1 files changed, 241 insertions, 386 deletions

diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c
index 790d9f4b8b0b..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>
@@ -57,174 +55,83 @@
 #include <net/rawv6.h>
 #include <net/ndisc.h>
 #include <net/addrconf.h>
-#include <net/inet_frag.h>
+#include <net/ipv6_frag.h>
 #include <net/inet_ecn.h>
 
-struct ip6frag_skb_cb
-{
-	struct inet6_skb_parm	h;
-	int			offset;
-};
-
-#define FRAG6_CB(skb)	((struct ip6frag_skb_cb*)((skb)->cb))
+static const char ip6_frag_cache_name[] = "ip6-frags";
 
-static inline u8 ip6_frag_ecn(const struct ipv6hdr *ipv6h)
+static u8 ip6_frag_ecn(const struct ipv6hdr *ipv6h)
 {
 	return 1 << (ipv6_get_dsfield(ipv6h) & INET_ECN_MASK);
 }
 
 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.
- */
-unsigned int inet6_hash_frag(__be32 id, const struct in6_addr *saddr,
-			     const struct in6_addr *daddr, u32 rnd)
-{
-	u32 c;
-
-	c = jhash_3words(ipv6_addr_hash(saddr), ipv6_addr_hash(daddr),
-			 (__force u32)id, rnd);
-
-	return c & (INETFRAGS_HASHSZ - 1);
-}
-EXPORT_SYMBOL_GPL(inet6_hash_frag);
-
-static unsigned int ip6_hashfn(struct inet_frag_queue *q)
-{
-	struct frag_queue *fq;
-
-	fq = container_of(q, struct frag_queue, q);
-	return inet6_hash_frag(fq->id, &fq->saddr, &fq->daddr, ip6_frags.rnd);
-}
+static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *skb,
+			  struct sk_buff *prev_tail, struct net_device *dev,
+			  int *refs);
 
-bool ip6_frag_match(struct inet_frag_queue *q, void *a)
+static void ip6_frag_expire(struct timer_list *t)
 {
+	struct inet_frag_queue *frag = timer_container_of(frag, t, timer);
 	struct frag_queue *fq;
-	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);
-}
-EXPORT_SYMBOL(ip6_frag_match);
+	fq = container_of(frag, struct frag_queue, q);
 
-void ip6_frag_init(struct inet_frag_queue *q, void *a)
-{
-	struct frag_queue *fq = container_of(q, struct frag_queue, q);
-	struct ip6_create_arg *arg = a;
-
-	fq->id = arg->id;
-	fq->user = arg->user;
-	fq->saddr = *arg->src;
-	fq->daddr = *arg->dst;
-	fq->ecn = arg->ecn;
+	ip6frag_expire_frag_queue(fq->q.fqdir->net, fq);
 }
-EXPORT_SYMBOL(ip6_frag_init);
 
-void ip6_expire_frag_queue(struct net *net, struct frag_queue *fq,
-			   struct inet_frags *frags)
-{
-	struct net_device *dev = NULL;
-
-	spin_lock(&fq->q.lock);
-
-	if (fq->q.last_in & INET_FRAG_COMPLETE)
-		goto out;
-
-	inet_frag_kill(&fq->q, frags);
-
-	rcu_read_lock();
-	dev = dev_get_by_index_rcu(net, fq->iif);
-	if (!dev)
-		goto out_rcu_unlock;
-
-	IP6_INC_STATS_BH(net, __in6_dev_get(dev), IPSTATS_MIB_REASMTIMEOUT);
-	IP6_INC_STATS_BH(net, __in6_dev_get(dev), IPSTATS_MIB_REASMFAILS);
-
-	/* Don't send error if the first segment did not arrive. */
-	if (!(fq->q.last_in & INET_FRAG_FIRST_IN) || !fq->q.fragments)
-		goto out_rcu_unlock;
-
-	/*
-	   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();
-out:
-	spin_unlock(&fq->q.lock);
-	inet_frag_put(&fq->q, frags);
-}
-EXPORT_SYMBOL(ip6_expire_frag_queue);
-
-static void ip6_frag_expire(unsigned long data)
-{
-	struct frag_queue *fq;
-	struct net *net;
-
-	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);
-}
-
-static __inline__ struct frag_queue *
-fq_find(struct net *net, __be32 id, const struct in6_addr *src,
-	const struct in6_addr *dst, u8 ecn)
+static struct frag_queue *
+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.ecn = ecn;
 
