Merge branch 'master' of master.kernel.org:/pub/scm/linux/kernel/git/davem/net-2.6

* 'master' of master.kernel.org:/pub/scm/linux/kernel/git/davem/net-2.6: (51 commits)
  [IPV6]: Fix again the fl6_sock_lookup() fixed locking
  [NETFILTER]: nf_conntrack_tcp: fix connection reopening fix
  [IPV6]: Fix race in ipv6_flowlabel_opt() when inserting two labels
  [IPV6]: Lost locking in fl6_sock_lookup
  [IPV6]: Lost locking when inserting a flowlabel in ipv6_fl_list
  [NETFILTER]: xt_sctp: fix mistake to pass a pointer where array is required
  [NET]: Fix OOPS due to missing check in dev_parse_header().
  [TCP]: Remove lost_retrans zero seqno special cases
  [NET]: fix carrier-on bug?
  [NET]: Fix uninitialised variable in ip_frag_reasm()
  [IPSEC]: Rename mode to outer_mode and add inner_mode
  [IPSEC]: Disallow combinations of RO and AH/ESP/IPCOMP
  [IPSEC]: Use the top IPv4 route's peer instead of the bottom
  [IPSEC]: Store afinfo pointer in xfrm_mode
  [IPSEC]: Add missing BEET checks
  [IPSEC]: Move type and mode map into xfrm_state.c
  [IPSEC]: Fix length check in xfrm_parse_spi
  [IPSEC]: Move ip_summed zapping out of xfrm6_rcv_spi
  [IPSEC]: Get nexthdr from caller in xfrm6_rcv_spi
  [IPSEC]: Move tunnel parsing for IPv4 out of xfrm4_input
  ...

43 files changed, 661 insertions, 806 deletions

diff --git a/net/atm/br2684.c b/net/atm/br2684.c
index c742d37bfb9..ba6428f204f 100644
--- a/net/atm/br2684.c
+++ b/net/atm/br2684.c
@@ -24,16 +24,6 @@ Author: Marcell GAL, 2000, XDSL Ltd, Hungary
 
 #include "common.h"
 
-/*
- * Define this to use a version of the code which interacts with the higher
- * layers in a more intellegent way, by always reserving enough space for
- * our header at the begining of the packet.  However, there may still be
- * some problems with programs like tcpdump.  In 2.5 we'll sort out what
- * we need to do to get this perfect.  For now we just will copy the packet
- * if we need space for the header
- */
-/* #define FASTER_VERSION */
-
 #ifdef SKB_DEBUG
 static void skb_debug(const struct sk_buff *skb)
 {
@@ -69,9 +59,7 @@ struct br2684_vcc {
 #ifdef CONFIG_ATM_BR2684_IPFILTER
 	struct br2684_filter filter;
 #endif /* CONFIG_ATM_BR2684_IPFILTER */
-#ifndef FASTER_VERSION
 	unsigned copies_needed, copies_failed;
-#endif /* FASTER_VERSION */
 };
 
 struct br2684_dev {
@@ -147,13 +135,6 @@ static int br2684_xmit_vcc(struct sk_buff *skb, struct br2684_dev *brdev,
 	struct br2684_vcc *brvcc)
 {
 	struct atm_vcc *atmvcc;
-#ifdef FASTER_VERSION
-	if (brvcc->encaps == e_llc)
-		memcpy(skb_push(skb, 8), llc_oui_pid_pad, 8);
-	/* last 2 bytes of llc_oui_pid_pad are managed by header routines;
-	   yes, you got it: 8 + 2 = sizeof(llc_oui_pid_pad)
-	 */
-#else
 	int minheadroom = (brvcc->encaps == e_llc) ? 10 : 2;
 	if (skb_headroom(skb) < minheadroom) {
 		struct sk_buff *skb2 = skb_realloc_headroom(skb, minheadroom);
@@ -170,7 +151,6 @@ static int br2684_xmit_vcc(struct sk_buff *skb, struct br2684_dev *brdev,
 		skb_copy_to_linear_data(skb, llc_oui_pid_pad, 10);
 	else
 		memset(skb->data, 0, 2);
-#endif /* FASTER_VERSION */
 	skb_debug(skb);
 
