static bool
socket_mt6_v1_v2(const struct sk_buff *skb, struct xt_action_param *par)
{
const struct xt_socket_mtinfo1 *info = (struct xt_socket_mtinfo1 *) par->matchinfo;
struct sock *sk = skb->sk;
if (!sk)
sk = xt_socket_lookup_slow_v6(skb, par->in);
if (sk) {
bool wildcard;
bool transparent = true;
/* Ignore sockets listening on INADDR_ANY
* unless XT_SOCKET_NOWILDCARD is set
*/
wildcard = (!(info->flags & XT_SOCKET_NOWILDCARD) &&
sk_fullsock(sk) &&
ipv6_addr_any(&sk->sk_v6_rcv_saddr));
/* Ignore non-transparent sockets,
* if XT_SOCKET_TRANSPARENT is used
*/
if (info->flags & XT_SOCKET_TRANSPARENT)
transparent = xt_socket_sk_is_transparent(sk);
if (sk != skb->sk)
sock_gen_put(sk);
if (wildcard || !transparent)
sk = NULL;
}
return sk != NULL;
}
static int tcp_diag_destroy(struct sk_buff *in_skb,
const struct inet_diag_req_v2 *req)
{
struct net *net = sock_net(in_skb->sk);
struct sock *sk = inet_diag_find_one_icsk(net, &tcp_hashinfo, req);
int err;
if (IS_ERR(sk))
return PTR_ERR(sk);
err = sock_diag_destroy(sk, ECONNABORTED);
sock_gen_put(sk);
return err;
}
/* "socket" match based redirection (no specific rule)
* ===================================================
*
* There are connections with dynamic endpoints (e.g. FTP data
* connection) that the user is unable to add explicit rules
* for. These are taken care of by a generic "socket" rule. It is
* assumed that the proxy application is trusted to open such
* connections without explicit iptables rule (except of course the
* generic 'socket' rule). In this case the following sockets are
* matched in preference order:
*
* - match: if there's a fully established connection matching the
* _packet_ tuple
*
* - match: if there's a non-zero bound listener (possibly with a
* non-local address) We don't accept zero-bound listeners, since
* then local services could intercept traffic going through the
* box.
*/
static bool
socket_match(const struct sk_buff *skb, struct xt_action_param *par,
const struct xt_socket_mtinfo1 *info)
{
struct sk_buff *pskb = (struct sk_buff *)skb;
struct sock *sk = skb->sk;
if (sk && !net_eq(xt_net(par), sock_net(sk)))
sk = NULL;
if (!sk)
sk = nf_sk_lookup_slow_v4(xt_net(par), skb, xt_in(par));
if (sk) {
bool wildcard;
bool transparent = true;
/* Ignore sockets listening on INADDR_ANY,
* unless XT_SOCKET_NOWILDCARD is set
*/
wildcard = (!(info->flags & XT_SOCKET_NOWILDCARD) &&
sk_fullsock(sk) &&
inet_sk(sk)->inet_rcv_saddr == 0);
/* Ignore non-transparent sockets,
* if XT_SOCKET_TRANSPARENT is used
*/
if (info->flags & XT_SOCKET_TRANSPARENT)
transparent = inet_sk_transparent(sk);
if (info->flags & XT_SOCKET_RESTORESKMARK && !wildcard &&
transparent && sk_fullsock(sk))
pskb->mark = sk->sk_mark;
if (sk != skb->sk)
sock_gen_put(sk);
if (wildcard || !transparent)
sk = NULL;
}
return sk != NULL;
}
static bool
socket_match(const struct sk_buff *skb, struct xt_action_param *par,
const struct xt_socket_mtinfo1 *info)
{
struct sock *sk;
sk = xt_socket_get4_sk(skb, par);
if (sk) {
bool wildcard;
bool transparent = true;
/* Ignore sockets listening on INADDR_ANY,
* unless XT_SOCKET_NOWILDCARD is set
*/
wildcard = (!(info->flags & XT_SOCKET_NOWILDCARD) &&
sk->sk_state != TCP_TIME_WAIT &&
inet_sk(sk)->inet_rcv_saddr == 0);
/* Ignore non-transparent sockets,
if XT_SOCKET_TRANSPARENT is used */
if (info->flags & XT_SOCKET_TRANSPARENT)
transparent = ((sk->sk_state != TCP_TIME_WAIT &&
inet_sk(sk)->transparent) ||
(sk->sk_state == TCP_TIME_WAIT &&
inet_twsk(sk)->tw_transparent));
if (sk != skb->sk)
sock_gen_put(sk);
if (wildcard || !transparent)
sk = NULL;
}
return (sk != NULL);
}
int inet_sk_diag_fill(struct sock *sk, struct inet_connection_sock *icsk,
struct sk_buff *skb, const struct inet_diag_req_v2 *req,
struct user_namespace *user_ns,
u32 portid, u32 seq, u16 nlmsg_flags,
const struct nlmsghdr *unlh)
{
const struct inet_sock *inet = inet_sk(sk);
const struct tcp_congestion_ops *ca_ops;
const struct inet_diag_handler *handler;
int ext = req->idiag_ext;
struct inet_diag_msg *r;
struct nlmsghdr *nlh;
struct nlattr *attr;
void *info = NULL;
handler = inet_diag_table[req->sdiag_protocol];
BUG_ON(!handler);
nlh = nlmsg_put(skb, portid, seq, unlh->nlmsg_type, sizeof(*r),
nlmsg_flags);
if (!nlh)
return -EMSGSIZE;
r = nlmsg_data(nlh);
BUG_ON(!sk_fullsock(sk));
inet_diag_msg_common_fill(r, sk);
r->idiag_state = sk->sk_state;
r->idiag_timer = 0;
r->idiag_retrans = 0;
if (nla_put_u8(skb, INET_DIAG_SHUTDOWN, sk->sk_shutdown))
goto errout;
/* IPv6 dual-stack sockets use inet->tos for IPv4 connections,
* hence this needs to be included regardless of socket family.
