ip_fragment.c

/*
 * INET		An implementation of the TCP/IP protocol suite for the LINUX
 *		operating system.  INET is implemented using the  BSD Socket
 *		interface as the means of communication with the user level.
 *
 *		The IP fragmentation functionality.
 *
 * Authors:	Fred N. van Kempen <waltje@uWalt.NL.Mugnet.ORG>
 *		Alan Cox <alan@lxorguk.ukuu.org.uk>
 *
 * Fixes:
 *		Alan Cox	:	Split from ip.c , see ip_input.c for history.
 *		David S. Miller :	Begin massive cleanup...
 *		Andi Kleen	:	Add sysctls.
 *		xxxx		:	Overlapfrag bug.
 *		Ultima          :       ip_expire() kernel panic.
 *		Bill Hawes	:	Frag accounting and evictor fixes.
 *		John McDonald	:	0 length frag bug.
 *		Alexey Kuznetsov:	SMP races, threading, cleanup.
 *		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>
#include <linux/mm.h>
#include <linux/jiffies.h>
#include <linux/skbuff.h>
#include <linux/list.h>
#include <linux/ip.h>
#include <linux/icmp.h>
#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>
#include <net/checksum.h>
#include <net/inetpeer.h>
#include <net/inet_frag.h>
#include <linux/tcp.h>
#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
 * as well. Or notify me, at least. --ANK
 */

static int sysctl_ipfrag_max_dist __read_mostly = 64;

struct ipfrag_skb_cb
{
	struct inet_skb_parm	h;
	int			offset;
};

#define FRAG_CB(skb)	((struct ipfrag_skb_cb *)((skb)->cb))

/* Describe an entry in the "incomplete datagrams" queue. */
struct ipq {
	struct inet_frag_queue q;

	u32		user;
	__be32		saddr;
	__be32		daddr;
	__be16		id;
	u8		protocol;
	u8		ecn; /* RFC3168 support */
	int             iif;
	unsigned int    rid;
	struct inet_peer *peer;
};

/* RFC 3168 support :
 * We want to check ECN values of all fragments, do detect invalid combinations.
 * In ipq->ecn, we store the OR value of each ip4_frag_ecn() fragment value.
 */
#define	IPFRAG_ECN_NOT_ECT	0x01 /* one frag had ECN_NOT_ECT */
#define	IPFRAG_ECN_ECT_1	0x02 /* one frag had ECN_ECT_1 */
#define	IPFRAG_ECN_ECT_0	0x04 /* one frag had ECN_ECT_0 */
#define	IPFRAG_ECN_CE		0x08 /* one frag had ECN_CE */

static inline u8 ip4_frag_ecn(u8 tos)
{
	return 1 << (tos & INET_ECN_MASK);
}

/* Given the OR values of all fragments, apply RFC 3168 5.3 requirements
 * Value : 0xff if frame should be dropped.
 *         0 or INET_ECN_CE value, to be ORed in to final iph->tos field
 */
static const u8 ip4_frag_ecn_table[16] = {
	/* at least one fragment had CE, and others ECT_0 or ECT_1 */
	[IPFRAG_ECN_CE | IPFRAG_ECN_ECT_0]			= INET_ECN_CE,
	[IPFRAG_ECN_CE | IPFRAG_ECN_ECT_1]			= INET_ECN_CE,
	[IPFRAG_ECN_CE | IPFRAG_ECN_ECT_0 | IPFRAG_ECN_ECT_1]	= INET_ECN_CE,