-	read_lock(&ip6_frags.lock);
-	hash = inet6_hash_frag(id, src, dst, ip6_frags.rnd);
+	if (!(ipv6_addr_type(&hdr->daddr) & (IPV6_ADDR_MULTICAST |
+					    IPV6_ADDR_LINKLOCAL)))
+		key.iif = 0;
 
-	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.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,
-			   struct frag_hdr *fhdr, int nhoff)
+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, int *refs)
 {
-	struct sk_buff *prev, *next;
+	int offset, end, fragsize;
+	struct sk_buff *prev_tail;
 	struct net_device *dev;
-	int offset, end;
-	struct net *net = dev_net(skb_dst(skb)->dev);
+	int err = -ENOENT;
+	SKB_DR(reason);
 	u8 ecn;
 
-	if (fq->q.last_in & 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;
 	end = offset + (ntohs(ipv6_hdr(skb)->payload_len) -
 			((u8 *)(fhdr + 1) - (u8 *)(ipv6_hdr(skb) + 1)));
 
 	if ((unsigned int)end > IPV6_MAXPLEN) {
-		IP6_INC_STATS_BH(net, ip6_dst_idev(skb_dst(skb)),
-				 IPSTATS_MIB_INHDRERRORS);
-		icmpv6_param_prob(skb, ICMPV6_HDR_FIELD,
-				  ((u8 *)&fhdr->frag_off -
-				   skb_network_header(skb)));
+		*prob_offset = (u8 *)&fhdr->frag_off - skb_network_header(skb);
+		/* note that if prob_offset is set, the skb is freed elsewhere,
+		 * we do not free it here.
+		 */
 		return -1;
 	}
 
@@ -243,9 +150,9 @@ static int ip6_frag_queue(struct frag_queue *fq, struct sk_buff *skb,
 		 * or have different end, the segment is corrupted.
 		 */
 		if (end < fq->q.len ||
-		    ((fq->q.last_in & INET_FRAG_LAST_IN) && end != fq->q.len))
-			goto err;
-		fq->q.last_in |= INET_FRAG_LAST_IN;
+		    ((fq->q.flags & INET_FRAG_LAST_IN) && end != fq->q.len))
+			goto discard_fq;
+		fq->q.flags |= INET_FRAG_LAST_IN;
 		fq->q.len = end;
 	} else {
 		/* Check if the fragment is rounded to 8 bytes.
@@ -255,253 +162,153 @@ static int ip6_frag_queue(struct frag_queue *fq, struct sk_buff *skb,
 			/* RFC2460 says always send parameter problem in
 			 * this case. -DaveM
 			 */
-			IP6_INC_STATS_BH(net, ip6_dst_idev(skb_dst(skb)),
-					 IPSTATS_MIB_INHDRERRORS);
-			icmpv6_param_prob(skb, ICMPV6_HDR_FIELD,
-					  offsetof(struct ipv6hdr, payload_len));
+			*prob_offset = offsetof(struct ipv6hdr, payload_len);
 			return -1;
 		}
 		if (end > fq->q.len) {
 			/* Some bits beyond end -> corruption. */
-			if (fq->q.last_in & INET_FRAG_LAST_IN)
-				goto err;
+			if (fq->q.flags & INET_FRAG_LAST_IN)
+				goto discard_fq;
 			fq->q.len = end;
 		}
 	}
 
 	if (end == offset)
-		goto err;
+		goto discard_fq;
 
