static void dccp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
u8 type, u8 code, int offset, __be32 info)
{
const struct ipv6hdr *hdr = (const struct ipv6hdr *)skb->data;
const struct dccp_hdr *dh = (struct dccp_hdr *)(skb->data + offset);
struct dccp_sock *dp;
struct ipv6_pinfo *np;
struct sock *sk;
int err;
__u64 seq;
struct net *net = dev_net(skb->dev);
if (skb->len < offset + sizeof(*dh) ||
skb->len < offset + __dccp_basic_hdr_len(dh)) {
ICMP6_INC_STATS_BH(net, __in6_dev_get(skb->dev),
ICMP6_MIB_INERRORS);
return;
}
sk = inet6_lookup(net, &dccp_hashinfo,
&hdr->daddr, dh->dccph_dport,
&hdr->saddr, dh->dccph_sport, inet6_iif(skb));
if (sk == NULL) {
ICMP6_INC_STATS_BH(net, __in6_dev_get(skb->dev),
ICMP6_MIB_INERRORS);
return;
}
if (sk->sk_state == DCCP_TIME_WAIT) {
inet_twsk_put(inet_twsk(sk));
return;
}
bh_lock_sock(sk);
if (sock_owned_by_user(sk))
NET_INC_STATS_BH(net, LINUX_MIB_LOCKDROPPEDICMPS);
if (sk->sk_state == DCCP_CLOSED)
goto out;
dp = dccp_sk(sk);
seq = dccp_hdr_seq(dh);
if ((1 << sk->sk_state) & ~(DCCPF_REQUESTING | DCCPF_LISTEN) &&
!between48(seq, dp->dccps_awl, dp->dccps_awh)) {
NET_INC_STATS_BH(net, LINUX_MIB_OUTOFWINDOWICMPS);
goto out;
}
np = inet6_sk(sk);
if (type == NDISC_REDIRECT) {
struct dst_entry *dst = __sk_dst_check(sk, np->dst_cookie);
if (dst)
dst->ops->redirect(dst, sk, skb);
goto out;
}
if (type == ICMPV6_PKT_TOOBIG) {
struct dst_entry *dst = NULL;
if (!ip6_sk_accept_pmtu(sk))
goto out;
if (sock_owned_by_user(sk))
goto out;
if ((1 << sk->sk_state) & (DCCPF_LISTEN | DCCPF_CLOSED))
goto out;
dst = inet6_csk_update_pmtu(sk, ntohl(info));
if (!dst)
goto out;
if (inet_csk(sk)->icsk_pmtu_cookie > dst_mtu(dst))
dccp_sync_mss(sk, dst_mtu(dst));
goto out;
}
icmpv6_err_convert(type, code, &err);
/* Might be for an request_sock */
switch (sk->sk_state) {
struct request_sock *req, **prev;
case DCCP_LISTEN:
if (sock_owned_by_user(sk))
goto out;
req = inet6_csk_search_req(sk, &prev, dh->dccph_dport,
&hdr->daddr, &hdr->saddr,
inet6_iif(skb));
if (req == NULL)
goto out;
/*
* ICMPs are not backlogged, hence we cannot get an established
* socket here.
*/
WARN_ON(req->sk != NULL);
if (!between48(seq, dccp_rsk(req)->dreq_iss,
dccp_rsk(req)->dreq_gss)) {
NET_INC_STATS_BH(net, LINUX_MIB_OUTOFWINDOWICMPS);
goto out;
}
inet_csk_reqsk_queue_drop(sk, req, prev);
goto out;
case DCCP_REQUESTING:
case DCCP_RESPOND: /* Cannot happen.
It can, it SYNs are crossed. --ANK */
if (!sock_owned_by_user(sk)) {
DCCP_INC_STATS_BH(DCCP_MIB_ATTEMPTFAILS);
sk->sk_err = err;
/*
* Wake people up to see the error
* (see connect in sock.c)
*/
sk->sk_error_report(sk);
dccp_done(sk);
} else
sk->sk_err_soft = err;
goto out;
}
if (!sock_owned_by_user(sk) && np->recverr) {
sk->sk_err = err;
sk->sk_error_report(sk);
} else
sk->sk_err_soft = err;
out:
bh_unlock_sock(sk);
sock_put(sk);
}
static int dccp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
int addr_len)
{
struct sockaddr_in6 *usin = (struct sockaddr_in6 *)uaddr;
struct inet_connection_sock *icsk = inet_csk(sk);
struct inet_sock *inet = inet_sk(sk);
struct ipv6_pinfo *np = inet6_sk(sk);
struct dccp_sock *dp = dccp_sk(sk);
struct in6_addr *saddr = NULL, *final_p = NULL, final;
struct flowi fl;
struct dst_entry *dst;
int addr_type;
int err;
dp->dccps_role = DCCP_ROLE_CLIENT;
if (addr_len < SIN6_LEN_RFC2133)
return -EINVAL;
if (usin->sin6_family != AF_INET6)
return -EAFNOSUPPORT;
memset(&fl, 0, sizeof(fl));
if (np->sndflow) {
fl.fl6_flowlabel = usin->sin6_flowinfo & IPV6_FLOWINFO_MASK;
IP6_ECN_flow_init(fl.fl6_flowlabel);
if (fl.fl6_flowlabel & IPV6_FLOWLABEL_MASK) {
struct ip6_flowlabel *flowlabel;
flowlabel = fl6_sock_lookup(sk, fl.fl6_flowlabel);
if (flowlabel == NULL)
return -EINVAL;
ipv6_addr_copy(&usin->sin6_addr, &flowlabel->dst);
fl6_sock_release(flowlabel);
}
}
/*
* connect() to INADDR_ANY means loopback (BSD'ism).
*/
if (ipv6_addr_any(&usin->sin6_addr))
usin->sin6_addr.s6_addr[15] = 1;
addr_type = ipv6_addr_type(&usin->sin6_addr);
if (addr_type & IPV6_ADDR_MULTICAST)
return -ENETUNREACH;
if (addr_type & IPV6_ADDR_LINKLOCAL) {
if (addr_len >= sizeof(struct sockaddr_in6) &&
usin->sin6_scope_id) {
/* If interface is set while binding, indices
* must coincide.
*/
if (sk->sk_bound_dev_if &&
sk->sk_bound_dev_if != usin->sin6_scope_id)
return -EINVAL;
sk->sk_bound_dev_if = usin->sin6_scope_id;
}
/* Connect to link-local address requires an interface */
if (!sk->sk_bound_dev_if)
return -EINVAL;
}
ipv6_addr_copy(&np->daddr, &usin->sin6_addr);
np->flow_label = fl.fl6_flowlabel;
/*
* DCCP over IPv4
*/
if (addr_type == IPV6_ADDR_MAPPED) {
u32 exthdrlen = icsk->icsk_ext_hdr_len;
struct sockaddr_in sin;
SOCK_DEBUG(sk, "connect: ipv4 mapped\n");
if (__ipv6_only_sock(sk))
return -ENETUNREACH;
sin.sin_family = AF_INET;
sin.sin_port = usin->sin6_port;
sin.sin_addr.s_addr = usin->sin6_addr.s6_addr32[3];
icsk->icsk_af_ops = &dccp_ipv6_mapped;
sk->sk_backlog_rcv = dccp_v4_do_rcv;
err = dccp_v4_connect(sk, (struct sockaddr *)&sin, sizeof(sin));
if (err) {
icsk->icsk_ext_hdr_len = exthdrlen;
icsk->icsk_af_ops = &dccp_ipv6_af_ops;
sk->sk_backlog_rcv = dccp_v6_do_rcv;
goto failure;
} else {
ipv6_addr_set(&np->saddr, 0, 0, htonl(0x0000FFFF),
inet->saddr);
ipv6_addr_set(&np->rcv_saddr, 0, 0, htonl(0x0000FFFF),
inet->rcv_saddr);
}
return err;
}
if (!ipv6_addr_any(&np->rcv_saddr))
saddr = &np->rcv_saddr;
fl.proto = IPPROTO_DCCP;
ipv6_addr_copy(&fl.fl6_dst, &np->daddr);
ipv6_addr_copy(&fl.fl6_src, saddr ? saddr : &np->saddr);
fl.oif = sk->sk_bound_dev_if;
fl.fl_ip_dport = usin->sin6_port;
fl.fl_ip_sport = inet->sport;
security_sk_classify_flow(sk, &fl);
if (np->opt != NULL && np->opt->srcrt != NULL) {
const struct rt0_hdr *rt0 = (struct rt0_hdr *)np->opt->srcrt;
ipv6_addr_copy(&final, &fl.fl6_dst);
ipv6_addr_copy(&fl.fl6_dst, rt0->addr);
final_p = &final;
}
err = ip6_dst_lookup(sk, &dst, &fl);
if (err)
goto failure;
if (final_p)
ipv6_addr_copy(&fl.fl6_dst, final_p);
err = __xfrm_lookup(sock_net(sk), &dst, &fl, sk, XFRM_LOOKUP_WAIT);
if (err < 0) {
if (err == -EREMOTE)
err = ip6_dst_blackhole(sk, &dst, &fl);
if (err < 0)
goto failure;
}
if (saddr == NULL) {
saddr = &fl.fl6_src;
ipv6_addr_copy(&np->rcv_saddr, saddr);
}
/* set the source address */
ipv6_addr_copy(&np->saddr, saddr);
inet->rcv_saddr = LOOPBACK4_IPV6;
__ip6_dst_store(sk, dst, NULL, NULL);
icsk->icsk_ext_hdr_len = 0;
if (np->opt != NULL)
icsk->icsk_ext_hdr_len = (np->opt->opt_flen +
np->opt->opt_nflen);
inet->dport = usin->sin6_port;
dccp_set_state(sk, DCCP_REQUESTING);
err = inet6_hash_connect(&dccp_death_row, sk);
if (err)
goto late_failure;
dp->dccps_iss = secure_dccpv6_sequence_number(np->saddr.s6_addr32,
np->daddr.s6_addr32,
inet->sport, inet->dport);
err = dccp_connect(sk);
if (err)
goto late_failure;
return 0;
late_failure:
dccp_set_state(sk, DCCP_CLOSED);
__sk_dst_reset(sk);
failure:
inet->dport = 0;
sk->sk_route_caps = 0;
return err;
}
void dccp_close(struct sock *sk, long timeout)
{
struct dccp_sock *dp = dccp_sk(sk);
struct sk_buff *skb;
int state;
lock_sock(sk);
sk->sk_shutdown = SHUTDOWN_MASK;
if (sk->sk_state == DCCP_LISTEN) {
dccp_set_state(sk, DCCP_CLOSED);
/* Special case. */
inet_csk_listen_stop(sk);
goto adjudge_to_death;
}
sk_stop_timer(sk, &dp->dccps_xmit_timer);
/*
* We need to flush the recv. buffs. We do this only on the
* descriptor close, not protocol-sourced closes, because the
*reader process may not have drained the data yet!
*/
/* FIXME: check for unread data */
while ((skb = __skb_dequeue(&sk->sk_receive_queue)) != NULL) {
__kfree_skb(skb);
}
if (sock_flag(sk, SOCK_LINGER) && !sk->sk_lingertime) {
/* Check zero linger _after_ checking for unread data. */
sk->sk_prot->disconnect(sk, 0);
} else if (dccp_close_state(sk)) {
dccp_send_close(sk, 1);
}
sk_stream_wait_close(sk, timeout);
adjudge_to_death:
state = sk->sk_state;
sock_hold(sk);
sock_orphan(sk);
atomic_inc(sk->sk_prot->orphan_count);
/*
* It is the last release_sock in its life. It will remove backlog.
*/
release_sock(sk);
/*
* Now socket is owned by kernel and we acquire BH lock
* to finish close. No need to check for user refs.
*/
local_bh_disable();
bh_lock_sock(sk);
BUG_TRAP(!sock_owned_by_user(sk));
/* Have we already been destroyed by a softirq or backlog? */
if (state != DCCP_CLOSED && sk->sk_state == DCCP_CLOSED)
goto out;
/*
* The last release_sock may have processed the CLOSE or RESET
* packet moving sock to CLOSED state, if not we have to fire
* the CLOSE/CLOSEREQ retransmission timer, see "8.3. Termination"
* in draft-ietf-dccp-spec-11. -acme
*/
if (sk->sk_state == DCCP_CLOSING) {
/* FIXME: should start at 2 * RTT */
/* Timer for repeating the CLOSE/CLOSEREQ until an answer. */
inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS,
inet_csk(sk)->icsk_rto,
DCCP_RTO_MAX);
#if 0
/* Yeah, we should use sk->sk_prot->orphan_count, etc */
dccp_set_state(sk, DCCP_CLOSED);
#endif
}
if (sk->sk_state == DCCP_CLOSED)
inet_csk_destroy_sock(sk);
/* Otherwise, socket is reprieved until protocol close. */
out:
bh_unlock_sock(sk);
local_bh_enable();
sock_put(sk);
}
static int dccp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
u8 type, u8 code, int offset, __be32 info)
{
const struct ipv6hdr *hdr = (const struct ipv6hdr *)skb->data;
const struct dccp_hdr *dh;
struct dccp_sock *dp;
struct ipv6_pinfo *np;
struct sock *sk;
int err;
__u64 seq;
struct net *net = dev_net(skb->dev);
/* Only need dccph_dport & dccph_sport which are the first
* 4 bytes in dccp header.
* Our caller (icmpv6_notify()) already pulled 8 bytes for us.
*/
BUILD_BUG_ON(offsetofend(struct dccp_hdr, dccph_sport) > 8);
BUILD_BUG_ON(offsetofend(struct dccp_hdr, dccph_dport) > 8);
dh = (struct dccp_hdr *)(skb->data + offset);
sk = __inet6_lookup_established(net, &dccp_hashinfo,
&hdr->daddr, dh->dccph_dport,
&hdr->saddr, ntohs(dh->dccph_sport),
inet6_iif(skb), 0);
if (!sk) {
__ICMP6_INC_STATS(net, __in6_dev_get(skb->dev),
ICMP6_MIB_INERRORS);
return -ENOENT;
}
if (sk->sk_state == DCCP_TIME_WAIT) {
inet_twsk_put(inet_twsk(sk));
return 0;
}
seq = dccp_hdr_seq(dh);
if (sk->sk_state == DCCP_NEW_SYN_RECV) {
dccp_req_err(sk, seq);
return 0;
}
bh_lock_sock(sk);
if (sock_owned_by_user(sk))
__NET_INC_STATS(net, LINUX_MIB_LOCKDROPPEDICMPS);
if (sk->sk_state == DCCP_CLOSED)
goto out;
dp = dccp_sk(sk);
if ((1 << sk->sk_state) & ~(DCCPF_REQUESTING | DCCPF_LISTEN) &&
!between48(seq, dp->dccps_awl, dp->dccps_awh)) {
__NET_INC_STATS(net, LINUX_MIB_OUTOFWINDOWICMPS);
goto out;
}
np = inet6_sk(sk);
if (type == NDISC_REDIRECT) {
if (!sock_owned_by_user(sk)) {
struct dst_entry *dst = __sk_dst_check(sk, np->dst_cookie);
if (dst)
dst->ops->redirect(dst, sk, skb);
}
goto out;
}
if (type == ICMPV6_PKT_TOOBIG) {
struct dst_entry *dst = NULL;
if (!ip6_sk_accept_pmtu(sk))
goto out;
if (sock_owned_by_user(sk))
goto out;
if ((1 << sk->sk_state) & (DCCPF_LISTEN | DCCPF_CLOSED))
goto out;
dst = inet6_csk_update_pmtu(sk, ntohl(info));
if (!dst)
goto out;
if (inet_csk(sk)->icsk_pmtu_cookie > dst_mtu(dst))
dccp_sync_mss(sk, dst_mtu(dst));
goto out;
}
icmpv6_err_convert(type, code, &err);
/* Might be for an request_sock */
switch (sk->sk_state) {
case DCCP_REQUESTING:
case DCCP_RESPOND: /* Cannot happen.
It can, it SYNs are crossed. --ANK */
if (!sock_owned_by_user(sk)) {
__DCCP_INC_STATS(DCCP_MIB_ATTEMPTFAILS);
sk->sk_err = err;
/*
* Wake people up to see the error
* (see connect in sock.c)
*/
sk->sk_error_report(sk);
dccp_done(sk);
} else
sk->sk_err_soft = err;
goto out;
}
if (!sock_owned_by_user(sk) && np->recverr) {
sk->sk_err = err;
sk->sk_error_report(sk);
} else
sk->sk_err_soft = err;
out:
bh_unlock_sock(sk);
sock_put(sk);
return 0;
}
static struct sock *dccp_v6_request_recv_sock(struct sock *sk,
struct sk_buff *skb,
struct request_sock *req,
struct dst_entry *dst)
{
struct inet6_request_sock *ireq6 = inet6_rsk(req);
struct ipv6_pinfo *newnp, *np = inet6_sk(sk);
struct inet_sock *newinet;
struct dccp_sock *newdp;
struct dccp6_sock *newdp6;
struct sock *newsk;
struct ipv6_txoptions *opt;
if (skb->protocol == htons(ETH_P_IP)) {
/*
* v6 mapped
*/
newsk = dccp_v4_request_recv_sock(sk, skb, req, dst);
if (newsk == NULL)
return NULL;
newdp6 = (struct dccp6_sock *)newsk;
newdp = dccp_sk(newsk);
newinet = inet_sk(newsk);
newinet->pinet6 = &newdp6->inet6;
newnp = inet6_sk(newsk);
memcpy(newnp, np, sizeof(struct ipv6_pinfo));
ipv6_addr_set(&newnp->daddr, 0, 0, htonl(0x0000FFFF),
newinet->daddr);
ipv6_addr_set(&newnp->saddr, 0, 0, htonl(0x0000FFFF),
newinet->saddr);
ipv6_addr_copy(&newnp->rcv_saddr, &newnp->saddr);
inet_csk(newsk)->icsk_af_ops = &dccp_ipv6_mapped;
newsk->sk_backlog_rcv = dccp_v4_do_rcv;
newnp->pktoptions = NULL;
newnp->opt = NULL;
newnp->mcast_oif = inet6_iif(skb);
newnp->mcast_hops = ipv6_hdr(skb)->hop_limit;
/*
* No need to charge this sock to the relevant IPv6 refcnt debug socks count
* here, dccp_create_openreq_child now does this for us, see the comment in
* that function for the gory details. -acme
*/
/* It is tricky place. Until this moment IPv4 tcp
worked with IPv6 icsk.icsk_af_ops.
