Merge branch 'inet-frags-bring-rhashtables-to-IP-defrag'

Eric Dumazet says:

====================
inet: frags: bring rhashtables to IP defrag

IP defrag processing is one of the remaining problematic layer in linux.

It uses static hash tables of 1024 buckets, and up to 128 items per bucket.

A work queue is supposed to garbage collect items when host is under memory
pressure, and doing a hash rebuild, changing seed used in hash computations.

This work queue blocks softirqs for up to 25 ms when doing a hash rebuild,
occurring every 5 seconds if host is under fire.

Then there is the problem of sharing this hash table for all netns.

It is time to switch to rhashtables, and allocate one of them per netns
to speedup netns dismantle, since this is a critical metric these days.

Lookup is now using RCU, and 64bit hosts can now provision whatever amount
of memory needed to handle the expected workloads.

v2: Addressed Herbert and Kirill feedbacks
  (Use rhashtable_free_and_destroy(), and split the big patch into small units)

v3: Removed the extra add_frag_mem_limit(...) from inet_frag_create()
    Removed the refcount_inc_not_zero() call from inet_frags_free_cb(),
    as we can exploit del_timer() return value.

v4: kbuild robot feedback about one missing static (squashed)
    Additional patches :
      inet: frags: do not clone skb in ip_expire()
      ipv6: frags: rewrite ip6_expire_frag_queue()
      rhashtable: reorganize struct rhashtable layout
      inet: frags: reorganize struct netns_frags
      inet: frags: get rid of ipfrag_skb_cb/FRAG_CB
      ipv6: frags: get rid of ip6frag_skb_cb/FRAG6_CB
      inet: frags: get rid of nf_ct_frag6_skb_cb/NFCT_FRAG6_CB
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

3 files changed, 186 insertions, 431 deletions

diff --git a/net/ipv4/inet_fragment.c b/net/ipv4/inet_fragment.c
index e8ec28999f5c..c9e35b81d093 100644
--- a/net/ipv4/inet_fragment.c
+++ b/net/ipv4/inet_fragment.c
@@ -25,12 +25,6 @@
 #include <net/inet_frag.h>
 #include <net/inet_ecn.h>
 
-#define INETFRAGS_EVICT_BUCKETS   128
-#define INETFRAGS_EVICT_MAX	  512
-
-/* don't rebuild inetfrag table with new secret more often than this */
-#define INETFRAGS_MIN_REBUILD_INTERVAL (5 * HZ)
-
 /* Given the OR values of all fragments, apply RFC 3168 5.3 requirements
  * Value : 0xff if frame should be dropped.
  *         0 or INET_ECN_CE value, to be ORed in to final iph->tos field
@@ -52,157 +46,8 @@ const u8 ip_frag_ecn_table[16] = {
 };
 EXPORT_SYMBOL(ip_frag_ecn_table);
 