+	err = -ENOMEM;
 	/* Point into the IP datagram 'data' part. */
 	if (!pskb_pull(skb, (u8 *) (fhdr + 1) - skb->data))
-		goto err;
-
-	if (pskb_trim_rcsum(skb, end - offset))
-		goto err;
-
-	/* Find out which fragments are in front and at the back of us
-	 * in the chain of fragments so far.  We must know where to put
-	 * this fragment, right?
-	 */
-	prev = fq->q.fragments_tail;
-	if (!prev || FRAG6_CB(prev)->offset < offset) {
-		next = NULL;
-		goto found;
-	}
-	prev = NULL;
-	for(next = fq->q.fragments; next != NULL; next = next->next) {
-		if (FRAG6_CB(next)->offset >= offset)
-			break;	/* bingo! */
-		prev = next;
-	}
-
-found:
-	/* RFC5722, Section 4, amended by Errata ID : 3089
-	 *                          When reassembling an IPv6 datagram, if
-	 *   one or more its constituent fragments is determined to be an
-	 *   overlapping fragment, the entire datagram (and any constituent
-	 *   fragments) MUST be silently discarded.
-	 */
-
-	/* Check for overlap with preceding fragment. */
-	if (prev &&
-	    (FRAG6_CB(prev)->offset + prev->len) > offset)
 		goto discard_fq;
 
-	/* Look for overlap with succeeding segment. */
-	if (next && FRAG6_CB(next)->offset < end)
+	err = pskb_trim_rcsum(skb, end - offset);
+	if (err)
 		goto discard_fq;
 
-	FRAG6_CB(skb)->offset = offset;
+	/* Note : skb->rbnode and skb->dev share the same location. */
+	dev = skb->dev;
+	/* Makes sure compiler wont do silly aliasing games */
+	barrier();
 
-	/* Insert this fragment in the chain of fragments. */
-	skb->next = next;
-	if (!next)
-		fq->q.fragments_tail = skb;
-	if (prev)
-		prev->next = skb;
-	else
-		fq->q.fragments = skb;
+	prev_tail = fq->q.fragments_tail;
+	err = inet_frag_queue_insert(&fq->q, skb, offset, end);
+	if (err)
+		goto insert_error;
 
-	dev = skb->dev;
-	if (dev) {
+	if (dev)
 		fq->iif = dev->ifindex;
-		skb->dev = NULL;
-	}
+
 	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, skb->truesize);
+	add_frag_mem_limit(fq->q.fqdir, skb->truesize);
+
+	fragsize = -skb_network_offset(skb) + skb->len;
+	if (fragsize > fq->q.max_size)
+		fq->q.max_size = fragsize;
 
 	/* The first fragment.
 	 * nhoffset is obtained from the first fragment, of course.
 	 */
 	if (offset == 0) {
 		fq->nhoffset = nhoff;
-		fq->q.last_in |= INET_FRAG_FIRST_IN;
+		fq->q.flags |= INET_FRAG_FIRST_IN;
 	}
 
-	if (fq->q.last_in == (INET_FRAG_FIRST_IN | INET_FRAG_LAST_IN) &&
+	if (fq->q.flags == (INET_FRAG_FIRST_IN | INET_FRAG_LAST_IN) &&
 	    fq->q.meat == fq->q.len) {
-		int res;
 		unsigned long orefdst = skb->_skb_refdst;
 
 		skb->_skb_refdst = 0UL;
-		res = ip6_frag_reasm(fq, prev, dev);
+		err = ip6_frag_reasm(fq, skb, prev_tail, dev, refs);
 		skb->_skb_refdst = orefdst;
-		return res;
+		return err;
 	}
 
 	skb_dst_drop(skb);
-	inet_frag_lru_move(&fq->q);
-	return -1;
+	return -EINPROGRESS;
 
+insert_error:
+	if (err == IPFRAG_DUP) {
+		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, &ip6_frags);
+	inet_frag_kill(&fq->q, refs);
+	__IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)),
+			IPSTATS_MIB_REASMFAILS);
 err:
-	IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)),
-		      IPSTATS_MIB_REASMFAILS);
-	kfree_skb(skb);
-	return -1;
+	kfree_skb_reason(skb, reason);
+	return err;
 }
 
