Merge tag 'v4.1.33' into 4.1-2.0.x-imx

Linux 4.1.33

* tag 'v4.1.33': (1760 commits)
  Linux 4.1.33
  Revert "ARC: mm: don't loose PTE_SPECIAL in pte_modify()"
  x86/AMD: Apply erratum 665 on machines without a BIOS fix
  x86/paravirt: Do not trace _paravirt_ident_*() functions
  ovl: listxattr: use strnlen()
  ovl: remove posix_acl_default from workdir
  serial: 8250: added acces i/o products quad and octal serial cards
  sysfs: correctly handle read offset on PREALLOC attrs
  sysfs: correctly handle short reads on PREALLOC attrs.
  kernfs: don't depend on d_find_any_alias() when generating notifications
  dm crypt: fix free of bad values after tfm allocation failure
  dm crypt: fix error with too large bios
  dm log writes: fix check of kthread_run() return value
  dm log writes: fix bug with too large bios
  dm log writes: move IO accounting earlier to fix error path
  NFSv4.x: Fix a refcount leak in nfs_callback_up_net
  xfs: prevent dropping ioend completions during buftarg wait
  xfs: fix superblock inprogress check
  USB: serial: option: add WeTelecom 0x6802 and 0x6803 products
  USB: avoid left shift by -1
  ...

Signed-off-by: Otavio Salvador <otavio@ossystems.com.br>

26 files changed, 503 insertions, 582 deletions

diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index a5aa54ea6533..0cc98b135b8f 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -259,6 +259,9 @@ static int inet_create(struct net *net, struct socket *sock, int protocol,
 	int try_loading_module = 0;
 	int err;
 
+	if (protocol < 0 || protocol >= IPPROTO_MAX)
+		return -EINVAL;
+
 	sock->state = SS_UNCONNECTED;
 
 	/* Look for the requested type/protocol pair. */
diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c
index 419d23c53ec7..a57056d87a43 100644
--- a/net/ipv4/devinet.c
+++ b/net/ipv4/devinet.c
@@ -334,6 +334,9 @@ static void __inet_del_ifa(struct in_device *in_dev, struct in_ifaddr **ifap,
 
 	ASSERT_RTNL();
 
+	if (in_dev->dead)
+		goto no_promotions;
+
 	/* 1. Deleting primary ifaddr forces deletion all secondaries
 	 * unless alias promotion is set
 	 **/
@@ -380,6 +383,7 @@ static void __inet_del_ifa(struct in_device *in_dev, struct in_ifaddr **ifap,
 			fib_del_ifaddr(ifa, ifa1);
 	}
 
+no_promotions:
 	/* 2. Unlink it */
 
 	*ifap = ifa1->ifa_next;
@@ -1839,7 +1843,7 @@ static int inet_netconf_get_devconf(struct sk_buff *in_skb,
 	if (err < 0)
 		goto errout;
 
-	err = EINVAL;
+	err = -EINVAL;
 	if (!tb[NETCONFA_IFINDEX])
 		goto errout;
 
diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index 872494e6e6eb..513b6aabc5b7 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -861,7 +861,11 @@ void fib_del_ifaddr(struct in_ifaddr *ifa, struct in_ifaddr *iprim)
 	if (ifa->ifa_flags & IFA_F_SECONDARY) {
 		prim = inet_ifa_byprefix(in_dev, any, ifa->ifa_mask);
 		if (!prim) {
-			pr_warn("%s: bug: prim == NULL\n", __func__);
+			/* if the device has been deleted, we don't perform
+			 * address promotion
+			 */
+			if (!in_dev->dead)
+				pr_warn("%s: bug: prim == NULL\n", __func__);
 			return;
 		}
 		if (iprim && iprim != prim) {
@@ -876,6 +880,9 @@ void fib_del_ifaddr(struct in_ifaddr *ifa, struct in_ifaddr *iprim)
 		subnet = 1;
 	}
 
+	if (in_dev->dead)
+		goto no_promotions;
+
 	/* Deletion is more complicated than add.
 	 * We should take care of not to delete too much :-)
 	 *
@@ -951,6 +958,7 @@ void fib_del_ifaddr(struct in_ifaddr *ifa, struct in_ifaddr *iprim)
 		}
 	}
 
+no_promotions:
 	if (!(ok & BRD_OK))
 		fib_magic(RTM_DELROUTE, RTN_BROADCAST, ifa->ifa_broadcast, 32, prim);
 	if (subnet && ifa->ifa_prefixlen < 31) {
diff --git a/net/ipv4/fou.c b/net/ipv4/fou.c
index 34968cd5c146..4b67937692c9 100644
--- a/net/ipv4/fou.c
+++ b/net/ipv4/fou.c
@@ -24,6 +24,7 @@ struct fou {
 	u16 type;
 	struct udp_offload udp_offloads;
 	struct list_head list;
+	struct rcu_head rcu;
 };
 
 #define FOU_F_REMCSUM_NOPARTIAL BIT(0)
@@ -421,7 +422,7 @@ static void fou_release(struct fou *fou)
 	list_del(&fou->list);
 	udp_tunnel_sock_release(sock);
 
-	kfree(fou);
+	kfree_rcu(fou, rcu);
 }
 
 static int fou_encap_init(struct sock *sk, struct fou *fou, struct fou_cfg *cfg)
diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c
index a3a697f5ffba..218abf9fb1ed 100644
--- a/net/ipv4/igmp.c
+++ b/net/ipv4/igmp.c
@@ -353,9 +353,8 @@ static struct sk_buff *igmpv3_newpack(struct net_device *dev, unsigned int mtu)
 	skb_dst_set(skb, &rt->dst);
 	skb->dev = dev;
 
-	skb->reserved_tailroom = skb_end_offset(skb) -
-				 min(mtu, skb_end_offset(skb));
 	skb_reserve(skb, hlen);
+	skb_tailroom_reserve(skb, mtu, tlen);
 
 	skb_reset_network_header(skb);
 	pip = ip_hdr(skb);
diff --git a/net/ipv4/inet_timewait_sock.c b/net/ipv4/inet_timewait_sock.c
index 00ec8d5d7e7e..bb96c1c4edd6 100644
--- a/net/ipv4/inet_timewait_sock.c
+++ b/net/ipv4/inet_timewait_sock.c
@@ -153,13 +153,15 @@ void __inet_twsk_hashdance(struct inet_timewait_sock *tw, struct sock *sk,
 	/*
 	 * Step 2: Hash TW into tcp ehash chain.
 	 * Notes :
-	 * - tw_refcnt is set to 3 because :
+	 * - tw_refcnt is set to 4 because :
 	 * - We have one reference from bhash chain.
 	 * - We have one reference from ehash chain.
+	 * - We have one reference from timer.
+	 * - One reference for ourself (our caller will release it).
 	 * We can use atomic_set() because prior spin_lock()/spin_unlock()
 	 * committed into memory all tw fields.
 	 */
-	atomic_set(&tw->tw_refcnt, 1 + 1 + 1);
+	atomic_set(&tw->tw_refcnt, 4);
 	inet_twsk_add_node_rcu(tw, &ehead->chain);
 
 	/* Step 3: Remove SK from hash chain */
@@ -243,7 +245,7 @@ void inet_twsk_deschedule(struct inet_timewait_sock *tw)
 }
 EXPORT_SYMBOL(inet_twsk_deschedule);
 
-void inet_twsk_schedule(struct inet_timewait_sock *tw, const int timeo)
+void __inet_twsk_schedule(struct inet_timewait_sock *tw, int timeo, bool rearm)
 {
 	/* timeout := RTO * 3.5
 	 *
@@ -271,12 +273,14 @@ void inet_twsk_schedule(struct inet_timewait_sock *tw, const int timeo)
 	 */
 
 	tw->tw_kill = timeo <= 4*HZ;
-	if (!mod_timer_pinned(&tw->tw_timer, jiffies + timeo)) {
-		atomic_inc(&tw->tw_refcnt);
+	if (!rearm) {
+		BUG_ON(mod_timer_pinned(&tw->tw_timer, jiffies + timeo));
 		atomic_inc(&tw->tw_dr->tw_count);
+	} else {
+		mod_timer_pending(&tw->tw_timer, jiffies + timeo);
 	}
 }
-EXPORT_SYMBOL_GPL(inet_twsk_schedule);
+EXPORT_SYMBOL_GPL(__inet_twsk_schedule);
 
 void inet_twsk_purge(struct inet_hashinfo *hashinfo,
 		     struct inet_timewait_death_row *twdr, int family)
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index c65b93a7b711..51573f8a39bc 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -235,6 +235,7 @@ static int ip_finish_output_gso(struct sock *sk, struct sk_buff *skb)
 	 * from host network stack.
 	 */
 	features = netif_skb_features(skb);
+	BUILD_BUG_ON(sizeof(*IPCB(skb)) > SKB_SGO_CB_OFFSET);
 	segs = skb_gso_segment(skb, features & ~NETIF_F_GSO_MASK);
 	if (IS_ERR_OR_NULL(segs)) {
 		kfree_skb(skb);
@@ -893,7 +894,7 @@ static int __ip_append_data(struct sock *sk,
 	if (((length > mtu) || (skb && skb_is_gso(skb))) &&
 	    (sk->sk_protocol == IPPROTO_UDP) &&
 	    (rt->dst.dev->features & NETIF_F_UFO) && !rt->dst.header_len &&
-	    (sk->sk_type == SOCK_DGRAM)) {
+	    (sk->sk_type == SOCK_DGRAM) && !sk->sk_no_check_tx) {
 		err = ip_ufo_append_data(sk, queue, getfrag, from, length,
 					 hh_len, fragheaderlen, transhdrlen,
 					 maxfraglen, flags);
diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c
index 6ddde89996f4..b6c7bdea4853 100644
--- a/net/ipv4/ip_sockglue.c
+++ b/net/ipv4/ip_sockglue.c
@@ -249,6 +249,8 @@ int ip_cmsg_send(struct net *net, struct msghdr *msg, struct ipcm_cookie *ipc,
 		switch (cmsg->cmsg_type) {
 		case IP_RETOPTS:
 			err = cmsg->cmsg_len - CMSG_ALIGN(sizeof(struct cmsghdr));
+
+			/* Our caller is responsible for freeing ipc->opt */
 			err = ip_options_get(net, &ipc->opt, CMSG_DATA(cmsg),
 					     err < 40 ? err : 40);
 			if (err)
diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c
index 626d9e56a6bd..35080a708b59 100644
--- a/net/ipv4/ip_tunnel.c
+++ b/net/ipv4/ip_tunnel.c
@@ -652,6 +652,8 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev,
 	inner_iph = (const struct iphdr *)skb_inner_network_header(skb);
 	connected = (tunnel->parms.iph.daddr != 0);
 
+	memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt));
+
 	dst = tnl_params->daddr;
 	if (dst == 0) {
 		/* NBMA tunnel */
@@ -749,7 +751,6 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev,
 				tunnel->err_time + IPTUNNEL_ERR_TIMEO)) {
 			tunnel->err_count--;
 
-			memset(IPCB(skb), 0, sizeof(*IPCB(skb)));
 			dst_link_failure(skb);
 		} else
 			tunnel->err_count = 0;
diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c
index a61200754f4b..ebf5821caefb 100644
--- a/net/ipv4/netfilter/arp_tables.c
+++ b/net/ipv4/netfilter/arp_tables.c
@@ -354,18 +354,20 @@ unsigned int arpt_do_table(struct sk_buff *skb,
 }
 
