X-Git-Url: http://ftp.safe.ca/?p=safe%2Fjmp%2Flinux-2.6;a=blobdiff_plain;f=net%2Fipv6%2Fudp.c;h=34efb3589ffac1dc4050132d7cf926c86e87a499;hp=e35921a4668991d134ae0ed352d2fb16b8a5f1f8;hb=2c8c1e7297e19bdef3c178c3ea41d898a7716e3e;hpb=dda61925f84d89e2f2a4597d6298a05a2bc05c20

diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index e35921a..34efb35 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -7,8 +7,6 @@
  *
  *	Based on linux/ipv4/udp.c
  *
- *	$Id: udp.c,v 1.65 2002/02/01 22:01:04 davem Exp $
- *
  *	Fixes:
  *	Hideaki YOSHIFUJI	:	sin6_scope_id support
  *	YOSHIFUJI Hideaki @USAGI and:	Support IPV6_V6ONLY socket option, which
@@ -51,64 +49,267 @@
 #include <linux/seq_file.h>
 #include "udp_impl.h"
 
+int ipv6_rcv_saddr_equal(const struct sock *sk, const struct sock *sk2)
+{
+	const struct in6_addr *sk_rcv_saddr6 = &inet6_sk(sk)->rcv_saddr;
+	const struct in6_addr *sk2_rcv_saddr6 = inet6_rcv_saddr(sk2);
+	__be32 sk1_rcv_saddr = inet_sk(sk)->inet_rcv_saddr;
+	__be32 sk2_rcv_saddr = inet_rcv_saddr(sk2);
+	int sk_ipv6only = ipv6_only_sock(sk);
+	int sk2_ipv6only = inet_v6_ipv6only(sk2);
+	int addr_type = ipv6_addr_type(sk_rcv_saddr6);
+	int addr_type2 = sk2_rcv_saddr6 ? ipv6_addr_type(sk2_rcv_saddr6) : IPV6_ADDR_MAPPED;
+
+	/* if both are mapped, treat as IPv4 */
+	if (addr_type == IPV6_ADDR_MAPPED && addr_type2 == IPV6_ADDR_MAPPED)
+		return (!sk2_ipv6only &&
+			(!sk1_rcv_saddr || !sk2_rcv_saddr ||
+			  sk1_rcv_saddr == sk2_rcv_saddr));
+
+	if (addr_type2 == IPV6_ADDR_ANY &&
+	    !(sk2_ipv6only && addr_type == IPV6_ADDR_MAPPED))
+		return 1;
+
+	if (addr_type == IPV6_ADDR_ANY &&
+	    !(sk_ipv6only && addr_type2 == IPV6_ADDR_MAPPED))
+		return 1;
+
+	if (sk2_rcv_saddr6 &&
+	    ipv6_addr_equal(sk_rcv_saddr6, sk2_rcv_saddr6))
+		return 1;
+
+	return 0;
+}
+
+static unsigned int udp6_portaddr_hash(struct net *net,
+				       const struct in6_addr *addr6,
+				       unsigned int port)
+{
+	unsigned int hash, mix = net_hash_mix(net);
+
+	if (ipv6_addr_any(addr6))
+		hash = jhash_1word(0, mix);
+	else if (ipv6_addr_v4mapped(addr6))
+		hash = jhash_1word(addr6->s6_addr32[3], mix);
+	else
+		hash = jhash2(addr6->s6_addr32, 4, mix);
+
+	return hash ^ port;
+}
+
+
 int udp_v6_get_port(struct sock *sk, unsigned short snum)
 {
-	return udp_lib_get_port(sk, snum, ipv6_rcv_saddr_equal);
+	unsigned int hash2_nulladdr =
+		udp6_portaddr_hash(sock_net(sk), &in6addr_any, snum);
+	unsigned int hash2_partial = 
+		udp6_portaddr_hash(sock_net(sk), &inet6_sk(sk)->rcv_saddr, 0);
+
+	/* precompute partial secondary hash */
+	udp_sk(sk)->udp_portaddr_hash = hash2_partial;
+	return udp_lib_get_port(sk, snum, ipv6_rcv_saddr_equal, hash2_nulladdr);
+}
+
+static inline int compute_score(struct sock *sk, struct net *net,
+				unsigned short hnum,
+				struct in6_addr *saddr, __be16 sport,
+				struct in6_addr *daddr, __be16 dport,
+				int dif)
+{
+	int score = -1;
+
+	if (net_eq(sock_net(sk), net) && udp_sk(sk)->udp_port_hash == hnum &&
+			sk->sk_family == PF_INET6) {
+		struct ipv6_pinfo *np = inet6_sk(sk);
+		struct inet_sock *inet = inet_sk(sk);
+
+		score = 0;
+		if (inet->inet_dport) {
+			if (inet->inet_dport != sport)
+				return -1;
+			score++;
+		}
+		if (!ipv6_addr_any(&np->rcv_saddr)) {
+			if (!ipv6_addr_equal(&np->rcv_saddr, daddr))
+				return -1;
+			score++;
+		}
+		if (!ipv6_addr_any(&np->daddr)) {
+			if (!ipv6_addr_equal(&np->daddr, saddr))
+				return -1;
+			score++;
+		}
+		if (sk->sk_bound_dev_if) {
+			if (sk->sk_bound_dev_if != dif)
+				return -1;
+			score++;
+		}
+	}
+	return score;
+}
+
+#define SCORE2_MAX (1 + 1 + 1)
+static inline int compute_score2(struct sock *sk, struct net *net,
+				const struct in6_addr *saddr, __be16 sport,
+				const struct in6_addr *daddr, unsigned short hnum,
+				int dif)
+{
+	int score = -1;
+
+	if (net_eq(sock_net(sk), net) && udp_sk(sk)->udp_port_hash == hnum &&
+			sk->sk_family == PF_INET6) {
+		struct ipv6_pinfo *np = inet6_sk(sk);
+		struct inet_sock *inet = inet_sk(sk);
+
+		if (!ipv6_addr_equal(&np->rcv_saddr, daddr))
+			return -1;
+		score = 0;
+		if (inet->inet_dport) {
+			if (inet->inet_dport != sport)
+				return -1;
+			score++;
+		}
+		if (!ipv6_addr_any(&np->daddr)) {
+			if (!ipv6_addr_equal(&np->daddr, saddr))
+				return -1;
+			score++;
+		}
+		if (sk->sk_bound_dev_if) {
+			if (sk->sk_bound_dev_if != dif)
+				return -1;
+			score++;
+		}
+	}
+	return score;
+}
+
+
+/* called with read_rcu_lock() */
+static struct sock *udp6_lib_lookup2(struct net *net,
+		const struct in6_addr *saddr, __be16 sport,
+		const struct in6_addr *daddr, unsigned int hnum, int dif,
+		struct udp_hslot *hslot2, unsigned int slot2)
+{
+	struct sock *sk, *result;
+	struct hlist_nulls_node *node;
+	int score, badness;
+
+begin:
+	result = NULL;
+	badness = -1;
+	udp_portaddr_for_each_entry_rcu(sk, node, &hslot2->head) {
+		score = compute_score2(sk, net, saddr, sport,
+				      daddr, hnum, dif);
+		if (score > badness) {
+			result = sk;
+			badness = score;
+			if (score == SCORE2_MAX)
+				goto exact_match;
+		}
+	}
+	/*
+	 * if the nulls value we got at the end of this lookup is
+	 * not the expected one, we must restart lookup.
+	 * We probably met an item that was moved to another chain.
+	 */
+	if (get_nulls_value(node) != slot2)
+		goto begin;
+
+	if (result) {
+exact_match:
+		if (unlikely(!atomic_inc_not_zero(&result->sk_refcnt)))
+			result = NULL;
+		else if (unlikely(compute_score2(result, net, saddr, sport,
+				  daddr, hnum, dif) < badness)) {
+			sock_put(result);
+			goto begin;
+		}
+	}
+	return result;
 }
 
