mirror of
https://mirrors.bfsu.edu.cn/git/linux.git
synced 2024-12-27 21:14:44 +08:00
c6f0f2e71f
This removes the ccid2_hc_tx_check_sanity function: it is redundant. Details: ======== The tx_check_sanity function performs three tests: 1) it checks that the circular TX list is sorted - in ascending order of sequence number (ccid2s_seq) - and time (ccid2s_sent), - in the direction from `tail' (hctx_seqt) to `head' (hctx_seqh); 2) it ensures that the entire list has the length seqbufc * CCID2_SEQBUF_LEN; 3) it ensures that pipe equals the number of packets that were not marked `acked' (ccid2s_acked) between `tail' and `head'. The following argues that each of these tests is redundant, this can be verified by going through the code. (1) is not necessary, since both time and GSS increase from one packet to the next, so that subsequent insertions in tx_packet_sent (which advance the `head' pointer) will be in ascending order of time and sequence number. In (2), the length of the list is always equal to seqbufc times CCID2_SEQBUF_LEN (set to 1024) unless allocation caused an earlier failure, because: * at initialisation (tx_init), there is one chunk of size 1024 and seqbufc=1; * subsequent calls to tx_alloc_seq take place whenever head->next == tail in tx_packet_sent; then a new chunk of size 1024 is inserted between head and tail, and seqbufc is incremented by one. To show that (3) is redundant requires looking at two cases. The `pipe' variable of the TX socket is incremented only in tx_packet_sent, and decremented in tx_packet_recv. When head == tail (TX history empty) then pipe should be 0, which is the case directly after initialisation and after a retransmission timeout has occurred (ccid2_hc_tx_rto_expire). The first case involves parsing Ack Vectors for packets recorded in the live portion of the buffer, between tail and head. For each packet marked by the receiver as received (state 0) or ECN-marked (state 1), pipe is decremented by one, so for all such packets the BUG_ON in tx_check_sanity will not trigger. The second case is the loss detection in the second half of tx_packet_recv, below the comment "Check for NUMDUPACK". The first while-loop here ensures that the sequence number of `seqp' is either above or equal to `high_ack', or otherwise equal to the highest sequence number sent so far (of the entry head->prev, as head points to the next unsent entry). The next while-loop ("while (1)") counts the number of acked packets starting from that position of seqp, going backwards in the direction from head->prev to tail. If NUMDUPACK=3 such packets were counted within this loop, `seqp' points to the last acknowledged packet of these, and the "if (done == NUMDUPACK)" block is entered next. The while-loop contained within that block in turn traverses the list backwards, from head to tail; the position of `seqp' is saved in the variable `last_acked'. For each packet not marked as `acked', a congestion event is triggered within the loop, and pipe is decremented. The loop terminates when `seqp' has reached `tail', whereupon tail is set to the position previously stored in `last_acked'. Thus, between `last_acked' and the previous position of `tail', - pipe has been decremented earlier if the packet was marked as state 0 or 1; - pipe was decremented if the packet was not marked as acked. That is, pipe has been decremented by the number of packets between `last_acked' and the previous position of `tail'. As a consequence, pipe now again reflects the number of packets which have not (yet) been acked between the new position of tail (at `last_acked') and head->prev, or 0 if head==tail. The result is that the BUG_ON condition in check_sanity will also not be triggered, hence the test (3) is also redundant. Signed-off-by: Gerrit Renker <gerrit@erg.abdn.ac.uk>
702 lines
18 KiB
C
702 lines
18 KiB
C
/*
|
|
* net/dccp/ccids/ccid2.c
|
|
*
|
|
* Copyright (c) 2005, 2006 Andrea Bittau <a.bittau@cs.ucl.ac.uk>
|
|
*
|
|
* Changes to meet Linux coding standards, and DCCP infrastructure fixes.
|
|
*
|
|
* Copyright (c) 2006 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.
|
|
*
|
|
* This program is distributed in the hope that it will be useful,
|
|
* but WITHOUT ANY WARRANTY; without even the implied warranty of
|
|
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
|
* GNU General Public License for more details.
