1 files changed, 490 insertions, 491 deletions

diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c
index e4fe9ee484d..cc85a9ba501 100644
--- a/net/ipv6/reassembly.c
+++ b/net/ipv6/reassembly.c
@@ -1,11 +1,9 @@
 /*
  *	IPv6 fragment reassembly
- *	Linux INET6 implementation 
+ *	Linux INET6 implementation
  *
  *	Authors:
- *	Pedro Roque		<roque@di.fc.ul.pt>	
- *
- *	$Id: reassembly.c,v 1.26 2001/03/07 22:00:57 davem Exp $
+ *	Pedro Roque		<roque@di.fc.ul.pt>
  *
  *	Based on: net/ipv4/ip_fragment.c
  *
@@ -15,8 +13,8 @@
  *      2 of the License, or (at your option) any later version.
  */
 
-/* 
- *	Fixes:	
+/*
+ *	Fixes:
  *	Andi Kleen	Make it work with multiple hosts.
  *			More RFC compliance.
  *
@@ -28,7 +26,9 @@
  *	YOSHIFUJI,H. @USAGI	Always remove fragment header to
  *				calculate ICV correctly.
  */
-#include <linux/config.h>
+
+#define pr_fmt(fmt) "IPv6: " fmt
+
 #include <linux/errno.h>
 #include <linux/types.h>
 #include <linux/string.h>
@@ -43,21 +43,22 @@
 #include <linux/icmpv6.h>
 #include <linux/random.h>
 #include <linux/jhash.h>
+#include <linux/skbuff.h>
+#include <linux/slab.h>
+#include <linux/export.h>
 
 #include <net/sock.h>
 #include <net/snmp.h>
 
 #include <net/ipv6.h>
+#include <net/ip6_route.h>
 #include <net/protocol.h>
 #include <net/transp_v6.h>
 #include <net/rawv6.h>
 #include <net/ndisc.h>
 #include <net/addrconf.h>
-
-int sysctl_ip6frag_high_thresh = 256*1024;
-int sysctl_ip6frag_low_thresh = 192*1024;
-
-int sysctl_ip6frag_time = IPV6_FRAG_TIMEOUT;
+#include <net/inet_frag.h>
+#include <net/inet_ecn.h>
 
 struct ip6frag_skb_cb
 {
@@ -67,391 +68,185 @@ struct ip6frag_skb_cb
 
 #define FRAG6_CB(skb)	((struct ip6frag_skb_cb*)((skb)->cb))
 
-
-/*
- *	Equivalent of ipv4 struct ipq
- */
-
-struct frag_queue
-{
-	struct frag_queue	*next;
-	struct list_head lru_list;		/* lru list member	*/
-
-	__u32			id;		/* fragment id		*/
-	struct in6_addr		saddr;
-	struct in6_addr		daddr;
-
-	spinlock_t		lock;
-	atomic_t		refcnt;
-	struct timer_list	timer;		/* expire timer		*/
-	struct sk_buff		*fragments;
-	int			len;
-	int			meat;
-	int			iif;
-	struct timeval		stamp;
-	unsigned int		csum;
-	__u8			last_in;	/* has first/last segment arrived? */
-#define COMPLETE		4
-#define FIRST_IN		2
-#define LAST_IN			1
-	__u16			nhoffset;
-	struct frag_queue	**pprev;
-};
-
-/* Hash table. */
-
-#define IP6Q_HASHSZ	64
-
-static struct frag_queue *ip6_frag_hash[IP6Q_HASHSZ];
-static DEFINE_RWLOCK(ip6_frag_lock);
-static u32 ip6_frag_hash_rnd;
-static LIST_HEAD(ip6_frag_lru_list);
-int ip6_frag_nqueues = 0;
-
-static __inline__ void __fq_unlink(struct frag_queue *fq)
-{
-	if(fq->next)
-		fq->next->pprev = fq->pprev;
-	*fq->pprev = fq->next;
-	list_del(&fq->lru_list);
-	ip6_frag_nqueues--;
-}
-
-static __inline__ void fq_unlink(struct frag_queue *fq)
+static inline u8 ip6_frag_ecn(const struct ipv6hdr *ipv6h)
 {
-	write_lock(&ip6_frag_lock);
-	__fq_unlink(fq);
-	write_unlock(&ip6_frag_lock);
+	return 1 << (ipv6_get_dsfield(ipv6h) & INET_ECN_MASK);
 }
 
-static unsigned int ip6qhashfn(u32 id, struct in6_addr *saddr,
-			       struct in6_addr *daddr)
-{
-	u32 a, b, c;
-
-	a = saddr->s6_addr32[0];
-	b = saddr->s6_addr32[1];
-	c = saddr->s6_addr32[2];
+static struct inet_frags ip6_frags;
 
-	a += JHASH_GOLDEN_RATIO;
-	b += JHASH_GOLDEN_RATIO;
-	c += ip6_frag_hash_rnd;
-	__jhash_mix(a, b, c);
+static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *prev,
+			  struct net_device *dev);
 