-static unsigned int
-inet_frag_hashfn(const struct inet_frags *f, const struct inet_frag_queue *q)
-{
-	return f->hashfn(q) & (INETFRAGS_HASHSZ - 1);
-}
-
-static bool inet_frag_may_rebuild(struct inet_frags *f)
-{
-	return time_after(jiffies,
-	       f->last_rebuild_jiffies + INETFRAGS_MIN_REBUILD_INTERVAL);
-}
-
-static void inet_frag_secret_rebuild(struct inet_frags *f)
-{
-	int i;
-
-	write_seqlock_bh(&f->rnd_seqlock);
-
-	if (!inet_frag_may_rebuild(f))
-		goto out;
-
-	get_random_bytes(&f->rnd, sizeof(u32));
-
-	for (i = 0; i < INETFRAGS_HASHSZ; i++) {
-		struct inet_frag_bucket *hb;
-		struct inet_frag_queue *q;
-		struct hlist_node *n;
-
-		hb = &f->hash[i];
-		spin_lock(&hb->chain_lock);
-
-		hlist_for_each_entry_safe(q, n, &hb->chain, list) {
-			unsigned int hval = inet_frag_hashfn(f, q);
-
-			if (hval != i) {
-				struct inet_frag_bucket *hb_dest;
-
-				hlist_del(&q->list);
-
-				/* Relink to new hash chain. */
-				hb_dest = &f->hash[hval];
-
-				/* This is the only place where we take
-				 * another chain_lock while already holding
-				 * one.  As this will not run concurrently,
-				 * we cannot deadlock on hb_dest lock below, if its
-				 * already locked it will be released soon since
-				 * other caller cannot be waiting for hb lock
-				 * that we've taken above.
-				 */
-				spin_lock_nested(&hb_dest->chain_lock,
-						 SINGLE_DEPTH_NESTING);
-				hlist_add_head(&q->list, &hb_dest->chain);
-				spin_unlock(&hb_dest->chain_lock);
-			}
-		}
-		spin_unlock(&hb->chain_lock);
-	}
-
-	f->rebuild = false;
-	f->last_rebuild_jiffies = jiffies;
-out:
-	write_sequnlock_bh(&f->rnd_seqlock);
-}
-
-static bool inet_fragq_should_evict(const struct inet_frag_queue *q)
-{
-	if (!hlist_unhashed(&q->list_evictor))
-		return false;
-
-	return q->net->low_thresh == 0 ||
-	       frag_mem_limit(q->net) >= q->net->low_thresh;
-}
-
-static unsigned int
-inet_evict_bucket(struct inet_frags *f, struct inet_frag_bucket *hb)
-{
-	struct inet_frag_queue *fq;
-	struct hlist_node *n;
-	unsigned int evicted = 0;
-	HLIST_HEAD(expired);
-
-	spin_lock(&hb->chain_lock);
-
-	hlist_for_each_entry_safe(fq, n, &hb->chain, list) {
-		if (!inet_fragq_should_evict(fq))
-			continue;
-
-		if (!del_timer(&fq->timer))
-			continue;
-
-		hlist_add_head(&fq->list_evictor, &expired);
-		++evicted;
-	}
-
-	spin_unlock(&hb->chain_lock);
-
-	hlist_for_each_entry_safe(fq, n, &expired, list_evictor)
-		f->frag_expire(&fq->timer);
-
-	return evicted;
-}
-
-static void inet_frag_worker(struct work_struct *work)
-{
-	unsigned int budget = INETFRAGS_EVICT_BUCKETS;
-	unsigned int i, evicted = 0;
-	struct inet_frags *f;
-
-	f = container_of(work, struct inet_frags, frags_work);
-
-	BUILD_BUG_ON(INETFRAGS_EVICT_BUCKETS >= INETFRAGS_HASHSZ);
-
-	local_bh_disable();
-
-	for (i = READ_ONCE(f->next_bucket); budget; --budget) {
-		evicted += inet_evict_bucket(f, &f->hash[i]);
-		i = (i + 1) & (INETFRAGS_HASHSZ - 1);
-		if (evicted > INETFRAGS_EVICT_MAX)
-			break;
-	}
-
-	f->next_bucket = i;
-
-	local_bh_enable();
-
-	if (f->rebuild && inet_frag_may_rebuild(f))
-		inet_frag_secret_rebuild(f);
-}
-
-static void inet_frag_schedule_worker(struct inet_frags *f)
-{
-	if (unlikely(!work_pending(&f->frags_work)))
-		schedule_work(&f->frags_work);
-}
-
 int inet_frags_init(struct inet_frags *f)
 {
-	int i;
-
-	INIT_WORK(&f->frags_work, inet_frag_worker);
-
-	for (i = 0; i < INETFRAGS_HASHSZ; i++) {
-		struct inet_frag_bucket *hb = &f->hash[i];
-
-		spin_lock_init(&hb->chain_lock);
-		INIT_HLIST_HEAD(&hb->chain);
-	}
-
-	seqlock_init(&f->rnd_seqlock);
-	f->last_rebuild_jiffies = 0;
 	f->frags_cachep = kmem_cache_create(f->frags_cache_name, f->qsize, 0, 0,
 					    NULL);
 	if (!f->frags_cachep)
@@ -214,83 +59,75 @@ EXPORT_SYMBOL(inet_frags_init);
 
 void inet_frags_fini(struct inet_frags *f)
 {
-	cancel_work_sync(&f->frags_work);
+	/* We must wait that all inet_frag_destroy_rcu() have completed. */
+	rcu_barrier();
+
 	kmem_cache_destroy(f->frags_cachep);
+	f->frags_cachep = NULL;
 }
 EXPORT_SYMBOL(inet_frags_fini);
 
-void inet_frags_exit_net(struct netns_frags *nf, struct inet_frags *f)
+static void inet_frags_free_cb(void *ptr, void *arg)
 {
-	unsigned int seq;
-	int i;
-
-	nf->low_thresh = 0;
+	struct inet_frag_queue *fq = ptr;
 