 	ATM_SKB(skb)->vcc = atmvcc = brvcc->atmvcc;
@@ -237,87 +217,6 @@ static struct net_device_stats *br2684_get_stats(struct net_device *dev)
 	return &BRPRIV(dev)->stats;
 }
 
-#ifdef FASTER_VERSION
-/*
- * These mirror eth_header and eth_header_cache.  They are not usually
- * exported for use in modules, so we grab them from net_device
- * after ether_setup() is done with it.  Bit of a hack.
- */
-static int (*my_eth_header)(struct sk_buff *, struct net_device *,
-	unsigned short, void *, void *, unsigned);
-static int (*my_eth_header_cache)(struct neighbour *, struct hh_cache *);
-
-static int
-br2684_header(struct sk_buff *skb, struct net_device *dev,
-	      unsigned short type, void *daddr, void *saddr, unsigned len)
-{
-	u16 *pad_before_eth;
-	int t = my_eth_header(skb, dev, type, daddr, saddr, len);
-	if (t > 0) {
-		pad_before_eth = (u16 *) skb_push(skb, 2);
-		*pad_before_eth = 0;
-		return dev->hard_header_len;	/* or return 16; ? */
-	} else
-		return t;
-}
-
-static int
-br2684_header_cache(struct neighbour *neigh, struct hh_cache *hh)
-{
-/* hh_data is 16 bytes long. if encaps is ether-llc we need 24, so
-xmit will add the additional header part in that case */
-	u16 *pad_before_eth = (u16 *)(hh->hh_data);
-	int t = my_eth_header_cache(neigh, hh);
-	DPRINTK("br2684_header_cache, neigh=%p, hh_cache=%p\n", neigh, hh);
-	if (t < 0)
-		return t;
-	else {
-		*pad_before_eth = 0;
-		hh->hh_len = PADLEN + ETH_HLEN;
-	}
-	return 0;
-}
-
-/*
- * This is similar to eth_type_trans, which cannot be used because of
- * our dev->hard_header_len
- */
-static inline __be16 br_type_trans(struct sk_buff *skb, struct net_device *dev)
-{
-	struct ethhdr *eth;
-	unsigned char *rawp;
-	eth = eth_hdr(skb);
-
-	if (is_multicast_ether_addr(eth->h_dest)) {
-		if (!compare_ether_addr(eth->h_dest, dev->broadcast))
-			skb->pkt_type = PACKET_BROADCAST;
-		else
-			skb->pkt_type = PACKET_MULTICAST;
-	}
-
-	else if (compare_ether_addr(eth->h_dest, dev->dev_addr))
-		skb->pkt_type = PACKET_OTHERHOST;
-
-	if (ntohs(eth->h_proto) >= 1536)
-		return eth->h_proto;
-
-	rawp = skb->data;
-
-	/*
-	 * This is a magic hack to spot IPX packets. Older Novell breaks
-	 * the protocol design and runs IPX over 802.3 without an 802.2 LLC
-	 * layer. We look for FFFF which isn't a used 802.2 SSAP/DSAP. This
-	 * won't work for fault tolerant netware but does for the rest.
-	 */
-	if (*(unsigned short *) rawp == 0xFFFF)
-		return htons(ETH_P_802_3);
-
-	/*
-	 * Real 802.2 LLC
-	 */
-	return htons(ETH_P_802_2);
-}
-#endif /* FASTER_VERSION */
 
 /*
  * We remember when the MAC gets set, so we don't override it later with
@@ -448,17 +347,8 @@ static void br2684_push(struct atm_vcc *atmvcc, struct sk_buff *skb)
 		return;
 	}
 
