bkgpl/cyb4_linux
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Creation of Cybook 2416 (actually Gen4) repository

Browse Source
This commit is contained in:
mlt
2009-12-18 17:10:00 +00:00
committed by godzil
commit 76f20f4d40
13791 changed files with 6812321 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

125
net/dccp/ccids/Kconfig Normal file
View File

@@ -0,0 +1,125 @@
menu "DCCP CCIDs Configuration (EXPERIMENTAL)"
depends on IP_DCCP && EXPERIMENTAL
config IP_DCCP_CCID2
tristate "CCID2 (TCP-Like) (EXPERIMENTAL)"
depends on IP_DCCP
def_tristate IP_DCCP
select IP_DCCP_ACKVEC
---help---
CCID 2, TCP-like Congestion Control, denotes Additive Increase,
Multiplicative Decrease (AIMD) congestion control with behavior
modelled directly on TCP, including congestion window, slow start,
timeouts, and so forth [RFC 2581]. CCID 2 achieves maximum
bandwidth over the long term, consistent with the use of end-to-end
congestion control, but halves its congestion window in response to
each congestion event. This leads to the abrupt rate changes
typical of TCP. Applications should use CCID 2 if they prefer
maximum bandwidth utilization to steadiness of rate. This is often
the case for applications that are not playing their data directly
to the user. For example, a hypothetical application that
transferred files over DCCP, using application-level retransmissions
for lost packets, would prefer CCID 2 to CCID 3. On-line games may
also prefer CCID 2.
CCID 2 is further described in RFC 4341,
http://www.ietf.org/rfc/rfc4341.txt
This text was extracted from RFC 4340 (sec. 10.1),
http://www.ietf.org/rfc/rfc4340.txt
To compile this CCID as a module, choose M here: the module will be
called dccp_ccid2.
If in doubt, say M.
config IP_DCCP_CCID2_DEBUG
bool "CCID2 debugging messages"
depends on IP_DCCP_CCID2
---help---
Enable CCID2-specific debugging messages.
When compiling CCID2 as a module, this debugging output can
additionally be toggled by setting the ccid2_debug module
parameter to 0 or 1.
If in doubt, say N.
config IP_DCCP_CCID3
tristate "CCID3 (TCP-Friendly) (EXPERIMENTAL)"
depends on IP_DCCP
def_tristate IP_DCCP
---help---
CCID 3 denotes TCP-Friendly Rate Control (TFRC), an equation-based
rate-controlled congestion control mechanism. TFRC is designed to
be reasonably fair when competing for bandwidth with TCP-like flows,
where a flow is "reasonably fair" if its sending rate is generally
within a factor of two of the sending rate of a TCP flow under the
same conditions. However, TFRC has a much lower variation of
throughput over time compared with TCP, which makes CCID 3 more
suitable than CCID 2 for applications such streaming media where a
relatively smooth sending rate is of importance.
CCID 3 is further described in RFC 4342,
http://www.ietf.org/rfc/rfc4342.txt
The TFRC congestion control algorithms were initially described in
RFC 3448.
This text was extracted from RFC 4340 (sec. 10.2),
http://www.ietf.org/rfc/rfc4340.txt
To compile this CCID as a module, choose M here: the module will be
called dccp_ccid3.
If in doubt, say M.
config IP_DCCP_TFRC_LIB
depends on IP_DCCP_CCID3
def_tristate IP_DCCP_CCID3
config IP_DCCP_CCID3_DEBUG
bool "CCID3 debugging messages"
depends on IP_DCCP_CCID3
---help---
Enable CCID3-specific debugging messages.
When compiling CCID3 as a module, this debugging output can
additionally be toggled by setting the ccid3_debug module
parameter to 0 or 1.
If in doubt, say N.
config IP_DCCP_CCID3_RTO
int "Use higher bound for nofeedback timer"
default 100
depends on IP_DCCP_CCID3 && EXPERIMENTAL
---help---
Use higher lower bound for nofeedback timer expiration.
The TFRC nofeedback timer normally expires after the maximum of 4
RTTs and twice the current send interval (RFC 3448, 4.3). On LANs
with a small RTT this can mean a high processing load and reduced
performance, since then the nofeedback timer is triggered very
frequently.
This option enables to set a higher lower bound for the nofeedback
value. Values in units of milliseconds can be set here.
A value of 0 disables this feature by enforcing the value specified
in RFC 3448. The following values have been suggested as bounds for
experimental use:
* 16-20ms to match the typical multimedia inter-frame interval
* 100ms as a reasonable compromise [default]
* 1000ms corresponds to the lower TCP RTO bound (RFC 2988, 2.4)
The default of 100ms is a compromise between a large value for
efficient DCCP implementations, and a small value to avoid disrupting
the network in times of congestion.
The purpose of the nofeedback timer is to slow DCCP down when there
is serious network congestion: experimenting with larger values should
therefore not be performed on WANs.
endmenu

9
net/dccp/ccids/Makefile Normal file
View File

@@ -0,0 +1,9 @@
obj-$(CONFIG_IP_DCCP_CCID3) += dccp_ccid3.o
dccp_ccid3-y := ccid3.o
obj-$(CONFIG_IP_DCCP_CCID2) += dccp_ccid2.o
dccp_ccid2-y := ccid2.o
obj-y += lib/

