static inline void dccp_do_pmtu_discovery(struct sock *sk,
const struct iphdr *iph,
u32 mtu)
{
struct dst_entry *dst;
const struct inet_sock *inet = inet_sk(sk);
const struct dccp_sock *dp = dccp_sk(sk);
if (sk->sk_state == DCCP_LISTEN)
return;
if ((dst = __sk_dst_check(sk, 0)) == NULL)
return;
dst->ops->update_pmtu(dst, mtu);
if (mtu < dst_mtu(dst) && ip_dont_fragment(sk, dst))
sk->sk_err_soft = EMSGSIZE;
mtu = dst_mtu(dst);
if (inet->pmtudisc != IP_PMTUDISC_DONT &&
inet_csk(sk)->icsk_pmtu_cookie > mtu) {
dccp_sync_mss(sk, mtu);
dccp_send_sync(sk, dp->dccps_gsr, DCCP_PKT_SYNC);
}
}
static int dccp_rcv_closereq(struct sock *sk, struct sk_buff *skb)
{
int queued = 0;
/*
* Step 7: Check for unexpected packet types
* If (S.is_server and P.type == CloseReq)
* Send Sync packet acknowledging P.seqno
* Drop packet and return
*/
if (dccp_sk(sk)->dccps_role != DCCP_ROLE_CLIENT) {
dccp_send_sync(sk, DCCP_SKB_CB(skb)->dccpd_seq, DCCP_PKT_SYNC);
return queued;
}
/* Step 13: process relevant Client states < CLOSEREQ */
switch (sk->sk_state) {
case DCCP_REQUESTING:
dccp_send_close(sk, 0);
dccp_set_state(sk, DCCP_CLOSING);
break;
case DCCP_OPEN:
case DCCP_PARTOPEN:
/* Give waiting application a chance to read pending data */
queued = 1;
dccp_fin(sk, skb);
dccp_set_state(sk, DCCP_PASSIVE_CLOSEREQ);
/* fall through */
case DCCP_PASSIVE_CLOSEREQ:
sk_wake_async(sk, SOCK_WAKE_WAITD, POLL_HUP);
}
return queued;
}
/**
* 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);
}
/*
* This routine does path mtu discovery as defined in RFC1191.
*/
static inline void dccp_do_pmtu_discovery(struct sock *sk,
const struct iphdr *iph,
u32 mtu)
{
struct dst_entry *dst;
const struct inet_sock *inet = inet_sk(sk);
const struct dccp_sock *dp = dccp_sk(sk);
/* We are not interested in DCCP_LISTEN and request_socks (RESPONSEs
* send out by Linux are always < 576bytes so they should go through
* unfragmented).
*/
if (sk->sk_state == DCCP_LISTEN)
return;
/* We don't check in the destentry if pmtu discovery is forbidden
* on this route. We just assume that no packet_to_big packets
* are send back when pmtu discovery is not active.
* There is a small race when the user changes this flag in the
* route, but I think that's acceptable.
*/
if ((dst = __sk_dst_check(sk, 0)) == NULL)
return;
dst->ops->update_pmtu(dst, mtu);
/* Something is about to be wrong... Remember soft error
* for the case, if this connection will not able to recover.
*/
if (mtu < dst_mtu(dst) && ip_dont_fragment(sk, dst))
sk->sk_err_soft = EMSGSIZE;
mtu = dst_mtu(dst);
if (inet->pmtudisc != IP_PMTUDISC_DONT &&
inet_csk(sk)->icsk_pmtu_cookie > mtu) {
dccp_sync_mss(sk, mtu);
/*
* From RFC 4340, sec. 14.1:
*
* DCCP-Sync packets are the best choice for upward
* probing, since DCCP-Sync probes do not risk application
* data loss.
*/
dccp_send_sync(sk, dp->dccps_gsr, DCCP_PKT_SYNC);
} /* else let the usual retransmit timer handle it */
}
static void dccp_rcv_closereq(struct sock *sk, struct sk_buff *skb)
{
/*
* Step 7: Check for unexpected packet types
* If (S.is_server and P.type == CloseReq)
* Send Sync packet acknowledging P.seqno
* Drop packet and return
*/
if (dccp_sk(sk)->dccps_role != DCCP_ROLE_CLIENT) {
dccp_send_sync(sk, DCCP_SKB_CB(skb)->dccpd_seq, DCCP_PKT_SYNC);
return;
}
if (sk->sk_state != DCCP_CLOSING)
dccp_set_state(sk, DCCP_CLOSING);
dccp_send_close(sk, 0);
}
/*
* This routine does path mtu discovery as defined in RFC1191.
