diff --git a/include/net/inet_frag.h b/include/net/inet_frag.h
index 32786a044718..3f237db0a426 100644
--- a/include/net/inet_frag.h
+++ b/include/net/inet_frag.h
@@ -1,10 +1,17 @@
 #ifndef __NET_FRAG_H__
 #define __NET_FRAG_H__
 
+#include <linux/percpu_counter.h>
+
 struct netns_frags {
 	int			nqueues;
-	atomic_t		mem;
 	struct list_head	lru_list;
+	spinlock_t		lru_lock;
+
+	/* The percpu_counter "mem" need to be cacheline aligned.
+	 *  mem.count must not share cacheline with other writers
+	 */
+	struct percpu_counter   mem ____cacheline_aligned_in_smp;
 
 	/* sysctls */
 	int			timeout;
@@ -13,12 +20,11 @@ struct netns_frags {
 };
 
 struct inet_frag_queue {
-	struct hlist_node	list;
-	struct netns_frags	*net;
-	struct list_head	lru_list;   /* lru list member */
 	spinlock_t		lock;
-	atomic_t		refcnt;
 	struct timer_list	timer;      /* when will this queue expire? */
+	struct list_head	lru_list;   /* lru list member */
+	struct hlist_node	list;
+	atomic_t		refcnt;
 	struct sk_buff		*fragments; /* list of received fragments */
 	struct sk_buff		*fragments_tail;
 	ktime_t			stamp;
@@ -31,24 +37,29 @@ struct inet_frag_queue {
 #define INET_FRAG_LAST_IN	1
 
 	u16			max_size;
+
+	struct netns_frags	*net;
 };
 
 #define INETFRAGS_HASHSZ		64
 
 struct inet_frags {
 	struct hlist_head	hash[INETFRAGS_HASHSZ];
-	rwlock_t		lock;
-	u32			rnd;
-	int			qsize;
+	/* This rwlock is a global lock (seperate per IPv4, IPv6 and
+	 * netfilter). Important to keep this on a seperate cacheline.
+	 */
+	rwlock_t		lock ____cacheline_aligned_in_smp;
 	int			secret_interval;
 	struct timer_list	secret_timer;
+	u32			rnd;
+	int			qsize;
 
 	unsigned int		(*hashfn)(struct inet_frag_queue *);
+	bool			(*match)(struct inet_frag_queue *q, void *arg);
 	void			(*constructor)(struct inet_frag_queue *q,
 						void *arg);
 	void			(*destructor)(struct inet_frag_queue *);
 	void			(*skb_free)(struct sk_buff *);
-	bool			(*match)(struct inet_frag_queue *q, void *arg);
 	void			(*frag_expire)(unsigned long data);
 };
 
@@ -72,4 +83,59 @@ static inline void inet_frag_put(struct inet_frag_queue *q, struct inet_frags *f
 		inet_frag_destroy(q, f, NULL);
 }
 
+/* Memory Tracking Functions. */
+
+/* The default percpu_counter batch size is not big enough to scale to
+ * fragmentation mem acct sizes.
+ * The mem size of a 64K fragment is approx:
+ *  (44 fragments * 2944 truesize) + frag_queue struct(200) = 129736 bytes
+ */
+static unsigned int frag_percpu_counter_batch = 130000;
+
+static inline int frag_mem_limit(struct netns_frags *nf)
+{
+	return percpu_counter_read(&nf->mem);
+}
+
+static inline void sub_frag_mem_limit(struct inet_frag_queue *q, int i)
+{
+	__percpu_counter_add(&q->net->mem, -i, frag_percpu_counter_batch);
+}
+
+static inline void add_frag_mem_limit(struct inet_frag_queue *q, int i)
+{
+	__percpu_counter_add(&q->net->mem, i, frag_percpu_counter_batch);
+}
+
+static inline void init_frag_mem_limit(struct netns_frags *nf)
+{
+	percpu_counter_init(&nf->mem, 0);
+}
+
+static inline int sum_frag_mem_limit(struct netns_frags *nf)
+{
+	return percpu_counter_sum_positive(&nf->mem);
+}
+
+static inline void inet_frag_lru_move(struct inet_frag_queue *q)
+{
+	spin_lock(&q->net->lru_lock);
+	list_move_tail(&q->lru_list, &q->net->lru_list);
+	spin_unlock(&q->net->lru_lock);
+}
+
+static inline void inet_frag_lru_del(struct inet_frag_queue *q)
+{
+	spin_lock(&q->net->lru_lock);
+	list_del(&q->lru_list);
+	spin_unlock(&q->net->lru_lock);
+}
+
+static inline void inet_frag_lru_add(struct netns_frags *nf,
+				     struct inet_frag_queue *q)
+{
+	spin_lock(&nf->lru_lock);
+	list_add_tail(&q->lru_list, &nf->lru_list);
+	spin_unlock(&nf->lru_lock);
+}
 #endif
diff --git a/include/net/ipv6.h b/include/net/ipv6.h
index c1878f7049c8..dc30b60975ef 100644
--- a/include/net/ipv6.h
+++ b/include/net/ipv6.h
@@ -288,7 +288,7 @@ static inline int ip6_frag_nqueues(struct net *net)
 