*/
if (ext & (1 << (INET_DIAG_TOS - 1)))
if (nla_put_u8(skb, INET_DIAG_TOS, inet->tos) < 0)
goto errout;
#if IS_ENABLED(CONFIG_IPV6)
if (r->idiag_family == AF_INET6) {
if (ext & (1 << (INET_DIAG_TCLASS - 1)))
if (nla_put_u8(skb, INET_DIAG_TCLASS,
inet6_sk(sk)->tclass) < 0)
goto errout;
if (((1 << sk->sk_state) & (TCPF_LISTEN | TCPF_CLOSE)) &&
nla_put_u8(skb, INET_DIAG_SKV6ONLY, ipv6_only_sock(sk)))
goto errout;
}
#endif
r->idiag_uid = from_kuid_munged(user_ns, sock_i_uid(sk));
r->idiag_inode = sock_i_ino(sk);
if (ext & (1 << (INET_DIAG_MEMINFO - 1))) {
struct inet_diag_meminfo minfo = {
.idiag_rmem = sk_rmem_alloc_get(sk),
.idiag_wmem = sk->sk_wmem_queued,
.idiag_fmem = sk->sk_forward_alloc,
.idiag_tmem = sk_wmem_alloc_get(sk),
};
if (nla_put(skb, INET_DIAG_MEMINFO, sizeof(minfo), &minfo) < 0)
goto errout;
}
if (ext & (1 << (INET_DIAG_SKMEMINFO - 1)))
if (sock_diag_put_meminfo(sk, skb, INET_DIAG_SKMEMINFO))
goto errout;
if (!icsk) {
handler->idiag_get_info(sk, r, NULL);
goto out;
}
#define EXPIRES_IN_MS(tmo) DIV_ROUND_UP((tmo - jiffies) * 1000, HZ)
if (icsk->icsk_pending == ICSK_TIME_RETRANS ||
icsk->icsk_pending == ICSK_TIME_EARLY_RETRANS ||
icsk->icsk_pending == ICSK_TIME_LOSS_PROBE) {
r->idiag_timer = 1;
r->idiag_retrans = icsk->icsk_retransmits;
r->idiag_expires = EXPIRES_IN_MS(icsk->icsk_timeout);
} else if (icsk->icsk_pending == ICSK_TIME_PROBE0) {
r->idiag_timer = 4;
r->idiag_retrans = icsk->icsk_probes_out;
r->idiag_expires = EXPIRES_IN_MS(icsk->icsk_timeout);
} else if (timer_pending(&sk->sk_timer)) {
r->idiag_timer = 2;
r->idiag_retrans = icsk->icsk_probes_out;
r->idiag_expires = EXPIRES_IN_MS(sk->sk_timer.expires);
} else {
r->idiag_timer = 0;
r->idiag_expires = 0;
}
#undef EXPIRES_IN_MS
if ((ext & (1 << (INET_DIAG_INFO - 1))) && handler->idiag_info_size) {
attr = nla_reserve(skb, INET_DIAG_INFO,
handler->idiag_info_size);
if (!attr)
goto errout;
info = nla_data(attr);
}
if (ext & (1 << (INET_DIAG_CONG - 1))) {
int err = 0;
rcu_read_lock();
ca_ops = READ_ONCE(icsk->icsk_ca_ops);
if (ca_ops)
err = nla_put_string(skb, INET_DIAG_CONG, ca_ops->name);
rcu_read_unlock();
if (err < 0)
goto errout;
}
handler->idiag_get_info(sk, r, info);
if (sk->sk_state < TCP_TIME_WAIT) {
union tcp_cc_info info;
size_t sz = 0;
int attr;
rcu_read_lock();
ca_ops = READ_ONCE(icsk->icsk_ca_ops);
if (ca_ops && ca_ops->get_info)
sz = ca_ops->get_info(sk, ext, &attr, &info);
rcu_read_unlock();
if (sz && nla_put(skb, attr, sz, &info) < 0)
goto errout;
}
out:
nlmsg_end(skb, nlh);
return 0;
errout:
nlmsg_cancel(skb, nlh);
return -EMSGSIZE;
}
EXPORT_SYMBOL_GPL(inet_sk_diag_fill);
static int inet_csk_diag_fill(struct sock *sk,
struct sk_buff *skb,
const struct inet_diag_req_v2 *req,
struct user_namespace *user_ns,
u32 portid, u32 seq, u16 nlmsg_flags,
const struct nlmsghdr *unlh)
{
return inet_sk_diag_fill(sk, inet_csk(sk), skb, req,
user_ns, portid, seq, nlmsg_flags, unlh);
}
static int inet_twsk_diag_fill(struct sock *sk,
struct sk_buff *skb,
u32 portid, u32 seq, u16 nlmsg_flags,
