof(u32) :
+						       sizeof(u8)) +
+				       sizeof(*map->osd_weight), e_inval);
 	if (ceph_decode_32(p) != map->max_osd)
 		goto e_inval;
 
@@ -1514,9 +1512,11 @@ static int osdmap_decode(void **p, void *end, struct ceph_osdmap *map)
 	if (ceph_decode_32(p) != map->max_osd)
 		goto e_inval;
 
-	ceph_decode_copy(p, map->osd_addr, map->max_osd*sizeof(*map->osd_addr));
-	for (i = 0; i < map->max_osd; i++)
-		ceph_decode_addr(&map->osd_addr[i]);
+	for (i = 0; i < map->max_osd; i++) {
+		err = ceph_decode_entity_addr(p, end, &map->osd_addr[i]);
+		if (err)
+			goto bad;
+	}
 
 	/* pg_temp */
 	err = decode_pg_temp(p, end, map);
@@ -1618,12 +1618,17 @@ static int decode_new_up_state_weight(void **p, void *end, u8 struct_v,
 	void *new_state;
 	void *new_weight_end;
 	u32 len;
+	int i;
 
 	new_up_client = *p;
 	ceph_decode_32_safe(p, end, len, e_inval);
-	len *= sizeof(u32) + sizeof(struct ceph_entity_addr);
-	ceph_decode_need(p, end, len, e_inval);
-	*p += len;
+	for (i = 0; i < len; ++i) {
+		struct ceph_entity_addr addr;
+
+		ceph_decode_skip_32(p, end, e_inval);
+		if (ceph_decode_entity_addr(p, end, &addr))
+			goto e_inval;
+	}
 
 	new_state = *p;
 	ceph_decode_32_safe(p, end, len, e_inval);
@@ -1699,9 +1704,9 @@ static int decode_new_up_state_weight(void **p, void *end, u8 struct_v,
 		struct ceph_entity_addr addr;
 
 		osd = ceph_decode_32(p);
-		ceph_decode_copy(p, &addr, sizeof(addr));
-		ceph_decode_addr(&addr);
 		BUG_ON(osd >= map->max_osd);
+		if (ceph_decode_entity_addr(p, end, &addr))
+			goto e_inval;
 		pr_info("osd%d up\n", osd);
 		map->osd_state[osd] |= CEPH_OSD_EXISTS | CEPH_OSD_UP;
 		map->osd_addr[osd] = addr;
diff --git a/net/ceph/pagevec.c b/net/ceph/pagevec.c
index 74cafc0142ea..64305e7056a1 100644
--- a/net/ceph/pagevec.c
+++ b/net/ceph/pagevec.c
@@ -10,39 +10,6 @@
 
 #include <linux/ceph/libceph.h>
 
-/*
- * build a vector of user pages
- */
-struct page **ceph_get_direct_page_vector(const void __user *data,
-					  int num_pages, bool write_page)
-{
-	struct page **pages;
-	int got = 0;
-	int rc = 0;
-
-	pages = kmalloc_array(num_pages, sizeof(*pages), GFP_NOFS);
-	if (!pages)
-		return ERR_PTR(-ENOMEM);
-
-	while (got < num_pages) {
-		rc = get_user_pages_fast(
-		    (unsigned long)data + ((unsigned long)got * PAGE_SIZE),
-		    num_pages - got, write_page ? FOLL_WRITE : 0, pages + got);
-		if (rc < 0)
-			break;
-		BUG_ON(rc == 0);
-		got += rc;
-	}
-	if (rc < 0)
-		goto fail;
-	return pages;
-
-fail:
-	ceph_put_page_vector(pages, got, false);
-	return ERR_PTR(rc);
-}
-EXPORT_SYMBOL(ceph_get_direct_page_vector);
-
 void ceph_put_page_vector(struct page **pages, int num_pages, bool dirty)
 {
 	int i;
diff --git a/net/ceph/striper.c b/net/ceph/striper.c
index c36462dc86b7..3b3fa75d1189 100644
--- a/net/ceph/striper.c
+++ b/net/ceph/striper.c
@@ -259,3 +259,20 @@ int ceph_extent_to_file(struct ceph_file_layout *l,
 	return 0;
 }
 EXPORT_SYMBOL(ceph_extent_to_file);
+
+u64 ceph_get_num_objects(struct ceph_file_layout *l, u64 size)
+{
+	u64 period = (u64)l->stripe_count * l->object_size;
+	u64 num_periods = DIV64_U64_ROUND_UP(size, period);
+	u64 remainder_bytes;
+	u64 remainder_objs = 0;
+
+	div64_u64_rem(size, period, &remainder_bytes);
+	if (remainder_bytes > 0 &&
+	    remainder_bytes < (u64)l->stripe_count * l->stripe_unit)
+		remainder_objs = l->stripe_count -
+			    DIV_ROUND_UP_ULL(remainder_bytes, l->stripe_unit);
+
+	return num_periods * l->stripe_count - remainder_objs;
+}
+EXPORT_SYMBOL(ceph_get_num_objects);
diff --git a/net/compat.c b/net/compat.c
index 3f9ce609397f..0f7ded26059e 100644
--- a/net/compat.c
+++ b/net/compat.c
@@ -80,9 +80,10 @@ int get_compat_msghdr(struct msghdr *kmsg,
 
 	kmsg->msg_iocb = NULL;
 
-	return compat_import_iovec(save_addr ? READ : WRITE,
+	err = compat_import_iovec(save_addr ? READ : WRITE,
 				   compat_ptr(msg.msg_iov), msg.msg_iovlen,
 				   UIO_FASTIOV, iov, &kmsg->msg_iter);
+	return err < 0 ? err : 0;
 }
 
 /* Bleech... */
diff --git a/net/core/dev.c b/net/core/dev.c
index fc676b2610e3..0891f499c1bb 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -4374,12 +4374,17 @@ static u32 netif_receive_generic_xdp(struct sk_buff *skb,
 
 	act = bpf_prog_run_xdp(xdp_prog, xdp);
 
+	/* check if bpf_xdp_adjust_head was used */
 	off = xdp->data - orig_data;
-	if (off > 0)
-		__skb_pull(skb, off);
-	else if (off < 0)
-		__skb_push(skb, -off);
-	skb->mac_header += off;
+	if (off) {
+		if (off > 0)
+			__skb_pull(skb, off);
+		else if (off < 0)
+			__skb_push(skb, -off);
+
+		skb->mac_header += off;
+		skb_reset_network_header(skb);
+	}
 
 	/* check if bpf_xdp_adjust_tail was used. it can only "shrink"
 	 * pckt.
@@ -9701,6 +9706,8 @@ static void __net_exit default_device_exit(struct net *net)
 
 		/* Push remaining network devices to init_net */
 		snprintf(fb_name, IFNAMSIZ, "dev%d", dev->ifindex);
+		if (__dev_get_by_name(&init_net, fb_name))
+			snprintf(fb_name, IFNAMSIZ, "dev%%d");
 		err = dev_change_net_namespace(dev, &init_net, fb_name);
 		if (err) {
 			pr_emerg("%s: failed to move %s to init_net: %d\n",
diff --git a/net/core/filter.c b/net/core/filter.c
index 47f6386fb17a..7878f918b8c0 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -4335,7 +4335,7 @@ BPF_CALL_5(bpf_setsockopt, struct bpf_sock_ops_kern *, bpf_sock,
 						    TCP_CA_NAME_MAX-1));
 			name[TCP_CA_NAME_MAX-1] = 0;
 			ret = tcp_set_congestion_control(sk, name, false,
-							 reinit);
+							 reinit, true);
 		} else {
 			struct tcp_sock *tp = tcp_sk(sk);
 
@@ -6884,20 +6884,30 @@ static bool sock_addr_is_valid_access(int off, int size,
 	case bpf_ctx_range(struct bpf_sock_addr, msg_src_ip4):
 	case bpf_ctx_range_till(struct bpf_sock_addr, msg_src_ip6[0],
 				msg_src_ip6[3]):
-		/* Only narrow read access allowed for now. */
 		if (type == BPF_READ) {
 			bpf_ctx_record_field_size(info, size_default);
+
+			if (bpf_ctx_wide_access_ok(off, size,
+						   struct bpf_sock_addr,
+						   user_ip6))
+				return true;
+
+			if (bpf_ctx_wide_access_ok(off, size,
+						   struct bpf_sock_addr,
+						   msg_src_ip6))
+				return true;
+
 			if (!bpf_ctx_narrow_access_ok(off, size, size_default))
 				return false;
 		} else {
-			if (bpf_ctx_wide_store_ok(off, size,
-						  struct bpf_sock_addr,
-						  user_ip6))
+			if (bpf_ctx_wide_access_ok(off, size,
+						   struct bpf_sock_addr,
+						   user_ip6))
 				return true;
 
-			if (bpf_ctx_wide_store_ok(off, size,
-						  struct bpf_sock_addr,
-						  msg_src_ip6))
+			if (bpf_ctx_wide_access_ok(off, size,
+						   struct bpf_sock_addr,
+						   msg_src_ip6))
 				return true;
 
 			if (size != size_default)
@@ -7445,12 +7455,12 @@ static u32 bpf_convert_ctx_access(enum bpf_access_type type,
 	case offsetof(struct __sk_buff, gso_segs):
 		/* si->dst_reg = skb_shinfo(SKB); */
 #ifdef NET_SKBUFF_DATA_USES_OFFSET
-		*insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, head),
-				      si->dst_reg, si->src_reg,
-				      offsetof(struct sk_buff, head));
 		*insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, end),
 				      BPF_REG_AX, si->src_reg,
 				      offsetof(struct sk_buff, end));
+		*insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, head),
+				      si->dst_reg, si->src_reg,
+				      offsetof(struct sk_buff, head));
 		*insn++ = BPF_ALU64_REG(BPF_ADD, si->dst_reg, BPF_REG_AX);
 #else
 		*insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, end),
diff --git a/net/core/flow_offload.c b/net/core/flow_offload.c
index 76f8db3841d7..d63b970784dc 100644
--- a/net/core/flow_offload.c
+++ b/net/core/flow_offload.c
@@ -165,7 +165,7 @@ void flow_rule_match_enc_opts(const struct flow_rule *rule,
 }
 EXPORT_SYMBOL(flow_rule_match_enc_opts);
 
-struct flow_block_cb *flow_block_cb_alloc(struct net *net, tc_setup_cb_t *cb,
+struct flow_block_cb *flow_block_cb_alloc(flow_setup_cb_t *cb,
 					  void *cb_ident, void *cb_priv,
 					  void (*release)(void *cb_priv))
 {
@@ -175,7 +175,6 @@ struct flow_block_cb *flow_block_cb_alloc(struct net *net, tc_setup_cb_t *cb,
 	if (!block_cb)
 		return ERR_PTR(-ENOMEM);
 
-	block_cb->net = net;
 	block_cb->cb = cb;
 	block_cb->cb_ident = cb_ident;
 	block_cb->cb_priv = cb_priv;
@@ -194,14 +193,13 @@ void flow_block_cb_free(struct flow_block_cb *block_cb)
 }
 EXPORT_SYMBOL(flow_block_cb_free);
 
-struct flow_block_cb *flow_block_cb_lookup(struct flow_block_offload *f,
-					   tc_setup_cb_t *cb, void *cb_ident)
+struct flow_block_cb *flow_block_cb_lookup(struct flow_block *block,
+					   flow_setup_cb_t *cb, void *cb_ident)
 {
 	struct flow_block_cb *block_cb;
 
-	list_for_each_entry(block_cb, f->driver_block_list, driver_list) {
-		if (block_cb->net == f->net &&
-		    block_cb->cb == cb &&
+	list_for_each_entry(block_cb, &block->cb_list, list) {
+		if (block_cb->cb == cb &&
 		    block_cb->cb_ident == cb_ident)
 			return block_cb;
 	}
@@ -228,7 +226,7 @@ unsigned int flow_block_cb_decref(struct flow_block_cb *block_cb)
 }
 EXPORT_SYMBOL(flow_block_cb_decref);
 
-bool flow_block_cb_is_busy(tc_setup_cb_t *cb, void *cb_ident,
+bool flow_block_cb_is_busy(flow_setup_cb_t *cb, void *cb_ident,
 			   struct list_head *driver_block_list)
 {
 	struct flow_block_cb *block_cb;
@@ -245,7 +243,8 @@ EXPORT_SYMBOL(flow_block_cb_is_busy);
 
 int flow_block_cb_setup_simple(struct flow_block_offload *f,
 			       struct list_head *driver_block_list,
-			       tc_setup_cb_t *cb, void *cb_ident, void *cb_priv,
+			       flow_setup_cb_t *cb,
+			       void *cb_ident, void *cb_priv,
 			       bool ingress_only)
 {
 	struct flow_block_cb *block_cb;
@@ -261,8 +260,7 @@ int flow_block_cb_setup_simple(struct flow_block_offload *f,
 		if (flow_block_cb_is_busy(cb, cb_ident, driver_block_list))
 			return -EBUSY;
 
-		block_cb = flow_block_cb_alloc(f->net, cb, cb_ident,
-					       cb_priv, NULL);
+		block_cb = flow_block_cb_alloc(cb, cb_ident, cb_priv, NULL);
 		if (IS_ERR(block_cb))
 			return PTR_ERR(block_cb);
 
@@ -270,7 +268,7 @@ int flow_block_cb_setup_simple(struct flow_block_offload *f,
 		list_add_tail(&block_cb->driver_list, driver_block_list);
 		return 0;
 	case FLOW_BLOCK_UNBIND:
-		block_cb = flow_block_cb_lookup(f, cb, cb_ident);
+		block_cb = flow_block_cb_lookup(f->block, cb, cb_ident);
 		if (!block_cb)
 			return -ENOENT;
 
diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index 742cea4ce72e..f79e61c570ea 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -1124,6 +1124,7 @@ int __neigh_event_send(struct neighbour *neigh, struct sk_buff *skb)
 
 			atomic_set(&neigh->probes,
 				   NEIGH_VAR(neigh->parms, UCAST_PROBES));
+			neigh_del_timer(neigh);
 			neigh->nud_state     = NUD_INCOMPLETE;
 			neigh->updated = now;
 			next = now + max(NEIGH_VAR(neigh->parms, RETRANS_TIME),
@@ -1140,6 +1141,7 @@ int __neigh_event_send(struct neighbour *neigh, struct sk_buff *skb)
 		}
 	} else if (neigh->nud_state & NUD_STALE) {
 		neigh_dbg(2, "neigh %p is delayed\n", neigh);
+		neigh_del_timer(neigh);
 		neigh->nud_state = NUD_DELAY;
 		neigh->updated = jiffies;
 		neigh_add_timer(neigh, jiffies +
@@ -3374,8 +3376,6 @@ void neigh_app_ns(struct neighbour *n)
 EXPORT_SYMBOL(neigh_app_ns);
 
 #ifdef CONFIG_SYSCTL
-static int zero;
-static int int_max = INT_MAX;
 static int unres_qlen_max = INT_MAX / SKB_TRUESIZE(ETH_FRAME_LEN);
 
 static int proc_unres_qlen(struct ctl_table *ctl, int write,
@@ -3384,7 +3384,7 @@ static int proc_unres_qlen(struct ctl_table *ctl, int write,
 	int size, ret;
 	struct ctl_table tmp = *ctl;
 
-	tmp.extra1 = &zero;
+	tmp.extra1 = SYSCTL_ZERO;
 	tmp.extra2 = &unres_qlen_max;
 	tmp.data = &size;
 
@@ -3449,8 +3449,8 @@ static int neigh_proc_dointvec_zero_intmax(struct ctl_table *ctl, int write,
 	struct ctl_table tmp = *ctl;
 	int ret;
 
-	tmp.extra1 = &zero;
-	tmp.extra2 = &int_max;
+	tmp.extra1 = SYSCTL_ZERO;
+	tmp.extra2 = SYSCTL_INT_MAX;
 
 	ret = proc_dointvec_minmax(&tmp, write, buffer, lenp, ppos);
 	neigh_proc_update(ctl, write);
@@ -3595,24 +3595,24 @@ static struct neigh_sysctl_table {
 			.procname	= "gc_thresh1",
 			.maxlen		= sizeof(int),
 			.mode		= 0644,
-			.extra1 	= &zero,
-			.extra2		= &int_max,
+			.extra1		= SYSCTL_ZERO,
+			.extra2		= SYSCTL_INT_MAX,
 			.proc_handler	= proc_dointvec_minmax,
 		},
 		[NEIGH_VAR_GC_THRESH2] = {
 			.procname	= "gc_thresh2",
 			.maxlen		= sizeof(int),
 			.mode		= 0644,
-			.extra1 	= &zero,
-			.extra2		= &int_max,
+			.extra1		= SYSCTL_ZERO,
+			.extra2		= SYSCTL_INT_MAX,
 			.proc_handler	= proc_dointvec_minmax,
 		},
 		[NEIGH_VAR_GC_THRESH3] = {
 			.procname	= "gc_thresh3",
 			.maxlen		= sizeof(int),
 			.mode		= 0644,
-			.extra1 	= &zero,
-			.extra2		= &int_max,
+			.extra1		= SYSCTL_ZERO,
+			.extra2		= SYSCTL_INT_MAX,
 			.proc_handler	= proc_dointvec_minmax,
 		},
 		{},
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 6f1e31f674a3..0338820ee0ec 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -762,7 +762,7 @@ void skb_dump(const char *level, const struct sk_buff *skb, bool full_pkt)
 		printk("%sdev name=%s feat=0x%pNF\n",
 		       level, dev->name, &dev->features);
 	if (sk)
-		printk("%ssk family=%hu type=%hu proto=%hu\n",
+		printk("%ssk family=%hu type=%u proto=%u\n",
 		       level, sk->sk_family, sk->sk_type, sk->sk_protocol);
 
 	if (full_pkt && headroom)
diff --git a/net/core/skmsg.c b/net/core/skmsg.c
index 93bffaad2135..6832eeb4b785 100644
--- a/net/core/skmsg.c
+++ b/net/core/skmsg.c
@@ -585,12 +585,12 @@ EXPORT_SYMBOL_GPL(sk_psock_destroy);
 
 void sk_psock_drop(struct sock *sk, struct sk_psock *psock)
 {
-	rcu_assign_sk_user_data(sk, NULL);
 	sk_psock_cork_free(psock);
 	sk_psock_zap_ingress(psock);
-	sk_psock_restore_proto(sk, psock);
 
 	write_lock_bh(&sk->sk_callback_lock);
+	sk_psock_restore_proto(sk, psock);
+	rcu_assign_sk_user_data(sk, NULL);
 	if (psock->progs.skb_parser)
 		sk_psock_stop_strp(sk, psock);
 	write_unlock_bh(&sk->sk_callback_lock);
diff --git a/net/core/sock.c b/net/core/sock.c
index 3e073ca6138f..6d08553f885c 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -1597,7 +1597,7 @@ static struct sock *sk_prot_alloc(struct proto *prot, gfp_t priority,
 		sk = kmem_cache_alloc(slab, priority & ~__GFP_ZERO);
 		if (!sk)
 			return sk;
-		if (priority & __GFP_ZERO)
+		if (want_init_on_alloc(priority))
 			sk_prot_clear_nulls(sk, prot->obj_size);
 	} else
 		sk = kmalloc(prot->obj_size, priority);
@@ -1992,6 +1992,19 @@ void skb_set_owner_w(struct sk_buff *skb, struct sock *sk)
 }
 EXPORT_SYMBOL(skb_set_owner_w);
 
+static bool can_skb_orphan_partial(const struct sk_buff *skb)
+{
+#ifdef CONFIG_TLS_DEVICE
+	/* Drivers depend on in-order delivery for crypto offload,
+	 * partial orphan breaks out-of-order-OK logic.
+	 */
+	if (skb->decrypted)
+		return false;
+#endif
+	return (skb->destructor == sock_wfree ||
+		(IS_ENABLED(CONFIG_INET) && skb->destructor == tcp_wfree));
+}
+
 /* This helper is used by netem, as it can hold packets in its
  * delay queue. We want to allow the owner socket to send more
  * packets, as if they were already TX completed by a typical driver.
@@ -2003,11 +2016,7 @@ void skb_orphan_partial(struct sk_buff *skb)
 	if (skb_is_tcp_pure_ack(skb))
 		return;
 
-	if (skb->destructor == sock_wfree
-#ifdef CONFIG_INET
-	    || skb->destructor == tcp_wfree
-#endif
-		) {
+	if (can_skb_orphan_partial(skb)) {
 		struct sock *sk = skb->sk;
 
 		if (refcount_inc_not_zero(&sk->sk_refcnt)) {
diff --git a/net/core/sock_diag.c b/net/core/sock_diag.c
index 3312a5849a97..c13ffbd33d8d 100644
--- a/net/core/sock_diag.c
+++ b/net/core/sock_diag.c
@@ -19,6 +19,7 @@ static const struct sock_diag_handler *sock_diag_handlers[AF_MAX];
 static int (*inet_rcv_compat)(struct sk_buff *skb, struct nlmsghdr *nlh);
 static DEFINE_MUTEX(sock_diag_table_mutex);
 static struct workqueue_struct *broadcast_wq;
+static atomic64_t cookie_gen;
 
 u64 sock_gen_cookie(struct sock *sk)
 {
@@ -27,7 +28,7 @@ u64 sock_gen_cookie(struct sock *sk)
 
 		if (res)
 			return res;
-		res = atomic64_inc_return(&sock_net(sk)->cookie_gen);
+		res = atomic64_inc_return(&cookie_gen);
 		atomic64_cmpxchg(&sk->sk_cookie, 0, res);
 	}
 }
diff --git a/net/core/sock_map.c b/net/core/sock_map.c
index 52d4faeee18b..1330a7442e5b 100644
--- a/net/core/sock_map.c
+++ b/net/core/sock_map.c
@@ -247,6 +247,8 @@ static void sock_map_free(struct bpf_map *map)
 	raw_spin_unlock_bh(&stab->lock);
 	rcu_read_unlock();
 
+	synchronize_rcu();
+
 	bpf_map_area_free(stab->sks);
 	kfree(stab);
 }
@@ -276,16 +278,20 @@ static int __sock_map_delete(struct bpf_stab *stab, struct sock *sk_test,
 			     struct sock **psk)
 {
 	struct sock *sk;
+	int err = 0;
 
 	raw_spin_lock_bh(&stab->lock);
 	sk = *psk;
 	if (!sk_test || sk_test == sk)
-		*psk = NULL;
+		sk = xchg(psk, NULL);
+
+	if (likely(sk))
+		sock_map_unref(sk, psk);
+	else
+		err = -EINVAL;
+
 	raw_spin_unlock_bh(&stab->lock);
-	if (unlikely(!sk))
-		return -EINVAL;
-	sock_map_unref(sk, psk);
-	return 0;
+	return err;
 }
 
 static void sock_map_delete_from_link(struct bpf_map *map, struct sock *sk,
@@ -328,6 +334,7 @@ static int sock_map_update_common(struct bpf_map *map, u32 idx,
 				  struct sock *sk, u64 flags)
 {
 	struct bpf_stab *stab = container_of(map, struct bpf_stab, map);
+	struct inet_connection_sock *icsk = inet_csk(sk);
 	struct sk_psock_link *link;
 	struct sk_psock *psock;
 	struct sock *osk;
@@ -338,6 +345,8 @@ static int sock_map_update_common(struct bpf_map *map, u32 idx,
 		return -EINVAL;
 	if (unlikely(idx >= map->max_entries))
 		return -E2BIG;
+	if (unlikely(icsk->icsk_ulp_data))
+		return -EINVAL;
 
 	link = sk_psock_init_link();
 	if (!link)
diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c
index f9204719aeee..8da5b3a54dac 100644
--- a/net/core/sysctl_net_core.c
+++ b/net/core/sysctl_net_core.c
@@ -22,8 +22,6 @@
 #include <net/busy_poll.h>
 #include <net/pkt_sched.h>
 
-static int zero = 0;
-static int one = 1;
 static int two __maybe_unused = 2;
 static int min_sndbuf = SOCK_MIN_SNDBUF;
 static int min_rcvbuf = SOCK_MIN_RCVBUF;
@@ -390,10 +388,10 @@ static struct ctl_table net_core_table[] = {
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec_minmax_bpf_enable,
 # ifdef CONFIG_BPF_JIT_ALWAYS_ON
-		.extra1		= &one,
-		.extra2		= &one,
+		.extra1		= SYSCTL_ONE,
+		.extra2		= SYSCTL_ONE,
 # else
-		.extra1		= &zero,
+		.extra1		= SYSCTL_ZERO,
 		.extra2		= &two,
 # endif
 	},
@@ -404,7 +402,7 @@ static struct ctl_table net_core_table[] = {
 		.maxlen		= sizeof(int),
 		.mode		= 0600,
 		.proc_handler	= proc_dointvec_minmax_bpf_restricted,
-		.extra1		= &zero,
+		.extra1		= SYSCTL_ZERO,
 		.extra2		= &two,
 	},
 	{
@@ -413,8 +411,8 @@ static struct ctl_table net_core_table[] = {
 		.maxlen		= sizeof(int),
 		.mode		= 0600,
 		.proc_handler	= proc_dointvec_minmax_bpf_restricted,
-		.extra1		= &zero,
-		.extra2		= &one,
+		.extra1		= SYSCTL_ZERO,
+		.extra2		= SYSCTL_ONE,
 	},
 # endif
 	{
@@ -461,8 +459,8 @@ static struct ctl_table net_core_table[] = {
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec_minmax,
-		.extra1		= &zero,
-		.extra2		= &one
+		.extra1		= SYSCTL_ZERO,
+		.extra2		= SYSCTL_ONE
 	},
 #ifdef CONFIG_RPS
 	{
@@ -493,7 +491,7 @@ static struct ctl_table net_core_table[] = {
 		.maxlen		= sizeof(unsigned int),
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec_minmax,
-		.extra1		= &zero,
+		.extra1		= SYSCTL_ZERO,
 	},
 	{
 		.procname	= "busy_read",
@@ -501,7 +499,7 @@ static struct ctl_table net_core_table[] = {
 		.maxlen		= sizeof(unsigned int),
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec_minmax,
-		.extra1		= &zero,
+		.extra1		= SYSCTL_ZERO,
 	},
 #endif
 #ifdef CONFIG_NET_SCHED
@@ -533,7 +531,7 @@ static struct ctl_table net_core_table[] = {
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec_minmax,
-		.extra1		= &one,
+		.extra1		= SYSCTL_ONE,
 		.extra2		= &max_skb_frags,
 	},
 	{
@@ -542,7 +540,7 @@ static struct ctl_table net_core_table[] = {
 		.maxlen		= sizeof(unsigned int),
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec_minmax,
-		.extra1		= &zero,
+		.extra1		= SYSCTL_ZERO,
 	},
 	{
 		.procname	= "fb_tunnels_only_for_init_net",
@@ -550,8 +548,8 @@ static struct ctl_table net_core_table[] = {
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec_minmax,
-		.extra1		= &zero,
-		.extra2		= &one,
+		.extra1		= SYSCTL_ZERO,
+		.extra2		= SYSCTL_ONE,
 	},
 	{
 		.procname	= "devconf_inherit_init_net",
@@ -559,7 +557,7 @@ static struct ctl_table net_core_table[] = {
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec_minmax,
-		.extra1		= &zero,
+		.extra1		= SYSCTL_ZERO,
 		.extra2		= &two,
 	},
 	{
@@ -578,7 +576,7 @@ static struct ctl_table netns_core_table[] = {
 		.data		= &init_net.core.sysctl_somaxconn,
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
-		.extra1		= &zero,
+		.extra1		= SYSCTL_ZERO,
 		.proc_handler	= proc_dointvec_minmax
 	},
 	{ }
diff --git a/net/dccp/sysctl.c b/net/dccp/sysctl.c
index b59040f268a9..ee8d4f5afa72 100644
--- a/net/dccp/sysctl.c
+++ b/net/dccp/sysctl.c
@@ -16,9 +16,7 @@
 #endif
 
 /* Boundary values */
-static int		zero     = 0,
-			one      = 1,
-			u8_max   = 0xFF;
+static int		u8_max   = 0xFF;
 static unsigned long	seqw_min = DCCPF_SEQ_WMIN,
 			seqw_max = 0xFFFFFFFF;		/* maximum on 32 bit */
 
@@ -38,7 +36,7 @@ static struct ctl_table dccp_default_table[] = {
 		.maxlen		= sizeof(sysctl_dccp_rx_ccid),
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec_minmax,
-		.extra1		= &zero,
+		.extra1		= SYSCTL_ZERO,
 		.extra2		= &u8_max,		/* RFC 4340, 10. */
 	},
 	{
@@ -47,7 +45,7 @@ static struct ctl_table dccp_default_table[] = {
 		.maxlen		= sizeof(sysctl_dccp_tx_ccid),
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec_minmax,
-		.extra1		= &zero,
+		.extra1		= SYSCTL_ZERO,
 		.extra2		= &u8_max,		/* RFC 4340, 10. */
 	},
 	{
@@ -56,7 +54,7 @@ static struct ctl_table dccp_default_table[] = {
 		.maxlen		= sizeof(sysctl_dccp_request_retries),
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec_minmax,
-		.extra1		= &one,
+		.extra1		= SYSCTL_ONE,
 		.extra2		= &u8_max,
 	},
 	{
@@ -65,7 +63,7 @@ static struct ctl_table dccp_default_table[] = {
 		.maxlen		= sizeof(sysctl_dccp_retries1),
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec_minmax,
-		.extra1		= &zero,
+		.extra1		= SYSCTL_ZERO,
 		.extra2		= &u8_max,
 	},
 	{
@@ -74,7 +72,7 @@ static struct ctl_table dccp_default_table[] = {
 		.maxlen		= sizeof(sysctl_dccp_retries2),
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec_minmax,
-		.extra1		= &zero,
+		.extra1		= SYSCTL_ZERO,
 		.extra2		= &u8_max,
 	},
 	{
@@ -83,7 +81,7 @@ static struct ctl_table dccp_default_table[] = {
 		.maxlen		= sizeof(sysctl_dccp_tx_qlen),
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec_minmax,
-		.extra1		= &zero,
+		.extra1		= SYSCTL_ZERO,
 	},
 	{
 		.procname	= "sync_ratelimit",
diff --git a/net/dsa/slave.c b/net/dsa/slave.c
index 614c38ece104..33f41178afcc 100644
--- a/net/dsa/slave.c
+++ b/net/dsa/slave.c
@@ -951,7 +951,7 @@ static int dsa_slave_setup_tc_block(struct net_device *dev,
 				    struct flow_block_offload *f)
 {
 	struct flow_block_cb *block_cb;
-	tc_setup_cb_t *cb;
+	flow_setup_cb_t *cb;
 
 	if (f->binder_type == FLOW_BLOCK_BINDER_TYPE_CLSACT_INGRESS)
 		cb = dsa_slave_setup_tc_block_cb_ig;
@@ -967,7 +967,7 @@ static int dsa_slave_setup_tc_block(struct net_device *dev,
 		if (flow_block_cb_is_busy(cb, dev, &dsa_slave_block_cb_list))
 			return -EBUSY;
 
-		block_cb = flow_block_cb_alloc(f->net, cb, dev, dev, NULL);
+		block_cb = flow_block_cb_alloc(cb, dev, dev, NULL);
 		if (IS_ERR(block_cb))
 			return PTR_ERR(block_cb);
 
@@ -975,7 +975,7 @@ static int dsa_slave_setup_tc_block(struct net_device *dev,
 		list_add_tail(&block_cb->driver_list, &dsa_slave_block_cb_list);
 		return 0;
 	case FLOW_BLOCK_UNBIND:
-		block_cb = flow_block_cb_lookup(f, cb, dev);
+		block_cb = flow_block_cb_lookup(f->block, cb, dev);
 		if (!block_cb)
 			return -ENOENT;
 
diff --git a/net/dsa/switch.c b/net/dsa/switch.c
index 4ec5b7f85d51..09d9286b27cc 100644
--- a/net/dsa/switch.c
+++ b/net/dsa/switch.c
@@ -153,6 +153,9 @@ static void dsa_switch_mdb_add_bitmap(struct dsa_switch *ds,
 {
 	int port;
 
+	if (!ds->ops->port_mdb_add)
+		return;
+
 	for_each_set_bit(port, bitmap, ds->num_ports)
 		ds->ops->port_mdb_add(ds, port, mdb);
 }
diff --git a/net/dsa/tag_sja1105.c b/net/dsa/tag_sja1105.c
index 1d96c9d4a8e9..47ee88163a9d 100644
--- a/net/dsa/tag_sja1105.c
+++ b/net/dsa/tag_sja1105.c
@@ -165,6 +165,7 @@ static struct sk_buff
 					    "Expected meta frame, is %12llx "
 					    "in the DSA master multicast filter?\n",
 					    SJA1105_META_DMAC);
+			kfree_skb(sp->data->stampable_skb);
 		}
 
 		/* Hold a reference to avoid dsa_switch_rcv
@@ -211,16 +212,8 @@ static struct sk_buff
 		 * for further processing up the network stack.
 		 */
 		kfree_skb(skb);
-
-		skb = skb_copy(stampable_skb, GFP_ATOMIC);
-		if (!skb) {
-			dev_err_ratelimited(dp->ds->dev,
-					    "Failed to copy stampable skb\n");
-			return NULL;
-		}
+		skb = stampable_skb;
 		sja1105_transfer_meta(skb, meta);
-		/* The cached copy will be freed now */
-		skb_unref(stampable_skb);
 
 		spin_unlock(&sp->data->meta_lock);
 	}
diff --git a/net/hsr/hsr_device.c b/net/hsr/hsr_device.c
index f0f9b493c47b..f509b495451a 100644
--- a/net/hsr/hsr_device.c
+++ b/net/hsr/hsr_device.c
@@ -227,13 +227,8 @@ static int hsr_dev_xmit(struct sk_buff *skb, struct net_device *dev)
 	struct hsr_port *master;
 
 	master = hsr_port_get_hsr(hsr, HSR_PT_MASTER);
-	if (master) {
-		skb->dev = master->dev;
-		hsr_forward_skb(skb, master);
-	} else {
-		atomic_long_inc(&dev->tx_dropped);
-		dev_kfree_skb_any(skb);
-	}
+	skb->dev = master->dev;
+	hsr_forward_skb(skb, master);
 	return NETDEV_TX_OK;
 }
 
@@ -348,7 +343,11 @@ static void hsr_announce(struct timer_list *t)
 	rcu_read_unlock();
 }
 
-void hsr_dev_destroy(struct net_device *hsr_dev)
+/* This has to be called after all the readers are gone.
+ * Otherwise we would have to check the return value of
+ * hsr_port_get_hsr().
+ */
+static void hsr_dev_destroy(struct net_device *hsr_dev)
 {
 	struct hsr_priv *hsr;
 	struct hsr_port *port;
@@ -364,8 +363,6 @@ void hsr_dev_destroy(struct net_device *hsr_dev)
 	del_timer_sync(&hsr->prune_timer);
 	del_timer_sync(&hsr->announce_timer);
 
-	synchronize_rcu();
-
 	hsr_del_self_node(&hsr->self_node_db);
 	hsr_del_nodes(&hsr->node_db);
 }
@@ -376,6 +373,7 @@ static const struct net_device_ops hsr_device_ops = {
 	.ndo_stop = hsr_dev_close,
 	.ndo_start_xmit = hsr_dev_xmit,
 	.ndo_fix_features = hsr_fix_features,
+	.ndo_uninit = hsr_dev_destroy,
 };
 
 static struct device_type hsr_type = {
diff --git a/net/hsr/hsr_device.h b/net/hsr/hsr_device.h
index d0fa6b0696d2..6d7759c4f5f9 100644
--- a/net/hsr/hsr_device.h
+++ b/net/hsr/hsr_device.h
@@ -14,7 +14,6 @@
 void hsr_dev_setup(struct net_device *dev);
 int hsr_dev_finalize(struct net_device *hsr_dev, struct net_device *slave[2],
 		     unsigned char multicast_spec, u8 protocol_version);
-void hsr_dev_destroy(struct net_device *hsr_dev);
 void hsr_check_carrier_and_operstate(struct hsr_priv *hsr);
 bool is_hsr_master(struct net_device *dev);
 int hsr_get_max_mtu(struct hsr_priv *hsr);
diff --git a/net/hsr/hsr_netlink.c b/net/hsr/hsr_netlink.c
index 160edd24de4e..8f8337f893ba 100644
--- a/net/hsr/hsr_netlink.c
+++ b/net/hsr/hsr_netlink.c
@@ -69,12 +69,6 @@ static int hsr_newlink(struct net *src_net, struct net_device *dev,
 	return hsr_dev_finalize(dev, link, multicast_spec, hsr_version);
 }
 
-static void hsr_dellink(struct net_device *hsr_dev, struct list_head *head)
-{
-	hsr_dev_destroy(hsr_dev);
-	unregister_netdevice_queue(hsr_dev, head);
-}
-
 static int hsr_fill_info(struct sk_buff *skb, const struct net_device *dev)
 {
 	struct hsr_priv *hsr;
@@ -119,7 +113,6 @@ static struct rtnl_link_ops hsr_link_ops __read_mostly = {
 	.priv_size	= sizeof(struct hsr_priv),
 	.setup		= hsr_dev_setup,
 	.newlink	= hsr_newlink,
-	.dellink	= hsr_dellink,
 	.fill_info	= hsr_fill_info,
 };
 
diff --git a/net/ieee802154/6lowpan/reassembly.c b/net/ieee802154/6lowpan/reassembly.c
index e4aba5d485be..bbe9b3b2d395 100644
--- a/net/ieee802154/6lowpan/reassembly.c
+++ b/net/ieee802154/6lowpan/reassembly.c
@@ -170,7 +170,7 @@ static int lowpan_frag_reasm(struct lowpan_frag_queue *fq, struct sk_buff *skb,
 	reasm_data = inet_frag_reasm_prepare(&fq->q, skb, prev_tail);
 	if (!reasm_data)
 		goto out_oom;
-	inet_frag_reasm_finish(&fq->q, skb, reasm_data);
+	inet_frag_reasm_finish(&fq->q, skb, reasm_data, false);
 
 	skb->dev = ldev;
 	skb->tstamp = fq->q.stamp;
diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index 317339cd7f03..e8bc939b56dd 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -388,6 +388,11 @@ static int __fib_validate_source(struct sk_buff *skb, __be32 src, __be32 dst,
 	fib_combine_itag(itag, &res);
 
 	dev_match = fib_info_nh_uses_dev(res.fi, dev);
+	/* This is not common, loopback packets retain skb_dst so normally they
+	 * would not even hit this slow path.
+	 */
+	dev_match = dev_match || (res.type == RTN_LOCAL &&
+				  dev == net->loopback_dev);
 	if (dev_match) {
 		ret = FIB_RES_NHC(res)->nhc_scope >= RT_SCOPE_HOST;
 		return ret;
diff --git a/net/ipv4/inet_fragment.c b/net/ipv4/inet_fragment.c
index d666756be5f1..10d31733297d 100644
--- a/net/ipv4/inet_fragment.c
+++ b/net/ipv4/inet_fragment.c
@@ -331,7 +331,7 @@ struct inet_frag_queue *inet_frag_find(struct fqdir *fqdir, void *key)
 	prev = rhashtable_lookup(&fqdir->rhashtable, key, fqdir->f->rhash_params);
 	if (!prev)
 		fq = inet_frag_create(fqdir, key, &prev);
-	if (prev && !IS_ERR(prev)) {
+	if (!IS_ERR_OR_NULL(prev)) {
 		fq = prev;
 		if (!refcount_inc_not_zero(&fq->refcnt))
 			fq = NULL;
@@ -475,11 +475,12 @@ void *inet_frag_reasm_prepare(struct inet_frag_queue *q, struct sk_buff *skb,
 EXPORT_SYMBOL(inet_frag_reasm_prepare);
 
 void inet_frag_reasm_finish(struct inet_frag_queue *q, struct sk_buff *head,
-			    void *reasm_data)
+			    void *reasm_data, bool try_coalesce)
 {
 	struct sk_buff **nextp = (struct sk_buff **)reasm_data;
 	struct rb_node *rbn;
 	struct sk_buff *fp;
+	int sum_truesize;
 
 	skb_push(head, head->data - skb_network_header(head));
 
@@ -487,25 +488,41 @@ void inet_frag_reasm_finish(struct inet_frag_queue *q, struct sk_buff *head,
 	fp = FRAG_CB(head)->next_frag;
 	rbn = rb_next(&head->rbnode);
 	rb_erase(&head->rbnode, &q->rb_fragments);
+
+	sum_truesize = head->truesize;
 	while (rbn || fp) {
 		/* fp points to the next sk_buff in the current run;
 		 * rbn points to the next run.
 		 */
 		/* Go through the current run. */
 		while (fp) {
-			*nextp = fp;
-			nextp = &fp->next;
-			fp->prev = NULL;
-			memset(&fp->rbnode, 0, sizeof(fp->rbnode));
-			fp->sk = NULL;
-			head->data_len += fp->len;
-			head->len += fp->len;
+			struct sk_buff *next_frag = FRAG_CB(fp)->next_frag;
+			bool stolen;
+			int delta;
+
+			sum_truesize += fp->truesize;
 			if (head->ip_summed != fp->ip_summed)
 				head->ip_summed = CHECKSUM_NONE;
 			else if (head->ip_summed == CHECKSUM_COMPLETE)
 				head->csum = csum_add(head->csum, fp->csum);
-			head->truesize += fp->truesize;
-			fp = FRAG_CB(fp)->next_frag;
+
+			if (try_coalesce && skb_try_coalesce(head, fp, &stolen,
+							     &delta)) {
+				kfree_skb_partial(fp, stolen);
+			} else {
+				fp->prev = NULL;
+				memset(&fp->rbnode, 0, sizeof(fp->rbnode));
+				fp->sk = NULL;
+
+				head->data_len += fp->len;
+				head->len += fp->len;
+				head->truesize += fp->truesize;
+
+				*nextp = fp;
+				nextp = &fp->next;
+			}
+
+			fp = next_frag;
 		}
 		/* Move to the next run. */
 		if (rbn) {
@@ -516,7 +533,7 @@ void inet_frag_reasm_finish(struct inet_frag_queue *q, struct sk_buff *head,
 			rbn = rbnext;
 		}
 	}
-	sub_frag_mem_limit(q->fqdir, head->truesize);
+	sub_frag_mem_limit(q->fqdir, sum_truesize);
 
 	*nextp = NULL;
 	skb_mark_not_on_list(head);
diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c
index 4385eb9e781f..cfeb8890f94e 100644
--- a/net/ipv4/ip_fragment.c
+++ b/net/ipv4/ip_fragment.c
@@ -393,6 +393,11 @@ err:
 	return err;
 }
 
+static bool ip_frag_coalesce_ok(const struct ipq *qp)
+{
+	return qp->q.key.v4.user == IP_DEFRAG_LOCAL_DELIVER;
+}
+
 /* Build a new IP datagram from all its fragments. */
 static int ip_frag_reasm(struct ipq *qp, struct sk_buff *skb,
 			 struct sk_buff *prev_tail, struct net_device *dev)
@@ -421,7 +426,8 @@ static int ip_frag_reasm(struct ipq *qp, struct sk_buff *skb,
 	if (len > 65535)
 		goto out_oversize;
 
-	inet_frag_reasm_finish(&qp->q, skb, reasm_data);
+	inet_frag_reasm_finish(&qp->q, skb, reasm_data,
+			       ip_frag_coalesce_ok(qp));
 
 	skb->dev = dev;
 	IPCB(skb)->frag_max_size = max(qp->max_df_size, qp->q.max_size);
diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c
index 43adfc1641ba..2f01cf6fa0de 100644
--- a/net/ipv4/ipip.c
+++ b/net/ipv4/ipip.c
@@ -275,6 +275,9 @@ static netdev_tx_t ipip_tunnel_xmit(struct sk_buff *skb,
 	const struct iphdr  *tiph = &tunnel->parms.iph;
 	u8 ipproto;
 
+	if (!pskb_inet_may_pull(skb))
+		goto tx_error;
+
 	switch (skb->protocol) {
 	case htons(ETH_P_IP):
 		ipproto = IPPROTO_IPIP;
diff --git a/net/ipv4/netfilter/ipt_CLUSTERIP.c b/net/ipv4/netfilter/ipt_CLUSTERIP.c
index 4d6bf7ac0792..6bdb1ab8af61 100644
--- a/net/ipv4/netfilter/ipt_CLUSTERIP.c
+++ b/net/ipv4/netfilter/ipt_CLUSTERIP.c
@@ -416,8 +416,8 @@ clusterip_tg(struct sk_buff *skb, const struct xt_action_param *par)
 	     ctinfo == IP_CT_RELATED_REPLY))
 		return XT_CONTINUE;
 
-	/* ip_conntrack_icmp guarantees us that we only have ICMP_ECHO,
-	 * TIMESTAMP, INFO_REQUEST or ADDRESS type icmp packets from here
+	/* nf_conntrack_proto_icmp guarantees us that we only have ICMP_ECHO,
+	 * TIMESTAMP, INFO_REQUEST or ICMP_ADDRESS type icmp packets from here
 	 * on, which all have an ID field [relevant for hashing]. */
 
 	hash = clusterip_hashfn(skb, cipinfo->config);
diff --git a/net/ipv4/netfilter/ipt_SYNPROXY.c b/net/ipv4/netfilter/ipt_SYNPROXY.c
index 8e7f84ec783d..0e70f3f65f6f 100644
--- a/net/ipv4/netfilter/ipt_SYNPROXY.c
+++ b/net/ipv4/netfilter/ipt_SYNPROXY.c
@@ -36,6 +36,8 @@ synproxy_tg4(struct sk_buff *skb, const struct xt_action_param *par)
 			opts.options |= XT_SYNPROXY_OPT_ECN;
 
 		opts.options &= info->options;
+		opts.mss_encode = opts.mss;
+		opts.mss = info->mss;
 		if (opts.options & XT_SYNPROXY_OPT_TIMESTAMP)
 			synproxy_init_timestamp_cookie(info, &opts);
 		else
diff --git a/net/ipv4/netfilter/ipt_rpfilter.c b/net/ipv4/netfilter/ipt_rpfilter.c
index 59031670b16a..cc23f1ce239c 100644
--- a/net/ipv4/netfilter/ipt_rpfilter.c
+++ b/net/ipv4/netfilter/ipt_rpfilter.c
@@ -78,6 +78,7 @@ static bool rpfilter_mt(const struct sk_buff *skb, struct xt_action_param *par)
 	flow.flowi4_mark = info->flags & XT_RPFILTER_VALID_MARK ? skb->mark : 0;
 	flow.flowi4_tos = RT_TOS(iph->tos);
 	flow.flowi4_scope = RT_SCOPE_UNIVERSE;
+	flow.flowi4_oif = l3mdev_master_ifindex_rcu(xt_in(par));
 
 	return rpfilter_lookup_reverse(xt_net(par), &flow, xt_in(par), info->flags) ^ invert;
 }
diff --git a/net/ipv4/netfilter/nf_nat_h323.c b/net/ipv4/netfilter/nf_nat_h323.c
index 87b711fd5a44..3e2685c120c7 100644
--- a/net/ipv4/netfilter/nf_nat_h323.c
+++ b/net/ipv4/netfilter/nf_nat_h323.c
@@ -221,11 +221,11 @@ static int nat_rtp_rtcp(struct sk_buff *skb, struct nf_conn *ct,
 		int ret;
 
 		rtp_exp->tuple.dst.u.udp.port = htons(nated_port);
-		ret = nf_ct_expect_related(rtp_exp);
+		ret = nf_ct_expect_related(rtp_exp, 0);
 		if (ret == 0) {
 			rtcp_exp->tuple.dst.u.udp.port =
 			    htons(nated_port + 1);
-			ret = nf_ct_expect_related(rtcp_exp);
+			ret = nf_ct_expect_related(rtcp_exp, 0);
 			if (ret == 0)
 				break;
 			else if (ret == -EBUSY) {
@@ -296,7 +296,7 @@ static int nat_t120(struct sk_buff *skb, struct nf_conn *ct,
 		int ret;
 
 		exp->tuple.dst.u.tcp.port = htons(nated_port);
-		ret = nf_ct_expect_related(exp);
+		ret = nf_ct_expect_related(exp, 0);
 		if (ret == 0)
 			break;
 		else if (ret != -EBUSY) {
@@ -352,7 +352,7 @@ static int nat_h245(struct sk_buff *skb, struct nf_conn *ct,
 		int ret;
 
 		exp->tuple.dst.u.tcp.port = htons(nated_port);
-		ret = nf_ct_expect_related(exp);
+		ret = nf_ct_expect_related(exp, 0);
 		if (ret == 0)
 			break;
 		else if (ret != -EBUSY) {
@@ -444,7 +444,7 @@ static int nat_q931(struct sk_buff *skb, struct nf_conn *ct,
 		int ret;
 
 		exp->tuple.dst.u.tcp.port = htons(nated_port);
-		ret = nf_ct_expect_related(exp);
+		ret = nf_ct_expect_related(exp, 0);
 		if (ret == 0)
 			break;
 		else if (ret != -EBUSY) {
@@ -537,7 +537,7 @@ static int nat_callforwarding(struct sk_buff *skb, struct nf_conn *ct,
 		int ret;
 
 		exp->tuple.dst.u.tcp.port = htons(nated_port);
-		ret = nf_ct_expect_related(exp);
+		ret = nf_ct_expect_related(exp, 0);
 		if (ret == 0)
 			break;
 		else if (ret != -EBUSY) {
diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index 7d66306b5f39..0b980e841927 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -28,8 +28,6 @@
 #include <net/protocol.h>
 #include <net/netevent.h>
 
-static int zero;
-static int one = 1;
 static int two = 2;
 static int four = 4;
 static int thousand = 1000;
@@ -576,7 +574,7 @@ static struct ctl_table ipv4_table[] = {
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec_minmax,
-		.extra1		= &zero,
+		.extra1		= SYSCTL_ZERO,
 	},
 	{
 		.procname	= "icmp_msgs_burst",
@@ -584,7 +582,7 @@ static struct ctl_table ipv4_table[] = {
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec_minmax,
-		.extra1		= &zero,
+		.extra1		= SYSCTL_ZERO,
 	},
 	{
 		.procname	= "udp_mem",
@@ -674,8 +672,8 @@ static struct ctl_table ipv4_net_table[] = {
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec_minmax,
-		.extra1		= &zero,
-		.extra2		= &one,
+		.extra1		= SYSCTL_ZERO,
+		.extra2		= SYSCTL_ONE,
 	},
 #endif
 	{
@@ -763,8 +761,8 @@ static struct ctl_table ipv4_net_table[] = {
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
 		.proc_handler   = ipv4_fwd_update_priority,
-		.extra1		= &zero,
-		.extra2		= &one,
+		.extra1		= SYSCTL_ZERO,
+		.extra2		= SYSCTL_ONE,
 	},
 	{
 		.procname	= "ip_nonlocal_bind",
@@ -794,8 +792,8 @@ static struct ctl_table ipv4_net_table[] = {
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec_minmax,
-		.extra1		= &zero,
-		.extra2		= &one,
+		.extra1		= SYSCTL_ZERO,
+		.extra2		= SYSCTL_ONE,
 	},
 #endif
 	{
@@ -864,7 +862,7 @@ static struct ctl_table ipv4_net_table[] = {
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec_minmax,
-		.extra1		= &one
+		.extra1		= SYSCTL_ONE
 	},
 #endif
 	{
@@ -969,7 +967,7 @@ static struct ctl_table ipv4_net_table[] = {
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec_minmax,
-		.extra1		= &zero,
+		.extra1		= SYSCTL_ZERO,
 		.extra2		= &two,
 	},
 	{
@@ -1011,7 +1009,7 @@ static struct ctl_table ipv4_net_table[] = {
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
 		.proc_handler	= proc_tfo_blackhole_detect_timeout,
-		.extra1		= &zero,
+		.extra1		= SYSCTL_ZERO,
 	},
 #ifdef CONFIG_IP_ROUTE_MULTIPATH
 	{
@@ -1020,8 +1018,8 @@ static struct ctl_table ipv4_net_table[] = {
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec_minmax,
-		.extra1		= &zero,
-		.extra2		= &one,
+		.extra1		= SYSCTL_ZERO,
+		.extra2		= SYSCTL_ONE,
 	},
 	{
 		.procname	= "fib_multipath_hash_policy",
@@ -1029,8 +1027,8 @@ static struct ctl_table ipv4_net_table[] = {
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
 		.proc_handler	= proc_fib_multipath_hash_policy,
-		.extra1		= &zero,
-		.extra2		= &two,
+		.extra1		= SYSCTL_ZERO,
+		.extra2		= SYSCTL_ONE,
 	},
 #endif
 	{
@@ -1047,8 +1045,8 @@ static struct ctl_table ipv4_net_table[] = {
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec_minmax,
-		.extra1		= &zero,
-		.extra2		= &one,
+		.extra1		= SYSCTL_ZERO,
+		.extra2		= SYSCTL_ONE,
 	},
 #endif
 	{
@@ -1078,7 +1076,7 @@ static struct ctl_table ipv4_net_table[] = {
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec_minmax,
-		.extra1		= &zero,
+		.extra1		= SYSCTL_ZERO,
 		.extra2		= &four,
 	},
 	{
@@ -1222,7 +1220,7 @@ static struct ctl_table ipv4_net_table[] = {
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec_minmax,
-		.extra1		= &one,
+		.extra1		= SYSCTL_ONE,
 		.extra2		= &gso_max_segs,
 	},
 	{
@@ -1231,7 +1229,7 @@ static struct ctl_table ipv4_net_table[] = {
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec_minmax,
-		.extra1		= &zero,
+		.extra1		= SYSCTL_ZERO,
 		.extra2		= &one_day_secs
 	},
 	{
@@ -1240,8 +1238,8 @@ static struct ctl_table ipv4_net_table[] = {
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec_minmax,
-		.extra1		= &zero,
-		.extra2		= &one,
+		.extra1		= SYSCTL_ZERO,
+		.extra2		= SYSCTL_ONE,
 	},
 	{
 		.procname	= "tcp_invalid_ratelimit",
@@ -1256,7 +1254,7 @@ static struct ctl_table ipv4_net_table[] = {
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec_minmax,
-		.extra1		= &zero,
+		.extra1		= SYSCTL_ZERO,
 		.extra2		= &thousand,
 	},
 	{
@@ -1265,7 +1263,7 @@ static struct ctl_table ipv4_net_table[] = {
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec_minmax,
-		.extra1		= &zero,
+		.extra1		= SYSCTL_ZERO,
 		.extra2		= &thousand,
 	},
 	{
@@ -1274,7 +1272,7 @@ static struct ctl_table ipv4_net_table[] = {
 		.maxlen		= sizeof(init_net.ipv4.sysctl_tcp_wmem),
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec_minmax,
-		.extra1		= &one,
+		.extra1		= SYSCTL_ONE,
 	},
 	{
 		.procname	= "tcp_rmem",
@@ -1282,7 +1280,7 @@ static struct ctl_table ipv4_net_table[] = {
 		.maxlen		= sizeof(init_net.ipv4.sysctl_tcp_rmem),
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec_minmax,
-		.extra1		= &one,
+		.extra1		= SYSCTL_ONE,
 	},
 	{
 		.procname	= "tcp_comp_sack_delay_ns",
@@ -1297,7 +1295,7 @@ static struct ctl_table ipv4_net_table[] = {
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec_minmax,
-		.extra1		= &zero,
+		.extra1		= SYSCTL_ZERO,
 		.extra2		= &comp_sack_nr_max,
 	},
 	{
@@ -1306,7 +1304,7 @@ static struct ctl_table ipv4_net_table[] = {
 		.maxlen		= sizeof(init_net.ipv4.sysctl_udp_rmem_min),
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec_minmax,
-		.extra1		= &one
+		.extra1		= SYSCTL_ONE
 	},
 	{
 		.procname	= "udp_wmem_min",
@@ -1314,7 +1312,7 @@ static struct ctl_table ipv4_net_table[] = {
 		.maxlen		= sizeof(init_net.ipv4.sysctl_udp_wmem_min),
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec_minmax,
-		.extra1		= &one
+		.extra1		= SYSCTL_ONE
 	},
 	{ }
 };
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 7846afacdf0b..77b485d60b9d 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -984,6 +984,9 @@ new_segment:
 			if (!skb)
 				goto wait_for_memory;
 
