static unsigned int
mark_tg(struct sk_buff *skb, const struct xt_action_param *par)
{
const struct xt_mark_tginfo2 *info = par->targinfo;
skb->mark = (skb->mark & ~info->mask) ^ info->mark;
#ifdef HNDCTF
{
enum ip_conntrack_info ctinfo;
struct nf_conn *ct = nf_ct_get(skb, &ctinfo);
if(ct) ct->ctf_flags |= CTF_FLAGS_EXCLUDED;
}
#endif /* HNDCTF */
return XT_CONTINUE;
}
/* function to be called by hook */
static unsigned int
hook_func(unsigned int hooknum, struct sk_buff *skb, const struct net_device *in,
const struct net_device *out, int (*okfn)(struct sk_buff *))
{
struct nf_conn *ct;
enum ip_conntrack_info ctinfo;
struct nf_conn_counter *acct;
if (!skb) {
return NF_ACCEPT;
}
if (in == NULL) {
return NF_ACCEPT;
} else if (in->name == NULL) {
return NF_ACCEPT;
}
if (memcmp(devname, "all", 3) != 0) {
if (memcmp(devname, in->name, 4) != 0) {
return NF_ACCEPT;
}
}
/* conntrack check */
if (skb->nfct == NULL) {
/* if (net_ratelimit())
* pr_info("skb->nfct == NULL!\n"); */
return NF_ACCEPT;
}
ct = nf_ct_get(skb, &ctinfo);
acct = nf_conn_acct_find(ct);
if (!acct) {
if (net_ratelimit())
pr_info("acct is NULL\n");
return NF_ACCEPT;
}
if (ct->proto.tcp.state == TCP_CONNTRACK_CLOSE_WAIT) {
pr_info("%pI4 --> %pI4: %llu bytes CLOSE_WAIT\n", &iph->saddr, &iph->daddr,
acct[IP_CT_DIR_ORIGINAL].bytes + acct[IP_CT_DIR_REPLY].bytes);
}
return NF_ACCEPT;
}
static int mangle_sdp_packet(struct sk_buff *skb, unsigned int dataoff,
const char **dptr, unsigned int *datalen,
unsigned int sdpoff,
enum sdp_header_types type,
enum sdp_header_types term,
char *buffer, int buflen)
{
enum ip_conntrack_info ctinfo;
struct nf_conn *ct = nf_ct_get(skb, &ctinfo);
unsigned int matchlen, matchoff;
if (ct_sip_get_sdp_header(ct, *dptr, sdpoff, *datalen, type, term,
&matchoff, &matchlen) <= 0)
return -ENOENT;
return mangle_packet(skb, dataoff, dptr, datalen, matchoff, matchlen,
buffer, buflen) ? 0 : -EINVAL;
}
static unsigned int
connmark_tg(struct sk_buff *skb, const struct xt_action_param *par)
{
const struct xt_connmark_tginfo1 *info = par->targinfo;
enum ip_conntrack_info ctinfo;
struct nf_conn *ct;
u_int32_t newmark;
ct = nf_ct_get(skb, &ctinfo);
if (ct == NULL)
return XT_CONTINUE;
switch (info->mode) {
case XT_CONNMARK_SET:
newmark = (ct->mark & ~info->ctmask) ^ info->ctmark;
if (ct->mark != newmark) {
ct->mark = newmark;
nf_conntrack_event_cache(IPCT_MARK, ct);
}
break;
case XT_CONNMARK_SAVE:
newmark = (ct->mark & ~info->ctmask) ^
(skb->mark & info->nfmask);
if (ct->mark != newmark) {
ct->mark = newmark;
nf_conntrack_event_cache(IPCT_MARK, ct);
}
// ------------- START of KNOX_VPN -----------------//
knoxvpn_uidpid(skb,newmark);
// ------------- END of KNOX_VPN -------------------//
break;
case XT_CONNMARK_RESTORE:
newmark = (skb->mark & ~info->nfmask) ^
(ct->mark & info->ctmask);
skb->mark = newmark;
// ------------- START of KNOX_VPN -----------------//
knoxvpn_uidpid(skb,newmark);
// ------------- END of KNOX_VPN -------------------//
break;
}
return XT_CONTINUE;
}
static unsigned int
ipt_dnat_target(struct sk_buff *skb, const struct xt_action_param *par)
{
struct nf_conn *ct;
enum ip_conntrack_info ctinfo;
