/**
* ipv6_skb_to_auditdata : fill auditdata from skb
* @skb : the skb
* @ad : the audit data to fill
* @proto : the layer 4 protocol
*
* return 0 on success
*/
int ipv6_skb_to_auditdata(struct sk_buff *skb,
struct common_audit_data *ad, u8 *proto)
{
int offset, ret = 0;
struct ipv6hdr *ip6;
u8 nexthdr;
__be16 frag_off;
ip6 = ipv6_hdr(skb);
if (ip6 == NULL)
return -EINVAL;
ad->u.net->v6info.saddr = ip6->saddr;
ad->u.net->v6info.daddr = ip6->daddr;
ret = 0;
/* IPv6 can have several extension header before the Transport header
* skip them */
offset = skb_network_offset(skb);
offset += sizeof(*ip6);
nexthdr = ip6->nexthdr;
offset = ipv6_skip_exthdr(skb, offset, &nexthdr, &frag_off);
if (offset < 0)
return 0;
if (proto)
*proto = nexthdr;
switch (nexthdr) {
case IPPROTO_TCP: {
struct tcphdr _tcph, *th;
th = skb_header_pointer(skb, offset, sizeof(_tcph), &_tcph);
if (th == NULL)
break;
ad->u.net->sport = th->source;
ad->u.net->dport = th->dest;
break;
}
case IPPROTO_UDP: {
struct udphdr _udph, *uh;
uh = skb_header_pointer(skb, offset, sizeof(_udph), &_udph);
if (uh == NULL)
break;
ad->u.net->sport = uh->source;
ad->u.net->dport = uh->dest;
break;
}
case IPPROTO_DCCP: {
struct dccp_hdr _dccph, *dh;
dh = skb_header_pointer(skb, offset, sizeof(_dccph), &_dccph);
if (dh == NULL)
break;
ad->u.net->sport = dh->dccph_sport;
ad->u.net->dport = dh->dccph_dport;
break;
}
case IPPROTO_SCTP: {
struct sctphdr _sctph, *sh;
sh = skb_header_pointer(skb, offset, sizeof(_sctph), &_sctph);
if (sh == NULL)
break;
ad->u.net->sport = sh->source;
ad->u.net->dport = sh->dest;
break;
}
default:
ret = -EINVAL;
}
return ret;
}
/*
* All outgoing AX.25 I frames pass via this routine. Therefore this is
* where the fragmentation of frames takes place. If fragment is set to
* zero then we are not allowed to do fragmentation, even if the frame
* is too large.
*/
void ax25_output(ax25_cb *ax25, int paclen, struct sk_buff *skb)
{
struct sk_buff *skbn;
unsigned char *p;
int frontlen, len, fragno, ka9qfrag, first = 1;
if (paclen < 16) {
WARN_ON_ONCE(1);
kfree_skb(skb);
return;
}
if ((skb->len - 1) > paclen) {
if (*skb->data == AX25_P_TEXT) {
skb_pull(skb, 1); /* skip PID */
ka9qfrag = 0;
} else {
paclen -= 2; /* Allow for fragment control info */
ka9qfrag = 1;
}
fragno = skb->len / paclen;
if (skb->len % paclen == 0) fragno--;
frontlen = skb_headroom(skb); /* Address space + CTRL */
while (skb->len > 0) {
spin_lock_bh(&ax25_frag_lock);
if ((skbn = alloc_skb(paclen + 2 + frontlen, GFP_ATOMIC)) == NULL) {
spin_unlock_bh(&ax25_frag_lock);
printk(KERN_CRIT "AX.25: ax25_output - out of memory\n");
return;
}
if (skb->sk != NULL)
skb_set_owner_w(skbn, skb->sk);
spin_unlock_bh(&ax25_frag_lock);
len = (paclen > skb->len) ? skb->len : paclen;
if (ka9qfrag == 1) {
skb_reserve(skbn, frontlen + 2);
skb_set_network_header(skbn,
skb_network_offset(skb));
skb_copy_from_linear_data(skb, skb_put(skbn, len), len);
p = skb_push(skbn, 2);
*p++ = AX25_P_SEGMENT;
*p = fragno--;
if (first) {
*p |= AX25_SEG_FIRST;
first = 0;
}
} else {
skb_reserve(skbn, frontlen + 1);
skb_set_network_header(skbn,
skb_network_offset(skb));
skb_copy_from_linear_data(skb, skb_put(skbn, len), len);
p = skb_push(skbn, 1);
*p = AX25_P_TEXT;
}
skb_pull(skb, len);
skb_queue_tail(&ax25->write_queue, skbn); /* Throw it on the queue */
}
kfree_skb(skb);
} else {
skb_queue_tail(&ax25->write_queue, skb); /* Throw it on the queue */
}
switch (ax25->ax25_dev->values[AX25_VALUES_PROTOCOL]) {
case AX25_PROTO_STD_SIMPLEX:
case AX25_PROTO_STD_DUPLEX:
ax25_kick(ax25);
break;
#ifdef CONFIG_AX25_DAMA_SLAVE
/*
* A DAMA slave is _required_ to work as normal AX.25L2V2
* if no DAMA master is available.