 static inline int ip6_frag_mem(struct net *net)
 {
-	return atomic_read(&net->ipv6.frags.mem);
+	return sum_frag_mem_limit(&net->ipv6.frags);
 }
 #endif
 
diff --git a/net/ipv4/inet_fragment.c b/net/ipv4/inet_fragment.c
index 4750d2b74d79..2e453bde6992 100644
--- a/net/ipv4/inet_fragment.c
+++ b/net/ipv4/inet_fragment.c
@@ -73,8 +73,9 @@ EXPORT_SYMBOL(inet_frags_init);
 void inet_frags_init_net(struct netns_frags *nf)
 {
 	nf->nqueues = 0;
-	atomic_set(&nf->mem, 0);
+	init_frag_mem_limit(nf);
 	INIT_LIST_HEAD(&nf->lru_list);
+	spin_lock_init(&nf->lru_lock);
 }
 EXPORT_SYMBOL(inet_frags_init_net);
 
@@ -91,6 +92,8 @@ void inet_frags_exit_net(struct netns_frags *nf, struct inet_frags *f)
 	local_bh_disable();
 	inet_frag_evictor(nf, f, true);
 	local_bh_enable();
+
+	percpu_counter_destroy(&nf->mem);
 }
 EXPORT_SYMBOL(inet_frags_exit_net);
 
@@ -98,9 +101,9 @@ static inline void fq_unlink(struct inet_frag_queue *fq, struct inet_frags *f)
 {
 	write_lock(&f->lock);
 	hlist_del(&fq->list);
-	list_del(&fq->lru_list);
 	fq->net->nqueues--;
 	write_unlock(&f->lock);
+	inet_frag_lru_del(fq);
 }
 
 void inet_frag_kill(struct inet_frag_queue *fq, struct inet_frags *f)
@@ -117,12 +120,8 @@ void inet_frag_kill(struct inet_frag_queue *fq, struct inet_frags *f)
 EXPORT_SYMBOL(inet_frag_kill);
 
 static inline void frag_kfree_skb(struct netns_frags *nf, struct inet_frags *f,
-		struct sk_buff *skb, int *work)
+		struct sk_buff *skb)
 {
-	if (work)
-		*work -= skb->truesize;
-
-	atomic_sub(skb->truesize, &nf->mem);
 	if (f->skb_free)
 		f->skb_free(skb);
 	kfree_skb(skb);
@@ -133,6 +132,7 @@ void inet_frag_destroy(struct inet_frag_queue *q, struct inet_frags *f,
 {
 	struct sk_buff *fp;
 	struct netns_frags *nf;
+	unsigned int sum, sum_truesize = 0;
 
 	WARN_ON(!(q->last_in & INET_FRAG_COMPLETE));
 	WARN_ON(del_timer(&q->timer) != 0);
@@ -143,13 +143,14 @@ void inet_frag_destroy(struct inet_frag_queue *q, struct inet_frags *f,
 	while (fp) {
 		struct sk_buff *xp = fp->next;
 
-		frag_kfree_skb(nf, f, fp, work);
+		sum_truesize += fp->truesize;
+		frag_kfree_skb(nf, f, fp);
 		fp = xp;
 	}
-
+	sum = sum_truesize + f->qsize;
 	if (work)
-		*work -= f->qsize;
-	atomic_sub(f->qsize, &nf->mem);
+		*work -= sum;
+	sub_frag_mem_limit(q, sum);
 
 	if (f->destructor)
 		f->destructor(q);
@@ -164,22 +165,23 @@ int inet_frag_evictor(struct netns_frags *nf, struct inet_frags *f, bool force)
 	int work, evicted = 0;
 
 	if (!force) {
-		if (atomic_read(&nf->mem) <= nf->high_thresh)
+		if (frag_mem_limit(nf) <= nf->high_thresh)
 			return 0;
 	}
 
