2005-06-23 23:19:55 +04:00
|
|
|
/*
|
|
|
|
* Plugable TCP congestion control support and newReno
|
|
|
|
* congestion control.
|
2012-08-22 14:11:26 +04:00
|
|
|
* Based on ideas from I/O scheduler support and Web100.
|
2005-06-23 23:19:55 +04:00
|
|
|
*
|
|
|
|
* Copyright (C) 2005 Stephen Hemminger <shemminger@osdl.org>
|
|
|
|
*/
|
|
|
|
|
2012-03-12 11:03:32 +04:00
|
|
|
#define pr_fmt(fmt) "TCP: " fmt
|
|
|
|
|
2005-06-23 23:19:55 +04:00
|
|
|
#include <linux/module.h>
|
|
|
|
#include <linux/mm.h>
|
|
|
|
#include <linux/types.h>
|
|
|
|
#include <linux/list.h>
|
include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h
percpu.h is included by sched.h and module.h and thus ends up being
included when building most .c files. percpu.h includes slab.h which
in turn includes gfp.h making everything defined by the two files
universally available and complicating inclusion dependencies.
percpu.h -> slab.h dependency is about to be removed. Prepare for
this change by updating users of gfp and slab facilities include those
headers directly instead of assuming availability. As this conversion
needs to touch large number of source files, the following script is
used as the basis of conversion.
http://userweb.kernel.org/~tj/misc/slabh-sweep.py
The script does the followings.
* Scan files for gfp and slab usages and update includes such that
only the necessary includes are there. ie. if only gfp is used,
gfp.h, if slab is used, slab.h.
* When the script inserts a new include, it looks at the include
blocks and try to put the new include such that its order conforms
to its surrounding. It's put in the include block which contains
core kernel includes, in the same order that the rest are ordered -
alphabetical, Christmas tree, rev-Xmas-tree or at the end if there
doesn't seem to be any matching order.
* If the script can't find a place to put a new include (mostly
because the file doesn't have fitting include block), it prints out
an error message indicating which .h file needs to be added to the
file.
The conversion was done in the following steps.
1. The initial automatic conversion of all .c files updated slightly
over 4000 files, deleting around 700 includes and adding ~480 gfp.h
and ~3000 slab.h inclusions. The script emitted errors for ~400
files.
2. Each error was manually checked. Some didn't need the inclusion,
some needed manual addition while adding it to implementation .h or
embedding .c file was more appropriate for others. This step added
inclusions to around 150 files.
3. The script was run again and the output was compared to the edits
from #2 to make sure no file was left behind.
4. Several build tests were done and a couple of problems were fixed.
e.g. lib/decompress_*.c used malloc/free() wrappers around slab
APIs requiring slab.h to be added manually.
5. The script was run on all .h files but without automatically
editing them as sprinkling gfp.h and slab.h inclusions around .h
files could easily lead to inclusion dependency hell. Most gfp.h
inclusion directives were ignored as stuff from gfp.h was usually
wildly available and often used in preprocessor macros. Each
slab.h inclusion directive was examined and added manually as
necessary.
6. percpu.h was updated not to include slab.h.
7. Build test were done on the following configurations and failures
were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my
distributed build env didn't work with gcov compiles) and a few
more options had to be turned off depending on archs to make things
build (like ipr on powerpc/64 which failed due to missing writeq).
* x86 and x86_64 UP and SMP allmodconfig and a custom test config.
* powerpc and powerpc64 SMP allmodconfig
* sparc and sparc64 SMP allmodconfig
* ia64 SMP allmodconfig
* s390 SMP allmodconfig
* alpha SMP allmodconfig
* um on x86_64 SMP allmodconfig
8. percpu.h modifications were reverted so that it could be applied as
a separate patch and serve as bisection point.
Given the fact that I had only a couple of failures from tests on step
6, I'm fairly confident about the coverage of this conversion patch.
If there is a breakage, it's likely to be something in one of the arch
headers which should be easily discoverable easily on most builds of
the specific arch.