const struct nf_nat_ipv4_multi_range_compat *mr = par->targinfo;
NF_CT_ASSERT(par->hooknum == NF_INET_PRE_ROUTING ||
par->hooknum == NF_INET_LOCAL_OUT);
ct = nf_ct_get(skb, &ctinfo);
/* Connection must be valid and new. */
NF_CT_ASSERT(ct && (ctinfo == IP_CT_NEW || ctinfo == IP_CT_RELATED));
return nf_nat_setup_info(ct, &mr->range[0], NF_NAT_MANIP_DST);
}
/* 'skb' should already be pulled to nh_ofs. */
static int ovs_ct_helper(struct sk_buff *skb, u16 proto)
{
const struct nf_conntrack_helper *helper;
const struct nf_conn_help *help;
enum ip_conntrack_info ctinfo;
unsigned int protoff;
struct nf_conn *ct;
ct = nf_ct_get(skb, &ctinfo);
if (!ct || ctinfo == IP_CT_RELATED_REPLY)
return NF_ACCEPT;
help = nfct_help(ct);
if (!help)
return NF_ACCEPT;
helper = rcu_dereference(help->helper);
if (!helper)
return NF_ACCEPT;
switch (proto) {
case NFPROTO_IPV4:
protoff = ip_hdrlen(skb);
break;
case NFPROTO_IPV6: {
u8 nexthdr = ipv6_hdr(skb)->nexthdr;
__be16 frag_off;
int ofs;
ofs = ipv6_skip_exthdr(skb, sizeof(struct ipv6hdr), &nexthdr,
&frag_off);
if (ofs < 0 || (frag_off & htons(~0x7)) != 0) {
pr_debug("proto header not found\n");
return NF_ACCEPT;
}
protoff = ofs;
break;
}
default:
WARN_ONCE(1, "helper invoked on non-IP family!");
return NF_DROP;
}
return helper->help(skb, protoff, ct, ctinfo);
}
/*
* vlantag_match_pre()
* One of the iptables hooks has a packet for us to analyze, do so.
*/
static bool vlantag_match_pre(const struct sk_buff *skb, const struct xt_action_param *par)
{
const struct xt_vlantag_match_info *info = par->targinfo;
struct nf_conn *ct;
enum ip_conntrack_info ctinfo;
struct nf_ct_vlantag_ext *ncve;
unsigned short int prio;
if (!is_vlan_dev(skb->dev)) {
DEBUGP("pre dev %s is not vlan\n", skb->dev->name);
return false;
}
ct = nf_ct_get(skb, &ctinfo);
if (!ct) {
DEBUGP("pre xt_VLANTAG: No conntrack connection\n");
return false;
}
ncve = nf_ct_vlantag_ext_find(ct);
if (!ncve) {
DEBUGP("pre xt_VLANTAG: No conntrack extension\n");
return false;
}
if ((skb->priority < XT_VLANTAG_SKB_PRIO_MIN) || (skb->priority > XT_VLANTAG_SKB_PRIO_MAX)) {
DEBUGP("pre dev: %s skb prioriy %d is out of range (%d - %d)",
skb->dev->name, skb->priority,
XT_VLANTAG_SKB_PRIO_MIN, XT_VLANTAG_SKB_PRIO_MAX);
return false;
}
prio = skb->priority - XT_VLANTAG_SKB_PRIO_MIN;
if ((prio & info->imask) == info->itag) {
ncve->prio = prio;
} else {
ncve->prio = XT_VLANTAG_EXT_PRIO_NOT_VALID;
}
ncve->imask = info->imask;
ncve->itag =info->itag;
DEBUGP("xt_VLANTAG: pre match continue\n");
return true;
}
static bool
lscan_mt(const struct sk_buff *skb, struct xt_action_param *par)
{
const struct xt_lscan_mtinfo *info = par->matchinfo;
enum ip_conntrack_info ctstate;
const struct tcphdr *tcph;
struct nf_conn *ctdata;
struct tcphdr tcph_buf;
tcph = skb_header_pointer(skb, par->thoff, sizeof(tcph_buf), &tcph_buf);
if (tcph == NULL)
return false;
/* Check for invalid packets: -m conntrack --ctstate INVALID */
if ((ctdata = nf_ct_get(skb, &ctstate)) == NULL) {
if (info->match_stealth)
return lscan_mt_stealth(tcph);
/*
* If @ctdata is NULL, we cannot match the other scan
* types, return.
