linux/net/ipv6/reassembly.c

660 lines
16 KiB
C
Raw Normal View History

/*
* IPv6 fragment reassembly
* Linux INET6 implementation
*
* Authors:
* Pedro Roque <roque@di.fc.ul.pt>
*
* $Id: reassembly.c,v 1.26 2001/03/07 22:00:57 davem Exp $
*
* 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.
*/
/*
* Fixes:
* Andi Kleen Make it work with multiple hosts.
* More RFC compliance.
*
* Horst von Brand Add missing #include <linux/string.h>
* Alexey Kuznetsov SMP races, threading, cleanup.
* Patrick McHardy LRU queue of frag heads for evictor.
* Mitsuru KANDA @USAGI Register inet6_protocol{}.
* David Stevens and
* YOSHIFUJI,H. @USAGI Always remove fragment header to
* calculate ICV correctly.
*/
#include <linux/errno.h>
#include <linux/types.h>
#include <linux/string.h>
#include <linux/socket.h>
#include <linux/sockios.h>
#include <linux/jiffies.h>
#include <linux/net.h>
#include <linux/list.h>
#include <linux/netdevice.h>
#include <linux/in6.h>
#include <linux/ipv6.h>
#include <linux/icmpv6.h>
#include <linux/random.h>
#include <linux/jhash.h>
#include <linux/skbuff.h>
#include <net/sock.h>
#include <net/snmp.h>
#include <net/ipv6.h>
#include <net/ip6_route.h>
#include <net/protocol.h>
#include <net/transp_v6.h>
#include <net/rawv6.h>
#include <net/ndisc.h>
#include <net/addrconf.h>
#include <net/inet_frag.h>
struct ip6frag_skb_cb
{
struct inet6_skb_parm h;
int offset;
};
#define FRAG6_CB(skb) ((struct ip6frag_skb_cb*)((skb)->cb))
/*
* Equivalent of ipv4 struct ipq
*/
struct frag_queue
{
struct inet_frag_queue q;
__be32 id; /* fragment id */
struct in6_addr saddr;
struct in6_addr daddr;
int iif;
unsigned int csum;
__u16 nhoffset;
};
struct inet_frags_ctl ip6_frags_ctl __read_mostly = {
.high_thresh = 256 * 1024,
.low_thresh = 192 * 1024,
.timeout = IPV6_FRAG_TIMEOUT,
.secret_interval = 10 * 60 * HZ,
};
static struct inet_frags ip6_frags;
int ip6_frag_nqueues(void)
{
return ip6_frags.nqueues;
}
int ip6_frag_mem(void)
{
return atomic_read(&ip6_frags.mem);
}
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.
*/
static unsigned int ip6qhashfn(__be32 id, struct in6_addr *saddr,
struct in6_addr *daddr)
{
u32 a, b, c;
a = (__force u32)saddr->s6_addr32[0];
b = (__force u32)saddr->s6_addr32[1];
c = (__force u32)saddr->s6_addr32[2];
a += JHASH_GOLDEN_RATIO;
b += JHASH_GOLDEN_RATIO;
c += ip6_frags.rnd;
__jhash_mix(a, b, c);
a += (__force u32)saddr->s6_addr32[3];
b += (__force u32)daddr->s6_addr32[0];
c += (__force u32)daddr->s6_addr32[1];
__jhash_mix(a, b, c);
a += (__force u32)daddr->s6_addr32[2];
b += (__force u32)daddr->s6_addr32[3];
c += (__force u32)id;
__jhash_mix(a, b, c);
return c & (INETFRAGS_HASHSZ - 1);
}
static unsigned int ip6_hashfn(struct inet_frag_queue *q)
{
struct frag_queue *fq;
fq = container_of(q, struct frag_queue, q);
return ip6qhashfn(fq->id, &fq->saddr, &fq->daddr);
}
int ip6_frag_match(struct inet_frag_queue *q, void *a)
{
struct frag_queue *fq;
struct ip6_create_arg *arg = a;
fq = container_of(q, struct frag_queue, q);
return (fq->id == arg->id &&
ipv6_addr_equal(&fq->saddr, arg->src) &&
ipv6_addr_equal(&fq->daddr, arg->dst));
}
EXPORT_SYMBOL(ip6_frag_match);
/* Memory Tracking Functions. */
static inline void frag_kfree_skb(struct sk_buff *skb, int *work)
{
if (work)
*work -= skb->truesize;
atomic_sub(skb->truesize, &ip6_frags.mem);
kfree_skb(skb);
}
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;
ipv6_addr_copy(&fq->saddr, arg->src);
ipv6_addr_copy(&fq->daddr, arg->dst);
}
EXPORT_SYMBOL(ip6_frag_init);
/* Destruction primitives. */
static __inline__ void fq_put(struct frag_queue *fq)
{
inet_frag_put(&fq->q, &ip6_frags);
}
/* Kill fq entry. It is not destroyed immediately,
* because caller (and someone more) holds reference count.