 static struct sock *__udp6_lib_lookup(struct net *net,
 				      struct in6_addr *saddr, __be16 sport,
 				      struct in6_addr *daddr, __be16 dport,
-				      int dif, struct hlist_head udptable[])
+				      int dif, struct udp_table *udptable)
 {
-	struct sock *sk, *result = NULL;
-	struct hlist_node *node;
+	struct sock *sk, *result;
+	struct hlist_nulls_node *node;
 	unsigned short hnum = ntohs(dport);
-	int badness = -1;
-
-	read_lock(&udp_hash_lock);
-	sk_for_each(sk, node, &udptable[hnum & (UDP_HTABLE_SIZE - 1)]) {
-		struct inet_sock *inet = inet_sk(sk);
-
-		if (net_eq(sock_net(sk), net) && sk->sk_hash == hnum &&
-				sk->sk_family == PF_INET6) {
-			struct ipv6_pinfo *np = inet6_sk(sk);
-			int score = 0;
-			if (inet->dport) {
-				if (inet->dport != sport)
-					continue;
-				score++;
-			}
-			if (!ipv6_addr_any(&np->rcv_saddr)) {
-				if (!ipv6_addr_equal(&np->rcv_saddr, daddr))
-					continue;
-				score++;
-			}
-			if (!ipv6_addr_any(&np->daddr)) {
-				if (!ipv6_addr_equal(&np->daddr, saddr))
-					continue;
-				score++;
-			}
-			if (sk->sk_bound_dev_if) {
-				if (sk->sk_bound_dev_if != dif)
-					continue;
-				score++;
-			}
-			if (score == 4) {
-				result = sk;
-				break;
-			} else if (score > badness) {
-				result = sk;
-				badness = score;
-			}
+	unsigned int hash2, slot2, slot = udp_hashfn(net, hnum, udptable->mask);
+	struct udp_hslot *hslot2, *hslot = &udptable->hash[slot];
+	int score, badness;
+
+	rcu_read_lock();
+	if (hslot->count > 10) {
+		hash2 = udp6_portaddr_hash(net, daddr, hnum);
+		slot2 = hash2 & udptable->mask;
+		hslot2 = &udptable->hash2[slot2];
+		if (hslot->count < hslot2->count)
+			goto begin;
+
+		result = udp6_lib_lookup2(net, saddr, sport,
+					  daddr, hnum, dif,
+					  hslot2, slot2);
+		if (!result) {
+			hash2 = udp6_portaddr_hash(net, &in6addr_any, hnum);
+			slot2 = hash2 & udptable->mask;
+			hslot2 = &udptable->hash2[slot2];
+			if (hslot->count < hslot2->count)
+				goto begin;
+
+			result = udp6_lib_lookup2(net, &in6addr_any, sport,
+						  daddr, hnum, dif,
+						  hslot2, slot2);
+		}
+		rcu_read_unlock();
+		return result;
+	}
+begin:
+	result = NULL;
+	badness = -1;
+	sk_nulls_for_each_rcu(sk, node, &hslot->head) {
+		score = compute_score(sk, net, hnum, saddr, sport, daddr, dport, dif);
+		if (score > badness) {
+			result = sk;
+			badness = score;
+		}
+	}
+	/*
+	 * if the nulls value we got at the end of this lookup is
+	 * not the expected one, we must restart lookup.
+	 * We probably met an item that was moved to another chain.
+	 */
+	if (get_nulls_value(node) != slot)
+		goto begin;
+
+	if (result) {
+		if (unlikely(!atomic_inc_not_zero(&result->sk_refcnt)))
+			result = NULL;
+		else if (unlikely(compute_score(result, net, hnum, saddr, sport,
+					daddr, dport, dif) < badness)) {
+			sock_put(result);
+			goto begin;
 		}
 	}
-	if (result)
-		sock_hold(result);
-	read_unlock(&udp_hash_lock);
+	rcu_read_unlock();
 	return result;
 }
 
