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:
* 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, including those not yet received) MUST be silently
* discarded.
*/
/* Check for overlap with preceding fragment. */
if (prev &&
(FRAG6_CB(prev)->offset + prev->len) - offset > 0)
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)
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_xmit(struct sock *sk, struct sk_buff *skb, struct flowi6 *fl6,
struct ipv6_txoptions *opt, int tclass)
{
struct net *net = sock_net(sk);
struct ipv6_pinfo *np = inet6_sk(sk);
struct in6_addr *first_hop = &fl6->daddr;
struct dst_entry *dst = skb_dst(skb);
struct ipv6hdr *hdr;
u8 proto = fl6->flowi6_proto;
int seg_len = skb->len;
int hlimit = -1;
u32 mtu;
if (opt) {
unsigned int head_room;
/* First: exthdrs may take lots of space (~8K for now)
MAX_HEADER is not enough.
*/
head_room = opt->opt_nflen + opt->opt_flen;
seg_len += head_room;
head_room += sizeof(struct ipv6hdr) + LL_RESERVED_SPACE(dst->dev);
if (skb_headroom(skb) < head_room) {
struct sk_buff *skb2 = skb_realloc_headroom(skb, head_room);
if (skb2 == NULL) {
IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)),
IPSTATS_MIB_OUTDISCARDS);
kfree_skb(skb);
return -ENOBUFS;
}
kfree_skb(skb);
skb = skb2;
skb_set_owner_w(skb, sk);
}
if (opt->opt_flen)
ipv6_push_frag_opts(skb, opt, &proto);
if (opt->opt_nflen)
ipv6_push_nfrag_opts(skb, opt, &proto, &first_hop);
}
skb_push(skb, sizeof(struct ipv6hdr));
skb_reset_network_header(skb);
hdr = ipv6_hdr(skb);
/*
* Fill in the IPv6 header
*/
if (np)
hlimit = np->hop_limit;
if (hlimit < 0)
hlimit = ip6_dst_hoplimit(dst);
*(__be32 *)hdr = htonl(0x60000000 | (tclass << 20)) | fl6->flowlabel;
hdr->payload_len = htons(seg_len);
hdr->nexthdr = proto;
hdr->hop_limit = hlimit;
hdr->saddr = fl6->saddr;
hdr->daddr = *first_hop;
skb->priority = sk->sk_priority;
skb->mark = sk->sk_mark;
mtu = dst_mtu(dst);
if ((skb->len <= mtu) || skb->local_df || skb_is_gso(skb)) {
IP6_UPD_PO_STATS(net, ip6_dst_idev(skb_dst(skb)),
IPSTATS_MIB_OUT, skb->len);
return NF_HOOK(NFPROTO_IPV6, NF_INET_LOCAL_OUT, skb, NULL,
dst->dev, dst_output);
}
if (net_ratelimit())
printk(KERN_DEBUG "IPv6: sending pkt_too_big to self\n");
skb->dev = dst->dev;
icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_FRAGFAILS);
kfree_skb(skb);
return -EMSGSIZE;
}
int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *))
{
struct sk_buff *frag;
struct rt6_info *rt = (struct rt6_info*)skb_dst(skb);
struct ipv6_pinfo *np = skb->sk ? inet6_sk(skb->sk) : NULL;
struct ipv6hdr *tmp_hdr;
struct frag_hdr *fh;
unsigned int mtu, hlen, left, len;
int hroom, troom;
__be32 frag_id = 0;
int ptr, offset = 0, err=0;
u8 *prevhdr, nexthdr = 0;
struct net *net = dev_net(skb_dst(skb)->dev);
hlen = ip6_find_1stfragopt(skb, &prevhdr);
nexthdr = *prevhdr;
mtu = ip6_skb_dst_mtu(skb);
/* We must not fragment if the socket is set to force MTU discovery
* or if the skb it not generated by a local socket.
*/
if (!skb->local_df && skb->len > mtu) {
skb->dev = skb_dst(skb)->dev;
icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)),
IPSTATS_MIB_FRAGFAILS);
kfree_skb(skb);
return -EMSGSIZE;
}
if (np && np->frag_size < mtu) {
if (np->frag_size)
mtu = np->frag_size;
}
mtu -= hlen + sizeof(struct frag_hdr);
if (skb_has_frag_list(skb)) {
int first_len = skb_pagelen(skb);
struct sk_buff *frag2;
if (first_len - hlen > mtu ||
((first_len - hlen) & 7) ||
skb_cloned(skb))
goto slow_path;
skb_walk_frags(skb, frag) {
/* Correct geometry. */
if (frag->len > mtu ||
((frag->len & 7) && frag->next) ||
skb_headroom(frag) < hlen)
goto slow_path_clean;
/* Partially cloned skb? */
if (skb_shared(frag))
goto slow_path_clean;
BUG_ON(frag->sk);
if (skb->sk) {
frag->sk = skb->sk;
frag->destructor = sock_wfree;
}
skb->truesize -= frag->truesize;
}
err = 0;
offset = 0;
frag = skb_shinfo(skb)->frag_list;
skb_frag_list_init(skb);
/* BUILD HEADER */
*prevhdr = NEXTHDR_FRAGMENT;
tmp_hdr = kmemdup(skb_network_header(skb), hlen, GFP_ATOMIC);
if (!tmp_hdr) {
IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)),
IPSTATS_MIB_FRAGFAILS);
return -ENOMEM;
}
__skb_pull(skb, hlen);
fh = (struct frag_hdr*)__skb_push(skb, sizeof(struct frag_hdr));
__skb_push(skb, hlen);
skb_reset_network_header(skb);
memcpy(skb_network_header(skb), tmp_hdr, hlen);
ipv6_select_ident(fh, rt);
fh->nexthdr = nexthdr;
fh->reserved = 0;
fh->frag_off = htons(IP6_MF);
frag_id = fh->identification;
first_len = skb_pagelen(skb);
skb->data_len = first_len - skb_headlen(skb);
skb->len = first_len;
ipv6_hdr(skb)->payload_len = htons(first_len -
sizeof(struct ipv6hdr));
dst_hold(&rt->dst);
for (;;) {
/* Prepare header of the next frame,
* before previous one went down. */
if (frag) {
frag->ip_summed = CHECKSUM_NONE;
skb_reset_transport_header(frag);
fh = (struct frag_hdr*)__skb_push(frag, sizeof(struct frag_hdr));
__skb_push(frag, hlen);
skb_reset_network_header(frag);
memcpy(skb_network_header(frag), tmp_hdr,
hlen);
offset += skb->len - hlen - sizeof(struct frag_hdr);
fh->nexthdr = nexthdr;
fh->reserved = 0;
fh->frag_off = htons(offset);
if (frag->next != NULL)
fh->frag_off |= htons(IP6_MF);
fh->identification = frag_id;
ipv6_hdr(frag)->payload_len =
htons(frag->len -
sizeof(struct ipv6hdr));
ip6_copy_metadata(frag, skb);
}
err = output(skb);
if(!err)
IP6_INC_STATS(net, ip6_dst_idev(&rt->dst),
IPSTATS_MIB_FRAGCREATES);
if (err || !frag)
break;
skb = frag;
frag = skb->next;
skb->next = NULL;
}
kfree(tmp_hdr);
if (err == 0) {
IP6_INC_STATS(net, ip6_dst_idev(&rt->dst),
IPSTATS_MIB_FRAGOKS);
dst_release(&rt->dst);
return 0;
}
while (frag) {
skb = frag->next;
kfree_skb(frag);
frag = skb;
}
IP6_INC_STATS(net, ip6_dst_idev(&rt->dst),
IPSTATS_MIB_FRAGFAILS);
dst_release(&rt->dst);
return err;
slow_path_clean:
skb_walk_frags(skb, frag2) {
if (frag2 == frag)
break;
frag2->sk = NULL;
frag2->destructor = NULL;
skb->truesize += frag2->truesize;
}
}
slow_path:
left = skb->len - hlen; /* Space per frame */
ptr = hlen; /* Where to start from */
/*
* Fragment the datagram.
*/
*prevhdr = NEXTHDR_FRAGMENT;
hroom = LL_RESERVED_SPACE(rt->dst.dev);
troom = rt->dst.dev->needed_tailroom;
/*
* Keep copying data until we run out.
*/
while(left > 0) {
len = left;
/* IF: it doesn't fit, use 'mtu' - the data space left */
if (len > mtu)
len = mtu;
/* IF: we are not sending up to and including the packet end
then align the next start on an eight byte boundary */
if (len < left) {
len &= ~7;
}
/*
* Allocate buffer.
*/
if ((frag = alloc_skb(len + hlen + sizeof(struct frag_hdr) +
hroom + troom, GFP_ATOMIC)) == NULL) {
NETDEBUG(KERN_INFO "IPv6: frag: no memory for new fragment!\n");
IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)),
IPSTATS_MIB_FRAGFAILS);
err = -ENOMEM;
goto fail;
}
/*
* Set up data on packet
*/
ip6_copy_metadata(frag, skb);
skb_reserve(frag, hroom);
skb_put(frag, len + hlen + sizeof(struct frag_hdr));
skb_reset_network_header(frag);
fh = (struct frag_hdr *)(skb_network_header(frag) + hlen);
frag->transport_header = (frag->network_header + hlen +
sizeof(struct frag_hdr));
/*
* Charge the memory for the fragment to any owner
* it might possess
*/
if (skb->sk)
skb_set_owner_w(frag, skb->sk);
/*
* Copy the packet header into the new buffer.
*/
skb_copy_from_linear_data(skb, skb_network_header(frag), hlen);
/*
* Build fragment header.
*/
fh->nexthdr = nexthdr;
fh->reserved = 0;
if (!frag_id) {
ipv6_select_ident(fh, rt);
frag_id = fh->identification;
} else
fh->identification = frag_id;
/*
* Copy a block of the IP datagram.
*/
if (skb_copy_bits(skb, ptr, skb_transport_header(frag), len))
BUG();
left -= len;
fh->frag_off = htons(offset);
if (left > 0)
fh->frag_off |= htons(IP6_MF);
ipv6_hdr(frag)->payload_len = htons(frag->len -
sizeof(struct ipv6hdr));
ptr += len;
offset += len;
/*
* Put this fragment into the sending queue.