*/
static __inline__ void fq_kill(struct frag_queue *fq)
{
inet_frag_kill(&fq->q, &ip6_frags);
}
static void ip6_evictor(struct inet6_dev *idev)
{
int evicted;
evicted = inet_frag_evictor(&ip6_frags);
if (evicted)
IP6_ADD_STATS_BH(idev, IPSTATS_MIB_REASMFAILS, evicted);
}
static void ip6_frag_expire(unsigned long data)
{
struct frag_queue *fq;
struct net_device *dev = NULL;
fq = container_of((struct inet_frag_queue *)data, struct frag_queue, q);
spin_lock(&fq->q.lock);
if (fq->q.last_in & COMPLETE)
goto out;
fq_kill(fq);
[NET]: Make the device list and device lookups per namespace. This patch makes most of the generic device layer network namespace safe. This patch makes dev_base_head a network namespace variable, and then it picks up a few associated variables. The functions: dev_getbyhwaddr dev_getfirsthwbytype dev_get_by_flags dev_get_by_name __dev_get_by_name dev_get_by_index __dev_get_by_index dev_ioctl dev_ethtool dev_load wireless_process_ioctl were modified to take a network namespace argument, and deal with it. vlan_ioctl_set and brioctl_set were modified so their hooks will receive a network namespace argument. So basically anthing in the core of the network stack that was affected to by the change of dev_base was modified to handle multiple network namespaces. The rest of the network stack was simply modified to explicitly use &init_net the initial network namespace. This can be fixed when those components of the network stack are modified to handle multiple network namespaces. For now the ifindex generator is left global. Fundametally ifindex numbers are per namespace, or else we will have corner case problems with migration when we get that far. At the same time there are assumptions in the network stack that the ifindex of a network device won't change. Making the ifindex number global seems a good compromise until the network stack can cope with ifindex changes when you change namespaces, and the like. Signed-off-by: Eric W. Biederman <ebiederm@xmission.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2007-09-17 18:56:21 +00:00
dev = dev_get_by_index(&init_net, fq->iif);
if (!dev)
goto out;
rcu_read_lock();
IP6_INC_STATS_BH(__in6_dev_get(dev), IPSTATS_MIB_REASMTIMEOUT);
IP6_INC_STATS_BH(__in6_dev_get(dev), IPSTATS_MIB_REASMFAILS);
rcu_read_unlock();
/* Don't send error if the first segment did not arrive. */
if (!(fq->q.last_in&FIRST_IN) || !fq->q.fragments)
goto out;
/*
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, dev);
out:
if (dev)
dev_put(dev);
spin_unlock(&fq->q.lock);
fq_put(fq);
}
static __inline__ struct frag_queue *
fq_find(__be32 id, struct in6_addr *src, struct in6_addr *dst,
struct inet6_dev *idev)
{
struct inet_frag_queue *q;
struct ip6_create_arg arg;
unsigned int hash;
arg.id = id;
arg.src = src;
arg.dst = dst;
hash = ip6qhashfn(id, src, dst);
q = inet_frag_find(&ip6_frags, &arg, hash);
if (q == NULL)
goto oom;
return container_of(q, struct frag_queue, q);
oom:
IP6_INC_STATS_BH(idev, IPSTATS_MIB_REASMFAILS);
return NULL;
}
static int ip6_frag_queue(struct frag_queue *fq, struct sk_buff *skb,
struct frag_hdr *fhdr, int nhoff)
{
struct sk_buff *prev, *next;
struct net_device *dev;
int offset, end;
if (fq->q.last_in & COMPLETE)
goto err;
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(ip6_dst_idev(skb->dst),
IPSTATS_MIB_INHDRERRORS);
icmpv6_param_prob(skb, ICMPV6_HDR_FIELD,
((u8 *)&fhdr->frag_off -
skb_network_header(skb)));
return -1;
}
if (skb->ip_summed == CHECKSUM_COMPLETE) {
const unsigned char *nh = skb_network_header(skb);
skb->csum = csum_sub(skb->csum,
csum_partial(nh, (u8 *)(fhdr + 1) - nh,
0));
}
/* Is this the final fragment? */
if (!(fhdr->frag_off & htons(IP6_MF))) {
/* If we already have some bits beyond end
* or have different end, the segment is corrupted.