-evict_again:
-	local_bh_disable();
-	seq = read_seqbegin(&f->rnd_seqlock);
-
-	for (i = 0; i < INETFRAGS_HASHSZ ; i++)
-		inet_evict_bucket(f, &f->hash[i]);
-
-	local_bh_enable();
-	cond_resched();
-
-	if (read_seqretry(&f->rnd_seqlock, seq) ||
-	    sum_frag_mem_limit(nf))
-		goto evict_again;
-}
-EXPORT_SYMBOL(inet_frags_exit_net);
-
-static struct inet_frag_bucket *
-get_frag_bucket_locked(struct inet_frag_queue *fq, struct inet_frags *f)
-__acquires(hb->chain_lock)
-{
-	struct inet_frag_bucket *hb;
-	unsigned int seq, hash;
-
- restart:
-	seq = read_seqbegin(&f->rnd_seqlock);
-
-	hash = inet_frag_hashfn(f, fq);
-	hb = &f->hash[hash];
+	/* If we can not cancel the timer, it means this frag_queue
+	 * is already disappearing, we have nothing to do.
+	 * Otherwise, we own a refcount until the end of this function.
+	 */
+	if (!del_timer(&fq->timer))
+		return;
 
-	spin_lock(&hb->chain_lock);
-	if (read_seqretry(&f->rnd_seqlock, seq)) {
-		spin_unlock(&hb->chain_lock);
-		goto restart;
+	spin_lock_bh(&fq->lock);
+	if (!(fq->flags & INET_FRAG_COMPLETE)) {
+		fq->flags |= INET_FRAG_COMPLETE;
+		refcount_dec(&fq->refcnt);
 	}
+	spin_unlock_bh(&fq->lock);
 
-	return hb;
+	inet_frag_put(fq);
 }
 
-static inline void fq_unlink(struct inet_frag_queue *fq, struct inet_frags *f)
+void inet_frags_exit_net(struct netns_frags *nf)
 {
-	struct inet_frag_bucket *hb;
+	nf->low_thresh = 0; /* prevent creation of new frags */
 
-	hb = get_frag_bucket_locked(fq, f);
-	hlist_del(&fq->list);
-	fq->flags |= INET_FRAG_COMPLETE;
-	spin_unlock(&hb->chain_lock);
+	rhashtable_free_and_destroy(&nf->rhashtable, inet_frags_free_cb, NULL);
 }
+EXPORT_SYMBOL(inet_frags_exit_net);
 
-void inet_frag_kill(struct inet_frag_queue *fq, struct inet_frags *f)
+void inet_frag_kill(struct inet_frag_queue *fq)
 {
 	if (del_timer(&fq->timer))
 		refcount_dec(&fq->refcnt);
 
 	if (!(fq->flags & INET_FRAG_COMPLETE)) {
-		fq_unlink(fq, f);
+		struct netns_frags *nf = fq->net;
+
+		fq->flags |= INET_FRAG_COMPLETE;
+		rhashtable_remove_fast(&nf->rhashtable, &fq->node, nf->f->rhash_params);
 		refcount_dec(&fq->refcnt);
 	}
 }
 EXPORT_SYMBOL(inet_frag_kill);
 
-void inet_frag_destroy(struct inet_frag_queue *q, struct inet_frags *f)
+static void inet_frag_destroy_rcu(struct rcu_head *head)
+{
+	struct inet_frag_queue *q = container_of(head, struct inet_frag_queue,
+						 rcu);
+	struct inet_frags *f = q->net->f;
+
+	if (f->destructor)
+		f->destructor(q);
+	kmem_cache_free(f->frags_cachep, q);
+}
+
+void inet_frag_destroy(struct inet_frag_queue *q)
 {
 	struct sk_buff *fp;
 	struct netns_frags *nf;
 	unsigned int sum, sum_truesize = 0;
+	struct inet_frags *f;
 
 	WARN_ON(!(q->flags & INET_FRAG_COMPLETE));
 	WARN_ON(del_timer(&q->timer) != 0);
@@ -298,6 +135,7 @@ void inet_frag_destroy(struct inet_frag_queue *q, struct inet_frags *f)
 	/* Release all fragment data. */
 	fp = q->fragments;
 	nf = q->net;
+	f = nf->f;
 	while (fp) {
 		struct sk_buff *xp = fp->next;
 
@@ -307,59 +145,20 @@ void inet_frag_destroy(struct inet_frag_queue *q, struct inet_frags *f)
 	}
 	sum = sum_truesize + f->qsize;
 
-	if (f->destructor)
-		f->destructor(q);
-	kmem_cache_free(f->frags_cachep, q);
+	call_rcu(&q->rcu, inet_frag_destroy_rcu);
 
 	sub_frag_mem_limit(nf, sum);
 }
 EXPORT_SYMBOL(inet_frag_destroy);
 
