linux/net/dccp/input.c

725 lines
21 KiB
C
Raw Normal View History

/*
* net/dccp/input.c
*
* An implementation of the DCCP protocol
* Arnaldo Carvalho de Melo <acme@conectiva.com.br>
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public License
* as published by the Free Software Foundation; either version
* 2 of the License, or (at your option) any later version.
*/
#include <linux/dccp.h>
#include <linux/skbuff.h>
#include <net/sock.h>
#include "ackvec.h"
#include "ccid.h"
#include "dccp.h"
/* rate-limit for syncs in reply to sequence-invalid packets; RFC 4340, 7.5.4 */
int sysctl_dccp_sync_ratelimit __read_mostly = HZ / 8;
static void dccp_enqueue_skb(struct sock *sk, struct sk_buff *skb)
{
__skb_pull(skb, dccp_hdr(skb)->dccph_doff * 4);
__skb_queue_tail(&sk->sk_receive_queue, skb);
skb_set_owner_r(skb, sk);
sk->sk_data_ready(sk, 0);
}
static void dccp_fin(struct sock *sk, struct sk_buff *skb)
{
/*
* On receiving Close/CloseReq, both RD/WR shutdown are performed.
* RFC 4340, 8.3 says that we MAY send further Data/DataAcks after
* receiving the closing segment, but there is no guarantee that such
* data will be processed at all.
*/
sk->sk_shutdown = SHUTDOWN_MASK;
sock_set_flag(sk, SOCK_DONE);
dccp_enqueue_skb(sk, skb);
}
[DCCP]: Integrate state transitions for passive-close This adds the necessary state transitions for the two forms of passive-close * PASSIVE_CLOSE - which is entered when a host receives a Close; * PASSIVE_CLOSEREQ - which is entered when a client receives a CloseReq. Here is a detailed account of what the patch does in each state. 1) Receiving CloseReq The pseudo-code in 8.5 says: Step 13: Process CloseReq If P.type == CloseReq and S.state < CLOSEREQ, Generate Close S.state := CLOSING Set CLOSING timer. This means we need to address what to do in CLOSED, LISTEN, REQUEST, RESPOND, PARTOPEN, and OPEN. * CLOSED: silently ignore - it may be a late or duplicate CloseReq; * LISTEN/RESPOND: will not appear, since Step 7 is performed first (we know we are the client); * REQUEST: perform Step 13 directly (no need to enqueue packet); * OPEN/PARTOPEN: enter PASSIVE_CLOSEREQ so that the application has a chance to process unread data. When already in PASSIVE_CLOSEREQ, no second CloseReq is enqueued. In any other state, the CloseReq is ignored. I think that this offers some robustness against rare and pathological cases: e.g. a simultaneous close where the client sends a Close and the server a CloseReq. The client will then be retransmitting its Close until it gets the Reset, so ignoring the CloseReq while in state CLOSING is sane. 2) Receiving Close The code below from 8.5 is unconditional. Step 14: Process Close If P.type == Close, Generate Reset(Closed) Tear down connection Drop packet and return Thus we need to consider all states: * CLOSED: silently ignore, since this can happen when a retransmitted or late Close arrives; * LISTEN: dccp_rcv_state_process() will generate a Reset ("No Connection"); * REQUEST: perform Step 14 directly (no need to enqueue packet); * RESPOND: dccp_check_req() will generate a Reset ("Packet Error") -- left it at that; * OPEN/PARTOPEN: enter PASSIVE_CLOSE so that application has a chance to process unread data; * CLOSEREQ: server performed active-close -- perform Step 14; * CLOSING: simultaneous-close: use a tie-breaker to avoid message ping-pong (see comment); * PASSIVE_CLOSEREQ: ignore - the peer has a bug (sending first a CloseReq and now a Close); * TIMEWAIT: packet is ignored. Note that the condition of receiving a packet in state CLOSED here is different from the condition "there is no socket for such a connection": the socket still exists, but its state indicates it is unusable. Last, dccp_finish_passive_close sets either DCCP_CLOSED or DCCP_CLOSING = TCP_CLOSING, so that sk_stream_wait_close() will wait for the final Reset (which will trigger CLOSING => CLOSED). Signed-off-by: Gerrit Renker <gerrit@erg.abdn.ac.uk> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2007-11-28 13:59:48 +00:00
static int dccp_rcv_close(struct sock *sk, struct sk_buff *skb)
{
[DCCP]: Integrate state transitions for passive-close This adds the necessary state transitions for the two forms of passive-close * PASSIVE_CLOSE - which is entered when a host receives a Close; * PASSIVE_CLOSEREQ - which is entered when a client receives a CloseReq. Here is a detailed account of what the patch does in each state. 1) Receiving CloseReq The pseudo-code in 8.5 says: Step 13: Process CloseReq If P.type == CloseReq and S.state < CLOSEREQ, Generate Close S.state := CLOSING Set CLOSING timer. This means we need to address what to do in CLOSED, LISTEN, REQUEST, RESPOND, PARTOPEN, and OPEN. * CLOSED: silently ignore - it may be a late or duplicate CloseReq; * LISTEN/RESPOND: will not appear, since Step 7 is performed first (we know we are the client); * REQUEST: perform Step 13 directly (no need to enqueue packet); * OPEN/PARTOPEN: enter PASSIVE_CLOSEREQ so that the application has a chance to process unread data. When already in PASSIVE_CLOSEREQ, no second CloseReq is enqueued. In any other state, the CloseReq is ignored. I think that this offers some robustness against rare and pathological cases: e.g. a simultaneous close where the client sends a Close and the server a CloseReq. The client will then be retransmitting its Close until it gets the Reset, so ignoring the CloseReq while in state CLOSING is sane. 2) Receiving Close The code below from 8.5 is unconditional. Step 14: Process Close If P.type == Close, Generate Reset(Closed) Tear down connection Drop packet and return Thus we need to consider all states: * CLOSED: silently ignore, since this can happen when a retransmitted or late Close arrives; * LISTEN: dccp_rcv_state_process() will generate a Reset ("No Connection"); * REQUEST: perform Step 14 directly (no need to enqueue packet); * RESPOND: dccp_check_req() will generate a Reset ("Packet Error") -- left it at that; * OPEN/PARTOPEN: enter PASSIVE_CLOSE so that application has a chance to process unread data; * CLOSEREQ: server performed active-close -- perform Step 14; * CLOSING: simultaneous-close: use a tie-breaker to avoid message ping-pong (see comment); * PASSIVE_CLOSEREQ: ignore - the peer has a bug (sending first a CloseReq and now a Close); * TIMEWAIT: packet is ignored. Note that the condition of receiving a packet in state CLOSED here is different from the condition "there is no socket for such a connection": the socket still exists, but its state indicates it is unusable. Last, dccp_finish_passive_close sets either DCCP_CLOSED or DCCP_CLOSING = TCP_CLOSING, so that sk_stream_wait_close() will wait for the final Reset (which will trigger CLOSING => CLOSED). Signed-off-by: Gerrit Renker <gerrit@erg.abdn.ac.uk> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2007-11-28 13:59:48 +00:00
int queued = 0;
switch (sk->sk_state) {
/*
* We ignore Close when received in one of the following states:
* - CLOSED (may be a late or duplicate packet)
* - PASSIVE_CLOSEREQ (the peer has sent a CloseReq earlier)
* - RESPOND (already handled by dccp_check_req)
*/
case DCCP_CLOSING:
/*
* Simultaneous-close: receiving a Close after sending one. This
* can happen if both client and server perform active-close and
* will result in an endless ping-pong of crossing and retrans-
* mitted Close packets, which only terminates when one of the
* nodes times out (min. 64 seconds). Quicker convergence can be
* achieved when one of the nodes acts as tie-breaker.