*/
if (end < fq->q.len ||
((fq->q.last_in & LAST_IN) && end != fq->q.len))
goto err;
fq->q.last_in |= LAST_IN;
fq->q.len = end;
} else {
/* Check if the fragment is rounded to 8 bytes.
* Required by the RFC.
*/
if (end & 0x7) {
/* RFC2460 says always send parameter problem in
* this case. -DaveM
*/
IP6_INC_STATS_BH(ip6_dst_idev(skb->dst),
IPSTATS_MIB_INHDRERRORS);
icmpv6_param_prob(skb, ICMPV6_HDR_FIELD,
offsetof(struct ipv6hdr, payload_len));
return -1;
}
if (end > fq->q.len) {
/* Some bits beyond end -> corruption. */
if (fq->q.last_in & LAST_IN)
goto err;
fq->q.len = end;
}
}
if (end == offset)
goto err;
/* 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 = NULL;
for(next = fq->q.fragments; next != NULL; next = next->next) {
if (FRAG6_CB(next)->offset >= offset)
break; /* bingo! */
prev = next;
}
/* 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 = (FRAG6_CB(prev)->offset + prev->len) - offset;
if (i > 0) {
offset += i;
if (end <= offset)
goto err;
if (!pskb_pull(skb, i))
goto err;
if (skb->ip_summed != CHECKSUM_UNNECESSARY)
skb->ip_summed = CHECKSUM_NONE;
}
}
/* Look for overlap with succeeding segments.
* If we can merge fragments, do it.
*/
while (next && FRAG6_CB(next)->offset < end) {
int i = end - FRAG6_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;
FRAG6_CB(next)->offset += i; /* next fragment */
fq->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
fq->q.fragments = next;
fq->q.meat -= free_it->len;
frag_kfree_skb(free_it, NULL);
}
}
FRAG6_CB(skb)->offset = offset;
/* Insert this fragment in the chain of fragments. */
skb->next = next;
if (prev)
prev->next = skb;
else
fq->q.fragments = skb;
dev = skb->dev;
if (dev) {
fq->iif = dev->ifindex;
skb->dev = NULL;
}
fq->q.stamp = skb->tstamp;
fq->q.meat += skb->len;
atomic_add(skb->truesize, &ip6_frags.mem);
/* The first fragment.
* nhoffset is obtained from the first fragment, of course.
*/
if (offset == 0) {
fq->nhoffset = nhoff;
fq->q.last_in |= FIRST_IN;
}
if (fq->q.last_in == (FIRST_IN | LAST_IN) && fq->q.meat == fq->q.len)
return ip6_frag_reasm(fq, prev, dev);
write_lock(&ip6_frags.lock);
list_move_tail(&fq->q.lru_list, &ip6_frags.lru_list);
write_unlock(&ip6_frags.lock);
return -1;
err:
IP6_INC_STATS(ip6_dst_idev(skb->dst), IPSTATS_MIB_REASMFAILS);
kfree_skb(skb);
return -1;
}
/*
* 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)
{
struct sk_buff *fp, *head = fq->q.fragments;
int payload_len;
unsigned int nhoff;
fq_kill(fq);
/* 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;
prev->next = fp;
skb_morph(head, fq->q.fragments);
head->next = fq->q.fragments->next;
kfree_skb(fq->q.fragments);
fq->q.fragments = head;
}
BUG_TRAP(head != NULL);
BUG_TRAP(FRAG6_CB(head)->offset == 0);
/* Unfragmented part is taken from the first segment. */
payload_len = ((head->data - skb_network_header(head)) -
sizeof(struct ipv6hdr) + fq->q.len -
sizeof(struct frag_hdr));
if (payload_len > IPV6_MAXPLEN)
goto out_oversize;
/* Head of list must not be cloned. */
if (skb_cloned(head) && pskb_expand_head(head, 0, 0, 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_shinfo(head)->frag_list) {