*/
err = output(frag);
if (err)
goto fail;
IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)),
IPSTATS_MIB_FRAGCREATES);
}
IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)),
IPSTATS_MIB_FRAGOKS);
kfree_skb(skb);
return err;
fail:
IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)),
IPSTATS_MIB_FRAGFAILS);
kfree_skb(skb);
return err;
}
static int ip6_input_finish(struct sk_buff *skb)
{
const struct inet6_protocol *ipprot;
unsigned int nhoff;
int nexthdr, raw;
u8 hash;
struct inet6_dev *idev;
struct net *net = dev_net(skb_dst(skb)->dev);
/*
* 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);
hash = nexthdr & (MAX_INET_PROTOS - 1);
if ((ipprot = rcu_dereference(inet6_protos[hash])) != 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))
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);
}
} else
IP6_INC_STATS_BH(net, idev, IPSTATS_MIB_INDELIVERS);
kfree_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)
{
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
* 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();
#ifdef CONFIG_HTC_NETWORK_MODIFY
if (!IS_ERR(skb) && (skb))
kfree_skb(skb);
#else
kfree_skb(skb);
#endif
return NET_RX_DROP;
}
static int xfrm_output_one(struct sk_buff *skb, int err)
{
struct dst_entry *dst = skb_dst(skb);
struct xfrm_state *x = dst->xfrm;
struct net *net = xs_net(x);
if (err <= 0)
goto resume;
do {
err = xfrm_state_check_space(x, skb);
if (err) {
XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTERROR);
goto error_nolock;
}
err = x->outer_mode->output(x, skb);
if (err) {
XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTSTATEMODEERROR);
goto error_nolock;
}
spin_lock_bh(&x->lock);
err = xfrm_state_check_expire(x);
if (err) {
XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTSTATEEXPIRED);
goto error;
}
if (x->type->flags & XFRM_TYPE_REPLAY_PROT) {
XFRM_SKB_CB(skb)->seq.output = ++x->replay.oseq;
if (unlikely(x->replay.oseq == 0)) {
XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTSTATESEQERROR);
x->replay.oseq--;
xfrm_audit_state_replay_overflow(x, skb);
err = -EOVERFLOW;
goto error;
}
if (xfrm_aevent_is_on(net))
xfrm_replay_notify(x, XFRM_REPLAY_UPDATE);
}
x->curlft.bytes += skb->len;
x->curlft.packets++;
spin_unlock_bh(&x->lock);
err = x->type->output(x, skb);
if (err == -EINPROGRESS)
goto out_exit;
resume:
if (err) {
XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTSTATEPROTOERROR);
goto error_nolock;
}
dst = skb_dst_pop(skb);
if (!dst) {
XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTERROR);
err = -EHOSTUNREACH;
goto error_nolock;
}
skb_dst_set_noref(skb, dst);
x = dst->xfrm;
} while (x && !(x->outer_mode->flags & XFRM_MODE_FLAG_TUNNEL));
err = 0;
out_exit:
return err;
error:
spin_unlock_bh(&x->lock);
error_nolock:
kfree_skb(skb);
goto out_exit;
}
/*
* Deliver the packet to the host
*/
void ip6_protocol_deliver_rcu(struct net *net, struct sk_buff *skb, int nexthdr,
bool have_final)
{
const struct inet6_protocol *ipprot;
struct inet6_dev *idev;
unsigned int nhoff;
bool raw;
/*
* Parse extension headers
*/
resubmit:
idev = ip6_dst_idev(skb_dst(skb));
nhoff = IP6CB(skb)->nhoff;
if (!have_final) {
if (!pskb_pull(skb, skb_transport_offset(skb)))
goto discard;
nexthdr = skb_network_header(skb)[nhoff];
}
resubmit_final:
raw = raw6_local_deliver(skb, nexthdr);
ipprot = rcu_dereference(inet6_protos[nexthdr]);
if (ipprot) {
int ret;
if (have_final) {
if (!(ipprot->flags & INET6_PROTO_FINAL)) {
/* Once we've seen a final protocol don't
* allow encapsulation on any non-final
* ones. This allows foo in UDP encapsulation
* to work.
*/
goto discard;
}
} else if (ipprot->flags & INET6_PROTO_FINAL) {
const struct ipv6hdr *hdr;
int sdif = inet6_sdif(skb);
struct net_device *dev;
/* Only do this once for first final protocol */
have_final = true;
/* 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);
/* skb->dev passed may be master dev for vrfs. */
if (sdif) {
dev = dev_get_by_index_rcu(net, sdif);
if (!dev)
goto discard;
} else {
dev = skb->dev;
}
if (ipv6_addr_is_multicast(&hdr->daddr) &&
!ipv6_chk_mcast_addr(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) {
if (ipprot->flags & INET6_PROTO_FINAL) {
/* Not an extension header, most likely UDP
* encapsulation. Use return value as nexthdr
* protocol not nhoff (which presumably is
* not set by handler).
*/
nexthdr = ret;
goto resubmit_final;
} else {
goto resubmit;
}
} else if (ret == 0) {
__IP6_INC_STATS(net, idev, IPSTATS_MIB_INDELIVERS);
}
} else {
if (!raw) {
if (xfrm6_policy_check(NULL, XFRM_POLICY_IN, skb)) {
__IP6_INC_STATS(net, idev,
IPSTATS_MIB_INUNKNOWNPROTOS);
icmpv6_send(skb, ICMPV6_PARAMPROB,
ICMPV6_UNK_NEXTHDR, nhoff);
}
kfree_skb(skb);
} else {
__IP6_INC_STATS(net, idev, IPSTATS_MIB_INDELIVERS);
consume_skb(skb);
}
}
return;
discard:
__IP6_INC_STATS(net, idev, IPSTATS_MIB_INDISCARDS);
kfree_skb(skb);
}
/* Reroute packet to local IPv4 stack after DNAT */
static int
__ip_vs_reroute_locally(struct sk_buff *skb)
{
struct rtable *rt = skb_rtable(skb);
struct net_device *dev = rt->dst.dev;
struct net *net = dev_net(dev);
struct iphdr *iph = ip_hdr(skb);
if (rt_is_input_route(rt)) {
unsigned long orefdst = skb->_skb_refdst;
if (ip_route_input(skb, iph->daddr, iph->saddr,
iph->tos, skb->dev))
return 0;
refdst_drop(orefdst);
} else {
struct flowi4 fl4 = {
.daddr = iph->daddr,
.saddr = iph->saddr,
.flowi4_tos = RT_TOS(iph->tos),
.flowi4_mark = skb->mark,
};
rt = ip_route_output_key(net, &fl4);
if (IS_ERR(rt))
return 0;
if (!(rt->rt_flags & RTCF_LOCAL)) {
ip_rt_put(rt);
return 0;
}
/* Drop old route. */
skb_dst_drop(skb);
skb_dst_set(skb, &rt->dst);
}
return 1;
}
#ifdef CONFIG_IP_VS_IPV6
static inline int __ip_vs_is_local_route6(struct rt6_info *rt)
{
return rt->rt6i_dev && rt->rt6i_dev->flags & IFF_LOOPBACK;
}
static struct dst_entry *
__ip_vs_route_output_v6(struct net *net, struct in6_addr *daddr,
struct in6_addr *ret_saddr, int do_xfrm)
{
struct dst_entry *dst;
struct flowi6 fl6 = {
.daddr = *daddr,
};
dst = ip6_route_output(net, NULL, &fl6);
if (dst->error)
goto out_err;
if (!ret_saddr)
return dst;
if (ipv6_addr_any(&fl6.saddr) &&
ipv6_dev_get_saddr(net, ip6_dst_idev(dst)->dev,
&fl6.daddr, 0, &fl6.saddr) < 0)
goto out_err;
if (do_xfrm) {
dst = xfrm_lookup(net, dst, flowi6_to_flowi(&fl6), NULL, 0);
if (IS_ERR(dst)) {
dst = NULL;
goto out_err;
}
}
ipv6_addr_copy(ret_saddr, &fl6.saddr);
return dst;
out_err:
dst_release(dst);
IP_VS_DBG_RL("ip6_route_output error, dest: %pI6\n", daddr);
return NULL;
}
/*
* Get route to destination or remote server
*/
static struct rt6_info *
__ip_vs_get_out_rt_v6(struct sk_buff *skb, struct ip_vs_dest *dest,
struct in6_addr *daddr, struct in6_addr *ret_saddr,
int do_xfrm, int rt_mode)
{
struct net *net = dev_net(skb_dst(skb)->dev);
struct rt6_info *rt; /* Route to the other host */
struct rt6_info *ort; /* Original route */
struct dst_entry *dst;
int local;
if (dest) {
spin_lock(&dest->dst_lock);
rt = (struct rt6_info *)__ip_vs_dst_check(dest, 0);
if (!rt) {
u32 cookie;
dst = __ip_vs_route_output_v6(net, &dest->addr.in6,
&dest->dst_saddr.in6,
do_xfrm);
if (!dst) {
spin_unlock(&dest->dst_lock);
return NULL;
}
rt = (struct rt6_info *) dst;
cookie = rt->rt6i_node ? rt->rt6i_node->fn_sernum : 0;
__ip_vs_dst_set(dest, 0, dst_clone(&rt->dst), cookie);
IP_VS_DBG(10, "new dst %pI6, src %pI6, refcnt=%d\n",
&dest->addr.in6, &dest->dst_saddr.in6,