* This is ok as both ends are done with data transfer and each
* end is just waiting for the other to acknowledge termination.
*/
if (dccp_sk(sk)->dccps_role != DCCP_ROLE_CLIENT)
break;
/* fall through */
case DCCP_REQUESTING:
case DCCP_ACTIVE_CLOSEREQ:
dccp_send_reset(sk, DCCP_RESET_CODE_CLOSED);
dccp_done(sk);
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_CLOSE);
/* fall through */
case DCCP_PASSIVE_CLOSE:
/*
* Retransmitted Close: we have already enqueued the first one.
*/
sk_wake_async(sk, SOCK_WAKE_WAITD, POLL_HUP);
}
return queued;
}
[DCCP]: Integrate state transitions for passive-close This adds the necessary state transitions for the two forms of passive-close * PASSIVE_CLOSE - which is entered when a host receives a Close; * PASSIVE_CLOSEREQ - which is entered when a client receives a CloseReq. Here is a detailed account of what the patch does in each state. 1) Receiving CloseReq The pseudo-code in 8.5 says: Step 13: Process CloseReq If P.type == CloseReq and S.state < CLOSEREQ, Generate Close S.state := CLOSING Set CLOSING timer. This means we need to address what to do in CLOSED, LISTEN, REQUEST, RESPOND, PARTOPEN, and OPEN. * CLOSED: silently ignore - it may be a late or duplicate CloseReq; * LISTEN/RESPOND: will not appear, since Step 7 is performed first (we know we are the client); * REQUEST: perform Step 13 directly (no need to enqueue packet); * OPEN/PARTOPEN: enter PASSIVE_CLOSEREQ so that the application has a chance to process unread data. When already in PASSIVE_CLOSEREQ, no second CloseReq is enqueued. In any other state, the CloseReq is ignored. I think that this offers some robustness against rare and pathological cases: e.g. a simultaneous close where the client sends a Close and the server a CloseReq. The client will then be retransmitting its Close until it gets the Reset, so ignoring the CloseReq while in state CLOSING is sane. 2) Receiving Close The code below from 8.5 is unconditional. Step 14: Process Close If P.type == Close, Generate Reset(Closed) Tear down connection Drop packet and return Thus we need to consider all states: * CLOSED: silently ignore, since this can happen when a retransmitted or late Close arrives; * LISTEN: dccp_rcv_state_process() will generate a Reset ("No Connection"); * REQUEST: perform Step 14 directly (no need to enqueue packet); * RESPOND: dccp_check_req() will generate a Reset ("Packet Error") -- left it at that; * OPEN/PARTOPEN: enter PASSIVE_CLOSE so that application has a chance to process unread data; * CLOSEREQ: server performed active-close -- perform Step 14; * CLOSING: simultaneous-close: use a tie-breaker to avoid message ping-pong (see comment); * PASSIVE_CLOSEREQ: ignore - the peer has a bug (sending first a CloseReq and now a Close); * TIMEWAIT: packet is ignored. Note that the condition of receiving a packet in state CLOSED here is different from the condition "there is no socket for such a connection": the socket still exists, but its state indicates it is unusable. Last, dccp_finish_passive_close sets either DCCP_CLOSED or DCCP_CLOSING = TCP_CLOSING, so that sk_stream_wait_close() will wait for the final Reset (which will trigger CLOSING => CLOSED). Signed-off-by: Gerrit Renker <gerrit@erg.abdn.ac.uk> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2007-11-28 13:59:48 +00:00
static int dccp_rcv_closereq(struct sock *sk, struct sk_buff *skb)
{
[DCCP]: Integrate state transitions for passive-close This adds the necessary state transitions for the two forms of passive-close * PASSIVE_CLOSE - which is entered when a host receives a Close; * PASSIVE_CLOSEREQ - which is entered when a client receives a CloseReq. Here is a detailed account of what the patch does in each state. 1) Receiving CloseReq The pseudo-code in 8.5 says: Step 13: Process CloseReq If P.type == CloseReq and S.state < CLOSEREQ, Generate Close S.state := CLOSING Set CLOSING timer. This means we need to address what to do in CLOSED, LISTEN, REQUEST, RESPOND, PARTOPEN, and OPEN. * CLOSED: silently ignore - it may be a late or duplicate CloseReq; * LISTEN/RESPOND: will not appear, since Step 7 is performed first (we know we are the client); * REQUEST: perform Step 13 directly (no need to enqueue packet); * OPEN/PARTOPEN: enter PASSIVE_CLOSEREQ so that the application has a chance to process unread data. When already in PASSIVE_CLOSEREQ, no second CloseReq is enqueued. In any other state, the CloseReq is ignored. I think that this offers some robustness against rare and pathological cases: e.g. a simultaneous close where the client sends a Close and the server a CloseReq. The client will then be retransmitting its Close until it gets the Reset, so ignoring the CloseReq while in state CLOSING is sane. 2) Receiving Close The code below from 8.5 is unconditional. Step 14: Process Close If P.type == Close, Generate Reset(Closed) Tear down connection Drop packet and return Thus we need to consider all states: * CLOSED: silently ignore, since this can happen when a retransmitted or late Close arrives; * LISTEN: dccp_rcv_state_process() will generate a Reset ("No Connection"); * REQUEST: perform Step 14 directly (no need to enqueue packet); * RESPOND: dccp_check_req() will generate a Reset ("Packet Error") -- left it at that; * OPEN/PARTOPEN: enter PASSIVE_CLOSE so that application has a chance to process unread data; * CLOSEREQ: server performed active-close -- perform Step 14; * CLOSING: simultaneous-close: use a tie-breaker to avoid message ping-pong (see comment); * PASSIVE_CLOSEREQ: ignore - the peer has a bug (sending first a CloseReq and now a Close); * TIMEWAIT: packet is ignored. Note that the condition of receiving a packet in state CLOSED here is different from the condition "there is no socket for such a connection": the socket still exists, but its state indicates it is unusable. Last, dccp_finish_passive_close sets either DCCP_CLOSED or DCCP_CLOSING = TCP_CLOSING, so that sk_stream_wait_close() will wait for the final Reset (which will trigger CLOSING => CLOSED). Signed-off-by: Gerrit Renker <gerrit@erg.abdn.ac.uk> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2007-11-28 13:59:48 +00:00
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);
