/* Returns verdict for packet, or -1 for invalid. */
static int icmp_packet(struct nf_conn *ct,
const struct sk_buff *skb,
unsigned int dataoff,
enum ip_conntrack_info ctinfo,
u_int8_t pf,
unsigned int hooknum)
{
/* Try to delete connection immediately after all replies:
won't actually vanish as we still have skb, and del_timer
means this will only run once even if count hits zero twice
(theoretically possible with SMP) */
if (CTINFO2DIR(ctinfo) == IP_CT_DIR_REPLY) {
if (atomic_dec_and_test(&ct->proto.icmp.count))
nf_ct_kill_acct(ct, ctinfo, skb);
} else {
atomic_inc(&ct->proto.icmp.count);
nf_conntrack_event_cache(IPCT_PROTOINFO_VOLATILE, ct);
nf_ct_refresh_acct(ct, ctinfo, skb, nf_ct_icmp_timeout);
}
return NF_ACCEPT;
}
static int dccp_packet(struct nf_conn *ct, const struct sk_buff *skb,
unsigned int dataoff, enum ip_conntrack_info ctinfo,
u_int8_t pf, unsigned int hooknum,
unsigned int *timeouts)
{
struct net *net = nf_ct_net(ct);
enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo);
struct dccp_hdr _dh, *dh;
u_int8_t type, old_state, new_state;
enum ct_dccp_roles role;
dh = skb_header_pointer(skb, dataoff, sizeof(_dh), &_dh);
BUG_ON(dh == NULL);
type = dh->dccph_type;
if (type == DCCP_PKT_RESET &&
!test_bit(IPS_SEEN_REPLY_BIT, &ct->status)) {
/* Tear down connection immediately if only reply is a RESET */
nf_ct_kill_acct(ct, ctinfo, skb);
return NF_ACCEPT;
}
spin_lock_bh(&ct->lock);
role = ct->proto.dccp.role[dir];
old_state = ct->proto.dccp.state;
new_state = dccp_state_table[role][type][old_state];
switch (new_state) {
case CT_DCCP_REQUEST:
if (old_state == CT_DCCP_TIMEWAIT &&
role == CT_DCCP_ROLE_SERVER) {
/* Reincarnation in the reverse direction: reopen and
* reverse client/server roles. */
ct->proto.dccp.role[dir] = CT_DCCP_ROLE_CLIENT;
ct->proto.dccp.role[!dir] = CT_DCCP_ROLE_SERVER;
}
break;
case CT_DCCP_RESPOND:
if (old_state == CT_DCCP_REQUEST)
ct->proto.dccp.handshake_seq = dccp_hdr_seq(dh);
break;
case CT_DCCP_PARTOPEN:
if (old_state == CT_DCCP_RESPOND &&
type == DCCP_PKT_ACK &&
dccp_ack_seq(dh) == ct->proto.dccp.handshake_seq)
set_bit(IPS_ASSURED_BIT, &ct->status);
break;
case CT_DCCP_IGNORE:
/*
* Connection tracking might be out of sync, so we ignore
* packets that might establish a new connection and resync
* if the server responds with a valid Response.
*/
if (ct->proto.dccp.last_dir == !dir &&
ct->proto.dccp.last_pkt == DCCP_PKT_REQUEST &&
type == DCCP_PKT_RESPONSE) {
ct->proto.dccp.role[!dir] = CT_DCCP_ROLE_CLIENT;
ct->proto.dccp.role[dir] = CT_DCCP_ROLE_SERVER;
ct->proto.dccp.handshake_seq = dccp_hdr_seq(dh);
new_state = CT_DCCP_RESPOND;
break;
}
ct->proto.dccp.last_dir = dir;
ct->proto.dccp.last_pkt = type;
spin_unlock_bh(&ct->lock);
if (LOG_INVALID(net, IPPROTO_DCCP))
nf_log_packet(pf, 0, skb, NULL, NULL, NULL,
"nf_ct_dccp: invalid packet ignored ");
return NF_ACCEPT;
case CT_DCCP_INVALID:
spin_unlock_bh(&ct->lock);
if (LOG_INVALID(net, IPPROTO_DCCP))
nf_log_packet(pf, 0, skb, NULL, NULL, NULL,
"nf_ct_dccp: invalid state transition ");
return -NF_ACCEPT;
}
ct->proto.dccp.last_dir = dir;
ct->proto.dccp.last_pkt = type;
ct->proto.dccp.state = new_state;
spin_unlock_bh(&ct->lock);
if (new_state != old_state)
nf_conntrack_event_cache(IPCT_PROTOINFO, ct);
nf_ct_refresh_acct(ct, ctinfo, skb, timeouts[new_state]);
return NF_ACCEPT;
}
static unsigned int
nf_nat_ipv4_fn(const struct nf_hook_ops *ops,
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_nat *nat;
/* maniptype == SRC for postrouting. */
enum nf_nat_manip_type maniptype = HOOK2MANIP(ops->hooknum);
/* We never see fragments: conntrack defrags on pre-routing
* and local-out, and nf_nat_out protects post-routing.
*/
NF_CT_ASSERT(!ip_is_fragment(ip_hdr(skb)));
ct = nf_ct_get(skb, &ctinfo);
/* Can't track? It's not due to stress, or conntrack would
* have dropped it. Hence it's the user's responsibilty to
* packet filter it out, or implement conntrack/NAT for that
* protocol. 8) --RR
*/
if (!ct)
return NF_ACCEPT;
/* Don't try to NAT if this packet is not conntracked */
if (nf_ct_is_untracked(ct))
return NF_ACCEPT;
nat = nfct_nat(ct);
if (!nat) {
/* NAT module was loaded late. */
if (nf_ct_is_confirmed(ct))
return NF_ACCEPT;
nat = nf_ct_ext_add(ct, NF_CT_EXT_NAT, GFP_ATOMIC);
if (nat == NULL) {
pr_debug("failed to add NAT extension\n");
return NF_ACCEPT;
}
}
switch (ctinfo) {
case IP_CT_RELATED:
case IP_CT_RELATED_REPLY:
if (ip_hdr(skb)->protocol == IPPROTO_ICMP) {
if (!nf_nat_icmp_reply_translation(skb, ct, ctinfo,
ops->hooknum))
return NF_DROP;
else
return NF_ACCEPT;
}
/* Fall thru... (Only ICMPs can be IP_CT_IS_REPLY) */
case IP_CT_NEW:
/* Seen it before? This can happen for loopback, retrans,
* or local packets.