*/
case AX25_PROTO_DAMA_SLAVE:
if (!ax25->ax25_dev->dama.slave) ax25_kick(ax25);
break;
#endif
}
}
static int tcf_csum_ipv6(struct sk_buff *skb, u32 update_flags)
{
struct ipv6hdr *ip6h;
struct ipv6_opt_hdr *ip6xh;
unsigned int hl, ixhl;
unsigned int pl;
int ntkoff;
u8 nexthdr;
ntkoff = skb_network_offset(skb);
hl = sizeof(*ip6h);
if (!pskb_may_pull(skb, hl + ntkoff))
goto fail;
ip6h = ipv6_hdr(skb);
pl = ntohs(ip6h->payload_len);
nexthdr = ip6h->nexthdr;
do {
switch (nexthdr) {
case NEXTHDR_FRAGMENT:
goto ignore_skb;
case NEXTHDR_ROUTING:
case NEXTHDR_HOP:
case NEXTHDR_DEST:
if (!pskb_may_pull(skb, hl + sizeof(*ip6xh) + ntkoff))
goto fail;
ip6xh = (void *)(skb_network_header(skb) + hl);
ixhl = ipv6_optlen(ip6xh);
if (!pskb_may_pull(skb, hl + ixhl + ntkoff))
goto fail;
ip6xh = (void *)(skb_network_header(skb) + hl);
if ((nexthdr == NEXTHDR_HOP) &&
!(tcf_csum_ipv6_hopopts(ip6xh, ixhl, &pl)))
goto fail;
nexthdr = ip6xh->nexthdr;
hl += ixhl;
break;
case IPPROTO_ICMPV6:
if (update_flags & TCA_CSUM_UPDATE_FLAG_ICMP)
if (!tcf_csum_ipv6_icmp(skb,
hl, pl + sizeof(*ip6h)))
goto fail;
goto done;
case IPPROTO_TCP:
if (update_flags & TCA_CSUM_UPDATE_FLAG_TCP)
if (!tcf_csum_ipv6_tcp(skb,
hl, pl + sizeof(*ip6h)))
goto fail;
goto done;
case IPPROTO_UDP:
if (update_flags & TCA_CSUM_UPDATE_FLAG_UDP)
if (!tcf_csum_ipv6_udp(skb, hl,
pl + sizeof(*ip6h), 0))
goto fail;
goto done;
case IPPROTO_UDPLITE:
if (update_flags & TCA_CSUM_UPDATE_FLAG_UDPLITE)
if (!tcf_csum_ipv6_udp(skb, hl,
pl + sizeof(*ip6h), 1))
goto fail;
goto done;
default:
goto ignore_skb;
}
} while (pskb_may_pull(skb, hl + 1 + ntkoff));
done:
ignore_skb:
return 1;
fail:
return 0;
}
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.dst;
struct flowi *fl = &inet->cork.fl;
unsigned char proto = fl->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;
ipv6_addr_copy(final_dst, &fl->fl6_dst);
__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 = fl->fl6_flowlabel |
htonl(0x60000000 | ((int)np->cork.tclass << 20));
hdr->hop_limit = np->cork.hop_limit;
hdr->nexthdr = proto;
ipv6_addr_copy(&hdr->saddr, &fl->fl6_src);
ipv6_addr_copy(&hdr->daddr, final_dst);
skb->priority = sk->sk_priority;
skb->mark = sk->sk_mark;
skb_dst_set(skb, dst_clone(&rt->u.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_BH(net, idev, icmp6_hdr(skb)->icmp6_type);
ICMP6_INC_STATS_BH(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;
}
int rpl_dev_queue_xmit(struct sk_buff *skb)
{
#undef dev_queue_xmit
int err = -ENOMEM;
bool mpls;
mpls = false;
/* Avoid traversing any VLAN tags that are present to determine if
* the ethtype is MPLS. Instead compare the mac_len (end of L2) and
* skb_network_offset() (beginning of L3) whose inequality will