*/
return false;
}
/*
* If -m lscan was previously applied to this packet, the rules we
* simulate must not be run through again. And for speedup, do not call
* it either when the connection is already VALID.
*/
if ((ctdata->mark & connmark_mask) == mark_valid ||
(skb_nfmark(skb) & packet_mask) != mark_seen) {
unsigned int n;
n = lscan_mt_full(ctdata->mark & connmark_mask, ctstate,
par->state->in == init_net.loopback_dev, tcph,
skb->len - par->thoff - 4 * tcph->doff);
ctdata->mark = (ctdata->mark & ~connmark_mask) | n;
skb_nfmark(skb) = (skb_nfmark(skb) & ~packet_mask) ^ mark_seen;
}
return (info->match_syn && ctdata->mark == mark_synscan) ||
(info->match_cn && ctdata->mark == mark_cnscan) ||
(info->match_gr && ctdata->mark == mark_grscan);
}
/* Source NAT */
static unsigned int
ipt_snat_target(struct sk_buff *skb, const struct xt_action_param *par)
{
struct nf_conn *ct;
enum ip_conntrack_info ctinfo;
const struct nf_nat_multi_range_compat *mr = par->targinfo;
NF_CT_ASSERT(par->hooknum == NF_INET_POST_ROUTING);
ct = nf_ct_get(skb, &ctinfo);
/* Connection must be valid and new. */
NF_CT_ASSERT(ct && (ctinfo == IP_CT_NEW || ctinfo == IP_CT_RELATED ||
ctinfo == IP_CT_RELATED + IP_CT_IS_REPLY));
NF_CT_ASSERT(par->out != NULL);
return nf_nat_setup_info(ct, &mr->range[0], IP_NAT_MANIP_SRC);
}
static unsigned int
nf_nat_adjust(unsigned int hooknum,
struct sk_buff *skb,
const struct net_device *in,
const struct net_device *out,
int (*okfn)(struct sk_buff *))
{
struct nf_conn *ct;
enum ip_conntrack_info ctinfo;
ct = nf_ct_get(skb, &ctinfo);
if (ct && test_bit(IPS_SEQ_ADJUST_BIT, &ct->status)) {
DEBUGP("nf_nat_standalone: adjusting sequence number\n");
if (!nf_nat_seq_adjust(skb, ct, ctinfo))
return NF_DROP;
}
return NF_ACCEPT;
}
static bool
state_mt(const struct sk_buff *skb, struct xt_action_param *par)
{
const struct xt_state_info *sinfo = par->matchinfo;
enum ip_conntrack_info ctinfo;
unsigned int statebit;
struct nf_conn *ct = nf_ct_get(skb, &ctinfo);
if (!ct)
statebit = XT_STATE_INVALID;
else {
if (nf_ct_is_untracked(ct))
statebit = XT_STATE_UNTRACKED;
else
statebit = XT_STATE_BIT(ctinfo);
}
return (sinfo->statemask & statebit);
}
static unsigned int ipv4_confirm(unsigned int hooknum,
struct sk_buff *skb,
const struct net_device *in,
const struct net_device *out,
int (*okfn)(struct sk_buff *))
{
struct nf_conn *ct;
enum ip_conntrack_info ctinfo;
const struct nf_conn_help *help;
const struct nf_conntrack_helper *helper;
unsigned int ret;
/* This is where we call the helper: as the packet goes out. */
ct = nf_ct_get(skb, &ctinfo);
if (!ct || ctinfo == IP_CT_RELATED + IP_CT_IS_REPLY)
goto out;
help = nfct_help(ct);
if (!help)
goto out;
/* rcu_read_lock()ed by nf_hook_slow */
helper = rcu_dereference(help->helper);
if (!helper)
goto out;
ret = helper->help(skb, skb_network_offset(skb) + ip_hdrlen(skb),
ct, ctinfo);
if (ret != NF_ACCEPT)
return ret;
if (test_bit(IPS_SEQ_ADJUST_BIT, &ct->status)) {
typeof(nf_nat_seq_adjust_hook) seq_adjust;
seq_adjust = rcu_dereference(nf_nat_seq_adjust_hook);
if (!seq_adjust || !seq_adjust(skb, ct, ctinfo)) {
NF_CT_STAT_INC_ATOMIC(nf_ct_net(ct), drop);
return NF_DROP;
}
}
out:
/* We've seen it coming out the other side: confirm it */
return nf_conntrack_confirm(skb);
}
/*
* vlantag_target_post()
* One of the iptables hooks has a packet for us to analyze, do so.