[DCCP]: Integrate state transitions for passive-close This adds the necessary state transitions for the two forms of passive-close * PASSIVE_CLOSE - which is entered when a host receives a Close; * PASSIVE_CLOSEREQ - which is entered when a client receives a CloseReq. Here is a detailed account of what the patch does in each state. 1) Receiving CloseReq The pseudo-code in 8.5 says: Step 13: Process CloseReq If P.type == CloseReq and S.state < CLOSEREQ, Generate Close S.state := CLOSING Set CLOSING timer. This means we need to address what to do in CLOSED, LISTEN, REQUEST, RESPOND, PARTOPEN, and OPEN. * CLOSED: silently ignore - it may be a late or duplicate CloseReq; * LISTEN/RESPOND: will not appear, since Step 7 is performed first (we know we are the client); * REQUEST: perform Step 13 directly (no need to enqueue packet); * OPEN/PARTOPEN: enter PASSIVE_CLOSEREQ so that the application has a chance to process unread data. When already in PASSIVE_CLOSEREQ, no second CloseReq is enqueued. In any other state, the CloseReq is ignored. I think that this offers some robustness against rare and pathological cases: e.g. a simultaneous close where the client sends a Close and the server a CloseReq. The client will then be retransmitting its Close until it gets the Reset, so ignoring the CloseReq while in state CLOSING is sane. 2) Receiving Close The code below from 8.5 is unconditional. Step 14: Process Close If P.type == Close, Generate Reset(Closed) Tear down connection Drop packet and return Thus we need to consider all states: * CLOSED: silently ignore, since this can happen when a retransmitted or late Close arrives; * LISTEN: dccp_rcv_state_process() will generate a Reset ("No Connection"); * REQUEST: perform Step 14 directly (no need to enqueue packet); * RESPOND: dccp_check_req() will generate a Reset ("Packet Error") -- left it at that; * OPEN/PARTOPEN: enter PASSIVE_CLOSE so that application has a chance to process unread data; * CLOSEREQ: server performed active-close -- perform Step 14; * CLOSING: simultaneous-close: use a tie-breaker to avoid message ping-pong (see comment); * PASSIVE_CLOSEREQ: ignore - the peer has a bug (sending first a CloseReq and now a Close); * TIMEWAIT: packet is ignored. Note that the condition of receiving a packet in state CLOSED here is different from the condition "there is no socket for such a connection": the socket still exists, but its state indicates it is unusable. Last, dccp_finish_passive_close sets either DCCP_CLOSED or DCCP_CLOSING = TCP_CLOSING, so that sk_stream_wait_close() will wait for the final Reset (which will trigger CLOSING => CLOSED). Signed-off-by: Gerrit Renker <gerrit@erg.abdn.ac.uk> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2007-11-28 13:59:48 +00:00
return queued;
}
[DCCP]: Integrate state transitions for passive-close This adds the necessary state transitions for the two forms of passive-close * PASSIVE_CLOSE - which is entered when a host receives a Close; * PASSIVE_CLOSEREQ - which is entered when a client receives a CloseReq. Here is a detailed account of what the patch does in each state. 1) Receiving CloseReq The pseudo-code in 8.5 says: Step 13: Process CloseReq If P.type == CloseReq and S.state < CLOSEREQ, Generate Close S.state := CLOSING Set CLOSING timer. This means we need to address what to do in CLOSED, LISTEN, REQUEST, RESPOND, PARTOPEN, and OPEN. * CLOSED: silently ignore - it may be a late or duplicate CloseReq; * LISTEN/RESPOND: will not appear, since Step 7 is performed first (we know we are the client); * REQUEST: perform Step 13 directly (no need to enqueue packet); * OPEN/PARTOPEN: enter PASSIVE_CLOSEREQ so that the application has a chance to process unread data. When already in PASSIVE_CLOSEREQ, no second CloseReq is enqueued. In any other state, the CloseReq is ignored. I think that this offers some robustness against rare and pathological cases: e.g. a simultaneous close where the client sends a Close and the server a CloseReq. The client will then be retransmitting its Close until it gets the Reset, so ignoring the CloseReq while in state CLOSING is sane. 2) Receiving Close The code below from 8.5 is unconditional. Step 14: Process Close If P.type == Close, Generate Reset(Closed) Tear down connection Drop packet and return Thus we need to consider all states: * CLOSED: silently ignore, since this can happen when a retransmitted or late Close arrives; * LISTEN: dccp_rcv_state_process() will generate a Reset ("No Connection"); * REQUEST: perform Step 14 directly (no need to enqueue packet); * RESPOND: dccp_check_req() will generate a Reset ("Packet Error") -- left it at that; * OPEN/PARTOPEN: enter PASSIVE_CLOSE so that application has a chance to process unread data; * CLOSEREQ: server performed active-close -- perform Step 14; * CLOSING: simultaneous-close: use a tie-breaker to avoid message ping-pong (see comment); * PASSIVE_CLOSEREQ: ignore - the peer has a bug (sending first a CloseReq and now a Close); * TIMEWAIT: packet is ignored. Note that the condition of receiving a packet in state CLOSED here is different from the condition "there is no socket for such a connection": the socket still exists, but its state indicates it is unusable. Last, dccp_finish_passive_close sets either DCCP_CLOSED or DCCP_CLOSING = TCP_CLOSING, so that sk_stream_wait_close() will wait for the final Reset (which will trigger CLOSING => CLOSED). Signed-off-by: Gerrit Renker <gerrit@erg.abdn.ac.uk> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2007-11-28 13:59:48 +00:00
/* 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);
[DCCP]: Integrate state transitions for passive-close This adds the necessary state transitions for the two forms of passive-close * PASSIVE_CLOSE - which is entered when a host receives a Close; * PASSIVE_CLOSEREQ - which is entered when a client receives a CloseReq. Here is a detailed account of what the patch does in each state. 