+static struct sock *__udp6_lib_lookup_skb(struct sk_buff *skb,
+					  __be16 sport, __be16 dport,
+					  struct udp_table *udptable)
+{
+	struct sock *sk;
+	struct ipv6hdr *iph = ipv6_hdr(skb);
+
+	if (unlikely(sk = skb_steal_sock(skb)))
+		return sk;
+	return __udp6_lib_lookup(dev_net(skb_dst(skb)->dev), &iph->saddr, sport,
+				 &iph->daddr, dport, inet6_iif(skb),
+				 udptable);
+}
+
 /*
  * 	This should be easy, if there is something there we
  * 	return it, otherwise we block.
@@ -125,6 +326,7 @@ int udpv6_recvmsg(struct kiocb *iocb, struct sock *sk,
 	int peeked;
 	int err;
 	int is_udplite = IS_UDPLITE(sk);
+	int is_udp4;
 
 	if (addr_len)
 		*addr_len=sizeof(struct sockaddr_in6);
@@ -145,6 +347,8 @@ try_again:
 	else if (copied < ulen)
 		msg->msg_flags |= MSG_TRUNC;
 
+	is_udp4 = (skb->protocol == htons(ETH_P_IP));
+
 	/*
 	 * If checksum is needed at all, try to do it while copying the
 	 * data.  If the data is truncated, or if we only want a partial
@@ -167,10 +371,16 @@ try_again:
 	if (err)
 		goto out_free;
 
-	if (!peeked)
-		UDP6_INC_STATS_USER(UDP_MIB_INDATAGRAMS, is_udplite);
+	if (!peeked) {
+		if (is_udp4)
+			UDP_INC_STATS_USER(sock_net(sk),
+					UDP_MIB_INDATAGRAMS, is_udplite);
+		else
+			UDP6_INC_STATS_USER(sock_net(sk),
+					UDP_MIB_INDATAGRAMS, is_udplite);
+	}
 
-	sock_recv_timestamp(msg, sk, skb);
+	sock_recv_ts_and_drops(msg, sk, skb);
 
 	/* Copy the address. */
 	if (msg->msg_name) {
@@ -182,9 +392,9 @@ try_again:
 		sin6->sin6_flowinfo = 0;
 		sin6->sin6_scope_id = 0;
 
-		if (skb->protocol == htons(ETH_P_IP))
-			ipv6_addr_set(&sin6->sin6_addr, 0, 0,
-				      htonl(0xffff), ip_hdr(skb)->saddr);
+		if (is_udp4)
+			ipv6_addr_set_v4mapped(ip_hdr(skb)->saddr,
+					       &sin6->sin6_addr);
 		else {
 			ipv6_addr_copy(&sin6->sin6_addr,
 				       &ipv6_hdr(skb)->saddr);
@@ -193,7 +403,7 @@ try_again:
 		}
 
 	}
-	if (skb->protocol == htons(ETH_P_IP)) {
+	if (is_udp4) {
 		if (inet->cmsg_flags)
 			ip_cmsg_recv(msg, skb);
 	} else {
@@ -206,16 +416,20 @@ try_again:
 		err = ulen;
 
 out_free:
-	lock_sock(sk);
-	skb_free_datagram(sk, skb);
-	release_sock(sk);
+	skb_free_datagram_locked(sk, skb);
 out:
 	return err;
 
 csum_copy_err:
 	lock_sock(sk);
-	if (!skb_kill_datagram(sk, skb, flags))
-		UDP6_INC_STATS_USER(UDP_MIB_INERRORS, is_udplite);
+	if (!skb_kill_datagram(sk, skb, flags)) {
+		if (is_udp4)
+			UDP_INC_STATS_USER(sock_net(sk),
+					UDP_MIB_INERRORS, is_udplite);
+		else
+			UDP6_INC_STATS_USER(sock_net(sk),
+					UDP_MIB_INERRORS, is_udplite);
+	}
 	release_sock(sk);
 
 	if (flags & MSG_DONTWAIT)
@@ -224,8 +438,8 @@ csum_copy_err:
 }
 
 void __udp6_lib_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
-		    int type, int code, int offset, __be32 info,
-		    struct hlist_head udptable[]                    )
+		    u8 type, u8 code, int offset, __be32 info,
+		    struct udp_table *udptable)
 {
 	struct ipv6_pinfo *np;
 	struct ipv6hdr *hdr = (struct ipv6hdr*)skb->data;
@@ -258,10 +472,10 @@ out:
 }
 
 static __inline__ void udpv6_err(struct sk_buff *skb,
-				 struct inet6_skb_parm *opt, int type,
-				 int code, int offset, __be32 info     )
+				 struct inet6_skb_parm *opt, u8 type,
+				 u8 code, int offset, __be32 info     )
 {
-	__udp6_lib_err(skb, opt, type, code, offset, info, udp_hash);
+	__udp6_lib_err(skb, opt, type, code, offset, info, &udp_table);
 }
 
 int udpv6_queue_rcv_skb(struct sock * sk, struct sk_buff *skb)
@@ -297,39 +511,43 @@ int udpv6_queue_rcv_skb(struct sock * sk, struct sk_buff *skb)
 			goto drop;
 	}
 