	/* invalid combinations : drop frame */
	[IPFRAG_ECN_NOT_ECT | IPFRAG_ECN_CE] = 0xff,
	[IPFRAG_ECN_NOT_ECT | IPFRAG_ECN_ECT_0] = 0xff,
	[IPFRAG_ECN_NOT_ECT | IPFRAG_ECN_ECT_1] = 0xff,
	[IPFRAG_ECN_NOT_ECT | IPFRAG_ECN_ECT_0 | IPFRAG_ECN_ECT_1] = 0xff,
	[IPFRAG_ECN_NOT_ECT | IPFRAG_ECN_CE | IPFRAG_ECN_ECT_0] = 0xff,
	[IPFRAG_ECN_NOT_ECT | IPFRAG_ECN_CE | IPFRAG_ECN_ECT_1] = 0xff,
	[IPFRAG_ECN_NOT_ECT | IPFRAG_ECN_CE | IPFRAG_ECN_ECT_0 | IPFRAG_ECN_ECT_1] = 0xff,
};

static struct inet_frags ip4_frags;

int ip_frag_nqueues(struct net *net)
{
	return net->ipv4.frags.nqueues;
}

int ip_frag_mem(struct net *net)
{
	return sum_frag_mem_limit(&net->ipv4.frags);
}

static int ip_frag_reasm(struct ipq *qp, struct sk_buff *prev,
			 struct net_device *dev);

struct ip4_create_arg {
	struct iphdr *iph;
	u32 user;
};

static unsigned int ipqhashfn(__be16 id, __be32 saddr, __be32 daddr, u8 prot)
{
	return jhash_3words((__force u32)id << 16 | prot,
			    (__force u32)saddr, (__force u32)daddr,
			    ip4_frags.rnd) & (INETFRAGS_HASHSZ - 1);
}

static unsigned int ip4_hashfn(struct inet_frag_queue *q)
{
	struct ipq *ipq;

	ipq = container_of(q, struct ipq, q);
	return ipqhashfn(ipq->id, ipq->saddr, ipq->daddr, ipq->protocol);
}

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;
}

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_v4(net->ipv4.peers, arg->iph->saddr, 1) : NULL;
}

static __inline__ void ip4_frag_free(struct inet_frag_queue *q)
{
	struct ipq *qp;

	qp = container_of(q, struct ipq, q);
	if (qp->peer)
		inet_putpeer(qp->peer);
}


/* Destruction primitives. */

static __inline__ void ipq_put(struct ipq *ipq)
{
	inet_frag_put(&ipq->q, &ip4_frags);
}

/* Kill ipq entry. It is not destroyed immediately,
 * because caller (and someone more) holds reference count.
 */
static void ipq_kill(struct ipq *ipq)
{
	inet_frag_kill(&ipq->q, &ip4_frags);
}

/* Memory limiting on fragments.  Evictor trashes the oldest
 * fragment queue until we are back under the threshold.
 */
static void ip_evictor(struct net *net)
{
	int evicted;

	evicted = inet_frag_evictor(&net->ipv4.frags, &ip4_frags, false);
	if (evicted)
		IP_ADD_STATS_BH(net, IPSTATS_MIB_REASMFAILS, evicted);
}

/*
 * Oops, a fragment queue timed out.  Kill it and send an ICMP reply.
 */
static void ip_expire(unsigned long arg)
{
	struct ipq *qp;
	struct net *net;

	qp = container_of((struct inet_frag_queue *) arg, struct ipq, q);
	net = container_of(qp->q.net, struct net, ipv4.frags);

	spin_lock(&qp->q.lock);

	if (qp->q.last_in & INET_FRAG_COMPLETE)
		goto out;

	ipq_kill(qp);

	IP_INC_STATS_BH(net, IPSTATS_MIB_REASMTIMEOUT);
	IP_INC_STATS_BH(net, IPSTATS_MIB_REASMFAILS);

	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;

		rcu_read_lock();
		head->dev = dev_get_by_index_rcu(net, qp->iif);
		if (!head->dev)
			goto out_rcu_unlock;

		/* skb dst is stale, drop it, and perform route lookup again */
		skb_dst_drop(head);
		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 &&
		     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:
	spin_unlock(&qp->q.lock);
	ipq_put(qp);
}

