9891578a40
Each TCP connection that uses the system default cc_newreno(4) congestion control algorithm module leaks a "struct newreno" (8 bytes of memory) at connection initialisation time. The NULL-pointer dereference is only germane when using the ABE feature, which is disabled by default. While at it: - Defer the allocation of memory until it is actually needed given that ABE is optional and disabled by default. - Document the ENOMEM errno in getsockopt(2)/setsockopt(2). - Document ENOMEM and ENOBUFS in tcp(4) as being synonymous given that they are used interchangeably throughout the code. - Fix a few other nits also accidentally omitted from the original patch. Reported by: Harsh Jain on freebsd-net@ Tested by: tjh@ Differential Revision: https://reviews.freebsd.org/D15358
395 lines
12 KiB
C
395 lines
12 KiB
C
/*-
|
|
* SPDX-License-Identifier: BSD-2-Clause-FreeBSD
|
|
*
|
|
* Copyright (c) 1982, 1986, 1988, 1990, 1993, 1994, 1995
|
|
* The Regents of the University of California.
|
|
* Copyright (c) 2007-2008,2010,2014
|
|
* Swinburne University of Technology, Melbourne, Australia.
|
|
* Copyright (c) 2009-2010 Lawrence Stewart <lstewart@freebsd.org>
|
|
* Copyright (c) 2010 The FreeBSD Foundation
|
|
* All rights reserved.
|
|
*
|
|
* This software was developed at the Centre for Advanced Internet
|
|
* Architectures, Swinburne University of Technology, by Lawrence Stewart, James
|
|
* Healy and David Hayes, made possible in part by a grant from the Cisco
|
|
* University Research Program Fund at Community Foundation Silicon Valley.
|
|
*
|
|
* Portions of this software were developed at the Centre for Advanced
|
|
* Internet Architectures, Swinburne University of Technology, Melbourne,
|
|
* Australia by David Hayes under sponsorship from the FreeBSD Foundation.
|
|
*
|
|
* Redistribution and use in source and binary forms, with or without
|
|
* modification, are permitted provided that the following conditions
|
|
* are met:
|
|
* 1. Redistributions of source code must retain the above copyright
|
|
* notice, this list of conditions and the following disclaimer.
|
|
* 2. Redistributions in binary form must reproduce the above copyright
|
|
* notice, this list of conditions and the following disclaimer in the
|
|
* documentation and/or other materials provided with the distribution.
|
|
*
|
|
* THIS SOFTWARE IS PROVIDED BY THE AUTHOR AND CONTRIBUTORS ``AS IS'' AND
|
|
* ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
|
|
* IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
|
|
* ARE DISCLAIMED. IN NO EVENT SHALL THE AUTHOR OR CONTRIBUTORS BE LIABLE
|
|
* FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
|
|
* DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
|
|
* OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
|
|
* HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
|
|
* LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
|
|
* OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
|
|
* SUCH DAMAGE.
|
|
*/
|
|
|
|
/*
|
|
* This software was first released in 2007 by James Healy and Lawrence Stewart
|
|
* whilst working on the NewTCP research project at Swinburne University of
|
|
* Technology's Centre for Advanced Internet Architectures, Melbourne,
|
|
* Australia, which was made possible in part by a grant from the Cisco
|
|
* University Research Program Fund at Community Foundation Silicon Valley.
|
|
* More details are available at:
|
|
* http://caia.swin.edu.au/urp/newtcp/
|
|
*
|
|
* Dec 2014 garmitage@swin.edu.au
|
|
* Borrowed code fragments from cc_cdg.c to add modifiable beta
|
|
* via sysctls.
