Release 4.11 net/ipv4/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>
#include <net/l3mdev.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 const char ip_frag_cache_name[] = "ip4-frags";


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 */
	
u16		max_df_size; /* largest frag with DF set seen */
	
int             iif;
	
int             vif;   /* L3 master device index */
	
unsigned int    rid;
	
struct inet_peer *peer;
};



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

Contributors
Person
Tokens
Prop
Commits
CommitProp
Eric Dumazet
18
100.00%
2
100.00%
Total
18
100.00%
2
100.00%


static struct inet_frags ip4_frags;



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

Contributors
Person
Tokens
Prop
Commits
CommitProp
Pavel Emelyanov
20
95.24%
2
66.67%
Jesper Dangaard Brouer
1
4.76%
1
33.33%
Total
21
100.00%
3
100.00%

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;
	
int vif;
};



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);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Linus Torvalds (pre-git)
21
32.81%
2
33.33%
Hannes Frederic Sowa
15
23.44%
1
16.67%
David S. Miller
13
20.31%
1
16.67%
Al Viro
12
18.75%
1
16.67%
Pavel Emelyanov
3
4.69%
1
16.67%
Total
64
100.00%
6
100.00%



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

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

Contributors
Person
Tokens
Prop
Commits
CommitProp
David S. Miller
23
45.10%
1
25.00%
Pavel Emelyanov
21
41.18%
1
25.00%
Yasuyuki Kozakai
5
9.80%
1
25.00%
Florian Westphal
2
3.92%
1
25.00%
Total
51
100.00%
4
100.00%



static bool ip4_frag_match(const struct inet_frag_queue *q, const void *a)
{
	const struct ipq *qp;
	const 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 &&
		qp->vif == arg->vif;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Pavel Emelyanov
87
87.00%
1
25.00%
David Ahern
8
8.00%
1
25.00%
Florian Westphal
4
4.00%
1
25.00%
Eric Dumazet
1
1.00%
1
25.00%
Total
100
100.00%
4
100.00%



static void ip4_frag_init(struct inet_frag_queue *q, const 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);

	const 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->vif = arg->vif;
	qp->user = arg->user;
	qp->peer = q->net->max_dist ?
		inet_getpeer_v4(net->ipv4.peers, arg->iph->saddr, arg->vif, 1) :
		NULL;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Pavel Emelyanov
102
58.96%
1
11.11%
Gao Feng
34
19.65%
1
11.11%
Eric Dumazet
13
7.51%
1
11.11%
David Ahern
12
6.94%
2
22.22%
Nikolay Borisov
5
2.89%
1
11.11%
David S. Miller
5
2.89%
2
22.22%
Florian Westphal
2
1.16%
1
11.11%
Total
173
100.00%
9
100.00%



static 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);
}


Contributors
Person
Tokens
Prop
Commits
CommitProp
Pavel Emelyanov
25
60.98%
1
20.00%
Linus Torvalds (pre-git)
9
21.95%
2
40.00%
David S. Miller
6
14.63%
1
20.00%
Linus Torvalds
1
2.44%
1
20.00%
Total
41
100.00%
5
100.00%

/* Destruction primitives. */



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

Contributors
Person
Tokens
Prop
Commits
CommitProp
Linus Torvalds (pre-git)
14
63.64%
2
40.00%
Pavel Emelyanov
8
36.36%
3
60.00%
Total
22
100.00%
5
100.00%

/* 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);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Linus Torvalds (pre-git)
18
81.82%
2
50.00%
Pavel Emelyanov
4
18.18%
2
50.00%
Total
22
100.00%
4
100.00%



static bool frag_expire_skip_icmp(u32 user)
{
	return user == IP_DEFRAG_AF_PACKET ||
	       ip_defrag_user_in_between(user, IP_DEFRAG_CONNTRACK_IN,
					 __IP_DEFRAG_CONNTRACK_IN_END) ||
	       ip_defrag_user_in_between(user, IP_DEFRAG_CONNTRACK_BRIDGE_IN,
					 __IP_DEFRAG_CONNTRACK_BRIDGE_IN);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Andy Zhou
32
100.00%
2
100.00%
Total
32
100.00%
2
100.00%

/*
 * 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);

	rcu_read_lock();
	spin_lock(&qp->q.lock);