-	a += saddr->s6_addr32[3];
-	b += daddr->s6_addr32[0];
-	c += daddr->s6_addr32[1];
-	__jhash_mix(a, b, c);
-
-	a += daddr->s6_addr32[2];
-	b += daddr->s6_addr32[3];
-	c += id;
-	__jhash_mix(a, b, c);
-
-	return c & (IP6Q_HASHSZ - 1);
-}
-
-static struct timer_list ip6_frag_secret_timer;
-int sysctl_ip6frag_secret_interval = 10 * 60 * HZ;
-
-static void ip6_frag_secret_rebuild(unsigned long dummy)
-{
-	unsigned long now = jiffies;
-	int i;
-
-	write_lock(&ip6_frag_lock);
-	get_random_bytes(&ip6_frag_hash_rnd, sizeof(u32));
-	for (i = 0; i < IP6Q_HASHSZ; i++) {
-		struct frag_queue *q;
-
-		q = ip6_frag_hash[i];
-		while (q) {
-			struct frag_queue *next = q->next;
-			unsigned int hval = ip6qhashfn(q->id,
-						       &q->saddr,
-						       &q->daddr);
-
-			if (hval != i) {
-				/* Unlink. */
-				if (q->next)
-					q->next->pprev = q->pprev;
-				*q->pprev = q->next;
-
-				/* Relink to new hash chain. */
-				if ((q->next = ip6_frag_hash[hval]) != NULL)
-					q->next->pprev = &q->next;
-				ip6_frag_hash[hval] = q;
-				q->pprev = &ip6_frag_hash[hval];
-			}
-
-			q = next;
-		}
-	}
-	write_unlock(&ip6_frag_lock);
-
-	mod_timer(&ip6_frag_secret_timer, now + sysctl_ip6frag_secret_interval);
-}
-
-atomic_t ip6_frag_mem = ATOMIC_INIT(0);
-
-/* Memory Tracking Functions. */
-static inline void frag_kfree_skb(struct sk_buff *skb, int *work)
-{
-	if (work)
-		*work -= skb->truesize;
-	atomic_sub(skb->truesize, &ip6_frag_mem);
-	kfree_skb(skb);
-}
-
-static inline void frag_free_queue(struct frag_queue *fq, int *work)
+/*
+ * callers should be careful not to use the hash value outside the ipfrag_lock
+ * as doing so could race with ipfrag_hash_rnd being recalculated.
+ */
+static unsigned int inet6_hash_frag(__be32 id, const struct in6_addr *saddr,
+				    const struct in6_addr *daddr)
 {
-	if (work)
-		*work -= sizeof(struct frag_queue);
-	atomic_sub(sizeof(struct frag_queue), &ip6_frag_mem);
-	kfree(fq);
-}
+	u32 c;
 
-static inline struct frag_queue *frag_alloc_queue(void)
-{
-	struct frag_queue *fq = kmalloc(sizeof(struct frag_queue), GFP_ATOMIC);
+	net_get_random_once(&ip6_frags.rnd, sizeof(ip6_frags.rnd));
+	c = jhash_3words(ipv6_addr_hash(saddr), ipv6_addr_hash(daddr),
+			 (__force u32)id, ip6_frags.rnd);
 
-	if(!fq)
-		return NULL;
-	atomic_add(sizeof(struct frag_queue), &ip6_frag_mem);
-	return fq;
+	return c & (INETFRAGS_HASHSZ - 1);
 }
 
-/* Destruction primitives. */
-
-/* Complete destruction of fq. */
-static void ip6_frag_destroy(struct frag_queue *fq, int *work)
+static unsigned int ip6_hashfn(struct inet_frag_queue *q)
 {
-	struct sk_buff *fp;
-
-	BUG_TRAP(fq->last_in&COMPLETE);
-	BUG_TRAP(del_timer(&fq->timer) == 0);
-
-	/* Release all fragment data. */
-	fp = fq->fragments;
-	while (fp) {
-		struct sk_buff *xp = fp->next;
-
-		frag_kfree_skb(fp, work);
-		fp = xp;
-	}
-
-	frag_free_queue(fq, work);
-}
+	struct frag_queue *fq;
 
-static __inline__ void fq_put(struct frag_queue *fq, int *work)
-{
-	if (atomic_dec_and_test(&fq->refcnt))
-		ip6_frag_destroy(fq, work);
+	fq = container_of(q, struct frag_queue, q);
+	return inet6_hash_frag(fq->id, &fq->saddr, &fq->daddr);
 }
 
-/* Kill fq entry. It is not destroyed immediately,
- * because caller (and someone more) holds reference count.
- */
-static __inline__ void fq_kill(struct frag_queue *fq)
+bool ip6_frag_match(struct inet_frag_queue *q, void *a)
 {
-	if (del_timer(&fq->timer))
-		atomic_dec(&fq->refcnt);
+	struct frag_queue *fq;
+	struct ip6_create_arg *arg = a;
 
-	if (!(fq->last_in & COMPLETE)) {
-		fq_unlink(fq);
-		atomic_dec(&fq->refcnt);
-		fq->last_in |= COMPLETE;
-	}
+	fq = container_of(q, struct frag_queue, q);
+	return	fq->id == arg->id &&
+		fq->user == arg->user &&
+		ipv6_addr_equal(&fq->saddr, arg->src) &&
+		ipv6_addr_equal(&fq->daddr, arg->dst);
 }
+EXPORT_SYMBOL(ip6_frag_match);
 
-static void ip6_evictor(void)
+void ip6_frag_init(struct inet_frag_queue *q, void *a)
 {
-	struct frag_queue *fq;
-	struct list_head *tmp;
-	int work;
-
-	work = atomic_read(&ip6_frag_mem) - sysctl_ip6frag_low_thresh;
-	if (work <= 0)
-		return;
-
-	while(work > 0) {
-		read_lock(&ip6_frag_lock);
-		if (list_empty(&ip6_frag_lru_list)) {
-			read_unlock(&ip6_frag_lock);
-			return;
-		}
-		tmp = ip6_frag_lru_list.next;
-		fq = list_entry(tmp, struct frag_queue, lru_list);
-		atomic_inc(&fq->refcnt);
-		read_unlock(&ip6_frag_lock);
-
-		spin_lock(&fq->lock);
-		if (!(fq->last_in&COMPLETE))
-			fq_kill(fq);
-		spin_unlock(&fq->lock);
-
-		fq_put(fq, &work);
-		IP6_INC_STATS_BH(IPSTATS_MIB_REASMFAILS);
-	}
+	struct frag_queue *fq = container_of(q, struct frag_queue, q);
+	struct ip6_create_arg *arg = a;
+
+	fq->id = arg->id;
+	fq->user = arg->user;
+	fq->saddr = *arg->src;
+	fq->daddr = *arg->dst;
+	fq->ecn = arg->ecn;
 }
+EXPORT_SYMBOL(ip6_frag_init);
 
-static void ip6_frag_expire(unsigned long data)
+void ip6_expire_frag_queue(struct net *net, struct frag_queue *fq,
+			   struct inet_frags *frags)
 {
-	struct frag_queue *fq = (struct frag_queue *) data;
+	struct net_device *dev = NULL;
 