atomic_read(&rt->dst.__refcnt));
}
if (ret_saddr)
ipv6_addr_copy(ret_saddr, &dest->dst_saddr.in6);
spin_unlock(&dest->dst_lock);
} else {
dst = __ip_vs_route_output_v6(net, daddr, ret_saddr, do_xfrm);
if (!dst)
return NULL;
rt = (struct rt6_info *) dst;
}
local = __ip_vs_is_local_route6(rt);
if (!((local ? IP_VS_RT_MODE_LOCAL : IP_VS_RT_MODE_NON_LOCAL) &
rt_mode)) {
IP_VS_DBG_RL("Stopping traffic to %s address, dest: %pI6\n",
local ? "local":"non-local", daddr);
dst_release(&rt->dst);
return NULL;
}
if (local && !(rt_mode & IP_VS_RT_MODE_RDR) &&
!((ort = (struct rt6_info *) skb_dst(skb)) &&
__ip_vs_is_local_route6(ort))) {
IP_VS_DBG_RL("Redirect from non-local address %pI6 to local "
"requires NAT method, dest: %pI6\n",
&ipv6_hdr(skb)->daddr, daddr);
dst_release(&rt->dst);
return NULL;
}
if (unlikely(!local && (!skb->dev || skb->dev->flags & IFF_LOOPBACK) &&
ipv6_addr_type(&ipv6_hdr(skb)->saddr) &
IPV6_ADDR_LOOPBACK)) {
IP_VS_DBG_RL("Stopping traffic from loopback address %pI6 "
"to non-local address, dest: %pI6\n",
&ipv6_hdr(skb)->saddr, daddr);
dst_release(&rt->dst);
return NULL;
}
return rt;
}
#endif
/*
* Release dest->dst_cache before a dest is removed
*/
void
ip_vs_dst_reset(struct ip_vs_dest *dest)
{
struct dst_entry *old_dst;
old_dst = dest->dst_cache;
dest->dst_cache = NULL;
dst_release(old_dst);
}
#define IP_VS_XMIT_TUNNEL(skb, cp) \
({ \
int __ret = NF_ACCEPT; \
\
(skb)->ipvs_property = 1; \
if (unlikely((cp)->flags & IP_VS_CONN_F_NFCT)) \
__ret = ip_vs_confirm_conntrack(skb); \
if (__ret == NF_ACCEPT) { \
nf_reset(skb); \
skb_forward_csum(skb); \
} \
__ret; \
})
#define IP_VS_XMIT_NAT(pf, skb, cp, local) \
do { \
(skb)->ipvs_property = 1; \
if (likely(!((cp)->flags & IP_VS_CONN_F_NFCT))) \
ip_vs_notrack(skb); \
else \
ip_vs_update_conntrack(skb, cp, 1); \
if (local) \
return NF_ACCEPT; \
skb_forward_csum(skb); \
NF_HOOK(pf, NF_INET_LOCAL_OUT, (skb), NULL, \
skb_dst(skb)->dev, dst_output); \
} while (0)
#define IP_VS_XMIT(pf, skb, cp, local) \
do { \
(skb)->ipvs_property = 1; \
if (likely(!((cp)->flags & IP_VS_CONN_F_NFCT))) \
ip_vs_notrack(skb); \
if (local) \
return NF_ACCEPT; \
skb_forward_csum(skb); \
NF_HOOK(pf, NF_INET_LOCAL_OUT, (skb), NULL, \
skb_dst(skb)->dev, dst_output); \
} while (0)
/*
* NULL transmitter (do nothing except return NF_ACCEPT)
*/
int
ip_vs_null_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
struct ip_vs_protocol *pp)
{
/* we do not touch skb and do not need pskb ptr */
IP_VS_XMIT(NFPROTO_IPV4, skb, cp, 1);
}
int
ip_vs_nat_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
struct ip_vs_protocol *pp)
{
struct rt6_info *rt; /* Route to the other host */
int mtu;
int local;
EnterFunction(10);
/* check if it is a connection of no-client-port */
if (unlikely(cp->flags & IP_VS_CONN_F_NO_CPORT)) {
__be16 _pt, *p;
p = skb_header_pointer(skb, sizeof(struct ipv6hdr),
sizeof(_pt), &_pt);
if (p == NULL)
goto tx_error;
ip_vs_conn_fill_cport(cp, *p);
IP_VS_DBG(10, "filled cport=%d\n", ntohs(*p));
}
if (!(rt = __ip_vs_get_out_rt_v6(skb, cp->dest, &cp->daddr.in6, NULL,
0, (IP_VS_RT_MODE_LOCAL |
IP_VS_RT_MODE_NON_LOCAL |
IP_VS_RT_MODE_RDR))))
goto tx_error_icmp;
local = __ip_vs_is_local_route6(rt);
/*
* Avoid duplicate tuple in reply direction for NAT traffic
* to local address when connection is sync-ed
*/
#if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE)
if (cp->flags & IP_VS_CONN_F_SYNC && local) {
enum ip_conntrack_info ctinfo;
struct nf_conn *ct = ct = nf_ct_get(skb, &ctinfo);
if (ct && !nf_ct_is_untracked(ct)) {
IP_VS_DBG_RL_PKT(10, AF_INET6, pp, skb, 0,
"ip_vs_nat_xmit_v6(): "
"stopping DNAT to local address");
goto tx_error_put;
}
}
#endif
/* From world but DNAT to loopback address? */
if (local && skb->dev && !(skb->dev->flags & IFF_LOOPBACK) &&
ipv6_addr_type(&rt->rt6i_dst.addr) & IPV6_ADDR_LOOPBACK) {
IP_VS_DBG_RL_PKT(1, AF_INET6, pp, skb, 0,
"ip_vs_nat_xmit_v6(): "
"stopping DNAT to loopback address");
goto tx_error_put;
}
/* MTU checking */
mtu = dst_mtu(&rt->dst);
if (skb->len > mtu && !skb_is_gso(skb)) {
if (!skb->dev) {
struct net *net = dev_net(skb_dst(skb)->dev);
skb->dev = net->loopback_dev;
}
icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
IP_VS_DBG_RL_PKT(0, AF_INET6, pp, skb, 0,
"ip_vs_nat_xmit_v6(): frag needed for");
goto tx_error_put;
}
/* copy-on-write the packet before mangling it */
if (!skb_make_writable(skb, sizeof(struct ipv6hdr)))
goto tx_error_put;
if (skb_cow(skb, rt->dst.dev->hard_header_len))
goto tx_error_put;
/* mangle the packet */
if (pp->dnat_handler && !pp->dnat_handler(skb, pp, cp))
goto tx_error;
ipv6_addr_copy(&ipv6_hdr(skb)->daddr, &cp->daddr.in6);
if (!local || !skb->dev) {
/* drop the old route when skb is not shared */
skb_dst_drop(skb);
skb_dst_set(skb, &rt->dst);
} else {
/* destined to loopback, do we need to change route? */
dst_release(&rt->dst);
}
IP_VS_DBG_PKT(10, AF_INET6, pp, skb, 0, "After DNAT");
/* FIXME: when application helper enlarges the packet and the length
is larger than the MTU of outgoing device, there will be still
MTU problem. */
/* Another hack: avoid icmp_send in ip_fragment */
skb->local_df = 1;
IP_VS_XMIT_NAT(NFPROTO_IPV6, skb, cp, local);
LeaveFunction(10);
return NF_STOLEN;
tx_error_icmp:
dst_link_failure(skb);
tx_error:
LeaveFunction(10);
kfree_skb(skb);
return NF_STOLEN;
tx_error_put:
dst_release(&rt->dst);
goto tx_error;
}
int
ip_vs_dr_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
struct ip_vs_protocol *pp)
{
struct rt6_info *rt; /* Route to the other host */
int mtu;
EnterFunction(10);
if (!(rt = __ip_vs_get_out_rt_v6(skb, cp->dest, &cp->daddr.in6, NULL,
0, (IP_VS_RT_MODE_LOCAL |
IP_VS_RT_MODE_NON_LOCAL))))
goto tx_error_icmp;
if (__ip_vs_is_local_route6(rt)) {
dst_release(&rt->dst);
IP_VS_XMIT(NFPROTO_IPV6, skb, cp, 1);
}
/* MTU checking */
mtu = dst_mtu(&rt->dst);
if (skb->len > mtu) {
if (!skb->dev) {
struct net *net = dev_net(skb_dst(skb)->dev);
skb->dev = net->loopback_dev;
}
icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
dst_release(&rt->dst);
IP_VS_DBG_RL("%s(): frag needed\n", __func__);
goto tx_error;
}
/*
* Call ip_send_check because we are not sure it is called
* after ip_defrag. Is copy-on-write needed?
*/
skb = skb_share_check(skb, GFP_ATOMIC);
if (unlikely(skb == NULL)) {
dst_release(&rt->dst);
return NF_STOLEN;
}
/* drop old route */
skb_dst_drop(skb);
skb_dst_set(skb, &rt->dst);
/* Another hack: avoid icmp_send in ip_fragment */
skb->local_df = 1;
IP_VS_XMIT(NFPROTO_IPV6, skb, cp, 0);
LeaveFunction(10);
return NF_STOLEN;
tx_error_icmp:
dst_link_failure(skb);
tx_error:
kfree_skb(skb);
LeaveFunction(10);
return NF_STOLEN;
}
int
ip_vs_icmp_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
struct ip_vs_protocol *pp, int offset, unsigned int hooknum)
{
struct rt6_info *rt; /* Route to the other host */
int mtu;
int rc;
int local;
int rt_mode;
EnterFunction(10);
/* The ICMP packet for VS/TUN, VS/DR and LOCALNODE will be
forwarded directly here, because there is no need to
translate address/port back */
if (IP_VS_FWD_METHOD(cp) != IP_VS_CONN_F_MASQ) {
if (cp->packet_xmit)
rc = cp->packet_xmit(skb, cp, pp);
else
rc = NF_ACCEPT;
/* do not touch skb anymore */
atomic_inc(&cp->in_pkts);
goto out;
}
/*
* mangle and send the packet here (only for VS/NAT)
*/
/* LOCALNODE from FORWARD hook is not supported */
rt_mode = (hooknum != NF_INET_FORWARD) ?