1) Receiving CloseReq The pseudo-code in 8.5 says: Step 13: Process CloseReq If P.type == CloseReq and S.state < CLOSEREQ, Generate Close S.state := CLOSING Set CLOSING timer. This means we need to address what to do in CLOSED, LISTEN, REQUEST, RESPOND, PARTOPEN, and OPEN. * CLOSED: silently ignore - it may be a late or duplicate CloseReq; * LISTEN/RESPOND: will not appear, since Step 7 is performed first (we know we are the client); * REQUEST: perform Step 13 directly (no need to enqueue packet); * OPEN/PARTOPEN: enter PASSIVE_CLOSEREQ so that the application has a chance to process unread data. When already in PASSIVE_CLOSEREQ, no second CloseReq is enqueued. In any other state, the CloseReq is ignored. I think that this offers some robustness against rare and pathological cases: e.g. a simultaneous close where the client sends a Close and the server a CloseReq. The client will then be retransmitting its Close until it gets the Reset, so ignoring the CloseReq while in state CLOSING is sane. 2) Receiving Close The code below from 8.5 is unconditional. Step 14: Process Close If P.type == Close, Generate Reset(Closed) Tear down connection Drop packet and return Thus we need to consider all states: * CLOSED: silently ignore, since this can happen when a retransmitted or late Close arrives; * LISTEN: dccp_rcv_state_process() will generate a Reset ("No Connection"); * REQUEST: perform Step 14 directly (no need to enqueue packet); * RESPOND: dccp_check_req() will generate a Reset ("Packet Error") -- left it at that; * OPEN/PARTOPEN: enter PASSIVE_CLOSE so that application has a chance to process unread data; * CLOSEREQ: server performed active-close -- perform Step 14; * CLOSING: simultaneous-close: use a tie-breaker to avoid message ping-pong (see comment); * PASSIVE_CLOSEREQ: ignore - the peer has a bug (sending first a CloseReq and now a Close); * TIMEWAIT: packet is ignored. Note that the condition of receiving a packet in state CLOSED here is different from the condition "there is no socket for such a connection": the socket still exists, but its state indicates it is unusable. Last, dccp_finish_passive_close sets either DCCP_CLOSED or DCCP_CLOSING = TCP_CLOSING, so that sk_stream_wait_close() will wait for the final Reset (which will trigger CLOSING => CLOSED). Signed-off-by: Gerrit Renker <gerrit@erg.abdn.ac.uk> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2007-11-28 13:59:48 +00:00
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;
}
static u8 dccp_reset_code_convert(const u8 code)
{
const u8 error_code[] = {
[DCCP_RESET_CODE_CLOSED] = 0, /* normal termination */
[DCCP_RESET_CODE_UNSPECIFIED] = 0, /* nothing known */
[DCCP_RESET_CODE_ABORTED] = ECONNRESET,
[DCCP_RESET_CODE_NO_CONNECTION] = ECONNREFUSED,
[DCCP_RESET_CODE_CONNECTION_REFUSED] = ECONNREFUSED,
[DCCP_RESET_CODE_TOO_BUSY] = EUSERS,
[DCCP_RESET_CODE_AGGRESSION_PENALTY] = EDQUOT,
[DCCP_RESET_CODE_PACKET_ERROR] = ENOMSG,
[DCCP_RESET_CODE_BAD_INIT_COOKIE] = EBADR,
[DCCP_RESET_CODE_BAD_SERVICE_CODE] = EBADRQC,
[DCCP_RESET_CODE_OPTION_ERROR] = EILSEQ,
[DCCP_RESET_CODE_MANDATORY_ERROR] = EOPNOTSUPP,
};
return code >= DCCP_MAX_RESET_CODES ? 0 : error_code[code];
}
static void dccp_rcv_reset(struct sock *sk, struct sk_buff *skb)
{
u8 err = dccp_reset_code_convert(dccp_hdr_reset(skb)->dccph_reset_code);
sk->sk_err = err;
/* Queue the equivalent of TCP fin so that dccp_recvmsg exits the loop */
dccp_fin(sk, skb);
if (err && !sock_flag(sk, SOCK_DEAD))
sk_wake_async(sk, SOCK_WAKE_IO, POLL_ERR);
dccp_time_wait(sk, DCCP_TIME_WAIT, 0);
}
static void dccp_handle_ackvec_processing(struct sock *sk, struct sk_buff *skb)
{
struct dccp_ackvec *av = dccp_sk(sk)->dccps_hc_rx_ackvec;
if (av == NULL)
return;
if (DCCP_SKB_CB(skb)->dccpd_ack_seq != DCCP_PKT_WITHOUT_ACK_SEQ)
dccp_ackvec_clear_state(av, DCCP_SKB_CB(skb)->dccpd_ack_seq);
dccp_ackvec_input(av, skb);
}
[DCCP]: Honour and make use of shutdown option set by user This extends the DCCP socket API by honouring any shutdown(2) option set by the user. The behaviour is, as much as possible, made consistent with the API for TCP's shutdown. This patch exploits the information provided by the user via the socket API to reduce processing costs: * if the read end is closed (SHUT_RD), it is not necessary to deliver to input CCID; * if the write end is closed (SHUT_WR), the same idea applies, but with a difference - as long as the TX queue has not been drained, we need to receive feedback to keep congestion-control rates up to date. Hence SHUT_WR is honoured only after the last packet (under congestion control) has been sent; * although SHUT_RDWR seems nonsensical, it is nevertheless supported in the same manner as for TCP (and agrees with test for SHUTDOWN_MASK in dccp_poll() in net/dccp/proto.c). Furthermore, most of the code already honours the sk_shutdown flags (dccp_recvmsg() for instance sets the read length to 0 if SHUT_RD had been called); CCID handling is now added to this by the present patch. There will also no longer be any delivery when the socket is in the final stages, i.e. when one of dccp_close(), dccp_fin(), or dccp_done() has been called - which is fine since at that stage the connection is its final stages. Motivation and background are on http://www.erg.abdn.ac.uk/users/gerrit/dccp/notes/shutdown A FIXME has been added to notify the other end if SHUT_RD has been set (RFC 4340, 11.7). Note: There is a comment in inet_shutdown() in net/ipv4/af_inet.c which asks to "make sure the socket is a TCP socket". This should probably be extended to mean `TCP or DCCP socket' (the code is also used by UDP and raw sockets). Signed-off-by: Gerrit Renker <gerrit@erg.abdn.ac.uk> Signed-off-by: Ian McDonald <ian.mcdonald@jandi.co.nz> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2007-11-21 11:56:48 +00:00
static void dccp_deliver_input_to_ccids(struct sock *sk, struct sk_buff *skb)
{
const struct dccp_sock *dp = dccp_sk(sk);
/* Don't deliver to RX CCID when node has shut down read end. */
if (!(sk->sk_shutdown & RCV_SHUTDOWN))
ccid_hc_rx_packet_recv(dp->dccps_hc_rx_ccid, sk, skb);
/*
* Until the TX queue has been drained, we can not honour SHUT_WR, since
* we need received feedback as input to adjust congestion control.
*/
if (sk->sk_write_queue.qlen > 0 || !(sk->sk_shutdown & SEND_SHUTDOWN))
ccid_hc_tx_packet_recv(dp->dccps_hc_tx_ccid, sk, skb);
}
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, seqno = DCCP_SKB_CB(skb)->dccpd_seq,
ackno = DCCP_SKB_CB(skb)->dccpd_ack_seq;
/*
* 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(ackno, dp->dccps_awl, dp->dccps_awh) &&
dccp_delta_seqno(dp->dccps_swl, seqno) >= 0)
dccp_update_gsr(sk, seqno);
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
*/
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 = ADD48(dp->dccps_gsr, 1);
lawl = dp->dccps_gar;
}
if (between48(seqno, lswl, dp->dccps_swh) &&
(ackno == DCCP_PKT_WITHOUT_ACK_SEQ ||
between48(ackno, lawl, dp->dccps_awh))) {
dccp_update_gsr(sk, seqno);
if (dh->dccph_type != DCCP_PKT_SYNC &&
(ackno != DCCP_PKT_WITHOUT_ACK_SEQ))
dp->dccps_gar = ackno;
} else {
unsigned long now = jiffies;
/*
* Step 6: Check sequence numbers
* Otherwise,
* If P.type == Reset,
* Send Sync packet acknowledging S.GSR
* Otherwise,
* Send Sync packet acknowledging P.seqno
* Drop packet and return
*
* These Syncs are rate-limited as per RFC 4340, 7.5.4:
* at most 1 / (dccp_sync_rate_limit * HZ) Syncs per second.