-	spin_lock(&fq->lock);
+	spin_lock(&fq->q.lock);
 
-	if (fq->last_in & COMPLETE)
+	if (fq->q.last_in & INET_FRAG_COMPLETE)
 		goto out;
 
-	fq_kill(fq);
+	inet_frag_kill(&fq->q, frags);
 
-	IP6_INC_STATS_BH(IPSTATS_MIB_REASMTIMEOUT);
-	IP6_INC_STATS_BH(IPSTATS_MIB_REASMFAILS);
+	rcu_read_lock();
+	dev = dev_get_by_index_rcu(net, fq->iif);
+	if (!dev)
+		goto out_rcu_unlock;
 
-	/* Send error only if the first segment arrived. */
-	if (fq->last_in&FIRST_IN && fq->fragments) {
-		struct net_device *dev = dev_get_by_index(fq->iif);
-
-		/*
-		   But use as source device on which LAST ARRIVED
-		   segment was received. And do not use fq->dev
-		   pointer directly, device might already disappeared.
-		 */
-		if (dev) {
-			fq->fragments->dev = dev;
-			icmpv6_send(fq->fragments, ICMPV6_TIME_EXCEED, ICMPV6_EXC_FRAGTIME, 0,
-				    dev);
-			dev_put(dev);
-		}
-	}
-out:
-	spin_unlock(&fq->lock);
-	fq_put(fq, NULL);
-}
-
-/* Creation primitives. */
+	IP6_INC_STATS_BH(net, __in6_dev_get(dev), IPSTATS_MIB_REASMTIMEOUT);
+	IP6_INC_STATS_BH(net, __in6_dev_get(dev), IPSTATS_MIB_REASMFAILS);
 
+	/* Don't send error if the first segment did not arrive. */
+	if (!(fq->q.last_in & INET_FRAG_FIRST_IN) || !fq->q.fragments)
+		goto out_rcu_unlock;
 
-static struct frag_queue *ip6_frag_intern(unsigned int hash,
-					  struct frag_queue *fq_in)
-{
-	struct frag_queue *fq;
-
-	write_lock(&ip6_frag_lock);
-#ifdef CONFIG_SMP
-	for (fq = ip6_frag_hash[hash]; fq; fq = fq->next) {
-		if (fq->id == fq_in->id && 
-		    ipv6_addr_equal(&fq_in->saddr, &fq->saddr) &&
-		    ipv6_addr_equal(&fq_in->daddr, &fq->daddr)) {
-			atomic_inc(&fq->refcnt);
-			write_unlock(&ip6_frag_lock);
-			fq_in->last_in |= COMPLETE;
-			fq_put(fq_in, NULL);
-			return fq;
-		}
-	}
-#endif
-	fq = fq_in;
-
-	if (!mod_timer(&fq->timer, jiffies + sysctl_ip6frag_time))
-		atomic_inc(&fq->refcnt);
-
-	atomic_inc(&fq->refcnt);
-	if((fq->next = ip6_frag_hash[hash]) != NULL)
-		fq->next->pprev = &fq->next;
-	ip6_frag_hash[hash] = fq;
-	fq->pprev = &ip6_frag_hash[hash];
-	INIT_LIST_HEAD(&fq->lru_list);
-	list_add_tail(&fq->lru_list, &ip6_frag_lru_list);
-	ip6_frag_nqueues++;
-	write_unlock(&ip6_frag_lock);
-	return fq;
+	/*
+	   But use as source device on which LAST ARRIVED
+	   segment was received. And do not use fq->dev
+	   pointer directly, device might already disappeared.
+	 */
+	fq->q.fragments->dev = dev;
+	icmpv6_send(fq->q.fragments, ICMPV6_TIME_EXCEED, ICMPV6_EXC_FRAGTIME, 0);
+out_rcu_unlock:
+	rcu_read_unlock();
+out:
+	spin_unlock(&fq->q.lock);
+	inet_frag_put(&fq->q, frags);
 }
+EXPORT_SYMBOL(ip6_expire_frag_queue);
 
-
-static struct frag_queue *
-ip6_frag_create(unsigned int hash, u32 id, struct in6_addr *src, struct in6_addr *dst)
+static void ip6_frag_expire(unsigned long data)
 {
 	struct frag_queue *fq;
+	struct net *net;
 
-	if ((fq = frag_alloc_queue()) == NULL)
-		goto oom;
-
-	memset(fq, 0, sizeof(struct frag_queue));
+	fq = container_of((struct inet_frag_queue *)data, struct frag_queue, q);
+	net = container_of(fq->q.net, struct net, ipv6.frags);
 
-	fq->id = id;
-	ipv6_addr_copy(&fq->saddr, src);
-	ipv6_addr_copy(&fq->daddr, dst);
-
-	init_timer(&fq->timer);
-	fq->timer.function = ip6_frag_expire;
-	fq->timer.data = (long) fq;
-	spin_lock_init(&fq->lock);
-	atomic_set(&fq->refcnt, 1);
-
-	return ip6_frag_intern(hash, fq);
-
-oom:
-	IP6_INC_STATS_BH(IPSTATS_MIB_REASMFAILS);
-	return NULL;
+	ip6_expire_frag_queue(net, fq, &ip6_frags);
 }
 