|
|
*
|
|
*/
|
|
|
|
#include <sys/cdefs.h>
|
|
__FBSDID("$FreeBSD$");
|
|
|
|
#include <sys/param.h>
|
|
#include <sys/kernel.h>
|
|
#include <sys/malloc.h>
|
|
#include <sys/module.h>
|
|
#include <sys/socket.h>
|
|
#include <sys/socketvar.h>
|
|
#include <sys/sysctl.h>
|
|
#include <sys/systm.h>
|
|
|
|
#include <net/vnet.h>
|
|
|
|
#include <netinet/tcp.h>
|
|
#include <netinet/tcp_seq.h>
|
|
#include <netinet/tcp_var.h>
|
|
#include <netinet/cc/cc.h>
|
|
#include <netinet/cc/cc_module.h>
|
|
#include <netinet/cc/cc_newreno.h>
|
|
|
|
static MALLOC_DEFINE(M_NEWRENO, "newreno data",
|
|
"newreno beta values");
|
|
|
|
#define CAST_PTR_INT(X) (*((int*)(X)))
|
|
|
|
static void newreno_cb_destroy(struct cc_var *ccv);
|
|
static void newreno_ack_received(struct cc_var *ccv, uint16_t type);
|
|
static void newreno_after_idle(struct cc_var *ccv);
|
|
static void newreno_cong_signal(struct cc_var *ccv, uint32_t type);
|
|
static void newreno_post_recovery(struct cc_var *ccv);
|
|
static int newreno_ctl_output(struct cc_var *ccv, struct sockopt *sopt, void *buf);
|
|
|
|
static VNET_DEFINE(uint32_t, newreno_beta) = 50;
|
|
static VNET_DEFINE(uint32_t, newreno_beta_ecn) = 80;
|
|
#define V_newreno_beta VNET(newreno_beta)
|
|
#define V_newreno_beta_ecn VNET(newreno_beta_ecn)
|
|
|
|
struct cc_algo newreno_cc_algo = {
|
|
.name = "newreno",
|
|
.cb_destroy = newreno_cb_destroy,
|
|
.ack_received = newreno_ack_received,
|
|
.after_idle = newreno_after_idle,
|
|
.cong_signal = newreno_cong_signal,
|
|
.post_recovery = newreno_post_recovery,
|
|
.ctl_output = newreno_ctl_output,
|
|
};
|
|
|
|
struct newreno {
|
|
uint32_t beta;
|
|
uint32_t beta_ecn;
|
|
};
|
|
|
|
static inline struct newreno *
|
|
newreno_malloc(struct cc_var *ccv)
|
|
{
|
|
struct newreno *nreno;
|
|
|
|
nreno = malloc(sizeof(struct newreno), M_NEWRENO, M_NOWAIT);
|
|
if (nreno != NULL) {
|
|
/* NB: nreno is not zeroed, so initialise all fields. */
|
|
nreno->beta = V_newreno_beta;
|
|
nreno->beta_ecn = V_newreno_beta_ecn;
|
|
ccv->cc_data = nreno;
|
|
}
|
|
|
|
return (nreno);
|
|
}
|
|
|
|
static void
|
|
newreno_cb_destroy(struct cc_var *ccv)
|
|
{
|
|
|
|
if (ccv->cc_data != NULL)
|
|
free(ccv->cc_data, M_NEWRENO);
|
|
}
|
|
|
|
static void
|
|
newreno_ack_received(struct cc_var *ccv, uint16_t type)
|
|
{
|
|
if (type == CC_ACK && !IN_RECOVERY(CCV(ccv, t_flags)) &&
|
|
(ccv->flags & CCF_CWND_LIMITED)) {
|
|
u_int cw = CCV(ccv, snd_cwnd);
|
|
u_int incr = CCV(ccv, t_maxseg);
|
|
|
|
/*
|
|
* Regular in-order ACK, open the congestion window.
|
|
* Method depends on which congestion control state we're
|
|
* in (slow start or cong avoid) and if ABC (RFC 3465) is
|
|
* enabled.
|
|
*
|
|
* slow start: cwnd <= ssthresh
|
|
* cong avoid: cwnd > ssthresh
|
|
*
|
|
* slow start and ABC (RFC 3465):
|
|
* Grow cwnd exponentially by the amount of data
|
|
* ACKed capping the max increment per ACK to
|
|
* (abc_l_var * maxseg) bytes.
|
|
*
|
|
* slow start without ABC (RFC 5681):
|
|
* Grow cwnd exponentially by maxseg per ACK.
|
|
*
|
|
* cong avoid and ABC (RFC 3465):
|
|
* Grow cwnd linearly by maxseg per RTT for each
|
|
* cwnd worth of ACKed data.
|
|
*
|
|
* cong avoid without ABC (RFC 5681):
|
|
* Grow cwnd linearly by approximately maxseg per RTT using
|
|
* maxseg^2 / cwnd per ACK as the increment.
|
|
* If cwnd > maxseg^2, fix the cwnd increment at 1 byte to
|
|
* avoid capping cwnd.
|
|
*/
|
|
if (cw > CCV(ccv, snd_ssthresh)) {
|
|
if (V_tcp_do_rfc3465) {
|
|
if (ccv->flags & CCF_ABC_SENTAWND)
|
|
ccv->flags &= ~CCF_ABC_SENTAWND;
|
|
else
|
|
incr = 0;
|
|
} else
|
|
incr = max((incr * incr / cw), 1);
|
|
} else if (V_tcp_do_rfc3465) {
|
|
/*
|
|
* In slow-start with ABC enabled and no RTO in sight?
|
|
* (Must not use abc_l_var > 1 if slow starting after
|
|
* an RTO. On RTO, snd_nxt = snd_una, so the
|
|
* snd_nxt == snd_max check is sufficient to
|
|
* handle this).
