This is the 4.4.174 stable release

-----BEGIN PGP SIGNATURE-----
 
 iQIzBAABCAAdFiEEZH8oZUiU471FcZm+ONu9yGCSaT4FAlxdWR4ACgkQONu9yGCS
 aT5Y0Q//YFvFKlYGFDE3yg3Q81b4O49bkO5bpgGqGs6cn7vfY4WxlKXDa4olHKdk
 DLsehAjLRV0MlJfV9kfPT03nCecyjzs8m4AH7OwqyujW2ZCM+YCOR2gx1fCK5KNb
 twO7mTIBKv38T2ilGLYqXBf1pha9DA2RMMKWCuMRIOagC/OYsfq2RkSnKH2p0gFP
 plsSpEYJ5rtVbk2Dxnf5y+simJmtzyiHoIBZJZq7tCRVT9XhJqMbxHeGFUwTFj7W
 AdWAx/zWM/OBe+NvSmqIdaiYxaNb91RjfeMZQrafRS/KcgsD80nNmT6Kk07NXfnT
 3eUHq2i+S8bokadcfcjA6UhT48kqh79vyllm71DeaNkuvaapPxkYYKESeNpeOcop
 06MyENBwUYrTCkuc3raC/0FLJ7Csxoe51V6M9VdQjtsvnX35DcX+9YiwGn32N5h/
 q9qdXJH6TaYhSGQozcAVhHWl5U1Nl76vw0LQXagvvUqJ4lCZVlYCptwzr7e2A6/Y
 WQQeFwUSp4Niw0m2HXmBP9unIzt5MhjknKrb3z962S48Ie4hM8LC/g/jwhFOrj6U
 XxuatqiUbjt8yyteSd1gVf82vjkDqR1YLk6qXFwvEJpPtZ7DmOQ8CgE2VLS+rbXP
 xFz5bZXuvW7kgqdm41DjHWqq8rT/81pooeGUPSLhY4VMUQ58poE=
 =hOLk
 -----END PGP SIGNATURE-----

Merge 4.4.174 into android-4.4

Changes in 4.4.174
	inet: frags: change inet_frags_init_net() return value
	inet: frags: add a pointer to struct netns_frags
	inet: frags: refactor ipfrag_init()
	inet: frags: refactor ipv6_frag_init()
	inet: frags: refactor lowpan_net_frag_init()
	rhashtable: add rhashtable_lookup_get_insert_key()
	rhashtable: Add rhashtable_lookup()
	rhashtable: add schedule points
	inet: frags: use rhashtables for reassembly units
	net: ieee802154: 6lowpan: fix frag reassembly
	ipfrag: really prevent allocation on netns exit
	inet: frags: remove some helpers
	inet: frags: get rif of inet_frag_evicting()
	inet: frags: remove inet_frag_maybe_warn_overflow()
	inet: frags: break the 2GB limit for frags storage
	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
	inet: frags: fix ip6frag_low_thresh boundary
	ip: discard IPv4 datagrams with overlapping segments.
	net: modify skb_rbtree_purge to return the truesize of all purged skbs.
	ipv6: defrag: drop non-last frags smaller than min mtu
	net: pskb_trim_rcsum() and CHECKSUM_COMPLETE are friends
	ip: use rb trees for IP frag queue.
	ip: add helpers to process in-order fragments faster.
	ip: process in-order fragments efficiently
	ip: frags: fix crash in ip_do_fragment()
	ipv4: frags: precedence bug in ip_expire()
	inet: frags: better deal with smp races
	net: fix pskb_trim_rcsum_slow() with odd trim offset
	net: ipv4: do not handle duplicate fragments as overlapping
	rcu: Force boolean subscript for expedited stall warnings
	Linux 4.4.174

Change-Id: I47eace4f47ffe0bf16b29615d09ed903c40a272b
Signed-off-by: Greg Kroah-Hartman <gregkh@google.com>

Documentation/networking/ip-sysctl.txt

@@ -112,14 +112,11 @@ min_adv_mss - INTEGER
 
 IP Fragmentation:
 
-ipfrag_high_thresh - INTEGER
+ipfrag_high_thresh - LONG INTEGER
-	Maximum memory used to reassemble IP fragments. When
+	Maximum memory used to reassemble IP fragments.
-	ipfrag_high_thresh bytes of memory is allocated for this purpose,
-	the fragment handler will toss packets until ipfrag_low_thresh
-	is reached. This also serves as a maximum limit to namespaces
-	different from the initial one.
 
-ipfrag_low_thresh - INTEGER
+ipfrag_low_thresh - LONG INTEGER
+	(Obsolete since linux-4.17)
 	Maximum memory used to reassemble IP fragments before the kernel
 	begins to remove incomplete fragment queues to free up resources.
 	The kernel still accepts new fragments for defragmentation.

Makefile

@@ -1,6 +1,6 @@
 VERSION = 4
 PATCHLEVEL = 4
-SUBLEVEL = 173
+SUBLEVEL = 174
 EXTRAVERSION =
 NAME = Blurry Fish Butt
 

include/linux/rhashtable.h

@@ -133,23 +133,23 @@ struct rhashtable_params {
 /**
  * struct rhashtable - Hash table handle
  * @tbl: Bucket table
- * @nelems: Number of elements in table
  * @key_len: Key length for hashfn
  * @elasticity: Maximum chain length before rehash
  * @p: Configuration parameters
  * @run_work: Deferred worker to expand/shrink asynchronously
  * @mutex: Mutex to protect current/future table swapping
  * @lock: Spin lock to protect walker list
+ * @nelems: Number of elements in table
  */
 struct rhashtable {
 	struct bucket_table __rcu	*tbl;
-	atomic_t			nelems;
 	unsigned int			key_len;
 	unsigned int			elasticity;
 	struct rhashtable_params	p;
 	struct work_struct		run_work;
 	struct mutex                    mutex;
 	spinlock_t			lock;
+	atomic_t			nelems;
 };
 
 /**
@@ -343,7 +343,8 @@ int rhashtable_init(struct rhashtable *ht,
 struct bucket_table *rhashtable_insert_slow(struct rhashtable *ht,
 					    const void *key,
 					    struct rhash_head *obj,
-					    struct bucket_table *old_tbl);
+					    struct bucket_table *old_tbl,
+					    void **data);
 int rhashtable_insert_rehash(struct rhashtable *ht, struct bucket_table *tbl);
 
 int rhashtable_walk_init(struct rhashtable *ht, struct rhashtable_iter *iter);
@@ -514,18 +515,8 @@ static inline int rhashtable_compare(struct rhashtable_compare_arg *arg,
 	return memcmp(ptr + ht->p.key_offset, arg->key, ht->p.key_len);
 }
 
-/**
+/* Internal function, do not use. */
- * rhashtable_lookup_fast - search hash table, inlined version
+static inline struct rhash_head *__rhashtable_lookup(
- * @ht:		hash table
- * @key:	the pointer to the key
- * @params:	hash table parameters
- *
- * Computes the hash value for the key and traverses the bucket chain looking
- * for a entry with an identical key. The first matching entry is returned.
- *
- * Returns the first entry on which the compare function returned true.
- */
-static inline void *rhashtable_lookup_fast(
 	struct rhashtable *ht, const void *key,
 	const struct rhashtable_params params)
 {
@@ -537,8 +528,6 @@ static inline void *rhashtable_lookup_fast(
 	struct rhash_head *he;
 	unsigned int hash;
 
-	rcu_read_lock();
-
 	tbl = rht_dereference_rcu(ht->tbl, ht);
 restart:
 	hash = rht_key_hashfn(ht, tbl, key, params);
@@ -547,8 +536,7 @@ restart:
 		    params.obj_cmpfn(&arg, rht_obj(ht, he)) :
 		    rhashtable_compare(&arg, rht_obj(ht, he)))
 			continue;
-		rcu_read_unlock();
+		return he;
-		return rht_obj(ht, he);
 	}
 
 	/* Ensure we see any new tables. */
@@ -557,13 +545,64 @@ restart:
 	tbl = rht_dereference_rcu(tbl->future_tbl, ht);
 	if (unlikely(tbl))
 		goto restart;
-	rcu_read_unlock();
 
 	return NULL;
 }
 
-/* Internal function, please use rhashtable_insert_fast() instead */
+/**
-static inline int __rhashtable_insert_fast(
+ * rhashtable_lookup - search hash table
+ * @ht:		hash table
+ * @key:	the pointer to the key
+ * @params:	hash table parameters
+ *
+ * Computes the hash value for the key and traverses the bucket chain looking
+ * for a entry with an identical key. The first matching entry is returned.
+ *
+ * This must only be called under the RCU read lock.
+ *
+ * Returns the first entry on which the compare function returned true.
+ */
+static inline void *rhashtable_lookup(
+	struct rhashtable *ht, const void *key,
+	const struct rhashtable_params params)
+{
+	struct rhash_head *he = __rhashtable_lookup(ht, key, params);
+
+	return he ? rht_obj(ht, he) : NULL;
+}
+
+/**
+ * rhashtable_lookup_fast - search hash table, without RCU read lock
+ * @ht:		hash table
+ * @key:	the pointer to the key
+ * @params:	hash table parameters
+ *
+ * Computes the hash value for the key and traverses the bucket chain looking
+ * for a entry with an identical key. The first matching entry is returned.
+ *
+ * Only use this function when you have other mechanisms guaranteeing
+ * that the object won't go away after the RCU read lock is released.
+ *
+ * Returns the first entry on which the compare function returned true.
+ */
+static inline void *rhashtable_lookup_fast(
+	struct rhashtable *ht, const void *key,
+	const struct rhashtable_params params)
+{
+	void *obj;
+
+	rcu_read_lock();
+	obj = rhashtable_lookup(ht, key, params);
+	rcu_read_unlock();
+
+	return obj;
+}
+
+/* Internal function, please use rhashtable_insert_fast() instead. This
+ * function returns the existing element already in hashes in there is a clash,
+ * otherwise it returns an error via ERR_PTR().
+ */
+static inline void *__rhashtable_insert_fast(
 	struct rhashtable *ht, const void *key, struct rhash_head *obj,
 	const struct rhashtable_params params)
 {
@@ -576,6 +615,7 @@ static inline int __rhashtable_insert_fast(
 	spinlock_t *lock;
 	unsigned int elasticity;
 	unsigned int hash;
+	void *data = NULL;
 	int err;
 
 restart:
@@ -600,11 +640,14 @@ restart:
 
 	new_tbl = rht_dereference_rcu(tbl->future_tbl, ht);
 	if (unlikely(new_tbl)) {
-		tbl = rhashtable_insert_slow(ht, key, obj, new_tbl);
+		tbl = rhashtable_insert_slow(ht, key, obj, new_tbl, &data);
 		if (!IS_ERR_OR_NULL(tbl))
 			goto slow_path;
 
 		err = PTR_ERR(tbl);
+		if (err == -EEXIST)
+			err = 0;
+
 		goto out;
 	}
 
@@ -618,25 +661,25 @@ slow_path:
 		err = rhashtable_insert_rehash(ht, tbl);
 		rcu_read_unlock();
 		if (err)
-			return err;
+			return ERR_PTR(err);
 
 		goto restart;
 	}
 
-	err = -EEXIST;
+	err = 0;
 	elasticity = ht->elasticity;
 	rht_for_each(head, tbl, hash) {
 		if (key &&
 		    unlikely(!(params.obj_cmpfn ?
 			       params.obj_cmpfn(&arg, rht_obj(ht, head)) :
-			       rhashtable_compare(&arg, rht_obj(ht, head)))))
+			       rhashtable_compare(&arg, rht_obj(ht, head))))) {
+			data = rht_obj(ht, head);
 			goto out;
+		}
 		if (!--elasticity)
 			goto slow_path;
 	}
 
-	err = 0;
-
 	head = rht_dereference_bucket(tbl->buckets[hash], tbl, hash);
 
