static void update_ip_l4_checksum(struct sk_buff *skb, struct iphdr *nh,
__be32 addr, __be32 new_addr)
{
int transport_len = skb->len - skb_transport_offset(skb);
if (nh->frag_off & htons(IP_OFFSET))
return;
if (nh->protocol == IPPROTO_TCP) {
if (likely(transport_len >= sizeof(struct tcphdr)))
inet_proto_csum_replace4(&tcp_hdr(skb)->check, skb,
addr, new_addr, 1);
} else if (nh->protocol == IPPROTO_UDP) {
if (likely(transport_len >= sizeof(struct udphdr))) {
struct udphdr *uh = udp_hdr(skb);
if (uh->check || skb->ip_summed == CHECKSUM_PARTIAL) {
inet_proto_csum_replace4(&uh->check, skb,
addr, new_addr, 1);
if (!uh->check)
uh->check = CSUM_MANGLED_0;
}
}
}
}
static void set_ip_addr(struct sk_buff *skb, struct iphdr *nh,
__be32 *addr, __be32 new_addr)
{
int transport_len = skb->len - skb_transport_offset(skb);
if (nh->protocol == IPPROTO_TCP) {
if (likely(transport_len >= sizeof(struct tcphdr)))
inet_proto_csum_replace4(&tcp_hdr(skb)->check, skb,
*addr, new_addr, 1);
} else if (nh->protocol == IPPROTO_UDP) {
if (likely(transport_len >= sizeof(struct udphdr))) {
struct udphdr *uh = udp_hdr(skb);
if (uh->check ||
get_ip_summed(skb) == OVS_CSUM_PARTIAL) {
inet_proto_csum_replace4(&uh->check, skb,
*addr, new_addr, 1);
if (!uh->check)
uh->check = CSUM_MANGLED_0;
}
}
}
csum_replace4(&nh->check, *addr, new_addr);
skb_clear_rxhash(skb);
*addr = new_addr;
}
int
nf_nat_seq_adjust(struct sk_buff *skb,
struct nf_conn *ct,
enum ip_conntrack_info ctinfo)
{
struct tcphdr *tcph;
int dir;
__be32 newseq, newack;
s16 seqoff, ackoff;
struct nf_conn_nat *nat = nfct_nat(ct);
struct nf_nat_seq *this_way, *other_way;
dir = CTINFO2DIR(ctinfo);
this_way = &nat->seq[dir];
other_way = &nat->seq[!dir];
#ifdef CONFIG_HTC_NETWORK_MODIFY
if (IS_ERR(this_way) || (!this_way))
printk(KERN_ERR "[NET] this_way is NULL in %s!\n", __func__);
#endif
if (!skb_make_writable(skb, ip_hdrlen(skb) + sizeof(*tcph)))
return 0;
tcph = (void *)skb->data + ip_hdrlen(skb);
if (after(ntohl(tcph->seq), this_way->correction_pos))
seqoff = this_way->offset_after;
else
seqoff = this_way->offset_before;
if (after(ntohl(tcph->ack_seq) - other_way->offset_before,
other_way->correction_pos))
ackoff = other_way->offset_after;
else
ackoff = other_way->offset_before;
newseq = htonl(ntohl(tcph->seq) + seqoff);
newack = htonl(ntohl(tcph->ack_seq) - ackoff);
inet_proto_csum_replace4(&tcph->check, skb, tcph->seq, newseq, 0);
inet_proto_csum_replace4(&tcph->check, skb, tcph->ack_seq, newack, 0);
pr_debug("Adjusting sequence number from %u->%u, ack from %u->%u\n",
ntohl(tcph->seq), ntohl(newseq), ntohl(tcph->ack_seq),
ntohl(newack));
tcph->seq = newseq;
tcph->ack_seq = newack;
return nf_nat_sack_adjust(skb, tcph, ct, ctinfo);
}
/* TCP sequence number adjustment. Returns 1 on success, 0 on failure */
int nf_ct_seq_adjust(struct sk_buff *skb,
struct nf_conn *ct, enum ip_conntrack_info ctinfo,
unsigned int protoff)
{
enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo);
struct tcphdr *tcph;
__be32 newseq, newack;
s32 seqoff, ackoff;
struct nf_conn_seqadj *seqadj = nfct_seqadj(ct);
struct nf_ct_seqadj *this_way, *other_way;
int res;
this_way = &seqadj->seq[dir];
other_way = &seqadj->seq[!dir];
