1 files changed, 86 insertions, 68 deletions

diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c
index 24264d0a4b85..25ec8001898d 100644
--- a/net/ipv6/reassembly.c
+++ b/net/ipv6/reassembly.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  *	IPv6 fragment reassembly
  *	Linux INET6 implementation
@@ -6,11 +7,6 @@
  *	Pedro Roque		<roque@di.fc.ul.pt>
  *
  *	Based on: net/ipv4/ip_fragment.c
- *
- *	This program is free software; you can redistribute it and/or
- *      modify it under the terms of the GNU General Public License
- *      as published by the Free Software Foundation; either version
- *      2 of the License, or (at your option) any later version.
  */
 
 /*
@@ -46,6 +42,8 @@
 #include <linux/skbuff.h>
 #include <linux/slab.h>
 #include <linux/export.h>
+#include <linux/tcp.h>
+#include <linux/udp.h>
 
 #include <net/sock.h>
 #include <net/snmp.h>
@@ -70,18 +68,17 @@ static u8 ip6_frag_ecn(const struct ipv6hdr *ipv6h)
 static struct inet_frags ip6_frags;
 
 static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *skb,
-			  struct sk_buff *prev_tail, struct net_device *dev);
+			  struct sk_buff *prev_tail, struct net_device *dev,
+			  int *refs);
 
 static void ip6_frag_expire(struct timer_list *t)
 {
-	struct inet_frag_queue *frag = from_timer(frag, t, timer);
+	struct inet_frag_queue *frag = timer_container_of(frag, t, timer);
 	struct frag_queue *fq;
-	struct net *net;
 
 	fq = container_of(frag, struct frag_queue, q);
-	net = container_of(fq->q.net, struct net, ipv6.frags);
 
-	ip6frag_expire_frag_queue(net, fq);
+	ip6frag_expire_frag_queue(fq->q.fqdir->net, fq);
 }
 
 static struct frag_queue *
@@ -100,26 +97,30 @@ fq_find(struct net *net, __be32 id, const struct ipv6hdr *hdr, int iif)
 					    IPV6_ADDR_LINKLOCAL)))
 		key.iif = 0;
 
-	q = inet_frag_find(&net->ipv6.frags, &key);
+	q = inet_frag_find(net->ipv6.fqdir, &key);
 	if (!q)
 		return NULL;
 
 	return container_of(q, struct frag_queue, q);
 }
 
-static int ip6_frag_queue(struct frag_queue *fq, struct sk_buff *skb,
+static int ip6_frag_queue(struct net *net,
+			  struct frag_queue *fq, struct sk_buff *skb,
 			  struct frag_hdr *fhdr, int nhoff,
-			  u32 *prob_offset)
+			  u32 *prob_offset, int *refs)
 {
-	struct net *net = dev_net(skb_dst(skb)->dev);
 	int offset, end, fragsize;
 	struct sk_buff *prev_tail;
 	struct net_device *dev;
 	int err = -ENOENT;
+	SKB_DR(reason);
 	u8 ecn;
 
-	if (fq->q.flags & INET_FRAG_COMPLETE)
+	/* If reassembly is already done, @skb must be a duplicate frag. */
+	if (fq->q.flags & INET_FRAG_COMPLETE) {
+		SKB_DR_SET(reason, DUP_FRAG);
 		goto err;
+	}
 
 	err = -EINVAL;
 	offset = ntohs(fhdr->frag_off) & ~0x7;
@@ -198,9 +199,10 @@ static int ip6_frag_queue(struct frag_queue *fq, struct sk_buff *skb,
 		fq->iif = dev->ifindex;
 
 	fq->q.stamp = skb->tstamp;
+	fq->q.tstamp_type = skb->tstamp_type;
 	fq->q.meat += skb->len;
 	fq->ecn |= ecn;
-	add_frag_mem_limit(fq->q.net, skb->truesize);
+	add_frag_mem_limit(fq->q.fqdir, skb->truesize);
 
 	fragsize = -skb_network_offset(skb) + skb->len;
 	if (fragsize > fq->q.max_size)
@@ -219,7 +221,7 @@ static int ip6_frag_queue(struct frag_queue *fq, struct sk_buff *skb,
 		unsigned long orefdst = skb->_skb_refdst;
 
