int ipv6_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev)
{
const struct ipv6hdr *hdr;
u32 pkt_len;
struct inet6_dev *idev;
struct net *net = dev_net(skb->dev);
if (skb->pkt_type == PACKET_OTHERHOST) {
kfree_skb(skb);
return NET_RX_DROP;
}
rcu_read_lock();
idev = __in6_dev_get(skb->dev);
IP6_UPD_PO_STATS_BH(net, idev, IPSTATS_MIB_IN, skb->len);
if ((skb = skb_share_check(skb, GFP_ATOMIC)) == NULL ||
!idev || unlikely(idev->cnf.disable_ipv6)) {
IP6_INC_STATS_BH(net, idev, IPSTATS_MIB_INDISCARDS);
goto drop;
}
memset(IP6CB(skb), 0, sizeof(struct inet6_skb_parm));
/*
* Store incoming device index. When the packet will
* be queued, we cannot refer to skb->dev anymore.
*
* BTW, when we send a packet for our own local address on a
* non-loopback interface (e.g. ethX), it is being delivered
* via the loopback interface (lo) here; skb->dev = loopback_dev.
* It, however, should be considered as if it is being
* arrived via the sending interface (ethX), because of the
* nature of scoping architecture. --yoshfuji
*/
IP6CB(skb)->iif = skb_dst(skb) ? ip6_dst_idev(skb_dst(skb))->dev->ifindex : dev->ifindex;
if (unlikely(!pskb_may_pull(skb, sizeof(*hdr))))
goto err;
hdr = ipv6_hdr(skb);
if (hdr->version != 6)
goto err;
/*
* RFC4291 2.5.3
* A packet received on an interface with a destination address
* of loopback must be dropped.
*/
if (!(dev->flags & IFF_LOOPBACK) &&
ipv6_addr_loopback(&hdr->daddr))
goto err;
/* RFC4291 2.7
* Nodes must not originate a packet to a multicast address whose scope
* field contains the reserved value 0; if such a packet is received, it
* must be silently dropped.
*/
if (ipv6_addr_is_multicast(&hdr->daddr) &&
IPV6_ADDR_MC_SCOPE(&hdr->daddr) == 0)
goto err;
/*
* RFC4291 2.7
* Multicast addresses must not be used as source addresses in IPv6
* packets or appear in any Routing header.
*/
if (ipv6_addr_is_multicast(&hdr->saddr))
goto err;
skb->transport_header = skb->network_header + sizeof(*hdr);
IP6CB(skb)->nhoff = offsetof(struct ipv6hdr, nexthdr);
pkt_len = ntohs(hdr->payload_len);
/* pkt_len may be zero if Jumbo payload option is present */
if (pkt_len || hdr->nexthdr != NEXTHDR_HOP) {
if (pkt_len + sizeof(struct ipv6hdr) > skb->len) {
IP6_INC_STATS_BH(net,
idev, IPSTATS_MIB_INTRUNCATEDPKTS);
goto drop;
}
if (pskb_trim_rcsum(skb, pkt_len + sizeof(struct ipv6hdr))) {
IP6_INC_STATS_BH(net, idev, IPSTATS_MIB_INHDRERRORS);
goto drop;
}
hdr = ipv6_hdr(skb);
}
if (hdr->nexthdr == NEXTHDR_HOP) {
if (ipv6_parse_hopopts(skb) < 0) {
IP6_INC_STATS_BH(net, idev, IPSTATS_MIB_INHDRERRORS);
rcu_read_unlock();
return NET_RX_DROP;
}
}
rcu_read_unlock();
/* Must drop socket now because of tproxy. */
skb_orphan(skb);
return NF_HOOK(NFPROTO_IPV6, NF_INET_PRE_ROUTING, skb, dev, NULL,
ip6_rcv_finish);
err:
IP6_INC_STATS_BH(net, idev, IPSTATS_MIB_INHDRERRORS);
drop:
rcu_read_unlock();
kfree_skb(skb);
return NET_RX_DROP;
}
int ipv6_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt)
{
struct ipv6hdr *hdr;
u32 pkt_len;
if (skb->pkt_type == PACKET_OTHERHOST)
goto drop;
IP6_INC_STATS_BH(IPSTATS_MIB_INRECEIVES);
if ((skb = skb_share_check(skb, GFP_ATOMIC)) == NULL) {
IP6_INC_STATS_BH(IPSTATS_MIB_INDISCARDS);
goto out;
}
/*
* Store incoming device index. When the packet will
* be queued, we cannot refer to skb->dev anymore.
*
* BTW, when we send a packet for our own local address on a
* non-loopback interface (e.g. ethX), it is being delivered
* via the loopback interface (lo) here; skb->dev = &loopback_dev.
* It, however, should be considered as if it is being
* arrived via the sending interface (ethX), because of the
* nature of scoping architecture. --yoshfuji
*/
IP6CB(skb)->iif = skb->dst ? ((struct rt6_info *)skb->dst)->rt6i_idev->dev->ifindex : dev->ifindex;
if (skb->len < sizeof(struct ipv6hdr))
goto err;
if (!pskb_may_pull(skb, sizeof(struct ipv6hdr))) {
IP6_INC_STATS_BH(IPSTATS_MIB_INHDRERRORS);
goto drop;
}
hdr = skb->nh.ipv6h;
if (hdr->version != 6)
goto err;
pkt_len = ntohs(hdr->payload_len);
/* pkt_len may be zero if Jumbo payload option is present */
if (pkt_len || hdr->nexthdr != NEXTHDR_HOP) {
if (pkt_len + sizeof(struct ipv6hdr) > skb->len)
goto truncated;
if (pskb_trim_rcsum(skb, pkt_len + sizeof(struct ipv6hdr))) {
IP6_INC_STATS_BH(IPSTATS_MIB_INHDRERRORS);
goto drop;
}
hdr = skb->nh.ipv6h;
}
if (hdr->nexthdr == NEXTHDR_HOP) {
skb->h.raw = (u8*)(hdr+1);
if (ipv6_parse_hopopts(skb, offsetof(struct ipv6hdr, nexthdr)) < 0) {
IP6_INC_STATS_BH(IPSTATS_MIB_INHDRERRORS);
return 0;
}
hdr = skb->nh.ipv6h;
}
static inline int ip6_input_finish(struct sk_buff *skb)
{
struct inet6_protocol *ipprot;
struct sock *raw_sk;
unsigned int nhoff;
int nexthdr;
u8 hash;
struct inet6_dev *idev;
/*
* Parse extension headers
*/
rcu_read_lock();
resubmit:
idev = ip6_dst_idev(skb->dst);
if (!pskb_pull(skb, skb->h.raw - skb->data))
goto discard;
nhoff = IP6CB(skb)->nhoff;
nexthdr = skb->nh.raw[nhoff];
raw_sk = sk_head(&raw_v6_htable[nexthdr & (MAX_INET_PROTOS - 1)]);
if (raw_sk && !ipv6_raw_deliver(skb, nexthdr))
raw_sk = NULL;
hash = nexthdr & (MAX_INET_PROTOS - 1);
if ((ipprot = rcu_dereference(inet6_protos[hash])) != NULL) {
int ret;
if (ipprot->flags & INET6_PROTO_FINAL) {
struct ipv6hdr *hdr;
/* Free reference early: we don't need it any more,
and it may hold ip_conntrack module loaded
indefinitely. */
nf_reset(skb);
skb_postpull_rcsum(skb, skb->nh.raw,
skb->h.raw - skb->nh.raw);
hdr = skb->nh.ipv6h;
if (ipv6_addr_is_multicast(&hdr->daddr) &&
!ipv6_chk_mcast_addr(skb->dev, &hdr->daddr,
&hdr->saddr) &&
!ipv6_is_mld(skb, nexthdr))
goto discard;
}
if (!(ipprot->flags & INET6_PROTO_NOPOLICY) &&
!xfrm6_policy_check(NULL, XFRM_POLICY_IN, skb))
goto discard;
ret = ipprot->handler(&skb);
if (ret > 0)
goto resubmit;
else if (ret == 0)
IP6_INC_STATS_BH(idev, IPSTATS_MIB_INDELIVERS);
} else {
if (!raw_sk) {
if (xfrm6_policy_check(NULL, XFRM_POLICY_IN, skb)) {
IP6_INC_STATS_BH(idev, IPSTATS_MIB_INUNKNOWNPROTOS);
icmpv6_send(skb, ICMPV6_PARAMPROB,
ICMPV6_UNK_NEXTHDR, nhoff,
skb->dev);
}
} else
IP6_INC_STATS_BH(idev, IPSTATS_MIB_INDELIVERS);
kfree_skb(skb);
}
rcu_read_unlock();
return 0;
discard:
IP6_INC_STATS_BH(idev, IPSTATS_MIB_INDISCARDS);
rcu_read_unlock();
kfree_skb(skb);
return 0;
}
static int ip6_finish_output2(struct sk_buff *skb)
{
struct dst_entry *dst = skb_dst(skb);
struct net_device *dev = dst->dev;
struct neighbour *neigh;
int res;
skb->protocol = htons(ETH_P_IPV6);
skb->dev = dev;
if (ipv6_addr_is_multicast(&ipv6_hdr(skb)->daddr)) {
struct inet6_dev *idev = ip6_dst_idev(skb_dst(skb));
if (!(dev->flags & IFF_LOOPBACK) && sk_mc_loop(skb->sk) &&
((mroute6_socket(dev_net(dev), skb) &&
!(IP6CB(skb)->flags & IP6SKB_FORWARDED)) ||
ipv6_chk_mcast_addr(dev, &ipv6_hdr(skb)->daddr,
&ipv6_hdr(skb)->saddr))) {
struct sk_buff *newskb = skb_clone(skb, GFP_ATOMIC);
/* Do not check for IFF_ALLMULTI; multicast routing
is not supported in any case.