-static struct inet_frag_queue *inet_frag_intern(struct netns_frags *nf,
-						struct inet_frag_queue *qp_in,
-						struct inet_frags *f,
-						void *arg)
-{
-	struct inet_frag_bucket *hb = get_frag_bucket_locked(qp_in, f);
-	struct inet_frag_queue *qp;
-
-#ifdef CONFIG_SMP
-	/* With SMP race we have to recheck hash table, because
-	 * such entry could have been created on other cpu before
-	 * we acquired hash bucket lock.
-	 */
-	hlist_for_each_entry(qp, &hb->chain, list) {
-		if (qp->net == nf && f->match(qp, arg)) {
-			refcount_inc(&qp->refcnt);
-			spin_unlock(&hb->chain_lock);
-			qp_in->flags |= INET_FRAG_COMPLETE;
-			inet_frag_put(qp_in, f);
-			return qp;
-		}
-	}
-#endif
-	qp = qp_in;
-	if (!mod_timer(&qp->timer, jiffies + nf->timeout))
-		refcount_inc(&qp->refcnt);
-
-	refcount_inc(&qp->refcnt);
-	hlist_add_head(&qp->list, &hb->chain);
-
-	spin_unlock(&hb->chain_lock);
-
-	return qp;
-}
-
 static struct inet_frag_queue *inet_frag_alloc(struct netns_frags *nf,
 					       struct inet_frags *f,
 					       void *arg)
 {
 	struct inet_frag_queue *q;
 
-	if (!nf->high_thresh || frag_mem_limit(nf) > nf->high_thresh) {
-		inet_frag_schedule_worker(f);
+	if (!nf->high_thresh || frag_mem_limit(nf) > nf->high_thresh)
 		return NULL;
-	}
 
 	q = kmem_cache_zalloc(f->frags_cachep, GFP_ATOMIC);
 	if (!q)
@@ -371,70 +170,51 @@ static struct inet_frag_queue *inet_frag_alloc(struct netns_frags *nf,
 
 	timer_setup(&q->timer, f->frag_expire, 0);
 	spin_lock_init(&q->lock);
-	refcount_set(&q->refcnt, 1);
+	refcount_set(&q->refcnt, 3);
 
 	return q;
 }
 
 static struct inet_frag_queue *inet_frag_create(struct netns_frags *nf,
-						struct inet_frags *f,
 						void *arg)
 {
+	struct inet_frags *f = nf->f;
 	struct inet_frag_queue *q;
+	int err;
 
 	q = inet_frag_alloc(nf, f, arg);
 	if (!q)
 		return NULL;
 
-	return inet_frag_intern(nf, q, f, arg);
+	mod_timer(&q->timer, jiffies + nf->timeout);
+
+	err = rhashtable_insert_fast(&nf->rhashtable, &q->node,
+				     f->rhash_params);
+	if (err < 0) {
+		q->flags |= INET_FRAG_COMPLETE;
+		inet_frag_kill(q);
+		inet_frag_destroy(q);
+		return NULL;
+	}
+	return q;
 }
 
-struct inet_frag_queue *inet_frag_find(struct netns_frags *nf,
-				       struct inet_frags *f, void *key,
-				       unsigned int hash)
+/* TODO : call from rcu_read_lock() and no longer use refcount_inc_not_zero() */
+struct inet_frag_queue *inet_frag_find(struct netns_frags *nf, void *key)
 {
-	struct inet_frag_bucket *hb;
-	struct inet_frag_queue *q;
-	int depth = 0;
-
-	if (frag_mem_limit(nf) > nf->low_thresh)
-		inet_frag_schedule_worker(f);
-
-	hash &= (INETFRAGS_HASHSZ - 1);
-	hb = &f->hash[hash];
-
-	spin_lock(&hb->chain_lock);
-	hlist_for_each_entry(q, &hb->chain, list) {
-		if (q->net == nf && f->match(q, key)) {
-			refcount_inc(&q->refcnt);
-			spin_unlock(&hb->chain_lock);
-			return q;
-		}
-		depth++;
-	}
-	spin_unlock(&hb->chain_lock);
+	struct inet_frag_queue *fq;
 
-	if (depth <= INETFRAGS_MAXDEPTH)
-		return inet_frag_create(nf, f, key);
+	rcu_read_lock();
 
-	if (inet_frag_may_rebuild(f)) {
-		if (!f->rebuild)
-			f->rebuild = true;
-		inet_frag_schedule_worker(f);
+	fq = rhashtable_lookup(&nf->rhashtable, key, nf->f->rhash_params);
+	if (fq) {
+		if (!refcount_inc_not_zero(&fq->refcnt))
+			fq = NULL;
+		rcu_read_unlock();
+		return fq;
 	}
+	rcu_read_unlock();
 