if (!skb_make_writable(skb, protoff + sizeof(*tcph)))
return 0;
tcph = (void *)skb->data + protoff;
spin_lock_bh(&ct->lock);
if (after(ntohl(tcph->seq), this_way->correction_pos))
seqoff = this_way->offset_after;
else
seqoff = this_way->offset_before;
if (after(ntohl(tcph->ack_seq) - other_way->offset_before,
other_way->correction_pos))
ackoff = other_way->offset_after;
else
ackoff = other_way->offset_before;
newseq = htonl(ntohl(tcph->seq) + seqoff);
newack = htonl(ntohl(tcph->ack_seq) - ackoff);
inet_proto_csum_replace4(&tcph->check, skb, tcph->seq, newseq, 0);
inet_proto_csum_replace4(&tcph->check, skb, tcph->ack_seq, newack, 0);
pr_debug("Adjusting sequence number from %u->%u, ack from %u->%u\n",
ntohl(tcph->seq), ntohl(newseq), ntohl(tcph->ack_seq),
ntohl(newack));
tcph->seq = newseq;
tcph->ack_seq = newack;
res = nf_ct_sack_adjust(skb, protoff, tcph, ct, ctinfo);
spin_unlock_bh(&ct->lock);
return res;
}
static inline void update_tp_pseudo_csum_4(struct sk_buff *skb, struct iphdr *ip, const __u32 old_addr, const __u32 new_addr)
{
const __u8 *l4h = &((__u8*)ip)[ip->ihl << 2];
if (ip->protocol == IPPROTO_TCP) {
struct tcphdr *tcp = (struct tcphdr*)l4h;
inet_proto_csum_replace4(&tcp->check, skb, old_addr, new_addr, 1);
} else if (ip->protocol == IPPROTO_UDP) {
struct udphdr *udp = (struct udphdr*)l4h;
if (udp->check || (skb->ip_summed == CHECKSUM_PARTIAL)) {
inet_proto_csum_replace4(&udp->check, skb, old_addr, new_addr, 1);
if (! udp->check) {
udp->check = CSUM_MANGLED_0;
}
}
}
}
unsigned int synproxy_tstamp_adjust(struct sk_buff *skb,
unsigned int protoff,
struct tcphdr *th,
struct nf_conn *ct,
enum ip_conntrack_info ctinfo,
const struct nf_conn_synproxy *synproxy)
{
unsigned int optoff, optend;
u32 *ptr, old;
if (synproxy->tsoff == 0)
return 1;
optoff = protoff + sizeof(struct tcphdr);
optend = protoff + th->doff * 4;
if (!skb_make_writable(skb, optend))
return 0;
while (optoff < optend) {
unsigned char *op = skb->data + optoff;
switch (op[0]) {
case TCPOPT_EOL:
return 1;
case TCPOPT_NOP:
optoff++;
continue;
default:
if (optoff + 1 == optend ||
optoff + op[1] > optend ||
op[1] < 2)
return 0;
if (op[0] == TCPOPT_TIMESTAMP &&
op[1] == TCPOLEN_TIMESTAMP) {
if (CTINFO2DIR(ctinfo) == IP_CT_DIR_REPLY) {
ptr = (u32 *)&op[2];
old = *ptr;
*ptr = htonl(ntohl(*ptr) -
synproxy->tsoff);
} else {
ptr = (u32 *)&op[6];
old = *ptr;
*ptr = htonl(ntohl(*ptr) +
synproxy->tsoff);
}
inet_proto_csum_replace4(&th->check, skb,
old, *ptr, 0);
return 1;
}
optoff += op[1];
}
}
return 1;
}
static void
sack_adjust(struct sk_buff *skb,
struct tcphdr *tcph,
unsigned int sackoff,
unsigned int sackend,
struct nf_nat_seq *natseq)
{
while (sackoff < sackend) {
struct tcp_sack_block_wire *sack;
__be32 new_start_seq, new_end_seq;
sack = (void *)skb->data + sackoff;
if (after(ntohl(sack->start_seq) - natseq->offset_before,
natseq->correction_pos))
new_start_seq = htonl(ntohl(sack->start_seq)
- natseq->offset_after);
else
new_start_seq = htonl(ntohl(sack->start_seq)
- natseq->offset_before);
if (after(ntohl(sack->end_seq) - natseq->offset_before,
natseq->correction_pos))
new_end_seq = htonl(ntohl(sack->end_seq)
- natseq->offset_after);
else
new_end_seq = htonl(ntohl(sack->end_seq)
- natseq->offset_before);