-	if ((rc = sock_queue_rcv_skb(sk,skb)) < 0) {
+	if ((rc = sock_queue_rcv_skb(sk, skb)) < 0) {
 		/* Note that an ENOMEM error is charged twice */
 		if (rc == -ENOMEM)
-			UDP6_INC_STATS_BH(UDP_MIB_RCVBUFERRORS, is_udplite);
-		goto drop;
+			UDP6_INC_STATS_BH(sock_net(sk),
+					UDP_MIB_RCVBUFERRORS, is_udplite);
+		goto drop_no_sk_drops_inc;
 	}
 
 	return 0;
 drop:
-	UDP6_INC_STATS_BH(UDP_MIB_INERRORS, is_udplite);
+	atomic_inc(&sk->sk_drops);
+drop_no_sk_drops_inc:
+	UDP6_INC_STATS_BH(sock_net(sk), UDP_MIB_INERRORS, is_udplite);
 	kfree_skb(skb);
 	return -1;
 }
 
-static struct sock *udp_v6_mcast_next(struct sock *sk,
+static struct sock *udp_v6_mcast_next(struct net *net, struct sock *sk,
 				      __be16 loc_port, struct in6_addr *loc_addr,
 				      __be16 rmt_port, struct in6_addr *rmt_addr,
 				      int dif)
 {
-	struct hlist_node *node;
+	struct hlist_nulls_node *node;
 	struct sock *s = sk;
 	unsigned short num = ntohs(loc_port);
 
-	sk_for_each_from(s, node) {
+	sk_nulls_for_each_from(s, node) {
 		struct inet_sock *inet = inet_sk(s);
 
-		if (sock_net(s) != sock_net(sk))
+		if (!net_eq(sock_net(s), net))
 			continue;
 
-		if (s->sk_hash == num && s->sk_family == PF_INET6) {
+		if (udp_sk(s)->udp_port_hash == num &&
+		    s->sk_family == PF_INET6) {
 			struct ipv6_pinfo *np = inet6_sk(s);
-			if (inet->dport) {
-				if (inet->dport != rmt_port)
+			if (inet->inet_dport) {
+				if (inet->inet_dport != rmt_port)
 					continue;
 			}
 			if (!ipv6_addr_any(&np->daddr) &&
@@ -351,47 +569,78 @@ static struct sock *udp_v6_mcast_next(struct sock *sk,
 	return NULL;
 }
 
+static void flush_stack(struct sock **stack, unsigned int count,
+			struct sk_buff *skb, unsigned int final)
+{
+	unsigned int i;
+	struct sock *sk;
+	struct sk_buff *skb1;
+
+	for (i = 0; i < count; i++) {
+		skb1 = (i == final) ? skb : skb_clone(skb, GFP_ATOMIC);
+
+		sk = stack[i];
+		if (skb1) {
+			bh_lock_sock(sk);
+			if (!sock_owned_by_user(sk))
+				udpv6_queue_rcv_skb(sk, skb1);
+			else
+				sk_add_backlog(sk, skb1);
+			bh_unlock_sock(sk);
+		} else {
+			atomic_inc(&sk->sk_drops);
+			UDP6_INC_STATS_BH(sock_net(sk),
+					UDP_MIB_RCVBUFERRORS, IS_UDPLITE(sk));
+			UDP6_INC_STATS_BH(sock_net(sk),
+					UDP_MIB_INERRORS, IS_UDPLITE(sk));
+		}
+	}
+}
 /*
  * Note: called only from the BH handler context,
  * so we don't need to lock the hashes.
  */
-static int __udp6_lib_mcast_deliver(struct sk_buff *skb, struct in6_addr *saddr,
-			   struct in6_addr *daddr, struct hlist_head udptable[])
+static int __udp6_lib_mcast_deliver(struct net *net, struct sk_buff *skb,
+		struct in6_addr *saddr, struct in6_addr *daddr,
+		struct udp_table *udptable)
 {
-	struct sock *sk, *sk2;
+	struct sock *sk, *stack[256 / sizeof(struct sock *)];
 	const struct udphdr *uh = udp_hdr(skb);
+	struct udp_hslot *hslot = udp_hashslot(udptable, net, ntohs(uh->dest));
 	int dif;
+	unsigned int i, count = 0;
 
-	read_lock(&udp_hash_lock);
-	sk = sk_head(&udptable[ntohs(uh->dest) & (UDP_HTABLE_SIZE - 1)]);
+	spin_lock(&hslot->lock);
+	sk = sk_nulls_head(&hslot->head);
 	dif = inet6_iif(skb);
-	sk = udp_v6_mcast_next(sk, uh->dest, daddr, uh->source, saddr, dif);
-	if (!sk) {
-		kfree_skb(skb);
-		goto out;
+	sk = udp_v6_mcast_next(net, sk, uh->dest, daddr, uh->source, saddr, dif);
+	while (sk) {
+		stack[count++] = sk;
+		sk = udp_v6_mcast_next(net, sk_nulls_next(sk), uh->dest, daddr,
+				       uh->source, saddr, dif);
+		if (unlikely(count == ARRAY_SIZE(stack))) {
+			if (!sk)
+				break;
+			flush_stack(stack, count, skb, ~0);
+			count = 0;
+		}
 	}
+	/*
+	 * before releasing the lock, we must take reference on sockets
+	 */
+	for (i = 0; i < count; i++)
+		sock_hold(stack[i]);
 