 	RCU_INIT_POINTER(obj->next, head);
@@ -651,7 +694,7 @@ out:
 	spin_unlock_bh(lock);
 	rcu_read_unlock();
 
-	return err;
+	return err ? ERR_PTR(err) : data;
 }
 
 /**
@@ -674,7 +717,13 @@ static inline int rhashtable_insert_fast(
 	struct rhashtable *ht, struct rhash_head *obj,
 	const struct rhashtable_params params)
 {
-	return __rhashtable_insert_fast(ht, NULL, obj, params);
+	void *ret;
+
+	ret = __rhashtable_insert_fast(ht, NULL, obj, params);
+	if (IS_ERR(ret))
+		return PTR_ERR(ret);
+
+	return ret == NULL ? 0 : -EEXIST;
 }
 
 /**
@@ -703,11 +752,15 @@ static inline int rhashtable_lookup_insert_fast(
 	const struct rhashtable_params params)
 {
 	const char *key = rht_obj(ht, obj);
+	void *ret;
 
 	BUG_ON(ht->p.obj_hashfn);
 
-	return __rhashtable_insert_fast(ht, key + ht->p.key_offset, obj,
+	ret = __rhashtable_insert_fast(ht, key + ht->p.key_offset, obj, params);
-					params);
+	if (IS_ERR(ret))
+		return PTR_ERR(ret);
+
+	return ret == NULL ? 0 : -EEXIST;
 }
 
 /**
@@ -735,6 +788,32 @@ static inline int rhashtable_lookup_insert_fast(
 static inline int rhashtable_lookup_insert_key(
 	struct rhashtable *ht, const void *key, struct rhash_head *obj,
 	const struct rhashtable_params params)
+{
+	void *ret;
+
+	BUG_ON(!ht->p.obj_hashfn || !key);
+
+	ret = __rhashtable_insert_fast(ht, key, obj, params);
+	if (IS_ERR(ret))
+		return PTR_ERR(ret);
+
+	return ret == NULL ? 0 : -EEXIST;
+}
+
+/**
+ * rhashtable_lookup_get_insert_key - lookup and insert object into hash table
+ * @ht:		hash table
+ * @obj:	pointer to hash head inside object
+ * @params:	hash table parameters
+ * @data:	pointer to element data already in hashes
+ *
+ * Just like rhashtable_lookup_insert_key(), but this function returns the
+ * object if it exists, NULL if it does not and the insertion was successful,
+ * and an ERR_PTR otherwise.
+ */
+static inline void *rhashtable_lookup_get_insert_key(
+	struct rhashtable *ht, const void *key, struct rhash_head *obj,
+	const struct rhashtable_params params)
 {
 	BUG_ON(!ht->p.obj_hashfn || !key);
 

include/linux/skbuff.h

@@ -556,9 +556,14 @@ struct sk_buff {
 				struct skb_mstamp skb_mstamp;
 			};
 		};
-		struct rb_node	rbnode; /* used in netem & tcp stack */
+		struct rb_node		rbnode; /* used in netem, ip4 defrag, and tcp stack */
 	};
-	struct sock		*sk;
+
+	union {
+		struct sock		*sk;
+		int			ip_defrag_offset;
+	};
+
 	struct net_device	*dev;
 
 	/*
@@ -2273,7 +2278,7 @@ static inline void __skb_queue_purge(struct sk_buff_head *list)
 		kfree_skb(skb);
 }
 
-void skb_rbtree_purge(struct rb_root *root);
+unsigned int skb_rbtree_purge(struct rb_root *root);
 
 void *netdev_alloc_frag(unsigned int fragsz);
 
@@ -2791,6 +2796,7 @@ static inline unsigned char *skb_push_rcsum(struct sk_buff *skb,
 	return skb->data;
 }
 
+int pskb_trim_rcsum_slow(struct sk_buff *skb, unsigned int len);
 /**
  *	pskb_trim_rcsum - trim received skb and update checksum
  *	@skb: buffer to trim
@@ -2805,9 +2811,7 @@ static inline int pskb_trim_rcsum(struct sk_buff *skb, unsigned int len)
 {
 	if (likely(len >= skb->len))
 		return 0;
-	if (skb->ip_summed == CHECKSUM_COMPLETE)
+	return pskb_trim_rcsum_slow(skb, len);
-		skb->ip_summed = CHECKSUM_NONE;
-	return __pskb_trim(skb, len);
 }
 
 #define rb_to_skb(rb) rb_entry_safe(rb, struct sk_buff, rbnode)

include/net/inet_frag.h

@@ -1,13 +1,19 @@
 #ifndef __NET_FRAG_H__
 #define __NET_FRAG_H__
 
+#include <linux/rhashtable.h>
+
 struct netns_frags {
-	/* Keep atomic mem on separate cachelines in structs that include it */
-	atomic_t		mem ____cacheline_aligned_in_smp;
 	/* sysctls */
+	long			high_thresh;
+	long			low_thresh;
 	int			timeout;
-	int			high_thresh;
+	struct inet_frags	*f;
-	int			low_thresh;
+
+	struct rhashtable       rhashtable ____cacheline_aligned_in_smp;
+
+	/* Keep atomic mem on separate cachelines in structs that include it */
+	atomic_long_t		mem ____cacheline_aligned_in_smp;
 };
 
 /**
@@ -23,74 +29,68 @@ enum {
 	INET_FRAG_COMPLETE	= BIT(2),
 };
 
+struct frag_v4_compare_key {
+	__be32		saddr;
+	__be32		daddr;
+	u32		user;
+	u32		vif;
+	__be16		id;
+	u16		protocol;
+};
+
+struct frag_v6_compare_key {
+	struct in6_addr	saddr;
+	struct in6_addr	daddr;
+	u32		user;
+	__be32		id;
+	u32		iif;
+};
+
 /**
  * struct inet_frag_queue - fragment queue
  *
- * @lock: spinlock protecting the queue
+ * @node: rhash node
+ * @key: keys identifying this frag.
  * @timer: queue expiration timer
- * @list: hash bucket list
+ * @lock: spinlock protecting this frag
  * @refcnt: reference count of the queue
  * @fragments: received fragments head
+ * @rb_fragments: received fragments rb-tree root
  * @fragments_tail: received fragments tail
+ * @last_run_head: the head of the last "run". see ip_fragment.c
  * @stamp: timestamp of the last received fragment
  * @len: total length of the original datagram
  * @meat: length of received fragments so far
  * @flags: fragment queue flags
  * @max_size: maximum received fragment size
  * @net: namespace that this frag belongs to
- * @list_evictor: list of queues to forcefully evict (e.g. due to low memory)
+ * @rcu: rcu head for freeing deferall
  */
 struct inet_frag_queue {
-	spinlock_t		lock;
+	struct rhash_head	node;
+	union {
+		struct frag_v4_compare_key v4;
+		struct frag_v6_compare_key v6;
+	} key;
 	struct timer_list	timer;
-	struct hlist_node	list;
+	spinlock_t		lock;
 	atomic_t		refcnt;
-	struct sk_buff		*fragments;
+	struct sk_buff		*fragments;  /* Used in IPv6. */
+	struct rb_root		rb_fragments; /* Used in IPv4. */
 	struct sk_buff		*fragments_tail;
+	struct sk_buff		*last_run_head;
 	ktime_t			stamp;
 	int			len;
 	int			meat;
 	__u8			flags;
 	u16			max_size;
-	struct netns_frags	*net;
+	struct netns_frags      *net;
-	struct hlist_node	list_evictor;
+	struct rcu_head		rcu;
-};
-
-#define INETFRAGS_HASHSZ	1024
-
-/* 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_frag_bucket {
-	struct hlist_head	chain;
-	spinlock_t		chain_lock;
 };
 
 struct inet_frags {
-	struct inet_frag_bucket	hash[INETFRAGS_HASHSZ];
-
-	struct work_struct	frags_work;
-	unsigned int next_bucket;
-	unsigned long last_rebuild_jiffies;
-	bool rebuild;
-
-	/* The first call to hashfn is responsible to initialize
-	 * rnd. This is best done with net_get_random_once.
-	 *
-	 * rnd_seqlock is used to let hash insertion detect
-	 * when it needs to re-lookup the hash chain to use.
-	 */
-	u32			rnd;
-	seqlock_t		rnd_seqlock;
 	int			qsize;
 
-	unsigned int		(*hashfn)(const struct inet_frag_queue *);
-	bool			(*match)(const struct inet_frag_queue *q,
-					 const void *arg);
 	void			(*constructor)(struct inet_frag_queue *q,
 					       const void *arg);
 	void			(*destructor)(struct inet_frag_queue *);
@@ -98,56 +98,47 @@ struct inet_frags {
 	void			(*frag_expire)(unsigned long data);
 	struct kmem_cache	*frags_cachep;
 	const char		*frags_cache_name;
+	struct rhashtable_params rhash_params;
 };
 
 int inet_frags_init(struct inet_frags *);
 void inet_frags_fini(struct inet_frags *);
 
-static inline void inet_frags_init_net(struct netns_frags *nf)
+static inline int inet_frags_init_net(struct netns_frags *nf)
 {
-	atomic_set(&nf->mem, 0);
+	atomic_long_set(&nf->mem, 0);
+	return rhashtable_init(&nf->rhashtable, &nf->f->rhash_params);
 }
-void inet_frags_exit_net(struct netns_frags *nf, struct inet_frags *f);
+void inet_frags_exit_net(struct netns_frags *nf);
 
-void inet_frag_kill(struct inet_frag_queue *q, struct inet_frags *f);
+void inet_frag_kill(struct inet_frag_queue *q);
-void inet_frag_destroy(struct inet_frag_queue *q, struct inet_frags *f);
+void inet_frag_destroy(struct inet_frag_queue *q);
-struct inet_frag_queue *inet_frag_find(struct netns_frags *nf,
+struct inet_frag_queue *inet_frag_find(struct netns_frags *nf, void *key);
-		struct inet_frags *f, void *key, unsigned int hash);
 
-void inet_frag_maybe_warn_overflow(struct inet_frag_queue *q,
+/* Free all skbs in the queue; return the sum of their truesizes. */
-				   const char *prefix);
+unsigned int inet_frag_rbtree_purge(struct rb_root *root);
 
-static inline void inet_frag_put(struct inet_frag_queue *q, struct inet_frags *f)
+static inline void inet_frag_put(struct inet_frag_queue *q)
 {
 	if (atomic_dec_and_test(&q->refcnt))
-		inet_frag_destroy(q, f);
+		inet_frag_destroy(q);
-}
-
-static inline bool inet_frag_evicting(struct inet_frag_queue *q)
-{
-	return !hlist_unhashed(&q->list_evictor);
 }
 
 /* Memory Tracking Functions. */
 
-static inline int frag_mem_limit(struct netns_frags *nf)
+static inline long frag_mem_limit(const struct netns_frags *nf)
 {
-	return atomic_read(&nf->mem);
+	return atomic_long_read(&nf->mem);
 }
 
-static inline void sub_frag_mem_limit(struct netns_frags *nf, int i)
+static inline void sub_frag_mem_limit(struct netns_frags *nf, long val)
 {
-	atomic_sub(i, &nf->mem);
+	atomic_long_sub(val, &nf->mem);
 }
 
-static inline void add_frag_mem_limit(struct netns_frags *nf, int i)
+static inline void add_frag_mem_limit(struct netns_frags *nf, long val)
 {
-	atomic_add(i, &nf->mem);
+	atomic_long_add(val, &nf->mem);
-}
-
-static inline int sum_frag_mem_limit(struct netns_frags *nf)
-{
-	return atomic_read(&nf->mem);
 }
 
 /* RFC 3168 support :

include/net/ip.h

@@ -525,7 +525,6 @@ static inline struct sk_buff *ip_check_defrag(struct net *net, struct sk_buff *s
 	return skb;
 }
 #endif
-int ip_frag_mem(struct net *net);
 