*/
if (newskb)
NF_HOOK(NFPROTO_IPV6, NF_INET_POST_ROUTING,
newskb, NULL, newskb->dev,
ip6_dev_loopback_xmit);
if (ipv6_hdr(skb)->hop_limit == 0) {
IP6_INC_STATS(dev_net(dev), idev,
IPSTATS_MIB_OUTDISCARDS);
kfree_skb(skb);
return 0;
}
}
IP6_UPD_PO_STATS(dev_net(dev), idev, IPSTATS_MIB_OUTMCAST,
skb->len);
}
rcu_read_lock();
if (dst->hh) {
res = neigh_hh_output(dst->hh, skb);
rcu_read_unlock();
return res;
} else {
neigh = dst_get_neighbour(dst);
if (neigh) {
res = neigh->output(skb);
rcu_read_unlock();
return res;
}
rcu_read_unlock();
}
IP6_INC_STATS_BH(dev_net(dst->dev),
ip6_dst_idev(dst), IPSTATS_MIB_OUTNOROUTES);
kfree_skb(skb);
return -EINVAL;
}
int ip6_forward(struct sk_buff *skb)
{
struct dst_entry *dst = skb->dst;
struct ipv6hdr *hdr = skb->nh.ipv6h;
struct inet6_skb_parm *opt = IP6CB(skb);
if (ipv6_devconf.forwarding == 0)
goto error;
if (skb_warn_if_lro(skb))
goto drop;
if (!xfrm6_policy_check(NULL, XFRM_POLICY_FWD, skb)) {
IP6_INC_STATS(ip6_dst_idev(dst), IPSTATS_MIB_INDISCARDS);
goto drop;
}
skb->ip_summed = CHECKSUM_NONE;
/*
* We DO NOT make any processing on
* RA packets, pushing them to user level AS IS
* without ane WARRANTY that application will be able
* to interpret them. The reason is that we
* cannot make anything clever here.
*
* We are not end-node, so that if packet contains
* AH/ESP, we cannot make anything.
* Defragmentation also would be mistake, RA packets
* cannot be fragmented, because there is no warranty
* that different fragments will go along one path. --ANK
*/
if (opt->ra) {
u8 *ptr = skb->nh.raw + opt->ra;
if (ip6_call_ra_chain(skb, (ptr[2]<<8) + ptr[3]))
return 0;
}
/*
* check and decrement ttl
*/
if (hdr->hop_limit <= 1) {
/* Force OUTPUT device used as source address */
skb->dev = dst->dev;
icmpv6_send(skb, ICMPV6_TIME_EXCEED, ICMPV6_EXC_HOPLIMIT,
0, skb->dev);
IP6_INC_STATS_BH(ip6_dst_idev(dst), IPSTATS_MIB_INHDRERRORS);
kfree_skb(skb);
return -ETIMEDOUT;
}
if (!xfrm6_route_forward(skb)) {
IP6_INC_STATS(ip6_dst_idev(dst), IPSTATS_MIB_INDISCARDS);
goto drop;
}
dst = skb->dst;
/* IPv6 specs say nothing about it, but it is clear that we cannot
send redirects to source routed frames.
*/
if (skb->dev == dst->dev && dst->neighbour && opt->srcrt == 0) {
struct in6_addr *target = NULL;
struct rt6_info *rt;
struct neighbour *n = dst->neighbour;
/*
* incoming and outgoing devices are the same
* send a redirect.
*/
rt = (struct rt6_info *) dst;
if ((rt->rt6i_flags & RTF_GATEWAY))
target = (struct in6_addr*)&n->primary_key;
else
target = &hdr->daddr;
/* Limit redirects both by destination (here)
and by source (inside ndisc_send_redirect)
*/
if (xrlim_allow(dst, 1*HZ))
ndisc_send_redirect(skb, n, target);
} else {
int addrtype = ipv6_addr_type(&hdr->saddr);
/* This check is security critical. */
if (addrtype == IPV6_ADDR_ANY ||
addrtype & (IPV6_ADDR_MULTICAST | IPV6_ADDR_LOOPBACK))
goto error;
if (addrtype & IPV6_ADDR_LINKLOCAL) {
icmpv6_send(skb, ICMPV6_DEST_UNREACH,
ICMPV6_NOT_NEIGHBOUR, 0, skb->dev);
goto error;
}
}
if (skb->len > dst_mtu(dst)) {
/* Again, force OUTPUT device used as source address */
skb->dev = dst->dev;
icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, dst_mtu(dst), skb->dev);
IP6_INC_STATS_BH(ip6_dst_idev(dst), IPSTATS_MIB_INTOOBIGERRORS);
IP6_INC_STATS_BH(ip6_dst_idev(dst), IPSTATS_MIB_FRAGFAILS);
kfree_skb(skb);
return -EMSGSIZE;
}
if (skb_cow(skb, dst->dev->hard_header_len)) {
IP6_INC_STATS(ip6_dst_idev(dst), IPSTATS_MIB_OUTDISCARDS);
goto drop;
}
hdr = skb->nh.ipv6h;
/* Mangling hops number delayed to point after skb COW */
hdr->hop_limit--;
IP6_INC_STATS_BH(ip6_dst_idev(dst), IPSTATS_MIB_OUTFORWDATAGRAMS);
return NF_HOOK(PF_INET6,NF_IP6_FORWARD, skb, skb->dev, dst->dev, ip6_forward_finish);
error:
IP6_INC_STATS_BH(ip6_dst_idev(dst), IPSTATS_MIB_INADDRERRORS);
drop:
kfree_skb(skb);
return -EINVAL;
}
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;
struct net *net = dev_net(skb_dst(skb)->dev);
if (fq->q.last_in & INET_FRAG_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(net, ip6_dst_idev(skb_dst(skb)),
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 & INET_FRAG_LAST_IN) && end != fq->q.len))
goto err;
fq->q.last_in |= INET_FRAG_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(net, ip6_dst_idev(skb_dst(skb)),
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 & INET_FRAG_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 = fq->q.fragments_tail;
if (!prev || FRAG6_CB(prev)->offset < offset) {
next = NULL;
goto found;
}
prev = NULL;
for(next = fq->q.fragments; next != NULL; next = next->next) {
if (FRAG6_CB(next)->offset >= offset)
break; /* bingo! */
prev = next;
}
found:
/* RFC5722, Section 4, amended by Errata ID : 3089
* When reassembling an IPv6 datagram, if
* one or more its constituent fragments is determined to be an
* overlapping fragment, the entire datagram (and any constituent
* fragments) MUST be silently discarded.
*/
/* Check for overlap with preceding fragment. */
if (prev &&
(FRAG6_CB(prev)->offset + prev->len) > offset)
goto discard_fq;
/* Look for overlap with succeeding segment. */
if (next && FRAG6_CB(next)->offset < end)
goto discard_fq;
FRAG6_CB(skb)->offset = offset;
/* Insert this fragment in the chain of fragments. */
skb->next = next;
if (!next)
fq->q.fragments_tail = skb;
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, &fq->q.net->mem);
/* The first fragment.
* nhoffset is obtained from the first fragment, of course.
