Merge tag 'v3.18.24' of git://git.kernel.org/pub/scm/linux/kernel/git/stable/linux-stable into linux-linaro-lsk-v3.18

Linux 3.18.24

# gpg: Signature made Sat Oct 31 13:44:30 2015 PDT using RSA key ID 97772CDC
# gpg: Can't check signature: public key not found

* tag 'v3.18.24' of git://git.kernel.org/pub/scm/linux/kernel/git/stable/linux-stable: (234 commits)
  Linux 3.18.24
  tty: fix stall caused by missing memory barrier in drivers/tty/n_tty.c
  Revert "tty: fix stall caused by missing memory barrier in drivers/tty/n_tty.c"
  Linux 3.18.23
  x86: Init per-cpu shadow copy of CR4 on 32-bit CPUs too
  3w-9xxx: don't unmap bounce buffered commands
  fib_rules: Fix dump_rules() not to exit early
  vfs: Test for and handle paths that are unreachable from their mnt_root
  md: flush ->event_work before stopping array.
  x86/nmi/64: Fix a paravirt stack-clobbering bug in the NMI code
  Revert "iio: bmg160: IIO_BUFFER and IIO_TRIGGERED_BUFFER are required"
  net: Fix skb_set_peeked use-after-free bug
  mm: check if section present during memory block registering
  hpfs: update ctime and mtime on directory modification
  drivercore: Fix unregistration path of platform devices
  ARM: OMAP2+: DRA7: clockdomain: change l4per2_7xx_clkdm to SW_WKUP
  of/address: Don't loop forever in of_find_matching_node_by_address().
  auxdisplay: ks0108: fix refcount
  Doc: ABI: testing: configfs-usb-gadget-sourcesink
  Doc: ABI: testing: configfs-usb-gadget-loopback
  ...

32 files changed, 456 insertions, 236 deletions

diff --git a/net/batman-adv/distributed-arp-table.c b/net/batman-adv/distributed-arp-table.c
index b5981113c9a7..4bbd72e90756 100644
--- a/net/batman-adv/distributed-arp-table.c
+++ b/net/batman-adv/distributed-arp-table.c
@@ -15,6 +15,7 @@
  * along with this program; if not, see <http://www.gnu.org/licenses/>.
  */
 
+#include <linux/bitops.h>
 #include <linux/if_ether.h>
 #include <linux/if_arp.h>
 #include <linux/if_vlan.h>
@@ -422,7 +423,7 @@ static bool batadv_is_orig_node_eligible(struct batadv_dat_candidate *res,
 	int j;
 
 	/* check if orig node candidate is running DAT */
-	if (!(candidate->capabilities & BATADV_ORIG_CAPA_HAS_DAT))
+	if (!test_bit(BATADV_ORIG_CAPA_HAS_DAT, &candidate->capabilities))
 		goto out;
 
 	/* Check if this node has already been selected... */
@@ -682,9 +683,9 @@ static void batadv_dat_tvlv_ogm_handler_v1(struct batadv_priv *bat_priv,
 					   uint16_t tvlv_value_len)
 {
 	if (flags & BATADV_TVLV_HANDLER_OGM_CIFNOTFND)
-		orig->capabilities &= ~BATADV_ORIG_CAPA_HAS_DAT;
+		clear_bit(BATADV_ORIG_CAPA_HAS_DAT, &orig->capabilities);
 	else
-		orig->capabilities |= BATADV_ORIG_CAPA_HAS_DAT;
+		set_bit(BATADV_ORIG_CAPA_HAS_DAT, &orig->capabilities);
 }
 
 /**
diff --git a/net/batman-adv/network-coding.c b/net/batman-adv/network-coding.c
index 8d04d174669e..65d19690d8ae 100644
--- a/net/batman-adv/network-coding.c
+++ b/net/batman-adv/network-coding.c
@@ -15,6 +15,7 @@
  * along with this program; if not, see <http://www.gnu.org/licenses/>.
  */
 
+#include <linux/bitops.h>
 #include <linux/debugfs.h>
 
 #include "main.h"
@@ -105,9 +106,9 @@ static void batadv_nc_tvlv_ogm_handler_v1(struct batadv_priv *bat_priv,
 					  uint16_t tvlv_value_len)
 {
 	if (flags & BATADV_TVLV_HANDLER_OGM_CIFNOTFND)
-		orig->capabilities &= ~BATADV_ORIG_CAPA_HAS_NC;
+		clear_bit(BATADV_ORIG_CAPA_HAS_NC, &orig->capabilities);
 	else
-		orig->capabilities |= BATADV_ORIG_CAPA_HAS_NC;
+		set_bit(BATADV_ORIG_CAPA_HAS_NC, &orig->capabilities);
 }
 
 /**
@@ -871,7 +872,7 @@ void batadv_nc_update_nc_node(struct batadv_priv *bat_priv,
 		goto out;
 
 	/* check if orig node is network coding enabled */
-	if (!(orig_node->capabilities & BATADV_ORIG_CAPA_HAS_NC))
+	if (!test_bit(BATADV_ORIG_CAPA_HAS_NC, &orig_node->capabilities))
 		goto out;
 
 	/* accept ogms from 'good' neighbors and single hop neighbors */
diff --git a/net/batman-adv/soft-interface.c b/net/batman-adv/soft-interface.c
index 5467955eb27c..492b0593dc2f 100644
--- a/net/batman-adv/soft-interface.c
+++ b/net/batman-adv/soft-interface.c
@@ -173,6 +173,7 @@ static int batadv_interface_tx(struct sk_buff *skb,
 	int gw_mode;
 	enum batadv_forw_mode forw_mode;
 	struct batadv_orig_node *mcast_single_orig = NULL;
+	int network_offset = ETH_HLEN;
 
 	if (atomic_read(&bat_priv->mesh_state) != BATADV_MESH_ACTIVE)
 		goto dropped;
@@ -185,14 +186,18 @@ static int batadv_interface_tx(struct sk_buff *skb,
 	case ETH_P_8021Q:
 		vhdr = vlan_eth_hdr(skb);
 
-		if (vhdr->h_vlan_encapsulated_proto != ethertype)
+		if (vhdr->h_vlan_encapsulated_proto != ethertype) {
+			network_offset += VLAN_HLEN;
 			break;
+		}
 
 		/* fall through */
 	case ETH_P_BATMAN:
 		goto dropped;
 	}
 
+	skb_set_network_header(skb, network_offset);
+
 	if (batadv_bla_tx(bat_priv, skb, vid))
 		goto dropped;
 
diff --git a/net/batman-adv/translation-table.c b/net/batman-adv/translation-table.c
index 5f59e7f899a0..58ad6ba429b3 100644
--- a/net/batman-adv/translation-table.c
+++ b/net/batman-adv/translation-table.c
@@ -15,6 +15,7 @@
  * along with this program; if not, see <http://www.gnu.org/licenses/>.
  */
 
+#include <linux/bitops.h>
 #include "main.h"
 #include "translation-table.h"
 #include "soft-interface.h"
@@ -1015,6 +1016,7 @@ uint16_t batadv_tt_local_remove(struct batadv_priv *bat_priv,
 	struct batadv_tt_local_entry *tt_local_entry;
 	uint16_t flags, curr_flags = BATADV_NO_FLAGS;
 	struct batadv_softif_vlan *vlan;
+	void *tt_entry_exists;
 
 	tt_local_entry = batadv_tt_local_hash_find(bat_priv, addr, vid);
 	if (!tt_local_entry)
@@ -1042,7 +1044,15 @@ uint16_t batadv_tt_local_remove(struct batadv_priv *bat_priv,
 	 * immediately purge it
 	 */
 	batadv_tt_local_event(bat_priv, tt_local_entry, BATADV_TT_CLIENT_DEL);
-	hlist_del_rcu(&tt_local_entry->common.hash_entry);
+
+	tt_entry_exists = batadv_hash_remove(bat_priv->tt.local_hash,
+					     batadv_compare_tt,
+					     batadv_choose_tt,
+					     &tt_local_entry->common);
+	if (!tt_entry_exists)
+		goto out;
+
+	/* extra call to free the local tt entry */
 	batadv_tt_local_entry_free_ref(tt_local_entry);
 
 	/* decrease the reference held for this vlan */
@@ -1844,7 +1854,7 @@ void batadv_tt_global_del_orig(struct batadv_priv *bat_priv,
 		}
 		spin_unlock_bh(list_lock);
 	}
-	orig_node->capa_initialized &= ~BATADV_ORIG_CAPA_HAS_TT;
+	clear_bit(BATADV_ORIG_CAPA_HAS_TT, &orig_node->capa_initialized);
 }
 
 static bool batadv_tt_global_to_purge(struct batadv_tt_global_entry *tt_global,
@@ -2804,7 +2814,7 @@ static void _batadv_tt_update_changes(struct batadv_priv *bat_priv,
 				return;
 		}
 	}
-	orig_node->capa_initialized |= BATADV_ORIG_CAPA_HAS_TT;
+	set_bit(BATADV_ORIG_CAPA_HAS_TT, &orig_node->capa_initialized);
 }
 
 static void batadv_tt_fill_gtable(struct batadv_priv *bat_priv,
@@ -3304,7 +3314,8 @@ static void batadv_tt_update_orig(struct batadv_priv *bat_priv,
 	bool has_tt_init;
 
 	tt_vlan = (struct batadv_tvlv_tt_vlan_data *)tt_buff;
-	has_tt_init = orig_node->capa_initialized & BATADV_ORIG_CAPA_HAS_TT;
+	has_tt_init = test_bit(BATADV_ORIG_CAPA_HAS_TT,
+			       &orig_node->capa_initialized);
 