|
|
*
|
|
* You should have received a copy of the GNU General Public License
|
|
* along with this program; if not, write to the Free Software
|
|
* Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
|
|
*/
|
|
|
|
/*
|
|
* This implementation should follow RFC 4341
|
|
*/
|
|
#include "../feat.h"
|
|
#include "../ccid.h"
|
|
#include "../dccp.h"
|
|
#include "ccid2.h"
|
|
|
|
|
|
#ifdef CONFIG_IP_DCCP_CCID2_DEBUG
|
|
static int ccid2_debug;
|
|
#define ccid2_pr_debug(format, a...) DCCP_PR_DEBUG(ccid2_debug, format, ##a)
|
|
#else
|
|
#define ccid2_pr_debug(format, a...)
|
|
#endif
|
|
|
|
static int ccid2_hc_tx_alloc_seq(struct ccid2_hc_tx_sock *hctx)
|
|
{
|
|
struct ccid2_seq *seqp;
|
|
int i;
|
|
|
|
/* check if we have space to preserve the pointer to the buffer */
|
|
if (hctx->seqbufc >= sizeof(hctx->seqbuf) / sizeof(struct ccid2_seq *))
|
|
return -ENOMEM;
|
|
|
|
/* allocate buffer and initialize linked list */
|
|
seqp = kmalloc(CCID2_SEQBUF_LEN * sizeof(struct ccid2_seq), gfp_any());
|
|
if (seqp == NULL)
|
|
return -ENOMEM;
|
|
|
|
for (i = 0; i < (CCID2_SEQBUF_LEN - 1); i++) {
|
|
seqp[i].ccid2s_next = &seqp[i + 1];
|
|
seqp[i + 1].ccid2s_prev = &seqp[i];
|
|
}
|
|
seqp[CCID2_SEQBUF_LEN - 1].ccid2s_next = seqp;
|
|
seqp->ccid2s_prev = &seqp[CCID2_SEQBUF_LEN - 1];
|
|
|
|
/* This is the first allocation. Initiate the head and tail. */
|
|
if (hctx->seqbufc == 0)
|
|
hctx->seqh = hctx->seqt = seqp;
|
|
else {
|
|
/* link the existing list with the one we just created */
|
|
hctx->seqh->ccid2s_next = seqp;
|
|
seqp->ccid2s_prev = hctx->seqh;
|
|
|
|
hctx->seqt->ccid2s_prev = &seqp[CCID2_SEQBUF_LEN - 1];
|
|
seqp[CCID2_SEQBUF_LEN - 1].ccid2s_next = hctx->seqt;
|
|
}
|
|
|
|
/* store the original pointer to the buffer so we can free it */
|
|
hctx->seqbuf[hctx->seqbufc] = seqp;
|
|
hctx->seqbufc++;
|
|
|
|
return 0;
|
|
}
|
|
|
|
static int ccid2_hc_tx_send_packet(struct sock *sk, struct sk_buff *skb)
|
|
{
|
|
if (ccid2_cwnd_network_limited(ccid2_hc_tx_sk(sk)))
|
|
return CCID_PACKET_WILL_DEQUEUE_LATER;
|
|
return CCID_PACKET_SEND_AT_ONCE;
|
|
}
|
|
|
|
static void ccid2_change_l_ack_ratio(struct sock *sk, u32 val)
|
|
{
|
|
struct dccp_sock *dp = dccp_sk(sk);
|
|
u32 max_ratio = DIV_ROUND_UP(ccid2_hc_tx_sk(sk)->cwnd, 2);
|
|
|
|
/*
|
|
* Ensure that Ack Ratio does not exceed ceil(cwnd/2), which is (2) from
|
|
* RFC 4341, 6.1.2. We ignore the statement that Ack Ratio 2 is always
|
|
* acceptable since this causes starvation/deadlock whenever cwnd < 2.
|
|
* The same problem arises when Ack Ratio is 0 (ie. Ack Ratio disabled).