const struct nlmsghdr *unlh)
{
struct inet_timewait_sock *tw = inet_twsk(sk);
struct inet_diag_msg *r;
struct nlmsghdr *nlh;
long tmo;
nlh = nlmsg_put(skb, portid, seq, unlh->nlmsg_type, sizeof(*r),
nlmsg_flags);
if (!nlh)
return -EMSGSIZE;
r = nlmsg_data(nlh);
BUG_ON(tw->tw_state != TCP_TIME_WAIT);
tmo = tw->tw_timer.expires - jiffies;
if (tmo < 0)
tmo = 0;
inet_diag_msg_common_fill(r, sk);
r->idiag_retrans = 0;
r->idiag_state = tw->tw_substate;
r->idiag_timer = 3;
r->idiag_expires = jiffies_to_msecs(tmo);
r->idiag_rqueue = 0;
r->idiag_wqueue = 0;
r->idiag_uid = 0;
r->idiag_inode = 0;
nlmsg_end(skb, nlh);
return 0;
}
static int inet_req_diag_fill(struct sock *sk, struct sk_buff *skb,
u32 portid, u32 seq, u16 nlmsg_flags,
const struct nlmsghdr *unlh)
{
struct inet_diag_msg *r;
struct nlmsghdr *nlh;
long tmo;
nlh = nlmsg_put(skb, portid, seq, unlh->nlmsg_type, sizeof(*r),
nlmsg_flags);
if (!nlh)
return -EMSGSIZE;
r = nlmsg_data(nlh);
inet_diag_msg_common_fill(r, sk);
r->idiag_state = TCP_SYN_RECV;
r->idiag_timer = 1;
r->idiag_retrans = inet_reqsk(sk)->num_retrans;
BUILD_BUG_ON(offsetof(struct inet_request_sock, ir_cookie) !=
offsetof(struct sock, sk_cookie));
tmo = inet_reqsk(sk)->rsk_timer.expires - jiffies;
r->idiag_expires = (tmo >= 0) ? jiffies_to_msecs(tmo) : 0;
r->idiag_rqueue = 0;
r->idiag_wqueue = 0;
r->idiag_uid = 0;
r->idiag_inode = 0;
nlmsg_end(skb, nlh);
return 0;
}
static int sk_diag_fill(struct sock *sk, struct sk_buff *skb,
const struct inet_diag_req_v2 *r,
struct user_namespace *user_ns,
u32 portid, u32 seq, u16 nlmsg_flags,
const struct nlmsghdr *unlh)
{
if (sk->sk_state == TCP_TIME_WAIT)
return inet_twsk_diag_fill(sk, skb, portid, seq,
nlmsg_flags, unlh);
if (sk->sk_state == TCP_NEW_SYN_RECV)
return inet_req_diag_fill(sk, skb, portid, seq,
nlmsg_flags, unlh);
return inet_csk_diag_fill(sk, skb, r, user_ns, portid, seq,
nlmsg_flags, unlh);
}
struct sock *inet_diag_find_one_icsk(struct net *net,
struct inet_hashinfo *hashinfo,
const struct inet_diag_req_v2 *req)
{
struct sock *sk;
if (req->sdiag_family == AF_INET)
sk = inet_lookup(net, hashinfo, req->id.idiag_dst[0],
req->id.idiag_dport, req->id.idiag_src[0],
req->id.idiag_sport, req->id.idiag_if);
#if IS_ENABLED(CONFIG_IPV6)
else if (req->sdiag_family == AF_INET6) {
if (ipv6_addr_v4mapped((struct in6_addr *)req->id.idiag_dst) &&
ipv6_addr_v4mapped((struct in6_addr *)req->id.idiag_src))
sk = inet_lookup(net, hashinfo, req->id.idiag_dst[3],
req->id.idiag_dport, req->id.idiag_src[3],
req->id.idiag_sport, req->id.idiag_if);
else
sk = inet6_lookup(net, hashinfo,
(struct in6_addr *)req->id.idiag_dst,
req->id.idiag_dport,
(struct in6_addr *)req->id.idiag_src,
req->id.idiag_sport,
req->id.idiag_if);
}
#endif
else
return ERR_PTR(-EINVAL);
if (!sk)
return ERR_PTR(-ENOENT);
if (sock_diag_check_cookie(sk, req->id.idiag_cookie)) {
sock_gen_put(sk);
return ERR_PTR(-ENOENT);
}
return sk;
}
EXPORT_SYMBOL_GPL(inet_diag_find_one_icsk);
int inet_diag_dump_one_icsk(struct inet_hashinfo *hashinfo,
