/*
* 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);
}
static struct inet_frags ip4_frags;
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;
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);
}
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);
}
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;
}
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;
}
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);
}
/* Destruction primitives. */
static void ipq_put(struct ipq *ipq)
{
inet_frag_put(