Signed-off-by: Tejun Heo <tj@kernel.org>
Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
2010-03-24 11:04:11 +03:00
|
|
|
#include <linux/gfp.h>
|
2005-06-23 23:19:55 +04:00
|
|
|
#include <net/tcp.h>
|
|
|
|
|
|
|
|
static DEFINE_SPINLOCK(tcp_cong_list_lock);
|
|
|
|
static LIST_HEAD(tcp_cong_list);
|
|
|
|
|
|
|
|
/* Simple linear search, don't expect many entries! */
|
|
|
|
static struct tcp_congestion_ops *tcp_ca_find(const char *name)
|
|
|
|
{
|
|
|
|
struct tcp_congestion_ops *e;
|
|
|
|
|
2005-06-24 07:37:36 +04:00
|
|
|
list_for_each_entry_rcu(e, &tcp_cong_list, list) {
|
2005-06-23 23:19:55 +04:00
|
|
|
if (strcmp(e->name, name) == 0)
|
|
|
|
return e;
|
|
|
|
}
|
|
|
|
|
|
|
|
return NULL;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
2007-02-17 21:07:33 +03:00
|
|
|
* Attach new congestion control algorithm to the list
|
2005-06-23 23:19:55 +04:00
|
|
|
* of available options.
|
|
|
|
*/
|
|
|
|
int tcp_register_congestion_control(struct tcp_congestion_ops *ca)
|
|
|
|
{
|
|
|
|
int ret = 0;
|
|
|
|
|
|
|
|
/* all algorithms must implement ssthresh and cong_avoid ops */
|
2006-06-06 04:30:08 +04:00
|
|
|
if (!ca->ssthresh || !ca->cong_avoid) {
|
2012-03-12 11:03:32 +04:00
|
|
|
pr_err("%s does not implement required ops\n", ca->name);
|
2005-06-23 23:19:55 +04:00
|
|
|
return -EINVAL;
|
|
|
|
}
|
|
|
|
|
|
|
|
spin_lock(&tcp_cong_list_lock);
|
|
|
|
if (tcp_ca_find(ca->name)) {
|
2012-03-12 11:03:32 +04:00
|
|
|
pr_notice("%s already registered\n", ca->name);
|
2005-06-23 23:19:55 +04:00
|
|
|
ret = -EEXIST;
|
|
|
|
} else {
|
2006-09-25 07:11:58 +04:00
|
|
|
list_add_tail_rcu(&ca->list, &tcp_cong_list);
|
2012-03-12 11:03:32 +04:00
|
|
|
pr_info("%s registered\n", ca->name);
|
2005-06-23 23:19:55 +04:00
|
|
|
}
|
|
|
|
spin_unlock(&tcp_cong_list_lock);
|
|
|
|
|
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
EXPORT_SYMBOL_GPL(tcp_register_congestion_control);
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Remove congestion control algorithm, called from
|
|
|
|
* the module's remove function. Module ref counts are used
|
|
|
|
* to ensure that this can't be done till all sockets using
|
|
|
|
* that method are closed.
|
|
|
|
*/
|
|
|
|
void tcp_unregister_congestion_control(struct tcp_congestion_ops *ca)
|
|
|
|
{
|
|
|
|
spin_lock(&tcp_cong_list_lock);
|
|
|
|
list_del_rcu(&ca->list);
|
|
|
|
spin_unlock(&tcp_cong_list_lock);
|
|
|
|
}
|
|
|
|
EXPORT_SYMBOL_GPL(tcp_unregister_congestion_control);
|
|
|
|
|
|
|
|
/* Assign choice of congestion control. */
|
2005-08-10 11:03:31 +04:00
|
|
|
void tcp_init_congestion_control(struct sock *sk)
|
2005-06-23 23:19:55 +04:00
|
|
|
{
|
2005-08-10 11:03:31 +04:00
|
|
|
struct inet_connection_sock *icsk = inet_csk(sk);
|
2005-06-23 23:19:55 +04:00
|
|
|
struct tcp_congestion_ops *ca;
|
|
|
|
|
2007-04-24 09:32:11 +04:00
|
|
|
/* if no choice made yet assign the current value set as default */
|
|
|
|
if (icsk->icsk_ca_ops == &tcp_init_congestion_ops) {
|
|
|
|
rcu_read_lock();
