struct nf_conn_colo *
nf_ct_colo_get(struct sk_buff *skb, struct colo_node *node, u32 flag)
{
enum ip_conntrack_info ctinfo;
struct nf_conn *ct;
struct nf_conn_colo *colo_conn;
ct = nf_ct_get(skb, &ctinfo);
if (ct == NULL || ct == nf_ct_untracked_get()) {
return NULL;
}
colo_conn = nfct_colo(ct);
if (colo_conn == NULL) {
colo_conn = nfct_create_colo(ct, node->vm_pid, flag);
if (colo_conn == NULL) {
pr_dbg("create colo conn failed!\n");
return NULL;
}
nfct_init_colo(colo_conn, node->vm_pid, flag);
pr_dbg("colo_tg: create conn %p for contrack %p node:%d,\n",
colo_conn, ct, node->vm_pid);
}
return colo_conn;
}
static unsigned int
tee_tg6(struct sk_buff *skb, const struct xt_action_param *par)
{
const struct xt_tee_tginfo *info = par->targinfo;
if (percpu_read(tee_active))
return XT_CONTINUE;
skb = pskb_copy(skb, GFP_ATOMIC);
if (skb == NULL)
return XT_CONTINUE;
#ifdef WITH_CONNTRACK
nf_conntrack_put(skb->nfct);
skb->nfct = &nf_ct_untracked_get()->ct_general;
skb->nfctinfo = IP_CT_NEW;
nf_conntrack_get(skb->nfct);
#endif
if (par->hooknum == NF_INET_PRE_ROUTING ||
par->hooknum == NF_INET_LOCAL_IN) {
struct ipv6hdr *iph = ipv6_hdr(skb);
--iph->hop_limit;
}
if (tee_tg_route6(skb, info)) {
percpu_write(tee_active, true);
ip6_local_out(skb);
percpu_write(tee_active, false);
} else {
kfree_skb(skb);
}
return XT_CONTINUE;
}
void nf_dup_ipv6(struct net *net, struct sk_buff *skb, unsigned int hooknum,
const struct in6_addr *gw, int oif)
{
if (this_cpu_read(nf_skb_duplicated))
return;
skb = pskb_copy(skb, GFP_ATOMIC);
if (skb == NULL)
return;
#if IS_ENABLED(CONFIG_NF_CONNTRACK)
nf_conntrack_put(skb->nfct);
skb->nfct = &nf_ct_untracked_get()->ct_general;
skb->nfctinfo = IP_CT_NEW;
nf_conntrack_get(skb->nfct);
#endif
if (hooknum == NF_INET_PRE_ROUTING ||
hooknum == NF_INET_LOCAL_IN) {
struct ipv6hdr *iph = ipv6_hdr(skb);
--iph->hop_limit;
}
if (nf_dup_ipv6_route(net, skb, gw, oif)) {
__this_cpu_write(nf_skb_duplicated, true);
ip6_local_out(net, skb->sk, skb);
__this_cpu_write(nf_skb_duplicated, false);
} else {
kfree_skb(skb);
}
}
static unsigned int
notrack_tg(struct sk_buff *skb, const struct xt_action_param *par)
{
/* Previously seen (loopback)? Ignore. */
if (skb->nfct != NULL)
return XT_CONTINUE;
skb->nfct = &nf_ct_untracked_get()->ct_general;
skb->nfctinfo = IP_CT_NEW;
nf_conntrack_get(skb->nfct);
return XT_CONTINUE;
}
static unsigned int
tee_tg4(struct sk_buff *skb, const struct xt_action_param *par)
{
const struct xt_tee_tginfo *info = par->targinfo;
struct iphdr *iph;
if (percpu_read(tee_active))
return XT_CONTINUE;
/*
* Copy the skb, and route the copy. Will later return %XT_CONTINUE for
* the original skb, which should continue on its way as if nothing has
* happened. The copy should be independently delivered to the TEE
* --gateway.
