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>

6 files changed, 186 insertions, 134 deletions

diff --git a/include/linux/rhashtable.h b/include/linux/rhashtable.h
index e50b31d18462..e97cdfd6cba9 100644
--- a/include/linux/rhashtable.h
+++ b/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);
 }
 
-/**
- * rhashtable_lookup_fast - search hash table, inlined version
- * @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(
+/* Internal function, do not use. */
+static inline struct rhash_head *__rhashtable_lookup(
 	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 rht_obj(ht, he);
+		return 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,
-					params);
+	ret = __rhashtable_insert_fast(ht, key + ht->p.key_offset, obj, params);
+	if (IS_ERR(ret))
+		return PTR_ERR(ret);
+
+	return ret == NULL ? 0 : -EEXIST;
 }
 
 /**
@@ -736,6 +789,32 @@ 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);
 
 	return __rhashtable_insert_fast(ht, key, obj, params);
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 6d39d81d3c38..502787c29ce9 100644
--- a/include/linux/skbuff.h
+++ b/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)
-		skb->ip_summed = CHECKSUM_NONE;
-	return __pskb_trim(skb, len);
+	return pskb_trim_rcsum_slow(skb, len);
 }
 
 #define rb_to_skb(rb) rb_entry_safe(rb, struct sk_buff, rbnode)
diff --git a/include/net/inet_frag.h b/include/net/inet_frag.h
index c26a6e4dc306..6260ec146142 100644
--- a/include/net/inet_frag.h
+++ b/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;
-	int			low_thresh;
+	struct inet_frags	*f;
+
+	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 hlist_node	list_evictor;
-};
-
-#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 netns_frags      *net;
+	struct rcu_head		rcu;
 };
 
 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_destroy(struct inet_frag_queue *q, struct inet_frags *f);
-struct inet_frag_queue *inet_frag_find(struct netns_frags *nf,
-		struct inet_frags *f, void *key, unsigned int hash);
+void inet_frag_kill(struct inet_frag_queue *q);
+void inet_frag_destroy(struct inet_frag_queue *q);
+struct inet_frag_queue *inet_frag_find(struct netns_frags *nf, void *key);
 
-void inet_frag_maybe_warn_overflow(struct inet_frag_queue *q,
-				   const char *prefix);
+/* Free all skbs in the queue; return the sum of their truesizes. */
+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);
-}
-
-static inline bool inet_frag_evicting(struct inet_frag_queue *q)
-{
-	return !hlist_unhashed(&q->list_evictor);
+		inet_frag_destroy(q);
 }
 
 /* Memory Tracking Functions. */
 
-static inline int frag_mem_limit(struct netns_frags *nf)
-{
-	return atomic_read(&nf->mem);
-}
-
-static inline void sub_frag_mem_limit(struct netns_frags *nf, int i)
+static inline long frag_mem_limit(const struct netns_frags *nf)
 {
-	atomic_sub(i, &nf->mem);
+	return atomic_long_read(&nf->mem);
 }
 
-static inline void add_frag_mem_limit(struct netns_frags *nf, int i)
+static inline void sub_frag_mem_limit(struct netns_frags *nf, long val)
 {
-	atomic_add(i, &nf->mem);
+	atomic_long_sub(val, &nf->mem);
 }
 
-static inline int sum_frag_mem_limit(struct netns_frags *nf)
+static inline void add_frag_mem_limit(struct netns_frags *nf, long val)
 {
-	return atomic_read(&nf->mem);
+	atomic_long_add(val, &nf->mem);
 }
 
 /* RFC 3168 support :
diff --git a/include/net/ip.h b/include/net/ip.h
index 10664a684acf..47651d8b51de 100644
--- a/include/net/ip.h
+++ b/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
diff --git a/include/net/ipv6.h b/include/net/ipv6.h
index 0e01d570fa22..c07cf9596b6f 100644
--- a/include/net/ipv6.h
+++ b/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,
-			   struct inet_frags *frags);
+void ip6_expire_frag_queue(struct net *net, struct frag_queue *fq);
 
 static inline bool ipv6_addr_any(const struct in6_addr *a)
 {
diff --git a/include/uapi/linux/snmp.h b/include/uapi/linux/snmp.h
index 25a9ad8bcef1..9de808ebce05 100644
--- a/include/uapi/linux/snmp.h
+++ b/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
 };