 /*
  *	Check if this packet is complete.
- *	Returns NULL on failure by any reason, and pointer
- *	to current nexthdr field in reassembled frame.
  *
  *	It is called with locked fq, and caller must check that
  *	queue is eligible for reassembly i.e. it is not COMPLETE,
  *	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 *prev,
-			  struct net_device *dev)
+static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *skb,
+			  struct sk_buff *prev_tail, struct net_device *dev,
+			  int *refs)
 {
-	struct net *net = container_of(fq->q.net, struct net, ipv6.frags);
-	struct sk_buff *fp, *head = fq->q.fragments;
-	int    payload_len;
+	struct net *net = fq->q.fqdir->net;
 	unsigned int nhoff;
-	int sum_truesize;
+	void *reasm_data;
+	int payload_len;
 	u8 ecn;
 
-	inet_frag_kill(&fq->q, &ip6_frags);
+	inet_frag_kill(&fq->q, refs);
 
 	ecn = ip_frag_ecn_table[fq->ecn];
 	if (unlikely(ecn == 0xff))
 		goto out_fail;
 
-	/* Make the one we just received the head. */
-	if (prev) {
-		head = prev->next;
-		fp = skb_clone(head, GFP_ATOMIC);
-
-		if (!fp)
-			goto out_oom;
-
-		fp->next = head->next;
-		if (!fp->next)
-			fq->q.fragments_tail = fp;
-		prev->next = fp;
-
-		skb_morph(head, fq->q.fragments);
-		head->next = fq->q.fragments->next;
-
-		consume_skb(fq->q.fragments);
-		fq->q.fragments = head;
-	}
-
-	WARN_ON(head == NULL);
-	WARN_ON(FRAG6_CB(head)->offset != 0);
+	reasm_data = inet_frag_reasm_prepare(&fq->q, skb, prev_tail);
+	if (!reasm_data)
+		goto out_oom;
 
-	/* Unfragmented part is taken from the first segment. */
-	payload_len = ((head->data - skb_network_header(head)) -
+	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;
 
-	/* Head of list must not be cloned. */
-	if (skb_unclone(head, GFP_ATOMIC))
-		goto out_oom;
-
-	/* 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_frag_list(head)) {
-		struct sk_buff *clone;
-		int i, plen = 0;
-
-		if ((clone = alloc_skb(0, GFP_ATOMIC)) == NULL)
-			goto out_oom;
-		clone->next = head->next;
-		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_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;
-		add_frag_mem_limit(&fq->q, clone->truesize);
-	}
-
 	/* We have to remove fragment header from datagram and to relocate
 	 * header in order to calculate ICV correctly. */
 	nhoff = fq->nhoffset;
-	skb_network_header(head)[nhoff] = skb_transport_header(head)[0];
-	memmove(head->head + sizeof(struct frag_hdr), head->head,
-		(head->data - head->head) - sizeof(struct frag_hdr));
-	head->mac_header += sizeof(struct frag_hdr);
-	head->network_header += sizeof(struct frag_hdr);
-
-	skb_reset_transport_header(head);
-	skb_push(head, head->data - skb_network_header(head));
-
-	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);
-
-		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(&fq->q, sum_truesize);
+	skb_network_header(skb)[nhoff] = skb_transport_header(skb)[0];
+	memmove(skb->head + sizeof(struct frag_hdr), skb->head,
+		(skb->data - skb->head) - sizeof(struct frag_hdr));
+	if (skb_mac_header_was_set(skb))
+		skb->mac_header += sizeof(struct frag_hdr);
+	skb->network_header += sizeof(struct frag_hdr);
+
+	skb_reset_transport_header(skb);
 
-	head->next = NULL;
-	head->dev = dev;
-	head->tstamp = fq->q.stamp;
-	ipv6_hdr(head)->payload_len = htons(payload_len);
-	ipv6_change_dsfield(ipv6_hdr(head), 0xff, ecn);
-	IP6CB(head)->nhoff = nhoff;
+	inet_frag_reasm_finish(&fq->q, skb, reasm_data, true);
+
+	skb->dev = dev;
+	ipv6_hdr(skb)->payload_len = htons(payload_len);
+	ipv6_change_dsfield(ipv6_hdr(skb), 0xff, ecn);
+	IP6CB(skb)->nhoff = nhoff;
+	IP6CB(skb)->flags |= IP6SKB_FRAGMENTED;
+	IP6CB(skb)->frag_max_size = fq->q.max_size;
 