 /*
  *	Functions provided by ip_forward.c

include/net/ipv6.h

@@ -320,13 +320,6 @@ static inline bool ipv6_accept_ra(struct inet6_dev *idev)
 	    idev->cnf.accept_ra;
 }
 
-#if IS_ENABLED(CONFIG_IPV6)
-static inline int ip6_frag_mem(struct net *net)
-{
-	return sum_frag_mem_limit(&net->ipv6.frags);
-}
-#endif
-
 #define IPV6_FRAG_HIGH_THRESH	(4 * 1024*1024)	/* 4194304 */
 #define IPV6_FRAG_LOW_THRESH	(3 * 1024*1024)	/* 3145728 */
 #define IPV6_FRAG_TIMEOUT	(60 * HZ)	/* 60 seconds */
@@ -505,17 +498,8 @@ enum ip6_defrag_users {
 	__IP6_DEFRAG_CONNTRACK_BRIDGE_IN = IP6_DEFRAG_CONNTRACK_BRIDGE_IN + USHRT_MAX,
 };
 
-struct ip6_create_arg {
-	__be32 id;
-	u32 user;
-	const struct in6_addr *src;
-	const struct in6_addr *dst;
-	int iif;
-	u8 ecn;
-};
-
 void ip6_frag_init(struct inet_frag_queue *q, const void *a);
-bool ip6_frag_match(const struct inet_frag_queue *q, const void *a);
+extern const struct rhashtable_params ip6_rhash_params;
 
 /*
  *	Equivalent of ipv4 struct ip
@@ -523,19 +507,13 @@ bool ip6_frag_match(const struct inet_frag_queue *q, const void *a);
 struct frag_queue {
 	struct inet_frag_queue	q;
 
-	__be32			id;		/* fragment id		*/
-	u32			user;
-	struct in6_addr		saddr;
-	struct in6_addr		daddr;
-
 	int			iif;
 	unsigned int		csum;
 	__u16			nhoffset;
 	u8			ecn;
 };
 
-void ip6_expire_frag_queue(struct net *net, struct frag_queue *fq,
+void ip6_expire_frag_queue(struct net *net, struct frag_queue *fq);
-			   struct inet_frags *frags);
 
 static inline bool ipv6_addr_any(const struct in6_addr *a)
 {

include/uapi/linux/snmp.h

@@ -55,6 +55,7 @@ enum
 	IPSTATS_MIB_ECT1PKTS,			/* InECT1Pkts */
 	IPSTATS_MIB_ECT0PKTS,			/* InECT0Pkts */
 	IPSTATS_MIB_CEPKTS,			/* InCEPkts */
+	IPSTATS_MIB_REASM_OVERLAPS,		/* ReasmOverlaps */
 	__IPSTATS_MIB_MAX
 };
 

kernel/rcu/tree.c

@@ -3817,7 +3817,7 @@ static void synchronize_sched_expedited_wait(struct rcu_state *rsp)
 					continue;
 				rdp = per_cpu_ptr(rsp->rda, cpu);
 				pr_cont(" %d-%c%c%c", cpu,
-					"O."[cpu_online(cpu)],
+					"O."[!!cpu_online(cpu)],
 					"o."[!!(rdp->grpmask & rnp->expmaskinit)],
 					"N."[!!(rdp->grpmask & rnp->expmaskinitnext)]);
 			}

lib/rhashtable.c

@@ -250,8 +250,10 @@ static int rhashtable_rehash_table(struct rhashtable *ht)
 	if (!new_tbl)
 		return 0;
 
-	for (old_hash = 0; old_hash < old_tbl->size; old_hash++)
+	for (old_hash = 0; old_hash < old_tbl->size; old_hash++) {
 		rhashtable_rehash_chain(ht, old_hash);
+		cond_resched();
+	}
 
 	/* Publish the new table pointer. */
 	rcu_assign_pointer(ht->tbl, new_tbl);
@@ -441,7 +443,8 @@ EXPORT_SYMBOL_GPL(rhashtable_insert_rehash);
 struct bucket_table *rhashtable_insert_slow(struct rhashtable *ht,
 					    const void *key,
 					    struct rhash_head *obj,
-					    struct bucket_table *tbl)
+					    struct bucket_table *tbl,
+					    void **data)
 {
 	struct rhash_head *head;
 	unsigned int hash;
@@ -452,8 +455,11 @@ struct bucket_table *rhashtable_insert_slow(struct rhashtable *ht,
 	spin_lock_nested(rht_bucket_lock(tbl, hash), SINGLE_DEPTH_NESTING);
 
 	err = -EEXIST;
-	if (key && rhashtable_lookup_fast(ht, key, ht->p))
+	if (key) {
-		goto exit;
+		*data = rhashtable_lookup_fast(ht, key, ht->p);
+		if (*data)
+			goto exit;
+	}
 
 	err = -E2BIG;
 	if (unlikely(rht_grow_above_max(ht, tbl)))
@@ -838,6 +844,7 @@ void rhashtable_free_and_destroy(struct rhashtable *ht,
 		for (i = 0; i < tbl->size; i++) {
 			struct rhash_head *pos, *next;
 
+			cond_resched();
 			for (pos = rht_dereference(tbl->buckets[i], ht),
 			     next = !rht_is_a_nulls(pos) ?
 					rht_dereference(pos->next, ht) : NULL;

net/core/skbuff.c

@@ -1502,6 +1502,21 @@ done:
 }
 EXPORT_SYMBOL(___pskb_trim);
 
+/* Note : use pskb_trim_rcsum() instead of calling this directly
+ */
+int pskb_trim_rcsum_slow(struct sk_buff *skb, unsigned int len)
+{
+	if (skb->ip_summed == CHECKSUM_COMPLETE) {
+		int delta = skb->len - len;
+
+		skb->csum = csum_block_sub(skb->csum,
+					   skb_checksum(skb, len, delta, 0),
+					   len);
+	}
+	return __pskb_trim(skb, len);
+}
+EXPORT_SYMBOL(pskb_trim_rcsum_slow);
+
 /**
  *	__pskb_pull_tail - advance tail of skb header
  *	@skb: buffer to reallocate
@@ -2380,23 +2395,27 @@ EXPORT_SYMBOL(skb_queue_purge);
 /**
  *	skb_rbtree_purge - empty a skb rbtree
  *	@root: root of the rbtree to empty
+ *	Return value: the sum of truesizes of all purged skbs.
  *
  *	Delete all buffers on an &sk_buff rbtree. Each buffer is removed from
  *	the list and one reference dropped. This function does not take
  *	any lock. Synchronization should be handled by the caller (e.g., TCP
  *	out-of-order queue is protected by the socket lock).
  */
-void skb_rbtree_purge(struct rb_root *root)
+unsigned int skb_rbtree_purge(struct rb_root *root)
 {
 	struct rb_node *p = rb_first(root);
+	unsigned int sum = 0;
 
 	while (p) {
 		struct sk_buff *skb = rb_entry(p, struct sk_buff, rbnode);
 
 		p = rb_next(p);
 		rb_erase(&skb->rbnode, root);
+		sum += skb->truesize;
 		kfree_skb(skb);
 	}
+	return sum;
 }
 
 /**

net/ieee802154/6lowpan/6lowpan_i.h

@@ -16,37 +16,19 @@ typedef unsigned __bitwise__ lowpan_rx_result;
 #define LOWPAN_DISPATCH_FRAG1           0xc0
 #define LOWPAN_DISPATCH_FRAGN           0xe0
 
-struct lowpan_create_arg {
+struct frag_lowpan_compare_key {
 	u16 tag;
 	u16 d_size;
-	const struct ieee802154_addr *src;
+	struct ieee802154_addr src;
-	const struct ieee802154_addr *dst;
+	struct ieee802154_addr dst;
 };
 
-/* Equivalent of ipv4 struct ip
+/* Equivalent of ipv4 struct ipq
  */
 struct lowpan_frag_queue {
 	struct inet_frag_queue	q;
-
-	u16			tag;
-	u16			d_size;
-	struct ieee802154_addr	saddr;
-	struct ieee802154_addr	daddr;
 };
 
-static inline u32 ieee802154_addr_hash(const struct ieee802154_addr *a)
-{
-	switch (a->mode) {
-	case IEEE802154_ADDR_LONG:
-		return (((__force u64)a->extended_addr) >> 32) ^
-			(((__force u64)a->extended_addr) & 0xffffffff);
-	case IEEE802154_ADDR_SHORT:
-		return (__force u32)(a->short_addr);
-	default:
-		return 0;
-	}
-}
-
 /* private device info */
 struct lowpan_dev_info {
 	struct net_device	*wdev; /* wpan device ptr */

net/ieee802154/6lowpan/reassembly.c

@@ -37,47 +37,15 @@ static struct inet_frags lowpan_frags;
 static int lowpan_frag_reasm(struct lowpan_frag_queue *fq,
 			     struct sk_buff *prev, struct net_device *ldev);
 
-static unsigned int lowpan_hash_frag(u16 tag, u16 d_size,
-				     const struct ieee802154_addr *saddr,
-				     const struct ieee802154_addr *daddr)
-{
-	net_get_random_once(&lowpan_frags.rnd, sizeof(lowpan_frags.rnd));
-	return jhash_3words(ieee802154_addr_hash(saddr),
-			    ieee802154_addr_hash(daddr),
-			    (__force u32)(tag + (d_size << 16)),
-			    lowpan_frags.rnd);
-}
-
-static unsigned int lowpan_hashfn(const struct inet_frag_queue *q)
-{
-	const struct lowpan_frag_queue *fq;
-
-	fq = container_of(q, struct lowpan_frag_queue, q);
-	return lowpan_hash_frag(fq->tag, fq->d_size, &fq->saddr, &fq->daddr);
-}
-
-static bool lowpan_frag_match(const struct inet_frag_queue *q, const void *a)
-{
-	const struct lowpan_frag_queue *fq;
-	const struct lowpan_create_arg *arg = a;
-
-	fq = container_of(q, struct lowpan_frag_queue, q);
-	return	fq->tag == arg->tag && fq->d_size == arg->d_size &&
-		ieee802154_addr_equal(&fq->saddr, arg->src) &&
-		ieee802154_addr_equal(&fq->daddr, arg->dst);
-}
-
 static void lowpan_frag_init(struct inet_frag_queue *q, const void *a)
 {
-	const struct lowpan_create_arg *arg = a;
+	const struct frag_lowpan_compare_key *key = a;
 	struct lowpan_frag_queue *fq;
 
 	fq = container_of(q, struct lowpan_frag_queue, q);
 
-	fq->tag = arg->tag;
+	BUILD_BUG_ON(sizeof(*key) > sizeof(q->key));
-	fq->d_size = arg->d_size;
+	memcpy(&q->key, key, sizeof(*key));
-	fq->saddr = *arg->src;
-	fq->daddr = *arg->dst;
 }
 
 static void lowpan_frag_expire(unsigned long data)
@@ -93,10 +61,10 @@ static void lowpan_frag_expire(unsigned long data)
 	if (fq->q.flags & INET_FRAG_COMPLETE)
 		goto out;
 
-	inet_frag_kill(&fq->q, &lowpan_frags);
+	inet_frag_kill(&fq->q);
 out:
 	spin_unlock(&fq->q.lock);
-	inet_frag_put(&fq->q, &lowpan_frags);
+	inet_frag_put(&fq->q);
 }
 
 static inline struct lowpan_frag_queue *
@@ -104,25 +72,20 @@ fq_find(struct net *net, const struct lowpan_802154_cb *cb,
 	const struct ieee802154_addr *src,
 	const struct ieee802154_addr *dst)
 {
-	struct inet_frag_queue *q;
-	struct lowpan_create_arg arg;
-	unsigned int hash;
 	struct netns_ieee802154_lowpan *ieee802154_lowpan =
 		net_ieee802154_lowpan(net);
+	struct frag_lowpan_compare_key key = {};
+	struct inet_frag_queue *q;
 