 	/* orig table not initialised AND first diff is in the OGM OR the ttvn
 	 * increased by one -> we can apply the attached changes
diff --git a/net/batman-adv/types.h b/net/batman-adv/types.h
index 8854c05622a9..fdf65b50e3ec 100644
--- a/net/batman-adv/types.h
+++ b/net/batman-adv/types.h
@@ -258,8 +258,8 @@ struct batadv_orig_node {
 	struct hlist_node mcast_want_all_ipv4_node;
 	struct hlist_node mcast_want_all_ipv6_node;
 #endif
-	uint8_t capabilities;
-	uint8_t capa_initialized;
+	unsigned long capabilities;
+	unsigned long capa_initialized;
 	atomic_t last_ttvn;
 	unsigned char *tt_buff;
 	int16_t tt_buff_len;
@@ -298,9 +298,9 @@ struct batadv_orig_node {
  *  (= orig node announces a tvlv of type BATADV_TVLV_MCAST)
  */
 enum batadv_orig_capabilities {
-	BATADV_ORIG_CAPA_HAS_DAT = BIT(0),
-	BATADV_ORIG_CAPA_HAS_NC = BIT(1),
-	BATADV_ORIG_CAPA_HAS_TT = BIT(2),
+	BATADV_ORIG_CAPA_HAS_DAT,
+	BATADV_ORIG_CAPA_HAS_NC,
+	BATADV_ORIG_CAPA_HAS_TT,
 	BATADV_ORIG_CAPA_HAS_MCAST = BIT(3),
 };
 
diff --git a/net/core/datagram.c b/net/core/datagram.c
index 3a402a7b20e9..61e99f315ed9 100644
--- a/net/core/datagram.c
+++ b/net/core/datagram.c
@@ -130,6 +130,35 @@ out_noerr:
 	goto out;
 }
 
+static int skb_set_peeked(struct sk_buff *skb)
+{
+	struct sk_buff *nskb;
+
+	if (skb->peeked)
+		return 0;
+
+	/* We have to unshare an skb before modifying it. */
+	if (!skb_shared(skb))
+		goto done;
+
+	nskb = skb_clone(skb, GFP_ATOMIC);
+	if (!nskb)
+		return -ENOMEM;
+
+	skb->prev->next = nskb;
+	skb->next->prev = nskb;
+	nskb->prev = skb->prev;
+	nskb->next = skb->next;
+
+	consume_skb(skb);
+	skb = nskb;
+
+done:
+	skb->peeked = 1;
+
+	return 0;
+}
+
 /**
  *	__skb_recv_datagram - Receive a datagram skbuff
  *	@sk: socket
@@ -164,7 +193,9 @@ out_noerr:
 struct sk_buff *__skb_recv_datagram(struct sock *sk, unsigned int flags,
 				    int *peeked, int *off, int *err)
 {
+	struct sk_buff_head *queue = &sk->sk_receive_queue;
 	struct sk_buff *skb, *last;
+	unsigned long cpu_flags;
 	long timeo;
 	/*
 	 * Caller is allowed not to check sk->sk_err before skb_recv_datagram()
@@ -183,8 +214,6 @@ struct sk_buff *__skb_recv_datagram(struct sock *sk, unsigned int flags,
 		 * Look at current nfs client by the way...
 		 * However, this function was correct in any case. 8)
 		 */
-		unsigned long cpu_flags;
-		struct sk_buff_head *queue = &sk->sk_receive_queue;
 		int _off = *off;
 
 		last = (struct sk_buff *)queue;
@@ -198,7 +227,11 @@ struct sk_buff *__skb_recv_datagram(struct sock *sk, unsigned int flags,
 					_off -= skb->len;
 					continue;
 				}
-				skb->peeked = 1;
+
+				error = skb_set_peeked(skb);
+				if (error)
+					goto unlock_err;
+
 				atomic_inc(&skb->users);
 			} else
 				__skb_unlink(skb, queue);
@@ -222,6 +255,8 @@ struct sk_buff *__skb_recv_datagram(struct sock *sk, unsigned int flags,
 
 	return NULL;
 
+unlock_err:
+	spin_unlock_irqrestore(&queue->lock, cpu_flags);
 no_packet:
 	*err = error;
 	return NULL;
diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c
index 185c341fafbd..99ae718b79be 100644
--- a/net/core/fib_rules.c
+++ b/net/core/fib_rules.c
@@ -621,15 +621,17 @@ static int dump_rules(struct sk_buff *skb, struct netlink_callback *cb,
 {
 	int idx = 0;
 	struct fib_rule *rule;
+	int err = 0;
 
 	rcu_read_lock();
 	list_for_each_entry_rcu(rule, &ops->rules_list, list) {
 		if (idx < cb->args[1])
 			goto skip;
 
-		if (fib_nl_fill_rule(skb, rule, NETLINK_CB(cb->skb).portid,
-				     cb->nlh->nlmsg_seq, RTM_NEWRULE,
-				     NLM_F_MULTI, ops) < 0)
+		err = fib_nl_fill_rule(skb, rule, NETLINK_CB(cb->skb).portid,
+				       cb->nlh->nlmsg_seq, RTM_NEWRULE,
+				       NLM_F_MULTI, ops);
+		if (err < 0)
 			break;
 skip:
 		idx++;
@@ -638,7 +640,7 @@ skip:
 	cb->args[1] = idx;
 	rules_ops_put(ops);
 
-	return skb->len;
+	return err;
 }
 
 static int fib_nl_dumprule(struct sk_buff *skb, struct netlink_callback *cb)
@@ -654,7 +656,9 @@ static int fib_nl_dumprule(struct sk_buff *skb, struct netlink_callback *cb)
 		if (ops == NULL)
 			return -EAFNOSUPPORT;
 
-		return dump_rules(skb, cb, ops);
+		dump_rules(skb, cb, ops);
+
+		return skb->len;
 	}
 
 	rcu_read_lock();
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index c522f7a00eab..c412db774603 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -805,7 +805,8 @@ static inline int rtnl_vfinfo_size(const struct net_device *dev,
 			 nla_total_size(sizeof(struct ifla_vf_vlan)) +
 			 nla_total_size(sizeof(struct ifla_vf_spoofchk)) +
 			 nla_total_size(sizeof(struct ifla_vf_rate)) +
-			 nla_total_size(sizeof(struct ifla_vf_link_state)));
+			 nla_total_size(sizeof(struct ifla_vf_link_state)) +
+			 nla_total_size(sizeof(struct ifla_vf_rss_query_en)));
 		return size;
 	} else
 		return 0;
@@ -1075,14 +1076,16 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev,
 			struct ifla_vf_tx_rate vf_tx_rate;
 			struct ifla_vf_spoofchk vf_spoofchk;
 			struct ifla_vf_link_state vf_linkstate;
+			struct ifla_vf_rss_query_en vf_rss_query_en;
 
 			/*
 			 * Not all SR-IOV capable drivers support the
-			 * spoofcheck query.  Preset to -1 so the user
-			 * space tool can detect that the driver didn't
-			 * report anything.
+			 * spoofcheck and "RSS query enable" query.  Preset to
+			 * -1 so the user space tool can detect that the driver
+			 * didn't report anything.
 			 */
 			ivi.spoofchk = -1;
+			ivi.rss_query_en = -1;
 			memset(ivi.mac, 0, sizeof(ivi.mac));
 			/* The default value for VF link state is "auto"
 			 * IFLA_VF_LINK_STATE_AUTO which equals zero
@@ -1095,7 +1098,8 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev,
 				vf_rate.vf =
 				vf_tx_rate.vf =
 				vf_spoofchk.vf =
-				vf_linkstate.vf = ivi.vf;
+				vf_linkstate.vf =
+				vf_rss_query_en.vf = ivi.vf;
 
 			memcpy(vf_mac.mac, ivi.mac, sizeof(ivi.mac));
 			vf_vlan.vlan = ivi.vlan;
@@ -1105,6 +1109,7 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev,
 			vf_rate.max_tx_rate = ivi.max_tx_rate;
 			vf_spoofchk.setting = ivi.spoofchk;
 			vf_linkstate.link_state = ivi.linkstate;
+			vf_rss_query_en.setting = ivi.rss_query_en;
 			vf = nla_nest_start(skb, IFLA_VF_INFO);
 			if (!vf) {
 				nla_nest_cancel(skb, vfinfo);
@@ -1119,7 +1124,10 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev,
 			    nla_put(skb, IFLA_VF_SPOOFCHK, sizeof(vf_spoofchk),
 				    &vf_spoofchk) ||
 			    nla_put(skb, IFLA_VF_LINK_STATE, sizeof(vf_linkstate),
-				    &vf_linkstate))
+				    &vf_linkstate) ||
+			    nla_put(skb, IFLA_VF_RSS_QUERY_EN,
+				    sizeof(vf_rss_query_en),
+				    &vf_rss_query_en))
 				goto nla_put_failure;
 			nla_nest_end(skb, vf);
 		}
@@ -1207,10 +1215,6 @@ static const struct nla_policy ifla_info_policy[IFLA_INFO_MAX+1] = {
 	[IFLA_INFO_SLAVE_DATA]	= { .type = NLA_NESTED },
 };
 