*/
if (!nf_nat_initialized(ct, maniptype)) {
unsigned int ret;
ret = nf_nat_rule_find(skb, ops->hooknum, in, out, ct);
if (ret != NF_ACCEPT)
return ret;
} else {
pr_debug("Already setup manip %s for ct %p\n",
maniptype == NF_NAT_MANIP_SRC ? "SRC" : "DST",
ct);
if (nf_nat_oif_changed(ops->hooknum, ctinfo, nat, out))
goto oif_changed;
}
break;
default:
/* ESTABLISHED */
NF_CT_ASSERT(ctinfo == IP_CT_ESTABLISHED ||
ctinfo == IP_CT_ESTABLISHED_REPLY);
if (nf_nat_oif_changed(ops->hooknum, ctinfo, nat, out))
goto oif_changed;
}
return nf_nat_packet(ct, ctinfo, ops->hooknum, skb);
oif_changed:
nf_ct_kill_acct(ct, ctinfo, skb);
return NF_DROP;
}
/* Returns verdict for packet, or -1 for invalid. */
static int tcp_packet(struct nf_conn *ct,
const struct sk_buff *skb,
unsigned int dataoff,
enum ip_conntrack_info ctinfo,
u_int8_t pf,
unsigned int hooknum)
{
struct net *net = nf_ct_net(ct);
struct nf_conntrack_tuple *tuple;
#if defined(CONFIG_MV_ETH_NFP_CT_LEARN)
struct nf_conntrack_tuple *tupleInverseDir;
#endif
enum tcp_conntrack new_state, old_state;
enum ip_conntrack_dir dir;
const struct tcphdr *th;
struct tcphdr _tcph;
unsigned long timeout;
unsigned int index;
th = skb_header_pointer(skb, dataoff, sizeof(_tcph), &_tcph);
BUG_ON(th == NULL);
spin_lock_bh(&ct->lock);
old_state = ct->proto.tcp.state;
dir = CTINFO2DIR(ctinfo);
index = get_conntrack_index(th);
new_state = tcp_conntracks[dir][index][old_state];
tuple = &ct->tuplehash[dir].tuple;
#if defined(CONFIG_MV_ETH_NFP_CT_LEARN)
tupleInverseDir = &ct->tuplehash[!dir].tuple;
#endif
switch (new_state) {
case TCP_CONNTRACK_SYN_SENT:
if (old_state < TCP_CONNTRACK_TIME_WAIT)
break;
/* RFC 1122: "When a connection is closed actively,
* it MUST linger in TIME-WAIT state for a time 2xMSL
* (Maximum Segment Lifetime). However, it MAY accept
* a new SYN from the remote TCP to reopen the connection
* directly from TIME-WAIT state, if..."
* We ignore the conditions because we are in the
* TIME-WAIT state anyway.
*
* Handle aborted connections: we and the server
* think there is an existing connection but the client
* aborts it and starts a new one.
*/
if (((ct->proto.tcp.seen[dir].flags
| ct->proto.tcp.seen[!dir].flags)
& IP_CT_TCP_FLAG_CLOSE_INIT)
|| (ct->proto.tcp.last_dir == dir
&& ct->proto.tcp.last_index == TCP_RST_SET)) {
/* Attempt to reopen a closed/aborted connection.
* Delete this connection and look up again. */
spin_unlock_bh(&ct->lock);
/* Only repeat if we can actually remove the timer.
* Destruction may already be in progress in process
* context and we must give it a chance to terminate.
*/
if (nf_ct_kill(ct))
return -NF_REPEAT;
return NF_DROP;
}
/* Fall through */
case TCP_CONNTRACK_IGNORE:
/* Ignored packets:
*
* Our connection entry may be out of sync, so ignore
* packets which may signal the real connection between
* the client and the server.
*
* a) SYN in ORIGINAL
* b) SYN/ACK in REPLY
* c) ACK in reply direction after initial SYN in original.
*
* If the ignored packet is invalid, the receiver will send
* a RST we'll catch below.
*/
if (index == TCP_SYNACK_SET
&& ct->proto.tcp.last_index == TCP_SYN_SET
&& ct->proto.tcp.last_dir != dir
&& ntohl(th->ack_seq) == ct->proto.tcp.last_end) {
/* b) This SYN/ACK acknowledges a SYN that we earlier
* ignored as invalid. This means that the client and
* the server are both in sync, while the firewall is
* not. We kill this session and block the SYN/ACK so
* that the client cannot but retransmit its SYN and
* thus initiate a clean new session.