|
|
*
|
|
* XXXLAS: Find a way to signal SS after RTO that
|
|
* doesn't rely on tcpcb vars.
|
|
*/
|
|
if (CCV(ccv, snd_nxt) == CCV(ccv, snd_max))
|
|
incr = min(ccv->bytes_this_ack,
|
|
ccv->nsegs * V_tcp_abc_l_var *
|
|
CCV(ccv, t_maxseg));
|
|
else
|
|
incr = min(ccv->bytes_this_ack, CCV(ccv, t_maxseg));
|
|
}
|
|
/* ABC is on by default, so incr equals 0 frequently. */
|
|
if (incr > 0)
|
|
CCV(ccv, snd_cwnd) = min(cw + incr,
|
|
TCP_MAXWIN << CCV(ccv, snd_scale));
|
|
}
|
|
}
|
|
|
|
static void
|
|
newreno_after_idle(struct cc_var *ccv)
|
|
{
|
|
int rw;
|
|
|
|
/*
|
|
* If we've been idle for more than one retransmit timeout the old
|
|
* congestion window is no longer current and we have to reduce it to
|
|
* the restart window before we can transmit again.
|
|
*
|
|
* The restart window is the initial window or the last CWND, whichever
|
|
* is smaller.
|
|
*
|
|
* This is done to prevent us from flooding the path with a full CWND at
|
|
* wirespeed, overloading router and switch buffers along the way.
|
|
*
|
|
* See RFC5681 Section 4.1. "Restarting Idle Connections".
|
|
*/
|
|
if (V_tcp_do_rfc3390)
|
|
rw = min(4 * CCV(ccv, t_maxseg),
|
|
max(2 * CCV(ccv, t_maxseg), 4380));
|
|
else
|
|
rw = CCV(ccv, t_maxseg) * 2;
|
|
|
|
CCV(ccv, snd_cwnd) = min(rw, CCV(ccv, snd_cwnd));
|
|
}
|
|
|
|
/*
|
|
* Perform any necessary tasks before we enter congestion recovery.
|
|
*/
|
|
static void
|
|
newreno_cong_signal(struct cc_var *ccv, uint32_t type)
|
|
{
|
|
struct newreno *nreno;
|
|
uint32_t beta, beta_ecn, cwin, factor;
|
|
u_int mss;
|
|
|
|
cwin = CCV(ccv, snd_cwnd);
|
|
mss = CCV(ccv, t_maxseg);
|
|
nreno = ccv->cc_data;
|
|
beta = (nreno == NULL) ? V_newreno_beta : nreno->beta;
|
|
beta_ecn = (nreno == NULL) ? V_newreno_beta_ecn : nreno->beta_ecn;
|
|
if (V_cc_do_abe && type == CC_ECN)
|
|
factor = beta_ecn;
|
|
else
|
|
factor = beta;
|
|
|
|
/* Catch algos which mistakenly leak private signal types. */
|
|
KASSERT((type & CC_SIGPRIVMASK) == 0,
|
|
("%s: congestion signal type 0x%08x is private\n", __func__, type));
|
|
|
|
cwin = max(((uint64_t)cwin * (uint64_t)factor) / (100ULL * (uint64_t)mss),
|
|
2) * mss;
|
|
|
|
switch (type) {
|
|
case CC_NDUPACK:
|
|
if (!IN_FASTRECOVERY(CCV(ccv, t_flags))) {
|
|
if (IN_CONGRECOVERY(CCV(ccv, t_flags) &&
|
|
V_cc_do_abe && V_cc_abe_frlossreduce)) {
|
|
CCV(ccv, snd_ssthresh) =
|
|
((uint64_t)CCV(ccv, snd_ssthresh) *
|
|
(uint64_t)beta) /
|
|
(100ULL * (uint64_t)beta_ecn);
|
|
}
|
|
if (!IN_CONGRECOVERY(CCV(ccv, t_flags)))
|
|
CCV(ccv, snd_ssthresh) = cwin;
|
|
ENTER_RECOVERY(CCV(ccv, t_flags));
|
|
}
|
|
break;
|
|
case CC_ECN:
|
|
if (!IN_CONGRECOVERY(CCV(ccv, t_flags))) {
|
|
CCV(ccv, snd_ssthresh) = cwin;
|
|
CCV(ccv, snd_cwnd) = cwin;
|
|
ENTER_CONGRECOVERY(CCV(ccv, t_flags));
|
|
}
|
|
break;
|
|
}
|
|
}
|
|
|
|
/*
|
|
* Perform any necessary tasks before we exit congestion recovery.