*/
if (offset == 0) {
fq->nhoffset = nhoff;
fq->q.last_in |= INET_FRAG_FIRST_IN;
}
if (fq->q.last_in == (INET_FRAG_FIRST_IN | INET_FRAG_LAST_IN) &&
fq->q.meat == fq->q.len) {
int res;
unsigned long orefdst = skb->_skb_refdst;
skb->_skb_refdst = 0UL;
res = ip6_frag_reasm(fq, prev, dev);
skb->_skb_refdst = orefdst;
return res;
}
skb_dst_drop(skb);
write_lock(&ip6_frags.lock);
list_move_tail(&fq->q.lru_list, &fq->q.net->lru_list);
write_unlock(&ip6_frags.lock);
return -1;
discard_fq:
fq_kill(fq);
err:
IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)),
IPSTATS_MIB_REASMFAILS);
kfree_skb(skb);
return -1;
}
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;
struct net *net = dev_net(skb_dst(skb)->dev);
if (fq->q.last_in & INET_FRAG_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(net, ip6_dst_idev(skb_dst(skb)),
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));
}
if (!(fhdr->frag_off & htons(IP6_MF))) {
if (end < fq->q.len ||
((fq->q.last_in & INET_FRAG_LAST_IN) && end != fq->q.len))
goto err;
fq->q.last_in |= INET_FRAG_LAST_IN;
fq->q.len = end;
} else {
if (end & 0x7) {
IP6_INC_STATS_BH(net, ip6_dst_idev(skb_dst(skb)),
IPSTATS_MIB_INHDRERRORS);
icmpv6_param_prob(skb, ICMPV6_HDR_FIELD,
offsetof(struct ipv6hdr, payload_len));
return -1;
}
if (end > fq->q.len) {
if (fq->q.last_in & INET_FRAG_LAST_IN)
goto err;
fq->q.len = end;
}
}
if (end == offset)
goto err;
if (!pskb_pull(skb, (u8 *) (fhdr + 1) - skb->data))
goto err;
if (pskb_trim_rcsum(skb, end - offset))
goto err;
prev = fq->q.fragments_tail;
if (!prev || FRAG6_CB(prev)->offset < offset) {
next = NULL;
goto found;
}
prev = NULL;
for(next = fq->q.fragments; next != NULL; next = next->next) {
if (FRAG6_CB(next)->offset >= offset)
break;
prev = next;
}
found:
if (prev &&
(FRAG6_CB(prev)->offset + prev->len) > offset)
goto discard_fq;
if (next && FRAG6_CB(next)->offset < end)
goto discard_fq;
FRAG6_CB(skb)->offset = offset;
skb->next = next;
if (!next)
fq->q.fragments_tail = skb;
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, &fq->q.net->mem);
if (offset == 0) {
fq->nhoffset = nhoff;
fq->q.last_in |= INET_FRAG_FIRST_IN;
}
if (fq->q.last_in == (INET_FRAG_FIRST_IN | INET_FRAG_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, &fq->q.net->lru_list);
write_unlock(&ip6_frags.lock);
return -1;
discard_fq:
fq_kill(fq);
err:
IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)),
IPSTATS_MIB_REASMFAILS);
kfree_skb(skb);
return -1;
}
int ip6_forward(struct sk_buff *skb)
{
struct dst_entry *dst = skb_dst(skb);
struct ipv6hdr *hdr = ipv6_hdr(skb);
struct inet6_skb_parm *opt = IP6CB(skb);
struct net *net = dev_net(dst->dev);
if (net->ipv6.devconf_all->forwarding == 0)
goto error;
if (skb_warn_if_lro(skb))
goto drop;
if (!xfrm6_policy_check(NULL, XFRM_POLICY_FWD, skb)) {
IP6_INC_STATS(net, ip6_dst_idev(dst), IPSTATS_MIB_INDISCARDS);
goto drop;
}
if (skb->pkt_type != PACKET_HOST)
goto drop;
skb_forward_csum(skb);
/*
* We DO NOT make any processing on
* RA packets, pushing them to user level AS IS
* without ane WARRANTY that application will be able
* to interpret them. The reason is that we
* cannot make anything clever here.
*
* We are not end-node, so that if packet contains
* AH/ESP, we cannot make anything.
* Defragmentation also would be mistake, RA packets
* cannot be fragmented, because there is no warranty
* that different fragments will go along one path. --ANK
*/
if (opt->ra) {
u8 *ptr = skb_network_header(skb) + opt->ra;
if (ip6_call_ra_chain(skb, (ptr[2]<<8) + ptr[3]))
return 0;
}
/*
* check and decrement ttl
*/
if (hdr->hop_limit <= 1) {
/* Force OUTPUT device used as source address */
skb->dev = dst->dev;
icmpv6_send(skb, ICMPV6_TIME_EXCEED, ICMPV6_EXC_HOPLIMIT,
0, skb->dev);
IP6_INC_STATS_BH(net,
ip6_dst_idev(dst), IPSTATS_MIB_INHDRERRORS);
kfree_skb(skb);
return -ETIMEDOUT;
}
/* XXX: idev->cnf.proxy_ndp? */
if (net->ipv6.devconf_all->proxy_ndp &&
pneigh_lookup(&nd_tbl, net, &hdr->daddr, skb->dev, 0)) {
int proxied = ip6_forward_proxy_check(skb);
if (proxied > 0)
return ip6_input(skb);
else if (proxied < 0) {
IP6_INC_STATS(net, ip6_dst_idev(dst),
IPSTATS_MIB_INDISCARDS);
goto drop;
}
}
if (!xfrm6_route_forward(skb)) {
IP6_INC_STATS(net, ip6_dst_idev(dst), IPSTATS_MIB_INDISCARDS);
goto drop;
}
dst = skb_dst(skb);
/* IPv6 specs say nothing about it, but it is clear that we cannot
send redirects to source routed frames.
We don't send redirects to frames decapsulated from IPsec.
*/
if (skb->dev == dst->dev && dst->neighbour && opt->srcrt == 0 &&
!skb_sec_path(skb)) {
struct in6_addr *target = NULL;
struct rt6_info *rt;
struct neighbour *n = dst->neighbour;
/*
* incoming and outgoing devices are the same
* send a redirect.
*/
rt = (struct rt6_info *) dst;
if ((rt->rt6i_flags & RTF_GATEWAY))
target = (struct in6_addr*)&n->primary_key;
else
target = &hdr->daddr;
/* Limit redirects both by destination (here)
and by source (inside ndisc_send_redirect)
*/
if (xrlim_allow(dst, 1*HZ))
ndisc_send_redirect(skb, n, target);
} else {
int addrtype = ipv6_addr_type(&hdr->saddr);
/* This check is security critical. */
if (addrtype == IPV6_ADDR_ANY ||
addrtype & (IPV6_ADDR_MULTICAST | IPV6_ADDR_LOOPBACK))
goto error;
if (addrtype & IPV6_ADDR_LINKLOCAL) {
icmpv6_send(skb, ICMPV6_DEST_UNREACH,
ICMPV6_NOT_NEIGHBOUR, 0, skb->dev);
goto error;
}
}
if (skb->len > dst_mtu(dst) && !skb_is_gso(skb)) {
/* Again, force OUTPUT device used as source address */
skb->dev = dst->dev;
icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, dst_mtu(dst), skb->dev);
IP6_INC_STATS_BH(net,
ip6_dst_idev(dst), IPSTATS_MIB_INTOOBIGERRORS);
IP6_INC_STATS_BH(net,
ip6_dst_idev(dst), IPSTATS_MIB_FRAGFAILS);
kfree_skb(skb);
return -EMSGSIZE;
}
/*
* We try to optimize forwarding of VE packets:
* do not decrement TTL (and so save skb_cow)
* during forwarding of outgoing pkts from VE.
* For incoming pkts we still do ttl decr,
* since such skb is not cloned and does not require
* actual cow. So, there is at least one place
* in pkts path with mandatory ttl decr, that is
* sufficient to prevent routing loops.