-static const struct nla_policy ifla_vfinfo_policy[IFLA_VF_INFO_MAX+1] = {
-	[IFLA_VF_INFO]		= { .type = NLA_NESTED },
-};
-
 static const struct nla_policy ifla_vf_policy[IFLA_VF_MAX+1] = {
 	[IFLA_VF_MAC]		= { .len = sizeof(struct ifla_vf_mac) },
 	[IFLA_VF_VLAN]		= { .len = sizeof(struct ifla_vf_vlan) },
@@ -1218,6 +1222,7 @@ static const struct nla_policy ifla_vf_policy[IFLA_VF_MAX+1] = {
 	[IFLA_VF_SPOOFCHK]	= { .len = sizeof(struct ifla_vf_spoofchk) },
 	[IFLA_VF_RATE]		= { .len = sizeof(struct ifla_vf_rate) },
 	[IFLA_VF_LINK_STATE]	= { .len = sizeof(struct ifla_vf_link_state) },
+	[IFLA_VF_RSS_QUERY_EN]	= { .len = sizeof(struct ifla_vf_rss_query_en) },
 };
 
 static const struct nla_policy ifla_port_policy[IFLA_PORT_MAX+1] = {
@@ -1356,85 +1361,98 @@ static int validate_linkmsg(struct net_device *dev, struct nlattr *tb[])
 	return 0;
 }
 
-static int do_setvfinfo(struct net_device *dev, struct nlattr *attr)
+static int do_setvfinfo(struct net_device *dev, struct nlattr **tb)
 {
-	int rem, err = -EINVAL;
-	struct nlattr *vf;
 	const struct net_device_ops *ops = dev->netdev_ops;
+	int err = -EINVAL;
 
-	nla_for_each_nested(vf, attr, rem) {
-		switch (nla_type(vf)) {
-		case IFLA_VF_MAC: {
-			struct ifla_vf_mac *ivm;
-			ivm = nla_data(vf);
-			err = -EOPNOTSUPP;
-			if (ops->ndo_set_vf_mac)
-				err = ops->ndo_set_vf_mac(dev, ivm->vf,
-							  ivm->mac);
-			break;
-		}
-		case IFLA_VF_VLAN: {
-			struct ifla_vf_vlan *ivv;
-			ivv = nla_data(vf);
-			err = -EOPNOTSUPP;
-			if (ops->ndo_set_vf_vlan)
-				err = ops->ndo_set_vf_vlan(dev, ivv->vf,
-							   ivv->vlan,
-							   ivv->qos);
-			break;
-		}
-		case IFLA_VF_TX_RATE: {
-			struct ifla_vf_tx_rate *ivt;
-			struct ifla_vf_info ivf;
-			ivt = nla_data(vf);
-			err = -EOPNOTSUPP;
-			if (ops->ndo_get_vf_config)
-				err = ops->ndo_get_vf_config(dev, ivt->vf,
-							     &ivf);
-			if (err)
-				break;
-			err = -EOPNOTSUPP;
-			if (ops->ndo_set_vf_rate)
-				err = ops->ndo_set_vf_rate(dev, ivt->vf,
-							   ivf.min_tx_rate,
-							   ivt->rate);
-			break;
-		}
-		case IFLA_VF_RATE: {
-			struct ifla_vf_rate *ivt;
-			ivt = nla_data(vf);
-			err = -EOPNOTSUPP;
-			if (ops->ndo_set_vf_rate)
-				err = ops->ndo_set_vf_rate(dev, ivt->vf,
-							   ivt->min_tx_rate,
-							   ivt->max_tx_rate);
-			break;
-		}
-		case IFLA_VF_SPOOFCHK: {
-			struct ifla_vf_spoofchk *ivs;
-			ivs = nla_data(vf);
-			err = -EOPNOTSUPP;
-			if (ops->ndo_set_vf_spoofchk)
-				err = ops->ndo_set_vf_spoofchk(dev, ivs->vf,
-							       ivs->setting);
-			break;
-		}
-		case IFLA_VF_LINK_STATE: {
-			struct ifla_vf_link_state *ivl;
-			ivl = nla_data(vf);
-			err = -EOPNOTSUPP;
-			if (ops->ndo_set_vf_link_state)
-				err = ops->ndo_set_vf_link_state(dev, ivl->vf,
-								 ivl->link_state);
-			break;
-		}
-		default:
-			err = -EINVAL;
-			break;
-		}
-		if (err)
-			break;
+	if (tb[IFLA_VF_MAC]) {
+		struct ifla_vf_mac *ivm = nla_data(tb[IFLA_VF_MAC]);
+
+		err = -EOPNOTSUPP;
+		if (ops->ndo_set_vf_mac)
+			err = ops->ndo_set_vf_mac(dev, ivm->vf,
+						  ivm->mac);
+		if (err < 0)
+			return err;
+	}
+
+	if (tb[IFLA_VF_VLAN]) {
+		struct ifla_vf_vlan *ivv = nla_data(tb[IFLA_VF_VLAN]);
+
+		err = -EOPNOTSUPP;
+		if (ops->ndo_set_vf_vlan)
+			err = ops->ndo_set_vf_vlan(dev, ivv->vf, ivv->vlan,
+						   ivv->qos);
+		if (err < 0)
+			return err;
 	}
+
+	if (tb[IFLA_VF_TX_RATE]) {
+		struct ifla_vf_tx_rate *ivt = nla_data(tb[IFLA_VF_TX_RATE]);
+		struct ifla_vf_info ivf;
+
+		err = -EOPNOTSUPP;
+		if (ops->ndo_get_vf_config)
+			err = ops->ndo_get_vf_config(dev, ivt->vf, &ivf);
+		if (err < 0)
+			return err;
+
+		err = -EOPNOTSUPP;
+		if (ops->ndo_set_vf_rate)
+			err = ops->ndo_set_vf_rate(dev, ivt->vf,
+						   ivf.min_tx_rate,
+						   ivt->rate);
+		if (err < 0)
+			return err;
+	}
+
+	if (tb[IFLA_VF_RATE]) {
+		struct ifla_vf_rate *ivt = nla_data(tb[IFLA_VF_RATE]);
+
+		err = -EOPNOTSUPP;
+		if (ops->ndo_set_vf_rate)
+			err = ops->ndo_set_vf_rate(dev, ivt->vf,
+						   ivt->min_tx_rate,
+						   ivt->max_tx_rate);
+		if (err < 0)
+			return err;
+	}
+
+	if (tb[IFLA_VF_SPOOFCHK]) {
+		struct ifla_vf_spoofchk *ivs = nla_data(tb[IFLA_VF_SPOOFCHK]);
+
+		err = -EOPNOTSUPP;
+		if (ops->ndo_set_vf_spoofchk)
+			err = ops->ndo_set_vf_spoofchk(dev, ivs->vf,
+						       ivs->setting);
+		if (err < 0)
+			return err;
+	}
+
+	if (tb[IFLA_VF_LINK_STATE]) {
+		struct ifla_vf_link_state *ivl = nla_data(tb[IFLA_VF_LINK_STATE]);
+
+		err = -EOPNOTSUPP;
+		if (ops->ndo_set_vf_link_state)
+			err = ops->ndo_set_vf_link_state(dev, ivl->vf,
+							 ivl->link_state);
+		if (err < 0)
+			return err;
+	}
+
+	if (tb[IFLA_VF_RSS_QUERY_EN]) {
+		struct ifla_vf_rss_query_en *ivrssq_en;
+
+		err = -EOPNOTSUPP;
+		ivrssq_en = nla_data(tb[IFLA_VF_RSS_QUERY_EN]);
+		if (ops->ndo_set_vf_rss_query_en)
+			err = ops->ndo_set_vf_rss_query_en(dev, ivrssq_en->vf,
+							   ivrssq_en->setting);
+		if (err < 0)
+			return err;
+	}
+
 	return err;
 }
 