-	arg.tag = cb->d_tag;
+	key.tag = cb->d_tag;
-	arg.d_size = cb->d_size;
+	key.d_size = cb->d_size;
-	arg.src = src;
+	key.src = *src;
-	arg.dst = dst;
+	key.dst = *dst;
 
-	hash = lowpan_hash_frag(cb->d_tag, cb->d_size, src, dst);
+	q = inet_frag_find(&ieee802154_lowpan->frags, &key);
-
+	if (!q)
-	q = inet_frag_find(&ieee802154_lowpan->frags,
-			   &lowpan_frags, &arg, hash);
-	if (IS_ERR_OR_NULL(q)) {
-		inet_frag_maybe_warn_overflow(q, pr_fmt());
 		return NULL;
-	}
+
 	return container_of(q, struct lowpan_frag_queue, q);
 }
 
@@ -229,7 +192,7 @@ static int lowpan_frag_reasm(struct lowpan_frag_queue *fq, struct sk_buff *prev,
 	struct sk_buff *fp, *head = fq->q.fragments;
 	int sum_truesize;
 
-	inet_frag_kill(&fq->q, &lowpan_frags);
+	inet_frag_kill(&fq->q);
 
 	/* Make the one we just received the head. */
 	if (prev) {
@@ -408,7 +371,7 @@ int lowpan_frag_rcv(struct sk_buff *skb, u8 frag_type)
 	struct lowpan_frag_queue *fq;
 	struct net *net = dev_net(skb->dev);
 	struct lowpan_802154_cb *cb = lowpan_802154_cb(skb);
-	struct ieee802154_hdr hdr;
+	struct ieee802154_hdr hdr = {};
 	int err;
 
 	if (ieee802154_hdr_peek_addrs(skb, &hdr) < 0)
@@ -437,7 +400,7 @@ int lowpan_frag_rcv(struct sk_buff *skb, u8 frag_type)
 		ret = lowpan_frag_queue(fq, skb, frag_type);
 		spin_unlock(&fq->q.lock);
 
-		inet_frag_put(&fq->q, &lowpan_frags);
+		inet_frag_put(&fq->q);
 		return ret;
 	}
 
@@ -447,24 +410,22 @@ err:
 }
 
 #ifdef CONFIG_SYSCTL
-static int zero;
 
 static struct ctl_table lowpan_frags_ns_ctl_table[] = {
 	{
 		.procname	= "6lowpanfrag_high_thresh",
 		.data		= &init_net.ieee802154_lowpan.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.ieee802154_lowpan.frags.low_thresh
 	},
 	{
 		.procname	= "6lowpanfrag_low_thresh",
 		.data		= &init_net.ieee802154_lowpan.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.ieee802154_lowpan.frags.high_thresh
 	},
 	{
@@ -580,14 +541,20 @@ static int __net_init lowpan_frags_init_net(struct net *net)
 {
 	struct netns_ieee802154_lowpan *ieee802154_lowpan =
 		net_ieee802154_lowpan(net);
+	int res;
 
 	ieee802154_lowpan->frags.high_thresh = IPV6_FRAG_HIGH_THRESH;
 	ieee802154_lowpan->frags.low_thresh = IPV6_FRAG_LOW_THRESH;
 	ieee802154_lowpan->frags.timeout = IPV6_FRAG_TIMEOUT;
+	ieee802154_lowpan->frags.f = &lowpan_frags;
 
-	inet_frags_init_net(&ieee802154_lowpan->frags);
+	res = inet_frags_init_net(&ieee802154_lowpan->frags);
-
+	if (res < 0)
-	return lowpan_frags_ns_sysctl_register(net);
+		return res;
+	res = lowpan_frags_ns_sysctl_register(net);
+	if (res < 0)
+		inet_frags_exit_net(&ieee802154_lowpan->frags);
+	return res;
 }
 
 static void __net_exit lowpan_frags_exit_net(struct net *net)
@@ -596,7 +563,7 @@ static void __net_exit lowpan_frags_exit_net(struct net *net)
 		net_ieee802154_lowpan(net);
 
 	lowpan_frags_ns_sysctl_unregister(net);
-	inet_frags_exit_net(&ieee802154_lowpan->frags, &lowpan_frags);
+	inet_frags_exit_net(&ieee802154_lowpan->frags);
 }
 
 static struct pernet_operations lowpan_frags_ops = {
@@ -604,33 +571,64 @@ static struct pernet_operations lowpan_frags_ops = {
 	.exit = lowpan_frags_exit_net,
 };
 
+static u32 lowpan_key_hashfn(const void *data, u32 len, u32 seed)
+{
+	return jhash2(data,
+		      sizeof(struct frag_lowpan_compare_key) / sizeof(u32), seed);
+}
+
+static u32 lowpan_obj_hashfn(const void *data, u32 len, u32 seed)
+{
+	const struct inet_frag_queue *fq = data;
+
+	return jhash2((const u32 *)&fq->key,
+		      sizeof(struct frag_lowpan_compare_key) / sizeof(u32), seed);
+}
+
+static int lowpan_obj_cmpfn(struct rhashtable_compare_arg *arg, const void *ptr)
+{
+	const struct frag_lowpan_compare_key *key = arg->key;
+	const struct inet_frag_queue *fq = ptr;
+
+	return !!memcmp(&fq->key, key, sizeof(*key));
+}
+
+static const struct rhashtable_params lowpan_rhash_params = {
+	.head_offset		= offsetof(struct inet_frag_queue, node),
+	.hashfn			= lowpan_key_hashfn,
+	.obj_hashfn		= lowpan_obj_hashfn,
+	.obj_cmpfn		= lowpan_obj_cmpfn,
+	.automatic_shrinking	= true,
+};
+
 int __init lowpan_net_frag_init(void)
 {
 	int ret;
 
-	ret = lowpan_frags_sysctl_register();
-	if (ret)
-		return ret;
-
-	ret = register_pernet_subsys(&lowpan_frags_ops);
-	if (ret)
-		goto err_pernet;
-
-	lowpan_frags.hashfn = lowpan_hashfn;
 	lowpan_frags.constructor = lowpan_frag_init;
 	lowpan_frags.destructor = NULL;
 	lowpan_frags.skb_free = NULL;
 	lowpan_frags.qsize = sizeof(struct frag_queue);
-	lowpan_frags.match = lowpan_frag_match;
 	lowpan_frags.frag_expire = lowpan_frag_expire;
 	lowpan_frags.frags_cache_name = lowpan_frags_cache_name;
+	lowpan_frags.rhash_params = lowpan_rhash_params;
 	ret = inet_frags_init(&lowpan_frags);
 	if (ret)
-		goto err_pernet;
+		goto out;
 
+	ret = lowpan_frags_sysctl_register();
+	if (ret)
+		goto err_sysctl;
+
+	ret = register_pernet_subsys(&lowpan_frags_ops);
+	if (ret)
+		goto err_pernet;
+out:
 	return ret;
 err_pernet:
 	lowpan_frags_sysctl_unregister();
+err_sysctl:
+	inet_frags_fini(&lowpan_frags);
 	return ret;
 }
 

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((unsigned long) fq);
-
-	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 = ACCESS_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)
@@ -214,73 +59,53 @@ 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;
+	struct inet_frag_queue *fq = ptr;
-	int i;
 
-	nf->low_thresh = 0;
+	/* 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;
 
-evict_again:
+	spin_lock_bh(&fq->lock);
-	local_bh_disable();
+	if (!(fq->flags & INET_FRAG_COMPLETE)) {
-	seq = read_seqbegin(&f->rnd_seqlock);
+		fq->flags |= INET_FRAG_COMPLETE;
+		atomic_dec(&fq->refcnt);
+	}
+	spin_unlock_bh(&fq->lock);
 
-	for (i = 0; i < INETFRAGS_HASHSZ ; i++)
+	inet_frag_put(fq);
-		inet_evict_bucket(f, &f->hash[i]);
+}
 
-	local_bh_enable();
+void inet_frags_exit_net(struct netns_frags *nf)
-	cond_resched();
+{
+	nf->high_thresh = 0; /* prevent creation of new frags */
 
-	if (read_seqretry(&f->rnd_seqlock, seq) ||
+	rhashtable_free_and_destroy(&nf->rhashtable, inet_frags_free_cb, NULL);
-	    sum_frag_mem_limit(nf))
-		goto evict_again;
 }
 EXPORT_SYMBOL(inet_frags_exit_net);
 
-static struct inet_frag_bucket *
+void inet_frag_kill(struct inet_frag_queue *fq)
-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];
-
-	spin_lock(&hb->chain_lock);
-	if (read_seqretry(&f->rnd_seqlock, seq)) {
-		spin_unlock(&hb->chain_lock);
-		goto restart;
-	}
-
-	return hb;
-}
-
-static inline void fq_unlink(struct inet_frag_queue *fq, struct inet_frags *f)
-{
-	struct inet_frag_bucket *hb;
-
-	hb = get_frag_bucket_locked(fq, f);
-	hlist_del(&fq->list);
-	fq->flags |= INET_FRAG_COMPLETE;
-	spin_unlock(&hb->chain_lock);
-}
-
-void inet_frag_kill(struct inet_frag_queue *fq, struct inet_frags *f)
 {
 	if (del_timer(&fq->timer))
 		atomic_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);
 		atomic_dec(&fq->refcnt);
 	}
 }
@@ -294,11 +119,23 @@ static inline void frag_kfree_skb(struct netns_frags *nf, struct inet_frags *f,
 	kfree_skb(skb);
 }
 
-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);
@@ -306,64 +143,35 @@ void inet_frag_destroy(struct inet_frag_queue *q, struct inet_frags *f)
 	/* Release all fragment data. */
 	fp = q->fragments;
 	nf = q->net;
-	while (fp) {
+	f = nf->f;
-		struct sk_buff *xp = fp->next;
+	if (fp) {
+		do {
+			struct sk_buff *xp = fp->next;
 
-		sum_truesize += fp->truesize;
+			sum_truesize += fp->truesize;
-		frag_kfree_skb(nf, f, fp);
+			frag_kfree_skb(nf, f, fp);
-		fp = xp;
+			fp = xp;
+		} while (fp);
+	} else {
+		sum_truesize = inet_frag_rbtree_purge(&q->rb_fragments);
 	}
 	sum = sum_truesize + f->qsize;
 
-	if (f->destructor)
+	call_rcu(&q->rcu, inet_frag_destroy_rcu);
-		f->destructor(q);
-	kmem_cache_free(f->frags_cachep, q);
 
 	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)) {
-			atomic_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))
-		atomic_inc(&qp->refcnt);
-
-	atomic_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)
+		return NULL;
+
 	q = kmem_cache_zalloc(f->frags_cachep, GFP_ATOMIC);
 	if (!q)
 		return NULL;
@@ -374,75 +182,52 @@ static struct inet_frag_queue *inet_frag_alloc(struct netns_frags *nf,
 
 	setup_timer(&q->timer, f->frag_expire, (unsigned long)q);
 	spin_lock_init(&q->lock);
-	atomic_set(&q->refcnt, 1);
+	atomic_set(&q->refcnt, 3);
 
 	return q;
 }
 
 static struct inet_frag_queue *inet_frag_create(struct netns_frags *nf,
-						struct inet_frags *f,
+						void *arg,
-						void *arg)
+						struct inet_frag_queue **prev)
 {
+	struct inet_frags *f = nf->f;
 	struct inet_frag_queue *q;
 
 	q = inet_frag_alloc(nf, f, arg);
-	if (!q)
+	if (!q) {
+		*prev = ERR_PTR(-ENOMEM);
 		return NULL;
+	}
+	mod_timer(&q->timer, jiffies + nf->timeout);
 