 /* All zeroes == unconditional rule. */
-static inline bool unconditional(const struct arpt_arp *arp)
+static inline bool unconditional(const struct arpt_entry *e)
 {
 	static const struct arpt_arp uncond;
 
-	return memcmp(arp, &uncond, sizeof(uncond)) == 0;
+	return e->target_offset == sizeof(struct arpt_entry) &&
+	       memcmp(&e->arp, &uncond, sizeof(uncond)) == 0;
 }
 
 /* Figures out from what hook each rule can be called: returns 0 if
  * there are loops.  Puts hook bitmask in comefrom.
  */
 static int mark_source_chains(const struct xt_table_info *newinfo,
-			      unsigned int valid_hooks, void *entry0)
+			      unsigned int valid_hooks, void *entry0,
+			      unsigned int *offsets)
 {
 	unsigned int hook;
 
@@ -397,11 +399,10 @@ static int mark_source_chains(const struct xt_table_info *newinfo,
 				|= ((1 << hook) | (1 << NF_ARP_NUMHOOKS));
 
 			/* Unconditional return/END. */
-			if ((e->target_offset == sizeof(struct arpt_entry) &&
+			if ((unconditional(e) &&
 			     (strcmp(t->target.u.user.name,
 				     XT_STANDARD_TARGET) == 0) &&
-			     t->verdict < 0 && unconditional(&e->arp)) ||
-			    visited) {
+			     t->verdict < 0) || visited) {
 				unsigned int oldpos, size;
 
 				if ((strcmp(t->target.u.user.name,
@@ -434,6 +435,8 @@ static int mark_source_chains(const struct xt_table_info *newinfo,
 				size = e->next_offset;
 				e = (struct arpt_entry *)
 					(entry0 + pos + size);
+				if (pos + size >= newinfo->size)
+					return 0;
 				e->counters.pcnt = pos;
 				pos += size;
 			} else {
@@ -453,9 +456,16 @@ static int mark_source_chains(const struct xt_table_info *newinfo,
 					/* This a jump; chase it. */
 					duprintf("Jump rule %u -> %u\n",
 						 pos, newpos);
+					if (!xt_find_jump_offset(offsets, newpos,
+								 newinfo->number))
+						return 0;
+					e = (struct arpt_entry *)
+						(entry0 + newpos);
 				} else {
 					/* ... this is a fallthru */
 					newpos = pos + e->next_offset;
+					if (newpos >= newinfo->size)
+						return 0;
 				}
 				e = (struct arpt_entry *)
 					(entry0 + newpos);
@@ -469,25 +479,6 @@ static int mark_source_chains(const struct xt_table_info *newinfo,
 	return 1;
 }
 
-static inline int check_entry(const struct arpt_entry *e, const char *name)
-{
-	const struct xt_entry_target *t;
-
-	if (!arp_checkentry(&e->arp)) {
-		duprintf("arp_tables: arp check failed %p %s.\n", e, name);
-		return -EINVAL;
-	}
-
-	if (e->target_offset + sizeof(struct xt_entry_target) > e->next_offset)
-		return -EINVAL;
-
-	t = arpt_get_target_c(e);
-	if (e->target_offset + t->u.target_size > e->next_offset)
-		return -EINVAL;
-
-	return 0;
-}
-
 static inline int check_target(struct arpt_entry *e, const char *name)
 {
 	struct xt_entry_target *t = arpt_get_target(e);
@@ -517,10 +508,6 @@ find_check_entry(struct arpt_entry *e, const char *name, unsigned int size)
 	struct xt_target *target;
 	int ret;
 
-	ret = check_entry(e, name);
-	if (ret)
-		return ret;
-
 	t = arpt_get_target(e);
 	target = xt_request_find_target(NFPROTO_ARP, t->u.user.name,
 					t->u.user.revision);
@@ -546,7 +533,7 @@ static bool check_underflow(const struct arpt_entry *e)
 	const struct xt_entry_target *t;
 	unsigned int verdict;
 
-	if (!unconditional(&e->arp))
+	if (!unconditional(e))
 		return false;
 	t = arpt_get_target_c(e);
 	if (strcmp(t->u.user.name, XT_STANDARD_TARGET) != 0)
@@ -565,9 +552,11 @@ static inline int check_entry_size_and_hooks(struct arpt_entry *e,
 					     unsigned int valid_hooks)
 {
 	unsigned int h;
+	int err;
 
 	if ((unsigned long)e % __alignof__(struct arpt_entry) != 0 ||
-	    (unsigned char *)e + sizeof(struct arpt_entry) >= limit) {
+	    (unsigned char *)e + sizeof(struct arpt_entry) >= limit ||
+	    (unsigned char *)e + e->next_offset > limit) {
 		duprintf("Bad offset %p\n", e);
 		return -EINVAL;
 	}
@@ -579,6 +568,14 @@ static inline int check_entry_size_and_hooks(struct arpt_entry *e,
 		return -EINVAL;
 	}
 
+	if (!arp_checkentry(&e->arp))
+		return -EINVAL;
+
+	err = xt_check_entry_offsets(e, e->elems, e->target_offset,
+				     e->next_offset);
+	if (err)
+		return err;
+
 	/* Check hooks & underflows */
 	for (h = 0; h < NF_ARP_NUMHOOKS; h++) {
 		if (!(valid_hooks & (1 << h)))
@@ -587,9 +584,9 @@ static inline int check_entry_size_and_hooks(struct arpt_entry *e,
 			newinfo->hook_entry[h] = hook_entries[h];
 		if ((unsigned char *)e - base == underflows[h]) {
 			if (!check_underflow(e)) {
-				pr_err("Underflows must be unconditional and "
-				       "use the STANDARD target with "
-				       "ACCEPT/DROP\n");
+				pr_debug("Underflows must be unconditional and "
+					 "use the STANDARD target with "
+					 "ACCEPT/DROP\n");
 				return -EINVAL;
 			}
 			newinfo->underflow[h] = underflows[h];
@@ -623,6 +620,7 @@ static int translate_table(struct xt_table_info *newinfo, void *entry0,
                            const struct arpt_replace *repl)
 {
 	struct arpt_entry *iter;
+	unsigned int *offsets;
 	unsigned int i;
 	int ret = 0;
 
@@ -636,6 +634,9 @@ static int translate_table(struct xt_table_info *newinfo, void *entry0,
 	}
 
 	duprintf("translate_table: size %u\n", newinfo->size);
+	offsets = xt_alloc_entry_offsets(newinfo->number);
+	if (!offsets)
+		return -ENOMEM;
 	i = 0;
 
 	/* Walk through entries, checking offsets. */
@@ -646,20 +647,21 @@ static int translate_table(struct xt_table_info *newinfo, void *entry0,
 						 repl->underflow,
 						 repl->valid_hooks);
 		if (ret != 0)
-			break;
+			goto out_free;
+		if (i < repl->num_entries)
+			offsets[i] = (void *)iter - entry0;
 		++i;
 		if (strcmp(arpt_get_target(iter)->u.user.name,
 		    XT_ERROR_TARGET) == 0)
 			++newinfo->stacksize;
 	}
 	duprintf("translate_table: ARPT_ENTRY_ITERATE gives %d\n", ret);
-	if (ret != 0)
-		return ret;
 
+	ret = -EINVAL;
 	if (i != repl->num_entries) {
 		duprintf("translate_table: %u not %u entries\n",
 			 i, repl->num_entries);
-		return -EINVAL;
+		goto out_free;
 	}
 
 	/* Check hooks all assigned */
@@ -670,19 +672,20 @@ static int translate_table(struct xt_table_info *newinfo, void *entry0,
 		if (newinfo->hook_entry[i] == 0xFFFFFFFF) {
 			duprintf("Invalid hook entry %u %u\n",
 				 i, repl->hook_entry[i]);
-			return -EINVAL;
+			goto out_free;
 		}
 		if (newinfo->underflow[i] == 0xFFFFFFFF) {
 			duprintf("Invalid underflow %u %u\n",
 				 i, repl->underflow[i]);
-			return -EINVAL;
+			goto out_free;
 		}
 	}
 
-	if (!mark_source_chains(newinfo, repl->valid_hooks, entry0)) {
-		duprintf("Looping hook\n");
-		return -ELOOP;
+	if (!mark_source_chains(newinfo, repl->valid_hooks, entry0, offsets)) {
+		ret = -ELOOP;
+		goto out_free;
 	}
+	kvfree(offsets);
 
 	/* Finally, each sanity check must pass */
 	i = 0;
@@ -709,6 +712,9 @@ static int translate_table(struct xt_table_info *newinfo, void *entry0,
 	}
 
 	return ret;
+ out_free:
+	kvfree(offsets);
+	return ret;
 }
 
 static void get_counters(const struct xt_table_info *t,
@@ -1118,56 +1124,18 @@ static int do_add_counters(struct net *net, const void __user *user,
 	unsigned int i, curcpu;
 	struct xt_counters_info tmp;
 	struct xt_counters *paddc;
-	unsigned int num_counters;
-	const char *name;
-	int size;
-	void *ptmp;
 	struct xt_table *t;
 	const struct xt_table_info *private;
 	int ret = 0;
 	void *loc_cpu_entry;
 	struct arpt_entry *iter;
 	unsigned int addend;
-#ifdef CONFIG_COMPAT
-	struct compat_xt_counters_info compat_tmp;
-
-	if (compat) {
-		ptmp = &compat_tmp;
-		size = sizeof(struct compat_xt_counters_info);
-	} else
-#endif
-	{
-		ptmp = &tmp;
-		size = sizeof(struct xt_counters_info);
-	}
 
-	if (copy_from_user(ptmp, user, size) != 0)
-		return -EFAULT;
-
-#ifdef CONFIG_COMPAT
-	if (compat) {
-		num_counters = compat_tmp.num_counters;
-		name = compat_tmp.name;
-	} else
-#endif
-	{
-		num_counters = tmp.num_counters;
-		name = tmp.name;
-	}
+	paddc = xt_copy_counters_from_user(user, len, &tmp, compat);
+	if (IS_ERR(paddc))
+		return PTR_ERR(paddc);
 
-	if (len != size + num_counters * sizeof(struct xt_counters))
-		return -EINVAL;
-
-	paddc = vmalloc(len - size);
-	if (!paddc)
-		return -ENOMEM;
-
-	if (copy_from_user(paddc, user + size, len - size) != 0) {
-		ret = -EFAULT;
-		goto free;
-	}
-
-	t = xt_find_table_lock(net, NFPROTO_ARP, name);
+	t = xt_find_table_lock(net, NFPROTO_ARP, tmp.name);
 	if (IS_ERR_OR_NULL(t)) {
 		ret = t ? PTR_ERR(t) : -ENOENT;
 		goto free;
@@ -1175,7 +1143,7 @@ static int do_add_counters(struct net *net, const void __user *user,
 
 	local_bh_disable();
 	private = t->private;
-	if (private->number != num_counters) {
+	if (private->number != tmp.num_counters) {
 		ret = -EINVAL;
 		goto unlock_up_free;
 	}
@@ -1201,6 +1169,18 @@ static int do_add_counters(struct net *net, const void __user *user,
 }
 
 #ifdef CONFIG_COMPAT
+struct compat_arpt_replace {
+	char				name[XT_TABLE_MAXNAMELEN];
+	u32				valid_hooks;
+	u32				num_entries;
+	u32				size;
+	u32				hook_entry[NF_ARP_NUMHOOKS];
+	u32				underflow[NF_ARP_NUMHOOKS];
+	u32				num_counters;
+	compat_uptr_t			counters;
+	struct compat_arpt_entry	entries[0];
+};
+
 static inline void compat_release_entry(struct compat_arpt_entry *e)
 {
 	struct xt_entry_target *t;
@@ -1209,24 +1189,22 @@ static inline void compat_release_entry(struct compat_arpt_entry *e)
 	module_put(t->u.kernel.target->me);
 }
 