857
net/dccp/ccids/ccid2.c Normal file
View File

@@ -0,0 +1,857 @@
/*
* 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
*
* BUGS:
* - sequence number wrapping
*/
#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)
static void ccid2_hc_tx_check_sanity(const struct ccid2_hc_tx_sock *hctx)
{
int len = 0;
int pipe = 0;
struct ccid2_seq *seqp = hctx->ccid2hctx_seqh;
/* there is data in the chain */
if (seqp != hctx->ccid2hctx_seqt) {
seqp = seqp->ccid2s_prev;
len++;
if (!seqp->ccid2s_acked)
pipe++;
while (seqp != hctx->ccid2hctx_seqt) {
struct ccid2_seq *prev = seqp->ccid2s_prev;
len++;
if (!prev->ccid2s_acked)
pipe++;
/* packets are sent sequentially */
BUG_ON(seqp->ccid2s_seq <= prev->ccid2s_seq);
BUG_ON(time_before(seqp->ccid2s_sent,
prev->ccid2s_sent));
seqp = prev;
}
}
BUG_ON(pipe != hctx->ccid2hctx_pipe);
ccid2_pr_debug("len of chain=%d\n", len);
do {
seqp = seqp->ccid2s_prev;
len++;
} while (seqp != hctx->ccid2hctx_seqh);
ccid2_pr_debug("total len=%d\n", len);
BUG_ON(len != hctx->ccid2hctx_seqbufc * CCID2_SEQBUF_LEN);
}
#else
#define ccid2_pr_debug(format, a...)
#define ccid2_hc_tx_check_sanity(hctx)
#endif
static int ccid2_hc_tx_alloc_seq(struct ccid2_hc_tx_sock *hctx, int num,
gfp_t gfp)
{
struct ccid2_seq *seqp;
int i;
/* check if we have space to preserve the pointer to the buffer */
if (hctx->ccid2hctx_seqbufc >= (sizeof(hctx->ccid2hctx_seqbuf) /
sizeof(struct ccid2_seq*)))
return -ENOMEM;
/* allocate buffer and initialize linked list */
seqp = kmalloc(sizeof(*seqp) * num, gfp);
if (seqp == NULL)
return -ENOMEM;
for (i = 0; i < (num - 1); i++) {
seqp[i].ccid2s_next = &seqp[i + 1];
seqp[i + 1].ccid2s_prev = &seqp[i];
}
seqp[num - 1].ccid2s_next = seqp;
seqp->ccid2s_prev = &seqp[num - 1];
/* This is the first allocation. Initiate the head and tail. */
if (hctx->ccid2hctx_seqbufc == 0)
hctx->ccid2hctx_seqh = hctx->ccid2hctx_seqt = seqp;
else {
/* link the existing list with the one we just created */
hctx->ccid2hctx_seqh->ccid2s_next = seqp;
seqp->ccid2s_prev = hctx->ccid2hctx_seqh;
hctx->ccid2hctx_seqt->ccid2s_prev = &seqp[num - 1];
seqp[num - 1].ccid2s_next = hctx->ccid2hctx_seqt;
}
/* store the original pointer to the buffer so we can free it */
hctx->ccid2hctx_seqbuf[hctx->ccid2hctx_seqbufc] = seqp;
hctx->ccid2hctx_seqbufc++;
return 0;
}
static int ccid2_hc_tx_send_packet(struct sock *sk, struct sk_buff *skb)
{
struct ccid2_hc_tx_sock *hctx;
switch (DCCP_SKB_CB(skb)->dccpd_type) {
case 0: /* XXX data packets from userland come through like this */
case DCCP_PKT_DATA:
case DCCP_PKT_DATAACK:
break;
/* No congestion control on other packets */
default:
return 0;
}
hctx = ccid2_hc_tx_sk(sk);
ccid2_pr_debug("pipe=%d cwnd=%d\n", hctx->ccid2hctx_pipe,
hctx->ccid2hctx_cwnd);
if (hctx->ccid2hctx_pipe < hctx->ccid2hctx_cwnd) {
/* OK we can send... make sure previous packet was sent off */
if (!hctx->ccid2hctx_sendwait) {
hctx->ccid2hctx_sendwait = 1;
return 0;
}
}
return 1; /* XXX CCID should dequeue when ready instead of polling */
}
static void ccid2_change_l_ack_ratio(struct sock *sk, int val)
{
struct dccp_sock *dp = dccp_sk(sk);
/*
* XXX I don't really agree with val != 2. If cwnd is 1, ack ratio
* should be 1... it shouldn't be allowed to become 2.
* -sorbo.
*/
if (val != 2) {
const struct ccid2_hc_tx_sock *hctx = ccid2_hc_tx_sk(sk);
int max = hctx->ccid2hctx_cwnd / 2;
/* round up */
if (hctx->ccid2hctx_cwnd & 1)
max++;
if (val > max)
val = max;
}
ccid2_pr_debug("changing local ack ratio to %d\n", val);
WARN_ON(val <= 0);
dp->dccps_l_ack_ratio = val;
}
static void ccid2_change_cwnd(struct ccid2_hc_tx_sock *hctx, int val)
{
if (val == 0)
val = 1;
/* XXX do we need to change ack ratio? */
ccid2_pr_debug("change cwnd to %d\n", val);
BUG_ON(val < 1);
hctx->ccid2hctx_cwnd = val;
}
static void ccid2_change_srtt(struct ccid2_hc_tx_sock *hctx, long val)
{
ccid2_pr_debug("change SRTT to %ld\n", val);
hctx->ccid2hctx_srtt = val;
}
static void ccid2_change_pipe(struct ccid2_hc_tx_sock *hctx, long val)
{
hctx->ccid2hctx_pipe = 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);
long s;
bh_lock_sock(sk);
if (sock_owned_by_user(sk)) {
sk_reset_timer(sk, &hctx->ccid2hctx_rtotimer,
jiffies + HZ / 5);
goto out;
}
ccid2_pr_debug("RTO_EXPIRE\n");
ccid2_hc_tx_check_sanity(hctx);
/* back-off timer */
hctx->ccid2hctx_rto <<= 1;
s = hctx->ccid2hctx_rto / HZ;
if (s > 60)
hctx->ccid2hctx_rto = 60 * HZ;
ccid2_start_rto_timer(sk);
/* adjust pipe, cwnd etc */
ccid2_change_pipe(hctx, 0);
hctx->ccid2hctx_ssthresh = hctx->ccid2hctx_cwnd >> 1;
if (hctx->ccid2hctx_ssthresh < 2)
hctx->ccid2hctx_ssthresh = 2;
ccid2_change_cwnd(hctx, 1);
/* clear state about stuff we sent */
hctx->ccid2hctx_seqt = hctx->ccid2hctx_seqh;
hctx->ccid2hctx_ssacks = 0;
hctx->ccid2hctx_acks = 0;
hctx->ccid2hctx_sent = 0;
/* clear ack ratio state. */
hctx->ccid2hctx_arsent = 0;
hctx->ccid2hctx_ackloss = 0;
hctx->ccid2hctx_rpseq = 0;
hctx->ccid2hctx_rpdupack = -1;
ccid2_change_l_ack_ratio(sk, 1);
ccid2_hc_tx_check_sanity(hctx);
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->ccid2hctx_rto);
BUG_ON(timer_pending(&hctx->ccid2hctx_rtotimer));
sk_reset_timer(sk, &hctx->ccid2hctx_rtotimer,
jiffies + hctx->ccid2hctx_rto);
}
static void ccid2_hc_tx_packet_sent(struct sock *sk, int more, 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;
u64 seq;
ccid2_hc_tx_check_sanity(hctx);
BUG_ON(!hctx->ccid2hctx_sendwait);
hctx->ccid2hctx_sendwait = 0;
ccid2_change_pipe(hctx, hctx->ccid2hctx_pipe + 1);
BUG_ON(hctx->ccid2hctx_pipe < 0);
/* There is an issue. What if another packet is sent between
* packet_send() and packet_sent(). Then the sequence number would be
* wrong.
* -sorbo.
*/
seq = dp->dccps_gss;
hctx->ccid2hctx_seqh->ccid2s_seq = seq;
hctx->ccid2hctx_seqh->ccid2s_acked = 0;
hctx->ccid2hctx_seqh->ccid2s_sent = jiffies;
next = hctx->ccid2hctx_seqh->ccid2s_next;
/* check if we need to alloc more space */
if (next == hctx->ccid2hctx_seqt) {
int rc;
ccid2_pr_debug("allocating more space in history\n");
rc = ccid2_hc_tx_alloc_seq(hctx, CCID2_SEQBUF_LEN, GFP_KERNEL);
BUG_ON(rc); /* XXX what do we do? */
next = hctx->ccid2hctx_seqh->ccid2s_next;
BUG_ON(next == hctx->ccid2hctx_seqt);
}
hctx->ccid2hctx_seqh = next;
ccid2_pr_debug("cwnd=%d pipe=%d\n", hctx->ccid2hctx_cwnd,
hctx->ccid2hctx_pipe);
hctx->ccid2hctx_sent++;
/* Ack Ratio. Need to maintain a concept of how many windows we sent */
hctx->ccid2hctx_arsent++;
/* We had an ack loss in this window... */
if (hctx->ccid2hctx_ackloss) {
if (hctx->ccid2hctx_arsent >= hctx->ccid2hctx_cwnd) {
hctx->ccid2hctx_arsent = 0;
hctx->ccid2hctx_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->ccid2hctx_cwnd * hctx->ccid2hctx_cwnd / denom;
if (hctx->ccid2hctx_arsent >= denom) {
ccid2_change_l_ack_ratio(sk, dp->dccps_l_ack_ratio - 1);
hctx->ccid2hctx_arsent = 0;
}
} else {
/* we can't increase ack ratio further [1] */
hctx->ccid2hctx_arsent = 0; /* or maybe set it to cwnd*/
}
}
/* setup RTO timer */
if (!timer_pending(&hctx->ccid2hctx_rtotimer))
ccid2_start_rto_timer(sk);
#ifdef CONFIG_IP_DCCP_CCID2_DEBUG
ccid2_pr_debug("pipe=%d\n", hctx->ccid2hctx_pipe);
ccid2_pr_debug("Sent: seq=%llu\n", (unsigned long long)seq);
do {
struct ccid2_seq *seqp = hctx->ccid2hctx_seqt;
while (seqp != hctx->ccid2hctx_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");
ccid2_hc_tx_check_sanity(hctx);
#endif
}
/* XXX Lame code duplication!
* returns -1 if none was found.
* else returns the next offset to use in the function call.
*/
static int ccid2_ackvector(struct sock *sk, struct sk_buff *skb, int offset,
unsigned char **vec, unsigned char *veclen)
{
const struct dccp_hdr *dh = dccp_hdr(skb);
unsigned char *options = (unsigned char *)dh + dccp_hdr_len(skb);
unsigned char *opt_ptr;
const unsigned char *opt_end = (unsigned char *)dh +
(dh->dccph_doff * 4);
unsigned char opt, len;
unsigned char *value;
BUG_ON(offset < 0);
options += offset;
opt_ptr = options;
if (opt_ptr >= opt_end)
return -1;
while (opt_ptr != opt_end) {
opt = *opt_ptr++;
len = 0;
value = NULL;
/* Check if this isn't a single byte option */
if (opt > DCCPO_MAX_RESERVED) {
if (opt_ptr == opt_end)
goto out_invalid_option;
len = *opt_ptr++;
if (len < 3)
goto out_invalid_option;
/*
* Remove the type and len fields, leaving
* just the value size
*/
len -= 2;
value = opt_ptr;
opt_ptr += len;
if (opt_ptr > opt_end)
goto out_invalid_option;
}
switch (opt) {
case DCCPO_ACK_VECTOR_0:
case DCCPO_ACK_VECTOR_1:
*vec = value;
*veclen = len;
return offset + (opt_ptr - options);
}
}
return -1;
out_invalid_option:
DCCP_BUG("Invalid option - this should not happen (previous parsing)!");
return -1;
}
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->ccid2hctx_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);
/* slow start */
if (hctx->ccid2hctx_cwnd < hctx->ccid2hctx_ssthresh) {
hctx->ccid2hctx_acks = 0;
/* We can increase cwnd at most maxincr [ack_ratio/2] */
if (*maxincr) {
/* increase every 2 acks */
hctx->ccid2hctx_ssacks++;
if (hctx->ccid2hctx_ssacks == 2) {
ccid2_change_cwnd(hctx, hctx->ccid2hctx_cwnd+1);
hctx->ccid2hctx_ssacks = 0;
*maxincr = *maxincr - 1;
}
} else {
/* increased cwnd enough for this single ack */
hctx->ccid2hctx_ssacks = 0;
}
} else {
hctx->ccid2hctx_ssacks = 0;
hctx->ccid2hctx_acks++;
if (hctx->ccid2hctx_acks >= hctx->ccid2hctx_cwnd) {
ccid2_change_cwnd(hctx, hctx->ccid2hctx_cwnd + 1);
hctx->ccid2hctx_acks = 0;
}
}
/* update RTO */
if (hctx->ccid2hctx_srtt == -1 ||
time_after(jiffies, hctx->ccid2hctx_lastrtt + hctx->ccid2hctx_srtt)) {
unsigned long r = (long)jiffies - (long)seqp->ccid2s_sent;
int s;
/* first measurement */
if (hctx->ccid2hctx_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->ccid2hctx_rttvar = r >> 1;
} else {
/* RTTVAR */
long tmp = hctx->ccid2hctx_srtt - r;
long srtt;
if (tmp < 0)
tmp *= -1;
tmp >>= 2;
hctx->ccid2hctx_rttvar *= 3;
hctx->ccid2hctx_rttvar >>= 2;
hctx->ccid2hctx_rttvar += tmp;
/* SRTT */
srtt = hctx->ccid2hctx_srtt;
srtt *= 7;
srtt >>= 3;
tmp = r >> 3;
srtt += tmp;
ccid2_change_srtt(hctx, srtt);
}
s = hctx->ccid2hctx_rttvar << 2;
/* clock granularity is 1 when based on jiffies */
if (!s)
s = 1;
hctx->ccid2hctx_rto = hctx->ccid2hctx_srtt + s;
/* must be at least a second */
s = hctx->ccid2hctx_rto / HZ;
/* DCCP doesn't require this [but I like it cuz my code sux] */
#if 1
if (s < 1)
hctx->ccid2hctx_rto = HZ;
#endif
/* max 60 seconds */
if (s > 60)
hctx->ccid2hctx_rto = HZ * 60;
hctx->ccid2hctx_lastrtt = jiffies;
ccid2_pr_debug("srtt: %ld rttvar: %ld rto: %ld (HZ=%d) R=%lu\n",
hctx->ccid2hctx_srtt, hctx->ccid2hctx_rttvar,
hctx->ccid2hctx_rto, HZ, r);
hctx->ccid2hctx_sent = 0;
}
/* 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);
ccid2_change_pipe(hctx, hctx->ccid2hctx_pipe-1);
BUG_ON(hctx->ccid2hctx_pipe < 0);
if (hctx->ccid2hctx_pipe == 0)
ccid2_hc_tx_kill_rto_timer(sk);
}
static void ccid2_congestion_event(struct ccid2_hc_tx_sock *hctx,
struct ccid2_seq *seqp)
{
if (time_before(seqp->ccid2s_sent, hctx->ccid2hctx_last_cong)) {
ccid2_pr_debug("Multiple losses in an RTT---treating as one\n");
return;
}
hctx->ccid2hctx_last_cong = jiffies;
ccid2_change_cwnd(hctx, hctx->ccid2hctx_cwnd >> 1);
hctx->ccid2hctx_ssthresh = hctx->ccid2hctx_cwnd;
if (hctx->ccid2hctx_ssthresh < 2)
hctx->ccid2hctx_ssthresh = 2;
}
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);
u64 ackno, seqno;
struct ccid2_seq *seqp;
unsigned char *vector;
unsigned char veclen;
int offset = 0;
int done = 0;
unsigned int maxincr = 0;
ccid2_hc_tx_check_sanity(hctx);
/* 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->ccid2hctx_rpdupack == -1) {
hctx->ccid2hctx_rpdupack = 0;
hctx->ccid2hctx_rpseq = seqno;
} else {
/* check if packet is consecutive */
if ((hctx->ccid2hctx_rpseq + 1) == seqno)
hctx->ccid2hctx_rpseq++;
/* it's a later packet */
else if (after48(seqno, hctx->ccid2hctx_rpseq)) {
hctx->ccid2hctx_rpdupack++;
/* check if we got enough dupacks */
if (hctx->ccid2hctx_rpdupack >=
hctx->ccid2hctx_numdupack) {
hctx->ccid2hctx_rpdupack = -1; /* XXX lame */
hctx->ccid2hctx_rpseq = 0;
ccid2_change_l_ack_ratio(sk, dp->dccps_l_ack_ratio << 1);
}
}
}
/* check forward path congestion */
/* still didn't send out new data packets */
if (hctx->ccid2hctx_seqh == hctx->ccid2hctx_seqt)
return;
switch (DCCP_SKB_CB(skb)->dccpd_type) {
case DCCP_PKT_ACK:
case DCCP_PKT_DATAACK:
break;
default:
return;
}
ackno = DCCP_SKB_CB(skb)->dccpd_ack_seq;
if (after48(ackno, hctx->ccid2hctx_high_ack))
hctx->ccid2hctx_high_ack = ackno;
seqp = hctx->ccid2hctx_seqt;
while (before48(seqp->ccid2s_seq, ackno)) {
seqp = seqp->ccid2s_next;
if (seqp == hctx->ccid2hctx_seqh) {
seqp = hctx->ccid2hctx_seqh->ccid2s_prev;
break;
}
}
/* If in slow-start, cwnd can increase at most Ack Ratio / 2 packets for
* this single ack. I round up.
* -sorbo.
*/
maxincr = dp->dccps_l_ack_ratio >> 1;
maxincr++;
/* go through all ack vectors */
while ((offset = ccid2_ackvector(sk, skb, offset,
&vector, &veclen)) != -1) {
/* go through this ack vector */
while (veclen--) {
const u8 rl = *vector & DCCP_ACKVEC_LEN_MASK;
u64 ackno_end_rl;
dccp_set_seqno(&ackno_end_rl, ackno - rl);
ccid2_pr_debug("ackvec start:%llu end:%llu\n",
(unsigned long long)ackno,
(unsigned long long)ackno_end_rl);
/* 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->ccid2hctx_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 = *vector &
DCCP_ACKVEC_STATE_MASK;
/* new packet received or marked */
if (state != DCCP_ACKVEC_STATE_NOT_RECEIVED &&
!seqp->ccid2s_acked) {
if (state ==
DCCP_ACKVEC_STATE_ECN_MARKED) {
ccid2_congestion_event(hctx,
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->ccid2hctx_seqt) {
done = 1;
break;
}
seqp = seqp->ccid2s_next;
}
if (done)
break;
dccp_set_seqno(&ackno, ackno_end_rl - 1);
vector++;
}
if (done)
break;
}
/* The state about what is acked should be correct now
* Check for NUMDUPACK
*/
seqp = hctx->ccid2hctx_seqt;
while (before48(seqp->ccid2s_seq, hctx->ccid2hctx_high_ack)) {
seqp = seqp->ccid2s_next;
if (seqp == hctx->ccid2hctx_seqh) {
seqp = hctx->ccid2hctx_seqh->ccid2s_prev;
break;
}
}
done = 0;
while (1) {
if (seqp->ccid2s_acked) {
done++;
if (done == hctx->ccid2hctx_numdupack)
break;
}
if (seqp == hctx->ccid2hctx_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 == hctx->ccid2hctx_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(hctx, seqp);
ccid2_hc_tx_dec_pipe(sk);
}
if (seqp == hctx->ccid2hctx_seqt)
break;
seqp = seqp->ccid2s_prev;
}
hctx->ccid2hctx_seqt = last_acked;
}
/* trim acked packets in tail */
while (hctx->ccid2hctx_seqt != hctx->ccid2hctx_seqh) {
if (!hctx->ccid2hctx_seqt->ccid2s_acked)
break;
hctx->ccid2hctx_seqt = hctx->ccid2hctx_seqt->ccid2s_next;
}
ccid2_hc_tx_check_sanity(hctx);
}
static int ccid2_hc_tx_init(struct ccid *ccid, struct sock *sk)
{
struct ccid2_hc_tx_sock *hctx = ccid_priv(ccid);
ccid2_change_cwnd(hctx, 1);
/* Initialize ssthresh to infinity. This means that we will exit the
* initial slow-start after the first packet loss. This is what we
* want.
*/
hctx->ccid2hctx_ssthresh = ~0;
hctx->ccid2hctx_numdupack = 3;
hctx->ccid2hctx_seqbufc = 0;
/* XXX init ~ to window size... */
if (ccid2_hc_tx_alloc_seq(hctx, CCID2_SEQBUF_LEN, GFP_ATOMIC) != 0)
return -ENOMEM;
hctx->ccid2hctx_sent = 0;
hctx->ccid2hctx_rto = 3 * HZ;
ccid2_change_srtt(hctx, -1);
hctx->ccid2hctx_rttvar = -1;
hctx->ccid2hctx_lastrtt = 0;
hctx->ccid2hctx_rpdupack = -1;
hctx->ccid2hctx_last_cong = jiffies;
hctx->ccid2hctx_high_ack = 0;
hctx->ccid2hctx_rtotimer.function = &ccid2_hc_tx_rto_expire;
hctx->ccid2hctx_rtotimer.data = (unsigned long)sk;
init_timer(&hctx->ccid2hctx_rtotimer);
ccid2_hc_tx_check_sanity(hctx);
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->ccid2hctx_seqbufc; i++)
kfree(hctx->ccid2hctx_seqbuf[i]);
hctx->ccid2hctx_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->ccid2hcrx_data++;
if (hcrx->ccid2hcrx_data >= dp->dccps_r_ack_ratio) {
dccp_send_ack(sk);
hcrx->ccid2hcrx_data = 0;
}
break;
}
}
static struct ccid_operations ccid2 = {
.ccid_id = DCCPC_CCID2,
.ccid_name = "ccid2",
.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_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, int, 0444);
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");