*/
if (time_before(now, (dp->dccps_rate_last +
sysctl_dccp_sync_ratelimit)))
return 0;
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) seqno,
(unsigned long long) dp->dccps_swh,
(ackno == DCCP_PKT_WITHOUT_ACK_SEQ) ? "doesn't exist"
: "exists",
(unsigned long long) lawl, (unsigned long long) ackno,
(unsigned long long) dp->dccps_awh);
dp->dccps_rate_last = now;
if (dh->dccph_type == DCCP_PKT_RESET)
seqno = dp->dccps_gsr;
dccp_send_sync(sk, seqno, DCCP_PKT_SYNC);
return -1;
}
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:
/*
[DCCP]: Honour and make use of shutdown option set by user This extends the DCCP socket API by honouring any shutdown(2) option set by the user. The behaviour is, as much as possible, made consistent with the API for TCP's shutdown. This patch exploits the information provided by the user via the socket API to reduce processing costs: * if the read end is closed (SHUT_RD), it is not necessary to deliver to input CCID; * if the write end is closed (SHUT_WR), the same idea applies, but with a difference - as long as the TX queue has not been drained, we need to receive feedback to keep congestion-control rates up to date. Hence SHUT_WR is honoured only after the last packet (under congestion control) has been sent; * although SHUT_RDWR seems nonsensical, it is nevertheless supported in the same manner as for TCP (and agrees with test for SHUTDOWN_MASK in dccp_poll() in net/dccp/proto.c). Furthermore, most of the code already honours the sk_shutdown flags (dccp_recvmsg() for instance sets the read length to 0 if SHUT_RD had been called); CCID handling is now added to this by the present patch. There will also no longer be any delivery when the socket is in the final stages, i.e. when one of dccp_close(), dccp_fin(), or dccp_done() has been called - which is fine since at that stage the connection is its final stages. Motivation and background are on http://www.erg.abdn.ac.uk/users/gerrit/dccp/notes/shutdown A FIXME has been added to notify the other end if SHUT_RD has been set (RFC 4340, 11.7). Note: There is a comment in inet_shutdown() in net/ipv4/af_inet.c which asks to "make sure the socket is a TCP socket". This should probably be extended to mean `TCP or DCCP socket' (the code is also used by UDP and raw sockets). Signed-off-by: Gerrit Renker <gerrit@erg.abdn.ac.uk> Signed-off-by: Ian McDonald <ian.mcdonald@jandi.co.nz> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2007-11-21 11:56:48 +00:00
* FIXME: schedule DATA_DROPPED (RFC 4340, 11.7.2) if and when
* - sk_shutdown == RCV_SHUTDOWN, use Code 1, "Not Listening"
* - sk_receive_queue is full, use Code 2, "Receive Buffer"
*/
dccp_enqueue_skb(sk, skb);
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_rcv_reset(sk, skb);
return 0;
case DCCP_PKT_CLOSEREQ:
[DCCP]: Integrate state transitions for passive-close This adds the necessary state transitions for the two forms of passive-close * PASSIVE_CLOSE - which is entered when a host receives a Close; * PASSIVE_CLOSEREQ - which is entered when a client receives a CloseReq. Here is a detailed account of what the patch does in each state. 1) Receiving CloseReq The pseudo-code in 8.5 says: Step 13: Process CloseReq If P.type == CloseReq and S.state < CLOSEREQ, Generate Close S.state := CLOSING Set CLOSING timer. This means we need to address what to do in CLOSED, LISTEN, REQUEST, RESPOND, PARTOPEN, and OPEN. * CLOSED: silently ignore - it may be a late or duplicate CloseReq; * LISTEN/RESPOND: will not appear, since Step 7 is performed first (we know we are the client); * REQUEST: perform Step 13 directly (no need to enqueue packet); * OPEN/PARTOPEN: enter PASSIVE_CLOSEREQ so that the application has a chance to process unread data. When already in PASSIVE_CLOSEREQ, no second CloseReq is enqueued. In any other state, the CloseReq is ignored. I think that this offers some robustness against rare and pathological cases: e.g. a simultaneous close where the client sends a Close and the server a CloseReq. The client will then be retransmitting its Close until it gets the Reset, so ignoring the CloseReq while in state CLOSING is sane. 2) Receiving Close The code below from 8.5 is unconditional. Step 14: Process Close If P.type == Close, Generate Reset(Closed) Tear down connection Drop packet and return Thus we need to consider all states: * CLOSED: silently ignore, since this can happen when a retransmitted or late Close arrives; * LISTEN: dccp_rcv_state_process() will generate a Reset ("No Connection"); * REQUEST: perform Step 14 directly (no need to enqueue packet); * RESPOND: dccp_check_req() will generate a Reset ("Packet Error") -- left it at that; * OPEN/PARTOPEN: enter PASSIVE_CLOSE so that application has a chance to process unread data; * CLOSEREQ: server performed active-close -- perform Step 14; * CLOSING: simultaneous-close: use a tie-breaker to avoid message ping-pong (see comment); * PASSIVE_CLOSEREQ: ignore - the peer has a bug (sending first a CloseReq and now a Close); * TIMEWAIT: packet is ignored. Note that the condition of receiving a packet in state CLOSED here is different from the condition "there is no socket for such a connection": the socket still exists, but its state indicates it is unusable. Last, dccp_finish_passive_close sets either DCCP_CLOSED or DCCP_CLOSING = TCP_CLOSING, so that sk_stream_wait_close() will wait for the final Reset (which will trigger CLOSING => CLOSED). Signed-off-by: Gerrit Renker <gerrit@erg.abdn.ac.uk> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2007-11-28 13:59:48 +00:00
if (dccp_rcv_closereq(sk, skb))
return 0;
goto discard;
case DCCP_PKT_CLOSE:
[DCCP]: Integrate state transitions for passive-close This adds the necessary state transitions for the two forms of passive-close * PASSIVE_CLOSE - which is entered when a host receives a Close; * PASSIVE_CLOSEREQ - which is entered when a client receives a CloseReq. Here is a detailed account of what the patch does in each state. 1) Receiving CloseReq The pseudo-code in 8.5 says: Step 13: Process CloseReq If P.type == CloseReq and S.state < CLOSEREQ, Generate Close S.state := CLOSING Set CLOSING timer. This means we need to address what to do in CLOSED, LISTEN, REQUEST, RESPOND, PARTOPEN, and OPEN. * CLOSED: silently ignore - it may be a late or duplicate CloseReq; * LISTEN/RESPOND: will not appear, since Step 7 is performed first (we know we are the client); * REQUEST: perform Step 13 directly (no need to enqueue packet); * OPEN/PARTOPEN: enter PASSIVE_CLOSEREQ so that the application has a chance to process unread data. When already in PASSIVE_CLOSEREQ, no second CloseReq is enqueued. In any other state, the CloseReq is ignored. I think that this offers some robustness against rare and pathological cases: e.g. a simultaneous close where the client sends a Close and the server a CloseReq. The client will then be retransmitting its Close until it gets the Reset, so ignoring the CloseReq while in state CLOSING is sane. 2) Receiving Close The code below from 8.5 is unconditional. Step 14: Process Close If P.type == Close, Generate Reset(Closed) Tear down connection Drop packet and return Thus we need to consider all states: * CLOSED: silently ignore, since this can happen when a retransmitted or late Close arrives; * LISTEN: dccp_rcv_state_process() will generate a Reset ("No Connection"); * REQUEST: perform Step 14 directly (no need to enqueue packet); * RESPOND: dccp_check_req() will generate a Reset ("Packet Error") -- left it at that; * OPEN/PARTOPEN: enter PASSIVE_CLOSE so that application has a chance to process unread data; * CLOSEREQ: server performed active-close -- perform Step 14; * CLOSING: simultaneous-close: use a tie-breaker to avoid message ping-pong (see comment); * PASSIVE_CLOSEREQ: ignore - the peer has a bug (sending first a CloseReq and now a Close); * TIMEWAIT: packet is ignored. Note that the condition of receiving a packet in state CLOSED here is different from the condition "there is no socket for such a connection": the socket still exists, but its state indicates it is unusable. Last, dccp_finish_passive_close sets either DCCP_CLOSED or DCCP_CLOSING = TCP_CLOSING, so that sk_stream_wait_close() will wait for the final Reset (which will trigger CLOSING => CLOSED). Signed-off-by: Gerrit Renker <gerrit@erg.abdn.ac.uk> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2007-11-28 13:59:48 +00:00
if (dccp_rcv_close(sk, skb))
return 0;
goto discard;
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 (dccp_delta_seqno(dp->dccps_osr,
DCCP_SKB_CB(skb)->dccpd_seq) >= 0) {
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;
}
int dccp_rcv_established(struct sock *sk, struct sk_buff *skb,
const struct dccp_hdr *dh, const unsigned len)
{
if (dccp_check_seqno(sk, skb))
goto discard;
if (dccp_parse_options(sk, NULL, skb))
return 1;
dccp_handle_ackvec_processing(sk, skb);
[DCCP]: Honour and make use of shutdown option set by user This extends the DCCP socket API by honouring any shutdown(2) option set by the user. The behaviour is, as much as possible, made consistent with the API for TCP's shutdown. This patch exploits the information provided by the user via the socket API to reduce processing costs: * if the read end is closed (SHUT_RD), it is not necessary to deliver to input CCID; * if the write end is closed (SHUT_WR), the same idea applies, but with a difference - as long as the TX queue has not been drained, we need to receive feedback to keep congestion-control rates up to date. Hence SHUT_WR is honoured only after the last packet (under congestion control) has been sent; * although SHUT_RDWR seems nonsensical, it is nevertheless supported in the same manner as for TCP (and agrees with test for SHUTDOWN_MASK in dccp_poll() in net/dccp/proto.c). Furthermore, most of the code already honours the sk_shutdown flags (dccp_recvmsg() for instance sets the read length to 0 if SHUT_RD had been called); CCID handling is now added to this by the present patch. There will also no longer be any delivery when the socket is in the final stages, i.e. when one of dccp_close(), dccp_fin(), or dccp_done() has been called - which is fine since at that stage the connection is its final stages. Motivation and background are on http://www.erg.abdn.ac.uk/users/gerrit/dccp/notes/shutdown A FIXME has been added to notify the other end if SHUT_RD has been set (RFC 4340, 11.7). Note: There is a comment in inet_shutdown() in net/ipv4/af_inet.c which asks to "make sure the socket is a TCP socket". This should probably be extended to mean `TCP or DCCP socket' (the code is also used by UDP and raw sockets). Signed-off-by: Gerrit Renker <gerrit@erg.abdn.ac.uk> Signed-off-by: Ian McDonald <ian.mcdonald@jandi.co.nz> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2007-11-21 11:56:48 +00:00
dccp_deliver_input_to_ccids(sk, skb);
return __dccp_rcv_established(sk, skb, dh, len);
discard:
__kfree_skb(skb);
return 0;
}
EXPORT_SYMBOL_GPL(dccp_rcv_established);
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);
long tstamp = dccp_timestamp();
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 option processing (Step 8) failed, return 1 here so that
* dccp_v4_do_rcv() sends a Reset. The Reset code depends on
* the option type and is set in dccp_parse_options().