-	return ERR_PTR(-ENOBUFS);
+	return inet_frag_create(nf, key);
 }
 EXPORT_SYMBOL(inet_frag_find);
-
-void inet_frag_maybe_warn_overflow(struct inet_frag_queue *q,
-				   const char *prefix)
-{
-	static const char msg[] = "inet_frag_find: Fragment hash bucket"
-		" list length grew over limit " __stringify(INETFRAGS_MAXDEPTH)
-		". Dropping fragment.\n";
-
-	if (PTR_ERR(q) == -ENOBUFS)
-		net_dbg_ratelimited("%s%s", prefix, msg);
-}
-EXPORT_SYMBOL(inet_frag_maybe_warn_overflow);
diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c
index bbf1b94942c0..994fa70a910f 100644
--- a/net/ipv4/ip_fragment.c
+++ b/net/ipv4/ip_fragment.c
@@ -57,27 +57,13 @@
  */
 static const char ip_frag_cache_name[] = "ip4-frags";
 
-struct ipfrag_skb_cb
-{
-	struct inet_skb_parm	h;
-	int			offset;
-};
-
-#define FRAG_CB(skb)	((struct ipfrag_skb_cb *)((skb)->cb))
-
 /* Describe an entry in the "incomplete datagrams" queue. */
 struct ipq {
 	struct inet_frag_queue q;
 
-	u32		user;
-	__be32		saddr;
-	__be32		daddr;
-	__be16		id;
-	u8		protocol;
 	u8		ecn; /* RFC3168 support */
 	u16		max_df_size; /* largest frag with DF set seen */
 	int             iif;
-	int             vif;   /* L3 master device index */
 	unsigned int    rid;
 	struct inet_peer *peer;
 };
@@ -89,49 +75,9 @@ static u8 ip4_frag_ecn(u8 tos)
 
 static struct inet_frags ip4_frags;
 
-int ip_frag_mem(struct net *net)
-{
-	return sum_frag_mem_limit(&net->ipv4.frags);
-}
-
 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;
-	int vif;
-};
-
-static unsigned int ipqhashfn(__be16 id, __be32 saddr, __be32 daddr, u8 prot)
-{
-	net_get_random_once(&ip4_frags.rnd, sizeof(ip4_frags.rnd));
-	return jhash_3words((__force u32)id << 16 | prot,
-			    (__force u32)saddr, (__force u32)daddr,
-			    ip4_frags.rnd);
-}
-
-static unsigned int ip4_hashfn(const struct inet_frag_queue *q)
-{
-	const struct ipq *ipq;
-
-	ipq = container_of(q, struct ipq, q);
-	return ipqhashfn(ipq->id, ipq->saddr, ipq->daddr, ipq->protocol);
-}
-
-static bool ip4_frag_match(const struct inet_frag_queue *q, const void *a)
-{
-	const struct ipq *qp;
-	const 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 &&
-		qp->vif == arg->vif;
-}
 
 static void ip4_frag_init(struct inet_frag_queue *q, const void *a)
 {
@@ -140,17 +86,12 @@ static void ip4_frag_init(struct inet_frag_queue *q, const void *a)
 					       frags);
 	struct net *net = container_of(ipv4, struct net, ipv4);
 
-	const struct ip4_create_arg *arg = a;
+	const struct frag_v4_compare_key *key = a;
 
-	qp->protocol = arg->iph->protocol;
-	qp->id = arg->iph->id;
-	qp->ecn = ip4_frag_ecn(arg->iph->tos);
-	qp->saddr = arg->iph->saddr;
-	qp->daddr = arg->iph->daddr;
-	qp->vif = arg->vif;
-	qp->user = arg->user;
+	q->key.v4 = *key;
+	qp->ecn = 0;
 	qp->peer = q->net->max_dist ?
-		inet_getpeer_v4(net->ipv4.peers, arg->iph->saddr, arg->vif, 1) :
+		inet_getpeer_v4(net->ipv4.peers, key->saddr, key->vif, 1) :
 		NULL;
 }
 
@@ -168,7 +109,7 @@ static void ip4_frag_free(struct inet_frag_queue *q)
 
 static void ipq_put(struct ipq *ipq)
 {
-	inet_frag_put(&ipq->q, &ip4_frags);
+	inet_frag_put(&ipq->q);
 }
 
 /* Kill ipq entry. It is not destroyed immediately,
@@ -176,7 +117,7 @@ static void ipq_put(struct ipq *ipq)
  */
 static void ipq_kill(struct ipq *ipq)
 {
-	inet_frag_kill(&ipq->q, &ip4_frags);
+	inet_frag_kill(&ipq->q);
 }
 
 static bool frag_expire_skip_icmp(u32 user)
@@ -194,8 +135,11 @@ static bool frag_expire_skip_icmp(u32 user)
 static void ip_expire(struct timer_list *t)
 {
 	struct inet_frag_queue *frag = from_timer(frag, t, timer);
-	struct ipq *qp;
+	const struct iphdr *iph;
+	struct sk_buff *head;
 	struct net *net;
+	struct ipq *qp;
+	int err;
 
 	qp = container_of(frag, struct ipq, q);
 	net = container_of(qp->q.net, struct net, ipv4.frags);
@@ -209,46 +153,38 @@ static void ip_expire(struct timer_list *t)
 	ipq_kill(qp);
 	__IP_INC_STATS(net, IPSTATS_MIB_REASMFAILS);
 