*/
spin_unlock_bh(&ct->lock);
if (LOG_INVALID(net, IPPROTO_TCP))
nf_log_packet(pf, 0, skb, NULL, NULL, NULL,
"nf_ct_tcp: killing out of sync session ");
nf_ct_kill(ct);
return NF_DROP;
}
ct->proto.tcp.last_index = index;
ct->proto.tcp.last_dir = dir;
ct->proto.tcp.last_seq = ntohl(th->seq);
ct->proto.tcp.last_end =
segment_seq_plus_len(ntohl(th->seq), skb->len, dataoff, th);
spin_unlock_bh(&ct->lock);
if (LOG_INVALID(net, IPPROTO_TCP))
nf_log_packet(pf, 0, skb, NULL, NULL, NULL,
"nf_ct_tcp: invalid packet ignored ");
return NF_ACCEPT;
case TCP_CONNTRACK_MAX:
/* Invalid packet */
pr_debug("nf_ct_tcp: Invalid dir=%i index=%u ostate=%u\n",
dir, get_conntrack_index(th), old_state);
spin_unlock_bh(&ct->lock);
if (LOG_INVALID(net, IPPROTO_TCP))
nf_log_packet(pf, 0, skb, NULL, NULL, NULL,
"nf_ct_tcp: invalid state ");
return -NF_ACCEPT;
case TCP_CONNTRACK_CLOSE:
if (index == TCP_RST_SET
&& (ct->proto.tcp.seen[!dir].flags & IP_CT_TCP_FLAG_MAXACK_SET)
&& before(ntohl(th->seq), ct->proto.tcp.seen[!dir].td_maxack)) {
/* Invalid RST */
spin_unlock_bh(&ct->lock);
if (LOG_INVALID(net, IPPROTO_TCP))
nf_log_packet(pf, 0, skb, NULL, NULL, NULL,
"nf_ct_tcp: invalid RST ");
return -NF_ACCEPT;
}
if (index == TCP_RST_SET
&& ((test_bit(IPS_SEEN_REPLY_BIT, &ct->status)
&& ct->proto.tcp.last_index == TCP_SYN_SET)
|| (!test_bit(IPS_ASSURED_BIT, &ct->status)
&& ct->proto.tcp.last_index == TCP_ACK_SET))
&& ntohl(th->ack_seq) == ct->proto.tcp.last_end) {
/* RST sent to invalid SYN or ACK we had let through
* at a) and c) above:
*
* a) SYN was in window then
* c) we hold a half-open connection.
*
* Delete our connection entry.
* We skip window checking, because packet might ACK
* segments we ignored. */
goto in_window;
}
/* Just fall through */
default:
/* Keep compilers happy. */
break;
}
#if defined(CONFIG_MV_ETH_NFP_CT_LEARN)
/*
* When connection is handled by NFP, we have to relax TCP tracking
* rules as not all packets goes through Linux conntrack.
*/
if ((tuple->nfp) || (tupleInverseDir->nfp))
goto in_window;
#endif /* CONFIG_MV_ETH_NFP_CT_LEARN */
if (!tcp_in_window(ct, &ct->proto.tcp, dir, index,
skb, dataoff, th, pf)) {
spin_unlock_bh(&ct->lock);
return -NF_ACCEPT;
}
in_window:
/* From now on we have got in-window packets */
ct->proto.tcp.last_index = index;
ct->proto.tcp.last_dir = dir;
pr_debug("tcp_conntracks: ");
nf_ct_dump_tuple(tuple);
pr_debug("syn=%i ack=%i fin=%i rst=%i old=%i new=%i\n",
(th->syn ? 1 : 0), (th->ack ? 1 : 0),
(th->fin ? 1 : 0), (th->rst ? 1 : 0),
old_state, new_state);
ct->proto.tcp.state = new_state;
if (old_state != new_state
&& new_state == TCP_CONNTRACK_FIN_WAIT)
ct->proto.tcp.seen[dir].flags |= IP_CT_TCP_FLAG_CLOSE_INIT;
if (ct->proto.tcp.retrans >= nf_ct_tcp_max_retrans &&
tcp_timeouts[new_state] > nf_ct_tcp_timeout_max_retrans)
timeout = nf_ct_tcp_timeout_max_retrans;
else if ((ct->proto.tcp.seen[0].flags | ct->proto.tcp.seen[1].flags) &
IP_CT_TCP_FLAG_DATA_UNACKNOWLEDGED &&
tcp_timeouts[new_state] > nf_ct_tcp_timeout_unacknowledged)
timeout = nf_ct_tcp_timeout_unacknowledged;
else
timeout = tcp_timeouts[new_state];
spin_unlock_bh(&ct->lock);
if (new_state != old_state)
nf_conntrack_event_cache(IPCT_PROTOINFO, ct);
if (!test_bit(IPS_SEEN_REPLY_BIT, &ct->status)) {
/* If only reply is a RST, we can consider ourselves not to
have an established connection: this is a fairly common
problem case, so we can delete the conntrack
immediately. --RR */
if (th->rst) {
nf_ct_kill_acct(ct, ctinfo, skb);
return NF_ACCEPT;
}
} else if (!test_bit(IPS_ASSURED_BIT, &ct->status)
&& (old_state == TCP_CONNTRACK_SYN_RECV
|| old_state == TCP_CONNTRACK_ESTABLISHED)
&& new_state == TCP_CONNTRACK_ESTABLISHED) {
/* Set ASSURED if we see see valid ack in ESTABLISHED
after SYN_RECV or a valid answer for a picked up
connection. */
set_bit(IPS_ASSURED_BIT, &ct->status);
nf_conntrack_event_cache(IPCT_STATUS, ct);
}
nf_ct_refresh_acct(ct, ctinfo, skb, timeout);
return NF_ACCEPT;
}
static int tcp_packet(struct nf_conn *ct,
const struct sk_buff *skb,
unsigned int dataoff,
enum ip_conntrack_info ctinfo,
u_int8_t pf,
unsigned int hooknum,
unsigned int *timeouts)
{
struct net *net = nf_ct_net(ct);
struct nf_conntrack_tuple *tuple;
enum tcp_conntrack new_state, old_state;
enum ip_conntrack_dir dir;
const struct tcphdr *th;
struct tcphdr _tcph;
unsigned long timeout;
unsigned int index;
th = skb_header_pointer(skb, dataoff, sizeof(_tcph), &_tcph);
BUG_ON(th == NULL);
spin_lock_bh(&ct->lock);
old_state = ct->proto.tcp.state;
dir = CTINFO2DIR(ctinfo);
index = get_conntrack_index(th);
new_state = tcp_conntracks[dir][index][old_state];
tuple = &ct->tuplehash[dir].tuple;
switch (new_state) {
case TCP_CONNTRACK_SYN_SENT:
if (old_state < TCP_CONNTRACK_TIME_WAIT)
break;
if (((ct->proto.tcp.seen[dir].flags
| ct->proto.tcp.seen[!dir].flags)
& IP_CT_TCP_FLAG_CLOSE_INIT)
|| (ct->proto.tcp.last_dir == dir
&& ct->proto.tcp.last_index == TCP_RST_SET)) {
spin_unlock_bh(&ct->lock);
if (nf_ct_kill(ct))
return -NF_REPEAT;
return NF_DROP;
}
case TCP_CONNTRACK_IGNORE:
if (index == TCP_SYNACK_SET
&& ct->proto.tcp.last_index == TCP_SYN_SET
&& ct->proto.tcp.last_dir != dir
&& ntohl(th->ack_seq) == ct->proto.tcp.last_end) {
old_state = TCP_CONNTRACK_SYN_SENT;
new_state = TCP_CONNTRACK_SYN_RECV;
ct->proto.tcp.seen[ct->proto.tcp.last_dir].td_end =
ct->proto.tcp.last_end;
ct->proto.tcp.seen[ct->proto.tcp.last_dir].td_maxend =
ct->proto.tcp.last_end;
ct->proto.tcp.seen[ct->proto.tcp.last_dir].td_maxwin =
ct->proto.tcp.last_win == 0 ?