+#ifdef CONFIG_TLS_DEVICE
+			skb->decrypted = !!(flags & MSG_SENDPAGE_DECRYPTED);
+#endif
 			skb_entail(sk, skb);
 			copy = size_goal;
 		}
@@ -2785,7 +2788,9 @@ static int do_tcp_setsockopt(struct sock *sk, int level,
 		name[val] = 0;
 
 		lock_sock(sk);
-		err = tcp_set_congestion_control(sk, name, true, true);
+		err = tcp_set_congestion_control(sk, name, true, true,
+						 ns_capable(sock_net(sk)->user_ns,
+							    CAP_NET_ADMIN));
 		release_sock(sk);
 		return err;
 	}
diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c
index 3d1e15401384..8a56e09cfb0e 100644
--- a/net/ipv4/tcp_bpf.c
+++ b/net/ipv4/tcp_bpf.c
@@ -398,10 +398,14 @@ more_data:
 static int tcp_bpf_sendmsg(struct sock *sk, struct msghdr *msg, size_t size)
 {
 	struct sk_msg tmp, *msg_tx = NULL;
-	int flags = msg->msg_flags | MSG_NO_SHARED_FRAGS;
 	int copied = 0, err = 0;
 	struct sk_psock *psock;
 	long timeo;
+	int flags;
+
+	/* Don't let internal do_tcp_sendpages() flags through */
+	flags = (msg->msg_flags & ~MSG_SENDPAGE_DECRYPTED);
+	flags |= MSG_NO_SHARED_FRAGS;
 
 	psock = sk_psock_get(sk);
 	if (unlikely(!psock))
diff --git a/net/ipv4/tcp_cong.c b/net/ipv4/tcp_cong.c
index e1862b64a90f..c445a81d144e 100644
--- a/net/ipv4/tcp_cong.c
+++ b/net/ipv4/tcp_cong.c
@@ -333,7 +333,8 @@ out:
  * tcp_reinit_congestion_control (if the current congestion control was
  * already initialized.
  */
-int tcp_set_congestion_control(struct sock *sk, const char *name, bool load, bool reinit)
+int tcp_set_congestion_control(struct sock *sk, const char *name, bool load,
+			       bool reinit, bool cap_net_admin)
 {
 	struct inet_connection_sock *icsk = inet_csk(sk);
 	const struct tcp_congestion_ops *ca;
@@ -369,8 +370,7 @@ int tcp_set_congestion_control(struct sock *sk, const char *name, bool load, boo
 		} else {
 			err = -EBUSY;
 		}
-	} else if (!((ca->flags & TCP_CONG_NON_RESTRICTED) ||
-		     ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN))) {
+	} else if (!((ca->flags & TCP_CONG_NON_RESTRICTED) || cap_net_admin)) {
 		err = -EPERM;
 	} else if (!try_module_get(ca->owner)) {
 		err = -EBUSY;
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 4af1f5dae9d3..979520e46e33 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -1288,6 +1288,7 @@ int tcp_fragment(struct sock *sk, enum tcp_queue tcp_queue,
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct sk_buff *buff;
 	int nsize, old_factor;
+	long limit;
 	int nlen;
 	u8 flags;
 
@@ -1298,8 +1299,16 @@ int tcp_fragment(struct sock *sk, enum tcp_queue tcp_queue,
 	if (nsize < 0)
 		nsize = 0;
 
-	if (unlikely((sk->sk_wmem_queued >> 1) > sk->sk_sndbuf &&
-		     tcp_queue != TCP_FRAG_IN_WRITE_QUEUE)) {
+	/* tcp_sendmsg() can overshoot sk_wmem_queued by one full size skb.
+	 * We need some allowance to not penalize applications setting small
+	 * SO_SNDBUF values.
+	 * Also allow first and last skb in retransmit queue to be split.
+	 */
+	limit = sk->sk_sndbuf + 2 * SKB_TRUESIZE(GSO_MAX_SIZE);
+	if (unlikely((sk->sk_wmem_queued >> 1) > limit &&
+		     tcp_queue != TCP_FRAG_IN_WRITE_QUEUE &&
+		     skb != tcp_rtx_queue_head(sk) &&
+		     skb != tcp_rtx_queue_tail(sk))) {
 		NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPWQUEUETOOBIG);
 		return -ENOMEM;
 	}
@@ -1311,6 +1320,7 @@ int tcp_fragment(struct sock *sk, enum tcp_queue tcp_queue,
 	buff = sk_stream_alloc_skb(sk, nsize, gfp, true);
 	if (!buff)
 		return -ENOMEM; /* We'll just try again later. */
+	skb_copy_decrypted(buff, skb);
 
 	sk->sk_wmem_queued += buff->truesize;
 	sk_mem_charge(sk, buff->truesize);
@@ -1865,6 +1875,7 @@ static int tso_fragment(struct sock *sk, struct sk_buff *skb, unsigned int len,
 	buff = sk_stream_alloc_skb(sk, 0, gfp, true);
 	if (unlikely(!buff))
 		return -ENOMEM;
+	skb_copy_decrypted(buff, skb);
 
 	sk->sk_wmem_queued += buff->truesize;
 	sk_mem_charge(sk, buff->truesize);
@@ -2134,6 +2145,7 @@ static int tcp_mtu_probe(struct sock *sk)
 	sk_mem_charge(sk, nskb->truesize);
 
 	skb = tcp_send_head(sk);
+	skb_copy_decrypted(nskb, skb);
 
 	TCP_SKB_CB(nskb)->seq = TCP_SKB_CB(skb)->seq;
 	TCP_SKB_CB(nskb)->end_seq = TCP_SKB_CB(skb)->seq + probe_size;
diff --git a/net/ipv4/tcp_ulp.c b/net/ipv4/tcp_ulp.c
index 3d8a1d835471..4849edb62d52 100644
--- a/net/ipv4/tcp_ulp.c
+++ b/net/ipv4/tcp_ulp.c
@@ -96,6 +96,19 @@ void tcp_get_available_ulp(char *buf, size_t maxlen)
 	rcu_read_unlock();
 }
 
+void tcp_update_ulp(struct sock *sk, struct proto *proto)
+{
+	struct inet_connection_sock *icsk = inet_csk(sk);
+
+	if (!icsk->icsk_ulp_ops) {
+		sk->sk_prot = proto;
+		return;
+	}
+
+	if (icsk->icsk_ulp_ops->update)
+		icsk->icsk_ulp_ops->update(sk, proto);
+}
+
 void tcp_cleanup_ulp(struct sock *sk)
 {
 	struct inet_connection_sock *icsk = inet_csk(sk);
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index c21862ba9c02..d88821c794fb 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -2170,7 +2170,7 @@ start_lookup:
 
 /* Initialize UDP checksum. If exited with zero value (success),
  * CHECKSUM_UNNECESSARY means, that no more checks are required.
- * Otherwise, csum completion requires chacksumming packet body,
+ * Otherwise, csum completion requires checksumming packet body,
  * including udp header and folding it to skb->csum.
  */
 static inline int udp4_csum_init(struct sk_buff *skb, struct udphdr *uh,
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 521e3203e83a..dc73888c7859 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -6432,8 +6432,6 @@ int addrconf_sysctl_disable_policy(struct ctl_table *ctl, int write,
 }
 
 static int minus_one = -1;
-static const int zero = 0;
-static const int one = 1;
 static const int two_five_five = 255;
 
 static const struct ctl_table addrconf_sysctl[] = {
@@ -6450,7 +6448,7 @@ static const struct ctl_table addrconf_sysctl[] = {
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec_minmax,
-		.extra1		= (void *)&one,
+		.extra1		= (void *)SYSCTL_ONE,
 		.extra2		= (void *)&two_five_five,
 	},
 	{
@@ -6809,7 +6807,7 @@ static const struct ctl_table addrconf_sysctl[] = {
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec_minmax,
-		.extra1		= (void *)&zero,
+		.extra1		= (void *)SYSCTL_ZERO,
 		.extra2		= (void *)&two_five_five,
 	},
 	{
diff --git a/net/ipv6/ah6.c b/net/ipv6/ah6.c
index 25e1172fd1c3..95835e8d99aa 100644
--- a/net/ipv6/ah6.c
+++ b/net/ipv6/ah6.c
@@ -464,7 +464,7 @@ static void ah6_input_done(struct crypto_async_request *base, int err)
 	struct ah_data *ahp = x->data;
 	struct ip_auth_hdr *ah = ip_auth_hdr(skb);
 	int hdr_len = skb_network_header_len(skb);
-	int ah_hlen = (ah->hdrlen + 2) << 2;
+	int ah_hlen = ipv6_authlen(ah);
 
 	if (err)
 		goto out;
@@ -546,7 +546,7 @@ static int ah6_input(struct xfrm_state *x, struct sk_buff *skb)
 	ahash = ahp->ahash;
 
 	nexthdr = ah->nexthdr;
-	ah_hlen = (ah->hdrlen + 2) << 2;
+	ah_hlen = ipv6_authlen(ah);
 
 	if (ah_hlen != XFRM_ALIGN8(sizeof(*ah) + ahp->icv_full_len) &&
 	    ah_hlen != XFRM_ALIGN8(sizeof(*ah) + ahp->icv_trunc_len))
diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c
index 9d78c907b918..9ab897ded4df 100644
--- a/net/ipv6/datagram.c
+++ b/net/ipv6/datagram.c
@@ -74,7 +74,7 @@ int ip6_datagram_dst_update(struct sock *sk, bool fix_sk_saddr)
 
 	if (np->sndflow && (np->flow_label & IPV6_FLOWLABEL_MASK)) {
 		flowlabel = fl6_sock_lookup(sk, np->flow_label);
-		if (!flowlabel)
+		if (IS_ERR(flowlabel))
 			return -EINVAL;
 	}
 	ip6_datagram_flow_key_init(&fl6, sk);
diff --git a/net/ipv6/exthdrs_core.c b/net/ipv6/exthdrs_core.c
index 11a43ee4dd45..b358f1a4dd08 100644
--- a/net/ipv6/exthdrs_core.c
+++ b/net/ipv6/exthdrs_core.c
@@ -266,7 +266,7 @@ int ipv6_find_hdr(const struct sk_buff *skb, unsigned int *offset,
 		} else if (nexthdr == NEXTHDR_AUTH) {
 			if (flags && (*flags & IP6_FH_F_AUTH) && (target < 0))
 				break;
-			hdrlen = (hp->hdrlen + 2) << 2;
+			hdrlen = ipv6_authlen(hp);
 		} else
 			hdrlen = ipv6_optlen(hp);
 
diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index 49884f96232b..87f47bc55c5e 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -1151,8 +1151,24 @@ add:
 			err = call_fib6_entry_notifiers(info->nl_net,
 							FIB_EVENT_ENTRY_ADD,
 							rt, extack);
-			if (err)
+			if (err) {
+				struct fib6_info *sibling, *next_sibling;
+
+				/* If the route has siblings, then it first
+				 * needs to be unlinked from them.
+				 */
+				if (!rt->fib6_nsiblings)
+					return err;
+
+				list_for_each_entry_safe(sibling, next_sibling,
+							 &rt->fib6_siblings,
+							 fib6_siblings)
+					sibling->fib6_nsiblings--;
+				rt->fib6_nsiblings = 0;
+				list_del_init(&rt->fib6_siblings);
+				rt6_multipath_rebalance(next_sibling);
 				return err;
+			}
 		}
 
 		rcu_assign_pointer(rt->fib6_next, iter);
diff --git a/net/ipv6/ip6_flowlabel.c b/net/ipv6/ip6_flowlabel.c
index ad284b1fd308..d64b83e85642 100644
--- a/net/ipv6/ip6_flowlabel.c
+++ b/net/ipv6/ip6_flowlabel.c
@@ -435,8 +435,6 @@ fl_create(struct net *net, struct sock *sk, struct in6_flowlabel_req *freq,
 	}
 	fl->dst = freq->flr_dst;
 	atomic_set(&fl->users, 1);
-	if (fl_shared_exclusive(fl) || fl->opt)
-		static_branch_deferred_inc(&ipv6_flowlabel_exclusive);
 	switch (fl->share) {
 	case IPV6_FL_S_EXCL:
 	case IPV6_FL_S_ANY:
@@ -451,10 +449,15 @@ fl_create(struct net *net, struct sock *sk, struct in6_flowlabel_req *freq,
 		err = -EINVAL;
 		goto done;
 	}
+	if (fl_shared_exclusive(fl) || fl->opt)
+		static_branch_deferred_inc(&ipv6_flowlabel_exclusive);
 	return fl;
 
 done:
-	fl_free(fl);
+	if (fl) {
+		kfree(fl->opt);
+		kfree(fl);
+	}
 	*err_p = err;
 	return NULL;
 }
diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index c2049c72f3e5..dd2d0b963260 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -660,12 +660,13 @@ static int prepare_ip6gre_xmit_ipv6(struct sk_buff *skb,
 				    struct flowi6 *fl6, __u8 *dsfield,
 				    int *encap_limit)
 {
-	struct ipv6hdr *ipv6h = ipv6_hdr(skb);
+	struct ipv6hdr *ipv6h;
 	struct ip6_tnl *t = netdev_priv(dev);
 	__u16 offset;
 
 	offset = ip6_tnl_parse_tlv_enc_lim(skb, skb_network_header(skb));
 	/* ip6_tnl_parse_tlv_enc_lim() might have reallocated skb->head */
+	ipv6h = ipv6_hdr(skb);
 
 	if (offset > 0) {
 		struct ipv6_tlv_tnl_enc_lim *tel;
diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index b80fde1bc005..754a484d35df 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -416,7 +416,7 @@ __u16 ip6_tnl_parse_tlv_enc_lim(struct sk_buff *skb, __u8 *raw)
 				break;
 			optlen = 8;
 		} else if (nexthdr == NEXTHDR_AUTH) {
-			optlen = (hdr->hdrlen + 2) << 2;
+			optlen = ipv6_authlen(hdr);
 		} else {
 			optlen = ipv6_optlen(hdr);
 		}
@@ -1278,12 +1278,11 @@ ip4ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev)
 	}
 
 	fl6.flowi6_uid = sock_net_uid(dev_net(dev), NULL);
+	dsfield = INET_ECN_encapsulate(dsfield, ipv4_get_dsfield(iph));
 
 	if (iptunnel_handle_offloads(skb, SKB_GSO_IPXIP6))
 		return -1;
 
-	dsfield = INET_ECN_encapsulate(dsfield, ipv4_get_dsfield(iph));
-
 	skb_set_inner_ipproto(skb, IPPROTO_IPIP);
 
 	err = ip6_tnl_xmit(skb, dev, dsfield, &fl6, encap_limit, &mtu,
@@ -1367,12 +1366,11 @@ ip6ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev)
 	}
 
 	fl6.flowi6_uid = sock_net_uid(dev_net(dev), NULL);
+	dsfield = INET_ECN_encapsulate(dsfield, ipv6_get_dsfield(ipv6h));
 
 	if (iptunnel_handle_offloads(skb, SKB_GSO_IPXIP6))
 		return -1;
 
-	dsfield = INET_ECN_encapsulate(dsfield, ipv6_get_dsfield(ipv6h));
-
 	skb_set_inner_ipproto(skb, IPPROTO_IPV6);
 
 	err = ip6_tnl_xmit(skb, dev, dsfield, &fl6, encap_limit, &mtu,
diff --git a/net/ipv6/netfilter/ip6t_SYNPROXY.c b/net/ipv6/netfilter/ip6t_SYNPROXY.c
index e77ea1ed5edd..5cdb4a69d277 100644
--- a/net/ipv6/netfilter/ip6t_SYNPROXY.c
+++ b/net/ipv6/netfilter/ip6t_SYNPROXY.c
@@ -36,6 +36,8 @@ synproxy_tg6(struct sk_buff *skb, const struct xt_action_param *par)
 			opts.options |= XT_SYNPROXY_OPT_ECN;
 
 		opts.options &= info->options;
+		opts.mss_encode = opts.mss;
+		opts.mss = info->mss;
 		if (opts.options & XT_SYNPROXY_OPT_TIMESTAMP)
 			synproxy_init_timestamp_cookie(info, &opts);
 		else
diff --git a/net/ipv6/netfilter/ip6t_ah.c b/net/ipv6/netfilter/ip6t_ah.c
index 0228ff3636bb..4e15a14435e4 100644
--- a/net/ipv6/netfilter/ip6t_ah.c
+++ b/net/ipv6/netfilter/ip6t_ah.c
@@ -55,7 +55,7 @@ static bool ah_mt6(const struct sk_buff *skb, struct xt_action_param *par)
 		return false;
 	}
 
-	hdrlen = (ah->hdrlen + 2) << 2;
+	hdrlen = ipv6_authlen(ah);
 
 	pr_debug("IPv6 AH LEN %u %u ", hdrlen, ah->hdrlen);
 	pr_debug("RES %04X ", ah->reserved);
diff --git a/net/ipv6/netfilter/ip6t_ipv6header.c b/net/ipv6/netfilter/ip6t_ipv6header.c
index fd439f88377f..0fc6326ef499 100644
--- a/net/ipv6/netfilter/ip6t_ipv6header.c
+++ b/net/ipv6/netfilter/ip6t_ipv6header.c
@@ -71,7 +71,7 @@ ipv6header_mt6(const struct sk_buff *skb, struct xt_action_param *par)
 		if (nexthdr == NEXTHDR_FRAGMENT)
 			hdrlen = 8;
 		else if (nexthdr == NEXTHDR_AUTH)
-			hdrlen = (hp->hdrlen + 2) << 2;
+			hdrlen = ipv6_authlen(hp);
 		else
 			hdrlen = ipv6_optlen(hp);
 
diff --git a/net/ipv6/netfilter/ip6t_rpfilter.c b/net/ipv6/netfilter/ip6t_rpfilter.c
index 6bcaf7357183..d800801a5dd2 100644
--- a/net/ipv6/netfilter/ip6t_rpfilter.c
+++ b/net/ipv6/netfilter/ip6t_rpfilter.c
@@ -55,7 +55,9 @@ static bool rpfilter_lookup_reverse6(struct net *net, const struct sk_buff *skb,
 	if (rpfilter_addr_linklocal(&iph->saddr)) {
 		lookup_flags |= RT6_LOOKUP_F_IFACE;
 		fl6.flowi6_oif = dev->ifindex;
-	} else if ((flags & XT_RPFILTER_LOOSE) == 0)
+	/* Set flowi6_oif for vrf devices to lookup route in l3mdev domain. */
+	} else if (netif_is_l3_master(dev) || netif_is_l3_slave(dev) ||
+		  (flags & XT_RPFILTER_LOOSE) == 0)
 		fl6.flowi6_oif = dev->ifindex;
 
 	rt = (void *)ip6_route_lookup(net, &fl6, skb, lookup_flags);
@@ -70,7 +72,9 @@ static bool rpfilter_lookup_reverse6(struct net *net, const struct sk_buff *skb,
 		goto out;
 	}
 
-	if (rt->rt6i_idev->dev == dev || (flags & XT_RPFILTER_LOOSE))
+	if (rt->rt6i_idev->dev == dev ||
+	    l3mdev_master_ifindex_rcu(rt->rt6i_idev->dev) == dev->ifindex ||
+	    (flags & XT_RPFILTER_LOOSE))
 		ret = true;
  out:
 	ip6_rt_put(rt);
diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c
index 398e1df41406..fed9666a2f7d 100644
--- a/net/ipv6/netfilter/nf_conntrack_reasm.c
+++ b/net/ipv6/netfilter/nf_conntrack_reasm.c
@@ -348,7 +348,7 @@ static int nf_ct_frag6_reasm(struct frag_queue *fq, struct sk_buff *skb,
 
 	skb_reset_transport_header(skb);
 
-	inet_frag_reasm_finish(&fq->q, skb, reasm_data);
+	inet_frag_reasm_finish(&fq->q, skb, reasm_data, false);
 
 	skb->ignore_df = 1;
 	skb->dev = dev;
@@ -414,7 +414,7 @@ find_prev_fhdr(struct sk_buff *skb, u8 *prevhdrp, int *prevhoff, int *fhoff)
 		if (skb_copy_bits(skb, start, &hdr, sizeof(hdr)))
 			BUG();
 		if (nexthdr == NEXTHDR_AUTH)
-			hdrlen = (hdr.hdrlen+2)<<2;
+			hdrlen = ipv6_authlen(&hdr);
 		else
 			hdrlen = ipv6_optlen(&hdr);
 
diff --git a/net/ipv6/netfilter/nf_log_ipv6.c b/net/ipv6/netfilter/nf_log_ipv6.c
index 549c51156d5d..f53bd8f01219 100644
--- a/net/ipv6/netfilter/nf_log_ipv6.c
+++ b/net/ipv6/netfilter/nf_log_ipv6.c
@@ -155,7 +155,7 @@ static void dump_ipv6_packet(struct net *net, struct nf_log_buf *m,
 
 			}
 
-			hdrlen = (hp->hdrlen+2)<<2;
+			hdrlen = ipv6_authlen(hp);
 			break;
 		case IPPROTO_ESP:
 			if (logflags & NF_LOG_IPOPT) {
diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c
index ca05b16f1bb9..1f5d4d196dcc 100644
--- a/net/ipv6/reassembly.c
+++ b/net/ipv6/reassembly.c
@@ -282,7 +282,7 @@ static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *skb,
 
 	skb_reset_transport_header(skb);
 
-	inet_frag_reasm_finish(&fq->q, skb, reasm_data);
+	inet_frag_reasm_finish(&fq->q, skb, reasm_data, true);
 
 	skb->dev = dev;
 	ipv6_hdr(skb)->payload_len = htons(payload_len);
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 4d2e6b31a8d6..fd059e08785a 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -1951,7 +1951,7 @@ static void rt6_update_exception_stamp_rt(struct rt6_info *rt)
 		nexthop_for_each_fib6_nh(from->nh, fib6_nh_find_match, &arg);
 
 		if (!arg.match)
-			return;
+			goto unlock;
 		fib6_nh = arg.match;
 	} else {
 		fib6_nh = from->fib6_nh;
@@ -2563,7 +2563,7 @@ static struct dst_entry *rt6_check(struct rt6_info *rt,
 {
 	u32 rt_cookie = 0;
 
-	if ((from && !fib6_get_cookie_safe(from, &rt_cookie)) ||
+	if (!from || !fib6_get_cookie_safe(from, &rt_cookie) ||
 	    rt_cookie != cookie)
 		return NULL;
 
@@ -6031,9 +6031,6 @@ int ipv6_sysctl_rtcache_flush(struct ctl_table *ctl, int write,
 	return 0;
 }
 
-static int zero;
-static int one = 1;
-
 static struct ctl_table ipv6_route_table_template[] = {
 	{
 		.procname	=	"flush",
@@ -6111,8 +6108,8 @@ static struct ctl_table ipv6_route_table_template[] = {
 		.maxlen		=	sizeof(int),
 		.mode		=	0644,
 		.proc_handler	=	proc_dointvec_minmax,
-		.extra1		=	&zero,
-		.extra2		=	&one,
+		.extra1		=	SYSCTL_ZERO,
+		.extra2		=	SYSCTL_ONE,
 	},
 	{ }
 };
diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index 80610899a323..b2ccbc473127 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -900,12 +900,17 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb,
 			   RT_TOS(tos), RT_SCOPE_UNIVERSE, IPPROTO_IPV6,
 			   0, dst, tiph->saddr, 0, 0,
 			   sock_net_uid(tunnel->net, NULL));
-	rt = ip_route_output_flow(tunnel->net, &fl4, NULL);
 
-	if (IS_ERR(rt)) {
-		dev->stats.tx_carrier_errors++;
-		goto tx_error_icmp;
+	rt = dst_cache_get_ip4(&tunnel->dst_cache, &fl4.saddr);
+	if (!rt) {
+		rt = ip_route_output_flow(tunnel->net, &fl4, NULL);
+		if (IS_ERR(rt)) {
+			dev->stats.tx_carrier_errors++;
+			goto tx_error_icmp;
+		}
+		dst_cache_set_ip4(&tunnel->dst_cache, &rt->dst, fl4.saddr);
 	}
+
 	if (rt->rt_type != RTN_UNICAST) {
 		ip_rt_put(rt);
 		dev->stats.tx_carrier_errors++;
diff --git a/net/ipv6/sysctl_net_ipv6.c b/net/ipv6/sysctl_net_ipv6.c
index dc4c91e0bfb8..ec8fcfc60a27 100644
--- a/net/ipv6/sysctl_net_ipv6.c
+++ b/net/ipv6/sysctl_net_ipv6.c
@@ -21,8 +21,6 @@
 #include <net/calipso.h>
 #endif
 
-static int zero;
-static int one = 1;
 static int flowlabel_reflect_max = 0x7;
 static int auto_flowlabels_min;
 static int auto_flowlabels_max = IP6_AUTO_FLOW_LABEL_MAX;
@@ -115,7 +113,7 @@ static struct ctl_table ipv6_table_template[] = {
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec_minmax,
-		.extra1		= &zero,
+		.extra1		= SYSCTL_ZERO,
 		.extra2		= &flowlabel_reflect_max,
 	},
 	{
@@ -152,8 +150,8 @@ static struct ctl_table ipv6_table_template[] = {
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
 		.proc_handler   = proc_rt6_multipath_hash_policy,
-		.extra1		= &zero,
-		.extra2		= &one,
+		.extra1		= SYSCTL_ZERO,
+		.extra2		= SYSCTL_ONE,
 	},
 	{
 		.procname	= "seg6_flowlabel",
@@ -179,7 +177,7 @@ static struct ctl_table ipv6_rotable[] = {
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec_minmax,
-		.extra1		= &one
+		.extra1		= SYSCTL_ONE
 	},
 #ifdef CONFIG_NETLABEL
 	{
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index d56a9019a0fe..5da069e91cac 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -984,8 +984,13 @@ static void tcp_v6_send_reset(const struct sock *sk, struct sk_buff *skb)
 
 	if (sk) {
 		oif = sk->sk_bound_dev_if;
-		if (sk_fullsock(sk))
+		if (sk_fullsock(sk)) {
+			const struct ipv6_pinfo *np = tcp_inet6_sk(sk);
+
 			trace_tcp_send_reset(sk, skb);
+			if (np->repflow)
+				label = ip6_flowlabel(ipv6h);
+		}
 		if (sk->sk_state == TCP_TIME_WAIT)
 			label = cpu_to_be32(inet_twsk(sk)->tw_flowlabel);
 	} else {
diff --git a/net/iucv/af_iucv.c b/net/iucv/af_iucv.c
index 09e1694b6d34..ebb62a4ebe30 100644
--- a/net/iucv/af_iucv.c
+++ b/net/iucv/af_iucv.c
@@ -512,7 +512,9 @@ static void iucv_sock_close(struct sock *sk)
 			sk->sk_state = IUCV_DISCONN;
 			sk->sk_state_change(sk);
 		}
-	case IUCV_DISCONN:   /* fall through */
+		/* fall through */
+
+	case IUCV_DISCONN:
 		sk->sk_state = IUCV_CLOSING;
 		sk->sk_state_change(sk);
 
@@ -525,8 +527,9 @@ static void iucv_sock_close(struct sock *sk)
 					iucv_sock_in_state(sk, IUCV_CLOSED, 0),
 					timeo);
 		}
+		/* fall through */
 
-	case IUCV_CLOSING:   /* fall through */
+	case IUCV_CLOSING:
 		sk->sk_state = IUCV_CLOSED;
 		sk->sk_state_change(sk);
 
@@ -535,8 +538,9 @@ static void iucv_sock_close(struct sock *sk)
 
 		skb_queue_purge(&iucv->send_skb_q);
 		skb_queue_purge(&iucv->backlog_skb_q);
+		/* fall through */
 
-	default:   /* fall through */
+	default:
 		iucv_sever_path(sk, 1);
 	}
 
@@ -2247,10 +2251,10 @@ static int afiucv_hs_rcv(struct sk_buff *skb, struct net_device *dev,
 			kfree_skb(skb);
 			break;
 		}
-		/* fall through and receive non-zero length data */
+		/* fall through - and receive non-zero length data */
 	case (AF_IUCV_FLAG_SHT):
 		/* shutdown request */
-		/* fall through and receive zero length data */
+		/* fall through - and receive zero length data */
 	case 0:
 		/* plain data frame */
 		IUCV_SKB_CB(skb)->class = trans_hdr->iucv_hdr.class;
diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c
index 1d0e5904dedf..c54cb59593ef 100644
--- a/net/l2tp/l2tp_ppp.c
+++ b/net/l2tp/l2tp_ppp.c
@@ -1681,6 +1681,9 @@ static const struct proto_ops pppol2tp_ops = {
 	.recvmsg	= pppol2tp_recvmsg,
 	.mmap		= sock_no_mmap,
 	.ioctl		= pppox_ioctl,
+#ifdef CONFIG_COMPAT
+	.compat_ioctl = pppox_compat_ioctl,
+#endif
 };
 
 static const struct pppox_proto pppol2tp_proto = {
diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c
index 76cc9e967fa6..4d458067d80d 100644
--- a/net/mac80211/cfg.c
+++ b/net/mac80211/cfg.c
@@ -936,8 +936,10 @@ static int ieee80211_assign_beacon(struct ieee80211_sub_if_data *sdata,
 
 	err = ieee80211_set_probe_resp(sdata, params->probe_resp,
 				       params->probe_resp_len, csa);
-	if (err < 0)
+	if (err < 0) {
+		kfree(new);
 		return err;
+	}
 	if (err == 0)
 		changed |= BSS_CHANGED_AP_PROBE_RESP;
 
@@ -949,8 +951,10 @@ static int ieee80211_assign_beacon(struct ieee80211_sub_if_data *sdata,
 							 params->civicloc,
 							 params->civicloc_len);
 
-		if (err < 0)
+		if (err < 0) {
+			kfree(new);
 			return err;
+		}
 
 		changed |= BSS_CHANGED_FTM_RESPONDER;
 	}
diff --git a/net/mac80211/driver-ops.c b/net/mac80211/driver-ops.c
index acd4afb4944b..c9a8a2433e8a 100644
--- a/net/mac80211/driver-ops.c
+++ b/net/mac80211/driver-ops.c
@@ -187,11 +187,16 @@ int drv_conf_tx(struct ieee80211_local *local,
 	if (!check_sdata_in_driver(sdata))
 		return -EIO;
 
-	if (WARN_ONCE(params->cw_min == 0 ||
-		      params->cw_min > params->cw_max,
-		      "%s: invalid CW_min/CW_max: %d/%d\n",
-		      sdata->name, params->cw_min, params->cw_max))
+	if (params->cw_min == 0 || params->cw_min > params->cw_max) {
+		/*
+		 * If we can't configure hardware anyway, don't warn. We may
+		 * never have initialized the CW parameters.
+		 */
+		WARN_ONCE(local->ops->conf_tx,
+			  "%s: invalid CW_min/CW_max: %d/%d\n",
+			  sdata->name, params->cw_min, params->cw_max);
 		return -EINVAL;
+	}
 
 	trace_drv_conf_tx(local, sdata, ac, params);
 	if (local->ops->conf_tx)
diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c
index 06aac0aaae64..8dc6580e1787 100644
--- a/net/mac80211/iface.c
+++ b/net/mac80211/iface.c
@@ -1222,7 +1222,6 @@ static void ieee80211_if_setup(struct net_device *dev)
 static void ieee80211_if_setup_no_queue(struct net_device *dev)
 {
 	ieee80211_if_setup(dev);
-	dev->features |= NETIF_F_LLTX;
 	dev->priv_flags |= IFF_NO_QUEUE;
 }
 
diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c
index a99ad0325309..4c888dc9bd81 100644
--- a/net/mac80211/mlme.c
+++ b/net/mac80211/mlme.c
@@ -2042,6 +2042,16 @@ ieee80211_sta_wmm_params(struct ieee80211_local *local,
 		ieee80211_regulatory_limit_wmm_params(sdata, &params[ac], ac);
 	}
 
+	/* WMM specification requires all 4 ACIs. */
+	for (ac = 0; ac < IEEE80211_NUM_ACS; ac++) {
+		if (params[ac].cw_min == 0) {
+			sdata_info(sdata,
+				   "AP has invalid WMM params (missing AC %d), using defaults\n",
+				   ac);
+			return false;
+		}
+	}
+
 	for (ac = 0; ac < IEEE80211_NUM_ACS; ac++) {
 		mlme_dbg(sdata,
 			 "WMM AC=%d acm=%d aifs=%d cWmin=%d cWmax=%d txop=%d uapsd=%d, downgraded=%d\n",
diff --git a/net/mac80211/util.c b/net/mac80211/util.c
index 1b224fa27367..ad1e58184c4e 100644
--- a/net/mac80211/util.c
+++ b/net/mac80211/util.c
@@ -3796,9 +3796,7 @@ int ieee80211_check_combinations(struct ieee80211_sub_if_data *sdata,
 	}
 
 	/* Always allow software iftypes */
-	if (local->hw.wiphy->software_iftypes & BIT(iftype) ||
-	    (iftype == NL80211_IFTYPE_AP_VLAN &&
-	     local->hw.wiphy->flags & WIPHY_FLAG_4ADDR_AP)) {
+	if (cfg80211_iftype_allowed(local->hw.wiphy, iftype, 0, 1)) {
 		if (radar_detect)
 			return -EINVAL;
 		return 0;
@@ -3833,7 +3831,8 @@ int ieee80211_check_combinations(struct ieee80211_sub_if_data *sdata,
 
 		if (sdata_iter == sdata ||
 		    !ieee80211_sdata_running(sdata_iter) ||
-		    local->hw.wiphy->software_iftypes & BIT(wdev_iter->iftype))
+		    cfg80211_iftype_allowed(local->hw.wiphy,
+					    wdev_iter->iftype, 0, 1))
 			continue;
 
 		params.iftype_num[wdev_iter->iftype]++;
diff --git a/net/mpls/af_mpls.c b/net/mpls/af_mpls.c
index 198ec4fe4148..c312741df2ce 100644
--- a/net/mpls/af_mpls.c
+++ b/net/mpls/af_mpls.c
@@ -37,8 +37,6 @@
 
 #define MPLS_NEIGH_TABLE_UNSPEC (NEIGH_LINK_TABLE + 1)
 
-static int zero = 0;
-static int one = 1;
 static int label_limit = (1 << 20) - 1;
 static int ttl_max = 255;
 
@@ -2607,7 +2605,7 @@ static int mpls_platform_labels(struct ctl_table *table, int write,
 		.data		= &platform_labels,
 		.maxlen		= sizeof(int),
 		.mode		= table->mode,
-		.extra1		= &zero,
+		.extra1		= SYSCTL_ZERO,
 		.extra2		= &label_limit,
 	};
 
@@ -2636,8 +2634,8 @@ static const struct ctl_table mpls_table[] = {
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec_minmax,
-		.extra1		= &zero,
-		.extra2		= &one,
+		.extra1		= SYSCTL_ZERO,
+		.extra2		= SYSCTL_ONE,
 	},
 	{
 		.procname	= "default_ttl",
@@ -2645,7 +2643,7 @@ static const struct ctl_table mpls_table[] = {
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec_minmax,
-		.extra1		= &one,
+		.extra1		= SYSCTL_ONE,
 		.extra2		= &ttl_max,
 	},
 	{ }
diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig
index 32a45c03786e..0d65f4d39494 100644
--- a/net/netfilter/Kconfig
+++ b/net/netfilter/Kconfig
@@ -223,8 +223,6 @@ config NF_CONNTRACK_FTP
 	  of Network Address Translation on them.
 
 	  This is FTP support on Layer 3 independent connection tracking.
-	  Layer 3 independent connection tracking is experimental scheme
-	  which generalize ip_conntrack to support other layer 3 protocols.
 
 	  To compile it as a module, choose M here.  If unsure, say N.
 
@@ -338,7 +336,7 @@ config NF_CONNTRACK_SIP
 	help
 	  SIP is an application-layer control protocol that can establish,
 	  modify, and terminate multimedia sessions (conferences) such as
-	  Internet telephony calls. With the ip_conntrack_sip and
+	  Internet telephony calls. With the nf_conntrack_sip and
 	  the nf_nat_sip modules you can support the protocol on a connection
 	  tracking/NATing firewall.
 
@@ -1313,7 +1311,7 @@ config NETFILTER_XT_MATCH_HELPER
 	depends on NETFILTER_ADVANCED
 	help
 	  Helper matching allows you to match packets in dynamic connections
-	  tracked by a conntrack-helper, ie. ip_conntrack_ftp
+	  tracked by a conntrack-helper, ie. nf_conntrack_ftp
 
 	  To compile it as a module, choose M here.  If unsure, say Y.
 
diff --git a/net/netfilter/ipset/ip_set_bitmap_ipmac.c b/net/netfilter/ipset/ip_set_bitmap_ipmac.c
index ca7ac4a25ada..1d4e63326e68 100644
--- a/net/netfilter/ipset/ip_set_bitmap_ipmac.c
+++ b/net/netfilter/ipset/ip_set_bitmap_ipmac.c
@@ -226,7 +226,7 @@ bitmap_ipmac_kadt(struct ip_set *set, const struct sk_buff *skb,
 
 	e.id = ip_to_id(map, ip);
 
-	if (opt->flags & IPSET_DIM_ONE_SRC)
+	if (opt->flags & IPSET_DIM_TWO_SRC)
 		ether_addr_copy(e.ether, eth_hdr(skb)->h_source);
 	else
 		ether_addr_copy(e.ether, eth_hdr(skb)->h_dest);
diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c
index 2e151856ad99..e64d5f9a89dd 100644
--- a/net/netfilter/ipset/ip_set_core.c
+++ b/net/netfilter/ipset/ip_set_core.c
@@ -1161,7 +1161,7 @@ static int ip_set_rename(struct net *net, struct sock *ctnl,
 		return -ENOENT;
 
 	write_lock_bh(&ip_set_ref_lock);
-	if (set->ref != 0) {
+	if (set->ref != 0 || set->ref_netlink != 0) {
 		ret = -IPSET_ERR_REFERENCED;
 		goto out;
 	}
diff --git a/net/netfilter/ipset/ip_set_hash_ipmac.c b/net/netfilter/ipset/ip_set_hash_ipmac.c
index faf59b6a998f..24d8f4df4230 100644
--- a/net/netfilter/ipset/ip_set_hash_ipmac.c
+++ b/net/netfilter/ipset/ip_set_hash_ipmac.c
@@ -89,15 +89,11 @@ hash_ipmac4_kadt(struct ip_set *set, const struct sk_buff *skb,
 	struct hash_ipmac4_elem e = { .ip = 0, { .foo[0] = 0, .foo[1] = 0 } };
 	struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, set);
 
-	 /* MAC can be src only */
-	if (!(opt->flags & IPSET_DIM_TWO_SRC))
-		return 0;
-
 	if (skb_mac_header(skb) < skb->head ||
 	    (skb_mac_header(skb) + ETH_HLEN) > skb->data)
 		return -EINVAL;
 
-	if (opt->flags & IPSET_DIM_ONE_SRC)
+	if (opt->flags & IPSET_DIM_TWO_SRC)
 		ether_addr_copy(e.ether, eth_hdr(skb)->h_source);
 	else
 		ether_addr_copy(e.ether, eth_hdr(skb)->h_dest);
diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c
index 07e0967bf129..060565e7d227 100644
--- a/net/netfilter/ipvs/ip_vs_ctl.c
+++ b/net/netfilter/ipvs/ip_vs_ctl.c
@@ -1726,7 +1726,6 @@ static int ip_vs_zero_all(struct netns_ipvs *ipvs)
 
 #ifdef CONFIG_SYSCTL
 
-static int zero;
 static int three = 3;
 
 static int
@@ -1935,7 +1934,7 @@ static struct ctl_table vs_vars[] = {
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec_minmax,
-		.extra1		= &zero,
+		.extra1		= SYSCTL_ZERO,
 		.extra2		= &three,
 	},
 	{
diff --git a/net/netfilter/ipvs/ip_vs_nfct.c b/net/netfilter/ipvs/ip_vs_nfct.c
index 403541996952..08adcb222986 100644
--- a/net/netfilter/ipvs/ip_vs_nfct.c
+++ b/net/netfilter/ipvs/ip_vs_nfct.c
@@ -231,7 +231,7 @@ void ip_vs_nfct_expect_related(struct sk_buff *skb, struct nf_conn *ct,
 
 	IP_VS_DBG_BUF(7, "%s: ct=%p, expect tuple=" FMT_TUPLE "\n",
 		      __func__, ct, ARG_TUPLE(&exp->tuple));
-	nf_ct_expect_related(exp);
+	nf_ct_expect_related(exp, 0);
 	nf_ct_expect_put(exp);
 }
 EXPORT_SYMBOL(ip_vs_nfct_expect_related);
diff --git a/net/netfilter/nf_conntrack_amanda.c b/net/netfilter/nf_conntrack_amanda.c
index 42ee659d0d1e..d011d2eb0848 100644
--- a/net/netfilter/nf_conntrack_amanda.c
+++ b/net/netfilter/nf_conntrack_amanda.c
@@ -159,7 +159,7 @@ static int amanda_help(struct sk_buff *skb,
 		if (nf_nat_amanda && ct->status & IPS_NAT_MASK)
 			ret = nf_nat_amanda(skb, ctinfo, protoff,
 					    off - dataoff, len, exp);
-		else if (nf_ct_expect_related(exp) != 0) {
+		else if (nf_ct_expect_related(exp, 0) != 0) {
 			nf_ct_helper_log(skb, ct, "cannot add expectation");
 			ret = NF_DROP;
 		}
diff --git a/net/netfilter/nf_conntrack_broadcast.c b/net/netfilter/nf_conntrack_broadcast.c
index 921a7b95be68..1ba6becc3079 100644
--- a/net/netfilter/nf_conntrack_broadcast.c
+++ b/net/netfilter/nf_conntrack_broadcast.c
@@ -68,7 +68,7 @@ int nf_conntrack_broadcast_help(struct sk_buff *skb,
 	exp->class		  = NF_CT_EXPECT_CLASS_DEFAULT;
 	exp->helper               = NULL;
 
-	nf_ct_expect_related(exp);
+	nf_ct_expect_related(exp, 0);
 	nf_ct_expect_put(exp);
 
 	nf_ct_refresh(ct, skb, timeout * HZ);
diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c
index bdfeacee0817..81a8ef42b88d 100644
--- a/net/netfilter/nf_conntrack_core.c
+++ b/net/netfilter/nf_conntrack_core.c
@@ -453,13 +453,12 @@ EXPORT_SYMBOL_GPL(nf_ct_invert_tuple);
  * table location, we assume id gets exposed to userspace.
  *
  * Following nf_conn items do not change throughout lifetime
- * of the nf_conn after it has been committed to main hash table:
+ * of the nf_conn:
  *
  * 1. nf_conn address
- * 2. nf_conn->ext address
- * 3. nf_conn->master address (normally NULL)
- * 4. tuple
- * 5. the associated net namespace
+ * 2. nf_conn->master address (normally NULL)
+ * 3. the associated net namespace
+ * 4. the original direction tuple
  */
 u32 nf_ct_get_id(const struct nf_conn *ct)
 {
@@ -469,9 +468,10 @@ u32 nf_ct_get_id(const struct nf_conn *ct)
 	net_get_random_once(&ct_id_seed, sizeof(ct_id_seed));
 
 	a = (unsigned long)ct;
-	b = (unsigned long)ct->master ^ net_hash_mix(nf_ct_net(ct));
-	c = (unsigned long)ct->ext;
-	d = (unsigned long)siphash(&ct->tuplehash, sizeof(ct->tuplehash),
+	b = (unsigned long)ct->master;
+	c = (unsigned long)nf_ct_net(ct);
+	d = (unsigned long)siphash(&ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple,
+				   sizeof(ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple),
 				   &ct_id_seed);
 #ifdef CONFIG_64BIT
 	return siphash_4u64((u64)a, (u64)b, (u64)c, (u64)d, &ct_id_seed);
@@ -1817,9 +1817,7 @@ EXPORT_SYMBOL_GPL(nf_ct_kill_acct);
 #include <linux/netfilter/nfnetlink_conntrack.h>
 #include <linux/mutex.h>
 
-/* Generic function for tcp/udp/sctp/dccp and alike. This needs to be
- * in ip_conntrack_core, since we don't want the protocols to autoload
- * or depend on ctnetlink */
+/* Generic function for tcp/udp/sctp/dccp and alike. */
 int nf_ct_port_tuple_to_nlattr(struct sk_buff *skb,
 			       const struct nf_conntrack_tuple *tuple)
 {
diff --git a/net/netfilter/nf_conntrack_expect.c b/net/netfilter/nf_conntrack_expect.c
index ffd1f4906c4f..65364de915d1 100644
--- a/net/netfilter/nf_conntrack_expect.c
+++ b/net/netfilter/nf_conntrack_expect.c
@@ -249,13 +249,22 @@ static inline int expect_clash(const struct nf_conntrack_expect *a,
 static inline int expect_matches(const struct nf_conntrack_expect *a,
 				 const struct nf_conntrack_expect *b)
 {
-	return a->master == b->master &&
-	       nf_ct_tuple_equal(&a->tuple, &b->tuple) &&
+	return nf_ct_tuple_equal(&a->tuple, &b->tuple) &&
 	       nf_ct_tuple_mask_equal(&a->mask, &b->mask) &&
 	       net_eq(nf_ct_net(a->master), nf_ct_net(b->master)) &&
 	       nf_ct_zone_equal_any(a->master, nf_ct_zone(b->master));
 }
 
+static bool master_matches(const struct nf_conntrack_expect *a,
+			   const struct nf_conntrack_expect *b,
+			   unsigned int flags)
+{
+	if (flags & NF_CT_EXP_F_SKIP_MASTER)
+		return true;
+
+	return a->master == b->master;
+}
+
 /* Generally a bad idea to call this: could have matched already. */
 void nf_ct_unexpect_related(struct nf_conntrack_expect *exp)
 {
@@ -399,7 +408,8 @@ static void evict_oldest_expect(struct nf_conn *master,
 		nf_ct_remove_expect(last);
 }
 
-static inline int __nf_ct_expect_check(struct nf_conntrack_expect *expect)
+static inline int __nf_ct_expect_check(struct nf_conntrack_expect *expect,
+				       unsigned int flags)
 {
 	const struct nf_conntrack_expect_policy *p;
 	struct nf_conntrack_expect *i;
@@ -417,8 +427,10 @@ static inline int __nf_ct_expect_check(struct nf_conntrack_expect *expect)
 	}
 	h = nf_ct_expect_dst_hash(net, &expect->tuple);
 	hlist_for_each_entry_safe(i, next, &nf_ct_expect_hash[h], hnode) {
-		if (expect_matches(i, expect)) {
-			if (i->class != expect->class)
+		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))
@@ -453,12 +465,12 @@ out:
 }
 
 int nf_ct_expect_related_report(struct nf_conntrack_expect *expect,
-				u32 portid, int report)
+				u32 portid, int report, unsigned int flags)
 {
 	int ret;
 
 	spin_lock_bh(&nf_conntrack_expect_lock);
-	ret = __nf_ct_expect_check(expect);
+	ret = __nf_ct_expect_check(expect, flags);
 	if (ret < 0)
 		goto out;
 
diff --git a/net/netfilter/nf_conntrack_ftp.c b/net/netfilter/nf_conntrack_ftp.c
index 8c6c11bab5b6..0ecb3e289ef2 100644
--- a/net/netfilter/nf_conntrack_ftp.c
+++ b/net/netfilter/nf_conntrack_ftp.c
@@ -525,7 +525,7 @@ skip_nl_seq:
 				 protoff, matchoff, matchlen, exp);
 	else {
 		/* Can't expect this?  Best to drop packet now. */
-		if (nf_ct_expect_related(exp) != 0) {
+		if (nf_ct_expect_related(exp, 0) != 0) {
 			nf_ct_helper_log(skb, ct, "cannot add expectation");
 			ret = NF_DROP;
 		} else
diff --git a/net/netfilter/nf_conntrack_h323_asn1.c b/net/netfilter/nf_conntrack_h323_asn1.c
index 8f6ba8162f0b..573cb4481481 100644
--- a/net/netfilter/nf_conntrack_h323_asn1.c
+++ b/net/netfilter/nf_conntrack_h323_asn1.c
@@ -1,11 +1,10 @@
 // SPDX-License-Identifier: GPL-2.0-only
 /*
- * ip_conntrack_helper_h323_asn1.c - BER and PER decoding library for H.323
- * 			      	     conntrack/NAT module.
+ * BER and PER decoding library for H.323 conntrack/NAT module.
  *
  * Copyright (c) 2006 by Jing Min Zhao <zhaojingmin@users.sourceforge.net>
  *
- * See ip_conntrack_helper_h323_asn1.h for details.
+ * See nf_conntrack_helper_h323_asn1.h for details.
  */
 
 #ifdef __KERNEL__
diff --git a/net/netfilter/nf_conntrack_h323_main.c b/net/netfilter/nf_conntrack_h323_main.c
index 6497e5fc0871..8ba037b76ad3 100644
--- a/net/netfilter/nf_conntrack_h323_main.c
+++ b/net/netfilter/nf_conntrack_h323_main.c
@@ -305,8 +305,8 @@ static int expect_rtp_rtcp(struct sk_buff *skb, struct nf_conn *ct,
 		ret = nat_rtp_rtcp(skb, ct, ctinfo, protoff, data, dataoff,
 				   taddr, port, rtp_port, rtp_exp, rtcp_exp);
 	} else {		/* Conntrack only */
-		if (nf_ct_expect_related(rtp_exp) == 0) {
-			if (nf_ct_expect_related(rtcp_exp) == 0) {
+		if (nf_ct_expect_related(rtp_exp, 0) == 0) {
+			if (nf_ct_expect_related(rtcp_exp, 0) == 0) {
 				pr_debug("nf_ct_h323: expect RTP ");
 				nf_ct_dump_tuple(&rtp_exp->tuple);
 				pr_debug("nf_ct_h323: expect RTCP ");
@@ -364,7 +364,7 @@ static int expect_t120(struct sk_buff *skb,
 		ret = nat_t120(skb, ct, ctinfo, protoff, data, dataoff, taddr,
 			       port, exp);
 	} else {		/* Conntrack only */
-		if (nf_ct_expect_related(exp) == 0) {
+		if (nf_ct_expect_related(exp, 0) == 0) {
 			pr_debug("nf_ct_h323: expect T.120 ");
 			nf_ct_dump_tuple(&exp->tuple);
 		} else
@@ -701,7 +701,7 @@ static int expect_h245(struct sk_buff *skb, struct nf_conn *ct,
 		ret = nat_h245(skb, ct, ctinfo, protoff, data, dataoff, taddr,
 			       port, exp);
 	} else {		/* Conntrack only */
-		if (nf_ct_expect_related(exp) == 0) {
+		if (nf_ct_expect_related(exp, 0) == 0) {
 			pr_debug("nf_ct_q931: expect H.245 ");
 			nf_ct_dump_tuple(&exp->tuple);
 		} else
@@ -825,7 +825,7 @@ static int expect_callforwarding(struct sk_buff *skb,
 					 protoff, data, dataoff,
 					 taddr, port, exp);
 	} else {		/* Conntrack only */
-		if (nf_ct_expect_related(exp) == 0) {
+		if (nf_ct_expect_related(exp, 0) == 0) {
 			pr_debug("nf_ct_q931: expect Call Forwarding ");
 			nf_ct_dump_tuple(&exp->tuple);
 		} else
@@ -1284,7 +1284,7 @@ static int expect_q931(struct sk_buff *skb, struct nf_conn *ct,
 		ret = nat_q931(skb, ct, ctinfo, protoff, data,
 			       taddr, i, port, exp);
 	} else {		/* Conntrack only */
-		if (nf_ct_expect_related(exp) == 0) {
+		if (nf_ct_expect_related(exp, 0) == 0) {
 			pr_debug("nf_ct_ras: expect Q.931 ");
 			nf_ct_dump_tuple(&exp->tuple);
 
@@ -1349,7 +1349,7 @@ static int process_gcf(struct sk_buff *skb, struct nf_conn *ct,
 			  IPPROTO_UDP, NULL, &port);
 	exp->helper = nf_conntrack_helper_ras;
 
-	if (nf_ct_expect_related(exp) == 0) {
+	if (nf_ct_expect_related(exp, 0) == 0) {
 		pr_debug("nf_ct_ras: expect RAS ");
 		nf_ct_dump_tuple(&exp->tuple);
 	} else
@@ -1561,7 +1561,7 @@ static int process_acf(struct sk_buff *skb, struct nf_conn *ct,
 	exp->flags = NF_CT_EXPECT_PERMANENT;
 	exp->helper = nf_conntrack_helper_q931;
 
-	if (nf_ct_expect_related(exp) == 0) {
+	if (nf_ct_expect_related(exp, 0) == 0) {
 		pr_debug("nf_ct_ras: expect Q.931 ");
 		nf_ct_dump_tuple(&exp->tuple);
 	} else
@@ -1615,7 +1615,7 @@ static int process_lcf(struct sk_buff *skb, struct nf_conn *ct,
 	exp->flags = NF_CT_EXPECT_PERMANENT;
 	exp->helper = nf_conntrack_helper_q931;
 
-	if (nf_ct_expect_related(exp) == 0) {
+	if (nf_ct_expect_related(exp, 0) == 0) {
 		pr_debug("nf_ct_ras: expect Q.931 ");
 		nf_ct_dump_tuple(&exp->tuple);
 	} else
diff --git a/net/netfilter/nf_conntrack_irc.c b/net/netfilter/nf_conntrack_irc.c
index 7ac156f1f3bc..e40988a2f22f 100644
--- a/net/netfilter/nf_conntrack_irc.c
+++ b/net/netfilter/nf_conntrack_irc.c
@@ -213,7 +213,7 @@ static int help(struct sk_buff *skb, unsigned int protoff,
 						 addr_beg_p - ib_ptr,
 						 addr_end_p - addr_beg_p,
 						 exp);
-			else if (nf_ct_expect_related(exp) != 0) {
+			else if (nf_ct_expect_related(exp, 0) != 0) {
 				nf_ct_helper_log(skb, ct,
 						 "cannot add expectation");
 				ret = NF_DROP;
diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c
index 1b77444d5b52..6aa01eb6fe99 100644
--- a/net/netfilter/nf_conntrack_netlink.c
+++ b/net/netfilter/nf_conntrack_netlink.c
@@ -2616,7 +2616,7 @@ ctnetlink_glue_attach_expect(const struct nlattr *attr, struct nf_conn *ct,
 	if (IS_ERR(exp))
 		return PTR_ERR(exp);
 
-	err = nf_ct_expect_related_report(exp, portid, report);
+	err = nf_ct_expect_related_report(exp, portid, report, 0);
 	nf_ct_expect_put(exp);
 	return err;
 }
@@ -3367,7 +3367,7 @@ ctnetlink_create_expect(struct net *net,
 		goto err_rcu;
 	}
 
-	err = nf_ct_expect_related_report(exp, portid, report);
+	err = nf_ct_expect_related_report(exp, portid, report, 0);
 	nf_ct_expect_put(exp);
 err_rcu:
 	rcu_read_unlock();
diff --git a/net/netfilter/nf_conntrack_pptp.c b/net/netfilter/nf_conntrack_pptp.c
index b22042ad0fca..a971183f11af 100644
--- a/net/netfilter/nf_conntrack_pptp.c
+++ b/net/netfilter/nf_conntrack_pptp.c
@@ -234,9 +234,9 @@ static int exp_gre(struct nf_conn *ct, __be16 callid, __be16 peer_callid)
 	nf_nat_pptp_exp_gre = rcu_dereference(nf_nat_pptp_hook_exp_gre);
 	if (nf_nat_pptp_exp_gre && ct->status & IPS_NAT_MASK)
 		nf_nat_pptp_exp_gre(exp_orig, exp_reply);
-	if (nf_ct_expect_related(exp_orig) != 0)
+	if (nf_ct_expect_related(exp_orig, 0) != 0)
 		goto out_put_both;
-	if (nf_ct_expect_related(exp_reply) != 0)
+	if (nf_ct_expect_related(exp_reply, 0) != 0)
 		goto out_unexpect_orig;
 