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

	ipq_kill(qp);
	__IP_INC_STATS(net, IPSTATS_MIB_REASMFAILS);

	if (!inet_frag_evicting(&qp->q)) {
		struct sk_buff *clone, *head = qp->q.fragments;
		const struct iphdr *iph;
		int err;

		__IP_INC_STATS(net, IPSTATS_MIB_REASMTIMEOUT);

		if (!(qp->q.flags & INET_FRAG_FIRST_IN) || !qp->q.fragments)
			goto out;

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


		/* 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;

		/* Only an end host needs to send an ICMP
                 * "Fragment Reassembly Timeout" message, per RFC792.
                 */
		if (frag_expire_skip_icmp(qp->user) &&
		    (skb_rtable(head)->rt_type != RTN_LOCAL))
			goto out;

		clone = skb_clone(head, GFP_ATOMIC);

		/* Send an ICMP "Fragment Reassembly Timeout" message. */
		if (clone) {
			spin_unlock(&qp->q.lock);
			icmp_send(clone, ICMP_TIME_EXCEEDED,
				  ICMP_EXC_FRAGTIME, 0);
			consume_skb(clone);
			goto out_rcu_unlock;
		}
	}
out:
	spin_unlock(&qp->q.lock);
out_rcu_unlock:
	rcu_read_unlock();
	ipq_put(qp);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Linus Torvalds (pre-git)
95
30.55%
7
24.14%
Eric Dumazet
73
23.47%
5
17.24%
Shan Wei
48
15.43%
1
3.45%
Pavel Emelyanov
47
15.11%
4
13.79%
Nikolay Aleksandrov
36
11.58%
3
10.34%
Andy Zhou
3
0.96%
1
3.45%
Vasily Averin
2
0.64%
1
3.45%
David S. Miller
2
0.64%
2
6.90%
Denis V. Lunev
1
0.32%
1
3.45%
Eric W. Biedermann
1
0.32%
1
3.45%
Joe Perches
1
0.32%
1
3.45%
Patrick McHardy
1
0.32%
1
3.45%
Hideaki Yoshifuji / 吉藤英明
1
0.32%
1
3.45%
Total
311
100.00%
29
100.00%

/* Find the correct entry in the "incomplete datagrams" queue for
 * this IP datagram, and create new one, if nothing is found.
 */


static struct ipq *ip_find(struct net *net, struct iphdr *iph,
			   u32 user, int vif)
{
	struct inet_frag_queue *q;
	struct ip4_create_arg arg;
	unsigned int hash;

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

	hash = ipqhashfn(iph->id, iph->saddr, iph->daddr, iph->protocol);

	q = inet_frag_find(&net->ipv4.frags, &ip4_frags, &arg, hash);
	if (IS_ERR_OR_NULL(q)) {
		inet_frag_maybe_warn_overflow(q, pr_fmt());
		return NULL;
	}
	return container_of(q, struct ipq, q);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Pavel Emelyanov
67
52.76%
4
36.36%
Linus Torvalds (pre-git)
23
18.11%
3
27.27%
Hannes Frederic Sowa
16
12.60%
1
9.09%
David Ahern
9
7.09%
1
9.09%
Patrick McHardy
7
5.51%
1
9.09%
Herbert Xu
5
3.94%
1
9.09%
Total
127
100.00%
11
100.00%

/* Is the fragment too far ahead to be part of ipq? */


static int ip_frag_too_far(struct ipq *qp)
{
	struct inet_peer *peer = qp->peer;
	unsigned int max = qp->q.net->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(net, IPSTATS_MIB_REASMFAILS);
	}

	return rc;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Herbert Xu
94
72.87%
1
20.00%
Pavel Emelyanov
27
20.93%
2
40.00%
Nikolay Borisov
7
5.43%
1
20.00%
Eric Dumazet
1
0.78%
1
20.00%
Total
129
100.00%
5
100.00%



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.net, sum_truesize);

	qp->q.flags = 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;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Herbert Xu
106
63.47%
1
10.00%
Jesper Dangaard Brouer
22
13.17%
1
10.00%
Pavel Emelyanov
22
13.17%
4
40.00%
Changli Gao
8
4.79%
1
10.00%
Eric Dumazet
6
3.59%
1
10.00%
Florian Westphal
2
1.20%
1
10.00%
Nikolay Aleksandrov
1
0.60%
1
10.00%
Total
167
100.00%
10
100.00%