*/
if (dccp_parse_options(sk, NULL, skb))
return 1;
/* Obtain usec RTT sample from SYN exchange (used by CCID 3) */
if (likely(dp->dccps_options_received.dccpor_timestamp_echo))
dp->dccps_syn_rtt = dccp_sample_rtt(sk, 10 * (tstamp -
dp->dccps_options_received.dccpor_timestamp_echo));
/* Stop the REQUEST timer */
inet_csk_clear_xmit_timer(sk, ICSK_TIME_RETRANS);
WARN_ON(sk->sk_send_head == NULL);
kfree_skb(sk->sk_send_head);
sk->sk_send_head = NULL;
/*
dccp: Fix the adjustments to AWL and SWL This fixes a problem and a potential loophole with regard to seqno/ackno validity: the problem is that the initial adjustments to AWL/SWL were only performed at the begin of the connection, during the handshake. Since the Sequence Window feature is always greater than Wmin=32 (7.5.2), it is however necessary to perform these adjustments at least for the first W/W' (variables as per 7.5.1) packets in the lifetime of a connection. This requirement is complicated by the fact that W/W' can change at any time during the lifetime of a connection. Therefore the consequence is to perform this safety check each time SWL/AWL are updated. A second problem solved by this patch is that the remote/local Sequence Window feature values (which set the bounds for AWL/SWL/SWH) are undefined until the feature negotiation has completed. During the initial handshake we have more stringent sequence number protection, the changes added by this patch effect that {A,S}W{L,H} are within the correct bounds at the instant that feature negotiation completes (since the SeqWin feature activation handlers call dccp_update_gsr/gss()). A detailed rationale is below -- can be removed from the commit message. 1. Server sequence number checks during initial handshake --------------------------------------------------------- The server can not use the fields of the listening socket for seqno/ackno checks and thus needs to store all relevant information on a per-connection basis on the dccp_request socket. This is a size-constrained structure and has currently only ISS (dreq_iss) and ISR (dreq_isr) defined. Adding further fields (SW{L,H}, AW{L,H}) would increase the size of the struct and it is questionable whether this will have any practical gain. The currently implemented solution is as follows. * receiving first Request: dccp_v{4,6}_conn_request sets ISR := P.seqno, ISS := dccp_v{4,6}_init_sequence() * sending first Response: dccp_v{4,6}_send_response via dccp_make_response() sets P.seqno := ISS, sets P.ackno := ISR * receiving retransmitted Request: dccp_check_req() overrides ISR := P.seqno * answering retransmitted Request: dccp_make_response() sets ISS += 1, otherwise as per first Response * completing the handshake: succeeds in dccp_check_req() for the first Ack where P.ackno == ISS (P.seqno is not tested) * creating child socket: ISS, ISR are copied from the request_sock This solution will succeed whenever the server can receive the Request and the subsequent Ack in succession, without retransmissions. If there is packet loss, the client needs to retransmit until this condition succeeds; it will otherwise eventually give up. Adding further fields to the request_sock could increase the robustness a bit, in that it would make possible to let a reordered Ack (from a retransmitted Response) pass. The argument against such a solution is that if the packet loss is not persistent and an Ack gets through, why not wait for the one answering the original response: if the loss is persistent, it is probably better to not start the connection in the first place. Long story short: the present design (by Arnaldo) is simple and will likely work just as well as a more complicated solution. As a consequence, {A,S}W{L,H} are not needed until the moment the request_sock is cloned into the accept queue. At that stage feature negotiation has completed, so that the values for the local and remote Sequence Window feature (7.5.2) are known, i.e. we are now in a better position to compute {A,S}W{L,H}. 2. Client sequence number checks during initial handshake --------------------------------------------------------- Until entering PARTOPEN the client does not need the adjustments, since it constrains the Ack window to the packet it sent. * sending first Request: dccp_v{4,6}_connect() choose ISS, dccp_connect() then sets GAR := ISS (as per 8.5), dccp_transmit_skb() (with the previous bug fix) sets GSS := ISS, AWL := ISS, AWH := GSS * n-th retransmitted Request (with previous patch): dccp_retransmit_skb() via timer calls dccp_transmit_skb(), which sets GSS := ISS+n and then AWL := ISS, AWH := ISS+n * receiving any Response: dccp_rcv_request_sent_state_process() -- accepts packet if AWL <= P.ackno <= AWH; -- sets GSR = ISR = P.seqno * sending the Ack completing the handshake: dccp_send_ack() calls dccp_transmit_skb(), which sets GSS += 1 and AWL := ISS, AWH := GSS Signed-off-by: Gerrit Renker <gerrit@erg.abdn.ac.uk>
2008-09-04 05:30:19 +00:00
* Set ISR, GSR from packet. ISS was set in dccp_v{4,6}_connect
* and GSS in dccp_transmit_skb(). Setting AWL/AWH and SWL/SWH
* is done as part of activating the feature values below, since
* these settings depend on the local/remote Sequence Window
* features, which were undefined or not confirmed until now.