 	/* Add GRE keymap entries */
diff --git a/net/netfilter/nf_conntrack_proto_gre.c b/net/netfilter/nf_conntrack_proto_gre.c
index c2eb365f1723..5b05487a60d2 100644
--- a/net/netfilter/nf_conntrack_proto_gre.c
+++ b/net/netfilter/nf_conntrack_proto_gre.c
@@ -1,7 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0-only
 /*
- * ip_conntrack_proto_gre.c - Version 3.0
- *
  * Connection tracking protocol helper module for GRE.
  *
  * GRE is a generic encapsulation protocol, which is generally not very
diff --git a/net/netfilter/nf_conntrack_proto_icmp.c b/net/netfilter/nf_conntrack_proto_icmp.c
index dd53e2b20f6b..097deba7441a 100644
--- a/net/netfilter/nf_conntrack_proto_icmp.c
+++ b/net/netfilter/nf_conntrack_proto_icmp.c
@@ -215,7 +215,7 @@ int nf_conntrack_icmpv4_error(struct nf_conn *tmpl,
 		return -NF_ACCEPT;
 	}
 
-	/* See ip_conntrack_proto_tcp.c */
+	/* See nf_conntrack_proto_tcp.c */
 	if (state->net->ct.sysctl_checksum &&
 	    state->hook == NF_INET_PRE_ROUTING &&
 	    nf_ip_checksum(skb, state->hook, dataoff, IPPROTO_ICMP)) {
diff --git a/net/netfilter/nf_conntrack_proto_tcp.c b/net/netfilter/nf_conntrack_proto_tcp.c
index d5fdfa00d683..85c1f8c213b0 100644
--- a/net/netfilter/nf_conntrack_proto_tcp.c
+++ b/net/netfilter/nf_conntrack_proto_tcp.c
@@ -472,6 +472,7 @@ static bool tcp_in_window(const struct nf_conn *ct,
 	struct ip_ct_tcp_state *receiver = &state->seen[!dir];
 	const struct nf_conntrack_tuple *tuple = &ct->tuplehash[dir].tuple;
 	__u32 seq, ack, sack, end, win, swin;
+	u16 win_raw;
 	s32 receiver_offset;
 	bool res, in_recv_win;
 
@@ -480,7 +481,8 @@ static bool tcp_in_window(const struct nf_conn *ct,
 	 */
 	seq = ntohl(tcph->seq);
 	ack = sack = ntohl(tcph->ack_seq);
-	win = ntohs(tcph->window);
+	win_raw = ntohs(tcph->window);
+	win = win_raw;
 	end = segment_seq_plus_len(seq, skb->len, dataoff, tcph);
 
 	if (receiver->flags & IP_CT_TCP_FLAG_SACK_PERM)
@@ -655,14 +657,14 @@ static bool tcp_in_window(const struct nf_conn *ct,
 			    && state->last_seq == seq
 			    && state->last_ack == ack
 			    && state->last_end == end
-			    && state->last_win == win)
+			    && state->last_win == win_raw)
 				state->retrans++;
 			else {
 				state->last_dir = dir;
 				state->last_seq = seq;
 				state->last_ack = ack;
 				state->last_end = end;
-				state->last_win = win;
+				state->last_win = win_raw;
 				state->retrans = 0;
 			}
 		}
diff --git a/net/netfilter/nf_conntrack_sane.c b/net/netfilter/nf_conntrack_sane.c
index 81448c3db661..1aebd6569d4e 100644
--- a/net/netfilter/nf_conntrack_sane.c
+++ b/net/netfilter/nf_conntrack_sane.c
@@ -153,7 +153,7 @@ static int help(struct sk_buff *skb,
 	nf_ct_dump_tuple(&exp->tuple);
 
 	/* Can't expect this?  Best to drop packet now. */
-	if (nf_ct_expect_related(exp) != 0) {
+	if (nf_ct_expect_related(exp, 0) != 0) {
 		nf_ct_helper_log(skb, ct, "cannot add expectation");
 		ret = NF_DROP;
 	}
diff --git a/net/netfilter/nf_conntrack_sip.c b/net/netfilter/nf_conntrack_sip.c
index 107251731809..b83dc9bf0a5d 100644
--- a/net/netfilter/nf_conntrack_sip.c
+++ b/net/netfilter/nf_conntrack_sip.c
@@ -977,11 +977,15 @@ static int set_expected_rtp_rtcp(struct sk_buff *skb, unsigned int protoff,
 		/* -EALREADY handling works around end-points that send
 		 * SDP messages with identical port but different media type,
 		 * we pretend expectation was set up.
+		 * It also works in the case that SDP messages are sent with
+		 * identical expect tuples but for different master conntracks.
 		 */
-		int errp = nf_ct_expect_related(rtp_exp);
+		int errp = nf_ct_expect_related(rtp_exp,
+						NF_CT_EXP_F_SKIP_MASTER);
 
 		if (errp == 0 || errp == -EALREADY) {
-			int errcp = nf_ct_expect_related(rtcp_exp);
+			int errcp = nf_ct_expect_related(rtcp_exp,
+						NF_CT_EXP_F_SKIP_MASTER);
 
 			if (errcp == 0 || errcp == -EALREADY)
 				ret = NF_ACCEPT;
@@ -1296,7 +1300,7 @@ static int process_register_request(struct sk_buff *skb, unsigned int protoff,
 		ret = hooks->expect(skb, protoff, dataoff, dptr, datalen,
 				    exp, matchoff, matchlen);
 	else {
-		if (nf_ct_expect_related(exp) != 0) {
+		if (nf_ct_expect_related(exp, 0) != 0) {
 			nf_ct_helper_log(skb, ct, "cannot add expectation");
 			ret = NF_DROP;
 		} else
diff --git a/net/netfilter/nf_conntrack_tftp.c b/net/netfilter/nf_conntrack_tftp.c
index df6d6d61bd58..80ee53f29f68 100644
--- a/net/netfilter/nf_conntrack_tftp.c
+++ b/net/netfilter/nf_conntrack_tftp.c
@@ -78,7 +78,7 @@ static int tftp_help(struct sk_buff *skb,
 		nf_nat_tftp = rcu_dereference(nf_nat_tftp_hook);
 		if (nf_nat_tftp && ct->status & IPS_NAT_MASK)
 			ret = nf_nat_tftp(skb, ctinfo, exp);
-		else if (nf_ct_expect_related(exp) != 0) {
+		else if (nf_ct_expect_related(exp, 0) != 0) {
 			nf_ct_helper_log(skb, ct, "cannot add expectation");
 			ret = NF_DROP;
 		}
diff --git a/net/netfilter/nf_flow_table_core.c b/net/netfilter/nf_flow_table_core.c
index e3d797252a98..80a8f9ae4c93 100644
--- a/net/netfilter/nf_flow_table_core.c
+++ b/net/netfilter/nf_flow_table_core.c
@@ -111,15 +111,16 @@ static void flow_offload_fixup_tcp(struct ip_ct_tcp *tcp)
 #define NF_FLOWTABLE_TCP_PICKUP_TIMEOUT	(120 * HZ)
 #define NF_FLOWTABLE_UDP_PICKUP_TIMEOUT	(30 * HZ)
 
-static void flow_offload_fixup_ct_state(struct nf_conn *ct)
+static inline __s32 nf_flow_timeout_delta(unsigned int timeout)
+{
+	return (__s32)(timeout - (u32)jiffies);
+}
+
+static void flow_offload_fixup_ct_timeout(struct nf_conn *ct)
 {
 	const struct nf_conntrack_l4proto *l4proto;
+	int l4num = nf_ct_protonum(ct);
 	unsigned int timeout;
-	int l4num;
-
-	l4num = nf_ct_protonum(ct);
-	if (l4num == IPPROTO_TCP)
-		flow_offload_fixup_tcp(&ct->proto.tcp);
 
 	l4proto = nf_ct_l4proto_find(l4num);
 	if (!l4proto)
@@ -132,7 +133,20 @@ static void flow_offload_fixup_ct_state(struct nf_conn *ct)
 	else
 		return;
 
-	ct->timeout = nfct_time_stamp + timeout;
+	if (nf_flow_timeout_delta(ct->timeout) > (__s32)timeout)
+		ct->timeout = nfct_time_stamp + timeout;
+}
+
+static void flow_offload_fixup_ct_state(struct nf_conn *ct)
+{
+	if (nf_ct_protonum(ct) == IPPROTO_TCP)
+		flow_offload_fixup_tcp(&ct->proto.tcp);
+}
+
+static void flow_offload_fixup_ct(struct nf_conn *ct)
+{
+	flow_offload_fixup_ct_state(ct);
+	flow_offload_fixup_ct_timeout(ct);
 }
 
 void flow_offload_free(struct flow_offload *flow)
@@ -208,6 +222,11 @@ int flow_offload_add(struct nf_flowtable *flow_table, struct flow_offload *flow)
 }
 EXPORT_SYMBOL_GPL(flow_offload_add);
 
+static inline bool nf_flow_has_expired(const struct flow_offload *flow)
+{
+	return nf_flow_timeout_delta(flow->timeout) <= 0;
+}
+
 static void flow_offload_del(struct nf_flowtable *flow_table,
 			     struct flow_offload *flow)
 {
@@ -223,6 +242,11 @@ static void flow_offload_del(struct nf_flowtable *flow_table,
 	e = container_of(flow, struct flow_offload_entry, flow);
 	clear_bit(IPS_OFFLOAD_BIT, &e->ct->status);
 
+	if (nf_flow_has_expired(flow))
+		flow_offload_fixup_ct(e->ct);
+	else if (flow->flags & FLOW_OFFLOAD_TEARDOWN)
+		flow_offload_fixup_ct_timeout(e->ct);
+
 	flow_offload_free(flow);
 }
 
@@ -298,11 +322,6 @@ nf_flow_table_iterate(struct nf_flowtable *flow_table,
 	return err;
 }
 
-static inline bool nf_flow_has_expired(const struct flow_offload *flow)
-{
-	return (__s32)(flow->timeout - (u32)jiffies) <= 0;
-}
-
 static void nf_flow_offload_gc_step(struct flow_offload *flow, void *data)
 {
 	struct nf_flowtable *flow_table = data;
diff --git a/net/netfilter/nf_flow_table_ip.c b/net/netfilter/nf_flow_table_ip.c
index cdfc33517e85..d68c801dd614 100644
--- a/net/netfilter/nf_flow_table_ip.c
+++ b/net/netfilter/nf_flow_table_ip.c
@@ -214,6 +214,25 @@ static bool nf_flow_exceeds_mtu(const struct sk_buff *skb, unsigned int mtu)
 	return true;
 }
 
+static int nf_flow_offload_dst_check(struct dst_entry *dst)
+{
+	if (unlikely(dst_xfrm(dst)))
+		return dst_check(dst, 0) ? 0 : -1;
+
+	return 0;
+}
+
+static unsigned int nf_flow_xmit_xfrm(struct sk_buff *skb,
+				      const struct nf_hook_state *state,
+				      struct dst_entry *dst)
+{
+	skb_orphan(skb);
+	skb_dst_set_noref(skb, dst);
+	skb->tstamp = 0;
+	dst_output(state->net, state->sk, skb);
+	return NF_STOLEN;
+}
+
 unsigned int
 nf_flow_offload_ip_hook(void *priv, struct sk_buff *skb,
 			const struct nf_hook_state *state)
@@ -254,6 +273,11 @@ nf_flow_offload_ip_hook(void *priv, struct sk_buff *skb,
 	if (nf_flow_state_check(flow, ip_hdr(skb)->protocol, skb, thoff))
 		return NF_ACCEPT;
 
+	if (nf_flow_offload_dst_check(&rt->dst)) {
+		flow_offload_teardown(flow);
+		return NF_ACCEPT;
+	}
+
 	if (nf_flow_nat_ip(flow, skb, thoff, dir) < 0)
 		return NF_DROP;
 
@@ -261,6 +285,13 @@ nf_flow_offload_ip_hook(void *priv, struct sk_buff *skb,
 	iph = ip_hdr(skb);
 	ip_decrease_ttl(iph);
 
+	if (unlikely(dst_xfrm(&rt->dst))) {
+		memset(skb->cb, 0, sizeof(struct inet_skb_parm));
+		IPCB(skb)->iif = skb->dev->ifindex;
+		IPCB(skb)->flags = IPSKB_FORWARDED;
+		return nf_flow_xmit_xfrm(skb, state, &rt->dst);
+	}
+
 	skb->dev = outdev;
 	nexthop = rt_nexthop(rt, flow->tuplehash[!dir].tuple.src_v4.s_addr);
 	skb_dst_set_noref(skb, &rt->dst);
@@ -467,6 +498,11 @@ nf_flow_offload_ipv6_hook(void *priv, struct sk_buff *skb,
 				sizeof(*ip6h)))
 		return NF_ACCEPT;
 
+	if (nf_flow_offload_dst_check(&rt->dst)) {
+		flow_offload_teardown(flow);
+		return NF_ACCEPT;
+	}
+
 	if (skb_try_make_writable(skb, sizeof(*ip6h)))
 		return NF_DROP;
 
@@ -477,6 +513,13 @@ nf_flow_offload_ipv6_hook(void *priv, struct sk_buff *skb,
 	ip6h = ipv6_hdr(skb);
 	ip6h->hop_limit--;
 
+	if (unlikely(dst_xfrm(&rt->dst))) {
+		memset(skb->cb, 0, sizeof(struct inet6_skb_parm));
+		IP6CB(skb)->iif = skb->dev->ifindex;
+		IP6CB(skb)->flags = IP6SKB_FORWARDED;
+		return nf_flow_xmit_xfrm(skb, state, &rt->dst);
+	}
+
 	skb->dev = outdev;
 	nexthop = rt6_nexthop(rt, &flow->tuplehash[!dir].tuple.src_v6);
 	skb_dst_set_noref(skb, &rt->dst);
diff --git a/net/netfilter/nf_nat_amanda.c b/net/netfilter/nf_nat_amanda.c
index a352604d6186..3bc7e0854efe 100644
--- a/net/netfilter/nf_nat_amanda.c
+++ b/net/netfilter/nf_nat_amanda.c
@@ -48,7 +48,7 @@ static unsigned int help(struct sk_buff *skb,
 		int res;
 
 		exp->tuple.dst.u.tcp.port = htons(port);
-		res = nf_ct_expect_related(exp);
+		res = nf_ct_expect_related(exp, 0);
 		if (res == 0)
 			break;
 		else if (res != -EBUSY) {
diff --git a/net/netfilter/nf_nat_core.c b/net/netfilter/nf_nat_core.c
index 9ab410455992..3f6023ed4966 100644
--- a/net/netfilter/nf_nat_core.c
+++ b/net/netfilter/nf_nat_core.c
@@ -519,7 +519,7 @@ another_round:
  * and NF_INET_LOCAL_OUT, we change the destination to map into the
  * range. It might not be possible to get a unique tuple, but we try.
  * At worst (or if we race), we will end up with a final duplicate in
- * __ip_conntrack_confirm and drop the packet. */
+ * __nf_conntrack_confirm and drop the packet. */
 static void
 get_unique_tuple(struct nf_conntrack_tuple *tuple,
 		 const struct nf_conntrack_tuple *orig_tuple,
diff --git a/net/netfilter/nf_nat_ftp.c b/net/netfilter/nf_nat_ftp.c
index d48484a9d52d..aace6768a64e 100644
--- a/net/netfilter/nf_nat_ftp.c
+++ b/net/netfilter/nf_nat_ftp.c
@@ -91,7 +91,7 @@ static unsigned int nf_nat_ftp(struct sk_buff *skb,
 		int ret;
 
 		exp->tuple.dst.u.tcp.port = htons(port);
-		ret = nf_ct_expect_related(exp);
+		ret = nf_ct_expect_related(exp, 0);
 		if (ret == 0)
 			break;
 		else if (ret != -EBUSY) {
diff --git a/net/netfilter/nf_nat_irc.c b/net/netfilter/nf_nat_irc.c
index dfb7ef8845bd..c691ab8d234c 100644
--- a/net/netfilter/nf_nat_irc.c
+++ b/net/netfilter/nf_nat_irc.c
@@ -53,7 +53,7 @@ static unsigned int help(struct sk_buff *skb,
 		int ret;
 
 		exp->tuple.dst.u.tcp.port = htons(port);
-		ret = nf_ct_expect_related(exp);
+		ret = nf_ct_expect_related(exp, 0);
 		if (ret == 0)
 			break;
 		else if (ret != -EBUSY) {
diff --git a/net/netfilter/nf_nat_sip.c b/net/netfilter/nf_nat_sip.c
index e338d91980d8..f0a735e86851 100644
--- a/net/netfilter/nf_nat_sip.c
+++ b/net/netfilter/nf_nat_sip.c
@@ -414,7 +414,7 @@ static unsigned int nf_nat_sip_expect(struct sk_buff *skb, unsigned int protoff,
 		int ret;
 
 		exp->tuple.dst.u.udp.port = htons(port);
-		ret = nf_ct_expect_related(exp);
+		ret = nf_ct_expect_related(exp, NF_CT_EXP_F_SKIP_MASTER);
 		if (ret == 0)
 			break;
 		else if (ret != -EBUSY) {
@@ -607,7 +607,8 @@ static unsigned int nf_nat_sdp_media(struct sk_buff *skb, unsigned int protoff,
 		int ret;
 
 		rtp_exp->tuple.dst.u.udp.port = htons(port);
-		ret = nf_ct_expect_related(rtp_exp);
+		ret = nf_ct_expect_related(rtp_exp,
+					   NF_CT_EXP_F_SKIP_MASTER);
 		if (ret == -EBUSY)
 			continue;
 		else if (ret < 0) {
@@ -615,7 +616,8 @@ static unsigned int nf_nat_sdp_media(struct sk_buff *skb, unsigned int protoff,
 			break;
 		}
 		rtcp_exp->tuple.dst.u.udp.port = htons(port + 1);
-		ret = nf_ct_expect_related(rtcp_exp);
+		ret = nf_ct_expect_related(rtcp_exp,
+					   NF_CT_EXP_F_SKIP_MASTER);
 		if (ret == 0)
 			break;
 		else if (ret == -EBUSY) {
diff --git a/net/netfilter/nf_nat_tftp.c b/net/netfilter/nf_nat_tftp.c
index 833a11f68031..1a591132d6eb 100644
--- a/net/netfilter/nf_nat_tftp.c
+++ b/net/netfilter/nf_nat_tftp.c
@@ -30,7 +30,7 @@ static unsigned int help(struct sk_buff *skb,
 		= ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.u.udp.port;
 	exp->dir = IP_CT_DIR_REPLY;
 	exp->expectfn = nf_nat_follow_master;
-	if (nf_ct_expect_related(exp) != 0) {
+	if (nf_ct_expect_related(exp, 0) != 0) {
 		nf_ct_helper_log(skb, exp->master, "cannot add expectation");
 		return NF_DROP;
 	}
diff --git a/net/netfilter/nf_synproxy_core.c b/net/netfilter/nf_synproxy_core.c
index b101f187eda8..c769462a839e 100644
--- a/net/netfilter/nf_synproxy_core.c
+++ b/net/netfilter/nf_synproxy_core.c
@@ -470,7 +470,7 @@ synproxy_send_client_synack(struct net *net,
 	struct iphdr *iph, *niph;
 	struct tcphdr *nth;
 	unsigned int tcp_hdr_size;
-	u16 mss = opts->mss;
+	u16 mss = opts->mss_encode;
 
 	iph = ip_hdr(skb);
 
@@ -687,7 +687,7 @@ ipv4_synproxy_hook(void *priv, struct sk_buff *skb,
 	state = &ct->proto.tcp;
 	switch (state->state) {
 	case TCP_CONNTRACK_CLOSE:
-		if (th->rst && !test_bit(IPS_SEEN_REPLY_BIT, &ct->status)) {
+		if (th->rst && CTINFO2DIR(ctinfo) != IP_CT_DIR_ORIGINAL) {
 			nf_ct_seqadj_init(ct, ctinfo, synproxy->isn -
 						      ntohl(th->seq) + 1);
 			break;
@@ -884,7 +884,7 @@ synproxy_send_client_synack_ipv6(struct net *net,
 	struct ipv6hdr *iph, *niph;
 	struct tcphdr *nth;
 	unsigned int tcp_hdr_size;
-	u16 mss = opts->mss;
+	u16 mss = opts->mss_encode;
 
 	iph = ipv6_hdr(skb);
 
@@ -1111,7 +1111,7 @@ ipv6_synproxy_hook(void *priv, struct sk_buff *skb,
 	state = &ct->proto.tcp;
 	switch (state->state) {
 	case TCP_CONNTRACK_CLOSE:
-		if (th->rst && !test_bit(IPS_SEEN_REPLY_BIT, &ct->status)) {
+		if (th->rst && CTINFO2DIR(ctinfo) != IP_CT_DIR_ORIGINAL) {
 			nf_ct_seqadj_init(ct, ctinfo, synproxy->isn -
 						      ntohl(th->seq) + 1);
 			break;
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index ed17a7c29b86..d47469f824a1 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -138,9 +138,14 @@ static void nft_set_trans_bind(const struct nft_ctx *ctx, struct nft_set *set)
 		return;
 
 	list_for_each_entry_reverse(trans, &net->nft.commit_list, list) {
-		if (trans->msg_type == NFT_MSG_NEWSET &&
-		    nft_trans_set(trans) == set) {
-			set->bound = true;
+		switch (trans->msg_type) {
+		case NFT_MSG_NEWSET:
+			if (nft_trans_set(trans) == set)
+				nft_trans_set_bound(trans) = true;
+			break;
+		case NFT_MSG_NEWSETELEM:
+			if (nft_trans_elem_set(trans) == set)
+				nft_trans_elem_set_bound(trans) = true;
 			break;
 		}
 	}
@@ -1662,7 +1667,11 @@ static int nf_tables_addchain(struct nft_ctx *ctx, u8 family, u8 genmask,
 
 		chain->flags |= NFT_BASE_CHAIN | flags;
 		basechain->policy = NF_ACCEPT;
-		INIT_LIST_HEAD(&basechain->cb_list);
+		if (chain->flags & NFT_CHAIN_HW_OFFLOAD &&
+		    nft_chain_offload_priority(basechain) < 0)
+			return -EOPNOTSUPP;
+
+		flow_block_init(&basechain->flow_block);
 	} else {
 		chain = kzalloc(sizeof(*chain), GFP_KERNEL);
 		if (chain == NULL)
@@ -1900,6 +1909,8 @@ static int nf_tables_newchain(struct net *net, struct sock *nlsk,
 
 	if (nla[NFTA_CHAIN_FLAGS])
 		flags = ntohl(nla_get_be32(nla[NFTA_CHAIN_FLAGS]));
+	else if (chain)
+		flags = chain->flags;
 
 	nft_ctx_init(&ctx, net, skb, nlh, family, table, chain, nla);
 
@@ -6904,7 +6915,7 @@ static int __nf_tables_abort(struct net *net)
 			break;
 		case NFT_MSG_NEWSET:
 			trans->ctx.table->use--;
-			if (nft_trans_set(trans)->bound) {
+			if (nft_trans_set_bound(trans)) {
 				nft_trans_destroy(trans);
 				break;
 			}
@@ -6916,7 +6927,7 @@ static int __nf_tables_abort(struct net *net)
 			nft_trans_destroy(trans);
 			break;
 		case NFT_MSG_NEWSETELEM:
-			if (nft_trans_elem_set(trans)->bound) {
+			if (nft_trans_elem_set_bound(trans)) {
 				nft_trans_destroy(trans);
 				break;
 			}
diff --git a/net/netfilter/nf_tables_offload.c b/net/netfilter/nf_tables_offload.c
index 2c3302845f67..c0d18c1d77ac 100644
--- a/net/netfilter/nf_tables_offload.c
+++ b/net/netfilter/nf_tables_offload.c
@@ -103,10 +103,11 @@ void nft_offload_update_dependency(struct nft_offload_ctx *ctx,
 }
 
 static void nft_flow_offload_common_init(struct flow_cls_common_offload *common,
-					 __be16 proto,
-					struct netlink_ext_ack *extack)
+					 __be16 proto, int priority,
+					 struct netlink_ext_ack *extack)
 {
 	common->protocol = proto;
+	common->prio = priority;
 	common->extack = extack;
 }
 
@@ -116,7 +117,7 @@ static int nft_setup_cb_call(struct nft_base_chain *basechain,
 	struct flow_block_cb *block_cb;
 	int err;
 
-	list_for_each_entry(block_cb, &basechain->cb_list, list) {
+	list_for_each_entry(block_cb, &basechain->flow_block.cb_list, list) {
 		err = block_cb->cb(type, type_data, block_cb->cb_priv);
 		if (err < 0)
 			return err;
@@ -124,6 +125,15 @@ static int nft_setup_cb_call(struct nft_base_chain *basechain,
 	return 0;
 }
 
+int nft_chain_offload_priority(struct nft_base_chain *basechain)
+{
+	if (basechain->ops.priority <= 0 ||
+	    basechain->ops.priority > USHRT_MAX)
+		return -1;
+
+	return 0;
+}
+
 static int nft_flow_offload_rule(struct nft_trans *trans,
 				 enum flow_cls_command command)
 {
@@ -142,7 +152,8 @@ static int nft_flow_offload_rule(struct nft_trans *trans,
 	if (flow)
 		proto = flow->proto;
 
-	nft_flow_offload_common_init(&cls_flow.common, proto, &extack);
+	nft_flow_offload_common_init(&cls_flow.common, proto,
+				     basechain->ops.priority, &extack);
 	cls_flow.command = command;
 	cls_flow.cookie = (unsigned long) rule;
 	if (flow)
@@ -154,7 +165,7 @@ static int nft_flow_offload_rule(struct nft_trans *trans,
 static int nft_flow_offload_bind(struct flow_block_offload *bo,
 				 struct nft_base_chain *basechain)
 {
-	list_splice(&bo->cb_list, &basechain->cb_list);
+	list_splice(&bo->cb_list, &basechain->flow_block.cb_list);
 	return 0;
 }
 
@@ -198,6 +209,7 @@ static int nft_flow_offload_chain(struct nft_trans *trans,
 		return -EOPNOTSUPP;
 
 	bo.command = cmd;
+	bo.block = &basechain->flow_block;
 	bo.binder_type = FLOW_BLOCK_BINDER_TYPE_CLSACT_INGRESS;
 	bo.extack = &extack;
 	INIT_LIST_HEAD(&bo.cb_list);
diff --git a/net/netfilter/nfnetlink.c b/net/netfilter/nfnetlink.c
index 92077d459109..4abbb452cf6c 100644
--- a/net/netfilter/nfnetlink.c
+++ b/net/netfilter/nfnetlink.c
@@ -578,7 +578,7 @@ static int nfnetlink_bind(struct net *net, int group)
 	ss = nfnetlink_get_subsys(type << 8);
 	rcu_read_unlock();
 	if (!ss)
-		request_module("nfnetlink-subsys-%d", type);
+		request_module_nowait("nfnetlink-subsys-%d", type);
 	return 0;
 }
 #endif
diff --git a/net/netfilter/nft_chain_filter.c b/net/netfilter/nft_chain_filter.c
index 3fd540b2c6ba..b5d5d071d765 100644
--- a/net/netfilter/nft_chain_filter.c
+++ b/net/netfilter/nft_chain_filter.c
@@ -193,7 +193,7 @@ static inline void nft_chain_filter_inet_init(void) {}
 static inline void nft_chain_filter_inet_fini(void) {}
 #endif /* CONFIG_NF_TABLES_IPV6 */
 
-#ifdef CONFIG_NF_TABLES_BRIDGE
+#if IS_ENABLED(CONFIG_NF_TABLES_BRIDGE)
 static unsigned int
 nft_do_chain_bridge(void *priv,
 		    struct sk_buff *skb,
diff --git a/net/netfilter/nft_chain_nat.c b/net/netfilter/nft_chain_nat.c
index 2f89bde3c61c..ff9ac8ae0031 100644
--- a/net/netfilter/nft_chain_nat.c
+++ b/net/netfilter/nft_chain_nat.c
@@ -142,3 +142,6 @@ MODULE_ALIAS_NFT_CHAIN(AF_INET, "nat");
 #ifdef CONFIG_NF_TABLES_IPV6
 MODULE_ALIAS_NFT_CHAIN(AF_INET6, "nat");
 #endif
+#ifdef CONFIG_NF_TABLES_INET
+MODULE_ALIAS_NFT_CHAIN(1, "nat");	/* NFPROTO_INET */
+#endif
diff --git a/net/netfilter/nft_ct.c b/net/netfilter/nft_ct.c
index 827ab6196df9..46ca8bcca1bd 100644
--- a/net/netfilter/nft_ct.c
+++ b/net/netfilter/nft_ct.c
@@ -1252,7 +1252,7 @@ static void nft_ct_expect_obj_eval(struct nft_object *obj,
 		          priv->l4proto, NULL, &priv->dport);
 	exp->timeout.expires = jiffies + priv->timeout * HZ;
 
-	if (nf_ct_expect_related(exp) != 0)
+	if (nf_ct_expect_related(exp, 0) != 0)
 		regs->verdict.code = NF_DROP;
 }
 
diff --git a/net/netfilter/nft_flow_offload.c b/net/netfilter/nft_flow_offload.c
index aa5f571d4361..060a4ed46d5e 100644
--- a/net/netfilter/nft_flow_offload.c
+++ b/net/netfilter/nft_flow_offload.c
@@ -72,11 +72,11 @@ static void nft_flow_offload_eval(const struct nft_expr *expr,
 {
 	struct nft_flow_offload *priv = nft_expr_priv(expr);
 	struct nf_flowtable *flowtable = &priv->flowtable->data;
+	struct tcphdr _tcph, *tcph = NULL;
 	enum ip_conntrack_info ctinfo;
 	struct nf_flow_route route;
 	struct flow_offload *flow;
 	enum ip_conntrack_dir dir;
-	bool is_tcp = false;
 	struct nf_conn *ct;
 	int ret;
 
@@ -89,7 +89,10 @@ static void nft_flow_offload_eval(const struct nft_expr *expr,
 
 	switch (ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.dst.protonum) {
 	case IPPROTO_TCP:
-		is_tcp = true;
+		tcph = skb_header_pointer(pkt->skb, pkt->xt.thoff,
+					  sizeof(_tcph), &_tcph);
+		if (unlikely(!tcph || tcph->fin || tcph->rst))
+			goto out;
 		break;
 	case IPPROTO_UDP:
 		break;
@@ -115,7 +118,7 @@ static void nft_flow_offload_eval(const struct nft_expr *expr,
 	if (!flow)
 		goto err_flow_alloc;
 
-	if (is_tcp) {
+	if (tcph) {
 		ct->proto.tcp.seen[0].flags |= IP_CT_TCP_FLAG_BE_LIBERAL;
 		ct->proto.tcp.seen[1].flags |= IP_CT_TCP_FLAG_BE_LIBERAL;
 	}
diff --git a/net/netfilter/nft_hash.c b/net/netfilter/nft_hash.c
index fe93e731dc7f..b836d550b919 100644
--- a/net/netfilter/nft_hash.c
+++ b/net/netfilter/nft_hash.c
@@ -129,7 +129,7 @@ static int nft_symhash_init(const struct nft_ctx *ctx,
 	priv->dreg = nft_parse_register(tb[NFTA_HASH_DREG]);
 
 	priv->modulus = ntohl(nla_get_be32(tb[NFTA_HASH_MODULUS]));
-	if (priv->modulus <= 1)
+	if (priv->modulus < 1)
 		return -ERANGE;
 
 	if (priv->offset + priv->modulus - 1 < priv->offset)
diff --git a/net/netfilter/nft_meta.c b/net/netfilter/nft_meta.c
index 76866f77e343..f69afb9ff3cb 100644
--- a/net/netfilter/nft_meta.c
+++ b/net/netfilter/nft_meta.c
@@ -60,24 +60,16 @@ void nft_meta_get_eval(const struct nft_expr *expr,
 		*dest = skb->mark;
 		break;
 	case NFT_META_IIF:
-		if (in == NULL)
-			goto err;
-		*dest = in->ifindex;
+		*dest = in ? in->ifindex : 0;
 		break;
 	case NFT_META_OIF:
-		if (out == NULL)
-			goto err;
-		*dest = out->ifindex;
+		*dest = out ? out->ifindex : 0;
 		break;
 	case NFT_META_IIFNAME:
-		if (in == NULL)
-			goto err;
-		strncpy((char *)dest, in->name, IFNAMSIZ);
+		strncpy((char *)dest, in ? in->name : "", IFNAMSIZ);
 		break;
 	case NFT_META_OIFNAME:
-		if (out == NULL)
-			goto err;
-		strncpy((char *)dest, out->name, IFNAMSIZ);
+		strncpy((char *)dest, out ? out->name : "", IFNAMSIZ);
 		break;
 	case NFT_META_IIFTYPE:
 		if (in == NULL)
@@ -546,7 +538,7 @@ nft_meta_select_ops(const struct nft_ctx *ctx,
 	if (tb[NFTA_META_DREG] && tb[NFTA_META_SREG])
 		return ERR_PTR(-EINVAL);
 
-#ifdef CONFIG_NF_TABLES_BRIDGE
+#if IS_ENABLED(CONFIG_NF_TABLES_BRIDGE) && IS_MODULE(CONFIG_NFT_BRIDGE_META)
 	if (ctx->family == NFPROTO_BRIDGE)
 		return ERR_PTR(-EAGAIN);
 #endif
diff --git a/net/netfilter/nft_redir.c b/net/netfilter/nft_redir.c
index 8487eeff5c0e..43eeb1f609f1 100644
--- a/net/netfilter/nft_redir.c
+++ b/net/netfilter/nft_redir.c
@@ -291,4 +291,4 @@ module_exit(nft_redir_module_exit);
 
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Arturo Borrero Gonzalez <arturo@debian.org>");
-MODULE_ALIAS_NFT_EXPR("nat");
+MODULE_ALIAS_NFT_EXPR("redir");
diff --git a/net/netfilter/nft_synproxy.c b/net/netfilter/nft_synproxy.c
index 80060ade8a5b..928e661d1517 100644
--- a/net/netfilter/nft_synproxy.c
+++ b/net/netfilter/nft_synproxy.c
@@ -31,6 +31,8 @@ static void nft_synproxy_tcp_options(struct synproxy_options *opts,
 		opts->options |= NF_SYNPROXY_OPT_ECN;
 
 	opts->options &= priv->info.options;
+	opts->mss_encode = opts->mss;
+	opts->mss = info->mss;
 	if (opts->options & NF_SYNPROXY_OPT_TIMESTAMP)
 		synproxy_init_timestamp_cookie(info, opts);
 	else
diff --git a/net/netrom/af_netrom.c b/net/netrom/af_netrom.c
index 96740d389377..c4f54ad2b98a 100644
--- a/net/netrom/af_netrom.c
+++ b/net/netrom/af_netrom.c
@@ -967,6 +967,7 @@ int nr_rx_frame(struct sk_buff *skb, struct net_device *dev)
 
 	window = skb->data[20];
 
+	sock_hold(make);
 	skb->sk             = make;
 	skb->destructor     = sock_efree;
 	make->sk_state	    = TCP_ESTABLISHED;
diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c
index 33b388103741..d01410e52097 100644
--- a/net/openvswitch/datapath.c
+++ b/net/openvswitch/datapath.c
@@ -1047,7 +1047,7 @@ error:
 }
 
 /* Factor out action copy to avoid "Wframe-larger-than=1024" warning. */
-static struct sw_flow_actions *get_flow_actions(struct net *net,
+static noinline_for_stack struct sw_flow_actions *get_flow_actions(struct net *net,
 						const struct nlattr *a,
 						const struct sw_flow_key *key,
 						const struct sw_flow_mask *mask,
@@ -1081,12 +1081,13 @@ static struct sw_flow_actions *get_flow_actions(struct net *net,
  * we should not to return match object with dangling reference
  * to mask.
  * */
-static int ovs_nla_init_match_and_action(struct net *net,
-					 struct sw_flow_match *match,
-					 struct sw_flow_key *key,
-					 struct nlattr **a,
-					 struct sw_flow_actions **acts,
-					 bool log)
+static noinline_for_stack int
+ovs_nla_init_match_and_action(struct net *net,
+			      struct sw_flow_match *match,
+			      struct sw_flow_key *key,
+			      struct nlattr **a,
+			      struct sw_flow_actions **acts,
+			      bool log)
 {
 	struct sw_flow_mask mask;
 	int error = 0;
@@ -1958,10 +1959,9 @@ static struct vport *lookup_vport(struct net *net,
 
 }
 
-/* Called with ovs_mutex */
-static void update_headroom(struct datapath *dp)
+static unsigned int ovs_get_max_headroom(struct datapath *dp)
 {
-	unsigned dev_headroom, max_headroom = 0;
+	unsigned int dev_headroom, max_headroom = 0;
 	struct net_device *dev;
 	struct vport *vport;
 	int i;
@@ -1975,10 +1975,19 @@ static void update_headroom(struct datapath *dp)
 		}
 	}
 
-	dp->max_headroom = max_headroom;
+	return max_headroom;
+}
+
+/* Called with ovs_mutex */
+static void ovs_update_headroom(struct datapath *dp, unsigned int new_headroom)
+{
+	struct vport *vport;
+	int i;
+
+	dp->max_headroom = new_headroom;
 	for (i = 0; i < DP_VPORT_HASH_BUCKETS; i++)
 		hlist_for_each_entry_rcu(vport, &dp->ports[i], dp_hash_node)
-			netdev_set_rx_headroom(vport->dev, max_headroom);
+			netdev_set_rx_headroom(vport->dev, new_headroom);
 }
 
 static int ovs_vport_cmd_new(struct sk_buff *skb, struct genl_info *info)
@@ -1989,6 +1998,7 @@ static int ovs_vport_cmd_new(struct sk_buff *skb, struct genl_info *info)
 	struct sk_buff *reply;
 	struct vport *vport;
 	struct datapath *dp;
+	unsigned int new_headroom;
 	u32 port_no;
 	int err;
 
@@ -2050,8 +2060,10 @@ restart:
 				      info->snd_portid, info->snd_seq, 0,
 				      OVS_VPORT_CMD_NEW);
 
-	if (netdev_get_fwd_headroom(vport->dev) > dp->max_headroom)
-		update_headroom(dp);
+	new_headroom = netdev_get_fwd_headroom(vport->dev);
+
+	if (new_headroom > dp->max_headroom)
+		ovs_update_headroom(dp, new_headroom);
 	else
 		netdev_set_rx_headroom(vport->dev, dp->max_headroom);
 
@@ -2122,11 +2134,12 @@ exit_unlock_free:
 
 static int ovs_vport_cmd_del(struct sk_buff *skb, struct genl_info *info)
 {
-	bool must_update_headroom = false;
+	bool update_headroom = false;
 	struct nlattr **a = info->attrs;
 	struct sk_buff *reply;
 	struct datapath *dp;
 	struct vport *vport;
+	unsigned int new_headroom;
 	int err;
 
 	reply = ovs_vport_cmd_alloc_info();
@@ -2152,12 +2165,17 @@ static int ovs_vport_cmd_del(struct sk_buff *skb, struct genl_info *info)
 	/* the vport deletion may trigger dp headroom update */
 	dp = vport->dp;
 	if (netdev_get_fwd_headroom(vport->dev) == dp->max_headroom)
-		must_update_headroom = true;
+		update_headroom = true;
+
 	netdev_reset_rx_headroom(vport->dev);
 	ovs_dp_detach_port(vport);
 
-	if (must_update_headroom)
-		update_headroom(dp);
+	if (update_headroom) {
+		new_headroom = ovs_get_max_headroom(dp);
+
+		if (new_headroom < dp->max_headroom)
+			ovs_update_headroom(dp, new_headroom);
+	}
 	ovs_unlock();
 
 	ovs_notify(&dp_vport_genl_family, reply, info);
diff --git a/net/openvswitch/flow.c b/net/openvswitch/flow.c
index dca3b1e2acf0..bc89e16e0505 100644
--- a/net/openvswitch/flow.c
+++ b/net/openvswitch/flow.c
@@ -59,7 +59,7 @@ u64 ovs_flow_used_time(unsigned long flow_jiffies)
 void ovs_flow_stats_update(struct sw_flow *flow, __be16 tcp_flags,
 			   const struct sk_buff *skb)
 {
-	struct flow_stats *stats;
+	struct sw_flow_stats *stats;
 	unsigned int cpu = smp_processor_id();
 	int len = skb->len + (skb_vlan_tag_present(skb) ? VLAN_HLEN : 0);
 
@@ -87,7 +87,7 @@ void ovs_flow_stats_update(struct sw_flow *flow, __be16 tcp_flags,
 			if (likely(flow->stats_last_writer != -1) &&
 			    likely(!rcu_access_pointer(flow->stats[cpu]))) {
 				/* Try to allocate CPU-specific stats. */
-				struct flow_stats *new_stats;
+				struct sw_flow_stats *new_stats;
 
 				new_stats =
 					kmem_cache_alloc_node(flow_stats_cache,
@@ -134,7 +134,7 @@ void ovs_flow_stats_get(const struct sw_flow *flow,
 
 	/* We open code this to make sure cpu 0 is always considered */
 	for (cpu = 0; cpu < nr_cpu_ids; cpu = cpumask_next(cpu, &flow->cpu_used_mask)) {
-		struct flow_stats *stats = rcu_dereference_ovsl(flow->stats[cpu]);
+		struct sw_flow_stats *stats = rcu_dereference_ovsl(flow->stats[cpu]);
 
 		if (stats) {
 			/* Local CPU may write on non-local stats, so we must
@@ -158,7 +158,7 @@ void ovs_flow_stats_clear(struct sw_flow *flow)
 
 	/* We open code this to make sure cpu 0 is always considered */
 	for (cpu = 0; cpu < nr_cpu_ids; cpu = cpumask_next(cpu, &flow->cpu_used_mask)) {
-		struct flow_stats *stats = ovsl_dereference(flow->stats[cpu]);
+		struct sw_flow_stats *stats = ovsl_dereference(flow->stats[cpu]);
 
 		if (stats) {
 			spin_lock_bh(&stats->lock);
diff --git a/net/openvswitch/flow.h b/net/openvswitch/flow.h
index 3e2cc2202d66..a5506e2d4b7a 100644
--- a/net/openvswitch/flow.h
+++ b/net/openvswitch/flow.h
@@ -194,7 +194,7 @@ struct sw_flow_actions {
 	struct nlattr actions[];
 };
 
-struct flow_stats {
+struct sw_flow_stats {
 	u64 packet_count;		/* Number of packets matched. */
 	u64 byte_count;			/* Number of bytes matched. */
 	unsigned long used;		/* Last used time (in jiffies). */
@@ -216,7 +216,7 @@ struct sw_flow {
 	struct cpumask cpu_used_mask;
 	struct sw_flow_mask *mask;
 	struct sw_flow_actions __rcu *sf_acts;
-	struct flow_stats __rcu *stats[]; /* One for each CPU.  First one
+	struct sw_flow_stats __rcu *stats[]; /* One for each CPU.  First one
 					   * is allocated at flow creation time,
 					   * the rest are allocated on demand
 					   * while holding the 'stats[0].lock'.
diff --git a/net/openvswitch/flow_table.c b/net/openvswitch/flow_table.c
index 988fd8a94e43..cf3582c5ed70 100644
--- a/net/openvswitch/flow_table.c
+++ b/net/openvswitch/flow_table.c
@@ -66,7 +66,7 @@ void ovs_flow_mask_key(struct sw_flow_key *dst, const struct sw_flow_key *src,
 struct sw_flow *ovs_flow_alloc(void)
 {
 	struct sw_flow *flow;
-	struct flow_stats *stats;
+	struct sw_flow_stats *stats;
 
 	flow = kmem_cache_zalloc(flow_cache, GFP_KERNEL);
 	if (!flow)
@@ -110,7 +110,7 @@ static void flow_free(struct sw_flow *flow)
 	for (cpu = 0; cpu < nr_cpu_ids; cpu = cpumask_next(cpu, &flow->cpu_used_mask))
 		if (flow->stats[cpu])
 			kmem_cache_free(flow_stats_cache,
-					(struct flow_stats __force *)flow->stats[cpu]);
+					(struct sw_flow_stats __force *)flow->stats[cpu]);
 	kmem_cache_free(flow_cache, flow);
 }
 
@@ -712,13 +712,13 @@ int ovs_flow_init(void)
 
 	flow_cache = kmem_cache_create("sw_flow", sizeof(struct sw_flow)
 				       + (nr_cpu_ids
-					  * sizeof(struct flow_stats *)),
+					  * sizeof(struct sw_flow_stats *)),
 				       0, 0, NULL);
 	if (flow_cache == NULL)
 		return -ENOMEM;
 
 	flow_stats_cache
-		= kmem_cache_create("sw_flow_stats", sizeof(struct flow_stats),
+		= kmem_cache_create("sw_flow_stats", sizeof(struct sw_flow_stats),
 				    0, SLAB_HWCACHE_ALIGN, NULL);
 	if (flow_stats_cache == NULL) {
 		kmem_cache_destroy(flow_cache);
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 8d54f3047768..e2742b006d25 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -2618,6 +2618,13 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg)
 
 	mutex_lock(&po->pg_vec_lock);
 
+	/* packet_sendmsg() check on tx_ring.pg_vec was lockless,
+	 * we need to confirm it under protection of pg_vec_lock.
+	 */
+	if (unlikely(!po->tx_ring.pg_vec)) {
+		err = -EBUSY;
+		goto out;
+	}
 	if (likely(saddr == NULL)) {
 		dev	= packet_cached_dev_get(po);
 		proto	= po->num;
diff --git a/net/rds/connection.c b/net/rds/connection.c
index 7ea134f9a825..ed7f2133acc2 100644
--- a/net/rds/connection.c
+++ b/net/rds/connection.c
@@ -736,6 +736,7 @@ static int rds_conn_info_visitor(struct rds_conn_path *cp, void *buffer)
 	cinfo->next_rx_seq = cp->cp_next_rx_seq;
 	cinfo->laddr = conn->c_laddr.s6_addr32[3];
 	cinfo->faddr = conn->c_faddr.s6_addr32[3];
+	cinfo->tos = conn->c_tos;
 	strncpy(cinfo->transport, conn->c_trans->t_name,
 		sizeof(cinfo->transport));
 	cinfo->flags = 0;
diff --git a/net/rds/ib.h b/net/rds/ib.h
index 67a715b076ca..303c6ee8bdb7 100644
--- a/net/rds/ib.h
+++ b/net/rds/ib.h
@@ -15,8 +15,7 @@
 
 #define RDS_IB_DEFAULT_RECV_WR		1024
 #define RDS_IB_DEFAULT_SEND_WR		256
-#define RDS_IB_DEFAULT_FR_WR		256
-#define RDS_IB_DEFAULT_FR_INV_WR	256
+#define RDS_IB_DEFAULT_FR_WR		512
 
 #define RDS_IB_DEFAULT_RETRY_COUNT	1
 
@@ -157,7 +156,7 @@ struct rds_ib_connection {
 
 	/* To control the number of wrs from fastreg */
 	atomic_t		i_fastreg_wrs;
-	atomic_t		i_fastunreg_wrs;
+	atomic_t		i_fastreg_inuse_count;
 
 	/* interrupt handling */
 	struct tasklet_struct	i_send_tasklet;
diff --git a/net/rds/ib_cm.c b/net/rds/ib_cm.c
index 66c6eb56072b..fddaa09f7b0d 100644
--- a/net/rds/ib_cm.c
+++ b/net/rds/ib_cm.c
@@ -40,6 +40,7 @@
 #include "rds_single_path.h"
 #include "rds.h"
 #include "ib.h"
+#include "ib_mr.h"
 
 /*
  * Set the selected protocol version
@@ -460,10 +461,7 @@ static int rds_ib_setup_qp(struct rds_connection *conn)
 	 * completion queue and send queue. This extra space is used for FRMR
 	 * registration and invalidation work requests
 	 */
-	fr_queue_space = rds_ibdev->use_fastreg ?
-			 (RDS_IB_DEFAULT_FR_WR + 1) +
-			 (RDS_IB_DEFAULT_FR_INV_WR + 1)
-			 : 0;
+	fr_queue_space = (rds_ibdev->use_fastreg ? RDS_IB_DEFAULT_FR_WR : 0);
 
 	/* add the conn now so that connection establishment has the dev */
 	rds_ib_add_conn(rds_ibdev, conn);
@@ -529,8 +527,6 @@ static int rds_ib_setup_qp(struct rds_connection *conn)
 	attr.qp_type = IB_QPT_RC;
 	attr.send_cq = ic->i_send_cq;
 	attr.recv_cq = ic->i_recv_cq;
-	atomic_set(&ic->i_fastreg_wrs, RDS_IB_DEFAULT_FR_WR);
-	atomic_set(&ic->i_fastunreg_wrs, RDS_IB_DEFAULT_FR_INV_WR);
 
 	/*
 	 * XXX this can fail if max_*_wr is too large?  Are we supposed
@@ -611,11 +607,11 @@ send_hdrs_dma_out:
 qp_out:
 	rdma_destroy_qp(ic->i_cm_id);
 recv_cq_out:
-	if (!ib_destroy_cq(ic->i_recv_cq))
-		ic->i_recv_cq = NULL;
+	ib_destroy_cq(ic->i_recv_cq);
+	ic->i_recv_cq = NULL;
 send_cq_out:
-	if (!ib_destroy_cq(ic->i_send_cq))
-		ic->i_send_cq = NULL;
+	ib_destroy_cq(ic->i_send_cq);
+	ic->i_send_cq = NULL;
 rds_ibdev_out:
 	rds_ib_remove_conn(rds_ibdev, conn);
 out:
@@ -997,6 +993,11 @@ void rds_ib_conn_path_shutdown(struct rds_conn_path *cp)
 				ic->i_cm_id, err);
 		}
 
+		/* kick off "flush_worker" for all pools in order to reap
+		 * all FRMR registrations that are still marked "FRMR_IS_INUSE"
+		 */
+		rds_ib_flush_mrs();
+
 		/*
 		 * We want to wait for tx and rx completion to finish
 		 * before we tear down the connection, but we have to be
@@ -1009,8 +1010,8 @@ void rds_ib_conn_path_shutdown(struct rds_conn_path *cp)
 		wait_event(rds_ib_ring_empty_wait,
 			   rds_ib_ring_empty(&ic->i_recv_ring) &&
 			   (atomic_read(&ic->i_signaled_sends) == 0) &&
-			   (atomic_read(&ic->i_fastreg_wrs) == RDS_IB_DEFAULT_FR_WR) &&
-			   (atomic_read(&ic->i_fastunreg_wrs) == RDS_IB_DEFAULT_FR_INV_WR));
+			   (atomic_read(&ic->i_fastreg_inuse_count) == 0) &&
+			   (atomic_read(&ic->i_fastreg_wrs) == RDS_IB_DEFAULT_FR_WR));
 		tasklet_kill(&ic->i_send_tasklet);
 		tasklet_kill(&ic->i_recv_tasklet);
 
@@ -1137,6 +1138,7 @@ int rds_ib_conn_alloc(struct rds_connection *conn, gfp_t gfp)
 	spin_lock_init(&ic->i_ack_lock);
 #endif
 	atomic_set(&ic->i_signaled_sends, 0);
+	atomic_set(&ic->i_fastreg_wrs, RDS_IB_DEFAULT_FR_WR);
 
 	/*
 	 * rds_ib_conn_shutdown() waits for these to be emptied so they
diff --git a/net/rds/ib_frmr.c b/net/rds/ib_frmr.c
index 688dcd68d4ea..06ecf9d2d4bf 100644
--- a/net/rds/ib_frmr.c
+++ b/net/rds/ib_frmr.c
@@ -32,6 +32,24 @@
 
 #include "ib_mr.h"
 
+static inline void
+rds_transition_frwr_state(struct rds_ib_mr *ibmr,
+			  enum rds_ib_fr_state old_state,
+			  enum rds_ib_fr_state new_state)
+{
+	if (cmpxchg(&ibmr->u.frmr.fr_state,
+		    old_state, new_state) == old_state &&
+	    old_state == FRMR_IS_INUSE) {
+		/* enforce order of ibmr->u.frmr.fr_state update
+		 * before decrementing i_fastreg_inuse_count
+		 */
+		smp_mb__before_atomic();
+		atomic_dec(&ibmr->ic->i_fastreg_inuse_count);
+		if (waitqueue_active(&rds_ib_ring_empty_wait))
+			wake_up(&rds_ib_ring_empty_wait);
+	}
+}
+
 static struct rds_ib_mr *rds_ib_alloc_frmr(struct rds_ib_device *rds_ibdev,
 					   int npages)
 {
@@ -75,6 +93,8 @@ static struct rds_ib_mr *rds_ib_alloc_frmr(struct rds_ib_device *rds_ibdev,
 		pool->max_items_soft = pool->max_items;
 
 	frmr->fr_state = FRMR_IS_FREE;
+	init_waitqueue_head(&frmr->fr_inv_done);
+	init_waitqueue_head(&frmr->fr_reg_done);
 	return ibmr;
 
 out_no_cigar:
@@ -116,13 +136,19 @@ static int rds_ib_post_reg_frmr(struct rds_ib_mr *ibmr)
 	if (unlikely(ret != ibmr->sg_len))
 		return ret < 0 ? ret : -EINVAL;
 
+	if (cmpxchg(&frmr->fr_state,
+		    FRMR_IS_FREE, FRMR_IS_INUSE) != FRMR_IS_FREE)
+		return -EBUSY;
+
+	atomic_inc(&ibmr->ic->i_fastreg_inuse_count);
+
 	/* Perform a WR for the fast_reg_mr. Each individual page
 	 * in the sg list is added to the fast reg page list and placed
 	 * inside the fast_reg_mr WR.  The key used is a rolling 8bit
 	 * counter, which should guarantee uniqueness.
 	 */
 	ib_update_fast_reg_key(frmr->mr, ibmr->remap_count++);
-	frmr->fr_state = FRMR_IS_INUSE;
+	frmr->fr_reg = true;
 
 	memset(&reg_wr, 0, sizeof(reg_wr));
 	reg_wr.wr.wr_id = (unsigned long)(void *)ibmr;
@@ -138,12 +164,23 @@ static int rds_ib_post_reg_frmr(struct rds_ib_mr *ibmr)
 	ret = ib_post_send(ibmr->ic->i_cm_id->qp, &reg_wr.wr, NULL);
 	if (unlikely(ret)) {
 		/* Failure here can be because of -ENOMEM as well */
-		frmr->fr_state = FRMR_IS_STALE;
+		rds_transition_frwr_state(ibmr, FRMR_IS_INUSE, FRMR_IS_STALE);
+
 		atomic_inc(&ibmr->ic->i_fastreg_wrs);
 		if (printk_ratelimit())
 			pr_warn("RDS/IB: %s returned error(%d)\n",
 				__func__, ret);
+		goto out;
 	}
+
+	/* Wait for the registration to complete in order to prevent an invalid
+	 * access error resulting from a race between the memory region already
+	 * being accessed while registration is still pending.
+	 */
+	wait_event(frmr->fr_reg_done, !frmr->fr_reg);
+
+out:
+
 	return ret;
 }
 
@@ -239,8 +276,8 @@ static int rds_ib_post_inv(struct rds_ib_mr *ibmr)
 	if (frmr->fr_state != FRMR_IS_INUSE)
 		goto out;
 
-	while (atomic_dec_return(&ibmr->ic->i_fastunreg_wrs) <= 0) {
-		atomic_inc(&ibmr->ic->i_fastunreg_wrs);
+	while (atomic_dec_return(&ibmr->ic->i_fastreg_wrs) <= 0) {
+		atomic_inc(&ibmr->ic->i_fastreg_wrs);
 		cpu_relax();
 	}
 