 static __inline__ struct frag_queue *
-fq_find(u32 id, struct in6_addr *src, struct in6_addr *dst)
+fq_find(struct net *net, __be32 id, const struct in6_addr *src,
+	const struct in6_addr *dst, u8 ecn)
 {
-	struct frag_queue *fq;
-	unsigned int hash = ip6qhashfn(id, src, dst);
-
-	read_lock(&ip6_frag_lock);
-	for(fq = ip6_frag_hash[hash]; fq; fq = fq->next) {
-		if (fq->id == id && 
-		    ipv6_addr_equal(src, &fq->saddr) &&
-		    ipv6_addr_equal(dst, &fq->daddr)) {
-			atomic_inc(&fq->refcnt);
-			read_unlock(&ip6_frag_lock);
-			return fq;
-		}
+	struct inet_frag_queue *q;
+	struct ip6_create_arg arg;
+	unsigned int hash;
+
+	arg.id = id;
+	arg.user = IP6_DEFRAG_LOCAL_DELIVER;
+	arg.src = src;
+	arg.dst = dst;
+	arg.ecn = ecn;
+
+	read_lock(&ip6_frags.lock);
+	hash = inet6_hash_frag(id, src, dst);
+
+	q = inet_frag_find(&net->ipv6.frags, &ip6_frags, &arg, hash);
+	if (IS_ERR_OR_NULL(q)) {
+		inet_frag_maybe_warn_overflow(q, pr_fmt());
+		return NULL;
 	}
-	read_unlock(&ip6_frag_lock);
-
-	return ip6_frag_create(hash, id, src, dst);
+	return container_of(q, struct frag_queue, q);
 }
 
-
-static void ip6_frag_queue(struct frag_queue *fq, struct sk_buff *skb, 
+static int ip6_frag_queue(struct frag_queue *fq, struct sk_buff *skb,
 			   struct frag_hdr *fhdr, int nhoff)
 {
 	struct sk_buff *prev, *next;
+	struct net_device *dev;
 	int offset, end;
+	struct net *net = dev_net(skb_dst(skb)->dev);
+	u8 ecn;
 
-	if (fq->last_in & COMPLETE)
+	if (fq->q.last_in & INET_FRAG_COMPLETE)
 		goto err;
 
 	offset = ntohs(fhdr->frag_off) & ~0x7;
-	end = offset + (ntohs(skb->nh.ipv6h->payload_len) -
-			((u8 *) (fhdr + 1) - (u8 *) (skb->nh.ipv6h + 1)));
+	end = offset + (ntohs(ipv6_hdr(skb)->payload_len) -
+			((u8 *)(fhdr + 1) - (u8 *)(ipv6_hdr(skb) + 1)));
 
 	if ((unsigned int)end > IPV6_MAXPLEN) {
-		IP6_INC_STATS_BH(IPSTATS_MIB_INHDRERRORS);
- 		icmpv6_param_prob(skb,ICMPV6_HDR_FIELD, (u8*)&fhdr->frag_off - skb->nh.raw);
- 		return;
+		IP6_INC_STATS_BH(net, ip6_dst_idev(skb_dst(skb)),
+				 IPSTATS_MIB_INHDRERRORS);
+		icmpv6_param_prob(skb, ICMPV6_HDR_FIELD,
+				  ((u8 *)&fhdr->frag_off -
+				   skb_network_header(skb)));
+		return -1;
 	}
 
- 	if (skb->ip_summed == CHECKSUM_HW)
- 		skb->csum = csum_sub(skb->csum,
- 				     csum_partial(skb->nh.raw, (u8*)(fhdr+1)-skb->nh.raw, 0));
+	ecn = ip6_frag_ecn(ipv6_hdr(skb));
+
+	if (skb->ip_summed == CHECKSUM_COMPLETE) {
+		const unsigned char *nh = skb_network_header(skb);
+		skb->csum = csum_sub(skb->csum,
+				     csum_partial(nh, (u8 *)(fhdr + 1) - nh,
+						  0));
+	}
 
 	/* Is this the final fragment? */
 	if (!(fhdr->frag_off & htons(IP6_MF))) {
 		/* If we already have some bits beyond end
 		 * or have different end, the segment is corrupted.
 		 */
-		if (end < fq->len ||
-		    ((fq->last_in & LAST_IN) && end != fq->len))
+		if (end < fq->q.len ||
+		    ((fq->q.last_in & INET_FRAG_LAST_IN) && end != fq->q.len))
 			goto err;
-		fq->last_in |= LAST_IN;
-		fq->len = end;
+		fq->q.last_in |= INET_FRAG_LAST_IN;
+		fq->q.len = end;
 	} else {
 		/* Check if the fragment is rounded to 8 bytes.
 		 * Required by the RFC.
@@ -460,16 +255,17 @@ static void ip6_frag_queue(struct frag_queue *fq, struct sk_buff *skb,
 			/* RFC2460 says always send parameter problem in
 			 * this case. -DaveM
 			 */
-			IP6_INC_STATS_BH(IPSTATS_MIB_INHDRERRORS);
-			icmpv6_param_prob(skb, ICMPV6_HDR_FIELD, 
+			IP6_INC_STATS_BH(net, ip6_dst_idev(skb_dst(skb)),
+					 IPSTATS_MIB_INHDRERRORS);
+			icmpv6_param_prob(skb, ICMPV6_HDR_FIELD,
 					  offsetof(struct ipv6hdr, payload_len));
-			return;
+			return -1;
 		}
-		if (end > fq->len) {
+		if (end > fq->q.len) {
 			/* Some bits beyond end -> corruption. */
-			if (fq->last_in & LAST_IN)
+			if (fq->q.last_in & INET_FRAG_LAST_IN)
 				goto err;
-			fq->len = end;
+			fq->q.len = end;
 		}
 	}
 
@@ -479,7 +275,7 @@ static void ip6_frag_queue(struct frag_queue *fq, struct sk_buff *skb,
 	/* Point into the IP datagram 'data' part. */
 	if (!pskb_pull(skb, (u8 *) (fhdr + 1) - skb->data))
 		goto err;
-	
+
 	if (pskb_trim_rcsum(skb, end - offset))
 		goto err;
 
@@ -487,97 +283,86 @@ static void ip6_frag_queue(struct frag_queue *fq, struct sk_buff *skb,
 	 * in the chain of fragments so far.  We must know where to put
 	 * this fragment, right?
 	 */
+	prev = fq->q.fragments_tail;
+	if (!prev || FRAG6_CB(prev)->offset < offset) {
+		next = NULL;
+		goto found;
+	}
 	prev = NULL;
-	for(next = fq->fragments; next != NULL; next = next->next) {
+	for(next = fq->q.fragments; next != NULL; next = next->next) {
 		if (FRAG6_CB(next)->offset >= offset)
 			break;	/* bingo! */
 		prev = next;
 	}
 