|
|
*/
|
|
if (val == 0 || val > max_ratio) {
|
|
DCCP_WARN("Limiting Ack Ratio (%u) to %u\n", val, max_ratio);
|
|
val = max_ratio;
|
|
}
|
|
if (val > DCCPF_ACK_RATIO_MAX)
|
|
val = DCCPF_ACK_RATIO_MAX;
|
|
|
|
if (val == dp->dccps_l_ack_ratio)
|
|
return;
|
|
|
|
ccid2_pr_debug("changing local ack ratio to %u\n", val);
|
|
dp->dccps_l_ack_ratio = val;
|
|
}
|
|
|
|
static void ccid2_change_srtt(struct ccid2_hc_tx_sock *hctx, long val)
|
|
{
|
|
ccid2_pr_debug("change SRTT to %ld\n", val);
|
|
hctx->srtt = val;
|
|
}
|
|
|
|
static void ccid2_start_rto_timer(struct sock *sk);
|
|
|
|
static void ccid2_hc_tx_rto_expire(unsigned long data)
|
|
{
|
|
struct sock *sk = (struct sock *)data;
|
|
struct ccid2_hc_tx_sock *hctx = ccid2_hc_tx_sk(sk);
|
|
const bool sender_was_blocked = ccid2_cwnd_network_limited(hctx);
|
|
long s;
|
|
|
|
bh_lock_sock(sk);
|
|
if (sock_owned_by_user(sk)) {
|
|
sk_reset_timer(sk, &hctx->rtotimer, jiffies + HZ / 5);
|
|
goto out;
|
|
}
|
|
|
|
ccid2_pr_debug("RTO_EXPIRE\n");
|
|
|
|
/* back-off timer */
|
|
hctx->rto <<= 1;
|
|
|
|
s = hctx->rto / HZ;
|
|
if (s > 60)
|
|
hctx->rto = 60 * HZ;
|
|
|
|
/* adjust pipe, cwnd etc */
|
|
hctx->ssthresh = hctx->cwnd / 2;
|
|
if (hctx->ssthresh < 2)
|
|
hctx->ssthresh = 2;
|
|
hctx->cwnd = 1;
|
|
hctx->pipe = 0;
|
|
|
|
/* clear state about stuff we sent */
|
|
hctx->seqt = hctx->seqh;
|
|
hctx->packets_acked = 0;
|
|
|
|
/* clear ack ratio state. */
|
|
hctx->rpseq = 0;
|
|
hctx->rpdupack = -1;
|
|
ccid2_change_l_ack_ratio(sk, 1);
|
|
|
|
/* if we were blocked before, we may now send cwnd=1 packet */
|
|
if (sender_was_blocked)
|
|
tasklet_schedule(&dccp_sk(sk)->dccps_xmitlet);
|
|
ccid2_start_rto_timer(sk);
|
|
out:
|
|
bh_unlock_sock(sk);
|
|
sock_put(sk);
|
|
}
|
|
|
|
static void ccid2_start_rto_timer(struct sock *sk)
|
|
{
|
|
struct ccid2_hc_tx_sock *hctx = ccid2_hc_tx_sk(sk);
|
|
|
|
ccid2_pr_debug("setting RTO timeout=%ld\n", hctx->rto);
|
|
|
|
BUG_ON(timer_pending(&hctx->rtotimer));
|
|
sk_reset_timer(sk, &hctx->rtotimer,
|
|
jiffies + hctx->rto);
|
|
}
|
|
|
|
static void ccid2_hc_tx_packet_sent(struct sock *sk, unsigned int len)
|
|
{
|
|
struct dccp_sock *dp = dccp_sk(sk);
|
|
struct ccid2_hc_tx_sock *hctx = ccid2_hc_tx_sk(sk);
|
|
struct ccid2_seq *next;
|
|
|
|
hctx->pipe++;
|
|
|
|
hctx->seqh->ccid2s_seq = dp->dccps_gss;
|
|
hctx->seqh->ccid2s_acked = 0;
|
|
hctx->seqh->ccid2s_sent = jiffies;
|
|
|
|
next = hctx->seqh->ccid2s_next;
|
|
/* check if we need to alloc more space */
|
|
if (next == hctx->seqt) {
|
|
if (ccid2_hc_tx_alloc_seq(hctx)) {
|
|
DCCP_CRIT("packet history - out of memory!");
|
|
/* FIXME: find a more graceful way to bail out */
|
|
return;
|
|
}
|
|
next = hctx->seqh->ccid2s_next;
|
|
BUG_ON(next == hctx->seqt);
|
|
}
|
|
hctx->seqh = next;
|
|
|
|
ccid2_pr_debug("cwnd=%d pipe=%d\n", hctx->cwnd, hctx->pipe);
|
|
|
|
/*
|
|
* FIXME: The code below is broken and the variables have been removed
|
|
* from the socket struct. The `ackloss' variable was always set to 0,
|
|
* and with arsent there are several problems:
|
|
* (i) it doesn't just count the number of Acks, but all sent packets;
|
|
* (ii) it is expressed in # of packets, not # of windows, so the
|
|
* comparison below uses the wrong formula: Appendix A of RFC 4341
|
|
* comes up with the number K = cwnd / (R^2 - R) of consecutive windows
|
|
* of data with no lost or marked Ack packets. If arsent were the # of
|
|
* consecutive Acks received without loss, then Ack Ratio needs to be
|
|
* decreased by 1 when
|
|
* arsent >= K * cwnd / R = cwnd^2 / (R^3 - R^2)
|
|
* where cwnd / R is the number of Acks received per window of data
|
|
* (cf. RFC 4341, App. A). The problems are that
|
|
* - arsent counts other packets as well;
|
|
* - the comparison uses a formula different from RFC 4341;
|
|
* - computing a cubic/quadratic equation each time is too complicated.