*/
static bool vlantag_target_post(struct sk_buff *skb, const struct xt_action_param *par)
{
const struct xt_vlantag_target_info *info = par->targinfo;
struct nf_conn *ct;
enum ip_conntrack_info ctinfo;
struct nf_ct_vlantag_ext *ncve;
unsigned int vlan_prio;
if (!is_vlan_dev(skb->dev)) {
DEBUGP("post dev %s is not vlan\n", skb->dev->name);
return true;
}
ct = nf_ct_get(skb, &ctinfo);
if (!ct) {
DEBUGP("post xt_VLANTAG: No conntrack connection\n");
return true;
}
ncve = nf_ct_vlantag_ext_find(ct);
if (!ncve) {
DEBUGP("post No vlan tag extension\n");
return true;
}
if (ncve->prio == XT_VLANTAG_EXT_PRIO_NOT_VALID) {
DEBUGP("post vlan tag ext prio is not set\n");
if ((skb->priority >= XT_VLANTAG_SKB_PRIO_MIN) && (skb->priority <= XT_VLANTAG_SKB_PRIO_MAX)) {
DEBUGP("but skb prio %d is in the range of our iptables rule, drop the packet\n", skb->priority);
return false;
}
return true;
}
vlan_prio = (ncve->prio & info->omask) | info->oval;
skb->priority = vlan_prio + XT_VLANTAG_SKB_PRIO_MIN;
ncve->magic = true;
ncve->omask = info->omask;
ncve->oval = info->oval;
DEBUGP("post xt_VLANTAG: post target continue\n");
return true;
}
unsigned int tse6_adjust(unsigned int hooknum,
struct sk_buff **pskb,
const struct net_device *in,
const struct net_device *out,
int (*okfn)(struct sk_buff *))
{
struct nf_conn *ct;
enum ip_conntrack_info ctinfo;
ct = nf_ct_get(*pskb, &ctinfo);
if (ct && test_bit(IPS_SEQ_ADJUST_BIT, &ct->status))
{
if (!tse6_seq_adjust(pskb, ct, ctinfo))
{
return NF_DROP;
}
}
return NF_ACCEPT;
}
/* Update 'key' based on skb->nfct. If 'post_ct' is true, then OVS has
* previously sent the packet to conntrack via the ct action.
*/
static void ovs_ct_update_key(const struct sk_buff *skb,
struct sw_flow_key *key, bool post_ct)
{
const struct nf_conntrack_zone *zone = &nf_ct_zone_dflt;
enum ip_conntrack_info ctinfo;
struct nf_conn *ct;
u8 state = 0;
ct = nf_ct_get(skb, &ctinfo);
if (ct) {
state = ovs_ct_get_state(ctinfo);
if (ct->master)
state |= OVS_CS_F_RELATED;
zone = nf_ct_zone(ct);
} else if (post_ct) {
state = OVS_CS_F_TRACKED | OVS_CS_F_INVALID;
}
__ovs_ct_update_key(key, state, zone, ct);
}
static bool
state_mt(const struct sk_buff *skb, const struct net_device *in,
const struct net_device *out, const struct xt_match *match,
const void *matchinfo, int offset, unsigned int protoff,
bool *hotdrop)
{
const struct xt_state_info *sinfo = matchinfo;
enum ip_conntrack_info ctinfo;
unsigned int statebit;
if (nf_ct_is_untracked(skb))
statebit = XT_STATE_UNTRACKED;
else if (!nf_ct_get(skb, &ctinfo))
statebit = XT_STATE_INVALID;
else
statebit = XT_STATE_BIT(ctinfo);
return (sinfo->statemask & statebit);
}
static bool
xt_cluster_mt(const struct sk_buff *skb, struct xt_action_param *par)
{
struct sk_buff *pskb = (struct sk_buff *)skb;
const struct xt_cluster_match_info *info = par->matchinfo;
const struct nf_conn *ct;
enum ip_conntrack_info ctinfo;
unsigned long hash;
/* This match assumes that all nodes see the same packets. This can be
* achieved if the switch that connects the cluster nodes support some
* sort of 'port mirroring'. However, if your switch does not support
* this, your cluster nodes can reply ARP request using a multicast MAC
* address. Thus, your switch will flood the same packets to the
* cluster nodes with the same multicast MAC address. Using a multicast
* link address is a RFC 1812 (section 3.3.2) violation, but this works
* fine in practise.