-	/* We found where to put this one.  Check for overlap with
-	 * preceding fragment, and, if needed, align things so that
-	 * any overlaps are eliminated.
+found:
+	/* RFC5722, Section 4, amended by Errata ID : 3089
+	 *                          When reassembling an IPv6 datagram, if
+	 *   one or more its constituent fragments is determined to be an
+	 *   overlapping fragment, the entire datagram (and any constituent
+	 *   fragments) MUST be silently discarded.
 	 */
-	if (prev) {
-		int i = (FRAG6_CB(prev)->offset + prev->len) - offset;
 
-		if (i > 0) {
-			offset += i;
-			if (end <= offset)
-				goto err;
-			if (!pskb_pull(skb, i))
-				goto err;
-			if (skb->ip_summed != CHECKSUM_UNNECESSARY)
-				skb->ip_summed = CHECKSUM_NONE;
-		}
-	}
-
-	/* Look for overlap with succeeding segments.
-	 * If we can merge fragments, do it.
-	 */
-	while (next && FRAG6_CB(next)->offset < end) {
-		int i = end - FRAG6_CB(next)->offset; /* overlap is 'i' bytes */
-
-		if (i < next->len) {
-			/* Eat head of the next overlapped fragment
-			 * and leave the loop. The next ones cannot overlap.
-			 */
-			if (!pskb_pull(next, i))
-				goto err;
-			FRAG6_CB(next)->offset += i;	/* next fragment */
-			fq->meat -= i;
-			if (next->ip_summed != CHECKSUM_UNNECESSARY)
-				next->ip_summed = CHECKSUM_NONE;
-			break;
-		} else {
-			struct sk_buff *free_it = next;
-
-			/* Old fragment is completely overridden with
-			 * new one drop it.
-			 */
-			next = next->next;
+	/* Check for overlap with preceding fragment. */
+	if (prev &&
+	    (FRAG6_CB(prev)->offset + prev->len) > offset)
+		goto discard_fq;
 
-			if (prev)
-				prev->next = next;
-			else
-				fq->fragments = next;
-
-			fq->meat -= free_it->len;
-			frag_kfree_skb(free_it, NULL);
-		}
-	}
+	/* Look for overlap with succeeding segment. */
+	if (next && FRAG6_CB(next)->offset < end)
+		goto discard_fq;
 
 	FRAG6_CB(skb)->offset = offset;
 
 	/* Insert this fragment in the chain of fragments. */
 	skb->next = next;
+	if (!next)
+		fq->q.fragments_tail = skb;
 	if (prev)
 		prev->next = skb;
 	else
-		fq->fragments = skb;
+		fq->q.fragments = skb;
 
-	if (skb->dev)
-		fq->iif = skb->dev->ifindex;
-	skb->dev = NULL;
-	skb_get_timestamp(skb, &fq->stamp);
-	fq->meat += skb->len;
-	atomic_add(skb->truesize, &ip6_frag_mem);
+	dev = skb->dev;
+	if (dev) {
+		fq->iif = dev->ifindex;
+		skb->dev = NULL;
+	}
+	fq->q.stamp = skb->tstamp;
+	fq->q.meat += skb->len;
+	fq->ecn |= ecn;
+	add_frag_mem_limit(&fq->q, skb->truesize);
 
 	/* The first fragment.
 	 * nhoffset is obtained from the first fragment, of course.
 	 */
 	if (offset == 0) {
 		fq->nhoffset = nhoff;
-		fq->last_in |= FIRST_IN;
+		fq->q.last_in |= INET_FRAG_FIRST_IN;
+	}
+
+	if (fq->q.last_in == (INET_FRAG_FIRST_IN | INET_FRAG_LAST_IN) &&
+	    fq->q.meat == fq->q.len) {
+		int res;
+		unsigned long orefdst = skb->_skb_refdst;
+
+		skb->_skb_refdst = 0UL;
+		res = ip6_frag_reasm(fq, prev, dev);
+		skb->_skb_refdst = orefdst;
+		return res;
 	}
-	write_lock(&ip6_frag_lock);
-	list_move_tail(&fq->lru_list, &ip6_frag_lru_list);
-	write_unlock(&ip6_frag_lock);
-	return;
 
+	skb_dst_drop(skb);
+	inet_frag_lru_move(&fq->q);
+	return -1;
+
+discard_fq:
+	inet_frag_kill(&fq->q, &ip6_frags);
 err:
-	IP6_INC_STATS(IPSTATS_MIB_REASMFAILS);
+	IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)),
+		      IPSTATS_MIB_REASMFAILS);
 	kfree_skb(skb);
+	return -1;
 }
 
 /*
@@ -589,32 +374,60 @@ err:
  *	queue is eligible for reassembly i.e. it is not COMPLETE,
  *	the last and the first frames arrived and all the bits are here.
  */
-static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff **skb_in,
-			  unsigned int *nhoffp,
+static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *prev,
 			  struct net_device *dev)
 {
-	struct sk_buff *fp, *head = fq->fragments;
+	struct net *net = container_of(fq->q.net, struct net, ipv6.frags);
+	struct sk_buff *fp, *head = fq->q.fragments;
 	int    payload_len;
 	unsigned int nhoff;
+	int sum_truesize;
+	u8 ecn;
+
+	inet_frag_kill(&fq->q, &ip6_frags);
+
+	ecn = ip_frag_ecn_table[fq->ecn];
+	if (unlikely(ecn == 0xff))
+		goto out_fail;
+
+	/* Make the one we just received the head. */
+	if (prev) {
+		head = prev->next;
+		fp = skb_clone(head, GFP_ATOMIC);
 
-	fq_kill(fq);
+		if (!fp)
+			goto out_oom;
+
+		fp->next = head->next;
+		if (!fp->next)
+			fq->q.fragments_tail = fp;
+		prev->next = fp;
+
+		skb_morph(head, fq->q.fragments);
+		head->next = fq->q.fragments->next;
 