struct sk_buff *in_skb,
const struct nlmsghdr *nlh,
const struct inet_diag_req_v2 *req)
{
struct net *net = sock_net(in_skb->sk);
struct sk_buff *rep;
struct sock *sk;
int err;
sk = inet_diag_find_one_icsk(net, hashinfo, req);
if (IS_ERR(sk))
return PTR_ERR(sk);
rep = nlmsg_new(inet_sk_attr_size(), GFP_KERNEL);
if (!rep) {
err = -ENOMEM;
goto out;
}
err = sk_diag_fill(sk, rep, req,
sk_user_ns(NETLINK_CB(in_skb).sk),
NETLINK_CB(in_skb).portid,
nlh->nlmsg_seq, 0, nlh);
if (err < 0) {
WARN_ON(err == -EMSGSIZE);
nlmsg_free(rep);
goto out;
}
err = netlink_unicast(net->diag_nlsk, rep, NETLINK_CB(in_skb).portid,
MSG_DONTWAIT);
if (err > 0)
err = 0;
out:
if (sk)
sock_gen_put(sk);
return err;
}
EXPORT_SYMBOL_GPL(inet_diag_dump_one_icsk);
static int inet_diag_cmd_exact(int cmd, struct sk_buff *in_skb,
const struct nlmsghdr *nlh,
const struct inet_diag_req_v2 *req)
{
const struct inet_diag_handler *handler;
int err;
handler = inet_diag_lock_handler(req->sdiag_protocol);
if (IS_ERR(handler))
err = PTR_ERR(handler);
else if (cmd == SOCK_DIAG_BY_FAMILY)
err = handler->dump_one(in_skb, nlh, req);
else if (cmd == SOCK_DESTROY_BACKPORT && handler->destroy)
err = handler->destroy(in_skb, req);
else
err = -EOPNOTSUPP;
inet_diag_unlock_handler(handler);
return err;
}
static int bitstring_match(const __be32 *a1, const __be32 *a2, int bits)
{
int words = bits >> 5;
bits &= 0x1f;
if (words) {
if (memcmp(a1, a2, words << 2))
return 0;
}
if (bits) {
__be32 w1, w2;
__be32 mask;
w1 = a1[words];
w2 = a2[words];
mask = htonl((0xffffffff) << (32 - bits));
if ((w1 ^ w2) & mask)
return 0;
}
return 1;
}
int inet_sk_diag_fill(struct sock *sk, struct inet_connection_sock *icsk,
struct sk_buff *skb, const struct inet_diag_req_v2 *req,
struct user_namespace *user_ns,
u32 portid, u32 seq, u16 nlmsg_flags,
const struct nlmsghdr *unlh,
bool net_admin)
{
const struct tcp_congestion_ops *ca_ops;
const struct inet_diag_handler *handler;
int ext = req->idiag_ext;
struct inet_diag_msg *r;
struct nlmsghdr *nlh;
struct nlattr *attr;
void *info = NULL;
handler = inet_diag_table[req->sdiag_protocol];
BUG_ON(!handler);
nlh = nlmsg_put(skb, portid, seq, unlh->nlmsg_type, sizeof(*r),
nlmsg_flags);
if (!nlh)
return -EMSGSIZE;
r = nlmsg_data(nlh);
BUG_ON(!sk_fullsock(sk));
inet_diag_msg_common_fill(r, sk);
r->idiag_state = sk->sk_state;
r->idiag_timer = 0;
r->idiag_retrans = 0;
if (inet_diag_msg_attrs_fill(sk, skb, r, ext, user_ns, net_admin))
goto errout;
if (ext & (1 << (INET_DIAG_MEMINFO - 1))) {
struct inet_diag_meminfo minfo = {
.idiag_rmem = sk_rmem_alloc_get(sk),
.idiag_wmem = sk->sk_wmem_queued,
.idiag_fmem = sk->sk_forward_alloc,
.idiag_tmem = sk_wmem_alloc_get(sk),
};
if (nla_put(skb, INET_DIAG_MEMINFO, sizeof(minfo), &minfo) < 0)
goto errout;
}
if (ext & (1 << (INET_DIAG_SKMEMINFO - 1)))
if (sock_diag_put_meminfo(sk, skb, INET_DIAG_SKMEMINFO))
goto errout;
/*
* RAW sockets might have user-defined protocols assigned,
* so report the one supplied on socket creation.