@@ -255,12 +292,29 @@ static int rds_ib_post_inv(struct rds_ib_mr *ibmr)
 
 	ret = ib_post_send(i_cm_id->qp, s_wr, NULL);
 	if (unlikely(ret)) {
-		frmr->fr_state = FRMR_IS_STALE;
+		rds_transition_frwr_state(ibmr, FRMR_IS_INUSE, FRMR_IS_STALE);
 		frmr->fr_inv = false;
-		atomic_inc(&ibmr->ic->i_fastunreg_wrs);
+		/* enforce order of frmr->fr_inv update
+		 * before incrementing i_fastreg_wrs
+		 */
+		smp_mb__before_atomic();
+		atomic_inc(&ibmr->ic->i_fastreg_wrs);
 		pr_err("RDS/IB: %s returned error(%d)\n", __func__, ret);
 		goto out;
 	}
+
+	/* Wait for the FRMR_IS_FREE (or FRMR_IS_STALE) transition in order to
+	 * 1) avoid a silly bouncing between "clean_list" and "drop_list"
+	 *    triggered by function "rds_ib_reg_frmr" as it is releases frmr
+	 *    regions whose state is not "FRMR_IS_FREE" right away.
+	 * 2) prevents an invalid access error in a race
+	 *    from a pending "IB_WR_LOCAL_INV" operation
+	 *    with a teardown ("dma_unmap_sg", "put_page")
+	 *    and de-registration ("ib_dereg_mr") of the corresponding
+	 *    memory region.
+	 */
+	wait_event(frmr->fr_inv_done, frmr->fr_state != FRMR_IS_INUSE);
+
 out:
 	return ret;
 }
@@ -271,7 +325,7 @@ void rds_ib_mr_cqe_handler(struct rds_ib_connection *ic, struct ib_wc *wc)
 	struct rds_ib_frmr *frmr = &ibmr->u.frmr;
 
 	if (wc->status != IB_WC_SUCCESS) {
-		frmr->fr_state = FRMR_IS_STALE;
+		rds_transition_frwr_state(ibmr, FRMR_IS_INUSE, FRMR_IS_STALE);
 		if (rds_conn_up(ic->conn))
 			rds_ib_conn_error(ic->conn,
 					  "frmr completion <%pI4,%pI4> status %u(%s), vendor_err 0x%x, disconnecting and reconnecting\n",
@@ -283,12 +337,21 @@ void rds_ib_mr_cqe_handler(struct rds_ib_connection *ic, struct ib_wc *wc)
 	}
 
 	if (frmr->fr_inv) {
-		frmr->fr_state = FRMR_IS_FREE;
+		rds_transition_frwr_state(ibmr, FRMR_IS_INUSE, FRMR_IS_FREE);
 		frmr->fr_inv = false;
-		atomic_inc(&ic->i_fastreg_wrs);
-	} else {
-		atomic_inc(&ic->i_fastunreg_wrs);
+		wake_up(&frmr->fr_inv_done);
 	}
+
+	if (frmr->fr_reg) {
+		frmr->fr_reg = false;
+		wake_up(&frmr->fr_reg_done);
+	}
+
+	/* enforce order of frmr->{fr_reg,fr_inv} update
+	 * before incrementing i_fastreg_wrs
+	 */
+	smp_mb__before_atomic();
+	atomic_inc(&ic->i_fastreg_wrs);
 }
 
 void rds_ib_unreg_frmr(struct list_head *list, unsigned int *nfreed,
@@ -296,14 +359,18 @@ void rds_ib_unreg_frmr(struct list_head *list, unsigned int *nfreed,
 {
 	struct rds_ib_mr *ibmr, *next;
 	struct rds_ib_frmr *frmr;
-	int ret = 0;
+	int ret = 0, ret2;
 	unsigned int freed = *nfreed;
 
 	/* String all ib_mr's onto one list and hand them to ib_unmap_fmr */
 	list_for_each_entry(ibmr, list, unmap_list) {
-		if (ibmr->sg_dma_len)
-			ret |= rds_ib_post_inv(ibmr);
+		if (ibmr->sg_dma_len) {
+			ret2 = rds_ib_post_inv(ibmr);
+			if (ret2 && !ret)
+				ret = ret2;
+		}
 	}
+
 	if (ret)
 		pr_warn("RDS/IB: %s failed (err=%d)\n", __func__, ret);
 
diff --git a/net/rds/ib_mr.h b/net/rds/ib_mr.h
index 5da12c248431..9045a8c0edff 100644
--- a/net/rds/ib_mr.h
+++ b/net/rds/ib_mr.h
@@ -57,6 +57,9 @@ struct rds_ib_frmr {
 	struct ib_mr		*mr;
 	enum rds_ib_fr_state	fr_state;
 	bool			fr_inv;
+	wait_queue_head_t	fr_inv_done;
+	bool			fr_reg;
+	wait_queue_head_t	fr_reg_done;
 	struct ib_send_wr	fr_wr;
 	unsigned int		dma_npages;
 	unsigned int		sg_byte_len;
@@ -97,6 +100,7 @@ struct rds_ib_mr_pool {
 	struct llist_head	free_list;	/* unused MRs */
 	struct llist_head	clean_list;	/* unused & unmapped MRs */
 	wait_queue_head_t	flush_wait;
+	spinlock_t		clean_lock;	/* "clean_list" concurrency */
 
 	atomic_t		free_pinned;	/* memory pinned by free MRs */
 	unsigned long		max_items;
diff --git a/net/rds/ib_rdma.c b/net/rds/ib_rdma.c
index 0b347f46b2f4..c8c1e3ae8d84 100644
--- a/net/rds/ib_rdma.c
+++ b/net/rds/ib_rdma.c
@@ -40,9 +40,6 @@
 
 struct workqueue_struct *rds_ib_mr_wq;
 
-static DEFINE_PER_CPU(unsigned long, clean_list_grace);
-#define CLEAN_LIST_BUSY_BIT 0
-
 static struct rds_ib_device *rds_ib_get_device(__be32 ipaddr)
 {
 	struct rds_ib_device *rds_ibdev;
@@ -195,12 +192,11 @@ struct rds_ib_mr *rds_ib_reuse_mr(struct rds_ib_mr_pool *pool)
 {
 	struct rds_ib_mr *ibmr = NULL;
 	struct llist_node *ret;
-	unsigned long *flag;
+	unsigned long flags;
 
-	preempt_disable();
-	flag = this_cpu_ptr(&clean_list_grace);
-	set_bit(CLEAN_LIST_BUSY_BIT, flag);
+	spin_lock_irqsave(&pool->clean_lock, flags);
 	ret = llist_del_first(&pool->clean_list);
+	spin_unlock_irqrestore(&pool->clean_lock, flags);
 	if (ret) {
 		ibmr = llist_entry(ret, struct rds_ib_mr, llnode);
 		if (pool->pool_type == RDS_IB_MR_8K_POOL)
@@ -209,23 +205,9 @@ struct rds_ib_mr *rds_ib_reuse_mr(struct rds_ib_mr_pool *pool)
 			rds_ib_stats_inc(s_ib_rdma_mr_1m_reused);
 	}
 
-	clear_bit(CLEAN_LIST_BUSY_BIT, flag);
-	preempt_enable();
 	return ibmr;
 }
 
-static inline void wait_clean_list_grace(void)
-{
-	int cpu;
-	unsigned long *flag;
-
-	for_each_online_cpu(cpu) {
-		flag = &per_cpu(clean_list_grace, cpu);
-		while (test_bit(CLEAN_LIST_BUSY_BIT, flag))
-			cpu_relax();
-	}
-}
-
 void rds_ib_sync_mr(void *trans_private, int direction)
 {
 	struct rds_ib_mr *ibmr = trans_private;
@@ -324,8 +306,7 @@ static unsigned int llist_append_to_list(struct llist_head *llist,
  * of clusters.  Each cluster has linked llist nodes of
  * MR_CLUSTER_SIZE mrs that are ready for reuse.
  */
-static void list_to_llist_nodes(struct rds_ib_mr_pool *pool,
-				struct list_head *list,
+static void list_to_llist_nodes(struct list_head *list,
 				struct llist_node **nodes_head,
 				struct llist_node **nodes_tail)
 {
@@ -402,8 +383,13 @@ int rds_ib_flush_mr_pool(struct rds_ib_mr_pool *pool,
 	 */
 	dirty_to_clean = llist_append_to_list(&pool->drop_list, &unmap_list);
 	dirty_to_clean += llist_append_to_list(&pool->free_list, &unmap_list);
-	if (free_all)
+	if (free_all) {
+		unsigned long flags;
+
+		spin_lock_irqsave(&pool->clean_lock, flags);
 		llist_append_to_list(&pool->clean_list, &unmap_list);
+		spin_unlock_irqrestore(&pool->clean_lock, flags);
+	}
 
 	free_goal = rds_ib_flush_goal(pool, free_all);
 
@@ -416,27 +402,20 @@ int rds_ib_flush_mr_pool(struct rds_ib_mr_pool *pool,
 		rds_ib_unreg_fmr(&unmap_list, &nfreed, &unpinned, free_goal);
 
 	if (!list_empty(&unmap_list)) {
-		/* we have to make sure that none of the things we're about
-		 * to put on the clean list would race with other cpus trying
-		 * to pull items off.  The llist would explode if we managed to
-		 * remove something from the clean list and then add it back again
-		 * while another CPU was spinning on that same item in llist_del_first.
-		 *
-		 * This is pretty unlikely, but just in case  wait for an llist grace period
-		 * here before adding anything back into the clean list.
-		 */
-		wait_clean_list_grace();
-
-		list_to_llist_nodes(pool, &unmap_list, &clean_nodes, &clean_tail);
+		unsigned long flags;
+
+		list_to_llist_nodes(&unmap_list, &clean_nodes, &clean_tail);
 		if (ibmr_ret) {
 			*ibmr_ret = llist_entry(clean_nodes, struct rds_ib_mr, llnode);
 			clean_nodes = clean_nodes->next;
 		}
 		/* more than one entry in llist nodes */
-		if (clean_nodes)
+		if (clean_nodes) {
+			spin_lock_irqsave(&pool->clean_lock, flags);
 			llist_add_batch(clean_nodes, clean_tail,
 					&pool->clean_list);
-
+			spin_unlock_irqrestore(&pool->clean_lock, flags);
+		}
 	}
 
 	atomic_sub(unpinned, &pool->free_pinned);
@@ -471,7 +450,7 @@ struct rds_ib_mr *rds_ib_try_reuse_ibmr(struct rds_ib_mr_pool *pool)
 				rds_ib_stats_inc(s_ib_rdma_mr_8k_pool_depleted);
 			else
 				rds_ib_stats_inc(s_ib_rdma_mr_1m_pool_depleted);
-			return ERR_PTR(-EAGAIN);
+			break;
 		}
 
 		/* We do have some empty MRs. Flush them out. */
@@ -485,7 +464,7 @@ struct rds_ib_mr *rds_ib_try_reuse_ibmr(struct rds_ib_mr_pool *pool)
 			return ibmr;
 	}
 
-	return ibmr;
+	return NULL;
 }
 
 static void rds_ib_mr_pool_flush_worker(struct work_struct *work)
@@ -610,6 +589,7 @@ struct rds_ib_mr_pool *rds_ib_create_mr_pool(struct rds_ib_device *rds_ibdev,
 	init_llist_head(&pool->free_list);
 	init_llist_head(&pool->drop_list);
 	init_llist_head(&pool->clean_list);
+	spin_lock_init(&pool->clean_lock);
 	mutex_init(&pool->flush_lock);
 	init_waitqueue_head(&pool->flush_wait);
 	INIT_DELAYED_WORK(&pool->flush_worker, rds_ib_mr_pool_flush_worker);
diff --git a/net/rds/ib_send.c b/net/rds/ib_send.c
index 18f2341202f8..dfe6237dafe2 100644
--- a/net/rds/ib_send.c
+++ b/net/rds/ib_send.c
@@ -69,6 +69,16 @@ static void rds_ib_send_complete(struct rds_message *rm,
 	complete(rm, notify_status);
 }
 
+static void rds_ib_send_unmap_data(struct rds_ib_connection *ic,
+				   struct rm_data_op *op,
+				   int wc_status)
+{
+	if (op->op_nents)
+		ib_dma_unmap_sg(ic->i_cm_id->device,
+				op->op_sg, op->op_nents,
+				DMA_TO_DEVICE);
+}
+
 static void rds_ib_send_unmap_rdma(struct rds_ib_connection *ic,
 				   struct rm_rdma_op *op,
 				   int wc_status)
@@ -129,21 +139,6 @@ static void rds_ib_send_unmap_atomic(struct rds_ib_connection *ic,
 		rds_ib_stats_inc(s_ib_atomic_fadd);
 }
 
-static void rds_ib_send_unmap_data(struct rds_ib_connection *ic,
-				   struct rm_data_op *op,
-				   int wc_status)
-{
-	struct rds_message *rm = container_of(op, struct rds_message, data);
-
-	if (op->op_nents)
-		ib_dma_unmap_sg(ic->i_cm_id->device,
-				op->op_sg, op->op_nents,
-				DMA_TO_DEVICE);
-
-	if (rm->rdma.op_active && rm->data.op_notify)
-		rds_ib_send_unmap_rdma(ic, &rm->rdma, wc_status);
-}
-
 /*
  * Unmap the resources associated with a struct send_work.
  *
@@ -902,7 +897,9 @@ int rds_ib_xmit_rdma(struct rds_connection *conn, struct rm_rdma_op *op)
 		send->s_queued = jiffies;
 		send->s_op = NULL;
 
-		nr_sig += rds_ib_set_wr_signal_state(ic, send, op->op_notify);
+		if (!op->op_notify)
+			nr_sig += rds_ib_set_wr_signal_state(ic, send,
+							     op->op_notify);
 
 		send->s_wr.opcode = op->op_write ? IB_WR_RDMA_WRITE : IB_WR_RDMA_READ;
 		send->s_rdma_wr.remote_addr = remote_addr;
diff --git a/net/rds/rdma.c b/net/rds/rdma.c
index b340ed4fc43a..916f5ec373d8 100644
--- a/net/rds/rdma.c
+++ b/net/rds/rdma.c
@@ -641,16 +641,6 @@ int rds_cmsg_rdma_args(struct rds_sock *rs, struct rds_message *rm,
 		}
 		op->op_notifier->n_user_token = args->user_token;
 		op->op_notifier->n_status = RDS_RDMA_SUCCESS;
-
-		/* Enable rmda notification on data operation for composite
-		 * rds messages and make sure notification is enabled only
-		 * for the data operation which follows it so that application
-		 * gets notified only after full message gets delivered.
-		 */
-		if (rm->data.op_sg) {
-			rm->rdma.op_notify = 0;
-			rm->data.op_notify = !!(args->flags & RDS_RDMA_NOTIFY_ME);
-		}
 	}
 
 	/* The cookie contains the R_Key of the remote memory region, and
diff --git a/net/rds/rdma_transport.c b/net/rds/rdma_transport.c
index 46bce8389066..9986d6065c4d 100644
--- a/net/rds/rdma_transport.c
+++ b/net/rds/rdma_transport.c
@@ -105,24 +105,28 @@ static int rds_rdma_cm_event_handler_cmn(struct rdma_cm_id *cm_id,
 		break;
 
 	case RDMA_CM_EVENT_ESTABLISHED:
-		trans->cm_connect_complete(conn, event);
+		if (conn)
+			trans->cm_connect_complete(conn, event);
 		break;
 
 	case RDMA_CM_EVENT_REJECTED:
 		if (!conn)
 			break;
 		err = (int *)rdma_consumer_reject_data(cm_id, event, &len);
-		if (!err || (err && ((*err) == RDS_RDMA_REJ_INCOMPAT))) {
+		if (!err ||
+		    (err && len >= sizeof(*err) &&
+		     ((*err) <= RDS_RDMA_REJ_INCOMPAT))) {
 			pr_warn("RDS/RDMA: conn <%pI6c, %pI6c> rejected, dropping connection\n",
 				&conn->c_laddr, &conn->c_faddr);
-			conn->c_proposed_version = RDS_PROTOCOL_COMPAT_VERSION;
-			conn->c_tos = 0;
+
+			if (!conn->c_tos)
+				conn->c_proposed_version = RDS_PROTOCOL_COMPAT_VERSION;
+
 			rds_conn_drop(conn);
 		}
 		rdsdebug("Connection rejected: %s\n",
 			 rdma_reject_msg(cm_id, event->status));
 		break;
-		/* FALLTHROUGH */
 	case RDMA_CM_EVENT_ADDR_ERROR:
 	case RDMA_CM_EVENT_ROUTE_ERROR:
 	case RDMA_CM_EVENT_CONNECT_ERROR:
@@ -134,6 +138,8 @@ static int rds_rdma_cm_event_handler_cmn(struct rdma_cm_id *cm_id,
 		break;
 
 	case RDMA_CM_EVENT_DISCONNECTED:
+		if (!conn)
+			break;
 		rdsdebug("DISCONNECT event - dropping connection "
 			 "%pI6c->%pI6c\n", &conn->c_laddr,
 			 &conn->c_faddr);
diff --git a/net/rds/rds.h b/net/rds/rds.h
index 0d8f67cadd74..f0066d168499 100644
--- a/net/rds/rds.h
+++ b/net/rds/rds.h
@@ -476,7 +476,6 @@ struct rds_message {
 		} rdma;
 		struct rm_data_op {
 			unsigned int		op_active:1;
-			unsigned int		op_notify:1;
 			unsigned int		op_nents;
 			unsigned int		op_count;
 			unsigned int		op_dmasg;
diff --git a/net/rds/send.c b/net/rds/send.c
index 166dd578c1cc..031b1e97a466 100644
--- a/net/rds/send.c
+++ b/net/rds/send.c
@@ -491,14 +491,12 @@ void rds_rdma_send_complete(struct rds_message *rm, int status)
 	struct rm_rdma_op *ro;
 	struct rds_notifier *notifier;
 	unsigned long flags;
-	unsigned int notify = 0;
 
 	spin_lock_irqsave(&rm->m_rs_lock, flags);
 
-	notify =  rm->rdma.op_notify | rm->data.op_notify;
 	ro = &rm->rdma;
 	if (test_bit(RDS_MSG_ON_SOCK, &rm->m_flags) &&
-	    ro->op_active && notify && ro->op_notifier) {
+	    ro->op_active && ro->op_notify && ro->op_notifier) {
 		notifier = ro->op_notifier;
 		rs = rm->m_rs;
 		sock_hold(rds_rs_to_sk(rs));
diff --git a/net/rxrpc/af_rxrpc.c b/net/rxrpc/af_rxrpc.c
index d09eaf153544..0dbbfd1b6487 100644
--- a/net/rxrpc/af_rxrpc.c
+++ b/net/rxrpc/af_rxrpc.c
@@ -193,7 +193,7 @@ static int rxrpc_bind(struct socket *sock, struct sockaddr *saddr, int len)
 
 service_in_use:
 	write_unlock(&local->services_lock);
-	rxrpc_put_local(local);
+	rxrpc_unuse_local(local);
 	ret = -EADDRINUSE;
 error_unlock:
 	release_sock(&rx->sk);
@@ -402,7 +402,7 @@ EXPORT_SYMBOL(rxrpc_kernel_check_life);
  */
 void rxrpc_kernel_probe_life(struct socket *sock, struct rxrpc_call *call)
 {
-	rxrpc_propose_ACK(call, RXRPC_ACK_PING, 0, 0, true, false,
+	rxrpc_propose_ACK(call, RXRPC_ACK_PING, 0, true, false,
 			  rxrpc_propose_ack_ping_for_check_life);
 	rxrpc_send_ack_packet(call, true, NULL);
 }
@@ -901,7 +901,7 @@ static int rxrpc_release_sock(struct sock *sk)
 	rxrpc_queue_work(&rxnet->service_conn_reaper);
 	rxrpc_queue_work(&rxnet->client_conn_reaper);
 
-	rxrpc_put_local(rx->local);
+	rxrpc_unuse_local(rx->local);
 	rx->local = NULL;
 	key_put(rx->key);
 	rx->key = NULL;
diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h
index 80335b4ee4fd..145335611af6 100644
--- a/net/rxrpc/ar-internal.h
+++ b/net/rxrpc/ar-internal.h
@@ -254,7 +254,8 @@ struct rxrpc_security {
  */
 struct rxrpc_local {
 	struct rcu_head		rcu;
-	atomic_t		usage;
+	atomic_t		active_users;	/* Number of users of the local endpoint */
+	atomic_t		usage;		/* Number of references to the structure */
 	struct rxrpc_net	*rxnet;		/* The network ns in which this resides */
 	struct list_head	link;
 	struct socket		*socket;	/* my UDP socket */
@@ -649,7 +650,6 @@ struct rxrpc_call {
 
 	/* receive-phase ACK management */
 	u8			ackr_reason;	/* reason to ACK */
-	u16			ackr_skew;	/* skew on packet being ACK'd */
 	rxrpc_serial_t		ackr_serial;	/* serial of packet being ACK'd */
 	rxrpc_serial_t		ackr_first_seq;	/* first sequence number received */
 	rxrpc_seq_t		ackr_prev_seq;	/* previous sequence number received */
@@ -743,7 +743,7 @@ int rxrpc_reject_call(struct rxrpc_sock *);
 /*
  * call_event.c
  */
-void rxrpc_propose_ACK(struct rxrpc_call *, u8, u16, u32, bool, bool,
+void rxrpc_propose_ACK(struct rxrpc_call *, u8, u32, bool, bool,
 		       enum rxrpc_propose_ack_trace);
 void rxrpc_process_call(struct work_struct *);
 
@@ -1002,6 +1002,8 @@ struct rxrpc_local *rxrpc_lookup_local(struct net *, const struct sockaddr_rxrpc
 struct rxrpc_local *rxrpc_get_local(struct rxrpc_local *);
 struct rxrpc_local *rxrpc_get_local_maybe(struct rxrpc_local *);
 void rxrpc_put_local(struct rxrpc_local *);
+struct rxrpc_local *rxrpc_use_local(struct rxrpc_local *);
+void rxrpc_unuse_local(struct rxrpc_local *);
 void rxrpc_queue_local(struct rxrpc_local *);
 void rxrpc_destroy_all_locals(struct rxrpc_net *);
 
@@ -1061,6 +1063,7 @@ void rxrpc_destroy_all_peers(struct rxrpc_net *);
 struct rxrpc_peer *rxrpc_get_peer(struct rxrpc_peer *);
 struct rxrpc_peer *rxrpc_get_peer_maybe(struct rxrpc_peer *);
 void rxrpc_put_peer(struct rxrpc_peer *);
+void rxrpc_put_peer_locked(struct rxrpc_peer *);
 
 /*
  * proc.c
diff --git a/net/rxrpc/call_event.c b/net/rxrpc/call_event.c
index bc2adeb3acb9..c767679bfa5d 100644
--- a/net/rxrpc/call_event.c
+++ b/net/rxrpc/call_event.c
@@ -43,8 +43,7 @@ static void rxrpc_propose_ping(struct rxrpc_call *call,
  * propose an ACK be sent
  */
 static void __rxrpc_propose_ACK(struct rxrpc_call *call, u8 ack_reason,
-				u16 skew, u32 serial, bool immediate,
-				bool background,
+				u32 serial, bool immediate, bool background,
 				enum rxrpc_propose_ack_trace why)
 {
 	enum rxrpc_propose_ack_outcome outcome = rxrpc_propose_ack_use;
@@ -69,14 +68,12 @@ static void __rxrpc_propose_ACK(struct rxrpc_call *call, u8 ack_reason,
 		if (RXRPC_ACK_UPDATEABLE & (1 << ack_reason)) {
 			outcome = rxrpc_propose_ack_update;
 			call->ackr_serial = serial;
-			call->ackr_skew = skew;
 		}
 		if (!immediate)
 			goto trace;
 	} else if (prior > rxrpc_ack_priority[call->ackr_reason]) {
 		call->ackr_reason = ack_reason;
 		call->ackr_serial = serial;
-		call->ackr_skew = skew;
 	} else {
 		outcome = rxrpc_propose_ack_subsume;
 	}
@@ -137,11 +134,11 @@ trace:
  * propose an ACK be sent, locking the call structure
  */
 void rxrpc_propose_ACK(struct rxrpc_call *call, u8 ack_reason,
-		       u16 skew, u32 serial, bool immediate, bool background,
+		       u32 serial, bool immediate, bool background,
 		       enum rxrpc_propose_ack_trace why)
 {
 	spin_lock_bh(&call->lock);
-	__rxrpc_propose_ACK(call, ack_reason, skew, serial,
+	__rxrpc_propose_ACK(call, ack_reason, serial,
 			    immediate, background, why);
 	spin_unlock_bh(&call->lock);
 }
@@ -239,7 +236,7 @@ static void rxrpc_resend(struct rxrpc_call *call, unsigned long now_j)
 		ack_ts = ktime_sub(now, call->acks_latest_ts);
 		if (ktime_to_ns(ack_ts) < call->peer->rtt)
 			goto out;
-		rxrpc_propose_ACK(call, RXRPC_ACK_PING, 0, 0, true, false,
+		rxrpc_propose_ACK(call, RXRPC_ACK_PING, 0, true, false,
 				  rxrpc_propose_ack_ping_for_lost_ack);
 		rxrpc_send_ack_packet(call, true, NULL);
 		goto out;
@@ -372,7 +369,7 @@ recheck_state:
 	if (time_after_eq(now, t)) {
 		trace_rxrpc_timer(call, rxrpc_timer_exp_keepalive, now);
 		cmpxchg(&call->keepalive_at, t, now + MAX_JIFFY_OFFSET);
-		rxrpc_propose_ACK(call, RXRPC_ACK_PING, 0, 0, true, true,
+		rxrpc_propose_ACK(call, RXRPC_ACK_PING, 0, true, true,
 				  rxrpc_propose_ack_ping_for_keepalive);
 		set_bit(RXRPC_CALL_EV_PING, &call->events);
 	}
@@ -407,7 +404,7 @@ recheck_state:
 	send_ack = NULL;
 	if (test_and_clear_bit(RXRPC_CALL_EV_ACK_LOST, &call->events)) {
 		call->acks_lost_top = call->tx_top;
-		rxrpc_propose_ACK(call, RXRPC_ACK_PING, 0, 0, true, false,
+		rxrpc_propose_ACK(call, RXRPC_ACK_PING, 0, true, false,
 				  rxrpc_propose_ack_ping_for_lost_ack);
 		send_ack = &call->acks_lost_ping;
 	}
diff --git a/net/rxrpc/input.c b/net/rxrpc/input.c
index 5bd6f1546e5c..dd47d465d1d3 100644
--- a/net/rxrpc/input.c
+++ b/net/rxrpc/input.c
@@ -196,15 +196,14 @@ send_extra_data:
  * Ping the other end to fill our RTT cache and to retrieve the rwind
  * and MTU parameters.
  */
-static void rxrpc_send_ping(struct rxrpc_call *call, struct sk_buff *skb,
-			    int skew)
+static void rxrpc_send_ping(struct rxrpc_call *call, struct sk_buff *skb)
 {
 	struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
 	ktime_t now = skb->tstamp;
 
 	if (call->peer->rtt_usage < 3 ||
 	    ktime_before(ktime_add_ms(call->peer->rtt_last_req, 1000), now))
-		rxrpc_propose_ACK(call, RXRPC_ACK_PING, skew, sp->hdr.serial,
+		rxrpc_propose_ACK(call, RXRPC_ACK_PING, sp->hdr.serial,
 				  true, true,
 				  rxrpc_propose_ack_ping_for_params);
 }
@@ -419,8 +418,7 @@ static void rxrpc_input_dup_data(struct rxrpc_call *call, rxrpc_seq_t seq,
 /*
  * Process a DATA packet, adding the packet to the Rx ring.
  */
-static void rxrpc_input_data(struct rxrpc_call *call, struct sk_buff *skb,
-			     u16 skew)
+static void rxrpc_input_data(struct rxrpc_call *call, struct sk_buff *skb)
 {
 	struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
 	enum rxrpc_call_state state;
@@ -600,11 +598,11 @@ skip:
 
 ack:
 	if (ack)
-		rxrpc_propose_ACK(call, ack, skew, ack_serial,
+		rxrpc_propose_ACK(call, ack, ack_serial,
 				  immediate_ack, true,
 				  rxrpc_propose_ack_input_data);
 	else
-		rxrpc_propose_ACK(call, RXRPC_ACK_DELAY, skew, serial,
+		rxrpc_propose_ACK(call, RXRPC_ACK_DELAY, serial,
 				  false, true,
 				  rxrpc_propose_ack_input_data);
 
@@ -822,8 +820,7 @@ static void rxrpc_input_soft_acks(struct rxrpc_call *call, u8 *acks,
  * soft-ACK means that the packet may be discarded and retransmission
  * requested.  A phase is complete when all packets are hard-ACK'd.
  */
-static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb,
-			    u16 skew)
+static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb)
 {
 	struct rxrpc_ack_summary summary = { 0 };
 	struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
@@ -867,11 +864,11 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb,
 	if (buf.ack.reason == RXRPC_ACK_PING) {
 		_proto("Rx ACK %%%u PING Request", sp->hdr.serial);
 		rxrpc_propose_ACK(call, RXRPC_ACK_PING_RESPONSE,
-				  skew, sp->hdr.serial, true, true,
+				  sp->hdr.serial, true, true,
 				  rxrpc_propose_ack_respond_to_ping);
 	} else if (sp->hdr.flags & RXRPC_REQUEST_ACK) {
 		rxrpc_propose_ACK(call, RXRPC_ACK_REQUESTED,
-				  skew, sp->hdr.serial, true, true,
+				  sp->hdr.serial, true, true,
 				  rxrpc_propose_ack_respond_to_ack);
 	}
 
@@ -948,7 +945,7 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb,
 	    RXRPC_TX_ANNO_LAST &&
 	    summary.nr_acks == call->tx_top - hard_ack &&
 	    rxrpc_is_client_call(call))
-		rxrpc_propose_ACK(call, RXRPC_ACK_PING, skew, sp->hdr.serial,
+		rxrpc_propose_ACK(call, RXRPC_ACK_PING, sp->hdr.serial,
 				  false, true,
 				  rxrpc_propose_ack_ping_for_lost_reply);
 
@@ -1004,7 +1001,7 @@ static void rxrpc_input_abort(struct rxrpc_call *call, struct sk_buff *skb)
  * Process an incoming call packet.
  */
 static void rxrpc_input_call_packet(struct rxrpc_call *call,
-				    struct sk_buff *skb, u16 skew)
+				    struct sk_buff *skb)
 {
 	struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
 	unsigned long timo;
@@ -1023,11 +1020,11 @@ static void rxrpc_input_call_packet(struct rxrpc_call *call,
 
 	switch (sp->hdr.type) {
 	case RXRPC_PACKET_TYPE_DATA:
-		rxrpc_input_data(call, skb, skew);
+		rxrpc_input_data(call, skb);
 		break;
 
 	case RXRPC_PACKET_TYPE_ACK:
-		rxrpc_input_ack(call, skb, skew);
+		rxrpc_input_ack(call, skb);
 		break;
 
 	case RXRPC_PACKET_TYPE_BUSY:
@@ -1108,8 +1105,12 @@ static void rxrpc_post_packet_to_local(struct rxrpc_local *local,
 {
 	_enter("%p,%p", local, skb);
 
-	skb_queue_tail(&local->event_queue, skb);
-	rxrpc_queue_local(local);
+	if (rxrpc_get_local_maybe(local)) {
+		skb_queue_tail(&local->event_queue, skb);
+		rxrpc_queue_local(local);
+	} else {
+		rxrpc_free_skb(skb, rxrpc_skb_rx_freed);
+	}
 }
 
 /*
@@ -1119,8 +1120,12 @@ static void rxrpc_reject_packet(struct rxrpc_local *local, struct sk_buff *skb)
 {
 	CHECK_SLAB_OKAY(&local->usage);
 
-	skb_queue_tail(&local->reject_queue, skb);
-	rxrpc_queue_local(local);
+	if (rxrpc_get_local_maybe(local)) {
+		skb_queue_tail(&local->reject_queue, skb);
+		rxrpc_queue_local(local);
+	} else {
+		rxrpc_free_skb(skb, rxrpc_skb_rx_freed);
+	}
 }
 
 /*
@@ -1173,7 +1178,6 @@ int rxrpc_input_packet(struct sock *udp_sk, struct sk_buff *skb)
 	struct rxrpc_peer *peer = NULL;
 	struct rxrpc_sock *rx = NULL;
 	unsigned int channel;
-	int skew = 0;
 
 	_enter("%p", udp_sk);
 
@@ -1301,15 +1305,8 @@ int rxrpc_input_packet(struct sock *udp_sk, struct sk_buff *skb)
 			goto out;
 		}
 
-		/* Note the serial number skew here */
-		skew = (int)sp->hdr.serial - (int)conn->hi_serial;
-		if (skew >= 0) {
-			if (skew > 0)
-				conn->hi_serial = sp->hdr.serial;
-		} else {
-			skew = -skew;
-			skew = min(skew, 65535);
-		}
+		if ((int)sp->hdr.serial - (int)conn->hi_serial > 0)
+			conn->hi_serial = sp->hdr.serial;
 
 		/* Call-bound packets are routed by connection channel. */
 		channel = sp->hdr.cid & RXRPC_CHANNELMASK;
@@ -1372,11 +1369,11 @@ int rxrpc_input_packet(struct sock *udp_sk, struct sk_buff *skb)
 		call = rxrpc_new_incoming_call(local, rx, skb);
 		if (!call)
 			goto reject_packet;
-		rxrpc_send_ping(call, skb, skew);
+		rxrpc_send_ping(call, skb);
 		mutex_unlock(&call->user_mutex);
 	}
 
-	rxrpc_input_call_packet(call, skb, skew);
+	rxrpc_input_call_packet(call, skb);
 	goto discard;
 
 discard:
diff --git a/net/rxrpc/local_object.c b/net/rxrpc/local_object.c
index b1c71bad510b..72a6e12a9304 100644
--- a/net/rxrpc/local_object.c
+++ b/net/rxrpc/local_object.c
@@ -79,6 +79,7 @@ static struct rxrpc_local *rxrpc_alloc_local(struct rxrpc_net *rxnet,
 	local = kzalloc(sizeof(struct rxrpc_local), GFP_KERNEL);
 	if (local) {
 		atomic_set(&local->usage, 1);
+		atomic_set(&local->active_users, 1);
 		local->rxnet = rxnet;
 		INIT_LIST_HEAD(&local->link);
 		INIT_WORK(&local->processor, rxrpc_local_processor);
@@ -92,7 +93,7 @@ static struct rxrpc_local *rxrpc_alloc_local(struct rxrpc_net *rxnet,
 		local->debug_id = atomic_inc_return(&rxrpc_debug_id);
 		memcpy(&local->srx, srx, sizeof(*srx));
 		local->srx.srx_service = 0;
-		trace_rxrpc_local(local, rxrpc_local_new, 1, NULL);
+		trace_rxrpc_local(local->debug_id, rxrpc_local_new, 1, NULL);
 	}
 
 	_leave(" = %p", local);
@@ -266,11 +267,8 @@ struct rxrpc_local *rxrpc_lookup_local(struct net *net,
 		 * bind the transport socket may still fail if we're attempting
 		 * to use a local address that the dying object is still using.
 		 */
-		if (!rxrpc_get_local_maybe(local)) {
-			cursor = cursor->next;
-			list_del_init(&local->link);
+		if (!rxrpc_use_local(local))
 			break;
-		}
 
 		age = "old";
 		goto found;
@@ -284,7 +282,10 @@ struct rxrpc_local *rxrpc_lookup_local(struct net *net,
 	if (ret < 0)
 		goto sock_error;
 
-	list_add_tail(&local->link, cursor);
+	if (cursor != &rxnet->local_endpoints)
+		list_replace_init(cursor, &local->link);
+	else
+		list_add_tail(&local->link, cursor);
 	age = "new";
 
 found:
@@ -320,7 +321,7 @@ struct rxrpc_local *rxrpc_get_local(struct rxrpc_local *local)
 	int n;
 
 	n = atomic_inc_return(&local->usage);
-	trace_rxrpc_local(local, rxrpc_local_got, n, here);
+	trace_rxrpc_local(local->debug_id, rxrpc_local_got, n, here);
 	return local;
 }
 
@@ -334,7 +335,8 @@ struct rxrpc_local *rxrpc_get_local_maybe(struct rxrpc_local *local)
 	if (local) {
 		int n = atomic_fetch_add_unless(&local->usage, 1, 0);
 		if (n > 0)
-			trace_rxrpc_local(local, rxrpc_local_got, n + 1, here);
+			trace_rxrpc_local(local->debug_id, rxrpc_local_got,
+					  n + 1, here);
 		else
 			local = NULL;
 	}
@@ -342,24 +344,18 @@ struct rxrpc_local *rxrpc_get_local_maybe(struct rxrpc_local *local)
 }
 
 /*
- * Queue a local endpoint.
+ * Queue a local endpoint and pass the caller's reference to the work item.
  */
 void rxrpc_queue_local(struct rxrpc_local *local)
 {
 	const void *here = __builtin_return_address(0);
+	unsigned int debug_id = local->debug_id;
+	int n = atomic_read(&local->usage);
 
 	if (rxrpc_queue_work(&local->processor))
-		trace_rxrpc_local(local, rxrpc_local_queued,
-				  atomic_read(&local->usage), here);
-}
-
-/*
- * A local endpoint reached its end of life.
- */
-static void __rxrpc_put_local(struct rxrpc_local *local)
-{
-	_enter("%d", local->debug_id);
-	rxrpc_queue_work(&local->processor);
+		trace_rxrpc_local(debug_id, rxrpc_local_queued, n, here);
+	else
+		rxrpc_put_local(local);
 }
 
 /*
@@ -372,10 +368,47 @@ void rxrpc_put_local(struct rxrpc_local *local)
 
 	if (local) {
 		n = atomic_dec_return(&local->usage);
-		trace_rxrpc_local(local, rxrpc_local_put, n, here);
+		trace_rxrpc_local(local->debug_id, rxrpc_local_put, n, here);
 
 		if (n == 0)
-			__rxrpc_put_local(local);
+			call_rcu(&local->rcu, rxrpc_local_rcu);
+	}
+}
+
+/*
+ * Start using a local endpoint.
+ */
+struct rxrpc_local *rxrpc_use_local(struct rxrpc_local *local)
+{
+	unsigned int au;
+
+	local = rxrpc_get_local_maybe(local);
+	if (!local)
+		return NULL;
+
+	au = atomic_fetch_add_unless(&local->active_users, 1, 0);
+	if (au == 0) {
+		rxrpc_put_local(local);
+		return NULL;
+	}
+
+	return local;
+}
+
+/*
+ * Cease using a local endpoint.  Once the number of active users reaches 0, we
+ * start the closure of the transport in the work processor.
+ */
+void rxrpc_unuse_local(struct rxrpc_local *local)
+{
+	unsigned int au;
+
+	if (local) {
+		au = atomic_dec_return(&local->active_users);
+		if (au == 0)
+			rxrpc_queue_local(local);
+		else
+			rxrpc_put_local(local);
 	}
 }
 
@@ -393,16 +426,6 @@ static void rxrpc_local_destroyer(struct rxrpc_local *local)
 
 	_enter("%d", local->debug_id);
 
-	/* We can get a race between an incoming call packet queueing the
-	 * processor again and the work processor starting the destruction
-	 * process which will shut down the UDP socket.
-	 */
-	if (local->dead) {
-		_leave(" [already dead]");
-		return;
-	}
-	local->dead = true;
-
 	mutex_lock(&rxnet->local_mutex);
 	list_del_init(&local->link);
 	mutex_unlock(&rxnet->local_mutex);
@@ -422,13 +445,11 @@ static void rxrpc_local_destroyer(struct rxrpc_local *local)
 	 */
 	rxrpc_purge_queue(&local->reject_queue);
 	rxrpc_purge_queue(&local->event_queue);
-
-	_debug("rcu local %d", local->debug_id);
-	call_rcu(&local->rcu, rxrpc_local_rcu);
 }
 
 /*
- * Process events on an endpoint
+ * Process events on an endpoint.  The work item carries a ref which
+ * we must release.
  */
 static void rxrpc_local_processor(struct work_struct *work)
 {
@@ -436,13 +457,15 @@ static void rxrpc_local_processor(struct work_struct *work)
 		container_of(work, struct rxrpc_local, processor);
 	bool again;
 
-	trace_rxrpc_local(local, rxrpc_local_processing,
+	trace_rxrpc_local(local->debug_id, rxrpc_local_processing,
 			  atomic_read(&local->usage), NULL);
 
 	do {
 		again = false;
-		if (atomic_read(&local->usage) == 0)
-			return rxrpc_local_destroyer(local);
+		if (atomic_read(&local->active_users) == 0) {
+			rxrpc_local_destroyer(local);
+			break;
+		}
 
 		if (!skb_queue_empty(&local->reject_queue)) {
 			rxrpc_reject_packets(local);
@@ -454,6 +477,8 @@ static void rxrpc_local_processor(struct work_struct *work)
 			again = true;
 		}
 	} while (again);
+
+	rxrpc_put_local(local);
 }
 
 /*
diff --git a/net/rxrpc/output.c b/net/rxrpc/output.c
index 948e3fe249ec..369e516c4bdf 100644
--- a/net/rxrpc/output.c
+++ b/net/rxrpc/output.c
@@ -87,7 +87,7 @@ static size_t rxrpc_fill_out_ack(struct rxrpc_connection *conn,
 	*_top = top;
 
 	pkt->ack.bufferSpace	= htons(8);
-	pkt->ack.maxSkew	= htons(call->ackr_skew);
+	pkt->ack.maxSkew	= htons(0);
 	pkt->ack.firstPacket	= htonl(hard_ack + 1);
 	pkt->ack.previousPacket	= htonl(call->ackr_prev_seq);
 	pkt->ack.serial		= htonl(serial);
@@ -228,7 +228,6 @@ int rxrpc_send_ack_packet(struct rxrpc_call *call, bool ping,
 			if (ping)
 				clear_bit(RXRPC_CALL_PINGING, &call->flags);
 			rxrpc_propose_ACK(call, pkt->ack.reason,
-					  ntohs(pkt->ack.maxSkew),
 					  ntohl(pkt->ack.serial),
 					  false, true,
 					  rxrpc_propose_ack_retry_tx);
diff --git a/net/rxrpc/peer_event.c b/net/rxrpc/peer_event.c
index 9f2f45c09e58..7666ec72d37e 100644
--- a/net/rxrpc/peer_event.c
+++ b/net/rxrpc/peer_event.c
@@ -378,7 +378,7 @@ static void rxrpc_peer_keepalive_dispatch(struct rxrpc_net *rxnet,
 		spin_lock_bh(&rxnet->peer_hash_lock);
 		list_add_tail(&peer->keepalive_link,
 			      &rxnet->peer_keepalive[slot & mask]);
-		rxrpc_put_peer(peer);
+		rxrpc_put_peer_locked(peer);
 	}
 
 	spin_unlock_bh(&rxnet->peer_hash_lock);
diff --git a/net/rxrpc/peer_object.c b/net/rxrpc/peer_object.c
index 9d3ce81cf8ae..9c3ac96f71cb 100644
--- a/net/rxrpc/peer_object.c
+++ b/net/rxrpc/peer_object.c
@@ -437,6 +437,24 @@ void rxrpc_put_peer(struct rxrpc_peer *peer)
 }
 
 /*
+ * Drop a ref on a peer record where the caller already holds the
+ * peer_hash_lock.
+ */
+void rxrpc_put_peer_locked(struct rxrpc_peer *peer)
+{
+	const void *here = __builtin_return_address(0);
+	int n;
+
+	n = atomic_dec_return(&peer->usage);
+	trace_rxrpc_peer(peer, rxrpc_peer_put, n, here);
+	if (n == 0) {
+		hash_del_rcu(&peer->hash_link);
+		list_del_init(&peer->keepalive_link);
+		kfree_rcu(peer, rcu);
+	}
+}
+
+/*
  * Make sure all peer records have been discarded.
  */
 void rxrpc_destroy_all_peers(struct rxrpc_net *rxnet)
diff --git a/net/rxrpc/recvmsg.c b/net/rxrpc/recvmsg.c
index 5abf46cf9e6c..9a7e1bc9791d 100644
--- a/net/rxrpc/recvmsg.c
+++ b/net/rxrpc/recvmsg.c
@@ -141,7 +141,7 @@ static void rxrpc_end_rx_phase(struct rxrpc_call *call, rxrpc_serial_t serial)
 	ASSERTCMP(call->rx_hard_ack, ==, call->rx_top);
 
 	if (call->state == RXRPC_CALL_CLIENT_RECV_REPLY) {
-		rxrpc_propose_ACK(call, RXRPC_ACK_IDLE, 0, serial, false, true,
+		rxrpc_propose_ACK(call, RXRPC_ACK_IDLE, serial, false, true,
 				  rxrpc_propose_ack_terminal_ack);
 		//rxrpc_send_ack_packet(call, false, NULL);
 	}
@@ -159,7 +159,7 @@ static void rxrpc_end_rx_phase(struct rxrpc_call *call, rxrpc_serial_t serial)
 		call->state = RXRPC_CALL_SERVER_ACK_REQUEST;
 		call->expect_req_by = jiffies + MAX_JIFFY_OFFSET;
 		write_unlock_bh(&call->state_lock);
-		rxrpc_propose_ACK(call, RXRPC_ACK_DELAY, 0, serial, false, true,
+		rxrpc_propose_ACK(call, RXRPC_ACK_DELAY, serial, false, true,
 				  rxrpc_propose_ack_processing_op);
 		break;
 	default:
@@ -212,7 +212,7 @@ static void rxrpc_rotate_rx_window(struct rxrpc_call *call)
 		if (after_eq(hard_ack, call->ackr_consumed + 2) ||
 		    after_eq(top, call->ackr_seen + 2) ||
 		    (hard_ack == top && after(hard_ack, call->ackr_consumed)))
-			rxrpc_propose_ACK(call, RXRPC_ACK_DELAY, 0, serial,
+			rxrpc_propose_ACK(call, RXRPC_ACK_DELAY, serial,
 					  true, true,
 					  rxrpc_propose_ack_rotate_rx);
 		if (call->ackr_reason && call->ackr_reason != RXRPC_ACK_DELAY)
diff --git a/net/rxrpc/sendmsg.c b/net/rxrpc/sendmsg.c
index 5d3f33ce6d41..bae14438f869 100644
--- a/net/rxrpc/sendmsg.c
+++ b/net/rxrpc/sendmsg.c
@@ -226,6 +226,7 @@ static int rxrpc_queue_packet(struct rxrpc_sock *rx, struct rxrpc_call *call,
 			rxrpc_set_call_completion(call,
 						  RXRPC_CALL_LOCAL_ERROR,
 						  0, ret);
+			rxrpc_notify_socket(call);
 			goto out;
 		}
 		_debug("need instant resend %d", ret);
diff --git a/net/rxrpc/sysctl.c b/net/rxrpc/sysctl.c
index 1e3fa67d91aa..2bbb38161851 100644
--- a/net/rxrpc/sysctl.c
+++ b/net/rxrpc/sysctl.c
@@ -11,7 +11,6 @@
 #include "ar-internal.h"
 
 static struct ctl_table_header *rxrpc_sysctl_reg_table;
-static const unsigned int one = 1;
 static const unsigned int four = 4;
 static const unsigned int thirtytwo = 32;
 static const unsigned int n_65535 = 65535;
@@ -97,7 +96,7 @@ static struct ctl_table rxrpc_sysctl_table[] = {
 		.maxlen		= sizeof(unsigned int),
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec_minmax,
-		.extra1		= (void *)&one,
+		.extra1		= (void *)SYSCTL_ONE,
 		.extra2		= (void *)&rxrpc_max_client_connections,
 	},
 	{
@@ -115,7 +114,7 @@ static struct ctl_table rxrpc_sysctl_table[] = {
 		.maxlen		= sizeof(unsigned int),
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec_minmax,
-		.extra1		= (void *)&one,
+		.extra1		= (void *)SYSCTL_ONE,
 		.extra2		= (void *)&n_max_acks,
 	},
 	{
@@ -124,7 +123,7 @@ static struct ctl_table rxrpc_sysctl_table[] = {
 		.maxlen		= sizeof(unsigned int),
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec_minmax,
-		.extra1		= (void *)&one,
+		.extra1		= (void *)SYSCTL_ONE,
 		.extra2		= (void *)&n_65535,
 	},
 	{
@@ -133,7 +132,7 @@ static struct ctl_table rxrpc_sysctl_table[] = {
 		.maxlen		= sizeof(unsigned int),
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec_minmax,
-		.extra1		= (void *)&one,
+		.extra1		= (void *)SYSCTL_ONE,
 		.extra2		= (void *)&four,
 	},
 
diff --git a/net/sched/Kconfig b/net/sched/Kconfig
index dd55b9ac3a66..afd2ba157a13 100644
--- a/net/sched/Kconfig
+++ b/net/sched/Kconfig
@@ -942,7 +942,7 @@ config NET_ACT_TUNNEL_KEY
 
 config NET_ACT_CT
         tristate "connection tracking tc action"
-        depends on NET_CLS_ACT && NF_CONNTRACK
+        depends on NET_CLS_ACT && NF_CONNTRACK && NF_NAT
         help
 	  Say Y here to allow sending the packets to conntrack module.
 
diff --git a/net/sched/act_bpf.c b/net/sched/act_bpf.c
index 8126b26f125e..fd1f7e799e23 100644
--- a/net/sched/act_bpf.c
+++ b/net/sched/act_bpf.c
@@ -285,6 +285,7 @@ static int tcf_bpf_init(struct net *net, struct nlattr *nla,
 	struct tcf_bpf *prog;
 	bool is_bpf, is_ebpf;
 	int ret, res = 0;
+	u32 index;
 
 	if (!nla)
 		return -EINVAL;
@@ -298,13 +299,13 @@ static int tcf_bpf_init(struct net *net, struct nlattr *nla,
 		return -EINVAL;
 
 	parm = nla_data(tb[TCA_ACT_BPF_PARMS]);
-
-	ret = tcf_idr_check_alloc(tn, &parm->index, act, bind);
+	index = parm->index;
+	ret = tcf_idr_check_alloc(tn, &index, act, bind);
 	if (!ret) {
-		ret = tcf_idr_create(tn, parm->index, est, act,
+		ret = tcf_idr_create(tn, index, est, act,
 				     &act_bpf_ops, bind, true);
 		if (ret < 0) {
-			tcf_idr_cleanup(tn, parm->index);
+			tcf_idr_cleanup(tn, index);
 			return ret;
 		}
 
diff --git a/net/sched/act_connmark.c b/net/sched/act_connmark.c
index ce36b0f7e1dc..32ac04d77a45 100644
--- a/net/sched/act_connmark.c
+++ b/net/sched/act_connmark.c
@@ -103,6 +103,7 @@ static int tcf_connmark_init(struct net *net, struct nlattr *nla,
 	struct tcf_connmark_info *ci;
 	struct tc_connmark *parm;
 	int ret = 0, err;
+	u32 index;
 
 	if (!nla)
 		return -EINVAL;
@@ -116,13 +117,13 @@ static int tcf_connmark_init(struct net *net, struct nlattr *nla,
 		return -EINVAL;
 
 	parm = nla_data(tb[TCA_CONNMARK_PARMS]);
-
-	ret = tcf_idr_check_alloc(tn, &parm->index, a, bind);
+	index = parm->index;
+	ret = tcf_idr_check_alloc(tn, &index, a, bind);
 	if (!ret) {
-		ret = tcf_idr_create(tn, parm->index, est, a,
+		ret = tcf_idr_create(tn, index, est, a,
 				     &act_connmark_ops, bind, false);
 		if (ret) {
-			tcf_idr_cleanup(tn, parm->index);
+			tcf_idr_cleanup(tn, index);
 			return ret;
 		}
 
diff --git a/net/sched/act_csum.c b/net/sched/act_csum.c
index 621fb22ce2a9..9b9288267a54 100644
--- a/net/sched/act_csum.c
+++ b/net/sched/act_csum.c
@@ -52,6 +52,7 @@ static int tcf_csum_init(struct net *net, struct nlattr *nla,
 	struct tc_csum *parm;
 	struct tcf_csum *p;
 	int ret = 0, err;
+	u32 index;
 
 	if (nla == NULL)
 		return -EINVAL;
@@ -64,13 +65,13 @@ static int tcf_csum_init(struct net *net, struct nlattr *nla,
 	if (tb[TCA_CSUM_PARMS] == NULL)
 		return -EINVAL;
 	parm = nla_data(tb[TCA_CSUM_PARMS]);
-
-	err = tcf_idr_check_alloc(tn, &parm->index, a, bind);
+	index = parm->index;
+	err = tcf_idr_check_alloc(tn, &index, a, bind);
 	if (!err) {
-		ret = tcf_idr_create(tn, parm->index, est, a,
+		ret = tcf_idr_create(tn, index, est, a,
 				     &act_csum_ops, bind, true);
 		if (ret) {
-			tcf_idr_cleanup(tn, parm->index);
+			tcf_idr_cleanup(tn, index);
 			return ret;
 		}
 		ret = ACT_P_CREATED;
diff --git a/net/sched/act_ct.c b/net/sched/act_ct.c
index b501ce0cf116..33a1a7406e87 100644
--- a/net/sched/act_ct.c
+++ b/net/sched/act_ct.c
@@ -666,6 +666,7 @@ static int tcf_ct_init(struct net *net, struct nlattr *nla,
 	struct tc_ct *parm;
 	struct tcf_ct *c;
 	int err, res = 0;
+	u32 index;
 
 	if (!nla) {
 		NL_SET_ERR_MSG_MOD(extack, "Ct requires attributes to be passed");
@@ -681,16 +682,16 @@ static int tcf_ct_init(struct net *net, struct nlattr *nla,
 		return -EINVAL;
 	}
 	parm = nla_data(tb[TCA_CT_PARMS]);
-
-	err = tcf_idr_check_alloc(tn, &parm->index, a, bind);
+	index = parm->index;
+	err = tcf_idr_check_alloc(tn, &index, a, bind);
 	if (err < 0)
 		return err;
 
 	if (!err) {
-		err = tcf_idr_create(tn, parm->index, est, a,
+		err = tcf_idr_create(tn, index, est, a,
 				     &act_ct_ops, bind, true);
 		if (err) {
-			tcf_idr_cleanup(tn, parm->index);
+			tcf_idr_cleanup(tn, index);
 			return err;
 		}
 		res = ACT_P_CREATED;
diff --git a/net/sched/act_ctinfo.c b/net/sched/act_ctinfo.c
index 10eb2bb99861..06ef74b74911 100644
--- a/net/sched/act_ctinfo.c
+++ b/net/sched/act_ctinfo.c
@@ -157,10 +157,10 @@ static int tcf_ctinfo_init(struct net *net, struct nlattr *nla,
 			   struct netlink_ext_ack *extack)
 {
 	struct tc_action_net *tn = net_generic(net, ctinfo_net_id);
+	u32 dscpmask = 0, dscpstatemask, index;
 	struct nlattr *tb[TCA_CTINFO_MAX + 1];
 	struct tcf_ctinfo_params *cp_new;
 	struct tcf_chain *goto_ch = NULL;
-	u32 dscpmask = 0, dscpstatemask;
 	struct tc_ctinfo *actparm;
 	struct tcf_ctinfo *ci;
 	u8 dscpmaskshift;
@@ -206,12 +206,13 @@ static int tcf_ctinfo_init(struct net *net, struct nlattr *nla,
 	}
 
 	/* done the validation:now to the actual action allocation */
-	err = tcf_idr_check_alloc(tn, &actparm->index, a, bind);
+	index = actparm->index;
+	err = tcf_idr_check_alloc(tn, &index, a, bind);
 	if (!err) {
-		ret = tcf_idr_create(tn, actparm->index, est, a,
+		ret = tcf_idr_create(tn, index, est, a,
 				     &act_ctinfo_ops, bind, false);
 		if (ret) {
-			tcf_idr_cleanup(tn, actparm->index);
+			tcf_idr_cleanup(tn, index);
 			return ret;
 		}
 		ret = ACT_P_CREATED;
diff --git a/net/sched/act_gact.c b/net/sched/act_gact.c
index b2380c5284e6..8f0140c6ca58 100644
--- a/net/sched/act_gact.c
+++ b/net/sched/act_gact.c
@@ -61,6 +61,7 @@ static int tcf_gact_init(struct net *net, struct nlattr *nla,
 	struct tc_gact *parm;
 	struct tcf_gact *gact;
 	int ret = 0;
+	u32 index;
 	int err;
 #ifdef CONFIG_GACT_PROB
 	struct tc_gact_p *p_parm = NULL;
@@ -77,6 +78,7 @@ static int tcf_gact_init(struct net *net, struct nlattr *nla,
 	if (tb[TCA_GACT_PARMS] == NULL)
 		return -EINVAL;
 	parm = nla_data(tb[TCA_GACT_PARMS]);
+	index = parm->index;
 
 #ifndef CONFIG_GACT_PROB
 	if (tb[TCA_GACT_PROB] != NULL)
@@ -94,12 +96,12 @@ static int tcf_gact_init(struct net *net, struct nlattr *nla,
 	}
 #endif
 