@@ -1630,14 +1648,21 @@ static int do_setlink(const struct sk_buff *skb,
 	}
 
 	if (tb[IFLA_VFINFO_LIST]) {
+		struct nlattr *vfinfo[IFLA_VF_MAX + 1];
 		struct nlattr *attr;
 		int rem;
+
 		nla_for_each_nested(attr, tb[IFLA_VFINFO_LIST], rem) {
-			if (nla_type(attr) != IFLA_VF_INFO) {
+			if (nla_type(attr) != IFLA_VF_INFO ||
+			    nla_len(attr) < NLA_HDRLEN) {
 				err = -EINVAL;
 				goto errout;
 			}
-			err = do_setvfinfo(dev, attr);
+			err = nla_parse_nested(vfinfo, IFLA_VF_MAX, attr,
+					       ifla_vf_policy);
+			if (err < 0)
+				goto errout;
+			err = do_setvfinfo(dev, vfinfo);
 			if (err < 0)
 				goto errout;
 			status |= DO_SETLINK_NOTIFY;
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index dc9f925b0cd5..9c7d88870e2b 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -2798,6 +2798,7 @@ void tcp_send_active_reset(struct sock *sk, gfp_t priority)
 	skb_reserve(skb, MAX_TCP_HEADER);
 	tcp_init_nondata_skb(skb, tcp_acceptable_seq(sk),
 			     TCPHDR_ACK | TCPHDR_RST);
+	skb_mstamp_get(&skb->skb_mstamp);
 	/* Send it off. */
 	if (tcp_transmit_skb(sk, skb, 0, priority))
 		NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPABORTFAILED);
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index c5e3194fd9a5..4ea975324888 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -1983,12 +1983,19 @@ void udp_v4_early_demux(struct sk_buff *skb)
 
 	skb->sk = sk;
 	skb->destructor = sock_efree;
-	dst = sk->sk_rx_dst;
+	dst = READ_ONCE(sk->sk_rx_dst);
 
 	if (dst)
 		dst = dst_check(dst, 0);
-	if (dst)
-		skb_dst_set_noref(skb, dst);
+	if (dst) {
+		/* DST_NOCACHE can not be used without taking a reference */
+		if (dst->flags & DST_NOCACHE) {
+			if (likely(atomic_inc_not_zero(&dst->__refcnt)))
+				skb_dst_set(skb, dst);
+		} else {
+			skb_dst_set_noref(skb, dst);
+		}
+	}
 }
 
 int udp_rcv(struct sk_buff *skb)
diff --git a/net/ipv6/exthdrs_offload.c b/net/ipv6/exthdrs_offload.c
index 447a7fbd1bb6..f5e2ba1c18bf 100644
--- a/net/ipv6/exthdrs_offload.c
+++ b/net/ipv6/exthdrs_offload.c
@@ -36,6 +36,6 @@ out:
 	return ret;
 
 out_rt:
-	inet_del_offload(&rthdr_offload, IPPROTO_ROUTING);
+	inet6_del_offload(&rthdr_offload, IPPROTO_ROUTING);
 	goto out;
 }
diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index 0e32d2e1bdbf..28d7a245ea34 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -360,7 +360,7 @@ static void ip6gre_tunnel_uninit(struct net_device *dev)
 	struct ip6_tnl *t = netdev_priv(dev);
 	struct ip6gre_net *ign = net_generic(t->net, ip6gre_net_id);
 
-	ip6gre_tunnel_unlink(ign, t);
+	ip6_tnl_dst_reset(netdev_priv(dev));
 	dev_put(dev);
 }
 
diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c
index 1a01d79b8698..0d58542f9db0 100644
--- a/net/ipv6/ip6mr.c
+++ b/net/ipv6/ip6mr.c
@@ -552,7 +552,7 @@ static void ipmr_mfc_seq_stop(struct seq_file *seq, void *v)
 
 	if (it->cache == &mrt->mfc6_unres_queue)
 		spin_unlock_bh(&mfc_unres_lock);
-	else if (it->cache == mrt->mfc6_cache_array)
+	else if (it->cache == &mrt->mfc6_cache_array[it->ct])
 		read_unlock(&mrt_lock);
 }
 
diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c
index 80ce44f6693d..45e782825567 100644
--- a/net/mac80211/tx.c
+++ b/net/mac80211/tx.c
@@ -299,9 +299,6 @@ ieee80211_tx_h_check_assoc(struct ieee80211_tx_data *tx)
 	if (tx->sdata->vif.type == NL80211_IFTYPE_WDS)
 		return TX_CONTINUE;
 
-	if (tx->sdata->vif.type == NL80211_IFTYPE_MESH_POINT)
-		return TX_CONTINUE;
-
 	if (tx->flags & IEEE80211_TX_PS_BUFFERED)
 		return TX_CONTINUE;
 
diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c
index 990decba1fe4..3a2fa9c044f8 100644
--- a/net/netfilter/ipvs/ip_vs_core.c
+++ b/net/netfilter/ipvs/ip_vs_core.c
@@ -313,7 +313,13 @@ ip_vs_sched_persist(struct ip_vs_service *svc,
 		 * return *ignored=0 i.e. ICMP and NF_DROP
 		 */
 		sched = rcu_dereference(svc->scheduler);
-		dest = sched->schedule(svc, skb, iph);
+		if (sched) {
+			/* read svc->sched_data after svc->scheduler */
+			smp_rmb();
+			dest = sched->schedule(svc, skb, iph);
+		} else {
+			dest = NULL;
+		}
 		if (!dest) {
 			IP_VS_DBG(1, "p-schedule: no dest found.\n");
 			kfree(param.pe_data);
@@ -461,7 +467,13 @@ ip_vs_schedule(struct ip_vs_service *svc, struct sk_buff *skb,
 	}
 
 	sched = rcu_dereference(svc->scheduler);
-	dest = sched->schedule(svc, skb, iph);
+	if (sched) {
+		/* read svc->sched_data after svc->scheduler */
+		smp_rmb();
+		dest = sched->schedule(svc, skb, iph);
+	} else {
+		dest = NULL;
+	}
 	if (dest == NULL) {
 		IP_VS_DBG(1, "Schedule: no dest found.\n");
 		return NULL;
diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c
index ac7ba689efe7..9b1452e8e868 100644
--- a/net/netfilter/ipvs/ip_vs_ctl.c
+++ b/net/netfilter/ipvs/ip_vs_ctl.c
@@ -828,15 +828,16 @@ __ip_vs_update_dest(struct ip_vs_service *svc, struct ip_vs_dest *dest,
 	__ip_vs_dst_cache_reset(dest);
 	spin_unlock_bh(&dest->dst_lock);
 
-	sched = rcu_dereference_protected(svc->scheduler, 1);
 	if (add) {
 		ip_vs_start_estimator(svc->net, &dest->stats);
 		list_add_rcu(&dest->n_list, &svc->destinations);
 		svc->num_dests++;
-		if (sched->add_dest)
+		sched = rcu_dereference_protected(svc->scheduler, 1);
+		if (sched && sched->add_dest)
 			sched->add_dest(svc, dest);
 	} else {
-		if (sched->upd_dest)
+		sched = rcu_dereference_protected(svc->scheduler, 1);
+		if (sched && sched->upd_dest)
 			sched->upd_dest(svc, dest);
 	}
 }
@@ -1070,7 +1071,7 @@ static void __ip_vs_unlink_dest(struct ip_vs_service *svc,
 		struct ip_vs_scheduler *sched;
 
 		sched = rcu_dereference_protected(svc->scheduler, 1);
-		if (sched->del_dest)
+		if (sched && sched->del_dest)
 			sched->del_dest(svc, dest);
 	}
 }
@@ -1161,11 +1162,14 @@ ip_vs_add_service(struct net *net, struct ip_vs_service_user_kern *u,
 	ip_vs_use_count_inc();
 
 	/* Lookup the scheduler by 'u->sched_name' */
-	sched = ip_vs_scheduler_get(u->sched_name);
-	if (sched == NULL) {
-		pr_info("Scheduler module ip_vs_%s not found\n", u->sched_name);
-		ret = -ENOENT;
-		goto out_err;
+	if (strcmp(u->sched_name, "none")) {
+		sched = ip_vs_scheduler_get(u->sched_name);
+		if (!sched) {
+			pr_info("Scheduler module ip_vs_%s not found\n",
+				u->sched_name);
+			ret = -ENOENT;
+			goto out_err;
+		}
 	}
 
 	if (u->pe_name && *u->pe_name) {
@@ -1226,10 +1230,12 @@ ip_vs_add_service(struct net *net, struct ip_vs_service_user_kern *u,
 	spin_lock_init(&svc->stats.lock);
 
 	/* Bind the scheduler */
-	ret = ip_vs_bind_scheduler(svc, sched);
-	if (ret)
-		goto out_err;
-	sched = NULL;
+	if (sched) {
+		ret = ip_vs_bind_scheduler(svc, sched);
+		if (ret)
+			goto out_err;
+		sched = NULL;
+	}
 
 	/* Bind the ct retriever */
 	RCU_INIT_POINTER(svc->pe, pe);
@@ -1277,17 +1283,20 @@ ip_vs_add_service(struct net *net, struct ip_vs_service_user_kern *u,
 static int
 ip_vs_edit_service(struct ip_vs_service *svc, struct ip_vs_service_user_kern *u)
 {
-	struct ip_vs_scheduler *sched, *old_sched;
+	struct ip_vs_scheduler *sched = NULL, *old_sched;
 	struct ip_vs_pe *pe = NULL, *old_pe = NULL;
 	int ret = 0;
 
 	/*
 	 * Lookup the scheduler, by 'u->sched_name'
 	 */
-	sched = ip_vs_scheduler_get(u->sched_name);
-	if (sched == NULL) {
-		pr_info("Scheduler module ip_vs_%s not found\n", u->sched_name);
-		return -ENOENT;
+	if (strcmp(u->sched_name, "none")) {
+		sched = ip_vs_scheduler_get(u->sched_name);
+		if (!sched) {
+			pr_info("Scheduler module ip_vs_%s not found\n",
+				u->sched_name);
+			return -ENOENT;
+		}
 	}
 	old_sched = sched;
 
