1 files changed, 108 insertions, 101 deletions

diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c
index 58f2139ebb5e..ec917f58d105 100644
--- a/net/ipv6/reassembly.c
+++ b/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;
-	fq->user = arg->user;
-	fq->saddr = *arg->src;
-	fq->daddr = *arg->dst;
-	fq->ecn = arg->ecn;
+	q->key.v6 = *key;
+	fq->ecn = 0;
 }
 EXPORT_SYMBOL(ip6_frag_init);
 
-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)
 {
 	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)
-		goto out_rcu_unlock;
+	head = fq->q.fragments;
+	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;
-	icmpv6_send(fq->q.fragments, ICMPV6_TIME_EXCEED, ICMPV6_EXC_FRAGTIME, 0);
-out_rcu_unlock:
-	rcu_read_unlock();
+	head->dev = dev;
+	skb_get(head);
+	spin_unlock(&fq->q.lock);
+
+	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,
-	const struct in6_addr *dst, int iif, u8 ecn)
+fq_find(struct net *net, __be32 id, const struct ipv6hdr *hdr, int iif)
 {
+	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;
-	arg.user = IP6_DEFRAG_LOCAL_DELIVER;
-	arg.src = src;
-	arg.dst = dst;
-	arg.iif = iif;
-	arg.ecn = ecn;
+	if (!(ipv6_addr_type(&hdr->daddr) & (IPV6_ADDR_MULTICAST |
+					    IPV6_ADDR_LINKLOCAL)))
+		key.iif = 0;
 
-	hash = inet6_hash_frag(id, src, dst);
-
-	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());
+	q = inet_frag_find(&net->ipv6.frags, &key);
+	if (!q)
 		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,
-		     skb->dev ? skb->dev->ifindex : 0, ip6_frag_ecn(hdr));
+	if (skb->len - skb_network_offset(skb) < IPV6_MIN_MTU &&
+	    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,
-		.extra1		= &zero,
+		.proc_handler	= proc_doulongvec_minmax,
 		.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;
 }