-	return inet_frag_intern(nf, q, f, arg);
+	*prev = rhashtable_lookup_get_insert_key(&nf->rhashtable, &q->key,
+						 &q->node, f->rhash_params);
+	if (*prev) {
+		q->flags |= INET_FRAG_COMPLETE;
+		inet_frag_kill(q);
+		inet_frag_destroy(q);
+		return NULL;
+	}
+	return q;
 }
+EXPORT_SYMBOL(inet_frag_create);
 
-struct inet_frag_queue *inet_frag_find(struct netns_frags *nf,
+/* TODO : call from rcu_read_lock() and no longer use refcount_inc_not_zero() */
-				       struct inet_frags *f, void *key,
+struct inet_frag_queue *inet_frag_find(struct netns_frags *nf, void *key)
-				       unsigned int hash)
 {
-	struct inet_frag_bucket *hb;
+	struct inet_frag_queue *fq = NULL, *prev;
-	struct inet_frag_queue *q;
-	int depth = 0;
 
-	if (!nf->high_thresh || frag_mem_limit(nf) > nf->high_thresh) {
+	rcu_read_lock();
-		inet_frag_schedule_worker(f);
+	prev = rhashtable_lookup(&nf->rhashtable, key, nf->f->rhash_params);
-		return NULL;
+	if (!prev)
+		fq = inet_frag_create(nf, key, &prev);
+	if (prev && !IS_ERR(prev)) {
+		fq = prev;
+		if (!atomic_inc_not_zero(&fq->refcnt))
+			fq = NULL;
 	}
-
+	rcu_read_unlock();
-	if (frag_mem_limit(nf) > nf->low_thresh)
+	return fq;
-		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)) {
-			atomic_inc(&q->refcnt);
-			spin_unlock(&hb->chain_lock);
-			return q;
-		}
-		depth++;
-	}
-	spin_unlock(&hb->chain_lock);
-
-	if (depth <= INETFRAGS_MAXDEPTH)
-		return inet_frag_create(nf, f, key);
-
-	if (inet_frag_may_rebuild(f)) {
-		if (!f->rebuild)
-			f->rebuild = true;
-		inet_frag_schedule_worker(f);
-	}
-
-	return ERR_PTR(-ENOBUFS);
 }
 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);

net/ipv4/ip_fragment.c

@@ -58,27 +58,64 @@
 static int sysctl_ipfrag_max_dist __read_mostly = 64;
 static const char ip_frag_cache_name[] = "ip4-frags";
 
-struct ipfrag_skb_cb
+/* Use skb->cb to track consecutive/adjacent fragments coming at
-{
+ * the end of the queue. Nodes in the rb-tree queue will
+ * contain "runs" of one or more adjacent fragments.
+ *
+ * Invariants:
+ * - next_frag is NULL at the tail of a "run";
+ * - the head of a "run" has the sum of all fragment lengths in frag_run_len.
+ */
+struct ipfrag_skb_cb {
 	struct inet_skb_parm	h;
-	int			offset;
+	struct sk_buff		*next_frag;
+	int			frag_run_len;
 };
 
-#define FRAG_CB(skb)	((struct ipfrag_skb_cb *)((skb)->cb))
+#define FRAG_CB(skb)		((struct ipfrag_skb_cb *)((skb)->cb))
+
+static void ip4_frag_init_run(struct sk_buff *skb)
+{
+	BUILD_BUG_ON(sizeof(struct ipfrag_skb_cb) > sizeof(skb->cb));
+
+	FRAG_CB(skb)->next_frag = NULL;
+	FRAG_CB(skb)->frag_run_len = skb->len;
+}
+
+/* Append skb to the last "run". */
+static void ip4_frag_append_to_last_run(struct inet_frag_queue *q,
+					struct sk_buff *skb)
+{
+	RB_CLEAR_NODE(&skb->rbnode);
+	FRAG_CB(skb)->next_frag = NULL;
+
+	FRAG_CB(q->last_run_head)->frag_run_len += skb->len;
+	FRAG_CB(q->fragments_tail)->next_frag = skb;
+	q->fragments_tail = skb;
+}
+
+/* Create a new "run" with the skb. */
+static void ip4_frag_create_run(struct inet_frag_queue *q, struct sk_buff *skb)
+{
+	if (q->last_run_head)
+		rb_link_node(&skb->rbnode, &q->last_run_head->rbnode,
+			     &q->last_run_head->rbnode.rb_right);
+	else
+		rb_link_node(&skb->rbnode, NULL, &q->rb_fragments.rb_node);
+	rb_insert_color(&skb->rbnode, &q->rb_fragments);
+
+	ip4_frag_init_run(skb);
+	q->fragments_tail = skb;
+	q->last_run_head = skb;
+}
 
 /* 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;
 };
@@ -90,49 +127,9 @@ static u8 ip4_frag_ecn(u8 tos)
 
 static struct inet_frags ip4_frags;
 
-int ip_frag_mem(struct net *net)
+static int ip_frag_reasm(struct ipq *qp, struct sk_buff *skb,
-{
+			 struct sk_buff *prev_tail, struct net_device *dev);
-	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)
 {
@@ -141,17 +138,12 @@ 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;
+	q->key.v4 = *key;
-	qp->id = arg->iph->id;
+	qp->ecn = 0;
-	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;
 	qp->peer = sysctl_ipfrag_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;
 }
 
@@ -169,7 +161,7 @@ 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,
@@ -177,7 +169,7 @@ 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 +186,11 @@ static bool frag_expire_skip_icmp(u32 user)
  */
 static void ip_expire(unsigned long arg)
 {
-	struct ipq *qp;
+	const struct iphdr *iph;
+	struct sk_buff *head = NULL;
 	struct net *net;
+	struct ipq *qp;
+	int err;
 
 	qp = container_of((struct inet_frag_queue *) arg, struct ipq, q);
 	net = container_of(qp->q.net, struct net, ipv4.frags);
@@ -208,51 +203,65 @@ static void ip_expire(unsigned long arg)
 
 	ipq_kill(qp);
 	IP_INC_STATS_BH(net, IPSTATS_MIB_REASMFAILS);
+	IP_INC_STATS_BH(net, IPSTATS_MIB_REASMTIMEOUT);
 
-	if (!inet_frag_evicting(&qp->q)) {
+	if (!(qp->q.flags & INET_FRAG_FIRST_IN))
-		struct sk_buff *clone, *head = qp->q.fragments;
+		goto out;
-		const struct iphdr *iph;
-		int err;
 
-		IP_INC_STATS_BH(net, IPSTATS_MIB_REASMTIMEOUT);
+	/* sk_buff::dev and sk_buff::rbnode are unionized. So we
-
+	 * pull the head out of the tree in order to be able to
-		if (!(qp->q.flags & INET_FRAG_FIRST_IN) || !qp->q.fragments)
+	 * deal with head->dev.
+	 */
+	if (qp->q.fragments) {
+		head = qp->q.fragments;
+		qp->q.fragments = head->next;
+	} else {
+		head = skb_rb_first(&qp->q.rb_fragments);
+		if (!head)
 			goto out;
-
+		if (FRAG_CB(head)->next_frag)
-		head->dev = dev_get_by_index_rcu(net, qp->iif);
+			rb_replace_node(&head->rbnode,
-		if (!head->dev)
+					&FRAG_CB(head)->next_frag->rbnode,
-			goto out;
+					&qp->q.rb_fragments);
-
+		else
-
+			rb_erase(&head->rbnode, &qp->q.rb_fragments);
-		/* skb has no dst, perform route lookup again */
+		memset(&head->rbnode, 0, sizeof(head->rbnode));
-		iph = ip_hdr(head);
+		barrier();
-		err = ip_route_input_noref(head, iph->daddr, iph->saddr,
-					   iph->tos, head->dev);
-		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->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;
-		}
 	}
+	if (head == qp->q.fragments_tail)
+		qp->q.fragments_tail = NULL;
+
+	sub_frag_mem_limit(qp->q.net, head->truesize);
+
+	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,
+					   iph->tos, head->dev);
+	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;
+
+	spin_unlock(&qp->q.lock);
+	icmp_send(head, ICMP_TIME_EXCEEDED, ICMP_EXC_FRAGTIME, 0);
+	goto out_rcu_unlock;
+
 out:
 	spin_unlock(&qp->q.lock);
 out_rcu_unlock:
 	rcu_read_unlock();
+	if (head)
+		kfree_skb(head);
 	ipq_put(qp);
 }
 
@@ -262,21 +271,20 @@ 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;
+	q = inet_frag_find(&net->ipv4.frags, &key);
-	arg.user = user;
+	if (!q)
-	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());
 		return NULL;
-	}
+
 	return container_of(q, struct ipq, q);
 }
 
@@ -296,7 +304,7 @@ static int ip_frag_too_far(struct ipq *qp)
 	end = atomic_inc_return(&peer->rid);
 	qp->rid = end;
 
-	rc = qp->q.fragments && (end - start) > max;
+	rc = qp->q.fragments_tail && (end - start) > max;
 
 	if (rc) {
 		struct net *net;
@@ -310,7 +318,6 @@ static 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)) {
@@ -318,21 +325,16 @@ static int ip_frag_reinit(struct ipq *qp)
 		return -ETIMEDOUT;
 	}
 
-	fp = qp->q.fragments;
+	sum_truesize = inet_frag_rbtree_purge(&qp->q.rb_fragments);
-	do {
-		struct sk_buff *xp = fp->next;
-
-		sum_truesize += fp->truesize;
-		kfree_skb(fp);
-		fp = xp;
-	} while (fp);
 	sub_frag_mem_limit(qp->q.net, sum_truesize);
 
 	qp->q.flags = 0;
 	qp->q.len = 0;
 	qp->q.meat = 0;
 	qp->q.fragments = NULL;
+	qp->q.rb_fragments = RB_ROOT;
 	qp->q.fragments_tail = NULL;
+	qp->q.last_run_head = NULL;
 	qp->iif = 0;
 	qp->ecn = 0;
 
@@ -342,11 +344,13 @@ static int ip_frag_reinit(struct ipq *qp)
 /* Add new segment to existing queue. */
 static int ip_frag_queue(struct ipq *qp, struct sk_buff *skb)
 {
-	struct sk_buff *prev, *next;
+	struct net *net = container_of(qp->q.net, struct net, ipv4.frags);
+	struct rb_node **rbn, *parent;
+	struct sk_buff *skb1, *prev_tail;
+	int ihl, end, skb1_run_end;
 	struct net_device *dev;
 	unsigned int fragsize;
 	int flags, offset;
-	int ihl, end;
 	int err = -ENOENT;
 	u8 ecn;
 
@@ -405,94 +409,68 @@ static int ip_frag_queue(struct ipq *qp, struct sk_buff *skb)
 	if (err)
 		goto err;
 