1 : ct->proto.tcp.last_win;
ct->proto.tcp.seen[ct->proto.tcp.last_dir].td_scale =
ct->proto.tcp.last_wscale;
ct->proto.tcp.seen[ct->proto.tcp.last_dir].flags =
ct->proto.tcp.last_flags;
memset(&ct->proto.tcp.seen[dir], 0,
sizeof(struct ip_ct_tcp_state));
break;
}
ct->proto.tcp.last_index = index;
ct->proto.tcp.last_dir = dir;
ct->proto.tcp.last_seq = ntohl(th->seq);
ct->proto.tcp.last_end =
segment_seq_plus_len(ntohl(th->seq), skb->len, dataoff, th);
ct->proto.tcp.last_win = ntohs(th->window);
if (index == TCP_SYN_SET && dir == IP_CT_DIR_ORIGINAL) {
struct ip_ct_tcp_state seen = {};
ct->proto.tcp.last_flags =
ct->proto.tcp.last_wscale = 0;
tcp_options(skb, dataoff, th, &seen);
if (seen.flags & IP_CT_TCP_FLAG_WINDOW_SCALE) {
ct->proto.tcp.last_flags |=
IP_CT_TCP_FLAG_WINDOW_SCALE;
ct->proto.tcp.last_wscale = seen.td_scale;
}
if (seen.flags & IP_CT_TCP_FLAG_SACK_PERM) {
ct->proto.tcp.last_flags |=
IP_CT_TCP_FLAG_SACK_PERM;
}
}
spin_unlock_bh(&ct->lock);
if (LOG_INVALID(net, IPPROTO_TCP))
nf_log_packet(pf, 0, skb, NULL, NULL, NULL,
"nf_ct_tcp: invalid packet ignored ");
return NF_ACCEPT;
case TCP_CONNTRACK_MAX:
pr_debug("nf_ct_tcp: Invalid dir=%i index=%u ostate=%u\n",
dir, get_conntrack_index(th), old_state);
spin_unlock_bh(&ct->lock);
if (LOG_INVALID(net, IPPROTO_TCP))
nf_log_packet(pf, 0, skb, NULL, NULL, NULL,
"nf_ct_tcp: invalid state ");
return -NF_ACCEPT;
case TCP_CONNTRACK_CLOSE:
if (index == TCP_RST_SET
&& (ct->proto.tcp.seen[!dir].flags & IP_CT_TCP_FLAG_MAXACK_SET)
&& before(ntohl(th->seq), ct->proto.tcp.seen[!dir].td_maxack)) {
spin_unlock_bh(&ct->lock);
if (LOG_INVALID(net, IPPROTO_TCP))
nf_log_packet(pf, 0, skb, NULL, NULL, NULL,
"nf_ct_tcp: invalid RST ");
return -NF_ACCEPT;
}
if (index == TCP_RST_SET
&& ((test_bit(IPS_SEEN_REPLY_BIT, &ct->status)
&& ct->proto.tcp.last_index == TCP_SYN_SET)
|| (!test_bit(IPS_ASSURED_BIT, &ct->status)
&& ct->proto.tcp.last_index == TCP_ACK_SET))
&& ntohl(th->ack_seq) == ct->proto.tcp.last_end) {
goto in_window;
}
default:
break;
}
if (!tcp_in_window(ct, &ct->proto.tcp, dir, index,
skb, dataoff, th, pf)) {
spin_unlock_bh(&ct->lock);
return -NF_ACCEPT;
}
in_window:
ct->proto.tcp.last_index = index;
ct->proto.tcp.last_dir = dir;
pr_debug("tcp_conntracks: ");
nf_ct_dump_tuple(tuple);
pr_debug("syn=%i ack=%i fin=%i rst=%i old=%i new=%i\n",
(th->syn ? 1 : 0), (th->ack ? 1 : 0),
(th->fin ? 1 : 0), (th->rst ? 1 : 0),
old_state, new_state);
ct->proto.tcp.state = new_state;
if (old_state != new_state
&& new_state == TCP_CONNTRACK_FIN_WAIT)
ct->proto.tcp.seen[dir].flags |= IP_CT_TCP_FLAG_CLOSE_INIT;
if (ct->proto.tcp.retrans >= nf_ct_tcp_max_retrans &&
timeouts[new_state] > timeouts[TCP_CONNTRACK_RETRANS])
timeout = timeouts[TCP_CONNTRACK_RETRANS];
else if ((ct->proto.tcp.seen[0].flags | ct->proto.tcp.seen[1].flags) &
IP_CT_TCP_FLAG_DATA_UNACKNOWLEDGED &&
timeouts[new_state] > timeouts[TCP_CONNTRACK_UNACK])
timeout = timeouts[TCP_CONNTRACK_UNACK];
else
timeout = timeouts[new_state];
spin_unlock_bh(&ct->lock);
if (new_state != old_state)
nf_conntrack_event_cache(IPCT_PROTOINFO, ct);
if (!test_bit(IPS_SEEN_REPLY_BIT, &ct->status)) {
if (th->rst) {
nf_ct_kill_acct(ct, ctinfo, skb);
return NF_ACCEPT;
}
} else if (!test_bit(IPS_ASSURED_BIT, &ct->status)
&& (old_state == TCP_CONNTRACK_SYN_RECV
|| old_state == TCP_CONNTRACK_ESTABLISHED)
&& new_state == TCP_CONNTRACK_ESTABLISHED) {
set_bit(IPS_ASSURED_BIT, &ct->status);
nf_conntrack_event_cache(IPCT_ASSURED, ct);
}