Sync it now.
*/
dccp_sync_mss(newsk, inet_csk(newsk)->icsk_pmtu_cookie);
return newsk;
}
opt = np->opt;
if (sk_acceptq_is_full(sk))
goto out_overflow;
if (dst == NULL) {
struct in6_addr *final_p = NULL, final;
struct flowi fl;
memset(&fl, 0, sizeof(fl));
fl.proto = IPPROTO_DCCP;
ipv6_addr_copy(&fl.fl6_dst, &ireq6->rmt_addr);
if (opt != NULL && opt->srcrt != NULL) {
const struct rt0_hdr *rt0 = (struct rt0_hdr *)opt->srcrt;
ipv6_addr_copy(&final, &fl.fl6_dst);
ipv6_addr_copy(&fl.fl6_dst, rt0->addr);
final_p = &final;
}
ipv6_addr_copy(&fl.fl6_src, &ireq6->loc_addr);
fl.oif = sk->sk_bound_dev_if;
fl.fl_ip_dport = inet_rsk(req)->rmt_port;
fl.fl_ip_sport = inet_rsk(req)->loc_port;
security_sk_classify_flow(sk, &fl);
if (ip6_dst_lookup(sk, &dst, &fl))
goto out;
if (final_p)
ipv6_addr_copy(&fl.fl6_dst, final_p);
if ((xfrm_lookup(sock_net(sk), &dst, &fl, sk, 0)) < 0)
goto out;
}
newsk = dccp_create_openreq_child(sk, req, skb);
if (newsk == NULL)
goto out;
/*
* No need to charge this sock to the relevant IPv6 refcnt debug socks
* count here, dccp_create_openreq_child now does this for us, see the
* comment in that function for the gory details. -acme
*/
__ip6_dst_store(newsk, dst, NULL, NULL);
newsk->sk_route_caps = dst->dev->features & ~(NETIF_F_IP_CSUM |
NETIF_F_TSO);
newdp6 = (struct dccp6_sock *)newsk;
newinet = inet_sk(newsk);
newinet->pinet6 = &newdp6->inet6;
newdp = dccp_sk(newsk);
newnp = inet6_sk(newsk);
memcpy(newnp, np, sizeof(struct ipv6_pinfo));
ipv6_addr_copy(&newnp->daddr, &ireq6->rmt_addr);
ipv6_addr_copy(&newnp->saddr, &ireq6->loc_addr);
ipv6_addr_copy(&newnp->rcv_saddr, &ireq6->loc_addr);
newsk->sk_bound_dev_if = ireq6->iif;
/* Now IPv6 options...
First: no IPv4 options.
*/
newinet->inet_opt = NULL;
/* Clone RX bits */
newnp->rxopt.all = np->rxopt.all;
/* Clone pktoptions received with SYN */
newnp->pktoptions = NULL;
if (ireq6->pktopts != NULL) {
newnp->pktoptions = skb_clone(ireq6->pktopts, GFP_ATOMIC);
kfree_skb(ireq6->pktopts);
ireq6->pktopts = NULL;
if (newnp->pktoptions)
skb_set_owner_r(newnp->pktoptions, newsk);
}
newnp->opt = NULL;
newnp->mcast_oif = inet6_iif(skb);
newnp->mcast_hops = ipv6_hdr(skb)->hop_limit;
/*
* Clone native IPv6 options from listening socket (if any)
*
* Yes, keeping reference count would be much more clever, but we make
* one more one thing there: reattach optmem to newsk.
*/
if (opt != NULL) {
newnp->opt = ipv6_dup_options(newsk, opt);
if (opt != np->opt)
sock_kfree_s(sk, opt, opt->tot_len);
}
inet_csk(newsk)->icsk_ext_hdr_len = 0;
if (newnp->opt != NULL)
inet_csk(newsk)->icsk_ext_hdr_len = (newnp->opt->opt_nflen +
newnp->opt->opt_flen);
dccp_sync_mss(newsk, dst_mtu(dst));
newinet->daddr = newinet->saddr = newinet->rcv_saddr = LOOPBACK4_IPV6;
__inet6_hash(newsk);
__inet_inherit_port(sk, newsk);
return newsk;
out_overflow:
NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_LISTENOVERFLOWS);
out:
NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_LISTENDROPS);
if (opt != NULL && opt != np->opt)
sock_kfree_s(sk, opt, opt->tot_len);
dst_release(dst);
return NULL;
}
int dccp_rcv_state_process(struct sock *sk, struct sk_buff *skb,
struct dccp_hdr *dh, unsigned len)
{
struct dccp_sock *dp = dccp_sk(sk);
struct dccp_skb_cb *dcb = DCCP_SKB_CB(skb);
const int old_state = sk->sk_state;
int queued = 0;
/*
* Step 3: Process LISTEN state
*
* If S.state == LISTEN,
* If P.type == Request or P contains a valid Init Cookie option,
* (* Must scan the packet's options to check for Init
* Cookies. Only Init Cookies are processed here,
* however; other options are processed in Step 8. This
* scan need only be performed if the endpoint uses Init
* Cookies *)
* (* Generate a new socket and switch to that socket *)
* Set S := new socket for this port pair
* S.state = RESPOND
* Choose S.ISS (initial seqno) or set from Init Cookies
* Initialize S.GAR := S.ISS
* Set S.ISR, S.GSR, S.SWL, S.SWH from packet or Init
* Cookies Continue with S.state == RESPOND
* (* A Response packet will be generated in Step 11 *)
* Otherwise,
* Generate Reset(No Connection) unless P.type == Reset
* Drop packet and return
*/
if (sk->sk_state == DCCP_LISTEN) {
if (dh->dccph_type == DCCP_PKT_REQUEST) {
if (inet_csk(sk)->icsk_af_ops->conn_request(sk,
skb) < 0)
return 1;
/* FIXME: do congestion control initialization */
goto discard;
}
if (dh->dccph_type == DCCP_PKT_RESET)
goto discard;
/* Caller (dccp_v4_do_rcv) will send Reset */
dcb->dccpd_reset_code = DCCP_RESET_CODE_NO_CONNECTION;
return 1;
}
if (sk->sk_state != DCCP_REQUESTING) {
if (dccp_check_seqno(sk, skb))
goto discard;
/*
* Step 8: Process options and mark acknowledgeable
*/
if (dccp_parse_options(sk, skb))
goto discard;
if (dcb->dccpd_ack_seq != DCCP_PKT_WITHOUT_ACK_SEQ)
dccp_event_ack_recv(sk, skb);
if (dccp_msk(sk)->dccpms_send_ack_vector &&
dccp_ackvec_add(dp->dccps_hc_rx_ackvec, sk,
DCCP_SKB_CB(skb)->dccpd_seq,
DCCP_ACKVEC_STATE_RECEIVED))
goto discard;
/* XXX see the comments in dccp_rcv_established about this */
if (dccp_sk(sk)->dccps_role == DCCP_ROLE_SERVER)
ccid_hc_rx_packet_recv(dp->dccps_hc_rx_ccid, sk, skb);
else
ccid_hc_tx_packet_recv(dp->dccps_hc_tx_ccid, sk, skb);
}
/*
* Step 9: Process Reset
* If P.type == Reset,
* Tear down connection
* S.state := TIMEWAIT
* Set TIMEWAIT timer
* Drop packet and return
*/
if (dh->dccph_type == DCCP_PKT_RESET) {
/*
* Queue the equivalent of TCP fin so that dccp_recvmsg
* exits the loop
*/
dccp_fin(sk, skb);
dccp_time_wait(sk, DCCP_TIME_WAIT, 0);
return 0;
/*
* Step 7: Check for unexpected packet types
* If (S.is_server and P.type == CloseReq)
* or (S.is_server and P.type == Response)
* or (S.is_client and P.type == Request)
* or (S.state == RESPOND and P.type == Data),
* Send Sync packet acknowledging P.seqno
* Drop packet and return
*/
} else if ((dp->dccps_role != DCCP_ROLE_CLIENT &&
(dh->dccph_type == DCCP_PKT_RESPONSE ||
dh->dccph_type == DCCP_PKT_CLOSEREQ)) ||
(dp->dccps_role == DCCP_ROLE_CLIENT &&
dh->dccph_type == DCCP_PKT_REQUEST) ||
(sk->sk_state == DCCP_RESPOND &&
dh->dccph_type == DCCP_PKT_DATA)) {
dccp_send_sync(sk, dcb->dccpd_seq, DCCP_PKT_SYNC);
goto discard;
} else if (dh->dccph_type == DCCP_PKT_CLOSEREQ) {
dccp_rcv_closereq(sk, skb);
goto discard;
} else if (dh->dccph_type == DCCP_PKT_CLOSE) {
dccp_rcv_close(sk, skb);
return 0;
}
if (unlikely(dh->dccph_type == DCCP_PKT_SYNC)) {
dccp_send_sync(sk, dcb->dccpd_seq, DCCP_PKT_SYNCACK);
goto discard;
}
switch (sk->sk_state) {
case DCCP_CLOSED:
dcb->dccpd_reset_code = DCCP_RESET_CODE_NO_CONNECTION;
return 1;
case DCCP_REQUESTING:
/* FIXME: do congestion control initialization */
queued = dccp_rcv_request_sent_state_process(sk, skb, dh, len);
if (queued >= 0)
return queued;
__kfree_skb(skb);
return 0;
case DCCP_RESPOND:
case DCCP_PARTOPEN:
queued = dccp_rcv_respond_partopen_state_process(sk, skb,
dh, len);
break;
}
if (dh->dccph_type == DCCP_PKT_ACK ||
dh->dccph_type == DCCP_PKT_DATAACK) {
switch (old_state) {
case DCCP_PARTOPEN:
sk->sk_state_change(sk);
sk_wake_async(sk, 0, POLL_OUT);
break;
}
}
if (!queued) {
discard:
__kfree_skb(skb);
}
return 0;
}
int dccp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
{
struct inet_sock *inet = inet_sk(sk);
struct dccp_sock *dp = dccp_sk(sk);
const struct sockaddr_in *usin = (struct sockaddr_in *)uaddr;
struct rtable *rt;
__be32 daddr, nexthop;
int tmp;
int err;
dp->dccps_role = DCCP_ROLE_CLIENT;
if (addr_len < sizeof(struct sockaddr_in))
return -EINVAL;
if (usin->sin_family != AF_INET)
return -EAFNOSUPPORT;
nexthop = daddr = usin->sin_addr.s_addr;
if (inet->opt != NULL && inet->opt->srr) {
if (daddr == 0)
return -EINVAL;
nexthop = inet->opt->faddr;
}
tmp = ip_route_connect(&rt, nexthop, inet->inet_saddr,
RT_CONN_FLAGS(sk), sk->sk_bound_dev_if,
IPPROTO_DCCP,
inet->inet_sport, usin->sin_port, sk, 1);
if (tmp < 0)
return tmp;
if (rt->rt_flags & (RTCF_MULTICAST | RTCF_BROADCAST)) {
ip_rt_put(rt);
return -ENETUNREACH;
}
if (inet->opt == NULL || !inet->opt->srr)
daddr = rt->rt_dst;
if (inet->inet_saddr == 0)
inet->inet_saddr = rt->rt_src;
inet->inet_rcv_saddr = inet->inet_saddr;
inet->inet_dport = usin->sin_port;
inet->inet_daddr = daddr;
inet_csk(sk)->icsk_ext_hdr_len = 0;
if (inet->opt != NULL)
inet_csk(sk)->icsk_ext_hdr_len = inet->opt->optlen;
/*
* Socket identity is still unknown (sport may be zero).
* However we set state to DCCP_REQUESTING and not releasing socket
* lock select source port, enter ourselves into the hash tables and
* complete initialization after this.
*/
dccp_set_state(sk, DCCP_REQUESTING);
err = inet_hash_connect(&dccp_death_row, sk);
if (err != 0)
goto failure;
err = ip_route_newports(&rt, IPPROTO_DCCP, inet->inet_sport,
inet->inet_dport, sk);
if (err != 0)
goto failure;
/* OK, now commit destination to socket. */
sk_setup_caps(sk, &rt->dst);
dp->dccps_iss = secure_dccp_sequence_number(inet->inet_saddr,
inet->inet_daddr,
inet->inet_sport,
inet->inet_dport);
inet->inet_id = dp->dccps_iss ^ jiffies;
err = dccp_connect(sk);
rt = NULL;
if (err != 0)
goto failure;
out:
return err;
failure:
/*
* This unhashes the socket and releases the local port, if necessary.
*/
dccp_set_state(sk, DCCP_CLOSED);
ip_rt_put(rt);
sk->sk_route_caps = 0;
inet->inet_dport = 0;
goto out;
}
static int threadfn(void *data)
{
struct socket *sock;
struct sockaddr_in addr;
int size,i;
char buf[bufsize+1];
if (sock_create_kern(AF_INET, SOCK_STREAM, IPPROTO_TCP, &sock) < 0) {
err("sock_create_kern");
goto out;
}
sock->sk->sk_reuse = 1;
memset(&addr, '\0', sizeof(addr));
addr.sin_family = AF_INET;
addr.sin_addr.s_addr = htonl(INADDR_ANY);
addr.sin_port = htons(9734);
if (kernel_bind(sock, &addr, sizeof(addr)) < 0) {
err("kernel_bind");
goto err;
}
if (kernel_listen(sock, 1024) < 0) {
err("kernel_listen");
goto err;
}
while (!kthread_should_stop()) {
struct socket *newsock;
struct inet_connection_sock *icsk = inet_csk(sock->sk);
struct socket_wq *wq;
rcu_read_lock();
wq = rcu_dereference(sock->sk->sk_wq);
wait_event_interruptible(wq->wait,!reqsk_queue_empty(&icsk->icsk_accept_queue) || kthread_should_stop());
if (!reqsk_queue_empty(&icsk->icsk_accept_queue)) {
if (kernel_accept(sock, &newsock, MSG_WAITALL) != 0) {
err("kernel_accept");
goto err;
}
printk(KERN_INFO "Server : accept a new connection request.\n");
// transfer_data(newsock);
memset(&buf, 0, bufsize+1);
size = receive(newsock, buf, bufsize/2);
printk(KERN_INFO "Server : received %d bytes\n", size);
//data processing
printk("Server : received data: %s\n", buf);
size = receive(newsock, buf, bufsize/2);
if (size < 0)
{
printk(KERN_INFO ": error getting datagram, sock_recvmsg error = %d\n", size);
break;
}
else
{
printk(KERN_INFO "Server : received %d bytes\n", size);
//data processing
printk("Server : received data: %s\n", buf);
for( i=0;i<bufsize/2;i++)
{
buf[i]+=1;
}
buf[i]=0 ;
// sending
//printk("buf=%s\n",buf);
size=send(newsock, buf, bufsize/2+1);
if(size<0)
printk("Server : error send\n");
}
//printk("ch =%c\n",ch);
sock_release(newsock);
}
}
err:
sock_release(sock);
out:
return 0;
}
/*
* All SKB's seen here are completely headerless. It is our
* job to build the DCCP header, and pass the packet down to
* IP so it can do the same plus pass the packet off to the
* device.
*/
static int dccp_transmit_skb(struct sock *sk, struct sk_buff *skb)
{
if (likely(skb != NULL)) {
const struct inet_sock *inet = inet_sk(sk);
const struct inet_connection_sock *icsk = inet_csk(sk);
struct dccp_sock *dp = dccp_sk(sk);
struct dccp_skb_cb *dcb = DCCP_SKB_CB(skb);
struct dccp_hdr *dh;
/* XXX For now we're using only 48 bits sequence numbers */
const u32 dccp_header_size = sizeof(*dh) +
sizeof(struct dccp_hdr_ext) +
dccp_packet_hdr_len(dcb->dccpd_type);
int err, set_ack = 1;
u64 ackno = dp->dccps_gsr;
dccp_inc_seqno(&dp->dccps_gss);
switch (dcb->dccpd_type) {
case DCCP_PKT_DATA:
set_ack = 0;
/* fall through */
case DCCP_PKT_DATAACK:
break;
case DCCP_PKT_REQUEST:
set_ack = 0;
/* fall through */
case DCCP_PKT_SYNC:
case DCCP_PKT_SYNCACK:
ackno = dcb->dccpd_seq;
/* fall through */
default:
/*
* Only data packets should come through with skb->sk
* set.
