void dccp_write_xmit(struct sock *sk, int block)
{
struct dccp_sock *dp = dccp_sk(sk);
struct sk_buff *skb;
while ((skb = skb_peek(&sk->sk_write_queue))) {
int err = ccid_hc_tx_send_packet(dp->dccps_hc_tx_ccid, sk, skb);
if (err > 0) {
if (!block) {
sk_reset_timer(sk, &dp->dccps_xmit_timer,
msecs_to_jiffies(err)+jiffies);
break;
} else
err = dccp_wait_for_ccid(sk, skb, err);
if (err && err != -EINTR)
DCCP_BUG("err=%d after dccp_wait_for_ccid", err);
}
skb_dequeue(&sk->sk_write_queue);
if (err == 0) {
struct dccp_skb_cb *dcb = DCCP_SKB_CB(skb);
const int len = skb->len;
if (sk->sk_state == DCCP_PARTOPEN) {
const u32 cur_mps = dp->dccps_mss_cache - DCCP_FEATNEG_OVERHEAD;
/*
* See 8.1.5 - Handshake Completion.
*
* For robustness we resend Confirm options until the client has
* entered OPEN. During the initial feature negotiation, the MPS
* is smaller than usual, reduced by the Change/Confirm options.
*/
if (!list_empty(&dp->dccps_featneg) && len > cur_mps) {
DCCP_WARN("Payload too large (%d) for featneg.\n", len);
dccp_send_ack(sk);
dccp_feat_list_purge(&dp->dccps_featneg);
}
inet_csk_schedule_ack(sk);
inet_csk_reset_xmit_timer(sk, ICSK_TIME_DACK,
inet_csk(sk)->icsk_rto,
DCCP_RTO_MAX);
dcb->dccpd_type = DCCP_PKT_DATAACK;
} else if (dccp_ack_pending(sk))
dcb->dccpd_type = DCCP_PKT_DATAACK;
else
dcb->dccpd_type = DCCP_PKT_DATA;
err = dccp_transmit_skb(sk, skb);
ccid_hc_tx_packet_sent(dp->dccps_hc_tx_ccid, sk, 0, len);
if (err)
DCCP_BUG("err=%d after ccid_hc_tx_packet_sent",
err);
} else {
dccp_pr_debug("packet discarded due to err=%d\n", err);
kfree_skb(skb);
}
}
}
int dccp_connect(struct sock *sk)
{
struct sk_buff *skb;
struct inet_connection_sock *icsk = inet_csk(sk);
dccp_connect_init(sk);
skb = alloc_skb(sk->sk_prot->max_header, sk->sk_allocation);
if (unlikely(skb == NULL))
return -ENOBUFS;
/* Reserve space for headers. */
skb_reserve(skb, sk->sk_prot->max_header);
DCCP_SKB_CB(skb)->dccpd_type = DCCP_PKT_REQUEST;
dccp_skb_entail(sk, skb);
dccp_transmit_skb(sk, skb_clone(skb, GFP_KERNEL));
DCCP_INC_STATS(DCCP_MIB_ACTIVEOPENS);
/* Timer for repeating the REQUEST until an answer. */
inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS,
icsk->icsk_rto, DCCP_RTO_MAX);
return 0;
}
/*
* Send a DCCP_PKT_CLOSE/CLOSEREQ. The caller locks the socket for us. This
* cannot be allowed to fail queueing a DCCP_PKT_CLOSE/CLOSEREQ frame under
* any circumstances.
*/
void dccp_send_close(struct sock *sk, const int active)
{
struct dccp_sock *dp = dccp_sk(sk);
struct sk_buff *skb;
const gfp_t prio = active ? GFP_KERNEL : GFP_ATOMIC;
skb = alloc_skb(sk->sk_prot->max_header, prio);
if (skb == NULL)
return;
/* Reserve space for headers and prepare control bits. */
skb_reserve(skb, sk->sk_prot->max_header);
if (dp->dccps_role == DCCP_ROLE_SERVER && !dp->dccps_server_timewait)
DCCP_SKB_CB(skb)->dccpd_type = DCCP_PKT_CLOSEREQ;
else
DCCP_SKB_CB(skb)->dccpd_type = DCCP_PKT_CLOSE;
if (active) {
skb = dccp_skb_entail(sk, skb);
/*
* Retransmission timer for active-close: RFC 4340, 8.3 requires
* to retransmit the Close/CloseReq until the CLOSING/CLOSEREQ
* state can be left. The initial timeout is 2 RTTs.