 		skb->_skb_refdst = 0UL;
-		err = ip6_frag_reasm(fq, skb, prev_tail, dev);
+		err = ip6_frag_reasm(fq, skb, prev_tail, dev, refs);
 		skb->_skb_refdst = orefdst;
 		return err;
 	}
@@ -229,18 +231,19 @@ static int ip6_frag_queue(struct frag_queue *fq, struct sk_buff *skb,
 
 insert_error:
 	if (err == IPFRAG_DUP) {
-		kfree_skb(skb);
-		return -EINVAL;
+		SKB_DR_SET(reason, DUP_FRAG);
+		err = -EINVAL;
+		goto err;
 	}
 	err = -EINVAL;
 	__IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)),
 			IPSTATS_MIB_REASM_OVERLAPS);
 discard_fq:
-	inet_frag_kill(&fq->q);
+	inet_frag_kill(&fq->q, refs);
 	__IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)),
 			IPSTATS_MIB_REASMFAILS);
 err:
-	kfree_skb(skb);
+	kfree_skb_reason(skb, reason);
 	return err;
 }
 
@@ -252,15 +255,16 @@ err:
  *	the last and the first frames arrived and all the bits are here.
  */
 static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *skb,
-			  struct sk_buff *prev_tail, struct net_device *dev)
+			  struct sk_buff *prev_tail, struct net_device *dev,
+			  int *refs)
 {
-	struct net *net = container_of(fq->q.net, struct net, ipv6.frags);
+	struct net *net = fq->q.fqdir->net;
 	unsigned int nhoff;
 	void *reasm_data;
 	int payload_len;
 	u8 ecn;
 
-	inet_frag_kill(&fq->q);
+	inet_frag_kill(&fq->q, refs);
 
 	ecn = ip_frag_ecn_table[fq->ecn];
 	if (unlikely(ecn == 0xff))
@@ -270,9 +274,9 @@ static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *skb,
 	if (!reasm_data)
 		goto out_oom;
 
-	payload_len = ((skb->data - skb_network_header(skb)) -
+	payload_len = -skb_network_offset(skb) -
 		       sizeof(struct ipv6hdr) + fq->q.len -
-		       sizeof(struct frag_hdr));
+		       sizeof(struct frag_hdr);
 	if (payload_len > IPV6_MAXPLEN)
 		goto out_oversize;
 
@@ -288,7 +292,7 @@ static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *skb,
 
 	skb_reset_transport_header(skb);
 
-	inet_frag_reasm_finish(&fq->q, skb, reasm_data);
+	inet_frag_reasm_finish(&fq->q, skb, reasm_data, true);
 
 	skb->dev = dev;
 	ipv6_hdr(skb)->payload_len = htons(payload_len);
@@ -301,10 +305,7 @@ static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *skb,
 	skb_postpush_rcsum(skb, skb_network_header(skb),
 			   skb_network_header_len(skb));
 
-	rcu_read_lock();
-	__IP6_INC_STATS(net, __in6_dev_get(dev), IPSTATS_MIB_REASMOKS);
-	rcu_read_unlock();
-	fq->q.fragments = NULL;
+	__IP6_INC_STATS(net, __in6_dev_stats_get(dev, skb), IPSTATS_MIB_REASMOKS);
 	fq->q.rb_fragments = RB_ROOT;
 	fq->q.fragments_tail = NULL;
 	fq->q.last_run_head = NULL;
@@ -316,19 +317,18 @@ out_oversize:
 out_oom:
 	net_dbg_ratelimited("ip6_frag_reasm: no memory for reassembly\n");
 out_fail:
-	rcu_read_lock();
-	__IP6_INC_STATS(net, __in6_dev_get(dev), IPSTATS_MIB_REASMFAILS);
-	rcu_read_unlock();
-	inet_frag_kill(&fq->q);
+	__IP6_INC_STATS(net, __in6_dev_stats_get(dev, skb), IPSTATS_MIB_REASMFAILS);
+	inet_frag_kill(&fq->q, refs);
 	return -1;
 }
 