IP_VS_RT_MODE_LOCAL | IP_VS_RT_MODE_NON_LOCAL |
IP_VS_RT_MODE_RDR : IP_VS_RT_MODE_NON_LOCAL;
if (!(rt = __ip_vs_get_out_rt_v6(skb, cp->dest, &cp->daddr.in6, NULL,
0, rt_mode)))
goto tx_error_icmp;
local = __ip_vs_is_local_route6(rt);
/*
* Avoid duplicate tuple in reply direction for NAT traffic
* to local address when connection is sync-ed
*/
#if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE)
if (cp->flags & IP_VS_CONN_F_SYNC && local) {
enum ip_conntrack_info ctinfo;
struct nf_conn *ct = ct = nf_ct_get(skb, &ctinfo);
if (ct && !nf_ct_is_untracked(ct)) {
IP_VS_DBG(10, "%s(): "
"stopping DNAT to local address %pI6\n",
__func__, &cp->daddr.in6);
goto tx_error_put;
}
}
#endif
/* From world but DNAT to loopback address? */
if (local && skb->dev && !(skb->dev->flags & IFF_LOOPBACK) &&
ipv6_addr_type(&rt->rt6i_dst.addr) & IPV6_ADDR_LOOPBACK) {
IP_VS_DBG(1, "%s(): "
"stopping DNAT to loopback %pI6\n",
__func__, &cp->daddr.in6);
goto tx_error_put;
}
/* MTU checking */
mtu = dst_mtu(&rt->dst);
if (skb->len > mtu && !skb_is_gso(skb)) {
if (!skb->dev) {
struct net *net = dev_net(skb_dst(skb)->dev);
skb->dev = net->loopback_dev;
}
icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
IP_VS_DBG_RL("%s(): frag needed\n", __func__);
goto tx_error_put;
}
/* copy-on-write the packet before mangling it */
if (!skb_make_writable(skb, offset))
goto tx_error_put;
if (skb_cow(skb, rt->dst.dev->hard_header_len))
goto tx_error_put;
ip_vs_nat_icmp_v6(skb, pp, cp, 0);
if (!local || !skb->dev) {
/* drop the old route when skb is not shared */
skb_dst_drop(skb);
skb_dst_set(skb, &rt->dst);
} else {
/* destined to loopback, do we need to change route? */
dst_release(&rt->dst);
}
/* Another hack: avoid icmp_send in ip_fragment */
skb->local_df = 1;
IP_VS_XMIT_NAT(NFPROTO_IPV6, skb, cp, local);
rc = NF_STOLEN;
goto out;
tx_error_icmp:
dst_link_failure(skb);
tx_error:
dev_kfree_skb(skb);
rc = NF_STOLEN;
out:
LeaveFunction(10);
return rc;
tx_error_put:
dst_release(&rt->dst);
goto tx_error;
}
//-----------------------------------------------------------------------------
static int _gtpusp_ksocket_process_gtp(const unsigned char * const rx_buf_pP, const int lenP, unsigned char* tx_buf_pP)
//-----------------------------------------------------------------------------
{
gtpv1u_msg_t gtpv1u_msg;
uint8_t msg_type;
struct iphdr *iph_p = NULL;
struct iphdr *new_iph_p= NULL;
struct sk_buff *skb_p = NULL;
const unsigned char * rx_buf_p = rx_buf_pP;
int err = 0;
struct rtable *rt = NULL;
struct flowi fl = {
.u = {
.ip4 = {
.daddr = 0,
.flowi4_tos = 0,
.flowi4_scope = RT_SCOPE_UNIVERSE,
}
}
};
msg_type = rx_buf_pP[1];
switch(msg_type) {
case GTP_ECHO_REQ:
PR_INFO(MODULE_NAME": TODO GTP ECHO_REQ, SEND TO GTPV1U TASK USER SPACE\n");
//TODO;
return 0;
break;
case GTP_ERROR_INDICATION:
PR_INFO(MODULE_NAME":TODO GTP ERROR INDICATION, SEND TO GTPV1U TASK USER SPACE\n");
//TODO;
return 0;
break;
case GTP_ECHO_RSP:
PR_INFO(MODULE_NAME":GTP ECHO_RSP, SEND TO GTPV1U TASK USER SPACE\n");
return 0;
break;
case GTP_GPDU: {
gtpv1u_msg.version = ((*rx_buf_p) & 0xE0) >> 5;
gtpv1u_msg.protocol_type = ((*rx_buf_p) & 0x10) >> 4;
gtpv1u_msg.ext_hdr_flag = ((*rx_buf_p) & 0x04) >> 2;
gtpv1u_msg.seq_num_flag = ((*rx_buf_p) & 0x02) >> 1;
gtpv1u_msg.npdu_num_flag = ((*rx_buf_p) & 0x01);
rx_buf_p++;
gtpv1u_msg.msg_type = *(rx_buf_p);
rx_buf_p++;
rx_buf_p += 2;
gtpv1u_msg.teid = ntohl(*((u_int32_t *)rx_buf_p));
rx_buf_p += 4;
if(gtpv1u_msg.ext_hdr_flag || gtpv1u_msg.seq_num_flag || gtpv1u_msg.npdu_num_flag) {
gtpv1u_msg.seq_num = ntohs(*(((u_int16_t *)rx_buf_p)));
rx_buf_p += 2;
gtpv1u_msg.npdu_num = *(rx_buf_p++);
gtpv1u_msg.next_ext_hdr_type = *(rx_buf_p++);
}
gtpv1u_msg.msg_buf_offset = (u_int32_t)(rx_buf_p - rx_buf_pP);
gtpv1u_msg.msg_buf_len = lenP - gtpv1u_msg.msg_buf_offset;
gtpv1u_msg.msg_len = lenP;
iph_p = (struct iphdr*)(&rx_buf_pP[gtpv1u_msg.msg_buf_offset]);
fl.u.ip4.daddr = iph_p->daddr;
fl.u.ip4.flowi4_tos = RT_TOS(iph_p->tos);
rt = ip_route_output_key(&init_net, &fl.u.ip4);
if (rt == NULL) {
PR_INFO("GTPURH: Failed to route packet to dst 0x%x. Error: (%d)\n", fl.u.ip4.daddr, err);
return NF_DROP;
}
if (rt->dst.dev == NULL) {
pr_info("GTPURH: dst dev NULL\n");
return 0;
}
skb_p = alloc_skb(LL_MAX_HEADER + ntohs(iph_p->tot_len), GFP_ATOMIC);
if (skb_p == NULL) {
return 0;
}
skb_p->priority = rt_tos2priority(iph_p->tos);
skb_p->pkt_type = PACKET_OTHERHOST;
skb_dst_set(skb_p, dst_clone(&rt->dst));
skb_p->dev = skb_dst(skb_p)->dev;
skb_reserve(skb_p, LL_MAX_HEADER + ntohs(iph_p->tot_len));
skb_p->protocol = htons(ETH_P_IP);
new_iph_p = (void *)skb_push(skb_p, ntohs(iph_p->tot_len) - (iph_p->ihl << 2));
skb_reset_transport_header(skb_p);
new_iph_p = (void *)skb_push(skb_p, iph_p->ihl << 2);
memcpy(new_iph_p, iph_p, ntohs(iph_p->tot_len));
skb_reset_network_header(skb_p);
skb_reset_inner_network_header(skb_p);
skb_reset_inner_transport_header(skb_p);
skb_p->mark = gtpv1u_msg.teid;
new_iph_p->ttl = ip4_dst_hoplimit(skb_dst(skb_p));
skb_p->ip_summed = CHECKSUM_NONE;
if (skb_p->len > dst_mtu(skb_dst(skb_p))) {
PR_INFO("GTPURH: bad length\n");
goto free_skb;
}
ip_local_out(skb_p);
return 0;
free_skb:
pr_info("GTPURH: Dropped skb\n");
kfree_skb(skb_p);
return 0;
}
break;
default:
PR_INFO(MODULE_NAME":ERROR GTPU msg type %u\n", msg_type);
return 0;
}
}
/* Send RST reply */
static void send_reset(struct sk_buff *oldskb, int hook)
{
struct sk_buff *nskb;
const struct iphdr *oiph;
struct iphdr *niph;
const struct tcphdr *oth;
struct tcphdr _otcph, *tcph;
/* IP header checks: fragment. */
if (ip_hdr(oldskb)->frag_off & htons(IP_OFFSET))
return;
oth = skb_header_pointer(oldskb, ip_hdrlen(oldskb),
sizeof(_otcph), &_otcph);
if (oth == NULL)
return;
/* No RST for RST. */
if (oth->rst)
return;
if (skb_rtable(oldskb)->rt_flags & (RTCF_BROADCAST | RTCF_MULTICAST))
return;
/* Check checksum */
if (nf_ip_checksum(oldskb, hook, ip_hdrlen(oldskb), IPPROTO_TCP))
return;
oiph = ip_hdr(oldskb);
nskb = alloc_skb(sizeof(struct iphdr) + sizeof(struct tcphdr) +
LL_MAX_HEADER, GFP_ATOMIC);
if (!nskb)
return;
skb_reserve(nskb, LL_MAX_HEADER);
skb_reset_network_header(nskb);
niph = (struct iphdr *)skb_put(nskb, sizeof(struct iphdr));
niph->version = 4;
niph->ihl = sizeof(struct iphdr) / 4;
niph->tos = 0;
niph->id = 0;
niph->frag_off = htons(IP_DF);
niph->protocol = IPPROTO_TCP;
niph->check = 0;
niph->saddr = oiph->daddr;
niph->daddr = oiph->saddr;
tcph = (struct tcphdr *)skb_put(nskb, sizeof(struct tcphdr));
memset(tcph, 0, sizeof(*tcph));
tcph->source = oth->dest;
tcph->dest = oth->source;
tcph->doff = sizeof(struct tcphdr) / 4;
if (oth->ack)
tcph->seq = oth->ack_seq;
else {
tcph->ack_seq = htonl(ntohl(oth->seq) + oth->syn + oth->fin +
oldskb->len - ip_hdrlen(oldskb) -
(oth->doff << 2));
tcph->ack = 1;
}
tcph->rst = 1;
tcph->check = ~tcp_v4_check(sizeof(struct tcphdr), niph->saddr,
niph->daddr, 0);
nskb->ip_summed = CHECKSUM_PARTIAL;
nskb->csum_start = (unsigned char *)tcph - nskb->head;
nskb->csum_offset = offsetof(struct tcphdr, check);
/* ip_route_me_harder expects skb->dst to be set */
skb_dst_set_noref(nskb, skb_dst(oldskb));
nskb->protocol = htons(ETH_P_IP);
if (ip_route_me_harder(nskb, RTN_UNSPEC))
goto free_nskb;
niph->ttl = ip4_dst_hoplimit(skb_dst(nskb));
/* "Never happens" */
if (nskb->len > dst_mtu(skb_dst(nskb)))
goto free_nskb;
nf_ct_attach(nskb, oldskb);
ip_local_out(nskb);
return;
free_nskb:
kfree_skb(nskb);
}
static int ip6mr_cache_report(struct net *net, struct sk_buff *pkt, mifi_t mifi,
int assert)
{
struct sk_buff *skb;
struct mrt6msg *msg;
int ret;
#ifdef CONFIG_IPV6_PIMSM_V2
if (assert == MRT6MSG_WHOLEPKT)
skb = skb_realloc_headroom(pkt, -skb_network_offset(pkt)
+sizeof(*msg));
else
#endif
skb = alloc_skb(sizeof(struct ipv6hdr) + sizeof(*msg), GFP_ATOMIC);
if (!skb)
return -ENOBUFS;
/* I suppose that internal messages
* do not require checksums */
skb->ip_summed = CHECKSUM_UNNECESSARY;
#ifdef CONFIG_IPV6_PIMSM_V2
if (assert == MRT6MSG_WHOLEPKT) {
/* Ugly, but we have no choice with this interface.
Duplicate old header, fix length etc.