-	if (!inet_frag_evicting(&qp->q)) {
-		struct sk_buff *clone, *head = qp->q.fragments;
-		const struct iphdr *iph;
-		int err;
+	head = qp->q.fragments;
 
-		__IP_INC_STATS(net, IPSTATS_MIB_REASMTIMEOUT);
+	__IP_INC_STATS(net, IPSTATS_MIB_REASMTIMEOUT);
 
-		if (!(qp->q.flags & INET_FRAG_FIRST_IN) || !qp->q.fragments)
-			goto out;
+	if (!(qp->q.flags & INET_FRAG_FIRST_IN) || !head)
+		goto out;
 
-		head->dev = dev_get_by_index_rcu(net, qp->iif);
-		if (!head->dev)
-			goto out;
+	head->dev = dev_get_by_index_rcu(net, qp->iif);
+	if (!head->dev)
+		goto out;
 
 
-		/* skb has no dst, perform route lookup again */
-		iph = ip_hdr(head);
-		err = ip_route_input_noref(head, iph->daddr, iph->saddr,
+	/* skb has no dst, perform route lookup again */
+	iph = ip_hdr(head);
+	err = ip_route_input_noref(head, iph->daddr, iph->saddr,
 					   iph->tos, head->dev);
-		if (err)
-			goto out;
+	if (err)
+		goto out;
+
+	/* Only an end host needs to send an ICMP
+	 * "Fragment Reassembly Timeout" message, per RFC792.
+	 */
+	if (frag_expire_skip_icmp(qp->q.key.v4.user) &&
+	    (skb_rtable(head)->rt_type != RTN_LOCAL))
+		goto out;
+
+	skb_get(head);
+	spin_unlock(&qp->q.lock);
+	icmp_send(head, ICMP_TIME_EXCEEDED, ICMP_EXC_FRAGTIME, 0);
+	kfree_skb(head);
+	goto out_rcu_unlock;
 
-		/* Only an end host needs to send an ICMP
-		 * "Fragment Reassembly Timeout" message, per RFC792.
-		 */
-		if (frag_expire_skip_icmp(qp->user) &&
-		    (skb_rtable(head)->rt_type != RTN_LOCAL))
-			goto out;
-
-		clone = skb_clone(head, GFP_ATOMIC);
-
-		/* Send an ICMP "Fragment Reassembly Timeout" message. */
-		if (clone) {
-			spin_unlock(&qp->q.lock);
-			icmp_send(clone, ICMP_TIME_EXCEEDED,
-				  ICMP_EXC_FRAGTIME, 0);
-			consume_skb(clone);
-			goto out_rcu_unlock;
-		}
-	}
 out:
 	spin_unlock(&qp->q.lock);
 out_rcu_unlock:
@@ -262,21 +198,20 @@ out_rcu_unlock:
 static struct ipq *ip_find(struct net *net, struct iphdr *iph,
 			   u32 user, int vif)
 {
+	struct frag_v4_compare_key key = {
+		.saddr = iph->saddr,
+		.daddr = iph->daddr,
+		.user = user,
+		.vif = vif,
+		.id = iph->id,
+		.protocol = iph->protocol,
+	};
 	struct inet_frag_queue *q;
-	struct ip4_create_arg arg;
-	unsigned int hash;
-
-	arg.iph = iph;
-	arg.user = user;
-	arg.vif = vif;
 
-	hash = ipqhashfn(iph->id, iph->saddr, iph->daddr, iph->protocol);
-
-	q = inet_frag_find(&net->ipv4.frags, &ip4_frags, &arg, hash);
-	if (IS_ERR_OR_NULL(q)) {
-		inet_frag_maybe_warn_overflow(q, pr_fmt());
+	q = inet_frag_find(&net->ipv4.frags, &key);
+	if (!q)
 		return NULL;
-	}
+
 	return container_of(q, struct ipq, q);
 }
 