-	sk2 = sk;
-	while ((sk2 = udp_v6_mcast_next(sk_next(sk2), uh->dest, daddr,
-					uh->source, saddr, dif))) {
-		struct sk_buff *buff = skb_clone(skb, GFP_ATOMIC);
-		if (buff) {
-			bh_lock_sock_nested(sk2);
-			if (!sock_owned_by_user(sk2))
-				udpv6_queue_rcv_skb(sk2, buff);
-			else
-				sk_add_backlog(sk2, buff);
-			bh_unlock_sock(sk2);
-		}
+	spin_unlock(&hslot->lock);
+
+	if (count) {
+		flush_stack(stack, count, skb, count - 1);
+
+		for (i = 0; i < count; i++)
+			sock_put(stack[i]);
+	} else {
+		kfree_skb(skb);
 	}
-	bh_lock_sock_nested(sk);
-	if (!sock_owned_by_user(sk))
-		udpv6_queue_rcv_skb(sk, skb);
-	else
-		sk_add_backlog(sk, skb);
-	bh_unlock_sock(sk);
-out:
-	read_unlock(&udp_hash_lock);
 	return 0;
 }
 
@@ -429,7 +678,7 @@ static inline int udp6_csum_init(struct sk_buff *skb, struct udphdr *uh,
 	return 0;
 }
 
-int __udp6_lib_rcv(struct sk_buff *skb, struct hlist_head udptable[],
+int __udp6_lib_rcv(struct sk_buff *skb, struct udp_table *udptable,
 		   int proto)
 {
 	struct sock *sk;
@@ -437,6 +686,7 @@ int __udp6_lib_rcv(struct sk_buff *skb, struct hlist_head udptable[],
 	struct net_device *dev = skb->dev;
 	struct in6_addr *saddr, *daddr;
 	u32 ulen = 0;
+	struct net *net = dev_net(skb->dev);
 
 	if (!pskb_may_pull(skb, sizeof(struct udphdr)))
 		goto short_packet;
@@ -475,7 +725,8 @@ int __udp6_lib_rcv(struct sk_buff *skb, struct hlist_head udptable[],
 	 *	Multicast receive code
 	 */
 	if (ipv6_addr_is_multicast(daddr))
-		return __udp6_lib_mcast_deliver(skb, saddr, daddr, udptable);
+		return __udp6_lib_mcast_deliver(net, skb,
+				saddr, daddr, udptable);
 
 	/* Unicast */
 
@@ -483,8 +734,7 @@ int __udp6_lib_rcv(struct sk_buff *skb, struct hlist_head udptable[],
 	 * check socket cache ... must talk to Alan about his plans
 	 * for sock caches... i'll skip this for now.
 	 */
-	sk = __udp6_lib_lookup(dev_net(skb->dev), saddr, uh->source,
-			       daddr, uh->dest, inet6_iif(skb), udptable);
+	sk = __udp6_lib_lookup_skb(skb, uh->source, uh->dest, udptable);
 
 	if (sk == NULL) {
 		if (!xfrm6_policy_check(NULL, XFRM_POLICY_IN, skb))
@@ -492,7 +742,8 @@ int __udp6_lib_rcv(struct sk_buff *skb, struct hlist_head udptable[],
 
 		if (udp_lib_checksum_complete(skb))
 			goto discard;
-		UDP6_INC_STATS_BH(UDP_MIB_NOPORTS, proto == IPPROTO_UDPLITE);
+		UDP6_INC_STATS_BH(net, UDP_MIB_NOPORTS,
+				proto == IPPROTO_UDPLITE);
 
 		icmpv6_send(skb, ICMPV6_DEST_UNREACH, ICMPV6_PORT_UNREACH, 0, dev);
 
@@ -502,7 +753,7 @@ int __udp6_lib_rcv(struct sk_buff *skb, struct hlist_head udptable[],
 
 	/* deliver */
 
-	bh_lock_sock_nested(sk);
+	bh_lock_sock(sk);
 	if (!sock_owned_by_user(sk))
 		udpv6_queue_rcv_skb(sk, skb);
 	else
@@ -517,14 +768,14 @@ short_packet:
 		       ulen, skb->len);
 
 discard:
-	UDP6_INC_STATS_BH(UDP_MIB_INERRORS, proto == IPPROTO_UDPLITE);
+	UDP6_INC_STATS_BH(net, UDP_MIB_INERRORS, proto == IPPROTO_UDPLITE);
 	kfree_skb(skb);
 	return 0;
 }
 
 static __inline__ int udpv6_rcv(struct sk_buff *skb)
 {
-	return __udp6_lib_rcv(skb, udp_hash, IPPROTO_UDP);
+	return __udp6_lib_rcv(skb, &udp_table, IPPROTO_UDP);
 }
 
 /*
@@ -534,13 +785,56 @@ static void udp_v6_flush_pending_frames(struct sock *sk)
 {
 	struct udp_sock *up = udp_sk(sk);
 
-	if (up->pending) {
+	if (up->pending == AF_INET)
+		udp_flush_pending_frames(sk);
+	else if (up->pending) {
 		up->len = 0;
 		up->pending = 0;
 		ip6_flush_pending_frames(sk);
 	}
 }
 