And all this only to mangle msg->im6_msgtype and
to set msg->im6_mbz to "mbz" :-)
*/
skb_push(skb, -skb_network_offset(pkt));
skb_push(skb, sizeof(*msg));
skb_reset_transport_header(skb);
msg = (struct mrt6msg *)skb_transport_header(skb);
msg->im6_mbz = 0;
msg->im6_msgtype = MRT6MSG_WHOLEPKT;
msg->im6_mif = net->ipv6.mroute_reg_vif_num;
msg->im6_pad = 0;
ipv6_addr_copy(&msg->im6_src, &ipv6_hdr(pkt)->saddr);
ipv6_addr_copy(&msg->im6_dst, &ipv6_hdr(pkt)->daddr);
skb->ip_summed = CHECKSUM_UNNECESSARY;
} else
#endif
{
/*
* Copy the IP header
*/
skb_put(skb, sizeof(struct ipv6hdr));
skb_reset_network_header(skb);
skb_copy_to_linear_data(skb, ipv6_hdr(pkt), sizeof(struct ipv6hdr));
/*
* Add our header
*/
skb_put(skb, sizeof(*msg));
skb_reset_transport_header(skb);
msg = (struct mrt6msg *)skb_transport_header(skb);
msg->im6_mbz = 0;
msg->im6_msgtype = assert;
msg->im6_mif = mifi;
msg->im6_pad = 0;
ipv6_addr_copy(&msg->im6_src, &ipv6_hdr(pkt)->saddr);
ipv6_addr_copy(&msg->im6_dst, &ipv6_hdr(pkt)->daddr);
skb_dst_set(skb, dst_clone(skb_dst(pkt)));
skb->ip_summed = CHECKSUM_UNNECESSARY;
}
if (net->ipv6.mroute6_sk == NULL) {
kfree_skb(skb);
return -EINVAL;
}
/*
* Deliver to user space multicast routing algorithms
*/
ret = sock_queue_rcv_skb(net->ipv6.mroute6_sk, skb);
if (ret < 0) {
if (net_ratelimit())
printk(KERN_WARNING "mroute6: pending queue full, dropping entries.\n");
kfree_skb(skb);
}
return ret;
}
static unsigned int
echo_tg4(struct sk_buff **poldskb, const struct xt_action_param *par)
{
const struct sk_buff *oldskb = *poldskb;
const struct udphdr *oldudp;
const struct iphdr *oldip;
struct udphdr *newudp, oldudp_buf;
struct iphdr *newip;
struct sk_buff *newskb;
unsigned int data_len;
void *payload;
/* This allows us to do the copy operation in fewer lines of code. */
if (skb_linearize(*poldskb) < 0)
return NF_DROP;
oldip = ip_hdr(oldskb);
oldudp = skb_header_pointer(oldskb, par->thoff,
sizeof(*oldudp), &oldudp_buf);
if (oldudp == NULL)
return NF_DROP;
if (ntohs(oldudp->len) <= sizeof(*oldudp))
return NF_DROP;
newskb = alloc_skb(LL_MAX_HEADER + sizeof(*newip) +
ntohs(oldudp->len), GFP_ATOMIC);
if (newskb == NULL)
return NF_DROP;
skb_reserve(newskb, LL_MAX_HEADER);
newskb->protocol = oldskb->protocol;
skb_reset_network_header(newskb);
newip = (void *)skb_put(newskb, sizeof(*newip));
newip->version = oldip->version;
newip->ihl = sizeof(*newip) / 4;
newip->tos = oldip->tos;
newip->id = 0;
newip->frag_off = htons(IP_DF);
newip->protocol = oldip->protocol;
newip->check = 0;
newip->saddr = oldip->daddr;
newip->daddr = oldip->saddr;
skb_reset_transport_header(newskb);
newudp = (void *)skb_put(newskb, sizeof(*newudp));
newudp->source = oldudp->dest;
newudp->dest = oldudp->source;
newudp->len = oldudp->len;
data_len = htons(oldudp->len) - sizeof(*oldudp);
payload = skb_header_pointer(oldskb, par->thoff +
sizeof(*oldudp), data_len, NULL);
memcpy(skb_put(newskb, data_len), payload, data_len);
#if 0
/*
* Since no fields are modified (we just swapped things around),
* this works too in our specific echo case.
*/
newudp->check = oldudp->check;
#else
newudp->check = 0;
newudp->check = csum_tcpudp_magic(newip->saddr, newip->daddr,
ntohs(newudp->len), IPPROTO_UDP,
csum_partial(newudp, ntohs(newudp->len), 0));
#endif
/* ip_route_me_harder expects the skb's dst to be set */
skb_dst_set(newskb, dst_clone(skb_dst(oldskb)));
if (ip_route_me_harder(&newskb, RTN_UNSPEC) != 0)
goto free_nskb;
#if LINUX_VERSION_CODE >= KERNEL_VERSION(2, 6, 38)
newip->ttl = ip4_dst_hoplimit(skb_dst(newskb));
#else
newip->ttl = dst_metric(skb_dst(newskb), RTAX_HOPLIMIT);
#endif
newskb->ip_summed = CHECKSUM_NONE;
/* "Never happens" (?) */
if (newskb->len > dst_mtu(skb_dst(newskb)))
goto free_nskb;
nf_ct_attach(newskb, *poldskb);
ip_local_out(newskb);
return NF_DROP;
free_nskb:
kfree_skb(newskb);
return NF_DROP;
}
/*
* IP Tunneling transmitter
*
* This function encapsulates the packet in a new IP packet, its
* destination will be set to cp->daddr. Most code of this function
* is taken from ipip.c.
*
* It is used in VS/TUN cluster. The load balancer selects a real
* server from a cluster based on a scheduling algorithm,
* encapsulates the request packet and forwards it to the selected
* server. For example, all real servers are configured with
* "ifconfig tunl0 <Virtual IP Address> up". When the server receives
* the encapsulated packet, it will decapsulate the packet, processe
* the request and return the response packets directly to the client
* without passing the load balancer. This can greatly increase the
* scalability of virtual server.
*
* Used for ANY protocol
*/
int
ip_vs_tunnel_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
struct ip_vs_protocol *pp)
{
struct rtable *rt; /* Route to the other host */
__be32 saddr; /* Source for tunnel */
struct net_device *tdev; /* Device to other host */
struct iphdr *old_iph = ip_hdr(skb);
u8 tos = old_iph->tos;
__be16 df = old_iph->frag_off;
struct iphdr *iph; /* Our new IP header */
unsigned int max_headroom; /* The extra header space needed */
int mtu;
int ret;
EnterFunction(10);
if (!(rt = __ip_vs_get_out_rt(skb, cp->dest, cp->daddr.ip,
RT_TOS(tos), IP_VS_RT_MODE_LOCAL |
IP_VS_RT_MODE_NON_LOCAL,
&saddr)))
goto tx_error_icmp;
if (rt->rt_flags & RTCF_LOCAL) {
ip_rt_put(rt);
IP_VS_XMIT(NFPROTO_IPV4, skb, cp, 1);
}
tdev = rt->dst.dev;
mtu = dst_mtu(&rt->dst) - sizeof(struct iphdr);
if (mtu < 68) {
IP_VS_DBG_RL("%s(): mtu less than 68\n", __func__);
goto tx_error_put;
}
if (skb_dst(skb))
skb_dst(skb)->ops->update_pmtu(skb_dst(skb), mtu);
df |= (old_iph->frag_off & htons(IP_DF));
if ((old_iph->frag_off & htons(IP_DF) &&
mtu < ntohs(old_iph->tot_len) && !skb_is_gso(skb))) {
icmp_send(skb, ICMP_DEST_UNREACH,ICMP_FRAG_NEEDED, htonl(mtu));
IP_VS_DBG_RL("%s(): frag needed\n", __func__);
goto tx_error_put;
}
/*
* Okay, now see if we can stuff it in the buffer as-is.
*/
max_headroom = LL_RESERVED_SPACE(tdev) + sizeof(struct iphdr);
if (skb_headroom(skb) < max_headroom
|| skb_cloned(skb) || skb_shared(skb)) {
struct sk_buff *new_skb =
skb_realloc_headroom(skb, max_headroom);
if (!new_skb) {
ip_rt_put(rt);
kfree_skb(skb);
IP_VS_ERR_RL("%s(): no memory\n", __func__);
return NF_STOLEN;
}
kfree_skb(skb);
skb = new_skb;
old_iph = ip_hdr(skb);
}
skb->transport_header = skb->network_header;
/* fix old IP header checksum */
ip_send_check(old_iph);
skb_push(skb, sizeof(struct iphdr));
skb_reset_network_header(skb);
memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt));
/* drop old route */
skb_dst_drop(skb);
skb_dst_set(skb, &rt->dst);
/*
* Push down and install the IPIP header.
*/
iph = ip_hdr(skb);
iph->version = 4;
iph->ihl = sizeof(struct iphdr)>>2;
iph->frag_off = df;
iph->protocol = IPPROTO_IPIP;
iph->tos = tos;
iph->daddr = cp->daddr.ip;
iph->saddr = saddr;
iph->ttl = old_iph->ttl;
ip_select_ident(iph, &rt->dst, NULL);
/* Another hack: avoid icmp_send in ip_fragment */
skb->local_df = 1;
ret = IP_VS_XMIT_TUNNEL(skb, cp);
if (ret == NF_ACCEPT)
ip_local_out(skb);
else if (ret == NF_DROP)
kfree_skb(skb);
LeaveFunction(10);
return NF_STOLEN;
tx_error_icmp:
dst_link_failure(skb);
tx_error:
kfree_skb(skb);
LeaveFunction(10);
return NF_STOLEN;
tx_error_put:
ip_rt_put(rt);
goto tx_error;
}
static unsigned int
echo_tg6(struct sk_buff **poldskb, const struct xt_action_param *par)
{
const struct sk_buff *oldskb = *poldskb;
const struct udphdr *oldudp;
const struct ipv6hdr *oldip;
struct udphdr *newudp, oldudp_buf;
struct ipv6hdr *newip;
struct sk_buff *newskb;
unsigned int data_len;
void *payload;
struct flowi6 fl;
struct dst_entry *dst = NULL;
struct net *net = dev_net((par->in != NULL) ? par->in : par->out);
/* This allows us to do the copy operation in fewer lines of code. */
if (skb_linearize(*poldskb) < 0)
return NF_DROP;
oldip = ipv6_hdr(oldskb);
oldudp = skb_header_pointer(oldskb, par->thoff,
sizeof(*oldudp), &oldudp_buf);
if (oldudp == NULL)
return NF_DROP;
if (ntohs(oldudp->len) <= sizeof(*oldudp))
return NF_DROP;
newskb = alloc_skb(LL_MAX_HEADER + sizeof(*newip) +
ntohs(oldudp->len), GFP_ATOMIC);
if (newskb == NULL)
return NF_DROP;
skb_reserve(newskb, LL_MAX_HEADER);
newskb->protocol = oldskb->protocol;
skb_reset_network_header(newskb);
newip = (void *)skb_put(newskb, sizeof(*newip));
newip->version = oldip->version;
newip->priority = oldip->priority;
memcpy(newip->flow_lbl, oldip->flow_lbl, sizeof(newip->flow_lbl));
newip->nexthdr = par->target->proto;
newip->saddr = oldip->daddr;
newip->daddr = oldip->saddr;
skb_reset_transport_header(newskb);
newudp = (void *)skb_put(newskb, sizeof(*newudp));
newudp->source = oldudp->dest;
newudp->dest = oldudp->source;
newudp->len = oldudp->len;
data_len = htons(oldudp->len) - sizeof(*oldudp);
payload = skb_header_pointer(oldskb, par->thoff +
sizeof(*oldudp), data_len, NULL);
memcpy(skb_put(newskb, data_len), payload, data_len);
#if 0
/*
* Since no fields are modified (we just swapped things around),
* this works too in our specific echo case.