@@ -410,13 +345,13 @@ static int ip_frag_queue(struct ipq *qp, struct sk_buff *skb)
 	 * this fragment, right?
 	 */
 	prev = qp->q.fragments_tail;
-	if (!prev || FRAG_CB(prev)->offset < offset) {
+	if (!prev || prev->ip_defrag_offset < offset) {
 		next = NULL;
 		goto found;
 	}
 	prev = NULL;
 	for (next = qp->q.fragments; next != NULL; next = next->next) {
-		if (FRAG_CB(next)->offset >= offset)
+		if (next->ip_defrag_offset >= offset)
 			break;	/* bingo! */
 		prev = next;
 	}
@@ -427,7 +362,7 @@ found:
 	 * any overlaps are eliminated.
 	 */
 	if (prev) {
-		int i = (FRAG_CB(prev)->offset + prev->len) - offset;
+		int i = (prev->ip_defrag_offset + prev->len) - offset;
 
 		if (i > 0) {
 			offset += i;
@@ -444,8 +379,8 @@ found:
 
 	err = -ENOMEM;
 
-	while (next && FRAG_CB(next)->offset < end) {
-		int i = end - FRAG_CB(next)->offset; /* overlap is 'i' bytes */
+	while (next && next->ip_defrag_offset < end) {
+		int i = end - next->ip_defrag_offset; /* overlap is 'i' bytes */
 
 		if (i < next->len) {
 			/* Eat head of the next overlapped fragment
@@ -453,7 +388,7 @@ found:
 			 */
 			if (!pskb_pull(next, i))
 				goto err;
-			FRAG_CB(next)->offset += i;
+			next->ip_defrag_offset += i;
 			qp->q.meat -= i;
 			if (next->ip_summed != CHECKSUM_UNNECESSARY)
 				next->ip_summed = CHECKSUM_NONE;
@@ -477,7 +412,13 @@ found:
 		}
 	}
 
-	FRAG_CB(skb)->offset = offset;
+	/* Note : skb->ip_defrag_offset and skb->dev share the same location */
+	dev = skb->dev;
+	if (dev)
+		qp->iif = dev->ifindex;
+	/* Makes sure compiler wont do silly aliasing games */
+	barrier();
+	skb->ip_defrag_offset = offset;
 
 	/* Insert this fragment in the chain of fragments. */
 	skb->next = next;
@@ -488,11 +429,6 @@ found:
 	else
 		qp->q.fragments = skb;
 
-	dev = skb->dev;
-	if (dev) {
-		qp->iif = dev->ifindex;
-		skb->dev = NULL;
-	}
 	qp->q.stamp = skb->tstamp;
 	qp->q.meat += skb->len;
 	qp->ecn |= ecn;
@@ -568,7 +504,7 @@ static int ip_frag_reasm(struct ipq *qp, struct sk_buff *prev,
 	}
 
 	WARN_ON(!head);
-	WARN_ON(FRAG_CB(head)->offset != 0);
+	WARN_ON(head->ip_defrag_offset != 0);
 
 	/* Allocate a new buffer for the datagram. */
 	ihlen = ip_hdrlen(head);
@@ -656,7 +592,7 @@ out_nomem:
 	err = -ENOMEM;
 	goto out_fail;
 out_oversize:
-	net_info_ratelimited("Oversized IP packet from %pI4\n", &qp->saddr);
+	net_info_ratelimited("Oversized IP packet from %pI4\n", &qp->q.key.v4.saddr);
 out_fail:
 	__IP_INC_STATS(net, IPSTATS_MIB_REASMFAILS);
 	return err;
@@ -731,23 +667,23 @@ struct sk_buff *ip_check_defrag(struct net *net, struct sk_buff *skb, u32 user)
 EXPORT_SYMBOL(ip_check_defrag);
 
 #ifdef CONFIG_SYSCTL
-static int zero;
+static long zero;
 
 static struct ctl_table ip4_frags_ns_ctl_table[] = {
 	{
 		.procname	= "ipfrag_high_thresh",
 		.data		= &init_net.ipv4.frags.high_thresh,
-		.maxlen		= sizeof(int),
+		.maxlen		= sizeof(unsigned long),
 		.mode		= 0644,
-		.proc_handler	= proc_dointvec_minmax,
+		.proc_handler	= proc_doulongvec_minmax,
 		.extra1		= &init_net.ipv4.frags.low_thresh
 	},
 	{
 		.procname	= "ipfrag_low_thresh",
 		.data		= &init_net.ipv4.frags.low_thresh,
-		.maxlen		= sizeof(int),
+		.maxlen		= sizeof(unsigned long),
 		.mode		= 0644,
-		.proc_handler	= proc_dointvec_minmax,
+		.proc_handler	= proc_doulongvec_minmax,
 		.extra1		= &zero,
 		.extra2		= &init_net.ipv4.frags.high_thresh
 	},
@@ -846,6 +782,8 @@ static void __init ip4_frags_ctl_register(void)
 
