1 files changed, 197 insertions, 74 deletions

diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c
index 86964b353c3..ed32313e307 100644
--- a/net/ipv4/ip_fragment.c
+++ b/net/ipv4/ip_fragment.c
@@ -20,6 +20,8 @@
  *		Patrick McHardy :	LRU queue of frag heads for evictor.
  */
 
+#define pr_fmt(fmt) "IPv4: " fmt
+
 #include <linux/compiler.h>
 #include <linux/module.h>
 #include <linux/types.h>
@@ -32,6 +34,9 @@
 #include <linux/netdevice.h>
 #include <linux/jhash.h>
 #include <linux/random.h>
+#include <linux/slab.h>
+#include <net/route.h>
+#include <net/dst.h>
 #include <net/sock.h>
 #include <net/ip.h>
 #include <net/icmp.h>
@@ -42,6 +47,7 @@
 #include <linux/udp.h>
 #include <linux/inet.h>
 #include <linux/netfilter_ipv4.h>
+#include <net/inet_ecn.h>
 
 /* NOTE. Logic of IP defragmentation is parallel to corresponding IPv6
  * code now. If you change something here, _PLEASE_ update ipv6/reassembly.c
@@ -67,11 +73,17 @@ struct ipq {
 	__be32		daddr;
 	__be16		id;
 	u8		protocol;
+	u8		ecn; /* RFC3168 support */
 	int             iif;
 	unsigned int    rid;
 	struct inet_peer *peer;
 };
 
+static inline u8 ip4_frag_ecn(u8 tos)
+{
+	return 1 << (tos & INET_ECN_MASK);
+}
+
 static struct inet_frags ip4_frags;
 
 int ip_frag_nqueues(struct net *net)
@@ -81,7 +93,7 @@ int ip_frag_nqueues(struct net *net)
 
 int ip_frag_mem(struct net *net)
 {
-	return atomic_read(&net->ipv4.frags.mem);
+	return sum_frag_mem_limit(&net->ipv4.frags);
 }
 
 static int ip_frag_reasm(struct ipq *qp, struct sk_buff *prev,
@@ -94,6 +106,7 @@ struct ip4_create_arg {
 
 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) & (INETFRAGS_HASHSZ - 1);
@@ -107,41 +120,36 @@ static unsigned int ip4_hashfn(struct inet_frag_queue *q)
 	return ipqhashfn(ipq->id, ipq->saddr, ipq->daddr, ipq->protocol);
 }
 
-static int ip4_frag_match(struct inet_frag_queue *q, void *a)
+static bool ip4_frag_match(struct inet_frag_queue *q, void *a)
 {
 	struct ipq *qp;
 	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);
-}
-
-/* Memory Tracking Functions. */
-static __inline__ void frag_kfree_skb(struct netns_frags *nf,
-		struct sk_buff *skb, int *work)
-{
-	if (work)
-		*work -= skb->truesize;
-	atomic_sub(skb->truesize, &nf->mem);
-	kfree_skb(skb);
+	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;
 }
 
 static void ip4_frag_init(struct inet_frag_queue *q, void *a)
 {
 	struct ipq *qp = container_of(q, struct ipq, q);
+	struct netns_ipv4 *ipv4 = container_of(q->net, struct netns_ipv4,
+					       frags);
+	struct net *net = container_of(ipv4, struct net, ipv4);
+
 	struct ip4_create_arg *arg = a;
 
 	qp->protocol = arg->iph->protocol;
 	qp->id = arg->iph->id;
+	qp->ecn = ip4_frag_ecn(arg->iph->tos);
 	qp->saddr = arg->iph->saddr;
 	qp->daddr = arg->iph->daddr;
 	qp->user = arg->user;
 	qp->peer = sysctl_ipfrag_max_dist ?
-		inet_getpeer(arg->iph->saddr, 1) : NULL;
+		inet_getpeer_v4(net->ipv4.peers, arg->iph->saddr, 1) : NULL;
 }
 
 static __inline__ void ip4_frag_free(struct inet_frag_queue *q)
@@ -176,7 +184,7 @@ static void ip_evictor(struct net *net)
 {
 	int evicted;
 