*/
newudp->check = oldudp->check;
#else
newudp->check = 0;
newudp->check = csum_ipv6_magic(&newip->saddr, &newip->daddr,
ntohs(newudp->len), IPPROTO_UDP,
csum_partial(newudp, ntohs(newudp->len), 0));
#endif
memset(&fl, 0, sizeof(fl));
fl.flowi6_proto = newip->nexthdr;
memcpy(&fl.saddr, &newip->saddr, sizeof(fl.saddr));
memcpy(&fl.daddr, &newip->daddr, sizeof(fl.daddr));
fl.fl6_sport = newudp->source;
fl.fl6_dport = newudp->dest;
security_skb_classify_flow((struct sk_buff *)oldskb, flowi6_to_flowi(&fl));
dst = ip6_route_output(net, NULL, &fl);
if (dst == NULL || dst->error != 0) {
dst_release(dst);
goto free_nskb;
}
skb_dst_set(newskb, dst);
#if LINUX_VERSION_CODE >= KERNEL_VERSION(2, 6, 38)
newip->hop_limit = ip6_dst_hoplimit(skb_dst(newskb));
#else
newip->hop_limit = dst_metric(skb_dst(newskb), RTAX_HOPLIMIT);
#endif
newskb->ip_summed = CHECKSUM_NONE;
/* "Never happens" (?) */
if (newskb->len > dst_mtu(skb_dst(newskb)))
goto free_nskb;
nf_ct_attach(newskb, *poldskb);
ip6_local_out(newskb);
return NF_DROP;
free_nskb:
kfree_skb(newskb);
return NF_DROP;
}
/* Get route to destination or remote server */
static struct rtable *
__ip_vs_get_out_rt(struct sk_buff *skb, struct ip_vs_dest *dest,
__be32 daddr, u32 rtos, int rt_mode, __be32 *ret_saddr)
{
struct net *net = dev_net(skb_dst(skb)->dev);
struct rtable *rt; /* Route to the other host */
struct rtable *ort; /* Original route */
int local;
if (dest) {
spin_lock(&dest->dst_lock);
if (!(rt = (struct rtable *)
__ip_vs_dst_check(dest, rtos))) {
struct flowi4 fl4;
memset(&fl4, 0, sizeof(fl4));
fl4.daddr = dest->addr.ip;
fl4.flowi4_tos = rtos;
rt = ip_route_output_key(net, &fl4);
if (IS_ERR(rt)) {
spin_unlock(&dest->dst_lock);
IP_VS_DBG_RL("ip_route_output error, dest: %pI4\n",
&dest->addr.ip);
return NULL;
}
__ip_vs_dst_set(dest, rtos, dst_clone(&rt->dst), 0);
dest->dst_saddr.ip = fl4.saddr;
IP_VS_DBG(10, "new dst %pI4, src %pI4, refcnt=%d, "
"rtos=%X\n",
&dest->addr.ip, &dest->dst_saddr.ip,
atomic_read(&rt->dst.__refcnt), rtos);
}
daddr = dest->addr.ip;
if (ret_saddr)
*ret_saddr = dest->dst_saddr.ip;
spin_unlock(&dest->dst_lock);
} else {
struct flowi4 fl4;
memset(&fl4, 0, sizeof(fl4));
fl4.daddr = daddr;
fl4.flowi4_tos = rtos;
rt = ip_route_output_key(net, &fl4);
if (IS_ERR(rt)) {
IP_VS_DBG_RL("ip_route_output error, dest: %pI4\n",
&daddr);
return NULL;
}
if (ret_saddr)
*ret_saddr = fl4.saddr;
}
local = rt->rt_flags & RTCF_LOCAL;
if (!((local ? IP_VS_RT_MODE_LOCAL : IP_VS_RT_MODE_NON_LOCAL) &
rt_mode)) {
IP_VS_DBG_RL("Stopping traffic to %s address, dest: %pI4\n",
(rt->rt_flags & RTCF_LOCAL) ?
"local":"non-local", &daddr);
ip_rt_put(rt);
return NULL;
}
if (local && !(rt_mode & IP_VS_RT_MODE_RDR) &&
!((ort = skb_rtable(skb)) && ort->rt_flags & RTCF_LOCAL)) {
IP_VS_DBG_RL("Redirect from non-local address %pI4 to local "
"requires NAT method, dest: %pI4\n",
&ip_hdr(skb)->daddr, &daddr);
ip_rt_put(rt);
return NULL;
}
if (unlikely(!local && ipv4_is_loopback(ip_hdr(skb)->saddr))) {
IP_VS_DBG_RL("Stopping traffic from loopback address %pI4 "
"to non-local address, dest: %pI4\n",
&ip_hdr(skb)->saddr, &daddr);
ip_rt_put(rt);
return NULL;
}
return rt;
}
static struct sk_buff *ip6_rcv_core(struct sk_buff *skb, struct net_device *dev,
struct net *net)
{
const struct ipv6hdr *hdr;
u32 pkt_len;
struct inet6_dev *idev;
if (skb->pkt_type == PACKET_OTHERHOST) {
kfree_skb(skb);
return NULL;
}
rcu_read_lock();
idev = __in6_dev_get(skb->dev);
__IP6_UPD_PO_STATS(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(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_valid_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;
__IP6_ADD_STATS(net, idev,
IPSTATS_MIB_NOECTPKTS +
(ipv6_get_dsfield(hdr) & INET_ECN_MASK),
max_t(unsigned short, 1, skb_shinfo(skb)->gso_segs));
/*
* RFC4291 2.5.3
* The loopback address must not be used as the source address in IPv6
* packets that are sent outside of a single node. [..]
* A packet received on an interface with a destination address
* of loopback must be dropped.
*/
if ((ipv6_addr_loopback(&hdr->saddr) ||
ipv6_addr_loopback(&hdr->daddr)) &&
!(dev->flags & IFF_LOOPBACK) &&
!netif_is_l3_master(dev))
goto err;
/* RFC4291 Errata ID: 3480
* Interface-Local scope spans only a single interface on a
* node and is useful only for loopback transmission of
* multicast. Packets with interface-local scope received
* from another node must be discarded.
*/
if (!(skb->pkt_type == PACKET_LOOPBACK ||
dev->flags & IFF_LOOPBACK) &&
ipv6_addr_is_multicast(&hdr->daddr) &&
IPV6_ADDR_MC_SCOPE(&hdr->daddr) == 1)
goto err;
/* If enabled, drop unicast packets that were encapsulated in link-layer
* multicast or broadcast to protected against the so-called "hole-196"
* attack in 802.11 wireless.
*/
if (!ipv6_addr_is_multicast(&hdr->daddr) &&
(skb->pkt_type == PACKET_BROADCAST ||
skb->pkt_type == PACKET_MULTICAST) &&
idev->cnf.drop_unicast_in_l2_multicast)
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(net,
idev, IPSTATS_MIB_INTRUNCATEDPKTS);
goto drop;
}
if (pskb_trim_rcsum(skb, pkt_len + sizeof(struct ipv6hdr))) {
__IP6_INC_STATS(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(net, idev, IPSTATS_MIB_INHDRERRORS);
rcu_read_unlock();
return NULL;
}
}
rcu_read_unlock();
/* Must drop socket now because of tproxy. */
skb_orphan(skb);
return skb;
err:
__IP6_INC_STATS(net, idev, IPSTATS_MIB_INHDRERRORS);
drop:
rcu_read_unlock();
kfree_skb(skb);
return NULL;
}
int
ip_vs_tunnel_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
struct ip_vs_protocol *pp)
{
struct rt6_info *rt; /* Route to the other host */
struct in6_addr saddr; /* Source for tunnel */
struct net_device *tdev; /* Device to other host */
struct ipv6hdr *old_iph = ipv6_hdr(skb);
struct ipv6hdr *iph; /* Our new IP header */
unsigned int max_headroom; /* The extra header space needed */
int mtu;
int ret;
EnterFunction(10);
if (!(rt = __ip_vs_get_out_rt_v6(skb, cp->dest, &cp->daddr.in6,
&saddr, 1, (IP_VS_RT_MODE_LOCAL |
IP_VS_RT_MODE_NON_LOCAL))))
goto tx_error_icmp;
if (__ip_vs_is_local_route6(rt)) {
dst_release(&rt->dst);
IP_VS_XMIT(NFPROTO_IPV6, skb, cp, 1);
}
tdev = rt->dst.dev;
mtu = dst_mtu(&rt->dst) - sizeof(struct ipv6hdr);
if (mtu < IPV6_MIN_MTU) {
IP_VS_DBG_RL("%s(): mtu less than %d\n", __func__,
IPV6_MIN_MTU);
goto tx_error_put;
}
if (skb_dst(skb))
skb_dst(skb)->ops->update_pmtu(skb_dst(skb), mtu);
if (mtu < ntohs(old_iph->payload_len) + sizeof(struct ipv6hdr) &&
!skb_is_gso(skb)) {
if (!skb->dev) {
struct net *net = dev_net(skb_dst(skb)->dev);
skb->dev = net->loopback_dev;
}
icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
IP_VS_DBG_RL("%s(): frag needed\n", __func__);
goto tx_error_put;
}
/*
* Okay, now see if we can stuff it in the buffer as-is.
*/
max_headroom = LL_RESERVED_SPACE(tdev) + sizeof(struct ipv6hdr);
if (skb_headroom(skb) < max_headroom
|| skb_cloned(skb) || skb_shared(skb)) {
struct sk_buff *new_skb =
skb_realloc_headroom(skb, max_headroom);
if (!new_skb) {
dst_release(&rt->dst);
kfree_skb(skb);
IP_VS_ERR_RL("%s(): no memory\n", __func__);
return NF_STOLEN;
}
kfree_skb(skb);
skb = new_skb;
old_iph = ipv6_hdr(skb);
}
skb->transport_header = skb->network_header;
skb_push(skb, sizeof(struct ipv6hdr));
skb_reset_network_header(skb);
memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt));
/* drop old route */
skb_dst_drop(skb);
skb_dst_set(skb, &rt->dst);
/*
* Push down and install the IPIP header.