@@ -1315,14 +1324,20 @@ ip_vs_edit_service(struct ip_vs_service *svc, struct ip_vs_service_user_kern *u)
 
 	old_sched = rcu_dereference_protected(svc->scheduler, 1);
 	if (sched != old_sched) {
+		if (old_sched) {
+			ip_vs_unbind_scheduler(svc, old_sched);
+			RCU_INIT_POINTER(svc->scheduler, NULL);
+			/* Wait all svc->sched_data users */
+			synchronize_rcu();
+		}
 		/* Bind the new scheduler */
-		ret = ip_vs_bind_scheduler(svc, sched);
-		if (ret) {
-			old_sched = sched;
-			goto out;
+		if (sched) {
+			ret = ip_vs_bind_scheduler(svc, sched);
+			if (ret) {
+				ip_vs_scheduler_put(sched);
+				goto out;
+			}
 		}
-		/* Unbind the old scheduler on success */
-		ip_vs_unbind_scheduler(svc, old_sched);
 	}
 
 	/*
@@ -1962,6 +1977,7 @@ static int ip_vs_info_seq_show(struct seq_file *seq, void *v)
 		const struct ip_vs_iter *iter = seq->private;
 		const struct ip_vs_dest *dest;
 		struct ip_vs_scheduler *sched = rcu_dereference(svc->scheduler);
+		char *sched_name = sched ? sched->name : "none";
 
 		if (iter->table == ip_vs_svc_table) {
 #ifdef CONFIG_IP_VS_IPV6
@@ -1970,18 +1986,18 @@ static int ip_vs_info_seq_show(struct seq_file *seq, void *v)
 					   ip_vs_proto_name(svc->protocol),
 					   &svc->addr.in6,
 					   ntohs(svc->port),
-					   sched->name);
+					   sched_name);
 			else
 #endif
 				seq_printf(seq, "%s  %08X:%04X %s %s ",
 					   ip_vs_proto_name(svc->protocol),
 					   ntohl(svc->addr.ip),
 					   ntohs(svc->port),
-					   sched->name,
+					   sched_name,
 					   (svc->flags & IP_VS_SVC_F_ONEPACKET)?"ops ":"");
 		} else {
 			seq_printf(seq, "FWM  %08X %s %s",
-				   svc->fwmark, sched->name,
+				   svc->fwmark, sched_name,
 				   (svc->flags & IP_VS_SVC_F_ONEPACKET)?"ops ":"");
 		}
 
@@ -2401,13 +2417,15 @@ static void
 ip_vs_copy_service(struct ip_vs_service_entry *dst, struct ip_vs_service *src)
 {
 	struct ip_vs_scheduler *sched;
+	char *sched_name;
 
 	sched = rcu_dereference_protected(src->scheduler, 1);
+	sched_name = sched ? sched->name : "none";
 	dst->protocol = src->protocol;
 	dst->addr = src->addr.ip;
 	dst->port = src->port;
 	dst->fwmark = src->fwmark;
-	strlcpy(dst->sched_name, sched->name, sizeof(dst->sched_name));
+	strlcpy(dst->sched_name, sched_name, sizeof(dst->sched_name));
 	dst->flags = src->flags;
 	dst->timeout = src->timeout / HZ;
 	dst->netmask = src->netmask;
@@ -2836,6 +2854,7 @@ static int ip_vs_genl_fill_service(struct sk_buff *skb,
 	struct nlattr *nl_service;
 	struct ip_vs_flags flags = { .flags = svc->flags,
 				     .mask = ~0 };
+	char *sched_name;
 
 	nl_service = nla_nest_start(skb, IPVS_CMD_ATTR_SERVICE);
 	if (!nl_service)
@@ -2854,8 +2873,9 @@ static int ip_vs_genl_fill_service(struct sk_buff *skb,
 	}
 
 	sched = rcu_dereference_protected(svc->scheduler, 1);
+	sched_name = sched ? sched->name : "none";
 	pe = rcu_dereference_protected(svc->pe, 1);
-	if (nla_put_string(skb, IPVS_SVC_ATTR_SCHED_NAME, sched->name) ||
+	if (nla_put_string(skb, IPVS_SVC_ATTR_SCHED_NAME, sched_name) ||
 	    (pe && nla_put_string(skb, IPVS_SVC_ATTR_PE_NAME, pe->name)) ||
 	    nla_put(skb, IPVS_SVC_ATTR_FLAGS, sizeof(flags), &flags) ||
 	    nla_put_u32(skb, IPVS_SVC_ATTR_TIMEOUT, svc->timeout / HZ) ||
diff --git a/net/netfilter/ipvs/ip_vs_sched.c b/net/netfilter/ipvs/ip_vs_sched.c
index 4dbcda6258bc..21b6b515a09c 100644
--- a/net/netfilter/ipvs/ip_vs_sched.c
+++ b/net/netfilter/ipvs/ip_vs_sched.c
@@ -74,7 +74,7 @@ void ip_vs_unbind_scheduler(struct ip_vs_service *svc,
 
 	if (sched->done_service)
 		sched->done_service(svc);
-	/* svc->scheduler can not be set to NULL */
+	/* svc->scheduler can be set to NULL only by caller */
 }
 
 
@@ -148,21 +148,21 @@ void ip_vs_scheduler_put(struct ip_vs_scheduler *scheduler)
 
 void ip_vs_scheduler_err(struct ip_vs_service *svc, const char *msg)
 {
-	struct ip_vs_scheduler *sched;
+	struct ip_vs_scheduler *sched = rcu_dereference(svc->scheduler);
+	char *sched_name = sched ? sched->name : "none";
 
-	sched = rcu_dereference(svc->scheduler);
 	if (svc->fwmark) {
 		IP_VS_ERR_RL("%s: FWM %u 0x%08X - %s\n",
-			     sched->name, svc->fwmark, svc->fwmark, msg);
+			     sched_name, svc->fwmark, svc->fwmark, msg);
 #ifdef CONFIG_IP_VS_IPV6
 	} else if (svc->af == AF_INET6) {
 		IP_VS_ERR_RL("%s: %s [%pI6c]:%d - %s\n",
-			     sched->name, ip_vs_proto_name(svc->protocol),
+			     sched_name, ip_vs_proto_name(svc->protocol),
 			     &svc->addr.in6, ntohs(svc->port), msg);
 #endif
 	} else {
 		IP_VS_ERR_RL("%s: %s %pI4:%d - %s\n",
-			     sched->name, ip_vs_proto_name(svc->protocol),
+			     sched_name, ip_vs_proto_name(svc->protocol),
 			     &svc->addr.ip, ntohs(svc->port), msg);
 	}
 }
diff --git a/net/netfilter/ipvs/ip_vs_sync.c b/net/netfilter/ipvs/ip_vs_sync.c
index 7162c86fd50d..72fac696c85e 100644
--- a/net/netfilter/ipvs/ip_vs_sync.c
+++ b/net/netfilter/ipvs/ip_vs_sync.c
@@ -612,7 +612,7 @@ static void ip_vs_sync_conn_v0(struct net *net, struct ip_vs_conn *cp,
 			pkts = atomic_add_return(1, &cp->in_pkts);
 		else
 			pkts = sysctl_sync_threshold(ipvs);
-		ip_vs_sync_conn(net, cp->control, pkts);
+		ip_vs_sync_conn(net, cp, pkts);
 	}
 }
 
diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c
index bd90bf8107da..72f030878e7a 100644
--- a/net/netfilter/ipvs/ip_vs_xmit.c
+++ b/net/netfilter/ipvs/ip_vs_xmit.c
@@ -130,7 +130,6 @@ static struct rtable *do_output_route4(struct net *net, __be32 daddr,
 
 	memset(&fl4, 0, sizeof(fl4));
 	fl4.daddr = daddr;
-	fl4.saddr = (rt_mode & IP_VS_RT_MODE_CONNECT) ? *saddr : 0;
 	fl4.flowi4_flags = (rt_mode & IP_VS_RT_MODE_KNOWN_NH) ?
 			   FLOWI_FLAG_KNOWN_NH : 0;
 
@@ -524,6 +523,21 @@ static inline int ip_vs_tunnel_xmit_prepare(struct sk_buff *skb,
 	return ret;
 }
 
+/* In the event of a remote destination, it's possible that we would have
+ * matches against an old socket (particularly a TIME-WAIT socket). This
+ * causes havoc down the line (ip_local_out et. al. expect regular sockets
+ * and invalid memory accesses will happen) so simply drop the association
+ * in this case.
+*/
+static inline void ip_vs_drop_early_demux_sk(struct sk_buff *skb)
+{
+	/* If dev is set, the packet came from the LOCAL_IN callback and
+	 * not from a local TCP socket.
+	 */
+	if (skb->dev)
+		skb_orphan(skb);
+}
+
 /* return NF_STOLEN (sent) or NF_ACCEPT if local=1 (not sent) */
 static inline int ip_vs_nat_send_or_cont(int pf, struct sk_buff *skb,
 					 struct ip_vs_conn *cp, int local)
@@ -535,12 +549,21 @@ static inline int ip_vs_nat_send_or_cont(int pf, struct sk_buff *skb,
 		ip_vs_notrack(skb);
 	else
 		ip_vs_update_conntrack(skb, cp, 1);
+
+	/* Remove the early_demux association unless it's bound for the
+	 * exact same port and address on this host after translation.
+	 */
+	if (!local || cp->vport != cp->dport ||
+	    !ip_vs_addr_equal(cp->af, &cp->vaddr, &cp->daddr))
+		ip_vs_drop_early_demux_sk(skb);
+
 	if (!local) {
 		skb_forward_csum(skb);
 		NF_HOOK(pf, NF_INET_LOCAL_OUT, skb, NULL, skb_dst(skb)->dev,
 			dst_output);
 	} else
 		ret = NF_ACCEPT;
+
 	return ret;
 }
 