*/
if (sk->sk_type == SOCK_RAW) {
if (nla_put_u8(skb, INET_DIAG_PROTOCOL, sk->sk_protocol))
goto errout;
}
if (!icsk) {
handler->idiag_get_info(sk, r, NULL);
goto out;
}
if (icsk->icsk_pending == ICSK_TIME_RETRANS ||
icsk->icsk_pending == ICSK_TIME_REO_TIMEOUT ||
icsk->icsk_pending == ICSK_TIME_LOSS_PROBE) {
r->idiag_timer = 1;
r->idiag_retrans = icsk->icsk_retransmits;
r->idiag_expires =
jiffies_to_msecs(icsk->icsk_timeout - jiffies);
} else if (icsk->icsk_pending == ICSK_TIME_PROBE0) {
r->idiag_timer = 4;
r->idiag_retrans = icsk->icsk_probes_out;
r->idiag_expires =
jiffies_to_msecs(icsk->icsk_timeout - jiffies);
} else if (timer_pending(&sk->sk_timer)) {
r->idiag_timer = 2;
r->idiag_retrans = icsk->icsk_probes_out;
r->idiag_expires =
jiffies_to_msecs(sk->sk_timer.expires - jiffies);
} else {
r->idiag_timer = 0;
r->idiag_expires = 0;
}
if ((ext & (1 << (INET_DIAG_INFO - 1))) && handler->idiag_info_size) {
attr = nla_reserve_64bit(skb, INET_DIAG_INFO,
handler->idiag_info_size,
INET_DIAG_PAD);
if (!attr)
goto errout;
info = nla_data(attr);
}
if (ext & (1 << (INET_DIAG_CONG - 1))) {
int err = 0;
rcu_read_lock();
ca_ops = READ_ONCE(icsk->icsk_ca_ops);
if (ca_ops)
err = nla_put_string(skb, INET_DIAG_CONG, ca_ops->name);
rcu_read_unlock();
if (err < 0)
goto errout;
}
handler->idiag_get_info(sk, r, info);
if (ext & (1 << (INET_DIAG_INFO - 1)) && handler->idiag_get_aux)
if (handler->idiag_get_aux(sk, net_admin, skb) < 0)
goto errout;
if (sk->sk_state < TCP_TIME_WAIT) {
union tcp_cc_info info;
size_t sz = 0;
int attr;
rcu_read_lock();
ca_ops = READ_ONCE(icsk->icsk_ca_ops);
if (ca_ops && ca_ops->get_info)
sz = ca_ops->get_info(sk, ext, &attr, &info);
rcu_read_unlock();
if (sz && nla_put(skb, attr, sz, &info) < 0)
goto errout;
}
if (ext & (1 << (INET_DIAG_CLASS_ID - 1))) {
u32 classid = 0;
#ifdef CONFIG_SOCK_CGROUP_DATA
classid = sock_cgroup_classid(&sk->sk_cgrp_data);
#endif
if (nla_put_u32(skb, INET_DIAG_CLASS_ID, classid))
goto errout;
}
out:
nlmsg_end(skb, nlh);
return 0;
errout:
nlmsg_cancel(skb, nlh);
return -EMSGSIZE;
}
EXPORT_SYMBOL_GPL(inet_sk_diag_fill);
static int inet_csk_diag_fill(struct sock *sk,
struct sk_buff *skb,
const struct inet_diag_req_v2 *req,
struct user_namespace *user_ns,
u32 portid, u32 seq, u16 nlmsg_flags,
const struct nlmsghdr *unlh,
bool net_admin)
{
return inet_sk_diag_fill(sk, inet_csk(sk), skb, req, user_ns,
portid, seq, nlmsg_flags, unlh, net_admin);
}
static int inet_twsk_diag_fill(struct sock *sk,
struct sk_buff *skb,
u32 portid, u32 seq, u16 nlmsg_flags,
const struct nlmsghdr *unlh)
{
struct inet_timewait_sock *tw = inet_twsk(sk);
struct inet_diag_msg *r;
struct nlmsghdr *nlh;
long tmo;
nlh = nlmsg_put(skb, portid, seq, unlh->nlmsg_type, sizeof(*r),
nlmsg_flags);
if (!nlh)
return -EMSGSIZE;
r = nlmsg_data(nlh);
BUG_ON(tw->tw_state != TCP_TIME_WAIT);
tmo = tw->tw_timer.expires - jiffies;
if (tmo < 0)
tmo = 0;
inet_diag_msg_common_fill(r, sk);
r->idiag_retrans = 0;
r->idiag_state = tw->tw_substate;
r->idiag_timer = 3;
r->idiag_expires = jiffies_to_msecs(tmo);
r->idiag_rqueue = 0;
r->idiag_wqueue = 0;
r->idiag_uid = 0;
r->idiag_inode = 0;
nlmsg_end(skb, nlh);
return 0;
}
static int inet_req_diag_fill(struct sock *sk, struct sk_buff *skb,
u32 portid, u32 seq, u16 nlmsg_flags,
const struct nlmsghdr *unlh, bool net_admin)
{
struct request_sock *reqsk = inet_reqsk(sk);
struct inet_diag_msg *r;
struct nlmsghdr *nlh;
long tmo;
nlh = nlmsg_put(skb, portid, seq, unlh->nlmsg_type, sizeof(*r),
nlmsg_flags);
if (!nlh)
return -EMSGSIZE;
r = nlmsg_data(nlh);
inet_diag_msg_common_fill(r, sk);
r->idiag_state = TCP_SYN_RECV;
r->idiag_timer = 1;
r->idiag_retrans = reqsk->num_retrans;
BUILD_BUG_ON(offsetof(struct inet_request_sock, ir_cookie) !=
offsetof(struct sock, sk_cookie));