-	evicted = inet_frag_evictor(&net->ipv4.frags, &ip4_frags);
+	evicted = inet_frag_evictor(&net->ipv4.frags, &ip4_frags, false);
 	if (evicted)
 		IP_ADD_STATS_BH(net, IPSTATS_MIB_REASMFAILS, evicted);
 }
@@ -204,12 +212,35 @@ static void ip_expire(unsigned long arg)
 
 	if ((qp->q.last_in & INET_FRAG_FIRST_IN) && qp->q.fragments != NULL) {
 		struct sk_buff *head = qp->q.fragments;
+		const struct iphdr *iph;
+		int err;
 
-		/* Send an ICMP "Fragment Reassembly Timeout" message. */
 		rcu_read_lock();
 		head->dev = dev_get_by_index_rcu(net, qp->iif);
-		if (head->dev)
-			icmp_send(head, ICMP_TIME_EXCEEDED, ICMP_EXC_FRAGTIME, 0);
+		if (!head->dev)
+			goto out_rcu_unlock;
+
+		/* 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_rcu_unlock;
+
+		/*
+		 * Only an end host needs to send an ICMP
+		 * "Fragment Reassembly Timeout" message, per RFC792.
+		 */
+		if (qp->user == IP_DEFRAG_AF_PACKET ||
+		    ((qp->user >= IP_DEFRAG_CONNTRACK_IN) &&
+		     (qp->user <= __IP_DEFRAG_CONNTRACK_IN_END) &&
+		     (skb_rtable(head)->rt_type != RTN_LOCAL)))
+			goto out_rcu_unlock;
+
+
+		/* Send an ICMP "Fragment Reassembly Timeout" message. */
+		icmp_send(head, ICMP_TIME_EXCEEDED, ICMP_EXC_FRAGTIME, 0);
+out_rcu_unlock:
 		rcu_read_unlock();
 	}
 out:
@@ -233,14 +264,11 @@ static inline struct ipq *ip_find(struct net *net, struct iphdr *iph, u32 user)
 	hash = ipqhashfn(iph->id, iph->saddr, iph->daddr, iph->protocol);
 
 	q = inet_frag_find(&net->ipv4.frags, &ip4_frags, &arg, hash);
-	if (q == NULL)
-		goto out_nomem;
-
+	if (IS_ERR_OR_NULL(q)) {
+		inet_frag_maybe_warn_overflow(q, pr_fmt());
+		return NULL;
+	}
 	return container_of(q, struct ipq, q);
-
-out_nomem:
-	LIMIT_NETDEBUG(KERN_ERR "ip_frag_create: no memory left !\n");
-	return NULL;
 }
 
 /* Is the fragment too far ahead to be part of ipq? */
@@ -274,6 +302,7 @@ static inline 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)) {
 		atomic_inc(&qp->q.refcnt);
@@ -283,15 +312,20 @@ static int ip_frag_reinit(struct ipq *qp)
 	fp = qp->q.fragments;
 	do {
 		struct sk_buff *xp = fp->next;
-		frag_kfree_skb(qp->q.net, fp, NULL);
+
+		sum_truesize += fp->truesize;
+		kfree_skb(fp);
 		fp = xp;
 	} while (fp);
+	sub_frag_mem_limit(&qp->q, sum_truesize);
 
 	qp->q.last_in = 0;
 	qp->q.len = 0;
 	qp->q.meat = 0;
 	qp->q.fragments = NULL;
+	qp->q.fragments_tail = NULL;
 	qp->iif = 0;
+	qp->ecn = 0;
 
 	return 0;
 }
@@ -304,6 +338,7 @@ static int ip_frag_queue(struct ipq *qp, struct sk_buff *skb)
 	int flags, offset;
 	int ihl, end;
 	int err = -ENOENT;
+	u8 ecn;
 
 	if (qp->q.last_in & INET_FRAG_COMPLETE)
 		goto err;
@@ -315,6 +350,7 @@ static int ip_frag_queue(struct ipq *qp, struct sk_buff *skb)
 		goto err;
 	}
 