*/
skb = pskb_copy(skb, GFP_ATOMIC);
if (skb == NULL)
return XT_CONTINUE;
#ifdef WITH_CONNTRACK
/* Avoid counting cloned packets towards the original connection. */
nf_conntrack_put(skb->nfct);
skb->nfct = &nf_ct_untracked_get()->ct_general;
skb->nfctinfo = IP_CT_NEW;
nf_conntrack_get(skb->nfct);
#endif
/*
* If we are in PREROUTING/INPUT, the checksum must be recalculated
* since the length could have changed as a result of defragmentation.
*
* We also decrease the TTL to mitigate potential TEE loops
* between two hosts.
*
* Set %IP_DF so that the original source is notified of a potentially
* decreased MTU on the clone route. IPv6 does this too.
*/
iph = ip_hdr(skb);
iph->frag_off |= htons(IP_DF);
if (par->hooknum == NF_INET_PRE_ROUTING ||
par->hooknum == NF_INET_LOCAL_IN)
--iph->ttl;
ip_send_check(iph);
if (tee_tg_route4(skb, info)) {
percpu_write(tee_active, true);
ip_local_out(skb);
percpu_write(tee_active, false);
} else {
kfree_skb(skb);
}
return XT_CONTINUE;
}
static inline int xt_ct_target(struct sk_buff *skb, struct nf_conn *ct)
{
/* Previously seen (loopback)? Ignore. */
if (skb->nfct != NULL)
return XT_CONTINUE;
/* special case the untracked ct : we want the percpu object */
if (!ct)
ct = nf_ct_untracked_get();
atomic_inc(&ct->ct_general.use);
skb->nfct = &ct->ct_general;
skb->nfctinfo = IP_CT_NEW;
return XT_CONTINUE;
}
void nf_dup_ipv4(struct net *net, struct sk_buff *skb, unsigned int hooknum,
const struct in_addr *gw, int oif)
{
struct iphdr *iph;
if (this_cpu_read(nf_skb_duplicated))
return;
/*
* Copy the skb, and route the copy. Will later return %XT_CONTINUE for
* the original skb, which should continue on its way as if nothing has
* happened. The copy should be independently delivered to the gateway.
*/
skb = pskb_copy(skb, GFP_ATOMIC);
if (skb == NULL)
return;
#if IS_ENABLED(CONFIG_NF_CONNTRACK)
/* Avoid counting cloned packets towards the original connection. */
nf_conntrack_put(skb->nfct);
skb->nfct = &nf_ct_untracked_get()->ct_general;
skb->nfctinfo = IP_CT_NEW;
nf_conntrack_get(skb->nfct);
#endif
/*
* If we are in PREROUTING/INPUT, the checksum must be recalculated
* since the length could have changed as a result of defragmentation.
*
* We also decrease the TTL to mitigate potential loops between two
* hosts.
*
* Set %IP_DF so that the original source is notified of a potentially
* decreased MTU on the clone route. IPv6 does this too.
*/
iph = ip_hdr(skb);
iph->frag_off |= htons(IP_DF);
if (hooknum == NF_INET_PRE_ROUTING ||
hooknum == NF_INET_LOCAL_IN)
--iph->ttl;
ip_send_check(iph);
if (nf_dup_ipv4_route(net, skb, gw, oif)) {
__this_cpu_write(nf_skb_duplicated, true);
ip_local_out(net, skb->sk, skb);
__this_cpu_write(nf_skb_duplicated, false);
} else {
kfree_skb(skb);
}
}
static unsigned int
notrack_tg(struct sk_buff *skb, const struct xt_action_param *par)
{
/* Previously seen (loopback)? Ignore. */
if (skb->nfct != NULL)
return XT_CONTINUE;
/* Attach fake conntrack entry.