@@ -554,6 +577,7 @@ static inline int ip_vs_send_or_cont(int pf, struct sk_buff *skb,
 	if (likely(!(cp->flags & IP_VS_CONN_F_NFCT)))
 		ip_vs_notrack(skb);
 	if (!local) {
+		ip_vs_drop_early_demux_sk(skb);
 		skb_forward_csum(skb);
 		NF_HOOK(pf, NF_INET_LOCAL_OUT, skb, NULL, skb_dst(skb)->dev,
 			dst_output);
@@ -842,6 +866,8 @@ ip_vs_prepare_tunneled_skb(struct sk_buff *skb, int skb_af,
 	struct ipv6hdr *old_ipv6h = NULL;
 #endif
 
+	ip_vs_drop_early_demux_sk(skb);
+
 	if (skb_headroom(skb) < max_headroom || skb_cloned(skb)) {
 		new_skb = skb_realloc_headroom(skb, max_headroom);
 		if (!new_skb)
diff --git a/net/netfilter/nf_conntrack_expect.c b/net/netfilter/nf_conntrack_expect.c
index 91a1837acd0e..26af45193ab7 100644
--- a/net/netfilter/nf_conntrack_expect.c
+++ b/net/netfilter/nf_conntrack_expect.c
@@ -219,7 +219,8 @@ static inline int expect_clash(const struct nf_conntrack_expect *a,
 			a->mask.src.u3.all[count] & b->mask.src.u3.all[count];
 	}
 
-	return nf_ct_tuple_mask_cmp(&a->tuple, &b->tuple, &intersect_mask);
+	return nf_ct_tuple_mask_cmp(&a->tuple, &b->tuple, &intersect_mask) &&
+	       nf_ct_zone(a->master) == nf_ct_zone(b->master);
 }
 
 static inline int expect_matches(const struct nf_conntrack_expect *a,
diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c
index 1bd9ed9e62f6..d3ea2999d0dc 100644
--- a/net/netfilter/nf_conntrack_netlink.c
+++ b/net/netfilter/nf_conntrack_netlink.c
@@ -2956,11 +2956,6 @@ ctnetlink_create_expect(struct net *net, u16 zone,
 	}
 
 	err = nf_ct_expect_related_report(exp, portid, report);
-	if (err < 0)
-		goto err_exp;
-
-	return 0;
-err_exp:
 	nf_ct_expect_put(exp);
 err_ct:
 	nf_ct_put(ct);
diff --git a/net/netfilter/nf_log.c b/net/netfilter/nf_log.c
index d7197649dba6..cfe93c2227c5 100644
--- a/net/netfilter/nf_log.c
+++ b/net/netfilter/nf_log.c
@@ -19,6 +19,9 @@
 static struct nf_logger __rcu *loggers[NFPROTO_NUMPROTO][NF_LOG_TYPE_MAX] __read_mostly;
 static DEFINE_MUTEX(nf_log_mutex);
 
+#define nft_log_dereference(logger) \
+	rcu_dereference_protected(logger, lockdep_is_held(&nf_log_mutex))
+
 static struct nf_logger *__find_logger(int pf, const char *str_logger)
 {
 	struct nf_logger *log;
@@ -28,8 +31,7 @@ static struct nf_logger *__find_logger(int pf, const char *str_logger)
 		if (loggers[pf][i] == NULL)
 			continue;
 
-		log = rcu_dereference_protected(loggers[pf][i],
-						lockdep_is_held(&nf_log_mutex));
+		log = nft_log_dereference(loggers[pf][i]);
 		if (!strncasecmp(str_logger, log->name, strlen(log->name)))
 			return log;
 	}
@@ -45,8 +47,7 @@ void nf_log_set(struct net *net, u_int8_t pf, const struct nf_logger *logger)
 		return;
 
 	mutex_lock(&nf_log_mutex);
-	log = rcu_dereference_protected(net->nf.nf_loggers[pf],
-					lockdep_is_held(&nf_log_mutex));
+	log = nft_log_dereference(net->nf.nf_loggers[pf]);
 	if (log == NULL)
 		rcu_assign_pointer(net->nf.nf_loggers[pf], logger);
 
@@ -61,8 +62,7 @@ void nf_log_unset(struct net *net, const struct nf_logger *logger)
 
 	mutex_lock(&nf_log_mutex);
 	for (i = 0; i < NFPROTO_NUMPROTO; i++) {
-		log = rcu_dereference_protected(net->nf.nf_loggers[i],
-				lockdep_is_held(&nf_log_mutex));
+		log = nft_log_dereference(net->nf.nf_loggers[i]);
 		if (log == logger)
 			RCU_INIT_POINTER(net->nf.nf_loggers[i], NULL);
 	}
@@ -97,12 +97,17 @@ EXPORT_SYMBOL(nf_log_register);
 
 void nf_log_unregister(struct nf_logger *logger)
 {
+	const struct nf_logger *log;
 	int i;
 
 	mutex_lock(&nf_log_mutex);
-	for (i = 0; i < NFPROTO_NUMPROTO; i++)
-		RCU_INIT_POINTER(loggers[i][logger->type], NULL);
+	for (i = 0; i < NFPROTO_NUMPROTO; i++) {
+		log = nft_log_dereference(loggers[i][logger->type]);
+		if (log == logger)
+			RCU_INIT_POINTER(loggers[i][logger->type], NULL);
+	}
 	mutex_unlock(&nf_log_mutex);
+	synchronize_rcu();
 }
 EXPORT_SYMBOL(nf_log_unregister);
 
@@ -297,8 +302,7 @@ static int seq_show(struct seq_file *s, void *v)
 	int i, ret;
 	struct net *net = seq_file_net(s);
 
-	logger = rcu_dereference_protected(net->nf.nf_loggers[*pos],
-					   lockdep_is_held(&nf_log_mutex));
+	logger = nft_log_dereference(net->nf.nf_loggers[*pos]);
 
 	if (!logger)
 		ret = seq_printf(s, "%2lld NONE (", *pos);
@@ -312,8 +316,7 @@ static int seq_show(struct seq_file *s, void *v)
 		if (loggers[*pos][i] == NULL)
 			continue;
 
-		logger = rcu_dereference_protected(loggers[*pos][i],
-					   lockdep_is_held(&nf_log_mutex));
+		logger = nft_log_dereference(loggers[*pos][i]);
 		ret = seq_printf(s, "%s", logger->name);
 		if (ret < 0)
 			return ret;
@@ -385,8 +388,7 @@ static int nf_log_proc_dostring(struct ctl_table *table, int write,
 		mutex_unlock(&nf_log_mutex);
 	} else {
 		mutex_lock(&nf_log_mutex);
-		logger = rcu_dereference_protected(net->nf.nf_loggers[tindex],
-						   lockdep_is_held(&nf_log_mutex));
+		logger = nft_log_dereference(net->nf.nf_loggers[tindex]);
 		if (!logger)
 			table->data = "NONE";
 		else
diff --git a/net/netfilter/nfnetlink.c b/net/netfilter/nfnetlink.c
index 1aa7049c93f5..e41bab38a3ca 100644
--- a/net/netfilter/nfnetlink.c
+++ b/net/netfilter/nfnetlink.c
@@ -433,6 +433,7 @@ done:
 static void nfnetlink_rcv(struct sk_buff *skb)
 {
 	struct nlmsghdr *nlh = nlmsg_hdr(skb);
+	u_int16_t res_id;
 	int msglen;
 
 	if (nlh->nlmsg_len < NLMSG_HDRLEN ||
@@ -457,7 +458,12 @@ static void nfnetlink_rcv(struct sk_buff *skb)
 
 		nfgenmsg = nlmsg_data(nlh);
 		skb_pull(skb, msglen);
-		nfnetlink_rcv_batch(skb, nlh, nfgenmsg->res_id);
+		/* Work around old nft using host byte order */
+		if (nfgenmsg->res_id == NFNL_SUBSYS_NFTABLES)
+			res_id = NFNL_SUBSYS_NFTABLES;
+		else
+			res_id = ntohs(nfgenmsg->res_id);
+		nfnetlink_rcv_batch(skb, nlh, res_id);
 	} else {
 		netlink_rcv_skb(skb, &nfnetlink_rcv_msg);
 	}
diff --git a/net/netfilter/nft_compat.c b/net/netfilter/nft_compat.c
index e22a2961cc39..ff6f35971ea2 100644
--- a/net/netfilter/nft_compat.c
+++ b/net/netfilter/nft_compat.c
@@ -561,6 +561,13 @@ struct nft_xt {
 
 static struct nft_expr_type nft_match_type;
 