* indicate the presence of an MPLS label stack. */
if (skb->mac_len != skb_network_offset(skb) && !supports_mpls_gso())
mpls = true;
if (mpls) {
int features;
features = netif_skb_features(skb);
/* As of v3.11 the kernel provides an mpls_features field in
* struct net_device which allows devices to advertise which
* features its supports for MPLS. This value defaults to
* NETIF_F_SG and as of v3.19.
*
* This compatibility code is intended for kernels older
* than v3.19 that do not support MPLS GSO and do not
* use mpls_features. Thus this code uses NETIF_F_SG
* directly in place of mpls_features.
*/
if (mpls)
features &= NETIF_F_SG;
if (netif_needs_gso(skb, features)) {
struct sk_buff *nskb;
nskb = skb_gso_segment(skb, features);
if (!nskb) {
if (unlikely(skb_cloned(skb) &&
pskb_expand_head(skb, 0, 0, GFP_ATOMIC)))
goto drop;
skb_shinfo(skb)->gso_type &= ~SKB_GSO_DODGY;
goto xmit;
}
if (IS_ERR(nskb)) {
err = PTR_ERR(nskb);
goto drop;
}
consume_skb(skb);
skb = nskb;
do {
nskb = skb->next;
skb->next = NULL;
err = dev_queue_xmit(skb);
skb = nskb;
} while (skb);
return err;
}
}
xmit:
return dev_queue_xmit(skb);
drop:
kfree_skb(skb);
return err;
}
/* Add new segment to existing queue. */
static int ip_frag_queue(struct ipq *qp, struct sk_buff *skb)
{
struct sk_buff *prev, *next;
struct net_device *dev;
int flags, offset;
int ihl, end;
int err = -ENOENT;
u8 ecn;
if (qp->q.last_in & INET_FRAG_COMPLETE)
goto err;
if (!(IPCB(skb)->flags & IPSKB_FRAG_COMPLETE) &&
unlikely(ip_frag_too_far(qp)) &&
unlikely(err = ip_frag_reinit(qp))) {
ipq_kill(qp);
goto err;
}
ecn = ip4_frag_ecn(ip_hdr(skb)->tos);
offset = ntohs(ip_hdr(skb)->frag_off);
flags = offset & ~IP_OFFSET;
offset &= IP_OFFSET;
offset <<= 3; /* offset is in 8-byte chunks */
ihl = ip_hdrlen(skb);
/* Determine the position of this fragment. */
end = offset + skb->len - skb_network_offset(skb) - ihl;
err = -EINVAL;
/* Is this the final fragment? */
if ((flags & IP_MF) == 0) {
/* If we already have some bits beyond end
* or have different end, the segment is corrupted.
*/
if (end < qp->q.len ||
((qp->q.last_in & INET_FRAG_LAST_IN) && end != qp->q.len))
goto err;
qp->q.last_in |= INET_FRAG_LAST_IN;
qp->q.len = end;
} else {
if (end&7) {
end &= ~7;
if (skb->ip_summed != CHECKSUM_UNNECESSARY)
skb->ip_summed = CHECKSUM_NONE;
}
if (end > qp->q.len) {
/* Some bits beyond end -> corruption. */
if (qp->q.last_in & INET_FRAG_LAST_IN)
goto err;
qp->q.len = end;
}
}
if (end == offset)
goto err;
err = -ENOMEM;
if (!pskb_pull(skb, skb_network_offset(skb) + ihl))
goto err;
err = pskb_trim_rcsum(skb, end - offset);
if (err)
goto err;
/* Find out which fragments are in front and at the back of us
* in the chain of fragments so far. We must know where to put
* this fragment, right?