91
net/dccp/ccids/ccid2.h Normal file
View File

@@ -0,0 +1,91 @@
/*
* net/dccp/ccids/ccid2.h
*
* Copyright (c) 2005 Andrea Bittau <a.bittau@cs.ucl.ac.uk>
*
* 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.
*/
#ifndef _DCCP_CCID2_H_
#define _DCCP_CCID2_H_
#include <linux/dccp.h>
#include <linux/timer.h>
#include <linux/types.h>
#include "../ccid.h"
struct sock;
struct ccid2_seq {
u64 ccid2s_seq;
unsigned long ccid2s_sent;
int ccid2s_acked;
struct ccid2_seq *ccid2s_prev;
struct ccid2_seq *ccid2s_next;
};
#define CCID2_SEQBUF_LEN 1024
#define CCID2_SEQBUF_MAX 128
/** struct ccid2_hc_tx_sock - CCID2 TX half connection
*
* @ccid2hctx_ssacks - ACKs recv in slow start
* @ccid2hctx_acks - ACKS recv in AI phase
* @ccid2hctx_sent - packets sent in this window
* @ccid2hctx_lastrtt -time RTT was last measured
* @ccid2hctx_arsent - packets sent [ack ratio]
* @ccid2hctx_ackloss - ack was lost in this win
* @ccid2hctx_rpseq - last consecutive seqno
* @ccid2hctx_rpdupack - dupacks since rpseq
*/
struct ccid2_hc_tx_sock {
int ccid2hctx_cwnd;
int ccid2hctx_ssacks;
int ccid2hctx_acks;
unsigned int ccid2hctx_ssthresh;
int ccid2hctx_pipe;
int ccid2hctx_numdupack;
struct ccid2_seq *ccid2hctx_seqbuf[CCID2_SEQBUF_MAX];
int ccid2hctx_seqbufc;
struct ccid2_seq *ccid2hctx_seqh;
struct ccid2_seq *ccid2hctx_seqt;
long ccid2hctx_rto;
long ccid2hctx_srtt;
long ccid2hctx_rttvar;
int ccid2hctx_sent;
unsigned long ccid2hctx_lastrtt;
struct timer_list ccid2hctx_rtotimer;
unsigned long ccid2hctx_arsent;
int ccid2hctx_ackloss;
u64 ccid2hctx_rpseq;
int ccid2hctx_rpdupack;
int ccid2hctx_sendwait;
unsigned long ccid2hctx_last_cong;
u64 ccid2hctx_high_ack;
};
struct ccid2_hc_rx_sock {
int ccid2hcrx_data;
};
static inline struct ccid2_hc_tx_sock *ccid2_hc_tx_sk(const struct sock *sk)
{
return ccid_priv(dccp_sk(sk)->dccps_hc_tx_ccid);
}
static inline struct ccid2_hc_rx_sock *ccid2_hc_rx_sk(const struct sock *sk)
{
return ccid_priv(dccp_sk(sk)->dccps_hc_rx_ccid);
}
#endif /* _DCCP_CCID2_H_ */