*/
WARN_ON(skb->sk);
skb_set_owner_w(skb, sk);
break;
}
dcb->dccpd_seq = dp->dccps_gss;
if (dccp_insert_options(sk, skb)) {
kfree_skb(skb);
return -EPROTO;
}
/* Build DCCP header and checksum it. */
dh = dccp_zeroed_hdr(skb, dccp_header_size);
dh->dccph_type = dcb->dccpd_type;
dh->dccph_sport = inet->sport;
dh->dccph_dport = inet->dport;
dh->dccph_doff = (dccp_header_size + dcb->dccpd_opt_len) / 4;
dh->dccph_ccval = dcb->dccpd_ccval;
dh->dccph_cscov = dp->dccps_pcslen;
/* XXX For now we're using only 48 bits sequence numbers */
dh->dccph_x = 1;
dp->dccps_awh = dp->dccps_gss;
dccp_hdr_set_seq(dh, dp->dccps_gss);
if (set_ack)
dccp_hdr_set_ack(dccp_hdr_ack_bits(skb), ackno);
switch (dcb->dccpd_type) {
case DCCP_PKT_REQUEST:
dccp_hdr_request(skb)->dccph_req_service =
dp->dccps_service;
break;
case DCCP_PKT_RESET:
dccp_hdr_reset(skb)->dccph_reset_code =
dcb->dccpd_reset_code;
break;
}
icsk->icsk_af_ops->send_check(sk, 0, skb);
if (set_ack)
dccp_event_ack_sent(sk);
DCCP_INC_STATS(DCCP_MIB_OUTSEGS);
memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt));
err = icsk->icsk_af_ops->queue_xmit(skb, 0);
return net_xmit_eval(err);
}
return -ENOBUFS;
}
int inet_sk_diag_fill(struct sock *sk, struct inet_connection_sock *icsk,
struct sk_buff *skb, 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);
struct inet_diag_msg *r;
struct nlmsghdr *nlh;
struct nlattr *attr;
void *info = NULL;
const struct inet_diag_handler *handler;
int ext = req->idiag_ext;
handler = inet_diag_table[req->sdiag_protocol];
BUG_ON(handler == NULL);
nlh = nlmsg_put(skb, portid, seq, unlh->nlmsg_type, sizeof(*r),
nlmsg_flags);
if (!nlh)
return -EMSGSIZE;
r = nlmsg_data(nlh);
BUG_ON(sk->sk_state == TCP_TIME_WAIT);
r->idiag_family = sk->sk_family;
r->idiag_state = sk->sk_state;
r->idiag_timer = 0;
r->idiag_retrans = 0;
r->id.idiag_if = sk->sk_bound_dev_if;
sock_diag_save_cookie(sk, r->id.idiag_cookie);
r->id.idiag_sport = inet->inet_sport;
r->id.idiag_dport = inet->inet_dport;
r->id.idiag_src[0] = inet->inet_rcv_saddr;
r->id.idiag_dst[0] = inet->inet_daddr;
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) {
const struct ipv6_pinfo *np = inet6_sk(sk);
*(struct in6_addr *)r->id.idiag_src = np->rcv_saddr;
*(struct in6_addr *)r->id.idiag_dst = np->daddr;
if (ext & (1 << (INET_DIAG_TCLASS - 1)))
if (nla_put_u8(skb, INET_DIAG_TCLASS, np->tclass) < 0)
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 == NULL) {
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) {
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))) {
attr = nla_reserve(skb, INET_DIAG_INFO,
sizeof(struct tcp_info));
if (!attr)
goto errout;
info = nla_data(attr);
}
if ((ext & (1 << (INET_DIAG_CONG - 1))) && icsk->icsk_ca_ops)
if (nla_put_string(skb, INET_DIAG_CONG,
icsk->icsk_ca_ops->name) < 0)
goto errout;
handler->idiag_get_info(sk, r, info);
if (sk->sk_state < TCP_TIME_WAIT &&
icsk->icsk_ca_ops && icsk->icsk_ca_ops->get_info)
icsk->icsk_ca_ops->get_info(sk, ext, skb);
out:
return nlmsg_end(skb, nlh);
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, 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 inet_timewait_sock *tw,
struct sk_buff *skb, struct inet_diag_req_v2 *req,
u32 portid, u32 seq, u16 nlmsg_flags,
const struct nlmsghdr *unlh)
{
long tmo;
struct inet_diag_msg *r;
struct nlmsghdr *nlh;
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_ttd - jiffies;
if (tmo < 0)
tmo = 0;
r->idiag_family = tw->tw_family;
r->idiag_retrans = 0;
r->id.idiag_if = tw->tw_bound_dev_if;
sock_diag_save_cookie(tw, r->id.idiag_cookie);
r->id.idiag_sport = tw->tw_sport;
r->id.idiag_dport = tw->tw_dport;
r->id.idiag_src[0] = tw->tw_rcv_saddr;
r->id.idiag_dst[0] = tw->tw_daddr;
r->idiag_state = tw->tw_substate;
r->idiag_timer = 3;
r->idiag_expires = DIV_ROUND_UP(tmo * 1000, HZ);
r->idiag_rqueue = 0;
r->idiag_wqueue = 0;
r->idiag_uid = 0;
r->idiag_inode = 0;
#if IS_ENABLED(CONFIG_IPV6)
if (tw->tw_family == AF_INET6) {
const struct inet6_timewait_sock *tw6 =
inet6_twsk((struct sock *)tw);
*(struct in6_addr *)r->id.idiag_src = tw6->tw_v6_rcv_saddr;
*(struct in6_addr *)r->id.idiag_dst = tw6->tw_v6_daddr;
}
#endif
return nlmsg_end(skb, nlh);
}
//start_listening
void moon_listen(void)
{
//For test purposes
moonraker_socket_t *listen;
listen = kmalloc(sizeof(moonraker_socket_t),GFP_KERNEL);
listen->proto = kmalloc(sizeof(moonraker_proto_t),GFP_KERNEL);
listen->proto->name = kmalloc(5,GFP_KERNEL);
listen->ip = 2130706433;
listen->port = 80;
listen->proto->defer_accept=0;
listen->keepalive_timeout=0;
listen->ack_pingpong=1;
listen->max_backlog=2048;
listen->defer_accept=1;
strcpy(listen->proto->name,"http");
//end for test purpose
struct sockaddr_in sin;
struct socket *sock = NULL;
struct sock *sk;
struct tcp_sock *tp;
struct inet_connection_sock *icsk;
moonraker_proto_t *proto = listen->proto;
u16 port = listen->port;
u32 addr = listen->ip; //127.0.0.1
int err = 0;
err = sock_create_kern(PF_INET, SOCK_STREAM, IPPROTO_TCP, &sock);
if (err) {
printk(KERN_ERR "Moonraker: error %d creating socket.\n", err);
goto error;
}
sin.sin_family = AF_INET;
sin.sin_addr.s_addr = htonl(addr);
sin.sin_port = htons(port);
sk = sock->sk;
icsk = inet_csk(sk);
sk->sk_reuse = 1;
sock_set_flag(sk, SOCK_URGINLINE);
err = sock->ops->bind(sock, (struct sockaddr*)&sin, sizeof(sin));
if (err){
printk(KERN_ERR "Moonraker: error %d binding socket. This means that probably some other process is (or was a short time ago) using addr %d\n",err,sin.sin_addr.s_addr);
goto error;
}
tp = tcp_sk(sk);
printk("listen sk accept_queue: %d.\n",!reqsk_queue_empty(&icsk->icsk_accept_queue));
icsk->icsk_ack.pingpong = listen->ack_pingpong;
sock_reset_flag(sk, SOCK_LINGER);
sk->sk_lingertime = 0;
tp->linger2 = listen->keepalive_timeout * HZ;
if (proto->defer_accept && !listen->keepalive_timeout && listen->defer_accept)
icsk->icsk_accept_queue.rskq_defer_accept = 1;
err = sock->ops->listen(sock, listen->max_backlog);
if (err) {
printk(KERN_ERR "Moonraker: error %d listening on socket.\n", err);
goto error;
}
printk(KERN_NOTICE "Moonraker: thread %d listens on %s://%d.%d.%d.%d:%d.\n",
1, proto->name, HIPQUAD(addr), port);
// return sock;
return;
error:
if (sock)
sock_release(sock);
return;
return NULL;
}
static void ctcp_set_state(struct sock *sk, u8 new_state)
{
inet_csk(sk)->icsk_ca_state = TCP_CA_Open;
}
static bool tcp_fastopen_create_child(struct sock *sk,
struct sk_buff *skb,
struct dst_entry *dst,
struct request_sock *req)
{
struct tcp_sock *tp = tcp_sk(sk);
struct request_sock_queue *queue = &inet_csk(sk)->icsk_accept_queue;
struct sock *child;
req->num_retrans = 0;
req->num_timeout = 0;
req->sk = NULL;
child = inet_csk(sk)->icsk_af_ops->syn_recv_sock(sk, skb, req, NULL);
if (child == NULL)
return false;
spin_lock(&queue->fastopenq->lock);
queue->fastopenq->qlen++;
spin_unlock(&queue->fastopenq->lock);
/* Initialize the child socket. Have to fix some values to take
* into account the child is a Fast Open socket and is created
* only out of the bits carried in the SYN packet.
*/
tp = tcp_sk(child);
tp->fastopen_rsk = req;
/* Do a hold on the listner sk so that if the listener is being
* closed, the child that has been accepted can live on and still
* access listen_lock.
*/
sock_hold(sk);
tcp_rsk(req)->listener = sk;
/* RFC1323: The window in SYN & SYN/ACK segments is never
* scaled. So correct it appropriately.
*/
tp->snd_wnd = ntohs(tcp_hdr(skb)->window);
/* Activate the retrans timer so that SYNACK can be retransmitted.
* The request socket is not added to the SYN table of the parent
* because it's been added to the accept queue directly.
*/
inet_csk_reset_xmit_timer(child, ICSK_TIME_RETRANS,
TCP_TIMEOUT_INIT, TCP_RTO_MAX);
/* Add the child socket directly into the accept queue */
inet_csk_reqsk_queue_add(sk, req, child);
/* Now finish processing the fastopen child socket. */
inet_csk(child)->icsk_af_ops->rebuild_header(child);
tcp_init_congestion_control(child);
tcp_mtup_init(child);
tcp_init_metrics(child);
tcp_init_buffer_space(child);
/* Queue the data carried in the SYN packet. We need to first
* bump skb's refcnt because the caller will attempt to free it.
*
* XXX (TFO) - we honor a zero-payload TFO request for now,
* (any reason not to?) but no need to queue the skb since
* there is no data. How about SYN+FIN?
*/
if (TCP_SKB_CB(skb)->end_seq != TCP_SKB_CB(skb)->seq + 1) {
skb = skb_get(skb);
skb_dst_drop(skb);
__skb_pull(skb, tcp_hdr(skb)->doff * 4);
skb_set_owner_r(skb, child);
__skb_queue_tail(&child->sk_receive_queue, skb);
tp->syn_data_acked = 1;
}
tcp_rsk(req)->rcv_nxt = tp->rcv_nxt = TCP_SKB_CB(skb)->end_seq;
sk->sk_data_ready(sk, 0);
bh_unlock_sock(child);
sock_put(child);
WARN_ON(req->sk == NULL);
return true;
}
/*
* All SKB's seen here are completely headerless. It is our
* job to build the DCCP header, and pass the packet down to
* IP so it can do the same plus pass the packet off to the
* device.
*/
static int dccp_transmit_skb(struct sock *sk, struct sk_buff *skb)
{
if (likely(skb != NULL)) {
const struct inet_sock *inet = inet_sk(sk);
const struct inet_connection_sock *icsk = inet_csk(sk);
struct dccp_sock *dp = dccp_sk(sk);
struct dccp_skb_cb *dcb = DCCP_SKB_CB(skb);
struct dccp_hdr *dh;
/* XXX For now we're using only 48 bits sequence numbers */
const u32 dccp_header_size = sizeof(*dh) +
sizeof(struct dccp_hdr_ext) +
dccp_packet_hdr_len(dcb->dccpd_type);
int err, set_ack = 1;
u64 ackno = dp->dccps_gsr;
dccp_inc_seqno(&dp->dccps_gss);
switch (dcb->dccpd_type) {
case DCCP_PKT_DATA:
set_ack = 0;
/* fall through */
case DCCP_PKT_DATAACK:
break;
case DCCP_PKT_REQUEST:
set_ack = 0;
/* fall through */
case DCCP_PKT_SYNC:
case DCCP_PKT_SYNCACK:
ackno = dcb->dccpd_seq;
/* fall through */
default:
/*
* Only data packets should come through with skb->sk
* set.
*/
WARN_ON(skb->sk);
skb_set_owner_w(skb, sk);
break;
}
dcb->dccpd_seq = dp->dccps_gss;
if (dccp_insert_options(sk, skb)) {
kfree_skb(skb);
return -EPROTO;
}
skb->h.raw = skb_push(skb, dccp_header_size);
dh = dccp_hdr(skb);
/* Build DCCP header and checksum it. */
memset(dh, 0, dccp_header_size);
dh->dccph_type = dcb->dccpd_type;
dh->dccph_sport = inet->sport;
dh->dccph_dport = inet->dport;
dh->dccph_doff = (dccp_header_size + dcb->dccpd_opt_len) / 4;
dh->dccph_ccval = dcb->dccpd_ccval;
/* XXX For now we're using only 48 bits sequence numbers */
dh->dccph_x = 1;
dp->dccps_awh = dp->dccps_gss;
dccp_hdr_set_seq(dh, dp->dccps_gss);
if (set_ack)
dccp_hdr_set_ack(dccp_hdr_ack_bits(skb), ackno);
switch (dcb->dccpd_type) {
case DCCP_PKT_REQUEST:
dccp_hdr_request(skb)->dccph_req_service =
dp->dccps_service;
break;
case DCCP_PKT_RESET:
dccp_hdr_reset(skb)->dccph_reset_code =
dcb->dccpd_reset_code;
break;
}
icsk->icsk_af_ops->send_check(sk, skb->len, skb);
if (set_ack)
dccp_event_ack_sent(sk);
DCCP_INC_STATS(DCCP_MIB_OUTSEGS);
memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt));
err = icsk->icsk_af_ops->queue_xmit(skb, 0);
if (err <= 0)
return err;
/* NET_XMIT_CN is special. It does not guarantee,
* that this packet is lost. It tells that device
* is about to start to drop packets or already
* drops some packets of the same priority and
* invokes us to send less aggressively.