*/
static inline void dccp_do_pmtu_discovery(struct sock *sk,
const struct iphdr *iph,
u32 mtu)
{
struct dst_entry *dst;
const struct inet_sock *inet = inet_sk(sk);
const struct dccp_sock *dp = dccp_sk(sk);
/* We are not interested in DCCP_LISTEN and request_socks (RESPONSEs
* send out by Linux are always < 576bytes so they should go through
* unfragmented).
*/
if (sk->sk_state == DCCP_LISTEN)
return;
dst = inet_csk_update_pmtu(sk, mtu);
if (!dst)
return;
/* Something is about to be wrong... Remember soft error
* for the case, if this connection will not able to recover.
*/
if (mtu < dst_mtu(dst) && ip_dont_fragment(sk, dst))
sk->sk_err_soft = EMSGSIZE;
mtu = dst_mtu(dst);
if (inet->pmtudisc != IP_PMTUDISC_DONT &&
ip_sk_accept_pmtu(sk) &&
inet_csk(sk)->icsk_pmtu_cookie > mtu) {
dccp_sync_mss(sk, mtu);
/*
* From RFC 4340, sec. 14.1:
*
* DCCP-Sync packets are the best choice for upward
* probing, since DCCP-Sync probes do not risk application
* data loss.
*/
dccp_send_sync(sk, dp->dccps_gsr, DCCP_PKT_SYNC);
} /* else let the usual retransmit timer handle it */
}
static int dccp_check_seqno(struct sock *sk, struct sk_buff *skb)
{
const struct dccp_hdr *dh = dccp_hdr(skb);
struct dccp_sock *dp = dccp_sk(sk);
u64 lswl, lawl;
/*
* Step 5: Prepare sequence numbers for Sync
* If P.type == Sync or P.type == SyncAck,
* If S.AWL <= P.ackno <= S.AWH and P.seqno >= S.SWL,
* / * P is valid, so update sequence number variables
* accordingly. After this update, P will pass the tests
* in Step 6. A SyncAck is generated if necessary in
* Step 15 * /
* Update S.GSR, S.SWL, S.SWH
* Otherwise,
* Drop packet and return
*/
if (dh->dccph_type == DCCP_PKT_SYNC ||
dh->dccph_type == DCCP_PKT_SYNCACK) {
if (between48(DCCP_SKB_CB(skb)->dccpd_ack_seq,
dp->dccps_awl, dp->dccps_awh) &&
!before48(DCCP_SKB_CB(skb)->dccpd_seq, dp->dccps_swl))
dccp_update_gsr(sk, DCCP_SKB_CB(skb)->dccpd_seq);
else
return -1;
}
/*
* Step 6: Check sequence numbers
* Let LSWL = S.SWL and LAWL = S.AWL
* If P.type == CloseReq or P.type == Close or P.type == Reset,
* LSWL := S.GSR + 1, LAWL := S.GAR
* If LSWL <= P.seqno <= S.SWH
* and (P.ackno does not exist or LAWL <= P.ackno <= S.AWH),
* Update S.GSR, S.SWL, S.SWH
* If P.type != Sync,
* Update S.GAR
* Otherwise,
* Send Sync packet acknowledging P.seqno
* Drop packet and return
*/
lswl = dp->dccps_swl;
lawl = dp->dccps_awl;
if (dh->dccph_type == DCCP_PKT_CLOSEREQ ||
dh->dccph_type == DCCP_PKT_CLOSE ||
dh->dccph_type == DCCP_PKT_RESET) {
lswl = dp->dccps_gsr;
dccp_inc_seqno(&lswl);
lawl = dp->dccps_gar;
}
if (between48(DCCP_SKB_CB(skb)->dccpd_seq, lswl, dp->dccps_swh) &&
(DCCP_SKB_CB(skb)->dccpd_ack_seq == DCCP_PKT_WITHOUT_ACK_SEQ ||
between48(DCCP_SKB_CB(skb)->dccpd_ack_seq,
lawl, dp->dccps_awh))) {