+	ecn = ip4_frag_ecn(ip_hdr(skb)->tos);
 	offset = ntohs(ip_hdr(skb)->frag_off);
 	flags = offset & ~IP_OFFSET;
 	offset &= IP_OFFSET;
@@ -328,7 +364,7 @@ static int ip_frag_queue(struct ipq *qp, struct sk_buff *skb)
 	/* Is this the final fragment? */
 	if ((flags & IP_MF) == 0) {
 		/* If we already have some bits beyond end
-		 * or have different end, the segment is corrrupted.
+		 * or have different end, the segment is corrupted.
 		 */
 		if (end < qp->q.len ||
 		    ((qp->q.last_in & INET_FRAG_LAST_IN) && end != qp->q.len))
@@ -363,6 +399,11 @@ static int ip_frag_queue(struct ipq *qp, struct sk_buff *skb)
 	 * 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)
@@ -370,6 +411,7 @@ static int ip_frag_queue(struct ipq *qp, struct sk_buff *skb)
 		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.
@@ -420,7 +462,8 @@ static int ip_frag_queue(struct ipq *qp, struct sk_buff *skb)
 				qp->q.fragments = next;
 
 			qp->q.meat -= free_it->len;
-			frag_kfree_skb(qp->q.net, free_it, NULL);
+			sub_frag_mem_limit(&qp->q, free_it->truesize);
+			kfree_skb(free_it);
 		}
 	}
 
@@ -428,6 +471,8 @@ static int ip_frag_queue(struct ipq *qp, struct sk_buff *skb)
 
 	/* Insert this fragment in the chain of fragments. */
 	skb->next = next;
+	if (!next)
+		qp->q.fragments_tail = skb;
 	if (prev)
 		prev->next = skb;
 	else
@@ -440,17 +485,27 @@ static int ip_frag_queue(struct ipq *qp, struct sk_buff *skb)
 	}
 	qp->q.stamp = skb->tstamp;
 	qp->q.meat += skb->len;
-	atomic_add(skb->truesize, &qp->q.net->mem);
+	qp->ecn |= ecn;
+	add_frag_mem_limit(&qp->q, skb->truesize);
 	if (offset == 0)
 		qp->q.last_in |= INET_FRAG_FIRST_IN;
 
+	if (ip_hdr(skb)->frag_off & htons(IP_DF) &&
+	    skb->len + ihl > qp->q.max_size)
+		qp->q.max_size = skb->len + ihl;
+
 	if (qp->q.last_in == (INET_FRAG_FIRST_IN | INET_FRAG_LAST_IN) &&
-	    qp->q.meat == qp->q.len)
-		return ip_frag_reasm(qp, prev, dev);
+	    qp->q.meat == qp->q.len) {
+		unsigned long orefdst = skb->_skb_refdst;
 
-	write_lock(&ip4_frags.lock);
-	list_move_tail(&qp->q.lru_list, &qp->q.net->lru_list);
-	write_unlock(&ip4_frags.lock);
+		skb->_skb_refdst = 0UL;
+		err = ip_frag_reasm(qp, prev, dev);
+		skb->_skb_refdst = orefdst;
+		return err;
+	}
+
+	skb_dst_drop(skb);
+	inet_frag_lru_move(&qp->q);
 	return -EINPROGRESS;
 
 err:
@@ -470,9 +525,16 @@ static int ip_frag_reasm(struct ipq *qp, struct sk_buff *prev,
 	int len;
 	int ihlen;
 	int err;
+	int sum_truesize;
+	u8 ecn;
 
 	ipq_kill(qp);
 
+	ecn = ip_frag_ecn_table[qp->ecn];
+	if (unlikely(ecn == 0xff)) {
+		err = -EINVAL;
+		goto out_fail;
+	}
 	/* Make the one we just received the head. */
 	if (prev) {
 		head = prev->next;
@@ -481,12 +543,14 @@ static int ip_frag_reasm(struct ipq *qp, struct sk_buff *prev,
 			goto out_nomem;
 
 		fp->next = head->next;
+		if (!fp->next)
+			qp->q.fragments_tail = fp;
 		prev->next = fp;
 
 		skb_morph(head, qp->q.fragments);
 		head->next = qp->q.fragments->next;
 
-		kfree_skb(qp->q.fragments);
+		consume_skb(qp->q.fragments);
 		qp->q.fragments = head;
 	}
 
@@ -502,13 +566,13 @@ static int ip_frag_reasm(struct ipq *qp, struct sk_buff *prev,
 		goto out_oversize;
 
 	/* Head of list must not be cloned. */
-	if (skb_cloned(head) && pskb_expand_head(head, 0, 0, GFP_ATOMIC))
+	if (skb_unclone(head, GFP_ATOMIC))
 		goto out_nomem;
 
 	/* If the first fragment is fragmented itself, we split
 	 * it to two chunks: the first with data and paged part
 	 * and the second, holding only fragments. */
-	if (skb_has_frags(head)) {
+	if (skb_has_frag_list(head)) {
 		struct sk_buff *clone;
 		int i, plen = 0;
 