-static inline int
+static int
 check_compat_entry_size_and_hooks(struct compat_arpt_entry *e,
 				  struct xt_table_info *newinfo,
 				  unsigned int *size,
 				  const unsigned char *base,
-				  const unsigned char *limit,
-				  const unsigned int *hook_entries,
-				  const unsigned int *underflows,
-				  const char *name)
+				  const unsigned char *limit)
 {
 	struct xt_entry_target *t;
 	struct xt_target *target;
 	unsigned int entry_offset;
-	int ret, off, h;
+	int ret, off;
 
 	duprintf("check_compat_entry_size_and_hooks %p\n", e);
 	if ((unsigned long)e % __alignof__(struct compat_arpt_entry) != 0 ||
-	    (unsigned char *)e + sizeof(struct compat_arpt_entry) >= limit) {
+	    (unsigned char *)e + sizeof(struct compat_arpt_entry) >= limit ||
+	    (unsigned char *)e + e->next_offset > limit) {
 		duprintf("Bad offset %p, limit = %p\n", e, limit);
 		return -EINVAL;
 	}
@@ -1238,8 +1216,11 @@ check_compat_entry_size_and_hooks(struct compat_arpt_entry *e,
 		return -EINVAL;
 	}
 
-	/* For purposes of check_entry casting the compat entry is fine */
-	ret = check_entry((struct arpt_entry *)e, name);
+	if (!arp_checkentry(&e->arp))
+		return -EINVAL;
+
+	ret = xt_compat_check_entry_offsets(e, e->elems, e->target_offset,
+					    e->next_offset);
 	if (ret)
 		return ret;
 
@@ -1263,17 +1244,6 @@ check_compat_entry_size_and_hooks(struct compat_arpt_entry *e,
 	if (ret)
 		goto release_target;
 
-	/* Check hooks & underflows */
-	for (h = 0; h < NF_ARP_NUMHOOKS; h++) {
-		if ((unsigned char *)e - base == hook_entries[h])
-			newinfo->hook_entry[h] = hook_entries[h];
-		if ((unsigned char *)e - base == underflows[h])
-			newinfo->underflow[h] = underflows[h];
-	}
-
-	/* Clear counters and comefrom */
-	memset(&e->counters, 0, sizeof(e->counters));
-	e->comefrom = 0;
 	return 0;
 
 release_target:
@@ -1282,18 +1252,17 @@ out:
 	return ret;
 }
 
-static int
+static void
 compat_copy_entry_from_user(struct compat_arpt_entry *e, void **dstptr,
-			    unsigned int *size, const char *name,
+			    unsigned int *size,
 			    struct xt_table_info *newinfo, unsigned char *base)
 {
 	struct xt_entry_target *t;
 	struct xt_target *target;
 	struct arpt_entry *de;
 	unsigned int origsize;
-	int ret, h;
+	int h;
 
-	ret = 0;
 	origsize = *size;
 	de = (struct arpt_entry *)*dstptr;
 	memcpy(de, e, sizeof(struct arpt_entry));
@@ -1314,144 +1283,81 @@ compat_copy_entry_from_user(struct compat_arpt_entry *e, void **dstptr,
 		if ((unsigned char *)de - base < newinfo->underflow[h])
 			newinfo->underflow[h] -= origsize - *size;
 	}
-	return ret;
 }
 
-static int translate_compat_table(const char *name,
-				  unsigned int valid_hooks,
-				  struct xt_table_info **pinfo,
+static int translate_compat_table(struct xt_table_info **pinfo,
 				  void **pentry0,
-				  unsigned int total_size,
-				  unsigned int number,
-				  unsigned int *hook_entries,
-				  unsigned int *underflows)
+				  const struct compat_arpt_replace *compatr)
 {
 	unsigned int i, j;
 	struct xt_table_info *newinfo, *info;
 	void *pos, *entry0, *entry1;
 	struct compat_arpt_entry *iter0;
-	struct arpt_entry *iter1;
+	struct arpt_replace repl;
 	unsigned int size;
 	int ret = 0;
 
 	info = *pinfo;
 	entry0 = *pentry0;
-	size = total_size;
-	info->number = number;
-
-	/* Init all hooks to impossible value. */
-	for (i = 0; i < NF_ARP_NUMHOOKS; i++) {
-		info->hook_entry[i] = 0xFFFFFFFF;
-		info->underflow[i] = 0xFFFFFFFF;
-	}
+	size = compatr->size;
+	info->number = compatr->num_entries;
 
 	duprintf("translate_compat_table: size %u\n", info->size);
 	j = 0;
 	xt_compat_lock(NFPROTO_ARP);
-	xt_compat_init_offsets(NFPROTO_ARP, number);
+	xt_compat_init_offsets(NFPROTO_ARP, compatr->num_entries);
 	/* Walk through entries, checking offsets. */
-	xt_entry_foreach(iter0, entry0, total_size) {
+	xt_entry_foreach(iter0, entry0, compatr->size) {
 		ret = check_compat_entry_size_and_hooks(iter0, info, &size,
 							entry0,
-							entry0 + total_size,
-							hook_entries,
-							underflows,
-							name);
+							entry0 + compatr->size);
 		if (ret != 0)
 			goto out_unlock;
 		++j;
 	}
 
 	ret = -EINVAL;
-	if (j != number) {
+	if (j != compatr->num_entries) {
 		duprintf("translate_compat_table: %u not %u entries\n",
-			 j, number);
+			 j, compatr->num_entries);
 		goto out_unlock;
 	}
 
-	/* Check hooks all assigned */
-	for (i = 0; i < NF_ARP_NUMHOOKS; i++) {
-		/* Only hooks which are valid */
-		if (!(valid_hooks & (1 << i)))
-			continue;
-		if (info->hook_entry[i] == 0xFFFFFFFF) {
-			duprintf("Invalid hook entry %u %u\n",
-				 i, hook_entries[i]);
-			goto out_unlock;
-		}
-		if (info->underflow[i] == 0xFFFFFFFF) {
-			duprintf("Invalid underflow %u %u\n",
-				 i, underflows[i]);
-			goto out_unlock;
-		}
-	}
-
 	ret = -ENOMEM;
 	newinfo = xt_alloc_table_info(size);
 	if (!newinfo)
 		goto out_unlock;
 
-	newinfo->number = number;
+	newinfo->number = compatr->num_entries;
 	for (i = 0; i < NF_ARP_NUMHOOKS; i++) {
 		newinfo->hook_entry[i] = info->hook_entry[i];
 		newinfo->underflow[i] = info->underflow[i];
 	}
 	entry1 = newinfo->entries[raw_smp_processor_id()];
 	pos = entry1;
-	size = total_size;
-	xt_entry_foreach(iter0, entry0, total_size) {
-		ret = compat_copy_entry_from_user(iter0, &pos, &size,
-						  name, newinfo, entry1);
-		if (ret != 0)
-			break;
-	}
+	size = compatr->size;
+	xt_entry_foreach(iter0, entry0, compatr->size)
+		compat_copy_entry_from_user(iter0, &pos, &size,
+					    newinfo, entry1);
+
+	/* all module references in entry0 are now gone */
+
 	xt_compat_flush_offsets(NFPROTO_ARP);
 	xt_compat_unlock(NFPROTO_ARP);
-	if (ret)
-		goto free_newinfo;
 
-	ret = -ELOOP;
-	if (!mark_source_chains(newinfo, valid_hooks, entry1))
-		goto free_newinfo;
+	memcpy(&repl, compatr, sizeof(*compatr));
 
-	i = 0;
-	xt_entry_foreach(iter1, entry1, newinfo->size) {
-		ret = check_target(iter1, name);
-		if (ret != 0)
-			break;
-		++i;
-		if (strcmp(arpt_get_target(iter1)->u.user.name,
-		    XT_ERROR_TARGET) == 0)
-			++newinfo->stacksize;
-	}
-	if (ret) {
-		/*
-		 * The first i matches need cleanup_entry (calls ->destroy)
-		 * because they had called ->check already. The other j-i
-		 * entries need only release.
-		 */
-		int skip = i;
-		j -= i;
-		xt_entry_foreach(iter0, entry0, newinfo->size) {
-			if (skip-- > 0)
-				continue;
-			if (j-- == 0)
-				break;
-			compat_release_entry(iter0);
-		}
-		xt_entry_foreach(iter1, entry1, newinfo->size) {
-			if (i-- == 0)
-				break;
-			cleanup_entry(iter1);
-		}
-		xt_free_table_info(newinfo);
-		return ret;
+	for (i = 0; i < NF_ARP_NUMHOOKS; i++) {
+		repl.hook_entry[i] = newinfo->hook_entry[i];
+		repl.underflow[i] = newinfo->underflow[i];
 	}
 
-	/* And one copy for every other CPU */
-	for_each_possible_cpu(i)
-		if (newinfo->entries[i] && newinfo->entries[i] != entry1)
-			memcpy(newinfo->entries[i], entry1, newinfo->size);
+	repl.num_counters = 0;
+	repl.counters = NULL;
+	repl.size = newinfo->size;
+	ret = translate_table(newinfo, entry1, &repl);
+	if (ret)
+		goto free_newinfo;
 
 	*pinfo = newinfo;
 	*pentry0 = entry1;
@@ -1460,31 +1366,18 @@ static int translate_compat_table(const char *name,
 
 free_newinfo:
 	xt_free_table_info(newinfo);
-out:
-	xt_entry_foreach(iter0, entry0, total_size) {
+	return ret;
+out_unlock:
+	xt_compat_flush_offsets(NFPROTO_ARP);
+	xt_compat_unlock(NFPROTO_ARP);
+	xt_entry_foreach(iter0, entry0, compatr->size) {
 		if (j-- == 0)
 			break;
 		compat_release_entry(iter0);
 	}
 	return ret;
-out_unlock:
-	xt_compat_flush_offsets(NFPROTO_ARP);
-	xt_compat_unlock(NFPROTO_ARP);
-	goto out;
 }
 
-struct compat_arpt_replace {
-	char				name[XT_TABLE_MAXNAMELEN];
-	u32				valid_hooks;
-	u32				num_entries;
-	u32				size;
-	u32				hook_entry[NF_ARP_NUMHOOKS];
-	u32				underflow[NF_ARP_NUMHOOKS];
-	u32				num_counters;
-	compat_uptr_t			counters;
-	struct compat_arpt_entry	entries[0];
-};
-
 static int compat_do_replace(struct net *net, void __user *user,
 			     unsigned int len)
 {
@@ -1518,10 +1411,7 @@ static int compat_do_replace(struct net *net, void __user *user,
 		goto free_newinfo;
 	}
 
-	ret = translate_compat_table(tmp.name, tmp.valid_hooks,
-				     &newinfo, &loc_cpu_entry, tmp.size,
-				     tmp.num_entries, tmp.hook_entry,
-				     tmp.underflow);
+	ret = translate_compat_table(&newinfo, &loc_cpu_entry, &tmp);
 	if (ret != 0)
 		goto free_newinfo;
 
diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c
index 2d0e265fef6e..8e729cba1e59 100644
--- a/net/ipv4/netfilter/ip_tables.c
+++ b/net/ipv4/netfilter/ip_tables.c
@@ -168,11 +168,12 @@ get_entry(const void *base, unsigned int offset)
 