*/
hdr = ipv6_hdr(skb);
if (skb->dev->features & NETIF_F_VENET) /* src is VENET device */
goto no_ttl_decr;
if (skb_cow(skb, dst->dev->hard_header_len)) {
IP6_INC_STATS(net, ip6_dst_idev(dst), IPSTATS_MIB_OUTDISCARDS);
goto drop;
}
hdr = ipv6_hdr(skb);
/* Mangling hops number delayed to point after skb COW */
hdr->hop_limit--;
no_ttl_decr:
IP6_INC_STATS_BH(net, ip6_dst_idev(dst), IPSTATS_MIB_OUTFORWDATAGRAMS);
return NF_HOOK(PF_INET6, NF_INET_FORWARD, skb, skb->dev, dst->dev,
ip6_forward_finish);
error:
IP6_INC_STATS_BH(net, ip6_dst_idev(dst), IPSTATS_MIB_INADDRERRORS);
drop:
kfree_skb(skb);
return -EINVAL;
}
int ipv6_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev)
{
struct ipv6hdr *hdr;
u32 pkt_len;
struct inet6_dev *idev;
if (skb->pkt_type == PACKET_OTHERHOST) {
kfree_skb(skb);
return 0;
}
rcu_read_lock();
idev = __in6_dev_get(skb->dev);
IP6_INC_STATS_BH(idev, IPSTATS_MIB_INRECEIVES);
if ((skb = skb_share_check(skb, GFP_ATOMIC)) == NULL ||
!idev || unlikely(idev->cnf.disable_ipv6)) {
IP6_INC_STATS_BH(idev, IPSTATS_MIB_INDISCARDS);
goto drop;
}
memset(IP6CB(skb), 0, sizeof(struct inet6_skb_parm));
/*
* Store incoming device index. When the packet will
* be queued, we cannot refer to skb->dev anymore.
*
* BTW, when we send a packet for our own local address on a
* non-loopback interface (e.g. ethX), it is being delivered
* via the loopback interface (lo) here; skb->dev = &loopback_dev.
* It, however, should be considered as if it is being
* arrived via the sending interface (ethX), because of the
* nature of scoping architecture. --yoshfuji
*/
IP6CB(skb)->iif = skb->dst ? ip6_dst_idev(skb->dst)->dev->ifindex : dev->ifindex;
if (unlikely(!pskb_may_pull(skb, sizeof(*hdr))))
goto err;
hdr = ipv6_hdr(skb);
if (hdr->version != 6)
goto err;
skb->transport_header = skb->network_header + sizeof(*hdr);
IP6CB(skb)->nhoff = offsetof(struct ipv6hdr, nexthdr);
pkt_len = ntohs(hdr->payload_len);
/* pkt_len may be zero if Jumbo payload option is present */
if (pkt_len || hdr->nexthdr != NEXTHDR_HOP) {
if (pkt_len + sizeof(struct ipv6hdr) > skb->len) {
IP6_INC_STATS_BH(idev, IPSTATS_MIB_INTRUNCATEDPKTS);
goto drop;
}
if (pskb_trim_rcsum(skb, pkt_len + sizeof(struct ipv6hdr))) {
IP6_INC_STATS_BH(idev, IPSTATS_MIB_INHDRERRORS);
goto drop;
}
hdr = ipv6_hdr(skb);
}
if (hdr->nexthdr == NEXTHDR_HOP) {
if (ipv6_parse_hopopts(skb) < 0) {
IP6_INC_STATS_BH(idev, IPSTATS_MIB_INHDRERRORS);
rcu_read_unlock();
return 0;
}
}
rcu_read_unlock();
return NF_HOOK(PF_INET6,NF_IP6_PRE_ROUTING, skb, dev, NULL, ip6_rcv_finish);
err:
IP6_INC_STATS_BH(idev, IPSTATS_MIB_INHDRERRORS);
drop:
rcu_read_unlock();
kfree_skb(skb);
return 0;
}
int ip6_mc_input(struct sk_buff *skb)
{
struct ipv6hdr *hdr;
int deliver;
IP6_INC_STATS_BH(ip6_dst_idev(skb->dst), IPSTATS_MIB_INMCASTPKTS);
hdr = ipv6_hdr(skb);
deliver = ipv6_chk_mcast_addr(skb->dev, &hdr->daddr, NULL);
#ifdef CONFIG_IPV6_MROUTE
/*
* IPv6 multicast router mode is now supported ;)
*/
if (dev_net(skb->dev)->ipv6.devconf_all->mc_forwarding &&
likely(!(IP6CB(skb)->flags & IP6SKB_FORWARDED))) {
/*
* Okay, we try to forward - split and duplicate
* packets.
*/
struct sk_buff *skb2;
struct inet6_skb_parm *opt = IP6CB(skb);
/* Check for MLD */
if (unlikely(opt->ra)) {
/* Check if this is a mld message */
u8 *ptr = skb_network_header(skb) + opt->ra;
struct icmp6hdr *icmp6;
u8 nexthdr = hdr->nexthdr;
int offset;
/* Check if the value of Router Alert
* is for MLD (0x0000).
*/
if ((ptr[2] | ptr[3]) == 0) {
deliver = 0;
if (!ipv6_ext_hdr(nexthdr)) {
/* BUG */
goto out;
}
offset = ipv6_skip_exthdr(skb, sizeof(*hdr),
&nexthdr);
if (offset < 0)
goto out;
if (nexthdr != IPPROTO_ICMPV6)
goto out;
if (!pskb_may_pull(skb, (skb_network_header(skb) +
offset + 1 - skb->data)))
goto out;
icmp6 = (struct icmp6hdr *)(skb_network_header(skb) + offset);
switch (icmp6->icmp6_type) {
case ICMPV6_MGM_QUERY:
case ICMPV6_MGM_REPORT:
case ICMPV6_MGM_REDUCTION:
case ICMPV6_MLD2_REPORT:
deliver = 1;
break;
}
goto out;
}
/* unknown RA - process it normally */
}
if (deliver)
skb2 = skb_clone(skb, GFP_ATOMIC);
else {
skb2 = skb;
skb = NULL;
}
if (skb2) {
skb2->dev = skb2->dst->dev;
ip6_mr_input(skb2);
}
}
out:
#endif
if (likely(deliver))
ip6_input(skb);
else {
/* discard */
kfree_skb(skb);
}
return 0;
}
int ipv6_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev)
{
struct ipv6hdr *hdr;
u32 pkt_len;
struct inet6_dev *idev;
if (skb->pkt_type == PACKET_OTHERHOST)
goto drop;
rcu_read_lock();
idev = __in6_dev_get(skb->dev);
IP6_INC_STATS_BH(IPSTATS_MIB_INRECEIVES);
/* purpose : CONFIG_IPV6 author : ChunRu date : 2011-04-21 */
/* description : add dad failure to hw addr mechanism */
if ((skb = skb_share_check(skb, GFP_ATOMIC)) == NULL ||
!idev || unlikely(idev->cnf.disable_ipv6))
{
IP6_INC_STATS_BH(IPSTATS_MIB_INDISCARDS);
/* purpose : CONFIG_IPV6 author : ChunRu date : 2011-10-21 */
/* description : fix memory keeping growing after dad fail */
goto drop;
}
/*
* Store incoming device index. When the packet will
* be queued, we cannot refer to skb->dev anymore.
*
* BTW, when we send a packet for our own local address on a
* non-loopback interface (e.g. ethX), it is being delivered
* via the loopback interface (lo) here; skb->dev = &loopback_dev.
* It, however, should be considered as if it is being
* arrived via the sending interface (ethX), because of the
* nature of scoping architecture. --yoshfuji
*/
IP6CB(skb)->iif = skb->dst ? ((struct rt6_info *)skb->dst)->rt6i_idev->dev->ifindex : dev->ifindex;
if (skb->len < sizeof(struct ipv6hdr))
goto err;
if (!pskb_may_pull(skb, sizeof(struct ipv6hdr))) {
IP6_INC_STATS_BH(IPSTATS_MIB_INHDRERRORS);
goto drop;
}
hdr = skb->nh.ipv6h;
if (hdr->version != 6)
goto err;
skb->h.raw = (u8 *)(hdr + 1);
IP6CB(skb)->nhoff = offsetof(struct ipv6hdr, nexthdr);
pkt_len = ntohs(hdr->payload_len);
/* pkt_len may be zero if Jumbo payload option is present */
if (pkt_len || hdr->nexthdr != NEXTHDR_HOP) {
if (pkt_len + sizeof(struct ipv6hdr) > skb->len)
goto truncated;
if (pskb_trim_rcsum(skb, pkt_len + sizeof(struct ipv6hdr))) {
IP6_INC_STATS_BH(IPSTATS_MIB_INHDRERRORS);
goto drop;
}
hdr = skb->nh.ipv6h;
}
if (hdr->nexthdr == NEXTHDR_HOP) {
if (ipv6_parse_hopopts(skb, IP6CB(skb)->nhoff) < 0) {
IP6_INC_STATS_BH(IPSTATS_MIB_INHDRERRORS);
rcu_read_unlock();
return 0;
}
hdr = skb->nh.ipv6h;
}
rcu_read_unlock();
return NF_HOOK(PF_INET6,NF_IP6_PRE_ROUTING, skb, dev, NULL, ip6_rcv_finish);
truncated:
IP6_INC_STATS_BH(IPSTATS_MIB_INTRUNCATEDPKTS);
err:
IP6_INC_STATS_BH(IPSTATS_MIB_INHDRERRORS);
drop:
rcu_read_unlock();
kfree_skb(skb);
out:
return 0;
}
int ip6_mc_input(struct sk_buff *skb)
{
struct ipv6hdr *hdr;
int deliver;
IP6_INC_STATS_BH(IPSTATS_MIB_INMCASTPKTS);
hdr = skb->nh.ipv6h;
deliver = likely(!(skb->dev->flags & (IFF_PROMISC|IFF_ALLMULTI))) ||
ipv6_chk_mcast_addr(skb->dev, &hdr->daddr, NULL);
#ifdef CONFIG_IPV6_MROUTE
/*
* IPv6 multicast router mode is now supported ;)
*/
if ((ipv6_addr_type(&hdr->daddr) & IPV6_ADDR_MULTICAST) &&
(IPV6_ADDR_MC_SCOPE(&hdr->daddr) == 0))
goto out;
if (ipv6_devconf.mc_forwarding &&
!(ipv6_addr_type(&hdr->daddr) & IPV6_ADDR_LINKLOCAL) &&
likely(!(IP6CB(skb)->flags & IP6SKB_FORWARDED))) {
/*
* Okay, we try to forward - split and duplicate
* packets.
