Merge branch 'ip-Use-rb-trees-for-IP-frag-queue'

Peter Oskolkov says:

====================
ip: Use rb trees for IP frag queue.

This patchset
 * changes IPv4 defrag behavior to match that of IPv6: overlapping
   fragments now cause the whole IP datagram to be discarded (suggested
   by David Miller): there are no legitimate use cases for overlapping
   fragments;
 * changes IPv4 defrag queue from a list to a rb tree (suggested
   by Eric Dumazet): this change removes a potential attach vector.

Upcoming patches will contain similar changes for IPv6 frag queue,
as well as a comprehensive IP defrag self-test (temporarily delayed).
====================
Signed-off-by: David S. Miller <davem@davemloft.net>

include/linux/skbuff.h

@@ -676,13 +676,16 @@ struct sk_buff {
 				 * UDP receive path is one user.
 				 */
 				unsigned long		dev_scratch;
-				int			ip_defrag_offset;
 			};
 		};
-		struct rb_node		rbnode; /* used in netem & tcp stack */
+		struct rb_node		rbnode; /* used in netem, ip4 defrag, and tcp stack */
 		struct list_head	list;
 	};
-	struct sock		*sk;
+
+	union {
+		struct sock		*sk;
+		int			ip_defrag_offset;
+	};
 
 	union {
 		ktime_t		tstamp;
@@ -2585,7 +2588,7 @@ 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);
 

include/net/inet_frag.h

@@ -75,7 +75,8 @@ struct inet_frag_queue {
 	struct timer_list	timer;
 	spinlock_t		lock;
 	refcount_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;
 	ktime_t			stamp;
 	int			len;

include/uapi/linux/snmp.h

@@ -56,6 +56,7 @@ enum
 	IPSTATS_MIB_ECT1PKTS,			/* InECT1Pkts */
 	IPSTATS_MIB_ECT0PKTS,			/* InECT0Pkts */
 	IPSTATS_MIB_CEPKTS,			/* InCEPkts */
+	IPSTATS_MIB_REASM_OVERLAPS,		/* ReasmOverlaps */
 	__IPSTATS_MIB_MAX
 };
 

net/core/skbuff.c

@@ -2858,23 +2858,27 @@ 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/ipv4/inet_fragment.c

@@ -137,12 +137,16 @@ void inet_frag_destroy(struct inet_frag_queue *q)
 	fp = q->fragments;
 	nf = q->net;
 	f = nf->f;
-	while (fp) {
-		struct sk_buff *xp = fp->next;
-
-		sum_truesize += fp->truesize;
-		kfree_skb(fp);
-		fp = xp;
+	if (fp) {
+		do {
+			struct sk_buff *xp = fp->next;
+
+			sum_truesize += fp->truesize;
+			kfree_skb(fp);
+			fp = xp;
+		} while (fp);
+	} else {
+		sum_truesize = skb_rbtree_purge(&q->rb_fragments);
 	}
 	sum = sum_truesize + f->qsize;
 

net/ipv4/proc.c

@@ -119,6 +119,7 @@ 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

@@ -463,6 +463,7 @@ nf_ct_frag6_reasm(struct frag_queue *fq, struct sk_buff *prev,  struct net_devic
 					  head->csum);
 
 	fq->q.fragments = NULL;
+	fq->q.rb_fragments = RB_ROOT;
 	fq->q.fragments_tail = NULL;
 
 	return true;

net/ipv6/reassembly.c

@@ -405,6 +405,7 @@ static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *prev,
 	__IP6_INC_STATS(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;