/* 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;
	unsigned int fragsize;
	int flags, offset;
	int ihl, end;
	int err = -ENOENT;
	u8 ecn;

	if (qp->q.flags & 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 - skb_network_offset(skb) - 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.flags & INET_FRAG_LAST_IN) && end != qp->q.len))
			goto err;
		qp->q.flags |= 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.flags & INET_FRAG_LAST_IN)
				goto err;
			qp->q.len = end;
		}
	}
	if (end == offset)
		goto err;

	err = -ENOMEM;
	if (!pskb_pull(skb, skb_network_offset(skb) + ihl))
		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.net, 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.net, skb->truesize);
	if (offset == 0)
		qp->q.flags |= INET_FRAG_FIRST_IN;

	fragsize = skb->len + ihl;

	if (fragsize > qp->q.max_size)
		qp->q.max_size = fragsize;

	if (ip_hdr(skb)->frag_off & htons(IP_DF) &&
	    fragsize > qp->max_df_size)
		qp->max_df_size = fragsize;

	if (qp->q.flags == (INET_FRAG_FIRST_IN | INET_FRAG_LAST_IN) &&
	    qp->q.meat == qp->q.len) {
		unsigned long orefdst = skb->_skb_refdst;

		skb->_skb_refdst = 0UL;
		err = ip_frag_reasm(qp, prev, dev);
		skb->_skb_refdst = orefdst;
		return err;
	}

	skb_dst_drop(skb);
	return -EINPROGRESS;

err:
	kfree_skb(skb);
	return err;
}


Contributors
Person
Tokens
Prop
Commits
CommitProp
Linus Torvalds (pre-git)
501
54.16%
13
36.11%
Herbert Xu
126
13.62%
2
5.56%
Eric Dumazet
57
6.16%
3
8.33%
Pavel Emelyanov
48
5.19%
2
5.56%
Changli Gao
46
4.97%
1
2.78%
Linus Torvalds
41
4.43%
1
2.78%
Florian Westphal
38
4.11%
2
5.56%
Patrick McHardy
23
2.49%
2
5.56%
Jesper Dangaard Brouer
12
1.30%
1
2.78%
Edward Hyunkoo Jee
10
1.08%
1
2.78%
Joe Perches
7
0.76%
1
2.78%
Nikolay Aleksandrov
6
0.65%
1
2.78%
Arnaldo Carvalho de Melo
6
0.65%
2
5.56%
Justin P. Mattock
1
0.11%
1
2.78%
Stephen Hemminger
1
0.11%
1
2.78%
Peter Zijlstra
1
0.11%
1
2.78%
Ian Morris
1
0.11%
1
2.78%
Total
925
100.00%
36
100.00%

/* 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;
	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;
		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);
	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_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_frag_list(head)) {
		struct sk_buff *clone;
		int i, plen = 0;

		clone = alloc_skb(0, GFP_ATOMIC);
		if (!clone)
			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.net, clone->truesize);
	}

	skb_shinfo(head)->frag_list = head->next;
	skb_push(head, head->data - skb_network_header(head));

	for (fp=head->next; fp; fp = fp->next) {
		head->data_len += fp->len;
		head->len += fp->len;
		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;
	}
	sub_frag_mem_limit(qp->q.net, head->truesize);

	head->next = NULL;
	head->dev = dev;
	head->tstamp = qp->q.stamp;
	IPCB(head)->frag_max_size = max(qp->max_df_size, qp->q.max_size);

	iph = ip_hdr(head);
	iph->tot_len = htons(len);
	iph->tos |= ecn;

	/* When we set IP_DF on a refragmented skb we must also force a
         * call to ip_fragment to avoid forwarding a DF-skb of size s while
         * original sender only sent fragments of size f (where f < s).
         *
         * We only set DF/IPSKB_FRAG_PMTU if such DF fragment was the largest
         * frag seen to avoid sending tiny DF-fragments in case skb was built
         * from one very small df-fragment and one large non-df frag.
         */
	if (qp->max_df_size == qp->q.max_size) {
		IPCB(head)->flags |= IPSKB_FRAG_PMTU;
		iph->frag_off = htons(IP_DF);
	} else {
		iph->frag_off = 0;
	}

	ip_send_check(iph);