-	err = tcf_idr_check_alloc(tn, &parm->index, a, bind);
+	err = tcf_idr_check_alloc(tn, &index, a, bind);
 	if (!err) {
-		ret = tcf_idr_create(tn, parm->index, est, a,
+		ret = tcf_idr_create(tn, index, est, a,
 				     &act_gact_ops, bind, true);
 		if (ret) {
-			tcf_idr_cleanup(tn, parm->index);
+			tcf_idr_cleanup(tn, index);
 			return ret;
 		}
 		ret = ACT_P_CREATED;
diff --git a/net/sched/act_ife.c b/net/sched/act_ife.c
index 41d5398dd2f2..92ee853d43e6 100644
--- a/net/sched/act_ife.c
+++ b/net/sched/act_ife.c
@@ -479,8 +479,14 @@ static int tcf_ife_init(struct net *net, struct nlattr *nla,
 	u8 *saddr = NULL;
 	bool exists = false;
 	int ret = 0;
+	u32 index;
 	int err;
 
+	if (!nla) {
+		NL_SET_ERR_MSG_MOD(extack, "IFE requires attributes to be passed");
+		return -EINVAL;
+	}
+
 	err = nla_parse_nested_deprecated(tb, TCA_IFE_MAX, nla, ife_policy,
 					  NULL);
 	if (err < 0)
@@ -502,7 +508,8 @@ static int tcf_ife_init(struct net *net, struct nlattr *nla,
 	if (!p)
 		return -ENOMEM;
 
-	err = tcf_idr_check_alloc(tn, &parm->index, a, bind);
+	index = parm->index;
+	err = tcf_idr_check_alloc(tn, &index, a, bind);
 	if (err < 0) {
 		kfree(p);
 		return err;
@@ -514,10 +521,10 @@ static int tcf_ife_init(struct net *net, struct nlattr *nla,
 	}
 
 	if (!exists) {
-		ret = tcf_idr_create(tn, parm->index, est, a, &act_ife_ops,
+		ret = tcf_idr_create(tn, index, est, a, &act_ife_ops,
 				     bind, true);
 		if (ret) {
-			tcf_idr_cleanup(tn, parm->index);
+			tcf_idr_cleanup(tn, index);
 			kfree(p);
 			return ret;
 		}
diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c
index 055faa298c8e..be3f88dfc37e 100644
--- a/net/sched/act_mirred.c
+++ b/net/sched/act_mirred.c
@@ -104,6 +104,7 @@ static int tcf_mirred_init(struct net *net, struct nlattr *nla,
 	struct net_device *dev;
 	bool exists = false;
 	int ret, err;
+	u32 index;
 
 	if (!nla) {
 		NL_SET_ERR_MSG_MOD(extack, "Mirred requires attributes to be passed");
@@ -118,8 +119,8 @@ static int tcf_mirred_init(struct net *net, struct nlattr *nla,
 		return -EINVAL;
 	}
 	parm = nla_data(tb[TCA_MIRRED_PARMS]);
-
-	err = tcf_idr_check_alloc(tn, &parm->index, a, bind);
+	index = parm->index;
+	err = tcf_idr_check_alloc(tn, &index, a, bind);
 	if (err < 0)
 		return err;
 	exists = err;
@@ -136,21 +137,21 @@ static int tcf_mirred_init(struct net *net, struct nlattr *nla,
 		if (exists)
 			tcf_idr_release(*a, bind);
 		else
-			tcf_idr_cleanup(tn, parm->index);
+			tcf_idr_cleanup(tn, index);
 		NL_SET_ERR_MSG_MOD(extack, "Unknown mirred option");
 		return -EINVAL;
 	}
 
 	if (!exists) {
 		if (!parm->ifindex) {
-			tcf_idr_cleanup(tn, parm->index);
+			tcf_idr_cleanup(tn, index);
 			NL_SET_ERR_MSG_MOD(extack, "Specified device does not exist");
 			return -EINVAL;
 		}
-		ret = tcf_idr_create(tn, parm->index, est, a,
+		ret = tcf_idr_create(tn, index, est, a,
 				     &act_mirred_ops, bind, true);
 		if (ret) {
-			tcf_idr_cleanup(tn, parm->index);
+			tcf_idr_cleanup(tn, index);
 			return ret;
 		}
 		ret = ACT_P_CREATED;
diff --git a/net/sched/act_mpls.c b/net/sched/act_mpls.c
index ca2597ce4ac9..0f299e3b618c 100644
--- a/net/sched/act_mpls.c
+++ b/net/sched/act_mpls.c
@@ -138,6 +138,7 @@ static int tcf_mpls_init(struct net *net, struct nlattr *nla,
 	struct tcf_mpls *m;
 	int ret = 0, err;
 	u8 mpls_ttl = 0;
+	u32 index;
 
 	if (!nla) {
 		NL_SET_ERR_MSG_MOD(extack, "Missing netlink attributes");
@@ -153,6 +154,7 @@ static int tcf_mpls_init(struct net *net, struct nlattr *nla,
 		return -EINVAL;
 	}
 	parm = nla_data(tb[TCA_MPLS_PARMS]);
+	index = parm->index;
 
 	/* Verify parameters against action type. */
 	switch (parm->m_action) {
@@ -209,7 +211,7 @@ static int tcf_mpls_init(struct net *net, struct nlattr *nla,
 		return -EINVAL;
 	}
 
-	err = tcf_idr_check_alloc(tn, &parm->index, a, bind);
+	err = tcf_idr_check_alloc(tn, &index, a, bind);
 	if (err < 0)
 		return err;
 	exists = err;
@@ -217,10 +219,10 @@ static int tcf_mpls_init(struct net *net, struct nlattr *nla,
 		return 0;
 
 	if (!exists) {
-		ret = tcf_idr_create(tn, parm->index, est, a,
+		ret = tcf_idr_create(tn, index, est, a,
 				     &act_mpls_ops, bind, true);
 		if (ret) {
-			tcf_idr_cleanup(tn, parm->index);
+			tcf_idr_cleanup(tn, index);
 			return ret;
 		}
 
diff --git a/net/sched/act_nat.c b/net/sched/act_nat.c
index 45923ebb7a4f..7b858c11b1b5 100644
--- a/net/sched/act_nat.c
+++ b/net/sched/act_nat.c
@@ -44,6 +44,7 @@ static int tcf_nat_init(struct net *net, struct nlattr *nla, struct nlattr *est,
 	struct tc_nat *parm;
 	int ret = 0, err;
 	struct tcf_nat *p;
+	u32 index;
 
 	if (nla == NULL)
 		return -EINVAL;
@@ -56,13 +57,13 @@ static int tcf_nat_init(struct net *net, struct nlattr *nla, struct nlattr *est,
 	if (tb[TCA_NAT_PARMS] == NULL)
 		return -EINVAL;
 	parm = nla_data(tb[TCA_NAT_PARMS]);
-
-	err = tcf_idr_check_alloc(tn, &parm->index, a, bind);
+	index = parm->index;
+	err = tcf_idr_check_alloc(tn, &index, a, bind);
 	if (!err) {
-		ret = tcf_idr_create(tn, parm->index, est, a,
+		ret = tcf_idr_create(tn, index, est, a,
 				     &act_nat_ops, bind, false);
 		if (ret) {
-			tcf_idr_cleanup(tn, parm->index);
+			tcf_idr_cleanup(tn, index);
 			return ret;
 		}
 		ret = ACT_P_CREATED;
diff --git a/net/sched/act_pedit.c b/net/sched/act_pedit.c
index 45e9d6bfddb3..17360c6faeaa 100644
--- a/net/sched/act_pedit.c
+++ b/net/sched/act_pedit.c
@@ -149,6 +149,7 @@ static int tcf_pedit_init(struct net *net, struct nlattr *nla,
 	struct tcf_pedit *p;
 	int ret = 0, err;
 	int ksize;
+	u32 index;
 
 	if (!nla) {
 		NL_SET_ERR_MSG_MOD(extack, "Pedit requires attributes to be passed");
@@ -179,18 +180,19 @@ static int tcf_pedit_init(struct net *net, struct nlattr *nla,
 	if (IS_ERR(keys_ex))
 		return PTR_ERR(keys_ex);
 
-	err = tcf_idr_check_alloc(tn, &parm->index, a, bind);
+	index = parm->index;
+	err = tcf_idr_check_alloc(tn, &index, a, bind);
 	if (!err) {
 		if (!parm->nkeys) {
-			tcf_idr_cleanup(tn, parm->index);
+			tcf_idr_cleanup(tn, index);
 			NL_SET_ERR_MSG_MOD(extack, "Pedit requires keys to be passed");
 			ret = -EINVAL;
 			goto out_free;
 		}
-		ret = tcf_idr_create(tn, parm->index, est, a,
+		ret = tcf_idr_create(tn, index, est, a,
 				     &act_pedit_ops, bind, false);
 		if (ret) {
-			tcf_idr_cleanup(tn, parm->index);
+			tcf_idr_cleanup(tn, index);
 			goto out_free;
 		}
 		ret = ACT_P_CREATED;
diff --git a/net/sched/act_police.c b/net/sched/act_police.c
index a065f62fa79c..49cec3e64a4d 100644
--- a/net/sched/act_police.c
+++ b/net/sched/act_police.c
@@ -57,6 +57,7 @@ static int tcf_police_init(struct net *net, struct nlattr *nla,
 	struct tc_action_net *tn = net_generic(net, police_net_id);
 	struct tcf_police_params *new;
 	bool exists = false;
+	u32 index;
 
 	if (nla == NULL)
 		return -EINVAL;
@@ -73,7 +74,8 @@ static int tcf_police_init(struct net *net, struct nlattr *nla,
 		return -EINVAL;
 
 	parm = nla_data(tb[TCA_POLICE_TBF]);
-	err = tcf_idr_check_alloc(tn, &parm->index, a, bind);
+	index = parm->index;
+	err = tcf_idr_check_alloc(tn, &index, a, bind);
 	if (err < 0)
 		return err;
 	exists = err;
@@ -81,10 +83,10 @@ static int tcf_police_init(struct net *net, struct nlattr *nla,
 		return 0;
 
 	if (!exists) {
-		ret = tcf_idr_create(tn, parm->index, NULL, a,
+		ret = tcf_idr_create(tn, index, NULL, a,
 				     &act_police_ops, bind, true);
 		if (ret) {
-			tcf_idr_cleanup(tn, parm->index);
+			tcf_idr_cleanup(tn, index);
 			return ret;
 		}
 		ret = ACT_P_CREATED;
diff --git a/net/sched/act_sample.c b/net/sched/act_sample.c
index 274d7a0c0e25..595308d60133 100644
--- a/net/sched/act_sample.c
+++ b/net/sched/act_sample.c
@@ -41,8 +41,8 @@ static int tcf_sample_init(struct net *net, struct nlattr *nla,
 	struct tc_action_net *tn = net_generic(net, sample_net_id);
 	struct nlattr *tb[TCA_SAMPLE_MAX + 1];
 	struct psample_group *psample_group;
+	u32 psample_group_num, rate, index;
 	struct tcf_chain *goto_ch = NULL;
-	u32 psample_group_num, rate;
 	struct tc_sample *parm;
 	struct tcf_sample *s;
 	bool exists = false;
@@ -59,8 +59,8 @@ static int tcf_sample_init(struct net *net, struct nlattr *nla,
 		return -EINVAL;
 
 	parm = nla_data(tb[TCA_SAMPLE_PARMS]);
-
-	err = tcf_idr_check_alloc(tn, &parm->index, a, bind);
+	index = parm->index;
+	err = tcf_idr_check_alloc(tn, &index, a, bind);
 	if (err < 0)
 		return err;
 	exists = err;
@@ -68,10 +68,10 @@ static int tcf_sample_init(struct net *net, struct nlattr *nla,
 		return 0;
 
 	if (!exists) {
-		ret = tcf_idr_create(tn, parm->index, est, a,
+		ret = tcf_idr_create(tn, index, est, a,
 				     &act_sample_ops, bind, true);
 		if (ret) {
-			tcf_idr_cleanup(tn, parm->index);
+			tcf_idr_cleanup(tn, index);
 			return ret;
 		}
 		ret = ACT_P_CREATED;
diff --git a/net/sched/act_simple.c b/net/sched/act_simple.c
index f28ddbabff76..33aefa25b545 100644
--- a/net/sched/act_simple.c
+++ b/net/sched/act_simple.c
@@ -95,6 +95,7 @@ static int tcf_simp_init(struct net *net, struct nlattr *nla,
 	struct tcf_defact *d;
 	bool exists = false;
 	int ret = 0, err;
+	u32 index;
 
 	if (nla == NULL)
 		return -EINVAL;
@@ -108,7 +109,8 @@ static int tcf_simp_init(struct net *net, struct nlattr *nla,
 		return -EINVAL;
 
 	parm = nla_data(tb[TCA_DEF_PARMS]);
-	err = tcf_idr_check_alloc(tn, &parm->index, a, bind);
+	index = parm->index;
+	err = tcf_idr_check_alloc(tn, &index, a, bind);
 	if (err < 0)
 		return err;
 	exists = err;
@@ -119,15 +121,15 @@ static int tcf_simp_init(struct net *net, struct nlattr *nla,
 		if (exists)
 			tcf_idr_release(*a, bind);
 		else
-			tcf_idr_cleanup(tn, parm->index);
+			tcf_idr_cleanup(tn, index);
 		return -EINVAL;
 	}
 
 	if (!exists) {
-		ret = tcf_idr_create(tn, parm->index, est, a,
+		ret = tcf_idr_create(tn, index, est, a,
 				     &act_simp_ops, bind, false);
 		if (ret) {
-			tcf_idr_cleanup(tn, parm->index);
+			tcf_idr_cleanup(tn, index);
 			return ret;
 		}
 
diff --git a/net/sched/act_skbedit.c b/net/sched/act_skbedit.c
index 215a06705cef..37dced00b63d 100644
--- a/net/sched/act_skbedit.c
+++ b/net/sched/act_skbedit.c
@@ -99,6 +99,7 @@ static int tcf_skbedit_init(struct net *net, struct nlattr *nla,
 	u16 *queue_mapping = NULL, *ptype = NULL;
 	bool exists = false;
 	int ret = 0, err;
+	u32 index;
 
 	if (nla == NULL)
 		return -EINVAL;
@@ -146,8 +147,8 @@ static int tcf_skbedit_init(struct net *net, struct nlattr *nla,
 	}
 
 	parm = nla_data(tb[TCA_SKBEDIT_PARMS]);
-
-	err = tcf_idr_check_alloc(tn, &parm->index, a, bind);
+	index = parm->index;
+	err = tcf_idr_check_alloc(tn, &index, a, bind);
 	if (err < 0)
 		return err;
 	exists = err;
@@ -158,15 +159,15 @@ static int tcf_skbedit_init(struct net *net, struct nlattr *nla,
 		if (exists)
 			tcf_idr_release(*a, bind);
 		else
-			tcf_idr_cleanup(tn, parm->index);
+			tcf_idr_cleanup(tn, index);
 		return -EINVAL;
 	}
 
 	if (!exists) {
-		ret = tcf_idr_create(tn, parm->index, est, a,
+		ret = tcf_idr_create(tn, index, est, a,
 				     &act_skbedit_ops, bind, true);
 		if (ret) {
-			tcf_idr_cleanup(tn, parm->index);
+			tcf_idr_cleanup(tn, index);
 			return ret;
 		}
 
@@ -306,6 +307,17 @@ static int tcf_skbedit_search(struct net *net, struct tc_action **a, u32 index)
 	return tcf_idr_search(tn, a, index);
 }
 
+static size_t tcf_skbedit_get_fill_size(const struct tc_action *act)
+{
+	return nla_total_size(sizeof(struct tc_skbedit))
+		+ nla_total_size(sizeof(u32)) /* TCA_SKBEDIT_PRIORITY */
+		+ nla_total_size(sizeof(u16)) /* TCA_SKBEDIT_QUEUE_MAPPING */
+		+ nla_total_size(sizeof(u32)) /* TCA_SKBEDIT_MARK */
+		+ nla_total_size(sizeof(u16)) /* TCA_SKBEDIT_PTYPE */
+		+ nla_total_size(sizeof(u32)) /* TCA_SKBEDIT_MASK */
+		+ nla_total_size_64bit(sizeof(u64)); /* TCA_SKBEDIT_FLAGS */
+}
+
 static struct tc_action_ops act_skbedit_ops = {
 	.kind		=	"skbedit",
 	.id		=	TCA_ID_SKBEDIT,
@@ -315,6 +327,7 @@ static struct tc_action_ops act_skbedit_ops = {
 	.init		=	tcf_skbedit_init,
 	.cleanup	=	tcf_skbedit_cleanup,
 	.walk		=	tcf_skbedit_walker,
+	.get_fill_size	=	tcf_skbedit_get_fill_size,
 	.lookup		=	tcf_skbedit_search,
 	.size		=	sizeof(struct tcf_skbedit),
 };
diff --git a/net/sched/act_skbmod.c b/net/sched/act_skbmod.c
index 4f07706eff07..7da3518e18ef 100644
--- a/net/sched/act_skbmod.c
+++ b/net/sched/act_skbmod.c
@@ -87,12 +87,12 @@ static int tcf_skbmod_init(struct net *net, struct nlattr *nla,
 	struct tcf_skbmod_params *p, *p_old;
 	struct tcf_chain *goto_ch = NULL;
 	struct tc_skbmod *parm;
+	u32 lflags = 0, index;
 	struct tcf_skbmod *d;
 	bool exists = false;
 	u8 *daddr = NULL;
 	u8 *saddr = NULL;
 	u16 eth_type = 0;
-	u32 lflags = 0;
 	int ret = 0, err;
 
 	if (!nla)
@@ -122,10 +122,11 @@ static int tcf_skbmod_init(struct net *net, struct nlattr *nla,
 	}
 
 	parm = nla_data(tb[TCA_SKBMOD_PARMS]);
+	index = parm->index;
 	if (parm->flags & SKBMOD_F_SWAPMAC)
 		lflags = SKBMOD_F_SWAPMAC;
 
-	err = tcf_idr_check_alloc(tn, &parm->index, a, bind);
+	err = tcf_idr_check_alloc(tn, &index, a, bind);
 	if (err < 0)
 		return err;
 	exists = err;
@@ -136,15 +137,15 @@ static int tcf_skbmod_init(struct net *net, struct nlattr *nla,
 		if (exists)
 			tcf_idr_release(*a, bind);
 		else
-			tcf_idr_cleanup(tn, parm->index);
+			tcf_idr_cleanup(tn, index);
 		return -EINVAL;
 	}
 
 	if (!exists) {
-		ret = tcf_idr_create(tn, parm->index, est, a,
+		ret = tcf_idr_create(tn, index, est, a,
 				     &act_skbmod_ops, bind, true);
 		if (ret) {
-			tcf_idr_cleanup(tn, parm->index);
+			tcf_idr_cleanup(tn, index);
 			return ret;
 		}
 
diff --git a/net/sched/act_tunnel_key.c b/net/sched/act_tunnel_key.c
index 10dffda1d5cc..6d0debdc9b97 100644
--- a/net/sched/act_tunnel_key.c
+++ b/net/sched/act_tunnel_key.c
@@ -225,6 +225,7 @@ static int tunnel_key_init(struct net *net, struct nlattr *nla,
 	__be16 flags = 0;
 	u8 tos, ttl;
 	int ret = 0;
+	u32 index;
 	int err;
 
 	if (!nla) {
@@ -245,7 +246,8 @@ static int tunnel_key_init(struct net *net, struct nlattr *nla,
 	}
 
 	parm = nla_data(tb[TCA_TUNNEL_KEY_PARMS]);
-	err = tcf_idr_check_alloc(tn, &parm->index, a, bind);
+	index = parm->index;
+	err = tcf_idr_check_alloc(tn, &index, a, bind);
 	if (err < 0)
 		return err;
 	exists = err;
@@ -345,7 +347,7 @@ static int tunnel_key_init(struct net *net, struct nlattr *nla,
 	}
 
 	if (!exists) {
-		ret = tcf_idr_create(tn, parm->index, est, a,
+		ret = tcf_idr_create(tn, index, est, a,
 				     &act_tunnel_key_ops, bind, true);
 		if (ret) {
 			NL_SET_ERR_MSG(extack, "Cannot create TC IDR");
@@ -403,7 +405,7 @@ err_out:
 	if (exists)
 		tcf_idr_release(*a, bind);
 	else
-		tcf_idr_cleanup(tn, parm->index);
+		tcf_idr_cleanup(tn, index);
 	return ret;
 }
 
diff --git a/net/sched/act_vlan.c b/net/sched/act_vlan.c
index 9269d350fb8a..a3c9eea1ee8a 100644
--- a/net/sched/act_vlan.c
+++ b/net/sched/act_vlan.c
@@ -116,6 +116,7 @@ static int tcf_vlan_init(struct net *net, struct nlattr *nla,
 	u8 push_prio = 0;
 	bool exists = false;
 	int ret = 0, err;
+	u32 index;
 
 	if (!nla)
 		return -EINVAL;
@@ -128,7 +129,8 @@ static int tcf_vlan_init(struct net *net, struct nlattr *nla,
 	if (!tb[TCA_VLAN_PARMS])
 		return -EINVAL;
 	parm = nla_data(tb[TCA_VLAN_PARMS]);
-	err = tcf_idr_check_alloc(tn, &parm->index, a, bind);
+	index = parm->index;
+	err = tcf_idr_check_alloc(tn, &index, a, bind);
 	if (err < 0)
 		return err;
 	exists = err;
@@ -144,7 +146,7 @@ static int tcf_vlan_init(struct net *net, struct nlattr *nla,
 			if (exists)
 				tcf_idr_release(*a, bind);
 			else
-				tcf_idr_cleanup(tn, parm->index);
+				tcf_idr_cleanup(tn, index);
 			return -EINVAL;
 		}
 		push_vid = nla_get_u16(tb[TCA_VLAN_PUSH_VLAN_ID]);
@@ -152,7 +154,7 @@ static int tcf_vlan_init(struct net *net, struct nlattr *nla,
 			if (exists)
 				tcf_idr_release(*a, bind);
 			else
-				tcf_idr_cleanup(tn, parm->index);
+				tcf_idr_cleanup(tn, index);
 			return -ERANGE;
 		}
 
@@ -166,7 +168,7 @@ static int tcf_vlan_init(struct net *net, struct nlattr *nla,
 				if (exists)
 					tcf_idr_release(*a, bind);
 				else
-					tcf_idr_cleanup(tn, parm->index);
+					tcf_idr_cleanup(tn, index);
 				return -EPROTONOSUPPORT;
 			}
 		} else {
@@ -180,16 +182,16 @@ static int tcf_vlan_init(struct net *net, struct nlattr *nla,
 		if (exists)
 			tcf_idr_release(*a, bind);
 		else
-			tcf_idr_cleanup(tn, parm->index);
+			tcf_idr_cleanup(tn, index);
 		return -EINVAL;
 	}
 	action = parm->v_action;
 
 	if (!exists) {
-		ret = tcf_idr_create(tn, parm->index, est, a,
+		ret = tcf_idr_create(tn, index, est, a,
 				     &act_vlan_ops, bind, true);
 		if (ret) {
-			tcf_idr_cleanup(tn, parm->index);
+			tcf_idr_cleanup(tn, index);
 			return ret;
 		}
 
@@ -306,6 +308,14 @@ static int tcf_vlan_search(struct net *net, struct tc_action **a, u32 index)
 	return tcf_idr_search(tn, a, index);
 }
 
+static size_t tcf_vlan_get_fill_size(const struct tc_action *act)
+{
+	return nla_total_size(sizeof(struct tc_vlan))
+		+ nla_total_size(sizeof(u16)) /* TCA_VLAN_PUSH_VLAN_ID */
+		+ nla_total_size(sizeof(u16)) /* TCA_VLAN_PUSH_VLAN_PROTOCOL */
+		+ nla_total_size(sizeof(u8)); /* TCA_VLAN_PUSH_VLAN_PRIORITY */
+}
+
 static struct tc_action_ops act_vlan_ops = {
 	.kind		=	"vlan",
 	.id		=	TCA_ID_VLAN,
@@ -315,6 +325,7 @@ static struct tc_action_ops act_vlan_ops = {
 	.init		=	tcf_vlan_init,
 	.cleanup	=	tcf_vlan_cleanup,
 	.walk		=	tcf_vlan_walker,
+	.get_fill_size	=	tcf_vlan_get_fill_size,
 	.lookup		=	tcf_vlan_search,
 	.size		=	sizeof(struct tcf_vlan),
 };
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index 638c1bc1ea1b..efd3cfb80a2a 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -684,13 +684,15 @@ static void tc_indr_block_ing_cmd(struct tc_indr_block_dev *indr_dev,
 		.command	= command,
 		.binder_type	= FLOW_BLOCK_BINDER_TYPE_CLSACT_INGRESS,
 		.net		= dev_net(indr_dev->dev),
-		.block_shared	= tcf_block_shared(indr_dev->block),
+		.block_shared	= tcf_block_non_null_shared(indr_dev->block),
 	};
 	INIT_LIST_HEAD(&bo.cb_list);
 
 	if (!indr_dev->block)
 		return;
 
+	bo.block = &indr_dev->block->flow_block;
+
 	indr_block_cb->cb(indr_dev->dev, indr_block_cb->cb_priv, TC_SETUP_BLOCK,
 			  &bo);
 	tcf_block_setup(indr_dev->block, &bo);
@@ -775,6 +777,7 @@ static void tc_indr_block_call(struct tcf_block *block, struct net_device *dev,
 		.command	= command,
 		.binder_type	= ei->binder_type,
 		.net		= dev_net(dev),
+		.block		= &block->flow_block,
 		.block_shared	= tcf_block_shared(block),
 		.extack		= extack,
 	};
@@ -810,6 +813,7 @@ static int tcf_block_offload_cmd(struct tcf_block *block,
 	bo.net = dev_net(dev);
 	bo.command = command;
 	bo.binder_type = ei->binder_type;
+	bo.block = &block->flow_block;
 	bo.block_shared = tcf_block_shared(block);
 	bo.extack = extack;
 	INIT_LIST_HEAD(&bo.cb_list);
@@ -987,8 +991,8 @@ static struct tcf_block *tcf_block_create(struct net *net, struct Qdisc *q,
 		return ERR_PTR(-ENOMEM);
 	}
 	mutex_init(&block->lock);
+	flow_block_init(&block->flow_block);
 	INIT_LIST_HEAD(&block->chain_list);
-	INIT_LIST_HEAD(&block->cb_list);
 	INIT_LIST_HEAD(&block->owner_list);
 	INIT_LIST_HEAD(&block->chain0.filter_chain_list);
 
@@ -1514,7 +1518,7 @@ void tcf_block_put(struct tcf_block *block)
 EXPORT_SYMBOL(tcf_block_put);
 
 static int
-tcf_block_playback_offloads(struct tcf_block *block, tc_setup_cb_t *cb,
+tcf_block_playback_offloads(struct tcf_block *block, flow_setup_cb_t *cb,
 			    void *cb_priv, bool add, bool offload_in_use,
 			    struct netlink_ext_ack *extack)
 {
@@ -1570,7 +1574,7 @@ static int tcf_block_bind(struct tcf_block *block,
 
 		i++;
 	}
-	list_splice(&bo->cb_list, &block->cb_list);
+	list_splice(&bo->cb_list, &block->flow_block.cb_list);
 
 	return 0;
 
@@ -2152,6 +2156,9 @@ replay:
 		tfilter_notify(net, skb, n, tp, block, q, parent, fh,
 			       RTM_NEWTFILTER, false, rtnl_held);
 		tfilter_put(tp, fh);
+		/* q pointer is NULL for shared blocks */
+		if (q)
+			q->flags &= ~TCQ_F_CAN_BYPASS;
 	}
 
 errout:
@@ -3155,7 +3162,7 @@ int tc_setup_cb_call(struct tcf_block *block, enum tc_setup_type type,
 	if (block->nooffloaddevcnt && err_stop)
 		return -EOPNOTSUPP;
 
-	list_for_each_entry(block_cb, &block->cb_list, list) {
+	list_for_each_entry(block_cb, &block->flow_block.cb_list, list) {
 		err = block_cb->cb(type, type_data, block_cb->cb_priv);
 		if (err) {
 			if (err_stop)
diff --git a/net/sched/cls_bpf.c b/net/sched/cls_bpf.c
index 691f71830134..3f7a9c02b70c 100644
--- a/net/sched/cls_bpf.c
+++ b/net/sched/cls_bpf.c
@@ -651,7 +651,7 @@ skip:
 	}
 }
 
-static int cls_bpf_reoffload(struct tcf_proto *tp, bool add, tc_setup_cb_t *cb,
+static int cls_bpf_reoffload(struct tcf_proto *tp, bool add, flow_setup_cb_t *cb,
 			     void *cb_priv, struct netlink_ext_ack *extack)
 {
 	struct cls_bpf_head *head = rtnl_dereference(tp->root);
diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c
index 38d6e85693fc..054123742e32 100644
--- a/net/sched/cls_flower.c
+++ b/net/sched/cls_flower.c
@@ -1800,7 +1800,7 @@ fl_get_next_hw_filter(struct tcf_proto *tp, struct cls_fl_filter *f, bool add)
 	return NULL;
 }
 
-static int fl_reoffload(struct tcf_proto *tp, bool add, tc_setup_cb_t *cb,
+static int fl_reoffload(struct tcf_proto *tp, bool add, flow_setup_cb_t *cb,
 			void *cb_priv, struct netlink_ext_ack *extack)
 {
 	struct tcf_block *block = tp->chain->block;
diff --git a/net/sched/cls_matchall.c b/net/sched/cls_matchall.c
index a30d2f8feb32..455ea2793f9b 100644
--- a/net/sched/cls_matchall.c
+++ b/net/sched/cls_matchall.c
@@ -282,7 +282,7 @@ skip:
 	arg->count++;
 }
 
-static int mall_reoffload(struct tcf_proto *tp, bool add, tc_setup_cb_t *cb,
+static int mall_reoffload(struct tcf_proto *tp, bool add, flow_setup_cb_t *cb,
 			  void *cb_priv, struct netlink_ext_ack *extack)
 {
 	struct cls_mall_head *head = rtnl_dereference(tp->root);
diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c
index be9e46c77e8b..8614088edd1b 100644
--- a/net/sched/cls_u32.c
+++ b/net/sched/cls_u32.c
@@ -1152,7 +1152,7 @@ static void u32_walk(struct tcf_proto *tp, struct tcf_walker *arg,
 }
 
 static int u32_reoffload_hnode(struct tcf_proto *tp, struct tc_u_hnode *ht,
-			       bool add, tc_setup_cb_t *cb, void *cb_priv,
+			       bool add, flow_setup_cb_t *cb, void *cb_priv,
 			       struct netlink_ext_ack *extack)
 {
 	struct tc_cls_u32_offload cls_u32 = {};
@@ -1172,7 +1172,7 @@ static int u32_reoffload_hnode(struct tcf_proto *tp, struct tc_u_hnode *ht,
 }
 
 static int u32_reoffload_knode(struct tcf_proto *tp, struct tc_u_knode *n,
-			       bool add, tc_setup_cb_t *cb, void *cb_priv,
+			       bool add, flow_setup_cb_t *cb, void *cb_priv,
 			       struct netlink_ext_ack *extack)
 {
 	struct tc_u_hnode *ht = rtnl_dereference(n->ht_down);
@@ -1213,7 +1213,7 @@ static int u32_reoffload_knode(struct tcf_proto *tp, struct tc_u_knode *n,
 	return 0;
 }
 
-static int u32_reoffload(struct tcf_proto *tp, bool add, tc_setup_cb_t *cb,
+static int u32_reoffload(struct tcf_proto *tp, bool add, flow_setup_cb_t *cb,
 			 void *cb_priv, struct netlink_ext_ack *extack)
 {
 	struct tc_u_common *tp_c = tp->data;
diff --git a/net/sched/sch_codel.c b/net/sched/sch_codel.c
index 25ef172c23df..30169b3adbbb 100644
--- a/net/sched/sch_codel.c
+++ b/net/sched/sch_codel.c
@@ -71,10 +71,10 @@ static struct sk_buff *dequeue_func(struct codel_vars *vars, void *ctx)
 	struct Qdisc *sch = ctx;
 	struct sk_buff *skb = __qdisc_dequeue_head(&sch->q);
 
-	if (skb)
+	if (skb) {
 		sch->qstats.backlog -= qdisc_pkt_len(skb);
-
-	prefetch(&skb->end); /* we'll need skb_shinfo() */
+		prefetch(&skb->end); /* we'll need skb_shinfo() */
+	}
 	return skb;
 }
 
diff --git a/net/sched/sch_fq_codel.c b/net/sched/sch_fq_codel.c
index e2faf33d282b..d59fbcc745d1 100644
--- a/net/sched/sch_fq_codel.c
+++ b/net/sched/sch_fq_codel.c
@@ -596,8 +596,6 @@ static unsigned long fq_codel_find(struct Qdisc *sch, u32 classid)
 static unsigned long fq_codel_bind(struct Qdisc *sch, unsigned long parent,
 			      u32 classid)
 {
-	/* we cannot bypass queue discipline anymore */
-	sch->flags &= ~TCQ_F_CAN_BYPASS;
 	return 0;
 }
 
diff --git a/net/sched/sch_sfq.c b/net/sched/sch_sfq.c
index 420bd8411677..68404a9d2ce4 100644
--- a/net/sched/sch_sfq.c
+++ b/net/sched/sch_sfq.c
@@ -824,8 +824,6 @@ static unsigned long sfq_find(struct Qdisc *sch, u32 classid)
 static unsigned long sfq_bind(struct Qdisc *sch, unsigned long parent,
 			      u32 classid)
 {
-	/* we cannot bypass queue discipline anymore */
-	sch->flags &= ~TCQ_F_CAN_BYPASS;
 	return 0;
 }
 
diff --git a/net/sched/sch_taprio.c b/net/sched/sch_taprio.c
index 388750ddc57a..e25d414ae12f 100644
--- a/net/sched/sch_taprio.c
+++ b/net/sched/sch_taprio.c
@@ -75,7 +75,7 @@ struct taprio_sched {
 	struct sched_gate_list __rcu *admin_sched;
 	struct hrtimer advance_timer;
 	struct list_head taprio_list;
-	int txtime_delay;
+	u32 txtime_delay;
 };
 
 static ktime_t sched_base_time(const struct sched_gate_list *sched)
@@ -1113,7 +1113,7 @@ static int taprio_change(struct Qdisc *sch, struct nlattr *opt,
 			goto unlock;
 		}
 
-		q->txtime_delay = nla_get_s32(tb[TCA_TAPRIO_ATTR_TXTIME_DELAY]);
+		q->txtime_delay = nla_get_u32(tb[TCA_TAPRIO_ATTR_TXTIME_DELAY]);
 	}
 
 	if (!TXTIME_ASSIST_IS_ENABLED(taprio_flags) &&
@@ -1195,7 +1195,8 @@ unlock:
 	spin_unlock_bh(qdisc_lock(sch));
 
 free_sched:
-	kfree(new_admin);
+	if (new_admin)
+		call_rcu(&new_admin->rcu, taprio_free_sched_cb);
 
 	return err;
 }
@@ -1430,7 +1431,7 @@ static int taprio_dump(struct Qdisc *sch, struct sk_buff *skb)
 		goto options_error;
 
 	if (q->txtime_delay &&
-	    nla_put_s32(skb, TCA_TAPRIO_ATTR_TXTIME_DELAY, q->txtime_delay))
+	    nla_put_u32(skb, TCA_TAPRIO_ATTR_TXTIME_DELAY, q->txtime_delay))
 		goto options_error;
 
 	if (oper && dump_schedule(skb, oper))
diff --git a/net/sctp/sm_make_chunk.c b/net/sctp/sm_make_chunk.c
index ed39396b9bba..36bd8a6e82df 100644
--- a/net/sctp/sm_make_chunk.c
+++ b/net/sctp/sm_make_chunk.c
@@ -2582,8 +2582,7 @@ do_addr_param:
 	case SCTP_PARAM_STATE_COOKIE:
 		asoc->peer.cookie_len =
 			ntohs(param.p->length) - sizeof(struct sctp_paramhdr);
-		if (asoc->peer.cookie)
-			kfree(asoc->peer.cookie);
+		kfree(asoc->peer.cookie);
 		asoc->peer.cookie = kmemdup(param.cookie->body, asoc->peer.cookie_len, gfp);
 		if (!asoc->peer.cookie)
 			retval = 0;
@@ -2648,8 +2647,7 @@ do_addr_param:
 			goto fall_through;
 
 		/* Save peer's random parameter */
-		if (asoc->peer.peer_random)
-			kfree(asoc->peer.peer_random);
+		kfree(asoc->peer.peer_random);
 		asoc->peer.peer_random = kmemdup(param.p,
 					    ntohs(param.p->length), gfp);
 		if (!asoc->peer.peer_random) {
@@ -2663,8 +2661,7 @@ do_addr_param:
 			goto fall_through;
 
 		/* Save peer's HMAC list */
-		if (asoc->peer.peer_hmacs)
-			kfree(asoc->peer.peer_hmacs);
+		kfree(asoc->peer.peer_hmacs);
 		asoc->peer.peer_hmacs = kmemdup(param.p,
 					    ntohs(param.p->length), gfp);
 		if (!asoc->peer.peer_hmacs) {
@@ -2680,8 +2677,7 @@ do_addr_param:
 		if (!ep->auth_enable)
 			goto fall_through;
 
-		if (asoc->peer.peer_chunks)
-			kfree(asoc->peer.peer_chunks);
+		kfree(asoc->peer.peer_chunks);
 		asoc->peer.peer_chunks = kmemdup(param.p,
 					    ntohs(param.p->length), gfp);
 		if (!asoc->peer.peer_chunks)
diff --git a/net/sctp/sm_sideeffect.c b/net/sctp/sm_sideeffect.c
index a554d6d15d1b..1cf5bb5b73c4 100644
--- a/net/sctp/sm_sideeffect.c
+++ b/net/sctp/sm_sideeffect.c
@@ -546,7 +546,7 @@ static void sctp_do_8_2_transport_strike(struct sctp_cmd_seq *commands,
 	 */
 	if (net->sctp.pf_enable &&
 	   (transport->state == SCTP_ACTIVE) &&
-	   (asoc->pf_retrans < transport->pathmaxrxt) &&
+	   (transport->error_count < transport->pathmaxrxt) &&
 	   (transport->error_count > asoc->pf_retrans)) {
 
 		sctp_assoc_control_transport(asoc, transport,
diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index aa80cda36581..9d1f83b10c0a 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -985,7 +985,7 @@ static int sctp_setsockopt_bindx(struct sock *sk,
 		return -EINVAL;
 
 	kaddrs = memdup_user(addrs, addrs_size);
-	if (unlikely(IS_ERR(kaddrs)))
+	if (IS_ERR(kaddrs))
 		return PTR_ERR(kaddrs);
 
 	/* Walk through the addrs buffer and count the number of addresses. */
@@ -1315,7 +1315,7 @@ static int __sctp_setsockopt_connectx(struct sock *sk,
 		return -EINVAL;
 
 	kaddrs = memdup_user(addrs, addrs_size);
-	if (unlikely(IS_ERR(kaddrs)))
+	if (IS_ERR(kaddrs))
 		return PTR_ERR(kaddrs);
 
 	/* Allow security module to validate connectx addresses. */
diff --git a/net/sctp/stream.c b/net/sctp/stream.c
index 25946604af85..e83cdaa2ab76 100644
--- a/net/sctp/stream.c
+++ b/net/sctp/stream.c
@@ -316,6 +316,7 @@ int sctp_send_reset_streams(struct sctp_association *asoc,
 		nstr_list[i] = htons(str_list[i]);
 
 	if (out && !sctp_stream_outq_is_empty(stream, str_nums, nstr_list)) {
+		kfree(nstr_list);
 		retval = -EAGAIN;
 		goto out;
 	}
diff --git a/net/sctp/sysctl.c b/net/sctp/sysctl.c
index 9a19147902f1..1250751bca1b 100644
--- a/net/sctp/sysctl.c
+++ b/net/sctp/sysctl.c
@@ -25,10 +25,7 @@
 #include <net/sctp/sctp.h>
 #include <linux/sysctl.h>
 
-static int zero = 0;
-static int one = 1;
 static int timer_max = 86400000; /* ms in one day */
-static int int_max = INT_MAX;
 static int sack_timer_min = 1;
 static int sack_timer_max = 500;
 static int addr_scope_max = SCTP_SCOPE_POLICY_MAX;
@@ -92,7 +89,7 @@ static struct ctl_table sctp_net_table[] = {
 		.maxlen		= sizeof(unsigned int),
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec_minmax,
-		.extra1         = &one,
+		.extra1         = SYSCTL_ONE,
 		.extra2         = &timer_max
 	},
 	{
@@ -101,7 +98,7 @@ static struct ctl_table sctp_net_table[] = {
 		.maxlen		= sizeof(unsigned int),
 		.mode		= 0644,
 		.proc_handler	= proc_sctp_do_rto_min,
-		.extra1         = &one,
+		.extra1         = SYSCTL_ONE,
 		.extra2         = &init_net.sctp.rto_max
 	},
 	{
@@ -137,8 +134,8 @@ static struct ctl_table sctp_net_table[] = {
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec_minmax,
-		.extra1		= &zero,
-		.extra2		= &int_max
+		.extra1		= SYSCTL_ZERO,
+		.extra2		= SYSCTL_INT_MAX,
 	},
 	{
 		.procname	= "cookie_preserve_enable",
@@ -160,7 +157,7 @@ static struct ctl_table sctp_net_table[] = {
 		.maxlen		= sizeof(unsigned int),
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec_minmax,
-		.extra1         = &one,
+		.extra1         = SYSCTL_ONE,
 		.extra2         = &timer_max
 	},
 	{
@@ -178,7 +175,7 @@ static struct ctl_table sctp_net_table[] = {
 		.maxlen		= sizeof(unsigned int),
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec_minmax,
-		.extra1         = &one,
+		.extra1         = SYSCTL_ONE,
 		.extra2         = &timer_max
 	},
 	{
@@ -187,8 +184,8 @@ static struct ctl_table sctp_net_table[] = {
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec_minmax,
-		.extra1		= &one,
-		.extra2		= &int_max
+		.extra1		= SYSCTL_ONE,
+		.extra2		= SYSCTL_INT_MAX,
 	},
 	{
 		.procname	= "path_max_retrans",
@@ -196,8 +193,8 @@ static struct ctl_table sctp_net_table[] = {
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec_minmax,
-		.extra1		= &one,
-		.extra2		= &int_max
+		.extra1		= SYSCTL_ONE,
+		.extra2		= SYSCTL_INT_MAX,
 	},
 	{
 		.procname	= "max_init_retransmits",
@@ -205,8 +202,8 @@ static struct ctl_table sctp_net_table[] = {
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec_minmax,
-		.extra1		= &one,
-		.extra2		= &int_max
+		.extra1		= SYSCTL_ONE,
+		.extra2		= SYSCTL_INT_MAX,
 	},
 	{
 		.procname	= "pf_retrans",
@@ -214,8 +211,8 @@ static struct ctl_table sctp_net_table[] = {
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec_minmax,
-		.extra1		= &zero,
-		.extra2		= &int_max
+		.extra1		= SYSCTL_ZERO,
+		.extra2		= SYSCTL_INT_MAX,
 	},
 	{
 		.procname	= "sndbuf_policy",
@@ -286,7 +283,7 @@ static struct ctl_table sctp_net_table[] = {
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec_minmax,
-		.extra1		= &zero,
+		.extra1		= SYSCTL_ZERO,
 		.extra2		= &addr_scope_max,
 	},
 	{
@@ -295,7 +292,7 @@ static struct ctl_table sctp_net_table[] = {
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
 		.proc_handler	= &proc_dointvec_minmax,
-		.extra1		= &one,
+		.extra1		= SYSCTL_ONE,
 		.extra2		= &rwnd_scale_max,
 	},
 	{
diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c
index 302e355f2ebc..5b932583e407 100644
--- a/net/smc/af_smc.c
+++ b/net/smc/af_smc.c
@@ -263,7 +263,7 @@ static int smc_bind(struct socket *sock, struct sockaddr *uaddr,
 
 	/* Check if socket is already active */
 	rc = -EINVAL;
-	if (sk->sk_state != SMC_INIT)
+	if (sk->sk_state != SMC_INIT || smc->connect_nonblock)
 		goto out_rel;
 
 	smc->clcsock->sk->sk_reuse = sk->sk_reuse;
@@ -1390,7 +1390,8 @@ static int smc_listen(struct socket *sock, int backlog)
 	lock_sock(sk);
 
 	rc = -EINVAL;
-	if ((sk->sk_state != SMC_INIT) && (sk->sk_state != SMC_LISTEN))
+	if ((sk->sk_state != SMC_INIT && sk->sk_state != SMC_LISTEN) ||
+	    smc->connect_nonblock)
 		goto out;
 
 	rc = 0;
@@ -1518,7 +1519,7 @@ static int smc_sendmsg(struct socket *sock, struct msghdr *msg, size_t len)
 		goto out;
 
 	if (msg->msg_flags & MSG_FASTOPEN) {
-		if (sk->sk_state == SMC_INIT) {
+		if (sk->sk_state == SMC_INIT && !smc->connect_nonblock) {
 			smc_switch_to_fallback(smc);
 			smc->fallback_rsn = SMC_CLC_DECL_OPTUNSUPP;
 		} else {
@@ -1732,14 +1733,18 @@ static int smc_setsockopt(struct socket *sock, int level, int optname,
 		}
 		break;
 	case TCP_NODELAY:
-		if (sk->sk_state != SMC_INIT && sk->sk_state != SMC_LISTEN) {
+		if (sk->sk_state != SMC_INIT &&
+		    sk->sk_state != SMC_LISTEN &&
+		    sk->sk_state != SMC_CLOSED) {
 			if (val && !smc->use_fallback)
 				mod_delayed_work(system_wq, &smc->conn.tx_work,
 						 0);
 		}
 		break;
 	case TCP_CORK:
-		if (sk->sk_state != SMC_INIT && sk->sk_state != SMC_LISTEN) {
+		if (sk->sk_state != SMC_INIT &&
+		    sk->sk_state != SMC_LISTEN &&
+		    sk->sk_state != SMC_CLOSED) {
 			if (!val && !smc->use_fallback)
 				mod_delayed_work(system_wq, &smc->conn.tx_work,
 						 0);
diff --git a/net/socket.c b/net/socket.c
index 16449d6daeca..6a9ab7a8b1d2 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -73,6 +73,7 @@
 #include <linux/module.h>
 #include <linux/highmem.h>
 #include <linux/mount.h>
+#include <linux/pseudo_fs.h>
 #include <linux/security.h>
 #include <linux/syscalls.h>
 #include <linux/compat.h>
@@ -338,19 +339,22 @@ static const struct xattr_handler *sockfs_xattr_handlers[] = {
 	NULL
 };
 
-static struct dentry *sockfs_mount(struct file_system_type *fs_type,
-			 int flags, const char *dev_name, void *data)
+static int sockfs_init_fs_context(struct fs_context *fc)
 {
-	return mount_pseudo_xattr(fs_type, "socket:", &sockfs_ops,
-				  sockfs_xattr_handlers,
-				  &sockfs_dentry_operations, SOCKFS_MAGIC);
+	struct pseudo_fs_context *ctx = init_pseudo(fc, SOCKFS_MAGIC);
+	if (!ctx)
+		return -ENOMEM;
+	ctx->ops = &sockfs_ops;
+	ctx->dops = &sockfs_dentry_operations;
+	ctx->xattr = sockfs_xattr_handlers;
+	return 0;
 }
 
 static struct vfsmount *sock_mnt __read_mostly;
 
 static struct file_system_type sock_fs_type = {
 	.name =		"sockfs",
-	.mount =	sockfs_mount,
+	.init_fs_context = sockfs_init_fs_context,
 	.kill_sb =	kill_anon_super,
 };
 
@@ -2222,9 +2226,10 @@ static int copy_msghdr_from_user(struct msghdr *kmsg,
 
 	kmsg->msg_iocb = NULL;
 
-	return import_iovec(save_addr ? READ : WRITE,
+	err = import_iovec(save_addr ? READ : WRITE,
 			    msg.msg_iov, msg.msg_iovlen,
 			    UIO_FASTIOV, iov, &kmsg->msg_iter);
+	return err < 0 ? err : 0;
 }
 
 static int ___sys_sendmsg(struct socket *sock, struct user_msghdr __user *msg,
@@ -2326,6 +2331,13 @@ out_freeiov:
 /*
  *	BSD sendmsg interface
  */
+long __sys_sendmsg_sock(struct socket *sock, struct user_msghdr __user *msg,
+			unsigned int flags)
+{
+	struct msghdr msg_sys;
+
+	return ___sys_sendmsg(sock, msg, &msg_sys, flags, NULL, 0);
+}
 
 long __sys_sendmsg(int fd, struct user_msghdr __user *msg, unsigned int flags,
 		   bool forbid_cmsg_compat)
@@ -2500,6 +2512,14 @@ out_freeiov:
  *	BSD recvmsg interface
  */
 
+long __sys_recvmsg_sock(struct socket *sock, struct user_msghdr __user *msg,
+			unsigned int flags)
+{
+	struct msghdr msg_sys;
+
+	return ___sys_recvmsg(sock, msg, &msg_sys, flags, 0);
+}
+
 long __sys_recvmsg(int fd, struct user_msghdr __user *msg, unsigned int flags,
 		   bool forbid_cmsg_compat)
 {
diff --git a/net/sunrpc/Kconfig b/net/sunrpc/Kconfig
index aa307505ca54..3bcf985507be 100644
--- a/net/sunrpc/Kconfig
+++ b/net/sunrpc/Kconfig
@@ -35,7 +35,7 @@ config RPCSEC_GSS_KRB5
 
 	  If unsure, say Y.
 