1288
net/dccp/ccids/ccid3.c Normal file
View File

File diff suppressed because it is too large Load Diff

184
net/dccp/ccids/ccid3.h Normal file
View File

@@ -0,0 +1,184 @@
/*
* net/dccp/ccids/ccid3.h
*
* Copyright (c) 2005-6 The University of Waikato, Hamilton, New Zealand.
*
* An implementation of the DCCP protocol
*
* This code has been developed by the University of Waikato WAND
* research group. For further information please see http://www.wand.net.nz/
* or e-mail Ian McDonald - ian.mcdonald@jandi.co.nz
*
* This code also uses code from Lulea University, rereleased as GPL by its
* authors:
* Copyright (c) 2003 Nils-Erik Mattsson, Joacim Haggmark, Magnus Erixzon
*
* Changes to meet Linux coding standards, to make it meet latest ccid3 draft
* and to make it work as a loadable module in the DCCP stack written by
* Arnaldo Carvalho de Melo <acme@conectiva.com.br>.
*
* Copyright (c) 2005 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.
*/
#ifndef _DCCP_CCID3_H_
#define _DCCP_CCID3_H_
#include <linux/list.h>
#include <linux/time.h>
#include <linux/types.h>
#include <linux/tfrc.h>
#include "../ccid.h"
/* Two seconds as per RFC 3448 4.2 */
#define TFRC_INITIAL_TIMEOUT (2 * USEC_PER_SEC)
/* In usecs - half the scheduling granularity as per RFC3448 4.6 */
#define TFRC_OPSYS_HALF_TIME_GRAN (USEC_PER_SEC / (2 * HZ))
/* Parameter t_mbi from [RFC 3448, 4.3]: backoff interval in seconds */
#define TFRC_T_MBI 64
/* What we think is a reasonable upper limit on RTT values */
#define CCID3_SANE_RTT_MAX ((suseconds_t)(4 * USEC_PER_SEC))
#define CCID3_RTT_SANITY_CHECK(rtt) do { \
if (rtt > CCID3_SANE_RTT_MAX) { \
DCCP_CRIT("RTT (%d) too large, substituting %d", \
(int)rtt, (int)CCID3_SANE_RTT_MAX); \
rtt = CCID3_SANE_RTT_MAX; \
} } while (0)
enum ccid3_options {
TFRC_OPT_LOSS_EVENT_RATE = 192,
TFRC_OPT_LOSS_INTERVALS = 193,
TFRC_OPT_RECEIVE_RATE = 194,
};
struct ccid3_options_received {
u64 ccid3or_seqno:48,
ccid3or_loss_intervals_idx:16;
u16 ccid3or_loss_intervals_len;
u32 ccid3or_loss_event_rate;
u32 ccid3or_receive_rate;
};
/* TFRC sender states */
enum ccid3_hc_tx_states {
TFRC_SSTATE_NO_SENT = 1,
TFRC_SSTATE_NO_FBACK,
TFRC_SSTATE_FBACK,
TFRC_SSTATE_TERM,
};
/** struct ccid3_hc_tx_sock - CCID3 sender half-connection socket
*
* @ccid3hctx_x - Current sending rate in 64 * bytes per second
* @ccid3hctx_x_recv - Receive rate in 64 * bytes per second
* @ccid3hctx_x_calc - Calculated rate in bytes per second
* @ccid3hctx_rtt - Estimate of current round trip time in usecs
* @ccid3hctx_p - Current loss event rate (0-1) scaled by 1000000
* @ccid3hctx_s - Packet size in bytes
* @ccid3hctx_t_rto - Nofeedback Timer setting in usecs
* @ccid3hctx_t_ipi - Interpacket (send) interval (RFC 3448, 4.6) in usecs
* @ccid3hctx_state - Sender state, one of %ccid3_hc_tx_states
* @ccid3hctx_last_win_count - Last window counter sent
* @ccid3hctx_t_last_win_count - Timestamp of earliest packet
* with last_win_count value sent
* @ccid3hctx_no_feedback_timer - Handle to no feedback timer
* @ccid3hctx_idle - Flag indicating that sender is idling
* @ccid3hctx_t_ld - Time last doubled during slow start
* @ccid3hctx_t_nom - Nominal send time of next packet
* @ccid3hctx_delta - Send timer delta (RFC 3448, 4.6) in usecs
* @ccid3hctx_hist - Packet history
* @ccid3hctx_options_received - Parsed set of retrieved options
*/
struct ccid3_hc_tx_sock {
struct tfrc_tx_info ccid3hctx_tfrc;
#define ccid3hctx_x ccid3hctx_tfrc.tfrctx_x
#define ccid3hctx_x_recv ccid3hctx_tfrc.tfrctx_x_recv
#define ccid3hctx_x_calc ccid3hctx_tfrc.tfrctx_x_calc
#define ccid3hctx_rtt ccid3hctx_tfrc.tfrctx_rtt
#define ccid3hctx_p ccid3hctx_tfrc.tfrctx_p
#define ccid3hctx_t_rto ccid3hctx_tfrc.tfrctx_rto
#define ccid3hctx_t_ipi ccid3hctx_tfrc.tfrctx_ipi
u16 ccid3hctx_s;
enum ccid3_hc_tx_states ccid3hctx_state:8;
u8 ccid3hctx_last_win_count;
u8 ccid3hctx_idle;
struct timeval ccid3hctx_t_last_win_count;
struct timer_list ccid3hctx_no_feedback_timer;
struct timeval ccid3hctx_t_ld;
struct timeval ccid3hctx_t_nom;
u32 ccid3hctx_delta;
struct list_head ccid3hctx_hist;
struct ccid3_options_received ccid3hctx_options_received;
};
/* TFRC receiver states */
enum ccid3_hc_rx_states {
TFRC_RSTATE_NO_DATA = 1,
TFRC_RSTATE_DATA,
TFRC_RSTATE_TERM = 127,
};
/** struct ccid3_hc_rx_sock - CCID3 receiver half-connection socket
*
* @ccid3hcrx_x_recv - Receiver estimate of send rate (RFC 3448 4.3)
* @ccid3hcrx_rtt - Receiver estimate of rtt (non-standard)
* @ccid3hcrx_p - current loss event rate (RFC 3448 5.4)
* @ccid3hcrx_seqno_nonloss - Last received non-loss sequence number
* @ccid3hcrx_ccval_nonloss - Last received non-loss Window CCVal
* @ccid3hcrx_ccval_last_counter - Tracks window counter (RFC 4342, 8.1)
* @ccid3hcrx_state - receiver state, one of %ccid3_hc_rx_states
* @ccid3hcrx_bytes_recv - Total sum of DCCP payload bytes
* @ccid3hcrx_tstamp_last_feedback - Time at which last feedback was sent
* @ccid3hcrx_tstamp_last_ack - Time at which last feedback was sent
* @ccid3hcrx_hist - Packet history
* @ccid3hcrx_li_hist - Loss Interval History
* @ccid3hcrx_s - Received packet size in bytes
* @ccid3hcrx_pinv - Inverse of Loss Event Rate (RFC 4342, sec. 8.5)
* @ccid3hcrx_elapsed_time - Time since packet reception
*/
struct ccid3_hc_rx_sock {
struct tfrc_rx_info ccid3hcrx_tfrc;
#define ccid3hcrx_x_recv ccid3hcrx_tfrc.tfrcrx_x_recv
#define ccid3hcrx_rtt ccid3hcrx_tfrc.tfrcrx_rtt
#define ccid3hcrx_p ccid3hcrx_tfrc.tfrcrx_p
u64 ccid3hcrx_seqno_nonloss:48,
ccid3hcrx_ccval_nonloss:4,
ccid3hcrx_ccval_last_counter:4;
enum ccid3_hc_rx_states ccid3hcrx_state:8;
u32 ccid3hcrx_bytes_recv;
struct timeval ccid3hcrx_tstamp_last_feedback;
struct timeval ccid3hcrx_tstamp_last_ack;
struct list_head ccid3hcrx_hist;
struct list_head ccid3hcrx_li_hist;
u16 ccid3hcrx_s;
u32 ccid3hcrx_pinv;
u32 ccid3hcrx_elapsed_time;
};
static inline struct ccid3_hc_tx_sock *ccid3_hc_tx_sk(const struct sock *sk)
{
return ccid_priv(dccp_sk(sk)->dccps_hc_tx_ccid);
}
static inline struct ccid3_hc_rx_sock *ccid3_hc_rx_sk(const struct sock *sk)
{
return ccid_priv(dccp_sk(sk)->dccps_hc_rx_ccid);
}
#endif /* _DCCP_CCID3_H_ */

3
net/dccp/ccids/lib/Makefile Normal file
View File

@@ -0,0 +1,3 @@
obj-$(CONFIG_IP_DCCP_TFRC_LIB) += dccp_tfrc_lib.o
dccp_tfrc_lib-y := loss_interval.o packet_history.o tfrc_equation.o

143
net/dccp/ccids/lib/loss_interval.c Normal file
View File

@@ -0,0 +1,143 @@
/*
* net/dccp/ccids/lib/loss_interval.c
*
* Copyright (c) 2005 The University of Waikato, Hamilton, New Zealand.
* Copyright (c) 2005-6 Ian McDonald <ian.mcdonald@jandi.co.nz>
* Copyright (c) 2005 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/module.h>
#include <net/sock.h>
#include "../../dccp.h"
#include "loss_interval.h"
struct dccp_li_hist *dccp_li_hist_new(const char *name)
{
struct dccp_li_hist *hist = kmalloc(sizeof(*hist), GFP_ATOMIC);
static const char dccp_li_hist_mask[] = "li_hist_%s";
char *slab_name;
if (hist == NULL)
goto out;
slab_name = kmalloc(strlen(name) + sizeof(dccp_li_hist_mask) - 1,
GFP_ATOMIC);
if (slab_name == NULL)
goto out_free_hist;
sprintf(slab_name, dccp_li_hist_mask, name);
hist->dccplih_slab = kmem_cache_create(slab_name,
sizeof(struct dccp_li_hist_entry),
0, SLAB_HWCACHE_ALIGN,
NULL, NULL);
if (hist->dccplih_slab == NULL)
goto out_free_slab_name;
out:
return hist;
out_free_slab_name:
kfree(slab_name);
out_free_hist:
kfree(hist);
hist = NULL;
goto out;
}
EXPORT_SYMBOL_GPL(dccp_li_hist_new);
void dccp_li_hist_delete(struct dccp_li_hist *hist)
{
const char* name = kmem_cache_name(hist->dccplih_slab);
kmem_cache_destroy(hist->dccplih_slab);
kfree(name);
kfree(hist);
}
EXPORT_SYMBOL_GPL(dccp_li_hist_delete);
void dccp_li_hist_purge(struct dccp_li_hist *hist, struct list_head *list)
{
struct dccp_li_hist_entry *entry, *next;
list_for_each_entry_safe(entry, next, list, dccplih_node) {
list_del_init(&entry->dccplih_node);
kmem_cache_free(hist->dccplih_slab, entry);
}
}
EXPORT_SYMBOL_GPL(dccp_li_hist_purge);
/* Weights used to calculate loss event rate */
/*
* These are integers as per section 8 of RFC3448. We can then divide by 4 *
* when we use it.
*/
static const int dccp_li_hist_w[DCCP_LI_HIST_IVAL_F_LENGTH] = {
4, 4, 4, 4, 3, 2, 1, 1,
};
u32 dccp_li_hist_calc_i_mean(struct list_head *list)
{
struct dccp_li_hist_entry *li_entry, *li_next;
int i = 0;
u32 i_tot;
u32 i_tot0 = 0;
u32 i_tot1 = 0;
u32 w_tot = 0;
list_for_each_entry_safe(li_entry, li_next, list, dccplih_node) {
if (li_entry->dccplih_interval != ~0) {
i_tot0 += li_entry->dccplih_interval * dccp_li_hist_w[i];
w_tot += dccp_li_hist_w[i];
if (i != 0)
i_tot1 += li_entry->dccplih_interval * dccp_li_hist_w[i - 1];
}
if (++i > DCCP_LI_HIST_IVAL_F_LENGTH)
break;
}
if (i != DCCP_LI_HIST_IVAL_F_LENGTH)
return 0;
i_tot = max(i_tot0, i_tot1);
if (!w_tot) {
DCCP_WARN("w_tot = 0\n");
return 1;
}
return i_tot / w_tot;
}
EXPORT_SYMBOL_GPL(dccp_li_hist_calc_i_mean);
int dccp_li_hist_interval_new(struct dccp_li_hist *hist,
struct list_head *list, const u64 seq_loss, const u8 win_loss)
{
struct dccp_li_hist_entry *entry;
int i;
for (i = 0; i < DCCP_LI_HIST_IVAL_F_LENGTH; i++) {
entry = dccp_li_hist_entry_new(hist, GFP_ATOMIC);
if (entry == NULL) {
dccp_li_hist_purge(hist, list);
DCCP_BUG("loss interval list entry is NULL");
return 0;
}
entry->dccplih_interval = ~0;
list_add(&entry->dccplih_node, list);
}
entry->dccplih_seqno = seq_loss;
entry->dccplih_win_count = win_loss;
return 1;
}
EXPORT_SYMBOL_GPL(dccp_li_hist_interval_new);