*/
dccp: Fix the adjustments to AWL and SWL This fixes a problem and a potential loophole with regard to seqno/ackno validity: the problem is that the initial adjustments to AWL/SWL were only performed at the begin of the connection, during the handshake. Since the Sequence Window feature is always greater than Wmin=32 (7.5.2), it is however necessary to perform these adjustments at least for the first W/W' (variables as per 7.5.1) packets in the lifetime of a connection. This requirement is complicated by the fact that W/W' can change at any time during the lifetime of a connection. Therefore the consequence is to perform this safety check each time SWL/AWL are updated. A second problem solved by this patch is that the remote/local Sequence Window feature values (which set the bounds for AWL/SWL/SWH) are undefined until the feature negotiation has completed. During the initial handshake we have more stringent sequence number protection, the changes added by this patch effect that {A,S}W{L,H} are within the correct bounds at the instant that feature negotiation completes (since the SeqWin feature activation handlers call dccp_update_gsr/gss()). A detailed rationale is below -- can be removed from the commit message. 1. Server sequence number checks during initial handshake --------------------------------------------------------- The server can not use the fields of the listening socket for seqno/ackno checks and thus needs to store all relevant information on a per-connection basis on the dccp_request socket. This is a size-constrained structure and has currently only ISS (dreq_iss) and ISR (dreq_isr) defined. Adding further fields (SW{L,H}, AW{L,H}) would increase the size of the struct and it is questionable whether this will have any practical gain. The currently implemented solution is as follows. * receiving first Request: dccp_v{4,6}_conn_request sets ISR := P.seqno, ISS := dccp_v{4,6}_init_sequence() * sending first Response: dccp_v{4,6}_send_response via dccp_make_response() sets P.seqno := ISS, sets P.ackno := ISR * receiving retransmitted Request: dccp_check_req() overrides ISR := P.seqno * answering retransmitted Request: dccp_make_response() sets ISS += 1, otherwise as per first Response * completing the handshake: succeeds in dccp_check_req() for the first Ack where P.ackno == ISS (P.seqno is not tested) * creating child socket: ISS, ISR are copied from the request_sock This solution will succeed whenever the server can receive the Request and the subsequent Ack in succession, without retransmissions. If there is packet loss, the client needs to retransmit until this condition succeeds; it will otherwise eventually give up. Adding further fields to the request_sock could increase the robustness a bit, in that it would make possible to let a reordered Ack (from a retransmitted Response) pass. The argument against such a solution is that if the packet loss is not persistent and an Ack gets through, why not wait for the one answering the original response: if the loss is persistent, it is probably better to not start the connection in the first place. Long story short: the present design (by Arnaldo) is simple and will likely work just as well as a more complicated solution. As a consequence, {A,S}W{L,H} are not needed until the moment the request_sock is cloned into the accept queue. At that stage feature negotiation has completed, so that the values for the local and remote Sequence Window feature (7.5.2) are known, i.e. we are now in a better position to compute {A,S}W{L,H}. 2. Client sequence number checks during initial handshake --------------------------------------------------------- Until entering PARTOPEN the client does not need the adjustments, since it constrains the Ack window to the packet it sent. * sending first Request: dccp_v{4,6}_connect() choose ISS, dccp_connect() then sets GAR := ISS (as per 8.5), dccp_transmit_skb() (with the previous bug fix) sets GSS := ISS, AWL := ISS, AWH := GSS * n-th retransmitted Request (with previous patch): dccp_retransmit_skb() via timer calls dccp_transmit_skb(), which sets GSS := ISS+n and then AWL := ISS, AWH := ISS+n * receiving any Response: dccp_rcv_request_sent_state_process() -- accepts packet if AWL <= P.ackno <= AWH; -- sets GSR = ISR = P.seqno * sending the Ack completing the handshake: dccp_send_ack() calls dccp_transmit_skb(), which sets GSS += 1 and AWL := ISS, AWH := GSS Signed-off-by: Gerrit Renker <gerrit@erg.abdn.ac.uk>
2008-09-04 05:30:19 +00:00
dp->dccps_gsr = dp->dccps_isr = DCCP_SKB_CB(skb)->dccpd_seq;
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);
/*
* If feature negotiation was successful, activate features now;
* an activation failure means that this host could not activate
* one ore more features (e.g. insufficient memory), which would
* leave at least one feature in an undefined state.
*/
if (dccp_feat_activate_values(sk, &dp->dccps_featneg))
goto unable_to_proceed;
/* 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, SOCK_WAKE_IO, 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;
unable_to_proceed:
DCCP_SKB_CB(skb)->dccpd_reset_code = DCCP_RESET_CODE_ABORTED;
/*
* We mark this socket as no longer usable, so that the loop in
* dccp_sendmsg() terminates and the application gets notified.
*/
dccp_set_state(sk, DCCP_CLOSED);
sk->sk_err = ECOMM;
return 1;
}
static int dccp_rcv_respond_partopen_state_process(struct sock *sk,
struct sk_buff *skb,
const struct dccp_hdr *dh,
const unsigned len)
{
int queued = 0;
switch (dh->dccph_type) {
case DCCP_PKT_RESET:
inet_csk_clear_xmit_timer(sk, ICSK_TIME_DACK);
break;
case DCCP_PKT_DATA:
if (sk->sk_state == DCCP_RESPOND)
break;
case DCCP_PKT_DATAACK:
case DCCP_PKT_ACK:
/*
* FIXME: we should be reseting the PARTOPEN (DELACK) timer
* here but only if we haven't used the DELACK timer for
* something else, like sending a delayed ack for a TIMESTAMP
* echo, etc, for now were not clearing it, sending an extra
* ACK when there is nothing else to do in DELACK is not a big
* deal after all.
*/
/* Stop the PARTOPEN timer */
if (sk->sk_state == DCCP_PARTOPEN)
inet_csk_clear_xmit_timer(sk, ICSK_TIME_DACK);
dccp_sk(sk)->dccps_osr = DCCP_SKB_CB(skb)->dccpd_seq;
dccp_set_state(sk, DCCP_OPEN);
if (dh->dccph_type == DCCP_PKT_DATAACK ||
dh->dccph_type == DCCP_PKT_DATA) {
__dccp_rcv_established(sk, skb, dh, len);
queued = 1; /* packet was queued
(by __dccp_rcv_established) */
}
break;
}
return queued;
}
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;
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 && sk->sk_state != DCCP_RESPOND) {
if (dccp_check_seqno(sk, skb))
goto discard;
/*
* Step 8: Process options and mark acknowledgeable
*/
if (dccp_parse_options(sk, NULL, skb))
return 1;
dccp_handle_ackvec_processing(sk, skb);
[DCCP]: Honour and make use of shutdown option set by user This extends the DCCP socket API by honouring any shutdown(2) option set by the user. The behaviour is, as much as possible, made consistent with the API for TCP's shutdown. This patch exploits the information provided by the user via the socket API to reduce processing costs: * if the read end is closed (SHUT_RD), it is not necessary to deliver to input CCID; * if the write end is closed (SHUT_WR), the same idea applies, but with a difference - as long as the TX queue has not been drained, we need to receive feedback to keep congestion-control rates up to date. Hence SHUT_WR is honoured only after the last packet (under congestion control) has been sent; * although SHUT_RDWR seems nonsensical, it is nevertheless supported in the same manner as for TCP (and agrees with test for SHUTDOWN_MASK in dccp_poll() in net/dccp/proto.c). Furthermore, most of the code already honours the sk_shutdown flags (dccp_recvmsg() for instance sets the read length to 0 if SHUT_RD had been called); CCID handling is now added to this by the present patch. There will also no longer be any delivery when the socket is in the final stages, i.e. when one of dccp_close(), dccp_fin(), or dccp_done() has been called - which is fine since at that stage the connection is its final stages. Motivation and background are on http://www.erg.abdn.ac.uk/users/gerrit/dccp/notes/shutdown A FIXME has been added to notify the other end if SHUT_RD has been set (RFC 4340, 11.7). Note: There is a comment in inet_shutdown() in net/ipv4/af_inet.c which asks to "make sure the socket is a TCP socket". This should probably be extended to mean `TCP or DCCP socket' (the code is also used by UDP and raw sockets). Signed-off-by: Gerrit Renker <gerrit@erg.abdn.ac.uk> Signed-off-by: Ian McDonald <ian.mcdonald@jandi.co.nz> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2007-11-21 11:56:48 +00:00