-	work = atomic_read(&nf->mem) - nf->low_thresh;
+	work = frag_mem_limit(nf) - nf->low_thresh;
 	while (work > 0) {
-		read_lock(&f->lock);
+		spin_lock(&nf->lru_lock);
+
 		if (list_empty(&nf->lru_list)) {
-			read_unlock(&f->lock);
+			spin_unlock(&nf->lru_lock);
 			break;
 		}
 
 		q = list_first_entry(&nf->lru_list,
 				struct inet_frag_queue, lru_list);
 		atomic_inc(&q->refcnt);
-		read_unlock(&f->lock);
+		spin_unlock(&nf->lru_lock);
 
 		spin_lock(&q->lock);
 		if (!(q->last_in & INET_FRAG_COMPLETE))
@@ -233,9 +235,9 @@ static struct inet_frag_queue *inet_frag_intern(struct netns_frags *nf,
 
 	atomic_inc(&qp->refcnt);
 	hlist_add_head(&qp->list, &f->hash[hash]);
-	list_add_tail(&qp->lru_list, &nf->lru_list);
 	nf->nqueues++;
 	write_unlock(&f->lock);
+	inet_frag_lru_add(nf, qp);
 	return qp;
 }
 
@@ -250,7 +252,8 @@ static struct inet_frag_queue *inet_frag_alloc(struct netns_frags *nf,
 
 	q->net = nf;
 	f->constructor(q, arg);
-	atomic_add(f->qsize, &nf->mem);
+	add_frag_mem_limit(q, f->qsize);
+
 	setup_timer(&q->timer, f->frag_expire, (unsigned long)q);
 	spin_lock_init(&q->lock);
 	atomic_set(&q->refcnt, 1);
diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c
index f55a4e61bfb8..1211613c6c34 100644
--- a/net/ipv4/ip_fragment.c
+++ b/net/ipv4/ip_fragment.c
@@ -122,7 +122,7 @@ int ip_frag_nqueues(struct net *net)
 
 int ip_frag_mem(struct net *net)
 {
-	return atomic_read(&net->ipv4.frags.mem);
+	return sum_frag_mem_limit(&net->ipv4.frags);
 }
 
 static int ip_frag_reasm(struct ipq *qp, struct sk_buff *prev,
@@ -161,13 +161,6 @@ static bool ip4_frag_match(struct inet_frag_queue *q, void *a)
 		qp->user == arg->user;
 }
 
-/* Memory Tracking Functions. */
-static void frag_kfree_skb(struct netns_frags *nf, struct sk_buff *skb)
-{
-	atomic_sub(skb->truesize, &nf->mem);
-	kfree_skb(skb);
-}
-
 static void ip4_frag_init(struct inet_frag_queue *q, void *a)
 {
 	struct ipq *qp = container_of(q, struct ipq, q);
@@ -340,6 +333,7 @@ static inline int ip_frag_too_far(struct ipq *qp)
 static int ip_frag_reinit(struct ipq *qp)
 {
 	struct sk_buff *fp;
+	unsigned int sum_truesize = 0;
 
 	if (!mod_timer(&qp->q.timer, jiffies + qp->q.net->timeout)) {
 		atomic_inc(&qp->q.refcnt);
@@ -349,9 +343,12 @@ static int ip_frag_reinit(struct ipq *qp)
 	fp = qp->q.fragments;
 	do {
 		struct sk_buff *xp = fp->next;
-		frag_kfree_skb(qp->q.net, fp);
+
+		sum_truesize += fp->truesize;
+		kfree_skb(fp);
 		fp = xp;
 	} while (fp);
+	sub_frag_mem_limit(&qp->q, sum_truesize);
 
 	qp->q.last_in = 0;
 	qp->q.len = 0;
@@ -496,7 +493,8 @@ found:
 				qp->q.fragments = next;
 
 			qp->q.meat -= free_it->len;
-			frag_kfree_skb(qp->q.net, free_it);
+			sub_frag_mem_limit(&qp->q, free_it->truesize);
+			kfree_skb(free_it);
 		}
 	}
 
@@ -519,7 +517,7 @@ found:
 	qp->q.stamp = skb->tstamp;
 	qp->q.meat += skb->len;
 	qp->ecn |= ecn;
-	atomic_add(skb->truesize, &qp->q.net->mem);
+	add_frag_mem_limit(&qp->q, skb->truesize);
 	if (offset == 0)
 		qp->q.last_in |= INET_FRAG_FIRST_IN;
 
@@ -531,9 +529,7 @@ found:
 	    qp->q.meat == qp->q.len)
 		return ip_frag_reasm(qp, prev, dev);
 