|
|
*/
|
|
static void
|
|
newreno_post_recovery(struct cc_var *ccv)
|
|
{
|
|
int pipe;
|
|
|
|
if (IN_FASTRECOVERY(CCV(ccv, t_flags))) {
|
|
/*
|
|
* Fast recovery will conclude after returning from this
|
|
* function. Window inflation should have left us with
|
|
* approximately snd_ssthresh outstanding data. But in case we
|
|
* would be inclined to send a burst, better to do it via the
|
|
* slow start mechanism.
|
|
*
|
|
* XXXLAS: Find a way to do this without needing curack
|
|
*/
|
|
if (V_tcp_do_rfc6675_pipe)
|
|
pipe = tcp_compute_pipe(ccv->ccvc.tcp);
|
|
else
|
|
pipe = CCV(ccv, snd_max) - ccv->curack;
|
|
|
|
if (pipe < CCV(ccv, snd_ssthresh))
|
|
CCV(ccv, snd_cwnd) = pipe + CCV(ccv, t_maxseg);
|
|
else
|
|
CCV(ccv, snd_cwnd) = CCV(ccv, snd_ssthresh);
|
|
}
|
|
}
|
|
|
|
static int
|
|
newreno_ctl_output(struct cc_var *ccv, struct sockopt *sopt, void *buf)
|
|
{
|
|
struct newreno *nreno;
|
|
struct cc_newreno_opts *opt;
|
|
|
|
if (sopt->sopt_valsize != sizeof(struct cc_newreno_opts))
|
|
return (EMSGSIZE);
|
|
|
|
nreno = ccv->cc_data;
|
|
opt = buf;
|
|
|
|
switch (sopt->sopt_dir) {
|
|
case SOPT_SET:
|
|
/* We cannot set without cc_data memory. */
|
|
if (nreno == NULL) {
|
|
nreno = newreno_malloc(ccv);
|
|
if (nreno == NULL)
|
|
return (ENOMEM);
|
|
}
|
|
switch (opt->name) {
|
|
case CC_NEWRENO_BETA:
|
|
nreno->beta = opt->val;
|
|
break;
|
|
case CC_NEWRENO_BETA_ECN:
|
|
if (!V_cc_do_abe)
|
|
return (EACCES);
|
|
nreno->beta_ecn = opt->val;
|
|
break;
|
|
default:
|
|
return (ENOPROTOOPT);
|
|
}
|
|
break;
|
|
case SOPT_GET:
|
|
switch (opt->name) {
|
|
case CC_NEWRENO_BETA:
|
|
opt->val = (nreno == NULL) ?
|
|
V_newreno_beta : nreno->beta;
|
|
break;
|
|
case CC_NEWRENO_BETA_ECN:
|
|
opt->val = (nreno == NULL) ?
|
|
V_newreno_beta_ecn : nreno->beta_ecn;
|
|
break;
|
|
default:
|
|
return (ENOPROTOOPT);
|
|
}
|
|
break;
|
|
default:
|
|
return (EINVAL);
|
|
}
|
|
|
|
return (0);
|
|
}
|
|
|
|
static int
|
|
newreno_beta_handler(SYSCTL_HANDLER_ARGS)
|
|
{
|
|
|
|
if (req->newptr != NULL ) {
|
|
if (arg1 == &VNET_NAME(newreno_beta_ecn) && !V_cc_do_abe)
|
|
return (EACCES);
|
|
if (CAST_PTR_INT(req->newptr) <= 0 || CAST_PTR_INT(req->newptr) > 100)
|
|
return (EINVAL);
|
|
}
|
|
|
|
return (sysctl_handle_int(oidp, arg1, arg2, req));
|
|
}
|
|
|
|
SYSCTL_DECL(_net_inet_tcp_cc_newreno);
|
|
SYSCTL_NODE(_net_inet_tcp_cc, OID_AUTO, newreno, CTLFLAG_RW, NULL,
|
|
"New Reno related settings");
|
|
|
|
SYSCTL_PROC(_net_inet_tcp_cc_newreno, OID_AUTO, beta,
|
|
CTLFLAG_VNET | CTLTYPE_UINT | CTLFLAG_RW,
|
|
&VNET_NAME(newreno_beta), 3, &newreno_beta_handler, "IU",
|
|
"New Reno beta, specified as number between 1 and 100");
|
|
|
|
SYSCTL_PROC(_net_inet_tcp_cc_newreno, OID_AUTO, beta_ecn,
|
|
CTLFLAG_VNET | CTLTYPE_UINT | CTLFLAG_RW,
|
|
&VNET_NAME(newreno_beta_ecn), 3, &newreno_beta_handler, "IU",
|
|
"New Reno beta ecn, specified as number between 1 and 100");
|
|
|
|
DECLARE_CC_MODULE(newreno, &newreno_cc_algo);
|