*/
return err == NET_XMIT_CN ? 0 : err;
}
return -ENOBUFS;
}
int dccp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
{
struct inet_sock *inet = inet_sk(sk);
struct dccp_sock *dp = dccp_sk(sk);
const struct sockaddr_in *usin = (struct sockaddr_in *)uaddr;
struct rtable *rt;
__be32 daddr, nexthop;
int tmp;
int err;
dp->dccps_role = DCCP_ROLE_CLIENT;
if (addr_len < sizeof(struct sockaddr_in))
return -EINVAL;
if (usin->sin_family != AF_INET)
return -EAFNOSUPPORT;
nexthop = daddr = usin->sin_addr.s_addr;
if (inet->opt != NULL && inet->opt->srr) {
if (daddr == 0)
return -EINVAL;
nexthop = inet->opt->faddr;
}
tmp = ip_route_connect(&rt, nexthop, inet->saddr,
RT_CONN_FLAGS(sk), sk->sk_bound_dev_if,
IPPROTO_DCCP,
inet->sport, usin->sin_port, sk, 1);
if (tmp < 0)
return tmp;
if (rt->rt_flags & (RTCF_MULTICAST | RTCF_BROADCAST)) {
ip_rt_put(rt);
return -ENETUNREACH;
}
if (inet->opt == NULL || !inet->opt->srr)
daddr = rt->rt_dst;
if (inet->saddr == 0)
inet->saddr = rt->rt_src;
inet->rcv_saddr = inet->saddr;
inet->dport = usin->sin_port;
inet->daddr = daddr;
inet_csk(sk)->icsk_ext_hdr_len = 0;
if (inet->opt != NULL)
inet_csk(sk)->icsk_ext_hdr_len = inet->opt->optlen;
dccp_set_state(sk, DCCP_REQUESTING);
err = inet_hash_connect(&dccp_death_row, sk);
if (err != 0)
goto failure;
err = ip_route_newports(&rt, IPPROTO_DCCP, inet->sport, inet->dport,
sk);
if (err != 0)
goto failure;
sk_setup_caps(sk, &rt->u.dst);
dp->dccps_iss = secure_dccp_sequence_number(inet->saddr, inet->daddr,
inet->sport, inet->dport);
inet->id = dp->dccps_iss ^ jiffies;
err = dccp_connect(sk);
rt = NULL;
if (err != 0)
goto failure;
out:
return err;
failure:
dccp_set_state(sk, DCCP_CLOSED);
ip_rt_put(rt);
sk->sk_route_caps = 0;
inet->dport = 0;
goto out;
}
static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
int addr_len)
{
struct sockaddr_in6 *usin = (struct sockaddr_in6 *) uaddr;
struct inet_sock *inet = inet_sk(sk);
struct inet_connection_sock *icsk = inet_csk(sk);
struct ipv6_pinfo *np = inet6_sk(sk);
struct tcp_sock *tp = tcp_sk(sk);
struct in6_addr *saddr = NULL, *final_p, final;
struct rt6_info *rt;
struct flowi6 fl6;
struct dst_entry *dst;
int addr_type;
int err;
if (addr_len < SIN6_LEN_RFC2133)
return -EINVAL;
if (usin->sin6_family != AF_INET6)
return -EAFNOSUPPORT;
memset(&fl6, 0, sizeof(fl6));
if (np->sndflow) {
fl6.flowlabel = usin->sin6_flowinfo&IPV6_FLOWINFO_MASK;
IP6_ECN_flow_init(fl6.flowlabel);
if (fl6.flowlabel&IPV6_FLOWLABEL_MASK) {
struct ip6_flowlabel *flowlabel;
flowlabel = fl6_sock_lookup(sk, fl6.flowlabel);
if (flowlabel == NULL)
return -EINVAL;
usin->sin6_addr = flowlabel->dst;
fl6_sock_release(flowlabel);
}
}
if(ipv6_addr_any(&usin->sin6_addr))
usin->sin6_addr.s6_addr[15] = 0x1;
addr_type = ipv6_addr_type(&usin->sin6_addr);
if(addr_type & IPV6_ADDR_MULTICAST)
return -ENETUNREACH;
if (addr_type&IPV6_ADDR_LINKLOCAL) {
if (addr_len >= sizeof(struct sockaddr_in6) &&
usin->sin6_scope_id) {
if (sk->sk_bound_dev_if &&
sk->sk_bound_dev_if != usin->sin6_scope_id)
return -EINVAL;
sk->sk_bound_dev_if = usin->sin6_scope_id;
}
if (!sk->sk_bound_dev_if)
return -EINVAL;
}
if (tp->rx_opt.ts_recent_stamp &&
!ipv6_addr_equal(&np->daddr, &usin->sin6_addr)) {
tp->rx_opt.ts_recent = 0;
tp->rx_opt.ts_recent_stamp = 0;
tp->write_seq = 0;
}
np->daddr = usin->sin6_addr;
np->flow_label = fl6.flowlabel;
if (addr_type == IPV6_ADDR_MAPPED) {
u32 exthdrlen = icsk->icsk_ext_hdr_len;
struct sockaddr_in sin;
SOCK_DEBUG(sk, "connect: ipv4 mapped\n");
if (__ipv6_only_sock(sk))
return -ENETUNREACH;
sin.sin_family = AF_INET;
sin.sin_port = usin->sin6_port;
sin.sin_addr.s_addr = usin->sin6_addr.s6_addr32[3];
icsk->icsk_af_ops = &ipv6_mapped;
sk->sk_backlog_rcv = tcp_v4_do_rcv;
#ifdef CONFIG_TCP_MD5SIG
tp->af_specific = &tcp_sock_ipv6_mapped_specific;
#endif
err = tcp_v4_connect(sk, (struct sockaddr *)&sin, sizeof(sin));
if (err) {
icsk->icsk_ext_hdr_len = exthdrlen;
icsk->icsk_af_ops = &ipv6_specific;
sk->sk_backlog_rcv = tcp_v6_do_rcv;
#ifdef CONFIG_TCP_MD5SIG
tp->af_specific = &tcp_sock_ipv6_specific;
#endif
goto failure;
} else {
ipv6_addr_set_v4mapped(inet->inet_saddr, &np->saddr);
ipv6_addr_set_v4mapped(inet->inet_rcv_saddr,
&np->rcv_saddr);
}
return err;
}
if (!ipv6_addr_any(&np->rcv_saddr))
saddr = &np->rcv_saddr;
fl6.flowi6_proto = IPPROTO_TCP;
fl6.daddr = np->daddr;
fl6.saddr = saddr ? *saddr : np->saddr;
fl6.flowi6_oif = sk->sk_bound_dev_if;
fl6.flowi6_mark = sk->sk_mark;
fl6.fl6_dport = usin->sin6_port;
fl6.fl6_sport = inet->inet_sport;
final_p = fl6_update_dst(&fl6, np->opt, &final);
security_sk_classify_flow(sk, flowi6_to_flowi(&fl6));
dst = ip6_dst_lookup_flow(sk, &fl6, final_p, true);
if (IS_ERR(dst)) {
err = PTR_ERR(dst);
goto failure;
}
if (saddr == NULL) {
saddr = &fl6.saddr;
np->rcv_saddr = *saddr;
}
np->saddr = *saddr;
inet->inet_rcv_saddr = LOOPBACK4_IPV6;
sk->sk_gso_type = SKB_GSO_TCPV6;
__ip6_dst_store(sk, dst, NULL, NULL);
rt = (struct rt6_info *) dst;
if (tcp_death_row.sysctl_tw_recycle &&
!tp->rx_opt.ts_recent_stamp &&
ipv6_addr_equal(&rt->rt6i_dst.addr, &np->daddr)) {
struct inet_peer *peer = rt6_get_peer(rt);
if (peer) {
inet_peer_refcheck(peer);
if ((u32)get_seconds() - peer->tcp_ts_stamp <= TCP_PAWS_MSL) {
tp->rx_opt.ts_recent_stamp = peer->tcp_ts_stamp;
tp->rx_opt.ts_recent = peer->tcp_ts;
}
}
}
icsk->icsk_ext_hdr_len = 0;
if (np->opt)
icsk->icsk_ext_hdr_len = (np->opt->opt_flen +
np->opt->opt_nflen);
tp->rx_opt.mss_clamp = IPV6_MIN_MTU - sizeof(struct tcphdr) - sizeof(struct ipv6hdr);
inet->inet_dport = usin->sin6_port;
tcp_set_state(sk, TCP_SYN_SENT);
err = inet6_hash_connect(&tcp_death_row, sk);
if (err)
goto late_failure;
if (!tp->write_seq)
tp->write_seq = secure_tcpv6_sequence_number(np->saddr.s6_addr32,
np->daddr.s6_addr32,
inet->inet_sport,
inet->inet_dport);
err = tcp_connect(sk);
if (err)
goto late_failure;
return 0;
late_failure:
tcp_set_state(sk, TCP_CLOSE);
__sk_dst_reset(sk);
failure:
inet->inet_dport = 0;
sk->sk_route_caps = 0;
return err;
}
static int dccp_rcv_request_sent_state_process(struct sock *sk,
struct sk_buff *skb,
const struct dccp_hdr *dh,
const unsigned len)
{
/*
* Step 4: Prepare sequence numbers in REQUEST
* If S.state == REQUEST,
* If (P.type == Response or P.type == Reset)
* and S.AWL <= P.ackno <= S.AWH,
* / * Set sequence number variables corresponding to the
* other endpoint, so P will pass the tests in Step 6 * /
* Set S.GSR, S.ISR, S.SWL, S.SWH
* / * Response processing continues in Step 10; Reset
* processing continues in Step 9 * /
*/
if (dh->dccph_type == DCCP_PKT_RESPONSE) {
const struct inet_connection_sock *icsk = inet_csk(sk);
struct dccp_sock *dp = dccp_sk(sk);
/* Stop the REQUEST timer */
inet_csk_clear_xmit_timer(sk, ICSK_TIME_RETRANS);
BUG_TRAP(sk->sk_send_head != NULL);
__kfree_skb(sk->sk_send_head);
sk->sk_send_head = NULL;
if (!between48(DCCP_SKB_CB(skb)->dccpd_ack_seq,
dp->dccps_awl, dp->dccps_awh)) {
dccp_pr_debug("invalid ackno: S.AWL=%llu, "
"P.ackno=%llu, S.AWH=%llu \n",
(unsigned long long)dp->dccps_awl,
(unsigned long long)DCCP_SKB_CB(skb)->dccpd_ack_seq,
(unsigned long long)dp->dccps_awh);
goto out_invalid_packet;
}
if (dccp_parse_options(sk, skb))
goto out_invalid_packet;
if (dccp_msk(sk)->dccpms_send_ack_vector &&
dccp_ackvec_add(dp->dccps_hc_rx_ackvec, sk,
DCCP_SKB_CB(skb)->dccpd_seq,
DCCP_ACKVEC_STATE_RECEIVED))
goto out_invalid_packet; /* FIXME: change error code */
dp->dccps_isr = DCCP_SKB_CB(skb)->dccpd_seq;
dccp_update_gsr(sk, dp->dccps_isr);
/*
* SWL and AWL are initially adjusted so that they are not less than
* the initial Sequence Numbers received and sent, respectively:
* SWL := max(GSR + 1 - floor(W/4), ISR),
* AWL := max(GSS - W' + 1, ISS).
* These adjustments MUST be applied only at the beginning of the
* connection.
*
* AWL was adjusted in dccp_v4_connect -acme
*/
dccp_set_seqno(&dp->dccps_swl,
max48(dp->dccps_swl, dp->dccps_isr));
dccp_sync_mss(sk, icsk->icsk_pmtu_cookie);
/*
* Step 10: Process REQUEST state (second part)
* If S.state == REQUEST,
* / * If we get here, P is a valid Response from the
* server (see Step 4), and we should move to
* PARTOPEN state. PARTOPEN means send an Ack,
* don't send Data packets, retransmit Acks
* periodically, and always include any Init Cookie
* from the Response * /
* S.state := PARTOPEN
* Set PARTOPEN timer
* Continue with S.state == PARTOPEN
* / * Step 12 will send the Ack completing the
* three-way handshake * /
*/
dccp_set_state(sk, DCCP_PARTOPEN);
/* Make sure socket is routed, for correct metrics. */
icsk->icsk_af_ops->rebuild_header(sk);
if (!sock_flag(sk, SOCK_DEAD)) {
sk->sk_state_change(sk);
sk_wake_async(sk, 0, POLL_OUT);
}
if (sk->sk_write_pending || icsk->icsk_ack.pingpong ||
icsk->icsk_accept_queue.rskq_defer_accept) {
/* Save one ACK. Data will be ready after
* several ticks, if write_pending is set.
*
* It may be deleted, but with this feature tcpdumps
* look so _wonderfully_ clever, that I was not able
* to stand against the temptation 8) --ANK
*/
/*
* OK, in DCCP we can as well do a similar trick, its
* even in the draft, but there is no need for us to
* schedule an ack here, as dccp_sendmsg does this for
* us, also stated in the draft. -acme
*/
__kfree_skb(skb);
return 0;
}
dccp_send_ack(sk);
return -1;
}
out_invalid_packet:
/* dccp_v4_do_rcv will send a reset */
DCCP_SKB_CB(skb)->dccpd_reset_code = DCCP_RESET_CODE_PACKET_ERROR;
return 1;
}
static void tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
u8 type, u8 code, int offset, __be32 info)
{
const struct ipv6hdr *hdr = (const struct ipv6hdr*)skb->data;
const struct tcphdr *th = (struct tcphdr *)(skb->data+offset);
struct ipv6_pinfo *np;
struct sock *sk;
int err;
struct tcp_sock *tp;
__u32 seq;
struct net *net = dev_net(skb->dev);
sk = inet6_lookup(net, &tcp_hashinfo, &hdr->daddr,
th->dest, &hdr->saddr, th->source, skb->dev->ifindex);
if (sk == NULL) {
ICMP6_INC_STATS_BH(net, __in6_dev_get(skb->dev),
ICMP6_MIB_INERRORS);
return;
}
if (sk->sk_state == TCP_TIME_WAIT) {
inet_twsk_put(inet_twsk(sk));
return;
}
bh_lock_sock(sk);
if (sock_owned_by_user(sk))
NET_INC_STATS_BH(net, LINUX_MIB_LOCKDROPPEDICMPS);
if (sk->sk_state == TCP_CLOSE)
goto out;
if (ipv6_hdr(skb)->hop_limit < inet6_sk(sk)->min_hopcount) {
NET_INC_STATS_BH(net, LINUX_MIB_TCPMINTTLDROP);
goto out;
}
tp = tcp_sk(sk);
seq = ntohl(th->seq);
if (sk->sk_state != TCP_LISTEN &&
!between(seq, tp->snd_una, tp->snd_nxt)) {
NET_INC_STATS_BH(net, LINUX_MIB_OUTOFWINDOWICMPS);
goto out;
}
np = inet6_sk(sk);
if (type == ICMPV6_PKT_TOOBIG) {
struct dst_entry *dst;
if (sock_owned_by_user(sk))
goto out;
if ((1 << sk->sk_state) & (TCPF_LISTEN | TCPF_CLOSE))
goto out;
dst = __sk_dst_check(sk, np->dst_cookie);
if (dst == NULL) {
struct inet_sock *inet = inet_sk(sk);
struct flowi6 fl6;
memset(&fl6, 0, sizeof(fl6));
fl6.flowi6_proto = IPPROTO_TCP;
fl6.daddr = np->daddr;
fl6.saddr = np->saddr;
fl6.flowi6_oif = sk->sk_bound_dev_if;
fl6.flowi6_mark = sk->sk_mark;
fl6.fl6_dport = inet->inet_dport;
fl6.fl6_sport = inet->inet_sport;
security_skb_classify_flow(skb, flowi6_to_flowi(&fl6));
dst = ip6_dst_lookup_flow(sk, &fl6, NULL, false);
if (IS_ERR(dst)) {
sk->sk_err_soft = -PTR_ERR(dst);
goto out;
}
} else
dst_hold(dst);
if (inet_csk(sk)->icsk_pmtu_cookie > dst_mtu(dst)) {
tcp_sync_mss(sk, dst_mtu(dst));
tcp_simple_retransmit(sk);
}
dst_release(dst);
goto out;
}
icmpv6_err_convert(type, code, &err);
switch (sk->sk_state) {
struct request_sock *req, **prev;
case TCP_LISTEN:
if (sock_owned_by_user(sk))
goto out;
req = inet6_csk_search_req(sk, &prev, th->dest, &hdr->daddr,
&hdr->saddr, inet6_iif(skb));
if (!req)
goto out;
WARN_ON(req->sk != NULL);
if (seq != tcp_rsk(req)->snt_isn) {
NET_INC_STATS_BH(net, LINUX_MIB_OUTOFWINDOWICMPS);
goto out;
}
inet_csk_reqsk_queue_drop(sk, req, prev);
goto out;
case TCP_SYN_SENT:
case TCP_SYN_RECV:
if (!sock_owned_by_user(sk)) {
sk->sk_err = err;
sk->sk_error_report(sk);
tcp_done(sk);
} else
sk->sk_err_soft = err;
goto out;
}
if (!sock_owned_by_user(sk) && np->recverr) {
sk->sk_err = err;
sk->sk_error_report(sk);
} else
sk->sk_err_soft = err;
out:
bh_unlock_sock(sk);
sock_put(sk);
}
static int do_ip_setsockopt(struct sock *sk, int level,
int optname, char __user *optval, unsigned int optlen)
{
struct inet_sock *inet = inet_sk(sk);
int val = 0, err;
switch (optname) {
case IP_PKTINFO:
case IP_RECVTTL:
case IP_RECVOPTS:
case IP_RECVTOS:
case IP_RETOPTS:
case IP_TOS:
case IP_TTL:
case IP_HDRINCL:
case IP_MTU_DISCOVER:
case IP_RECVERR:
case IP_ROUTER_ALERT:
case IP_FREEBIND:
case IP_PASSSEC:
case IP_TRANSPARENT:
case IP_MINTTL:
case IP_NODEFRAG:
case IP_MULTICAST_TTL:
case IP_MULTICAST_ALL:
case IP_MULTICAST_LOOP:
case IP_RECVORIGDSTADDR:
if (optlen >= sizeof(int)) {
if (get_user(val, (int __user *) optval))
return -EFAULT;
} else if (optlen >= sizeof(char)) {
unsigned char ucval;
if (get_user(ucval, (unsigned char __user *) optval))
return -EFAULT;
val = (int) ucval;
}
}
/* If optlen==0, it is equivalent to val == 0 */
if (ip_mroute_opt(optname))
return ip_mroute_setsockopt(sk, optname, optval, optlen);
err = 0;
lock_sock(sk);
switch (optname) {
case IP_OPTIONS:
{
struct ip_options_rcu *old, *opt = NULL;
if (optlen > 40)
goto e_inval;
err = ip_options_get_from_user(sock_net(sk), &opt,
optval, optlen);
if (err)
break;
old = rcu_dereference_protected(inet->inet_opt,
sock_owned_by_user(sk));
if (inet->is_icsk) {
struct inet_connection_sock *icsk = inet_csk(sk);
#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
if (sk->sk_family == PF_INET ||
(!((1 << sk->sk_state) &
(TCPF_LISTEN | TCPF_CLOSE)) &&
inet->inet_daddr != LOOPBACK4_IPV6)) {
#endif
if (old)
icsk->icsk_ext_hdr_len -= old->opt.optlen;
if (opt)
icsk->icsk_ext_hdr_len += opt->opt.optlen;
icsk->icsk_sync_mss(sk, icsk->icsk_pmtu_cookie);