pr_debug("sack_adjust: start_seq: %d->%d, end_seq: %d->%d\n",
ntohl(sack->start_seq), new_start_seq,
ntohl(sack->end_seq), new_end_seq);
inet_proto_csum_replace4(&tcph->check, skb,
sack->start_seq, new_start_seq, 0);
inet_proto_csum_replace4(&tcph->check, skb,
sack->end_seq, new_end_seq, 0);
sack->start_seq = new_start_seq;
sack->end_seq = new_end_seq;
sackoff += sizeof(*sack);
}
}
void modisg_snat_oper(struct sk_buff *p_psoSKB, struct iphdr *p_psoIP)
{
struct tcphdr *psoTCP = tcp_hdr(p_psoSKB);
__be32 uiSrcAddr;
if(psoTCP == NULL)
return;
/* производим подмену адреса отправителя */
uiSrcAddr = modisg_dnat_get(p_psoIP->daddr, psoTCP->dest);
csum_replace4(&p_psoIP->check, p_psoIP->saddr, uiSrcAddr);
inet_proto_csum_replace4(&psoTCP->check, p_psoSKB, p_psoIP->saddr, uiSrcAddr, 1);
p_psoIP->saddr = uiSrcAddr;
}
void modisg_dnat_oper(struct sk_buff *p_psoSKB, struct iphdr *p_psoIP)
{
struct tcphdr *psoTCP = tcp_hdr(p_psoSKB);
if(psoTCP == NULL)
return;
/* сохраняем значение адреса назначения в таблице */
modisg_dnat_set(p_psoIP->saddr, psoTCP->source, p_psoIP->daddr);
/* пересчитываем контрольные суммы */
csum_replace4(&p_psoIP->check, p_psoIP->daddr, L4R_ADDR);
inet_proto_csum_replace4(&psoTCP->check, p_psoSKB, p_psoIP->daddr, L4R_ADDR, 1);
p_psoIP->daddr = L4R_ADDR;
}
static bool
tcp_manip_pkt(struct sk_buff *skb,
unsigned int iphdroff,
const struct nf_conntrack_tuple *tuple,
enum nf_nat_manip_type maniptype)
{
const struct iphdr *iph = (struct iphdr *)(skb->data + iphdroff);
struct tcphdr *hdr;
unsigned int hdroff = iphdroff + iph->ihl*4;
__be32 oldip, newip;
__be16 *portptr, newport, oldport;
int hdrsize = 8; /* TCP connection tracking guarantees this much */
/* this could be a inner header returned in icmp packet; in such
cases we cannot update the checksum field since it is outside of
the 8 bytes of transport layer headers we are guaranteed */
if (skb->len >= hdroff + sizeof(struct tcphdr))
hdrsize = sizeof(struct tcphdr);
if (!skb_make_writable(skb, hdroff + hdrsize))
return false;
iph = (struct iphdr *)(skb->data + iphdroff);
hdr = (struct tcphdr *)(skb->data + hdroff);
if (maniptype == NF_NAT_MANIP_SRC) {
/* Get rid of src ip and src pt */
oldip = iph->saddr;
newip = tuple->src.u3.ip;
newport = tuple->src.u.tcp.port;
portptr = &hdr->source;
} else {
/* Get rid of dst ip and dst pt */
oldip = iph->daddr;
newip = tuple->dst.u3.ip;
newport = tuple->dst.u.tcp.port;
portptr = &hdr->dest;
}
oldport = *portptr;
*portptr = newport;
if (hdrsize < sizeof(*hdr))
return true;
inet_proto_csum_replace4(&hdr->check, skb, oldip, newip, 1);
inet_proto_csum_replace2(&hdr->check, skb, oldport, newport, 0);
return true;
}
static bool
tcp_manip_pkt(struct sk_buff *skb,
unsigned int iphdroff,
const struct nf_conntrack_tuple *tuple,
enum nf_nat_manip_type maniptype)
{
const struct iphdr *iph = (struct iphdr *)(skb->data + iphdroff);
struct tcphdr *hdr;
unsigned int hdroff = iphdroff + iph->ihl*4;
__be32 oldip, newip;
__be16 *portptr, newport, oldport;
int hdrsize = 8;
if (skb->len >= hdroff + sizeof(struct tcphdr))
hdrsize = sizeof(struct tcphdr);
if (!skb_make_writable(skb, hdroff + hdrsize))
return false;
iph = (struct iphdr *)(skb->data + iphdroff);