@@ -518,51 +582,65 @@ static int ip_frag_reasm(struct ipq *qp, struct sk_buff *prev,
 		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_shinfo(head)->frags[i].size;
+		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->len -= clone->len;
 		clone->csum = 0;
 		clone->ip_summed = head->ip_summed;
-		atomic_add(clone->truesize, &qp->q.net->mem);
+		add_frag_mem_limit(&qp->q, clone->truesize);
 	}
 
-	skb_shinfo(head)->frag_list = head->next;
 	skb_push(head, head->data - skb_network_header(head));
-	atomic_sub(head->truesize, &qp->q.net->mem);
 
-	for (fp=head->next; fp; fp = fp->next) {
-		head->data_len += fp->len;
-		head->len += fp->len;
+	sum_truesize = head->truesize;
+	for (fp = head->next; fp;) {
+		bool headstolen;
+		int delta;
+		struct sk_buff *next = fp->next;
+
+		sum_truesize += fp->truesize;
 		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;
-		atomic_sub(fp->truesize, &qp->q.net->mem);
+
+		if (skb_try_coalesce(head, fp, &headstolen, &delta)) {
+			kfree_skb_partial(fp, headstolen);
+		} else {
+			if (!skb_shinfo(head)->frag_list)
+				skb_shinfo(head)->frag_list = fp;
+			head->data_len += fp->len;
+			head->len += fp->len;
+			head->truesize += fp->truesize;
+		}
+		fp = next;
 	}
+	sub_frag_mem_limit(&qp->q, sum_truesize);
 
 	head->next = NULL;
 	head->dev = dev;
 	head->tstamp = qp->q.stamp;
+	IPCB(head)->frag_max_size = qp->q.max_size;
 
 	iph = ip_hdr(head);
-	iph->frag_off = 0;
+	/* max_size != 0 implies at least one fragment had IP_DF set */
+	iph->frag_off = qp->q.max_size ? htons(IP_DF) : 0;
 	iph->tot_len = htons(len);
+	iph->tos |= ecn;
 	IP_INC_STATS_BH(net, IPSTATS_MIB_REASMOKS);
 	qp->q.fragments = NULL;
+	qp->q.fragments_tail = NULL;
 	return 0;
 
 out_nomem:
-	LIMIT_NETDEBUG(KERN_ERR "IP: queue_glue: no memory for gluing "
-			      "queue %p\n", qp);
+	LIMIT_NETDEBUG(KERN_ERR pr_fmt("queue_glue: no memory for gluing queue %p\n"),
+		       qp);
 	err = -ENOMEM;
 	goto out_fail;
 out_oversize:
-	if (net_ratelimit())
-		printk(KERN_INFO "Oversized IP packet from %pI4.\n",
-			&qp->saddr);
+	net_info_ratelimited("Oversized IP packet from %pI4\n", &qp->saddr);
 out_fail:
 	IP_INC_STATS_BH(net, IPSTATS_MIB_REASMFAILS);
 	return err;
@@ -578,8 +656,7 @@ int ip_defrag(struct sk_buff *skb, u32 user)
 	IP_INC_STATS_BH(net, IPSTATS_MIB_REASMREQDS);
 
 	/* Start by cleaning up the memory. */
-	if (atomic_read(&net->ipv4.frags.mem) > net->ipv4.frags.high_thresh)
-		ip_evictor(net);
+	ip_evictor(net);
 
 	/* Lookup (or create) queue header */
 	if ((qp = ip_find(net, ip_hdr(skb), user)) != NULL) {
@@ -598,6 +675,42 @@ int ip_defrag(struct sk_buff *skb, u32 user)
 	kfree_skb(skb);
 	return -ENOMEM;
 }
+EXPORT_SYMBOL(ip_defrag);
+
+struct sk_buff *ip_check_defrag(struct sk_buff *skb, u32 user)
+{
+	struct iphdr iph;
+	u32 len;
+
+	if (skb->protocol != htons(ETH_P_IP))
+		return skb;
+
+	if (!skb_copy_bits(skb, 0, &iph, sizeof(iph)))
+		return skb;
+
+	if (iph.ihl < 5 || iph.version != 4)
+		return skb;
+
+	len = ntohs(iph.tot_len);
+	if (skb->len < len || len < (iph.ihl * 4))
+		return skb;
+
+	if (ip_is_fragment(&iph)) {
+		skb = skb_share_check(skb, GFP_ATOMIC);
+		if (skb) {
+			if (!pskb_may_pull(skb, iph.ihl*4))
+				return skb;
+			if (pskb_trim_rcsum(skb, len))
+				return skb;
+			memset(IPCB(skb), 0, sizeof(struct inet_skb_parm));
+			if (ip_defrag(skb, user))
+				return NULL;
+			skb_clear_hash(skb);
+		}
+	}
+	return skb;
+}
+EXPORT_SYMBOL(ip_check_defrag);
 