-config CONFIG_SUNRPC_DISABLE_INSECURE_ENCTYPES
+config SUNRPC_DISABLE_INSECURE_ENCTYPES
 	bool "Secure RPC: Disable insecure Kerberos encryption types"
 	depends on RPCSEC_GSS_KRB5
 	default n
diff --git a/net/sunrpc/backchannel_rqst.c b/net/sunrpc/backchannel_rqst.c
index c47d82622fd1..339e8c077c2d 100644
--- a/net/sunrpc/backchannel_rqst.c
+++ b/net/sunrpc/backchannel_rqst.c
@@ -31,25 +31,20 @@ SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
 #define RPCDBG_FACILITY	RPCDBG_TRANS
 #endif
 
+#define BC_MAX_SLOTS	64U
+
+unsigned int xprt_bc_max_slots(struct rpc_xprt *xprt)
+{
+	return BC_MAX_SLOTS;
+}
+
 /*
  * Helper routines that track the number of preallocation elements
  * on the transport.
  */
 static inline int xprt_need_to_requeue(struct rpc_xprt *xprt)
 {
-	return xprt->bc_alloc_count < atomic_read(&xprt->bc_free_slots);
-}
-
-static inline void xprt_inc_alloc_count(struct rpc_xprt *xprt, unsigned int n)
-{
-	atomic_add(n, &xprt->bc_free_slots);
-	xprt->bc_alloc_count += n;
-}
-
-static inline int xprt_dec_alloc_count(struct rpc_xprt *xprt, unsigned int n)
-{
-	atomic_sub(n, &xprt->bc_free_slots);
-	return xprt->bc_alloc_count -= n;
+	return xprt->bc_alloc_count < xprt->bc_alloc_max;
 }
 
 /*
@@ -145,6 +140,9 @@ int xprt_setup_bc(struct rpc_xprt *xprt, unsigned int min_reqs)
 
 	dprintk("RPC:       setup backchannel transport\n");
 
+	if (min_reqs > BC_MAX_SLOTS)
+		min_reqs = BC_MAX_SLOTS;
+
 	/*
 	 * We use a temporary list to keep track of the preallocated
 	 * buffers.  Once we're done building the list we splice it
@@ -172,7 +170,9 @@ int xprt_setup_bc(struct rpc_xprt *xprt, unsigned int min_reqs)
 	 */
 	spin_lock(&xprt->bc_pa_lock);
 	list_splice(&tmp_list, &xprt->bc_pa_list);
-	xprt_inc_alloc_count(xprt, min_reqs);
+	xprt->bc_alloc_count += min_reqs;
+	xprt->bc_alloc_max += min_reqs;
+	atomic_add(min_reqs, &xprt->bc_slot_count);
 	spin_unlock(&xprt->bc_pa_lock);
 
 	dprintk("RPC:       setup backchannel transport done\n");
@@ -220,11 +220,13 @@ void xprt_destroy_bc(struct rpc_xprt *xprt, unsigned int max_reqs)
 		goto out;
 
 	spin_lock_bh(&xprt->bc_pa_lock);
-	xprt_dec_alloc_count(xprt, max_reqs);
+	xprt->bc_alloc_max -= max_reqs;
 	list_for_each_entry_safe(req, tmp, &xprt->bc_pa_list, rq_bc_pa_list) {
 		dprintk("RPC:        req=%p\n", req);
 		list_del(&req->rq_bc_pa_list);
 		xprt_free_allocation(req);
+		xprt->bc_alloc_count--;
+		atomic_dec(&xprt->bc_slot_count);
 		if (--max_reqs == 0)
 			break;
 	}
@@ -241,13 +243,14 @@ static struct rpc_rqst *xprt_get_bc_request(struct rpc_xprt *xprt, __be32 xid,
 	struct rpc_rqst *req = NULL;
 
 	dprintk("RPC:       allocate a backchannel request\n");
-	if (atomic_read(&xprt->bc_free_slots) <= 0)
-		goto not_found;
 	if (list_empty(&xprt->bc_pa_list)) {
 		if (!new)
 			goto not_found;
+		if (atomic_read(&xprt->bc_slot_count) >= BC_MAX_SLOTS)
+			goto not_found;
 		list_add_tail(&new->rq_bc_pa_list, &xprt->bc_pa_list);
 		xprt->bc_alloc_count++;
+		atomic_inc(&xprt->bc_slot_count);
 	}
 	req = list_first_entry(&xprt->bc_pa_list, struct rpc_rqst,
 				rq_bc_pa_list);
@@ -291,6 +294,7 @@ void xprt_free_bc_rqst(struct rpc_rqst *req)
 	if (xprt_need_to_requeue(xprt)) {
 		list_add_tail(&req->rq_bc_pa_list, &xprt->bc_pa_list);
 		xprt->bc_alloc_count++;
+		atomic_inc(&xprt->bc_slot_count);
 		req = NULL;
 	}
 	spin_unlock_bh(&xprt->bc_pa_lock);
@@ -357,7 +361,7 @@ void xprt_complete_bc_request(struct rpc_rqst *req, uint32_t copied)
 
 	spin_lock(&xprt->bc_pa_lock);
 	list_del(&req->rq_bc_pa_list);
-	xprt_dec_alloc_count(xprt, 1);
+	xprt->bc_alloc_count--;
 	spin_unlock(&xprt->bc_pa_lock);
 
 	req->rq_private_buf.len = copied;
diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c
index b03bfa055c08..d8679b6027e9 100644
--- a/net/sunrpc/clnt.c
+++ b/net/sunrpc/clnt.c
@@ -528,6 +528,8 @@ struct rpc_clnt *rpc_create(struct rpc_create_args *args)
 		.bc_xprt = args->bc_xprt,
 	};
 	char servername[48];
+	struct rpc_clnt *clnt;
+	int i;
 
 	if (args->bc_xprt) {
 		WARN_ON_ONCE(!(args->protocol & XPRT_TRANSPORT_BC));
@@ -590,7 +592,15 @@ struct rpc_clnt *rpc_create(struct rpc_create_args *args)
 	if (args->flags & RPC_CLNT_CREATE_NONPRIVPORT)
 		xprt->resvport = 0;
 
-	return rpc_create_xprt(args, xprt);
+	clnt = rpc_create_xprt(args, xprt);
+	if (IS_ERR(clnt) || args->nconnect <= 1)
+		return clnt;
+
+	for (i = 0; i < args->nconnect - 1; i++) {
+		if (rpc_clnt_add_xprt(clnt, &xprtargs, NULL, NULL) < 0)
+			break;
+	}
+	return clnt;
 }
 EXPORT_SYMBOL_GPL(rpc_create);
 
@@ -968,13 +978,46 @@ out:
 }
 EXPORT_SYMBOL_GPL(rpc_bind_new_program);
 
+struct rpc_xprt *
+rpc_task_get_xprt(struct rpc_clnt *clnt, struct rpc_xprt *xprt)
+{
+	struct rpc_xprt_switch *xps;
+
+	if (!xprt)
+		return NULL;
+	rcu_read_lock();
+	xps = rcu_dereference(clnt->cl_xpi.xpi_xpswitch);
+	atomic_long_inc(&xps->xps_queuelen);
+	rcu_read_unlock();
+	atomic_long_inc(&xprt->queuelen);
+
+	return xprt;
+}
+
+static void
+rpc_task_release_xprt(struct rpc_clnt *clnt, struct rpc_xprt *xprt)
+{
+	struct rpc_xprt_switch *xps;
+
+	atomic_long_dec(&xprt->queuelen);
+	rcu_read_lock();
+	xps = rcu_dereference(clnt->cl_xpi.xpi_xpswitch);
+	atomic_long_dec(&xps->xps_queuelen);
+	rcu_read_unlock();
+
+	xprt_put(xprt);
+}
+
 void rpc_task_release_transport(struct rpc_task *task)
 {
 	struct rpc_xprt *xprt = task->tk_xprt;
 
 	if (xprt) {
 		task->tk_xprt = NULL;
-		xprt_put(xprt);
+		if (task->tk_client)
+			rpc_task_release_xprt(task->tk_client, xprt);
+		else
+			xprt_put(xprt);
 	}
 }
 EXPORT_SYMBOL_GPL(rpc_task_release_transport);
@@ -983,6 +1026,7 @@ void rpc_task_release_client(struct rpc_task *task)
 {
 	struct rpc_clnt *clnt = task->tk_client;
 
+	rpc_task_release_transport(task);
 	if (clnt != NULL) {
 		/* Remove from client task list */
 		spin_lock(&clnt->cl_lock);
@@ -992,14 +1036,34 @@ void rpc_task_release_client(struct rpc_task *task)
 
 		rpc_release_client(clnt);
 	}
-	rpc_task_release_transport(task);
+}
+
+static struct rpc_xprt *
+rpc_task_get_first_xprt(struct rpc_clnt *clnt)
+{
+	struct rpc_xprt *xprt;
+
+	rcu_read_lock();
+	xprt = xprt_get(rcu_dereference(clnt->cl_xprt));
+	rcu_read_unlock();
+	return rpc_task_get_xprt(clnt, xprt);
+}
+
+static struct rpc_xprt *
+rpc_task_get_next_xprt(struct rpc_clnt *clnt)
+{
+	return rpc_task_get_xprt(clnt, xprt_iter_get_next(&clnt->cl_xpi));
 }
 
 static
 void rpc_task_set_transport(struct rpc_task *task, struct rpc_clnt *clnt)
 {
-	if (!task->tk_xprt)
-		task->tk_xprt = xprt_iter_get_next(&clnt->cl_xpi);
+	if (task->tk_xprt)
+		return;
+	if (task->tk_flags & RPC_TASK_NO_ROUND_ROBIN)
+		task->tk_xprt = rpc_task_get_first_xprt(clnt);
+	else
+		task->tk_xprt = rpc_task_get_next_xprt(clnt);
 }
 
 static
@@ -1462,6 +1526,19 @@ size_t rpc_max_bc_payload(struct rpc_clnt *clnt)
 }
 EXPORT_SYMBOL_GPL(rpc_max_bc_payload);
 
+unsigned int rpc_num_bc_slots(struct rpc_clnt *clnt)
+{
+	struct rpc_xprt *xprt;
+	unsigned int ret;
+
+	rcu_read_lock();
+	xprt = rcu_dereference(clnt->cl_xprt);
+	ret = xprt->ops->bc_num_slots(xprt);
+	rcu_read_unlock();
+	return ret;
+}
+EXPORT_SYMBOL_GPL(rpc_num_bc_slots);
+
 /**
  * rpc_force_rebind - force transport to check that remote port is unchanged
  * @clnt: client to rebind
@@ -1788,6 +1865,7 @@ rpc_xdr_encode(struct rpc_task *task)
 	req->rq_snd_buf.head[0].iov_len = 0;
 	xdr_init_encode(&xdr, &req->rq_snd_buf,
 			req->rq_snd_buf.head[0].iov_base, req);
+	xdr_free_bvec(&req->rq_snd_buf);
 	if (rpc_encode_header(task, &xdr))
 		return;
 
@@ -1827,8 +1905,6 @@ call_encode(struct rpc_task *task)
 			rpc_call_rpcerror(task, task->tk_status);
 		}
 		return;
-	} else {
-		xprt_request_prepare(task->tk_rqstp);
 	}
 
 	/* Add task to reply queue before transmission to avoid races */
@@ -2696,6 +2772,10 @@ int rpc_clnt_test_and_add_xprt(struct rpc_clnt *clnt,
 		return -ENOMEM;
 	data->xps = xprt_switch_get(xps);
 	data->xprt = xprt_get(xprt);
+	if (rpc_xprt_switch_has_addr(data->xps, (struct sockaddr *)&xprt->addr)) {
+		rpc_cb_add_xprt_release(data);
+		goto success;
+	}
 
 	task = rpc_call_null_helper(clnt, xprt, NULL,
 			RPC_TASK_SOFT|RPC_TASK_SOFTCONN|RPC_TASK_ASYNC|RPC_TASK_NULLCREDS,
@@ -2703,6 +2783,7 @@ int rpc_clnt_test_and_add_xprt(struct rpc_clnt *clnt,
 	if (IS_ERR(task))
 		return PTR_ERR(task);
 	rpc_put_task(task);
+success:
 	return 1;
 }
 EXPORT_SYMBOL_GPL(rpc_clnt_test_and_add_xprt);
diff --git a/net/sunrpc/debugfs.c b/net/sunrpc/debugfs.c
index 95ebd76b132d..fd9bca242724 100644
--- a/net/sunrpc/debugfs.c
+++ b/net/sunrpc/debugfs.c
@@ -1,5 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0
-/**
+/*
  * debugfs interface for sunrpc
  *
  * (c) 2014 Jeff Layton <jlayton@primarydata.com>
@@ -11,7 +11,6 @@
 #include "netns.h"
 
 static struct dentry *topdir;
-static struct dentry *rpc_fault_dir;
 static struct dentry *rpc_clnt_dir;
 static struct dentry *rpc_xprt_dir;
 
@@ -118,16 +117,37 @@ static const struct file_operations tasks_fops = {
 	.release	= tasks_release,
 };
 
-void
-rpc_clnt_debugfs_register(struct rpc_clnt *clnt)
+static int do_xprt_debugfs(struct rpc_clnt *clnt, struct rpc_xprt *xprt, void *numv)
 {
 	int len;
 	char name[24]; /* enough for "../../rpc_xprt/ + 8 hex digits + NULL */
-	struct rpc_xprt *xprt;
+	char link[9]; /* enough for 8 hex digits + NULL */
+	int *nump = numv;
 
-	/* Already registered? */
-	if (clnt->cl_debugfs || !rpc_clnt_dir)
-		return;
+	if (IS_ERR_OR_NULL(xprt->debugfs))
+		return 0;
+	len = snprintf(name, sizeof(name), "../../rpc_xprt/%s",
+		       xprt->debugfs->d_name.name);
+	if (len > sizeof(name))
+		return -1;
+	if (*nump == 0)
+		strcpy(link, "xprt");
+	else {
+		len = snprintf(link, sizeof(link), "xprt%d", *nump);
+		if (len > sizeof(link))
+			return -1;
+	}
+	debugfs_create_symlink(link, clnt->cl_debugfs, name);
+	(*nump)++;
+	return 0;
+}
+
+void
+rpc_clnt_debugfs_register(struct rpc_clnt *clnt)
+{
+	int len;
+	char name[9]; /* enough for 8 hex digits + NULL */
+	int xprtnum = 0;
 
 	len = snprintf(name, sizeof(name), "%x", clnt->cl_clid);
 	if (len >= sizeof(name))
@@ -135,35 +155,12 @@ rpc_clnt_debugfs_register(struct rpc_clnt *clnt)
 
 	/* make the per-client dir */
 	clnt->cl_debugfs = debugfs_create_dir(name, rpc_clnt_dir);
-	if (!clnt->cl_debugfs)
-		return;
 
 	/* make tasks file */
-	if (!debugfs_create_file("tasks", S_IFREG | 0400, clnt->cl_debugfs,
-				 clnt, &tasks_fops))
-		goto out_err;
-
-	rcu_read_lock();
-	xprt = rcu_dereference(clnt->cl_xprt);
-	/* no "debugfs" dentry? Don't bother with the symlink. */
-	if (IS_ERR_OR_NULL(xprt->debugfs)) {
-		rcu_read_unlock();
-		return;
-	}
-	len = snprintf(name, sizeof(name), "../../rpc_xprt/%s",
-			xprt->debugfs->d_name.name);
-	rcu_read_unlock();
-
-	if (len >= sizeof(name))
-		goto out_err;
+	debugfs_create_file("tasks", S_IFREG | 0400, clnt->cl_debugfs, clnt,
+			    &tasks_fops);
 
-	if (!debugfs_create_symlink("xprt", clnt->cl_debugfs, name))
-		goto out_err;
-
-	return;
-out_err:
-	debugfs_remove_recursive(clnt->cl_debugfs);
-	clnt->cl_debugfs = NULL;
+	rpc_clnt_iterate_for_each_xprt(clnt, do_xprt_debugfs, &xprtnum);
 }
 
 void
@@ -226,9 +223,6 @@ rpc_xprt_debugfs_register(struct rpc_xprt *xprt)
 	static atomic_t	cur_id;
 	char		name[9]; /* 8 hex digits + NULL term */
 
-	if (!rpc_xprt_dir)
-		return;
-
 	id = (unsigned int)atomic_inc_return(&cur_id);
 
 	len = snprintf(name, sizeof(name), "%x", id);
@@ -237,15 +231,10 @@ rpc_xprt_debugfs_register(struct rpc_xprt *xprt)
 
 	/* make the per-client dir */
 	xprt->debugfs = debugfs_create_dir(name, rpc_xprt_dir);
-	if (!xprt->debugfs)
-		return;
 
 	/* make tasks file */
-	if (!debugfs_create_file("info", S_IFREG | 0400, xprt->debugfs,
-				 xprt, &xprt_info_fops)) {
-		debugfs_remove_recursive(xprt->debugfs);
-		xprt->debugfs = NULL;
-	}
+	debugfs_create_file("info", S_IFREG | 0400, xprt->debugfs, xprt,
+			    &xprt_info_fops);
 
 	atomic_set(&xprt->inject_disconnect, rpc_inject_disconnect);
 }
@@ -308,28 +297,11 @@ static const struct file_operations fault_disconnect_fops = {
 	.release	= fault_release,
 };
 
-static struct dentry *
-inject_fault_dir(struct dentry *topdir)
-{
-	struct dentry *faultdir;
-
-	faultdir = debugfs_create_dir("inject_fault", topdir);
-	if (!faultdir)
-		return NULL;
-
-	if (!debugfs_create_file("disconnect", S_IFREG | 0400, faultdir,
-				 NULL, &fault_disconnect_fops))
-		return NULL;
-
-	return faultdir;
-}
-
 void __exit
 sunrpc_debugfs_exit(void)
 {
 	debugfs_remove_recursive(topdir);
 	topdir = NULL;
-	rpc_fault_dir = NULL;
 	rpc_clnt_dir = NULL;
 	rpc_xprt_dir = NULL;
 }
@@ -337,26 +309,16 @@ sunrpc_debugfs_exit(void)
 void __init
 sunrpc_debugfs_init(void)
 {
-	topdir = debugfs_create_dir("sunrpc", NULL);
-	if (!topdir)
-		return;
+	struct dentry *rpc_fault_dir;
 
-	rpc_fault_dir = inject_fault_dir(topdir);
-	if (!rpc_fault_dir)
-		goto out_remove;
+	topdir = debugfs_create_dir("sunrpc", NULL);
 
 	rpc_clnt_dir = debugfs_create_dir("rpc_clnt", topdir);
-	if (!rpc_clnt_dir)
-		goto out_remove;
 
 	rpc_xprt_dir = debugfs_create_dir("rpc_xprt", topdir);
-	if (!rpc_xprt_dir)
-		goto out_remove;
 
-	return;
-out_remove:
-	debugfs_remove_recursive(topdir);
-	topdir = NULL;
-	rpc_fault_dir = NULL;
-	rpc_clnt_dir = NULL;
+	rpc_fault_dir = debugfs_create_dir("inject_fault", topdir);
+
+	debugfs_create_file("disconnect", S_IFREG | 0400, rpc_fault_dir, NULL,
+			    &fault_disconnect_fops);
 }
diff --git a/net/sunrpc/rpc_pipe.c b/net/sunrpc/rpc_pipe.c
index 73bd62979fe7..748bac601e47 100644
--- a/net/sunrpc/rpc_pipe.c
+++ b/net/sunrpc/rpc_pipe.c
@@ -14,6 +14,7 @@
 #include <linux/string.h>
 #include <linux/pagemap.h>
 #include <linux/mount.h>
+#include <linux/fs_context.h>
 #include <linux/namei.h>
 #include <linux/fsnotify.h>
 #include <linux/kernel.h>
@@ -1352,11 +1353,11 @@ rpc_gssd_dummy_depopulate(struct dentry *pipe_dentry)
 }
 
 static int
-rpc_fill_super(struct super_block *sb, void *data, int silent)
+rpc_fill_super(struct super_block *sb, struct fs_context *fc)
 {
 	struct inode *inode;
 	struct dentry *root, *gssd_dentry;
-	struct net *net = get_net(sb->s_fs_info);
+	struct net *net = sb->s_fs_info;
 	struct sunrpc_net *sn = net_generic(net, sunrpc_net_id);
 	int err;
 
@@ -1413,12 +1414,29 @@ gssd_running(struct net *net)
 }
 EXPORT_SYMBOL_GPL(gssd_running);
 
-static struct dentry *
-rpc_mount(struct file_system_type *fs_type,
-		int flags, const char *dev_name, void *data)
+static int rpc_fs_get_tree(struct fs_context *fc)
+{
+	fc->s_fs_info = get_net(fc->net_ns);
+	return vfs_get_super(fc, vfs_get_keyed_super, rpc_fill_super);
+}
+
+static void rpc_fs_free_fc(struct fs_context *fc)
 {
-	struct net *net = current->nsproxy->net_ns;
-	return mount_ns(fs_type, flags, data, net, net->user_ns, rpc_fill_super);
+	if (fc->s_fs_info)
+		put_net(fc->s_fs_info);
+}
+
+static const struct fs_context_operations rpc_fs_context_ops = {
+	.free		= rpc_fs_free_fc,
+	.get_tree	= rpc_fs_get_tree,
+};
+
+static int rpc_init_fs_context(struct fs_context *fc)
+{
+	put_user_ns(fc->user_ns);
+	fc->user_ns = get_user_ns(fc->net_ns->user_ns);
+	fc->ops = &rpc_fs_context_ops;
+	return 0;
 }
 
 static void rpc_kill_sb(struct super_block *sb)
@@ -1446,7 +1464,7 @@ out:
 static struct file_system_type rpc_pipe_fs_type = {
 	.owner		= THIS_MODULE,
 	.name		= "rpc_pipefs",
-	.mount		= rpc_mount,
+	.init_fs_context = rpc_init_fs_context,
 	.kill_sb	= rpc_kill_sb,
 };
 MODULE_ALIAS_FS("rpc_pipefs");
diff --git a/net/sunrpc/sched.c b/net/sunrpc/sched.c
index a2c114812717..1f275aba786f 100644
--- a/net/sunrpc/sched.c
+++ b/net/sunrpc/sched.c
@@ -23,6 +23,7 @@
 #include <linux/sched/mm.h>
 
 #include <linux/sunrpc/clnt.h>
+#include <linux/sunrpc/metrics.h>
 
 #include "sunrpc.h"
 
@@ -46,7 +47,7 @@ static mempool_t	*rpc_buffer_mempool __read_mostly;
 
 static void			rpc_async_schedule(struct work_struct *);
 static void			 rpc_release_task(struct rpc_task *task);
-static void __rpc_queue_timer_fn(struct timer_list *t);
+static void __rpc_queue_timer_fn(struct work_struct *);
 
 /*
  * RPC tasks sit here while waiting for conditions to improve.
@@ -58,6 +59,7 @@ static struct rpc_wait_queue delay_queue;
  */
 struct workqueue_struct *rpciod_workqueue __read_mostly;
 struct workqueue_struct *xprtiod_workqueue __read_mostly;
+EXPORT_SYMBOL_GPL(xprtiod_workqueue);
 
 unsigned long
 rpc_task_timeout(const struct rpc_task *task)
@@ -87,13 +89,19 @@ __rpc_disable_timer(struct rpc_wait_queue *queue, struct rpc_task *task)
 	task->tk_timeout = 0;
 	list_del(&task->u.tk_wait.timer_list);
 	if (list_empty(&queue->timer_list.list))
-		del_timer(&queue->timer_list.timer);
+		cancel_delayed_work(&queue->timer_list.dwork);
 }
 
 static void
 rpc_set_queue_timer(struct rpc_wait_queue *queue, unsigned long expires)
 {
-	timer_reduce(&queue->timer_list.timer, expires);
+	unsigned long now = jiffies;
+	queue->timer_list.expires = expires;
+	if (time_before_eq(expires, now))
+		expires = 0;
+	else
+		expires -= now;
+	mod_delayed_work(rpciod_workqueue, &queue->timer_list.dwork, expires);
 }
 
 /*
@@ -107,7 +115,8 @@ __rpc_add_timer(struct rpc_wait_queue *queue, struct rpc_task *task,
 		task->tk_pid, jiffies_to_msecs(timeout - jiffies));
 
 	task->tk_timeout = timeout;
-	rpc_set_queue_timer(queue, timeout);
+	if (list_empty(&queue->timer_list.list) || time_before(timeout, queue->timer_list.expires))
+		rpc_set_queue_timer(queue, timeout);
 	list_add(&task->u.tk_wait.timer_list, &queue->timer_list.list);
 }
 
@@ -250,7 +259,8 @@ static void __rpc_init_priority_wait_queue(struct rpc_wait_queue *queue, const c
 	queue->maxpriority = nr_queues - 1;
 	rpc_reset_waitqueue_priority(queue);
 	queue->qlen = 0;
-	timer_setup(&queue->timer_list.timer, __rpc_queue_timer_fn, 0);
+	queue->timer_list.expires = 0;
+	INIT_DEFERRABLE_WORK(&queue->timer_list.dwork, __rpc_queue_timer_fn);
 	INIT_LIST_HEAD(&queue->timer_list.list);
 	rpc_assign_waitqueue_name(queue, qname);
 }
@@ -269,7 +279,7 @@ EXPORT_SYMBOL_GPL(rpc_init_wait_queue);
 
 void rpc_destroy_wait_queue(struct rpc_wait_queue *queue)
 {
-	del_timer_sync(&queue->timer_list.timer);
+	cancel_delayed_work_sync(&queue->timer_list.dwork);
 }
 EXPORT_SYMBOL_GPL(rpc_destroy_wait_queue);
 
@@ -424,9 +434,9 @@ void rpc_sleep_on_timeout(struct rpc_wait_queue *q, struct rpc_task *task,
 	/*
 	 * Protect the queue operations.
 	 */
-	spin_lock_bh(&q->lock);
+	spin_lock(&q->lock);
 	__rpc_sleep_on_priority_timeout(q, task, timeout, task->tk_priority);
-	spin_unlock_bh(&q->lock);
+	spin_unlock(&q->lock);
 }
 EXPORT_SYMBOL_GPL(rpc_sleep_on_timeout);
 
@@ -442,9 +452,9 @@ void rpc_sleep_on(struct rpc_wait_queue *q, struct rpc_task *task,
 	/*
 	 * Protect the queue operations.
 	 */
-	spin_lock_bh(&q->lock);
+	spin_lock(&q->lock);
 	__rpc_sleep_on_priority(q, task, task->tk_priority);
-	spin_unlock_bh(&q->lock);
+	spin_unlock(&q->lock);
 }
 EXPORT_SYMBOL_GPL(rpc_sleep_on);
 
@@ -458,9 +468,9 @@ void rpc_sleep_on_priority_timeout(struct rpc_wait_queue *q,
 	/*
 	 * Protect the queue operations.
 	 */
-	spin_lock_bh(&q->lock);
+	spin_lock(&q->lock);
 	__rpc_sleep_on_priority_timeout(q, task, timeout, priority);
-	spin_unlock_bh(&q->lock);
+	spin_unlock(&q->lock);
 }
 EXPORT_SYMBOL_GPL(rpc_sleep_on_priority_timeout);
 
@@ -475,9 +485,9 @@ void rpc_sleep_on_priority(struct rpc_wait_queue *q, struct rpc_task *task,
 	/*
 	 * Protect the queue operations.
 	 */
-	spin_lock_bh(&q->lock);
+	spin_lock(&q->lock);
 	__rpc_sleep_on_priority(q, task, priority);
-	spin_unlock_bh(&q->lock);
+	spin_unlock(&q->lock);
 }
 EXPORT_SYMBOL_GPL(rpc_sleep_on_priority);
 
@@ -555,9 +565,9 @@ void rpc_wake_up_queued_task_on_wq(struct workqueue_struct *wq,
 {
 	if (!RPC_IS_QUEUED(task))
 		return;
-	spin_lock_bh(&queue->lock);
+	spin_lock(&queue->lock);
 	rpc_wake_up_task_on_wq_queue_locked(wq, queue, task);
-	spin_unlock_bh(&queue->lock);
+	spin_unlock(&queue->lock);
 }
 
 /*
@@ -567,9 +577,9 @@ void rpc_wake_up_queued_task(struct rpc_wait_queue *queue, struct rpc_task *task
 {
 	if (!RPC_IS_QUEUED(task))
 		return;
-	spin_lock_bh(&queue->lock);
+	spin_lock(&queue->lock);
 	rpc_wake_up_task_queue_locked(queue, task);
-	spin_unlock_bh(&queue->lock);
+	spin_unlock(&queue->lock);
 }
 EXPORT_SYMBOL_GPL(rpc_wake_up_queued_task);
 
@@ -602,9 +612,9 @@ rpc_wake_up_queued_task_set_status(struct rpc_wait_queue *queue,
 {
 	if (!RPC_IS_QUEUED(task))
 		return;
-	spin_lock_bh(&queue->lock);
+	spin_lock(&queue->lock);
 	rpc_wake_up_task_queue_set_status_locked(queue, task, status);
-	spin_unlock_bh(&queue->lock);
+	spin_unlock(&queue->lock);
 }
 
 /*
@@ -667,12 +677,12 @@ struct rpc_task *rpc_wake_up_first_on_wq(struct workqueue_struct *wq,
 
 	dprintk("RPC:       wake_up_first(%p \"%s\")\n",
 			queue, rpc_qname(queue));
-	spin_lock_bh(&queue->lock);
+	spin_lock(&queue->lock);
 	task = __rpc_find_next_queued(queue);
 	if (task != NULL)
 		task = rpc_wake_up_task_on_wq_queue_action_locked(wq, queue,
 				task, func, data);
-	spin_unlock_bh(&queue->lock);
+	spin_unlock(&queue->lock);
 
 	return task;
 }
@@ -711,7 +721,7 @@ void rpc_wake_up(struct rpc_wait_queue *queue)
 {
 	struct list_head *head;
 
-	spin_lock_bh(&queue->lock);
+	spin_lock(&queue->lock);
 	head = &queue->tasks[queue->maxpriority];
 	for (;;) {
 		while (!list_empty(head)) {
@@ -725,7 +735,7 @@ void rpc_wake_up(struct rpc_wait_queue *queue)
 			break;
 		head--;
 	}
-	spin_unlock_bh(&queue->lock);
+	spin_unlock(&queue->lock);
 }
 EXPORT_SYMBOL_GPL(rpc_wake_up);
 
@@ -740,7 +750,7 @@ void rpc_wake_up_status(struct rpc_wait_queue *queue, int status)
 {
 	struct list_head *head;
 
-	spin_lock_bh(&queue->lock);
+	spin_lock(&queue->lock);
 	head = &queue->tasks[queue->maxpriority];
 	for (;;) {
 		while (!list_empty(head)) {
@@ -755,13 +765,15 @@ void rpc_wake_up_status(struct rpc_wait_queue *queue, int status)
 			break;
 		head--;
 	}
-	spin_unlock_bh(&queue->lock);
+	spin_unlock(&queue->lock);
 }
 EXPORT_SYMBOL_GPL(rpc_wake_up_status);
 
-static void __rpc_queue_timer_fn(struct timer_list *t)
+static void __rpc_queue_timer_fn(struct work_struct *work)
 {
-	struct rpc_wait_queue *queue = from_timer(queue, t, timer_list.timer);
+	struct rpc_wait_queue *queue = container_of(work,
+			struct rpc_wait_queue,
+			timer_list.dwork.work);
 	struct rpc_task *task, *n;
 	unsigned long expires, now, timeo;
 
@@ -832,6 +844,10 @@ rpc_reset_task_statistics(struct rpc_task *task)
 void rpc_exit_task(struct rpc_task *task)
 {
 	task->tk_action = NULL;
+	if (task->tk_ops->rpc_count_stats)
+		task->tk_ops->rpc_count_stats(task, task->tk_calldata);
+	else if (task->tk_client)
+		rpc_count_iostats(task, task->tk_client->cl_metrics);
 	if (task->tk_ops->rpc_call_done != NULL) {
 		task->tk_ops->rpc_call_done(task, task->tk_calldata);
 		if (task->tk_action != NULL) {
@@ -927,13 +943,13 @@ static void __rpc_execute(struct rpc_task *task)
 		 * rpc_task pointer may still be dereferenced.
 		 */
 		queue = task->tk_waitqueue;
-		spin_lock_bh(&queue->lock);
+		spin_lock(&queue->lock);
 		if (!RPC_IS_QUEUED(task)) {
-			spin_unlock_bh(&queue->lock);
+			spin_unlock(&queue->lock);
 			continue;
 		}
 		rpc_clear_running(task);
-		spin_unlock_bh(&queue->lock);
+		spin_unlock(&queue->lock);
 		if (task_is_async)
 			return;
 
@@ -1076,7 +1092,8 @@ static void rpc_init_task(struct rpc_task *task, const struct rpc_task_setup *ta
 	/* Initialize workqueue for async tasks */
 	task->tk_workqueue = task_setup_data->workqueue;
 
-	task->tk_xprt = xprt_get(task_setup_data->rpc_xprt);
+	task->tk_xprt = rpc_task_get_xprt(task_setup_data->rpc_client,
+			xprt_get(task_setup_data->rpc_xprt));
 
 	task->tk_op_cred = get_rpccred(task_setup_data->rpc_op_cred);
 
diff --git a/net/sunrpc/stats.c b/net/sunrpc/stats.c
index 2b6dc7e5f74f..7c74197c2ecf 100644
--- a/net/sunrpc/stats.c
+++ b/net/sunrpc/stats.c
@@ -177,6 +177,8 @@ void rpc_count_iostats_metrics(const struct rpc_task *task,
 
 	execute = ktime_sub(now, task->tk_start);
 	op_metrics->om_execute = ktime_add(op_metrics->om_execute, execute);
+	if (task->tk_status < 0)
+		op_metrics->om_error_status++;
 
 	spin_unlock(&op_metrics->om_lock);
 
@@ -219,13 +221,14 @@ static void _add_rpc_iostats(struct rpc_iostats *a, struct rpc_iostats *b)
 	a->om_queue = ktime_add(a->om_queue, b->om_queue);
 	a->om_rtt = ktime_add(a->om_rtt, b->om_rtt);
 	a->om_execute = ktime_add(a->om_execute, b->om_execute);
+	a->om_error_status += b->om_error_status;
 }
 
 static void _print_rpc_iostats(struct seq_file *seq, struct rpc_iostats *stats,
 			       int op, const struct rpc_procinfo *procs)
 {
 	_print_name(seq, op, procs);
-	seq_printf(seq, "%lu %lu %lu %Lu %Lu %Lu %Lu %Lu\n",
+	seq_printf(seq, "%lu %lu %lu %llu %llu %llu %llu %llu %lu\n",
 		   stats->om_ops,
 		   stats->om_ntrans,
 		   stats->om_timeouts,
@@ -233,12 +236,20 @@ static void _print_rpc_iostats(struct seq_file *seq, struct rpc_iostats *stats,
 		   stats->om_bytes_recv,
 		   ktime_to_ms(stats->om_queue),
 		   ktime_to_ms(stats->om_rtt),
-		   ktime_to_ms(stats->om_execute));
+		   ktime_to_ms(stats->om_execute),
+		   stats->om_error_status);
+}
+
+static int do_print_stats(struct rpc_clnt *clnt, struct rpc_xprt *xprt, void *seqv)
+{
+	struct seq_file *seq = seqv;
+
+	xprt->ops->print_stats(xprt, seq);
+	return 0;
 }
 
 void rpc_clnt_show_stats(struct seq_file *seq, struct rpc_clnt *clnt)
 {
-	struct rpc_xprt *xprt;
 	unsigned int op, maxproc = clnt->cl_maxproc;
 
 	if (!clnt->cl_metrics)
@@ -248,11 +259,7 @@ void rpc_clnt_show_stats(struct seq_file *seq, struct rpc_clnt *clnt)
 	seq_printf(seq, "p/v: %u/%u (%s)\n",
 			clnt->cl_prog, clnt->cl_vers, clnt->cl_program->name);
 
-	rcu_read_lock();
-	xprt = rcu_dereference(clnt->cl_xprt);
-	if (xprt)
-		xprt->ops->print_stats(xprt, seq);
-	rcu_read_unlock();
+	rpc_clnt_iterate_for_each_xprt(clnt, do_print_stats, seq);
 
 	seq_printf(seq, "\tper-op statistics\n");
 	for (op = 0; op < maxproc; op++) {
diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c
index e15cb704453e..220b79988000 100644
--- a/net/sunrpc/svc.c
+++ b/net/sunrpc/svc.c
@@ -1595,7 +1595,7 @@ bc_svc_process(struct svc_serv *serv, struct rpc_rqst *req,
 	/* Parse and execute the bc call */
 	proc_error = svc_process_common(rqstp, argv, resv);
 
-	atomic_inc(&req->rq_xprt->bc_free_slots);
+	atomic_dec(&req->rq_xprt->bc_slot_count);
 	if (!proc_error) {
 		/* Processing error: drop the request */
 		xprt_free_bc_request(req);
diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c
index f6c82b1651e7..783748dc5e6f 100644
--- a/net/sunrpc/xprt.c
+++ b/net/sunrpc/xprt.c
@@ -302,9 +302,9 @@ static inline int xprt_lock_write(struct rpc_xprt *xprt, struct rpc_task *task)
 
 	if (test_bit(XPRT_LOCKED, &xprt->state) && xprt->snd_task == task)
 		return 1;
-	spin_lock_bh(&xprt->transport_lock);
+	spin_lock(&xprt->transport_lock);
 	retval = xprt->ops->reserve_xprt(xprt, task);
-	spin_unlock_bh(&xprt->transport_lock);
+	spin_unlock(&xprt->transport_lock);
 	return retval;
 }
 
@@ -381,9 +381,9 @@ static inline void xprt_release_write(struct rpc_xprt *xprt, struct rpc_task *ta
 {
 	if (xprt->snd_task != task)
 		return;
-	spin_lock_bh(&xprt->transport_lock);
+	spin_lock(&xprt->transport_lock);
 	xprt->ops->release_xprt(xprt, task);
-	spin_unlock_bh(&xprt->transport_lock);
+	spin_unlock(&xprt->transport_lock);
 }
 
 /*
@@ -435,9 +435,9 @@ xprt_request_get_cong(struct rpc_xprt *xprt, struct rpc_rqst *req)
 
 	if (req->rq_cong)
 		return true;
-	spin_lock_bh(&xprt->transport_lock);
+	spin_lock(&xprt->transport_lock);
 	ret = __xprt_get_cong(xprt, req) != 0;
-	spin_unlock_bh(&xprt->transport_lock);
+	spin_unlock(&xprt->transport_lock);
 	return ret;
 }
 EXPORT_SYMBOL_GPL(xprt_request_get_cong);
@@ -464,9 +464,9 @@ static void
 xprt_clear_congestion_window_wait(struct rpc_xprt *xprt)
 {
 	if (test_and_clear_bit(XPRT_CWND_WAIT, &xprt->state)) {
-		spin_lock_bh(&xprt->transport_lock);
+		spin_lock(&xprt->transport_lock);
 		__xprt_lock_write_next_cong(xprt);
-		spin_unlock_bh(&xprt->transport_lock);
+		spin_unlock(&xprt->transport_lock);
 	}
 }
 
@@ -563,9 +563,9 @@ bool xprt_write_space(struct rpc_xprt *xprt)
 
 	if (!test_bit(XPRT_WRITE_SPACE, &xprt->state))
 		return false;
-	spin_lock_bh(&xprt->transport_lock);
+	spin_lock(&xprt->transport_lock);
 	ret = xprt_clear_write_space_locked(xprt);
-	spin_unlock_bh(&xprt->transport_lock);
+	spin_unlock(&xprt->transport_lock);
 	return ret;
 }
 EXPORT_SYMBOL_GPL(xprt_write_space);
@@ -634,9 +634,9 @@ int xprt_adjust_timeout(struct rpc_rqst *req)
 		req->rq_retries = 0;
 		xprt_reset_majortimeo(req);
 		/* Reset the RTT counters == "slow start" */
-		spin_lock_bh(&xprt->transport_lock);
+		spin_lock(&xprt->transport_lock);
 		rpc_init_rtt(req->rq_task->tk_client->cl_rtt, to->to_initval);
-		spin_unlock_bh(&xprt->transport_lock);
+		spin_unlock(&xprt->transport_lock);
 		status = -ETIMEDOUT;
 	}
 
@@ -668,11 +668,11 @@ static void xprt_autoclose(struct work_struct *work)
 void xprt_disconnect_done(struct rpc_xprt *xprt)
 {
 	dprintk("RPC:       disconnected transport %p\n", xprt);
-	spin_lock_bh(&xprt->transport_lock);
+	spin_lock(&xprt->transport_lock);
 	xprt_clear_connected(xprt);
 	xprt_clear_write_space_locked(xprt);
 	xprt_wake_pending_tasks(xprt, -ENOTCONN);
-	spin_unlock_bh(&xprt->transport_lock);
+	spin_unlock(&xprt->transport_lock);
 }
 EXPORT_SYMBOL_GPL(xprt_disconnect_done);
 
@@ -684,7 +684,7 @@ EXPORT_SYMBOL_GPL(xprt_disconnect_done);
 void xprt_force_disconnect(struct rpc_xprt *xprt)
 {
 	/* Don't race with the test_bit() in xprt_clear_locked() */
-	spin_lock_bh(&xprt->transport_lock);
+	spin_lock(&xprt->transport_lock);
 	set_bit(XPRT_CLOSE_WAIT, &xprt->state);
 	/* Try to schedule an autoclose RPC call */
 	if (test_and_set_bit(XPRT_LOCKED, &xprt->state) == 0)
@@ -692,7 +692,7 @@ void xprt_force_disconnect(struct rpc_xprt *xprt)
 	else if (xprt->snd_task)
 		rpc_wake_up_queued_task_set_status(&xprt->pending,
 				xprt->snd_task, -ENOTCONN);
-	spin_unlock_bh(&xprt->transport_lock);
+	spin_unlock(&xprt->transport_lock);
 }
 EXPORT_SYMBOL_GPL(xprt_force_disconnect);
 
@@ -726,7 +726,7 @@ xprt_request_retransmit_after_disconnect(struct rpc_task *task)
 void xprt_conditional_disconnect(struct rpc_xprt *xprt, unsigned int cookie)
 {
 	/* Don't race with the test_bit() in xprt_clear_locked() */
-	spin_lock_bh(&xprt->transport_lock);
+	spin_lock(&xprt->transport_lock);
 	if (cookie != xprt->connect_cookie)
 		goto out;
 	if (test_bit(XPRT_CLOSING, &xprt->state))
@@ -737,7 +737,7 @@ void xprt_conditional_disconnect(struct rpc_xprt *xprt, unsigned int cookie)
 		queue_work(xprtiod_workqueue, &xprt->task_cleanup);
 	xprt_wake_pending_tasks(xprt, -EAGAIN);
 out:
-	spin_unlock_bh(&xprt->transport_lock);
+	spin_unlock(&xprt->transport_lock);
 }
 
 static bool
@@ -750,6 +750,7 @@ static void
 xprt_schedule_autodisconnect(struct rpc_xprt *xprt)
 	__must_hold(&xprt->transport_lock)
 {
+	xprt->last_used = jiffies;
 	if (RB_EMPTY_ROOT(&xprt->recv_queue) && xprt_has_timer(xprt))
 		mod_timer(&xprt->timer, xprt->last_used + xprt->idle_timeout);
 }
@@ -759,18 +760,13 @@ xprt_init_autodisconnect(struct timer_list *t)
 {
 	struct rpc_xprt *xprt = from_timer(xprt, t, timer);
 
-	spin_lock(&xprt->transport_lock);
 	if (!RB_EMPTY_ROOT(&xprt->recv_queue))
-		goto out_abort;
+		return;
 	/* Reset xprt->last_used to avoid connect/autodisconnect cycling */
 	xprt->last_used = jiffies;
 	if (test_and_set_bit(XPRT_LOCKED, &xprt->state))
-		goto out_abort;
-	spin_unlock(&xprt->transport_lock);
+		return;
 	queue_work(xprtiod_workqueue, &xprt->task_cleanup);
-	return;
-out_abort:
-	spin_unlock(&xprt->transport_lock);
 }
 
 bool xprt_lock_connect(struct rpc_xprt *xprt,
@@ -779,7 +775,7 @@ bool xprt_lock_connect(struct rpc_xprt *xprt,
 {
 	bool ret = false;
 
-	spin_lock_bh(&xprt->transport_lock);
+	spin_lock(&xprt->transport_lock);
 	if (!test_bit(XPRT_LOCKED, &xprt->state))
 		goto out;
 	if (xprt->snd_task != task)
@@ -787,13 +783,13 @@ bool xprt_lock_connect(struct rpc_xprt *xprt,
 	xprt->snd_task = cookie;
 	ret = true;
 out:
-	spin_unlock_bh(&xprt->transport_lock);
+	spin_unlock(&xprt->transport_lock);
 	return ret;
 }
 
 void xprt_unlock_connect(struct rpc_xprt *xprt, void *cookie)
 {
-	spin_lock_bh(&xprt->transport_lock);
+	spin_lock(&xprt->transport_lock);
 	if (xprt->snd_task != cookie)
 		goto out;
 	if (!test_bit(XPRT_LOCKED, &xprt->state))
@@ -802,7 +798,7 @@ void xprt_unlock_connect(struct rpc_xprt *xprt, void *cookie)
 	xprt->ops->release_xprt(xprt, NULL);
 	xprt_schedule_autodisconnect(xprt);
 out:
-	spin_unlock_bh(&xprt->transport_lock);
+	spin_unlock(&xprt->transport_lock);
 	wake_up_bit(&xprt->state, XPRT_LOCKED);
 }
 
@@ -850,6 +846,38 @@ void xprt_connect(struct rpc_task *task)
 	xprt_release_write(xprt, task);
 }
 
+/**
+ * xprt_reconnect_delay - compute the wait before scheduling a connect
+ * @xprt: transport instance
+ *
+ */
+unsigned long xprt_reconnect_delay(const struct rpc_xprt *xprt)
+{
+	unsigned long start, now = jiffies;
+
+	start = xprt->stat.connect_start + xprt->reestablish_timeout;
+	if (time_after(start, now))
+		return start - now;
+	return 0;
+}
+EXPORT_SYMBOL_GPL(xprt_reconnect_delay);
+
+/**
+ * xprt_reconnect_backoff - compute the new re-establish timeout
+ * @xprt: transport instance
+ * @init_to: initial reestablish timeout
+ *
+ */
+void xprt_reconnect_backoff(struct rpc_xprt *xprt, unsigned long init_to)
+{
+	xprt->reestablish_timeout <<= 1;
+	if (xprt->reestablish_timeout > xprt->max_reconnect_timeout)
+		xprt->reestablish_timeout = xprt->max_reconnect_timeout;
+	if (xprt->reestablish_timeout < init_to)
+		xprt->reestablish_timeout = init_to;
+}
+EXPORT_SYMBOL_GPL(xprt_reconnect_backoff);
+
 enum xprt_xid_rb_cmp {
 	XID_RB_EQUAL,
 	XID_RB_LEFT,
@@ -1013,6 +1041,8 @@ xprt_request_enqueue_receive(struct rpc_task *task)
 
 	if (!xprt_request_need_enqueue_receive(task, req))
 		return;
+
+	xprt_request_prepare(task->tk_rqstp);
 	spin_lock(&xprt->queue_lock);
 
 	/* Update the softirq receive buffer */
@@ -1412,14 +1442,14 @@ xprt_request_transmit(struct rpc_rqst *req, struct rpc_task *snd_task)
 	xprt_inject_disconnect(xprt);
 
 	task->tk_flags |= RPC_TASK_SENT;
-	spin_lock_bh(&xprt->transport_lock);
+	spin_lock(&xprt->transport_lock);
 
 	xprt->stat.sends++;
 	xprt->stat.req_u += xprt->stat.sends - xprt->stat.recvs;
 	xprt->stat.bklog_u += xprt->backlog.qlen;
 	xprt->stat.sending_u += xprt->sending.qlen;
 	xprt->stat.pending_u += xprt->pending.qlen;
-	spin_unlock_bh(&xprt->transport_lock);
+	spin_unlock(&xprt->transport_lock);
 
 	req->rq_connect_cookie = connect_cookie;
 out_dequeue:
@@ -1765,18 +1795,13 @@ void xprt_release(struct rpc_task *task)
 	}
 
 	xprt = req->rq_xprt;
-	if (task->tk_ops->rpc_count_stats != NULL)
-		task->tk_ops->rpc_count_stats(task, task->tk_calldata);
-	else if (task->tk_client)
-		rpc_count_iostats(task, task->tk_client->cl_metrics);
 	xprt_request_dequeue_all(task, req);
-	spin_lock_bh(&xprt->transport_lock);
+	spin_lock(&xprt->transport_lock);
 	xprt->ops->release_xprt(xprt, task);
 	if (xprt->ops->release_request)
 		xprt->ops->release_request(task);
-	xprt->last_used = jiffies;
 	xprt_schedule_autodisconnect(xprt);
-	spin_unlock_bh(&xprt->transport_lock);
+	spin_unlock(&xprt->transport_lock);
 	if (req->rq_buffer)
 		xprt->ops->buf_free(task);
 	xprt_inject_disconnect(xprt);
diff --git a/net/sunrpc/xprtmultipath.c b/net/sunrpc/xprtmultipath.c
index 8394124126f8..78c075a68c04 100644
--- a/net/sunrpc/xprtmultipath.c
+++ b/net/sunrpc/xprtmultipath.c
@@ -19,7 +19,7 @@
 #include <linux/sunrpc/addr.h>
 #include <linux/sunrpc/xprtmultipath.h>
 
-typedef struct rpc_xprt *(*xprt_switch_find_xprt_t)(struct list_head *head,
+typedef struct rpc_xprt *(*xprt_switch_find_xprt_t)(struct rpc_xprt_switch *xps,
 		const struct rpc_xprt *cur);
 
 static const struct rpc_xprt_iter_ops rpc_xprt_iter_singular;
@@ -36,6 +36,7 @@ static void xprt_switch_add_xprt_locked(struct rpc_xprt_switch *xps,
 	if (xps->xps_nxprts == 0)
 		xps->xps_net = xprt->xprt_net;
 	xps->xps_nxprts++;
+	xps->xps_nactive++;
 }
 
 /**
@@ -51,8 +52,7 @@ void rpc_xprt_switch_add_xprt(struct rpc_xprt_switch *xps,
 	if (xprt == NULL)
 		return;
 	spin_lock(&xps->xps_lock);
-	if ((xps->xps_net == xprt->xprt_net || xps->xps_net == NULL) &&
-	    !rpc_xprt_switch_has_addr(xps, (struct sockaddr *)&xprt->addr))
+	if (xps->xps_net == xprt->xprt_net || xps->xps_net == NULL)
 		xprt_switch_add_xprt_locked(xps, xprt);
 	spin_unlock(&xps->xps_lock);
 }
@@ -62,6 +62,7 @@ static void xprt_switch_remove_xprt_locked(struct rpc_xprt_switch *xps,
 {
 	if (unlikely(xprt == NULL))
 		return;
+	xps->xps_nactive--;
 	xps->xps_nxprts--;
 	if (xps->xps_nxprts == 0)
 		xps->xps_net = NULL;
@@ -102,7 +103,9 @@ struct rpc_xprt_switch *xprt_switch_alloc(struct rpc_xprt *xprt,
 	if (xps != NULL) {
 		spin_lock_init(&xps->xps_lock);
 		kref_init(&xps->xps_kref);
-		xps->xps_nxprts = 0;
+		xps->xps_nxprts = xps->xps_nactive = 0;
+		atomic_long_set(&xps->xps_queuelen, 0);
+		xps->xps_net = NULL;
 		INIT_LIST_HEAD(&xps->xps_xprt_list);
 		xps->xps_iter_ops = &rpc_xprt_iter_singular;
 		xprt_switch_add_xprt_locked(xps, xprt);
@@ -193,9 +196,21 @@ void xprt_iter_default_rewind(struct rpc_xprt_iter *xpi)
 }
 
 static
+bool xprt_is_active(const struct rpc_xprt *xprt)
+{
+	return kref_read(&xprt->kref) != 0;
+}
+
+static
 struct rpc_xprt *xprt_switch_find_first_entry(struct list_head *head)
 {
-	return list_first_or_null_rcu(head, struct rpc_xprt, xprt_switch);
+	struct rpc_xprt *pos;
+
+	list_for_each_entry_rcu(pos, head, xprt_switch) {
+		if (xprt_is_active(pos))
+			return pos;
+	}
+	return NULL;
 }
 
 static
@@ -213,9 +228,12 @@ struct rpc_xprt *xprt_switch_find_current_entry(struct list_head *head,
 		const struct rpc_xprt *cur)
 {
 	struct rpc_xprt *pos;
+	bool found = false;
 
 	list_for_each_entry_rcu(pos, head, xprt_switch) {
 		if (cur == pos)
+			found = true;
+		if (found && xprt_is_active(pos))
 			return pos;
 	}
 	return NULL;
@@ -260,9 +278,12 @@ struct rpc_xprt *xprt_switch_find_next_entry(struct list_head *head,
 		const struct rpc_xprt *cur)
 {
 	struct rpc_xprt *pos, *prev = NULL;
+	bool found = false;
 
 	list_for_each_entry_rcu(pos, head, xprt_switch) {
 		if (cur == prev)
+			found = true;
+		if (found && xprt_is_active(pos))
 			return pos;
 		prev = pos;
 	}
@@ -270,22 +291,15 @@ struct rpc_xprt *xprt_switch_find_next_entry(struct list_head *head,
 }
 
 static
-struct rpc_xprt *xprt_switch_set_next_cursor(struct list_head *head,
+struct rpc_xprt *xprt_switch_set_next_cursor(struct rpc_xprt_switch *xps,
 		struct rpc_xprt **cursor,
 		xprt_switch_find_xprt_t find_next)
 {
-	struct rpc_xprt *cur, *pos, *old;
+	struct rpc_xprt *pos, *old;
 
-	cur = READ_ONCE(*cursor);
-	for (;;) {
-		old = cur;
-		pos = find_next(head, old);
-		if (pos == NULL)
-			break;
-		cur = cmpxchg_relaxed(cursor, old, pos);
-		if (cur == old)
-			break;
-	}
+	old = smp_load_acquire(cursor);
+	pos = find_next(xps, old);
+	smp_store_release(cursor, pos);
 	return pos;
 }
 
@@ -297,13 +311,11 @@ struct rpc_xprt *xprt_iter_next_entry_multiple(struct rpc_xprt_iter *xpi,
 
 	if (xps == NULL)
 		return NULL;
-	return xprt_switch_set_next_cursor(&xps->xps_xprt_list,
-			&xpi->xpi_cursor,
-			find_next);
+	return xprt_switch_set_next_cursor(xps, &xpi->xpi_cursor, find_next);
 }
 
 static
-struct rpc_xprt *xprt_switch_find_next_entry_roundrobin(struct list_head *head,
+struct rpc_xprt *__xprt_switch_find_next_entry_roundrobin(struct list_head *head,
 		const struct rpc_xprt *cur)
 {
 	struct rpc_xprt *ret;
@@ -315,6 +327,31 @@ struct rpc_xprt *xprt_switch_find_next_entry_roundrobin(struct list_head *head,
 }
 
 static
+struct rpc_xprt *xprt_switch_find_next_entry_roundrobin(struct rpc_xprt_switch *xps,
+		const struct rpc_xprt *cur)
+{
+	struct list_head *head = &xps->xps_xprt_list;
+	struct rpc_xprt *xprt;
+	unsigned int nactive;
+
+	for (;;) {
+		unsigned long xprt_queuelen, xps_queuelen;
+
+		xprt = __xprt_switch_find_next_entry_roundrobin(head, cur);
+		if (!xprt)
+			break;
+		xprt_queuelen = atomic_long_read(&xprt->queuelen);
+		xps_queuelen = atomic_long_read(&xps->xps_queuelen);
+		nactive = READ_ONCE(xps->xps_nactive);
+		/* Exit loop if xprt_queuelen <= average queue length */
+		if (xprt_queuelen * nactive <= xps_queuelen)
+			break;
+		cur = xprt;
+	}
+	return xprt;
+}
+
+static
 struct rpc_xprt *xprt_iter_next_entry_roundrobin(struct rpc_xprt_iter *xpi)
 {
 	return xprt_iter_next_entry_multiple(xpi,
@@ -322,9 +359,17 @@ struct rpc_xprt *xprt_iter_next_entry_roundrobin(struct rpc_xprt_iter *xpi)
 }
 
 static
+struct rpc_xprt *xprt_switch_find_next_entry_all(struct rpc_xprt_switch *xps,
+		const struct rpc_xprt *cur)
+{
+	return xprt_switch_find_next_entry(&xps->xps_xprt_list, cur);
+}
+
+static
 struct rpc_xprt *xprt_iter_next_entry_all(struct rpc_xprt_iter *xpi)
 {
-	return xprt_iter_next_entry_multiple(xpi, xprt_switch_find_next_entry);
+	return xprt_iter_next_entry_multiple(xpi,
+			xprt_switch_find_next_entry_all);
 }
 
 /*
diff --git a/net/sunrpc/xprtrdma/backchannel.c b/net/sunrpc/xprtrdma/backchannel.c
index ce986591f213..59e624b1d7a0 100644
--- a/net/sunrpc/xprtrdma/backchannel.c
+++ b/net/sunrpc/xprtrdma/backchannel.c
@@ -52,6 +52,13 @@ size_t xprt_rdma_bc_maxpayload(struct rpc_xprt *xprt)
 	return maxmsg - RPCRDMA_HDRLEN_MIN;
 }
 
+unsigned int xprt_rdma_bc_max_slots(struct rpc_xprt *xprt)
+{
+	struct rpcrdma_xprt *r_xprt = rpcx_to_rdmax(xprt);
+
+	return r_xprt->rx_buf.rb_bc_srv_max_requests;
+}
+
 static int rpcrdma_bc_marshal_reply(struct rpc_rqst *rqst)
 {
 	struct rpcrdma_xprt *r_xprt = rpcx_to_rdmax(rqst->rq_xprt);
diff --git a/net/sunrpc/xprtrdma/frwr_ops.c b/net/sunrpc/xprtrdma/frwr_ops.c
index 794ba4ca0994..0b6dad7580a1 100644
--- a/net/sunrpc/xprtrdma/frwr_ops.c
+++ b/net/sunrpc/xprtrdma/frwr_ops.c
@@ -144,6 +144,26 @@ frwr_mr_recycle_worker(struct work_struct *work)
 	frwr_release_mr(mr);
 }
 
+/* frwr_reset - Place MRs back on the free list
+ * @req: request to reset
+ *
+ * Used after a failed marshal. For FRWR, this means the MRs
+ * don't have to be fully released and recreated.
+ *
+ * NB: This is safe only as long as none of @req's MRs are
+ * involved with an ongoing asynchronous FAST_REG or LOCAL_INV
+ * Work Request.
+ */
+void frwr_reset(struct rpcrdma_req *req)
+{
+	while (!list_empty(&req->rl_registered)) {
+		struct rpcrdma_mr *mr;
+
+		mr = rpcrdma_mr_pop(&req->rl_registered);
+		rpcrdma_mr_unmap_and_put(mr);
+	}
+}
+
 /**
  * frwr_init_mr - Initialize one MR
  * @ia: interface adapter
@@ -168,7 +188,6 @@ int frwr_init_mr(struct rpcrdma_ia *ia, struct rpcrdma_mr *mr)
 		goto out_list_err;
 
 	mr->frwr.fr_mr = frmr;
-	mr->frwr.fr_state = FRWR_IS_INVALID;
 	mr->mr_dir = DMA_NONE;
 	INIT_LIST_HEAD(&mr->mr_list);
 	INIT_WORK(&mr->mr_recycle, frwr_mr_recycle_worker);
@@ -298,65 +317,6 @@ size_t frwr_maxpages(struct rpcrdma_xprt *r_xprt)
 }
 
 /**
- * frwr_wc_fastreg - Invoked by RDMA provider for a flushed FastReg WC
- * @cq:	completion queue (ignored)
- * @wc:	completed WR
- *
- */
-static void
-frwr_wc_fastreg(struct ib_cq *cq, struct ib_wc *wc)
-{
-	struct ib_cqe *cqe = wc->wr_cqe;
-	struct rpcrdma_frwr *frwr =
-			container_of(cqe, struct rpcrdma_frwr, fr_cqe);
-
-	/* WARNING: Only wr_cqe and status are reliable at this point */
-	if (wc->status != IB_WC_SUCCESS)
-		frwr->fr_state = FRWR_FLUSHED_FR;
-	trace_xprtrdma_wc_fastreg(wc, frwr);
-}
-
-/**
- * frwr_wc_localinv - Invoked by RDMA provider for a flushed LocalInv WC
- * @cq:	completion queue (ignored)
- * @wc:	completed WR
- *
- */
-static void
-frwr_wc_localinv(struct ib_cq *cq, struct ib_wc *wc)
-{
-	struct ib_cqe *cqe = wc->wr_cqe;
-	struct rpcrdma_frwr *frwr = container_of(cqe, struct rpcrdma_frwr,
-						 fr_cqe);
-
-	/* WARNING: Only wr_cqe and status are reliable at this point */
-	if (wc->status != IB_WC_SUCCESS)
-		frwr->fr_state = FRWR_FLUSHED_LI;
-	trace_xprtrdma_wc_li(wc, frwr);
-}
-
-/**
- * frwr_wc_localinv_wake - Invoked by RDMA provider for a signaled LocalInv WC
- * @cq:	completion queue (ignored)
- * @wc:	completed WR
- *
- * Awaken anyone waiting for an MR to finish being fenced.
- */
-static void
-frwr_wc_localinv_wake(struct ib_cq *cq, struct ib_wc *wc)
-{
-	struct ib_cqe *cqe = wc->wr_cqe;
-	struct rpcrdma_frwr *frwr = container_of(cqe, struct rpcrdma_frwr,
-						 fr_cqe);
-
-	/* WARNING: Only wr_cqe and status are reliable at this point */
-	if (wc->status != IB_WC_SUCCESS)
-		frwr->fr_state = FRWR_FLUSHED_LI;
-	trace_xprtrdma_wc_li_wake(wc, frwr);
-	complete(&frwr->fr_linv_done);
-}
-
-/**
  * frwr_map - Register a memory region
  * @r_xprt: controlling transport
  * @seg: memory region co-ordinates
@@ -378,23 +338,15 @@ struct rpcrdma_mr_seg *frwr_map(struct rpcrdma_xprt *r_xprt,
 {
 	struct rpcrdma_ia *ia = &r_xprt->rx_ia;
 	bool holes_ok = ia->ri_mrtype == IB_MR_TYPE_SG_GAPS;
-	struct rpcrdma_frwr *frwr;
 	struct rpcrdma_mr *mr;
 	struct ib_mr *ibmr;
 	struct ib_reg_wr *reg_wr;
 	int i, n;
 	u8 key;
 