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_shinfo(head)->frag_list = NULL;
for (i=0; i<skb_shinfo(head)->nr_frags; i++)
plen += skb_shinfo(head)->frags[i].size;
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;
atomic_add(clone->truesize, &ip6_frags.mem);
}
/* 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_shinfo(head)->frag_list = head->next;
skb_reset_transport_header(head);
skb_push(head, head->data - skb_network_header(head));
atomic_sub(head->truesize, &ip6_frags.mem);
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;
atomic_sub(fp->truesize, &ip6_frags.mem);
}
head->next = NULL;
head->dev = dev;
head->tstamp = fq->q.stamp;
ipv6_hdr(head)->payload_len = htons(payload_len);
IP6CB(head)->nhoff = nhoff;
/* 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);
rcu_read_lock();
IP6_INC_STATS_BH(__in6_dev_get(dev), IPSTATS_MIB_REASMOKS);
rcu_read_unlock();
fq->q.fragments = NULL;
return 1;
out_oversize:
if (net_ratelimit())
printk(KERN_DEBUG "ip6_frag_reasm: payload len = %d\n", payload_len);
goto out_fail;
out_oom:
if (net_ratelimit())
printk(KERN_DEBUG "ip6_frag_reasm: no memory for reassembly\n");
out_fail:
rcu_read_lock();
IP6_INC_STATS_BH(__in6_dev_get(dev), IPSTATS_MIB_REASMFAILS);
rcu_read_unlock();
return -1;
}
static int ipv6_frag_rcv(struct sk_buff *skb)
{
struct frag_hdr *fhdr;
struct frag_queue *fq;
struct ipv6hdr *hdr = ipv6_hdr(skb);
IP6_INC_STATS_BH(ip6_dst_idev(skb->dst), IPSTATS_MIB_REASMREQDS);
/* Jumbo payload inhibits frag. header */
if (hdr->payload_len==0) {
IP6_INC_STATS(ip6_dst_idev(skb->dst), IPSTATS_MIB_INHDRERRORS);
icmpv6_param_prob(skb, ICMPV6_HDR_FIELD,
skb_network_header_len(skb));
return -1;
}
if (!pskb_may_pull(skb, (skb_transport_offset(skb) +
sizeof(struct frag_hdr)))) {
IP6_INC_STATS(ip6_dst_idev(skb->dst), IPSTATS_MIB_INHDRERRORS);
icmpv6_param_prob(skb, ICMPV6_HDR_FIELD,
skb_network_header_len(skb));
return -1;
}
hdr = ipv6_hdr(skb);
fhdr = (struct frag_hdr *)skb_transport_header(skb);
if (!(fhdr->frag_off & htons(0xFFF9))) {
/* It is not a fragmented frame */
skb->transport_header += sizeof(struct frag_hdr);
IP6_INC_STATS_BH(ip6_dst_idev(skb->dst), IPSTATS_MIB_REASMOKS);
IP6CB(skb)->nhoff = (u8 *)fhdr - skb_network_header(skb);
return 1;
}
if (atomic_read(&ip6_frags.mem) > ip6_frags_ctl.high_thresh)
ip6_evictor(ip6_dst_idev(skb->dst));
if ((fq = fq_find(fhdr->identification, &hdr->saddr, &hdr->daddr,
ip6_dst_idev(skb->dst))) != NULL) {
int ret;
spin_lock(&fq->q.lock);
ret = ip6_frag_queue(fq, skb, fhdr, IP6CB(skb)->nhoff);
spin_unlock(&fq->q.lock);
fq_put(fq);
return ret;
}
IP6_INC_STATS_BH(ip6_dst_idev(skb->dst), IPSTATS_MIB_REASMFAILS);
kfree_skb(skb);
return -1;
}
static struct inet6_protocol frag_protocol =
{
.handler = ipv6_frag_rcv,
.flags = INET6_PROTO_NOPOLICY,
};
int __init ipv6_frag_init(void)
{
int ret;
ret = inet6_add_protocol(&frag_protocol, IPPROTO_FRAGMENT);
if (ret)
goto out;
ip6_frags.ctl = &ip6_frags_ctl;
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;
inet_frags_init(&ip6_frags);
out:
return ret;
}
void ipv6_frag_exit(void)
{
inet_frags_fini(&ip6_frags);
inet6_del_protocol(&frag_protocol, IPPROTO_FRAGMENT);
}