+static bool nft_match_cmp(const struct xt_match *match,
+			  const char *name, u32 rev, u32 family)
+{
+	return strcmp(match->name, name) == 0 && match->revision == rev &&
+	       (match->family == NFPROTO_UNSPEC || match->family == family);
+}
+
 static const struct nft_expr_ops *
 nft_match_select_ops(const struct nft_ctx *ctx,
 		     const struct nlattr * const tb[])
@@ -568,7 +575,7 @@ nft_match_select_ops(const struct nft_ctx *ctx,
 	struct nft_xt *nft_match;
 	struct xt_match *match;
 	char *mt_name;
-	__u32 rev, family;
+	u32 rev, family;
 
 	if (tb[NFTA_MATCH_NAME] == NULL ||
 	    tb[NFTA_MATCH_REV] == NULL ||
@@ -583,9 +590,12 @@ nft_match_select_ops(const struct nft_ctx *ctx,
 	list_for_each_entry(nft_match, &nft_match_list, head) {
 		struct xt_match *match = nft_match->ops.data;
 
-		if (strcmp(match->name, mt_name) == 0 &&
-		    match->revision == rev && match->family == family)
+		if (nft_match_cmp(match, mt_name, rev, family)) {
+			if (!try_module_get(match->me))
+				return ERR_PTR(-ENOENT);
+
 			return &nft_match->ops;
+		}
 	}
 
 	match = xt_request_find_match(family, mt_name, rev);
@@ -631,6 +641,13 @@ static LIST_HEAD(nft_target_list);
 
 static struct nft_expr_type nft_target_type;
 
+static bool nft_target_cmp(const struct xt_target *tg,
+			   const char *name, u32 rev, u32 family)
+{
+	return strcmp(tg->name, name) == 0 && tg->revision == rev &&
+	       (tg->family == NFPROTO_UNSPEC || tg->family == family);
+}
+
 static const struct nft_expr_ops *
 nft_target_select_ops(const struct nft_ctx *ctx,
 		      const struct nlattr * const tb[])
@@ -638,7 +655,7 @@ nft_target_select_ops(const struct nft_ctx *ctx,
 	struct nft_xt *nft_target;
 	struct xt_target *target;
 	char *tg_name;
-	__u32 rev, family;
+	u32 rev, family;
 
 	if (tb[NFTA_TARGET_NAME] == NULL ||
 	    tb[NFTA_TARGET_REV] == NULL ||
@@ -653,9 +670,12 @@ nft_target_select_ops(const struct nft_ctx *ctx,
 	list_for_each_entry(nft_target, &nft_target_list, head) {
 		struct xt_target *target = nft_target->ops.data;
 
-		if (strcmp(target->name, tg_name) == 0 &&
-		    target->revision == rev && target->family == family)
+		if (nft_target_cmp(target, tg_name, rev, family)) {
+			if (!try_module_get(target->me))
+				return ERR_PTR(-ENOENT);
+
 			return &nft_target->ops;
+		}
 	}
 
 	target = xt_request_find_target(family, tg_name, rev);
diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index 6ffd1ebaba93..fe106b50053e 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -133,6 +133,24 @@ static inline u32 netlink_group_mask(u32 group)
 	return group ? 1 << (group - 1) : 0;
 }
 
+static struct sk_buff *netlink_to_full_skb(const struct sk_buff *skb,
+					   gfp_t gfp_mask)
+{
+	unsigned int len = skb_end_offset(skb);
+	struct sk_buff *new;
+
+	new = alloc_skb(len, gfp_mask);
+	if (new == NULL)
+		return NULL;
+
+	NETLINK_CB(new).portid = NETLINK_CB(skb).portid;
+	NETLINK_CB(new).dst_group = NETLINK_CB(skb).dst_group;
+	NETLINK_CB(new).creds = NETLINK_CB(skb).creds;
+
+	memcpy(skb_put(new, len), skb->data, len);
+	return new;
+}
+
 int netlink_add_tap(struct netlink_tap *nt)
 {
 	if (unlikely(nt->dev->type != ARPHRD_NETLINK))
@@ -215,7 +233,11 @@ static int __netlink_deliver_tap_skb(struct sk_buff *skb,
 	int ret = -ENOMEM;
 
 	dev_hold(dev);
-	nskb = skb_clone(skb, GFP_ATOMIC);
+
+	if (netlink_skb_is_mmaped(skb) || is_vmalloc_addr(skb->head))
+		nskb = netlink_to_full_skb(skb, GFP_ATOMIC);
+	else
+		nskb = skb_clone(skb, GFP_ATOMIC);
 	if (nskb) {
 		nskb->dev = dev;
 		nskb->protocol = htons((u16) sk->sk_protocol);
@@ -287,11 +309,6 @@ static void netlink_rcv_wake(struct sock *sk)
 }
 
 #ifdef CONFIG_NETLINK_MMAP
-static bool netlink_skb_is_mmaped(const struct sk_buff *skb)
-{
-	return NETLINK_CB(skb).flags & NETLINK_SKB_MMAPED;
-}
-
 static bool netlink_rx_is_mmaped(struct sock *sk)
 {
 	return nlk_sk(sk)->rx_ring.pg_vec != NULL;
@@ -843,7 +860,6 @@ static void netlink_ring_set_copied(struct sock *sk, struct sk_buff *skb)
 }
 
 #else /* CONFIG_NETLINK_MMAP */
-#define netlink_skb_is_mmaped(skb)	false
 #define netlink_rx_is_mmaped(sk)	false
 #define netlink_tx_is_mmaped(sk)	false
 #define netlink_mmap			sock_no_mmap
diff --git a/net/netlink/af_netlink.h b/net/netlink/af_netlink.h
index b20a1731759b..3951874e715d 100644
--- a/net/netlink/af_netlink.h
+++ b/net/netlink/af_netlink.h
@@ -57,6 +57,15 @@ static inline struct netlink_sock *nlk_sk(struct sock *sk)
 	return container_of(sk, struct netlink_sock, sk);
 }
 
+static inline bool netlink_skb_is_mmaped(const struct sk_buff *skb)
+{
+#ifdef CONFIG_NETLINK_MMAP
+	return NETLINK_CB(skb).flags & NETLINK_SKB_MMAPED;
+#else
+	return false;
+#endif /* CONFIG_NETLINK_MMAP */
+}
+
 struct netlink_table {
 	struct rhashtable	hash;
 	struct hlist_head	mc_list;
diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c
index 28213dff723d..acf6b2edba65 100644
--- a/net/openvswitch/datapath.c
+++ b/net/openvswitch/datapath.c
@@ -834,7 +834,7 @@ static int ovs_flow_cmd_new(struct sk_buff *skb, struct genl_info *info)
 	if (error)
 		goto err_kfree_flow;
 
-	ovs_flow_mask_key(&new_flow->key, &new_flow->unmasked_key, &mask);
+	ovs_flow_mask_key(&new_flow->key, &new_flow->unmasked_key, true, &mask);
 
 	/* Validate actions. */
 	acts = ovs_nla_alloc_flow_actions(nla_len(a[OVS_FLOW_ATTR_ACTIONS]));
@@ -949,7 +949,7 @@ static struct sw_flow_actions *get_flow_actions(const struct nlattr *a,
 	if (IS_ERR(acts))
 		return acts;
 
-	ovs_flow_mask_key(&masked_key, key, mask);
+	ovs_flow_mask_key(&masked_key, key, true, mask);
 	error = ovs_nla_copy_actions(a, &masked_key, 0, &acts);
 	if (error) {
 		OVS_NLERR("Flow actions may not be safe on all matching packets.\n");
diff --git a/net/openvswitch/flow_table.c b/net/openvswitch/flow_table.c
index cf2d853646f0..740041a09b9d 100644
--- a/net/openvswitch/flow_table.c
+++ b/net/openvswitch/flow_table.c
@@ -56,20 +56,21 @@ static u16 range_n_bytes(const struct sw_flow_key_range *range)
 }
 
 void ovs_flow_mask_key(struct sw_flow_key *dst, const struct sw_flow_key *src,
-		       const struct sw_flow_mask *mask)
+		       bool full, const struct sw_flow_mask *mask)
 {
-	const long *m = (const long *)((const u8 *)&mask->key +
-				mask->range.start);
-	const long *s = (const long *)((const u8 *)src +
-				mask->range.start);
-	long *d = (long *)((u8 *)dst + mask->range.start);
+	int start = full ? 0 : mask->range.start;
+	int len = full ? sizeof *dst : range_n_bytes(&mask->range);
+	const long *m = (const long *)((const u8 *)&mask->key + start);
+	const long *s = (const long *)((const u8 *)src + start);
+	long *d = (long *)((u8 *)dst + start);
 	int i;
 
-	/* The memory outside of the 'mask->range' are not set since
-	 * further operations on 'dst' only uses contents within
-	 * 'mask->range'.
+	/* If 'full' is true then all of 'dst' is fully initialized. Otherwise,
+	 * if 'full' is false the memory outside of the 'mask->range' is left
+	 * uninitialized. This can be used as an optimization when further
+	 * operations on 'dst' only use contents within 'mask->range'.
 	 */
-	for (i = 0; i < range_n_bytes(&mask->range); i += sizeof(long))
+	for (i = 0; i < len; i += sizeof(long))
 		*d++ = *s++ & *m++;
 }
 