nf_ct_refresh_acct(ct, ctinfo, skb, timeout);
return NF_ACCEPT;
}
static unsigned int
nf_nat_ipv6_fn(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_nat *nat;
enum nf_nat_manip_type maniptype = HOOK2MANIP(hooknum);
__be16 frag_off;
int hdrlen;
u8 nexthdr;
ct = nf_ct_get(skb, &ctinfo);
/* Can't track? It's not due to stress, or conntrack would
* have dropped it. Hence it's the user's responsibilty to
* packet filter it out, or implement conntrack/NAT for that
* protocol. 8) --RR
*/
if (!ct)
return NF_ACCEPT;
/* Don't try to NAT if this packet is not conntracked */
if (nf_ct_is_untracked(ct))
return NF_ACCEPT;
nat = nfct_nat(ct);
if (!nat) {
/* NAT module was loaded late. */
if (nf_ct_is_confirmed(ct))
return NF_ACCEPT;
nat = nf_ct_ext_add(ct, NF_CT_EXT_NAT, GFP_ATOMIC);
if (nat == NULL) {
pr_debug("failed to add NAT extension\n");
return NF_ACCEPT;
}
}
switch (ctinfo) {
case IP_CT_RELATED:
case IP_CT_RELATED_REPLY:
nexthdr = ipv6_hdr(skb)->nexthdr;
hdrlen = ipv6_skip_exthdr(skb, sizeof(struct ipv6hdr),
&nexthdr, &frag_off);
if (hdrlen >= 0 && nexthdr == IPPROTO_ICMPV6) {
if (!nf_nat_icmpv6_reply_translation(skb, ct, ctinfo,
hooknum, hdrlen))
return NF_DROP;
else
return NF_ACCEPT;
}
/* Fall thru... (Only ICMPs can be IP_CT_IS_REPLY) */
case IP_CT_NEW:
/* Seen it before? This can happen for loopback, retrans,
* or local packets.
*/
if (!nf_nat_initialized(ct, maniptype)) {
unsigned int ret;
ret = nf_nat_rule_find(skb, hooknum, in, out, ct);
if (ret != NF_ACCEPT)
return ret;
} else {
pr_debug("Already setup manip %s for ct %p\n",
maniptype == NF_NAT_MANIP_SRC ? "SRC" : "DST",
ct);
if (nf_nat_oif_changed(hooknum, ctinfo, nat, out))
goto oif_changed;
}
break;
default:
/* ESTABLISHED */
NF_CT_ASSERT(ctinfo == IP_CT_ESTABLISHED ||
ctinfo == IP_CT_ESTABLISHED_REPLY);
if (nf_nat_oif_changed(hooknum, ctinfo, nat, out))
goto oif_changed;
}
return nf_nat_packet(ct, ctinfo, hooknum, skb);
oif_changed:
nf_ct_kill_acct(ct, ctinfo, skb);
return NF_DROP;
}
/* Returns verdict for packet, or -1 for invalid. */
static int tcp_packet(struct nf_conn *ct,
struct sk_buff *skb,
unsigned int dataoff,
enum ip_conntrack_info ctinfo,
const struct nf_hook_state *state)
{
struct net *net = nf_ct_net(ct);
struct nf_tcp_net *tn = nf_tcp_pernet(net);
struct nf_conntrack_tuple *tuple;
enum tcp_conntrack new_state, old_state;
unsigned int index, *timeouts;
enum ip_conntrack_dir dir;
const struct tcphdr *th;
struct tcphdr _tcph;
unsigned long timeout;
th = skb_header_pointer(skb, dataoff, sizeof(_tcph), &_tcph);
if (th == NULL)
return -NF_ACCEPT;
if (tcp_error(th, skb, dataoff, state))
return -NF_ACCEPT;
if (!nf_ct_is_confirmed(ct) && !tcp_new(ct, skb, dataoff, th))
return -NF_ACCEPT;
spin_lock_bh(&ct->lock);
old_state = ct->proto.tcp.state;
dir = CTINFO2DIR(ctinfo);
index = get_conntrack_index(th);
new_state = tcp_conntracks[dir][index][old_state];
tuple = &ct->tuplehash[dir].tuple;
switch (new_state) {
case TCP_CONNTRACK_SYN_SENT:
if (old_state < TCP_CONNTRACK_TIME_WAIT)
break;
/* RFC 1122: "When a connection is closed actively,
* it MUST linger in TIME-WAIT state for a time 2xMSL
* (Maximum Segment Lifetime). However, it MAY accept
* a new SYN from the remote TCP to reopen the connection
* directly from TIME-WAIT state, if..."
* We ignore the conditions because we are in the
* TIME-WAIT state anyway.
*
* Handle aborted connections: we and the server
* think there is an existing connection but the client
* aborts it and starts a new one.