-#ifdef FASTER_VERSION
-	/* FIXME: tcpdump shows that pointer to mac header is 2 bytes earlier,
-	   than should be. What else should I set? */
-	skb_pull(skb, plen);
-	skb_set_mac_header(skb, -ETH_HLEN);
-	skb->pkt_type = PACKET_HOST;
-	skb->protocol = br_type_trans(skb, net_dev);
-#else
 	skb_pull(skb, plen - ETH_HLEN);
 	skb->protocol = eth_type_trans(skb, net_dev);
-#endif /* FASTER_VERSION */
 #ifdef CONFIG_ATM_BR2684_IPFILTER
 	if (unlikely(packet_fails_filter(skb->protocol, brvcc, skb))) {
 		brdev->stats.rx_dropped++;
@@ -584,13 +474,6 @@ static void br2684_setup(struct net_device *netdev)
 	ether_setup(netdev);
 	brdev->net_dev = netdev;
 
-#ifdef FASTER_VERSION
-	my_eth_header = netdev->hard_header;
-	netdev->hard_header = br2684_header;
-	my_eth_header_cache = netdev->hard_header_cache;
-	netdev->hard_header_cache = br2684_header_cache;
-	netdev->hard_header_len = sizeof(llc_oui_pid_pad) + ETH_HLEN;	/* 10 + 14 */
-#endif
 	my_eth_mac_addr = netdev->set_mac_address;
 	netdev->set_mac_address = br2684_mac_addr;
 	netdev->hard_start_xmit = br2684_start_xmit;
@@ -719,16 +602,12 @@ static int br2684_seq_show(struct seq_file *seq, void *v)
 
 	list_for_each_entry(brvcc, &brdev->brvccs, brvccs) {
 		seq_printf(seq, "  vcc %d.%d.%d: encaps=%s"
-#ifndef FASTER_VERSION
 				    ", failed copies %u/%u"
-#endif /* FASTER_VERSION */
 				    "\n", brvcc->atmvcc->dev->number,
 				    brvcc->atmvcc->vpi, brvcc->atmvcc->vci,
 				    (brvcc->encaps == e_llc) ? "LLC" : "VC"
-#ifndef FASTER_VERSION
 				    , brvcc->copies_failed
 				    , brvcc->copies_needed
-#endif /* FASTER_VERSION */
 				    );
 #ifdef CONFIG_ATM_BR2684_IPFILTER
 #define b1(var, byte)	((u8 *) &brvcc->filter.var)[byte]
diff --git a/net/core/filter.c b/net/core/filter.c
index bd903aaf7aa..1f0068eae50 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -387,6 +387,25 @@ int sk_chk_filter(struct sock_filter *filter, int flen)
 }
 
 /**
+ * 	sk_filter_rcu_release: Release a socket filter by rcu_head
+ *	@rcu: rcu_head that contains the sk_filter to free
+ */
+static void sk_filter_rcu_release(struct rcu_head *rcu)
+{
+	struct sk_filter *fp = container_of(rcu, struct sk_filter, rcu);
+
+	sk_filter_release(fp);
+}
+
+static void sk_filter_delayed_uncharge(struct sock *sk, struct sk_filter *fp)
+{
+	unsigned int size = sk_filter_len(fp);
+
+	atomic_sub(size, &sk->sk_omem_alloc);
+	call_rcu_bh(&fp->rcu, sk_filter_rcu_release);
+}
+
+/**
  *	sk_attach_filter - attach a socket filter
  *	@fprog: the filter program
  *	@sk: the socket to use
@@ -398,7 +417,7 @@ int sk_chk_filter(struct sock_filter *filter, int flen)
  */
 int sk_attach_filter(struct sock_fprog *fprog, struct sock *sk)
 {
-	struct sk_filter *fp;
+	struct sk_filter *fp, *old_fp;
 	unsigned int fsize = sizeof(struct sock_filter) * fprog->len;
 	int err;
 
@@ -418,19 +437,34 @@ int sk_attach_filter(struct sock_fprog *fprog, struct sock *sk)
 	fp->len = fprog->len;
 
 	err = sk_chk_filter(fp->insns, fp->len);
-	if (!err) {
-		struct sk_filter *old_fp;
-
-		rcu_read_lock_bh();
-		old_fp = rcu_dereference(sk->sk_filter);
-		rcu_assign_pointer(sk->sk_filter, fp);
-		rcu_read_unlock_bh();
-		fp = old_fp;
+	if (err) {
+		sk_filter_uncharge(sk, fp);
+		return err;
 	}
 