#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
}
#endif
}
rcu_assign_pointer(inet->inet_opt, opt);
if (old)
call_rcu(&old->rcu, opt_kfree_rcu);
break;
}
case IP_PKTINFO:
if (val)
inet->cmsg_flags |= IP_CMSG_PKTINFO;
else
inet->cmsg_flags &= ~IP_CMSG_PKTINFO;
break;
case IP_RECVTTL:
if (val)
inet->cmsg_flags |= IP_CMSG_TTL;
else
inet->cmsg_flags &= ~IP_CMSG_TTL;
break;
case IP_RECVTOS:
if (val)
inet->cmsg_flags |= IP_CMSG_TOS;
else
inet->cmsg_flags &= ~IP_CMSG_TOS;
break;
case IP_RECVOPTS:
if (val)
inet->cmsg_flags |= IP_CMSG_RECVOPTS;
else
inet->cmsg_flags &= ~IP_CMSG_RECVOPTS;
break;
case IP_RETOPTS:
if (val)
inet->cmsg_flags |= IP_CMSG_RETOPTS;
else
inet->cmsg_flags &= ~IP_CMSG_RETOPTS;
break;
case IP_PASSSEC:
if (val)
inet->cmsg_flags |= IP_CMSG_PASSSEC;
else
inet->cmsg_flags &= ~IP_CMSG_PASSSEC;
break;
case IP_RECVORIGDSTADDR:
if (val)
inet->cmsg_flags |= IP_CMSG_ORIGDSTADDR;
else
inet->cmsg_flags &= ~IP_CMSG_ORIGDSTADDR;
break;
case IP_TOS: /* This sets both TOS and Precedence */
if (sk->sk_type == SOCK_STREAM) {
val &= ~INET_ECN_MASK;
val |= inet->tos & INET_ECN_MASK;
}
if (inet->tos != val) {
inet->tos = val;
sk->sk_priority = rt_tos2priority(val);
sk_dst_reset(sk);
}
break;
case IP_TTL:
if (optlen < 1)
goto e_inval;
if (val != -1 && (val < 1 || val > 255))
goto e_inval;
inet->uc_ttl = val;
break;
case IP_HDRINCL:
if (sk->sk_type != SOCK_RAW) {
err = -ENOPROTOOPT;
break;
}
inet->hdrincl = val ? 1 : 0;
break;
case IP_NODEFRAG:
if (sk->sk_type != SOCK_RAW) {
err = -ENOPROTOOPT;
break;
}
inet->nodefrag = val ? 1 : 0;
break;
case IP_MTU_DISCOVER:
if (val < IP_PMTUDISC_DONT || val > IP_PMTUDISC_PROBE)
goto e_inval;
inet->pmtudisc = val;
break;
case IP_RECVERR:
inet->recverr = !!val;
if (!val)
skb_queue_purge(&sk->sk_error_queue);
break;
case IP_MULTICAST_TTL:
if (sk->sk_type == SOCK_STREAM)
goto e_inval;
if (optlen < 1)
goto e_inval;
if (val == -1)
val = 1;
if (val < 0 || val > 255)
goto e_inval;
inet->mc_ttl = val;
break;
case IP_MULTICAST_LOOP:
if (optlen < 1)
goto e_inval;
inet->mc_loop = !!val;
break;
case IP_MULTICAST_IF:
{
struct ip_mreqn mreq;
struct net_device *dev = NULL;
if (sk->sk_type == SOCK_STREAM)
goto e_inval;
/*
* Check the arguments are allowable
*/
if (optlen < sizeof(struct in_addr))
goto e_inval;
err = -EFAULT;
if (optlen >= sizeof(struct ip_mreqn)) {
if (copy_from_user(&mreq, optval, sizeof(mreq)))
break;
} else {
memset(&mreq, 0, sizeof(mreq));
if (optlen >= sizeof(struct ip_mreq)) {
if (copy_from_user(&mreq, optval,
sizeof(struct ip_mreq)))
break;
} else if (optlen >= sizeof(struct in_addr)) {
if (copy_from_user(&mreq.imr_address, optval,
sizeof(struct in_addr)))
break;
}
}
if (!mreq.imr_ifindex) {
if (mreq.imr_address.s_addr == htonl(INADDR_ANY)) {
inet->mc_index = 0;
inet->mc_addr = 0;
err = 0;
break;
}
dev = ip_dev_find(sock_net(sk), mreq.imr_address.s_addr);
if (dev)
mreq.imr_ifindex = dev->ifindex;
} else
dev = dev_get_by_index(sock_net(sk), mreq.imr_ifindex);
err = -EADDRNOTAVAIL;
if (!dev)
break;
dev_put(dev);
err = -EINVAL;
if (sk->sk_bound_dev_if &&
mreq.imr_ifindex != sk->sk_bound_dev_if)
break;
inet->mc_index = mreq.imr_ifindex;
inet->mc_addr = mreq.imr_address.s_addr;
err = 0;
break;
}
case IP_ADD_MEMBERSHIP:
case IP_DROP_MEMBERSHIP:
{
struct ip_mreqn mreq;
err = -EPROTO;
if (inet_sk(sk)->is_icsk)
break;
if (optlen < sizeof(struct ip_mreq))
goto e_inval;
err = -EFAULT;
if (optlen >= sizeof(struct ip_mreqn)) {
if (copy_from_user(&mreq, optval, sizeof(mreq)))
break;
} else {
memset(&mreq, 0, sizeof(mreq));
if (copy_from_user(&mreq, optval, sizeof(struct ip_mreq)))
break;
}
if (optname == IP_ADD_MEMBERSHIP)
err = ip_mc_join_group(sk, &mreq);
else
err = ip_mc_leave_group(sk, &mreq);
break;
}
case IP_MSFILTER:
{
struct ip_msfilter *msf;
if (optlen < IP_MSFILTER_SIZE(0))
goto e_inval;
if (optlen > sysctl_optmem_max) {
err = -ENOBUFS;
break;
}
msf = kmalloc(optlen, GFP_KERNEL);
if (!msf) {
err = -ENOBUFS;
break;
}
err = -EFAULT;
if (copy_from_user(msf, optval, optlen)) {
kfree(msf);
break;
}
/* numsrc >= (1G-4) overflow in 32 bits */
if (msf->imsf_numsrc >= 0x3ffffffcU ||
msf->imsf_numsrc > sysctl_igmp_max_msf) {
kfree(msf);
err = -ENOBUFS;
break;
}
if (IP_MSFILTER_SIZE(msf->imsf_numsrc) > optlen) {
kfree(msf);
err = -EINVAL;
break;
}
err = ip_mc_msfilter(sk, msf, 0);
kfree(msf);
break;
}
case IP_BLOCK_SOURCE:
case IP_UNBLOCK_SOURCE:
case IP_ADD_SOURCE_MEMBERSHIP:
case IP_DROP_SOURCE_MEMBERSHIP:
{
struct ip_mreq_source mreqs;
int omode, add;
if (optlen != sizeof(struct ip_mreq_source))
goto e_inval;
if (copy_from_user(&mreqs, optval, sizeof(mreqs))) {
err = -EFAULT;
break;
}
if (optname == IP_BLOCK_SOURCE) {
omode = MCAST_EXCLUDE;
add = 1;
} else if (optname == IP_UNBLOCK_SOURCE) {
omode = MCAST_EXCLUDE;
add = 0;
} else if (optname == IP_ADD_SOURCE_MEMBERSHIP) {
struct ip_mreqn mreq;
mreq.imr_multiaddr.s_addr = mreqs.imr_multiaddr;
mreq.imr_address.s_addr = mreqs.imr_interface;
mreq.imr_ifindex = 0;
err = ip_mc_join_group(sk, &mreq);
if (err && err != -EADDRINUSE)
break;
omode = MCAST_INCLUDE;
add = 1;
} else /* IP_DROP_SOURCE_MEMBERSHIP */ {
omode = MCAST_INCLUDE;
add = 0;
}
err = ip_mc_source(add, omode, sk, &mreqs, 0);
break;
}
case MCAST_JOIN_GROUP:
case MCAST_LEAVE_GROUP:
{
struct group_req greq;
struct sockaddr_in *psin;
struct ip_mreqn mreq;
if (optlen < sizeof(struct group_req))
goto e_inval;
err = -EFAULT;
if (copy_from_user(&greq, optval, sizeof(greq)))
break;
psin = (struct sockaddr_in *)&greq.gr_group;
if (psin->sin_family != AF_INET)
goto e_inval;
memset(&mreq, 0, sizeof(mreq));
mreq.imr_multiaddr = psin->sin_addr;
mreq.imr_ifindex = greq.gr_interface;
if (optname == MCAST_JOIN_GROUP)
err = ip_mc_join_group(sk, &mreq);
else
err = ip_mc_leave_group(sk, &mreq);
break;
}
case MCAST_JOIN_SOURCE_GROUP:
case MCAST_LEAVE_SOURCE_GROUP:
case MCAST_BLOCK_SOURCE:
case MCAST_UNBLOCK_SOURCE:
{
struct group_source_req greqs;
struct ip_mreq_source mreqs;
struct sockaddr_in *psin;
int omode, add;
if (optlen != sizeof(struct group_source_req))
goto e_inval;
if (copy_from_user(&greqs, optval, sizeof(greqs))) {
err = -EFAULT;
break;
}
if (greqs.gsr_group.ss_family != AF_INET ||
greqs.gsr_source.ss_family != AF_INET) {
err = -EADDRNOTAVAIL;
break;
}
psin = (struct sockaddr_in *)&greqs.gsr_group;
mreqs.imr_multiaddr = psin->sin_addr.s_addr;
psin = (struct sockaddr_in *)&greqs.gsr_source;
mreqs.imr_sourceaddr = psin->sin_addr.s_addr;
mreqs.imr_interface = 0; /* use index for mc_source */
if (optname == MCAST_BLOCK_SOURCE) {
omode = MCAST_EXCLUDE;
add = 1;
} else if (optname == MCAST_UNBLOCK_SOURCE) {
omode = MCAST_EXCLUDE;
add = 0;
} else if (optname == MCAST_JOIN_SOURCE_GROUP) {
struct ip_mreqn mreq;
psin = (struct sockaddr_in *)&greqs.gsr_group;
mreq.imr_multiaddr = psin->sin_addr;
mreq.imr_address.s_addr = 0;
mreq.imr_ifindex = greqs.gsr_interface;
err = ip_mc_join_group(sk, &mreq);
if (err && err != -EADDRINUSE)
break;
greqs.gsr_interface = mreq.imr_ifindex;
omode = MCAST_INCLUDE;
add = 1;
} else /* MCAST_LEAVE_SOURCE_GROUP */ {
omode = MCAST_INCLUDE;
add = 0;
}
err = ip_mc_source(add, omode, sk, &mreqs,
greqs.gsr_interface);
break;
}
case MCAST_MSFILTER:
{
struct sockaddr_in *psin;
struct ip_msfilter *msf = NULL;
struct group_filter *gsf = NULL;
int msize, i, ifindex;
if (optlen < GROUP_FILTER_SIZE(0))
goto e_inval;
if (optlen > sysctl_optmem_max) {
err = -ENOBUFS;
break;
}
gsf = kmalloc(optlen, GFP_KERNEL);
if (!gsf) {
err = -ENOBUFS;
break;
}
err = -EFAULT;
if (copy_from_user(gsf, optval, optlen))
goto mc_msf_out;
/* numsrc >= (4G-140)/128 overflow in 32 bits */
if (gsf->gf_numsrc >= 0x1ffffff ||
gsf->gf_numsrc > sysctl_igmp_max_msf) {
err = -ENOBUFS;
goto mc_msf_out;
}
if (GROUP_FILTER_SIZE(gsf->gf_numsrc) > optlen) {
err = -EINVAL;
goto mc_msf_out;
}
msize = IP_MSFILTER_SIZE(gsf->gf_numsrc);
msf = kmalloc(msize, GFP_KERNEL);
if (!msf) {
err = -ENOBUFS;
goto mc_msf_out;
}
ifindex = gsf->gf_interface;
psin = (struct sockaddr_in *)&gsf->gf_group;
if (psin->sin_family != AF_INET) {
err = -EADDRNOTAVAIL;
goto mc_msf_out;
}
msf->imsf_multiaddr = psin->sin_addr.s_addr;
msf->imsf_interface = 0;
msf->imsf_fmode = gsf->gf_fmode;
msf->imsf_numsrc = gsf->gf_numsrc;
err = -EADDRNOTAVAIL;
for (i = 0; i < gsf->gf_numsrc; ++i) {
psin = (struct sockaddr_in *)&gsf->gf_slist[i];
if (psin->sin_family != AF_INET)
goto mc_msf_out;
msf->imsf_slist[i] = psin->sin_addr.s_addr;
}
kfree(gsf);
gsf = NULL;
err = ip_mc_msfilter(sk, msf, ifindex);
mc_msf_out:
kfree(msf);
kfree(gsf);
break;
}
case IP_MULTICAST_ALL:
if (optlen < 1)
goto e_inval;
if (val != 0 && val != 1)
goto e_inval;
inet->mc_all = val;
break;
case IP_ROUTER_ALERT:
err = ip_ra_control(sk, val ? 1 : 0, NULL);
break;
case IP_FREEBIND:
if (optlen < 1)
goto e_inval;
inet->freebind = !!val;
break;
case IP_IPSEC_POLICY:
case IP_XFRM_POLICY:
err = -EPERM;
if (!capable(CAP_NET_ADMIN))
break;
err = xfrm_user_policy(sk, optname, optval, optlen);
break;
case IP_TRANSPARENT:
if (!!val && !capable(CAP_NET_RAW) && !capable(CAP_NET_ADMIN)) {
err = -EPERM;
break;
}
if (optlen < 1)
goto e_inval;
inet->transparent = !!val;
break;
case IP_MINTTL:
if (optlen < 1)
goto e_inval;
if (val < 0 || val > 255)
goto e_inval;
inet->min_ttl = val;
break;
default:
err = -ENOPROTOOPT;
break;
}
release_sock(sk);
return err;
e_inval:
release_sock(sk);
return -EINVAL;
}
/* Save metrics learned by this TCP session. This function is called
* only, when TCP finishes successfully i.e. when it enters TIME-WAIT
* or goes from LAST-ACK to CLOSE.
*/
void tcp_update_metrics(struct sock *sk)
{
const struct inet_connection_sock *icsk = inet_csk(sk);
struct dst_entry *dst = __sk_dst_get(sk);
struct tcp_sock *tp = tcp_sk(sk);
struct tcp_metrics_block *tm;
unsigned long rtt;
u32 val;
int m;
if (sysctl_tcp_nometrics_save || !dst)
return;
if (dst->flags & DST_HOST)
dst_confirm(dst);
rcu_read_lock();
if (icsk->icsk_backoff || !tp->srtt_us) {
/* This session failed to estimate rtt. Why?
* Probably, no packets returned in time. Reset our
* results.
*/
tm = tcp_get_metrics(sk, dst, false);
if (tm && !tcp_metric_locked(tm, TCP_METRIC_RTT))
tcp_metric_set(tm, TCP_METRIC_RTT, 0);
goto out_unlock;
} else
tm = tcp_get_metrics(sk, dst, true);
if (!tm)
goto out_unlock;
rtt = tcp_metric_get(tm, TCP_METRIC_RTT);
m = rtt - tp->srtt_us;
/* If newly calculated rtt larger than stored one, store new
* one. Otherwise, use EWMA. Remember, rtt overestimation is
* always better than underestimation.
*/
if (!tcp_metric_locked(tm, TCP_METRIC_RTT)) {
if (m <= 0)
rtt = tp->srtt_us;
else
rtt -= (m >> 3);
tcp_metric_set(tm, TCP_METRIC_RTT, rtt);
}
if (!tcp_metric_locked(tm, TCP_METRIC_RTTVAR)) {
unsigned long var;
if (m < 0)
m = -m;
/* Scale deviation to rttvar fixed point */
m >>= 1;
if (m < tp->mdev_us)
m = tp->mdev_us;
var = tcp_metric_get(tm, TCP_METRIC_RTTVAR);
if (m >= var)
var = m;
else
var -= (var - m) >> 2;
tcp_metric_set(tm, TCP_METRIC_RTTVAR, var);
}
static struct sock *dccp_v6_request_recv_sock(const struct sock *sk,
struct sk_buff *skb,
struct request_sock *req,
struct dst_entry *dst,
struct request_sock *req_unhash,
bool *own_req)
{
struct inet_request_sock *ireq = inet_rsk(req);
struct ipv6_pinfo *newnp;
const struct ipv6_pinfo *np = inet6_sk(sk);
struct ipv6_txoptions *opt;
struct inet_sock *newinet;
struct dccp6_sock *newdp6;
struct sock *newsk;
if (skb->protocol == htons(ETH_P_IP)) {
/*
* v6 mapped
*/
newsk = dccp_v4_request_recv_sock(sk, skb, req, dst,
req_unhash, own_req);
if (newsk == NULL)
return NULL;
newdp6 = (struct dccp6_sock *)newsk;
newinet = inet_sk(newsk);
newinet->pinet6 = &newdp6->inet6;
newnp = inet6_sk(newsk);
memcpy(newnp, np, sizeof(struct ipv6_pinfo));
newnp->saddr = newsk->sk_v6_rcv_saddr;
inet_csk(newsk)->icsk_af_ops = &dccp_ipv6_mapped;
newsk->sk_backlog_rcv = dccp_v4_do_rcv;
newnp->pktoptions = NULL;
newnp->opt = NULL;
newnp->ipv6_mc_list = NULL;
newnp->ipv6_ac_list = NULL;
newnp->ipv6_fl_list = NULL;
newnp->mcast_oif = inet_iif(skb);
newnp->mcast_hops = ip_hdr(skb)->ttl;
/*
* No need to charge this sock to the relevant IPv6 refcnt debug socks count
* here, dccp_create_openreq_child now does this for us, see the comment in
* that function for the gory details. -acme
*/
/* It is tricky place. Until this moment IPv4 tcp
worked with IPv6 icsk.icsk_af_ops.
Sync it now.
*/
dccp_sync_mss(newsk, inet_csk(newsk)->icsk_pmtu_cookie);
return newsk;
}
if (sk_acceptq_is_full(sk))
goto out_overflow;
if (!dst) {
struct flowi6 fl6;
dst = inet6_csk_route_req(sk, &fl6, req, IPPROTO_DCCP);
if (!dst)
goto out;
}
newsk = dccp_create_openreq_child(sk, req, skb);
if (newsk == NULL)
goto out_nonewsk;
/*
* No need to charge this sock to the relevant IPv6 refcnt debug socks
* count here, dccp_create_openreq_child now does this for us, see the
* comment in that function for the gory details. -acme
*/
ip6_dst_store(newsk, dst, NULL, NULL);
newsk->sk_route_caps = dst->dev->features & ~(NETIF_F_IP_CSUM |
NETIF_F_TSO);
newdp6 = (struct dccp6_sock *)newsk;
newinet = inet_sk(newsk);
newinet->pinet6 = &newdp6->inet6;
newnp = inet6_sk(newsk);
memcpy(newnp, np, sizeof(struct ipv6_pinfo));
newsk->sk_v6_daddr = ireq->ir_v6_rmt_addr;
newnp->saddr = ireq->ir_v6_loc_addr;
newsk->sk_v6_rcv_saddr = ireq->ir_v6_loc_addr;
newsk->sk_bound_dev_if = ireq->ir_iif;
/* Now IPv6 options...
First: no IPv4 options.
*/
newinet->inet_opt = NULL;
/* Clone RX bits */
newnp->rxopt.all = np->rxopt.all;
newnp->ipv6_mc_list = NULL;
newnp->ipv6_ac_list = NULL;
newnp->ipv6_fl_list = NULL;
newnp->pktoptions = NULL;
newnp->opt = NULL;
newnp->mcast_oif = inet6_iif(skb);
newnp->mcast_hops = ipv6_hdr(skb)->hop_limit;
/*
* Clone native IPv6 options from listening socket (if any)
*
* Yes, keeping reference count would be much more clever, but we make
* one more one thing there: reattach optmem to newsk.
