freebsd-nq/sys/netinet/cc.h

165 lines
6.1 KiB
C
Raw Normal View History

This commit marks the first formal contribution of the "Five New TCP Congestion Control Algorithms for FreeBSD" FreeBSD Foundation funded project. More details about the project are available at: http://caia.swin.edu.au/freebsd/5cc/ - Add a KPI and supporting infrastructure to allow modular congestion control algorithms to be used in the net stack. Algorithms can maintain per-connection state if required, and connections maintain their own algorithm pointer, which allows different connections to concurrently use different algorithms. The TCP_CONGESTION socket option can be used with getsockopt()/setsockopt() to programmatically query or change the congestion control algorithm respectively from within an application at runtime. - Integrate the framework with the TCP stack in as least intrusive a manner as possible. Care was also taken to develop the framework in a way that should allow integration with other congestion aware transport protocols (e.g. SCTP) in the future. The hope is that we will one day be able to share a single set of congestion control algorithm modules between all congestion aware transport protocols. - Introduce a new congestion recovery (TF_CONGRECOVERY) state into the TCP stack and use it to decouple the meaning of recovery from a congestion event and recovery from packet loss (TF_FASTRECOVERY) a la RFC2581. ECN and delay based congestion control protocols don't generally need to recover from packet loss and need a different way to note a congestion recovery episode within the stack. - Remove the net.inet.tcp.newreno sysctl, which simplifies some portions of code and ensures the stack always uses the appropriate mechanisms for recovering from packet loss during a congestion recovery episode. - Extract the NewReno congestion control algorithm from the TCP stack and massage it into module form. NewReno is always built into the kernel and will remain the default algorithm for the forseeable future. Implementations of additional different algorithms will become available in the near future. - Bump __FreeBSD_version to 900025 and note in UPDATING that rebuilding code that relies on the size of "struct tcpcb" is required. Many thanks go to the Cisco University Research Program Fund at Community Foundation Silicon Valley and the FreeBSD Foundation. Their support of our work at the Centre for Advanced Internet Architectures, Swinburne University of Technology is greatly appreciated. In collaboration with: David Hayes <dahayes at swin edu au> and Grenville Armitage <garmitage at swin edu au> Sponsored by: Cisco URP, FreeBSD Foundation Reviewed by: rpaulo Tested by: David Hayes (and many others over the years) MFC after: 3 months
2010-11-12 06:41:55 +00:00
/*-
* Copyright (c) 2007-2008
* 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, by Lawrence Stewart and James Healy,
* 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.
*
* $FreeBSD$
*/
/*
* This software was first released in 2007 by James Healy and Lawrence Stewart
* whilst working on the NewTCP research project at Swinburne University'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/
*/
#ifndef _NETINET_CC_H_
#define _NETINET_CC_H_
/* XXX: TCP_CA_NAME_MAX define lives in tcp.h for compat reasons. */
#include <netinet/tcp.h>
/* Global CC vars. */
extern STAILQ_HEAD(cc_head, cc_algo) cc_list;
extern const int tcprexmtthresh;
extern struct cc_algo newreno_cc_algo;
/* Per-netstack bits. */
VNET_DECLARE(struct cc_algo *, default_cc_ptr);
#define V_default_cc_ptr VNET(default_cc_ptr)
This commit marks the first formal contribution of the "Five New TCP Congestion Control Algorithms for FreeBSD" FreeBSD Foundation funded project. More details about the project are available at: http://caia.swin.edu.au/freebsd/5cc/ - Add a KPI and supporting infrastructure to allow modular congestion control algorithms to be used in the net stack. Algorithms can maintain per-connection state if required, and connections maintain their own algorithm pointer, which allows different connections to concurrently use different algorithms. The TCP_CONGESTION socket option can be used with getsockopt()/setsockopt() to programmatically query or change the congestion control algorithm respectively from within an application at runtime. - Integrate the framework with the TCP stack in as least intrusive a manner as possible. Care was also taken to develop the framework in a way that should allow integration with other congestion aware transport protocols (e.g. SCTP) in the future. The hope is that we will one day be able to share a single set of congestion control algorithm modules between all congestion aware transport protocols. - Introduce a new congestion recovery (TF_CONGRECOVERY) state into the TCP stack and use it to decouple the meaning of recovery from a congestion event and recovery from packet loss (TF_FASTRECOVERY) a la RFC2581. ECN and delay based congestion control protocols don't generally need to recover from packet loss and need a different way to note a congestion recovery episode within the stack. - Remove the net.inet.tcp.newreno sysctl, which simplifies some portions of code and ensures the stack always uses the appropriate mechanisms for recovering from packet loss during a congestion recovery episode. - Extract the NewReno congestion control algorithm from the TCP stack and massage it into module form. NewReno is always built into the kernel and will remain the default algorithm for the forseeable future. Implementations of additional different algorithms will become available in the near future. - Bump __FreeBSD_version to 900025 and note in UPDATING that rebuilding code that relies on the size of "struct tcpcb" is required. Many thanks go to the Cisco University Research Program Fund at Community Foundation Silicon Valley and the FreeBSD Foundation. Their support of our work at the Centre for Advanced Internet Architectures, Swinburne University of Technology is greatly appreciated. In collaboration with: David Hayes <dahayes at swin edu au> and Grenville Armitage <garmitage at swin edu au> Sponsored by: Cisco URP, FreeBSD Foundation Reviewed by: rpaulo Tested by: David Hayes (and many others over the years) MFC after: 3 months
2010-11-12 06:41:55 +00:00
/* Define the new net.inet.tcp.cc sysctl tree. */
SYSCTL_DECL(_net_inet_tcp_cc);
/* CC housekeeping functions. */
int cc_register_algo(struct cc_algo *add_cc);
int cc_deregister_algo(struct cc_algo *remove_cc);
/*
* Wrapper around transport structs that contain same-named congestion
* control variables. Allows algos to be shared amongst multiple CC aware
* transprots.