|
|
* Hence a different algorithm is needed.
|
|
*/
|
|
#if 0
|
|
/* Ack Ratio. Need to maintain a concept of how many windows we sent */
|
|
hctx->arsent++;
|
|
/* We had an ack loss in this window... */
|
|
if (hctx->ackloss) {
|
|
if (hctx->arsent >= hctx->cwnd) {
|
|
hctx->arsent = 0;
|
|
hctx->ackloss = 0;
|
|
}
|
|
} else {
|
|
/* No acks lost up to now... */
|
|
/* decrease ack ratio if enough packets were sent */
|
|
if (dp->dccps_l_ack_ratio > 1) {
|
|
/* XXX don't calculate denominator each time */
|
|
int denom = dp->dccps_l_ack_ratio * dp->dccps_l_ack_ratio -
|
|
dp->dccps_l_ack_ratio;
|
|
|
|
denom = hctx->cwnd * hctx->cwnd / denom;
|
|
|
|
if (hctx->arsent >= denom) {
|
|
ccid2_change_l_ack_ratio(sk, dp->dccps_l_ack_ratio - 1);
|
|
hctx->arsent = 0;
|
|
}
|
|
} else {
|
|
/* we can't increase ack ratio further [1] */
|
|
hctx->arsent = 0; /* or maybe set it to cwnd*/
|
|
}
|
|
}
|
|
#endif
|
|
|
|
/* setup RTO timer */
|
|
if (!timer_pending(&hctx->rtotimer))
|
|
ccid2_start_rto_timer(sk);
|
|
|
|
#ifdef CONFIG_IP_DCCP_CCID2_DEBUG
|
|
do {
|
|
struct ccid2_seq *seqp = hctx->seqt;
|
|
|
|
while (seqp != hctx->seqh) {
|
|
ccid2_pr_debug("out seq=%llu acked=%d time=%lu\n",
|
|
(unsigned long long)seqp->ccid2s_seq,
|
|
seqp->ccid2s_acked, seqp->ccid2s_sent);
|
|
seqp = seqp->ccid2s_next;
|
|
}
|
|
} while (0);
|
|
ccid2_pr_debug("=========\n");
|
|
#endif
|
|
}
|
|
|
|
static void ccid2_hc_tx_kill_rto_timer(struct sock *sk)
|
|
{
|
|
struct ccid2_hc_tx_sock *hctx = ccid2_hc_tx_sk(sk);
|
|
|
|
sk_stop_timer(sk, &hctx->rtotimer);
|
|
ccid2_pr_debug("deleted RTO timer\n");
|
|
}
|
|
|
|
static inline void ccid2_new_ack(struct sock *sk,
|
|
struct ccid2_seq *seqp,
|
|
unsigned int *maxincr)
|
|
{
|
|
struct ccid2_hc_tx_sock *hctx = ccid2_hc_tx_sk(sk);
|
|
|
|
if (hctx->cwnd < hctx->ssthresh) {
|
|
if (*maxincr > 0 && ++hctx->packets_acked == 2) {
|
|
hctx->cwnd += 1;
|
|
*maxincr -= 1;
|
|
hctx->packets_acked = 0;
|
|
}
|
|
} else if (++hctx->packets_acked >= hctx->cwnd) {
|
|
hctx->cwnd += 1;
|
|
hctx->packets_acked = 0;
|
|
}
|
|
|
|
/* update RTO */
|
|
if (hctx->srtt == -1 ||
|
|
time_after(jiffies, hctx->lastrtt + hctx->srtt)) {
|
|
unsigned long r = (long)jiffies - (long)seqp->ccid2s_sent;
|
|
int s;
|
|
|
|
/* first measurement */
|
|
if (hctx->srtt == -1) {
|
|
ccid2_pr_debug("R: %lu Time=%lu seq=%llu\n",
|
|
r, jiffies,
|
|
(unsigned long long)seqp->ccid2s_seq);
|
|
ccid2_change_srtt(hctx, r);
|
|
hctx->rttvar = r >> 1;
|
|
} else {
|
|
/* RTTVAR */
|
|
long tmp = hctx->srtt - r;
|
|
long srtt;
|
|
|
|
if (tmp < 0)
|
|
tmp *= -1;
|
|
|
|
tmp >>= 2;
|
|
hctx->rttvar *= 3;
|
|
hctx->rttvar >>= 2;
|
|
hctx->rttvar += tmp;
|
|
|
|
/* SRTT */
|
|
