1 files changed, 90 insertions, 9 deletions

diff --git a/include/net/inet_frag.h b/include/net/inet_frag.h
index 32786a044718..0a1dcc2fa2f5 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 +37,36 @@ struct inet_frag_queue {
 #define INET_FRAG_LAST_IN	1
 
 	u16			max_size;
+
+	struct netns_frags	*net;
 };
 
 #define INETFRAGS_HASHSZ		64
 
+/* averaged:
+ * max_depth = default ipfrag_high_thresh / INETFRAGS_HASHSZ /
+ *	       rounded up (SKB_TRUELEN(0) + sizeof(struct ipq or
+ *	       struct frag_queue))
+ */
+#define INETFRAGS_MAXDEPTH		128
+
 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);
 };
 
@@ -65,6 +83,8 @@ int inet_frag_evictor(struct netns_frags *nf, struct inet_frags *f, bool force);
 struct inet_frag_queue *inet_frag_find(struct netns_frags *nf,
 		struct inet_frags *f, void *key, unsigned int hash)
 	__releases(&f->lock);
+void inet_frag_maybe_warn_overflow(struct inet_frag_queue *q,
+				   const char *prefix);
 
 static inline void inet_frag_put(struct inet_frag_queue *q, struct inet_frags *f)
 {
@@ -72,4 +92,65 @@ 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)
+{
+	int res;
+
+	local_bh_disable();
+	res = percpu_counter_sum_positive(&nf->mem);
+	local_bh_enable();
+
+	return res;
+}
+
+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