*/
struct sk_buff *skb2;
struct inet6_skb_parm *opt = IP6CB(skb);
/* Check for MLD */
if (unlikely(opt->ra)) {
/* Check if this is a mld message */
//u8 *ptr = skb_network_header(skb) + opt->ra;
u8 *ptr;
struct icmp6hdr *icmp6;
u8 nexthdr = hdr->nexthdr;
int offset;
ptr = (u8 *) (skb->nh.raw + opt->ra); //chunru: copy from ip6_output
/* Check if the value of Router Alert
* is for MLD (0x0000).
*/
if ((ptr[2] | ptr[3]) == 0) {
deliver = 0;
if (!ipv6_ext_hdr(nexthdr)) {
/* BUG */
goto out;
}
offset = ipv6_skip_exthdr(skb, sizeof(*hdr),
&nexthdr);
if (offset < 0)
goto out;
if (nexthdr != IPPROTO_ICMPV6)
goto out;
if (!pskb_may_pull(skb, (skb->nh.raw + offset + 1 - skb->data)))
goto out;
icmp6 = (struct icmp6hdr *)( skb->nh.raw + offset);
switch (icmp6->icmp6_type) {
case ICMPV6_MGM_QUERY:
case ICMPV6_MGM_REPORT:
case ICMPV6_MGM_REDUCTION:
case ICMPV6_MLD2_REPORT:
deliver = 1;
break;
}
goto out;
}
/* unknown RA - process it normally */
}
if (deliver)
{
skb2 = skb_clone(skb, GFP_ATOMIC);
}
else {
skb2 = skb;
skb = NULL;
}
if (skb2) {
ip6_mr_input(skb2);
}
}
out:
#endif
if (likely(deliver)) {
ip6_input(skb);
return 0;
}
#ifdef CONFIG_IPV6_MROUTE
else if(skb) {
/* discard */
kfree_skb(skb);
}
#else
/* discard */
kfree_skb(skb);
#endif
return 0;
}
int ipv6_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt)
{
struct ipv6hdr *hdr;
u32 pkt_len;
struct inet6_dev *idev = NULL;
int saddr_type, daddr_type;
if (skb->pkt_type == PACKET_OTHERHOST)
goto drop;
idev = in6_dev_get(dev);
IP6_INC_STATS_BH(idev,Ip6InReceives);
if ((skb = skb_share_check(skb, GFP_ATOMIC)) == NULL)
goto out;
/* Store incoming device index. When the packet will
be queued, we cannot refer to skb->dev anymore.
*/
((struct inet6_skb_parm *)skb->cb)->iif = dev->ifindex;
if (skb->len < sizeof(struct ipv6hdr))
goto err;
if (!pskb_may_pull(skb, sizeof(struct ipv6hdr)))
goto drop;
hdr = skb->nh.ipv6h;
if (hdr->version != 6)
goto err;
saddr_type = ipv6_addr_type(&hdr->saddr);
daddr_type = ipv6_addr_type(&hdr->daddr);
if ((saddr_type & IPV6_ADDR_MULTICAST) ||
(daddr_type == IPV6_ADDR_ANY))
goto drop; /*XXX*/
if (((saddr_type & IPV6_ADDR_LOOPBACK) ||
(daddr_type & IPV6_ADDR_LOOPBACK)) &&
!(dev->flags & IFF_LOOPBACK))
goto drop; /*XXX*/
#ifdef CONFIG_IPV6_DROP_FAKE_V4MAPPED
if (saddr_type == IPV6_ADDR_MAPPED ||
daddr_type == IPV6_ADDR_MAPPED)
goto drop; /*XXX*/
#endif
pkt_len = ntohs(hdr->payload_len);
/* pkt_len may be zero if Jumbo payload option is present */
if (pkt_len || hdr->nexthdr != NEXTHDR_HOP) {
if (pkt_len + sizeof(struct ipv6hdr) > skb->len)
goto truncated;
if (pkt_len + sizeof(struct ipv6hdr) < skb->len) {
if (__pskb_trim(skb, pkt_len + sizeof(struct ipv6hdr)))
goto drop;
hdr = skb->nh.ipv6h;
if (skb->ip_summed == CHECKSUM_HW)
skb->ip_summed = CHECKSUM_NONE;
}
}
if (hdr->nexthdr == NEXTHDR_HOP) {
skb->h.raw = (u8*)(hdr+1);
if (ipv6_parse_hopopts(skb, offsetof(struct ipv6hdr, nexthdr)) < 0) {
IP6_INC_STATS_BH(idev,Ip6InHdrErrors);
if (idev)
in6_dev_put(idev);
return 0;
}
hdr = skb->nh.ipv6h;
}
static int ip6_finish_output2(struct sk_buff *skb)
{
struct dst_entry *dst = skb_dst(skb);
struct net_device *dev = dst->dev;
struct neighbour *neigh;
struct in6_addr *nexthop;
int ret;
skb->protocol = htons(ETH_P_IPV6);
skb->dev = dev;
if (ipv6_addr_is_multicast(&ipv6_hdr(skb)->daddr)) {
struct inet6_dev *idev = ip6_dst_idev(skb_dst(skb));
if (!(dev->flags & IFF_LOOPBACK) && sk_mc_loop(skb->sk) &&
((mroute6_socket(dev_net(dev), skb) &&
!(IP6CB(skb)->flags & IP6SKB_FORWARDED)) ||
ipv6_chk_mcast_addr(dev, &ipv6_hdr(skb)->daddr,
&ipv6_hdr(skb)->saddr))) {
struct sk_buff *newskb = skb_clone(skb, GFP_ATOMIC);
/* Do not check for IFF_ALLMULTI; multicast routing
is not supported in any case.