@@ -418,7 +419,7 @@ static struct sw_flow *masked_flow_lookup(struct table_instance *ti,
 	u32 hash;
 	struct sw_flow_key masked_key;
 
-	ovs_flow_mask_key(&masked_key, unmasked, mask);
+	ovs_flow_mask_key(&masked_key, unmasked, false, mask);
 	hash = flow_hash(&masked_key, key_start, key_end);
 	head = find_bucket(ti, hash);
 	hlist_for_each_entry_rcu(flow, head, hash_node[ti->node_ver]) {
diff --git a/net/openvswitch/flow_table.h b/net/openvswitch/flow_table.h
index 5918bff7f3f6..2f0cf200ede9 100644
--- a/net/openvswitch/flow_table.h
+++ b/net/openvswitch/flow_table.h
@@ -82,5 +82,5 @@ bool ovs_flow_cmp_unmasked_key(const struct sw_flow *flow,
 			       struct sw_flow_match *match);
 
 void ovs_flow_mask_key(struct sw_flow_key *dst, const struct sw_flow_key *src,
-		       const struct sw_flow_mask *mask);
+		       bool full, const struct sw_flow_mask *mask);
 #endif /* flow_table.h */
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 5dcfe05ea232..bf6097793170 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -2645,7 +2645,7 @@ static int packet_release(struct socket *sock)
 static int packet_do_bind(struct sock *sk, struct net_device *dev, __be16 proto)
 {
 	struct packet_sock *po = pkt_sk(sk);
-	const struct net_device *dev_curr;
+	struct net_device *dev_curr;
 	__be16 proto_curr;
 	bool need_rehook;
 
@@ -2669,15 +2669,13 @@ static int packet_do_bind(struct sock *sk, struct net_device *dev, __be16 proto)
 
 		po->num = proto;
 		po->prot_hook.type = proto;
-
-		if (po->prot_hook.dev)
-			dev_put(po->prot_hook.dev);
-
 		po->prot_hook.dev = dev;
 
 		po->ifindex = dev ? dev->ifindex : 0;
 		packet_cached_dev_assign(po, dev);
 	}
+	if (dev_curr)
+		dev_put(dev_curr);
 
 	if (proto == 0 || !need_rehook)
 		goto out_unlock;
diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c
index 8f34b27d5775..143c4ebd55fa 100644
--- a/net/sctp/protocol.c
+++ b/net/sctp/protocol.c
@@ -1166,7 +1166,7 @@ static void sctp_v4_del_protocol(void)
 	unregister_inetaddr_notifier(&sctp_inetaddr_notifier);
 }
 
-static int __net_init sctp_net_init(struct net *net)
+static int __net_init sctp_defaults_init(struct net *net)
 {
 	int status;
 
@@ -1259,12 +1259,6 @@ static int __net_init sctp_net_init(struct net *net)
 
 	sctp_dbg_objcnt_init(net);
 
-	/* Initialize the control inode/socket for handling OOTB packets.  */
-	if ((status = sctp_ctl_sock_init(net))) {
-		pr_err("Failed to initialize the SCTP control sock\n");
-		goto err_ctl_sock_init;
-	}
-
 	/* Initialize the local address list. */
 	INIT_LIST_HEAD(&net->sctp.local_addr_list);
 	spin_lock_init(&net->sctp.local_addr_lock);
@@ -1280,9 +1274,6 @@ static int __net_init sctp_net_init(struct net *net)
 
 	return 0;
 
-err_ctl_sock_init:
-	sctp_dbg_objcnt_exit(net);
-	sctp_proc_exit(net);
 err_init_proc:
 	cleanup_sctp_mibs(net);
 err_init_mibs:
@@ -1291,15 +1282,12 @@ err_sysctl_register:
 	return status;
 }
 
-static void __net_exit sctp_net_exit(struct net *net)
+static void __net_exit sctp_defaults_exit(struct net *net)
 {
 	/* Free the local address list */
 	sctp_free_addr_wq(net);
 	sctp_free_local_addr_list(net);
 
-	/* Free the control endpoint.  */
-	inet_ctl_sock_destroy(net->sctp.ctl_sock);
-
 	sctp_dbg_objcnt_exit(net);
 
 	sctp_proc_exit(net);
@@ -1307,9 +1295,32 @@ static void __net_exit sctp_net_exit(struct net *net)
 	sctp_sysctl_net_unregister(net);
 }
 
-static struct pernet_operations sctp_net_ops = {
-	.init = sctp_net_init,
-	.exit = sctp_net_exit,
+static struct pernet_operations sctp_defaults_ops = {
+	.init = sctp_defaults_init,
+	.exit = sctp_defaults_exit,
+};
+
+static int __net_init sctp_ctrlsock_init(struct net *net)
+{
+	int status;
+
+	/* Initialize the control inode/socket for handling OOTB packets.  */
+	status = sctp_ctl_sock_init(net);
+	if (status)
+		pr_err("Failed to initialize the SCTP control sock\n");
+
+	return status;
+}
+
+static void __net_init sctp_ctrlsock_exit(struct net *net)
+{
+	/* Free the control endpoint.  */
+	inet_ctl_sock_destroy(net->sctp.ctl_sock);
+}
+
+static struct pernet_operations sctp_ctrlsock_ops = {
+	.init = sctp_ctrlsock_init,
+	.exit = sctp_ctrlsock_exit,
 };
 
 /* Initialize the universe into something sensible.  */
@@ -1443,8 +1454,11 @@ static __init int sctp_init(void)
 	sctp_v4_pf_init();
 	sctp_v6_pf_init();
 
-	status = sctp_v4_protosw_init();
+	status = register_pernet_subsys(&sctp_defaults_ops);
+	if (status)
+		goto err_register_defaults;
 
+	status = sctp_v4_protosw_init();
 	if (status)
 		goto err_protosw_init;
 
@@ -1452,9 +1466,9 @@ static __init int sctp_init(void)
 	if (status)
 		goto err_v6_protosw_init;
 
-	status = register_pernet_subsys(&sctp_net_ops);
+	status = register_pernet_subsys(&sctp_ctrlsock_ops);
 	if (status)
-		goto err_register_pernet_subsys;
+		goto err_register_ctrlsock;
 
 	status = sctp_v4_add_protocol();
 	if (status)
@@ -1470,12 +1484,14 @@ out:
 err_v6_add_protocol:
 	sctp_v4_del_protocol();
 err_add_protocol:
-	unregister_pernet_subsys(&sctp_net_ops);
-err_register_pernet_subsys:
+	unregister_pernet_subsys(&sctp_ctrlsock_ops);
+err_register_ctrlsock:
 	sctp_v6_protosw_exit();
 err_v6_protosw_init:
 	sctp_v4_protosw_exit();
 err_protosw_init:
+	unregister_pernet_subsys(&sctp_defaults_ops);
+err_register_defaults:
 	sctp_v4_pf_exit();
 	sctp_v6_pf_exit();
 	sctp_sysctl_unregister();
@@ -1508,12 +1524,14 @@ static __exit void sctp_exit(void)
 	sctp_v6_del_protocol();
 	sctp_v4_del_protocol();
 
-	unregister_pernet_subsys(&sctp_net_ops);
+	unregister_pernet_subsys(&sctp_ctrlsock_ops);
 
 	/* Free protosw registrations */
 	sctp_v6_protosw_exit();
 	sctp_v4_protosw_exit();
 
+	unregister_pernet_subsys(&sctp_defaults_ops);
+
 	/* Unregister with socket layer. */
 	sctp_v6_pf_exit();
 	sctp_v4_pf_exit();
diff --git a/net/sunrpc/xprtrdma/svc_rdma_sendto.c b/net/sunrpc/xprtrdma/svc_rdma_sendto.c
index 9f1b50689c0f..03252a652e4b 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_sendto.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_sendto.c
@@ -372,6 +372,7 @@ static int send_reply(struct svcxprt_rdma *rdma,
 		      int byte_count)
 {
 	struct ib_send_wr send_wr;
+	u32 xdr_off;
 	int sge_no;
 	int sge_bytes;
 	int page_no;
@@ -406,8 +407,8 @@ static int send_reply(struct svcxprt_rdma *rdma,
 	ctxt->direction = DMA_TO_DEVICE;
 
 	/* Map the payload indicated by 'byte_count' */
+	xdr_off = 0;
 	for (sge_no = 1; byte_count && sge_no < vec->count; sge_no++) {
-		int xdr_off = 0;
 		sge_bytes = min_t(size_t, vec->sge[sge_no].iov_len, byte_count);
 		byte_count -= sge_bytes;
 		ctxt->sge[sge_no].addr =
@@ -443,6 +444,14 @@ static int send_reply(struct svcxprt_rdma *rdma,
 	rqstp->rq_next_page = rqstp->rq_respages + 1;
 
 	BUG_ON(sge_no > rdma->sc_max_sge);
+
+	/* The loop above bumps sc_dma_used for each sge. The
+	 * xdr_buf.tail gets a separate sge, but resides in the
+	 * same page as xdr_buf.head. Don't count it twice.
+	 */
+	if (sge_no > ctxt->count)
+		atomic_dec(&rdma->sc_dma_used);
+
 	memset(&send_wr, 0, sizeof send_wr);
 	ctxt->wr_op = IB_WR_SEND;
 	send_wr.wr_id = (unsigned long)ctxt;