 /* All zeroes == unconditional rule. */
 /* Mildly perf critical (only if packet tracing is on) */
-static inline bool unconditional(const struct ipt_ip *ip)
+static inline bool unconditional(const struct ipt_entry *e)
 {
 	static const struct ipt_ip uncond;
 
-	return memcmp(ip, &uncond, sizeof(uncond)) == 0;
+	return e->target_offset == sizeof(struct ipt_entry) &&
+	       memcmp(&e->ip, &uncond, sizeof(uncond)) == 0;
 #undef FWINV
 }
 
@@ -229,11 +230,10 @@ get_chainname_rulenum(const struct ipt_entry *s, const struct ipt_entry *e,
 	} else if (s == e) {
 		(*rulenum)++;
 
-		if (s->target_offset == sizeof(struct ipt_entry) &&
+		if (unconditional(s) &&
 		    strcmp(t->target.u.kernel.target->name,
 			   XT_STANDARD_TARGET) == 0 &&
-		   t->verdict < 0 &&
-		   unconditional(&s->ip)) {
+		   t->verdict < 0) {
 			/* Tail of chains: STANDARD target (return/policy) */
 			*comment = *chainname == hookname
 				? comments[NF_IP_TRACE_COMMENT_POLICY]
@@ -442,7 +442,8 @@ ipt_do_table(struct sk_buff *skb,
    there are loops.  Puts hook bitmask in comefrom. */
 static int
 mark_source_chains(const struct xt_table_info *newinfo,
-		   unsigned int valid_hooks, void *entry0)
+		   unsigned int valid_hooks, void *entry0,
+		   unsigned int *offsets)
 {
 	unsigned int hook;
 
@@ -471,11 +472,10 @@ mark_source_chains(const struct xt_table_info *newinfo,
 			e->comefrom |= ((1 << hook) | (1 << NF_INET_NUMHOOKS));
 
 			/* Unconditional return/END. */
-			if ((e->target_offset == sizeof(struct ipt_entry) &&
+			if ((unconditional(e) &&
 			     (strcmp(t->target.u.user.name,
 				     XT_STANDARD_TARGET) == 0) &&
-			     t->verdict < 0 && unconditional(&e->ip)) ||
-			    visited) {
+			     t->verdict < 0) || visited) {
 				unsigned int oldpos, size;
 
 				if ((strcmp(t->target.u.user.name,
@@ -516,6 +516,8 @@ mark_source_chains(const struct xt_table_info *newinfo,
 				size = e->next_offset;
 				e = (struct ipt_entry *)
 					(entry0 + pos + size);
+				if (pos + size >= newinfo->size)
+					return 0;
 				e->counters.pcnt = pos;
 				pos += size;
 			} else {
@@ -534,9 +536,16 @@ mark_source_chains(const struct xt_table_info *newinfo,
 					/* This a jump; chase it. */
 					duprintf("Jump rule %u -> %u\n",
 						 pos, newpos);
+					if (!xt_find_jump_offset(offsets, newpos,
+								 newinfo->number))
+						return 0;
+					e = (struct ipt_entry *)
+						(entry0 + newpos);
 				} else {
 					/* ... this is a fallthru */
 					newpos = pos + e->next_offset;
+					if (newpos >= newinfo->size)
+						return 0;
 				}
 				e = (struct ipt_entry *)
 					(entry0 + newpos);
@@ -564,27 +573,6 @@ static void cleanup_match(struct xt_entry_match *m, struct net *net)
 }
 
 static int
-check_entry(const struct ipt_entry *e, const char *name)
-{
-	const struct xt_entry_target *t;
-
-	if (!ip_checkentry(&e->ip)) {
-		duprintf("ip check failed %p %s.\n", e, name);
-		return -EINVAL;
-	}
-
-	if (e->target_offset + sizeof(struct xt_entry_target) >
-	    e->next_offset)
-		return -EINVAL;
-
-	t = ipt_get_target_c(e);
-	if (e->target_offset + t->u.target_size > e->next_offset)
-		return -EINVAL;
-
-	return 0;
-}
-
-static int
 check_match(struct xt_entry_match *m, struct xt_mtchk_param *par)
 {
 	const struct ipt_ip *ip = par->entryinfo;
@@ -661,10 +649,6 @@ find_check_entry(struct ipt_entry *e, struct net *net, const char *name,
 	struct xt_mtchk_param mtpar;
 	struct xt_entry_match *ematch;
 
-	ret = check_entry(e, name);
-	if (ret)
-		return ret;
-
 	j = 0;
 	mtpar.net	= net;
 	mtpar.table     = name;
@@ -708,7 +692,7 @@ static bool check_underflow(const struct ipt_entry *e)
 	const struct xt_entry_target *t;
 	unsigned int verdict;
 
-	if (!unconditional(&e->ip))
+	if (!unconditional(e))
 		return false;
 	t = ipt_get_target_c(e);
 	if (strcmp(t->u.user.name, XT_STANDARD_TARGET) != 0)
@@ -728,9 +712,11 @@ check_entry_size_and_hooks(struct ipt_entry *e,
 			   unsigned int valid_hooks)
 {
 	unsigned int h;
+	int err;
 
 	if ((unsigned long)e % __alignof__(struct ipt_entry) != 0 ||
-	    (unsigned char *)e + sizeof(struct ipt_entry) >= limit) {
+	    (unsigned char *)e + sizeof(struct ipt_entry) >= limit ||
+	    (unsigned char *)e + e->next_offset > limit) {
 		duprintf("Bad offset %p\n", e);
 		return -EINVAL;
 	}
@@ -742,6 +728,14 @@ check_entry_size_and_hooks(struct ipt_entry *e,
 		return -EINVAL;
 	}
 
+	if (!ip_checkentry(&e->ip))
+		return -EINVAL;
+
+	err = xt_check_entry_offsets(e, e->elems, e->target_offset,
+				     e->next_offset);
+	if (err)
+		return err;
+
 	/* Check hooks & underflows */
 	for (h = 0; h < NF_INET_NUMHOOKS; h++) {
 		if (!(valid_hooks & (1 << h)))
@@ -750,9 +744,9 @@ check_entry_size_and_hooks(struct ipt_entry *e,
 			newinfo->hook_entry[h] = hook_entries[h];
 		if ((unsigned char *)e - base == underflows[h]) {
 			if (!check_underflow(e)) {
-				pr_err("Underflows must be unconditional and "
-				       "use the STANDARD target with "
-				       "ACCEPT/DROP\n");
+				pr_debug("Underflows must be unconditional and "
+					 "use the STANDARD target with "
+					 "ACCEPT/DROP\n");
 				return -EINVAL;
 			}
 			newinfo->underflow[h] = underflows[h];
@@ -793,6 +787,7 @@ translate_table(struct net *net, struct xt_table_info *newinfo, void *entry0,
                 const struct ipt_replace *repl)
 {
 	struct ipt_entry *iter;
+	unsigned int *offsets;
 	unsigned int i;
 	int ret = 0;
 
@@ -806,6 +801,9 @@ translate_table(struct net *net, struct xt_table_info *newinfo, void *entry0,
 	}
 
 	duprintf("translate_table: size %u\n", newinfo->size);
+	offsets = xt_alloc_entry_offsets(newinfo->number);
+	if (!offsets)
+		return -ENOMEM;
 	i = 0;
 	/* Walk through entries, checking offsets. */
 	xt_entry_foreach(iter, entry0, newinfo->size) {
@@ -815,17 +813,20 @@ translate_table(struct net *net, struct xt_table_info *newinfo, void *entry0,
 						 repl->underflow,
 						 repl->valid_hooks);
 		if (ret != 0)
-			return ret;
+			goto out_free;
+		if (i < repl->num_entries)
+			offsets[i] = (void *)iter - entry0;
 		++i;
 		if (strcmp(ipt_get_target(iter)->u.user.name,
 		    XT_ERROR_TARGET) == 0)
 			++newinfo->stacksize;
 	}
 
+	ret = -EINVAL;
 	if (i != repl->num_entries) {
 		duprintf("translate_table: %u not %u entries\n",
 			 i, repl->num_entries);
-		return -EINVAL;
+		goto out_free;
 	}
 
 	/* Check hooks all assigned */
@@ -836,17 +837,20 @@ translate_table(struct net *net, struct xt_table_info *newinfo, void *entry0,
 		if (newinfo->hook_entry[i] == 0xFFFFFFFF) {
 			duprintf("Invalid hook entry %u %u\n",
 				 i, repl->hook_entry[i]);
-			return -EINVAL;
+			goto out_free;
 		}
 		if (newinfo->underflow[i] == 0xFFFFFFFF) {
 			duprintf("Invalid underflow %u %u\n",
 				 i, repl->underflow[i]);
-			return -EINVAL;
+			goto out_free;
 		}
 	}
 
-	if (!mark_source_chains(newinfo, repl->valid_hooks, entry0))
-		return -ELOOP;
+	if (!mark_source_chains(newinfo, repl->valid_hooks, entry0, offsets)) {
+		ret = -ELOOP;
+		goto out_free;
+	}
+	kvfree(offsets);
 
 	/* Finally, each sanity check must pass */
 	i = 0;
@@ -873,6 +877,9 @@ translate_table(struct net *net, struct xt_table_info *newinfo, void *entry0,
 	}
 
 	return ret;
+ out_free:
+	kvfree(offsets);
+	return ret;
 }
 
 static void
@@ -1306,56 +1313,18 @@ do_add_counters(struct net *net, const void __user *user,
 	unsigned int i, curcpu;
 	struct xt_counters_info tmp;
 	struct xt_counters *paddc;
-	unsigned int num_counters;
-	const char *name;
-	int size;
-	void *ptmp;
 	struct xt_table *t;
 	const struct xt_table_info *private;
 	int ret = 0;
 	void *loc_cpu_entry;
 	struct ipt_entry *iter;
 	unsigned int addend;
-#ifdef CONFIG_COMPAT
-	struct compat_xt_counters_info compat_tmp;
-
-	if (compat) {
-		ptmp = &compat_tmp;
-		size = sizeof(struct compat_xt_counters_info);
-	} else
-#endif
-	{
-		ptmp = &tmp;
-		size = sizeof(struct xt_counters_info);
-	}
 
-	if (copy_from_user(ptmp, user, size) != 0)
-		return -EFAULT;
+	paddc = xt_copy_counters_from_user(user, len, &tmp, compat);
+	if (IS_ERR(paddc))
+		return PTR_ERR(paddc);
 