/* Find the correct entry in the "incomplete datagrams" queue for
 * this IP datagram, and create new one, if nothing is found.
 */
static inline struct ipq *ip_find(struct net *net, struct iphdr *iph, u32 user)
{
	struct inet_frag_queue *q;
	struct ip4_create_arg arg;
	unsigned int hash;

	arg.iph = iph;
	arg.user = user;

	read_lock(&ip4_frags.lock);
	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;

	return container_of(q, struct ipq, q);

out_nomem:
	LIMIT_NETDEBUG(KERN_ERR pr_fmt("ip_frag_create: no memory left !\n"));
	return NULL;
}

/* Is the fragment too far ahead to be part of ipq? */
static inline int ip_frag_too_far(struct ipq *qp)
{
	struct inet_peer *peer = qp->peer;
	unsigned int max = sysctl_ipfrag_max_dist;
	unsigned int start, end;

	int rc;

	if (!peer || !max)
		return 0;

	start = qp->rid;
	end = atomic_inc_return(&peer->rid);
	qp->rid = end;

	rc = qp->q.fragments && (end - start) > max;

	if (rc) {
		struct net *net;

		net = container_of(qp->q.net, struct net, ipv4.frags);
		IP_INC_STATS_BH(net, IPSTATS_MIB_REASMFAILS);
	}

	return rc;
}

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);
		return -ETIMEDOUT;
	}

	fp = qp->q.fragments;
	do {
		struct sk_buff *xp = fp->next;

		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;
}

/* Add new segment to existing queue. */
static int ip_frag_queue(struct ipq *qp, struct sk_buff *skb)
{
	struct sk_buff *prev, *next;
	struct net_device *dev;
	int flags, offset;
	int ihl, end;
	int err = -ENOENT;
	u8 ecn;

	if (qp->q.last_in & INET_FRAG_COMPLETE)
		goto err;

	if (!(IPCB(skb)->flags & IPSKB_FRAG_COMPLETE) &&
	    unlikely(ip_frag_too_far(qp)) &&
	    unlikely(err = ip_frag_reinit(qp))) {
		ipq_kill(qp);
		goto err;
	}

	ecn = ip4_frag_ecn(ip_hdr(skb)->tos);
	offset = ntohs(ip_hdr(skb)->frag_off);
	flags = offset & ~IP_OFFSET;
	offset &= IP_OFFSET;
	offset <<= 3;		/* offset is in 8-byte chunks */
	ihl = ip_hdrlen(skb);

	/* Determine the position of this fragment. */
	end = offset + skb->len - ihl;
	err = -EINVAL;

	/* 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 corrupted.
		 */
		if (end < qp->q.len ||
		    ((qp->q.last_in & INET_FRAG_LAST_IN) && end != qp->q.len))
			goto err;
		qp->q.last_in |= INET_FRAG_LAST_IN;
		qp->q.len = end;
	} else {
		if (end&7) {
			end &= ~7;
			if (skb->ip_summed != CHECKSUM_UNNECESSARY)
				skb->ip_summed = CHECKSUM_NONE;
		}
		if (end > qp->q.len) {
			/* Some bits beyond end -> corruption. */
			if (qp->q.last_in & INET_FRAG_LAST_IN)
				goto err;
			qp->q.len = end;
		}
	}
	if (end == offset)
		goto err;

	err = -ENOMEM;
	if (pskb_pull(skb, ihl) == NULL)
		goto err;

	err = pskb_trim_rcsum(skb, end - offset);
	if (err)
		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 = 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)
			break;	/* bingo! */
		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.
	 */
	if (prev) {
		int i = (FRAG_CB(prev)->offset + prev->len) - offset;

		if (i > 0) {
			offset += i;
			err = -EINVAL;
			if (end <= offset)
				goto err;
			err = -ENOMEM;
			if (!pskb_pull(skb, i))
				goto err;
			if (skb->ip_summed != CHECKSUM_UNNECESSARY)
				skb->ip_summed = CHECKSUM_NONE;
		}
	}

	err = -ENOMEM;

	while (next && FRAG_CB(next)->offset < end) {
		int i = end - FRAG_CB(next)->offset; /* overlap is 'i' bytes */

		if (i < next->len) {
			/* Eat head of the next overlapped fragment
			 * and leave the loop. The next ones cannot overlap.
			 */
			if (!pskb_pull(next, i))
				goto err;
			FRAG_CB(next)->offset += i;
			qp->q.meat -= i;
			if (next->ip_summed != CHECKSUM_UNNECESSARY)
				next->ip_summed = CHECKSUM_NONE;
			break;
		} else {
			struct sk_buff *free_it = next;