*/
struct cc_var {
void *cc_data; /* Per-connection private CC algorithm data. */
int bytes_this_ack; /* # bytes acked by the current ACK. */
tcp_seq curack; /* Most recent ACK. */
uint32_t flags; /* Flags for cc_var (see below) */
int type; /* Indicates which ptr is valid in ccvc. */
union ccv_container {
struct tcpcb *tcp;
struct sctp_nets *sctp;
} ccvc;
};
/* cc_var flags. */
#define CCF_ABC_SENTAWND 0x0001 /* ABC counted cwnd worth of bytes? */
#define CCF_CWND_LIMITED 0x0002 /* Are we currently cwnd limited? */
/* ACK types passed to the ack_received() hook. */
#define CC_ACK 0x0001 /* Regular in sequence ACK. */
#define CC_DUPACK 0x0002 /* Duplicate ACK. */
#define CC_PARTIALACK 0x0004 /* Not yet. */
#define CC_SACK 0x0008 /* Not yet. */
/*
* Congestion signal types passed to the cong_signal() hook. The highest order 8
* bits (0x01000000 - 0x80000000) are reserved for CC algos to declare their own
* congestion signal types.
*/
#define CC_ECN 0x000001/* ECN marked packet received. */
#define CC_RTO 0x000002/* RTO fired. */
#define CC_RTO_ERR 0x000004/* RTO fired in error. */
#define CC_NDUPACK 0x000008/* Threshold of dupack's reached. */
/*
* Structure to hold data and function pointers that together represent a
* congestion control algorithm.
*/
struct cc_algo {
char name[TCP_CA_NAME_MAX];
/* Init global module state on kldload. */
int (*mod_init)(void);
/* Cleanup global module state on kldunload. */
int (*mod_destroy)(void);
/* Init CC state for a new control block. */
int (*cb_init)(struct cc_var *ccv);
/* Cleanup CC state for a terminating control block. */
void (*cb_destroy)(struct cc_var *ccv);
/* Init variables for a newly established connection. */
void (*conn_init)(struct cc_var *ccv);
/* Called on receipt of an ack. */
void (*ack_received)(struct cc_var *ccv, uint16_t type);
/* Called on detection of a congestion signal. */
void (*cong_signal)(struct cc_var *ccv, uint32_t type);
/* Called after exiting congestion recovery. */
void (*post_recovery)(struct cc_var *ccv);
/* Called when data transfer resumes after an idle period. */
void (*after_idle)(struct cc_var *ccv);
STAILQ_ENTRY (cc_algo) entries;
};
/* Macro to obtain the CC algo's struct ptr. */
#define CC_ALGO(tp) ((tp)->cc_algo)
/* Macro to obtain the CC algo's data ptr. */
#define CC_DATA(tp) ((tp)->ccv->cc_data)
/* Macro to obtain the system default CC algo's struct ptr. */
#define CC_DEFAULT() V_default_cc_ptr
This commit marks the first formal contribution of the "Five New TCP Congestion Control Algorithms for FreeBSD" FreeBSD Foundation funded project. More details about the project are available at: http://caia.swin.edu.au/freebsd/5cc/ - Add a KPI and supporting infrastructure to allow modular congestion control algorithms to be used in the net stack. Algorithms can maintain per-connection state if required, and connections maintain their own algorithm pointer, which allows different connections to concurrently use different algorithms. The TCP_CONGESTION socket option can be used with getsockopt()/setsockopt() to programmatically query or change the congestion control algorithm respectively from within an application at runtime. - Integrate the framework with the TCP stack in as least intrusive a manner as possible. Care was also taken to develop the framework in a way that should allow integration with other congestion aware transport protocols (e.g. SCTP) in the future. The hope is that we will one day be able to share a single set of congestion control algorithm modules between all congestion aware transport protocols. - Introduce a new congestion recovery (TF_CONGRECOVERY) state into the TCP stack and use it to decouple the meaning of recovery from a congestion event and recovery from packet loss (TF_FASTRECOVERY) a la RFC2581. ECN and delay based congestion control protocols don't generally need to recover from packet loss and need a different way to note a congestion recovery episode within the stack. - Remove the net.inet.tcp.newreno sysctl, which simplifies some portions of code and ensures the stack always uses the appropriate mechanisms for recovering from packet loss during a congestion