-	BUG_TRAP(head != NULL);
-	BUG_TRAP(FRAG6_CB(head)->offset == 0);
+		consume_skb(fq->q.fragments);
+		fq->q.fragments = head;
+	}
+
+	WARN_ON(head == NULL);
+	WARN_ON(FRAG6_CB(head)->offset != 0);
 
 	/* Unfragmented part is taken from the first segment. */
-	payload_len = (head->data - head->nh.raw) - sizeof(struct ipv6hdr) + fq->len - sizeof(struct frag_hdr);
+	payload_len = ((head->data - skb_network_header(head)) -
+		       sizeof(struct ipv6hdr) + fq->q.len -
+		       sizeof(struct frag_hdr));
 	if (payload_len > IPV6_MAXPLEN)
 		goto out_oversize;
 
 	/* Head of list must not be cloned. */
-	if (skb_cloned(head) && pskb_expand_head(head, 0, 0, GFP_ATOMIC))
+	if (skb_unclone(head, GFP_ATOMIC))
 		goto out_oom;
 
 	/* If the first fragment is fragmented itself, we split
 	 * it to two chunks: the first with data and paged part
 	 * and the second, holding only fragments. */
-	if (skb_shinfo(head)->frag_list) {
+	if (skb_has_frag_list(head)) {
 		struct sk_buff *clone;
 		int i, plen = 0;
 
@@ -623,146 +436,332 @@ static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff **skb_in,
 		clone->next = head->next;
 		head->next = clone;
 		skb_shinfo(clone)->frag_list = skb_shinfo(head)->frag_list;
-		skb_shinfo(head)->frag_list = NULL;
-		for (i=0; i<skb_shinfo(head)->nr_frags; i++)
-			plen += skb_shinfo(head)->frags[i].size;
+		skb_frag_list_init(head);
+		for (i = 0; i < skb_shinfo(head)->nr_frags; i++)
+			plen += skb_frag_size(&skb_shinfo(head)->frags[i]);
 		clone->len = clone->data_len = head->data_len - plen;
 		head->data_len -= clone->len;
 		head->len -= clone->len;
 		clone->csum = 0;
 		clone->ip_summed = head->ip_summed;
-		atomic_add(clone->truesize, &ip6_frag_mem);
+		add_frag_mem_limit(&fq->q, clone->truesize);
 	}
 
 	/* We have to remove fragment header from datagram and to relocate
 	 * header in order to calculate ICV correctly. */
 	nhoff = fq->nhoffset;
-	head->nh.raw[nhoff] = head->h.raw[0];
-	memmove(head->head + sizeof(struct frag_hdr), head->head, 
+	skb_network_header(head)[nhoff] = skb_transport_header(head)[0];
+	memmove(head->head + sizeof(struct frag_hdr), head->head,
 		(head->data - head->head) - sizeof(struct frag_hdr));
-	head->mac.raw += sizeof(struct frag_hdr);
-	head->nh.raw += sizeof(struct frag_hdr);
+	head->mac_header += sizeof(struct frag_hdr);
+	head->network_header += sizeof(struct frag_hdr);
+
+	skb_reset_transport_header(head);
+	skb_push(head, head->data - skb_network_header(head));
 
-	skb_shinfo(head)->frag_list = head->next;
-	head->h.raw = head->data;
-	skb_push(head, head->data - head->nh.raw);
-	atomic_sub(head->truesize, &ip6_frag_mem);
+	sum_truesize = head->truesize;
+	for (fp = head->next; fp;) {
+		bool headstolen;
+		int delta;
+		struct sk_buff *next = fp->next;
 
-	for (fp=head->next; fp; fp = fp->next) {
-		head->data_len += fp->len;
-		head->len += fp->len;
+		sum_truesize += fp->truesize;
 		if (head->ip_summed != fp->ip_summed)
 			head->ip_summed = CHECKSUM_NONE;
-		else if (head->ip_summed == CHECKSUM_HW)
+		else if (head->ip_summed == CHECKSUM_COMPLETE)
 			head->csum = csum_add(head->csum, fp->csum);
-		head->truesize += fp->truesize;
-		atomic_sub(fp->truesize, &ip6_frag_mem);
+
+		if (skb_try_coalesce(head, fp, &headstolen, &delta)) {
+			kfree_skb_partial(fp, headstolen);
+		} else {
+			if (!skb_shinfo(head)->frag_list)
+				skb_shinfo(head)->frag_list = fp;
+			head->data_len += fp->len;
+			head->len += fp->len;
+			head->truesize += fp->truesize;
+		}
+		fp = next;
 	}
+	sub_frag_mem_limit(&fq->q, sum_truesize);
 
 	head->next = NULL;
 	head->dev = dev;
-	skb_set_timestamp(head, &fq->stamp);
-	head->nh.ipv6h->payload_len = htons(payload_len);
-
-	*skb_in = head;
+	head->tstamp = fq->q.stamp;
+	ipv6_hdr(head)->payload_len = htons(payload_len);
+	ipv6_change_dsfield(ipv6_hdr(head), 0xff, ecn);
+	IP6CB(head)->nhoff = nhoff;
+	IP6CB(head)->flags |= IP6SKB_FRAGMENTED;
 