-	if (fp)
-		sk_filter_release(sk, fp);
-	return err;
+	rcu_read_lock_bh();
+	old_fp = rcu_dereference(sk->sk_filter);
+	rcu_assign_pointer(sk->sk_filter, fp);
+	rcu_read_unlock_bh();
+
+	sk_filter_delayed_uncharge(sk, old_fp);
+	return 0;
+}
+
+int sk_detach_filter(struct sock *sk)
+{
+	int ret = -ENOENT;
+	struct sk_filter *filter;
+
+	rcu_read_lock_bh();
+	filter = rcu_dereference(sk->sk_filter);
+	if (filter) {
+		rcu_assign_pointer(sk->sk_filter, NULL);
+		sk_filter_delayed_uncharge(sk, filter);
+		ret = 0;
+	}
+	rcu_read_unlock_bh();
+	return ret;
 }
 
 EXPORT_SYMBOL(sk_chk_filter);
diff --git a/net/core/pktgen.c b/net/core/pktgen.c
index 2100c734b10..8cae60c5338 100644
--- a/net/core/pktgen.c
+++ b/net/core/pktgen.c
@@ -2454,7 +2454,7 @@ static int pktgen_output_ipsec(struct sk_buff *skb, struct pktgen_dev *pkt_dev)
 	spin_lock(&x->lock);
 	iph = ip_hdr(skb);
 
-	err = x->mode->output(x, skb);
+	err = x->outer_mode->output(x, skb);
 	if (err)
 		goto error;
 	err = x->type->output(x, skb);
diff --git a/net/core/sock.c b/net/core/sock.c
index d45ecdccc6a..d292b4113d6 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -428,7 +428,6 @@ int sock_setsockopt(struct socket *sock, int level, int optname,
 		    char __user *optval, int optlen)
 {
 	struct sock *sk=sock->sk;
-	struct sk_filter *filter;
 	int val;
 	int valbool;
 	struct linger ling;
@@ -652,16 +651,7 @@ set_rcvbuf:
 		break;
 
 	case SO_DETACH_FILTER:
-		rcu_read_lock_bh();
-		filter = rcu_dereference(sk->sk_filter);
-		if (filter) {
-			rcu_assign_pointer(sk->sk_filter, NULL);
-			sk_filter_release(sk, filter);
-			rcu_read_unlock_bh();
-			break;
-		}
-		rcu_read_unlock_bh();
-		ret = -ENONET;
+		ret = sk_detach_filter(sk);
 		break;
 
 	case SO_PASSSEC:
@@ -925,7 +915,7 @@ void sk_free(struct sock *sk)
 
 	filter = rcu_dereference(sk->sk_filter);
 	if (filter) {
-		sk_filter_release(sk, filter);
+		sk_filter_uncharge(sk, filter);
 		rcu_assign_pointer(sk->sk_filter, NULL);
 	}
 
diff --git a/net/dccp/input.c b/net/dccp/input.c
index 19d7e1dbd87..3560a2a875a 100644
--- a/net/dccp/input.c
+++ b/net/dccp/input.c
@@ -19,6 +19,9 @@
 #include "ccid.h"
 #include "dccp.h"
 
+/* rate-limit for syncs in reply to sequence-invalid packets; RFC 4340, 7.5.4 */
+int sysctl_dccp_sync_ratelimit	__read_mostly = HZ / 8;
+
 static void dccp_fin(struct sock *sk, struct sk_buff *skb)
 {
 	sk->sk_shutdown |= RCV_SHUTDOWN;
diff --git a/net/dccp/sysctl.c b/net/dccp/sysctl.c
index 9364b2fb4db..c62c05039f6 100644
--- a/net/dccp/sysctl.c
+++ b/net/dccp/sysctl.c
@@ -18,9 +18,6 @@
 #error This file should not be compiled without CONFIG_SYSCTL defined
 #endif
 