*/
prev = qp->q.fragments_tail;
if (!prev || FRAG_CB(prev)->offset < offset) {
next = NULL;
goto found;
}
prev = NULL;
for (next = qp->q.fragments; next != NULL; next = next->next) {
if (FRAG_CB(next)->offset >= offset)
break; /* bingo! */
prev = next;
}
found:
/* We found where to put this one. Check for overlap with
* preceding fragment, and, if needed, align things so that
* any overlaps are eliminated.
*/
if (prev) {
int i = (FRAG_CB(prev)->offset + prev->len) - offset;
if (i > 0) {
offset += i;
err = -EINVAL;
if (end <= offset)
goto err;
err = -ENOMEM;
if (!pskb_pull(skb, i))
goto err;
if (skb->ip_summed != CHECKSUM_UNNECESSARY)
skb->ip_summed = CHECKSUM_NONE;
}
}
err = -ENOMEM;
while (next && FRAG_CB(next)->offset < end) {
int i = end - FRAG_CB(next)->offset; /* overlap is 'i' bytes */
if (i < next->len) {
/* Eat head of the next overlapped fragment
* and leave the loop. The next ones cannot overlap.
*/
if (!pskb_pull(next, i))
goto err;
FRAG_CB(next)->offset += i;
qp->q.meat -= i;
if (next->ip_summed != CHECKSUM_UNNECESSARY)
next->ip_summed = CHECKSUM_NONE;
break;
} else {
struct sk_buff *free_it = next;
/* Old fragment is completely overridden with
* new one drop it.
*/
next = next->next;
if (prev)
prev->next = next;
else
qp->q.fragments = next;
qp->q.meat -= free_it->len;
frag_kfree_skb(qp->q.net, free_it);
}
}
FRAG_CB(skb)->offset = offset;
/* Insert this fragment in the chain of fragments. */
skb->next = next;
if (!next)
qp->q.fragments_tail = skb;
if (prev)
prev->next = skb;
else
qp->q.fragments = skb;
dev = skb->dev;
if (dev) {
qp->iif = dev->ifindex;
skb->dev = NULL;
}
qp->q.stamp = skb->tstamp;
qp->q.meat += skb->len;
qp->ecn |= ecn;
atomic_add(skb->truesize, &qp->q.net->mem);
if (offset == 0)
qp->q.last_in |= INET_FRAG_FIRST_IN;
if (ip_hdr(skb)->frag_off & htons(IP_DF) &&
skb->len + ihl > qp->q.max_size)
qp->q.max_size = skb->len + ihl;
if (qp->q.last_in == (INET_FRAG_FIRST_IN | INET_FRAG_LAST_IN) &&
qp->q.meat == qp->q.len) {
unsigned long orefdst = skb->_skb_refdst;
skb->_skb_refdst = 0UL;
err = ip_frag_reasm(qp, prev, dev);
skb->_skb_refdst = orefdst;
return err;
}
skb_dst_drop(skb);
write_lock(&ip4_frags.lock);
list_move_tail(&qp->q.lru_list, &qp->q.net->lru_list);
write_unlock(&ip4_frags.lock);
return -EINPROGRESS;
err:
kfree_skb(skb);
return err;
}
static int ip6mr_cache_report(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 = 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 = dst_clone(pkt->dst);
skb->ip_summed = CHECKSUM_UNNECESSARY;
skb_pull(skb, sizeof(struct ipv6hdr));
}
if (mroute6_socket == NULL) {
kfree_skb(skb);
return -EINVAL;
}
/*
* Deliver to user space multicast routing algorithms
*/
if ((ret = sock_queue_rcv_skb(mroute6_socket, skb)) < 0) {
if (net_ratelimit())
printk(KERN_WARNING "mroute6: pending queue full, dropping entries.\n");
kfree_skb(skb);
}
return ret;
}
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;