 static int ipv6_frag_rcv(struct sk_buff *skb)
 {
+	const struct ipv6hdr *hdr = ipv6_hdr(skb);
+	struct net *net = skb_dst_dev_net(skb);
 	struct frag_hdr *fhdr;
 	struct frag_queue *fq;
-	const struct ipv6hdr *hdr = ipv6_hdr(skb);
-	struct net *net = dev_net(skb_dst(skb)->dev);
+	u8 nexthdr;
 	int iif;
 
 	if (IP6CB(skb)->flags & IP6SKB_FRAGMENTED)
@@ -347,7 +347,7 @@ static int ipv6_frag_rcv(struct sk_buff *skb)
 	hdr = ipv6_hdr(skb);
 	fhdr = (struct frag_hdr *)skb_transport_header(skb);
 
-	if (!(fhdr->frag_off & htons(0xFFF9))) {
+	if (!(fhdr->frag_off & htons(IP6_OFFSET | IP6_MF))) {
 		/* It is not a fragmented frame */
 		skb->transport_header += sizeof(struct frag_hdr);
 		__IP6_INC_STATS(net,
@@ -355,23 +355,41 @@ static int ipv6_frag_rcv(struct sk_buff *skb)
 
 		IP6CB(skb)->nhoff = (u8 *)fhdr - skb_network_header(skb);
 		IP6CB(skb)->flags |= IP6SKB_FRAGMENTED;
+		IP6CB(skb)->frag_max_size = ntohs(hdr->payload_len) +
+					    sizeof(struct ipv6hdr);
 		return 1;
 	}
 
+	/* RFC 8200, Section 4.5 Fragment Header:
+	 * If the first fragment does not include all headers through an
+	 * Upper-Layer header, then that fragment should be discarded and
+	 * an ICMP Parameter Problem, Code 3, message should be sent to
+	 * the source of the fragment, with the Pointer field set to zero.
+	 */
+	nexthdr = hdr->nexthdr;
+	if (ipv6frag_thdr_truncated(skb, skb_network_offset(skb) + sizeof(struct ipv6hdr), &nexthdr)) {
+		__IP6_INC_STATS(net, __in6_dev_get_safely(skb->dev),
+				IPSTATS_MIB_INHDRERRORS);
+		icmpv6_param_prob(skb, ICMPV6_HDR_INCOMP, 0);
+		return -1;
+	}
+
 	iif = skb->dev ? skb->dev->ifindex : 0;
+	rcu_read_lock();
 	fq = fq_find(net, fhdr->identification, hdr, iif);
 	if (fq) {
 		u32 prob_offset = 0;
-		int ret;
+		int ret, refs = 0;
 
 		spin_lock(&fq->q.lock);
 
 		fq->iif = iif;
-		ret = ip6_frag_queue(fq, skb, fhdr, IP6CB(skb)->nhoff,
-				     &prob_offset);
+		ret = ip6_frag_queue(net, fq, skb, fhdr, IP6CB(skb)->nhoff,
+				     &prob_offset, &refs);
 
 		spin_unlock(&fq->q.lock);
-		inet_frag_put(&fq->q);
+		rcu_read_unlock();
+		inet_frag_putn(&fq->q, refs);
 		if (prob_offset) {
 			__IP6_INC_STATS(net, __in6_dev_get_safely(skb->dev),
 					IPSTATS_MIB_INHDRERRORS);
@@ -380,6 +398,7 @@ static int ipv6_frag_rcv(struct sk_buff *skb)
 		}
 		return ret;
 	}
+	rcu_read_unlock();
 
 	__IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_REASMFAILS);
 	kfree_skb(skb);
@@ -402,28 +421,22 @@ static const struct inet6_protocol frag_protocol = {
 static struct ctl_table ip6_frags_ns_ctl_table[] = {
 	{
 		.procname	= "ip6frag_high_thresh",
-		.data		= &init_net.ipv6.frags.high_thresh,
 		.maxlen		= sizeof(unsigned long),
 		.mode		= 0644,
 		.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(unsigned long),
 		.mode		= 0644,
 		.proc_handler	= proc_doulongvec_minmax,
-		.extra2		= &init_net.ipv6.frags.high_thresh
 	},
 	{
 		.procname	= "ip6frag_time",
-		.data		= &init_net.ipv6.frags.timeout,
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec_jiffies,
 	},
-	{ }
 };
 