-#ifdef CONFIG_COMPAT
-	if (compat) {
-		num_counters = compat_tmp.num_counters;
-		name = compat_tmp.name;
-	} else
-#endif
-	{
-		num_counters = tmp.num_counters;
-		name = tmp.name;
-	}
-
-	if (len != size + num_counters * sizeof(struct xt_counters))
-		return -EINVAL;
-
-	paddc = vmalloc(len - size);
-	if (!paddc)
-		return -ENOMEM;
-
-	if (copy_from_user(paddc, user + size, len - size) != 0) {
-		ret = -EFAULT;
-		goto free;
-	}
-
-	t = xt_find_table_lock(net, AF_INET, name);
+	t = xt_find_table_lock(net, AF_INET, tmp.name);
 	if (IS_ERR_OR_NULL(t)) {
 		ret = t ? PTR_ERR(t) : -ENOENT;
 		goto free;
@@ -1363,7 +1332,7 @@ do_add_counters(struct net *net, const void __user *user,
 
 	local_bh_disable();
 	private = t->private;
-	if (private->number != num_counters) {
+	if (private->number != tmp.num_counters) {
 		ret = -EINVAL;
 		goto unlock_up_free;
 	}
@@ -1442,7 +1411,6 @@ compat_copy_entry_to_user(struct ipt_entry *e, void __user **dstptr,
 
 static int
 compat_find_calc_match(struct xt_entry_match *m,
-		       const char *name,
 		       const struct ipt_ip *ip,
 		       unsigned int hookmask,
 		       int *size)
@@ -1478,21 +1446,19 @@ check_compat_entry_size_and_hooks(struct compat_ipt_entry *e,
 				  struct xt_table_info *newinfo,
 				  unsigned int *size,
 				  const unsigned char *base,
-				  const unsigned char *limit,
-				  const unsigned int *hook_entries,
-				  const unsigned int *underflows,
-				  const char *name)
+				  const unsigned char *limit)
 {
 	struct xt_entry_match *ematch;
 	struct xt_entry_target *t;
 	struct xt_target *target;
 	unsigned int entry_offset;
 	unsigned int j;
-	int ret, off, h;
+	int ret, off;
 
 	duprintf("check_compat_entry_size_and_hooks %p\n", e);
 	if ((unsigned long)e % __alignof__(struct compat_ipt_entry) != 0 ||
-	    (unsigned char *)e + sizeof(struct compat_ipt_entry) >= limit) {
+	    (unsigned char *)e + sizeof(struct compat_ipt_entry) >= limit ||
+	    (unsigned char *)e + e->next_offset > limit) {
 		duprintf("Bad offset %p, limit = %p\n", e, limit);
 		return -EINVAL;
 	}
@@ -1504,8 +1470,11 @@ check_compat_entry_size_and_hooks(struct compat_ipt_entry *e,
 		return -EINVAL;
 	}
 
-	/* For purposes of check_entry casting the compat entry is fine */
-	ret = check_entry((struct ipt_entry *)e, name);
+	if (!ip_checkentry(&e->ip))
+		return -EINVAL;
+
+	ret = xt_compat_check_entry_offsets(e, e->elems,
+					    e->target_offset, e->next_offset);
 	if (ret)
 		return ret;
 
@@ -1513,8 +1482,8 @@ check_compat_entry_size_and_hooks(struct compat_ipt_entry *e,
 	entry_offset = (void *)e - (void *)base;
 	j = 0;
 	xt_ematch_foreach(ematch, e) {
-		ret = compat_find_calc_match(ematch, name,
-					     &e->ip, e->comefrom, &off);
+		ret = compat_find_calc_match(ematch, &e->ip, e->comefrom,
+					     &off);
 		if (ret != 0)
 			goto release_matches;
 		++j;
@@ -1537,17 +1506,6 @@ check_compat_entry_size_and_hooks(struct compat_ipt_entry *e,
 	if (ret)
 		goto out;
 
-	/* Check hooks & underflows */
-	for (h = 0; h < NF_INET_NUMHOOKS; h++) {
-		if ((unsigned char *)e - base == hook_entries[h])
-			newinfo->hook_entry[h] = hook_entries[h];
-		if ((unsigned char *)e - base == underflows[h])
-			newinfo->underflow[h] = underflows[h];
-	}
-
-	/* Clear counters and comefrom */
-	memset(&e->counters, 0, sizeof(e->counters));
-	e->comefrom = 0;
 	return 0;
 
 out:
@@ -1561,19 +1519,18 @@ release_matches:
 	return ret;
 }
 
-static int
+static void
 compat_copy_entry_from_user(struct compat_ipt_entry *e, void **dstptr,
-			    unsigned int *size, const char *name,
+			    unsigned int *size,
 			    struct xt_table_info *newinfo, unsigned char *base)
 {
 	struct xt_entry_target *t;
 	struct xt_target *target;
 	struct ipt_entry *de;
 	unsigned int origsize;
-	int ret, h;
+	int h;
 	struct xt_entry_match *ematch;
 
-	ret = 0;
 	origsize = *size;
 	de = (struct ipt_entry *)*dstptr;
 	memcpy(de, e, sizeof(struct ipt_entry));
@@ -1582,198 +1539,104 @@ compat_copy_entry_from_user(struct compat_ipt_entry *e, void **dstptr,
 	*dstptr += sizeof(struct ipt_entry);
 	*size += sizeof(struct ipt_entry) - sizeof(struct compat_ipt_entry);
 
-	xt_ematch_foreach(ematch, e) {
-		ret = xt_compat_match_from_user(ematch, dstptr, size);
-		if (ret != 0)
-			return ret;
-	}
+	xt_ematch_foreach(ematch, e)
+		xt_compat_match_from_user(ematch, dstptr, size);
+
 	de->target_offset = e->target_offset - (origsize - *size);
 	t = compat_ipt_get_target(e);
 	target = t->u.kernel.target;
 	xt_compat_target_from_user(t, dstptr, size);
 
 	de->next_offset = e->next_offset - (origsize - *size);
+
 	for (h = 0; h < NF_INET_NUMHOOKS; h++) {
 		if ((unsigned char *)de - base < newinfo->hook_entry[h])
 			newinfo->hook_entry[h] -= origsize - *size;
 		if ((unsigned char *)de - base < newinfo->underflow[h])
 			newinfo->underflow[h] -= origsize - *size;
 	}
-	return ret;
-}
-
-static int
-compat_check_entry(struct ipt_entry *e, struct net *net, const char *name)
-{
-	struct xt_entry_match *ematch;
-	struct xt_mtchk_param mtpar;
-	unsigned int j;
-	int ret = 0;
-
-	j = 0;
-	mtpar.net	= net;
-	mtpar.table     = name;
-	mtpar.entryinfo = &e->ip;
-	mtpar.hook_mask = e->comefrom;
-	mtpar.family    = NFPROTO_IPV4;
-	xt_ematch_foreach(ematch, e) {
-		ret = check_match(ematch, &mtpar);
-		if (ret != 0)
-			goto cleanup_matches;
-		++j;
-	}
-
-	ret = check_target(e, net, name);
-	if (ret)
-		goto cleanup_matches;
-	return 0;
-
- cleanup_matches:
-	xt_ematch_foreach(ematch, e) {
-		if (j-- == 0)
-			break;
-		cleanup_match(ematch, net);
-	}
-	return ret;
 }
 
 static int
 translate_compat_table(struct net *net,
-		       const char *name,
-		       unsigned int valid_hooks,
 		       struct xt_table_info **pinfo,
 		       void **pentry0,
-		       unsigned int total_size,
-		       unsigned int number,
-		       unsigned int *hook_entries,
-		       unsigned int *underflows)
+		       const struct compat_ipt_replace *compatr)
 {
 	unsigned int i, j;
 	struct xt_table_info *newinfo, *info;
 	void *pos, *entry0, *entry1;
 	struct compat_ipt_entry *iter0;
-	struct ipt_entry *iter1;
+	struct ipt_replace repl;
 	unsigned int size;
 	int ret;
 
 	info = *pinfo;
 	entry0 = *pentry0;
-	size = total_size;
-	info->number = number;
-
-	/* Init all hooks to impossible value. */
-	for (i = 0; i < NF_INET_NUMHOOKS; i++) {
-		info->hook_entry[i] = 0xFFFFFFFF;
-		info->underflow[i] = 0xFFFFFFFF;
-	}
+	size = compatr->size;
+	info->number = compatr->num_entries;
 
 	duprintf("translate_compat_table: size %u\n", info->size);
 	j = 0;
 	xt_compat_lock(AF_INET);
-	xt_compat_init_offsets(AF_INET, number);
+	xt_compat_init_offsets(AF_INET, compatr->num_entries);
 	/* Walk through entries, checking offsets. */
-	xt_entry_foreach(iter0, entry0, total_size) {
+	xt_entry_foreach(iter0, entry0, compatr->size) {
 		ret = check_compat_entry_size_and_hooks(iter0, info, &size,
 							entry0,
-							entry0 + total_size,
-							hook_entries,
-							underflows,
-							name);
+							entry0 + compatr->size);
 		if (ret != 0)
 			goto out_unlock;
 		++j;
 	}
 
 	ret = -EINVAL;
-	if (j != number) {
+	if (j != compatr->num_entries) {
 		duprintf("translate_compat_table: %u not %u entries\n",
-			 j, number);
+			 j, compatr->num_entries);
 		goto out_unlock;
 	}
 
-	/* Check hooks all assigned */
-	for (i = 0; i < NF_INET_NUMHOOKS; i++) {
-		/* Only hooks which are valid */
-		if (!(valid_hooks & (1 << i)))
-			continue;
-		if (info->hook_entry[i] == 0xFFFFFFFF) {
-			duprintf("Invalid hook entry %u %u\n",
-				 i, hook_entries[i]);
-			goto out_unlock;
-		}
-		if (info->underflow[i] == 0xFFFFFFFF) {
-			duprintf("Invalid underflow %u %u\n",
-				 i, underflows[i]);
-			goto out_unlock;
-		}
-	}
-
 	ret = -ENOMEM;
 	newinfo = xt_alloc_table_info(size);
 	if (!newinfo)
 		goto out_unlock;
 
-	newinfo->number = number;
+	newinfo->number = compatr->num_entries;
 	for (i = 0; i < NF_INET_NUMHOOKS; i++) {
-		newinfo->hook_entry[i] = info->hook_entry[i];
-		newinfo->underflow[i] = info->underflow[i];
+		newinfo->hook_entry[i] = compatr->hook_entry[i];
+		newinfo->underflow[i] = compatr->underflow[i];
 	}
 	entry1 = newinfo->entries[raw_smp_processor_id()];
 	pos = entry1;
-	size = total_size;
-	xt_entry_foreach(iter0, entry0, total_size) {
-		ret = compat_copy_entry_from_user(iter0, &pos, &size,
-						  name, newinfo, entry1);
-		if (ret != 0)
-			break;
-	}
+	size = compatr->size;
+	xt_entry_foreach(iter0, entry0, compatr->size)
+		compat_copy_entry_from_user(iter0, &pos, &size,
+					    newinfo, entry1);
+
+	/* all module references in entry0 are now gone.
+	 * entry1/newinfo contains a 64bit ruleset that looks exactly as
+	 * generated by 64bit userspace.
+	 *
+	 * Call standard translate_table() to validate all hook_entrys,
+	 * underflows, check for loops, etc.
+	 */
 	xt_compat_flush_offsets(AF_INET);
 	xt_compat_unlock(AF_INET);
-	if (ret)
-		goto free_newinfo;
 
-	ret = -ELOOP;
-	if (!mark_source_chains(newinfo, valid_hooks, entry1))
-		goto free_newinfo;
+	memcpy(&repl, compatr, sizeof(*compatr));
 
-	i = 0;
-	xt_entry_foreach(iter1, entry1, newinfo->size) {
-		ret = compat_check_entry(iter1, net, name);
-		if (ret != 0)
-			break;
-		++i;
-		if (strcmp(ipt_get_target(iter1)->u.user.name,
-		    XT_ERROR_TARGET) == 0)
-			++newinfo->stacksize;
-	}
-	if (ret) {
-		/*
-		 * The first i matches need cleanup_entry (calls ->destroy)
-		 * because they had called ->check already. The other j-i
-		 * entries need only release.
-		 */
-		int skip = i;
-		j -= i;
-		xt_entry_foreach(iter0, entry0, newinfo->size) {
-			if (skip-- > 0)
-				continue;
-			if (j-- == 0)
-				break;
-			compat_release_entry(iter0);
-		}
-		xt_entry_foreach(iter1, entry1, newinfo->size) {
-			if (i-- == 0)
-				break;
-			cleanup_entry(iter1, net);
-		}
-		xt_free_table_info(newinfo);
-		return ret;
+	for (i = 0; i < NF_INET_NUMHOOKS; i++) {
+		repl.hook_entry[i] = newinfo->hook_entry[i];
+		repl.underflow[i] = newinfo->underflow[i];
 	}
 