-	/* Find out which fragments are in front and at the back of us
+	/* Note : skb->rbnode and skb->dev share the same location. */
-	 * in the chain of fragments so far.  We must know where to put
-	 * this fragment, right?
-	 */
-	prev = qp->q.fragments_tail;
-	if (!prev || FRAG_CB(prev)->offset < offset) {
-		next = NULL;
-		goto found;
-	}
-	prev = NULL;
-	for (next = qp->q.fragments; next != NULL; next = next->next) {
-		if (FRAG_CB(next)->offset >= offset)
-			break;	/* bingo! */
-		prev = next;
-	}
-
-found:
-	/* We found where to put this one.  Check for overlap with
-	 * preceding fragment, and, if needed, align things so that
-	 * any overlaps are eliminated.
-	 */
-	if (prev) {
-		int i = (FRAG_CB(prev)->offset + prev->len) - offset;
-
-		if (i > 0) {
-			offset += i;
-			err = -EINVAL;
-			if (end <= offset)
-				goto err;
-			err = -ENOMEM;
-			if (!pskb_pull(skb, i))
-				goto err;
-			if (skb->ip_summed != CHECKSUM_UNNECESSARY)
-				skb->ip_summed = CHECKSUM_NONE;
-		}
-	}
-
-	err = -ENOMEM;
-
-	while (next && FRAG_CB(next)->offset < end) {
-		int i = end - FRAG_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;
-			FRAG_CB(next)->offset += i;
-			qp->q.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;
-
-			if (prev)
-				prev->next = next;
-			else
-				qp->q.fragments = next;
-
-			qp->q.meat -= free_it->len;
-			sub_frag_mem_limit(qp->q.net, free_it->truesize);
-			kfree_skb(free_it);
-		}
-	}
-
-	FRAG_CB(skb)->offset = offset;
-
-	/* Insert this fragment in the chain of fragments. */
-	skb->next = next;
-	if (!next)
-		qp->q.fragments_tail = skb;
-	if (prev)
-		prev->next = skb;
-	else
-		qp->q.fragments = skb;
-
 	dev = skb->dev;
-	if (dev) {
+	/* Makes sure compiler wont do silly aliasing games */
-		qp->iif = dev->ifindex;
+	barrier();
-		skb->dev = NULL;
+
+	/* 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.
+	 *
+	 * We do the same here for IPv4 (and increment an snmp counter) but
+	 * we do not want to drop the whole queue in response to a duplicate
+	 * fragment.
+	 */
+
+	err = -EINVAL;
+	/* Find out where to put this fragment.  */
+	prev_tail = qp->q.fragments_tail;
+	if (!prev_tail)
+		ip4_frag_create_run(&qp->q, skb);  /* First fragment. */
+	else if (prev_tail->ip_defrag_offset + prev_tail->len < end) {
+		/* This is the common case: skb goes to the end. */
+		/* Detect and discard overlaps. */
+		if (offset < prev_tail->ip_defrag_offset + prev_tail->len)
+			goto discard_qp;
+		if (offset == prev_tail->ip_defrag_offset + prev_tail->len)
+			ip4_frag_append_to_last_run(&qp->q, skb);
+		else
+			ip4_frag_create_run(&qp->q, skb);
+	} else {
+		/* Binary search. Note that skb can become the first fragment,
+		 * but not the last (covered above).
+		 */
+		rbn = &qp->q.rb_fragments.rb_node;
+		do {
+			parent = *rbn;
+			skb1 = rb_to_skb(parent);
+			skb1_run_end = skb1->ip_defrag_offset +
+				       FRAG_CB(skb1)->frag_run_len;
+			if (end <= skb1->ip_defrag_offset)
+				rbn = &parent->rb_left;
+			else if (offset >= skb1_run_end)
+				rbn = &parent->rb_right;
+			else if (offset >= skb1->ip_defrag_offset &&
+				 end <= skb1_run_end)
+				goto err; /* No new data, potential duplicate */
+			else
+				goto discard_qp; /* Found an overlap */
+		} while (*rbn);
+		/* Here we have parent properly set, and rbn pointing to
+		 * one of its NULL left/right children. Insert skb.
+		 */
+		ip4_frag_init_run(skb);
+		rb_link_node(&skb->rbnode, parent, rbn);
+		rb_insert_color(&skb->rbnode, &qp->q.rb_fragments);
 	}
+
+	if (dev)
+		qp->iif = dev->ifindex;
+	skb->ip_defrag_offset = offset;
+
 	qp->q.stamp = skb->tstamp;
 	qp->q.meat += skb->len;
 	qp->ecn |= ecn;
@@ -514,7 +492,7 @@ found:
 		unsigned long orefdst = skb->_skb_refdst;
 
 		skb->_skb_refdst = 0UL;
-		err = ip_frag_reasm(qp, prev, dev);
+		err = ip_frag_reasm(qp, skb, prev_tail, dev);
 		skb->_skb_refdst = orefdst;
 		return err;
 	}
@@ -522,20 +500,23 @@ found:
 	skb_dst_drop(skb);
 	return -EINPROGRESS;
 
+discard_qp:
+	inet_frag_kill(&qp->q);
+	IP_INC_STATS_BH(net, IPSTATS_MIB_REASM_OVERLAPS);
 err:
 	kfree_skb(skb);
 	return err;
 }
 
-
 /* Build a new IP datagram from all its fragments. */
-
+static int ip_frag_reasm(struct ipq *qp, struct sk_buff *skb,
-static int ip_frag_reasm(struct ipq *qp, struct sk_buff *prev,
+			 struct sk_buff *prev_tail, struct net_device *dev)
-			 struct net_device *dev)
 {
 	struct net *net = container_of(qp->q.net, struct net, ipv4.frags);
 	struct iphdr *iph;
-	struct sk_buff *fp, *head = qp->q.fragments;
+	struct sk_buff *fp, *head = skb_rb_first(&qp->q.rb_fragments);
+	struct sk_buff **nextp; /* To build frag_list. */
+	struct rb_node *rbn;
 	int len;
 	int ihlen;
 	int err;
@@ -549,26 +530,27 @@ static int ip_frag_reasm(struct ipq *qp, struct sk_buff *prev,
 		goto out_fail;
 	}
 	/* Make the one we just received the head. */
-	if (prev) {
+	if (head != skb) {
-		head = prev->next;
+		fp = skb_clone(skb, GFP_ATOMIC);
-		fp = skb_clone(head, GFP_ATOMIC);
 		if (!fp)
 			goto out_nomem;
-
+		FRAG_CB(fp)->next_frag = FRAG_CB(skb)->next_frag;
-		fp->next = head->next;
+		if (RB_EMPTY_NODE(&skb->rbnode))
-		if (!fp->next)
+			FRAG_CB(prev_tail)->next_frag = fp;
+		else
+			rb_replace_node(&skb->rbnode, &fp->rbnode,
+					&qp->q.rb_fragments);
+		if (qp->q.fragments_tail == skb)
 			qp->q.fragments_tail = fp;
-		prev->next = fp;
+		skb_morph(skb, head);
-
+		FRAG_CB(skb)->next_frag = FRAG_CB(head)->next_frag;
-		skb_morph(head, qp->q.fragments);
+		rb_replace_node(&head->rbnode, &skb->rbnode,
-		head->next = qp->q.fragments->next;
+				&qp->q.rb_fragments);
-
+		consume_skb(head);
-		consume_skb(qp->q.fragments);
+		head = skb;
-		qp->q.fragments = head;
 	}
 
-	WARN_ON(!head);
+	WARN_ON(head->ip_defrag_offset != 0);
-	WARN_ON(FRAG_CB(head)->offset != 0);
 
 	/* Allocate a new buffer for the datagram. */
 	ihlen = ip_hdrlen(head);
@@ -592,35 +574,61 @@ static int ip_frag_reasm(struct ipq *qp, struct sk_buff *prev,
 		clone = alloc_skb(0, GFP_ATOMIC);
 		if (!clone)
 			goto out_nomem;
-		clone->next = head->next;
-		head->next = clone;
 		skb_shinfo(clone)->frag_list = skb_shinfo(head)->frag_list;
 		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->truesize += clone->truesize;
-		head->len -= clone->len;
 		clone->csum = 0;
 		clone->ip_summed = head->ip_summed;
 		add_frag_mem_limit(qp->q.net, clone->truesize);
+		skb_shinfo(head)->frag_list = clone;
+		nextp = &clone->next;
+	} else {
+		nextp = &skb_shinfo(head)->frag_list;
 	}
 
-	skb_shinfo(head)->frag_list = head->next;
 	skb_push(head, head->data - skb_network_header(head));
 
-	for (fp=head->next; fp; fp = fp->next) {
+	/* Traverse the tree in order, to build frag_list. */
-		head->data_len += fp->len;
+	fp = FRAG_CB(head)->next_frag;
-		head->len += fp->len;
+	rbn = rb_next(&head->rbnode);
-		if (head->ip_summed != fp->ip_summed)
+	rb_erase(&head->rbnode, &qp->q.rb_fragments);
-			head->ip_summed = CHECKSUM_NONE;
+	while (rbn || fp) {
-		else if (head->ip_summed == CHECKSUM_COMPLETE)
+		/* fp points to the next sk_buff in the current run;
-			head->csum = csum_add(head->csum, fp->csum);
+		 * rbn points to the next run.
-		head->truesize += fp->truesize;
+		 */
+		/* Go through the current run. */
+		while (fp) {
+			*nextp = fp;
+			nextp = &fp->next;
+			fp->prev = NULL;
+			memset(&fp->rbnode, 0, sizeof(fp->rbnode));
+			fp->sk = NULL;
+			head->data_len += fp->len;
+			head->len += fp->len;
+			if (head->ip_summed != fp->ip_summed)
+				head->ip_summed = CHECKSUM_NONE;
+			else if (head->ip_summed == CHECKSUM_COMPLETE)
+				head->csum = csum_add(head->csum, fp->csum);
+			head->truesize += fp->truesize;
+			fp = FRAG_CB(fp)->next_frag;
+		}
+		/* Move to the next run. */
+		if (rbn) {
+			struct rb_node *rbnext = rb_next(rbn);
+
+			fp = rb_to_skb(rbn);
+			rb_erase(rbn, &qp->q.rb_fragments);
+			rbn = rbnext;
+		}
 	}
 	sub_frag_mem_limit(qp->q.net, head->truesize);
 
+	*nextp = NULL;
 	head->next = NULL;
+	head->prev = NULL;
 	head->dev = dev;
 	head->tstamp = qp->q.stamp;
 	IPCB(head)->frag_max_size = max(qp->max_df_size, qp->q.max_size);
@@ -648,7 +656,9 @@ static int ip_frag_reasm(struct ipq *qp, struct sk_buff *prev,
 
 	IP_INC_STATS_BH(net, IPSTATS_MIB_REASMOKS);
 	qp->q.fragments = NULL;
+	qp->q.rb_fragments = RB_ROOT;
 	qp->q.fragments_tail = NULL;
+	qp->q.last_run_head = NULL;
 	return 0;
 
 out_nomem:
@@ -656,7 +666,7 @@ 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_BH(net, IPSTATS_MIB_REASMFAILS);
 	return err;
@@ -734,25 +744,46 @@ struct sk_buff *ip_check_defrag(struct net *net, struct sk_buff *skb, u32 user)
 }
 EXPORT_SYMBOL(ip_check_defrag);
 
+unsigned int inet_frag_rbtree_purge(struct rb_root *root)
+{
+	struct rb_node *p = rb_first(root);
+	unsigned int sum = 0;
+
+	while (p) {
+		struct sk_buff *skb = rb_entry(p, struct sk_buff, rbnode);
+
+		p = rb_next(p);
+		rb_erase(&skb->rbnode, root);
+		while (skb) {
+			struct sk_buff *next = FRAG_CB(skb)->next_frag;
+
+			sum += skb->truesize;
+			kfree_skb(skb);
+			skb = next;
+		}
+	}
+	return sum;
+}
+EXPORT_SYMBOL(inet_frag_rbtree_purge);
+
 #ifdef CONFIG_SYSCTL
-static int zero;
+static int dist_min;
 
 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
 	},
 	{
@@ -781,7 +812,7 @@ static struct ctl_table ip4_frags_ctl_table[] = {
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec_minmax,
-		.extra1		= &zero
+		.extra1		= &dist_min,
 	},
 	{ }
 };
@@ -853,6 +884,8 @@ 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
@@ -876,15 +909,21 @@ static int __net_init ipv4_frags_init_net(struct net *net)
 	 */
 	net->ipv4.frags.timeout = IP_FRAG_TIME;
 
-	inet_frags_init_net(&net->ipv4.frags);
+	net->ipv4.frags.f = &ip4_frags;
 
-	return ip4_frags_ns_ctl_register(net);
+	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 = {
@@ -892,18 +931,50 @@ 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.skb_free = NULL;
 	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);
 }

net/ipv4/proc.c

@@ -52,7 +52,6 @@
 static int sockstat_seq_show(struct seq_file *seq, void *v)
 {
 	struct net *net = seq->private;
-	unsigned int frag_mem;
 	int orphans, sockets;
 
 	local_bh_disable();
@@ -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 %lu\n",
-	seq_printf(seq,  "FRAG: inuse %u memory %u\n", !!frag_mem, frag_mem);
+		   atomic_read(&net->ipv4.frags.rhashtable.nelems),
+		   frag_mem_limit(&net->ipv4.frags));
 	return 0;
 }
 