			/* Old fragment is completely overridden with
			 * new one drop it.
			 */
			next = next->next;

			if (prev)
				prev->next = next;
			else
				qp->q.fragments = next;

			qp->q.meat -= free_it->len;
			sub_frag_mem_limit(&qp->q, free_it->truesize);
			kfree_skb(free_it);
		}
	}

	FRAG_CB(skb)->offset = offset;

	/* Insert this fragment in the chain of fragments. */
	skb->next = next;
	if (!next)
		qp->q.fragments_tail = skb;
	if (prev)
		prev->next = skb;
	else
		qp->q.fragments = skb;

	dev = skb->dev;
	if (dev) {
		qp->iif = dev->ifindex;
		skb->dev = NULL;
	}
	qp->q.stamp = skb->tstamp;
	qp->q.meat += skb->len;
	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);

	inet_frag_lru_move(&qp->q);
	return -EINPROGRESS;

err:
	kfree_skb(skb);
	return err;
}


/* Build a new IP datagram from all its fragments. */

static int ip_frag_reasm(struct ipq *qp, struct sk_buff *prev,
			 struct net_device *dev)
{
	struct net *net = container_of(qp->q.net, struct net, ipv4.frags);
	struct iphdr *iph;
	struct sk_buff *fp, *head = qp->q.fragments;
	int len;
	int ihlen;
	int err;
	int sum_truesize;
	u8 ecn;

	ipq_kill(qp);

	ecn = ip4_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;
		fp = skb_clone(head, GFP_ATOMIC);
		if (!fp)
			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;

		consume_skb(qp->q.fragments);
		qp->q.fragments = head;
	}

	WARN_ON(head == NULL);
	WARN_ON(FRAG_CB(head)->offset != 0);

	/* Allocate a new buffer for the datagram. */
	ihlen = ip_hdrlen(head);
	len = ihlen + qp->q.len;

	err = -E2BIG;
	if (len > 65535)
		goto out_oversize;

	/* Head of list must not be cloned. */
	if (skb_cloned(head) && pskb_expand_head(head, 0, 0, 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_frag_list(head)) {
		struct sk_buff *clone;
		int i, plen = 0;

		if ((clone = alloc_skb(0, GFP_ATOMIC)) == NULL)
			goto out_nomem;
		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(&qp->q, clone->truesize);
	}

	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(&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);
	/* 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 pr_fmt("queue_glue: no memory for gluing queue %p\n"),
		       qp);
	err = -ENOMEM;
	goto out_fail;
out_oversize:
	net_info_ratelimited("Oversized IP packet from %pI4\n", &qp->saddr);
out_fail:
	IP_INC_STATS_BH(net, IPSTATS_MIB_REASMFAILS);
	return err;
}

/* Process an incoming IP datagram fragment. */
int ip_defrag(struct sk_buff *skb, u32 user)
{
	struct ipq *qp;
	struct net *net;

	net = skb->dev ? dev_net(skb->dev) : dev_net(skb_dst(skb)->dev);
	IP_INC_STATS_BH(net, IPSTATS_MIB_REASMREQDS);

	/* Start by cleaning up the memory. */
	ip_evictor(net);

	/* Lookup (or create) queue header */
	if ((qp = ip_find(net, ip_hdr(skb), user)) != NULL) {
		int ret;

		spin_lock(&qp->q.lock);

		ret = ip_frag_queue(qp, skb);

		spin_unlock(&qp->q.lock);
		ipq_put(qp);
		return ret;
	}

	IP_INC_STATS_BH(net, IPSTATS_MIB_REASMFAILS);
	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->rxhash = 0;
		}
	}
	return skb;
}
EXPORT_SYMBOL(ip_check_defrag);