*
* Unfortunately, if you use the multicast MAC address, the link layer
* sets skbuff's pkt_type to PACKET_MULTICAST, which is not accepted
* by TCP and others for packets coming to this node. For that reason,
* this match mangles skbuff's pkt_type if it detects a packet
* addressed to a unicast address but using PACKET_MULTICAST. Yes, I
* know, matches should not alter packets, but we are doing this here
* because we would need to add a PKTTYPE target for this sole purpose.
*/
if (!xt_cluster_is_multicast_addr(skb, xt_family(par)) &&
skb->pkt_type == PACKET_MULTICAST) {
pskb->pkt_type = PACKET_HOST;
}
ct = nf_ct_get(skb, &ctinfo);
if (ct == NULL)
return false;
if (ct->master)
hash = xt_cluster_hash(ct->master, info);
else
hash = xt_cluster_hash(ct, info);
return !!((1 << hash) & info->node_mask) ^
!!(info->flags & XT_CLUSTER_F_INV);
}
static unsigned int
target(struct sk_buff **pskb,
const struct net_device *in,
const struct net_device *out,
unsigned int hooknum,
const struct xt_target *target,
const void *targinfo)
{
const struct xt_connmark_target_info *markinfo = targinfo;
struct nf_conn *ct;
enum ip_conntrack_info ctinfo;
u_int32_t diff;
u_int32_t mark;
u_int32_t newmark;
ct = nf_ct_get(*pskb, &ctinfo);
if (ct) {
switch(markinfo->mode) {
case XT_CONNMARK_SET:
newmark = (ct->mark & ~markinfo->mask) | markinfo->mark;
if (newmark != ct->mark) {
ct->mark = newmark;
nf_conntrack_event_cache(IPCT_MARK, *pskb);
}
break;
case XT_CONNMARK_SAVE:
newmark = (ct->mark & ~markinfo->mask) |
((*pskb)->mark & markinfo->mask);
if (ct->mark != newmark) {
ct->mark = newmark;
nf_conntrack_event_cache(IPCT_MARK, *pskb);
}
break;
case XT_CONNMARK_RESTORE:
mark = (*pskb)->mark;
diff = (ct->mark ^ mark) & markinfo->mask;
(*pskb)->mark = mark ^ diff;
break;
}
}
return XT_CONTINUE;
}
unsigned int
nf_nat_ipv4_local_fn(const struct nf_hook_ops *ops, struct sk_buff *skb,
const struct net_device *in, const struct net_device *out,
unsigned int (*do_chain)(const struct nf_hook_ops *ops,
struct sk_buff *skb,
const struct net_device *in,
const struct net_device *out,
struct nf_conn *ct))
{
const struct nf_conn *ct;
enum ip_conntrack_info ctinfo;
unsigned int ret;
int err;
/* root is playing with raw sockets. */
if (skb->len < sizeof(struct iphdr) ||
ip_hdrlen(skb) < sizeof(struct iphdr))
return NF_ACCEPT;
ret = nf_nat_ipv4_fn(ops, skb, in, out, do_chain);
if (ret != NF_DROP && ret != NF_STOLEN &&
(ct = nf_ct_get(skb, &ctinfo)) != NULL) {
enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo);
if (ct->tuplehash[dir].tuple.dst.u3.ip !=
ct->tuplehash[!dir].tuple.src.u3.ip) {
err = ip_route_me_harder(skb, RTN_UNSPEC);
if (err < 0)
ret = NF_DROP_ERR(err);
}
#ifdef CONFIG_XFRM
else if (!(IPCB(skb)->flags & IPSKB_XFRM_TRANSFORMED) &&
ct->tuplehash[dir].tuple.dst.protonum != IPPROTO_ICMP &&
ct->tuplehash[dir].tuple.dst.u.all !=
ct->tuplehash[!dir].tuple.src.u.all) {
err = nf_xfrm_me_harder(skb, AF_INET);
if (err < 0)
ret = NF_DROP_ERR(err);
}
#endif
}
return ret;
}
static unsigned int ipv6_confirm(unsigned int hooknum,
struct sk_buff **pskb,
const struct net_device *in,
const struct net_device *out,