*/
iph = ipv6_hdr(skb);
iph->version = 6;
iph->nexthdr = IPPROTO_IPV6;
iph->payload_len = old_iph->payload_len;
be16_add_cpu(&iph->payload_len, sizeof(*old_iph));
iph->priority = old_iph->priority;
memset(&iph->flow_lbl, 0, sizeof(iph->flow_lbl));
ipv6_addr_copy(&iph->daddr, &cp->daddr.in6);
ipv6_addr_copy(&iph->saddr, &saddr);
iph->hop_limit = old_iph->hop_limit;
/* Another hack: avoid icmp_send in ip_fragment */
skb->local_df = 1;
ret = IP_VS_XMIT_TUNNEL(skb, cp);
if (ret == NF_ACCEPT)
ip6_local_out(skb);
else if (ret == NF_DROP)
kfree_skb(skb);
LeaveFunction(10);
return NF_STOLEN;
tx_error_icmp:
dst_link_failure(skb);
tx_error:
kfree_skb(skb);
LeaveFunction(10);
return NF_STOLEN;
tx_error_put:
dst_release(&rt->dst);
goto tx_error;
}
int ip6_mc_input(struct sk_buff *skb)
{
int sdif = inet6_sdif(skb);
const struct ipv6hdr *hdr;
struct net_device *dev;
bool deliver;
__IP6_UPD_PO_STATS(dev_net(skb_dst(skb)->dev),
__in6_dev_get_safely(skb->dev), IPSTATS_MIB_INMCAST,
skb->len);
/* skb->dev passed may be master dev for vrfs. */
if (sdif) {
rcu_read_lock();
dev = dev_get_by_index_rcu(dev_net(skb->dev), sdif);
if (!dev) {
rcu_read_unlock();
kfree_skb(skb);
return -ENODEV;
}
} else {
dev = skb->dev;
}
hdr = ipv6_hdr(skb);
deliver = ipv6_chk_mcast_addr(dev, &hdr->daddr, NULL);
if (sdif)
rcu_read_unlock();
#ifdef CONFIG_IPV6_MROUTE
/*
* IPv6 multicast router mode is now supported ;)
*/
if (dev_net(skb->dev)->ipv6.devconf_all->mc_forwarding &&
!(ipv6_addr_type(&hdr->daddr) &
(IPV6_ADDR_LOOPBACK|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->flags & IP6SKB_ROUTERALERT)) {
/* Check if this is a mld message */
u8 nexthdr = hdr->nexthdr;
__be16 frag_off;
int offset;
/* Check if the value of Router Alert
* is for MLD (0x0000).
*/
if (opt->ra == htons(IPV6_OPT_ROUTERALERT_MLD)) {
deliver = false;
if (!ipv6_ext_hdr(nexthdr)) {
/* BUG */
goto out;
}
offset = ipv6_skip_exthdr(skb, sizeof(*hdr),
&nexthdr, &frag_off);
if (offset < 0)
goto out;
if (ipv6_is_mld(skb, nexthdr, offset))
deliver = true;
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);
else {
/* discard */
kfree_skb(skb);
}
return 0;
}
static inline void
_decode_session6(struct sk_buff *skb, struct flowi *fl, int reverse)
{
struct flowi6 *fl6 = &fl->u.ip6;
int onlyproto = 0;
u16 offset = skb_network_header_len(skb);
const struct ipv6hdr *hdr = ipv6_hdr(skb);
struct ipv6_opt_hdr *exthdr;
const unsigned char *nh = skb_network_header(skb);
u8 nexthdr = nh[IP6CB(skb)->nhoff];
int oif = 0;
if (skb_dst(skb))
oif = skb_dst(skb)->dev->ifindex;
memset(fl6, 0, sizeof(struct flowi6));
fl6->flowi6_mark = skb->mark;
fl6->flowi6_oif = reverse ? skb->skb_iif : oif;
fl6->daddr = reverse ? hdr->saddr : hdr->daddr;
fl6->saddr = reverse ? hdr->daddr : hdr->saddr;
while (nh + offset + 1 < skb->data ||
pskb_may_pull(skb, nh + offset + 1 - skb->data)) {
nh = skb_network_header(skb);
exthdr = (struct ipv6_opt_hdr *)(nh + offset);
switch (nexthdr) {
case NEXTHDR_FRAGMENT:
onlyproto = 1;
case NEXTHDR_ROUTING:
case NEXTHDR_HOP:
case NEXTHDR_DEST:
offset += ipv6_optlen(exthdr);
nexthdr = exthdr->nexthdr;
exthdr = (struct ipv6_opt_hdr *)(nh + offset);
break;
case IPPROTO_UDP:
case IPPROTO_UDPLITE:
case IPPROTO_TCP:
case IPPROTO_SCTP:
case IPPROTO_DCCP:
if (!onlyproto && (nh + offset + 4 < skb->data ||
pskb_may_pull(skb, nh + offset + 4 - skb->data))) {
__be16 *ports;
nh = skb_network_header(skb);
ports = (__be16 *)(nh + offset);
fl6->fl6_sport = ports[!!reverse];
fl6->fl6_dport = ports[!reverse];
}
fl6->flowi6_proto = nexthdr;
return;
case IPPROTO_ICMPV6:
if (!onlyproto && pskb_may_pull(skb, nh + offset + 2 - skb->data)) {
u8 *icmp;
nh = skb_network_header(skb);
icmp = (u8 *)(nh + offset);
fl6->fl6_icmp_type = icmp[0];
fl6->fl6_icmp_code = icmp[1];
}
fl6->flowi6_proto = nexthdr;
return;
#if IS_ENABLED(CONFIG_IPV6_MIP6)
case IPPROTO_MH:
if (!onlyproto && pskb_may_pull(skb, nh + offset + 3 - skb->data)) {
struct ip6_mh *mh;
nh = skb_network_header(skb);
mh = (struct ip6_mh *)(nh + offset);
fl6->fl6_mh_type = mh->ip6mh_type;
}
fl6->flowi6_proto = nexthdr;
return;
#endif
/* XXX Why are there these headers? */
case IPPROTO_AH:
case IPPROTO_ESP:
case IPPROTO_COMP:
default:
fl6->fl6_ipsec_spi = 0;
fl6->flowi6_proto = nexthdr;
return;
}
}
}
int ip6_mc_input(struct sk_buff *skb)
{
const struct ipv6hdr *hdr;
int deliver;
IP6_UPD_PO_STATS_BH(dev_net(skb_dst(skb)->dev),
ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_INMCAST,
skb->len);
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 &&
!(ipv6_addr_type(&hdr->daddr) &
(IPV6_ADDR_LOOPBACK|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;
struct icmp6hdr *icmp6;
u8 nexthdr = hdr->nexthdr;
__be16 frag_off;
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, &frag_off);
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) {
ip6_mr_input(skb2);
}
}
out:
#endif
if (likely(deliver))
ip6_input(skb);
else {
/* discard */
kfree_skb(skb);
}
return 0;
}
static netdev_tx_t ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev)
{
struct ip_tunnel *tunnel = netdev_priv(dev);
struct net_device_stats *stats = &tunnel->dev->stats;
struct iphdr *old_iph = ip_hdr(skb);
struct iphdr *tiph;
u8 tos;
__be16 df;
struct rtable *rt; /* Route to the other host */
struct net_device *tdev; /* Device to other host */
struct iphdr *iph; /* Our new IP header */
unsigned int max_headroom; /* The extra header space needed */
int gre_hlen;
__be32 dst;
int mtu;
if (dev->type == ARPHRD_ETHER)
IPCB(skb)->flags = 0;
if (dev->header_ops && dev->type == ARPHRD_IPGRE) {
gre_hlen = 0;
tiph = (struct iphdr *)skb->data;
} else {
gre_hlen = tunnel->hlen;
tiph = &tunnel->parms.iph;
}
if ((dst = tiph->daddr) == 0) {
/* NBMA tunnel */
if (skb_dst(skb) == NULL) {
stats->tx_fifo_errors++;
goto tx_error;
}
if (skb->protocol == htons(ETH_P_IP)) {
rt = skb_rtable(skb);
if ((dst = rt->rt_gateway) == 0)
goto tx_error_icmp;
}
#ifdef CONFIG_IPV6
else if (skb->protocol == htons(ETH_P_IPV6)) {
struct in6_addr *addr6;
int addr_type;
struct neighbour *neigh = skb_dst(skb)->neighbour;
if (neigh == NULL)
goto tx_error;
addr6 = (struct in6_addr *)&neigh->primary_key;
addr_type = ipv6_addr_type(addr6);
if (addr_type == IPV6_ADDR_ANY) {
addr6 = &ipv6_hdr(skb)->daddr;
addr_type = ipv6_addr_type(addr6);
}
if ((addr_type & IPV6_ADDR_COMPATv4) == 0)
goto tx_error_icmp;
dst = addr6->s6_addr32[3];
}
#endif
else
goto tx_error;
}
tos = tiph->tos;
if (tos == 1) {
tos = 0;
if (skb->protocol == htons(ETH_P_IP))
tos = old_iph->tos;
}
{
struct flowi fl = { .oif = tunnel->parms.link,
.nl_u = { .ip4_u =
{ .daddr = dst,
.saddr = tiph->saddr,
.tos = RT_TOS(tos) } },
.proto = IPPROTO_GRE };
if (ip_route_output_key(dev_net(dev), &rt, &fl)) {
stats->tx_carrier_errors++;
goto tx_error;
}
}
int ip6_push_pending_frames(struct sock *sk)
{
struct sk_buff *skb, *tmp_skb;
struct sk_buff **tail_skb;
struct in6_addr final_dst_buf, *final_dst = &final_dst_buf;
struct inet_sock *inet = inet_sk(sk);
struct ipv6_pinfo *np = inet6_sk(sk);
struct net *net = sock_net(sk);
struct ipv6hdr *hdr;
struct ipv6_txoptions *opt = np->cork.opt;
struct rt6_info *rt = (struct rt6_info *)inet->cork.base.dst;
struct flowi6 *fl6 = &inet->cork.fl.u.ip6;
unsigned char proto = fl6->flowi6_proto;
int err = 0;
if ((skb = __skb_dequeue(&sk->sk_write_queue)) == NULL)
goto out;
tail_skb = &(skb_shinfo(skb)->frag_list);
/* move skb->data to ip header from ext header */
if (skb->data < skb_network_header(skb))
__skb_pull(skb, skb_network_offset(skb));
while ((tmp_skb = __skb_dequeue(&sk->sk_write_queue)) != NULL) {
__skb_pull(tmp_skb, skb_network_header_len(skb));
*tail_skb = tmp_skb;
tail_skb = &(tmp_skb->next);
skb->len += tmp_skb->len;
skb->data_len += tmp_skb->len;
skb->truesize += tmp_skb->truesize;
tmp_skb->destructor = NULL;