srtt = hctx->srtt;
|
|
srtt *= 7;
|
|
srtt >>= 3;
|
|
tmp = r >> 3;
|
|
srtt += tmp;
|
|
ccid2_change_srtt(hctx, srtt);
|
|
}
|
|
s = hctx->rttvar << 2;
|
|
/* clock granularity is 1 when based on jiffies */
|
|
if (!s)
|
|
s = 1;
|
|
hctx->rto = hctx->srtt + s;
|
|
|
|
/* must be at least a second */
|
|
s = hctx->rto / HZ;
|
|
/* DCCP doesn't require this [but I like it cuz my code sux] */
|
|
#if 1
|
|
if (s < 1)
|
|
hctx->rto = HZ;
|
|
#endif
|
|
/* max 60 seconds */
|
|
if (s > 60)
|
|
hctx->rto = HZ * 60;
|
|
|
|
hctx->lastrtt = jiffies;
|
|
|
|
ccid2_pr_debug("srtt: %ld rttvar: %ld rto: %ld (HZ=%d) R=%lu\n",
|
|
hctx->srtt, hctx->rttvar,
|
|
hctx->rto, HZ, r);
|
|
}
|
|
|
|
/* we got a new ack, so re-start RTO timer */
|
|
ccid2_hc_tx_kill_rto_timer(sk);
|
|
ccid2_start_rto_timer(sk);
|
|
}
|
|
|
|
static void ccid2_hc_tx_dec_pipe(struct sock *sk)
|
|
{
|
|
struct ccid2_hc_tx_sock *hctx = ccid2_hc_tx_sk(sk);
|
|
|
|
if (hctx->pipe == 0)
|
|
DCCP_BUG("pipe == 0");
|
|
else
|
|
hctx->pipe--;
|
|
|
|
if (hctx->pipe == 0)
|
|
ccid2_hc_tx_kill_rto_timer(sk);
|
|
}
|
|
|
|
static void ccid2_congestion_event(struct sock *sk, struct ccid2_seq *seqp)
|
|
{
|
|
struct ccid2_hc_tx_sock *hctx = ccid2_hc_tx_sk(sk);
|
|
|
|
if (time_before(seqp->ccid2s_sent, hctx->last_cong)) {
|
|
ccid2_pr_debug("Multiple losses in an RTT---treating as one\n");
|
|
return;
|
|
}
|
|
|
|
hctx->last_cong = jiffies;
|
|
|
|
hctx->cwnd = hctx->cwnd / 2 ? : 1U;
|
|
hctx->ssthresh = max(hctx->cwnd, 2U);
|
|
|
|
/* Avoid spurious timeouts resulting from Ack Ratio > cwnd */
|
|
if (dccp_sk(sk)->dccps_l_ack_ratio > hctx->cwnd)
|
|
ccid2_change_l_ack_ratio(sk, hctx->cwnd);
|
|
}
|
|
|
|
static int ccid2_hc_tx_parse_options(struct sock *sk, u8 packet_type,
|
|
u8 option, u8 *optval, u8 optlen)
|
|
{
|
|
struct ccid2_hc_tx_sock *hctx = ccid2_hc_tx_sk(sk);
|
|
|
|
switch (option) {
|
|
case DCCPO_ACK_VECTOR_0:
|
|
case DCCPO_ACK_VECTOR_1:
|
|
return dccp_ackvec_parsed_add(&hctx->av_chunks, optval, optlen,
|
|
option - DCCPO_ACK_VECTOR_0);
|
|
}
|
|
return 0;
|
|
}
|
|
|
|
static void ccid2_hc_tx_packet_recv(struct sock *sk, struct sk_buff *skb)
|
|
{
|
|
struct dccp_sock *dp = dccp_sk(sk);
|
|
struct ccid2_hc_tx_sock *hctx = ccid2_hc_tx_sk(sk);
|
|
const bool sender_was_blocked = ccid2_cwnd_network_limited(hctx);
|
|
struct dccp_ackvec_parsed *avp;
|
|
u64 ackno, seqno;
|
|
struct ccid2_seq *seqp;
|
|
int done = 0;
|
|
unsigned int maxincr = 0;
|
|
|
|
/* check reverse path congestion */
|
|
seqno = DCCP_SKB_CB(skb)->dccpd_seq;
|
|
|
|
/* XXX this whole "algorithm" is broken. Need to fix it to keep track
|
|
* of the seqnos of the dupacks so that rpseq and rpdupack are correct
|
|
* -sorbo.