+/**
+ * 	udp6_hwcsum_outgoing  -  handle outgoing HW checksumming
+ * 	@sk: 	socket we are sending on
+ * 	@skb: 	sk_buff containing the filled-in UDP header
+ * 	        (checksum field must be zeroed out)
+ */
+static void udp6_hwcsum_outgoing(struct sock *sk, struct sk_buff *skb,
+				 const struct in6_addr *saddr,
+				 const struct in6_addr *daddr, int len)
+{
+	unsigned int offset;
+	struct udphdr *uh = udp_hdr(skb);
+	__wsum csum = 0;
+
+	if (skb_queue_len(&sk->sk_write_queue) == 1) {
+		/* Only one fragment on the socket.  */
+		skb->csum_start = skb_transport_header(skb) - skb->head;
+		skb->csum_offset = offsetof(struct udphdr, check);
+		uh->check = ~csum_ipv6_magic(saddr, daddr, len, IPPROTO_UDP, 0);
+	} else {
+		/*
+		 * HW-checksum won't work as there are two or more
+		 * fragments on the socket so that all csums of sk_buffs
+		 * should be together
+		 */
+		offset = skb_transport_offset(skb);
+		skb->csum = skb_checksum(skb, offset, skb->len - offset, 0);
+
+		skb->ip_summed = CHECKSUM_NONE;
+
+		skb_queue_walk(&sk->sk_write_queue, skb) {
+			csum = csum_add(csum, skb->csum);
+		}
+
+		uh->check = csum_ipv6_magic(saddr, daddr, len, IPPROTO_UDP,
+					    csum);
+		if (uh->check == 0)
+			uh->check = CSUM_MANGLED_0;
+	}
+}
+
 /*
  *	Sending
  */
@@ -571,7 +865,11 @@ static int udp_v6_push_pending_frames(struct sock *sk)
 
 	if (is_udplite)
 		csum = udplite_csum_outgoing(sk, skb);
-	 else
+	else if (skb->ip_summed == CHECKSUM_PARTIAL) { /* UDP hardware csum */
+		udp6_hwcsum_outgoing(sk, skb, &fl->fl6_src, &fl->fl6_dst,
+				     up->len);
+		goto send;
+	} else
 		csum = udp_csum_outgoing(sk, skb);
 
 	/* add protocol-dependent pseudo-header */
@@ -580,12 +878,20 @@ static int udp_v6_push_pending_frames(struct sock *sk)
 	if (uh->check == 0)
 		uh->check = CSUM_MANGLED_0;
 
+send:
 	err = ip6_push_pending_frames(sk);
+	if (err) {
+		if (err == -ENOBUFS && !inet6_sk(sk)->recverr) {
+			UDP6_INC_STATS_USER(sock_net(sk),
+					    UDP_MIB_SNDBUFERRORS, is_udplite);
+			err = 0;
+		}
+	} else
+		UDP6_INC_STATS_USER(sock_net(sk),
+				    UDP_MIB_OUTDATAGRAMS, is_udplite);
 out:
 	up->len = 0;
 	up->pending = 0;
-	if (!err)
-		UDP6_INC_STATS_USER(UDP_MIB_OUTDATAGRAMS, is_udplite);
 	return err;
 }
 
@@ -644,7 +950,7 @@ int udpv6_sendmsg(struct kiocb *iocb, struct sock *sk,
 		if (ipv6_addr_v4mapped(daddr)) {
 			struct sockaddr_in sin;
 			sin.sin_family = AF_INET;
-			sin.sin_port = sin6 ? sin6->sin6_port : inet->dport;
+			sin.sin_port = sin6 ? sin6->sin6_port : inet->inet_dport;
 			sin.sin_addr.s_addr = daddr->s6_addr32[3];
 			msg->msg_name = &sin;
 			msg->msg_namelen = sizeof(sin);
@@ -717,7 +1023,7 @@ do_udp_sendmsg:
 		if (sk->sk_state != TCP_ESTABLISHED)
 			return -EDESTADDRREQ;
 
-		fl.fl_ip_dport = inet->dport;
+		fl.fl_ip_dport = inet->inet_dport;
 		daddr = &np->daddr;
 		fl.fl6_flowlabel = np->flow_label;
 		connected = 1;
@@ -726,12 +1032,17 @@ do_udp_sendmsg:
 	if (!fl.oif)
 		fl.oif = sk->sk_bound_dev_if;
 
+	if (!fl.oif)
+		fl.oif = np->sticky_pktinfo.ipi6_ifindex;
+
+	fl.mark = sk->sk_mark;
+
 	if (msg->msg_controllen) {
 		opt = &opt_space;
 		memset(opt, 0, sizeof(struct ipv6_txoptions));
 		opt->tot_len = sizeof(*opt);
 
-		err = datagram_send_ctl(msg, &fl, opt, &hlimit, &tclass);
+		err = datagram_send_ctl(sock_net(sk), msg, &fl, opt, &hlimit, &tclass);
 		if (err < 0) {
 			fl6_sock_release(flowlabel);
 			return err;
@@ -752,10 +1063,13 @@ do_udp_sendmsg:
 	opt = ipv6_fixup_options(&opt_space, opt);
 
 	fl.proto = sk->sk_protocol;
-	ipv6_addr_copy(&fl.fl6_dst, daddr);
+	if (!ipv6_addr_any(daddr))
+		ipv6_addr_copy(&fl.fl6_dst, daddr);
+	else
+		fl.fl6_dst.s6_addr[15] = 0x1; /* :: means loopback (BSD'ism) */
 	if (ipv6_addr_any(&fl.fl6_src) && !ipv6_addr_any(&np->saddr))
 		ipv6_addr_copy(&fl.fl6_src, &np->saddr);
-	fl.fl_ip_sport = inet->sport;
+	fl.fl_ip_sport = inet->inet_sport;
 
 	/* merge ip6_build_xmit from ip6_output */
 	if (opt && opt->srcrt) {
@@ -779,7 +1093,8 @@ do_udp_sendmsg:
 	if (final_p)
 		ipv6_addr_copy(&fl.fl6_dst, final_p);
 