* Since RTT measurement is done by the CCIDs, there is no easy
* way to get an RTT sample. The fallback RTT from RFC 4340, 3.4
* is too low (200ms); we use a high value to avoid unnecessary
* retransmissions when the link RTT is > 0.2 seconds.
* FIXME: Let main module sample RTTs and use that instead.
*/
inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS,
DCCP_TIMEOUT_INIT, DCCP_RTO_MAX);
}
dccp_transmit_skb(sk, skb);
}
int dccp_connect(struct sock *sk)
{
struct sk_buff *skb;
struct inet_connection_sock *icsk = inet_csk(sk);
if (dccp_feat_finalise_settings(dccp_sk(sk)))
return -EPROTO;
dccp_connect_init(sk);
skb = alloc_skb(sk->sk_prot->max_header, sk->sk_allocation);
if (unlikely(skb == NULL))
return -ENOBUFS;
skb_reserve(skb, sk->sk_prot->max_header);
DCCP_SKB_CB(skb)->dccpd_type = DCCP_PKT_REQUEST;
dccp_skb_entail(sk, skb);
dccp_transmit_skb(sk, skb_clone(skb, GFP_KERNEL));
DCCP_INC_STATS(DCCP_MIB_ACTIVEOPENS);
inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS,
icsk->icsk_rto, DCCP_RTO_MAX);
return 0;
}
void dccp_send_close(struct sock *sk, const int active)
{
struct dccp_sock *dp = dccp_sk(sk);
struct sk_buff *skb;
const gfp_t prio = active ? GFP_KERNEL : GFP_ATOMIC;
skb = alloc_skb(sk->sk_prot->max_header, prio);
if (skb == NULL)
return;
skb_reserve(skb, sk->sk_prot->max_header);
if (dp->dccps_role == DCCP_ROLE_SERVER && !dp->dccps_server_timewait)
DCCP_SKB_CB(skb)->dccpd_type = DCCP_PKT_CLOSEREQ;
else
DCCP_SKB_CB(skb)->dccpd_type = DCCP_PKT_CLOSE;
if (active) {
dccp_write_xmit(sk, 1);
dccp_skb_entail(sk, skb);
dccp_transmit_skb(sk, skb_clone(skb, prio));
inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS,
DCCP_TIMEOUT_INIT, DCCP_RTO_MAX);
} else
dccp_transmit_skb(sk, skb);
}
int dccp_write_xmit(struct sock *sk, struct sk_buff *skb, long *timeo)
{
const struct dccp_sock *dp = dccp_sk(sk);
int err = ccid_hc_tx_send_packet(dp->dccps_hc_tx_ccid, sk, skb,
skb->len);
if (err > 0)
err = dccp_wait_for_ccid(sk, skb, timeo);
if (err == 0) {
struct dccp_skb_cb *dcb = DCCP_SKB_CB(skb);
const int len = skb->len;
if (sk->sk_state == DCCP_PARTOPEN) {
/* See 8.1.5. Handshake Completion */
inet_csk_schedule_ack(sk);
inet_csk_reset_xmit_timer(sk, ICSK_TIME_DACK,
inet_csk(sk)->icsk_rto,
DCCP_RTO_MAX);
dcb->dccpd_type = DCCP_PKT_DATAACK;
} else if (dccp_ack_pending(sk))
dcb->dccpd_type = DCCP_PKT_DATAACK;
else
dcb->dccpd_type = DCCP_PKT_DATA;
err = dccp_transmit_skb(sk, skb);
ccid_hc_tx_packet_sent(dp->dccps_hc_tx_ccid, sk, 0, len);
} else
kfree_skb(skb);
return err;
}
/**
* dccp_xmit_packet - Send data packet under control of CCID
* Transmits next-queued payload and informs CCID to account for the packet.