57
net/dccp/ccids/lib/loss_interval.h Normal file
View File

@@ -0,0 +1,57 @@
#ifndef _DCCP_LI_HIST_
#define _DCCP_LI_HIST_
/*
* net/dccp/ccids/lib/loss_interval.h
*
* Copyright (c) 2005 The University of Waikato, Hamilton, New Zealand.
* Copyright (c) 2005 Ian McDonald <ian.mcdonald@jandi.co.nz>
* Copyright (c) 2005 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/list.h>
#include <linux/slab.h>
#include <linux/time.h>
#define DCCP_LI_HIST_IVAL_F_LENGTH 8
struct dccp_li_hist {
struct kmem_cache *dccplih_slab;
};
extern struct dccp_li_hist *dccp_li_hist_new(const char *name);
extern void dccp_li_hist_delete(struct dccp_li_hist *hist);
struct dccp_li_hist_entry {
struct list_head dccplih_node;
u64 dccplih_seqno:48,
dccplih_win_count:4;
u32 dccplih_interval;
};
static inline struct dccp_li_hist_entry *
dccp_li_hist_entry_new(struct dccp_li_hist *hist,
const gfp_t prio)
{
return kmem_cache_alloc(hist->dccplih_slab, prio);
}
static inline void dccp_li_hist_entry_delete(struct dccp_li_hist *hist,
struct dccp_li_hist_entry *entry)
{
if (entry != NULL)
kmem_cache_free(hist->dccplih_slab, entry);
}
extern void dccp_li_hist_purge(struct dccp_li_hist *hist,
struct list_head *list);
extern u32 dccp_li_hist_calc_i_mean(struct list_head *list);
extern int dccp_li_hist_interval_new(struct dccp_li_hist *hist,
struct list_head *list, const u64 seq_loss, const u8 win_loss);
#endif /* _DCCP_LI_HIST_ */

300
net/dccp/ccids/lib/packet_history.c Normal file
View File

@@ -0,0 +1,300 @@
/*
* net/dccp/packet_history.c
*
* Copyright (c) 2005-6 The University of Waikato, Hamilton, New Zealand.
*
* An implementation of the DCCP protocol
*
* This code has been developed by the University of Waikato WAND
* research group. For further information please see http://www.wand.net.nz/
* or e-mail Ian McDonald - ian.mcdonald@jandi.co.nz
*
* This code also uses code from Lulea University, rereleased as GPL by its
* authors:
* Copyright (c) 2003 Nils-Erik Mattsson, Joacim Haggmark, Magnus Erixzon
*
* Changes to meet Linux coding standards, to make it meet latest ccid3 draft
* and to make it work as a loadable module in the DCCP stack written by
* Arnaldo Carvalho de Melo <acme@conectiva.com.br>.
*
* Copyright (c) 2005 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.
*/
#include <linux/module.h>
#include <linux/string.h>
#include "packet_history.h"
/*
* Transmitter History Routines
*/
struct dccp_tx_hist *dccp_tx_hist_new(const char *name)
{
struct dccp_tx_hist *hist = kmalloc(sizeof(*hist), GFP_ATOMIC);
static const char dccp_tx_hist_mask[] = "tx_hist_%s";
char *slab_name;
if (hist == NULL)
goto out;
slab_name = kmalloc(strlen(name) + sizeof(dccp_tx_hist_mask) - 1,
GFP_ATOMIC);
if (slab_name == NULL)
goto out_free_hist;
sprintf(slab_name, dccp_tx_hist_mask, name);
hist->dccptxh_slab = kmem_cache_create(slab_name,
sizeof(struct dccp_tx_hist_entry),
0, SLAB_HWCACHE_ALIGN,
NULL, NULL);
if (hist->dccptxh_slab == NULL)
goto out_free_slab_name;
out:
return hist;
out_free_slab_name:
kfree(slab_name);
out_free_hist:
kfree(hist);
hist = NULL;
goto out;
}
EXPORT_SYMBOL_GPL(dccp_tx_hist_new);
void dccp_tx_hist_delete(struct dccp_tx_hist *hist)
{
const char* name = kmem_cache_name(hist->dccptxh_slab);
kmem_cache_destroy(hist->dccptxh_slab);
kfree(name);
kfree(hist);
}
EXPORT_SYMBOL_GPL(dccp_tx_hist_delete);
struct dccp_tx_hist_entry *
dccp_tx_hist_find_entry(const struct list_head *list, const u64 seq)
{
struct dccp_tx_hist_entry *packet = NULL, *entry;
list_for_each_entry(entry, list, dccphtx_node)
if (entry->dccphtx_seqno == seq) {
packet = entry;
break;
}
return packet;
}
EXPORT_SYMBOL_GPL(dccp_tx_hist_find_entry);
void dccp_tx_hist_purge(struct dccp_tx_hist *hist, struct list_head *list)
{
struct dccp_tx_hist_entry *entry, *next;
list_for_each_entry_safe(entry, next, list, dccphtx_node) {
list_del_init(&entry->dccphtx_node);
dccp_tx_hist_entry_delete(hist, entry);
}
}
EXPORT_SYMBOL_GPL(dccp_tx_hist_purge);
void dccp_tx_hist_purge_older(struct dccp_tx_hist *hist,
struct list_head *list,
struct dccp_tx_hist_entry *packet)
{
struct dccp_tx_hist_entry *next;
list_for_each_entry_safe_continue(packet, next, list, dccphtx_node) {
list_del_init(&packet->dccphtx_node);
dccp_tx_hist_entry_delete(hist, packet);
}
}
EXPORT_SYMBOL_GPL(dccp_tx_hist_purge_older);
/*
* Receiver History Routines
*/
struct dccp_rx_hist *dccp_rx_hist_new(const char *name)
{
struct dccp_rx_hist *hist = kmalloc(sizeof(*hist), GFP_ATOMIC);
static const char dccp_rx_hist_mask[] = "rx_hist_%s";
char *slab_name;
if (hist == NULL)
goto out;
slab_name = kmalloc(strlen(name) + sizeof(dccp_rx_hist_mask) - 1,
GFP_ATOMIC);
if (slab_name == NULL)
goto out_free_hist;
sprintf(slab_name, dccp_rx_hist_mask, name);
hist->dccprxh_slab = kmem_cache_create(slab_name,
sizeof(struct dccp_rx_hist_entry),
0, SLAB_HWCACHE_ALIGN,
NULL, NULL);
if (hist->dccprxh_slab == NULL)
goto out_free_slab_name;
out:
return hist;
out_free_slab_name:
kfree(slab_name);
out_free_hist:
kfree(hist);
hist = NULL;
goto out;
}
EXPORT_SYMBOL_GPL(dccp_rx_hist_new);
void dccp_rx_hist_delete(struct dccp_rx_hist *hist)
{
const char* name = kmem_cache_name(hist->dccprxh_slab);
kmem_cache_destroy(hist->dccprxh_slab);
kfree(name);
kfree(hist);
}
EXPORT_SYMBOL_GPL(dccp_rx_hist_delete);
int dccp_rx_hist_find_entry(const struct list_head *list, const u64 seq,
u8 *ccval)
{
struct dccp_rx_hist_entry *packet = NULL, *entry;
list_for_each_entry(entry, list, dccphrx_node)
if (entry->dccphrx_seqno == seq) {
packet = entry;
break;
}
if (packet)
*ccval = packet->dccphrx_ccval;
return packet != NULL;
}
EXPORT_SYMBOL_GPL(dccp_rx_hist_find_entry);
struct dccp_rx_hist_entry *
dccp_rx_hist_find_data_packet(const struct list_head *list)
{
struct dccp_rx_hist_entry *entry, *packet = NULL;
list_for_each_entry(entry, list, dccphrx_node)
if (entry->dccphrx_type == DCCP_PKT_DATA ||
entry->dccphrx_type == DCCP_PKT_DATAACK) {
packet = entry;
break;
}
return packet;
}
EXPORT_SYMBOL_GPL(dccp_rx_hist_find_data_packet);
void dccp_rx_hist_add_packet(struct dccp_rx_hist *hist,
struct list_head *rx_list,
struct list_head *li_list,
struct dccp_rx_hist_entry *packet,
u64 nonloss_seqno)
{
struct dccp_rx_hist_entry *entry, *next;
u8 num_later = 0;
list_add(&packet->dccphrx_node, rx_list);
num_later = TFRC_RECV_NUM_LATE_LOSS + 1;
if (!list_empty(li_list)) {
list_for_each_entry_safe(entry, next, rx_list, dccphrx_node) {
if (num_later == 0) {
if (after48(nonloss_seqno,
entry->dccphrx_seqno)) {
list_del_init(&entry->dccphrx_node);
dccp_rx_hist_entry_delete(hist, entry);
}
} else if (dccp_rx_hist_entry_data_packet(entry))
--num_later;
}
} else {
int step = 0;
u8 win_count = 0; /* Not needed, but lets shut up gcc */
int tmp;
/*
* We have no loss interval history so we need at least one
* rtt:s of data packets to approximate rtt.
*/
list_for_each_entry_safe(entry, next, rx_list, dccphrx_node) {
if (num_later == 0) {
switch (step) {
case 0:
step = 1;
/* OK, find next data packet */
num_later = 1;
break;
case 1:
step = 2;
/* OK, find next data packet */
num_later = 1;
win_count = entry->dccphrx_ccval;
break;
case 2:
tmp = win_count - entry->dccphrx_ccval;
if (tmp < 0)
tmp += TFRC_WIN_COUNT_LIMIT;
if (tmp > TFRC_WIN_COUNT_PER_RTT + 1) {
/*
* We have found a packet older
* than one rtt remove the rest
*/
step = 3;
} else /* OK, find next data packet */
num_later = 1;
break;
case 3:
list_del_init(&entry->dccphrx_node);
dccp_rx_hist_entry_delete(hist, entry);
break;
}
} else if (dccp_rx_hist_entry_data_packet(entry))
--num_later;
}
}
}
EXPORT_SYMBOL_GPL(dccp_rx_hist_add_packet);
void dccp_rx_hist_purge(struct dccp_rx_hist *hist, struct list_head *list)
{
struct dccp_rx_hist_entry *entry, *next;
list_for_each_entry_safe(entry, next, list, dccphrx_node) {
list_del_init(&entry->dccphrx_node);
kmem_cache_free(hist->dccprxh_slab, entry);
}
}
EXPORT_SYMBOL_GPL(dccp_rx_hist_purge);
MODULE_AUTHOR("Ian McDonald <ian.mcdonald@jandi.co.nz>, "
"Arnaldo Carvalho de Melo <acme@ghostprotocols.net>");
MODULE_DESCRIPTION("DCCP TFRC library");
MODULE_LICENSE("GPL");