-	write_lock(&ip4_frags.lock);
-	list_move_tail(&qp->q.lru_list, &qp->q.net->lru_list);
-	write_unlock(&ip4_frags.lock);
+	inet_frag_lru_move(&qp->q);
 	return -EINPROGRESS;
 
 err:
@@ -617,7 +613,7 @@ static int ip_frag_reasm(struct ipq *qp, struct sk_buff *prev,
 		head->len -= clone->len;
 		clone->csum = 0;
 		clone->ip_summed = head->ip_summed;
-		atomic_add(clone->truesize, &qp->q.net->mem);
+		add_frag_mem_limit(&qp->q, clone->truesize);
 	}
 
 	skb_push(head, head->data - skb_network_header(head));
@@ -645,7 +641,7 @@ static int ip_frag_reasm(struct ipq *qp, struct sk_buff *prev,
 		}
 		fp = next;
 	}
-	atomic_sub(sum_truesize, &qp->q.net->mem);
+	sub_frag_mem_limit(&qp->q, sum_truesize);
 
 	head->next = NULL;
 	head->dev = dev;
diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c
index 3dacecc99065..c674f158efa8 100644
--- a/net/ipv6/netfilter/nf_conntrack_reasm.c
+++ b/net/ipv6/netfilter/nf_conntrack_reasm.c
@@ -319,7 +319,7 @@ found:
 	fq->q.meat += skb->len;
 	if (payload_len > fq->q.max_size)
 		fq->q.max_size = payload_len;
-	atomic_add(skb->truesize, &fq->q.net->mem);
+	add_frag_mem_limit(&fq->q, skb->truesize);
 
 	/* The first fragment.
 	 * nhoffset is obtained from the first fragment, of course.
@@ -328,9 +328,8 @@ found:
 		fq->nhoffset = nhoff;
 		fq->q.last_in |= INET_FRAG_FIRST_IN;
 	}
-	write_lock(&nf_frags.lock);
-	list_move_tail(&fq->q.lru_list, &fq->q.net->lru_list);
-	write_unlock(&nf_frags.lock);
+
+	inet_frag_lru_move(&fq->q);
 	return 0;
 
 discard_fq:
@@ -398,7 +397,7 @@ nf_ct_frag6_reasm(struct frag_queue *fq, struct net_device *dev)
 		clone->ip_summed = head->ip_summed;
 
 		NFCT_FRAG6_CB(clone)->orig = NULL;
-		atomic_add(clone->truesize, &fq->q.net->mem);
+		add_frag_mem_limit(&fq->q, clone->truesize);
 	}
 
 	/* We have to remove fragment header from datagram and to relocate
@@ -422,7 +421,7 @@ nf_ct_frag6_reasm(struct frag_queue *fq, struct net_device *dev)
 			head->csum = csum_add(head->csum, fp->csum);
 		head->truesize += fp->truesize;
 	}
-	atomic_sub(head->truesize, &fq->q.net->mem);
+	sub_frag_mem_limit(&fq->q, head->truesize);
 
 	head->local_df = 1;
 	head->next = NULL;
diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c
index e5253ec9e0fc..bab2c270f292 100644
--- a/net/ipv6/reassembly.c
+++ b/net/ipv6/reassembly.c
@@ -327,7 +327,7 @@ found:
 	}
 	fq->q.stamp = skb->tstamp;
 	fq->q.meat += skb->len;
-	atomic_add(skb->truesize, &fq->q.net->mem);
+	add_frag_mem_limit(&fq->q, skb->truesize);
 
 	/* The first fragment.
 	 * nhoffset is obtained from the first fragment, of course.
@@ -341,9 +341,7 @@ found:
 	    fq->q.meat == fq->q.len)
 		return ip6_frag_reasm(fq, prev, dev);
 
-	write_lock(&ip6_frags.lock);
-	list_move_tail(&fq->q.lru_list, &fq->q.net->lru_list);
-	write_unlock(&ip6_frags.lock);
+	inet_frag_lru_move(&fq->q);
 	return -1;
 
 discard_fq:
@@ -429,7 +427,7 @@ static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *prev,
 		head->len -= clone->len;
 		clone->csum = 0;
 		clone->ip_summed = head->ip_summed;
-		atomic_add(clone->truesize, &fq->q.net->mem);
+		add_frag_mem_limit(&fq->q, clone->truesize);
 	}
 
 	/* We have to remove fragment header from datagram and to relocate
@@ -467,7 +465,7 @@ static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *prev,
 		}
 		fp = next;
 	}
-	atomic_sub(sum_truesize, &fq->q.net->mem);
+	sub_frag_mem_limit(&fq->q, sum_truesize);
 
 	head->next = NULL;
 	head->dev = dev;