*/
static void dccp_xmit_packet(struct sock *sk)
{
int err, len;
struct dccp_sock *dp = dccp_sk(sk);
struct sk_buff *skb = dccp_qpolicy_pop(sk);
if (unlikely(skb == NULL))
return;
len = skb->len;
if (sk->sk_state == DCCP_PARTOPEN) {
const u32 cur_mps = dp->dccps_mss_cache - DCCP_FEATNEG_OVERHEAD;
/*
* See 8.1.5 - Handshake Completion.
*
* For robustness we resend Confirm options until the client has
* entered OPEN. During the initial feature negotiation, the MPS
* is smaller than usual, reduced by the Change/Confirm options.
*/
if (!list_empty(&dp->dccps_featneg) && len > cur_mps) {
DCCP_WARN("Payload too large (%d) for featneg.\n", len);
dccp_send_ack(sk);
dccp_feat_list_purge(&dp->dccps_featneg);
}
inet_csk_schedule_ack(sk);
inet_csk_reset_xmit_timer(sk, ICSK_TIME_DACK,
inet_csk(sk)->icsk_rto,
DCCP_RTO_MAX);
DCCP_SKB_CB(skb)->dccpd_type = DCCP_PKT_DATAACK;
} else if (dccp_ack_pending(sk)) {
DCCP_SKB_CB(skb)->dccpd_type = DCCP_PKT_DATAACK;
} else {
DCCP_SKB_CB(skb)->dccpd_type = DCCP_PKT_DATA;
}
err = dccp_transmit_skb(sk, skb);
if (err)
dccp_pr_debug("transmit_skb() returned err=%d\n", err);
/*
* Register this one as sent even if an error occurred. To the remote
* end a local packet drop is indistinguishable from network loss, i.e.
* any local drop will eventually be reported via receiver feedback.
*/
ccid_hc_tx_packet_sent(dp->dccps_hc_tx_ccid, sk, len);
/*
* If the CCID needs to transfer additional header options out-of-band
* (e.g. Ack Vectors or feature-negotiation options), it activates this
* flag to schedule a Sync. The Sync will automatically incorporate all
* currently pending header options, thus clearing the backlog.
*/
if (dp->dccps_sync_scheduled)
dccp_send_sync(sk, dp->dccps_gsr, DCCP_PKT_SYNC);
}
void dccp_write_xmit(struct sock *sk, int block)
{
struct dccp_sock *dp = dccp_sk(sk);
struct sk_buff *skb;
while ((skb = skb_peek(&sk->sk_write_queue))) {
int err = ccid_hc_tx_send_packet(dp->dccps_hc_tx_ccid, sk, skb);
if (err > 0) {
if (!block) {
sk_reset_timer(sk, &dp->dccps_xmit_timer,
msecs_to_jiffies(err)+jiffies);
break;
} else
err = dccp_wait_for_ccid(sk, skb, err);
if (err && err != -EINTR)
DCCP_BUG("err=%d after dccp_wait_for_ccid", err);
}
skb_dequeue(&sk->sk_write_queue);
if (err == 0) {
struct dccp_skb_cb *dcb = DCCP_SKB_CB(skb);
const int len = skb->len;
if (sk->sk_state == DCCP_PARTOPEN) {
const u32 cur_mps = dp->dccps_mss_cache - DCCP_FEATNEG_OVERHEAD;
if (!list_empty(&dp->dccps_featneg) && len > cur_mps) {
DCCP_WARN("Payload too large (%d) for featneg.\n", len);
dccp_send_ack(sk);
dccp_feat_list_purge(&dp->dccps_featneg);
}
inet_csk_schedule_ack(sk);
inet_csk_reset_xmit_timer(sk, ICSK_TIME_DACK,
inet_csk(sk)->icsk_rto,
DCCP_RTO_MAX);
dcb->dccpd_type = DCCP_PKT_DATAACK;
} else if (dccp_ack_pending(sk))
dcb->dccpd_type = DCCP_PKT_DATAACK;
else
dcb->dccpd_type = DCCP_PKT_DATA;
err = dccp_transmit_skb(sk, skb);
ccid_hc_tx_packet_sent(dp->dccps_hc_tx_ccid, sk, 0, len);
if (err)
DCCP_BUG("err=%d after ccid_hc_tx_packet_sent",
err);
} else {
dccp_pr_debug("packet discarded due to err=%d\n", err);