 	/* Yes, and fold redundant checksum back. 8) */
-	if (head->ip_summed == CHECKSUM_COMPLETE)
-		head->csum = csum_partial(skb_network_header(head),
-					  skb_network_header_len(head),
-					  head->csum);
+	skb_postpush_rcsum(skb, skb_network_header(skb),
+			   skb_network_header_len(skb));
 
-	rcu_read_lock();
-	IP6_INC_STATS_BH(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;
 	return 1;
 
 out_oversize:
@@ -510,24 +317,27 @@ out_oversize:
 out_oom:
 	net_dbg_ratelimited("ip6_frag_reasm: no memory for reassembly\n");
 out_fail:
-	rcu_read_lock();
-	IP6_INC_STATS_BH(net, __in6_dev_get(dev), IPSTATS_MIB_REASMFAILS);
-	rcu_read_unlock();
+	__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);
-	int evicted;
+	u8 nexthdr;
+	int iif;
+
+	if (IP6CB(skb)->flags & IP6SKB_FRAGMENTED)
+		goto fail_hdr;
 
-	IP6_INC_STATS_BH(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_REASMREQDS);
+	__IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_REASMREQDS);
 
 	/* Jumbo payload inhibits frag. header */
-	if (hdr->payload_len==0)
+	if (hdr->payload_len == 0)
 		goto fail_hdr;
 
 	if (!pskb_may_pull(skb, (skb_transport_offset(skb) +
@@ -537,86 +347,108 @@ 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_BH(net,
-				 ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_REASMOKS);
+		__IP6_INC_STATS(net,
+				ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_REASMOKS);
 
 		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;
 	}
 
-	evicted = inet_frag_evictor(&net->ipv6.frags, &ip6_frags, false);
-	if (evicted)
-		IP6_ADD_STATS_BH(net, ip6_dst_idev(skb_dst(skb)),
-				 IPSTATS_MIB_REASMFAILS, evicted);
+	/* 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;
+	}
 
-	fq = fq_find(net, fhdr->identification, &hdr->saddr, &hdr->daddr,
-		     ip6_frag_ecn(hdr));
-	if (fq != NULL) {
-		int ret;
+	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, refs = 0;
 
 		spin_lock(&fq->q.lock);
 
-		ret = ip6_frag_queue(fq, skb, fhdr, IP6CB(skb)->nhoff);
+		fq->iif = iif;
+		ret = ip6_frag_queue(net, fq, skb, fhdr, IP6CB(skb)->nhoff,
+				     &prob_offset, &refs);
 
 		spin_unlock(&fq->q.lock);
-		inet_frag_put(&fq->q, &ip6_frags);
+		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);
+			/* icmpv6_param_prob() calls kfree_skb(skb) */
+			icmpv6_param_prob(skb, ICMPV6_HDR_FIELD, prob_offset);
+		}
 		return ret;
 	}
+	rcu_read_unlock();
 
-	IP6_INC_STATS_BH(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_REASMFAILS);
+	__IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_REASMFAILS);
 	kfree_skb(skb);
 	return -1;
 
 fail_hdr:
-	IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_INHDRERRORS);
+	__IP6_INC_STATS(net, __in6_dev_get_safely(skb->dev),
+			IPSTATS_MIB_INHDRERRORS);
 	icmpv6_param_prob(skb, ICMPV6_HDR_FIELD, skb_network_header_len(skb));
 	return -1;
 }
 
-static const struct inet6_protocol frag_protocol =
-{
+static const struct inet6_protocol frag_protocol = {
 	.handler	=	ipv6_frag_rcv,
 	.flags		=	INET6_PROTO_NOPOLICY,
 };
 