-	/* And one copy for every other CPU */
-	for_each_possible_cpu(i)
-		if (newinfo->entries[i] && newinfo->entries[i] != entry1)
-			memcpy(newinfo->entries[i], entry1, newinfo->size);
+	repl.num_counters = 0;
+	repl.counters = NULL;
+	repl.size = newinfo->size;
+	ret = translate_table(net, newinfo, entry1, &repl);
+	if (ret)
+		goto free_newinfo;
 
 	*pinfo = newinfo;
 	*pentry0 = entry1;
@@ -1782,17 +1645,16 @@ translate_compat_table(struct net *net,
 
 free_newinfo:
 	xt_free_table_info(newinfo);
-out:
-	xt_entry_foreach(iter0, entry0, total_size) {
+	return ret;
+out_unlock:
+	xt_compat_flush_offsets(AF_INET);
+	xt_compat_unlock(AF_INET);
+	xt_entry_foreach(iter0, entry0, compatr->size) {
 		if (j-- == 0)
 			break;
 		compat_release_entry(iter0);
 	}
 	return ret;
-out_unlock:
-	xt_compat_flush_offsets(AF_INET);
-	xt_compat_unlock(AF_INET);
-	goto out;
 }
 
 static int
@@ -1829,10 +1691,7 @@ compat_do_replace(struct net *net, void __user *user, unsigned int len)
 		goto free_newinfo;
 	}
 
-	ret = translate_compat_table(net, tmp.name, tmp.valid_hooks,
-				     &newinfo, &loc_cpu_entry, tmp.size,
-				     tmp.num_entries, tmp.hook_entry,
-				     tmp.underflow);
+	ret = translate_compat_table(net, &newinfo, &loc_cpu_entry, &tmp);
 	if (ret != 0)
 		goto free_newinfo;
 
diff --git a/net/ipv4/netfilter/nf_nat_masquerade_ipv4.c b/net/ipv4/netfilter/nf_nat_masquerade_ipv4.c
index c6eb42100e9a..ea91058b5f6f 100644
--- a/net/ipv4/netfilter/nf_nat_masquerade_ipv4.c
+++ b/net/ipv4/netfilter/nf_nat_masquerade_ipv4.c
@@ -108,10 +108,18 @@ static int masq_inet_event(struct notifier_block *this,
 			   unsigned long event,
 			   void *ptr)
 {
-	struct net_device *dev = ((struct in_ifaddr *)ptr)->ifa_dev->dev;
+	struct in_device *idev = ((struct in_ifaddr *)ptr)->ifa_dev;
 	struct netdev_notifier_info info;
 
-	netdev_notifier_info_init(&info, dev);
+	/* The masq_dev_notifier will catch the case of the device going
+	 * down.  So if the inetdev is dead and being destroyed we have
+	 * no work to do.  Otherwise this is an individual address removal
+	 * and we have to perform the flush.
+	 */
+	if (idev->dead)
+		return NOTIFY_DONE;
+
+	netdev_notifier_info_init(&info, idev->dev);
 	return masq_device_event(this, event, &info);
 }
 
diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c
index 05ff44b758df..f6ee0d561aab 100644
--- a/net/ipv4/ping.c
+++ b/net/ipv4/ping.c
@@ -745,8 +745,10 @@ static int ping_v4_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 
 	if (msg->msg_controllen) {
 		err = ip_cmsg_send(sock_net(sk), msg, &ipc, false);
-		if (err)
+		if (unlikely(err)) {
+			kfree(ipc.opt);
 			return err;
+		}
 		if (ipc.opt)
 			free = 1;
 	}
diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c
index 561cd4b8fc6e..c77aac75759d 100644
--- a/net/ipv4/raw.c
+++ b/net/ipv4/raw.c
@@ -543,8 +543,10 @@ static int raw_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 
 	if (msg->msg_controllen) {
 		err = ip_cmsg_send(sock_net(sk), msg, &ipc, false);
-		if (err)
+		if (unlikely(err)) {
+			kfree(ipc.opt);
 			goto out;
+		}
 		if (ipc.opt)
 			free = 1;
 	}
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index f45f2a12f37b..eb1d9839a257 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -125,6 +125,7 @@ static int ip_rt_mtu_expires __read_mostly	= 10 * 60 * HZ;
 static int ip_rt_min_pmtu __read_mostly		= 512 + 20 + 20;
 static int ip_rt_min_advmss __read_mostly	= 256;
 
+static int ip_rt_gc_timeout __read_mostly	= RT_GC_TIMEOUT;
 /*
  *	Interface to generic destination cache.
  */
@@ -753,7 +754,7 @@ static void __ip_do_redirect(struct rtable *rt, struct sk_buff *skb, struct flow
 				struct fib_nh *nh = &FIB_RES_NH(res);
 
 				update_or_create_fnhe(nh, fl4->daddr, new_gw,
-						      0, 0);
+						0, jiffies + ip_rt_gc_timeout);
 			}
 			if (kill_route)
 				rt->dst.obsolete = DST_OBSOLETE_KILL;
@@ -1538,6 +1539,36 @@ static void ip_handle_martian_source(struct net_device *dev,
 #endif
 }
 
+static void ip_del_fnhe(struct fib_nh *nh, __be32 daddr)
+{
+	struct fnhe_hash_bucket *hash;
+	struct fib_nh_exception *fnhe, __rcu **fnhe_p;
+	u32 hval = fnhe_hashfun(daddr);
+
+	spin_lock_bh(&fnhe_lock);
+
+	hash = rcu_dereference_protected(nh->nh_exceptions,
+					 lockdep_is_held(&fnhe_lock));
+	hash += hval;
+
+	fnhe_p = &hash->chain;
+	fnhe = rcu_dereference_protected(*fnhe_p, lockdep_is_held(&fnhe_lock));
+	while (fnhe) {
+		if (fnhe->fnhe_daddr == daddr) {
+			rcu_assign_pointer(*fnhe_p, rcu_dereference_protected(
+				fnhe->fnhe_next, lockdep_is_held(&fnhe_lock)));
+			fnhe_flush_routes(fnhe);
+			kfree_rcu(fnhe, rcu);
+			break;
+		}
+		fnhe_p = &fnhe->fnhe_next;
+		fnhe = rcu_dereference_protected(fnhe->fnhe_next,
+						 lockdep_is_held(&fnhe_lock));
+	}
+
+	spin_unlock_bh(&fnhe_lock);
+}
+
 /* called in rcu_read_lock() section */
 static int __mkroute_input(struct sk_buff *skb,
 			   const struct fib_result *res,
@@ -1592,11 +1623,20 @@ static int __mkroute_input(struct sk_buff *skb,
 
 	fnhe = find_exception(&FIB_RES_NH(*res), daddr);
 	if (do_cache) {
-		if (fnhe)
+		if (fnhe) {
 			rth = rcu_dereference(fnhe->fnhe_rth_input);
-		else
-			rth = rcu_dereference(FIB_RES_NH(*res).nh_rth_input);
+			if (rth && rth->dst.expires &&
+			    time_after(jiffies, rth->dst.expires)) {
+				ip_del_fnhe(&FIB_RES_NH(*res), daddr);
+				fnhe = NULL;
+			} else {
+				goto rt_cache;
+			}
+		}
+
+		rth = rcu_dereference(FIB_RES_NH(*res).nh_rth_input);
 
+rt_cache:
 		if (rt_cache_valid(rth)) {
 			skb_dst_set_noref(skb, &rth->dst);
 			goto out;
@@ -1936,6 +1976,18 @@ static struct rtable *__mkroute_output(const struct fib_result *res,
 		 */
 		if (fi && res->prefixlen < 4)
 			fi = NULL;
+	} else if ((type == RTN_LOCAL) && (orig_oif != 0) &&
+		   (orig_oif != dev_out->ifindex)) {
+		/* For local routes that require a particular output interface
+		 * we do not want to cache the result.  Caching the result
+		 * causes incorrect behaviour when there are multiple source
+		 * addresses on the interface, the end result being that if the
+		 * intended recipient is waiting on that interface for the
+		 * packet he won't receive it because it will be delivered on
+		 * the loopback interface and the IP_PKTINFO ipi_ifindex will
+		 * be set to the loopback interface as well.
+		 */
+		fi = NULL;
 	}
 
 	fnhe = NULL;
@@ -1945,19 +1997,29 @@ static struct rtable *__mkroute_output(const struct fib_result *res,
 		struct fib_nh *nh = &FIB_RES_NH(*res);
 
 		fnhe = find_exception(nh, fl4->daddr);
-		if (fnhe)
+		if (fnhe) {
 			prth = &fnhe->fnhe_rth_output;
-		else {
-			if (unlikely(fl4->flowi4_flags &
-				     FLOWI_FLAG_KNOWN_NH &&
-				     !(nh->nh_gw &&
-				       nh->nh_scope == RT_SCOPE_LINK))) {
-				do_cache = false;
-				goto add;
+			rth = rcu_dereference(*prth);
+			if (rth && rth->dst.expires &&
+			    time_after(jiffies, rth->dst.expires)) {
+				ip_del_fnhe(nh, fl4->daddr);
+				fnhe = NULL;
+			} else {
+				goto rt_cache;
 			}
-			prth = raw_cpu_ptr(nh->nh_pcpu_rth_output);
 		}
+
+		if (unlikely(fl4->flowi4_flags &
+			     FLOWI_FLAG_KNOWN_NH &&
+			     !(nh->nh_gw &&
+			       nh->nh_scope == RT_SCOPE_LINK))) {
+			do_cache = false;
+			goto add;
+		}
+		prth = raw_cpu_ptr(nh->nh_pcpu_rth_output);
 		rth = rcu_dereference(*prth);
+
+rt_cache:
 		if (rt_cache_valid(rth)) {
 			dst_hold(&rth->dst);
 			return rth;
@@ -2504,7 +2566,6 @@ void ip_rt_multicast_event(struct in_device *in_dev)
 }
 
 #ifdef CONFIG_SYSCTL
-static int ip_rt_gc_timeout __read_mostly	= RT_GC_TIMEOUT;
 static int ip_rt_gc_interval __read_mostly  = 60 * HZ;
 static int ip_rt_gc_min_interval __read_mostly	= HZ / 2;
 static int ip_rt_gc_elasticity __read_mostly	= 8;
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index bb2ce74f6004..19d385a0f02d 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -279,6 +279,7 @@
 