hdr = (struct tcphdr *)(skb->data + hdroff);
if (maniptype == NF_NAT_MANIP_SRC) {
oldip = iph->saddr;
newip = tuple->src.u3.ip;
newport = tuple->src.u.tcp.port;
portptr = &hdr->source;
} else {
oldip = iph->daddr;
newip = tuple->dst.u3.ip;
newport = tuple->dst.u.tcp.port;
portptr = &hdr->dest;
}
oldport = *portptr;
*portptr = newport;
if (hdrsize < sizeof(*hdr))
return true;
inet_proto_csum_replace4(&hdr->check, skb, oldip, newip, 1);
inet_proto_csum_replace2(&hdr->check, skb, oldport, newport, 0);
return true;
}
static void nf_nat_ipv4_csum_update(struct sk_buff *skb,
unsigned int iphdroff, __sum16 *check,
const struct nf_conntrack_tuple *t,
enum nf_nat_manip_type maniptype)
{
struct iphdr *iph = (struct iphdr *)(skb->data + iphdroff);
__be32 oldip, newip;
if (maniptype == NF_NAT_MANIP_SRC) {
oldip = iph->saddr;
newip = t->src.u3.ip;
} else {
oldip = iph->daddr;
newip = t->dst.u3.ip;
}
inet_proto_csum_replace4(check, skb, oldip, newip, true);
}
static bool
dccp_manip_pkt(struct sk_buff *skb,
unsigned int iphdroff,
const struct nf_conntrack_tuple *tuple,
enum nf_nat_manip_type maniptype)
{
const struct iphdr *iph = (const void *)(skb->data + iphdroff);
struct dccp_hdr *hdr;
unsigned int hdroff = iphdroff + iph->ihl * 4;
__be32 oldip, newip;
__be16 *portptr, oldport, newport;
int hdrsize = 8; /* DCCP connection tracking guarantees this much */
if (skb->len >= hdroff + sizeof(struct dccp_hdr))
hdrsize = sizeof(struct dccp_hdr);
if (!skb_make_writable(skb, hdroff + hdrsize))
return false;
iph = (struct iphdr *)(skb->data + iphdroff);
hdr = (struct dccp_hdr *)(skb->data + hdroff);
if (maniptype == IP_NAT_MANIP_SRC) {
oldip = iph->saddr;
newip = tuple->src.u3.ip;
newport = tuple->src.u.dccp.port;
portptr = &hdr->dccph_sport;
} else {
oldip = iph->daddr;
newip = tuple->dst.u3.ip;
newport = tuple->dst.u.dccp.port;
portptr = &hdr->dccph_dport;
}
oldport = *portptr;
*portptr = newport;
if (hdrsize < sizeof(*hdr))
return true;
inet_proto_csum_replace4(&hdr->dccph_checksum, skb, oldip, newip, 1);
inet_proto_csum_replace2(&hdr->dccph_checksum, skb, oldport, newport,
0);
return true;
}
static bool
udp_manip_pkt(struct sk_buff *skb,
unsigned int iphdroff,
const struct nf_conntrack_tuple *tuple,
enum nf_nat_manip_type maniptype)
{
const struct iphdr *iph = (struct iphdr *)(skb->data + iphdroff);
struct udphdr *hdr;
unsigned int hdroff = iphdroff + iph->ihl*4;
__be32 oldip, newip;
__be16 *portptr, newport;
if (!skb_make_writable(skb, hdroff + sizeof(*hdr)))
return false;
iph = (struct iphdr *)(skb->data + iphdroff);
hdr = (struct udphdr *)(skb->data + hdroff);
if (maniptype == NF_NAT_MANIP_SRC) {
/* Get rid of src ip and src pt */
oldip = iph->saddr;
newip = tuple->src.u3.ip;
newport = tuple->src.u.udp.port;
portptr = &hdr->source;
} else {
/* Get rid of dst ip and dst pt */
oldip = iph->daddr;
newip = tuple->dst.u3.ip;
newport = tuple->dst.u.udp.port;
portptr = &hdr->dest;
}
if (hdr->check || skb->ip_summed == CHECKSUM_PARTIAL) {
inet_proto_csum_replace4(&hdr->check, skb, oldip, newip, 1);
inet_proto_csum_replace2(&hdr->check, skb, *portptr, newport,
0);
if (!hdr->check)
hdr->check = CSUM_MANGLED_0;
}
*portptr = newport;
return true;
}