}
static bool arphdr_ok(struct sk_buff *skb)
{
return pskb_may_pull(skb, skb_network_offset(skb) +
sizeof(struct arp_eth_header));
}
static int tcf_pedit(struct sk_buff *skb, const struct tc_action *a,
struct tcf_result *res)
{
struct tcf_pedit *p = to_pedit(a);
int i;
unsigned int off;
if (skb_unclone(skb, GFP_ATOMIC))
return p->tcf_action;
off = skb_network_offset(skb);
spin_lock(&p->tcf_lock);
tcf_lastuse_update(&p->tcf_tm);
if (p->tcfp_nkeys > 0) {
struct tc_pedit_key *tkey = p->tcfp_keys;
for (i = p->tcfp_nkeys; i > 0; i--, tkey++) {
u32 *ptr, _data;
int offset = tkey->off;
if (tkey->offmask) {
char *d, _d;
if (!offset_valid(skb, off + tkey->at)) {
pr_info("tc filter pedit 'at' offset %d out of bounds\n",
off + tkey->at);
goto bad;
}
d = skb_header_pointer(skb, off + tkey->at, 1,
&_d);
if (!d)
goto bad;
offset += (*d & tkey->offmask) >> tkey->shift;
}
if (offset % 4) {
pr_info("tc filter pedit"
" offset must be on 32 bit boundaries\n");
goto bad;
}
if (!offset_valid(skb, off + offset)) {
pr_info("tc filter pedit offset %d out of bounds\n",
offset);
goto bad;
}
ptr = skb_header_pointer(skb, off + offset, 4, &_data);
if (!ptr)
goto bad;
/* just do it, baby */
*ptr = ((*ptr & tkey->mask) ^ tkey->val);
if (ptr == &_data)
skb_store_bits(skb, off + offset, ptr, 4);
}
goto done;
} else
static netdev_tx_t vrf_process_v4_outbound(struct sk_buff *skb,
struct net_device *vrf_dev)
{
struct iphdr *ip4h = ip_hdr(skb);
int ret = NET_XMIT_DROP;
struct flowi4 fl4 = {
/* needed to match OIF rule */
.flowi4_oif = vrf_dev->ifindex,
.flowi4_iif = LOOPBACK_IFINDEX,
.flowi4_tos = RT_TOS(ip4h->tos),
.flowi4_flags = FLOWI_FLAG_ANYSRC | FLOWI_FLAG_SKIP_NH_OIF,
.flowi4_proto = ip4h->protocol,
.daddr = ip4h->daddr,
.saddr = ip4h->saddr,
};
struct net *net = dev_net(vrf_dev);
struct rtable *rt;
rt = ip_route_output_flow(net, &fl4, NULL);
if (IS_ERR(rt))
goto err;
skb_dst_drop(skb);
/* if dst.dev is loopback or the VRF device again this is locally
* originated traffic destined to a local address. Short circuit
* to Rx path using our local dst
*/
if (rt->dst.dev == net->loopback_dev || rt->dst.dev == vrf_dev) {
struct net_vrf *vrf = netdev_priv(vrf_dev);
struct rtable *rth_local;
struct dst_entry *dst = NULL;
ip_rt_put(rt);
rcu_read_lock();
rth_local = rcu_dereference(vrf->rth_local);
if (likely(rth_local)) {
dst = &rth_local->dst;
dst_hold(dst);
}
rcu_read_unlock();
if (unlikely(!dst))
goto err;
return vrf_local_xmit(skb, vrf_dev, dst);
}
skb_dst_set(skb, &rt->dst);
/* strip the ethernet header added for pass through VRF device */
__skb_pull(skb, skb_network_offset(skb));
if (!ip4h->saddr) {
ip4h->saddr = inet_select_addr(skb_dst(skb)->dev, 0,
RT_SCOPE_LINK);
}
ret = vrf_ip_local_out(dev_net(skb_dst(skb)->dev), skb->sk, skb);
if (unlikely(net_xmit_eval(ret)))
vrf_dev->stats.tx_errors++;
else
ret = NET_XMIT_SUCCESS;
out:
return ret;
err:
vrf_tx_error(vrf_dev, skb);