 #ifdef CONFIG_SYSCTL
+
 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
+		.proc_handler	= proc_doulongvec_minmax,
 	},
 	{
 		.procname	= "ip6frag_low_thresh",
-		.data		= &init_net.ipv6.frags.low_thresh,
-		.maxlen		= sizeof(int),
+		.maxlen		= sizeof(unsigned long),
 		.mode		= 0644,
-		.proc_handler	= proc_dointvec
+		.proc_handler	= proc_doulongvec_minmax,
 	},
 	{
 		.procname	= "ip6frag_time",
-		.data		= &init_net.ipv6.frags.timeout,
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec_jiffies,
 	},
-	{ }
 };
 
+/* secret interval has been deprecated */
+static int ip6_frags_secret_interval_unused;
 static struct ctl_table ip6_frags_ctl_table[] = {
 	{
 		.procname	= "ip6frag_secret_interval",
-		.data		= &ip6_frags.secret_interval,
+		.data		= &ip6_frags_secret_interval_unused,
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec_jiffies,
 	},
-	{ }
 };
 
 static int __net_init ip6_frags_ns_sysctl_register(struct net *net)
@@ -627,20 +459,19 @@ static int __net_init ip6_frags_ns_sysctl_register(struct net *net)
 	table = ip6_frags_ns_ctl_table;
 	if (!net_eq(net, &init_net)) {
 		table = kmemdup(table, sizeof(ip6_frags_ns_ctl_table), GFP_KERNEL);
-		if (table == NULL)
+		if (!table)
 			goto err_alloc;
 
-		table[0].data = &net->ipv6.frags.high_thresh;
-		table[1].data = &net->ipv6.frags.low_thresh;
-		table[2].data = &net->ipv6.frags.timeout;
-
-		/* Don't export sysctls to unprivileged users */
-		if (net->user_ns != &init_user_ns)
-			table[0].procname = NULL;
 	}
-
-	hdr = register_net_sysctl(net, "net/ipv6", table);
-	if (hdr == NULL)
+	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;
 
 	net->ipv6.sysctl.frags_hdr = hdr;
@@ -655,7 +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);
@@ -677,55 +508,86 @@ static void ip6_frags_sysctl_unregister(void)
 	unregister_net_sysctl_table(ip6_ctl_header);
 }
 #else
-static inline int ip6_frags_ns_sysctl_register(struct net *net)
+static int ip6_frags_ns_sysctl_register(struct net *net)
 {
 	return 0;
 }
 
-static inline void ip6_frags_ns_sysctl_unregister(struct net *net)
+static void ip6_frags_ns_sysctl_unregister(struct net *net)
 {
 }
 
-static inline int ip6_frags_sysctl_register(void)
+static int ip6_frags_sysctl_register(void)
 {
 	return 0;
 }
 
-static inline void ip6_frags_sysctl_unregister(void)
+static void ip6_frags_sysctl_unregister(void)
 {
 }
 #endif
 
 static int __net_init ipv6_frags_init_net(struct net *net)
 {
-	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;
+	int res;
+
+	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;
 
-	inet_frags_init_net(&net->ipv6.frags);
+	res = ip6_frags_ns_sysctl_register(net);
+	if (res < 0)
+		fqdir_exit(net->ipv6.fqdir);
+	return res;
+}
 
-	return ip6_frags_ns_sysctl_register(net);
+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, &ip6_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 = {
+	.head_offset		= offsetof(struct inet_frag_queue, node),
+	.hashfn			= ip6frag_key_hashfn,
+	.obj_hashfn		= ip6frag_obj_hashfn,
+	.obj_cmpfn		= ip6frag_obj_cmpfn,
+	.automatic_shrinking	= true,
 };
 
 int __init ipv6_frag_init(void)
 {
 	int ret;
 
-	ret = inet6_add_protocol(&frag_protocol, IPPROTO_FRAGMENT);
+	ip6_frags.constructor = ip6frag_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;
@@ -734,15 +596,6 @@ 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.secret_interval = 10 * 60 * HZ;
-	inet_frags_init(&ip6_frags);
 out:
 	return ret;
 
@@ -750,13 +603,15 @@ err_pernet:
 	ip6_frags_sysctl_unregister();
 err_sysctl:
 	inet6_del_protocol(&frag_protocol, IPPROTO_FRAGMENT);
+err_protocol:
+	inet_frags_fini(&ip6_frags);
 	goto out;
 }
 
 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);
 }