|
|
*/
|
|
/* need to bootstrap */
|
|
if (hctx->rpdupack == -1) {
|
|
hctx->rpdupack = 0;
|
|
hctx->rpseq = seqno;
|
|
} else {
|
|
/* check if packet is consecutive */
|
|
if (dccp_delta_seqno(hctx->rpseq, seqno) == 1)
|
|
hctx->rpseq = seqno;
|
|
/* it's a later packet */
|
|
else if (after48(seqno, hctx->rpseq)) {
|
|
hctx->rpdupack++;
|
|
|
|
/* check if we got enough dupacks */
|
|
if (hctx->rpdupack >= NUMDUPACK) {
|
|
hctx->rpdupack = -1; /* XXX lame */
|
|
hctx->rpseq = 0;
|
|
|
|
ccid2_change_l_ack_ratio(sk, 2 * dp->dccps_l_ack_ratio);
|
|
}
|
|
}
|
|
}
|
|
|
|
/* check forward path congestion */
|
|
if (dccp_packet_without_ack(skb))
|
|
return;
|
|
|
|
/* still didn't send out new data packets */
|
|
if (hctx->seqh == hctx->seqt)
|
|
goto done;
|
|
|
|
ackno = DCCP_SKB_CB(skb)->dccpd_ack_seq;
|
|
if (after48(ackno, hctx->high_ack))
|
|
hctx->high_ack = ackno;
|
|
|
|
seqp = hctx->seqt;
|
|
while (before48(seqp->ccid2s_seq, ackno)) {
|
|
seqp = seqp->ccid2s_next;
|
|
if (seqp == hctx->seqh) {
|
|
seqp = hctx->seqh->ccid2s_prev;
|
|
break;
|
|
}
|
|
}
|
|
|
|
/*
|
|
* In slow-start, cwnd can increase up to a maximum of Ack Ratio/2
|
|
* packets per acknowledgement. Rounding up avoids that cwnd is not
|
|
* advanced when Ack Ratio is 1 and gives a slight edge otherwise.
|
|
*/
|
|
if (hctx->cwnd < hctx->ssthresh)
|
|
maxincr = DIV_ROUND_UP(dp->dccps_l_ack_ratio, 2);
|
|
|
|
/* go through all ack vectors */
|
|
list_for_each_entry(avp, &hctx->av_chunks, node) {
|
|
/* go through this ack vector */
|
|
for (; avp->len--; avp->vec++) {
|
|
u64 ackno_end_rl = SUB48(ackno,
|
|
dccp_ackvec_runlen(avp->vec));
|
|
|
|
ccid2_pr_debug("ackvec %llu |%u,%u|\n",
|
|
(unsigned long long)ackno,
|
|
dccp_ackvec_state(avp->vec) >> 6,
|
|
dccp_ackvec_runlen(avp->vec));
|
|
/* if the seqno we are analyzing is larger than the
|
|
* current ackno, then move towards the tail of our
|
|
* seqnos.