 #ifdef CONFIG_SYSCTL
 static int zero;
@@ -646,7 +759,7 @@ static struct ctl_table ip4_frags_ctl_table[] = {
 	{ }
 };
 
-static int ip4_frags_ns_ctl_register(struct net *net)
+static int __net_init ip4_frags_ns_ctl_register(struct net *net)
 {
 	struct ctl_table *table;
 	struct ctl_table_header *hdr;
@@ -660,9 +773,13 @@ static int ip4_frags_ns_ctl_register(struct net *net)
 		table[0].data = &net->ipv4.frags.high_thresh;
 		table[1].data = &net->ipv4.frags.low_thresh;
 		table[2].data = &net->ipv4.frags.timeout;
+
+		/* Don't export sysctls to unprivileged users */
+		if (net->user_ns != &init_user_ns)
+			table[0].procname = NULL;
 	}
 
-	hdr = register_net_sysctl_table(net, net_ipv4_ctl_path, table);
+	hdr = register_net_sysctl(net, "net/ipv4", table);
 	if (hdr == NULL)
 		goto err_reg;
 
@@ -676,7 +793,7 @@ err_alloc:
 	return -ENOMEM;
 }
 
-static void ip4_frags_ns_ctl_unregister(struct net *net)
+static void __net_exit ip4_frags_ns_ctl_unregister(struct net *net)
 {
 	struct ctl_table *table;
 
@@ -687,7 +804,7 @@ static void ip4_frags_ns_ctl_unregister(struct net *net)
 
 static void ip4_frags_ctl_register(void)
 {
-	register_net_sysctl_rotable(net_ipv4_ctl_path, ip4_frags_ctl_table);
+	register_net_sysctl(&init_net, "net/ipv4", ip4_frags_ctl_table);
 }
 #else
 static inline int ip4_frags_ns_ctl_register(struct net *net)
@@ -704,16 +821,24 @@ static inline void ip4_frags_ctl_register(void)
 }
 #endif
 
-static int ipv4_frags_init_net(struct net *net)
+static int __net_init ipv4_frags_init_net(struct net *net)
 {
-	/*
-	 * Fragment cache limits. We will commit 256K at one time. Should we
-	 * cross that limit we will prune down to 192K. This should cope with
-	 * even the most extreme cases without allowing an attacker to
-	 * measurably harm machine performance.
+	/* Fragment cache limits.
+	 *
+	 * The fragment memory accounting code, (tries to) account for
+	 * the real memory usage, by measuring both the size of frag
+	 * queue struct (inet_frag_queue (ipv4:ipq/ipv6:frag_queue))
+	 * and the SKB's truesize.
+	 *
+	 * A 64K fragment consumes 129736 bytes (44*2944)+200
+	 * (1500 truesize == 2944, sizeof(struct ipq) == 200)
+	 *
+	 * We will commit 4MB at one time. Should we cross that limit
+	 * we will prune down to 3MB, making room for approx 8 big 64K
+	 * fragments 8x128k.
 	 */
-	net->ipv4.frags.high_thresh = 256 * 1024;
-	net->ipv4.frags.low_thresh = 192 * 1024;
+	net->ipv4.frags.high_thresh = 4 * 1024 * 1024;
+	net->ipv4.frags.low_thresh  = 3 * 1024 * 1024;
 	/*
 	 * Important NOTE! Fragment queue must be destroyed before MSL expires.
 	 * RFC791 is wrong proposing to prolongate timer each fragment arrival
@@ -726,7 +851,7 @@ static int ipv4_frags_init_net(struct net *net)
 	return ip4_frags_ns_ctl_register(net);
 }
 
-static void ipv4_frags_exit_net(struct net *net)
+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);
@@ -751,5 +876,3 @@ void __init ipfrag_init(void)
 	ip4_frags.secret_interval = 10 * 60 * HZ;
 	inet_frags_init(&ip4_frags);
 }
-
-EXPORT_SYMBOL(ip_defrag);