-/* rate-limit for syncs in reply to sequence-invalid packets; RFC 4340, 7.5.4 */
-int sysctl_dccp_sync_ratelimit	__read_mostly = HZ / 8;
-
 static struct ctl_table dccp_default_table[] = {
 	{
 		.procname	= "seq_window",
diff --git a/net/ieee80211/ieee80211_crypt_tkip.c b/net/ieee80211/ieee80211_crypt_tkip.c
index 6cc54eeca3e..72e6ab66834 100644
--- a/net/ieee80211/ieee80211_crypt_tkip.c
+++ b/net/ieee80211/ieee80211_crypt_tkip.c
@@ -586,7 +586,7 @@ static void michael_mic_hdr(struct sk_buff *skb, u8 * hdr)
 	if (stype & IEEE80211_STYPE_QOS_DATA) {
 		const struct ieee80211_hdr_3addrqos *qoshdr =
 			(struct ieee80211_hdr_3addrqos *)skb->data;
-		hdr[12] = qoshdr->qos_ctl & cpu_to_le16(IEEE80211_QCTL_TID);
+		hdr[12] = le16_to_cpu(qoshdr->qos_ctl) & IEEE80211_QCTL_TID;
 	} else
 		hdr[12] = 0;		/* priority */
 
diff --git a/net/ipv4/inet_fragment.c b/net/ipv4/inet_fragment.c
index 484cf512858..e15e04fc666 100644
--- a/net/ipv4/inet_fragment.c
+++ b/net/ipv4/inet_fragment.c
@@ -136,7 +136,9 @@ void inet_frag_destroy(struct inet_frag_queue *q, struct inet_frags *f,
 		*work -= f->qsize;
 	atomic_sub(f->qsize, &f->mem);
 
-	f->destructor(q);
+	if (f->destructor)
+		f->destructor(q);
+	kfree(q);
 
 }
 EXPORT_SYMBOL(inet_frag_destroy);
@@ -172,3 +174,88 @@ int inet_frag_evictor(struct inet_frags *f)
 	return evicted;
 }
 EXPORT_SYMBOL(inet_frag_evictor);
+
+static struct inet_frag_queue *inet_frag_intern(struct inet_frag_queue *qp_in,
+		struct inet_frags *f, unsigned int hash, void *arg)
+{
+	struct inet_frag_queue *qp;
+#ifdef CONFIG_SMP
+	struct hlist_node *n;
+#endif
+
+	write_lock(&f->lock);
+#ifdef CONFIG_SMP
+	/* With SMP race we have to recheck hash table, because
+	 * such entry could be created on other cpu, while we
+	 * promoted read lock to write lock.
+	 */
+	hlist_for_each_entry(qp, n, &f->hash[hash], list) {
+		if (f->match(qp, arg)) {
+			atomic_inc(&qp->refcnt);
+			write_unlock(&f->lock);
+			qp_in->last_in |= COMPLETE;
+			inet_frag_put(qp_in, f);
+			return qp;
+		}
+	}
+#endif
+	qp = qp_in;
+	if (!mod_timer(&qp->timer, jiffies + f->ctl->timeout))
+		atomic_inc(&qp->refcnt);
+
+	atomic_inc(&qp->refcnt);
+	hlist_add_head(&qp->list, &f->hash[hash]);
+	list_add_tail(&qp->lru_list, &f->lru_list);
+	f->nqueues++;
+	write_unlock(&f->lock);
+	return qp;
+}
+
+static struct inet_frag_queue *inet_frag_alloc(struct inet_frags *f, void *arg)
+{
+	struct inet_frag_queue *q;
+
+	q = kzalloc(f->qsize, GFP_ATOMIC);
+	if (q == NULL)
+		return NULL;
+
+	f->constructor(q, arg);
+	atomic_add(f->qsize, &f->mem);
+	setup_timer(&q->timer, f->frag_expire, (unsigned long)q);
+	spin_lock_init(&q->lock);
+	atomic_set(&q->refcnt, 1);
+
+	return q;
+}
+
+static struct inet_frag_queue *inet_frag_create(struct inet_frags *f,
+		void *arg, unsigned int hash)
+{
+	struct inet_frag_queue *q;
+
+	q = inet_frag_alloc(f, arg);
+	if (q == NULL)
+		return NULL;
+
+	return inet_frag_intern(q, f, hash, arg);
+}
+
+struct inet_frag_queue *inet_frag_find(struct inet_frags *f, void *key,
+		unsigned int hash)
+{
+	struct inet_frag_queue *q;
+	struct hlist_node *n;
+
+	read_lock(&f->lock);
+	hlist_for_each_entry(q, n, &f->hash[hash], list) {
+		if (f->match(q, key)) {
+			atomic_inc(&q->refcnt);
+			read_unlock(&f->lock);
+			return q;
+		}
+	}
+	read_unlock(&f->lock);
+
+	return inet_frag_create(f, key, hash);
+}
+EXPORT_SYMBOL(inet_frag_find);
diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c
index 443b3f89192..2143bf30597 100644
--- a/net/ipv4/ip_fragment.c
+++ b/net/ipv4/ip_fragment.c
@@ -108,6 +108,11 @@ int ip_frag_mem(void)
 static int ip_frag_reasm(struct ipq *qp, struct sk_buff *prev,
 			 struct net_device *dev);
 