|
|
*/
|
|
while (after48(seqp->ccid2s_seq, ackno)) {
|
|
if (seqp == hctx->seqt) {
|
|
done = 1;
|
|
break;
|
|
}
|
|
seqp = seqp->ccid2s_prev;
|
|
}
|
|
if (done)
|
|
break;
|
|
|
|
/* check all seqnos in the range of the vector
|
|
* run length
|
|
*/
|
|
while (between48(seqp->ccid2s_seq,ackno_end_rl,ackno)) {
|
|
const u8 state = dccp_ackvec_state(avp->vec);
|
|
|
|
/* new packet received or marked */
|
|
if (state != DCCPAV_NOT_RECEIVED &&
|
|
!seqp->ccid2s_acked) {
|
|
if (state == DCCPAV_ECN_MARKED)
|
|
ccid2_congestion_event(sk,
|
|
seqp);
|
|
else
|
|
ccid2_new_ack(sk, seqp,
|
|
&maxincr);
|
|
|
|
seqp->ccid2s_acked = 1;
|
|
ccid2_pr_debug("Got ack for %llu\n",
|
|
(unsigned long long)seqp->ccid2s_seq);
|
|
ccid2_hc_tx_dec_pipe(sk);
|
|
}
|
|
if (seqp == hctx->seqt) {
|
|
done = 1;
|
|
break;
|
|
}
|
|
seqp = seqp->ccid2s_prev;
|
|
}
|
|
if (done)
|
|
break;
|
|
|
|
ackno = SUB48(ackno_end_rl, 1);
|
|
}
|
|
if (done)
|
|
break;
|
|
}
|
|
|
|
/* The state about what is acked should be correct now
|
|
* Check for NUMDUPACK
|
|
*/
|
|
seqp = hctx->seqt;
|
|
while (before48(seqp->ccid2s_seq, hctx->high_ack)) {
|
|
seqp = seqp->ccid2s_next;
|
|
if (seqp == hctx->seqh) {
|
|
seqp = hctx->seqh->ccid2s_prev;
|
|
break;
|
|
}
|
|
}
|
|
done = 0;
|
|
while (1) {
|
|
if (seqp->ccid2s_acked) {
|
|
done++;
|
|
if (done == NUMDUPACK)
|
|
break;
|
|
}
|
|
if (seqp == hctx->seqt)
|
|
break;
|
|
seqp = seqp->ccid2s_prev;
|
|
}
|
|
|
|
/* If there are at least 3 acknowledgements, anything unacknowledged
|
|
* below the last sequence number is considered lost
|
|
*/
|
|
if (done == NUMDUPACK) {
|
|
struct ccid2_seq *last_acked = seqp;
|
|
|
|
/* check for lost packets */
|
|
while (1) {
|
|
if (!seqp->ccid2s_acked) {
|
|
ccid2_pr_debug("Packet lost: %llu\n",
|
|
(unsigned long long)seqp->ccid2s_seq);
|
|
/* XXX need to traverse from tail -> head in
|
|
* order to detect multiple congestion events in
|
|
* one ack vector.
|
|
*/
|
|
ccid2_congestion_event(sk, seqp);
|
|
ccid2_hc_tx_dec_pipe(sk);
|
|
}
|
|
if (seqp == hctx->seqt)
|
|
break;
|
|
seqp = seqp->ccid2s_prev;
|
|
}
|
|
|
|
hctx->seqt = last_acked;
|
|
}
|
|
|
|
/* trim acked packets in tail */
|
|
while (hctx->seqt != hctx->seqh) {
|
|
if (!hctx->seqt->ccid2s_acked)
|
|
break;
|
|
|
|
hctx->seqt = hctx->seqt->ccid2s_next;
|
|
}
|
|
|
|
done:
|
|
/* check if incoming Acks allow pending packets to be sent */
|
|
if (sender_was_blocked && !ccid2_cwnd_network_limited(hctx))
|
|
tasklet_schedule(&dccp_sk(sk)->dccps_xmitlet);
|
|
dccp_ackvec_parsed_cleanup(&hctx->av_chunks);
|
|
}
|
|
|
|
static int ccid2_hc_tx_init(struct ccid *ccid, struct sock *sk)
|
|
{
|
|
struct ccid2_hc_tx_sock *hctx = ccid_priv(ccid);
|
|
struct dccp_sock *dp = dccp_sk(sk);
|
|
u32 max_ratio;
|
|
|
|
/* RFC 4341, 5: initialise ssthresh to arbitrarily high (max) value */
|
|
hctx->ssthresh = ~0U;
|
|
|
|
/*
|
|
* RFC 4341, 5: "The cwnd parameter is initialized to at most four
|
|
* packets for new connections, following the rules from [RFC3390]".
|
|
* We need to convert the bytes of RFC3390 into the packets of RFC 4341.