kfree_skb(skb);
}
}
}
void dccp_write_xmit(struct sock *sk, int block)
{
struct dccp_sock *dp = dccp_sk(sk);
struct sk_buff *skb;
long timeo = 30000; /* If a packet is taking longer than 2 secs
we have other issues */
while ((skb = skb_peek(&sk->sk_write_queue))) {
int err = ccid_hc_tx_send_packet(dp->dccps_hc_tx_ccid, sk, skb,
skb->len);
if (err > 0) {
if (!block) {
sk_reset_timer(sk, &dp->dccps_xmit_timer,
msecs_to_jiffies(err)+jiffies);
break;
} else
err = dccp_wait_for_ccid(sk, skb, &timeo);
if (err) {
printk(KERN_CRIT "%s:err at dccp_wait_for_ccid"
" %d\n", __FUNCTION__, err);
dump_stack();
}
}
skb_dequeue(&sk->sk_write_queue);
if (err == 0) {
struct dccp_skb_cb *dcb = DCCP_SKB_CB(skb);
const int len = skb->len;
if (sk->sk_state == DCCP_PARTOPEN) {
/* See 8.1.5. Handshake Completion */
inet_csk_schedule_ack(sk);
inet_csk_reset_xmit_timer(sk, ICSK_TIME_DACK,
inet_csk(sk)->icsk_rto,
DCCP_RTO_MAX);
dcb->dccpd_type = DCCP_PKT_DATAACK;
} else if (dccp_ack_pending(sk))
dcb->dccpd_type = DCCP_PKT_DATAACK;
else
dcb->dccpd_type = DCCP_PKT_DATA;
err = dccp_transmit_skb(sk, skb);
ccid_hc_tx_packet_sent(dp->dccps_hc_tx_ccid, sk, 0, len);
if (err) {
printk(KERN_CRIT "%s:err from "
"ccid_hc_tx_packet_sent %d\n",
__FUNCTION__, err);
dump_stack();
}
} else
kfree(skb);
}
}
void dccp_write_xmit(struct sock *sk, int block)
{
struct dccp_sock *dp = dccp_sk(sk);
struct sk_buff *skb;
while ((skb = skb_peek(&sk->sk_write_queue))) {
int err = ccid_hc_tx_send_packet(dp->dccps_hc_tx_ccid, sk, skb);
if (err > 0) {
if (!block) {
sk_reset_timer(sk, &dp->dccps_xmit_timer,
msecs_to_jiffies(err)+jiffies);
break;
} else
err = dccp_wait_for_ccid(sk, skb, err);
if (err && err != -EINTR)
DCCP_BUG("err=%d after dccp_wait_for_ccid", err);
}
skb_dequeue(&sk->sk_write_queue);
if (err == 0) {
struct dccp_skb_cb *dcb = DCCP_SKB_CB(skb);
const int len = skb->len;
if (sk->sk_state == DCCP_PARTOPEN) {
/* See 8.1.5. Handshake Completion */
inet_csk_schedule_ack(sk);
inet_csk_reset_xmit_timer(sk, ICSK_TIME_DACK,
inet_csk(sk)->icsk_rto,
DCCP_RTO_MAX);
dcb->dccpd_type = DCCP_PKT_DATAACK;
} else if (dccp_ack_pending(sk))
dcb->dccpd_type = DCCP_PKT_DATAACK;
else
dcb->dccpd_type = DCCP_PKT_DATA;
err = dccp_transmit_skb(sk, skb);
ccid_hc_tx_packet_sent(dp->dccps_hc_tx_ccid, sk, 0, len);
if (err)
DCCP_BUG("err=%d after ccid_hc_tx_packet_sent",
err);
} else {
dccp_pr_debug("packet discarded due to err=%d\n", err);
kfree_skb(skb);
}
}
}
void dccp_send_ack(struct sock *sk)
{
/* If we have been reset, we may not send again. */
if (sk->sk_state != DCCP_CLOSED) {
struct sk_buff *skb = alloc_skb(sk->sk_prot->max_header,
GFP_ATOMIC);
if (skb == NULL) {
inet_csk_schedule_ack(sk);
inet_csk(sk)->icsk_ack.ato = TCP_ATO_MIN;
inet_csk_reset_xmit_timer(sk, ICSK_TIME_DACK,
TCP_DELACK_MAX,
DCCP_RTO_MAX);
return;
}
/* Reserve space for headers */
skb_reserve(skb, sk->sk_prot->max_header);
DCCP_SKB_CB(skb)->dccpd_type = DCCP_PKT_ACK;
dccp_transmit_skb(sk, skb);
}
}
/*
* Do all connect socket setups that can be done AF independent.