If there is a real ct entry correspondig to this packet,
it'll hang aroun till timing out. We don't deal with it
for performance reasons. JK */
skb->nfct = &nf_ct_untracked_get()->ct_general;
skb->nfctinfo = IP_CT_NEW;
nf_conntrack_get(skb->nfct);
return XT_CONTINUE;
}
static int
icmpv6_error(struct net *net, struct nf_conn *tmpl,
struct sk_buff *skb, unsigned int dataoff,
enum ip_conntrack_info *ctinfo, u_int8_t pf, unsigned int hooknum)
{
const struct icmp6hdr *icmp6h;
struct icmp6hdr _ih;
int type;
icmp6h = skb_header_pointer(skb, dataoff, sizeof(_ih), &_ih);
if (icmp6h == NULL) {
if (LOG_INVALID(net, IPPROTO_ICMPV6))
nf_log_packet(PF_INET6, 0, skb, NULL, NULL, NULL,
"nf_ct_icmpv6: short packet ");
return -NF_ACCEPT;
}
if (net->ct.sysctl_checksum && hooknum == NF_INET_PRE_ROUTING &&
nf_ip6_checksum(skb, hooknum, dataoff, IPPROTO_ICMPV6)) {
if (LOG_INVALID(net, IPPROTO_ICMPV6))
nf_log_packet(PF_INET6, 0, skb, NULL, NULL, NULL,
"nf_ct_icmpv6: ICMPv6 checksum failed ");
return -NF_ACCEPT;
}
type = icmp6h->icmp6_type - 130;
if (type >= 0 && type < sizeof(noct_valid_new) &&
noct_valid_new[type]) {
skb->nfct = &nf_ct_untracked_get()->ct_general;
skb->nfctinfo = IP_CT_NEW;
nf_conntrack_get(skb->nfct);
return NF_ACCEPT;
}
if (icmp6h->icmp6_type >= 128)
return NF_ACCEPT;
return icmpv6_error_message(net, tmpl, skb, dataoff, ctinfo, hooknum);
}
static int xt_ct_tg_check(const struct xt_tgchk_param *par)
{
struct xt_ct_target_info *info = par->targinfo;
struct nf_conntrack_tuple t;
struct nf_conn_help *help;
struct nf_conn *ct;
int ret = 0;
u8 proto;
if (info->flags & ~XT_CT_NOTRACK)
return -EINVAL;
if (info->flags & XT_CT_NOTRACK) {
ct = nf_ct_untracked_get();
atomic_inc(&ct->ct_general.use);
goto out;
}
#ifndef CONFIG_NF_CONNTRACK_ZONES
if (info->zone)
goto err1;
#endif
ret = nf_ct_l3proto_try_module_get(par->family);
if (ret < 0)
goto err1;
memset(&t, 0, sizeof(t));
ct = nf_conntrack_alloc(par->net, info->zone, &t, &t, GFP_KERNEL);
ret = PTR_ERR(ct);
if (IS_ERR(ct))
goto err2;
ret = 0;
if ((info->ct_events || info->exp_events) &&
!nf_ct_ecache_ext_add(ct, info->ct_events, info->exp_events,
GFP_KERNEL))
goto err3;
if (info->helper[0]) {
ret = -ENOENT;
proto = xt_ct_find_proto(par);
if (!proto)
goto err3;
ret = -ENOMEM;
help = nf_ct_helper_ext_add(ct, GFP_KERNEL);
if (help == NULL)
goto err3;
ret = -ENOENT;
help->helper = nf_conntrack_helper_try_module_get(info->helper,
par->family,
proto);
if (help->helper == NULL)
goto err3;
}
__set_bit(IPS_TEMPLATE_BIT, &ct->status);
__set_bit(IPS_CONFIRMED_BIT, &ct->status);
out:
info->ct = ct;
return 0;
err3:
nf_conntrack_free(ct);
err2:
nf_ct_l3proto_module_put(par->family);
err1:
return ret;
}
static int xt_ct_tg_check_v1(const struct xt_tgchk_param *par)
{
struct xt_ct_target_info_v1 *info = par->targinfo;
struct nf_conntrack_tuple t;
struct nf_conn_help *help;