@@ -132,6 +132,7 @@ static const struct snmp_mib snmp4_ipextstats_list[] = {
 	SNMP_MIB_ITEM("InECT1Pkts", IPSTATS_MIB_ECT1PKTS),
 	SNMP_MIB_ITEM("InECT0Pkts", IPSTATS_MIB_ECT0PKTS),
 	SNMP_MIB_ITEM("InCEPkts", IPSTATS_MIB_CEPKTS),
+	SNMP_MIB_ITEM("ReasmOverlaps", IPSTATS_MIB_REASM_OVERLAPS),
 	SNMP_MIB_SENTINEL
 };
 

net/ipv6/netfilter/nf_conntrack_reasm.c

@@ -64,7 +64,6 @@ struct nf_ct_frag6_skb_cb
 static struct inet_frags nf_frags;
 
 #ifdef CONFIG_SYSCTL
-static int zero;
 
 static struct ctl_table nf_ct_frag6_sysctl_table[] = {
 	{
@@ -77,18 +76,17 @@ static struct ctl_table nf_ct_frag6_sysctl_table[] = {
 	{
 		.procname	= "nf_conntrack_frag6_low_thresh",
 		.data		= &init_net.nf_frag.frags.low_thresh,
-		.maxlen		= sizeof(unsigned int),
+		.maxlen		= sizeof(unsigned long),
 		.mode		= 0644,
-		.proc_handler	= proc_dointvec_minmax,
+		.proc_handler	= proc_doulongvec_minmax,
-		.extra1		= &zero,
 		.extra2		= &init_net.nf_frag.frags.high_thresh
 	},
 	{
 		.procname	= "nf_conntrack_frag6_high_thresh",
 		.data		= &init_net.nf_frag.frags.high_thresh,
-		.maxlen		= sizeof(unsigned int),
+		.maxlen		= sizeof(unsigned long),
 		.mode		= 0644,
-		.proc_handler	= proc_dointvec_minmax,
+		.proc_handler	= proc_doulongvec_minmax,
 		.extra1		= &init_net.nf_frag.frags.low_thresh
 	},
 	{ }
@@ -153,23 +151,6 @@ static inline u8 ip6_frag_ecn(const struct ipv6hdr *ipv6h)
 	return 1 << (ipv6_get_dsfield(ipv6h) & INET_ECN_MASK);
 }
 
-static unsigned int nf_hash_frag(__be32 id, const struct in6_addr *saddr,
-				 const struct in6_addr *daddr)
-{
-	net_get_random_once(&nf_frags.rnd, sizeof(nf_frags.rnd));
-	return jhash_3words(ipv6_addr_hash(saddr), ipv6_addr_hash(daddr),
-			    (__force u32)id, nf_frags.rnd);
-}
-
-
-static unsigned int nf_hashfn(const struct inet_frag_queue *q)
-{
-	const struct frag_queue *nq;
-
-	nq = container_of(q, struct frag_queue, q);
-	return nf_hash_frag(nq->id, &nq->saddr, &nq->daddr);
-}
-
 static void nf_skb_free(struct sk_buff *skb)
 {
 	if (NFCT_FRAG6_CB(skb)->orig)
@@ -184,34 +165,26 @@ static void nf_ct_frag6_expire(unsigned long data)
 	fq = container_of((struct inet_frag_queue *)data, struct frag_queue, q);
 	net = container_of(fq->q.net, struct net, nf_frag.frags);
 
-	ip6_expire_frag_queue(net, fq, &nf_frags);
+	ip6_expire_frag_queue(net, fq);
 }
 
 /* Creation primitives. */
-static inline struct frag_queue *fq_find(struct net *net, __be32 id,
+static struct frag_queue *fq_find(struct net *net, __be32 id, u32 user,
-					 u32 user, struct in6_addr *src,
+				  const struct ipv6hdr *hdr, int iif)
-					 struct in6_addr *dst, int iif, u8 ecn)
 {
+	struct frag_v6_compare_key key = {
+		.id = id,
+		.saddr = hdr->saddr,
+		.daddr = hdr->daddr,
+		.user = user,
+		.iif = iif,
+	};
 	struct inet_frag_queue *q;
-	struct ip6_create_arg arg;
-	unsigned int hash;
 
-	arg.id = id;
+	q = inet_frag_find(&net->nf_frag.frags, &key);
-	arg.user = user;
+	if (!q)
-	arg.src = src;
-	arg.dst = dst;
-	arg.iif = iif;
-	arg.ecn = ecn;
-
-	local_bh_disable();
-	hash = nf_hash_frag(id, src, dst);
-
-	q = inet_frag_find(&net->nf_frag.frags, &nf_frags, &arg, hash);
-	local_bh_enable();
-	if (IS_ERR_OR_NULL(q)) {
-		inet_frag_maybe_warn_overflow(q, pr_fmt());
 		return NULL;
-	}
+
 	return container_of(q, struct frag_queue, q);
 }
 
@@ -362,7 +335,7 @@ found:
 	return 0;
 
 discard_fq:
-	inet_frag_kill(&fq->q, &nf_frags);
+	inet_frag_kill(&fq->q);
 err:
 	return -1;
 }
@@ -383,7 +356,7 @@ nf_ct_frag6_reasm(struct frag_queue *fq, struct net_device *dev)
 	int    payload_len;
 	u8 ecn;
 
-	inet_frag_kill(&fq->q, &nf_frags);
+	inet_frag_kill(&fq->q);
 
 	WARN_ON(head == NULL);
 	WARN_ON(NFCT_FRAG6_CB(head)->offset != 0);
@@ -454,6 +427,7 @@ nf_ct_frag6_reasm(struct frag_queue *fq, struct net_device *dev)
 		else if (head->ip_summed == CHECKSUM_COMPLETE)
 			head->csum = csum_add(head->csum, fp->csum);
 		head->truesize += fp->truesize;
+		fp->sk = NULL;
 	}
 	sub_frag_mem_limit(fq->q.net, head->truesize);
 
@@ -472,6 +446,7 @@ nf_ct_frag6_reasm(struct frag_queue *fq, struct net_device *dev)
 					  head->csum);
 
 	fq->q.fragments = NULL;
+	fq->q.rb_fragments = RB_ROOT;
 	fq->q.fragments_tail = NULL;
 
 	/* all original skbs are linked into the NFCT_FRAG6_CB(head).orig */
@@ -601,9 +576,13 @@ struct sk_buff *nf_ct_frag6_gather(struct net *net, struct sk_buff *skb, u32 use
 	hdr = ipv6_hdr(clone);
 	fhdr = (struct frag_hdr *)skb_transport_header(clone);
 
+	if (clone->len - skb_network_offset(clone) < IPV6_MIN_MTU &&
+	    fhdr->frag_off & htons(IP6_MF))
+		goto ret_orig;
+
 	skb_orphan(skb);
-	fq = fq_find(net, fhdr->identification, user, &hdr->saddr, &hdr->daddr,
+	fq = fq_find(net, fhdr->identification, user, hdr,
-		     skb->dev ? skb->dev->ifindex : 0, ip6_frag_ecn(hdr));
+		     skb->dev ? skb->dev->ifindex : 0);
 	if (fq == NULL) {
 		pr_debug("Can't find and can't create new queue\n");
 		goto ret_orig;
@@ -614,7 +593,7 @@ struct sk_buff *nf_ct_frag6_gather(struct net *net, struct sk_buff *skb, u32 use
 	if (nf_ct_frag6_queue(fq, clone, fhdr, nhoff) < 0) {
 		spin_unlock_bh(&fq->q.lock);
 		pr_debug("Can't insert skb to queue\n");
-		inet_frag_put(&fq->q, &nf_frags);
+		inet_frag_put(&fq->q);
 		goto ret_orig;
 	}
 
@@ -626,7 +605,7 @@ struct sk_buff *nf_ct_frag6_gather(struct net *net, struct sk_buff *skb, u32 use
 	}
 	spin_unlock_bh(&fq->q.lock);
 
-	inet_frag_put(&fq->q, &nf_frags);
+	inet_frag_put(&fq->q);
 	return ret_skb;
 
 ret_orig:
@@ -650,18 +629,26 @@ EXPORT_SYMBOL_GPL(nf_ct_frag6_consume_orig);
 
 static int nf_ct_net_init(struct net *net)
 {
+	int res;
+
 	net->nf_frag.frags.high_thresh = IPV6_FRAG_HIGH_THRESH;
 	net->nf_frag.frags.low_thresh = IPV6_FRAG_LOW_THRESH;
 	net->nf_frag.frags.timeout = IPV6_FRAG_TIMEOUT;
-	inet_frags_init_net(&net->nf_frag.frags);
+	net->nf_frag.frags.f = &nf_frags;
 
-	return nf_ct_frag6_sysctl_register(net);
+	res = inet_frags_init_net(&net->nf_frag.frags);
+	if (res < 0)
+		return res;
+	res = nf_ct_frag6_sysctl_register(net);
+	if (res < 0)
+		inet_frags_exit_net(&net->nf_frag.frags);
+	return res;
 }
 
 static void nf_ct_net_exit(struct net *net)
 {
 	nf_ct_frags6_sysctl_unregister(net);
-	inet_frags_exit_net(&net->nf_frag.frags, &nf_frags);
+	inet_frags_exit_net(&net->nf_frag.frags);
 }
 
 static struct pernet_operations nf_ct_net_ops = {
@@ -673,14 +660,13 @@ int nf_ct_frag6_init(void)
 {
 	int ret = 0;
 
-	nf_frags.hashfn = nf_hashfn;
 	nf_frags.constructor = ip6_frag_init;
 	nf_frags.destructor = NULL;
 	nf_frags.skb_free = nf_skb_free;
 	nf_frags.qsize = sizeof(struct frag_queue);
-	nf_frags.match = ip6_frag_match;
 	nf_frags.frag_expire = nf_ct_frag6_expire;
 	nf_frags.frags_cache_name = nf_frags_cache_name;
+	nf_frags.rhash_params = ip6_rhash_params;
 	ret = inet_frags_init(&nf_frags);
 	if (ret)
 		goto out;

net/ipv6/proc.c

@@ -33,7 +33,6 @@
 static int sockstat6_seq_show(struct seq_file *seq, void *v)
 {
 	struct net *net = seq->private;
-	unsigned int frag_mem = ip6_frag_mem(net);
 
 	seq_printf(seq, "TCP6: inuse %d\n",
 		       sock_prot_inuse_get(net, &tcpv6_prot));
@@ -43,7 +42,9 @@ static int sockstat6_seq_show(struct seq_file *seq, void *v)
 			sock_prot_inuse_get(net, &udplitev6_prot));
 	seq_printf(seq, "RAW6: inuse %d\n",
 		       sock_prot_inuse_get(net, &rawv6_prot));
-	seq_printf(seq, "FRAG6: inuse %u memory %u\n", !!frag_mem, frag_mem);
+	seq_printf(seq, "FRAG6: inuse %u memory %lu\n",
+		   atomic_read(&net->ipv6.frags.rhashtable.nelems),
+		   frag_mem_limit(&net->ipv6.frags));
 	return 0;
 }
 

net/ipv6/reassembly.c

@@ -79,94 +79,58 @@ static struct inet_frags ip6_frags;
 static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *prev,
 			  struct net_device *dev);
 