 /* secret interval has been deprecated */
@@ -436,7 +449,6 @@ static struct ctl_table ip6_frags_ctl_table[] = {
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec_jiffies,
 	},
-	{ }
 };
 
 static int __net_init ip6_frags_ns_sysctl_register(struct net *net)
@@ -450,14 +462,15 @@ static int __net_init ip6_frags_ns_sysctl_register(struct net *net)
 		if (!table)
 			goto err_alloc;
 
-		table[0].data = &net->ipv6.frags.high_thresh;
-		table[0].extra1 = &net->ipv6.frags.low_thresh;
-		table[1].data = &net->ipv6.frags.low_thresh;
-		table[1].extra2 = &net->ipv6.frags.high_thresh;
-		table[2].data = &net->ipv6.frags.timeout;
 	}
-
-	hdr = register_net_sysctl(net, "net/ipv6", table);
+	table[0].data	= &net->ipv6.fqdir->high_thresh;
+	table[0].extra1	= &net->ipv6.fqdir->low_thresh;
+	table[1].data	= &net->ipv6.fqdir->low_thresh;
+	table[1].extra2	= &net->ipv6.fqdir->high_thresh;
+	table[2].data	= &net->ipv6.fqdir->timeout;
+
+	hdr = register_net_sysctl_sz(net, "net/ipv6", table,
+				     ARRAY_SIZE(ip6_frags_ns_ctl_table));
 	if (!hdr)
 		goto err_reg;
 
@@ -473,7 +486,7 @@ err_alloc:
 
 static void __net_exit ip6_frags_ns_sysctl_unregister(struct net *net)
 {
-	struct ctl_table *table;
+	const struct ctl_table *table;
 
 	table = net->ipv6.sysctl.frags_hdr->ctl_table_arg;
 	unregister_net_sysctl_table(net->ipv6.sysctl.frags_hdr);
@@ -518,30 +531,35 @@ 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;
-
-	res = inet_frags_init_net(&net->ipv6.frags);
+	res = fqdir_init(&net->ipv6.fqdir, &ip6_frags, net);
 	if (res < 0)
 		return res;
 
+	net->ipv6.fqdir->high_thresh = IPV6_FRAG_HIGH_THRESH;
+	net->ipv6.fqdir->low_thresh = IPV6_FRAG_LOW_THRESH;
+	net->ipv6.fqdir->timeout = IPV6_FRAG_TIMEOUT;
+
 	res = ip6_frags_ns_sysctl_register(net);
 	if (res < 0)
-		inet_frags_exit_net(&net->ipv6.frags);
+		fqdir_exit(net->ipv6.fqdir);
 	return res;
 }
 
+static void __net_exit ipv6_frags_pre_exit_net(struct net *net)
+{
+	fqdir_pre_exit(net->ipv6.fqdir);
+}
+
 static void __net_exit ipv6_frags_exit_net(struct net *net)
 {
 	ip6_frags_ns_sysctl_unregister(net);
-	inet_frags_exit_net(&net->ipv6.frags);
+	fqdir_exit(net->ipv6.fqdir);
 }
 
 static struct pernet_operations ip6_frags_ops = {
-	.init = ipv6_frags_init_net,
-	.exit = ipv6_frags_exit_net,
+	.init		= ipv6_frags_init_net,
+	.pre_exit	= ipv6_frags_pre_exit_net,
+	.exit		= ipv6_frags_exit_net,
 };
 
 static const struct rhashtable_params ip6_rhash_params = {
@@ -592,8 +610,8 @@ err_protocol:
 
 void ipv6_frag_exit(void)
 {
-	inet_frags_fini(&ip6_frags);
 	ip6_frags_sysctl_unregister();
 	unregister_pernet_subsys(&ip6_frags_ops);
 	inet6_del_protocol(&frag_protocol, IPPROTO_FRAGMENT);
+	inet_frags_fini(&ip6_frags);
 }