+struct ip4_create_arg {
+	struct iphdr *iph;
+	u32 user;
+};
+
 static unsigned int ipqhashfn(__be16 id, __be32 saddr, __be32 daddr, u8 prot)
 {
 	return jhash_3words((__force u32)id << 16 | prot,
@@ -123,6 +128,19 @@ static unsigned int ip4_hashfn(struct inet_frag_queue *q)
 	return ipqhashfn(ipq->id, ipq->saddr, ipq->daddr, ipq->protocol);
 }
 
+static int ip4_frag_match(struct inet_frag_queue *q, void *a)
+{
+	struct ipq *qp;
+	struct ip4_create_arg *arg = a;
+
+	qp = container_of(q, struct ipq, q);
+	return (qp->id == arg->iph->id &&
+			qp->saddr == arg->iph->saddr &&
+			qp->daddr == arg->iph->daddr &&
+			qp->protocol == arg->iph->protocol &&
+			qp->user == arg->user);
+}
+
 /* Memory Tracking Functions. */
 static __inline__ void frag_kfree_skb(struct sk_buff *skb, int *work)
 {
@@ -132,6 +150,20 @@ static __inline__ void frag_kfree_skb(struct sk_buff *skb, int *work)
 	kfree_skb(skb);
 }
 
+static void ip4_frag_init(struct inet_frag_queue *q, void *a)
+{
+	struct ipq *qp = container_of(q, struct ipq, q);
+	struct ip4_create_arg *arg = a;
+
+	qp->protocol = arg->iph->protocol;
+	qp->id = arg->iph->id;
+	qp->saddr = arg->iph->saddr;
+	qp->daddr = arg->iph->daddr;
+	qp->user = arg->user;
+	qp->peer = sysctl_ipfrag_max_dist ?
+		inet_getpeer(arg->iph->saddr, 1) : NULL;
+}
+
 static __inline__ void ip4_frag_free(struct inet_frag_queue *q)
 {
 	struct ipq *qp;
@@ -139,17 +171,6 @@ static __inline__ void ip4_frag_free(struct inet_frag_queue *q)
 	qp = container_of(q, struct ipq, q);
 	if (qp->peer)
 		inet_putpeer(qp->peer);
-	kfree(qp);
-}
-
-static __inline__ struct ipq *frag_alloc_queue(void)
-{
-	struct ipq *qp = kzalloc(sizeof(struct ipq), GFP_ATOMIC);
-
-	if (!qp)
-		return NULL;
-	atomic_add(sizeof(struct ipq), &ip4_frags.mem);
-	return qp;
 }
 