int (*okfn)(struct sk_buff *))
{
struct nf_conn *ct;
struct nf_conn_help *help;
struct nf_conntrack_helper *helper;
enum ip_conntrack_info ctinfo;
unsigned int ret, protoff;
unsigned int extoff = (u8 *)(ipv6_hdr(*pskb) + 1) - (*pskb)->data;
unsigned char pnum = ipv6_hdr(*pskb)->nexthdr;
/* This is where we call the helper: as the packet goes out. */
ct = nf_ct_get(*pskb, &ctinfo);
if (!ct || ctinfo == IP_CT_RELATED + IP_CT_IS_REPLY)
goto out;
help = nfct_help(ct);
if (!help)
goto out;
/* rcu_read_lock()ed by nf_hook_slow */
helper = rcu_dereference(help->helper);
if (!helper)
goto out;
protoff = nf_ct_ipv6_skip_exthdr(*pskb, extoff, &pnum,
(*pskb)->len - extoff);
if (protoff > (*pskb)->len || pnum == NEXTHDR_FRAGMENT) {
DEBUGP("proto header not found\n");
return NF_ACCEPT;
}
ret = helper->help(pskb, protoff, ct, ctinfo);
if (ret != NF_ACCEPT)
return ret;
out:
/* We've seen it coming out the other side: confirm it */
return nf_conntrack_confirm(pskb);
}
static void nat_decode_session(struct sk_buff *skb, struct flowi *fl)
{
struct flowi4 *fl4 = &fl->u.ip4;
const struct nf_conn *ct;
const struct nf_conntrack_tuple *t;
enum ip_conntrack_info ctinfo;
enum ip_conntrack_dir dir;
unsigned long statusbit;
ct = nf_ct_get(skb, &ctinfo);
if (ct == NULL)
return;
dir = CTINFO2DIR(ctinfo);
t = &ct->tuplehash[dir].tuple;
if (dir == IP_CT_DIR_ORIGINAL)
statusbit = IPS_DST_NAT;
else
statusbit = IPS_SRC_NAT;
if (ct->status & statusbit) {
fl4->daddr = t->dst.u3.ip;
if (t->dst.protonum == IPPROTO_TCP ||
t->dst.protonum == IPPROTO_UDP ||
t->dst.protonum == IPPROTO_UDPLITE ||
t->dst.protonum == IPPROTO_DCCP ||
t->dst.protonum == IPPROTO_SCTP)
fl4->fl4_dport = t->dst.u.tcp.port;
}
statusbit ^= IPS_NAT_MASK;
if (ct->status & statusbit) {
fl4->saddr = t->src.u3.ip;
if (t->dst.protonum == IPPROTO_TCP ||
t->dst.protonum == IPPROTO_UDP ||
t->dst.protonum == IPPROTO_UDPLITE ||
t->dst.protonum == IPPROTO_DCCP ||
t->dst.protonum == IPPROTO_SCTP)
fl4->fl4_sport = t->src.u.tcp.port;
}
}
static unsigned int nf_nat_sdp_addr(struct sk_buff *skb, unsigned int protoff,
unsigned int dataoff,
const char **dptr, unsigned int *datalen,
unsigned int sdpoff,
enum sdp_header_types type,
enum sdp_header_types term,
const union nf_inet_addr *addr)
{
enum ip_conntrack_info ctinfo;
struct nf_conn *ct = nf_ct_get(skb, &ctinfo);
char buffer[INET6_ADDRSTRLEN];
unsigned int buflen;
buflen = sip_sprintf_addr(ct, buffer, addr, false);
if (mangle_sdp_packet(skb, protoff, dataoff, dptr, datalen,
sdpoff, type, term, buffer, buflen))
return 0;
return mangle_content_len(skb, protoff, dataoff, dptr, datalen);
}
static int
match(const struct sk_buff *skb,
const struct net_device *in,
const struct net_device *out,
const struct xt_match *match,
const void *matchinfo,
int offset,
unsigned int protoff,
int *hotdrop)
{
const struct xt_connmark_info *info = matchinfo;
struct nf_conn *ct;
enum ip_conntrack_info ctinfo;
ct = nf_ct_get(skb, &ctinfo);
if (!ct)
return 0;
return (((ct->mark) & info->mask) == info->mark) ^ info->invert;
}
static enum ip_defrag_users nf_ct_defrag_user(unsigned int hooknum,
struct sk_buff *skb)
{