tmp_skb->sk = NULL;
}
/* Allow local fragmentation. */
if (np->pmtudisc < IPV6_PMTUDISC_DO)
skb->local_df = 1;
*final_dst = fl6->daddr;
__skb_pull(skb, skb_network_header_len(skb));
if (opt && opt->opt_flen)
ipv6_push_frag_opts(skb, opt, &proto);
if (opt && opt->opt_nflen)
ipv6_push_nfrag_opts(skb, opt, &proto, &final_dst);
skb_push(skb, sizeof(struct ipv6hdr));
skb_reset_network_header(skb);
hdr = ipv6_hdr(skb);
*(__be32*)hdr = fl6->flowlabel |
htonl(0x60000000 | ((int)np->cork.tclass << 20));
hdr->hop_limit = np->cork.hop_limit;
hdr->nexthdr = proto;
hdr->saddr = fl6->saddr;
hdr->daddr = *final_dst;
skb->priority = sk->sk_priority;
skb->mark = sk->sk_mark;
skb_dst_set(skb, dst_clone(&rt->dst));
IP6_UPD_PO_STATS(net, rt->rt6i_idev, IPSTATS_MIB_OUT, skb->len);
if (proto == IPPROTO_ICMPV6) {
struct inet6_dev *idev = ip6_dst_idev(skb_dst(skb));
ICMP6MSGOUT_INC_STATS(net, idev, icmp6_hdr(skb)->icmp6_type);
ICMP6_INC_STATS(net, idev, ICMP6_MIB_OUTMSGS);
}
err = ip6_local_out(skb);
if (err) {
if (err > 0)
err = net_xmit_errno(err);
if (err)
goto error;
}
out:
ip6_cork_release(inet, np);
return err;
error:
IP6_INC_STATS(net, rt->rt6i_idev, IPSTATS_MIB_OUTDISCARDS);
goto out;
}
static struct sk_buff *tnl_skb_gso_segment(struct sk_buff *skb,
netdev_features_t features,
bool tx_path,
sa_family_t sa_family)
{
void *iph = skb_network_header(skb);
int pkt_hlen = skb_inner_network_offset(skb); /* inner l2 + tunnel hdr. */
int mac_offset = skb_inner_mac_offset(skb);
int outer_l3_offset = skb_network_offset(skb);
int outer_l4_offset = skb_transport_offset(skb);
struct sk_buff *skb1 = skb;
struct dst_entry *dst = skb_dst(skb);
struct sk_buff *segs;
__be16 proto = skb->protocol;
char cb[sizeof(skb->cb)];
OVS_GSO_CB(skb)->ipv6 = (sa_family == AF_INET6);
/* setup whole inner packet to get protocol. */
__skb_pull(skb, mac_offset);
skb->protocol = __skb_network_protocol(skb);
/* setup l3 packet to gso, to get around segmentation bug on older kernel.*/
__skb_pull(skb, (pkt_hlen - mac_offset));
skb_reset_mac_header(skb);
skb_reset_network_header(skb);
skb_reset_transport_header(skb);
/* From 3.9 kernel skb->cb is used by skb gso. Therefore
* make copy of it to restore it back. */
memcpy(cb, skb->cb, sizeof(cb));
skb->encapsulation = 0;
/* We are handling offloads by segmenting l3 packet, so
* no need to call OVS compat segmentation function. */
#ifdef HAVE___SKB_GSO_SEGMENT
#undef __skb_gso_segment
segs = __skb_gso_segment(skb, 0, tx_path);
#else
#undef skb_gso_segment
segs = skb_gso_segment(skb, 0);
#endif
if (!segs || IS_ERR(segs))
goto free;
skb = segs;
while (skb) {
__skb_push(skb, pkt_hlen);
skb_reset_mac_header(skb);
skb_set_network_header(skb, outer_l3_offset);
skb_set_transport_header(skb, outer_l4_offset);
skb->mac_len = 0;
memcpy(skb_network_header(skb), iph, pkt_hlen);
memcpy(skb->cb, cb, sizeof(cb));
skb->protocol = proto;
if (skb->next)
dst = dst_clone(dst);
skb_dst_set(skb, dst);
OVS_GSO_CB(skb)->fix_segment(skb);
skb = skb->next;
}
free:
consume_skb(skb1);
return segs;
}
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_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);
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 == 1 &&
pneigh_lookup(&nd_tbl, net, &hdr->daddr, skb->dev, 0))
|| net->ipv6.devconf_all->proxy_ndp >= 2) {
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 && opt->srcrt == 0 && !skb_sec_path(skb)) {
struct in6_addr *target = NULL;
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;
if (!rt->rt6i_peer)
rt6_bind_peer(rt, 1);
/* Limit redirects both by destination (here)
and by source (inside ndisc_send_redirect)
*/
if (inet_peer_xrlim_allow(rt->rt6i_peer, 1*HZ))
ndisc_send_redirect(skb, 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);
goto error;
}
}
mtu = dst_mtu(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(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);
return NF_HOOK(NFPROTO_IPV6, 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;
}
void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev,
const struct iphdr *tnl_params, u8 protocol)
{
struct ip_tunnel *tunnel = netdev_priv(dev);
const struct iphdr *inner_iph;
struct flowi4 fl4;
u8 tos, ttl;
__be16 df;
struct rtable *rt; /* Route to the other host */
unsigned int max_headroom; /* The extra header space needed */
__be32 dst;
bool connected;
inner_iph = (const struct iphdr *)skb_inner_network_header(skb);
connected = (tunnel->parms.iph.daddr != 0);
dst = tnl_params->daddr;
if (dst == 0) {
/* NBMA tunnel */
if (!skb_dst(skb)) {
dev->stats.tx_fifo_errors++;
goto tx_error;
}
if (skb->protocol == htons(ETH_P_IP)) {
rt = skb_rtable(skb);
dst = rt_nexthop(rt, inner_iph->daddr);
}
#if IS_ENABLED(CONFIG_IPV6)
else if (skb->protocol == htons(ETH_P_IPV6)) {
const struct in6_addr *addr6;
struct neighbour *neigh;
bool do_tx_error_icmp;
int addr_type;
neigh = dst_neigh_lookup(skb_dst(skb),
&ipv6_hdr(skb)->daddr);
if (!neigh)
goto tx_error;
addr6 = (const struct in6_addr *)&neigh->primary_key;
addr_type = ipv6_addr_type(addr6);
if (addr_type == IPV6_ADDR_ANY) {
addr6 = &ipv6_hdr(skb)->daddr;
addr_type = ipv6_addr_type(addr6);
}
if ((addr_type & IPV6_ADDR_COMPATv4) == 0)
do_tx_error_icmp = true;
else {
do_tx_error_icmp = false;
dst = addr6->s6_addr32[3];
}
neigh_release(neigh);
if (do_tx_error_icmp)
goto tx_error_icmp;
}
#endif
else
goto tx_error;
connected = false;
}
tos = tnl_params->tos;
if (tos & 0x1) {
tos &= ~0x1;
if (skb->protocol == htons(ETH_P_IP)) {
tos = inner_iph->tos;
connected = false;
} else if (skb->protocol == htons(ETH_P_IPV6)) {
tos = ipv6_get_dsfield((const struct ipv6hdr *)inner_iph);
connected = false;
}
}
init_tunnel_flow(&fl4, protocol, dst, tnl_params->saddr,
tunnel->parms.o_key, RT_TOS(tos), tunnel->parms.link);
if (ip_tunnel_encap(skb, tunnel, &protocol, &fl4) < 0)
goto tx_error;
rt = connected ? tunnel_rtable_get(tunnel, 0, &fl4.saddr) : NULL;
if (!rt) {
rt = ip_route_output_key(tunnel->net, &fl4);
if (IS_ERR(rt)) {
dev->stats.tx_carrier_errors++;
goto tx_error;
}
if (connected)
tunnel_dst_set(tunnel, &rt->dst, fl4.saddr);
}
if (rt->dst.dev == dev) {
ip_rt_put(rt);
dev->stats.collisions++;
goto tx_error;
}
if (tnl_update_pmtu(dev, skb, rt, tnl_params->frag_off, inner_iph)) {
ip_rt_put(rt);
goto tx_error;
}
if (tunnel->err_count > 0) {
if (time_before(jiffies,
tunnel->err_time + IPTUNNEL_ERR_TIMEO)) {
tunnel->err_count--;
memset(IPCB(skb), 0, sizeof(*IPCB(skb)));
dst_link_failure(skb);
} else
tunnel->err_count = 0;
}
tos = ip_tunnel_ecn_encap(tos, inner_iph, skb);
ttl = tnl_params->ttl;
if (ttl == 0) {
if (skb->protocol == htons(ETH_P_IP))
ttl = inner_iph->ttl;
#if IS_ENABLED(CONFIG_IPV6)
else if (skb->protocol == htons(ETH_P_IPV6))
ttl = ((const struct ipv6hdr *)inner_iph)->hop_limit;
#endif
else
ttl = ip4_dst_hoplimit(&rt->dst);
}
df = tnl_params->frag_off;
if (skb->protocol == htons(ETH_P_IP))
df |= (inner_iph->frag_off&htons(IP_DF));
max_headroom = LL_RESERVED_SPACE(rt->dst.dev) + sizeof(struct iphdr)
+ rt->dst.header_len + ip_encap_hlen(&tunnel->encap);
if (max_headroom > dev->needed_headroom)
dev->needed_headroom = max_headroom;
if (skb_cow_head(skb, dev->needed_headroom)) {
ip_rt_put(rt);
dev->stats.tx_dropped++;
kfree_skb(skb);
return;
}
iptunnel_xmit(NULL, rt, skb, fl4.saddr, fl4.daddr, protocol, tos, ttl,
df, !net_eq(tunnel->net, dev_net(dev)));
return;
#if IS_ENABLED(CONFIG_IPV6)
tx_error_icmp:
dst_link_failure(skb);
#endif
tx_error:
dev->stats.tx_errors++;
kfree_skb(skb);
}
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 = 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(skb)),
IPSTATS_MIB_REASMFAILS);
kfree_skb(skb);
return -1;
}
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);
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;
}