b8d60729de
NOTE: HEADS UP read the note below if your kernel config is not including GENERIC!! This patch does a bit of cleanup on TCP congestion control modules. There were some rather interesting surprises that one could get i.e. where you use a socket option to change from one CC (say cc_cubic) to another CC (say cc_vegas) and you could in theory get a memory failure and end up on cc_newreno. This is not what one would expect. The new code fixes this by requiring a cc_data_sz() function so we can malloc with M_WAITOK and pass in to the init function preallocated memory. The CC init is expected in this case *not* to fail but if it does and a module does break the "no fail with memory given" contract we do fall back to the CC that was in place at the time. This also fixes up a set of common newreno utilities that can be shared amongst other CC modules instead of the other CC modules reaching into newreno and executing what they think is a "common and understood" function. Lets put these functions in cc.c and that way we have a common place that is easily findable by future developers or bug fixers. This also allows newreno to evolve and grow support for its features i.e. ABE and HYSTART++ without having to dance through hoops for other CC modules, instead both newreno and the other modules just call into the common functions if they desire that behavior or roll there own if that makes more sense. Note: This commit changes the kernel configuration!! If you are not using GENERIC in some form you must add a CC module option (one of CC_NEWRENO, CC_VEGAS, CC_CUBIC, CC_CDG, CC_CHD, CC_DCTCP, CC_HTCP, CC_HD). You can have more than one defined as well if you desire. Note that if you create a kernel configuration that does not define a congestion control module and includes INET or INET6 the kernel compile will break. Also you need to define a default, generic adds 'options CC_DEFAULT=\"newreno\" but you can specify any string that represents the name of the CC module (same names that show up in the CC module list under net.inet.tcp.cc). If you fail to add the options CC_DEFAULT in your kernel configuration the kernel build will also break. Reviewed by: Michael Tuexen Sponsored by: Netflix Inc. RELNOTES:YES Differential Revision: https://reviews.freebsd.org/D32693
229 lines
8.5 KiB
C
229 lines
8.5 KiB
C
/*-
|
|
* 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 of Technology, 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 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/
|
|
*/
|
|
|
|
#ifndef _NETINET_CC_CC_H_
|
|
#define _NETINET_CC_CC_H_
|
|
|
|
#ifdef _KERNEL
|
|
|
|
MALLOC_DECLARE(M_CC_MEM);
|
|
|
|
/* Global CC vars. */
|
|
extern STAILQ_HEAD(cc_head, cc_algo) cc_list;
|
|
extern const int tcprexmtthresh;
|
|
|
|
/* Per-netstack bits. */
|
|
VNET_DECLARE(struct cc_algo *, default_cc_ptr);
|
|
#define V_default_cc_ptr VNET(default_cc_ptr)
|
|
|
|
VNET_DECLARE(int, cc_do_abe);
|
|
#define V_cc_do_abe VNET(cc_do_abe)
|
|
|
|
VNET_DECLARE(int, cc_abe_frlossreduce);
|
|
#define V_cc_abe_frlossreduce VNET(cc_abe_frlossreduce)
|
|
|
|
/* 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;
|
|
uint16_t nsegs; /* # segments coalesced into current chain. */
|
|
uint8_t labc; /* Dont use system abc use passed in */
|
|
};
|
|
|
|
/* cc_var flags. */
|
|
#define CCF_ABC_SENTAWND 0x0001 /* ABC counted cwnd worth of bytes? */
|
|
#define CCF_CWND_LIMITED 0x0002 /* Are we currently cwnd limited? */
|
|
#define CCF_USE_LOCAL_ABC 0x0004 /* Dont use the system l_abc val */
|
|
#define CCF_ACKNOW 0x0008 /* Will this ack be sent now? */
|
|
#define CCF_IPHDR_CE 0x0010 /* Does this packet set CE bit? */
|
|
#define CCF_TCPHDR_CWR 0x0020 /* Does this packet set CWR bit? */
|
|
#define CCF_MAX_CWND 0x0040 /* Have we reached maximum cwnd? */
|
|
#define CCF_CHG_MAX_CWND 0x0080 /* Cubic max_cwnd changed, for K */
|
|
#define CCF_USR_IWND 0x0100 /* User specified initial window */
|
|
#define CCF_USR_IWND_INIT_NSEG 0x0200 /* Convert segs to bytes on conn init */
|
|
|
|
/* 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. */
|
|
#endif /* _KERNEL */
|
|
|
|
/*
|
|
* 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 0x00000001 /* ECN marked packet received. */
|
|
#define CC_RTO 0x00000002 /* RTO fired. */
|
|
#define CC_RTO_ERR 0x00000004 /* RTO fired in error. */
|
|
#define CC_NDUPACK 0x00000008 /* Threshold of dupack's reached. */
|
|
|
|
#define CC_SIGPRIVMASK 0xFF000000 /* Mask to check if sig is private. */
|
|
|
|
#ifdef _KERNEL
|
|
/*
|
|
* 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);
|
|
|
|
/* Return the size of the void pointer the CC needs for state */
|
|
size_t (*cc_data_sz)(void);
|
|
|
|
/*
|
|
* Init CC state for a new control block. The CC
|
|
* module may be passed a NULL ptr indicating that
|
|
* it must allocate the memory. If it is passed a
|
|
* non-null pointer it is pre-allocated memory by
|
|
* the caller and the cb_init is expected to use that memory.
|
|
* It is not expected to fail if memory is passed in and
|
|
* all currently defined modules do not.
|
|
*/
|
|
int (*cb_init)(struct cc_var *ccv, void *ptr);
|
|
|
|
/* 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);
|
|
|
|
/* Called for an additional ECN processing apart from RFC3168. */
|
|
void (*ecnpkt_handler)(struct cc_var *ccv);
|
|
|
|
/* Called when a new "round" begins, if the transport is tracking rounds. */
|
|
void (*newround)(struct cc_var *ccv, uint32_t round_cnt);
|
|
|
|
/*
|
|
* Called when a RTT sample is made (fas = flight at send, if you dont have it
|
|
* send the cwnd in).
|
|
*/
|
|
void (*rttsample)(struct cc_var *ccv, uint32_t usec_rtt, uint32_t rxtcnt, uint32_t fas);
|
|
|
|
/* Called for {get|set}sockopt() on a TCP socket with TCP_CCALGOOPT. */
|
|
int (*ctl_output)(struct cc_var *, struct sockopt *, void *);
|
|
|
|
STAILQ_ENTRY (cc_algo) entries;
|
|
uint8_t flags;
|
|
};
|
|
|
|
#define CC_MODULE_BEING_REMOVED 0x01 /* The module is being removed */
|
|
|
|
/* 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_ALGO() V_default_cc_ptr
|
|
|
|
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)
|
|
|
|
#define CC_ALGOOPT_LIMIT 2048
|
|
|
|
/*
|
|
* These routines give NewReno behavior to the caller
|
|
* they require no state and can be used by any other CC
|
|
* module that wishes to use NewReno type behaviour (along
|
|
* with anything else they may add on, pre or post call).
|
|
*/
|
|
void newreno_cc_post_recovery(struct cc_var *);
|
|
void newreno_cc_after_idle(struct cc_var *);
|
|
void newreno_cc_cong_signal(struct cc_var *, uint32_t );
|
|
void newreno_cc_ack_received(struct cc_var *, uint16_t);
|
|
|
|
#endif /* _KERNEL */
|
|
#endif /* _NETINET_CC_CC_H_ */
|