202
net/dccp/ccids/lib/packet_history.h Normal file
View File

@@ -0,0 +1,202 @@
/*
* net/dccp/packet_history.h
*
* Copyright (c) 2005-6 The University of Waikato, Hamilton, New Zealand.
*
* An implementation of the DCCP protocol
*
* This code has been developed by the University of Waikato WAND
* research group. For further information please see http://www.wand.net.nz/
* or e-mail Ian McDonald - ian.mcdonald@jandi.co.nz
*
* This code also uses code from Lulea University, rereleased as GPL by its
* authors:
* Copyright (c) 2003 Nils-Erik Mattsson, Joacim Haggmark, Magnus Erixzon
*
* Changes to meet Linux coding standards, to make it meet latest ccid3 draft
* and to make it work as a loadable module in the DCCP stack written by
* Arnaldo Carvalho de Melo <acme@conectiva.com.br>.
*
* Copyright (c) 2005 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.
*/
#ifndef _DCCP_PKT_HIST_
#define _DCCP_PKT_HIST_
#include <linux/list.h>
#include <linux/slab.h>
#include <linux/time.h>
#include "../../dccp.h"
/* Number of later packets received before one is considered lost */
#define TFRC_RECV_NUM_LATE_LOSS 3
#define TFRC_WIN_COUNT_PER_RTT 4
#define TFRC_WIN_COUNT_LIMIT 16
/*
* Transmitter History data structures and declarations
*/
struct dccp_tx_hist_entry {
struct list_head dccphtx_node;
u64 dccphtx_seqno:48,
dccphtx_sent:1;
u32 dccphtx_rtt;
struct timeval dccphtx_tstamp;
};
struct dccp_tx_hist {
struct kmem_cache *dccptxh_slab;
};
extern struct dccp_tx_hist *dccp_tx_hist_new(const char *name);
extern void dccp_tx_hist_delete(struct dccp_tx_hist *hist);
static inline struct dccp_tx_hist_entry *
dccp_tx_hist_entry_new(struct dccp_tx_hist *hist,
const gfp_t prio)
{
struct dccp_tx_hist_entry *entry = kmem_cache_alloc(hist->dccptxh_slab,
prio);
if (entry != NULL)
entry->dccphtx_sent = 0;
return entry;
}
static inline struct dccp_tx_hist_entry *
dccp_tx_hist_head(struct list_head *list)
{
struct dccp_tx_hist_entry *head = NULL;
if (!list_empty(list))
head = list_entry(list->next, struct dccp_tx_hist_entry,
dccphtx_node);
return head;
}
extern struct dccp_tx_hist_entry *
dccp_tx_hist_find_entry(const struct list_head *list,
const u64 seq);
static inline void dccp_tx_hist_add_entry(struct list_head *list,
struct dccp_tx_hist_entry *entry)
{
list_add(&entry->dccphtx_node, list);
}
static inline void dccp_tx_hist_entry_delete(struct dccp_tx_hist *hist,
struct dccp_tx_hist_entry *entry)
{
if (entry != NULL)
kmem_cache_free(hist->dccptxh_slab, entry);
}
extern void dccp_tx_hist_purge(struct dccp_tx_hist *hist,
struct list_head *list);
extern void dccp_tx_hist_purge_older(struct dccp_tx_hist *hist,
struct list_head *list,
struct dccp_tx_hist_entry *next);
/*
* Receiver History data structures and declarations
*/
struct dccp_rx_hist_entry {
struct list_head dccphrx_node;
u64 dccphrx_seqno:48,
dccphrx_ccval:4,
dccphrx_type:4;
u32 dccphrx_ndp; /* In fact it is from 8 to 24 bits */
struct timeval dccphrx_tstamp;
};
struct dccp_rx_hist {
struct kmem_cache *dccprxh_slab;
};
extern struct dccp_rx_hist *dccp_rx_hist_new(const char *name);
extern void dccp_rx_hist_delete(struct dccp_rx_hist *hist);
static inline struct dccp_rx_hist_entry *
dccp_rx_hist_entry_new(struct dccp_rx_hist *hist,
const struct sock *sk,
const u32 ndp,
const struct sk_buff *skb,
const gfp_t prio)
{
struct dccp_rx_hist_entry *entry = kmem_cache_alloc(hist->dccprxh_slab,
prio);
if (entry != NULL) {
const struct dccp_hdr *dh = dccp_hdr(skb);
entry->dccphrx_seqno = DCCP_SKB_CB(skb)->dccpd_seq;
entry->dccphrx_ccval = dh->dccph_ccval;
entry->dccphrx_type = dh->dccph_type;
entry->dccphrx_ndp = ndp;
dccp_timestamp(sk, &entry->dccphrx_tstamp);
}
return entry;
}
static inline struct dccp_rx_hist_entry *
dccp_rx_hist_head(struct list_head *list)
{
struct dccp_rx_hist_entry *head = NULL;
if (!list_empty(list))
head = list_entry(list->next, struct dccp_rx_hist_entry,
dccphrx_node);
return head;
}
extern int dccp_rx_hist_find_entry(const struct list_head *list, const u64 seq,
u8 *ccval);
extern struct dccp_rx_hist_entry *
dccp_rx_hist_find_data_packet(const struct list_head *list);
extern void dccp_rx_hist_add_packet(struct dccp_rx_hist *hist,
struct list_head *rx_list,
struct list_head *li_list,
struct dccp_rx_hist_entry *packet,
u64 nonloss_seqno);
static inline void dccp_rx_hist_entry_delete(struct dccp_rx_hist *hist,
struct dccp_rx_hist_entry *entry)
{
if (entry != NULL)
kmem_cache_free(hist->dccprxh_slab, entry);
}
extern void dccp_rx_hist_purge(struct dccp_rx_hist *hist,
struct list_head *list);
static inline int
dccp_rx_hist_entry_data_packet(const struct dccp_rx_hist_entry *entry)
{
return entry->dccphrx_type == DCCP_PKT_DATA ||
entry->dccphrx_type == DCCP_PKT_DATAACK;
}
extern u64 dccp_rx_hist_detect_loss(struct list_head *rx_list,
struct list_head *li_list, u8 *win_loss);
#endif /* _DCCP_PKT_HIST_ */

43
net/dccp/ccids/lib/tfrc.h Normal file
View File

@@ -0,0 +1,43 @@
#ifndef _TFRC_H_
#define _TFRC_H_
/*
* net/dccp/ccids/lib/tfrc.h
*
* Copyright (c) 2005 The University of Waikato, Hamilton, New Zealand.
* Copyright (c) 2005 Ian McDonald <ian.mcdonald@jandi.co.nz>
* Copyright (c) 2005 Arnaldo Carvalho de Melo <acme@conectiva.com.br>
* Copyright (c) 2003 Nils-Erik Mattsson, Joacim Haggmark, Magnus Erixzon
*
* 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/types.h>
#include <asm/div64.h>
/* integer-arithmetic divisions of type (a * 1000000)/b */
static inline u64 scaled_div(u64 a, u32 b)
{
BUG_ON(b==0);
a *= 1000000;
do_div(a, b);
return a;
}
static inline u32 scaled_div32(u64 a, u32 b)
{
u64 result = scaled_div(a, b);
if (result > UINT_MAX) {
DCCP_CRIT("Overflow: a(%llu)/b(%u) > ~0U",
(unsigned long long)a, b);
return UINT_MAX;
}
return result;
}
extern u32 tfrc_calc_x(u16 s, u32 R, u32 p);
extern u32 tfrc_calc_x_reverse_lookup(u32 fvalue);
#endif /* _TFRC_H_ */