struct nf_conn *ct;
int ret = 0;
u8 proto;
#ifdef CONFIG_NF_CONNTRACK_TIMEOUT
struct ctnl_timeout *timeout;
#endif
if (info->flags & ~XT_CT_NOTRACK)
return -EINVAL;
if (info->flags & XT_CT_NOTRACK) {
ct = nf_ct_untracked_get();
atomic_inc(&ct->ct_general.use);
goto out;
}
#ifndef CONFIG_NF_CONNTRACK_ZONES
if (info->zone)
goto err1;
#endif
ret = nf_ct_l3proto_try_module_get(par->family);
if (ret < 0)
goto err1;
memset(&t, 0, sizeof(t));
ct = nf_conntrack_alloc(par->net, info->zone, &t, &t, GFP_KERNEL);
ret = PTR_ERR(ct);
if (IS_ERR(ct))
goto err2;
ret = 0;
if ((info->ct_events || info->exp_events) &&
!nf_ct_ecache_ext_add(ct, info->ct_events, info->exp_events,
GFP_KERNEL))
goto err3;
if (info->helper[0]) {
ret = -ENOENT;
proto = xt_ct_find_proto(par);
if (!proto) {
pr_info("You must specify a L4 protocol, "
"and not use inversions on it.\n");
goto err3;
}
ret = -ENOMEM;
help = nf_ct_helper_ext_add(ct, GFP_KERNEL);
if (help == NULL)
goto err3;
ret = -ENOENT;
help->helper = nf_conntrack_helper_try_module_get(info->helper,
par->family,
proto);
if (help->helper == NULL) {
pr_info("No such helper \"%s\"\n", info->helper);
goto err3;
}
}
#ifdef CONFIG_NF_CONNTRACK_TIMEOUT
if (info->timeout[0]) {
typeof(nf_ct_timeout_find_get_hook) timeout_find_get;
struct nf_conn_timeout *timeout_ext;
rcu_read_lock();
timeout_find_get =
rcu_dereference(nf_ct_timeout_find_get_hook);
if (timeout_find_get) {
const struct ipt_entry *e = par->entryinfo;
struct nf_conntrack_l4proto *l4proto;
if (e->ip.invflags & IPT_INV_PROTO) {
ret = -EINVAL;
pr_info("You cannot use inversion on "
"L4 protocol\n");
goto err4;
}
timeout = timeout_find_get(info->timeout);
if (timeout == NULL) {
ret = -ENOENT;
pr_info("No such timeout policy \"%s\"\n",
info->timeout);
goto err4;
}
if (timeout->l3num != par->family) {
ret = -EINVAL;
pr_info("Timeout policy `%s' can only be "
"used by L3 protocol number %d\n",
info->timeout, timeout->l3num);
goto err5;
}
/* Make sure the timeout policy matches any existing
* protocol tracker, otherwise default to generic.
*/
l4proto = __nf_ct_l4proto_find(par->family,
e->ip.proto);
if (timeout->l4proto->l4proto != l4proto->l4proto) {
ret = -EINVAL;
pr_info("Timeout policy `%s' can only be "
"used by L4 protocol number %d\n",
info->timeout,
timeout->l4proto->l4proto);
goto err5;
}
timeout_ext = nf_ct_timeout_ext_add(ct, timeout,
GFP_ATOMIC);
if (timeout_ext == NULL) {
ret = -ENOMEM;
goto err5;
}
} else {
ret = -ENOENT;
pr_info("Timeout policy base is empty\n");
goto err4;
}
rcu_read_unlock();
}
#endif
__set_bit(IPS_TEMPLATE_BIT, &ct->status);
__set_bit(IPS_CONFIRMED_BIT, &ct->status);
out:
info->ct = ct;
return 0;
#ifdef CONFIG_NF_CONNTRACK_TIMEOUT
err5:
__xt_ct_tg_timeout_put(timeout);
err4:
rcu_read_unlock();
#endif
err3:
nf_conntrack_free(ct);
err2:
nf_ct_l3proto_module_put(par->family);
err1:
return ret;
}