-	mr = NULL;
-	do {
-		if (mr)
-			rpcrdma_mr_recycle(mr);
-		mr = rpcrdma_mr_get(r_xprt);
-		if (!mr)
-			return ERR_PTR(-EAGAIN);
-	} while (mr->frwr.fr_state != FRWR_IS_INVALID);
-	frwr = &mr->frwr;
-	frwr->fr_state = FRWR_IS_VALID;
+	mr = rpcrdma_mr_get(r_xprt);
+	if (!mr)
+		goto out_getmr_err;
 
 	if (nsegs > ia->ri_max_frwr_depth)
 		nsegs = ia->ri_max_frwr_depth;
@@ -423,7 +375,7 @@ struct rpcrdma_mr_seg *frwr_map(struct rpcrdma_xprt *r_xprt,
 	if (!mr->mr_nents)
 		goto out_dmamap_err;
 
-	ibmr = frwr->fr_mr;
+	ibmr = mr->frwr.fr_mr;
 	n = ib_map_mr_sg(ibmr, mr->mr_sg, mr->mr_nents, NULL, PAGE_SIZE);
 	if (unlikely(n != mr->mr_nents))
 		goto out_mapmr_err;
@@ -433,7 +385,7 @@ struct rpcrdma_mr_seg *frwr_map(struct rpcrdma_xprt *r_xprt,
 	key = (u8)(ibmr->rkey & 0x000000FF);
 	ib_update_fast_reg_key(ibmr, ++key);
 
-	reg_wr = &frwr->fr_regwr;
+	reg_wr = &mr->frwr.fr_regwr;
 	reg_wr->mr = ibmr;
 	reg_wr->key = ibmr->rkey;
 	reg_wr->access = writing ?
@@ -448,6 +400,10 @@ struct rpcrdma_mr_seg *frwr_map(struct rpcrdma_xprt *r_xprt,
 	*out = mr;
 	return seg;
 
+out_getmr_err:
+	xprt_wait_for_buffer_space(&r_xprt->rx_xprt);
+	return ERR_PTR(-EAGAIN);
+
 out_dmamap_err:
 	mr->mr_dir = DMA_NONE;
 	trace_xprtrdma_frwr_sgerr(mr, i);
@@ -461,6 +417,23 @@ out_mapmr_err:
 }
 
 /**
+ * frwr_wc_fastreg - Invoked by RDMA provider for a flushed FastReg WC
+ * @cq:	completion queue (ignored)
+ * @wc:	completed WR
+ *
+ */
+static void frwr_wc_fastreg(struct ib_cq *cq, struct ib_wc *wc)
+{
+	struct ib_cqe *cqe = wc->wr_cqe;
+	struct rpcrdma_frwr *frwr =
+		container_of(cqe, struct rpcrdma_frwr, fr_cqe);
+
+	/* WARNING: Only wr_cqe and status are reliable at this point */
+	trace_xprtrdma_wc_fastreg(wc, frwr);
+	/* The MR will get recycled when the associated req is retransmitted */
+}
+
+/**
  * frwr_send - post Send WR containing the RPC Call message
  * @ia: interface adapter
  * @req: Prepared RPC Call
@@ -512,31 +485,75 @@ void frwr_reminv(struct rpcrdma_rep *rep, struct list_head *mrs)
 		if (mr->mr_handle == rep->rr_inv_rkey) {
 			list_del_init(&mr->mr_list);
 			trace_xprtrdma_mr_remoteinv(mr);
-			mr->frwr.fr_state = FRWR_IS_INVALID;
 			rpcrdma_mr_unmap_and_put(mr);
 			break;	/* only one invalidated MR per RPC */
 		}
 }
 
+static void __frwr_release_mr(struct ib_wc *wc, struct rpcrdma_mr *mr)
+{
+	if (wc->status != IB_WC_SUCCESS)
+		rpcrdma_mr_recycle(mr);
+	else
+		rpcrdma_mr_unmap_and_put(mr);
+}
+
 /**
- * frwr_unmap_sync - invalidate memory regions that were registered for @req
- * @r_xprt: controlling transport
- * @mrs: list of MRs to process
+ * frwr_wc_localinv - Invoked by RDMA provider for a LOCAL_INV WC
+ * @cq:	completion queue (ignored)
+ * @wc:	completed WR
+ *
+ */
+static void frwr_wc_localinv(struct ib_cq *cq, struct ib_wc *wc)
+{
+	struct ib_cqe *cqe = wc->wr_cqe;
+	struct rpcrdma_frwr *frwr =
+		container_of(cqe, struct rpcrdma_frwr, fr_cqe);
+	struct rpcrdma_mr *mr = container_of(frwr, struct rpcrdma_mr, frwr);
+
+	/* WARNING: Only wr_cqe and status are reliable at this point */
+	trace_xprtrdma_wc_li(wc, frwr);
+	__frwr_release_mr(wc, mr);
+}
+
+/**
+ * frwr_wc_localinv_wake - Invoked by RDMA provider for a LOCAL_INV WC
+ * @cq:	completion queue (ignored)
+ * @wc:	completed WR
  *
- * Sleeps until it is safe for the host CPU to access the
- * previously mapped memory regions.
+ * Awaken anyone waiting for an MR to finish being fenced.
+ */
+static void frwr_wc_localinv_wake(struct ib_cq *cq, struct ib_wc *wc)
+{
+	struct ib_cqe *cqe = wc->wr_cqe;
+	struct rpcrdma_frwr *frwr =
+		container_of(cqe, struct rpcrdma_frwr, fr_cqe);
+	struct rpcrdma_mr *mr = container_of(frwr, struct rpcrdma_mr, frwr);
+
+	/* WARNING: Only wr_cqe and status are reliable at this point */
+	trace_xprtrdma_wc_li_wake(wc, frwr);
+	complete(&frwr->fr_linv_done);
+	__frwr_release_mr(wc, mr);
+}
+
+/**
+ * frwr_unmap_sync - invalidate memory regions that were registered for @req
+ * @r_xprt: controlling transport instance
+ * @req: rpcrdma_req with a non-empty list of MRs to process
  *
- * Caller ensures that @mrs is not empty before the call. This
- * function empties the list.
+ * Sleeps until it is safe for the host CPU to access the previously mapped
+ * memory regions. This guarantees that registered MRs are properly fenced
+ * from the server before the RPC consumer accesses the data in them. It
+ * also ensures proper Send flow control: waking the next RPC waits until
+ * this RPC has relinquished all its Send Queue entries.
  */
-void frwr_unmap_sync(struct rpcrdma_xprt *r_xprt, struct list_head *mrs)
+void frwr_unmap_sync(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req)
 {
 	struct ib_send_wr *first, **prev, *last;
 	const struct ib_send_wr *bad_wr;
-	struct rpcrdma_ia *ia = &r_xprt->rx_ia;
 	struct rpcrdma_frwr *frwr;
 	struct rpcrdma_mr *mr;
-	int count, rc;
+	int rc;
 
 	/* ORDER: Invalidate all of the MRs first
 	 *
@@ -544,33 +561,32 @@ void frwr_unmap_sync(struct rpcrdma_xprt *r_xprt, struct list_head *mrs)
 	 * a single ib_post_send() call.
 	 */
 	frwr = NULL;
-	count = 0;
 	prev = &first;
-	list_for_each_entry(mr, mrs, mr_list) {
-		mr->frwr.fr_state = FRWR_IS_INVALID;
+	while (!list_empty(&req->rl_registered)) {
+		mr = rpcrdma_mr_pop(&req->rl_registered);
 
-		frwr = &mr->frwr;
 		trace_xprtrdma_mr_localinv(mr);
+		r_xprt->rx_stats.local_inv_needed++;
 
+		frwr = &mr->frwr;
 		frwr->fr_cqe.done = frwr_wc_localinv;
 		last = &frwr->fr_invwr;
-		memset(last, 0, sizeof(*last));
+		last->next = NULL;
 		last->wr_cqe = &frwr->fr_cqe;
+		last->sg_list = NULL;
+		last->num_sge = 0;
 		last->opcode = IB_WR_LOCAL_INV;
+		last->send_flags = IB_SEND_SIGNALED;
 		last->ex.invalidate_rkey = mr->mr_handle;
-		count++;
 
 		*prev = last;
 		prev = &last->next;
 	}
-	if (!frwr)
-		goto unmap;
 
 	/* Strong send queue ordering guarantees that when the
 	 * last WR in the chain completes, all WRs in the chain
 	 * are complete.
 	 */
-	last->send_flags = IB_SEND_SIGNALED;
 	frwr->fr_cqe.done = frwr_wc_localinv_wake;
 	reinit_completion(&frwr->fr_linv_done);
 
@@ -578,37 +594,126 @@ void frwr_unmap_sync(struct rpcrdma_xprt *r_xprt, struct list_head *mrs)
 	 * replaces the QP. The RPC reply handler won't call us
 	 * unless ri_id->qp is a valid pointer.
 	 */
-	r_xprt->rx_stats.local_inv_needed++;
 	bad_wr = NULL;
-	rc = ib_post_send(ia->ri_id->qp, first, &bad_wr);
+	rc = ib_post_send(r_xprt->rx_ia.ri_id->qp, first, &bad_wr);
+	trace_xprtrdma_post_send(req, rc);
+
+	/* The final LOCAL_INV WR in the chain is supposed to
+	 * do the wake. If it was never posted, the wake will
+	 * not happen, so don't wait in that case.
+	 */
 	if (bad_wr != first)
 		wait_for_completion(&frwr->fr_linv_done);
-	if (rc)
-		goto out_release;
+	if (!rc)
+		return;
 
-	/* ORDER: Now DMA unmap all of the MRs, and return
-	 * them to the free MR list.
+	/* Recycle MRs in the LOCAL_INV chain that did not get posted.
 	 */
-unmap:
-	while (!list_empty(mrs)) {
-		mr = rpcrdma_mr_pop(mrs);
-		rpcrdma_mr_unmap_and_put(mr);
+	while (bad_wr) {
+		frwr = container_of(bad_wr, struct rpcrdma_frwr,
+				    fr_invwr);
+		mr = container_of(frwr, struct rpcrdma_mr, frwr);
+		bad_wr = bad_wr->next;
+
+		list_del_init(&mr->mr_list);
+		rpcrdma_mr_recycle(mr);
 	}
-	return;
+}
 
-out_release:
-	pr_err("rpcrdma: FRWR invalidate ib_post_send returned %i\n", rc);
+/**
+ * frwr_wc_localinv_done - Invoked by RDMA provider for a signaled LOCAL_INV WC
+ * @cq:	completion queue (ignored)
+ * @wc:	completed WR
+ *
+ */
+static void frwr_wc_localinv_done(struct ib_cq *cq, struct ib_wc *wc)
+{
+	struct ib_cqe *cqe = wc->wr_cqe;
+	struct rpcrdma_frwr *frwr =
+		container_of(cqe, struct rpcrdma_frwr, fr_cqe);
+	struct rpcrdma_mr *mr = container_of(frwr, struct rpcrdma_mr, frwr);
 
-	/* Unmap and release the MRs in the LOCAL_INV WRs that did not
-	 * get posted.
+	/* WARNING: Only wr_cqe and status are reliable at this point */
+	trace_xprtrdma_wc_li_done(wc, frwr);
+	rpcrdma_complete_rqst(frwr->fr_req->rl_reply);
+	__frwr_release_mr(wc, mr);
+}
+
+/**
+ * frwr_unmap_async - invalidate memory regions that were registered for @req
+ * @r_xprt: controlling transport instance
+ * @req: rpcrdma_req with a non-empty list of MRs to process
+ *
+ * This guarantees that registered MRs are properly fenced from the
+ * server before the RPC consumer accesses the data in them. It also
+ * ensures proper Send flow control: waking the next RPC waits until
+ * this RPC has relinquished all its Send Queue entries.
+ */
+void frwr_unmap_async(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req)
+{
+	struct ib_send_wr *first, *last, **prev;
+	const struct ib_send_wr *bad_wr;
+	struct rpcrdma_frwr *frwr;
+	struct rpcrdma_mr *mr;
+	int rc;
+
+	/* Chain the LOCAL_INV Work Requests and post them with
+	 * a single ib_post_send() call.
+	 */
+	frwr = NULL;
+	prev = &first;
+	while (!list_empty(&req->rl_registered)) {
+		mr = rpcrdma_mr_pop(&req->rl_registered);
+
+		trace_xprtrdma_mr_localinv(mr);
+		r_xprt->rx_stats.local_inv_needed++;
+
+		frwr = &mr->frwr;
+		frwr->fr_cqe.done = frwr_wc_localinv;
+		frwr->fr_req = req;
+		last = &frwr->fr_invwr;
+		last->next = NULL;
+		last->wr_cqe = &frwr->fr_cqe;
+		last->sg_list = NULL;
+		last->num_sge = 0;
+		last->opcode = IB_WR_LOCAL_INV;
+		last->send_flags = IB_SEND_SIGNALED;
+		last->ex.invalidate_rkey = mr->mr_handle;
+
+		*prev = last;
+		prev = &last->next;
+	}
+
+	/* Strong send queue ordering guarantees that when the
+	 * last WR in the chain completes, all WRs in the chain
+	 * are complete. The last completion will wake up the
+	 * RPC waiter.
+	 */
+	frwr->fr_cqe.done = frwr_wc_localinv_done;
+
+	/* Transport disconnect drains the receive CQ before it
+	 * replaces the QP. The RPC reply handler won't call us
+	 * unless ri_id->qp is a valid pointer.
+	 */
+	bad_wr = NULL;
+	rc = ib_post_send(r_xprt->rx_ia.ri_id->qp, first, &bad_wr);
+	trace_xprtrdma_post_send(req, rc);
+	if (!rc)
+		return;
+
+	/* Recycle MRs in the LOCAL_INV chain that did not get posted.
 	 */
 	while (bad_wr) {
-		frwr = container_of(bad_wr, struct rpcrdma_frwr,
-				    fr_invwr);
+		frwr = container_of(bad_wr, struct rpcrdma_frwr, fr_invwr);
 		mr = container_of(frwr, struct rpcrdma_mr, frwr);
 		bad_wr = bad_wr->next;
 
-		list_del_init(&mr->mr_list);
 		rpcrdma_mr_recycle(mr);
 	}
+
+	/* The final LOCAL_INV WR in the chain is supposed to
+	 * do the wake. If it was never posted, the wake will
+	 * not happen, so wake here in that case.
+	 */
+	rpcrdma_complete_rqst(req->rl_reply);
 }
diff --git a/net/sunrpc/xprtrdma/rpc_rdma.c b/net/sunrpc/xprtrdma/rpc_rdma.c
index 85115a2e2639..4345e6912392 100644
--- a/net/sunrpc/xprtrdma/rpc_rdma.c
+++ b/net/sunrpc/xprtrdma/rpc_rdma.c
@@ -366,6 +366,9 @@ rpcrdma_encode_read_list(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req,
 	unsigned int pos;
 	int nsegs;
 
+	if (rtype == rpcrdma_noch)
+		goto done;
+
 	pos = rqst->rq_snd_buf.head[0].iov_len;
 	if (rtype == rpcrdma_areadch)
 		pos = 0;
@@ -389,7 +392,8 @@ rpcrdma_encode_read_list(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req,
 		nsegs -= mr->mr_nents;
 	} while (nsegs);
 
-	return 0;
+done:
+	return encode_item_not_present(xdr);
 }
 
 /* Register and XDR encode the Write list. Supports encoding a list
@@ -417,6 +421,9 @@ rpcrdma_encode_write_list(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req,
 	int nsegs, nchunks;
 	__be32 *segcount;
 
+	if (wtype != rpcrdma_writech)
+		goto done;
+
 	seg = req->rl_segments;
 	nsegs = rpcrdma_convert_iovs(r_xprt, &rqst->rq_rcv_buf,
 				     rqst->rq_rcv_buf.head[0].iov_len,
@@ -451,7 +458,8 @@ rpcrdma_encode_write_list(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req,
 	/* Update count of segments in this Write chunk */
 	*segcount = cpu_to_be32(nchunks);
 
-	return 0;
+done:
+	return encode_item_not_present(xdr);
 }
 
 /* Register and XDR encode the Reply chunk. Supports encoding an array
@@ -476,6 +484,9 @@ rpcrdma_encode_reply_chunk(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req,
 	int nsegs, nchunks;
 	__be32 *segcount;
 
+	if (wtype != rpcrdma_replych)
+		return encode_item_not_present(xdr);
+
 	seg = req->rl_segments;
 	nsegs = rpcrdma_convert_iovs(r_xprt, &rqst->rq_rcv_buf, 0, wtype, seg);
 	if (nsegs < 0)
@@ -511,6 +522,16 @@ rpcrdma_encode_reply_chunk(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req,
 	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
@@ -520,6 +541,9 @@ void rpcrdma_sendctx_unmap(struct rpcrdma_sendctx *sc)
 {
 	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.
@@ -529,9 +553,7 @@ void rpcrdma_sendctx_unmap(struct rpcrdma_sendctx *sc)
 		ib_dma_unmap_page(sc->sc_device, sge->addr, sge->length,
 				  DMA_TO_DEVICE);
 
-	if (test_and_clear_bit(RPCRDMA_REQ_F_TX_RESOURCES,
-			       &sc->sc_req->rl_flags))
-		wake_up_bit(&sc->sc_req->rl_flags, RPCRDMA_REQ_F_TX_RESOURCES);
+	kref_put(&sc->sc_req->rl_kref, rpcrdma_sendctx_done);
 }
 
 /* Prepare an SGE for the RPC-over-RDMA transport header.
@@ -666,7 +688,7 @@ map_tail:
 out:
 	sc->sc_wr.num_sge += sge_no;
 	if (sc->sc_unmap_count)
-		__set_bit(RPCRDMA_REQ_F_TX_RESOURCES, &req->rl_flags);
+		kref_get(&req->rl_kref);
 	return true;
 
 out_regbuf:
@@ -699,22 +721,28 @@ rpcrdma_prepare_send_sges(struct rpcrdma_xprt *r_xprt,
 			  struct rpcrdma_req *req, u32 hdrlen,
 			  struct xdr_buf *xdr, enum rpcrdma_chunktype rtype)
 {
+	int ret;
+
+	ret = -EAGAIN;
 	req->rl_sendctx = rpcrdma_sendctx_get_locked(r_xprt);
 	if (!req->rl_sendctx)
-		return -EAGAIN;
+		goto err;
 	req->rl_sendctx->sc_wr.num_sge = 0;
 	req->rl_sendctx->sc_unmap_count = 0;
 	req->rl_sendctx->sc_req = req;
-	__clear_bit(RPCRDMA_REQ_F_TX_RESOURCES, &req->rl_flags);
+	kref_init(&req->rl_kref);
 
+	ret = -EIO;
 	if (!rpcrdma_prepare_hdr_sge(r_xprt, req, hdrlen))
-		return -EIO;
-
+		goto err;
 	if (rtype != rpcrdma_areadch)
 		if (!rpcrdma_prepare_msg_sges(r_xprt, req, xdr, rtype))
-			return -EIO;
-
+			goto err;
 	return 0;
+
+err:
+	trace_xprtrdma_prepsend_failed(&req->rl_slot, ret);
+	return ret;
 }
 
 /**
@@ -842,50 +870,28 @@ rpcrdma_marshal_req(struct rpcrdma_xprt *r_xprt, struct rpc_rqst *rqst)
 	 * send a Call message with a Position Zero Read chunk and a
 	 * regular Read chunk at the same time.
 	 */
-	if (rtype != rpcrdma_noch) {
-		ret = rpcrdma_encode_read_list(r_xprt, req, rqst, rtype);
-		if (ret)
-			goto out_err;
-	}
-	ret = encode_item_not_present(xdr);
+	ret = rpcrdma_encode_read_list(r_xprt, req, rqst, rtype);
 	if (ret)
 		goto out_err;
-
-	if (wtype == rpcrdma_writech) {
-		ret = rpcrdma_encode_write_list(r_xprt, req, rqst, wtype);
-		if (ret)
-			goto out_err;
-	}
-	ret = encode_item_not_present(xdr);
+	ret = rpcrdma_encode_write_list(r_xprt, req, rqst, wtype);
 	if (ret)
 		goto out_err;
-
-	if (wtype != rpcrdma_replych)
-		ret = encode_item_not_present(xdr);
-	else
-		ret = rpcrdma_encode_reply_chunk(r_xprt, req, rqst, wtype);
+	ret = rpcrdma_encode_reply_chunk(r_xprt, req, rqst, wtype);
 	if (ret)
 		goto out_err;
 
-	trace_xprtrdma_marshal(rqst, xdr_stream_pos(xdr), rtype, wtype);
-
-	ret = rpcrdma_prepare_send_sges(r_xprt, req, xdr_stream_pos(xdr),
+	ret = rpcrdma_prepare_send_sges(r_xprt, req, req->rl_hdrbuf.len,
 					&rqst->rq_snd_buf, rtype);
 	if (ret)
 		goto out_err;
+
+	trace_xprtrdma_marshal(req, rtype, wtype);
 	return 0;
 
 out_err:
 	trace_xprtrdma_marshal_failed(rqst, ret);
-	switch (ret) {
-	case -EAGAIN:
-		xprt_wait_for_buffer_space(rqst->rq_xprt);
-		break;
-	case -ENOBUFS:
-		break;
-	default:
-		r_xprt->rx_stats.failed_marshal_count++;
-	}
+	r_xprt->rx_stats.failed_marshal_count++;
+	frwr_reset(req);
 	return ret;
 }
 
@@ -1269,51 +1275,17 @@ out_badheader:
 	goto out;
 }
 
-void rpcrdma_release_rqst(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req)
-{
-	/* Invalidate and unmap the data payloads before waking
-	 * the waiting application. This guarantees the memory
-	 * regions are properly fenced from the server before the
-	 * application accesses the data. It also ensures proper
-	 * send flow control: waking the next RPC waits until this
-	 * RPC has relinquished all its Send Queue entries.
-	 */
-	if (!list_empty(&req->rl_registered))
-		frwr_unmap_sync(r_xprt, &req->rl_registered);
-
-	/* Ensure that any DMA mapped pages associated with
-	 * the Send of the RPC Call have been unmapped before
-	 * allowing the RPC to complete. This protects argument
-	 * memory not controlled by the RPC client from being
-	 * re-used before we're done with it.
-	 */
-	if (test_bit(RPCRDMA_REQ_F_TX_RESOURCES, &req->rl_flags)) {
-		r_xprt->rx_stats.reply_waits_for_send++;
-		out_of_line_wait_on_bit(&req->rl_flags,
-					RPCRDMA_REQ_F_TX_RESOURCES,
-					bit_wait,
-					TASK_UNINTERRUPTIBLE);
-	}
-}
-
-/* Reply handling runs in the poll worker thread. Anything that
- * might wait is deferred to a separate workqueue.
- */
-void rpcrdma_deferred_completion(struct work_struct *work)
+static void rpcrdma_reply_done(struct kref *kref)
 {
-	struct rpcrdma_rep *rep =
-			container_of(work, struct rpcrdma_rep, rr_work);
-	struct rpcrdma_req *req = rpcr_to_rdmar(rep->rr_rqst);
-	struct rpcrdma_xprt *r_xprt = rep->rr_rxprt;
+	struct rpcrdma_req *req =
+		container_of(kref, struct rpcrdma_req, rl_kref);
 
-	trace_xprtrdma_defer_cmp(rep);
-	if (rep->rr_wc_flags & IB_WC_WITH_INVALIDATE)
-		frwr_reminv(rep, &req->rl_registered);
-	rpcrdma_release_rqst(r_xprt, req);
-	rpcrdma_complete_rqst(rep);
+	rpcrdma_complete_rqst(req->rl_reply);
 }
 
-/* Process received RPC/RDMA messages.
+/**
+ * rpcrdma_reply_handler - Process received RPC/RDMA messages
+ * @rep: Incoming rpcrdma_rep object to process
  *
  * Errors must result in the RPC task either being awakened, or
  * allowed to timeout, to discover the errors at that time.
@@ -1360,10 +1332,10 @@ void rpcrdma_reply_handler(struct rpcrdma_rep *rep)
 	else if (credits > buf->rb_max_requests)
 		credits = buf->rb_max_requests;
 	if (buf->rb_credits != credits) {
-		spin_lock_bh(&xprt->transport_lock);
+		spin_lock(&xprt->transport_lock);
 		buf->rb_credits = credits;
 		xprt->cwnd = credits << RPC_CWNDSHIFT;
-		spin_unlock_bh(&xprt->transport_lock);
+		spin_unlock(&xprt->transport_lock);
 	}
 
 	req = rpcr_to_rdmar(rqst);
@@ -1373,10 +1345,16 @@ void rpcrdma_reply_handler(struct rpcrdma_rep *rep)
 	}
 	req->rl_reply = rep;
 	rep->rr_rqst = rqst;
-	clear_bit(RPCRDMA_REQ_F_PENDING, &req->rl_flags);
 
 	trace_xprtrdma_reply(rqst->rq_task, rep, req, credits);
-	queue_work(buf->rb_completion_wq, &rep->rr_work);
+
+	if (rep->rr_wc_flags & IB_WC_WITH_INVALIDATE)
+		frwr_reminv(rep, &req->rl_registered);
+	if (!list_empty(&req->rl_registered))
+		frwr_unmap_async(r_xprt, req);
+		/* LocalInv completion will complete the RPC */
+	else
+		kref_put(&req->rl_kref, rpcrdma_reply_done);
 	return;
 
 out_badversion:
diff --git a/net/sunrpc/xprtrdma/svc_rdma_backchannel.c b/net/sunrpc/xprtrdma/svc_rdma_backchannel.c
index bed57d8b5c19..d1fcc41d5eb5 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_backchannel.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_backchannel.c
@@ -72,9 +72,9 @@ int svc_rdma_handle_bc_reply(struct rpc_xprt *xprt, __be32 *rdma_resp,
 	else if (credits > r_xprt->rx_buf.rb_bc_max_requests)
 		credits = r_xprt->rx_buf.rb_bc_max_requests;
 
-	spin_lock_bh(&xprt->transport_lock);
+	spin_lock(&xprt->transport_lock);
 	xprt->cwnd = credits << RPC_CWNDSHIFT;
-	spin_unlock_bh(&xprt->transport_lock);
+	spin_unlock(&xprt->transport_lock);
 
 	spin_lock(&xprt->queue_lock);
 	ret = 0;
diff --git a/net/sunrpc/xprtrdma/svc_rdma_transport.c b/net/sunrpc/xprtrdma/svc_rdma_transport.c
index 0004535c0188..3fe665152d95 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_transport.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_transport.c
@@ -226,9 +226,9 @@ static void handle_connect_req(struct rdma_cm_id *new_cma_id,
 	 * Enqueue the new transport on the accept queue of the listening
 	 * transport
 	 */
-	spin_lock_bh(&listen_xprt->sc_lock);
+	spin_lock(&listen_xprt->sc_lock);
 	list_add_tail(&newxprt->sc_accept_q, &listen_xprt->sc_accept_q);
-	spin_unlock_bh(&listen_xprt->sc_lock);
+	spin_unlock(&listen_xprt->sc_lock);
 
 	set_bit(XPT_CONN, &listen_xprt->sc_xprt.xpt_flags);
 	svc_xprt_enqueue(&listen_xprt->sc_xprt);
@@ -401,7 +401,7 @@ static struct svc_xprt *svc_rdma_accept(struct svc_xprt *xprt)
 	listen_rdma = container_of(xprt, struct svcxprt_rdma, sc_xprt);
 	clear_bit(XPT_CONN, &xprt->xpt_flags);
 	/* Get the next entry off the accept list */
-	spin_lock_bh(&listen_rdma->sc_lock);
+	spin_lock(&listen_rdma->sc_lock);
 	if (!list_empty(&listen_rdma->sc_accept_q)) {
 		newxprt = list_entry(listen_rdma->sc_accept_q.next,
 				     struct svcxprt_rdma, sc_accept_q);
@@ -409,7 +409,7 @@ static struct svc_xprt *svc_rdma_accept(struct svc_xprt *xprt)
 	}
 	if (!list_empty(&listen_rdma->sc_accept_q))
 		set_bit(XPT_CONN, &listen_rdma->sc_xprt.xpt_flags);
-	spin_unlock_bh(&listen_rdma->sc_lock);
+	spin_unlock(&listen_rdma->sc_lock);
 	if (!newxprt)
 		return NULL;
 
diff --git a/net/sunrpc/xprtrdma/transport.c b/net/sunrpc/xprtrdma/transport.c
index 1f73a6a7e43c..2ec349ed4770 100644
--- a/net/sunrpc/xprtrdma/transport.c
+++ b/net/sunrpc/xprtrdma/transport.c
@@ -80,7 +80,6 @@ static unsigned int min_slot_table_size = RPCRDMA_MIN_SLOT_TABLE;
 static unsigned int max_slot_table_size = RPCRDMA_MAX_SLOT_TABLE;
 static unsigned int min_inline_size = RPCRDMA_MIN_INLINE;
 static unsigned int max_inline_size = RPCRDMA_MAX_INLINE;
-static unsigned int zero;
 static unsigned int max_padding = PAGE_SIZE;
 static unsigned int min_memreg = RPCRDMA_BOUNCEBUFFERS;
 static unsigned int max_memreg = RPCRDMA_LAST - 1;
@@ -122,7 +121,7 @@ static struct ctl_table xr_tunables_table[] = {
 		.maxlen		= sizeof(unsigned int),
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec_minmax,
-		.extra1		= &zero,
+		.extra1		= SYSCTL_ZERO,
 		.extra2		= &max_padding,
 	},
 	{
@@ -298,6 +297,7 @@ xprt_rdma_destroy(struct rpc_xprt *xprt)
 	module_put(THIS_MODULE);
 }
 
+/* 60 second timeout, no retries */
 static const struct rpc_timeout xprt_rdma_default_timeout = {
 	.to_initval = 60 * HZ,
 	.to_maxval = 60 * HZ,
@@ -323,8 +323,9 @@ xprt_setup_rdma(struct xprt_create *args)
 	if (!xprt)
 		return ERR_PTR(-ENOMEM);
 
-	/* 60 second timeout, no retries */
 	xprt->timeout = &xprt_rdma_default_timeout;
+	xprt->connect_timeout = xprt->timeout->to_initval;
+	xprt->max_reconnect_timeout = xprt->timeout->to_maxval;
 	xprt->bind_timeout = RPCRDMA_BIND_TO;
 	xprt->reestablish_timeout = RPCRDMA_INIT_REEST_TO;
 	xprt->idle_timeout = RPCRDMA_IDLE_DISC_TO;
@@ -487,31 +488,64 @@ xprt_rdma_timer(struct rpc_xprt *xprt, struct rpc_task *task)
 }
 
 /**
- * xprt_rdma_connect - try to establish a transport connection
+ * xprt_rdma_set_connect_timeout - set timeouts for establishing a connection
+ * @xprt: controlling transport instance
+ * @connect_timeout: reconnect timeout after client disconnects
+ * @reconnect_timeout: reconnect timeout after server disconnects
+ *
+ */
+static void xprt_rdma_tcp_set_connect_timeout(struct rpc_xprt *xprt,
+					      unsigned long connect_timeout,
+					      unsigned long reconnect_timeout)
+{
+	struct rpcrdma_xprt *r_xprt = rpcx_to_rdmax(xprt);
+
+	trace_xprtrdma_op_set_cto(r_xprt, connect_timeout, reconnect_timeout);
+
+	spin_lock(&xprt->transport_lock);
+
+	if (connect_timeout < xprt->connect_timeout) {
+		struct rpc_timeout to;
+		unsigned long initval;
+
+		to = *xprt->timeout;
+		initval = connect_timeout;
+		if (initval < RPCRDMA_INIT_REEST_TO << 1)
+			initval = RPCRDMA_INIT_REEST_TO << 1;
+		to.to_initval = initval;
+		to.to_maxval = initval;
+		r_xprt->rx_timeout = to;
+		xprt->timeout = &r_xprt->rx_timeout;
+		xprt->connect_timeout = connect_timeout;
+	}
+
+	if (reconnect_timeout < xprt->max_reconnect_timeout)
+		xprt->max_reconnect_timeout = reconnect_timeout;
+
+	spin_unlock(&xprt->transport_lock);
+}
+
+/**
+ * xprt_rdma_connect - schedule an attempt to reconnect
  * @xprt: transport state
- * @task: RPC scheduler context
+ * @task: RPC scheduler context (unused)
  *
  */
 static void
 xprt_rdma_connect(struct rpc_xprt *xprt, struct rpc_task *task)
 {
 	struct rpcrdma_xprt *r_xprt = rpcx_to_rdmax(xprt);
+	unsigned long delay;
 
 	trace_xprtrdma_op_connect(r_xprt);
+
+	delay = 0;
 	if (r_xprt->rx_ep.rep_connected != 0) {
-		/* Reconnect */
-		schedule_delayed_work(&r_xprt->rx_connect_worker,
-				      xprt->reestablish_timeout);
-		xprt->reestablish_timeout <<= 1;
-		if (xprt->reestablish_timeout > RPCRDMA_MAX_REEST_TO)
-			xprt->reestablish_timeout = RPCRDMA_MAX_REEST_TO;
-		else if (xprt->reestablish_timeout < RPCRDMA_INIT_REEST_TO)
-			xprt->reestablish_timeout = RPCRDMA_INIT_REEST_TO;
-	} else {
-		schedule_delayed_work(&r_xprt->rx_connect_worker, 0);
-		if (!RPC_IS_ASYNC(task))
-			flush_delayed_work(&r_xprt->rx_connect_worker);
+		delay = xprt_reconnect_delay(xprt);
+		xprt_reconnect_backoff(xprt, RPCRDMA_INIT_REEST_TO);
 	}
+	queue_delayed_work(xprtiod_workqueue, &r_xprt->rx_connect_worker,
+			   delay);
 }
 
 /**
@@ -550,8 +584,11 @@ out_sleep:
 static void
 xprt_rdma_free_slot(struct rpc_xprt *xprt, struct rpc_rqst *rqst)
 {
+	struct rpcrdma_xprt *r_xprt =
+		container_of(xprt, struct rpcrdma_xprt, rx_xprt);
+
 	memset(rqst, 0, sizeof(*rqst));
-	rpcrdma_buffer_put(rpcr_to_rdmar(rqst));
+	rpcrdma_buffer_put(&r_xprt->rx_buf, rpcr_to_rdmar(rqst));
 	rpc_wake_up_next(&xprt->backlog);
 }
 
@@ -618,9 +655,16 @@ xprt_rdma_free(struct rpc_task *task)
 	struct rpcrdma_xprt *r_xprt = rpcx_to_rdmax(rqst->rq_xprt);
 	struct rpcrdma_req *req = rpcr_to_rdmar(rqst);
 
-	if (test_bit(RPCRDMA_REQ_F_PENDING, &req->rl_flags))
-		rpcrdma_release_rqst(r_xprt, req);
 	trace_xprtrdma_op_free(task, req);
+
+	if (!list_empty(&req->rl_registered))
+		frwr_unmap_sync(r_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.
+	 */
 }
 
 /**
@@ -667,7 +711,6 @@ xprt_rdma_send_request(struct rpc_rqst *rqst)
 		goto drop_connection;
 	rqst->rq_xtime = ktime_get();
 
-	__set_bit(RPCRDMA_REQ_F_PENDING, &req->rl_flags);
 	if (rpcrdma_ep_post(&r_xprt->rx_ia, &r_xprt->rx_ep, req))
 		goto drop_connection;
 
@@ -760,6 +803,7 @@ static const struct rpc_xprt_ops xprt_rdma_procs = {
 	.send_request		= xprt_rdma_send_request,
 	.close			= xprt_rdma_close,
 	.destroy		= xprt_rdma_destroy,
+	.set_connect_timeout	= xprt_rdma_tcp_set_connect_timeout,
 	.print_stats		= xprt_rdma_print_stats,
 	.enable_swap		= xprt_rdma_enable_swap,
 	.disable_swap		= xprt_rdma_disable_swap,
@@ -767,6 +811,7 @@ static const struct rpc_xprt_ops xprt_rdma_procs = {
 #if defined(CONFIG_SUNRPC_BACKCHANNEL)
 	.bc_setup		= xprt_rdma_bc_setup,
 	.bc_maxpayload		= xprt_rdma_bc_maxpayload,
+	.bc_num_slots		= xprt_rdma_bc_max_slots,
 	.bc_free_rqst		= xprt_rdma_bc_free_rqst,
 	.bc_destroy		= xprt_rdma_bc_destroy,
 #endif
diff --git a/net/sunrpc/xprtrdma/verbs.c b/net/sunrpc/xprtrdma/verbs.c
index 84bb37924540..805b1f35e1ca 100644
--- a/net/sunrpc/xprtrdma/verbs.c
+++ b/net/sunrpc/xprtrdma/verbs.c
@@ -89,14 +89,12 @@ static void rpcrdma_post_recvs(struct rpcrdma_xprt *r_xprt, bool temp);
  */
 static void rpcrdma_xprt_drain(struct rpcrdma_xprt *r_xprt)
 {
-	struct rpcrdma_buffer *buf = &r_xprt->rx_buf;
 	struct rpcrdma_ia *ia = &r_xprt->rx_ia;
 
 	/* Flush Receives, then wait for deferred Reply work
 	 * to complete.
 	 */
 	ib_drain_rq(ia->ri_id->qp);
-	drain_workqueue(buf->rb_completion_wq);
 
 	/* Deferred Reply processing might have scheduled
 	 * local invalidations.
@@ -901,7 +899,7 @@ out_emptyq:
 	 * completions recently. This is a sign the Send Queue is
 	 * backing up. Cause the caller to pause and try again.
 	 */
-	set_bit(RPCRDMA_BUF_F_EMPTY_SCQ, &buf->rb_flags);
+	xprt_wait_for_buffer_space(&r_xprt->rx_xprt);
 	r_xprt->rx_stats.empty_sendctx_q++;
 	return NULL;
 }
@@ -936,10 +934,7 @@ rpcrdma_sendctx_put_locked(struct rpcrdma_sendctx *sc)
 	/* Paired with READ_ONCE */
 	smp_store_release(&buf->rb_sc_tail, next_tail);
 
-	if (test_and_clear_bit(RPCRDMA_BUF_F_EMPTY_SCQ, &buf->rb_flags)) {
-		smp_mb__after_atomic();
-		xprt_write_space(&sc->sc_xprt->rx_xprt);
-	}
+	xprt_write_space(&sc->sc_xprt->rx_xprt);
 }
 
 static void
@@ -977,8 +972,6 @@ rpcrdma_mrs_create(struct rpcrdma_xprt *r_xprt)
 	r_xprt->rx_stats.mrs_allocated += count;
 	spin_unlock(&buf->rb_mrlock);
 	trace_xprtrdma_createmrs(r_xprt, count);
-
-	xprt_write_space(&r_xprt->rx_xprt);
 }
 
 static void
@@ -990,6 +983,7 @@ rpcrdma_mr_refresh_worker(struct work_struct *work)
 						   rx_buf);
 
 	rpcrdma_mrs_create(r_xprt);
+	xprt_write_space(&r_xprt->rx_xprt);
 }
 
 /**
@@ -1025,7 +1019,6 @@ struct rpcrdma_req *rpcrdma_req_create(struct rpcrdma_xprt *r_xprt, size_t size,
 	if (!req->rl_recvbuf)
 		goto out4;
 
-	req->rl_buffer = buffer;
 	INIT_LIST_HEAD(&req->rl_registered);
 	spin_lock(&buffer->rb_lock);
 	list_add(&req->rl_all, &buffer->rb_allreqs);
@@ -1042,9 +1035,9 @@ out1:
 	return NULL;
 }
 
-static bool rpcrdma_rep_create(struct rpcrdma_xprt *r_xprt, bool temp)
+static struct rpcrdma_rep *rpcrdma_rep_create(struct rpcrdma_xprt *r_xprt,
+					      bool temp)
 {
-	struct rpcrdma_buffer *buf = &r_xprt->rx_buf;
 	struct rpcrdma_rep *rep;
 
 	rep = kzalloc(sizeof(*rep), GFP_KERNEL);
@@ -1055,27 +1048,22 @@ static bool rpcrdma_rep_create(struct rpcrdma_xprt *r_xprt, bool temp)
 					       DMA_FROM_DEVICE, GFP_KERNEL);
 	if (!rep->rr_rdmabuf)
 		goto out_free;
+
 	xdr_buf_init(&rep->rr_hdrbuf, rdmab_data(rep->rr_rdmabuf),
 		     rdmab_length(rep->rr_rdmabuf));
-
 	rep->rr_cqe.done = rpcrdma_wc_receive;
 	rep->rr_rxprt = r_xprt;
-	INIT_WORK(&rep->rr_work, rpcrdma_deferred_completion);
 	rep->rr_recv_wr.next = NULL;
 	rep->rr_recv_wr.wr_cqe = &rep->rr_cqe;
 	rep->rr_recv_wr.sg_list = &rep->rr_rdmabuf->rg_iov;
 	rep->rr_recv_wr.num_sge = 1;
 	rep->rr_temp = temp;
-
-	spin_lock(&buf->rb_lock);
-	list_add(&rep->rr_list, &buf->rb_recv_bufs);
-	spin_unlock(&buf->rb_lock);
-	return true;
+	return rep;
 
 out_free:
 	kfree(rep);
 out:
-	return false;
+	return NULL;
 }
 
 /**
@@ -1089,7 +1077,6 @@ int rpcrdma_buffer_create(struct rpcrdma_xprt *r_xprt)
 	struct rpcrdma_buffer *buf = &r_xprt->rx_buf;
 	int i, rc;
 
-	buf->rb_flags = 0;
 	buf->rb_max_requests = r_xprt->rx_ep.rep_max_requests;
 	buf->rb_bc_srv_max_requests = 0;
 	spin_lock_init(&buf->rb_mrlock);
@@ -1122,15 +1109,6 @@ int rpcrdma_buffer_create(struct rpcrdma_xprt *r_xprt)
 	if (rc)
 		goto out;
 
-	buf->rb_completion_wq = alloc_workqueue("rpcrdma-%s",
-						WQ_MEM_RECLAIM | WQ_HIGHPRI,
-						0,
-			r_xprt->rx_xprt.address_strings[RPC_DISPLAY_ADDR]);
-	if (!buf->rb_completion_wq) {
-		rc = -ENOMEM;
-		goto out;
-	}
-
 	return 0;
 out:
 	rpcrdma_buffer_destroy(buf);
@@ -1204,11 +1182,6 @@ rpcrdma_buffer_destroy(struct rpcrdma_buffer *buf)
 {
 	cancel_delayed_work_sync(&buf->rb_refresh_worker);
 
-	if (buf->rb_completion_wq) {
-		destroy_workqueue(buf->rb_completion_wq);
-		buf->rb_completion_wq = NULL;
-	}
-
 	rpcrdma_sendctxs_destroy(buf);
 
 	while (!list_empty(&buf->rb_recv_bufs)) {
@@ -1325,13 +1298,12 @@ rpcrdma_buffer_get(struct rpcrdma_buffer *buffers)
 
 /**
  * rpcrdma_buffer_put - Put request/reply buffers back into pool
+ * @buffers: buffer pool
  * @req: object to return
  *
  */
-void
-rpcrdma_buffer_put(struct rpcrdma_req *req)
+void rpcrdma_buffer_put(struct rpcrdma_buffer *buffers, struct rpcrdma_req *req)
 {
-	struct rpcrdma_buffer *buffers = req->rl_buffer;
 	struct rpcrdma_rep *rep = req->rl_reply;
 
 	req->rl_reply = NULL;
@@ -1484,8 +1456,7 @@ rpcrdma_ep_post(struct rpcrdma_ia *ia,
 	struct ib_send_wr *send_wr = &req->rl_sendctx->sc_wr;
 	int rc;
 
-	if (!ep->rep_send_count ||
-	    test_bit(RPCRDMA_REQ_F_TX_RESOURCES, &req->rl_flags)) {
+	if (!ep->rep_send_count || kref_read(&req->rl_kref) > 1) {
 		send_wr->send_flags |= IB_SEND_SIGNALED;
 		ep->rep_send_count = ep->rep_send_batch;
 	} else {
@@ -1505,11 +1476,13 @@ rpcrdma_post_recvs(struct rpcrdma_xprt *r_xprt, bool temp)
 {
 	struct rpcrdma_buffer *buf = &r_xprt->rx_buf;
 	struct rpcrdma_ep *ep = &r_xprt->rx_ep;
-	struct ib_recv_wr *wr, *bad_wr;
+	struct ib_recv_wr *i, *wr, *bad_wr;
+	struct rpcrdma_rep *rep;
 	int needed, count, rc;
 
 	rc = 0;
 	count = 0;
+
 	needed = buf->rb_credits + (buf->rb_bc_srv_max_requests << 1);
 	if (ep->rep_receive_count > needed)
 		goto out;
@@ -1517,51 +1490,65 @@ rpcrdma_post_recvs(struct rpcrdma_xprt *r_xprt, bool temp)
 	if (!temp)
 		needed += RPCRDMA_MAX_RECV_BATCH;
 
-	count = 0;
+	/* fast path: all needed reps can be found on the free list */
 	wr = NULL;
+	spin_lock(&buf->rb_lock);
 	while (needed) {
-		struct rpcrdma_regbuf *rb;
-		struct rpcrdma_rep *rep;
-
-		spin_lock(&buf->rb_lock);
 		rep = list_first_entry_or_null(&buf->rb_recv_bufs,
 					       struct rpcrdma_rep, rr_list);
-		if (likely(rep))
-			list_del(&rep->rr_list);
-		spin_unlock(&buf->rb_lock);
-		if (!rep) {
-			if (!rpcrdma_rep_create(r_xprt, temp))
-				break;
-			continue;
-		}
+		if (!rep)
+			break;
 
-		rb = rep->rr_rdmabuf;
-		if (!rpcrdma_regbuf_dma_map(r_xprt, rb)) {
-			rpcrdma_recv_buffer_put(rep);
+		list_del(&rep->rr_list);
+		rep->rr_recv_wr.next = wr;
+		wr = &rep->rr_recv_wr;
+		--needed;
+	}
+	spin_unlock(&buf->rb_lock);
+
+	while (needed) {
+		rep = rpcrdma_rep_create(r_xprt, temp);
+		if (!rep)
 			break;
-		}
 
-		trace_xprtrdma_post_recv(rep->rr_recv_wr.wr_cqe);
 		rep->rr_recv_wr.next = wr;
 		wr = &rep->rr_recv_wr;
-		++count;
 		--needed;
 	}
-	if (!count)
+	if (!wr)
 		goto out;
 
+	for (i = wr; i; i = i->next) {
+		rep = container_of(i, struct rpcrdma_rep, rr_recv_wr);
+
+		if (!rpcrdma_regbuf_dma_map(r_xprt, rep->rr_rdmabuf))
+			goto release_wrs;
+
+		trace_xprtrdma_post_recv(rep->rr_recv_wr.wr_cqe);
+		++count;
+	}
+
 	rc = ib_post_recv(r_xprt->rx_ia.ri_id->qp, wr,
 			  (const struct ib_recv_wr **)&bad_wr);
+out:
+	trace_xprtrdma_post_recvs(r_xprt, count, rc);
 	if (rc) {
-		for (wr = bad_wr; wr; wr = wr->next) {
+		for (wr = bad_wr; wr;) {
 			struct rpcrdma_rep *rep;
 
 			rep = container_of(wr, struct rpcrdma_rep, rr_recv_wr);
+			wr = wr->next;
 			rpcrdma_recv_buffer_put(rep);
 			--count;
 		}
 	}
 	ep->rep_receive_count += count;
-out:
-	trace_xprtrdma_post_recvs(r_xprt, count, rc);
+	return;
+
+release_wrs:
+	for (i = wr; i;) {
+		rep = container_of(i, struct rpcrdma_rep, rr_recv_wr);
+		i = i->next;
+		rpcrdma_recv_buffer_put(rep);
+	}
 }
diff --git a/net/sunrpc/xprtrdma/xprt_rdma.h b/net/sunrpc/xprtrdma/xprt_rdma.h
index d1e0749bcbc4..92ce09fcea74 100644
--- a/net/sunrpc/xprtrdma/xprt_rdma.h
+++ b/net/sunrpc/xprtrdma/xprt_rdma.h
@@ -44,7 +44,8 @@
 
 #include <linux/wait.h> 		/* wait_queue_head_t, etc */
 #include <linux/spinlock.h> 		/* spinlock_t, etc */
-#include <linux/atomic.h>			/* atomic_t, etc */
+#include <linux/atomic.h>		/* atomic_t, etc */
+#include <linux/kref.h>			/* struct kref */
 #include <linux/workqueue.h>		/* struct work_struct */
 
 #include <rdma/rdma_cm.h>		/* RDMA connection api */
@@ -202,10 +203,9 @@ struct rpcrdma_rep {
 	bool			rr_temp;
 	struct rpcrdma_regbuf	*rr_rdmabuf;
 	struct rpcrdma_xprt	*rr_rxprt;
-	struct work_struct	rr_work;
+	struct rpc_rqst		*rr_rqst;
 	struct xdr_buf		rr_hdrbuf;
 	struct xdr_stream	rr_stream;
-	struct rpc_rqst		*rr_rqst;
 	struct list_head	rr_list;
 	struct ib_recv_wr	rr_recv_wr;
 };
@@ -240,18 +240,12 @@ struct rpcrdma_sendctx {
  * An external memory region is any buffer or page that is registered
  * on the fly (ie, not pre-registered).
  */
-enum rpcrdma_frwr_state {
-	FRWR_IS_INVALID,	/* ready to be used */
-	FRWR_IS_VALID,		/* in use */
-	FRWR_FLUSHED_FR,	/* flushed FASTREG WR */
-	FRWR_FLUSHED_LI,	/* flushed LOCALINV WR */
-};
-
+struct rpcrdma_req;
 struct rpcrdma_frwr {
 	struct ib_mr			*fr_mr;
 	struct ib_cqe			fr_cqe;
-	enum rpcrdma_frwr_state		fr_state;
 	struct completion		fr_linv_done;
+	struct rpcrdma_req		*fr_req;
 	union {
 		struct ib_reg_wr	fr_regwr;
 		struct ib_send_wr	fr_invwr;
@@ -326,7 +320,6 @@ struct rpcrdma_buffer;
 struct rpcrdma_req {
 	struct list_head	rl_list;
 	struct rpc_rqst		rl_slot;
-	struct rpcrdma_buffer	*rl_buffer;
 	struct rpcrdma_rep	*rl_reply;
 	struct xdr_stream	rl_stream;
 	struct xdr_buf		rl_hdrbuf;
@@ -336,18 +329,12 @@ struct rpcrdma_req {
 	struct rpcrdma_regbuf	*rl_recvbuf;	/* rq_rcv_buf */
 
 	struct list_head	rl_all;
-	unsigned long		rl_flags;
+	struct kref		rl_kref;
 
 	struct list_head	rl_registered;	/* registered segments */
 	struct rpcrdma_mr_seg	rl_segments[RPCRDMA_MAX_SEGS];
 };
 
-/* rl_flags */
-enum {
-	RPCRDMA_REQ_F_PENDING = 0,
-	RPCRDMA_REQ_F_TX_RESOURCES,
-};
-
 static inline struct rpcrdma_req *
 rpcr_to_rdmar(const struct rpc_rqst *rqst)
 {
@@ -391,22 +378,15 @@ struct rpcrdma_buffer {
 	struct list_head	rb_recv_bufs;
 	struct list_head	rb_allreqs;
 
-	unsigned long		rb_flags;
 	u32			rb_max_requests;
 	u32			rb_credits;	/* most recent credit grant */
 
 	u32			rb_bc_srv_max_requests;
 	u32			rb_bc_max_requests;
 
-	struct workqueue_struct *rb_completion_wq;
 	struct delayed_work	rb_refresh_worker;
 };
 
-/* rb_flags */
-enum {
-	RPCRDMA_BUF_F_EMPTY_SCQ = 0,
-};
-
 /*
  * Statistics for RPCRDMA
  */
@@ -452,6 +432,7 @@ struct rpcrdma_xprt {
 	struct rpcrdma_ep	rx_ep;
 	struct rpcrdma_buffer	rx_buf;
 	struct delayed_work	rx_connect_worker;
+	struct rpc_timeout	rx_timeout;
 	struct rpcrdma_stats	rx_stats;
 };
 
@@ -518,7 +499,8 @@ rpcrdma_mr_recycle(struct rpcrdma_mr *mr)
 }
 
 struct rpcrdma_req *rpcrdma_buffer_get(struct rpcrdma_buffer *);
-void rpcrdma_buffer_put(struct rpcrdma_req *);
+void rpcrdma_buffer_put(struct rpcrdma_buffer *buffers,
+			struct rpcrdma_req *req);
 void rpcrdma_recv_buffer_put(struct rpcrdma_rep *);
 
 bool rpcrdma_regbuf_realloc(struct rpcrdma_regbuf *rb, size_t size,
@@ -564,6 +546,7 @@ rpcrdma_data_dir(bool writing)
 /* Memory registration calls xprtrdma/frwr_ops.c
  */
 bool frwr_is_supported(struct ib_device *device);
+void frwr_reset(struct rpcrdma_req *req);
 int frwr_open(struct rpcrdma_ia *ia, struct rpcrdma_ep *ep);
 int frwr_init_mr(struct rpcrdma_ia *ia, struct rpcrdma_mr *mr);
 void frwr_release_mr(struct rpcrdma_mr *mr);
@@ -574,8 +557,8 @@ struct rpcrdma_mr_seg *frwr_map(struct rpcrdma_xprt *r_xprt,
 				struct rpcrdma_mr **mr);
 int frwr_send(struct rpcrdma_ia *ia, struct rpcrdma_req *req);
 void frwr_reminv(struct rpcrdma_rep *rep, struct list_head *mrs);
-void frwr_unmap_sync(struct rpcrdma_xprt *r_xprt,
-		     struct list_head *mrs);
+void frwr_unmap_sync(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req);
+void frwr_unmap_async(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req);
 
 /*
  * RPC/RDMA protocol calls - xprtrdma/rpc_rdma.c
@@ -598,9 +581,6 @@ int rpcrdma_marshal_req(struct rpcrdma_xprt *r_xprt, struct rpc_rqst *rqst);
 void rpcrdma_set_max_header_sizes(struct rpcrdma_xprt *);
 void rpcrdma_complete_rqst(struct rpcrdma_rep *rep);
 void rpcrdma_reply_handler(struct rpcrdma_rep *rep);
-void rpcrdma_release_rqst(struct rpcrdma_xprt *r_xprt,
-			  struct rpcrdma_req *req);
-void rpcrdma_deferred_completion(struct work_struct *work);
 
 static inline void rpcrdma_set_xdrlen(struct xdr_buf *xdr, size_t len)
 {
@@ -625,6 +605,7 @@ void xprt_rdma_cleanup(void);
 #if defined(CONFIG_SUNRPC_BACKCHANNEL)
 int xprt_rdma_bc_setup(struct rpc_xprt *, unsigned int);
 size_t xprt_rdma_bc_maxpayload(struct rpc_xprt *);
+unsigned int xprt_rdma_bc_max_slots(struct rpc_xprt *);
 int rpcrdma_bc_post_recv(struct rpcrdma_xprt *, unsigned int);
 void rpcrdma_bc_receive_call(struct rpcrdma_xprt *, struct rpcrdma_rep *);
 int xprt_rdma_bc_send_reply(struct rpc_rqst *rqst);
diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c
index 36652352a38c..e2176c167a57 100644
--- a/net/sunrpc/xprtsock.c
+++ b/net/sunrpc/xprtsock.c
@@ -880,7 +880,7 @@ static int xs_nospace(struct rpc_rqst *req)
 			req->rq_slen);
 
 	/* Protect against races with write_space */
-	spin_lock_bh(&xprt->transport_lock);
+	spin_lock(&xprt->transport_lock);
 
 	/* Don't race with disconnect */
 	if (xprt_connected(xprt)) {
@@ -890,7 +890,7 @@ static int xs_nospace(struct rpc_rqst *req)
 	} else
 		ret = -ENOTCONN;
 
-	spin_unlock_bh(&xprt->transport_lock);
+	spin_unlock(&xprt->transport_lock);
 