recovery episode. - Extract the NewReno congestion control algorithm from the TCP stack and massage it into module form. NewReno is always built into the kernel and will remain the default algorithm for the forseeable future. Implementations of additional different algorithms will become available in the near future. - Bump __FreeBSD_version to 900025 and note in UPDATING that rebuilding code that relies on the size of "struct tcpcb" is required. Many thanks go to the Cisco University Research Program Fund at Community Foundation Silicon Valley and the FreeBSD Foundation. Their support of our work at the Centre for Advanced Internet Architectures, Swinburne University of Technology is greatly appreciated. In collaboration with: David Hayes <dahayes at swin edu au> and Grenville Armitage <garmitage at swin edu au> Sponsored by: Cisco URP, FreeBSD Foundation Reviewed by: rpaulo Tested by: David Hayes (and many others over the years) MFC after: 3 months
2010-11-12 06:41:55 +00:00
extern struct rwlock cc_list_lock;
#define CC_LIST_LOCK_INIT() rw_init(&cc_list_lock, "cc_list")
#define CC_LIST_LOCK_DESTROY() rw_destroy(&cc_list_lock)
#define CC_LIST_RLOCK() rw_rlock(&cc_list_lock)
#define CC_LIST_RUNLOCK() rw_runlock(&cc_list_lock)
#define CC_LIST_WLOCK() rw_wlock(&cc_list_lock)
#define CC_LIST_WUNLOCK() rw_wunlock(&cc_list_lock)
#define CC_LIST_LOCK_ASSERT() rw_assert(&cc_list_lock, RA_LOCKED)
This commit marks the first formal contribution of the "Five New TCP Congestion Control Algorithms for FreeBSD" FreeBSD Foundation funded project. More details about the project are available at: http://caia.swin.edu.au/freebsd/5cc/ - Add a KPI and supporting infrastructure to allow modular congestion control algorithms to be used in the net stack. Algorithms can maintain per-connection state if required, and connections maintain their own algorithm pointer, which allows different connections to concurrently use different algorithms. The TCP_CONGESTION socket option can be used with getsockopt()/setsockopt() to programmatically query or change the congestion control algorithm respectively from within an application at runtime. - Integrate the framework with the TCP stack in as least intrusive a manner as possible. Care was also taken to develop the framework in a way that should allow integration with other congestion aware transport protocols (e.g. SCTP) in the future. The hope is that we will one day be able to share a single set of congestion control algorithm modules between all congestion aware transport protocols. - Introduce a new congestion recovery (TF_CONGRECOVERY) state into the TCP stack and use it to decouple the meaning of recovery from a congestion event and recovery from packet loss (TF_FASTRECOVERY) a la RFC2581. ECN and delay based congestion control protocols don't generally need to recover from packet loss and need a different way to note a congestion recovery episode within the stack. - Remove the net.inet.tcp.newreno sysctl, which simplifies some portions of code and ensures the stack always uses the appropriate mechanisms for recovering from packet loss during a congestion recovery episode. - Extract the NewReno congestion control algorithm from the TCP stack and massage it into module form. NewReno is always built into the kernel and will remain the default algorithm for the forseeable future. Implementations of additional different algorithms will become available in the near future. - Bump __FreeBSD_version to 900025 and note in UPDATING that rebuilding code that relies on the size of "struct tcpcb" is required. Many thanks go to the Cisco University Research Program Fund at Community Foundation Silicon Valley and the FreeBSD Foundation. Their support of our work at the Centre for Advanced Internet Architectures, Swinburne University of Technology is greatly appreciated. In collaboration with: David Hayes <dahayes at swin edu au> and Grenville Armitage <garmitage at swin edu au> Sponsored by: Cisco URP, FreeBSD Foundation Reviewed by: rpaulo Tested by: David Hayes (and many others over the years) MFC after: 3 months
2010-11-12 06:41:55 +00:00
#endif /* _NETINET_CC_H_ */