*/
if (newskb)
NF_HOOK(NFPROTO_IPV6, NF_INET_POST_ROUTING,
newskb, NULL, newskb->dev,
dev_loopback_xmit);
if (ipv6_hdr(skb)->hop_limit == 0) {
IP6_INC_STATS(dev_net(dev), idev,
IPSTATS_MIB_OUTDISCARDS);
kfree_skb(skb);
return 0;
}
}
IP6_UPD_PO_STATS(dev_net(dev), idev, IPSTATS_MIB_OUTMCAST,
skb->len);
if (IPV6_ADDR_MC_SCOPE(&ipv6_hdr(skb)->daddr) <=
IPV6_ADDR_SCOPE_NODELOCAL &&
!(dev->flags & IFF_LOOPBACK)) {
kfree_skb(skb);
return 0;
}
}
rcu_read_lock_bh();
nexthop = rt6_nexthop((struct rt6_info *)dst, &ipv6_hdr(skb)->daddr);
neigh = __ipv6_neigh_lookup_noref(dst->dev, nexthop);
if (unlikely(!neigh))
neigh = __neigh_create(&nd_tbl, nexthop, dst->dev, false);
if (!IS_ERR(neigh)) {
ret = dst_neigh_output(dst, neigh, skb);
rcu_read_unlock_bh();
return ret;
}
rcu_read_unlock_bh();
IP6_INC_STATS_BH(dev_net(dst->dev),
ip6_dst_idev(dst), IPSTATS_MIB_OUTNOROUTES);
kfree_skb(skb);
return -EINVAL;
}
static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *prev,
struct net_device *dev)
{
struct net *net = container_of(fq->q.net, struct net, ipv6.frags);
struct sk_buff *fp, *head = fq->q.fragments;
int payload_len;
unsigned int nhoff;
fq_kill(fq);
if (prev) {
head = prev->next;
fp = skb_clone(head, GFP_ATOMIC);
if (!fp)
goto out_oom;
fp->next = head->next;
if (!fp->next)
fq->q.fragments_tail = fp;
prev->next = fp;
skb_morph(head, fq->q.fragments);
head->next = fq->q.fragments->next;
kfree_skb(fq->q.fragments);
fq->q.fragments = head;
}
WARN_ON(head == NULL);
WARN_ON(FRAG6_CB(head)->offset != 0);
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;
if (skb_cloned(head) && pskb_expand_head(head, 0, 0, GFP_ATOMIC))
goto out_oom;
if (skb_has_frag_list(head)) {
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_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;
atomic_add(clone->truesize, &fq->q.net->mem);
}
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));
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(head->truesize, &fq->q.net->mem);
head->next = NULL;
head->dev = dev;
head->tstamp = fq->q.stamp;
ipv6_hdr(head)->payload_len = htons(payload_len);
IP6CB(head)->nhoff = nhoff;
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(net, __in6_dev_get(dev), IPSTATS_MIB_REASMOKS);
rcu_read_unlock();
fq->q.fragments = NULL;
fq->q.fragments_tail = 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(net, __in6_dev_get(dev), IPSTATS_MIB_REASMFAILS);
rcu_read_unlock();
return -1;
}
static int ip6_dst_lookup_tail(struct sock *sk,
struct dst_entry **dst, struct flowi6 *fl6)
{
struct net *net = sock_net(sk);
#ifdef CONFIG_IPV6_OPTIMISTIC_DAD
struct neighbour *n;
struct rt6_info *rt;
#endif
int err;
if (*dst == NULL)
*dst = ip6_route_output(net, sk, fl6);
if ((err = (*dst)->error))
goto out_err_release;
if (ipv6_addr_any(&fl6->saddr)) {
struct rt6_info *rt = (struct rt6_info *) *dst;
err = ip6_route_get_saddr(net, rt, &fl6->daddr,
sk ? inet6_sk(sk)->srcprefs : 0,
&fl6->saddr);
if (err)
goto out_err_release;
}
#ifdef CONFIG_IPV6_OPTIMISTIC_DAD
/*
* Here if the dst entry we've looked up
* has a neighbour entry that is in the INCOMPLETE
* state and the src address from the flow is
* marked as OPTIMISTIC, we release the found
* dst entry and replace it instead with the
* dst entry of the nexthop router
*/
rt = (struct rt6_info *) *dst;
rcu_read_lock_bh();
n = __ipv6_neigh_lookup_noref(rt->dst.dev, rt6_nexthop(rt, &fl6->daddr));
err = n && !(n->nud_state & NUD_VALID) ? -EINVAL : 0;
rcu_read_unlock_bh();
if (err) {
struct inet6_ifaddr *ifp;
struct flowi6 fl_gw6;
int redirect;
ifp = ipv6_get_ifaddr(net, &fl6->saddr,
(*dst)->dev, 1);
redirect = (ifp && ifp->flags & IFA_F_OPTIMISTIC);
if (ifp)
in6_ifa_put(ifp);
if (redirect) {
/*
* We need to get the dst entry for the
* default router instead
*/
dst_release(*dst);
memcpy(&fl_gw6, fl6, sizeof(struct flowi6));
memset(&fl_gw6.daddr, 0, sizeof(struct in6_addr));
*dst = ip6_route_output(net, sk, &fl_gw6);
if ((err = (*dst)->error))
goto out_err_release;
}
}
#endif
return 0;
out_err_release:
if (err == -ENETUNREACH)
IP6_INC_STATS_BH(net, NULL, IPSTATS_MIB_OUTNOROUTES);
dst_release(*dst);
*dst = NULL;
return err;
}
/*
* 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 **skb_in,
struct net_device *dev)
{
struct sk_buff *fp, *head = fq->fragments;
int remove_fraghdr = 0;
int payload_len;
int nhoff;
fq_kill(fq);
BUG_TRAP(head != NULL);
BUG_TRAP(FRAG6_CB(head)->offset == 0);
/* Unfragmented part is taken from the first segment. */
payload_len = (head->data - head->nh.raw) - sizeof(struct ipv6hdr) + fq->len;
nhoff = head->h.raw - head->nh.raw;
if (payload_len > 65535) {
payload_len -= 8;
if (payload_len > 65535)
goto out_oversize;
remove_fraghdr = 1;
}
/* 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_frag_mem);
}
/* Normally we do not remove frag header from datagram, but
* we have to do this and to relocate header, when payload
* is > 65535-8. */
if (remove_fraghdr) {
nhoff = fq->nhoffset;
head->nh.raw[nhoff] = head->h.raw[0];
memmove(head->head+8, head->head, (head->data-head->head)-8);
head->mac.raw += 8;
head->nh.raw += 8;
} else {
((struct frag_hdr*)head->h.raw)->frag_off = 0;
}
skb_shinfo(head)->frag_list = head->next;
head->h.raw = head->data;
skb_push(head, head->data - head->nh.raw);
atomic_sub(head->truesize, &ip6_frag_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_HW)
head->csum = csum_add(head->csum, fp->csum);
head->truesize += fp->truesize;
atomic_sub(fp->truesize, &ip6_frag_mem);
}
head->next = NULL;
head->dev = dev;
head->stamp = fq->stamp;
head->nh.ipv6h->payload_len = ntohs(payload_len);
*skb_in = head;
/* Yes, and fold redundant checksum back. 8) */
if (head->ip_summed == CHECKSUM_HW)
head->csum = csum_partial(head->nh.raw, head->h.raw-head->nh.raw, head->csum);
IP6_INC_STATS_BH(Ip6ReasmOKs);
fq->fragments = NULL;
return nhoff;
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:
IP6_INC_STATS_BH(Ip6ReasmFails);
return -1;
}
int ip6_forward(struct sk_buff *skb)
{
struct dst_entry *dst = skb_dst(skb);
struct ipv6hdr *hdr = ipv6_hdr(skb);
struct inet6_skb_parm *opt = IP6CB(skb);
struct net *net = dev_net(dst->dev);
u32 mtu;
if (net->ipv6.devconf_all->forwarding == 0)
goto error;
if (skb->pkt_type != PACKET_HOST)
goto drop;
if (skb_warn_if_lro(skb))
goto drop;
if (!xfrm6_policy_check(NULL, XFRM_POLICY_FWD, skb)) {
IP6_INC_STATS_BH(net, ip6_dst_idev(dst),
IPSTATS_MIB_INDISCARDS);
goto drop;
}
skb_forward_csum(skb);
/*
* We DO NOT make any processing on
* RA packets, pushing them to user level AS IS
* without ane WARRANTY that application will be able
* to interpret them. The reason is that we
* cannot make anything clever here.
*
* We are not end-node, so that if packet contains
* AH/ESP, we cannot make anything.
* Defragmentation also would be mistake, RA packets
* cannot be fragmented, because there is no warranty
* that different fragments will go along one path. --ANK
*/
if (unlikely(opt->flags & IP6SKB_ROUTERALERT)) {
if (ip6_call_ra_chain(skb, ntohs(opt->ra)))
return 0;
}
/*
* check and decrement ttl
*/
if (hdr->hop_limit <= 1) {
/* Force OUTPUT device used as source address */
skb->dev = dst->dev;
icmpv6_send(skb, ICMPV6_TIME_EXCEED, ICMPV6_EXC_HOPLIMIT, 0);
IP6_INC_STATS_BH(net, ip6_dst_idev(dst),
IPSTATS_MIB_INHDRERRORS);
kfree_skb(skb);
return -ETIMEDOUT;
}
/* XXX: idev->cnf.proxy_ndp? */
if (net->ipv6.devconf_all->proxy_ndp &&
pneigh_lookup(&nd_tbl, net, &hdr->daddr, skb->dev, 0)) {
int proxied = ip6_forward_proxy_check(skb);
if (proxied > 0)
return ip6_input(skb);
else if (proxied < 0) {
IP6_INC_STATS_BH(net, ip6_dst_idev(dst),
IPSTATS_MIB_INDISCARDS);
goto drop;
}
}
if (!xfrm6_route_forward(skb)) {
IP6_INC_STATS_BH(net, ip6_dst_idev(dst),
IPSTATS_MIB_INDISCARDS);
goto drop;
}
dst = skb_dst(skb);
/* IPv6 specs say nothing about it, but it is clear that we cannot
send redirects to source routed frames.