*/
opt = ireq->ipv6_opt;
if (!opt)
opt = rcu_dereference(np->opt);
if (opt) {
opt = ipv6_dup_options(newsk, opt);
RCU_INIT_POINTER(newnp->opt, opt);
}
inet_csk(newsk)->icsk_ext_hdr_len = 0;
if (opt)
inet_csk(newsk)->icsk_ext_hdr_len = opt->opt_nflen +
opt->opt_flen;
dccp_sync_mss(newsk, dst_mtu(dst));
newinet->inet_daddr = newinet->inet_saddr = LOOPBACK4_IPV6;
newinet->inet_rcv_saddr = LOOPBACK4_IPV6;
if (__inet_inherit_port(sk, newsk) < 0) {
inet_csk_prepare_forced_close(newsk);
dccp_done(newsk);
goto out;
}
*own_req = inet_ehash_nolisten(newsk, req_to_sk(req_unhash));
/* Clone pktoptions received with SYN, if we own the req */
if (*own_req && ireq->pktopts) {
newnp->pktoptions = skb_clone(ireq->pktopts, GFP_ATOMIC);
consume_skb(ireq->pktopts);
ireq->pktopts = NULL;
if (newnp->pktoptions)
skb_set_owner_r(newnp->pktoptions, newsk);
}
return newsk;
out_overflow:
__NET_INC_STATS(sock_net(sk), LINUX_MIB_LISTENOVERFLOWS);
out_nonewsk:
dst_release(dst);
out:
__NET_INC_STATS(sock_net(sk), LINUX_MIB_LISTENDROPS);
return NULL;
}
static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
int addr_len)
{
struct sockaddr_in6 *usin = (struct sockaddr_in6 *) uaddr;
struct inet_sock *inet = inet_sk(sk);
struct inet_connection_sock *icsk = inet_csk(sk);
struct ipv6_pinfo *np = inet6_sk(sk);
struct tcp_sock *tp = tcp_sk(sk);
struct in6_addr *saddr = NULL, *final_p = NULL, final;
struct flowi fl;
struct dst_entry *dst;
int addr_type;
int err;
if (addr_len < SIN6_LEN_RFC2133)
return -EINVAL;
if (usin->sin6_family != AF_INET6)
return(-EAFNOSUPPORT);
memset(&fl, 0, sizeof(fl));
if (np->sndflow) {
fl.fl6_flowlabel = usin->sin6_flowinfo&IPV6_FLOWINFO_MASK;
IP6_ECN_flow_init(fl.fl6_flowlabel);
if (fl.fl6_flowlabel&IPV6_FLOWLABEL_MASK) {
struct ip6_flowlabel *flowlabel;
flowlabel = fl6_sock_lookup(sk, fl.fl6_flowlabel);
if (flowlabel == NULL)
return -EINVAL;
ipv6_addr_copy(&usin->sin6_addr, &flowlabel->dst);
fl6_sock_release(flowlabel);
}
}
/*
* connect() to INADDR_ANY means loopback (BSD'ism).
*/
if(ipv6_addr_any(&usin->sin6_addr))
usin->sin6_addr.s6_addr[15] = 0x1;
addr_type = ipv6_addr_type(&usin->sin6_addr);
if(addr_type & IPV6_ADDR_MULTICAST)
return -ENETUNREACH;
if (addr_type&IPV6_ADDR_LINKLOCAL) {
if (addr_len >= sizeof(struct sockaddr_in6) &&
usin->sin6_scope_id) {
/* If interface is set while binding, indices
* must coincide.
*/
if (sk->sk_bound_dev_if &&
sk->sk_bound_dev_if != usin->sin6_scope_id)
return -EINVAL;
sk->sk_bound_dev_if = usin->sin6_scope_id;
}
/* Connect to link-local address requires an interface */
if (!sk->sk_bound_dev_if)
return -EINVAL;
}
if (tp->rx_opt.ts_recent_stamp &&
!ipv6_addr_equal(&np->daddr, &usin->sin6_addr)) {
tp->rx_opt.ts_recent = 0;
tp->rx_opt.ts_recent_stamp = 0;
tp->write_seq = 0;
}
ipv6_addr_copy(&np->daddr, &usin->sin6_addr);
np->flow_label = fl.fl6_flowlabel;
/*
* TCP over IPv4
*/
if (addr_type == IPV6_ADDR_MAPPED) {
u32 exthdrlen = icsk->icsk_ext_hdr_len;
struct sockaddr_in sin;
SOCK_DEBUG(sk, "connect: ipv4 mapped\n");
if (__ipv6_only_sock(sk))
return -ENETUNREACH;
sin.sin_family = AF_INET;
sin.sin_port = usin->sin6_port;
sin.sin_addr.s_addr = usin->sin6_addr.s6_addr32[3];
icsk->icsk_af_ops = &ipv6_mapped;
sk->sk_backlog_rcv = tcp_v4_do_rcv;
err = tcp_v4_connect(sk, (struct sockaddr *)&sin, sizeof(sin));
if (err) {
icsk->icsk_ext_hdr_len = exthdrlen;
icsk->icsk_af_ops = &ipv6_specific;
sk->sk_backlog_rcv = tcp_v6_do_rcv;
goto failure;
} else {
ipv6_addr_set(&np->saddr, 0, 0, htonl(0x0000FFFF),
inet->saddr);
ipv6_addr_set(&np->rcv_saddr, 0, 0, htonl(0x0000FFFF),
inet->rcv_saddr);
}
return err;
}
if (!ipv6_addr_any(&np->rcv_saddr))
saddr = &np->rcv_saddr;
fl.proto = IPPROTO_TCP;
ipv6_addr_copy(&fl.fl6_dst, &np->daddr);
ipv6_addr_copy(&fl.fl6_src,
(saddr ? saddr : &np->saddr));
fl.oif = sk->sk_bound_dev_if;
fl.fl_ip_dport = usin->sin6_port;
fl.fl_ip_sport = inet->sport;
if (np->opt && np->opt->srcrt) {
struct rt0_hdr *rt0 = (struct rt0_hdr *)np->opt->srcrt;
ipv6_addr_copy(&final, &fl.fl6_dst);
ipv6_addr_copy(&fl.fl6_dst, rt0->addr);
final_p = &final;
}
err = ip6_dst_lookup(sk, &dst, &fl);
if (err)
goto failure;
if (final_p) {
ipv6_addr_copy(&fl.fl6_dst, final_p);
fl.flags |= FLOWI_FLAG_NOTROUTE;
}
if ((err = xfrm_lookup(&dst, &fl, sk, 0)) < 0)
goto failure;
if (saddr == NULL) {
saddr = &fl.fl6_src;
ipv6_addr_copy(&np->rcv_saddr, saddr);
}
/* set the source address */
ipv6_addr_copy(&np->saddr, saddr);
inet->rcv_saddr = LOOPBACK4_IPV6;
ip6_dst_store(sk, dst, NULL);
sk->sk_route_caps = dst->dev->features &
~(NETIF_F_IP_CSUM | NETIF_F_TSO);
icsk->icsk_ext_hdr_len = 0;
if (np->opt)
icsk->icsk_ext_hdr_len = (np->opt->opt_flen +
np->opt->opt_nflen);
tp->rx_opt.mss_clamp = IPV6_MIN_MTU - sizeof(struct tcphdr) - sizeof(struct ipv6hdr);
inet->dport = usin->sin6_port;
tcp_set_state(sk, TCP_SYN_SENT);
err = inet6_hash_connect(&tcp_death_row, sk);
if (err)
goto late_failure;
if (!tp->write_seq)
tp->write_seq = secure_tcpv6_sequence_number(np->saddr.s6_addr32,
np->daddr.s6_addr32,
inet->sport,
inet->dport);
err = tcp_connect(sk);
if (err)
goto late_failure;
return 0;
late_failure:
tcp_set_state(sk, TCP_CLOSE);
__sk_dst_reset(sk);
failure:
inet->dport = 0;
sk->sk_route_caps = 0;
return err;
}
static int dccp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
int addr_len)
{
struct sockaddr_in6 *usin = (struct sockaddr_in6 *)uaddr;
struct inet_connection_sock *icsk = inet_csk(sk);
struct inet_sock *inet = inet_sk(sk);
struct ipv6_pinfo *np = inet6_sk(sk);
struct dccp_sock *dp = dccp_sk(sk);
struct in6_addr *saddr = NULL, *final_p, final;
struct ipv6_txoptions *opt;
struct flowi6 fl6;
struct dst_entry *dst;
int addr_type;
int err;
dp->dccps_role = DCCP_ROLE_CLIENT;
if (addr_len < SIN6_LEN_RFC2133)
return -EINVAL;
if (usin->sin6_family != AF_INET6)
return -EAFNOSUPPORT;
memset(&fl6, 0, sizeof(fl6));
if (np->sndflow) {
fl6.flowlabel = usin->sin6_flowinfo & IPV6_FLOWINFO_MASK;
IP6_ECN_flow_init(fl6.flowlabel);
if (fl6.flowlabel & IPV6_FLOWLABEL_MASK) {
struct ip6_flowlabel *flowlabel;
flowlabel = fl6_sock_lookup(sk, fl6.flowlabel);
if (flowlabel == NULL)
return -EINVAL;
fl6_sock_release(flowlabel);
}
}
/*
* connect() to INADDR_ANY means loopback (BSD'ism).
*/
if (ipv6_addr_any(&usin->sin6_addr))
usin->sin6_addr.s6_addr[15] = 1;
addr_type = ipv6_addr_type(&usin->sin6_addr);
if (addr_type & IPV6_ADDR_MULTICAST)
return -ENETUNREACH;
if (addr_type & IPV6_ADDR_LINKLOCAL) {
if (addr_len >= sizeof(struct sockaddr_in6) &&
usin->sin6_scope_id) {
/* If interface is set while binding, indices
* must coincide.
*/
if (sk->sk_bound_dev_if &&
sk->sk_bound_dev_if != usin->sin6_scope_id)
return -EINVAL;
sk->sk_bound_dev_if = usin->sin6_scope_id;
}
/* Connect to link-local address requires an interface */
if (!sk->sk_bound_dev_if)
return -EINVAL;
}
sk->sk_v6_daddr = usin->sin6_addr;
np->flow_label = fl6.flowlabel;
/*
* DCCP over IPv4
*/
if (addr_type == IPV6_ADDR_MAPPED) {
u32 exthdrlen = icsk->icsk_ext_hdr_len;
struct sockaddr_in sin;
SOCK_DEBUG(sk, "connect: ipv4 mapped\n");
if (__ipv6_only_sock(sk))
return -ENETUNREACH;
sin.sin_family = AF_INET;
sin.sin_port = usin->sin6_port;
sin.sin_addr.s_addr = usin->sin6_addr.s6_addr32[3];
icsk->icsk_af_ops = &dccp_ipv6_mapped;
sk->sk_backlog_rcv = dccp_v4_do_rcv;
err = dccp_v4_connect(sk, (struct sockaddr *)&sin, sizeof(sin));
if (err) {
icsk->icsk_ext_hdr_len = exthdrlen;
icsk->icsk_af_ops = &dccp_ipv6_af_ops;
sk->sk_backlog_rcv = dccp_v6_do_rcv;
goto failure;
}
np->saddr = sk->sk_v6_rcv_saddr;
return err;
}
if (!ipv6_addr_any(&sk->sk_v6_rcv_saddr))
saddr = &sk->sk_v6_rcv_saddr;
fl6.flowi6_proto = IPPROTO_DCCP;
fl6.daddr = sk->sk_v6_daddr;
fl6.saddr = saddr ? *saddr : np->saddr;
fl6.flowi6_oif = sk->sk_bound_dev_if;
fl6.fl6_dport = usin->sin6_port;
fl6.fl6_sport = inet->inet_sport;
security_sk_classify_flow(sk, flowi6_to_flowi(&fl6));
opt = rcu_dereference_protected(np->opt, lockdep_sock_is_held(sk));
final_p = fl6_update_dst(&fl6, opt, &final);
dst = ip6_dst_lookup_flow(sk, &fl6, final_p);
if (IS_ERR(dst)) {
err = PTR_ERR(dst);
goto failure;
}
if (saddr == NULL) {
saddr = &fl6.saddr;
sk->sk_v6_rcv_saddr = *saddr;
}
/* set the source address */
np->saddr = *saddr;
inet->inet_rcv_saddr = LOOPBACK4_IPV6;
ip6_dst_store(sk, dst, NULL, NULL);
icsk->icsk_ext_hdr_len = 0;
if (opt)
icsk->icsk_ext_hdr_len = opt->opt_flen + opt->opt_nflen;
inet->inet_dport = usin->sin6_port;
dccp_set_state(sk, DCCP_REQUESTING);
err = inet6_hash_connect(&dccp_death_row, sk);
if (err)
goto late_failure;
dp->dccps_iss = secure_dccpv6_sequence_number(np->saddr.s6_addr32,
sk->sk_v6_daddr.s6_addr32,
inet->inet_sport,
inet->inet_dport);
err = dccp_connect(sk);
if (err)
goto late_failure;
return 0;
late_failure:
dccp_set_state(sk, DCCP_CLOSED);
__sk_dst_reset(sk);
failure:
inet->inet_dport = 0;
sk->sk_route_caps = 0;
return err;
}
static void tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
int type, int code, int offset, __u32 info)
{
struct ipv6hdr *hdr = (struct ipv6hdr*)skb->data;
const struct tcphdr *th = (struct tcphdr *)(skb->data+offset);
struct ipv6_pinfo *np;
struct sock *sk;
int err;
struct tcp_sock *tp;
__u32 seq;
sk = inet6_lookup(&tcp_hashinfo, &hdr->daddr, th->dest, &hdr->saddr,
th->source, skb->dev->ifindex);
if (sk == NULL) {
ICMP6_INC_STATS_BH(__in6_dev_get(skb->dev), ICMP6_MIB_INERRORS);
return;
}
if (sk->sk_state == TCP_TIME_WAIT) {
inet_twsk_put((struct inet_timewait_sock *)sk);
return;
}
bh_lock_sock(sk);
if (sock_owned_by_user(sk))
NET_INC_STATS_BH(LINUX_MIB_LOCKDROPPEDICMPS);
if (sk->sk_state == TCP_CLOSE)
goto out;
tp = tcp_sk(sk);
seq = ntohl(th->seq);
if (sk->sk_state != TCP_LISTEN &&
!between(seq, tp->snd_una, tp->snd_nxt)) {
NET_INC_STATS_BH(LINUX_MIB_OUTOFWINDOWICMPS);
goto out;
}
np = inet6_sk(sk);
if (type == ICMPV6_PKT_TOOBIG) {
struct dst_entry *dst = NULL;
if (sock_owned_by_user(sk))
goto out;
if ((1 << sk->sk_state) & (TCPF_LISTEN | TCPF_CLOSE))
goto out;
/* icmp should have updated the destination cache entry */
dst = __sk_dst_check(sk, np->dst_cookie);
if (dst == NULL) {
struct inet_sock *inet = inet_sk(sk);
struct flowi fl;
/* BUGGG_FUTURE: Again, it is not clear how
to handle rthdr case. Ignore this complexity
for now.
*/
memset(&fl, 0, sizeof(fl));
fl.proto = IPPROTO_TCP;
ipv6_addr_copy(&fl.fl6_dst, &np->daddr);
ipv6_addr_copy(&fl.fl6_src, &np->saddr);
fl.oif = sk->sk_bound_dev_if;
fl.fl_ip_dport = inet->dport;
fl.fl_ip_sport = inet->sport;
if ((err = ip6_dst_lookup(sk, &dst, &fl))) {
sk->sk_err_soft = -err;
goto out;
}
if ((err = xfrm_lookup(&dst, &fl, sk, 0)) < 0) {
sk->sk_err_soft = -err;
goto out;
}
} else
dst_hold(dst);
if (inet_csk(sk)->icsk_pmtu_cookie > dst_mtu(dst)) {
tcp_sync_mss(sk, dst_mtu(dst));
tcp_simple_retransmit(sk);
} /* else let the usual retransmit timer handle it */
dst_release(dst);
goto out;
}
icmpv6_err_convert(type, code, &err);
/* Might be for an request_sock */
switch (sk->sk_state) {
struct request_sock *req, **prev;
case TCP_LISTEN:
if (sock_owned_by_user(sk))
goto out;
req = inet6_csk_search_req(sk, &prev, th->dest, &hdr->daddr,
&hdr->saddr, inet6_iif(skb));
if (!req)
goto out;
/* ICMPs are not backlogged, hence we cannot get
* an established socket here.
*/
BUG_TRAP(req->sk == NULL);
if (seq != tcp_rsk(req)->snt_isn) {
NET_INC_STATS_BH(LINUX_MIB_OUTOFWINDOWICMPS);
goto out;
}
inet_csk_reqsk_queue_drop(sk, req, prev);
goto out;
case TCP_SYN_SENT:
case TCP_SYN_RECV: /* Cannot happen.
It can, it SYNs are crossed. --ANK */
if (!sock_owned_by_user(sk)) {
TCP_INC_STATS_BH(TCP_MIB_ATTEMPTFAILS);
sk->sk_err = err;
sk->sk_error_report(sk); /* Wake people up to see the error (see connect in sock.c) */
tcp_done(sk);
} else
sk->sk_err_soft = err;
goto out;
}
if (!sock_owned_by_user(sk) && np->recverr) {
sk->sk_err = err;
sk->sk_error_report(sk);
} else
sk->sk_err_soft = err;
out:
bh_unlock_sock(sk);
sock_put(sk);
}
static void dccp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
u8 type, u8 code, int offset, __be32 info)
{
struct ipv6hdr *hdr = (struct ipv6hdr *)skb->data;
const struct dccp_hdr *dh = (struct dccp_hdr *)(skb->data + offset);
struct dccp_sock *dp;
struct ipv6_pinfo *np;
struct sock *sk;
int err;
__u64 seq;
struct net *net = dev_net(skb->dev);
if (skb->len < offset + sizeof(*dh) ||
skb->len < offset + __dccp_basic_hdr_len(dh)) {
ICMP6_INC_STATS_BH(net, __in6_dev_get(skb->dev),
ICMP6_MIB_INERRORS);
return;
}
sk = inet6_lookup(net, &dccp_hashinfo,
&hdr->daddr, dh->dccph_dport,
&hdr->saddr, dh->dccph_sport, inet6_iif(skb));
if (sk == NULL) {
ICMP6_INC_STATS_BH(net, __in6_dev_get(skb->dev),
ICMP6_MIB_INERRORS);
return;
}
if (sk->sk_state == DCCP_TIME_WAIT) {
inet_twsk_put(inet_twsk(sk));
return;
}
bh_lock_sock(sk);
if (sock_owned_by_user(sk))
NET_INC_STATS_BH(net, LINUX_MIB_LOCKDROPPEDICMPS);
if (sk->sk_state == DCCP_CLOSED)
goto out;
dp = dccp_sk(sk);
seq = dccp_hdr_seq(dh);
if ((1 << sk->sk_state) & ~(DCCPF_REQUESTING | DCCPF_LISTEN) &&
!between48(seq, dp->dccps_awl, dp->dccps_awh)) {
NET_INC_STATS_BH(net, LINUX_MIB_OUTOFWINDOWICMPS);
goto out;
}
np = inet6_sk(sk);
if (type == ICMPV6_PKT_TOOBIG) {
struct dst_entry *dst = NULL;
if (sock_owned_by_user(sk))
goto out;
if ((1 << sk->sk_state) & (DCCPF_LISTEN | DCCPF_CLOSED))
goto out;
/* icmp should have updated the destination cache entry */
dst = __sk_dst_check(sk, np->dst_cookie);
if (dst == NULL) {
struct inet_sock *inet = inet_sk(sk);
struct flowi fl;
/* BUGGG_FUTURE: Again, it is not clear how
to handle rthdr case. Ignore this complexity
for now.