#ifdef CONFIG_SYSCTL
static int zero;

static struct ctl_table ip4_frags_ns_ctl_table[] = {
	{
		.procname	= "ipfrag_high_thresh",
		.data		= &init_net.ipv4.frags.high_thresh,
		.maxlen		= sizeof(int),
		.mode		= 0644,
		.proc_handler	= proc_dointvec
	},
	{
		.procname	= "ipfrag_low_thresh",
		.data		= &init_net.ipv4.frags.low_thresh,
		.maxlen		= sizeof(int),
		.mode		= 0644,
		.proc_handler	= proc_dointvec
	},
	{
		.procname	= "ipfrag_time",
		.data		= &init_net.ipv4.frags.timeout,
		.maxlen		= sizeof(int),
		.mode		= 0644,
		.proc_handler	= proc_dointvec_jiffies,
	},
	{ }
};

static struct ctl_table ip4_frags_ctl_table[] = {
	{
		.procname	= "ipfrag_secret_interval",
		.data		= &ip4_frags.secret_interval,
		.maxlen		= sizeof(int),
		.mode		= 0644,
		.proc_handler	= proc_dointvec_jiffies,
	},
	{
		.procname	= "ipfrag_max_dist",
		.data		= &sysctl_ipfrag_max_dist,
		.maxlen		= sizeof(int),
		.mode		= 0644,
		.proc_handler	= proc_dointvec_minmax,
		.extra1		= &zero
	},
	{ }
};

static int __net_init ip4_frags_ns_ctl_register(struct net *net)
{
	struct ctl_table *table;
	struct ctl_table_header *hdr;

	table = ip4_frags_ns_ctl_table;
	if (!net_eq(net, &init_net)) {
		table = kmemdup(table, sizeof(ip4_frags_ns_ctl_table), GFP_KERNEL);
		if (table == NULL)
			goto err_alloc;

		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(net, "net/ipv4", table);
	if (hdr == NULL)
		goto err_reg;

	net->ipv4.frags_hdr = hdr;
	return 0;

err_reg:
	if (!net_eq(net, &init_net))
		kfree(table);
err_alloc:
	return -ENOMEM;
}

static void __net_exit ip4_frags_ns_ctl_unregister(struct net *net)
{
	struct ctl_table *table;

	table = net->ipv4.frags_hdr->ctl_table_arg;
	unregister_net_sysctl_table(net->ipv4.frags_hdr);
	kfree(table);
}

static void ip4_frags_ctl_register(void)
{
	register_net_sysctl(&init_net, "net/ipv4", ip4_frags_ctl_table);
}
#else
static inline int ip4_frags_ns_ctl_register(struct net *net)
{
	return 0;
}

static inline void ip4_frags_ns_ctl_unregister(struct net *net)
{
}

static inline void ip4_frags_ctl_register(void)
{
}
#endif

static int __net_init ipv4_frags_init_net(struct net *net)
{
	/* 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 = 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
	 * by TTL.
	 */
	net->ipv4.frags.timeout = IP_FRAG_TIME;

	inet_frags_init_net(&net->ipv4.frags);

	return ip4_frags_ns_ctl_register(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);
}

static struct pernet_operations ip4_frags_ops = {
	.init = ipv4_frags_init_net,
	.exit = ipv4_frags_exit_net,
};

void __init ipfrag_init(void)
{
	ip4_frags_ctl_register();
	register_pernet_subsys(&ip4_frags_ops);
	ip4_frags.hashfn = ip4_hashfn;
	ip4_frags.constructor = ip4_frag_init;
	ip4_frags.destructor = ip4_frag_free;
	ip4_frags.skb_free = NULL;
	ip4_frags.qsize = sizeof(struct ipq);
	ip4_frags.match = ip4_frag_match;
	ip4_frags.frag_expire = ip_expire;
	ip4_frags.secret_interval = 10 * 60 * HZ;
	inet_frags_init(&ip4_frags);
}