We don't send redirects to frames decapsulated from IPsec.
*/
if (skb->dev == dst->dev && opt->srcrt == 0 && !skb_sec_path(skb)) {
struct in6_addr *target = NULL;
struct inet_peer *peer;
struct rt6_info *rt;
/*
* incoming and outgoing devices are the same
* send a redirect.
*/
rt = (struct rt6_info *) dst;
if (rt->rt6i_flags & RTF_GATEWAY)
target = &rt->rt6i_gateway;
else
target = &hdr->daddr;
peer = inet_getpeer_v6(net->ipv6.peers, &rt->rt6i_dst.addr, 1);
/* Limit redirects both by destination (here)
and by source (inside ndisc_send_redirect)
*/
if (inet_peer_xrlim_allow(peer, 1*HZ))
ndisc_send_redirect(skb, target);
if (peer)
inet_putpeer(peer);
} else {
int addrtype = ipv6_addr_type(&hdr->saddr);
/* This check is security critical. */
if (addrtype == IPV6_ADDR_ANY ||
addrtype & (IPV6_ADDR_MULTICAST | IPV6_ADDR_LOOPBACK))
goto error;
if (addrtype & IPV6_ADDR_LINKLOCAL) {
icmpv6_send(skb, ICMPV6_DEST_UNREACH,
ICMPV6_NOT_NEIGHBOUR, 0);
goto error;
}
}
mtu = ip6_dst_mtu_forward(dst);
if (mtu < IPV6_MIN_MTU)
mtu = IPV6_MIN_MTU;
if (ip6_pkt_too_big(skb, mtu)) {
/* Again, force OUTPUT device used as source address */
skb->dev = dst->dev;
icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
IP6_INC_STATS_BH(net, ip6_dst_idev(dst),
IPSTATS_MIB_INTOOBIGERRORS);
IP6_INC_STATS_BH(net, ip6_dst_idev(dst),
IPSTATS_MIB_FRAGFAILS);
kfree_skb(skb);
return -EMSGSIZE;
}
if (skb_cow(skb, dst->dev->hard_header_len)) {
IP6_INC_STATS_BH(net, ip6_dst_idev(dst),
IPSTATS_MIB_OUTDISCARDS);
goto drop;
}
hdr = ipv6_hdr(skb);
/* Mangling hops number delayed to point after skb COW */
hdr->hop_limit--;
IP6_INC_STATS_BH(net, ip6_dst_idev(dst), IPSTATS_MIB_OUTFORWDATAGRAMS);
IP6_ADD_STATS_BH(net, ip6_dst_idev(dst), IPSTATS_MIB_OUTOCTETS, skb->len);
return NF_HOOK(NFPROTO_IPV6, NF_INET_FORWARD, NULL, skb,
skb->dev, dst->dev,
ip6_forward_finish);
error:
IP6_INC_STATS_BH(net, ip6_dst_idev(dst), IPSTATS_MIB_INADDRERRORS);
drop:
kfree_skb(skb);
return -EINVAL;
}
static int ipv6_frag_rcv(struct sk_buff *skb)
{
struct frag_hdr *fhdr;
struct frag_queue *fq;
const struct ipv6hdr *hdr = ipv6_hdr(skb);
struct net *net = dev_net(skb_dst(skb)->dev);
int evicted;
if (IP6CB(skb)->flags & IP6SKB_FRAGMENTED)
goto fail_hdr;
IP6_INC_STATS_BH(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_REASMREQDS);
/* Jumbo payload inhibits frag. header */
if (hdr->payload_len==0)
goto fail_hdr;
if (!pskb_may_pull(skb, (skb_transport_offset(skb) +
sizeof(struct frag_hdr))))
goto fail_hdr;
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(net,
ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_REASMOKS);
IP6CB(skb)->nhoff = (u8 *)fhdr - skb_network_header(skb);
IP6CB(skb)->flags |= IP6SKB_FRAGMENTED;
return 1;
}
evicted = inet_frag_evictor(&net->ipv6.frags, &ip6_frags, false);
if (evicted)
IP6_ADD_STATS_BH(net, ip6_dst_idev(skb_dst(skb)),
IPSTATS_MIB_REASMFAILS, evicted);
fq = fq_find(net, fhdr->identification, &hdr->saddr, &hdr->daddr,
ip6_frag_ecn(hdr));
if (fq != NULL) {
int ret;
spin_lock(&fq->q.lock);
ret = ip6_frag_queue(fq, skb, fhdr, IP6CB(skb)->nhoff);
spin_unlock(&fq->q.lock);
inet_frag_put(&fq->q, &ip6_frags);
return ret;
}
IP6_INC_STATS_BH(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_REASMFAILS);
kfree_skb(skb);
return -1;
fail_hdr:
IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_INHDRERRORS);
icmpv6_param_prob(skb, ICMPV6_HDR_FIELD, skb_network_header_len(skb));
return -1;
}
static int ip6_dst_lookup_tail(struct sock *sk,
struct dst_entry **dst, struct flowi *fl)
{
int err;
if (*dst == NULL)
*dst = ip6_route_output(sk, fl);
if ((err = (*dst)->error))
goto out_err_release;
if (ipv6_addr_any(&fl->fl6_src)) {
err = ipv6_get_saddr(*dst, &fl->fl6_dst, &fl->fl6_src);
if (err)
goto out_err_release;
}
#ifdef CONFIG_IPV6_OPTIMISTIC_DAD
/*
* Here if the dst entry we've looked up
* has a neighbour entry that is in the INCOMPLETE
* state and the src address from the flow is
* marked as OPTIMISTIC, we release the found
* dst entry and replace it instead with the
* dst entry of the nexthop router
*/
if ((*dst)->neighbour && !((*dst)->neighbour->nud_state & NUD_VALID)) {
struct inet6_ifaddr *ifp;
struct flowi fl_gw;
int redirect;
ifp = ipv6_get_ifaddr(&fl->fl6_src, (*dst)->dev, 1);
redirect = (ifp && ifp->flags & IFA_F_OPTIMISTIC);
if (ifp)
in6_ifa_put(ifp);
if (redirect) {
/*
* We need to get the dst entry for the
* default router instead
*/
dst_release(*dst);
memcpy(&fl_gw, fl, sizeof(struct flowi));
memset(&fl_gw.fl6_dst, 0, sizeof(struct in6_addr));
*dst = ip6_route_output(sk, &fl_gw);
if ((err = (*dst)->error))
goto out_err_release;
}
}
#endif
return 0;
out_err_release:
if (err == -ENETUNREACH)
IP6_INC_STATS_BH(NULL, IPSTATS_MIB_OUTNOROUTES);
dst_release(*dst);
*dst = NULL;
return err;
}
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;
struct net *net = dev_net(skb->dst->dev);
if (fq->q.last_in & INET_FRAG_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(net, 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 & INET_FRAG_LAST_IN) && end != fq->q.len))
goto err;
fq->q.last_in |= INET_FRAG_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(net, 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 & INET_FRAG_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(fq->q.net, 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, &fq->q.net->mem);
/* The first fragment.
* nhoffset is obtained from the first fragment, of course.
