![Tejun Heo](/assets/img/avatar_default.png)
percpu.h is included by sched.h and module.h and thus ends up being included when building most .c files. percpu.h includes slab.h which in turn includes gfp.h making everything defined by the two files universally available and complicating inclusion dependencies. percpu.h -> slab.h dependency is about to be removed. Prepare for this change by updating users of gfp and slab facilities include those headers directly instead of assuming availability. As this conversion needs to touch large number of source files, the following script is used as the basis of conversion. http://userweb.kernel.org/~tj/misc/slabh-sweep.py The script does the followings. * Scan files for gfp and slab usages and update includes such that only the necessary includes are there. ie. if only gfp is used, gfp.h, if slab is used, slab.h. * When the script inserts a new include, it looks at the include blocks and try to put the new include such that its order conforms to its surrounding. It's put in the include block which contains core kernel includes, in the same order that the rest are ordered - alphabetical, Christmas tree, rev-Xmas-tree or at the end if there doesn't seem to be any matching order. * If the script can't find a place to put a new include (mostly because the file doesn't have fitting include block), it prints out an error message indicating which .h file needs to be added to the file. The conversion was done in the following steps. 1. The initial automatic conversion of all .c files updated slightly over 4000 files, deleting around 700 includes and adding ~480 gfp.h and ~3000 slab.h inclusions. The script emitted errors for ~400 files. 2. Each error was manually checked. Some didn't need the inclusion, some needed manual addition while adding it to implementation .h or embedding .c file was more appropriate for others. This step added inclusions to around 150 files. 3. The script was run again and the output was compared to the edits from #2 to make sure no file was left behind. 4. Several build tests were done and a couple of problems were fixed. e.g. lib/decompress_*.c used malloc/free() wrappers around slab APIs requiring slab.h to be added manually. 5. The script was run on all .h files but without automatically editing them as sprinkling gfp.h and slab.h inclusions around .h files could easily lead to inclusion dependency hell. Most gfp.h inclusion directives were ignored as stuff from gfp.h was usually wildly available and often used in preprocessor macros. Each slab.h inclusion directive was examined and added manually as necessary. 6. percpu.h was updated not to include slab.h. 7. Build test were done on the following configurations and failures were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my distributed build env didn't work with gcov compiles) and a few more options had to be turned off depending on archs to make things build (like ipr on powerpc/64 which failed due to missing writeq). * x86 and x86_64 UP and SMP allmodconfig and a custom test config. * powerpc and powerpc64 SMP allmodconfig * sparc and sparc64 SMP allmodconfig * ia64 SMP allmodconfig * s390 SMP allmodconfig * alpha SMP allmodconfig * um on x86_64 SMP allmodconfig 8. percpu.h modifications were reverted so that it could be applied as a separate patch and serve as bisection point. Given the fact that I had only a couple of failures from tests on step 6, I'm fairly confident about the coverage of this conversion patch. If there is a breakage, it's likely to be something in one of the arch headers which should be easily discoverable easily on most builds of the specific arch. Signed-off-by: Tejun Heo <tj@kernel.org> Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
745 lines
22 KiB
C
745 lines
22 KiB
C
/*
|
|
* 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 <linux/slab.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);
|
|
}
|
|
|
|
static int dccp_rcv_close(struct sock *sk, struct sk_buff *skb)
|
|
{
|
|
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;
|
|
}
|
|
|
|
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;
|
|
}
|
|
|
|
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_event_ack_recv(struct sock *sk, struct sk_buff *skb)
|
|
{
|
|
struct dccp_sock *dp = dccp_sk(sk);
|
|
|
|
if (dp->dccps_hc_rx_ackvec != NULL)
|
|
dccp_ackvec_check_rcv_ackno(dp->dccps_hc_rx_ackvec, sk,
|
|
DCCP_SKB_CB(skb)->dccpd_ack_seq);
|
|
}
|
|
|
|
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:
|
|
/*
|
|
* 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:
|
|
if (dccp_rcv_closereq(sk, skb))
|
|
return 0;
|
|
goto discard;
|
|
case DCCP_PKT_CLOSE:
|
|
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)
|
|
{
|
|
struct dccp_sock *dp = dccp_sk(sk);
|
|
|
|
if (dccp_check_seqno(sk, skb))
|
|
goto discard;
|
|
|
|
if (dccp_parse_options(sk, NULL, skb))
|
|
return 1;
|
|
|
|
if (DCCP_SKB_CB(skb)->dccpd_ack_seq != DCCP_PKT_WITHOUT_ACK_SEQ)
|
|
dccp_event_ack_recv(sk, skb);
|
|
|
|
if (dp->dccps_hc_rx_ackvec != NULL &&
|
|
dccp_ackvec_add(dp->dccps_hc_rx_ackvec, sk,
|
|
DCCP_SKB_CB(skb)->dccpd_seq,
|
|
DCCP_ACKVEC_STATE_RECEIVED))
|
|
goto discard;
|
|
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;
|
|
|
|
dp->dccps_isr = DCCP_SKB_CB(skb)->dccpd_seq;
|
|
dccp_update_gsr(sk, dp->dccps_isr);
|
|
/*
|
|
* SWL and AWL are initially adjusted so that they are not less than
|
|
* the initial Sequence Numbers received and sent, respectively:
|
|
* SWL := max(GSR + 1 - floor(W/4), ISR),
|
|
* AWL := max(GSS - W' + 1, ISS).
|
|
* These adjustments MUST be applied only at the beginning of the
|
|
* connection.
|
|
*
|
|
* AWL was adjusted in dccp_v4_connect -acme
|
|
*/
|
|
dccp_set_seqno(&dp->dccps_swl,
|
|
max48(dp->dccps_swl, dp->dccps_isr));
|
|
|
|
dccp_sync_mss(sk, icsk->icsk_pmtu_cookie);
|
|
|
|
/*
|
|
* Step 10: Process REQUEST state (second part)
|
|
* If S.state == REQUEST,
|
|
* / * If we get here, P is a valid Response from the
|
|
* server (see Step 4), and we should move to
|
|
* PARTOPEN state. PARTOPEN means send an Ack,
|
|
* don't send Data packets, retransmit Acks
|
|
* periodically, and always include any Init Cookie
|
|
* from the Response * /
|
|
* S.state := PARTOPEN
|
|
* Set PARTOPEN timer
|
|
* Continue with S.state == PARTOPEN
|
|
* / * Step 12 will send the Ack completing the
|
|
* three-way handshake * /
|
|
*/
|
|
dccp_set_state(sk, DCCP_PARTOPEN);
|
|
|
|
/*
|
|
* 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;
|
|
|
|
if (dcb->dccpd_ack_seq != DCCP_PKT_WITHOUT_ACK_SEQ)
|
|
dccp_event_ack_recv(sk, skb);
|
|
|
|
if (dp->dccps_hc_rx_ackvec != NULL &&
|
|
dccp_ackvec_add(dp->dccps_hc_rx_ackvec, sk,
|
|
DCCP_SKB_CB(skb)->dccpd_seq,
|
|
DCCP_ACKVEC_STATE_RECEIVED))
|
|
goto discard;
|
|
|
|
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) {
|
|
if (dccp_rcv_closereq(sk, skb))
|
|
return 0;
|
|
goto discard;
|
|
} else if (dh->dccph_type == DCCP_PKT_CLOSE) {
|
|
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;
|
|
}
|