-/*
- * 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)
-{
-	net_get_random_once(&ip6_frags.rnd, sizeof(ip6_frags.rnd));
-	return jhash_3words(ipv6_addr_hash(saddr), ipv6_addr_hash(daddr),
-			    (__force u32)id, ip6_frags.rnd);
-}
-
-static unsigned int ip6_hashfn(const struct inet_frag_queue *q)
-{
-	const struct frag_queue *fq;
-
-	fq = container_of(q, struct frag_queue, q);
-	return inet6_hash_frag(fq->id, &fq->saddr, &fq->daddr);
-}
-
-bool ip6_frag_match(const struct inet_frag_queue *q, const void *a)
-{
-	const struct frag_queue *fq;
-	const struct ip6_create_arg *arg = a;
-
-	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) &&
-		(arg->iif == fq->iif ||
-		 !(ipv6_addr_type(arg->dst) & (IPV6_ADDR_MULTICAST |
-					       IPV6_ADDR_LINKLOCAL)));
-}
-EXPORT_SYMBOL(ip6_frag_match);
-
 void ip6_frag_init(struct inet_frag_queue *q, const void *a)
 {
 	struct frag_queue *fq = container_of(q, struct frag_queue, q);
-	const struct ip6_create_arg *arg = a;
+	const struct frag_v6_compare_key *key = a;
 
-	fq->id = arg->id;
+	q->key.v6 = *key;
-	fq->user = arg->user;
+	fq->ecn = 0;
-	fq->saddr = *arg->src;
-	fq->daddr = *arg->dst;
-	fq->ecn = arg->ecn;
 }
 EXPORT_SYMBOL(ip6_frag_init);
 
-void ip6_expire_frag_queue(struct net *net, struct frag_queue *fq,
+void ip6_expire_frag_queue(struct net *net, struct frag_queue *fq)
-			   struct inet_frags *frags)
 {
 	struct net_device *dev = NULL;
+	struct sk_buff *head;
 
+	rcu_read_lock();
 	spin_lock(&fq->q.lock);
 
 	if (fq->q.flags & INET_FRAG_COMPLETE)
 		goto out;
 
-	inet_frag_kill(&fq->q, frags);
+	inet_frag_kill(&fq->q);
 
-	rcu_read_lock();
 	dev = dev_get_by_index_rcu(net, fq->iif);
 	if (!dev)
-		goto out_rcu_unlock;
+		goto out;
 
 	IP6_INC_STATS_BH(net, __in6_dev_get(dev), IPSTATS_MIB_REASMFAILS);
-
-	if (inet_frag_evicting(&fq->q))
-		goto out_rcu_unlock;
-
 	IP6_INC_STATS_BH(net, __in6_dev_get(dev), IPSTATS_MIB_REASMTIMEOUT);
 
 	/* Don't send error if the first segment did not arrive. */
-	if (!(fq->q.flags & INET_FRAG_FIRST_IN) || !fq->q.fragments)
+	head = fq->q.fragments;
-		goto out_rcu_unlock;
+	if (!(fq->q.flags & INET_FRAG_FIRST_IN) || !head)
+		goto out;
 
 	/* 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;
+	head->dev = dev;
-	icmpv6_send(fq->q.fragments, ICMPV6_TIME_EXCEED, ICMPV6_EXC_FRAGTIME, 0);
+	skb_get(head);
-out_rcu_unlock:
+	spin_unlock(&fq->q.lock);
-	rcu_read_unlock();
+
+	icmpv6_send(head, ICMPV6_TIME_EXCEED, ICMPV6_EXC_FRAGTIME, 0);
+	kfree_skb(head);
+	goto out_rcu_unlock;
+
 out:
 	spin_unlock(&fq->q.lock);
-	inet_frag_put(&fq->q, frags);
+out_rcu_unlock:
+	rcu_read_unlock();
+	inet_frag_put(&fq->q);
 }
 EXPORT_SYMBOL(ip6_expire_frag_queue);
 
@@ -178,31 +142,29 @@ static void ip6_frag_expire(unsigned long data)
 	fq = container_of((struct inet_frag_queue *)data, struct frag_queue, q);
 	net = container_of(fq->q.net, struct net, ipv6.frags);
 
-	ip6_expire_frag_queue(net, fq, &ip6_frags);
+	ip6_expire_frag_queue(net, fq);
 }
 
 static struct frag_queue *
-fq_find(struct net *net, __be32 id, const struct in6_addr *src,
+fq_find(struct net *net, __be32 id, const struct ipv6hdr *hdr, int iif)
-	const struct in6_addr *dst, int iif, u8 ecn)
 {
+	struct frag_v6_compare_key key = {
+		.id = id,
+		.saddr = hdr->saddr,
+		.daddr = hdr->daddr,
+		.user = IP6_DEFRAG_LOCAL_DELIVER,
+		.iif = iif,
+	};
 	struct inet_frag_queue *q;
-	struct ip6_create_arg arg;
-	unsigned int hash;
 
-	arg.id = id;
+	if (!(ipv6_addr_type(&hdr->daddr) & (IPV6_ADDR_MULTICAST |
-	arg.user = IP6_DEFRAG_LOCAL_DELIVER;
+					    IPV6_ADDR_LINKLOCAL)))
-	arg.src = src;
+		key.iif = 0;
-	arg.dst = dst;
-	arg.iif = iif;
-	arg.ecn = ecn;
 
-	hash = inet6_hash_frag(id, src, dst);
+	q = inet_frag_find(&net->ipv6.frags, &key);
-
+	if (!q)
-	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;
-	}
+
 	return container_of(q, struct frag_queue, q);
 }
 
@@ -359,7 +321,7 @@ found:
 	return -1;
 
 discard_fq:
-	inet_frag_kill(&fq->q, &ip6_frags);
+	inet_frag_kill(&fq->q);
 err:
 	IP6_INC_STATS_BH(net, ip6_dst_idev(skb_dst(skb)),
 			 IPSTATS_MIB_REASMFAILS);
@@ -386,7 +348,7 @@ static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *prev,
 	int sum_truesize;
 	u8 ecn;
 
-	inet_frag_kill(&fq->q, &ip6_frags);
+	inet_frag_kill(&fq->q);
 
 	ecn = ip_frag_ecn_table[fq->ecn];
 	if (unlikely(ecn == 0xff))
@@ -503,6 +465,7 @@ static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *prev,
 	IP6_INC_STATS_BH(net, __in6_dev_get(dev), IPSTATS_MIB_REASMOKS);
 	rcu_read_unlock();
 	fq->q.fragments = NULL;
+	fq->q.rb_fragments = RB_ROOT;
 	fq->q.fragments_tail = NULL;
 	return 1;
 
@@ -524,6 +487,7 @@ static int ipv6_frag_rcv(struct sk_buff *skb)
 	struct frag_queue *fq;
 	const struct ipv6hdr *hdr = ipv6_hdr(skb);
 	struct net *net = dev_net(skb_dst(skb)->dev);
+	int iif;
 
 	if (IP6CB(skb)->flags & IP6SKB_FRAGMENTED)
 		goto fail_hdr;
@@ -552,17 +516,22 @@ static int ipv6_frag_rcv(struct sk_buff *skb)
 		return 1;
 	}
 
-	fq = fq_find(net, fhdr->identification, &hdr->saddr, &hdr->daddr,
+	if (skb->len - skb_network_offset(skb) < IPV6_MIN_MTU &&
-		     skb->dev ? skb->dev->ifindex : 0, ip6_frag_ecn(hdr));
+	    fhdr->frag_off & htons(IP6_MF))
+		goto fail_hdr;
+
+	iif = skb->dev ? skb->dev->ifindex : 0;
+	fq = fq_find(net, fhdr->identification, hdr, iif);
 	if (fq) {
 		int ret;
 
 		spin_lock(&fq->q.lock);
 
+		fq->iif = iif;
 		ret = ip6_frag_queue(fq, skb, fhdr, IP6CB(skb)->nhoff);
 
 		spin_unlock(&fq->q.lock);
-		inet_frag_put(&fq->q, &ip6_frags);
+		inet_frag_put(&fq->q);
 		return ret;
 	}
 
@@ -583,24 +552,22 @@ static const struct inet6_protocol frag_protocol = {
 };
 
 #ifdef CONFIG_SYSCTL
-static int zero;
 
 static struct ctl_table ip6_frags_ns_ctl_table[] = {
 	{
 		.procname	= "ip6frag_high_thresh",
 		.data		= &init_net.ipv6.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.ipv6.frags.low_thresh
 	},
 	{
 		.procname	= "ip6frag_low_thresh",
 		.data		= &init_net.ipv6.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.ipv6.frags.high_thresh
 	},
 	{
@@ -708,19 +675,27 @@ static void ip6_frags_sysctl_unregister(void)
 
 static int __net_init ipv6_frags_init_net(struct net *net)
 {
+	int res;
+
 	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;
+	net->ipv6.frags.f = &ip6_frags;
 
-	inet_frags_init_net(&net->ipv6.frags);
+	res = inet_frags_init_net(&net->ipv6.frags);
+	if (res < 0)
+		return res;
 
-	return ip6_frags_ns_sysctl_register(net);
+	res = ip6_frags_ns_sysctl_register(net);
+	if (res < 0)
+		inet_frags_exit_net(&net->ipv6.frags);
+	return res;
 }
 
 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);
+	inet_frags_exit_net(&net->ipv6.frags);
 }
 
 static struct pernet_operations ip6_frags_ops = {
@@ -728,14 +703,55 @@ static struct pernet_operations ip6_frags_ops = {
 	.exit = ipv6_frags_exit_net,
 };
 
+static u32 ip6_key_hashfn(const void *data, u32 len, u32 seed)
+{
+	return jhash2(data,
+		      sizeof(struct frag_v6_compare_key) / sizeof(u32), seed);
+}
+
+static u32 ip6_obj_hashfn(const void *data, u32 len, u32 seed)
+{
+	const struct inet_frag_queue *fq = data;
+
+	return jhash2((const u32 *)&fq->key.v6,
+		      sizeof(struct frag_v6_compare_key) / sizeof(u32), seed);
+}
+
+static int ip6_obj_cmpfn(struct rhashtable_compare_arg *arg, const void *ptr)
+{
+	const struct frag_v6_compare_key *key = arg->key;
+	const struct inet_frag_queue *fq = ptr;
+
+	return !!memcmp(&fq->key, key, sizeof(*key));
+}
+
+const struct rhashtable_params ip6_rhash_params = {
+	.head_offset		= offsetof(struct inet_frag_queue, node),
+	.hashfn			= ip6_key_hashfn,
+	.obj_hashfn		= ip6_obj_hashfn,
+	.obj_cmpfn		= ip6_obj_cmpfn,
+	.automatic_shrinking	= true,
+};
+EXPORT_SYMBOL(ip6_rhash_params);
+
 int __init ipv6_frag_init(void)
 {
 	int ret;
 
-	ret = inet6_add_protocol(&frag_protocol, IPPROTO_FRAGMENT);
+	ip6_frags.constructor = ip6_frag_init;
+	ip6_frags.destructor = NULL;
+	ip6_frags.qsize = sizeof(struct frag_queue);
+	ip6_frags.frag_expire = ip6_frag_expire;
+	ip6_frags.frags_cache_name = ip6_frag_cache_name;
+	ip6_frags.rhash_params = ip6_rhash_params;
+	ret = inet_frags_init(&ip6_frags);
 	if (ret)
 		goto out;
 
+	ret = inet6_add_protocol(&frag_protocol, IPPROTO_FRAGMENT);
+	if (ret)
+		goto err_protocol;
+
 	ret = ip6_frags_sysctl_register();
 	if (ret)
 		goto err_sysctl;
@@ -744,17 +760,6 @@ int __init ipv6_frag_init(void)
 	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.frags_cache_name = ip6_frag_cache_name;
-	ret = inet_frags_init(&ip6_frags);
-	if (ret)
-		goto err_pernet;
 out:
 	return ret;
 
@@ -762,6 +767,8 @@ err_pernet:
 	ip6_frags_sysctl_unregister();
 err_sysctl:
 	inet6_del_protocol(&frag_protocol, IPPROTO_FRAGMENT);
+err_protocol:
+	inet_frags_fini(&ip6_frags);
 	goto out;
 }