 
@@ -185,7 +206,9 @@ static void ip_evictor(void)
  */
 static void ip_expire(unsigned long arg)
 {
-	struct ipq *qp = (struct ipq *) arg;
+	struct ipq *qp;
+
+	qp = container_of((struct inet_frag_queue *) arg, struct ipq, q);
 
 	spin_lock(&qp->q.lock);
 
@@ -210,112 +233,30 @@ out:
 	ipq_put(qp);
 }
 
-/* Creation primitives. */
-
-static struct ipq *ip_frag_intern(struct ipq *qp_in)
+/* Find the correct entry in the "incomplete datagrams" queue for
+ * this IP datagram, and create new one, if nothing is found.
+ */
+static inline struct ipq *ip_find(struct iphdr *iph, u32 user)
 {
-	struct ipq *qp;
-#ifdef CONFIG_SMP
-	struct hlist_node *n;
-#endif
+	struct inet_frag_queue *q;
+	struct ip4_create_arg arg;
 	unsigned int hash;
 
-	write_lock(&ip4_frags.lock);
-	hash = ipqhashfn(qp_in->id, qp_in->saddr, qp_in->daddr,
-			 qp_in->protocol);
-#ifdef CONFIG_SMP
-	/* With SMP race we have to recheck hash table, because
-	 * such entry could be created on other cpu, while we
-	 * promoted read lock to write lock.
-	 */
-	hlist_for_each_entry(qp, n, &ip4_frags.hash[hash], q.list) {
-		if (qp->id == qp_in->id		&&
-		    qp->saddr == qp_in->saddr	&&
-		    qp->daddr == qp_in->daddr	&&
-		    qp->protocol == qp_in->protocol &&
-		    qp->user == qp_in->user) {
-			atomic_inc(&qp->q.refcnt);
-			write_unlock(&ip4_frags.lock);
-			qp_in->q.last_in |= COMPLETE;
-			ipq_put(qp_in);
-			return qp;
-		}
-	}
-#endif
-	qp = qp_in;
-
-	if (!mod_timer(&qp->q.timer, jiffies + ip4_frags_ctl.timeout))
-		atomic_inc(&qp->q.refcnt);
+	arg.iph = iph;
+	arg.user = user;
+	hash = ipqhashfn(iph->id, iph->saddr, iph->daddr, iph->protocol);
 
-	atomic_inc(&qp->q.refcnt);
-	hlist_add_head(&qp->q.list, &ip4_frags.hash[hash]);
-	INIT_LIST_HEAD(&qp->q.lru_list);
-	list_add_tail(&qp->q.lru_list, &ip4_frags.lru_list);
-	ip4_frags.nqueues++;
-	write_unlock(&ip4_frags.lock);
-	return qp;
-}
-
-/* Add an entry to the 'ipq' queue for a newly received IP datagram. */
-static struct ipq *ip_frag_create(struct iphdr *iph, u32 user)
-{
-	struct ipq *qp;
-
-	if ((qp = frag_alloc_queue()) == NULL)
+	q = inet_frag_find(&ip4_frags, &arg, hash);
+	if (q == NULL)
 		goto out_nomem;
 
-	qp->protocol = iph->protocol;
-	qp->id = iph->id;
-	qp->saddr = iph->saddr;
-	qp->daddr = iph->daddr;
-	qp->user = user;
-	qp->peer = sysctl_ipfrag_max_dist ? inet_getpeer(iph->saddr, 1) : NULL;
-
-	/* Initialize a timer for this entry. */
-	init_timer(&qp->q.timer);
-	qp->q.timer.data = (unsigned long) qp;	/* pointer to queue	*/
-	qp->q.timer.function = ip_expire;		/* expire function	*/
-	spin_lock_init(&qp->q.lock);
-	atomic_set(&qp->q.refcnt, 1);
-
-	return ip_frag_intern(qp);
+	return container_of(q, struct ipq, q);
 
 out_nomem:
 	LIMIT_NETDEBUG(KERN_ERR "ip_frag_create: no memory left !\n");
 	return NULL;
 }
 