 	/* Yes, and fold redundant checksum back. 8) */
-	if (head->ip_summed == CHECKSUM_HW)
-		head->csum = csum_partial(head->nh.raw, head->h.raw-head->nh.raw, head->csum);
-
-	IP6_INC_STATS_BH(IPSTATS_MIB_REASMOKS);
-	fq->fragments = NULL;
-	*nhoffp = nhoff;
+	if (head->ip_summed == CHECKSUM_COMPLETE)
+		head->csum = csum_partial(skb_network_header(head),
+					  skb_network_header_len(head),
+					  head->csum);
+
+	rcu_read_lock();
+	IP6_INC_STATS_BH(net, __in6_dev_get(dev), IPSTATS_MIB_REASMOKS);
+	rcu_read_unlock();
+	fq->q.fragments = NULL;
+	fq->q.fragments_tail = NULL;
 	return 1;
 
 out_oversize:
-	if (net_ratelimit())
-		printk(KERN_DEBUG "ip6_frag_reasm: payload len = %d\n", payload_len);
+	net_dbg_ratelimited("ip6_frag_reasm: payload len = %d\n", payload_len);
 	goto out_fail;
 out_oom:
-	if (net_ratelimit())
-		printk(KERN_DEBUG "ip6_frag_reasm: no memory for reassembly\n");
+	net_dbg_ratelimited("ip6_frag_reasm: no memory for reassembly\n");
 out_fail:
-	IP6_INC_STATS_BH(IPSTATS_MIB_REASMFAILS);
+	rcu_read_lock();
+	IP6_INC_STATS_BH(net, __in6_dev_get(dev), IPSTATS_MIB_REASMFAILS);
+	rcu_read_unlock();
 	return -1;
 }
 
-static int ipv6_frag_rcv(struct sk_buff **skbp, unsigned int *nhoffp)
+static int ipv6_frag_rcv(struct sk_buff *skb)
 {
-	struct sk_buff *skb = *skbp; 
-	struct net_device *dev = skb->dev;
 	struct frag_hdr *fhdr;
 	struct frag_queue *fq;
-	struct ipv6hdr *hdr;
+	const struct ipv6hdr *hdr = ipv6_hdr(skb);
+	struct net *net = dev_net(skb_dst(skb)->dev);
+	int evicted;
 
-	hdr = skb->nh.ipv6h;
+	if (IP6CB(skb)->flags & IP6SKB_FRAGMENTED)
+		goto fail_hdr;
 
-	IP6_INC_STATS_BH(IPSTATS_MIB_REASMREQDS);
+	IP6_INC_STATS_BH(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_REASMREQDS);
 
 	/* Jumbo payload inhibits frag. header */
-	if (hdr->payload_len==0) {
-		IP6_INC_STATS(IPSTATS_MIB_INHDRERRORS);
-		icmpv6_param_prob(skb, ICMPV6_HDR_FIELD, skb->h.raw-skb->nh.raw);
-		return -1;
-	}
-	if (!pskb_may_pull(skb, (skb->h.raw-skb->data)+sizeof(struct frag_hdr))) {
-		IP6_INC_STATS(IPSTATS_MIB_INHDRERRORS);
-		icmpv6_param_prob(skb, ICMPV6_HDR_FIELD, skb->h.raw-skb->nh.raw);
-		return -1;
-	}
+	if (hdr->payload_len==0)
+		goto fail_hdr;
 
-	hdr = skb->nh.ipv6h;
-	fhdr = (struct frag_hdr *)skb->h.raw;
+	if (!pskb_may_pull(skb, (skb_transport_offset(skb) +
+				 sizeof(struct frag_hdr))))
+		goto fail_hdr;
+
+	hdr = ipv6_hdr(skb);
+	fhdr = (struct frag_hdr *)skb_transport_header(skb);
 
 	if (!(fhdr->frag_off & htons(0xFFF9))) {
 		/* It is not a fragmented frame */
-		skb->h.raw += sizeof(struct frag_hdr);
-		IP6_INC_STATS_BH(IPSTATS_MIB_REASMOKS);
+		skb->transport_header += sizeof(struct frag_hdr);
+		IP6_INC_STATS_BH(net,
+				 ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_REASMOKS);
 
-		*nhoffp = (u8*)fhdr - skb->nh.raw;
+		IP6CB(skb)->nhoff = (u8 *)fhdr - skb_network_header(skb);
+		IP6CB(skb)->flags |= IP6SKB_FRAGMENTED;
 		return 1;
 	}
 
-	if (atomic_read(&ip6_frag_mem) > sysctl_ip6frag_high_thresh)
-		ip6_evictor();
-
-	if ((fq = fq_find(fhdr->identification, &hdr->saddr, &hdr->daddr)) != NULL) {
-		int ret = -1;
+	evicted = inet_frag_evictor(&net->ipv6.frags, &ip6_frags, false);
+	if (evicted)
+		IP6_ADD_STATS_BH(net, ip6_dst_idev(skb_dst(skb)),
+				 IPSTATS_MIB_REASMFAILS, evicted);
 
-		spin_lock(&fq->lock);
+	fq = fq_find(net, fhdr->identification, &hdr->saddr, &hdr->daddr,
+		     ip6_frag_ecn(hdr));
+	if (fq != NULL) {
+		int ret;
 
-		ip6_frag_queue(fq, skb, fhdr, *nhoffp);
+		spin_lock(&fq->q.lock);
 
-		if (fq->last_in == (FIRST_IN|LAST_IN) &&
-		    fq->meat == fq->len)
-			ret = ip6_frag_reasm(fq, skbp, nhoffp, dev);
+		ret = ip6_frag_queue(fq, skb, fhdr, IP6CB(skb)->nhoff);
 
-		spin_unlock(&fq->lock);
-		fq_put(fq, NULL);
+		spin_unlock(&fq->q.lock);
+		inet_frag_put(&fq->q, &ip6_frags);
 		return ret;
 	}
 
-	IP6_INC_STATS_BH(IPSTATS_MIB_REASMFAILS);
+	IP6_INC_STATS_BH(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_REASMFAILS);
 	kfree_skb(skb);
 	return -1;
+
+fail_hdr:
+	IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_INHDRERRORS);
+	icmpv6_param_prob(skb, ICMPV6_HDR_FIELD, skb_network_header_len(skb));
+	return -1;
 }
 
-static struct inet6_protocol frag_protocol =
+static const struct inet6_protocol frag_protocol =
 {
 	.handler	=	ipv6_frag_rcv,
 	.flags		=	INET6_PROTO_NOPOLICY,
 };
 