tmo = inet_reqsk(sk)->rsk_timer.expires - jiffies;
r->idiag_expires = (tmo >= 0) ? jiffies_to_msecs(tmo) : 0;
r->idiag_rqueue = 0;
r->idiag_wqueue = 0;
r->idiag_uid = 0;
r->idiag_inode = 0;
if (net_admin && nla_put_u32(skb, INET_DIAG_MARK,
inet_rsk(reqsk)->ir_mark))
return -EMSGSIZE;
nlmsg_end(skb, nlh);
return 0;
}
static int sk_diag_fill(struct sock *sk, struct sk_buff *skb,
const struct inet_diag_req_v2 *r,
struct user_namespace *user_ns,
u32 portid, u32 seq, u16 nlmsg_flags,
const struct nlmsghdr *unlh, bool net_admin)
{
if (sk->sk_state == TCP_TIME_WAIT)
return inet_twsk_diag_fill(sk, skb, portid, seq,
nlmsg_flags, unlh);
if (sk->sk_state == TCP_NEW_SYN_RECV)
return inet_req_diag_fill(sk, skb, portid, seq,
nlmsg_flags, unlh, net_admin);
return inet_csk_diag_fill(sk, skb, r, user_ns, portid, seq,
nlmsg_flags, unlh, net_admin);
}
struct sock *inet_diag_find_one_icsk(struct net *net,
struct inet_hashinfo *hashinfo,
const struct inet_diag_req_v2 *req)
{
struct sock *sk;
rcu_read_lock();
if (req->sdiag_family == AF_INET)
sk = inet_lookup(net, hashinfo, NULL, 0, req->id.idiag_dst[0],
req->id.idiag_dport, req->id.idiag_src[0],
req->id.idiag_sport, req->id.idiag_if);
#if IS_ENABLED(CONFIG_IPV6)
else if (req->sdiag_family == AF_INET6) {
if (ipv6_addr_v4mapped((struct in6_addr *)req->id.idiag_dst) &&
ipv6_addr_v4mapped((struct in6_addr *)req->id.idiag_src))
sk = inet_lookup(net, hashinfo, NULL, 0, req->id.idiag_dst[3],
req->id.idiag_dport, req->id.idiag_src[3],
req->id.idiag_sport, req->id.idiag_if);
else
sk = inet6_lookup(net, hashinfo, NULL, 0,
(struct in6_addr *)req->id.idiag_dst,
req->id.idiag_dport,
(struct in6_addr *)req->id.idiag_src,
req->id.idiag_sport,
req->id.idiag_if);
}
#endif
else {
rcu_read_unlock();
return ERR_PTR(-EINVAL);
}
rcu_read_unlock();
if (!sk)
return ERR_PTR(-ENOENT);
if (sock_diag_check_cookie(sk, req->id.idiag_cookie)) {
sock_gen_put(sk);
return ERR_PTR(-ENOENT);
}
return sk;
}
EXPORT_SYMBOL_GPL(inet_diag_find_one_icsk);
int inet_diag_dump_one_icsk(struct inet_hashinfo *hashinfo,
struct sk_buff *in_skb,
const struct nlmsghdr *nlh,
const struct inet_diag_req_v2 *req)
{
bool net_admin = netlink_net_capable(in_skb, CAP_NET_ADMIN);
struct net *net = sock_net(in_skb->sk);
struct sk_buff *rep;
struct sock *sk;
int err;
sk = inet_diag_find_one_icsk(net, hashinfo, req);
if (IS_ERR(sk))
return PTR_ERR(sk);
rep = nlmsg_new(inet_sk_attr_size(sk, req, net_admin), GFP_KERNEL);
if (!rep) {
err = -ENOMEM;
goto out;
}
err = sk_diag_fill(sk, rep, req,
sk_user_ns(NETLINK_CB(in_skb).sk),
NETLINK_CB(in_skb).portid,
nlh->nlmsg_seq, 0, nlh, net_admin);
if (err < 0) {
WARN_ON(err == -EMSGSIZE);
nlmsg_free(rep);
goto out;
}
err = netlink_unicast(net->diag_nlsk, rep, NETLINK_CB(in_skb).portid,
MSG_DONTWAIT);
if (err > 0)
err = 0;
out:
if (sk)
sock_gen_put(sk);
return err;
}
static bool
socket_mt4_v0(const struct sk_buff *skb, struct xt_action_param *par)
{
static struct xt_socket_mtinfo1 xt_info_v0 = {
.flags = 0,
};
return socket_match(skb, par, &xt_info_v0);
}
static bool
socket_mt4_v1_v2(const struct sk_buff *skb, struct xt_action_param *par)
{
return socket_match(skb, par, par->matchinfo);
}
#ifdef XT_SOCKET_HAVE_IPV6
static int
extract_icmp6_fields(const struct sk_buff *skb,
unsigned int outside_hdrlen,
int *protocol,
const struct in6_addr **raddr,
const struct in6_addr **laddr,
__be16 *rport,
__be16 *lport,
struct ipv6hdr *ipv6_var)
{
const struct ipv6hdr *inside_iph;
struct icmp6hdr *icmph, _icmph;
__be16 *ports, _ports[2];
u8 inside_nexthdr;
__be16 inside_fragoff;
int inside_hdrlen;
icmph = skb_header_pointer(skb, outside_hdrlen,
sizeof(_icmph), &_icmph);
if (icmph == NULL)
return 1;
if (icmph->icmp6_type & ICMPV6_INFOMSG_MASK)
return 1;
inside_iph = skb_header_pointer(skb, outside_hdrlen + sizeof(_icmph),