-/* Find the correct entry in the "incomplete datagrams" queue for
- * this IP datagram, and create new one, if nothing is found.
- */
-static inline struct ipq *ip_find(struct iphdr *iph, u32 user)
-{
-	__be16 id = iph->id;
-	__be32 saddr = iph->saddr;
-	__be32 daddr = iph->daddr;
-	__u8 protocol = iph->protocol;
-	unsigned int hash;
-	struct ipq *qp;
-	struct hlist_node *n;
-
-	read_lock(&ip4_frags.lock);
-	hash = ipqhashfn(id, saddr, daddr, protocol);
-	hlist_for_each_entry(qp, n, &ip4_frags.hash[hash], q.list) {
-		if (qp->id == id		&&
-		    qp->saddr == saddr	&&
-		    qp->daddr == daddr	&&
-		    qp->protocol == protocol &&
-		    qp->user == user) {
-			atomic_inc(&qp->q.refcnt);
-			read_unlock(&ip4_frags.lock);
-			return qp;
-		}
-	}
-	read_unlock(&ip4_frags.lock);
-
-	return ip_frag_create(iph, user);
-}
-
 /* Is the fragment too far ahead to be part of ipq? */
 static inline int ip_frag_too_far(struct ipq *qp)
 {
@@ -545,7 +486,6 @@ static int ip_frag_reasm(struct ipq *qp, struct sk_buff *prev,
 	if (prev) {
 		head = prev->next;
 		fp = skb_clone(head, GFP_ATOMIC);
-
 		if (!fp)
 			goto out_nomem;
 
@@ -571,7 +511,6 @@ static int ip_frag_reasm(struct ipq *qp, struct sk_buff *prev,
 		goto out_oversize;
 
 	/* Head of list must not be cloned. */
-	err = -ENOMEM;
 	if (skb_cloned(head) && pskb_expand_head(head, 0, 0, GFP_ATOMIC))
 		goto out_nomem;
 
@@ -627,6 +566,7 @@ static int ip_frag_reasm(struct ipq *qp, struct sk_buff *prev,
 out_nomem:
 	LIMIT_NETDEBUG(KERN_ERR "IP: queue_glue: no memory for gluing "
 			      "queue %p\n", qp);
+	err = -ENOMEM;
 	goto out_fail;
 out_oversize:
 	if (net_ratelimit())
@@ -671,9 +611,12 @@ void __init ipfrag_init(void)
 {
 	ip4_frags.ctl = &ip4_frags_ctl;
 	ip4_frags.hashfn = ip4_hashfn;
+	ip4_frags.constructor = ip4_frag_init;
 	ip4_frags.destructor = ip4_frag_free;
 	ip4_frags.skb_free = NULL;
 	ip4_frags.qsize = sizeof(struct ipq);
+	ip4_frags.match = ip4_frag_match;
+	ip4_frags.frag_expire = ip_expire;
 	inet_frags_init(&ip4_frags);
 }
 
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 0f00966b178..9288220b73a 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -1121,7 +1121,7 @@ static int tcp_mark_lost_retrans(struct sock *sk, u32 received_upto)
 	struct sk_buff *skb;
 	int flag = 0;
 	int cnt = 0;
-	u32 new_low_seq = 0;
+	u32 new_low_seq = tp->snd_nxt;
 
 	tcp_for_write_queue(skb, sk) {
 		u32 ack_seq = TCP_SKB_CB(skb)->ack_seq;
@@ -1153,7 +1153,7 @@ static int tcp_mark_lost_retrans(struct sock *sk, u32 received_upto)
 				NET_INC_STATS_BH(LINUX_MIB_TCPLOSTRETRANSMIT);
 			}
 		} else {
-			if (!new_low_seq || before(ack_seq, new_low_seq))
+			if (before(ack_seq, new_low_seq))
 				new_low_seq = ack_seq;
 			cnt += tcp_skb_pcount(skb);
 		}
@@ -1242,7 +1242,7 @@ tcp_sacktag_write_queue(struct sock *sk, struct sk_buff *ack_skb, u32 prior_snd_