-void __init ipv6_frag_init(void)
+#ifdef CONFIG_SYSCTL
+static struct ctl_table ip6_frags_ns_ctl_table[] = {
+	{
+		.procname	= "ip6frag_high_thresh",
+		.data		= &init_net.ipv6.frags.high_thresh,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec
+	},
+	{
+		.procname	= "ip6frag_low_thresh",
+		.data		= &init_net.ipv6.frags.low_thresh,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec
+	},
+	{
+		.procname	= "ip6frag_time",
+		.data		= &init_net.ipv6.frags.timeout,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_jiffies,
+	},
+	{ }
+};
+
+static struct ctl_table ip6_frags_ctl_table[] = {
+	{
+		.procname	= "ip6frag_secret_interval",
+		.data		= &ip6_frags.secret_interval,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_jiffies,
+	},
+	{ }
+};
+
+static int __net_init ip6_frags_ns_sysctl_register(struct net *net)
 {
-	if (inet6_add_protocol(&frag_protocol, IPPROTO_FRAGMENT) < 0)
-		printk(KERN_ERR "ipv6_frag_init: Could not register protocol\n");
+	struct ctl_table *table;
+	struct ctl_table_header *hdr;
+
+	table = ip6_frags_ns_ctl_table;
+	if (!net_eq(net, &init_net)) {
+		table = kmemdup(table, sizeof(ip6_frags_ns_ctl_table), GFP_KERNEL);
+		if (table == NULL)
+			goto err_alloc;
+
+		table[0].data = &net->ipv6.frags.high_thresh;
+		table[1].data = &net->ipv6.frags.low_thresh;
+		table[2].data = &net->ipv6.frags.timeout;
+
+		/* Don't export sysctls to unprivileged users */
+		if (net->user_ns != &init_user_ns)
+			table[0].procname = NULL;
+	}
+
+	hdr = register_net_sysctl(net, "net/ipv6", table);
+	if (hdr == NULL)
+		goto err_reg;
+
+	net->ipv6.sysctl.frags_hdr = hdr;
+	return 0;
+
+err_reg:
+	if (!net_eq(net, &init_net))
+		kfree(table);
+err_alloc:
+	return -ENOMEM;
+}
+
+static void __net_exit ip6_frags_ns_sysctl_unregister(struct net *net)
+{
+	struct ctl_table *table;
+
+	table = net->ipv6.sysctl.frags_hdr->ctl_table_arg;
+	unregister_net_sysctl_table(net->ipv6.sysctl.frags_hdr);
+	if (!net_eq(net, &init_net))
+		kfree(table);
+}
+
+static struct ctl_table_header *ip6_ctl_header;
+
+static int ip6_frags_sysctl_register(void)
+{
+	ip6_ctl_header = register_net_sysctl(&init_net, "net/ipv6",
+			ip6_frags_ctl_table);
+	return ip6_ctl_header == NULL ? -ENOMEM : 0;
+}
+
+static void ip6_frags_sysctl_unregister(void)
+{
+	unregister_net_sysctl_table(ip6_ctl_header);
+}
+#else
+static inline int ip6_frags_ns_sysctl_register(struct net *net)
+{
+	return 0;
+}
+
+static inline void ip6_frags_ns_sysctl_unregister(struct net *net)
+{
+}
+
+static inline int ip6_frags_sysctl_register(void)
+{
+	return 0;
+}
+
+static inline void ip6_frags_sysctl_unregister(void)
+{
+}
+#endif
+
+static int __net_init ipv6_frags_init_net(struct net *net)
+{
+	net->ipv6.frags.high_thresh = IPV6_FRAG_HIGH_THRESH;
+	net->ipv6.frags.low_thresh = IPV6_FRAG_LOW_THRESH;
+	net->ipv6.frags.timeout = IPV6_FRAG_TIMEOUT;
+
+	inet_frags_init_net(&net->ipv6.frags);
+
+	return ip6_frags_ns_sysctl_register(net);
+}
 
-	ip6_frag_hash_rnd = (u32) ((num_physpages ^ (num_physpages>>7)) ^
-				   (jiffies ^ (jiffies >> 6)));
+static void __net_exit ipv6_frags_exit_net(struct net *net)
+{
+	ip6_frags_ns_sysctl_unregister(net);
+	inet_frags_exit_net(&net->ipv6.frags, &ip6_frags);
+}
 
-	init_timer(&ip6_frag_secret_timer);
-	ip6_frag_secret_timer.function = ip6_frag_secret_rebuild;
-	ip6_frag_secret_timer.expires = jiffies + sysctl_ip6frag_secret_interval;
-	add_timer(&ip6_frag_secret_timer);
+static struct pernet_operations ip6_frags_ops = {
+	.init = ipv6_frags_init_net,
+	.exit = ipv6_frags_exit_net,
+};
+
+int __init ipv6_frag_init(void)
+{
+	int ret;
+
+	ret = inet6_add_protocol(&frag_protocol, IPPROTO_FRAGMENT);
+	if (ret)
+		goto out;
+
+	ret = ip6_frags_sysctl_register();
+	if (ret)
+		goto err_sysctl;
+
+	ret = register_pernet_subsys(&ip6_frags_ops);
+	if (ret)
+		goto err_pernet;
+
+	ip6_frags.hashfn = ip6_hashfn;
+	ip6_frags.constructor = ip6_frag_init;
+	ip6_frags.destructor = NULL;
+	ip6_frags.skb_free = NULL;
+	ip6_frags.qsize = sizeof(struct frag_queue);
+	ip6_frags.match = ip6_frag_match;
+	ip6_frags.frag_expire = ip6_frag_expire;
+	ip6_frags.secret_interval = 10 * 60 * HZ;
+	inet_frags_init(&ip6_frags);
+out:
+	return ret;
+
+err_pernet:
+	ip6_frags_sysctl_unregister();
+err_sysctl:
+	inet6_del_protocol(&frag_protocol, IPPROTO_FRAGMENT);
+	goto out;
+}
+
+void ipv6_frag_exit(void)
+{
+	inet_frags_fini(&ip6_frags);
+	ip6_frags_sysctl_unregister();
+	unregister_pernet_subsys(&ip6_frags_ops);
+	inet6_del_protocol(&frag_protocol, IPPROTO_FRAGMENT);
 }