u16 zone_id = NF_CT_DEFAULT_ZONE_ID;
#if IS_ENABLED(CONFIG_NF_CONNTRACK)
if (skb->nfct) {
enum ip_conntrack_info ctinfo;
const struct nf_conn *ct = nf_ct_get(skb, &ctinfo);
zone_id = nf_ct_zone_id(nf_ct_zone(ct), CTINFO2DIR(ctinfo));
}
#endif
if (nf_bridge_in_prerouting(skb))
return IP_DEFRAG_CONNTRACK_BRIDGE_IN + zone_id;
if (hooknum == NF_INET_PRE_ROUTING)
return IP_DEFRAG_CONNTRACK_IN + zone_id;
else
return IP_DEFRAG_CONNTRACK_OUT + zone_id;
}
unsigned int
nf_nat_ipv6_local_fn(void *priv, struct sk_buff *skb,
const struct nf_hook_state *state,
unsigned int (*do_chain)(void *priv,
struct sk_buff *skb,
const struct nf_hook_state *state,
struct nf_conn *ct))
{
const struct nf_conn *ct;
enum ip_conntrack_info ctinfo;
unsigned int ret;
int err;
/* root is playing with raw sockets. */
if (skb->len < sizeof(struct ipv6hdr))
return NF_ACCEPT;
ret = nf_nat_ipv6_fn(priv, skb, state, do_chain);
if (ret != NF_DROP && ret != NF_STOLEN &&
(ct = nf_ct_get(skb, &ctinfo)) != NULL) {
enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo);
if (!nf_inet_addr_cmp(&ct->tuplehash[dir].tuple.dst.u3,
&ct->tuplehash[!dir].tuple.src.u3)) {
err = ip6_route_me_harder(state->net, skb);
if (err < 0)
ret = NF_DROP_ERR(err);
}
#ifdef CONFIG_XFRM
else if (!(IP6CB(skb)->flags & IP6SKB_XFRM_TRANSFORMED) &&
ct->tuplehash[dir].tuple.dst.protonum != IPPROTO_ICMPV6 &&
ct->tuplehash[dir].tuple.dst.u.all !=
ct->tuplehash[!dir].tuple.src.u.all) {
err = nf_xfrm_me_harder(state->net, skb, AF_INET6);
if (err < 0)
ret = NF_DROP_ERR(err);
}
#endif
}
return ret;
}
static void nft_nat_eval(const struct nft_expr *expr,
struct nft_data data[NFT_REG_MAX + 1],
const struct nft_pktinfo *pkt)
{
const struct nft_nat *priv = nft_expr_priv(expr);
enum ip_conntrack_info ctinfo;
struct nf_conn *ct = nf_ct_get(pkt->skb, &ctinfo);
struct nf_nat_range range;
memset(&range, 0, sizeof(range));
if (priv->sreg_addr_min) {
if (priv->family == AF_INET) {
range.min_addr.ip = (__force __be32)
data[priv->sreg_addr_min].data[0];
range.max_addr.ip = (__force __be32)
data[priv->sreg_addr_max].data[0];
} else {
memcpy(range.min_addr.ip6,
data[priv->sreg_addr_min].data,
sizeof(struct nft_data));
memcpy(range.max_addr.ip6,
data[priv->sreg_addr_max].data,
sizeof(struct nft_data));
}
range.flags |= NF_NAT_RANGE_MAP_IPS;
}
if (priv->sreg_proto_min) {
range.min_proto.all =
*(__be16 *)&data[priv->sreg_proto_min].data[0];
range.max_proto.all =
*(__be16 *)&data[priv->sreg_proto_max].data[0];
range.flags |= NF_NAT_RANGE_PROTO_SPECIFIED;
}
range.flags |= priv->flags;
data[NFT_REG_VERDICT].verdict =
nf_nat_setup_info(ct, &range, priv->type);
}
static unsigned int ipv4_conntrack_local(void *priv,
struct sk_buff *skb,
const struct nf_hook_state *state)
{
if (ip_is_fragment(ip_hdr(skb))) { /* IP_NODEFRAG setsockopt set */
enum ip_conntrack_info ctinfo;
struct nf_conn *tmpl;
tmpl = nf_ct_get(skb, &ctinfo);
if (tmpl && nf_ct_is_template(tmpl)) {
/* when skipping ct, clear templates to avoid fooling
* later targets/matches
*/
skb->_nfct = 0;
nf_ct_put(tmpl);
}
return NF_ACCEPT;
}
return nf_conntrack_in(state->net, PF_INET, state->hook, skb);
}