sizeof(*ipv6_var), ipv6_var);
if (inside_iph == NULL)
return 1;
inside_nexthdr = inside_iph->nexthdr;
inside_hdrlen = ipv6_skip_exthdr(skb, outside_hdrlen + sizeof(_icmph) +
sizeof(*ipv6_var),
&inside_nexthdr, &inside_fragoff);
if (inside_hdrlen < 0)
return 1; /* hjm: Packet has no/incomplete transport layer headers. */
if (inside_nexthdr != IPPROTO_TCP &&
inside_nexthdr != IPPROTO_UDP)
return 1;
ports = skb_header_pointer(skb, inside_hdrlen,
sizeof(_ports), &_ports);
if (ports == NULL)
return 1;
/* the inside IP packet is the one quoted from our side, thus
* its saddr is the local address */
*protocol = inside_nexthdr;
*laddr = &inside_iph->saddr;
*lport = ports[0];
*raddr = &inside_iph->daddr;
*rport = ports[1];
return 0;
}
static struct sock *
xt_socket_get_sock_v6(struct net *net, const u8 protocol,
const struct in6_addr *saddr, const struct in6_addr *daddr,
const __be16 sport, const __be16 dport,
const struct net_device *in)
{
switch (protocol) {
case IPPROTO_TCP:
return inet6_lookup(net, &tcp_hashinfo,
saddr, sport, daddr, dport,
in->ifindex);
case IPPROTO_UDP:
return udp6_lib_lookup(net, saddr, sport, daddr, dport,
in->ifindex);
}
return NULL;
}
static bool
socket_mt6_v1_v2(const struct sk_buff *skb, struct xt_action_param *par)
{
struct ipv6hdr ipv6_var, *iph = ipv6_hdr(skb);
struct udphdr _hdr, *hp = NULL;
struct sock *sk = skb->sk;
const struct in6_addr *daddr = NULL, *saddr = NULL;
__be16 uninitialized_var(dport), uninitialized_var(sport);
int thoff = 0, uninitialized_var(tproto);
const struct xt_socket_mtinfo1 *info = (struct xt_socket_mtinfo1 *) par->matchinfo;
tproto = ipv6_find_hdr(skb, &thoff, -1, NULL, NULL);
if (tproto < 0) {
pr_debug("unable to find transport header in IPv6 packet, dropping\n");
return NF_DROP;
}
if (tproto == IPPROTO_UDP || tproto == IPPROTO_TCP) {
hp = skb_header_pointer(skb, thoff,
sizeof(_hdr), &_hdr);
if (hp == NULL)
return false;
saddr = &iph->saddr;
sport = hp->source;
daddr = &iph->daddr;
dport = hp->dest;
} else if (tproto == IPPROTO_ICMPV6) {
if (extract_icmp6_fields(skb, thoff, &tproto, &saddr, &daddr,
&sport, &dport, &ipv6_var))
return false;
} else {
return false;
}
if (!sk)
sk = xt_socket_get_sock_v6(dev_net(skb->dev), tproto,
saddr, daddr, sport, dport,
par->in);
if (sk) {
bool wildcard;
bool transparent = true;
/* Ignore sockets listening on INADDR_ANY
* unless XT_SOCKET_NOWILDCARD is set
*/
wildcard = (!(info->flags & XT_SOCKET_NOWILDCARD) &&
sk->sk_state != TCP_TIME_WAIT &&
ipv6_addr_any(&sk->sk_v6_rcv_saddr));
/* Ignore non-transparent sockets,
if XT_SOCKET_TRANSPARENT is used */
if (info->flags & XT_SOCKET_TRANSPARENT)
transparent = ((sk->sk_state != TCP_TIME_WAIT &&
inet_sk(sk)->transparent) ||
(sk->sk_state == TCP_TIME_WAIT &&
inet_twsk(sk)->tw_transparent));
if (sk != skb->sk)
sock_gen_put(sk);
if (wildcard || !transparent)
sk = NULL;
}
pr_debug("proto %hhd %pI6:%hu -> %pI6:%hu "
"(orig %pI6:%hu) sock %p\n",
tproto, saddr, ntohs(sport),
daddr, ntohs(dport),
&iph->daddr, hp ? ntohs(hp->dest) : 0, sk);
return (sk != NULL);
}
#endif
static int socket_mt_v1_check(const struct xt_mtchk_param *par)
{
const struct xt_socket_mtinfo1 *info = (struct xt_socket_mtinfo1 *) par->matchinfo;
if (info->flags & ~XT_SOCKET_FLAGS_V1) {
pr_info("unknown flags 0x%x\n", info->flags & ~XT_SOCKET_FLAGS_V1);
return -EINVAL;
}
return 0;
}
static int socket_mt_v2_check(const struct xt_mtchk_param *par)
{
const struct xt_socket_mtinfo2 *info = (struct xt_socket_mtinfo2 *) par->matchinfo;
if (info->flags & ~XT_SOCKET_FLAGS_V2) {
pr_info("unknown flags 0x%x\n", info->flags & ~XT_SOCKET_FLAGS_V2);
return -EINVAL;
}
return 0;
}
static struct xt_match socket_mt_reg[] __read_mostly = {
{
.name = "socket",
.revision = 0,
.family = NFPROTO_IPV4,