|
|
*/
|
|
hctx->cwnd = clamp(4380U / dp->dccps_mss_cache, 2U, 4U);
|
|
|
|
/* Make sure that Ack Ratio is enabled and within bounds. */
|
|
max_ratio = DIV_ROUND_UP(hctx->cwnd, 2);
|
|
if (dp->dccps_l_ack_ratio == 0 || dp->dccps_l_ack_ratio > max_ratio)
|
|
dp->dccps_l_ack_ratio = max_ratio;
|
|
|
|
/* XXX init ~ to window size... */
|
|
if (ccid2_hc_tx_alloc_seq(hctx))
|
|
return -ENOMEM;
|
|
|
|
hctx->rto = 3 * HZ;
|
|
ccid2_change_srtt(hctx, -1);
|
|
hctx->rttvar = -1;
|
|
hctx->rpdupack = -1;
|
|
hctx->last_cong = jiffies;
|
|
setup_timer(&hctx->rtotimer, ccid2_hc_tx_rto_expire, (unsigned long)sk);
|
|
INIT_LIST_HEAD(&hctx->av_chunks);
|
|
return 0;
|
|
}
|
|
|
|
static void ccid2_hc_tx_exit(struct sock *sk)
|
|
{
|
|
struct ccid2_hc_tx_sock *hctx = ccid2_hc_tx_sk(sk);
|
|
int i;
|
|
|
|
ccid2_hc_tx_kill_rto_timer(sk);
|
|
|
|
for (i = 0; i < hctx->seqbufc; i++)
|
|
kfree(hctx->seqbuf[i]);
|
|
hctx->seqbufc = 0;
|
|
}
|
|
|
|
static void ccid2_hc_rx_packet_recv(struct sock *sk, struct sk_buff *skb)
|
|
{
|
|
const struct dccp_sock *dp = dccp_sk(sk);
|
|
struct ccid2_hc_rx_sock *hcrx = ccid2_hc_rx_sk(sk);
|
|
|
|
switch (DCCP_SKB_CB(skb)->dccpd_type) {
|
|
case DCCP_PKT_DATA:
|
|
case DCCP_PKT_DATAACK:
|
|
hcrx->data++;
|
|
if (hcrx->data >= dp->dccps_r_ack_ratio) {
|
|
dccp_send_ack(sk);
|
|
hcrx->data = 0;
|
|
}
|
|
break;
|
|
}
|
|
}
|
|
|
|
static struct ccid_operations ccid2 = {
|
|
.ccid_id = DCCPC_CCID2,
|
|
.ccid_name = "TCP-like",
|
|
.ccid_owner = THIS_MODULE,
|
|
.ccid_hc_tx_obj_size = sizeof(struct ccid2_hc_tx_sock),
|
|
.ccid_hc_tx_init = ccid2_hc_tx_init,
|
|
.ccid_hc_tx_exit = ccid2_hc_tx_exit,
|
|
.ccid_hc_tx_send_packet = ccid2_hc_tx_send_packet,
|
|
.ccid_hc_tx_packet_sent = ccid2_hc_tx_packet_sent,
|
|
.ccid_hc_tx_parse_options = ccid2_hc_tx_parse_options,
|
|
.ccid_hc_tx_packet_recv = ccid2_hc_tx_packet_recv,
|
|
.ccid_hc_rx_obj_size = sizeof(struct ccid2_hc_rx_sock),
|
|
.ccid_hc_rx_packet_recv = ccid2_hc_rx_packet_recv,
|
|
};
|
|
|
|
#ifdef CONFIG_IP_DCCP_CCID2_DEBUG
|
|
module_param(ccid2_debug, bool, 0644);
|
|
MODULE_PARM_DESC(ccid2_debug, "Enable debug messages");
|
|
#endif
|
|
|
|
static __init int ccid2_module_init(void)
|
|
{
|
|
return ccid_register(&ccid2);
|
|
}
|
|
module_init(ccid2_module_init);
|
|
|
|
static __exit void ccid2_module_exit(void)
|
|
{
|
|
ccid_unregister(&ccid2);
|
|
}
|
|
module_exit(ccid2_module_exit);
|
|
|
|
MODULE_AUTHOR("Andrea Bittau <a.bittau@cs.ucl.ac.uk>");
|
|
MODULE_DESCRIPTION("DCCP TCP-Like (CCID2) CCID");
|
|
MODULE_LICENSE("GPL");
|
|
MODULE_ALIAS("net-dccp-ccid-2");
|