static int tcf_nat(struct sk_buff *skb, struct tc_action *a,
struct tcf_result *res)
{
struct tcf_nat *p = a->priv;
struct iphdr *iph;
__be32 old_addr;
__be32 new_addr;
__be32 mask;
__be32 addr;
int egress;
int action;
int ihl;
int noff;
spin_lock(&p->tcf_lock);
p->tcf_tm.lastuse = jiffies;
old_addr = p->old_addr;
new_addr = p->new_addr;
mask = p->mask;
egress = p->flags & TCA_NAT_FLAG_EGRESS;
action = p->tcf_action;
p->tcf_bstats.bytes += qdisc_pkt_len(skb);
p->tcf_bstats.packets++;
spin_unlock(&p->tcf_lock);
if (unlikely(action == TC_ACT_SHOT))
goto drop;
noff = skb_network_offset(skb);
if (!pskb_may_pull(skb, sizeof(*iph) + noff))
goto drop;
iph = ip_hdr(skb);
if (egress)
addr = iph->saddr;
else
addr = iph->daddr;
if (!((old_addr ^ addr) & mask)) {
if (skb_cloned(skb) &&
!skb_clone_writable(skb, sizeof(*iph) + noff) &&
pskb_expand_head(skb, 0, 0, GFP_ATOMIC))
goto drop;
new_addr &= mask;
new_addr |= addr & ~mask;
/* Rewrite IP header */
iph = ip_hdr(skb);
if (egress)
iph->saddr = new_addr;
else
iph->daddr = new_addr;
csum_replace4(&iph->check, addr, new_addr);
} else if ((iph->frag_off & htons(IP_OFFSET)) ||
iph->protocol != IPPROTO_ICMP) {
goto out;
}
ihl = iph->ihl * 4;
/* It would be nice to share code with stateful NAT. */
switch (iph->frag_off & htons(IP_OFFSET) ? 0 : iph->protocol) {
case IPPROTO_TCP:
{
struct tcphdr *tcph;
if (!pskb_may_pull(skb, ihl + sizeof(*tcph) + noff) ||
(skb_cloned(skb) &&
!skb_clone_writable(skb, ihl + sizeof(*tcph) + noff) &&
pskb_expand_head(skb, 0, 0, GFP_ATOMIC)))
goto drop;
tcph = (void *)(skb_network_header(skb) + ihl);
inet_proto_csum_replace4(&tcph->check, skb, addr, new_addr, 1);
break;
}
case IPPROTO_UDP:
{
struct udphdr *udph;
if (!pskb_may_pull(skb, ihl + sizeof(*udph) + noff) ||
(skb_cloned(skb) &&
!skb_clone_writable(skb, ihl + sizeof(*udph) + noff) &&
pskb_expand_head(skb, 0, 0, GFP_ATOMIC)))
goto drop;
udph = (void *)(skb_network_header(skb) + ihl);
if (udph->check || skb->ip_summed == CHECKSUM_PARTIAL) {
inet_proto_csum_replace4(&udph->check, skb, addr,
new_addr, 1);
if (!udph->check)
udph->check = CSUM_MANGLED_0;
}
break;
}
case IPPROTO_ICMP:
{
struct icmphdr *icmph;
if (!pskb_may_pull(skb, ihl + sizeof(*icmph) + noff))
goto drop;
icmph = (void *)(skb_network_header(skb) + ihl);
if ((icmph->type != ICMP_DEST_UNREACH) &&
(icmph->type != ICMP_TIME_EXCEEDED) &&
(icmph->type != ICMP_PARAMETERPROB))
break;
if (!pskb_may_pull(skb, ihl + sizeof(*icmph) + sizeof(*iph) +
noff))
goto drop;
icmph = (void *)(skb_network_header(skb) + ihl);
iph = (void *)(icmph + 1);
if (egress)
addr = iph->daddr;
else
addr = iph->saddr;
if ((old_addr ^ addr) & mask)
break;
if (skb_cloned(skb) &&
!skb_clone_writable(skb, ihl + sizeof(*icmph) +
sizeof(*iph) + noff) &&
pskb_expand_head(skb, 0, 0, GFP_ATOMIC))
goto drop;
icmph = (void *)(skb_network_header(skb) + ihl);
iph = (void *)(icmph + 1);
new_addr &= mask;
new_addr |= addr & ~mask;
/* XXX Fix up the inner checksums. */
if (egress)
iph->daddr = new_addr;
else
iph->saddr = new_addr;
inet_proto_csum_replace4(&icmph->checksum, skb, addr, new_addr,
0);
break;
}
default:
break;
}
out:
return action;
drop:
spin_lock(&p->tcf_lock);
p->tcf_qstats.drops++;
spin_unlock(&p->tcf_lock);
return TC_ACT_SHOT;
}