.match = socket_mt4_v0,
.hooks = (1 << NF_INET_PRE_ROUTING) |
(1 << NF_INET_LOCAL_IN),
.me = THIS_MODULE,
},
{
.name = "socket",
.revision = 1,
.family = NFPROTO_IPV4,
.match = socket_mt4_v1_v2,
.checkentry = socket_mt_v1_check,
.matchsize = sizeof(struct xt_socket_mtinfo1),
.hooks = (1 << NF_INET_PRE_ROUTING) |
(1 << NF_INET_LOCAL_IN),
.me = THIS_MODULE,
},
#ifdef XT_SOCKET_HAVE_IPV6
{
.name = "socket",
static bool
socket_mt4_v0(const struct sk_buff *skb, struct xt_action_param *par)
{
static struct xt_socket_mtinfo1 xt_info_v0 = {
.flags = 0,
};
return socket_match(skb, par, &xt_info_v0);
}
static bool
socket_mt4_v1_v2_v3(const struct sk_buff *skb, struct xt_action_param *par)
{
return socket_match(skb, par, par->matchinfo);
}
#if IS_ENABLED(CONFIG_IP6_NF_IPTABLES)
static bool
socket_mt6_v1_v2_v3(const struct sk_buff *skb, struct xt_action_param *par)
{
const struct xt_socket_mtinfo1 *info = (struct xt_socket_mtinfo1 *) par->matchinfo;
struct sk_buff *pskb = (struct sk_buff *)skb;
struct sock *sk = skb->sk;
if (sk && !net_eq(xt_net(par), sock_net(sk)))
sk = NULL;
if (!sk)
sk = nf_sk_lookup_slow_v6(xt_net(par), skb, xt_in(par));
if (sk) {
bool wildcard;
bool transparent = true;
/* Ignore sockets listening on INADDR_ANY
* unless XT_SOCKET_NOWILDCARD is set
*/
wildcard = (!(info->flags & XT_SOCKET_NOWILDCARD) &&
sk_fullsock(sk) &&
ipv6_addr_any(&sk->sk_v6_rcv_saddr));
/* Ignore non-transparent sockets,
* if XT_SOCKET_TRANSPARENT is used
*/
if (info->flags & XT_SOCKET_TRANSPARENT)
transparent = inet_sk_transparent(sk);
if (info->flags & XT_SOCKET_RESTORESKMARK && !wildcard &&
transparent && sk_fullsock(sk))
pskb->mark = sk->sk_mark;
if (sk != skb->sk)
sock_gen_put(sk);
if (wildcard || !transparent)
sk = NULL;
}
return sk != NULL;
}
#endif
static int socket_mt_enable_defrag(struct net *net, int family)
{
switch (family) {
case NFPROTO_IPV4:
return nf_defrag_ipv4_enable(net);
#if IS_ENABLED(CONFIG_IP6_NF_IPTABLES)
case NFPROTO_IPV6:
return nf_defrag_ipv6_enable(net);
#endif
}
WARN_ONCE(1, "Unknown family %d\n", family);
return 0;
}
static int socket_mt_v1_check(const struct xt_mtchk_param *par)
{
const struct xt_socket_mtinfo1 *info = (struct xt_socket_mtinfo1 *) par->matchinfo;
int err;
err = socket_mt_enable_defrag(par->net, par->family);
if (err)
return err;
if (info->flags & ~XT_SOCKET_FLAGS_V1) {
pr_info_ratelimited("unknown flags 0x%x\n",
info->flags & ~XT_SOCKET_FLAGS_V1);
return -EINVAL;
}
return 0;
}
static int socket_mt_v2_check(const struct xt_mtchk_param *par)
{
const struct xt_socket_mtinfo2 *info = (struct xt_socket_mtinfo2 *) par->matchinfo;
int err;
err = socket_mt_enable_defrag(par->net, par->family);
if (err)
return err;
if (info->flags & ~XT_SOCKET_FLAGS_V2) {
pr_info_ratelimited("unknown flags 0x%x\n",
info->flags & ~XT_SOCKET_FLAGS_V2);
return -EINVAL;
}
return 0;
}
static int socket_mt_v3_check(const struct xt_mtchk_param *par)
{
const struct xt_socket_mtinfo3 *info =
(struct xt_socket_mtinfo3 *)par->matchinfo;
int err;
err = socket_mt_enable_defrag(par->net, par->family);
if (err)
return err;
if (info->flags & ~XT_SOCKET_FLAGS_V3) {
pr_info_ratelimited("unknown flags 0x%x\n",
info->flags & ~XT_SOCKET_FLAGS_V3);
return -EINVAL;
}
return 0;
}
static struct xt_match socket_mt_reg[] __read_mostly = {
{
.name = "socket",
.revision = 0,
.family = NFPROTO_IPV4,
.match = socket_mt4_v0,
.hooks = (1 << NF_INET_PRE_ROUTING) |
(1 << NF_INET_LOCAL_IN),
.me = THIS_MODULE,
},
{
.name = "socket",
.revision = 1,
.family = NFPROTO_IPV4,
.match = socket_mt4_v1_v2_v3,
.checkentry = socket_mt_v1_check,
.matchsize = sizeof(struct xt_socket_mtinfo1),
.hooks = (1 << NF_INET_PRE_ROUTING) |
(1 << NF_INET_LOCAL_IN),
.me = THIS_MODULE,
},
#if IS_ENABLED(CONFIG_IP6_NF_IPTABLES)
{
.name = "socket",