 #include <asm/uaccess.h>
 #include <asm/ioctls.h>
+#include <asm/unaligned.h>
 #include <net/busy_poll.h>
 
 int sysctl_tcp_fin_timeout __read_mostly = TCP_FIN_TIMEOUT;
@@ -921,7 +922,7 @@ new_segment:
 
 		i = skb_shinfo(skb)->nr_frags;
 		can_coalesce = skb_can_coalesce(skb, i, page, offset);
-		if (!can_coalesce && i >= MAX_SKB_FRAGS) {
+		if (!can_coalesce && i >= sysctl_max_skb_frags) {
 			tcp_mark_push(tp, skb);
 			goto new_segment;
 		}
@@ -1187,7 +1188,7 @@ new_segment:
 
 			if (!skb_can_coalesce(skb, i, pfrag->page,
 					      pfrag->offset)) {
-				if (i == MAX_SKB_FRAGS || !sg) {
+				if (i == sysctl_max_skb_frags || !sg) {
 					tcp_mark_push(tp, skb);
 					goto new_segment;
 				}
@@ -2603,6 +2604,7 @@ void tcp_get_info(struct sock *sk, struct tcp_info *info)
 	const struct inet_connection_sock *icsk = inet_csk(sk);
 	u32 now = tcp_time_stamp;
 	unsigned int start;
+	u64 rate64;
 	u32 rate;
 
 	memset(info, 0, sizeof(*info));
@@ -2665,15 +2667,17 @@ void tcp_get_info(struct sock *sk, struct tcp_info *info)
 	info->tcpi_total_retrans = tp->total_retrans;
 
 	rate = READ_ONCE(sk->sk_pacing_rate);
-	info->tcpi_pacing_rate = rate != ~0U ? rate : ~0ULL;
+	rate64 = rate != ~0U ? rate : ~0ULL;
+	put_unaligned(rate64, &info->tcpi_pacing_rate);
 
 	rate = READ_ONCE(sk->sk_max_pacing_rate);
-	info->tcpi_max_pacing_rate = rate != ~0U ? rate : ~0ULL;
+	rate64 = rate != ~0U ? rate : ~0ULL;
+	put_unaligned(rate64, &info->tcpi_max_pacing_rate);
 
 	do {
 		start = u64_stats_fetch_begin_irq(&tp->syncp);
-		info->tcpi_bytes_acked = tp->bytes_acked;
-		info->tcpi_bytes_received = tp->bytes_received;
+		put_unaligned(tp->bytes_acked, &info->tcpi_bytes_acked);
+		put_unaligned(tp->bytes_received, &info->tcpi_bytes_received);
 	} while (u64_stats_fetch_retry_irq(&tp->syncp, start));
 }
 EXPORT_SYMBOL_GPL(tcp_get_info);
diff --git a/net/ipv4/tcp_cubic.c b/net/ipv4/tcp_cubic.c
index 06d3d665a9fd..3ce0b861cc0e 100644
--- a/net/ipv4/tcp_cubic.c
+++ b/net/ipv4/tcp_cubic.c
@@ -151,6 +151,27 @@ static void bictcp_init(struct sock *sk)
 		tcp_sk(sk)->snd_ssthresh = initial_ssthresh;
 }
 
+static void bictcp_cwnd_event(struct sock *sk, enum tcp_ca_event event)
+{
+	if (event == CA_EVENT_TX_START) {
+		struct bictcp *ca = inet_csk_ca(sk);
+		u32 now = tcp_time_stamp;
+		s32 delta;
+
+		delta = now - tcp_sk(sk)->lsndtime;
+
+		/* We were application limited (idle) for a while.
+		 * Shift epoch_start to keep cwnd growth to cubic curve.
+		 */
+		if (ca->epoch_start && delta > 0) {
+			ca->epoch_start += delta;
+			if (after(ca->epoch_start, now))
+				ca->epoch_start = now;
+		}
+		return;
+	}
+}
+
 /* calculate the cubic root of x using a table lookup followed by one
  * Newton-Raphson iteration.
  * Avg err ~= 0.195%
@@ -450,6 +471,7 @@ static struct tcp_congestion_ops cubictcp __read_mostly = {
 	.cong_avoid	= bictcp_cong_avoid,
 	.set_state	= bictcp_state,
 	.undo_cwnd	= bictcp_undo_cwnd,
+	.cwnd_event	= bictcp_cwnd_event,
 	.pkts_acked     = bictcp_acked,
 	.owner		= THIS_MODULE,
 	.name		= "cubic",
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 87463c814896..36b93adfd7da 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -89,7 +89,7 @@ int sysctl_tcp_adv_win_scale __read_mostly = 1;
 EXPORT_SYMBOL(sysctl_tcp_adv_win_scale);
 
 /* rfc5961 challenge ack rate limiting */
-int sysctl_tcp_challenge_ack_limit = 100;
+int sysctl_tcp_challenge_ack_limit = 1000;
 
 int sysctl_tcp_stdurg __read_mostly;
 int sysctl_tcp_rfc1337 __read_mostly;
@@ -3343,6 +3343,23 @@ static int tcp_ack_update_window(struct sock *sk, const struct sk_buff *skb, u32
 	return flag;
 }
 
+static bool __tcp_oow_rate_limited(struct net *net, int mib_idx,
+				   u32 *last_oow_ack_time)
+{
+	if (*last_oow_ack_time) {
+		s32 elapsed = (s32)(tcp_time_stamp - *last_oow_ack_time);
+
+		if (0 <= elapsed && elapsed < sysctl_tcp_invalid_ratelimit) {
+			NET_INC_STATS(net, mib_idx);
+			return true;	/* rate-limited: don't send yet! */
+		}
+	}
+
+	*last_oow_ack_time = tcp_time_stamp;
+
+	return false;	/* not rate-limited: go ahead, send dupack now! */
+}
+
 /* Return true if we're currently rate-limiting out-of-window ACKs and
  * thus shouldn't send a dupack right now. We rate-limit dupacks in
  * response to out-of-window SYNs or ACKs to mitigate ACK loops or DoS
@@ -3356,21 +3373,9 @@ bool tcp_oow_rate_limited(struct net *net, const struct sk_buff *skb,
 	/* Data packets without SYNs are not likely part of an ACK loop. */
 	if ((TCP_SKB_CB(skb)->seq != TCP_SKB_CB(skb)->end_seq) &&
 	    !tcp_hdr(skb)->syn)
-		goto not_rate_limited;
-
-	if (*last_oow_ack_time) {
-		s32 elapsed = (s32)(tcp_time_stamp - *last_oow_ack_time);
-
-		if (0 <= elapsed && elapsed < sysctl_tcp_invalid_ratelimit) {
-			NET_INC_STATS_BH(net, mib_idx);
-			return true;	/* rate-limited: don't send yet! */
-		}
-	}
-
-	*last_oow_ack_time = tcp_time_stamp;
+		return false;
 
-not_rate_limited:
-	return false;	/* not rate-limited: go ahead, send dupack now! */
+	return __tcp_oow_rate_limited(net, mib_idx, last_oow_ack_time);
 }
 
 /* RFC 5961 7 [ACK Throttling] */
@@ -3380,21 +3385,26 @@ static void tcp_send_challenge_ack(struct sock *sk, const struct sk_buff *skb)
 	static u32 challenge_timestamp;
 	static unsigned int challenge_count;
 	struct tcp_sock *tp = tcp_sk(sk);
-	u32 now;
+	u32 count, now;
 
 	/* First check our per-socket dupack rate limit. */
-	if (tcp_oow_rate_limited(sock_net(sk), skb,
-				 LINUX_MIB_TCPACKSKIPPEDCHALLENGE,
-				 &tp->last_oow_ack_time))
+	if (__tcp_oow_rate_limited(sock_net(sk),
+				   LINUX_MIB_TCPACKSKIPPEDCHALLENGE,
+				   &tp->last_oow_ack_time))
 		return;
 
-	/* Then check the check host-wide RFC 5961 rate limit. */
+	/* Then check host-wide RFC 5961 rate limit. */
 	now = jiffies / HZ;
 	if (now != challenge_timestamp) {
+		u32 half = (sysctl_tcp_challenge_ack_limit + 1) >> 1;
+
 		challenge_timestamp = now;
-		challenge_count = 0;
+		WRITE_ONCE(challenge_count, half +
+			   prandom_u32_max(sysctl_tcp_challenge_ack_limit));
 	}
-	if (++challenge_count <= sysctl_tcp_challenge_ack_limit) {
+	count = READ_ONCE(challenge_count);
+	if (count > 0) {
+		WRITE_ONCE(challenge_count, count - 1);
 		NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPCHALLENGEACK);
 		tcp_send_ack(sk);
 	}
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 88203e755af8..13b92d595138 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -705,7 +705,8 @@ release_sk1:
    outside socket context is ugly, certainly. What can I do?
  */
 
-static void tcp_v4_send_ack(struct sk_buff *skb, u32 seq, u32 ack,
+static void tcp_v4_send_ack(struct net *net,
+			    struct sk_buff *skb, u32 seq, u32 ack,
 			    u32 win, u32 tsval, u32 tsecr, int oif,
 			    struct tcp_md5sig_key *key,
 			    int reply_flags, u8 tos)
@@ -720,7 +721,6 @@ static void tcp_v4_send_ack(struct sk_buff *skb, u32 seq, u32 ack,
 			];
 	} rep;
 	struct ip_reply_arg arg;
-	struct net *net = dev_net(skb_dst(skb)->dev);
 
 	memset(&rep.th, 0, sizeof(struct tcphdr));
 	memset(&arg, 0, sizeof(arg));
@@ -782,7 +782,8 @@ static void tcp_v4_timewait_ack(struct sock *sk, struct sk_buff *skb)
 	struct inet_timewait_sock *tw = inet_twsk(sk);
 	struct tcp_timewait_sock *tcptw = tcp_twsk(sk);
 
-	tcp_v4_send_ack(skb, tcptw->tw_snd_nxt, tcptw->tw_rcv_nxt,
+	tcp_v4_send_ack(sock_net(sk), skb,
+			tcptw->tw_snd_nxt, tcptw->tw_rcv_nxt,
 			tcptw->tw_rcv_wnd >> tw->tw_rcv_wscale,
 			tcp_time_stamp + tcptw->tw_ts_offset,
 			tcptw->tw_ts_recent,
@@ -801,8 +802,10 @@ static void tcp_v4_reqsk_send_ack(struct sock *sk, struct sk_buff *skb,
 	/* sk->sk_state == TCP_LISTEN -> for regular TCP_SYN_RECV
 	 * sk->sk_state == TCP_SYN_RECV -> for Fast Open.
 	 */
-	tcp_v4_send_ack(skb, (sk->sk_state == TCP_LISTEN) ?
-			tcp_rsk(req)->snt_isn + 1 : tcp_sk(sk)->snd_nxt,
+	u32 seq = (sk->sk_state == TCP_LISTEN) ? tcp_rsk(req)->snt_isn + 1 :
+					     tcp_sk(sk)->snd_nxt;
+
+	tcp_v4_send_ack(sock_net(sk), skb, seq,
 			tcp_rsk(req)->rcv_nxt, req->rcv_wnd,
 			tcp_time_stamp,
 			req->ts_recent,
@@ -1509,7 +1512,7 @@ bool tcp_prequeue(struct sock *sk, struct sk_buff *skb)
 	if (likely(sk->sk_rx_dst))
 		skb_dst_drop(skb);
 	else
-		skb_dst_force(skb);
+		skb_dst_force_safe(skb);
 
 	__skb_queue_tail(&tp->ucopy.prequeue, skb);
 	tp->ucopy.memory += skb->truesize;
@@ -1714,8 +1717,7 @@ void inet_sk_rx_dst_set(struct sock *sk, const struct sk_buff *skb)
 {
 	struct dst_entry *dst = skb_dst(skb);
 