*/
if (((ct->proto.tcp.seen[dir].flags
| ct->proto.tcp.seen[!dir].flags)
& IP_CT_TCP_FLAG_CLOSE_INIT)
|| (ct->proto.tcp.last_dir == dir
&& ct->proto.tcp.last_index == TCP_RST_SET)) {
/* Attempt to reopen a closed/aborted connection.
* Delete this connection and look up again. */
spin_unlock_bh(&ct->lock);
/* Only repeat if we can actually remove the timer.
* Destruction may already be in progress in process
* context and we must give it a chance to terminate.
*/
if (nf_ct_kill(ct))
return -NF_REPEAT;
return NF_DROP;
}
/* Fall through */
case TCP_CONNTRACK_IGNORE:
/* Ignored packets:
*
* Our connection entry may be out of sync, so ignore
* packets which may signal the real connection between
* the client and the server.
*
* a) SYN in ORIGINAL
* b) SYN/ACK in REPLY
* c) ACK in reply direction after initial SYN in original.
*
* If the ignored packet is invalid, the receiver will send
* a RST we'll catch below.
*/
if (index == TCP_SYNACK_SET
&& ct->proto.tcp.last_index == TCP_SYN_SET
&& ct->proto.tcp.last_dir != dir
&& ntohl(th->ack_seq) == ct->proto.tcp.last_end) {
/* b) This SYN/ACK acknowledges a SYN that we earlier
* ignored as invalid. This means that the client and
* the server are both in sync, while the firewall is
* not. We get in sync from the previously annotated
* values.
*/
old_state = TCP_CONNTRACK_SYN_SENT;
new_state = TCP_CONNTRACK_SYN_RECV;
ct->proto.tcp.seen[ct->proto.tcp.last_dir].td_end =
ct->proto.tcp.last_end;
ct->proto.tcp.seen[ct->proto.tcp.last_dir].td_maxend =
ct->proto.tcp.last_end;
ct->proto.tcp.seen[ct->proto.tcp.last_dir].td_maxwin =
ct->proto.tcp.last_win == 0 ?
1 : ct->proto.tcp.last_win;
ct->proto.tcp.seen[ct->proto.tcp.last_dir].td_scale =
ct->proto.tcp.last_wscale;
ct->proto.tcp.last_flags &= ~IP_CT_EXP_CHALLENGE_ACK;
ct->proto.tcp.seen[ct->proto.tcp.last_dir].flags =
ct->proto.tcp.last_flags;
memset(&ct->proto.tcp.seen[dir], 0,
sizeof(struct ip_ct_tcp_state));
break;
}
ct->proto.tcp.last_index = index;
ct->proto.tcp.last_dir = dir;
ct->proto.tcp.last_seq = ntohl(th->seq);
ct->proto.tcp.last_end =
segment_seq_plus_len(ntohl(th->seq), skb->len, dataoff, th);
ct->proto.tcp.last_win = ntohs(th->window);
/* a) This is a SYN in ORIGINAL. The client and the server
* may be in sync but we are not. In that case, we annotate
* the TCP options and let the packet go through. If it is a
* valid SYN packet, the server will reply with a SYN/ACK, and
* then we'll get in sync. Otherwise, the server potentially
* responds with a challenge ACK if implementing RFC5961.
*/
if (index == TCP_SYN_SET && dir == IP_CT_DIR_ORIGINAL) {
struct ip_ct_tcp_state seen = {};
ct->proto.tcp.last_flags =
ct->proto.tcp.last_wscale = 0;
tcp_options(skb, dataoff, th, &seen);
if (seen.flags & IP_CT_TCP_FLAG_WINDOW_SCALE) {
ct->proto.tcp.last_flags |=
IP_CT_TCP_FLAG_WINDOW_SCALE;
ct->proto.tcp.last_wscale = seen.td_scale;
}
if (seen.flags & IP_CT_TCP_FLAG_SACK_PERM) {
ct->proto.tcp.last_flags |=
IP_CT_TCP_FLAG_SACK_PERM;
}
/* Mark the potential for RFC5961 challenge ACK,
* this pose a special problem for LAST_ACK state
* as ACK is intrepretated as ACKing last FIN.
*/
if (old_state == TCP_CONNTRACK_LAST_ACK)
ct->proto.tcp.last_flags |=
IP_CT_EXP_CHALLENGE_ACK;
}
spin_unlock_bh(&ct->lock);
nf_ct_l4proto_log_invalid(skb, ct, "invalid packet ignored in "
"state %s ", tcp_conntrack_names[old_state]);
return NF_ACCEPT;
case TCP_CONNTRACK_MAX:
/* Special case for SYN proxy: when the SYN to the server or
* the SYN/ACK from the server is lost, the client may transmit
* a keep-alive packet while in SYN_SENT state. This needs to
* be associated with the original conntrack entry in order to
* generate a new SYN with the correct sequence number.
*/
if (nfct_synproxy(ct) && old_state == TCP_CONNTRACK_SYN_SENT &&
index == TCP_ACK_SET && dir == IP_CT_DIR_ORIGINAL &&
ct->proto.tcp.last_dir == IP_CT_DIR_ORIGINAL &&
ct->proto.tcp.seen[dir].td_end - 1 == ntohl(th->seq)) {
pr_debug("nf_ct_tcp: SYN proxy client keep alive\n");
spin_unlock_bh(&ct->lock);
return NF_ACCEPT;
}
/* Invalid packet */
pr_debug("nf_ct_tcp: Invalid dir=%i index=%u ostate=%u\n",
dir, get_conntrack_index(th), old_state);
spin_unlock_bh(&ct->lock);
nf_ct_l4proto_log_invalid(skb, ct, "invalid state");
return -NF_ACCEPT;
case TCP_CONNTRACK_TIME_WAIT:
/* RFC5961 compliance cause stack to send "challenge-ACK"
* e.g. in response to spurious SYNs. Conntrack MUST
* not believe this ACK is acking last FIN.