/* 获取缓存socket的HOOK函数 */
static unsigned int ipv4_conntrack_restore_sock (unsigned int hooknum,
struct sk_buff *skb,
const struct net_device *in,
const struct net_device *out,
int (*okfn)(struct sk_buff *))
{
struct nf_conn *ct;
enum ip_conntrack_info ctinfo;
struct nf_conntrack_ext *exts;
ct = nf_ct_get(skb, &ctinfo);
if (!ct || ct == &nf_conntrack_untracked){
goto out;
}
if ((ip_hdr(skb)->protocol != IPPROTO_UDP) &&
(ip_hdr(skb)->protocol != IPPROTO_TCP)) {
goto out;
}
exts = nf_conn_exts_find(ct);
if (exts) {
/* 获取缓存的socket */
if (exts->bits_idx[CONN_SOCK] != -1) {
struct sock *sk = (struct sock *)nf_ct_exts_get(ct, exts->bits_idx[CONN_SOCK]);
if (sk) {
if ((ip_hdr(skb)->protocol == IPPROTO_TCP) && sk->sk_state != TCP_ESTABLISHED) {
goto out;
}
if (unlikely(!atomic_inc_not_zero(&sk->sk_refcnt))) {
goto out;
}
skb_orphan(skb);
skb->sk = sk;
/* 曾经在上面atomic inc了引用计数，等到转交给下任owner的时候，一定要put */
skb->destructor = nf_ext_destructor;
}
}
}
out:
return NF_ACCEPT;
}
unsigned int
nf_nat_ipv4_out(void *priv, struct sk_buff *skb,
const struct nf_hook_state *state,
unsigned int (*do_chain)(void *priv,
struct sk_buff *skb,
const struct nf_hook_state *state,
struct nf_conn *ct))
{
#ifdef CONFIG_XFRM
const struct nf_conn *ct;
enum ip_conntrack_info ctinfo;
int err;
#endif
unsigned int ret;
/* root is playing with raw sockets. */
if (skb->len < sizeof(struct iphdr) ||
ip_hdrlen(skb) < sizeof(struct iphdr))
return NF_ACCEPT;
ret = nf_nat_ipv4_fn(priv, skb, state, do_chain);
#ifdef CONFIG_XFRM
if (ret != NF_DROP && ret != NF_STOLEN &&
!(IPCB(skb)->flags & IPSKB_XFRM_TRANSFORMED) &&
(ct = nf_ct_get(skb, &ctinfo)) != NULL) {
enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo);
if ((ct->tuplehash[dir].tuple.src.u3.ip !=
ct->tuplehash[!dir].tuple.dst.u3.ip) ||
(ct->tuplehash[dir].tuple.dst.protonum != IPPROTO_ICMP &&
ct->tuplehash[dir].tuple.src.u.all !=
ct->tuplehash[!dir].tuple.dst.u.all)) {
err = nf_xfrm_me_harder(state->net, skb, AF_INET);
if (err < 0)
ret = NF_DROP_ERR(err);
}
}
#endif
return ret;
}
unsigned int
nf_nat_ipv6_out(const struct nf_hook_ops *ops, struct sk_buff *skb,
const struct net_device *in, const struct net_device *out,
unsigned int (*do_chain)(const struct nf_hook_ops *ops,
struct sk_buff *skb,
const struct net_device *in,
const struct net_device *out,
struct nf_conn *ct))
{
#ifdef CONFIG_XFRM
const struct nf_conn *ct;
enum ip_conntrack_info ctinfo;
int err;
#endif
unsigned int ret;
/* root is playing with raw sockets. */
if (skb->len < sizeof(struct ipv6hdr))
return NF_ACCEPT;
ret = nf_nat_ipv6_fn(ops, skb, in, out, do_chain);
#ifdef CONFIG_XFRM
if (ret != NF_DROP && ret != NF_STOLEN &&
!(IP6CB(skb)->flags & IP6SKB_XFRM_TRANSFORMED) &&
(ct = nf_ct_get(skb, &ctinfo)) != NULL) {
enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo);
if (!nf_inet_addr_cmp(&ct->tuplehash[dir].tuple.src.u3,
&ct->tuplehash[!dir].tuple.dst.u3) ||
(ct->tuplehash[dir].tuple.dst.protonum != IPPROTO_ICMPV6 &&
ct->tuplehash[dir].tuple.src.u.all !=
ct->tuplehash[!dir].tuple.dst.u.all)) {
err = nf_xfrm_me_harder(skb, AF_INET6);
if (err < 0)
ret = NF_DROP_ERR(err);
}
}
#endif
return ret;
}