 static int __net_init ipv4_frags_init_net(struct net *net)
 {
+	int res;
+
 	/* Fragment cache limits.
 	 *
 	 * The fragment memory accounting code, (tries to) account for
@@ -870,16 +808,21 @@ static int __net_init ipv4_frags_init_net(struct net *net)
 	net->ipv4.frags.timeout = IP_FRAG_TIME;
 
 	net->ipv4.frags.max_dist = 64;
-
-	inet_frags_init_net(&net->ipv4.frags);
-
-	return ip4_frags_ns_ctl_register(net);
+	net->ipv4.frags.f = &ip4_frags;
+
+	res = inet_frags_init_net(&net->ipv4.frags);
+	if (res < 0)
+		return res;
+	res = ip4_frags_ns_ctl_register(net);
+	if (res < 0)
+		inet_frags_exit_net(&net->ipv4.frags);
+	return res;
 }
 
 static void __net_exit ipv4_frags_exit_net(struct net *net)
 {
 	ip4_frags_ns_ctl_unregister(net);
-	inet_frags_exit_net(&net->ipv4.frags, &ip4_frags);
+	inet_frags_exit_net(&net->ipv4.frags);
 }
 
 static struct pernet_operations ip4_frags_ops = {
@@ -887,17 +830,49 @@ static struct pernet_operations ip4_frags_ops = {
 	.exit = ipv4_frags_exit_net,
 };
 
+
+static u32 ip4_key_hashfn(const void *data, u32 len, u32 seed)
+{
+	return jhash2(data,
+		      sizeof(struct frag_v4_compare_key) / sizeof(u32), seed);
+}
+
+static u32 ip4_obj_hashfn(const void *data, u32 len, u32 seed)
+{
+	const struct inet_frag_queue *fq = data;
+
+	return jhash2((const u32 *)&fq->key.v4,
+		      sizeof(struct frag_v4_compare_key) / sizeof(u32), seed);
+}
+
+static int ip4_obj_cmpfn(struct rhashtable_compare_arg *arg, const void *ptr)
+{
+	const struct frag_v4_compare_key *key = arg->key;
+	const struct inet_frag_queue *fq = ptr;
+
+	return !!memcmp(&fq->key, key, sizeof(*key));
+}
+
+static const struct rhashtable_params ip4_rhash_params = {
+	.head_offset		= offsetof(struct inet_frag_queue, node),
+	.key_offset		= offsetof(struct inet_frag_queue, key),
+	.key_len		= sizeof(struct frag_v4_compare_key),
+	.hashfn			= ip4_key_hashfn,
+	.obj_hashfn		= ip4_obj_hashfn,
+	.obj_cmpfn		= ip4_obj_cmpfn,
+	.automatic_shrinking	= true,
+};
+
 void __init ipfrag_init(void)
 {
-	ip4_frags_ctl_register();
-	register_pernet_subsys(&ip4_frags_ops);
-	ip4_frags.hashfn = ip4_hashfn;
 	ip4_frags.constructor = ip4_frag_init;
 	ip4_frags.destructor = ip4_frag_free;
 	ip4_frags.qsize = sizeof(struct ipq);
-	ip4_frags.match = ip4_frag_match;
 	ip4_frags.frag_expire = ip_expire;
 	ip4_frags.frags_cache_name = ip_frag_cache_name;
+	ip4_frags.rhash_params = ip4_rhash_params;
 	if (inet_frags_init(&ip4_frags))
 		panic("IP: failed to allocate ip4_frags cache\n");
+	ip4_frags_ctl_register();
+	register_pernet_subsys(&ip4_frags_ops);
 }
diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c
index adfb75340275..a058de677e94 100644
--- a/net/ipv4/proc.c
+++ b/net/ipv4/proc.c
@@ -54,7 +54,6 @@
 static int sockstat_seq_show(struct seq_file *seq, void *v)
 {
 	struct net *net = seq->private;
-	unsigned int frag_mem;
 	int orphans, sockets;
 
 	orphans = percpu_counter_sum_positive(&tcp_orphan_count);
@@ -72,8 +71,9 @@ static int sockstat_seq_show(struct seq_file *seq, void *v)
 		   sock_prot_inuse_get(net, &udplite_prot));
 	seq_printf(seq, "RAW: inuse %d\n",
 		   sock_prot_inuse_get(net, &raw_prot));
-	frag_mem = ip_frag_mem(net);
-	seq_printf(seq,  "FRAG: inuse %u memory %u\n", !!frag_mem, frag_mem);
+	seq_printf(seq,  "FRAG: inuse %u memory %lu\n",
+		   atomic_read(&net->ipv4.frags.rhashtable.nelems),
+		   frag_mem_limit(&net->ipv4.frags));
 	return 0;
 }