*/
memset(&fl, 0, sizeof(fl));
fl.proto = IPPROTO_DCCP;
ipv6_addr_copy(&fl.fl6_dst, &np->daddr);
ipv6_addr_copy(&fl.fl6_src, &np->saddr);
fl.oif = sk->sk_bound_dev_if;
fl.fl_ip_dport = inet->dport;
fl.fl_ip_sport = inet->sport;
security_sk_classify_flow(sk, &fl);
err = ip6_dst_lookup(sk, &dst, &fl);
if (err) {
sk->sk_err_soft = -err;
goto out;
}
err = xfrm_lookup(net, &dst, &fl, sk, 0);
if (err < 0) {
sk->sk_err_soft = -err;
goto out;
}
} else
dst_hold(dst);
if (inet_csk(sk)->icsk_pmtu_cookie > dst_mtu(dst)) {
dccp_sync_mss(sk, dst_mtu(dst));
} /* else let the usual retransmit timer handle it */
dst_release(dst);
goto out;
}
icmpv6_err_convert(type, code, &err);
/* Might be for an request_sock */
switch (sk->sk_state) {
struct request_sock *req, **prev;
case DCCP_LISTEN:
if (sock_owned_by_user(sk))
goto out;
req = inet6_csk_search_req(sk, &prev, dh->dccph_dport,
&hdr->daddr, &hdr->saddr,
inet6_iif(skb));
if (req == NULL)
goto out;
/*
* ICMPs are not backlogged, hence we cannot get an established
* socket here.
*/
WARN_ON(req->sk != NULL);
if (seq != dccp_rsk(req)->dreq_iss) {
NET_INC_STATS_BH(net, LINUX_MIB_OUTOFWINDOWICMPS);
goto out;
}
inet_csk_reqsk_queue_drop(sk, req, prev);
goto out;
case DCCP_REQUESTING:
case DCCP_RESPOND: /* Cannot happen.
It can, it SYNs are crossed. --ANK */
if (!sock_owned_by_user(sk)) {
DCCP_INC_STATS_BH(DCCP_MIB_ATTEMPTFAILS);
sk->sk_err = err;
/*
* Wake people up to see the error
* (see connect in sock.c)
*/
sk->sk_error_report(sk);
dccp_done(sk);
} else
sk->sk_err_soft = err;
goto out;
}
if (!sock_owned_by_user(sk) && np->recverr) {
sk->sk_err = err;
sk->sk_error_report(sk);
} else
sk->sk_err_soft = err;
out:
bh_unlock_sock(sk);
sock_put(sk);
}
/*
* All SKB's seen here are completely headerless. It is our
* job to build the DCCP header, and pass the packet down to
* IP so it can do the same plus pass the packet off to the
* device.
*/
static int dccp_transmit_skb(struct sock *sk, struct sk_buff *skb)
{
if (likely(skb != NULL)) {
struct inet_sock *inet = inet_sk(sk);
const struct inet_connection_sock *icsk = inet_csk(sk);
struct dccp_sock *dp = dccp_sk(sk);
struct dccp_skb_cb *dcb = DCCP_SKB_CB(skb);
struct dccp_hdr *dh;
/* XXX For now we're using only 48 bits sequence numbers */
const u32 dccp_header_size = sizeof(*dh) +
sizeof(struct dccp_hdr_ext) +
dccp_packet_hdr_len(dcb->dccpd_type);
int err, set_ack = 1;
u64 ackno = dp->dccps_gsr;
/*
* Increment GSS here already in case the option code needs it.
* Update GSS for real only if option processing below succeeds.
*/
dcb->dccpd_seq = ADD48(dp->dccps_gss, 1);
switch (dcb->dccpd_type) {
case DCCP_PKT_DATA:
set_ack = 0;
/* fall through */
case DCCP_PKT_DATAACK:
case DCCP_PKT_RESET:
break;
case DCCP_PKT_REQUEST:
set_ack = 0;
/* Use ISS on the first (non-retransmitted) Request. */
if (icsk->icsk_retransmits == 0)
dcb->dccpd_seq = dp->dccps_iss;
/* fall through */
case DCCP_PKT_SYNC:
case DCCP_PKT_SYNCACK:
ackno = dcb->dccpd_ack_seq;
/* fall through */
default:
/*
* Set owner/destructor: some skbs are allocated via
* alloc_skb (e.g. when retransmission may happen).
* Only Data, DataAck, and Reset packets should come
* through here with skb->sk set.
*/
WARN_ON(skb->sk);
skb_set_owner_w(skb, sk);
break;
}
if (dccp_insert_options(sk, skb)) {
kfree_skb(skb);
return -EPROTO;
}
/* Build DCCP header and checksum it. */
dh = dccp_zeroed_hdr(skb, dccp_header_size);
dh->dccph_type = dcb->dccpd_type;
dh->dccph_sport = inet->inet_sport;
dh->dccph_dport = inet->inet_dport;
dh->dccph_doff = (dccp_header_size + dcb->dccpd_opt_len) / 4;
dh->dccph_ccval = dcb->dccpd_ccval;
dh->dccph_cscov = dp->dccps_pcslen;
/* XXX For now we're using only 48 bits sequence numbers */
dh->dccph_x = 1;
dccp_update_gss(sk, dcb->dccpd_seq);
dccp_hdr_set_seq(dh, dp->dccps_gss);
if (set_ack)
dccp_hdr_set_ack(dccp_hdr_ack_bits(skb), ackno);
switch (dcb->dccpd_type) {
case DCCP_PKT_REQUEST:
dccp_hdr_request(skb)->dccph_req_service =
dp->dccps_service;
/*
* Limit Ack window to ISS <= P.ackno <= GSS, so that
* only Responses to Requests we sent are considered.
*/
dp->dccps_awl = dp->dccps_iss;
break;
case DCCP_PKT_RESET:
dccp_hdr_reset(skb)->dccph_reset_code =
dcb->dccpd_reset_code;
break;
}
icsk->icsk_af_ops->send_check(sk, skb);
if (set_ack)
dccp_event_ack_sent(sk);
DCCP_INC_STATS(DCCP_MIB_OUTSEGS);
err = icsk->icsk_af_ops->queue_xmit(sk, skb, &inet->cork.fl);
return net_xmit_eval(err);
}
return -ENOBUFS;
}
int dccp_init_sock(struct sock *sk, const __u8 ctl_sock_initialized)
{
struct dccp_sock *dp = dccp_sk(sk);
struct dccp_minisock *dmsk = dccp_msk(sk);
struct inet_connection_sock *icsk = inet_csk(sk);
dccp_minisock_init(&dp->dccps_minisock);
do_gettimeofday(&dp->dccps_epoch);
/*
* FIXME: We're hardcoding the CCID, and doing this at this point makes
* the listening (master) sock get CCID control blocks, which is not
* necessary, but for now, to not mess with the test userspace apps,
* lets leave it here, later the real solution is to do this in a
* setsockopt(CCIDs-I-want/accept). -acme
*/
if (likely(ctl_sock_initialized)) {
int rc = dccp_feat_init(dmsk);
if (rc)
return rc;
if (dmsk->dccpms_send_ack_vector) {
dp->dccps_hc_rx_ackvec = dccp_ackvec_alloc(GFP_KERNEL);
if (dp->dccps_hc_rx_ackvec == NULL)
return -ENOMEM;
}
dp->dccps_hc_rx_ccid = ccid_hc_rx_new(dmsk->dccpms_rx_ccid,
sk, GFP_KERNEL);
dp->dccps_hc_tx_ccid = ccid_hc_tx_new(dmsk->dccpms_tx_ccid,
sk, GFP_KERNEL);
if (unlikely(dp->dccps_hc_rx_ccid == NULL ||
dp->dccps_hc_tx_ccid == NULL)) {
ccid_hc_rx_delete(dp->dccps_hc_rx_ccid, sk);
ccid_hc_tx_delete(dp->dccps_hc_tx_ccid, sk);
if (dmsk->dccpms_send_ack_vector) {
dccp_ackvec_free(dp->dccps_hc_rx_ackvec);
dp->dccps_hc_rx_ackvec = NULL;
}
dp->dccps_hc_rx_ccid = dp->dccps_hc_tx_ccid = NULL;
return -ENOMEM;
}
} else {
/* control socket doesn't need feat nego */
INIT_LIST_HEAD(&dmsk->dccpms_pending);
INIT_LIST_HEAD(&dmsk->dccpms_conf);
}
dccp_init_xmit_timers(sk);
icsk->icsk_rto = DCCP_TIMEOUT_INIT;
icsk->icsk_syn_retries = sysctl_dccp_request_retries;
sk->sk_state = DCCP_CLOSED;
sk->sk_write_space = dccp_write_space;
icsk->icsk_sync_mss = dccp_sync_mss;
dp->dccps_mss_cache = 536;
dp->dccps_role = DCCP_ROLE_UNDEFINED;
dp->dccps_service = DCCP_SERVICE_CODE_IS_ABSENT;
dp->dccps_l_ack_ratio = dp->dccps_r_ack_ratio = 1;
return 0;
}
/* This will initiate an outgoing connection. */
int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
{
struct inet_sock *inet = inet_sk(sk);
struct tcp_sock *tp = tcp_sk(sk);
struct sockaddr_in *usin = (struct sockaddr_in *)uaddr;
struct rtable *rt;
u32 daddr, nexthop;
int tmp;
int err;
if (addr_len < sizeof(struct sockaddr_in))
return -EINVAL;
if (usin->sin_family != AF_INET)
return -EAFNOSUPPORT;
nexthop = daddr = usin->sin_addr.s_addr;
if (inet->opt && inet->opt->srr) {
if (!daddr)
return -EINVAL;
nexthop = inet->opt->faddr;
}
tmp = ip_route_connect(&rt, nexthop, inet->saddr,
RT_CONN_FLAGS(sk), sk->sk_bound_dev_if,
IPPROTO_TCP,
inet->sport, usin->sin_port, sk);
if (tmp < 0)
return tmp;
if (rt->rt_flags & (RTCF_MULTICAST | RTCF_BROADCAST)) {
ip_rt_put(rt);
return -ENETUNREACH;
}
if (!inet->opt || !inet->opt->srr)
daddr = rt->rt_dst;
if (!inet->saddr)
inet->saddr = rt->rt_src;
inet->rcv_saddr = inet->saddr;
if (tp->rx_opt.ts_recent_stamp && inet->daddr != daddr) {
/* Reset inherited state */
tp->rx_opt.ts_recent = 0;
tp->rx_opt.ts_recent_stamp = 0;
tp->write_seq = 0;
}
if (tcp_death_row.sysctl_tw_recycle &&
!tp->rx_opt.ts_recent_stamp && rt->rt_dst == daddr) {
struct inet_peer *peer = rt_get_peer(rt);
/* VJ's idea. We save last timestamp seen from
* the destination in peer table, when entering state TIME-WAIT
* and initialize rx_opt.ts_recent from it, when trying new connection.
*/
if (peer && peer->tcp_ts_stamp + TCP_PAWS_MSL >= xtime.tv_sec) {
tp->rx_opt.ts_recent_stamp = peer->tcp_ts_stamp;
tp->rx_opt.ts_recent = peer->tcp_ts;
}
}
inet->dport = usin->sin_port;
inet->daddr = daddr;
inet_csk(sk)->icsk_ext_hdr_len = 0;
if (inet->opt)
inet_csk(sk)->icsk_ext_hdr_len = inet->opt->optlen;
tp->rx_opt.mss_clamp = 536;
/* Socket identity is still unknown (sport may be zero).
* However we set state to SYN-SENT and not releasing socket
* lock select source port, enter ourselves into the hash tables and
* complete initialization after this.
*/
tcp_set_state(sk, TCP_SYN_SENT);
err = inet_hash_connect(&tcp_death_row, sk);
if (err)
goto failure;
err = ip_route_newports(&rt, IPPROTO_TCP, inet->sport, inet->dport, sk);
if (err)
goto failure;
/* OK, now commit destination to socket. */
sk_setup_caps(sk, &rt->u.dst);
if (!tp->write_seq)
tp->write_seq = secure_tcp_sequence_number(inet->saddr,
inet->daddr,
inet->sport,
usin->sin_port);
inet->id = tp->write_seq ^ jiffies;
err = tcp_connect(sk);
rt = NULL;
if (err)
goto failure;
return 0;
failure:
/* This unhashes the socket and releases the local port, if necessary. */
tcp_set_state(sk, TCP_CLOSE);
ip_rt_put(rt);
sk->sk_route_caps = 0;
inet->dport = 0;
return err;
}
static int do_ipv6_setsockopt(struct sock *sk, int level, int optname,
char __user *optval, unsigned int optlen)
{
struct ipv6_pinfo *np = inet6_sk(sk);
struct net *net = sock_net(sk);
int val, valbool;
int retv = -ENOPROTOOPT;
if (optval == NULL)
val=0;
else {
if (optlen >= sizeof(int)) {
if (get_user(val, (int __user *) optval))
return -EFAULT;
} else
val = 0;
}
valbool = (val!=0);
if (ip6_mroute_opt(optname))
return ip6_mroute_setsockopt(sk, optname, optval, optlen);
lock_sock(sk);
switch (optname) {
case IPV6_ADDRFORM:
if (optlen < sizeof(int))
goto e_inval;
if (val == PF_INET) {
struct ipv6_txoptions *opt;
struct sk_buff *pktopt;
if (sk->sk_type == SOCK_RAW)
break;
if (sk->sk_protocol == IPPROTO_UDP ||
sk->sk_protocol == IPPROTO_UDPLITE) {
struct udp_sock *up = udp_sk(sk);
if (up->pending == AF_INET6) {
retv = -EBUSY;
break;
}
} else if (sk->sk_protocol != IPPROTO_TCP)
break;
if (sk->sk_state != TCP_ESTABLISHED) {
retv = -ENOTCONN;
break;
}
if (ipv6_only_sock(sk) ||
!ipv6_addr_v4mapped(&np->daddr)) {
retv = -EADDRNOTAVAIL;
break;
}
fl6_free_socklist(sk);
ipv6_sock_mc_close(sk);
/*
* Sock is moving from IPv6 to IPv4 (sk_prot), so
* remove it from the refcnt debug socks count in the
* original family...
*/
sk_refcnt_debug_dec(sk);
if (sk->sk_protocol == IPPROTO_TCP) {
struct inet_connection_sock *icsk = inet_csk(sk);
local_bh_disable();
sock_prot_inuse_add(net, sk->sk_prot, -1);
sock_prot_inuse_add(net, &tcp_prot, 1);
local_bh_enable();
sk->sk_prot = &tcp_prot;
icsk->icsk_af_ops = &ipv4_specific;
sk->sk_socket->ops = &inet_stream_ops;
sk->sk_family = PF_INET;
tcp_sync_mss(sk, icsk->icsk_pmtu_cookie);
} else {
struct proto *prot = &udp_prot;
if (sk->sk_protocol == IPPROTO_UDPLITE)
prot = &udplite_prot;
local_bh_disable();
sock_prot_inuse_add(net, sk->sk_prot, -1);
sock_prot_inuse_add(net, prot, 1);
local_bh_enable();
sk->sk_prot = prot;
sk->sk_socket->ops = &inet_dgram_ops;
sk->sk_family = PF_INET;
}
opt = xchg(&np->opt, NULL);
if (opt)
sock_kfree_s(sk, opt, opt->tot_len);
pktopt = xchg(&np->pktoptions, NULL);
kfree_skb(pktopt);
sk->sk_destruct = inet_sock_destruct;
/*
* ... and add it to the refcnt debug socks count
* in the new family. -acme
*/
sk_refcnt_debug_inc(sk);
module_put(THIS_MODULE);
retv = 0;
break;
}
goto e_inval;
case IPV6_V6ONLY:
if (optlen < sizeof(int) ||
inet_sk(sk)->inet_num)
goto e_inval;
np->ipv6only = valbool;
retv = 0;
break;
case IPV6_RECVPKTINFO:
if (optlen < sizeof(int))
goto e_inval;
np->rxopt.bits.rxinfo = valbool;
retv = 0;
break;
case IPV6_2292PKTINFO:
if (optlen < sizeof(int))
goto e_inval;
np->rxopt.bits.rxoinfo = valbool;
retv = 0;
break;
case IPV6_RECVHOPLIMIT:
if (optlen < sizeof(int))
goto e_inval;
np->rxopt.bits.rxhlim = valbool;
retv = 0;
break;
case IPV6_2292HOPLIMIT:
if (optlen < sizeof(int))
goto e_inval;
np->rxopt.bits.rxohlim = valbool;
retv = 0;
break;
case IPV6_RECVRTHDR:
if (optlen < sizeof(int))
goto e_inval;
np->rxopt.bits.srcrt = valbool;
retv = 0;
break;
case IPV6_2292RTHDR:
if (optlen < sizeof(int))
goto e_inval;
np->rxopt.bits.osrcrt = valbool;
retv = 0;
break;
case IPV6_RECVHOPOPTS:
if (optlen < sizeof(int))
goto e_inval;
np->rxopt.bits.hopopts = valbool;
retv = 0;
break;
case IPV6_2292HOPOPTS:
if (optlen < sizeof(int))
goto e_inval;
np->rxopt.bits.ohopopts = valbool;
retv = 0;
break;
case IPV6_RECVDSTOPTS:
if (optlen < sizeof(int))
goto e_inval;
np->rxopt.bits.dstopts = valbool;
retv = 0;
break;
case IPV6_2292DSTOPTS:
if (optlen < sizeof(int))
goto e_inval;
np->rxopt.bits.odstopts = valbool;
retv = 0;
break;
case IPV6_TCLASS:
if (optlen < sizeof(int))
goto e_inval;
if (val < -1 || val > 0xff)
goto e_inval;
/* RFC 3542, 6.5: default traffic class of 0x0 */
if (val == -1)
val = 0;
np->tclass = val;
retv = 0;
break;
case IPV6_RECVTCLASS:
if (optlen < sizeof(int))
goto e_inval;
np->rxopt.bits.rxtclass = valbool;
retv = 0;
break;
case IPV6_FLOWINFO:
if (optlen < sizeof(int))
goto e_inval;
np->rxopt.bits.rxflow = valbool;
retv = 0;
break;
case IPV6_RECVPATHMTU:
if (optlen < sizeof(int))
goto e_inval;
np->rxopt.bits.rxpmtu = valbool;
retv = 0;
break;
case IPV6_TRANSPARENT:
if (valbool && !capable(CAP_NET_ADMIN) && !capable(CAP_NET_RAW)) {
retv = -EPERM;
break;
}
if (optlen < sizeof(int))
goto e_inval;
/* we don't have a separate transparent bit for IPV6 we use the one in the IPv4 socket */
inet_sk(sk)->transparent = valbool;
retv = 0;
break;
case IPV6_RECVORIGDSTADDR:
if (optlen < sizeof(int))
goto e_inval;
np->rxopt.bits.rxorigdstaddr = valbool;
retv = 0;
break;
case IPV6_HOPOPTS:
case IPV6_RTHDRDSTOPTS:
case IPV6_RTHDR:
case IPV6_DSTOPTS:
{
struct ipv6_txoptions *opt;
/* remove any sticky options header with a zero option
* length, per RFC3542.