697
net/dccp/ccids/lib/tfrc_equation.c Normal file
View File

@@ -0,0 +1,697 @@
/*
* net/dccp/ccids/lib/tfrc_equation.c
*
* Copyright (c) 2005 The University of Waikato, Hamilton, New Zealand.
* Copyright (c) 2005 Ian McDonald <ian.mcdonald@jandi.co.nz>
* Copyright (c) 2005 Arnaldo Carvalho de Melo <acme@conectiva.com.br>
* Copyright (c) 2003 Nils-Erik Mattsson, Joacim Haggmark, Magnus Erixzon
*
* 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/module.h>
#include "../../dccp.h"
#include "tfrc.h"
#define TFRC_CALC_X_ARRSIZE 500
#define TFRC_CALC_X_SPLIT 50000 /* 0.05 * 1000000, details below */
#define TFRC_SMALLEST_P (TFRC_CALC_X_SPLIT/TFRC_CALC_X_ARRSIZE)
/*
TFRC TCP Reno Throughput Equation Lookup Table for f(p)
The following two-column lookup table implements a part of the TCP throughput
equation from [RFC 3448, sec. 3.1]:
s
X_calc = --------------------------------------------------------------
R * sqrt(2*b*p/3) + (3 * t_RTO * sqrt(3*b*p/8) * (p + 32*p^3))
Where:
X is the transmit rate in bytes/second
s is the packet size in bytes
R is the round trip time in seconds
p is the loss event rate, between 0 and 1.0, of the number of loss
events as a fraction of the number of packets transmitted
t_RTO is the TCP retransmission timeout value in seconds
b is the number of packets acknowledged by a single TCP ACK
We can assume that b = 1 and t_RTO is 4 * R. The equation now becomes:
s
X_calc = -------------------------------------------------------
R * sqrt(p*2/3) + (12 * R * sqrt(p*3/8) * (p + 32*p^3))
which we can break down into:
s
X_calc = ---------
R * f(p)
where f(p) is given for 0 < p <= 1 by:
f(p) = sqrt(2*p/3) + 12 * sqrt(3*p/8) * (p + 32*p^3)
Since this is kernel code, floating-point arithmetic is avoided in favour of
integer arithmetic. This means that nearly all fractional parameters are
scaled by 1000000:
* the parameters p and R
* the return result f(p)
The lookup table therefore actually tabulates the following function g(q):
g(q) = 1000000 * f(q/1000000)
Hence, when p <= 1, q must be less than or equal to 1000000. To achieve finer
granularity for the practically more relevant case of small values of p (up to
5%), the second column is used; the first one ranges up to 100%. This split
corresponds to the value of q = TFRC_CALC_X_SPLIT. At the same time this also
determines the smallest resolution possible with this lookup table:
TFRC_SMALLEST_P = TFRC_CALC_X_SPLIT / TFRC_CALC_X_ARRSIZE
The entire table is generated by:
for(i=0; i < TFRC_CALC_X_ARRSIZE; i++) {
lookup[i][0] = g((i+1) * 1000000/TFRC_CALC_X_ARRSIZE);
lookup[i][1] = g((i+1) * TFRC_CALC_X_SPLIT/TFRC_CALC_X_ARRSIZE);
}
With the given configuration, we have, with M = TFRC_CALC_X_ARRSIZE-1,
lookup[0][0] = g(1000000/(M+1)) = 1000000 * f(0.2%)
lookup[M][0] = g(1000000) = 1000000 * f(100%)
lookup[0][1] = g(TFRC_SMALLEST_P) = 1000000 * f(0.01%)
lookup[M][1] = g(TFRC_CALC_X_SPLIT) = 1000000 * f(5%)
In summary, the two columns represent f(p) for the following ranges:
* The first column is for 0.002 <= p <= 1.0
* The second column is for 0.0001 <= p <= 0.05
Where the columns overlap, the second (finer-grained) is given preference,
i.e. the first column is used only for p >= 0.05.
*/
static const u32 tfrc_calc_x_lookup[TFRC_CALC_X_ARRSIZE][2] = {
{ 37172, 8172 },
{ 53499, 11567 },
{ 66664, 14180 },
{ 78298, 16388 },
{ 89021, 18339 },
{ 99147, 20108 },
{ 108858, 21738 },
{ 118273, 23260 },
{ 127474, 24693 },
{ 136520, 26052 },
{ 145456, 27348 },
{ 154316, 28589 },
{ 163130, 29783 },
{ 171919, 30935 },
{ 180704, 32049 },
{ 189502, 33130 },
{ 198328, 34180 },
{ 207194, 35202 },
{ 216114, 36198 },
{ 225097, 37172 },
{ 234153, 38123 },
{ 243294, 39055 },
{ 252527, 39968 },
{ 261861, 40864 },
{ 271305, 41743 },
{ 280866, 42607 },
{ 290553, 43457 },
{ 300372, 44293 },
{ 310333, 45117 },
{ 320441, 45929 },
{ 330705, 46729 },
{ 341131, 47518 },
{ 351728, 48297 },
{ 362501, 49066 },
{ 373460, 49826 },
{ 384609, 50577 },
{ 395958, 51320 },
{ 407513, 52054 },
{ 419281, 52780 },
{ 431270, 53499 },
{ 443487, 54211 },
{ 455940, 54916 },
{ 468635, 55614 },
{ 481581, 56306 },
{ 494785, 56991 },
{ 508254, 57671 },
{ 521996, 58345 },
{ 536019, 59014 },
{ 550331, 59677 },
{ 564939, 60335 },
{ 579851, 60988 },
{ 595075, 61636 },
{ 610619, 62279 },
{ 626491, 62918 },
{ 642700, 63553 },
{ 659253, 64183 },
{ 676158, 64809 },
{ 693424, 65431 },
{ 711060, 66050 },
{ 729073, 66664 },
{ 747472, 67275 },
{ 766266, 67882 },
{ 785464, 68486 },
{ 805073, 69087 },
{ 825103, 69684 },
{ 845562, 70278 },
{ 866460, 70868 },
{ 887805, 71456 },
{ 909606, 72041 },
{ 931873, 72623 },
{ 954614, 73202 },
{ 977839, 73778 },
{ 1001557, 74352 },
{ 1025777, 74923 },
{ 1050508, 75492 },
{ 1075761, 76058 },
{ 1101544, 76621 },
{ 1127867, 77183 },
{ 1154739, 77741 },
{ 1182172, 78298 },
{ 1210173, 78852 },
{ 1238753, 79405 },
{ 1267922, 79955 },
{ 1297689, 80503 },
{ 1328066, 81049 },
{ 1359060, 81593 },
{ 1390684, 82135 },
{ 1422947, 82675 },
{ 1455859, 83213 },
{ 1489430, 83750 },
{ 1523671, 84284 },
{ 1558593, 84817 },
{ 1594205, 85348 },
{ 1630518, 85878 },
{ 1667543, 86406 },
{ 1705290, 86932 },
{ 1743770, 87457 },
{ 1782994, 87980 },
{ 1822973, 88501 },
{ 1863717, 89021 },
{ 1905237, 89540 },
{ 1947545, 90057 },
{ 1990650, 90573 },
{ 2034566, 91087 },
{ 2079301, 91600 },
{ 2124869, 92111 },
{ 2171279, 92622 },
{ 2218543, 93131 },
{ 2266673, 93639 },
{ 2315680, 94145 },
{ 2365575, 94650 },
{ 2416371, 95154 },
{ 2468077, 95657 },
{ 2520707, 96159 },
{ 2574271, 96660 },
{ 2628782, 97159 },
{ 2684250, 97658 },
{ 2740689, 98155 },
{ 2798110, 98651 },
{ 2856524, 99147 },
{ 2915944, 99641 },
{ 2976382, 100134 },
{ 3037850, 100626 },
{ 3100360, 101117 },
{ 3163924, 101608 },
{ 3228554, 102097 },
{ 3294263, 102586 },
{ 3361063, 103073 },
{ 3428966, 103560 },
{ 3497984, 104045 },
{ 3568131, 104530 },
{ 3639419, 105014 },
{ 3711860, 105498 },
{ 3785467, 105980 },
{ 3860253, 106462 },
{ 3936229, 106942 },
{ 4013410, 107422 },
{ 4091808, 107902 },
{ 4171435, 108380 },
{ 4252306, 108858 },
{ 4334431, 109335 },
{ 4417825, 109811 },
{ 4502501, 110287 },
{ 4588472, 110762 },
{ 4675750, 111236 },
{ 4764349, 111709 },
{ 4854283, 112182 },
{ 4945564, 112654 },
{ 5038206, 113126 },
{ 5132223, 113597 },
{ 5227627, 114067 },
{ 5324432, 114537 },
{ 5422652, 115006 },
{ 5522299, 115474 },
{ 5623389, 115942 },
{ 5725934, 116409 },
{ 5829948, 116876 },
{ 5935446, 117342 },
{ 6042439, 117808 },
{ 6150943, 118273 },
{ 6260972, 118738 },
{ 6372538, 119202 },
{ 6485657, 119665 },
{ 6600342, 120128 },
{ 6716607, 120591 },
{ 6834467, 121053 },
{ 6953935, 121514 },
{ 7075025, 121976 },
{ 7197752, 122436 },
{ 7322131, 122896 },
{ 7448175, 123356 },
{ 7575898, 123815 },
{ 7705316, 124274 },
{ 7836442, 124733 },
{ 7969291, 125191 },
{ 8103877, 125648 },
{ 8240216, 126105 },
{ 8378321, 126562 },
{ 8518208, 127018 },
{ 8659890, 127474 },
{ 8803384, 127930 },
{ 8948702, 128385 },
{ 9095861, 128840 },
{ 9244875, 129294 },
{ 9395760, 129748 },
{ 9548529, 130202 },
{ 9703198, 130655 },
{ 9859782, 131108 },
{ 10018296, 131561 },
{ 10178755, 132014 },
{ 10341174, 132466 },
{ 10505569, 132917 },
{ 10671954, 133369 },
{ 10840345, 133820 },
{ 11010757, 134271 },
{ 11183206, 134721 },
{ 11357706, 135171 },
{ 11534274, 135621 },
{ 11712924, 136071 },
{ 11893673, 136520 },
{ 12076536, 136969 },
{ 12261527, 137418 },
{ 12448664, 137867 },
{ 12637961, 138315 },
{ 12829435, 138763 },
{ 13023101, 139211 },
{ 13218974, 139658 },
{ 13417071, 140106 },
{ 13617407, 140553 },
{ 13819999, 140999 },
{ 14024862, 141446 },
{ 14232012, 141892 },
{ 14441465, 142339 },
{ 14653238, 142785 },
{ 14867346, 143230 },
{ 15083805, 143676 },
{ 15302632, 144121 },
{ 15523842, 144566 },
{ 15747453, 145011 },
{ 15973479, 145456 },
{ 16201939, 145900 },
{ 16432847, 146345 },
{ 16666221, 146789 },
{ 16902076, 147233 },
{ 17140429, 147677 },
{ 17381297, 148121 },
{ 17624696, 148564 },
{ 17870643, 149007 },
{ 18119154, 149451 },
{ 18370247, 149894 },
{ 18623936, 150336 },
{ 18880241, 150779 },
{ 19139176, 151222 },
{ 19400759, 151664 },
{ 19665007, 152107 },
{ 19931936, 152549 },
{ 20201564, 152991 },
{ 20473907, 153433 },
{ 20748982, 153875 },
{ 21026807, 154316 },
{ 21307399, 154758 },
{ 21590773, 155199 },
{ 21876949, 155641 },
{ 22165941, 156082 },
{ 22457769, 156523 },
{ 22752449, 156964 },
{ 23049999, 157405 },
{ 23350435, 157846 },
{ 23653774, 158287 },
{ 23960036, 158727 },
{ 24269236, 159168 },