dccp_update_gsr(sk, DCCP_SKB_CB(skb)->dccpd_seq);
if (dh->dccph_type != DCCP_PKT_SYNC &&
(DCCP_SKB_CB(skb)->dccpd_ack_seq !=
DCCP_PKT_WITHOUT_ACK_SEQ))
dp->dccps_gar = DCCP_SKB_CB(skb)->dccpd_ack_seq;
} else {
DCCP_WARN("DCCP: Step 6 failed for %s packet, "
"(LSWL(%llu) <= P.seqno(%llu) <= S.SWH(%llu)) and "
"(P.ackno %s or LAWL(%llu) <= P.ackno(%llu) <= S.AWH(%llu), "
"sending SYNC...\n", dccp_packet_name(dh->dccph_type),
(unsigned long long) lswl,
(unsigned long long) DCCP_SKB_CB(skb)->dccpd_seq,
(unsigned long long) dp->dccps_swh,
(DCCP_SKB_CB(skb)->dccpd_ack_seq ==
DCCP_PKT_WITHOUT_ACK_SEQ) ? "doesn't exist" : "exists",
(unsigned long long) lawl,
(unsigned long long) DCCP_SKB_CB(skb)->dccpd_ack_seq,
(unsigned long long) dp->dccps_awh);
dccp_send_sync(sk, DCCP_SKB_CB(skb)->dccpd_seq, DCCP_PKT_SYNC);
return -1;
}
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_established(struct sock *sk, struct sk_buff *skb,
const struct dccp_hdr *dh, const unsigned len)
{
struct dccp_sock *dp = dccp_sk(sk);
switch (dccp_hdr(skb)->dccph_type) {
case DCCP_PKT_DATAACK:
case DCCP_PKT_DATA:
/*
* FIXME: check if sk_receive_queue is full, schedule DATA_DROPPED
* option if it is.
*/
__skb_pull(skb, dh->dccph_doff * 4);
__skb_queue_tail(&sk->sk_receive_queue, skb);
skb_set_owner_r(skb, sk);
sk->sk_data_ready(sk, 0);
return 0;
case DCCP_PKT_ACK:
goto discard;
case DCCP_PKT_RESET:
/*
* Step 9: Process Reset
* If P.type == Reset,
* Tear down connection
* S.state := TIMEWAIT
* Set TIMEWAIT timer
* Drop packet and return
*/
dccp_fin(sk, skb);
dccp_time_wait(sk, DCCP_TIME_WAIT, 0);
return 0;
case DCCP_PKT_CLOSEREQ:
dccp_rcv_closereq(sk, skb);
goto discard;
case DCCP_PKT_CLOSE:
dccp_rcv_close(sk, skb);
return 0;
case DCCP_PKT_REQUEST:
/* Step 7
* or (S.is_server and P.type == Response)
* or (S.is_client and P.type == Request)
* or (S.state >= OPEN and P.type == Request
* and P.seqno >= S.OSR)
* or (S.state >= OPEN and P.type == Response
* and P.seqno >= S.OSR)
* or (S.state == RESPOND and P.type == Data),
* Send Sync packet acknowledging P.seqno
* Drop packet and return
*/
if (dp->dccps_role != DCCP_ROLE_LISTEN)
goto send_sync;
goto check_seq;
case DCCP_PKT_RESPONSE:
if (dp->dccps_role != DCCP_ROLE_CLIENT)
goto send_sync;
check_seq:
if (!before48(DCCP_SKB_CB(skb)->dccpd_seq, dp->dccps_osr)) {
send_sync:
dccp_send_sync(sk, DCCP_SKB_CB(skb)->dccpd_seq,
DCCP_PKT_SYNC);
}
break;
case DCCP_PKT_SYNC:
dccp_send_sync(sk, DCCP_SKB_CB(skb)->dccpd_seq,
DCCP_PKT_SYNCACK);
/*
* From RFC 4340, sec. 5.7
*
* As with DCCP-Ack packets, DCCP-Sync and DCCP-SyncAck packets
* MAY have non-zero-length application data areas, whose
* contents receivers MUST ignore.
*/
goto discard;
}
DCCP_INC_STATS_BH(DCCP_MIB_INERRS);
discard:
__kfree_skb(skb);
return 0;
}