|
|
|
|
list_for_each_entry_rcu(ca, &tcp_cong_list, list) {
|
|
|
|
if (try_module_get(ca->owner)) {
|
|
|
|
icsk->icsk_ca_ops = ca;
|
|
|
|
break;
|
|
|
|
}
|
2005-06-24 07:37:36 +04:00
|
|
|
|
2007-04-24 09:32:11 +04:00
|
|
|
/* fallback to next available */
|
2005-06-23 23:19:55 +04:00
|
|
|
}
|
2007-04-24 09:32:11 +04:00
|
|
|
rcu_read_unlock();
|
2005-06-23 23:19:55 +04:00
|
|
|
}
|
|
|
|
|
2005-08-10 11:03:31 +04:00
|
|
|
if (icsk->icsk_ca_ops->init)
|
|
|
|
icsk->icsk_ca_ops->init(sk);
|
2005-06-23 23:19:55 +04:00
|
|
|
}
|
|
|
|
|
|
|
|
/* Manage refcounts on socket close. */
|
2005-08-10 11:03:31 +04:00
|
|
|
void tcp_cleanup_congestion_control(struct sock *sk)
|
2005-06-23 23:19:55 +04:00
|
|
|
{
|
2005-08-10 11:03:31 +04:00
|
|
|
struct inet_connection_sock *icsk = inet_csk(sk);
|
|
|
|
|
|
|
|
if (icsk->icsk_ca_ops->release)
|
|
|
|
icsk->icsk_ca_ops->release(sk);
|
|
|
|
module_put(icsk->icsk_ca_ops->owner);
|
2005-06-23 23:19:55 +04:00
|
|
|
}
|
|
|
|
|
|
|
|
/* Used by sysctl to change default congestion control */
|
|
|
|
int tcp_set_default_congestion_control(const char *name)
|
|
|
|
{
|
|
|
|
struct tcp_congestion_ops *ca;
|
|
|
|
int ret = -ENOENT;
|
|
|
|
|
|
|
|
spin_lock(&tcp_cong_list_lock);
|
|
|
|
ca = tcp_ca_find(name);
|
2008-10-17 02:24:51 +04:00
|
|
|
#ifdef CONFIG_MODULES
|
2009-08-13 17:44:51 +04:00
|
|
|
if (!ca && capable(CAP_NET_ADMIN)) {
|
2005-06-23 23:19:55 +04:00
|
|
|
spin_unlock(&tcp_cong_list_lock);
|
|
|
|
|
|
|
|
request_module("tcp_%s", name);
|
|
|
|
spin_lock(&tcp_cong_list_lock);
|
|
|
|
ca = tcp_ca_find(name);
|
|
|
|
}
|
|
|
|
#endif
|
|
|
|
|
|
|
|
if (ca) {
|
2007-04-24 09:26:16 +04:00
|
|
|
ca->flags |= TCP_CONG_NON_RESTRICTED; /* default is always allowed */
|
2005-06-23 23:19:55 +04:00
|
|
|
list_move(&ca->list, &tcp_cong_list);
|
|
|
|
ret = 0;
|
|
|
|
}
|
|
|
|
spin_unlock(&tcp_cong_list_lock);
|
|
|
|
|
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
2006-11-01 04:31:33 +03:00
|
|
|
/* Set default value from kernel configuration at bootup */
|
|
|
|
static int __init tcp_congestion_default(void)
|
|
|
|
{
|
|
|
|
return tcp_set_default_congestion_control(CONFIG_DEFAULT_TCP_CONG);
|
|
|
|
}
|
|
|
|
late_initcall(tcp_congestion_default);
|
|
|
|
|
|
|
|
|
2006-11-10 03:32:06 +03:00
|
|
|
/* Build string with list of available congestion control values */
|
|
|
|
void tcp_get_available_congestion_control(char *buf, size_t maxlen)
|
|
|
|
{
|
|
|
|
struct tcp_congestion_ops *ca;
|
|
|
|
size_t offs = 0;
|
|
|
|
|
|
|
|
rcu_read_lock();
|
|
|
|
list_for_each_entry_rcu(ca, &tcp_cong_list, list) {
|
|
|
|
offs += snprintf(buf + offs, maxlen - offs,
|
|
|
|
"%s%s",
|
|
|
|
offs == 0 ? "" : " ", ca->name);
|
|
|
|
|
|
|
|
}
|
|
|
|
rcu_read_unlock();
|
|
|
|
}
|
|
|
|
|
2005-06-23 23:19:55 +04:00
|
|
|
/* Get current default congestion control */
|
|
|
|
void tcp_get_default_congestion_control(char *name)
|
|
|
|
{
|
|
|
|
struct tcp_congestion_ops *ca;
|
|
|
|
/* We will always have reno... */
|