goto out;
}
static netdev_tx_t is_ip_tx_frame(struct sk_buff *skb, struct net_device *dev)
{
switch (skb->protocol) {
case htons(ETH_P_IP):
return vrf_process_v4_outbound(skb, dev);
case htons(ETH_P_IPV6):
return vrf_process_v6_outbound(skb, dev);
default:
vrf_tx_error(dev, skb);
return NET_XMIT_DROP;
}
}
static netdev_tx_t vrf_xmit(struct sk_buff *skb, struct net_device *dev)
{
int len = skb->len;
netdev_tx_t ret = is_ip_tx_frame(skb, dev);
if (likely(ret == NET_XMIT_SUCCESS || ret == NET_XMIT_CN)) {
struct pcpu_dstats *dstats = this_cpu_ptr(dev->dstats);
u64_stats_update_begin(&dstats->syncp);
dstats->tx_pkts++;
dstats->tx_bytes += len;
u64_stats_update_end(&dstats->syncp);
} else {
this_cpu_inc(dev->dstats->tx_drps);
}
return ret;
}
static netdev_tx_t vrf_process_v6_outbound(struct sk_buff *skb,
struct net_device *dev)
{
const struct ipv6hdr *iph = ipv6_hdr(skb);
struct net *net = dev_net(skb->dev);
struct flowi6 fl6 = {
/* needed to match OIF rule */
.flowi6_oif = dev->ifindex,
.flowi6_iif = LOOPBACK_IFINDEX,
.daddr = iph->daddr,
.saddr = iph->saddr,
.flowlabel = ip6_flowinfo(iph),
.flowi6_mark = skb->mark,
.flowi6_proto = iph->nexthdr,
.flowi6_flags = FLOWI_FLAG_SKIP_NH_OIF,
};
int ret = NET_XMIT_DROP;
struct dst_entry *dst;
struct dst_entry *dst_null = &net->ipv6.ip6_null_entry->dst;
dst = ip6_route_output(net, NULL, &fl6);
if (dst == dst_null)
goto err;
skb_dst_drop(skb);
/* if dst.dev is loopback or the VRF device again this is locally
* originated traffic destined to a local address. Short circuit
* to Rx path using our local dst
*/
if (dst->dev == net->loopback_dev || dst->dev == dev) {
struct net_vrf *vrf = netdev_priv(dev);
struct rt6_info *rt6_local;
/* release looked up dst and use cached local dst */
dst_release(dst);
rcu_read_lock();
rt6_local = rcu_dereference(vrf->rt6_local);
if (unlikely(!rt6_local)) {
rcu_read_unlock();
goto err;
}
/* Ordering issue: cached local dst is created on newlink
* before the IPv6 initialization. Using the local dst
* requires rt6i_idev to be set so make sure it is.
*/
if (unlikely(!rt6_local->rt6i_idev)) {
rt6_local->rt6i_idev = in6_dev_get(dev);
if (!rt6_local->rt6i_idev) {
rcu_read_unlock();
goto err;
}
}
dst = &rt6_local->dst;
dst_hold(dst);
rcu_read_unlock();
return vrf_local_xmit(skb, dev, &rt6_local->dst);
}
skb_dst_set(skb, dst);
/* strip the ethernet header added for pass through VRF device */
__skb_pull(skb, skb_network_offset(skb));
ret = vrf_ip6_local_out(net, skb->sk, skb);
if (unlikely(net_xmit_eval(ret)))
dev->stats.tx_errors++;
else
ret = NET_XMIT_SUCCESS;
return ret;
err:
vrf_tx_error(dev, skb);
return NET_XMIT_DROP;
}
#else
static netdev_tx_t vrf_process_v6_outbound(struct sk_buff *skb,
struct net_device *dev)
{
vrf_tx_error(dev, skb);
return NET_XMIT_DROP;
}
static int ipip_output(struct xfrm_state *x, struct sk_buff *skb)
{
skb_push(skb, -skb_network_offset(skb));
return 0;
}