dccp_deliver_input_to_ccids(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) {
dccp_rcv_reset(sk, skb);
return 0;
/*
* Step 7: Check for unexpected packet types
* If (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) ||
(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]: Integrate state transitions for passive-close This adds the necessary state transitions for the two forms of passive-close * PASSIVE_CLOSE - which is entered when a host receives a Close; * PASSIVE_CLOSEREQ - which is entered when a client receives a CloseReq. Here is a detailed account of what the patch does in each state. 1) Receiving CloseReq The pseudo-code in 8.5 says: Step 13: Process CloseReq If P.type == CloseReq and S.state < CLOSEREQ, Generate Close S.state := CLOSING Set CLOSING timer. This means we need to address what to do in CLOSED, LISTEN, REQUEST, RESPOND, PARTOPEN, and OPEN. * CLOSED: silently ignore - it may be a late or duplicate CloseReq; * LISTEN/RESPOND: will not appear, since Step 7 is performed first (we know we are the client); * REQUEST: perform Step 13 directly (no need to enqueue packet); * OPEN/PARTOPEN: enter PASSIVE_CLOSEREQ so that the application has a chance to process unread data. When already in PASSIVE_CLOSEREQ, no second CloseReq is enqueued. In any other state, the CloseReq is ignored. I think that this offers some robustness against rare and pathological cases: e.g. a simultaneous close where the client sends a Close and the server a CloseReq. The client will then be retransmitting its Close until it gets the Reset, so ignoring the CloseReq while in state CLOSING is sane. 2) Receiving Close The code below from 8.5 is unconditional. Step 14: Process Close If P.type == Close, Generate Reset(Closed) Tear down connection Drop packet and return Thus we need to consider all states: * CLOSED: silently ignore, since this can happen when a retransmitted or late Close arrives; * LISTEN: dccp_rcv_state_process() will generate a Reset ("No Connection"); * REQUEST: perform Step 14 directly (no need to enqueue packet); * RESPOND: dccp_check_req() will generate a Reset ("Packet Error") -- left it at that; * OPEN/PARTOPEN: enter PASSIVE_CLOSE so that application has a chance to process unread data; * CLOSEREQ: server performed active-close -- perform Step 14; * CLOSING: simultaneous-close: use a tie-breaker to avoid message ping-pong (see comment); * PASSIVE_CLOSEREQ: ignore - the peer has a bug (sending first a CloseReq and now a Close); * TIMEWAIT: packet is ignored. Note that the condition of receiving a packet in state CLOSED here is different from the condition "there is no socket for such a connection": the socket still exists, but its state indicates it is unusable. Last, dccp_finish_passive_close sets either DCCP_CLOSED or DCCP_CLOSING = TCP_CLOSING, so that sk_stream_wait_close() will wait for the final Reset (which will trigger CLOSING => CLOSED). Signed-off-by: Gerrit Renker <gerrit@erg.abdn.ac.uk> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2007-11-28 13:59:48 +00:00
if (dccp_rcv_closereq(sk, skb))
return 0;
goto discard;
} else if (dh->dccph_type == DCCP_PKT_CLOSE) {
[DCCP]: Integrate state transitions for passive-close This adds the necessary state transitions for the two forms of passive-close * PASSIVE_CLOSE - which is entered when a host receives a Close; * PASSIVE_CLOSEREQ - which is entered when a client receives a CloseReq. Here is a detailed account of what the patch does in each state. 1) Receiving CloseReq The pseudo-code in 8.5 says: Step 13: Process CloseReq If P.type == CloseReq and S.state < CLOSEREQ, Generate Close S.state := CLOSING Set CLOSING timer. This means we need to address what to do in CLOSED, LISTEN, REQUEST, RESPOND, PARTOPEN, and OPEN. * CLOSED: silently ignore - it may be a late or duplicate CloseReq; * LISTEN/RESPOND: will not appear, since Step 7 is performed first (we know we are the client); * REQUEST: perform Step 13 directly (no need to enqueue packet); * OPEN/PARTOPEN: enter PASSIVE_CLOSEREQ so that the application has a chance to process unread data. When already in PASSIVE_CLOSEREQ, no second CloseReq is enqueued. In any other state, the CloseReq is ignored. I think that this offers some robustness against rare and pathological cases: e.g. a simultaneous close where the client sends a Close and the server a CloseReq. The client will then be retransmitting its Close until it gets the Reset, so ignoring the CloseReq while in state CLOSING is sane. 2) Receiving Close The code below from 8.5 is unconditional. Step 14: Process Close If P.type == Close, Generate Reset(Closed) Tear down connection Drop packet and return Thus we need to consider all states: * CLOSED: silently ignore, since this can happen when a retransmitted or late Close arrives; * LISTEN: dccp_rcv_state_process() will generate a Reset ("No Connection"); * REQUEST: perform Step 14 directly (no need to enqueue packet); * RESPOND: dccp_check_req() will generate a Reset ("Packet Error") -- left it at that; * OPEN/PARTOPEN: enter PASSIVE_CLOSE so that application has a chance to process unread data; * CLOSEREQ: server performed active-close -- perform Step 14; * CLOSING: simultaneous-close: use a tie-breaker to avoid message ping-pong (see comment); * PASSIVE_CLOSEREQ: ignore - the peer has a bug (sending first a CloseReq and now a Close); * TIMEWAIT: packet is ignored. Note that the condition of receiving a packet in state CLOSED here is different from the condition "there is no socket for such a connection": the socket still exists, but its state indicates it is unusable. Last, dccp_finish_passive_close sets either DCCP_CLOSED or DCCP_CLOSING = TCP_CLOSING, so that sk_stream_wait_close() will wait for the final Reset (which will trigger CLOSING => CLOSED). Signed-off-by: Gerrit Renker <gerrit@erg.abdn.ac.uk> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2007-11-28 13:59:48 +00:00
if (dccp_rcv_close(sk, skb))
return 0;
goto discard;
}
switch (sk->sk_state) {
case DCCP_CLOSED:
dcb->dccpd_reset_code = DCCP_RESET_CODE_NO_CONNECTION;
return 1;
case DCCP_REQUESTING:
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, SOCK_WAKE_IO, POLL_OUT);
break;
}
} else if (unlikely(dh->dccph_type == DCCP_PKT_SYNC)) {
dccp_send_sync(sk, dcb->dccpd_seq, DCCP_PKT_SYNCACK);
goto discard;
}
if (!queued) {
discard:
__kfree_skb(skb);
}
return 0;
}
EXPORT_SYMBOL_GPL(dccp_rcv_state_process);
/**
* dccp_sample_rtt - Validate and finalise computation of RTT sample
* @delta: number of microseconds between packet and acknowledgment
* The routine is kept generic to work in different contexts. It should be
* called immediately when the ACK used for the RTT sample arrives.
*/
u32 dccp_sample_rtt(struct sock *sk, long delta)
{
/* dccpor_elapsed_time is either zeroed out or set and > 0 */
delta -= dccp_sk(sk)->dccps_options_received.dccpor_elapsed_time * 10;
if (unlikely(delta <= 0)) {
DCCP_WARN("unusable RTT sample %ld, using min\n", delta);
return DCCP_SANE_RTT_MIN;
}
if (unlikely(delta > DCCP_SANE_RTT_MAX)) {
DCCP_WARN("RTT sample %ld too large, using max\n", delta);
return DCCP_SANE_RTT_MAX;
}
return delta;
}
EXPORT_SYMBOL_GPL(dccp_sample_rtt);