-	if (dst) {
-		dst_hold(dst);
+	if (dst && dst_hold_safe(dst)) {
 		sk->sk_rx_dst = dst;
 		inet_sk(sk)->rx_dst_ifindex = skb->skb_iif;
 	}
diff --git a/net/ipv4/tcp_metrics.c b/net/ipv4/tcp_metrics.c
index a51d63a43e33..9c840c5c6047 100644
--- a/net/ipv4/tcp_metrics.c
+++ b/net/ipv4/tcp_metrics.c
@@ -566,7 +566,7 @@ reset:
 	 */
 	if (crtt > tp->srtt_us) {
 		/* Set RTO like tcp_rtt_estimator(), but from cached RTT. */
-		crtt /= 8 * USEC_PER_MSEC;
+		crtt /= 8 * USEC_PER_SEC / HZ;
 		inet_csk(sk)->icsk_rto = crtt + max(2 * crtt, tcp_rto_min(sk));
 	} else if (tp->srtt_us == 0) {
 		/* RFC6298: 5.7 We've failed to get a valid RTT sample from
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index 17e7339ee5ca..fec2907b85e8 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -163,9 +163,9 @@ kill_with_rst:
 		if (tcp_death_row.sysctl_tw_recycle &&
 		    tcptw->tw_ts_recent_stamp &&
 		    tcp_tw_remember_stamp(tw))
-			inet_twsk_schedule(tw, tw->tw_timeout);
+			inet_twsk_reschedule(tw, tw->tw_timeout);
 		else
-			inet_twsk_schedule(tw, TCP_TIMEWAIT_LEN);
+			inet_twsk_reschedule(tw, TCP_TIMEWAIT_LEN);
 		return TCP_TW_ACK;
 	}
 
@@ -203,7 +203,7 @@ kill:
 				return TCP_TW_SUCCESS;
 			}
 		}
-		inet_twsk_schedule(tw, TCP_TIMEWAIT_LEN);
+		inet_twsk_reschedule(tw, TCP_TIMEWAIT_LEN);
 
 		if (tmp_opt.saw_tstamp) {
 			tcptw->tw_ts_recent	  = tmp_opt.rcv_tsval;
@@ -253,7 +253,7 @@ kill:
 		 * Do not reschedule in the last case.
 		 */
 		if (paws_reject || th->ack)
-			inet_twsk_schedule(tw, TCP_TIMEWAIT_LEN);
+			inet_twsk_reschedule(tw, TCP_TIMEWAIT_LEN);
 
 		return tcp_timewait_check_oow_rate_limit(
 			tw, skb, LINUX_MIB_TCPACKSKIPPEDTIMEWAIT);
@@ -324,9 +324,6 @@ void tcp_time_wait(struct sock *sk, int state, int timeo)
 		} while (0);
 #endif
 
-		/* Linkage updates. */
-		__inet_twsk_hashdance(tw, sk, &tcp_hashinfo);
-
 		/* Get the TIME_WAIT timeout firing. */
 		if (timeo < rto)
 			timeo = rto;
@@ -340,6 +337,8 @@ void tcp_time_wait(struct sock *sk, int state, int timeo)
 		}
 
 		inet_twsk_schedule(tw, timeo);
+		/* Linkage updates. */
+		__inet_twsk_hashdance(tw, sk, &tcp_hashinfo);
 		inet_twsk_put(tw);
 	} else {
 		/* Sorry, if we're out of memory, just CLOSE this
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 986440b24978..ae66c8426ad0 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -2627,8 +2627,10 @@ int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb)
 	 */
 	if (unlikely((NET_IP_ALIGN && ((unsigned long)skb->data & 3)) ||
 		     skb_headroom(skb) >= 0xFFFF)) {
-		struct sk_buff *nskb = __pskb_copy(skb, MAX_TCP_HEADER,
-						   GFP_ATOMIC);
+		struct sk_buff *nskb;
+
+		skb_mstamp_get(&skb->skb_mstamp);
+		nskb = __pskb_copy(skb, MAX_TCP_HEADER, GFP_ATOMIC);
 		err = nskb ? tcp_transmit_skb(sk, nskb, 0, GFP_ATOMIC) :
 			     -ENOBUFS;
 	} else {
@@ -3143,7 +3145,7 @@ static int tcp_send_syn_data(struct sock *sk, struct sk_buff *syn)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct tcp_fastopen_request *fo = tp->fastopen_req;
-	int syn_loss = 0, space, err = 0, copied;
+	int syn_loss = 0, space, err = 0;
 	unsigned long last_syn_loss = 0;
 	struct sk_buff *syn_data;
 
@@ -3181,17 +3183,18 @@ static int tcp_send_syn_data(struct sock *sk, struct sk_buff *syn)
 		goto fallback;
 	syn_data->ip_summed = CHECKSUM_PARTIAL;
 	memcpy(syn_data->cb, syn->cb, sizeof(syn->cb));
-	copied = copy_from_iter(skb_put(syn_data, space), space,
-				&fo->data->msg_iter);
-	if (unlikely(!copied)) {
-		kfree_skb(syn_data);
-		goto fallback;
-	}
-	if (copied != space) {
-		skb_trim(syn_data, copied);
-		space = copied;
+	if (space) {
+		int copied = copy_from_iter(skb_put(syn_data, space), space,
+					    &fo->data->msg_iter);
+		if (unlikely(!copied)) {
+			kfree_skb(syn_data);
+			goto fallback;
+		}
+		if (copied != space) {
+			skb_trim(syn_data, copied);
+			space = copied;
+		}
 	}
-
 	/* No more data pending in inet_wait_for_connect() */
 	if (space == fo->size)
 		fo->data = NULL;
diff --git a/net/ipv4/tcp_yeah.c b/net/ipv4/tcp_yeah.c
index 17d35662930d..3e6a472e6b88 100644
--- a/net/ipv4/tcp_yeah.c
+++ b/net/ipv4/tcp_yeah.c
@@ -219,7 +219,7 @@ static u32 tcp_yeah_ssthresh(struct sock *sk)
 	yeah->fast_count = 0;
 	yeah->reno_count = max(yeah->reno_count>>1, 2U);
 
-	return tp->snd_cwnd - reduction;
+	return max_t(int, tp->snd_cwnd - reduction, 2);
 }
 
 static struct tcp_congestion_ops tcp_yeah __read_mostly = {
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 1b8c5ba7d5f7..031752efe1ab 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -963,8 +963,10 @@ int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 	if (msg->msg_controllen) {
 		err = ip_cmsg_send(sock_net(sk), msg, &ipc,
 				   sk->sk_family == AF_INET6);
-		if (err)
+		if (unlikely(err)) {
+			kfree(ipc.opt);
 			return err;
+		}
 		if (ipc.opt)
 			free = 1;
 		connected = 0;
@@ -1977,10 +1979,14 @@ void udp_v4_early_demux(struct sk_buff *skb)
 		if (!in_dev)
 			return;
 
-		ours = ip_check_mc_rcu(in_dev, iph->daddr, iph->saddr,
-				       iph->protocol);
-		if (!ours)
-			return;
+		/* we are supposed to accept bcast packets */
+		if (skb->pkt_type == PACKET_MULTICAST) {
+			ours = ip_check_mc_rcu(in_dev, iph->daddr, iph->saddr,
+					       iph->protocol);
+			if (!ours)
+				return;
+		}
+
 		sk = __udp4_lib_mcast_demux_lookup(net, uh->dest, iph->daddr,
 						   uh->source, iph->saddr, dif);
 	} else if (skb->pkt_type == PACKET_HOST) {
diff --git a/net/ipv4/udp_tunnel.c b/net/ipv4/udp_tunnel.c
index 6bb98cc193c9..7b534ac04056 100644
--- a/net/ipv4/udp_tunnel.c
+++ b/net/ipv4/udp_tunnel.c
@@ -90,6 +90,8 @@ int udp_tunnel_xmit_skb(struct rtable *rt, struct sock *sk, struct sk_buff *skb,
 	uh->source = src_port;
 	uh->len = htons(skb->len);
 
+	memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt));
+
 	udp_set_csum(nocheck, skb, src, dst, skb->len);
 
 	return iptunnel_xmit(sk, rt, skb, src, dst, IPPROTO_UDP,
diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c
index bff69746e05f..78526087126d 100644
--- a/net/ipv4/xfrm4_policy.c
+++ b/net/ipv4/xfrm4_policy.c
@@ -230,7 +230,7 @@ static void xfrm4_dst_ifdown(struct dst_entry *dst, struct net_device *dev,
 	xfrm_dst_ifdown(dst, dev);
 }
 
-static struct dst_ops xfrm4_dst_ops = {
+static struct dst_ops xfrm4_dst_ops_template = {
 	.family =		AF_INET,
 	.gc =			xfrm4_garbage_collect,
 	.update_pmtu =		xfrm4_update_pmtu,
@@ -244,7 +244,7 @@ static struct dst_ops xfrm4_dst_ops = {
 
 static struct xfrm_policy_afinfo xfrm4_policy_afinfo = {
 	.family = 		AF_INET,
-	.dst_ops =		&xfrm4_dst_ops,
+	.dst_ops =		&xfrm4_dst_ops_template,
 	.dst_lookup =		xfrm4_dst_lookup,
 	.get_saddr =		xfrm4_get_saddr,
 	.decode_session =	_decode_session4,
@@ -266,7 +266,7 @@ static struct ctl_table xfrm4_policy_table[] = {
 	{ }
 };
 
-static int __net_init xfrm4_net_init(struct net *net)
+static int __net_init xfrm4_net_sysctl_init(struct net *net)
 {
 	struct ctl_table *table;
 	struct ctl_table_header *hdr;
@@ -294,7 +294,7 @@ err_alloc:
 	return -ENOMEM;
 }
 
-static void __net_exit xfrm4_net_exit(struct net *net)
+static void __net_exit xfrm4_net_sysctl_exit(struct net *net)
 {
 	struct ctl_table *table;
 
@@ -306,12 +306,44 @@ static void __net_exit xfrm4_net_exit(struct net *net)
 	if (!net_eq(net, &init_net))
 		kfree(table);
 }
+#else /* CONFIG_SYSCTL */
+static int inline xfrm4_net_sysctl_init(struct net *net)
+{
+	return 0;
+}
+
+static void inline xfrm4_net_sysctl_exit(struct net *net)
+{
+}
+#endif
+
+static int __net_init xfrm4_net_init(struct net *net)
+{
+	int ret;
+
+	memcpy(&net->xfrm.xfrm4_dst_ops, &xfrm4_dst_ops_template,
+	       sizeof(xfrm4_dst_ops_template));
+	ret = dst_entries_init(&net->xfrm.xfrm4_dst_ops);
+	if (ret)
+		return ret;
+
+	ret = xfrm4_net_sysctl_init(net);
+	if (ret)
+		dst_entries_destroy(&net->xfrm.xfrm4_dst_ops);
+
+	return ret;
+}
+
+static void __net_exit xfrm4_net_exit(struct net *net)
+{
+	xfrm4_net_sysctl_exit(net);
+	dst_entries_destroy(&net->xfrm.xfrm4_dst_ops);
+}
 
 static struct pernet_operations __net_initdata xfrm4_net_ops = {
 	.init	= xfrm4_net_init,
 	.exit	= xfrm4_net_exit,
 };
-#endif
 
 static void __init xfrm4_policy_init(void)
 {
@@ -320,13 +352,9 @@ static void __init xfrm4_policy_init(void)
 
 void __init xfrm4_init(void)
 {
-	dst_entries_init(&xfrm4_dst_ops);
-
 	xfrm4_state_init();
 	xfrm4_policy_init();
 	xfrm4_protocol_init();
-#ifdef CONFIG_SYSCTL
 	register_pernet_subsys(&xfrm4_net_ops);
-#endif
 }