*/
int dccp_connect(struct sock *sk)
{
struct sk_buff *skb;
struct dccp_sock *dp = dccp_sk(sk);
struct dst_entry *dst = __sk_dst_get(sk);
struct inet_connection_sock *icsk = inet_csk(sk);
sk->sk_err = 0;
sock_reset_flag(sk, SOCK_DONE);
dccp_sync_mss(sk, dst_mtu(dst));
/* do not connect if feature negotiation setup fails */
if (dccp_feat_finalise_settings(dccp_sk(sk)))
return -EPROTO;
/* Initialise GAR as per 8.5; AWL/AWH are set in dccp_transmit_skb() */
dp->dccps_gar = dp->dccps_iss;
skb = alloc_skb(sk->sk_prot->max_header, sk->sk_allocation);
if (unlikely(skb == NULL))
return -ENOBUFS;
/* Reserve space for headers. */
skb_reserve(skb, sk->sk_prot->max_header);
DCCP_SKB_CB(skb)->dccpd_type = DCCP_PKT_REQUEST;
dccp_transmit_skb(sk, dccp_skb_entail(sk, skb));
DCCP_INC_STATS(DCCP_MIB_ACTIVEOPENS);
/* Timer for repeating the REQUEST until an answer. */
icsk->icsk_retransmits = 0;
inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS,
icsk->icsk_rto, DCCP_RTO_MAX);
return 0;
}
void dccp_close(struct sock *sk, long timeout)
{
struct sk_buff *skb;
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;
}
/*
* 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:
/*
* 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));
sock_hold(sk);
sock_orphan(sk);
/*
* 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
}
atomic_inc(sk->sk_prot->orphan_count);
if (sk->sk_state == DCCP_CLOSED)
inet_csk_destroy_sock(sk);
/* Otherwise, socket is reprieved until protocol close. */
bh_unlock_sock(sk);
local_bh_enable();
sock_put(sk);
}
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;
struct request_sock_queue *queue = &inet_csk(sk)->icsk_accept_queue;
struct sock *child;
u32 end_seq;
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)
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;
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 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);
atomic_set(&req->rsk_refcnt, 1);
/* 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.
* Note that IPv6 might also have used skb_get() trick
* in tcp_v6_conn_request() to keep this SYN around (treq->pktopts)
* So we need to eventually get a clone of the packet,
* before inserting it in sk_receive_queue.
*
* 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?
*/
end_seq = TCP_SKB_CB(skb)->end_seq;
if (end_seq != TCP_SKB_CB(skb)->seq + 1) {
struct sk_buff *skb2;
if (unlikely(skb_shared(skb)))
skb2 = skb_clone(skb, GFP_ATOMIC);
else
skb2 = skb_get(skb);
if (likely(skb2)) {
skb_dst_drop(skb2);
__skb_pull(skb2, tcp_hdrlen(skb));
skb_set_owner_r(skb2, child);
__skb_queue_tail(&child->sk_receive_queue, skb2);
tp->syn_data_acked = 1;
/* u64_stats_update_begin(&tp->syncp) not needed here,
* as we certainly are not changing upper 32bit value (0)
*/
tp->bytes_received = end_seq - TCP_SKB_CB(skb)->seq - 1;
} else {
end_seq = TCP_SKB_CB(skb)->seq + 1;
}
}
tcp_rsk(req)->rcv_nxt = tp->rcv_nxt = end_seq;
sk->sk_data_ready(sk);
bh_unlock_sock(child);
sock_put(child);
WARN_ON(!req->sk);
return true;
}
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);
tp->max_window = tp->snd_wnd;
/* 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;
}
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;
}