	__IP_INC_STATS(net, IPSTATS_MIB_REASMOKS);
	qp->q.fragments = NULL;
	qp->q.fragments_tail = NULL;
	return 0;

out_nomem:
	net_dbg_ratelimited("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(net, IPSTATS_MIB_REASMFAILS);
	return err;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Linus Torvalds (pre-git)
222
30.45%
9
18.75%
Linus Torvalds
155
21.26%
1
2.08%
Herbert Xu
91
12.48%
1
2.08%
Florian Westphal
76
10.43%
3
6.25%
Eric Dumazet
44
6.04%
7
14.58%
Pavel Emelyanov
25
3.43%
3
6.25%
Changli Gao
23
3.16%
1
2.08%
Jorge Boncompte
22
3.02%
1
2.08%
Patrick McHardy
21
2.88%
2
4.17%
Arnaldo Carvalho de Melo
9
1.23%
3
6.25%
Ian Morris
6
0.82%
1
2.08%
Jesper Dangaard Brouer
6
0.82%
1
2.08%
Joe Perches
6
0.82%
4
8.33%
Edward Hyunkoo Jee
5
0.69%
1
2.08%
David Howells
5
0.69%
1
2.08%
Ilpo Järvinen
3
0.41%
1
2.08%
Hideaki Yoshifuji / 吉藤英明
2
0.27%
1
2.08%
David S. Miller
2
0.27%
2
4.17%
Heikki Orsila
2
0.27%
1
2.08%
David Ford
1
0.14%
1
2.08%
Harvey Harrison
1
0.14%
1
2.08%
Hannes Frederic Sowa
1
0.14%
1
2.08%
Pravin B Shelar
1
0.14%
1
2.08%
Total
729
100.00%
48
100.00%

/* Process an incoming IP datagram fragment. */


int ip_defrag(struct net *net, struct sk_buff *skb, u32 user)
{
	struct net_device *dev = skb->dev ? : skb_dst(skb)->dev;
	int vif = l3mdev_master_ifindex_rcu(dev);
	struct ipq *qp;

	__IP_INC_STATS(net, IPSTATS_MIB_REASMREQDS);
	skb_orphan(skb);

	/* Lookup (or create) queue header */
	qp = ip_find(net, ip_hdr(skb), user, vif);
	if (qp) {
		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(net, IPSTATS_MIB_REASMFAILS);
	kfree_skb(skb);
	return -ENOMEM;
}
Contributors
Person
Tokens
Prop
Commits
CommitProp
Linus Torvalds (pre-git)
62
44.60%
5
22.73%
David Ahern
21
15.11%
2
9.09%
Pavel Emelyanov
18
12.95%
4
18.18%
Herbert Xu
6
4.32%
2
9.09%
Eric W. Biedermann
5
3.60%
1
4.55%
Joe Stringer
5
3.60%
1
4.55%
Patrick McHardy
5
3.60%
1
4.55%
Arnaldo Carvalho de Melo
4
2.88%
1
4.55%
Phil Oester
4
2.88%
1
4.55%
Ian Morris
4
2.88%
1
4.55%
Hideaki Yoshifuji / 吉藤英明
3
2.16%
2
9.09%
Eric Dumazet
2
1.44%
1
4.55%
Total
139
100.00%
22
100.00%


EXPORT_SYMBOL(ip_defrag);



struct sk_buff *ip_check_defrag(struct net *net, struct sk_buff *skb, u32 user)
{
	struct iphdr iph;
	int netoff;
	u32 len;

	if (skb->protocol != htons(ETH_P_IP))
		return skb;

	netoff = skb_network_offset(skb);

	if (skb_copy_bits(skb, netoff, &iph, sizeof(iph)) < 0)
		return skb;

	if (iph.ihl < 5 || iph.version != 4)
		return skb;

	len = ntohs(iph.tot_len);
	if (skb->len < netoff + 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, netoff + iph.ihl * 4))
				return skb;
			if (pskb_trim_rcsum(skb, netoff + len))
				return skb;
			memset(IPCB(skb), 0, sizeof(struct inet_skb_parm));
			if (ip_defrag(net, skb, user))
				return NULL;
			skb_clear_hash(skb);
		}
	}
	return skb;
}
Contributors
Person
Tokens
Prop
Commits
CommitProp
Eric Dumazet
160
73.39%
1
16.67%
Johannes Berg
29
13.30%
1
16.67%
Alexander Drozdov
19
8.72%
2
33.33%
Eric W. Biedermann
7
3.21%
1
16.67%
Tom Herbert
3
1.38%
1
16.67%
Total
218
100.00%
6
100.00%