-	if ((err = __xfrm_lookup(&dst, &fl, sk, XFRM_LOOKUP_WAIT)) < 0) {
+	err = __xfrm_lookup(sock_net(sk), &dst, &fl, sk, XFRM_LOOKUP_WAIT);
+	if (err < 0) {
 		if (err == -EREMOTE)
 			err = ip6_dst_blackhole(sk, &dst, &fl);
 		if (err < 0)
@@ -795,11 +1110,8 @@ do_udp_sendmsg:
 			hlimit = ip6_dst_hoplimit(dst);
 	}
 
-	if (tclass < 0) {
+	if (tclass < 0)
 		tclass = np->tclass;
-		if (tclass < 0)
-			tclass = 0;
-	}
 
 	if (msg->msg_flags&MSG_CONFIRM)
 		goto do_confirm;
@@ -845,12 +1157,14 @@ do_append_data:
 		} else {
 			dst_release(dst);
 		}
+		dst = NULL;
 	}
 
 	if (err > 0)
 		err = np->recverr ? net_xmit_errno(err) : 0;
 	release_sock(sk);
 out:
+	dst_release(dst);
 	fl6_sock_release(flowlabel);
 	if (!err)
 		return len;
@@ -862,7 +1176,8 @@ out:
 	 * seems like overkill.
 	 */
 	if (err == -ENOBUFS || test_bit(SOCK_NOSPACE, &sk->sk_socket->flags)) {
-		UDP6_INC_STATS_USER(UDP_MIB_SNDBUFERRORS, is_udplite);
+		UDP6_INC_STATS_USER(sock_net(sk),
+				UDP_MIB_SNDBUFERRORS, is_udplite);
 	}
 	return err;
 
@@ -874,22 +1189,20 @@ do_confirm:
 	goto out;
 }
 
-int udpv6_destroy_sock(struct sock *sk)
+void udpv6_destroy_sock(struct sock *sk)
 {
 	lock_sock(sk);
 	udp_v6_flush_pending_frames(sk);
 	release_sock(sk);
 
 	inet6_destroy_sock(sk);
-
-	return 0;
 }
 
 /*
  *	Socket option code for UDP
  */
 int udpv6_setsockopt(struct sock *sk, int level, int optname,
-		     char __user *optval, int optlen)
+		     char __user *optval, unsigned int optlen)
 {
 	if (level == SOL_UDP  ||  level == SOL_UDPLITE)
 		return udp_lib_setsockopt(sk, level, optname, optval, optlen,
@@ -899,7 +1212,7 @@ int udpv6_setsockopt(struct sock *sk, int level, int optname,
 
 #ifdef CONFIG_COMPAT
 int compat_udpv6_setsockopt(struct sock *sk, int level, int optname,
-			    char __user *optval, int optlen)
+			    char __user *optval, unsigned int optlen)
 {
 	if (level == SOL_UDP  ||  level == SOL_UDPLITE)
 		return udp_lib_setsockopt(sk, level, optname, optval, optlen,
@@ -926,9 +1239,102 @@ int compat_udpv6_getsockopt(struct sock *sk, int level, int optname,
 }
 #endif
 
-static struct inet6_protocol udpv6_protocol = {
+static int udp6_ufo_send_check(struct sk_buff *skb)
+{
+	struct ipv6hdr *ipv6h;
+	struct udphdr *uh;
+
+	if (!pskb_may_pull(skb, sizeof(*uh)))
+		return -EINVAL;
+
+	ipv6h = ipv6_hdr(skb);
+	uh = udp_hdr(skb);
+
+	uh->check = ~csum_ipv6_magic(&ipv6h->saddr, &ipv6h->daddr, skb->len,
+				     IPPROTO_UDP, 0);
+	skb->csum_start = skb_transport_header(skb) - skb->head;
+	skb->csum_offset = offsetof(struct udphdr, check);
+	skb->ip_summed = CHECKSUM_PARTIAL;
+	return 0;
+}
+
+static struct sk_buff *udp6_ufo_fragment(struct sk_buff *skb, int features)
+{
+	struct sk_buff *segs = ERR_PTR(-EINVAL);
+	unsigned int mss;
+	unsigned int unfrag_ip6hlen, unfrag_len;
+	struct frag_hdr *fptr;
+	u8 *mac_start, *prevhdr;
+	u8 nexthdr;
+	u8 frag_hdr_sz = sizeof(struct frag_hdr);
+	int offset;
+	__wsum csum;
+
+	mss = skb_shinfo(skb)->gso_size;
+	if (unlikely(skb->len <= mss))
+		goto out;
+
+	if (skb_gso_ok(skb, features | NETIF_F_GSO_ROBUST)) {
+		/* Packet is from an untrusted source, reset gso_segs. */
+		int type = skb_shinfo(skb)->gso_type;
+
+		if (unlikely(type & ~(SKB_GSO_UDP | SKB_GSO_DODGY) ||
+			     !(type & (SKB_GSO_UDP))))
+			goto out;
+
+		skb_shinfo(skb)->gso_segs = DIV_ROUND_UP(skb->len, mss);
+
+		segs = NULL;
+		goto out;
+	}
+
+	/* Do software UFO. Complete and fill in the UDP checksum as HW cannot
+	 * do checksum of UDP packets sent as multiple IP fragments.
+	 */
+	offset = skb->csum_start - skb_headroom(skb);
+	csum = skb_checksum(skb, offset, skb->len- offset, 0);
+	offset += skb->csum_offset;
+	*(__sum16 *)(skb->data + offset) = csum_fold(csum);
+	skb->ip_summed = CHECKSUM_NONE;
+
+	/* Check if there is enough headroom to insert fragment header. */
+	if ((skb_headroom(skb) < frag_hdr_sz) &&
+	    pskb_expand_head(skb, frag_hdr_sz, 0, GFP_ATOMIC))
+		goto out;
+
+	/* Find the unfragmentable header and shift it left by frag_hdr_sz
+	 * bytes to insert fragment header.
+	 */
+	unfrag_ip6hlen = ip6_find_1stfragopt(skb, &prevhdr);
+	nexthdr = *prevhdr;
+	*prevhdr = NEXTHDR_FRAGMENT;
+	unfrag_len = skb_network_header(skb) - skb_mac_header(skb) +
+		     unfrag_ip6hlen;
+	mac_start = skb_mac_header(skb);
+	memmove(mac_start-frag_hdr_sz, mac_start, unfrag_len);
+
+	skb->mac_header -= frag_hdr_sz;
+	skb->network_header -= frag_hdr_sz;
+
+	fptr = (struct frag_hdr *)(skb_network_header(skb) + unfrag_ip6hlen);
+	fptr->nexthdr = nexthdr;
+	fptr->reserved = 0;
+	ipv6_select_ident(fptr);
+
+	/* Fragment the skb. ipv6 header and the remaining fields of the
+	 * fragment header are updated in ipv6_gso_segment()
+	 */
+	segs = skb_segment(skb, features);
+
+out:
+	return segs;
+}
+
+static const struct inet6_protocol udpv6_protocol = {
 	.handler	=	udpv6_rcv,
 	.err_handler	=	udpv6_err,
+	.gso_send_check =	udp6_ufo_send_check,
+	.gso_segment	=	udp6_ufo_fragment,
 	.flags		=	INET6_PROTO_NOPOLICY|INET6_PROTO_FINAL,
 };
 
