int dccp_destroy_sock(struct sock *sk)
{
struct dccp_sock *dp = dccp_sk(sk);
struct dccp_minisock *dmsk = dccp_msk(sk);
/*
* DCCP doesn't use sk_write_queue, just sk_send_head
* for retransmissions
*/
if (sk->sk_send_head != NULL) {
kfree_skb(sk->sk_send_head);
sk->sk_send_head = NULL;
}
/* Clean up a referenced DCCP bind bucket. */
if (inet_csk(sk)->icsk_bind_hash != NULL)
inet_put_port(sk);
kfree(dp->dccps_service_list);
dp->dccps_service_list = NULL;
if (dmsk->dccpms_send_ack_vector) {
dccp_ackvec_free(dp->dccps_hc_rx_ackvec);
dp->dccps_hc_rx_ackvec = NULL;
}
ccid_hc_rx_delete(dp->dccps_hc_rx_ccid, sk);
ccid_hc_tx_delete(dp->dccps_hc_tx_ccid, sk);
dp->dccps_hc_rx_ccid = dp->dccps_hc_tx_ccid = NULL;
/* clean up feature negotiation state */
dccp_feat_clean(dmsk);
return 0;
}
static int jdccp_sendmsg(struct kiocb *iocb, struct sock *sk,
struct msghdr *msg, size_t size)
{
const struct dccp_minisock *dmsk = dccp_msk(sk);
const struct inet_sock *inet = inet_sk(sk);
const struct ccid3_hc_tx_sock *hctx;
if (dmsk->dccpms_tx_ccid == DCCPC_CCID3)
hctx = ccid3_hc_tx_sk(sk);
else
hctx = NULL;
if (port == 0 || ntohs(inet->dport) == port ||
ntohs(inet->sport) == port) {
if (hctx)
printl("%d.%d.%d.%d:%u %d.%d.%d.%d:%u %d %d %d %d %d\n",
NIPQUAD(inet->saddr), ntohs(inet->sport),
NIPQUAD(inet->daddr), ntohs(inet->dport), size,
hctx->ccid3hctx_s, hctx->ccid3hctx_rtt,
hctx->ccid3hctx_p, hctx->ccid3hctx_t_ipi);
else
printl("%d.%d.%d.%d:%u %d.%d.%d.%d:%u %d\n",
NIPQUAD(inet->saddr), ntohs(inet->sport),
NIPQUAD(inet->daddr), ntohs(inet->dport), size);
}
jprobe_return();
return 0;
}
/* byte 1 is feature. the rest is the preference list */
static int dccp_setsockopt_change(struct sock *sk, int type,
struct dccp_so_feat __user *optval)
{
struct dccp_so_feat opt;
u8 *val;
int rc;
if (copy_from_user(&opt, optval, sizeof(opt)))
return -EFAULT;
val = kmalloc(opt.dccpsf_len, GFP_KERNEL);
if (!val)
return -ENOMEM;
if (copy_from_user(val, opt.dccpsf_val, opt.dccpsf_len)) {
rc = -EFAULT;
goto out_free_val;
}
rc = dccp_feat_change(dccp_msk(sk), type, opt.dccpsf_feat,
val, opt.dccpsf_len, GFP_KERNEL);
if (rc)
goto out_free_val;
out:
return rc;
out_free_val:
kfree(val);
goto out;
}
int dccp_rcv_established(struct sock *sk, struct sk_buff *skb,
const struct dccp_hdr *dh, const unsigned len)
{
struct dccp_sock *dp = dccp_sk(sk);
if (dccp_check_seqno(sk, skb))
goto discard;
if (dccp_parse_options(sk, skb))
goto discard;
if (DCCP_SKB_CB(skb)->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;
ccid_hc_rx_packet_recv(dp->dccps_hc_rx_ccid, sk, skb);
ccid_hc_tx_packet_recv(dp->dccps_hc_tx_ccid, sk, skb);
return __dccp_rcv_established(sk, skb, dh, len);
discard:
__kfree_skb(skb);
return 0;
}
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;
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_INVALID_VALUE;
dp->dccps_l_ack_ratio = dp->dccps_r_ack_ratio = 1;
return 0;
}
static void dccp_event_ack_recv(struct sock *sk, struct sk_buff *skb)
{
struct dccp_sock *dp = dccp_sk(sk);
if (dccp_msk(sk)->dccpms_send_ack_vector)
dccp_ackvec_check_rcv_ackno(dp->dccps_hc_rx_ackvec, sk,
DCCP_SKB_CB(skb)->dccpd_ack_seq);
}
static void dccp_get_info(struct sock *sk, struct tcp_info *info)
{
struct dccp_sock *dp = dccp_sk(sk);
const struct inet_connection_sock *icsk = inet_csk(sk);
memset(info, 0, sizeof(*info));
info->tcpi_state = sk->sk_state;
info->tcpi_retransmits = icsk->icsk_retransmits;
info->tcpi_probes = icsk->icsk_probes_out;
info->tcpi_backoff = icsk->icsk_backoff;
info->tcpi_pmtu = icsk->icsk_pmtu_cookie;
if (dccp_msk(sk)->dccpms_send_ack_vector)
info->tcpi_options |= TCPI_OPT_SACK;
ccid_hc_rx_get_info(dp->dccps_hc_rx_ccid, sk, info);
ccid_hc_tx_get_info(dp->dccps_hc_tx_ccid, sk, info);
}
int dccp_rcv_established(struct sock *sk, struct sk_buff *skb,
const struct dccp_hdr *dh, const unsigned len)
{
struct dccp_sock *dp = dccp_sk(sk);
if (dccp_check_seqno(sk, skb))
goto discard;
if (dccp_parse_options(sk, skb))
goto discard;
if (DCCP_SKB_CB(skb)->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;
/*
* Deliver to the CCID module in charge.
* FIXME: Currently DCCP operates one-directional only, i.e. a listening
* server is not at the same time a connecting client. There is
* not much sense in delivering to both rx/tx sides at the moment
* (only one is active at a time); when moving to bidirectional
* service, this needs to be revised.
*/
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);
return __dccp_rcv_established(sk, skb, dh, len);
discard:
__kfree_skb(skb);
return 0;
}
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;
}
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;
}