cregit-Linux how code gets into the kernel

Release 4.11 net/ipv4/ip_fragment.c

Directory: net/ipv4
/*
 * 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
PersonTokensPropCommitsCommitProp
Eric Dumazet18100.00%2100.00%


Total18100.00%2100.00%




static struct inet_frags ip4_frags;




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


Contributors
PersonTokensPropCommitsCommitProp
Pavel Emelyanov2095.24%266.67%


Jesper Dangaard Brouer14.76%133.33%


Total21100.00%3100.00%



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
PersonTokensPropCommitsCommitProp
Linus Torvalds (pre-git)2132.81%233.33%


Hannes Frederic Sowa1523.44%116.67%


David S. Miller1320.31%116.67%


Al Viro1218.75%116.67%


Pavel Emelyanov34.69%116.67%


Total64100.00%6100.00%






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
PersonTokensPropCommitsCommitProp
David S. Miller2345.10%125.00%


Pavel Emelyanov2141.18%125.00%


Yasuyuki Kozakai59.80%125.00%


Florian Westphal23.92%125.00%


Total51100.00%4100.00%






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
PersonTokensPropCommitsCommitProp
Pavel Emelyanov8787.00%125.00%


David Ahern88.00%125.00%


Florian Westphal44.00%125.00%


Eric Dumazet11.00%125.00%


Total100100.00%4100.00%






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
PersonTokensPropCommitsCommitProp
Pavel Emelyanov10258.96%111.11%


Gao Feng3419.65%111.11%


Eric Dumazet137.51%111.11%


David Ahern126.94%222.22%


Nikolay Borisov52.89%111.11%


David S. Miller52.89%222.22%


Florian Westphal21.16%111.11%


Total173100.00%9100.00%






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
PersonTokensPropCommitsCommitProp
Pavel Emelyanov2560.98%120.00%


Linus Torvalds (pre-git)921.95%240.00%


David S. Miller614.63%120.00%


Linus Torvalds12.44%120.00%


Total41100.00%5100.00%



/* Destruction primitives. */




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


Contributors
PersonTokensPropCommitsCommitProp
Linus Torvalds (pre-git)1463.64%240.00%


Pavel Emelyanov836.36%360.00%


Total22100.00%5100.00%



/* 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
PersonTokensPropCommitsCommitProp
Linus Torvalds (pre-git)1881.82%250.00%


Pavel Emelyanov418.18%250.00%


Total22100.00%4100.00%






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
PersonTokensPropCommitsCommitProp
Andy Zhou32100.00%2100.00%


Total32100.00%2100.00%



/*
 * 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
PersonTokensPropCommitsCommitProp
Linus Torvalds (pre-git)9530.55%724.14%


Eric Dumazet7323.47%517.24%


Shan Wei4815.43%13.45%


Pavel Emelyanov4715.11%413.79%


Nikolay Aleksandrov3611.58%310.34%


Andy Zhou30.96%13.45%


Vasily Averin20.64%13.45%


David S. Miller20.64%26.90%


Denis V. Lunev10.32%13.45%


Eric W. Biedermann10.32%13.45%


Joe Perches10.32%13.45%


Patrick McHardy10.32%13.45%


Hideaki Yoshifuji / 吉藤英明10.32%13.45%


Total311100.00%29100.00%



/* 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
PersonTokensPropCommitsCommitProp
Pavel Emelyanov6752.76%436.36%


Linus Torvalds (pre-git)2318.11%327.27%


Hannes Frederic Sowa1612.60%19.09%


David Ahern97.09%19.09%


Patrick McHardy75.51%19.09%


Herbert Xu53.94%19.09%


Total127100.00%11100.00%



/* 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
PersonTokensPropCommitsCommitProp
Herbert Xu9472.87%120.00%


Pavel Emelyanov2720.93%240.00%


Nikolay Borisov75.43%120.00%


Eric Dumazet10.78%120.00%


Total129100.00%5100.00%






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
PersonTokensPropCommitsCommitProp
Herbert Xu10663.47%110.00%


Jesper Dangaard Brouer2213.17%110.00%


Pavel Emelyanov2213.17%440.00%


Changli Gao84.79%110.00%


Eric Dumazet63.59%110.00%


Florian Westphal21.20%110.00%


Nikolay Aleksandrov10.60%110.00%


Total167100.00%10100.00%



/* 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
PersonTokensPropCommitsCommitProp
Linus Torvalds (pre-git)50154.16%1336.11%


Herbert Xu12613.62%25.56%


Eric Dumazet576.16%38.33%


Pavel Emelyanov485.19%25.56%


Changli Gao464.97%12.78%


Linus Torvalds414.43%12.78%


Florian Westphal384.11%25.56%


Patrick McHardy232.49%25.56%


Jesper Dangaard Brouer121.30%12.78%


Edward Hyunkoo Jee101.08%12.78%


Joe Perches70.76%12.78%


Nikolay Aleksandrov60.65%12.78%


Arnaldo Carvalho de Melo60.65%25.56%


Justin P. Mattock10.11%12.78%


Stephen Hemminger10.11%12.78%


Peter Zijlstra10.11%12.78%


Ian Morris10.11%12.78%


Total925100.00%36100.00%



/* 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->