*/
if (optlen == 0)
optval = NULL;
else if (optval == NULL)
goto e_inval;
else if (optlen < sizeof(struct ipv6_opt_hdr) ||
optlen & 0x7 || optlen > 8 * 255)
goto e_inval;
/* hop-by-hop / destination options are privileged option */
retv = -EPERM;
if (optname != IPV6_RTHDR && !capable(CAP_NET_RAW))
break;
opt = ipv6_renew_options(sk, np->opt, optname,
(struct ipv6_opt_hdr __user *)optval,
optlen);
if (IS_ERR(opt)) {
retv = PTR_ERR(opt);
break;
}
/* routing header option needs extra check */
retv = -EINVAL;
if (optname == IPV6_RTHDR && opt && opt->srcrt) {
struct ipv6_rt_hdr *rthdr = opt->srcrt;
switch (rthdr->type) {
#if defined(CONFIG_IPV6_MIP6) || defined(CONFIG_IPV6_MIP6_MODULE)
case IPV6_SRCRT_TYPE_2:
if (rthdr->hdrlen != 2 ||
rthdr->segments_left != 1)
goto sticky_done;
break;
#endif
default:
goto sticky_done;
}
}
retv = 0;
opt = ipv6_update_options(sk, opt);
sticky_done:
if (opt)
sock_kfree_s(sk, opt, opt->tot_len);
break;
}
case IPV6_PKTINFO:
{
struct in6_pktinfo pkt;
if (optlen == 0)
goto e_inval;
else if (optlen < sizeof(struct in6_pktinfo) || optval == NULL)
goto e_inval;
if (copy_from_user(&pkt, optval, sizeof(struct in6_pktinfo))) {
retv = -EFAULT;
break;
}
if (sk->sk_bound_dev_if && pkt.ipi6_ifindex != sk->sk_bound_dev_if)
goto e_inval;
np->sticky_pktinfo.ipi6_ifindex = pkt.ipi6_ifindex;
np->sticky_pktinfo.ipi6_addr = pkt.ipi6_addr;
retv = 0;
break;
}
case IPV6_2292PKTOPTIONS:
{
struct ipv6_txoptions *opt = NULL;
struct msghdr msg;
struct flowi6 fl6;
int junk;
memset(&fl6, 0, sizeof(fl6));
fl6.flowi6_oif = sk->sk_bound_dev_if;
fl6.flowi6_mark = sk->sk_mark;
if (optlen == 0)
goto update;
/* 1K is probably excessive
* 1K is surely not enough, 2K per standard header is 16K.
*/
retv = -EINVAL;
if (optlen > 64*1024)
break;
opt = sock_kmalloc(sk, sizeof(*opt) + optlen, GFP_KERNEL);
retv = -ENOBUFS;
if (opt == NULL)
break;
memset(opt, 0, sizeof(*opt));
opt->tot_len = sizeof(*opt) + optlen;
retv = -EFAULT;
if (copy_from_user(opt+1, optval, optlen))
goto done;
msg.msg_controllen = optlen;
msg.msg_control = (void*)(opt+1);
retv = ip6_datagram_send_ctl(net, sk, &msg, &fl6, opt, &junk, &junk,
&junk);
if (retv)
goto done;
update:
retv = 0;
opt = ipv6_update_options(sk, opt);
done:
if (opt)
sock_kfree_s(sk, opt, opt->tot_len);
break;
}
case IPV6_UNICAST_HOPS:
if (optlen < sizeof(int))
goto e_inval;
if (val > 255 || val < -1)
goto e_inval;
np->hop_limit = val;
retv = 0;
break;
case IPV6_MULTICAST_HOPS:
if (sk->sk_type == SOCK_STREAM)
break;
if (optlen < sizeof(int))
goto e_inval;
if (val > 255 || val < -1)
goto e_inval;
np->mcast_hops = (val == -1 ? IPV6_DEFAULT_MCASTHOPS : val);
retv = 0;
break;
case IPV6_MULTICAST_LOOP:
if (optlen < sizeof(int))
goto e_inval;
if (val != valbool)
goto e_inval;
np->mc_loop = valbool;
retv = 0;
break;
case IPV6_UNICAST_IF:
{
struct net_device *dev = NULL;
int ifindex;
if (optlen != sizeof(int))
goto e_inval;
ifindex = (__force int)ntohl((__force __be32)val);
if (ifindex == 0) {
np->ucast_oif = 0;
retv = 0;
break;
}
dev = dev_get_by_index(net, ifindex);
retv = -EADDRNOTAVAIL;
if (!dev)
break;
dev_put(dev);
retv = -EINVAL;
if (sk->sk_bound_dev_if)
break;
np->ucast_oif = ifindex;
retv = 0;
break;
}
case IPV6_MULTICAST_IF:
if (sk->sk_type == SOCK_STREAM)
break;
if (optlen < sizeof(int))
goto e_inval;
if (val) {
struct net_device *dev;
if (sk->sk_bound_dev_if && sk->sk_bound_dev_if != val)
goto e_inval;
dev = dev_get_by_index(net, val);
if (!dev) {
retv = -ENODEV;
break;
}
dev_put(dev);
}
np->mcast_oif = val;
retv = 0;
break;
case IPV6_ADD_MEMBERSHIP:
case IPV6_DROP_MEMBERSHIP:
{
struct ipv6_mreq mreq;
if (optlen < sizeof(struct ipv6_mreq))
goto e_inval;
retv = -EPROTO;
if (inet_sk(sk)->is_icsk)
break;
retv = -EFAULT;
if (copy_from_user(&mreq, optval, sizeof(struct ipv6_mreq)))
break;
if (optname == IPV6_ADD_MEMBERSHIP)
retv = ipv6_sock_mc_join(sk, mreq.ipv6mr_ifindex, &mreq.ipv6mr_multiaddr);
else
retv = ipv6_sock_mc_drop(sk, mreq.ipv6mr_ifindex, &mreq.ipv6mr_multiaddr);
break;
}
case IPV6_JOIN_ANYCAST:
case IPV6_LEAVE_ANYCAST:
{
struct ipv6_mreq mreq;
if (optlen < sizeof(struct ipv6_mreq))
goto e_inval;
retv = -EFAULT;
if (copy_from_user(&mreq, optval, sizeof(struct ipv6_mreq)))
break;
if (optname == IPV6_JOIN_ANYCAST)
retv = ipv6_sock_ac_join(sk, mreq.ipv6mr_ifindex, &mreq.ipv6mr_acaddr);
else
retv = ipv6_sock_ac_drop(sk, mreq.ipv6mr_ifindex, &mreq.ipv6mr_acaddr);
break;
}
case MCAST_JOIN_GROUP:
case MCAST_LEAVE_GROUP:
{
struct group_req greq;
struct sockaddr_in6 *psin6;
if (optlen < sizeof(struct group_req))
goto e_inval;
retv = -EFAULT;
if (copy_from_user(&greq, optval, sizeof(struct group_req)))
break;
if (greq.gr_group.ss_family != AF_INET6) {
retv = -EADDRNOTAVAIL;
break;
}
psin6 = (struct sockaddr_in6 *)&greq.gr_group;
if (optname == MCAST_JOIN_GROUP)
retv = ipv6_sock_mc_join(sk, greq.gr_interface,
&psin6->sin6_addr);
else
retv = ipv6_sock_mc_drop(sk, greq.gr_interface,
&psin6->sin6_addr);
break;
}
case MCAST_JOIN_SOURCE_GROUP:
case MCAST_LEAVE_SOURCE_GROUP:
case MCAST_BLOCK_SOURCE:
case MCAST_UNBLOCK_SOURCE:
{
struct group_source_req greqs;
int omode, add;
if (optlen < sizeof(struct group_source_req))
goto e_inval;
if (copy_from_user(&greqs, optval, sizeof(greqs))) {
retv = -EFAULT;
break;
}
if (greqs.gsr_group.ss_family != AF_INET6 ||
greqs.gsr_source.ss_family != AF_INET6) {
retv = -EADDRNOTAVAIL;
break;
}
if (optname == MCAST_BLOCK_SOURCE) {
omode = MCAST_EXCLUDE;
add = 1;
} else if (optname == MCAST_UNBLOCK_SOURCE) {
omode = MCAST_EXCLUDE;
add = 0;
} else if (optname == MCAST_JOIN_SOURCE_GROUP) {
struct sockaddr_in6 *psin6;
psin6 = (struct sockaddr_in6 *)&greqs.gsr_group;
retv = ipv6_sock_mc_join(sk, greqs.gsr_interface,
&psin6->sin6_addr);
/* prior join w/ different source is ok */
if (retv && retv != -EADDRINUSE)
break;
omode = MCAST_INCLUDE;
add = 1;
} else /* MCAST_LEAVE_SOURCE_GROUP */ {
omode = MCAST_INCLUDE;
add = 0;
}
retv = ip6_mc_source(add, omode, sk, &greqs);
break;
}
case MCAST_MSFILTER:
{
extern int sysctl_mld_max_msf;
struct group_filter *gsf;
if (optlen < GROUP_FILTER_SIZE(0))
goto e_inval;
if (optlen > sysctl_optmem_max) {
retv = -ENOBUFS;
break;
}
gsf = kmalloc(optlen,GFP_KERNEL);
if (!gsf) {
retv = -ENOBUFS;
break;
}
retv = -EFAULT;
if (copy_from_user(gsf, optval, optlen)) {
kfree(gsf);
break;
}
/* numsrc >= (4G-140)/128 overflow in 32 bits */
if (gsf->gf_numsrc >= 0x1ffffffU ||
gsf->gf_numsrc > sysctl_mld_max_msf) {
kfree(gsf);
retv = -ENOBUFS;
break;
}
if (GROUP_FILTER_SIZE(gsf->gf_numsrc) > optlen) {
kfree(gsf);
retv = -EINVAL;
break;
}
retv = ip6_mc_msfilter(sk, gsf);
kfree(gsf);
break;
}
case IPV6_ROUTER_ALERT:
if (optlen < sizeof(int))
goto e_inval;
retv = ip6_ra_control(sk, val);
break;
case IPV6_MTU_DISCOVER:
if (optlen < sizeof(int))
goto e_inval;
if (val < IP_PMTUDISC_DONT || val > IP_PMTUDISC_PROBE)
goto e_inval;
np->pmtudisc = val;
retv = 0;
break;
case IPV6_MTU:
if (optlen < sizeof(int))
goto e_inval;
if (val && val < IPV6_MIN_MTU)
goto e_inval;
np->frag_size = val;
retv = 0;
break;
case IPV6_RECVERR:
if (optlen < sizeof(int))
goto e_inval;
np->recverr = valbool;
if (!val)
skb_queue_purge(&sk->sk_error_queue);
retv = 0;
break;
case IPV6_FLOWINFO_SEND:
if (optlen < sizeof(int))
goto e_inval;
np->sndflow = valbool;
retv = 0;
break;
case IPV6_FLOWLABEL_MGR:
retv = ipv6_flowlabel_opt(sk, optval, optlen);
break;
case IPV6_IPSEC_POLICY:
case IPV6_XFRM_POLICY:
retv = -EPERM;
if (!capable(CAP_NET_ADMIN))
break;
retv = xfrm_user_policy(sk, optname, optval, optlen);
break;
case IPV6_ADDR_PREFERENCES:
{
unsigned int pref = 0;
unsigned int prefmask = ~0;
if (optlen < sizeof(int))
goto e_inval;
retv = -EINVAL;
/* check PUBLIC/TMP/PUBTMP_DEFAULT conflicts */
switch (val & (IPV6_PREFER_SRC_PUBLIC|
IPV6_PREFER_SRC_TMP|
IPV6_PREFER_SRC_PUBTMP_DEFAULT)) {
case IPV6_PREFER_SRC_PUBLIC:
pref |= IPV6_PREFER_SRC_PUBLIC;
break;
case IPV6_PREFER_SRC_TMP:
pref |= IPV6_PREFER_SRC_TMP;
break;
case IPV6_PREFER_SRC_PUBTMP_DEFAULT:
break;
case 0:
goto pref_skip_pubtmp;
default:
goto e_inval;
}
prefmask &= ~(IPV6_PREFER_SRC_PUBLIC|
IPV6_PREFER_SRC_TMP);
pref_skip_pubtmp:
/* check HOME/COA conflicts */
switch (val & (IPV6_PREFER_SRC_HOME|IPV6_PREFER_SRC_COA)) {
case IPV6_PREFER_SRC_HOME:
break;
case IPV6_PREFER_SRC_COA:
pref |= IPV6_PREFER_SRC_COA;
case 0:
goto pref_skip_coa;
default:
goto e_inval;
}
prefmask &= ~IPV6_PREFER_SRC_COA;
pref_skip_coa:
/* check CGA/NONCGA conflicts */
switch (val & (IPV6_PREFER_SRC_CGA|IPV6_PREFER_SRC_NONCGA)) {
case IPV6_PREFER_SRC_CGA:
case IPV6_PREFER_SRC_NONCGA:
case 0:
break;
default:
goto e_inval;
}
np->srcprefs = (np->srcprefs & prefmask) | pref;
retv = 0;
break;
}
case IPV6_MINHOPCOUNT:
if (optlen < sizeof(int))
goto e_inval;
if (val < 0 || val > 255)
goto e_inval;
np->min_hopcount = val;
retv = 0;
break;
case IPV6_DONTFRAG:
np->dontfrag = valbool;
retv = 0;
break;
}
release_sock(sk);
return retv;
e_inval:
release_sock(sk);
return -EINVAL;
}
static struct sock *tcp_fastopen_create_child(struct sock *sk,
struct sk_buff *skb,
struct dst_entry *dst,
struct request_sock *req)
{
struct tcp_sock *tp;
struct request_sock_queue *queue = &inet_csk(sk)->icsk_accept_queue;
struct sock *child;
bool own_req;
req->num_retrans = 0;
req->num_timeout = 0;
req->sk = NULL;
child = inet_csk(sk)->icsk_af_ops->syn_recv_sock(sk, skb, req, NULL,
NULL, &own_req);
if (!child)
return NULL;
spin_lock(&queue->fastopenq.lock);
queue->fastopenq.qlen++;
spin_unlock(&queue->fastopenq.lock);
/* Initialize the child socket. Have to fix some values to take
* into account the child is a Fast Open socket and is created
* only out of the bits carried in the SYN packet.
*/
tp = tcp_sk(child);
tp->fastopen_rsk = req;
tcp_rsk(req)->tfo_listener = true;
/* RFC1323: The window in SYN & SYN/ACK segments is never
* scaled. So correct it appropriately.
*/
tp->snd_wnd = ntohs(tcp_hdr(skb)->window);
/* Activate the retrans timer so that SYNACK can be retransmitted.
* The request socket is not added to the ehash
* because it's been added to the accept queue directly.
*/
inet_csk_reset_xmit_timer(child, ICSK_TIME_RETRANS,
TCP_TIMEOUT_INIT, TCP_RTO_MAX);
atomic_set(&req->rsk_refcnt, 2);
/* Now finish processing the fastopen child socket. */
inet_csk(child)->icsk_af_ops->rebuild_header(child);
tcp_init_congestion_control(child);
tcp_mtup_init(child);
tcp_init_metrics(child);
tcp_init_buffer_space(child);
tp->rcv_nxt = TCP_SKB_CB(skb)->seq + 1;
tcp_fastopen_add_skb(child, skb);
tcp_rsk(req)->rcv_nxt = tp->rcv_nxt;
tp->rcv_wup = tp->rcv_nxt;
/* tcp_conn_request() is sending the SYNACK,
* and queues the child into listener accept queue.
*/
return child;
}