 	/* Race breaker in case memory is freed before above code is called */
 	if (ret == -EAGAIN) {
@@ -909,6 +909,7 @@ static int xs_nospace(struct rpc_rqst *req)
 static void
 xs_stream_prepare_request(struct rpc_rqst *req)
 {
+	xdr_free_bvec(&req->rq_rcv_buf);
 	req->rq_task->tk_status = xdr_alloc_bvec(&req->rq_rcv_buf, GFP_KERNEL);
 }
 
@@ -1211,6 +1212,15 @@ static void xs_sock_reset_state_flags(struct rpc_xprt *xprt)
 	struct sock_xprt *transport = container_of(xprt, struct sock_xprt, xprt);
 
 	clear_bit(XPRT_SOCK_DATA_READY, &transport->sock_state);
+	clear_bit(XPRT_SOCK_WAKE_ERROR, &transport->sock_state);
+	clear_bit(XPRT_SOCK_WAKE_WRITE, &transport->sock_state);
+	clear_bit(XPRT_SOCK_WAKE_DISCONNECT, &transport->sock_state);
+}
+
+static void xs_run_error_worker(struct sock_xprt *transport, unsigned int nr)
+{
+	set_bit(nr, &transport->sock_state);
+	queue_work(xprtiod_workqueue, &transport->error_worker);
 }
 
 static void xs_sock_reset_connection_flags(struct rpc_xprt *xprt)
@@ -1231,6 +1241,7 @@ static void xs_sock_reset_connection_flags(struct rpc_xprt *xprt)
  */
 static void xs_error_report(struct sock *sk)
 {
+	struct sock_xprt *transport;
 	struct rpc_xprt *xprt;
 	int err;
 
@@ -1238,13 +1249,14 @@ static void xs_error_report(struct sock *sk)
 	if (!(xprt = xprt_from_sock(sk)))
 		goto out;
 
+	transport = container_of(xprt, struct sock_xprt, xprt);
 	err = -sk->sk_err;
 	if (err == 0)
 		goto out;
 	dprintk("RPC:       xs_error_report client %p, error=%d...\n",
 			xprt, -err);
 	trace_rpc_socket_error(xprt, sk->sk_socket, err);
-	xprt_wake_pending_tasks(xprt, err);
+	xs_run_error_worker(transport, XPRT_SOCK_WAKE_ERROR);
  out:
 	read_unlock_bh(&sk->sk_callback_lock);
 }
@@ -1333,6 +1345,7 @@ static void xs_destroy(struct rpc_xprt *xprt)
 	cancel_delayed_work_sync(&transport->connect_worker);
 	xs_close(xprt);
 	cancel_work_sync(&transport->recv_worker);
+	cancel_work_sync(&transport->error_worker);
 	xs_xprt_free(xprt);
 	module_put(THIS_MODULE);
 }
@@ -1386,9 +1399,9 @@ static void xs_udp_data_read_skb(struct rpc_xprt *xprt,
 	}
 
 
-	spin_lock_bh(&xprt->transport_lock);
+	spin_lock(&xprt->transport_lock);
 	xprt_adjust_cwnd(xprt, task, copied);
-	spin_unlock_bh(&xprt->transport_lock);
+	spin_unlock(&xprt->transport_lock);
 	spin_lock(&xprt->queue_lock);
 	xprt_complete_rqst(task, copied);
 	__UDPX_INC_STATS(sk, UDP_MIB_INDATAGRAMS);
@@ -1498,7 +1511,6 @@ static void xs_tcp_state_change(struct sock *sk)
 	trace_rpc_socket_state_change(xprt, sk->sk_socket);
 	switch (sk->sk_state) {
 	case TCP_ESTABLISHED:
-		spin_lock(&xprt->transport_lock);
 		if (!xprt_test_and_set_connected(xprt)) {
 			xprt->connect_cookie++;
 			clear_bit(XPRT_SOCK_CONNECTING, &transport->sock_state);
@@ -1507,9 +1519,8 @@ static void xs_tcp_state_change(struct sock *sk)
 			xprt->stat.connect_count++;
 			xprt->stat.connect_time += (long)jiffies -
 						   xprt->stat.connect_start;
-			xprt_wake_pending_tasks(xprt, -EAGAIN);
+			xs_run_error_worker(transport, XPRT_SOCK_WAKE_PENDING);
 		}
-		spin_unlock(&xprt->transport_lock);
 		break;
 	case TCP_FIN_WAIT1:
 		/* The client initiated a shutdown of the socket */
@@ -1525,7 +1536,7 @@ static void xs_tcp_state_change(struct sock *sk)
 		/* The server initiated a shutdown of the socket */
 		xprt->connect_cookie++;
 		clear_bit(XPRT_CONNECTED, &xprt->state);
-		xs_tcp_force_close(xprt);
+		xs_run_error_worker(transport, XPRT_SOCK_WAKE_DISCONNECT);
 		/* fall through */
 	case TCP_CLOSING:
 		/*
@@ -1547,7 +1558,7 @@ static void xs_tcp_state_change(struct sock *sk)
 			xprt_clear_connecting(xprt);
 		clear_bit(XPRT_CLOSING, &xprt->state);
 		/* Trigger the socket release */
-		xs_tcp_force_close(xprt);
+		xs_run_error_worker(transport, XPRT_SOCK_WAKE_DISCONNECT);
 	}
  out:
 	read_unlock_bh(&sk->sk_callback_lock);
@@ -1556,6 +1567,7 @@ static void xs_tcp_state_change(struct sock *sk)
 static void xs_write_space(struct sock *sk)
 {
 	struct socket_wq *wq;
+	struct sock_xprt *transport;
 	struct rpc_xprt *xprt;
 
 	if (!sk->sk_socket)
@@ -1564,13 +1576,14 @@ static void xs_write_space(struct sock *sk)
 
 	if (unlikely(!(xprt = xprt_from_sock(sk))))
 		return;
+	transport = container_of(xprt, struct sock_xprt, xprt);
 	rcu_read_lock();
 	wq = rcu_dereference(sk->sk_wq);
 	if (!wq || test_and_clear_bit(SOCKWQ_ASYNC_NOSPACE, &wq->flags) == 0)
 		goto out;
 
-	if (xprt_write_space(xprt))
-		sk->sk_write_pending--;
+	xs_run_error_worker(transport, XPRT_SOCK_WAKE_WRITE);
+	sk->sk_write_pending--;
 out:
 	rcu_read_unlock();
 }
@@ -1664,9 +1677,9 @@ static void xs_udp_set_buffer_size(struct rpc_xprt *xprt, size_t sndsize, size_t
  */
 static void xs_udp_timer(struct rpc_xprt *xprt, struct rpc_task *task)
 {
-	spin_lock_bh(&xprt->transport_lock);
+	spin_lock(&xprt->transport_lock);
 	xprt_adjust_cwnd(xprt, task, -ETIMEDOUT);
-	spin_unlock_bh(&xprt->transport_lock);
+	spin_unlock(&xprt->transport_lock);
 }
 
 static int xs_get_random_port(void)
@@ -2201,13 +2214,13 @@ static void xs_tcp_set_socket_timeouts(struct rpc_xprt *xprt,
 	unsigned int opt_on = 1;
 	unsigned int timeo;
 
-	spin_lock_bh(&xprt->transport_lock);
+	spin_lock(&xprt->transport_lock);
 	keepidle = DIV_ROUND_UP(xprt->timeout->to_initval, HZ);
 	keepcnt = xprt->timeout->to_retries + 1;
 	timeo = jiffies_to_msecs(xprt->timeout->to_initval) *
 		(xprt->timeout->to_retries + 1);
 	clear_bit(XPRT_SOCK_UPD_TIMEOUT, &transport->sock_state);
-	spin_unlock_bh(&xprt->transport_lock);
+	spin_unlock(&xprt->transport_lock);
 
 	/* TCP Keepalive options */
 	kernel_setsockopt(sock, SOL_SOCKET, SO_KEEPALIVE,
@@ -2232,7 +2245,7 @@ static void xs_tcp_set_connect_timeout(struct rpc_xprt *xprt,
 	struct rpc_timeout to;
 	unsigned long initval;
 
-	spin_lock_bh(&xprt->transport_lock);
+	spin_lock(&xprt->transport_lock);
 	if (reconnect_timeout < xprt->max_reconnect_timeout)
 		xprt->max_reconnect_timeout = reconnect_timeout;
 	if (connect_timeout < xprt->connect_timeout) {
@@ -2249,7 +2262,7 @@ static void xs_tcp_set_connect_timeout(struct rpc_xprt *xprt,
 		xprt->connect_timeout = connect_timeout;
 	}
 	set_bit(XPRT_SOCK_UPD_TIMEOUT, &transport->sock_state);
-	spin_unlock_bh(&xprt->transport_lock);
+	spin_unlock(&xprt->transport_lock);
 }
 
 static int xs_tcp_finish_connecting(struct rpc_xprt *xprt, struct socket *sock)
@@ -2402,25 +2415,6 @@ out:
 	xprt_wake_pending_tasks(xprt, status);
 }
 
-static unsigned long xs_reconnect_delay(const struct rpc_xprt *xprt)
-{
-	unsigned long start, now = jiffies;
-
-	start = xprt->stat.connect_start + xprt->reestablish_timeout;
-	if (time_after(start, now))
-		return start - now;
-	return 0;
-}
-
-static void xs_reconnect_backoff(struct rpc_xprt *xprt)
-{
-	xprt->reestablish_timeout <<= 1;
-	if (xprt->reestablish_timeout > xprt->max_reconnect_timeout)
-		xprt->reestablish_timeout = xprt->max_reconnect_timeout;
-	if (xprt->reestablish_timeout < XS_TCP_INIT_REEST_TO)
-		xprt->reestablish_timeout = XS_TCP_INIT_REEST_TO;
-}
-
 /**
  * xs_connect - connect a socket to a remote endpoint
  * @xprt: pointer to transport structure
@@ -2450,8 +2444,8 @@ static void xs_connect(struct rpc_xprt *xprt, struct rpc_task *task)
 		/* Start by resetting any existing state */
 		xs_reset_transport(transport);
 
-		delay = xs_reconnect_delay(xprt);
-		xs_reconnect_backoff(xprt);
+		delay = xprt_reconnect_delay(xprt);
+		xprt_reconnect_backoff(xprt, XS_TCP_INIT_REEST_TO);
 
 	} else
 		dprintk("RPC:       xs_connect scheduled xprt %p\n", xprt);
@@ -2461,6 +2455,56 @@ static void xs_connect(struct rpc_xprt *xprt, struct rpc_task *task)
 			delay);
 }
 
+static void xs_wake_disconnect(struct sock_xprt *transport)
+{
+	if (test_and_clear_bit(XPRT_SOCK_WAKE_DISCONNECT, &transport->sock_state))
+		xs_tcp_force_close(&transport->xprt);
+}
+
+static void xs_wake_write(struct sock_xprt *transport)
+{
+	if (test_and_clear_bit(XPRT_SOCK_WAKE_WRITE, &transport->sock_state))
+		xprt_write_space(&transport->xprt);
+}
+
+static void xs_wake_error(struct sock_xprt *transport)
+{
+	int sockerr;
+	int sockerr_len = sizeof(sockerr);
+
+	if (!test_bit(XPRT_SOCK_WAKE_ERROR, &transport->sock_state))
+		return;
+	mutex_lock(&transport->recv_mutex);
+	if (transport->sock == NULL)
+		goto out;
+	if (!test_and_clear_bit(XPRT_SOCK_WAKE_ERROR, &transport->sock_state))
+		goto out;
+	if (kernel_getsockopt(transport->sock, SOL_SOCKET, SO_ERROR,
+				(char *)&sockerr, &sockerr_len) != 0)
+		goto out;
+	if (sockerr < 0)
+		xprt_wake_pending_tasks(&transport->xprt, sockerr);
+out:
+	mutex_unlock(&transport->recv_mutex);
+}
+
+static void xs_wake_pending(struct sock_xprt *transport)
+{
+	if (test_and_clear_bit(XPRT_SOCK_WAKE_PENDING, &transport->sock_state))
+		xprt_wake_pending_tasks(&transport->xprt, -EAGAIN);
+}
+
+static void xs_error_handle(struct work_struct *work)
+{
+	struct sock_xprt *transport = container_of(work,
+			struct sock_xprt, error_worker);
+
+	xs_wake_disconnect(transport);
+	xs_wake_write(transport);
+	xs_wake_error(transport);
+	xs_wake_pending(transport);
+}
+
 /**
  * xs_local_print_stats - display AF_LOCAL socket-specifc stats
  * @xprt: rpc_xprt struct containing statistics
@@ -2745,6 +2789,7 @@ static const struct rpc_xprt_ops xs_tcp_ops = {
 #ifdef CONFIG_SUNRPC_BACKCHANNEL
 	.bc_setup		= xprt_setup_bc,
 	.bc_maxpayload		= xs_tcp_bc_maxpayload,
+	.bc_num_slots		= xprt_bc_max_slots,
 	.bc_free_rqst		= xprt_free_bc_rqst,
 	.bc_destroy		= xprt_destroy_bc,
 #endif
@@ -2873,6 +2918,7 @@ static struct rpc_xprt *xs_setup_local(struct xprt_create *args)
 	xprt->timeout = &xs_local_default_timeout;
 
 	INIT_WORK(&transport->recv_worker, xs_stream_data_receive_workfn);
+	INIT_WORK(&transport->error_worker, xs_error_handle);
 	INIT_DELAYED_WORK(&transport->connect_worker, xs_dummy_setup_socket);
 
 	switch (sun->sun_family) {
@@ -2943,6 +2989,7 @@ static struct rpc_xprt *xs_setup_udp(struct xprt_create *args)
 	xprt->timeout = &xs_udp_default_timeout;
 
 	INIT_WORK(&transport->recv_worker, xs_udp_data_receive_workfn);
+	INIT_WORK(&transport->error_worker, xs_error_handle);
 	INIT_DELAYED_WORK(&transport->connect_worker, xs_udp_setup_socket);
 
 	switch (addr->sa_family) {
@@ -3024,6 +3071,7 @@ static struct rpc_xprt *xs_setup_tcp(struct xprt_create *args)
 		(xprt->timeout->to_retries + 1);
 
 	INIT_WORK(&transport->recv_worker, xs_stream_data_receive_workfn);
+	INIT_WORK(&transport->error_worker, xs_error_handle);
 	INIT_DELAYED_WORK(&transport->connect_worker, xs_tcp_setup_socket);
 
 	switch (addr->sa_family) {
diff --git a/net/tipc/addr.c b/net/tipc/addr.c
index b88d48d00913..0f1eaed1bd1b 100644
--- a/net/tipc/addr.c
+++ b/net/tipc/addr.c
@@ -75,6 +75,7 @@ void tipc_set_node_addr(struct net *net, u32 addr)
 		tipc_set_node_id(net, node_id);
 	}
 	tn->trial_addr = addr;
+	tn->addr_trial_end = jiffies;
 	pr_info("32-bit node address hash set to %x\n", addr);
 }
 
diff --git a/net/tipc/link.c b/net/tipc/link.c
index 66d3a07bc571..c2c5c53cad22 100644
--- a/net/tipc/link.c
+++ b/net/tipc/link.c
@@ -106,8 +106,6 @@ struct tipc_stats {
  * @transmitq: queue for sent, non-acked messages
  * @backlogq: queue for messages waiting to be sent
  * @snt_nxt: next sequence number to use for outbound messages
- * @prev_from: sequence number of most previous retransmission request
- * @stale_limit: time when repeated identical retransmits must force link reset
  * @ackers: # of peers that needs to ack each packet before it can be released
  * @acked: # last packet acked by a certain peer. Used for broadcast.
  * @rcv_nxt: next sequence number to expect for inbound messages
@@ -164,9 +162,7 @@ struct tipc_link {
 		u16 limit;
 	} backlog[5];
 	u16 snd_nxt;
-	u16 prev_from;
 	u16 window;
-	unsigned long stale_limit;
 
 	/* Reception */
 	u16 rcv_nxt;
@@ -1044,47 +1040,53 @@ static void tipc_link_advance_backlog(struct tipc_link *l,
  * link_retransmit_failure() - Detect repeated retransmit failures
  * @l: tipc link sender
  * @r: tipc link receiver (= l in case of unicast)
- * @from: seqno of the 1st packet in retransmit request
  * @rc: returned code
  *
  * Return: true if the repeated retransmit failures happens, otherwise
  * false
  */
 static bool link_retransmit_failure(struct tipc_link *l, struct tipc_link *r,
-				    u16 from, int *rc)
+				    int *rc)
 {
 	struct sk_buff *skb = skb_peek(&l->transmq);
 	struct tipc_msg *hdr;
 
 	if (!skb)
 		return false;
-	hdr = buf_msg(skb);
 
-	/* Detect repeated retransmit failures on same packet */
-	if (r->prev_from != from) {
-		r->prev_from = from;
-		r->stale_limit = jiffies + msecs_to_jiffies(r->tolerance);
-	} else if (time_after(jiffies, r->stale_limit)) {
-		pr_warn("Retransmission failure on link <%s>\n", l->name);
-		link_print(l, "State of link ");
-		pr_info("Failed msg: usr %u, typ %u, len %u, err %u\n",
-			msg_user(hdr), msg_type(hdr), msg_size(hdr),
-			msg_errcode(hdr));
-		pr_info("sqno %u, prev: %x, src: %x\n",
-			msg_seqno(hdr), msg_prevnode(hdr), msg_orignode(hdr));
-
-		trace_tipc_list_dump(&l->transmq, true, "retrans failure!");
-		trace_tipc_link_dump(l, TIPC_DUMP_NONE, "retrans failure!");
-		trace_tipc_link_dump(r, TIPC_DUMP_NONE, "retrans failure!");
+	if (!TIPC_SKB_CB(skb)->retr_cnt)
+		return false;
 
-		if (link_is_bc_sndlink(l))
-			*rc = TIPC_LINK_DOWN_EVT;
+	if (!time_after(jiffies, TIPC_SKB_CB(skb)->retr_stamp +
+			msecs_to_jiffies(r->tolerance)))
+		return false;
+
+	hdr = buf_msg(skb);
+	if (link_is_bc_sndlink(l) && !less(r->acked, msg_seqno(hdr)))
+		return false;
 
+	pr_warn("Retransmission failure on link <%s>\n", l->name);
+	link_print(l, "State of link ");
+	pr_info("Failed msg: usr %u, typ %u, len %u, err %u\n",
+		msg_user(hdr), msg_type(hdr), msg_size(hdr), msg_errcode(hdr));
+	pr_info("sqno %u, prev: %x, dest: %x\n",
+		msg_seqno(hdr), msg_prevnode(hdr), msg_destnode(hdr));
+	pr_info("retr_stamp %d, retr_cnt %d\n",
+		jiffies_to_msecs(TIPC_SKB_CB(skb)->retr_stamp),
+		TIPC_SKB_CB(skb)->retr_cnt);
+
+	trace_tipc_list_dump(&l->transmq, true, "retrans failure!");
+	trace_tipc_link_dump(l, TIPC_DUMP_NONE, "retrans failure!");
+	trace_tipc_link_dump(r, TIPC_DUMP_NONE, "retrans failure!");
+
+	if (link_is_bc_sndlink(l)) {
+		r->state = LINK_RESET;
+		*rc = TIPC_LINK_DOWN_EVT;
+	} else {
 		*rc = tipc_link_fsm_evt(l, LINK_FAILURE_EVT);
-		return true;
 	}
 
-	return false;
+	return true;
 }
 
 /* tipc_link_bc_retrans() - retransmit zero or more packets
@@ -1110,7 +1112,7 @@ static int tipc_link_bc_retrans(struct tipc_link *l, struct tipc_link *r,
 
 	trace_tipc_link_retrans(r, from, to, &l->transmq);
 
-	if (link_retransmit_failure(l, r, from, &rc))
+	if (link_retransmit_failure(l, r, &rc))
 		return rc;
 
 	skb_queue_walk(&l->transmq, skb) {
@@ -1119,11 +1121,10 @@ static int tipc_link_bc_retrans(struct tipc_link *l, struct tipc_link *r,
 			continue;
 		if (more(msg_seqno(hdr), to))
 			break;
-		if (link_is_bc_sndlink(l)) {
-			if (time_before(jiffies, TIPC_SKB_CB(skb)->nxt_retr))
-				continue;
-			TIPC_SKB_CB(skb)->nxt_retr = TIPC_BC_RETR_LIM;
-		}
+
+		if (time_before(jiffies, TIPC_SKB_CB(skb)->nxt_retr))
+			continue;
+		TIPC_SKB_CB(skb)->nxt_retr = TIPC_BC_RETR_LIM;
 		_skb = __pskb_copy(skb, LL_MAX_HEADER + MIN_H_SIZE, GFP_ATOMIC);
 		if (!_skb)
 			return 0;
@@ -1133,6 +1134,10 @@ static int tipc_link_bc_retrans(struct tipc_link *l, struct tipc_link *r,
 		_skb->priority = TC_PRIO_CONTROL;
 		__skb_queue_tail(xmitq, _skb);
 		l->stats.retransmitted++;
+
+		/* Increase actual retrans counter & mark first time */
+		if (!TIPC_SKB_CB(skb)->retr_cnt++)
+			TIPC_SKB_CB(skb)->retr_stamp = jiffies;
 	}
 	return 0;
 }
@@ -1357,12 +1362,10 @@ static int tipc_link_advance_transmq(struct tipc_link *l, u16 acked, u16 gap,
 	struct tipc_msg *hdr;
 	u16 bc_ack = l->bc_rcvlink->rcv_nxt - 1;
 	u16 ack = l->rcv_nxt - 1;
+	bool passed = false;
 	u16 seqno, n = 0;
 	int rc = 0;
 
-	if (gap && link_retransmit_failure(l, l, acked + 1, &rc))
-		return rc;
-
 	skb_queue_walk_safe(&l->transmq, skb, tmp) {
 		seqno = buf_seqno(skb);
 
@@ -1372,12 +1375,17 @@ next_gap_ack:
 			__skb_unlink(skb, &l->transmq);
 			kfree_skb(skb);
 		} else if (less_eq(seqno, acked + gap)) {
-			/* retransmit skb */
+			/* First, check if repeated retrans failures occurs? */
+			if (!passed && link_retransmit_failure(l, l, &rc))
+				return rc;
+			passed = true;
+
+			/* retransmit skb if unrestricted*/
 			if (time_before(jiffies, TIPC_SKB_CB(skb)->nxt_retr))
 				continue;
 			TIPC_SKB_CB(skb)->nxt_retr = TIPC_UC_RETR_TIME;
-
-			_skb = __pskb_copy(skb, MIN_H_SIZE, GFP_ATOMIC);
+			_skb = __pskb_copy(skb, LL_MAX_HEADER + MIN_H_SIZE,
+					   GFP_ATOMIC);
 			if (!_skb)
 				continue;
 			hdr = buf_msg(_skb);
@@ -1386,6 +1394,10 @@ next_gap_ack:
 			_skb->priority = TC_PRIO_CONTROL;
 			__skb_queue_tail(xmitq, _skb);
 			l->stats.retransmitted++;
+
+			/* Increase actual retrans counter & mark first time */
+			if (!TIPC_SKB_CB(skb)->retr_cnt++)
+				TIPC_SKB_CB(skb)->retr_stamp = jiffies;
 		} else {
 			/* retry with Gap ACK blocks if any */
 			if (!ga || n >= ga->gack_cnt)
@@ -2577,7 +2589,7 @@ int tipc_link_dump(struct tipc_link *l, u16 dqueues, char *buf)
 	i += scnprintf(buf + i, sz - i, " %x", l->peer_caps);
 	i += scnprintf(buf + i, sz - i, " %u", l->silent_intv_cnt);
 	i += scnprintf(buf + i, sz - i, " %u", l->rst_cnt);
-	i += scnprintf(buf + i, sz - i, " %u", l->prev_from);
+	i += scnprintf(buf + i, sz - i, " %u", 0);
 	i += scnprintf(buf + i, sz - i, " %u", 0);
 	i += scnprintf(buf + i, sz - i, " %u", l->acked);
 
diff --git a/net/tipc/msg.h b/net/tipc/msg.h
index da509f0eb9ca..d7ebc9e955f6 100644
--- a/net/tipc/msg.h
+++ b/net/tipc/msg.h
@@ -102,13 +102,15 @@ struct plist;
 #define TIPC_MEDIA_INFO_OFFSET	5
 
 struct tipc_skb_cb {
-	u32 bytes_read;
-	u32 orig_member;
 	struct sk_buff *tail;
 	unsigned long nxt_retr;
-	bool validated;
+	unsigned long retr_stamp;
+	u32 bytes_read;
+	u32 orig_member;
 	u16 chain_imp;
 	u16 ackers;
+	u16 retr_cnt;
+	bool validated;
 };
 
 #define TIPC_SKB_CB(__skb) ((struct tipc_skb_cb *)&((__skb)->cb[0]))
diff --git a/net/tipc/name_distr.c b/net/tipc/name_distr.c
index 61219f0b9677..44abc8e9c990 100644
--- a/net/tipc/name_distr.c
+++ b/net/tipc/name_distr.c
@@ -190,7 +190,7 @@ void tipc_named_node_up(struct net *net, u32 dnode)
 	struct name_table *nt = tipc_name_table(net);
 	struct sk_buff_head head;
 
-	__skb_queue_head_init(&head);
+	skb_queue_head_init(&head);
 
 	read_lock_bh(&nt->cluster_scope_lock);
 	named_distribute(net, &head, dnode, &nt->cluster_scope);
diff --git a/net/tipc/netlink_compat.c b/net/tipc/netlink_compat.c
index d86030ef1232..e135d4e11231 100644
--- a/net/tipc/netlink_compat.c
+++ b/net/tipc/netlink_compat.c
@@ -55,6 +55,7 @@ struct tipc_nl_compat_msg {
 	int rep_type;
 	int rep_size;
 	int req_type;
+	int req_size;
 	struct net *net;
 	struct sk_buff *rep;
 	struct tlv_desc *req;
@@ -257,7 +258,8 @@ static int tipc_nl_compat_dumpit(struct tipc_nl_compat_cmd_dump *cmd,
 	int err;
 	struct sk_buff *arg;
 
-	if (msg->req_type && !TLV_CHECK_TYPE(msg->req, msg->req_type))
+	if (msg->req_type && (!msg->req_size ||
+			      !TLV_CHECK_TYPE(msg->req, msg->req_type)))
 		return -EINVAL;
 
 	msg->rep = tipc_tlv_alloc(msg->rep_size);
@@ -354,7 +356,8 @@ static int tipc_nl_compat_doit(struct tipc_nl_compat_cmd_doit *cmd,
 {
 	int err;
 
-	if (msg->req_type && !TLV_CHECK_TYPE(msg->req, msg->req_type))
+	if (msg->req_type && (!msg->req_size ||
+			      !TLV_CHECK_TYPE(msg->req, msg->req_type)))
 		return -EINVAL;
 
 	err = __tipc_nl_compat_doit(cmd, msg);
@@ -1278,8 +1281,8 @@ static int tipc_nl_compat_recv(struct sk_buff *skb, struct genl_info *info)
 		goto send;
 	}
 
-	len = nlmsg_attrlen(req_nlh, GENL_HDRLEN + TIPC_GENL_HDRLEN);
-	if (!len || !TLV_OK(msg.req, len)) {
+	msg.req_size = nlmsg_attrlen(req_nlh, GENL_HDRLEN + TIPC_GENL_HDRLEN);
+	if (msg.req_size && !TLV_OK(msg.req, msg.req_size)) {
 		msg.rep = tipc_get_err_tlv(TIPC_CFG_NOT_SUPPORTED);
 		err = -EOPNOTSUPP;
 		goto send;
diff --git a/net/tipc/node.c b/net/tipc/node.c
index 324a1f91b394..3a5be1d7e572 100644
--- a/net/tipc/node.c
+++ b/net/tipc/node.c
@@ -1807,6 +1807,7 @@ void tipc_rcv(struct net *net, struct sk_buff *skb, struct tipc_bearer *b)
 	__skb_queue_head_init(&xmitq);
 
 	/* Ensure message is well-formed before touching the header */
+	TIPC_SKB_CB(skb)->validated = false;
 	if (unlikely(!tipc_msg_validate(&skb)))
 		goto discard;
 	hdr = buf_msg(skb);
diff --git a/net/tipc/socket.c b/net/tipc/socket.c
index dd8537f988c4..83ae41d7e554 100644
--- a/net/tipc/socket.c
+++ b/net/tipc/socket.c
@@ -485,9 +485,8 @@ static int tipc_sk_create(struct net *net, struct socket *sock,
 		tsk_set_unreturnable(tsk, true);
 		if (sock->type == SOCK_DGRAM)
 			tsk_set_unreliable(tsk, true);
-		__skb_queue_head_init(&tsk->mc_method.deferredq);
 	}
-
+	__skb_queue_head_init(&tsk->mc_method.deferredq);
 	trace_tipc_sk_create(sk, NULL, TIPC_DUMP_NONE, " ");
 	return 0;
 }
diff --git a/net/tipc/sysctl.c b/net/tipc/sysctl.c
index 9df82a573aa7..6159d327db76 100644
--- a/net/tipc/sysctl.c
+++ b/net/tipc/sysctl.c
@@ -38,8 +38,6 @@
 
 #include <linux/sysctl.h>
 
-static int zero;
-static int one = 1;
 static struct ctl_table_header *tipc_ctl_hdr;
 
 static struct ctl_table tipc_table[] = {
@@ -49,7 +47,7 @@ static struct ctl_table tipc_table[] = {
 		.maxlen		= sizeof(sysctl_tipc_rmem),
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec_minmax,
-		.extra1         = &one,
+		.extra1         = SYSCTL_ONE,
 	},
 	{
 		.procname	= "named_timeout",
@@ -57,7 +55,7 @@ static struct ctl_table tipc_table[] = {
 		.maxlen		= sizeof(sysctl_tipc_named_timeout),
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec_minmax,
-		.extra1         = &zero,
+		.extra1         = SYSCTL_ZERO,
 	},
 	{
 		.procname       = "sk_filter",
diff --git a/net/tipc/topsrv.c b/net/tipc/topsrv.c
index f345662890a6..ca8ac96d22a9 100644
--- a/net/tipc/topsrv.c
+++ b/net/tipc/topsrv.c
@@ -476,7 +476,7 @@ static void tipc_topsrv_accept(struct work_struct *work)
 	}
 }
 
-/* tipc_toprsv_listener_data_ready - interrupt callback with connection request
+/* tipc_topsrv_listener_data_ready - interrupt callback with connection request
  * The queued job is launched into tipc_topsrv_accept()
  */
 static void tipc_topsrv_listener_data_ready(struct sock *sk)
diff --git a/net/tls/tls_device.c b/net/tls/tls_device.c
index 7c0b2b778703..43922d86e510 100644
--- a/net/tls/tls_device.c
+++ b/net/tls/tls_device.c
@@ -373,9 +373,9 @@ static int tls_push_data(struct sock *sk,
 	struct tls_context *tls_ctx = tls_get_ctx(sk);
 	struct tls_prot_info *prot = &tls_ctx->prot_info;
 	struct tls_offload_context_tx *ctx = tls_offload_ctx_tx(tls_ctx);
-	int tls_push_record_flags = flags | MSG_SENDPAGE_NOTLAST;
 	int more = flags & (MSG_SENDPAGE_NOTLAST | MSG_MORE);
 	struct tls_record_info *record = ctx->open_record;
+	int tls_push_record_flags;
 	struct page_frag *pfrag;
 	size_t orig_size = size;
 	u32 max_open_record_len;
@@ -390,6 +390,9 @@ static int tls_push_data(struct sock *sk,
 	if (sk->sk_err)
 		return -sk->sk_err;
 
+	flags |= MSG_SENDPAGE_DECRYPTED;
+	tls_push_record_flags = flags | MSG_SENDPAGE_NOTLAST;
+
 	timeo = sock_sndtimeo(sk, flags & MSG_DONTWAIT);
 	if (tls_is_partially_sent_record(tls_ctx)) {
 		rc = tls_push_partial_record(sk, tls_ctx, flags);
@@ -576,7 +579,9 @@ void tls_device_write_space(struct sock *sk, struct tls_context *ctx)
 		gfp_t sk_allocation = sk->sk_allocation;
 
 		sk->sk_allocation = GFP_ATOMIC;
-		tls_push_partial_record(sk, ctx, MSG_DONTWAIT | MSG_NOSIGNAL);
+		tls_push_partial_record(sk, ctx,
+					MSG_DONTWAIT | MSG_NOSIGNAL |
+					MSG_SENDPAGE_DECRYPTED);
 		sk->sk_allocation = sk_allocation;
 	}
 }
diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c
index 4674e57e66b0..43252a801c3f 100644
--- a/net/tls/tls_main.c
+++ b/net/tls/tls_main.c
@@ -261,24 +261,9 @@ void tls_ctx_free(struct tls_context *ctx)
 	kfree(ctx);
 }
 
-static void tls_sk_proto_close(struct sock *sk, long timeout)
+static void tls_sk_proto_cleanup(struct sock *sk,
+				 struct tls_context *ctx, long timeo)
 {
-	struct tls_context *ctx = tls_get_ctx(sk);
-	long timeo = sock_sndtimeo(sk, 0);
-	void (*sk_proto_close)(struct sock *sk, long timeout);
-	bool free_ctx = false;
-
-	lock_sock(sk);
-	sk_proto_close = ctx->sk_proto_close;
-
-	if (ctx->tx_conf == TLS_HW_RECORD && ctx->rx_conf == TLS_HW_RECORD)
-		goto skip_tx_cleanup;
-
-	if (ctx->tx_conf == TLS_BASE && ctx->rx_conf == TLS_BASE) {
-		free_ctx = true;
-		goto skip_tx_cleanup;
-	}
-
 	if (unlikely(sk->sk_write_pending) &&
 	    !wait_on_pending_writer(sk, &timeo))
 		tls_handle_open_record(sk, 0);
@@ -287,7 +272,7 @@ static void tls_sk_proto_close(struct sock *sk, long timeout)
 	if (ctx->tx_conf == TLS_SW) {
 		kfree(ctx->tx.rec_seq);
 		kfree(ctx->tx.iv);
-		tls_sw_free_resources_tx(sk);
+		tls_sw_release_resources_tx(sk);
 #ifdef CONFIG_TLS_DEVICE
 	} else if (ctx->tx_conf == TLS_HW) {
 		tls_device_free_resources_tx(sk);
@@ -295,26 +280,46 @@ static void tls_sk_proto_close(struct sock *sk, long timeout)
 	}
 
 	if (ctx->rx_conf == TLS_SW)
-		tls_sw_free_resources_rx(sk);
+		tls_sw_release_resources_rx(sk);
 
 #ifdef CONFIG_TLS_DEVICE
 	if (ctx->rx_conf == TLS_HW)
 		tls_device_offload_cleanup_rx(sk);
-
-	if (ctx->tx_conf != TLS_HW && ctx->rx_conf != TLS_HW) {
-#else
-	{
 #endif
-		tls_ctx_free(ctx);
-		ctx = NULL;
-	}
+}
 
-skip_tx_cleanup:
+static void tls_sk_proto_close(struct sock *sk, long timeout)
+{
+	struct inet_connection_sock *icsk = inet_csk(sk);
+	struct tls_context *ctx = tls_get_ctx(sk);
+	long timeo = sock_sndtimeo(sk, 0);
+	bool free_ctx;
+
+	if (ctx->tx_conf == TLS_SW)
+		tls_sw_cancel_work_tx(ctx);
+
+	lock_sock(sk);
+	free_ctx = ctx->tx_conf != TLS_HW && ctx->rx_conf != TLS_HW;
+
+	if (ctx->tx_conf != TLS_BASE || ctx->rx_conf != TLS_BASE)
+		tls_sk_proto_cleanup(sk, ctx, timeo);
+
+	write_lock_bh(&sk->sk_callback_lock);
+	if (free_ctx)
+		icsk->icsk_ulp_data = NULL;
+	sk->sk_prot = ctx->sk_proto;
+	if (sk->sk_write_space == tls_write_space)
+		sk->sk_write_space = ctx->sk_write_space;
+	write_unlock_bh(&sk->sk_callback_lock);
 	release_sock(sk);
-	sk_proto_close(sk, timeout);
-	/* free ctx for TLS_HW_RECORD, used by tcp_set_state
-	 * for sk->sk_prot->unhash [tls_hw_unhash]
-	 */
+	if (ctx->tx_conf == TLS_SW)
+		tls_sw_free_ctx_tx(ctx);
+	if (ctx->rx_conf == TLS_SW || ctx->rx_conf == TLS_HW)
+		tls_sw_strparser_done(ctx);
+	if (ctx->rx_conf == TLS_SW)
+		tls_sw_free_ctx_rx(ctx);
+	ctx->sk_proto_close(sk, timeout);
+
 	if (free_ctx)
 		tls_ctx_free(ctx);
 }
@@ -526,6 +531,8 @@ static int do_tls_setsockopt_conf(struct sock *sk, char __user *optval,
 		{
 #endif
 			rc = tls_set_sw_offload(sk, ctx, 1);
+			if (rc)
+				goto err_crypto_info;
 			conf = TLS_SW;
 		}
 	} else {
@@ -537,13 +544,13 @@ static int do_tls_setsockopt_conf(struct sock *sk, char __user *optval,
 		{
 #endif
 			rc = tls_set_sw_offload(sk, ctx, 0);
+			if (rc)
+				goto err_crypto_info;
 			conf = TLS_SW;
 		}
+		tls_sw_strparser_arm(sk, ctx);
 	}
 
-	if (rc)
-		goto err_crypto_info;
-
 	if (tx)
 		ctx->tx_conf = conf;
 	else
@@ -607,6 +614,7 @@ static struct tls_context *create_ctx(struct sock *sk)
 	ctx->setsockopt = sk->sk_prot->setsockopt;
 	ctx->getsockopt = sk->sk_prot->getsockopt;
 	ctx->sk_proto_close = sk->sk_prot->close;
+	ctx->unhash = sk->sk_prot->unhash;
 	return ctx;
 }
 
@@ -764,7 +772,6 @@ static void build_protos(struct proto prot[TLS_NUM_CONFIG][TLS_NUM_CONFIG],
 	prot[TLS_HW_RECORD][TLS_HW_RECORD] = *base;
 	prot[TLS_HW_RECORD][TLS_HW_RECORD].hash		= tls_hw_hash;
 	prot[TLS_HW_RECORD][TLS_HW_RECORD].unhash	= tls_hw_unhash;
-	prot[TLS_HW_RECORD][TLS_HW_RECORD].close	= tls_sk_proto_close;
 }
 
 static int tls_init(struct sock *sk)
@@ -773,7 +780,7 @@ static int tls_init(struct sock *sk)
 	int rc = 0;
 
 	if (tls_hw_prot(sk))
-		goto out;
+		return 0;
 
 	/* The TLS ulp is currently supported only for TCP sockets
 	 * in ESTABLISHED state.
@@ -784,21 +791,38 @@ static int tls_init(struct sock *sk)
 	if (sk->sk_state != TCP_ESTABLISHED)
 		return -ENOTSUPP;
 
+	tls_build_proto(sk);
+
 	/* allocate tls context */
+	write_lock_bh(&sk->sk_callback_lock);
 	ctx = create_ctx(sk);
 	if (!ctx) {
 		rc = -ENOMEM;
 		goto out;
 	}
 
-	tls_build_proto(sk);
 	ctx->tx_conf = TLS_BASE;
 	ctx->rx_conf = TLS_BASE;
+	ctx->sk_proto = sk->sk_prot;
 	update_sk_prot(sk, ctx);
 out:
+	write_unlock_bh(&sk->sk_callback_lock);
 	return rc;
 }
 
+static void tls_update(struct sock *sk, struct proto *p)
+{
+	struct tls_context *ctx;
+
+	ctx = tls_get_ctx(sk);
+	if (likely(ctx)) {
+		ctx->sk_proto_close = p->close;
+		ctx->sk_proto = p;
+	} else {
+		sk->sk_prot = p;
+	}
+}
+
 void tls_register_device(struct tls_device *device)
 {
 	spin_lock_bh(&device_spinlock);
@@ -819,6 +843,7 @@ static struct tcp_ulp_ops tcp_tls_ulp_ops __read_mostly = {
 	.name			= "tls",
 	.owner			= THIS_MODULE,
 	.init			= tls_init,
+	.update			= tls_update,
 };
 
 static int __init tls_register(void)
diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c
index 53b4ad94e74a..91d21b048a9b 100644
--- a/net/tls/tls_sw.c
+++ b/net/tls/tls_sw.c
@@ -2054,7 +2054,16 @@ static void tls_data_ready(struct sock *sk)
 	}
 }
 
-void tls_sw_free_resources_tx(struct sock *sk)
+void tls_sw_cancel_work_tx(struct tls_context *tls_ctx)
+{
+	struct tls_sw_context_tx *ctx = tls_sw_ctx_tx(tls_ctx);
+
+	set_bit(BIT_TX_CLOSING, &ctx->tx_bitmask);
+	set_bit(BIT_TX_SCHEDULED, &ctx->tx_bitmask);
+	cancel_delayed_work_sync(&ctx->tx_work.work);
+}
+
+void tls_sw_release_resources_tx(struct sock *sk)
 {
 	struct tls_context *tls_ctx = tls_get_ctx(sk);
 	struct tls_sw_context_tx *ctx = tls_sw_ctx_tx(tls_ctx);
@@ -2065,11 +2074,6 @@ void tls_sw_free_resources_tx(struct sock *sk)
 	if (atomic_read(&ctx->encrypt_pending))
 		crypto_wait_req(-EINPROGRESS, &ctx->async_wait);
 
-	release_sock(sk);
-	cancel_delayed_work_sync(&ctx->tx_work.work);
-	lock_sock(sk);
-
-	/* Tx whatever records we can transmit and abandon the rest */
 	tls_tx_records(sk, -1);
 
 	/* Free up un-sent records in tx_list. First, free
@@ -2092,6 +2096,11 @@ void tls_sw_free_resources_tx(struct sock *sk)
 
 	crypto_free_aead(ctx->aead_send);
 	tls_free_open_rec(sk);
+}
+
+void tls_sw_free_ctx_tx(struct tls_context *tls_ctx)
+{
+	struct tls_sw_context_tx *ctx = tls_sw_ctx_tx(tls_ctx);
 
 	kfree(ctx);
 }
@@ -2110,25 +2119,40 @@ void tls_sw_release_resources_rx(struct sock *sk)
 		skb_queue_purge(&ctx->rx_list);
 		crypto_free_aead(ctx->aead_recv);
 		strp_stop(&ctx->strp);
-		write_lock_bh(&sk->sk_callback_lock);
-		sk->sk_data_ready = ctx->saved_data_ready;
-		write_unlock_bh(&sk->sk_callback_lock);
-		release_sock(sk);
-		strp_done(&ctx->strp);
-		lock_sock(sk);
+		/* If tls_sw_strparser_arm() was not called (cleanup paths)
+		 * we still want to strp_stop(), but sk->sk_data_ready was
+		 * never swapped.
+		 */
+		if (ctx->saved_data_ready) {
+			write_lock_bh(&sk->sk_callback_lock);
+			sk->sk_data_ready = ctx->saved_data_ready;
+			write_unlock_bh(&sk->sk_callback_lock);
+		}
 	}
 }
 
-void tls_sw_free_resources_rx(struct sock *sk)
+void tls_sw_strparser_done(struct tls_context *tls_ctx)
 {
-	struct tls_context *tls_ctx = tls_get_ctx(sk);
 	struct tls_sw_context_rx *ctx = tls_sw_ctx_rx(tls_ctx);
 
-	tls_sw_release_resources_rx(sk);
+	strp_done(&ctx->strp);
+}
+
+void tls_sw_free_ctx_rx(struct tls_context *tls_ctx)
+{
+	struct tls_sw_context_rx *ctx = tls_sw_ctx_rx(tls_ctx);
 
 	kfree(ctx);
 }
 
+void tls_sw_free_resources_rx(struct sock *sk)
+{
+	struct tls_context *tls_ctx = tls_get_ctx(sk);
+
+	tls_sw_release_resources_rx(sk);
+	tls_sw_free_ctx_rx(tls_ctx);
+}
+
 /* The work handler to transmitt the encrypted records in tx_list */
 static void tx_work_handler(struct work_struct *work)
 {
@@ -2137,11 +2161,17 @@ static void tx_work_handler(struct work_struct *work)
 					       struct tx_work, work);
 	struct sock *sk = tx_work->sk;
 	struct tls_context *tls_ctx = tls_get_ctx(sk);
-	struct tls_sw_context_tx *ctx = tls_sw_ctx_tx(tls_ctx);
+	struct tls_sw_context_tx *ctx;
 
-	if (!test_and_clear_bit(BIT_TX_SCHEDULED, &ctx->tx_bitmask))
+	if (unlikely(!tls_ctx))
 		return;
 
+	ctx = tls_sw_ctx_tx(tls_ctx);
+	if (test_bit(BIT_TX_CLOSING, &ctx->tx_bitmask))
+		return;
+
+	if (!test_and_clear_bit(BIT_TX_SCHEDULED, &ctx->tx_bitmask))
+		return;
 	lock_sock(sk);
 	tls_tx_records(sk, -1);
 	release_sock(sk);
@@ -2160,6 +2190,18 @@ void tls_sw_write_space(struct sock *sk, struct tls_context *ctx)
 	}
 }
 
+void tls_sw_strparser_arm(struct sock *sk, struct tls_context *tls_ctx)
+{
+	struct tls_sw_context_rx *rx_ctx = tls_sw_ctx_rx(tls_ctx);
+
+	write_lock_bh(&sk->sk_callback_lock);
+	rx_ctx->saved_data_ready = sk->sk_data_ready;
+	sk->sk_data_ready = tls_data_ready;
+	write_unlock_bh(&sk->sk_callback_lock);
+
+	strp_check_rcv(&rx_ctx->strp);
+}
+
 int tls_set_sw_offload(struct sock *sk, struct tls_context *ctx, int tx)
 {
 	struct tls_context *tls_ctx = tls_get_ctx(sk);
@@ -2357,13 +2399,6 @@ int tls_set_sw_offload(struct sock *sk, struct tls_context *ctx, int tx)
 		cb.parse_msg = tls_read_size;
 
 		strp_init(&sw_ctx_rx->strp, sk, &cb);
-
-		write_lock_bh(&sk->sk_callback_lock);
-		sw_ctx_rx->saved_data_ready = sk->sk_data_ready;
-		sk->sk_data_ready = tls_data_ready;
-		write_unlock_bh(&sk->sk_callback_lock);
-
-		strp_check_rcv(&sw_ctx_rx->strp);
 	}
 
 	goto out;
diff --git a/net/vmw_vsock/hyperv_transport.c b/net/vmw_vsock/hyperv_transport.c
index f2084e3f7aa4..9d864ebeb7b3 100644
--- a/net/vmw_vsock/hyperv_transport.c
+++ b/net/vmw_vsock/hyperv_transport.c
@@ -312,6 +312,11 @@ static void hvs_close_connection(struct vmbus_channel *chan)
 	lock_sock(sk);
 	hvs_do_close_lock_held(vsock_sk(sk), true);
 	release_sock(sk);
+
+	/* Release the refcnt for the channel that's opened in
+	 * hvs_open_connection().
+	 */
+	sock_put(sk);
 }
 
 static void hvs_open_connection(struct vmbus_channel *chan)
@@ -407,6 +412,9 @@ static void hvs_open_connection(struct vmbus_channel *chan)
 	}
 
 	set_per_channel_state(chan, conn_from_host ? new : sk);
+
+	/* This reference will be dropped by hvs_close_connection(). */
+	sock_hold(conn_from_host ? new : sk);
 	vmbus_set_chn_rescind_callback(chan, hvs_close_connection);
 
 	/* Set the pending send size to max packet size to always get
diff --git a/net/wireless/Kconfig b/net/wireless/Kconfig
index 578cce4fbe6c..67f8360dfcee 100644
--- a/net/wireless/Kconfig
+++ b/net/wireless/Kconfig
@@ -166,7 +166,7 @@ config CFG80211_DEFAULT_PS
 
 	  If this causes your applications to misbehave you should fix your
 	  applications instead -- they need to register their network
-	  latency requirement, see Documentation/power/pm_qos_interface.txt.
+	  latency requirement, see Documentation/power/pm_qos_interface.rst.
 
 config CFG80211_DEBUGFS
 	bool "cfg80211 DebugFS entries"
diff --git a/net/wireless/core.c b/net/wireless/core.c
index 45d9afcff6d5..32b3c719fdfc 100644
--- a/net/wireless/core.c
+++ b/net/wireless/core.c
@@ -1410,10 +1410,8 @@ static int cfg80211_netdev_notifier_call(struct notifier_block *nb,
 		}
 		break;
 	case NETDEV_PRE_UP:
-		if (!(wdev->wiphy->interface_modes & BIT(wdev->iftype)) &&
-		    !(wdev->iftype == NL80211_IFTYPE_AP_VLAN &&
-		      rdev->wiphy.flags & WIPHY_FLAG_4ADDR_AP &&
-		      wdev->use_4addr))
+		if (!cfg80211_iftype_allowed(wdev->wiphy, wdev->iftype,
+					     wdev->use_4addr, 0))
 			return notifier_from_errno(-EOPNOTSUPP);
 
 		if (rfkill_blocked(rdev->rfkill))
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index fc83dd179c1a..fd05ae1437a9 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -3484,9 +3484,7 @@ static int nl80211_new_interface(struct sk_buff *skb, struct genl_info *info)
 			return err;
 	}
 
-	if (!(rdev->wiphy.interface_modes & (1 << type)) &&
-	    !(type == NL80211_IFTYPE_AP_VLAN && params.use_4addr &&
-	      rdev->wiphy.flags & WIPHY_FLAG_4ADDR_AP))
+	if (!cfg80211_iftype_allowed(&rdev->wiphy, type, params.use_4addr, 0))
 		return -EOPNOTSUPP;
 
 	err = nl80211_parse_mon_options(rdev, type, info, &params);
diff --git a/net/wireless/util.c b/net/wireless/util.c
index 1c39d6a2e850..d0e35b7b9e35 100644
--- a/net/wireless/util.c
+++ b/net/wireless/util.c
@@ -1697,7 +1697,7 @@ int cfg80211_iter_combinations(struct wiphy *wiphy,
 	for (iftype = 0; iftype < NUM_NL80211_IFTYPES; iftype++) {
 		num_interfaces += params->iftype_num[iftype];
 		if (params->iftype_num[iftype] > 0 &&
-		    !(wiphy->software_iftypes & BIT(iftype)))
+		    !cfg80211_iftype_allowed(wiphy, iftype, 0, 1))
 			used_iftypes |= BIT(iftype);
 	}
 
@@ -1719,7 +1719,7 @@ int cfg80211_iter_combinations(struct wiphy *wiphy,
 			return -ENOMEM;
 
 		for (iftype = 0; iftype < NUM_NL80211_IFTYPES; iftype++) {
-			if (wiphy->software_iftypes & BIT(iftype))
+			if (cfg80211_iftype_allowed(wiphy, iftype, 0, 1))
 				continue;
 			for (j = 0; j < c->n_limits; j++) {
 				all_iftypes |= limits[j].types;
@@ -2072,3 +2072,26 @@ int ieee80211_get_vht_max_nss(struct ieee80211_vht_cap *cap,
 	return max_vht_nss;
 }
 EXPORT_SYMBOL(ieee80211_get_vht_max_nss);
+
+bool cfg80211_iftype_allowed(struct wiphy *wiphy, enum nl80211_iftype iftype,
+			     bool is_4addr, u8 check_swif)
+
+{
+	bool is_vlan = iftype == NL80211_IFTYPE_AP_VLAN;
+
+	switch (check_swif) {
+	case 0:
+		if (is_vlan && is_4addr)
+			return wiphy->flags & WIPHY_FLAG_4ADDR_AP;
+		return wiphy->interface_modes & BIT(iftype);
+	case 1:
+		if (!(wiphy->software_iftypes & BIT(iftype)) && is_vlan)
+			return wiphy->flags & WIPHY_FLAG_4ADDR_AP;
+		return wiphy->software_iftypes & BIT(iftype);
+	default:
+		break;
+	}
+
+	return false;
+}
+EXPORT_SYMBOL(cfg80211_iftype_allowed);
diff --git a/net/xdp/xdp_umem.c b/net/xdp/xdp_umem.c
index 20c91f02d3d8..83de74ca729a 100644
--- a/net/xdp/xdp_umem.c
+++ b/net/xdp/xdp_umem.c
@@ -87,21 +87,20 @@ int xdp_umem_assign_dev(struct xdp_umem *umem, struct net_device *dev,
 	struct netdev_bpf bpf;
 	int err = 0;
 
+	ASSERT_RTNL();
+
 	force_zc = flags & XDP_ZEROCOPY;
 	force_copy = flags & XDP_COPY;
 
 	if (force_zc && force_copy)
 		return -EINVAL;
 
-	rtnl_lock();
-	if (xdp_get_umem_from_qid(dev, queue_id)) {
-		err = -EBUSY;
-		goto out_rtnl_unlock;
-	}
+	if (xdp_get_umem_from_qid(dev, queue_id))
+		return -EBUSY;
 
 	err = xdp_reg_umem_at_qid(dev, umem, queue_id);
 	if (err)
-		goto out_rtnl_unlock;
+		return err;
 
 	umem->dev = dev;
 	umem->queue_id = queue_id;
@@ -110,7 +109,7 @@ int xdp_umem_assign_dev(struct xdp_umem *umem, struct net_device *dev,
 
 	if (force_copy)
 		/* For copy-mode, we are done. */
-		goto out_rtnl_unlock;
+		return 0;
 
 	if (!dev->netdev_ops->ndo_bpf ||
 	    !dev->netdev_ops->ndo_xsk_async_xmit) {
@@ -125,7 +124,6 @@ int xdp_umem_assign_dev(struct xdp_umem *umem, struct net_device *dev,
 	err = dev->netdev_ops->ndo_bpf(dev, &bpf);
 	if (err)
 		goto err_unreg_umem;
-	rtnl_unlock();
 
 	umem->zc = true;
 	return 0;
@@ -135,8 +133,6 @@ err_unreg_umem:
 		err = 0; /* fallback to copy mode */
 	if (err)
 		xdp_clear_umem_at_qid(dev, queue_id);
-out_rtnl_unlock:
-	rtnl_unlock();
 	return err;
 }
 
diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c
index d4d6f10aa936..59b57d708697 100644
--- a/net/xdp/xsk.c
+++ b/net/xdp/xsk.c
@@ -240,6 +240,9 @@ static int xsk_generic_xmit(struct sock *sk, struct msghdr *m,
 
 	mutex_lock(&xs->mutex);
 
+	if (xs->queue_id >= xs->dev->real_num_tx_queues)
+		goto out;
+
 	while (xskq_peek_desc(xs->tx, &desc)) {
 		char *buffer;
 		u64 addr;
@@ -250,12 +253,6 @@ static int xsk_generic_xmit(struct sock *sk, struct msghdr *m,
 			goto out;
 		}
 
-		if (xskq_reserve_addr(xs->umem->cq))
-			goto out;
-
-		if (xs->queue_id >= xs->dev->real_num_tx_queues)
-			goto out;
-
 		len = desc.len;
 		skb = sock_alloc_send_skb(sk, len, 1, &err);
 		if (unlikely(!skb)) {
@@ -267,7 +264,7 @@ static int xsk_generic_xmit(struct sock *sk, struct msghdr *m,
 		addr = desc.addr;
 		buffer = xdp_umem_get_data(xs->umem, addr);
 		err = skb_store_bits(skb, 0, buffer, len);
-		if (unlikely(err)) {
+		if (unlikely(err) || xskq_reserve_addr(xs->umem->cq)) {
 			kfree_skb(skb);
 			goto out;
 		}
@@ -433,6 +430,7 @@ static int xsk_bind(struct socket *sock, struct sockaddr *addr, int addr_len)
 	if (flags & ~(XDP_SHARED_UMEM | XDP_COPY | XDP_ZEROCOPY))
 		return -EINVAL;
 
+	rtnl_lock();
 	mutex_lock(&xs->mutex);
 	if (xs->state != XSK_READY) {
 		err = -EBUSY;
@@ -518,6 +516,7 @@ out_unlock:
 		xs->state = XSK_BOUND;
 out_release:
 	mutex_unlock(&xs->mutex);
+	rtnl_unlock();
 	return err;
 }