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_minmax,
		.extra1		= &init_net.ipv4.frags.low_thresh
	},
	{
		.procname	= "ipfrag_low_thresh",
		.data		= &init_net.ipv4.frags.low_thresh,
		.maxlen		= sizeof(int),
		.mode		= 0644,
		.proc_handler	= proc_dointvec_minmax,
		.extra1		= &zero,
		.extra2		= &init_net.ipv4.frags.high_thresh
	},
	{
		.procname	= "ipfrag_time",
		.data		= &init_net.ipv4.frags.timeout,
		.maxlen		= sizeof(int),
		.mode		= 0644,
		.proc_handler	= proc_dointvec_jiffies,
        },
	{
		.procname	= "ipfrag_max_dist",
		.data		= &init_net.ipv4.frags.max_dist,
		.maxlen		= sizeof(int),
		.mode		= 0644,
		.proc_handler	= proc_dointvec_minmax,
		.extra1		= &zero
	},
	{ }
};

/* secret interval has been deprecated */

static int ip4_frags_secret_interval_unused;

static struct ctl_table ip4_frags_ctl_table[] = {
	{
		.procname	= "ipfrag_secret_interval",
		.data		= &ip4_frags_secret_interval_unused,
		.maxlen		= sizeof(int),
		.mode		= 0644,
		.proc_handler	= proc_dointvec_jiffies,
        },
	{ }
};



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)
			goto err_alloc;

		table[0].data = &net->ipv4.frags.high_thresh;
		table[0].extra1 = &net->ipv4.frags.low_thresh;
		table[0].extra2 = &init_net.ipv4.frags.high_thresh;
		table[1].data = &net->ipv4.frags.low_thresh;
		table[1].extra2 = &net->ipv4.frags.high_thresh;
		table[2].data = &net->ipv4.frags.timeout;
		table[3].data = &net->ipv4.frags.max_dist;
	}

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

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

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

Contributors
Person
Tokens
Prop
Commits
CommitProp
Pavel Emelyanov
148
65.20%
5
45.45%
Nikolay Aleksandrov
48
21.15%
1
9.09%
Nikolay Borisov
16
7.05%
1
9.09%
Octavian Purdila
10
4.41%
1
9.09%
Eric W. Biedermann
2
0.88%
1
9.09%
Ian Morris
2
0.88%
1
9.09%
Alexey Dobriyan
1
0.44%
1
9.09%
Total
227
100.00%
11
100.00%



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);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Pavel Emelyanov
40
97.56%
2
66.67%
Alexey Dobriyan
1
2.44%
1
33.33%
Total
41
100.00%
3
100.00%



static void __init ip4_frags_ctl_register(void)
{
	register_net_sysctl(&init_net, "net/ipv4", ip4_frags_ctl_table);
}
Contributors
Person
Tokens
Prop
Commits
CommitProp
Pavel Emelyanov
13
68.42%
1
33.33%
Eric W. Biedermann
5
26.32%
1
33.33%
Fabian Frederick
1
5.26%
1
33.33%
Total
19
100.00%
3
100.00%

#else


static int ip4_frags_ns_ctl_register(struct net *net)
{
	return 0;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Pavel Emelyanov
14
100.00%
2
100.00%
Total
14
100.00%
2
100.00%



static void ip4_frags_ns_ctl_unregister(struct net *net)
{
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Pavel Emelyanov
10
100.00%
2
100.00%
Total
10
100.00%
2
100.00%



static void __init ip4_frags_ctl_register(void)
{
}
Contributors
Person
Tokens
Prop
Commits
CommitProp
Pavel Emelyanov
7
87.50%
1
50.00%
Fabian Frederick
1
12.50%
1
50.00%
Total
8
100.00%
2
100.00%

#endif



static int __net_init ipv4_frags_init_net(struct net *net)
{
	int res;