*/
if (offset == 0) {
fq->nhoffset = nhoff;
fq->q.last_in |= INET_FRAG_FIRST_IN;
}
if (fq->q.last_in == (INET_FRAG_FIRST_IN | INET_FRAG_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, &fq->q.net->lru_list);
write_unlock(&ip6_frags.lock);
return -1;
err:
IP6_INC_STATS(net, 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 net *net = container_of(fq->q.net, struct net, ipv6.frags);
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;
if (!fp->next)
fq->q.fragments_tail = fp;
prev->next = fp;
skb_morph(head, fq->q.fragments);
head->next = fq->q.fragments->next;
kfree_skb(fq->q.fragments);
fq->q.fragments = head;
}
WARN_ON(head == NULL);
WARN_ON(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_has_frag_list(head)) {
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_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;
atomic_add(clone->truesize, &fq->q.net->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));
if (skb_mac_header_was_set(head))
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));
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(head->truesize, &fq->q.net->mem);
head->next = NULL;
head->dev = dev;
head->tstamp = fq->q.stamp;
ipv6_hdr(head)->payload_len = htons(payload_len);
IP6CB(head)->nhoff = nhoff;
IP6CB(head)->flags |= IP6SKB_FRAGMENTED;
/* 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(net, __in6_dev_get(dev), IPSTATS_MIB_REASMOKS);
rcu_read_unlock();
fq->q.fragments = NULL;
fq->q.fragments_tail = NULL;
return 1;
out_oversize:
net_dbg_ratelimited("ip6_frag_reasm: payload len = %d\n", payload_len);
goto out_fail;
out_oom:
net_dbg_ratelimited("ip6_frag_reasm: no memory for reassembly\n");
out_fail:
rcu_read_lock();
IP6_INC_STATS_BH(net, __in6_dev_get(dev), IPSTATS_MIB_REASMFAILS);
rcu_read_unlock();
return -1;
}
static int ip6_input_finish(struct sk_buff *skb)
{
struct net *net = dev_net(skb_dst(skb)->dev);
const struct inet6_protocol *ipprot;
struct inet6_dev *idev;
unsigned int nhoff;
int nexthdr;
bool raw;
/*
* Parse extension headers
*/
rcu_read_lock();
resubmit:
idev = ip6_dst_idev(skb_dst(skb));
if (!pskb_pull(skb, skb_transport_offset(skb)))
goto discard;
nhoff = IP6CB(skb)->nhoff;
nexthdr = skb_network_header(skb)[nhoff];
raw = raw6_local_deliver(skb, nexthdr);
if ((ipprot = rcu_dereference(inet6_protos[nexthdr])) != NULL) {
int ret;
if (ipprot->flags & INET6_PROTO_FINAL) {
const struct ipv6hdr *hdr;
/* Free reference early: we don't need it any more,
and it may hold ip_conntrack module loaded
indefinitely. */
nf_reset(skb);
skb_postpull_rcsum(skb, skb_network_header(skb),
skb_network_header_len(skb));
hdr = ipv6_hdr(skb);
if (ipv6_addr_is_multicast(&hdr->daddr) &&
!ipv6_chk_mcast_addr(skb->dev, &hdr->daddr,
&hdr->saddr) &&
!ipv6_is_mld(skb, nexthdr, skb_network_header_len(skb)))
goto discard;
}
if (!(ipprot->flags & INET6_PROTO_NOPOLICY) &&
!xfrm6_policy_check(NULL, XFRM_POLICY_IN, skb))
goto discard;
ret = ipprot->handler(skb);
if (ret > 0)
goto resubmit;
else if (ret == 0)
IP6_INC_STATS_BH(net, idev, IPSTATS_MIB_INDELIVERS);
} else {
if (!raw) {
if (xfrm6_policy_check(NULL, XFRM_POLICY_IN, skb)) {
IP6_INC_STATS_BH(net, idev,
IPSTATS_MIB_INUNKNOWNPROTOS);
icmpv6_send(skb, ICMPV6_PARAMPROB,
ICMPV6_UNK_NEXTHDR, nhoff);
}
kfree_skb(skb);
} else {
IP6_INC_STATS_BH(net, idev, IPSTATS_MIB_INDELIVERS);
consume_skb(skb);
}
}
rcu_read_unlock();
return 0;
discard:
IP6_INC_STATS_BH(net, idev, IPSTATS_MIB_INDISCARDS);
rcu_read_unlock();
kfree_skb(skb);
return 0;
}
int ipv6_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev)
{
struct ipv6hdr *hdr;
u32 pkt_len;
struct inet6_dev *idev;
struct net_device_extended *ext = dev_extended(dev);
if (skb->pkt_type == PACKET_OTHERHOST) {
kfree_skb(skb);
return 0;
}
rcu_read_lock();
idev = __in6_dev_get(skb->dev);
IP6_INC_STATS_BH(idev, IPSTATS_MIB_INRECEIVES);
if ((skb = skb_share_check(skb, GFP_ATOMIC)) == NULL ||
(ext && unlikely(ext->ipv6_devconf_ext.disable_ipv6))) {
IP6_INC_STATS_BH(idev, IPSTATS_MIB_INDISCARDS);
rcu_read_unlock();
goto out;
}
memset(IP6CB(skb), 0, sizeof(struct inet6_skb_parm));
/*
* Store incoming device index. When the packet will
* be queued, we cannot refer to skb->dev anymore.
*
* BTW, when we send a packet for our own local address on a
* non-loopback interface (e.g. ethX), it is being delivered
* via the loopback interface (lo) here; skb->dev = &loopback_dev.
* It, however, should be considered as if it is being
* arrived via the sending interface (ethX), because of the
* nature of scoping architecture. --yoshfuji
*/
IP6CB(skb)->iif = skb->dst ? ((struct rt6_info *)skb->dst)->rt6i_idev->dev->ifindex : dev->ifindex;
if (unlikely(!pskb_may_pull(skb, sizeof(*hdr))))
goto err;
hdr = skb->nh.ipv6h;
if (hdr->version != 6)
goto err;
/*
* RFC4291 2.5.3
* A packet received on an interface with a destination address
* of loopback must be dropped.
*/
if (!(dev->flags & IFF_LOOPBACK) &&
ipv6_addr_loopback(&hdr->daddr))
goto err;
skb->h.raw = (u8 *)(hdr + 1);
IP6CB(skb)->nhoff = offsetof(struct ipv6hdr, nexthdr);
pkt_len = ntohs(hdr->payload_len);
/* pkt_len may be zero if Jumbo payload option is present */
if (pkt_len || hdr->nexthdr != NEXTHDR_HOP) {
if (pkt_len + sizeof(struct ipv6hdr) > skb->len)
goto truncated;
if (pskb_trim_rcsum(skb, pkt_len + sizeof(struct ipv6hdr))) {
IP6_INC_STATS_BH(idev, IPSTATS_MIB_INHDRERRORS);
goto drop;
}
hdr = skb->nh.ipv6h;
}
if (hdr->nexthdr == NEXTHDR_HOP) {
if (ipv6_parse_hopopts(skb) < 0) {
IP6_INC_STATS_BH(idev, IPSTATS_MIB_INHDRERRORS);
rcu_read_unlock();
return 0;
}
}
rcu_read_unlock();
return NF_HOOK(PF_INET6,NF_IP6_PRE_ROUTING, skb, dev, NULL, ip6_rcv_finish);
truncated:
IP6_INC_STATS_BH(idev, IPSTATS_MIB_INTRUNCATEDPKTS);
err:
IP6_INC_STATS_BH(idev, IPSTATS_MIB_INHDRERRORS);
drop:
rcu_read_unlock();
kfree_skb(skb);
out:
return 0;
}
int ipv6_reassembly(struct sk_buff **skbp, int nhoff)
{
struct sk_buff *skb = *skbp;
struct inet6_dev *idev = in6_dev_get(skb->dev);
struct net_device *dev = skb->dev;
struct frag_hdr *fhdr;
struct frag_queue *fq;
struct ipv6hdr *hdr;
hdr = skb->nh.ipv6h;
IP6_INC_STATS_BH(idev,Ip6ReasmReqds);
/* Jumbo payload inhibits frag. header */
if (hdr->payload_len==0) {
if (idev)
in6_dev_put(idev);
icmpv6_param_prob(skb, ICMPV6_HDR_FIELD, skb->h.raw-skb->nh.raw);
return -1;
}
if (!pskb_may_pull(skb, (skb->h.raw-skb->data)+sizeof(struct frag_hdr))) {
if (idev)
in6_dev_put(idev);
icmpv6_param_prob(skb, ICMPV6_HDR_FIELD, skb->h.raw-skb->nh.raw);
return -1;
}
hdr = skb->nh.ipv6h;
fhdr = (struct frag_hdr *)skb->h.raw;
if (!(fhdr->frag_off & htons(0xFFF9))) {
/* It is not a fragmented frame */
skb->h.raw += sizeof(struct frag_hdr);
IP6_INC_STATS_BH(idev,Ip6ReasmOKs);
if (idev)
in6_dev_put(idev);
return (u8*)fhdr - skb->nh.raw;
}
if (atomic_read(&ip6_frag_mem) > sysctl_ip6frag_high_thresh)
ip6_evictor(idev);
if ((fq = fq_find(fhdr->identification, &hdr->saddr, &hdr->daddr, idev)) != NULL) {
int ret = -1;
spin_lock(&fq->lock);
ip6_frag_queue(fq, skb, fhdr, nhoff);
if (fq->last_in == (FIRST_IN|LAST_IN) &&
fq->meat == fq->len)
ret = ip6_frag_reasm(fq, skbp, dev);
spin_unlock(&fq->lock);
fq_put(fq);
if (idev)
in6_dev_put(idev);
return ret;
}
IP6_INC_STATS_BH(idev,Ip6ReasmFails);
if (idev)
in6_dev_put(idev);
kfree_skb(skb);
return -1;
}