@@ -944,23 +1350,24 @@ static void udp6_sock_seq_show(struct seq_file *seq, struct sock *sp, int bucket
 
 	dest  = &np->daddr;
 	src   = &np->rcv_saddr;
-	destp = ntohs(inet->dport);
-	srcp  = ntohs(inet->sport);
+	destp = ntohs(inet->inet_dport);
+	srcp  = ntohs(inet->inet_sport);
 	seq_printf(seq,
-		   "%4d: %08X%08X%08X%08X:%04X %08X%08X%08X%08X:%04X "
-		   "%02X %08X:%08X %02X:%08lX %08X %5d %8d %lu %d %p\n",
+		   "%5d: %08X%08X%08X%08X:%04X %08X%08X%08X%08X:%04X "
+		   "%02X %08X:%08X %02X:%08lX %08X %5d %8d %lu %d %p %d\n",
 		   bucket,
 		   src->s6_addr32[0], src->s6_addr32[1],
 		   src->s6_addr32[2], src->s6_addr32[3], srcp,
 		   dest->s6_addr32[0], dest->s6_addr32[1],
 		   dest->s6_addr32[2], dest->s6_addr32[3], destp,
 		   sp->sk_state,
-		   atomic_read(&sp->sk_wmem_alloc),
-		   atomic_read(&sp->sk_rmem_alloc),
+		   sk_wmem_alloc_get(sp),
+		   sk_rmem_alloc_get(sp),
 		   0, 0L, 0,
 		   sock_i_uid(sp), 0,
 		   sock_i_ino(sp),
-		   atomic_read(&sp->sk_refcnt), sp);
+		   atomic_read(&sp->sk_refcnt), sp,
+		   atomic_read(&sp->sk_drops));
 }
 
 int udp6_seq_show(struct seq_file *seq, void *v)
@@ -971,25 +1378,25 @@ int udp6_seq_show(struct seq_file *seq, void *v)
 			   "local_address                         "
 			   "remote_address                        "
 			   "st tx_queue rx_queue tr tm->when retrnsmt"
-			   "   uid  timeout inode\n");
+			   "   uid  timeout inode ref pointer drops\n");
 	else
 		udp6_sock_seq_show(seq, v, ((struct udp_iter_state *)seq->private)->bucket);
 	return 0;
 }
 
-static struct file_operations udp6_seq_fops;
 static struct udp_seq_afinfo udp6_seq_afinfo = {
-	.owner		= THIS_MODULE,
 	.name		= "udp6",
 	.family		= AF_INET6,
-	.hashtable	= udp_hash,
-	.seq_fops	= &udp6_seq_fops,
+	.udp_table	= &udp_table,
+	.seq_fops	= {
+		.owner	=	THIS_MODULE,
+	},
 	.seq_ops	= {
 		.show		= udp6_seq_show,
 	},
 };
 
-int udp6_proc_init(struct net *net)
+int __net_init udp6_proc_init(struct net *net)
 {
 	return udp_proc_register(net, &udp6_seq_afinfo);
 }
@@ -1022,7 +1429,8 @@ struct proto udpv6_prot = {
 	.sysctl_wmem	   = &sysctl_udp_wmem_min,
 	.sysctl_rmem	   = &sysctl_udp_rmem_min,
 	.obj_size	   = sizeof(struct udp6_sock),
-	.h.udp_hash	   = udp_hash,
+	.slab_flags	   = SLAB_DESTROY_BY_RCU,
+	.h.udp_table	   = &udp_table,
 #ifdef CONFIG_COMPAT
 	.compat_setsockopt = compat_udpv6_setsockopt,
 	.compat_getsockopt = compat_udpv6_getsockopt,
@@ -1034,7 +1442,6 @@ static struct inet_protosw udpv6_protosw = {
 	.protocol =  IPPROTO_UDP,
 	.prot =      &udpv6_prot,
 	.ops =       &inet6_dgram_ops,
-	.capability =-1,
 	.no_check =  UDP_CSUM_DEFAULT,
 	.flags =     INET_PROTOSW_PERMANENT,
 };