*/
if (old_state == TCP_CONNTRACK_LAST_ACK &&
index == TCP_ACK_SET &&
ct->proto.tcp.last_dir != dir &&
ct->proto.tcp.last_index == TCP_SYN_SET &&
(ct->proto.tcp.last_flags & IP_CT_EXP_CHALLENGE_ACK)) {
/* Detected RFC5961 challenge ACK */
ct->proto.tcp.last_flags &= ~IP_CT_EXP_CHALLENGE_ACK;
spin_unlock_bh(&ct->lock);
nf_ct_l4proto_log_invalid(skb, ct, "challenge-ack ignored");
return NF_ACCEPT; /* Don't change state */
}
break;
case TCP_CONNTRACK_SYN_SENT2:
/* tcp_conntracks table is not smart enough to handle
* simultaneous open.
*/
ct->proto.tcp.last_flags |= IP_CT_TCP_SIMULTANEOUS_OPEN;
break;
case TCP_CONNTRACK_SYN_RECV:
if (dir == IP_CT_DIR_REPLY && index == TCP_ACK_SET &&
ct->proto.tcp.last_flags & IP_CT_TCP_SIMULTANEOUS_OPEN)
new_state = TCP_CONNTRACK_ESTABLISHED;
break;
case TCP_CONNTRACK_CLOSE:
if (index == TCP_RST_SET
&& (ct->proto.tcp.seen[!dir].flags & IP_CT_TCP_FLAG_MAXACK_SET)
&& before(ntohl(th->seq), ct->proto.tcp.seen[!dir].td_maxack)) {
/* Invalid RST */
spin_unlock_bh(&ct->lock);
nf_ct_l4proto_log_invalid(skb, ct, "invalid rst");
return -NF_ACCEPT;
}
if (index == TCP_RST_SET
&& ((test_bit(IPS_SEEN_REPLY_BIT, &ct->status)
&& ct->proto.tcp.last_index == TCP_SYN_SET)
|| (!test_bit(IPS_ASSURED_BIT, &ct->status)
&& ct->proto.tcp.last_index == TCP_ACK_SET))
&& ntohl(th->ack_seq) == ct->proto.tcp.last_end) {
/* RST sent to invalid SYN or ACK we had let through
* at a) and c) above:
*
* a) SYN was in window then
* c) we hold a half-open connection.
*
* Delete our connection entry.
* We skip window checking, because packet might ACK
* segments we ignored. */
goto in_window;
}
/* Just fall through */
default:
/* Keep compilers happy. */
break;
}
if (!tcp_in_window(ct, &ct->proto.tcp, dir, index,
skb, dataoff, th)) {
spin_unlock_bh(&ct->lock);
return -NF_ACCEPT;
}
in_window:
/* From now on we have got in-window packets */
ct->proto.tcp.last_index = index;
ct->proto.tcp.last_dir = dir;
pr_debug("tcp_conntracks: ");
nf_ct_dump_tuple(tuple);
pr_debug("syn=%i ack=%i fin=%i rst=%i old=%i new=%i\n",
(th->syn ? 1 : 0), (th->ack ? 1 : 0),
(th->fin ? 1 : 0), (th->rst ? 1 : 0),
old_state, new_state);
ct->proto.tcp.state = new_state;
if (old_state != new_state
&& new_state == TCP_CONNTRACK_FIN_WAIT)
ct->proto.tcp.seen[dir].flags |= IP_CT_TCP_FLAG_CLOSE_INIT;
timeouts = nf_ct_timeout_lookup(ct);
if (!timeouts)
timeouts = tn->timeouts;
if (ct->proto.tcp.retrans >= tn->tcp_max_retrans &&
timeouts[new_state] > timeouts[TCP_CONNTRACK_RETRANS])
timeout = timeouts[TCP_CONNTRACK_RETRANS];
else if ((ct->proto.tcp.seen[0].flags | ct->proto.tcp.seen[1].flags) &
IP_CT_TCP_FLAG_DATA_UNACKNOWLEDGED &&
timeouts[new_state] > timeouts[TCP_CONNTRACK_UNACK])
timeout = timeouts[TCP_CONNTRACK_UNACK];
else if (ct->proto.tcp.last_win == 0 &&
timeouts[new_state] > timeouts[TCP_CONNTRACK_RETRANS])
timeout = timeouts[TCP_CONNTRACK_RETRANS];
else
timeout = timeouts[new_state];
spin_unlock_bh(&ct->lock);
if (new_state != old_state)
nf_conntrack_event_cache(IPCT_PROTOINFO, ct);
if (!test_bit(IPS_SEEN_REPLY_BIT, &ct->status)) {
/* If only reply is a RST, we can consider ourselves not to
have an established connection: this is a fairly common
problem case, so we can delete the conntrack
immediately. --RR */
if (th->rst) {
nf_ct_kill_acct(ct, ctinfo, skb);
return NF_ACCEPT;
}
/* ESTABLISHED without SEEN_REPLY, i.e. mid-connection
* pickup with loose=1. Avoid large ESTABLISHED timeout.