	/* 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;

	net->ipv4.frags.max_dist = 64;

	res = inet_frags_init_net(&net->ipv4.frags);
	if (res)
		return res;
	res = ip4_frags_ns_ctl_register(net);
	if (res)
		inet_frags_uninit_net(&net->ipv4.frags);
	return res;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Pavel Emelyanov
60
55.56%
5
55.56%
Eric Dumazet
30
27.78%
1
11.11%
Nikolay Borisov
10
9.26%
1
11.11%
Jesper Dangaard Brouer
7
6.48%
1
11.11%
Alexey Dobriyan
1
0.93%
1
11.11%
Total
108
100.00%
9
100.00%



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);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Pavel Emelyanov
29
96.67%
2
66.67%
Alexey Dobriyan
1
3.33%
1
33.33%
Total
30
100.00%
3
100.00%


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.qsize = sizeof(struct ipq);
	ip4_frags.match = ip4_frag_match;
	ip4_frags.frag_expire = ip_expire;
	ip4_frags.frags_cache_name = ip_frag_cache_name;
	if (inet_frags_init(&ip4_frags))
		panic("IP: failed to allocate ip4_frags cache\n");
}
Contributors
Person
Tokens
Prop
Commits
CommitProp
Pavel Emelyanov
53
69.74%
11
78.57%
Nikolay Aleksandrov
13
17.11%
1
7.14%
David S. Miller
9
11.84%
1
7.14%
Eric Dumazet
1
1.32%
1
7.14%
Total
76
100.00%
14
100.00%

Overall Contributors
Person
Tokens
Prop
Commits
CommitProp
Pavel Emelyanov
1119
25.93%
24
16.33%
Linus Torvalds (pre-git)
1054
24.43%
20
13.61%
Herbert Xu
462
10.71%
3
2.04%
Eric Dumazet
423
9.80%
15
10.20%
Linus Torvalds
200
4.63%
2
1.36%
Nikolay Aleksandrov
144
3.34%
5
3.40%
Florian Westphal
128
2.97%
4
2.72%
Changli Gao
77
1.78%
1
0.68%
Nikolay Borisov
73
1.69%
1
0.68%
David S. Miller
67
1.55%
8
5.44%
Patrick McHardy
64
1.48%
6
4.08%
David Ahern
60
1.39%
3
2.04%
Shan Wei
54
1.25%
1
0.68%
Jesper Dangaard Brouer
48
1.11%
2
1.36%
Andy Zhou
35
0.81%
2
1.36%
Gao Feng
34
0.79%
1
0.68%
Hannes Frederic Sowa
32
0.74%
3
2.04%
Johannes Berg
29
0.67%
1
0.68%
Arnaldo Carvalho de Melo
22
0.51%
4
2.72%
Jorge Boncompte
22
0.51%
1
0.68%
Joe Perches
21
0.49%
5
3.40%
Eric W. Biedermann
21
0.49%
5
3.40%
Alexander Drozdov
19
0.44%
2
1.36%
Edward Hyunkoo Jee
15
0.35%
1
0.68%
Al Viro
15
0.35%
1
0.68%
Ian Morris
13
0.30%
2
1.36%
Octavian Purdila
10
0.23%
1
0.68%
Hideaki Yoshifuji / 吉藤英明
6
0.14%
2
1.36%
Yasuyuki Kozakai
5
0.12%
1
0.68%
David Howells
5
0.12%
1
0.68%
Joe Stringer
5
0.12%
1
0.68%
Phil Oester
4
0.09%
1
0.68%
Alexey Dobriyan
4
0.09%
1
0.68%
Tejun Heo
3
0.07%
1
0.68%
Ilpo Järvinen
3
0.07%
1
0.68%
Tom Herbert
3
0.07%
1
0.68%
Vasily Averin
2
0.05%
1
0.68%
Heikki Orsila
2
0.05%
1
0.68%
Fabian Frederick
2
0.05%
1
0.68%
Stephen Hemminger
1
0.02%
1
0.68%
Alan Cox
1
0.02%
1
0.68%
Pravin B Shelar
1
0.02%
1
0.68%
Harvey Harrison
1
0.02%
1
0.68%
David Ford
1
0.02%
1
0.68%
Jianjun Kong
1
0.02%
1
0.68%
Justin P. Mattock
1
0.02%
1
0.68%
Rusty Russell
1
0.02%
1
0.68%
Denis V. Lunev
1
0.02%
1
0.68%
Peter Zijlstra
1
0.02%
1
0.68%
Total
4315
100.00%
147
100.00%
Directory: net/ipv4

Information contained on this website is for historical information purposes only and does not indicate or represent copyright ownership.