{ 24581392, 159608 },
{ 24896521, 160049 },
{ 25214642, 160489 },
{ 25535772, 160929 },
{ 25859927, 161370 },
{ 26187127, 161810 },
{ 26517388, 162250 },
{ 26850728, 162690 },
{ 27187165, 163130 },
{ 27526716, 163569 },
{ 27869400, 164009 },
{ 28215234, 164449 },
{ 28564236, 164889 },
{ 28916423, 165328 },
{ 29271815, 165768 },
{ 29630428, 166208 },
{ 29992281, 166647 },
{ 30357392, 167087 },
{ 30725779, 167526 },
{ 31097459, 167965 },
{ 31472452, 168405 },
{ 31850774, 168844 },
{ 32232445, 169283 },
{ 32617482, 169723 },
{ 33005904, 170162 },
{ 33397730, 170601 },
{ 33792976, 171041 },
{ 34191663, 171480 },
{ 34593807, 171919 },
{ 34999428, 172358 },
{ 35408544, 172797 },
{ 35821174, 173237 },
{ 36237335, 173676 },
{ 36657047, 174115 },
{ 37080329, 174554 },
{ 37507197, 174993 },
{ 37937673, 175433 },
{ 38371773, 175872 },
{ 38809517, 176311 },
{ 39250924, 176750 },
{ 39696012, 177190 },
{ 40144800, 177629 },
{ 40597308, 178068 },
{ 41053553, 178507 },
{ 41513554, 178947 },
{ 41977332, 179386 },
{ 42444904, 179825 },
{ 42916290, 180265 },
{ 43391509, 180704 },
{ 43870579, 181144 },
{ 44353520, 181583 },
{ 44840352, 182023 },
{ 45331092, 182462 },
{ 45825761, 182902 },
{ 46324378, 183342 },
{ 46826961, 183781 },
{ 47333531, 184221 },
{ 47844106, 184661 },
{ 48358706, 185101 },
{ 48877350, 185541 },
{ 49400058, 185981 },
{ 49926849, 186421 },
{ 50457743, 186861 },
{ 50992759, 187301 },
{ 51531916, 187741 },
{ 52075235, 188181 },
{ 52622735, 188622 },
{ 53174435, 189062 },
{ 53730355, 189502 },
{ 54290515, 189943 },
{ 54854935, 190383 },
{ 55423634, 190824 },
{ 55996633, 191265 },
{ 56573950, 191706 },
{ 57155606, 192146 },
{ 57741621, 192587 },
{ 58332014, 193028 },
{ 58926806, 193470 },
{ 59526017, 193911 },
{ 60129666, 194352 },
{ 60737774, 194793 },
{ 61350361, 195235 },
{ 61967446, 195677 },
{ 62589050, 196118 },
{ 63215194, 196560 },
{ 63845897, 197002 },
{ 64481179, 197444 },
{ 65121061, 197886 },
{ 65765563, 198328 },
{ 66414705, 198770 },
{ 67068508, 199213 },
{ 67726992, 199655 },
{ 68390177, 200098 },
{ 69058085, 200540 },
{ 69730735, 200983 },
{ 70408147, 201426 },
{ 71090343, 201869 },
{ 71777343, 202312 },
{ 72469168, 202755 },
{ 73165837, 203199 },
{ 73867373, 203642 },
{ 74573795, 204086 },
{ 75285124, 204529 },
{ 76001380, 204973 },
{ 76722586, 205417 },
{ 77448761, 205861 },
{ 78179926, 206306 },
{ 78916102, 206750 },
{ 79657310, 207194 },
{ 80403571, 207639 },
{ 81154906, 208084 },
{ 81911335, 208529 },
{ 82672880, 208974 },
{ 83439562, 209419 },
{ 84211402, 209864 },
{ 84988421, 210309 },
{ 85770640, 210755 },
{ 86558080, 211201 },
{ 87350762, 211647 },
{ 88148708, 212093 },
{ 88951938, 212539 },
{ 89760475, 212985 },
{ 90574339, 213432 },
{ 91393551, 213878 },
{ 92218133, 214325 },
{ 93048107, 214772 },
{ 93883493, 215219 },
{ 94724314, 215666 },
{ 95570590, 216114 },
{ 96422343, 216561 },
{ 97279594, 217009 },
{ 98142366, 217457 },
{ 99010679, 217905 },
{ 99884556, 218353 },
{ 100764018, 218801 },
{ 101649086, 219250 },
{ 102539782, 219698 },
{ 103436128, 220147 },
{ 104338146, 220596 },
{ 105245857, 221046 },
{ 106159284, 221495 },
{ 107078448, 221945 },
{ 108003370, 222394 },
{ 108934074, 222844 },
{ 109870580, 223294 },
{ 110812910, 223745 },
{ 111761087, 224195 },
{ 112715133, 224646 },
{ 113675069, 225097 },
{ 114640918, 225548 },
{ 115612702, 225999 },
{ 116590442, 226450 },
{ 117574162, 226902 },
{ 118563882, 227353 },
{ 119559626, 227805 },
{ 120561415, 228258 },
{ 121569272, 228710 },
{ 122583219, 229162 },
{ 123603278, 229615 },
{ 124629471, 230068 },
{ 125661822, 230521 },
{ 126700352, 230974 },
{ 127745083, 231428 },
{ 128796039, 231882 },
{ 129853241, 232336 },
{ 130916713, 232790 },
{ 131986475, 233244 },
{ 133062553, 233699 },
{ 134144966, 234153 },
{ 135233739, 234608 },
{ 136328894, 235064 },
{ 137430453, 235519 },
{ 138538440, 235975 },
{ 139652876, 236430 },
{ 140773786, 236886 },
{ 141901190, 237343 },
{ 143035113, 237799 },
{ 144175576, 238256 },
{ 145322604, 238713 },
{ 146476218, 239170 },
{ 147636442, 239627 },
{ 148803298, 240085 },
{ 149976809, 240542 },
{ 151156999, 241000 },
{ 152343890, 241459 },
{ 153537506, 241917 },
{ 154737869, 242376 },
{ 155945002, 242835 },
{ 157158929, 243294 },
{ 158379673, 243753 },
{ 159607257, 244213 },
{ 160841704, 244673 },
{ 162083037, 245133 },
{ 163331279, 245593 },
{ 164586455, 246054 },
{ 165848586, 246514 },
{ 167117696, 246975 },
{ 168393810, 247437 },
{ 169676949, 247898 },
{ 170967138, 248360 },
{ 172264399, 248822 },
{ 173568757, 249284 },
{ 174880235, 249747 },
{ 176198856, 250209 },
{ 177524643, 250672 },
{ 178857621, 251136 },
{ 180197813, 251599 },
{ 181545242, 252063 },
{ 182899933, 252527 },
{ 184261908, 252991 },
{ 185631191, 253456 },
{ 187007807, 253920 },
{ 188391778, 254385 },
{ 189783129, 254851 },
{ 191181884, 255316 },
{ 192588065, 255782 },
{ 194001698, 256248 },
{ 195422805, 256714 },
{ 196851411, 257181 },
{ 198287540, 257648 },
{ 199731215, 258115 },
{ 201182461, 258582 },
{ 202641302, 259050 },
{ 204107760, 259518 },
{ 205581862, 259986 },
{ 207063630, 260454 },
{ 208553088, 260923 },
{ 210050262, 261392 },
{ 211555174, 261861 },
{ 213067849, 262331 },
{ 214588312, 262800 },
{ 216116586, 263270 },
{ 217652696, 263741 },
{ 219196666, 264211 },
{ 220748520, 264682 },
{ 222308282, 265153 },
{ 223875978, 265625 },
{ 225451630, 266097 },
{ 227035265, 266569 },
{ 228626905, 267041 },
{ 230226576, 267514 },
{ 231834302, 267986 },
{ 233450107, 268460 },
{ 235074016, 268933 },
{ 236706054, 269407 },
{ 238346244, 269881 },
{ 239994613, 270355 },
{ 241651183, 270830 },
{ 243315981, 271305 }
};
/* return largest index i such that fval <= lookup[i][small] */
static inline u32 tfrc_binsearch(u32 fval, u8 small)
{
u32 try, low = 0, high = TFRC_CALC_X_ARRSIZE - 1;
while (low < high) {
try = (low + high) / 2;
if (fval <= tfrc_calc_x_lookup[try][small])
high = try;
else
low = try + 1;
}
return high;
}
/**
* tfrc_calc_x - Calculate the send rate as per section 3.1 of RFC3448
*
* @s: packet size in bytes
* @R: RTT scaled by 1000000 (i.e., microseconds)
* @p: loss ratio estimate scaled by 1000000
* Returns X_calc in bytes per second (not scaled).
*/
u32 tfrc_calc_x(u16 s, u32 R, u32 p)
{
u16 index;
u32 f;
u64 result;
/* check against invalid parameters and divide-by-zero */
BUG_ON(p > 1000000); /* p must not exceed 100% */
BUG_ON(p == 0); /* f(0) = 0, divide by zero */
if (R == 0) { /* possible divide by zero */
DCCP_CRIT("WARNING: RTT is 0, returning maximum X_calc.");
return ~0U;
}
if (p <= TFRC_CALC_X_SPLIT) { /* 0.0000 < p <= 0.05 */
if (p < TFRC_SMALLEST_P) { /* 0.0000 < p < 0.0001 */
DCCP_WARN("Value of p (%d) below resolution. "
"Substituting %d\n", p, TFRC_SMALLEST_P);
index = 0;
} else /* 0.0001 <= p <= 0.05 */
index = p/TFRC_SMALLEST_P - 1;
f = tfrc_calc_x_lookup[index][1];
} else { /* 0.05 < p <= 1.00 */
index = p/(1000000/TFRC_CALC_X_ARRSIZE) - 1;
f = tfrc_calc_x_lookup[index][0];
}
/*
* Compute X = s/(R*f(p)) in bytes per second.
* Since f(p) and R are both scaled by 1000000, we need to multiply by
* 1000000^2. To avoid overflow, the result is computed in two stages.
* This works under almost all reasonable operational conditions, for a
* wide range of parameters. Yet, should some strange combination of
* parameters result in overflow, the use of scaled_div32 will catch
* this and return UINT_MAX - which is a logically adequate consequence.
*/
result = scaled_div(s, R);
return scaled_div32(result, f);
}
EXPORT_SYMBOL_GPL(tfrc_calc_x);
/*
* tfrc_calc_x_reverse_lookup - try to find p given f(p)
*
* @fvalue: function value to match, scaled by 1000000
* Returns closest match for p, also scaled by 1000000
*/
u32 tfrc_calc_x_reverse_lookup(u32 fvalue)
{
int index;
if (fvalue == 0) /* f(p) = 0 whenever p = 0 */
return 0;
/* Error cases. */
if (fvalue < tfrc_calc_x_lookup[0][1]) {
DCCP_WARN("fvalue %d smaller than resolution\n", fvalue);
return tfrc_calc_x_lookup[0][1];
}
if (fvalue > tfrc_calc_x_lookup[TFRC_CALC_X_ARRSIZE - 1][0]) {
DCCP_WARN("fvalue %d exceeds bounds!\n", fvalue);
return 1000000;
}
if (fvalue <= tfrc_calc_x_lookup[TFRC_CALC_X_ARRSIZE - 1][1]) {
index = tfrc_binsearch(fvalue, 1);
return (index + 1) * TFRC_CALC_X_SPLIT / TFRC_CALC_X_ARRSIZE;
}
/* else ... it must be in the coarse-grained column */
index = tfrc_binsearch(fvalue, 0);
return (index + 1) * 1000000 / TFRC_CALC_X_ARRSIZE;
}
EXPORT_SYMBOL_GPL(tfrc_calc_x_reverse_lookup);