*/
if (new_state == TCP_CONNTRACK_ESTABLISHED &&
timeout > timeouts[TCP_CONNTRACK_UNACK])
timeout = timeouts[TCP_CONNTRACK_UNACK];
} else if (!test_bit(IPS_ASSURED_BIT, &ct->status)
&& (old_state == TCP_CONNTRACK_SYN_RECV
|| old_state == TCP_CONNTRACK_ESTABLISHED)
&& new_state == TCP_CONNTRACK_ESTABLISHED) {
/* Set ASSURED if we see see valid ack in ESTABLISHED
after SYN_RECV or a valid answer for a picked up
connection. */
set_bit(IPS_ASSURED_BIT, &ct->status);
nf_conntrack_event_cache(IPCT_ASSURED, ct);
}
nf_ct_refresh_acct(ct, ctinfo, skb, timeout);
return NF_ACCEPT;
}
unsigned int
nf_nat_ipv4_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))
{
struct nf_conn *ct;
enum ip_conntrack_info ctinfo;
struct nf_conn_nat *nat;
/* maniptype == SRC for postrouting. */
enum nf_nat_manip_type maniptype = HOOK2MANIP(state->hook);
ct = nf_ct_get(skb, &ctinfo);
/* Can't track? It's not due to stress, or conntrack would
* have dropped it. Hence it's the user's responsibilty to
* packet filter it out, or implement conntrack/NAT for that
* protocol. 8) --RR
*/
if (!ct)
return NF_ACCEPT;
nat = nfct_nat(ct);
switch (ctinfo) {
case IP_CT_RELATED:
case IP_CT_RELATED_REPLY:
if (ip_hdr(skb)->protocol == IPPROTO_ICMP) {
if (!nf_nat_icmp_reply_translation(skb, ct, ctinfo,
state->hook))
return NF_DROP;
else
return NF_ACCEPT;
}
/* Only ICMPs can be IP_CT_IS_REPLY: */
/* fall through */
case IP_CT_NEW:
/* Seen it before? This can happen for loopback, retrans,
* or local packets.
*/
if (!nf_nat_initialized(ct, maniptype)) {
unsigned int ret;
ret = do_chain(priv, skb, state, ct);
if (ret != NF_ACCEPT)
return ret;
if (nf_nat_initialized(ct, HOOK2MANIP(state->hook)))
break;
ret = nf_nat_alloc_null_binding(ct, state->hook);
if (ret != NF_ACCEPT)
return ret;
} else {
pr_debug("Already setup manip %s for ct %p\n",
maniptype == NF_NAT_MANIP_SRC ? "SRC" : "DST",
ct);
if (nf_nat_oif_changed(state->hook, ctinfo, nat,
state->out))
goto oif_changed;
}
break;
default:
/* ESTABLISHED */
WARN_ON(ctinfo != IP_CT_ESTABLISHED &&
ctinfo != IP_CT_ESTABLISHED_REPLY);
if (nf_nat_oif_changed(state->hook, ctinfo, nat, state->out))
goto oif_changed;
}
return nf_nat_packet(ct, ctinfo, state->hook, skb);
oif_changed:
nf_ct_kill_acct(ct, ctinfo, skb);
return NF_DROP;
}
static int dccp_packet(struct nf_conn *ct, const struct sk_buff *skb,
unsigned int dataoff, enum ip_conntrack_info ctinfo,
u_int8_t pf, unsigned int hooknum)
{
struct net *net = nf_ct_net(ct);
struct dccp_net *dn;
enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo);
struct dccp_hdr _dh, *dh;
u_int8_t type, old_state, new_state;
enum ct_dccp_roles role;
dh = skb_header_pointer(skb, dataoff, sizeof(_dh), &dh);
BUG_ON(dh == NULL);
type = dh->dccph_type;
if (type == DCCP_PKT_RESET &&
!test_bit(IPS_SEEN_REPLY_BIT, &ct->status)) {
nf_ct_kill_acct(ct, ctinfo, skb);
return NF_ACCEPT;
}
spin_lock_bh(&ct->lock);
role = ct->proto.dccp.role[dir];
old_state = ct->proto.dccp.state;
new_state = dccp_state_table[role][type][old_state];
switch (new_state) {
case CT_DCCP_REQUEST:
if (old_state == CT_DCCP_TIMEWAIT &&
role == CT_DCCP_ROLE_SERVER) {
ct->proto.dccp.role[dir] = CT_DCCP_ROLE_CLIENT;
ct->proto.dccp.role[!dir] = CT_DCCP_ROLE_SERVER;
}
break;
case CT_DCCP_RESPOND:
if (old_state == CT_DCCP_REQUEST)
ct->proto.dccp.handshake_seq = dccp_hdr_seq(dh);
break;
case CT_DCCP_PARTOPEN:
if (old_state == CT_DCCP_RESPOND &&
type == DCCP_PKT_ACK &&
dccp_ack_seq(dh) == ct->proto.dccp.handshake_seq)
set_bit(IPS_ASSURED_BIT, &ct->status);
break;
case CT_DCCP_IGNORE:
if (ct->proto.dccp.last_dir == !dir &&
ct->proto.dccp.last_pkt == DCCP_PKT_REQUEST &&
type == DCCP_PKT_RESPONSE) {
ct->proto.dccp.role[!dir] = CT_DCCP_ROLE_CLIENT;
ct->proto.dccp.role[dir] = CT_DCCP_ROLE_SERVER;
ct->proto.dccp.handshake_seq = dccp_hdr_seq(dh);
new_state = CT_DCCP_RESPOND;
break;
}
ct->proto.dccp.last_dir = dir;
ct->proto.dccp.last_pkt = type;
spin_unlock_bh(&ct->lock);
if (LOG_INVALID(net, IPPROTO_DCCP))
nf_log_packet(pf, 0, skb, NULL, NULL, NULL,
"nf_ct_dccp: invalid packet ignored ");
return NF_ACCEPT;
case CT_DCCP_INVALID:
spin_unlock_bh(&ct->lock);
if (LOG_INVALID(net, IPPROTO_DCCP))
nf_log_packet(pf, 0, skb, NULL, NULL, NULL,
"nf_ct_dccp: invalid state transition ");
return -NF_ACCEPT;
}
ct->proto.dccp.last_dir = dir;
ct->proto.dccp.last_pkt = type;
ct->proto.dccp.state = new_state;
spin_unlock_bh(&ct->lock);
if (new_state != old_state)
nf_conntrack_event_cache(IPCT_PROTOINFO, ct);
dn = dccp_pernet(net);
nf_ct_refresh_acct(ct, ctinfo, skb, dn->dccp_timeout[new_state]);
return NF_ACCEPT;
}