|
|
|
BUG_ON(list_empty(&tcp_cong_list));
|
|
|
|
|
|
|
|
rcu_read_lock();
|
|
|
|
ca = list_entry(tcp_cong_list.next, struct tcp_congestion_ops, list);
|
|
|
|
strncpy(name, ca->name, TCP_CA_NAME_MAX);
|
|
|
|
rcu_read_unlock();
|
|
|
|
}
|
|
|
|
|
2006-11-10 03:35:15 +03:00
|
|
|
/* Built list of non-restricted congestion control values */
|
|
|
|
void tcp_get_allowed_congestion_control(char *buf, size_t maxlen)
|
|
|
|
{
|
|
|
|
struct tcp_congestion_ops *ca;
|
|
|
|
size_t offs = 0;
|
|
|
|
|
|
|
|
*buf = '\0';
|
|
|
|
rcu_read_lock();
|
|
|
|
list_for_each_entry_rcu(ca, &tcp_cong_list, list) {
|
2007-04-24 09:26:16 +04:00
|
|
|
if (!(ca->flags & TCP_CONG_NON_RESTRICTED))
|
2006-11-10 03:35:15 +03:00
|
|
|
continue;
|
|
|
|
offs += snprintf(buf + offs, maxlen - offs,
|
|
|
|
"%s%s",
|
|
|
|
offs == 0 ? "" : " ", ca->name);
|
|
|
|
|
|
|
|
}
|
|
|
|
rcu_read_unlock();
|
|
|
|
}
|
|
|
|
|
|
|
|
/* Change list of non-restricted congestion control */
|
|
|
|
int tcp_set_allowed_congestion_control(char *val)
|
|
|
|
{
|
|
|
|
struct tcp_congestion_ops *ca;
|
2010-08-28 06:31:56 +04:00
|
|
|
char *saved_clone, *clone, *name;
|
2006-11-10 03:35:15 +03:00
|
|
|
int ret = 0;
|
|
|
|
|
2010-08-28 06:31:56 +04:00
|
|
|
saved_clone = clone = kstrdup(val, GFP_USER);
|
2006-11-10 03:35:15 +03:00
|
|
|
if (!clone)
|
|
|
|
return -ENOMEM;
|
|
|
|
|
|
|
|
spin_lock(&tcp_cong_list_lock);
|
|
|
|
/* pass 1 check for bad entries */
|
|
|
|
while ((name = strsep(&clone, " ")) && *name) {
|
|
|
|
ca = tcp_ca_find(name);
|
|
|
|
if (!ca) {
|
|
|
|
ret = -ENOENT;
|
|
|
|
goto out;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2007-04-24 09:26:16 +04:00
|
|
|
/* pass 2 clear old values */
|
2006-11-10 03:35:15 +03:00
|
|
|
list_for_each_entry_rcu(ca, &tcp_cong_list, list)
|
2007-04-24 09:26:16 +04:00
|
|
|
ca->flags &= ~TCP_CONG_NON_RESTRICTED;
|
2006-11-10 03:35:15 +03:00
|
|
|
|
|
|
|
/* pass 3 mark as allowed */
|
|
|
|
while ((name = strsep(&val, " ")) && *name) {
|
|
|
|
ca = tcp_ca_find(name);
|
|
|
|
WARN_ON(!ca);
|
|
|
|
if (ca)
|
2007-04-24 09:26:16 +04:00
|
|
|
ca->flags |= TCP_CONG_NON_RESTRICTED;
|
2006-11-10 03:35:15 +03:00
|
|
|
}
|
|
|
|
out:
|
|
|
|
spin_unlock(&tcp_cong_list_lock);
|
2010-08-28 06:31:56 +04:00
|
|
|
kfree(saved_clone);
|
2006-11-10 03:35:15 +03:00
|
|
|
|
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
|
|
|
|
2005-06-24 07:37:36 +04:00
|
|
|
/* Change congestion control for socket */
|
2005-08-10 11:03:31 +04:00
|
|
|
int tcp_set_congestion_control(struct sock *sk, const char *name)
|
2005-06-24 07:37:36 +04:00
|
|
|
{
|
2005-08-10 11:03:31 +04:00
|
|
|
struct inet_connection_sock *icsk = inet_csk(sk);
|
2005-06-24 07:37:36 +04:00
|
|
|
struct tcp_congestion_ops *ca;
|
|
|
|
int err = 0;
|
|
|
|
|
|
|
|
rcu_read_lock();
|
|
|
|
ca = tcp_ca_find(name);
|
2007-04-24 09:32:11 +04:00
|
|
|
|
2006-11-10 03:36:36 +03:00
|
|
|
/* no change asking for existing value */
|
2005-08-10 11:03:31 +04:00
|
|
|
if (ca == icsk->icsk_ca_ops)
|
2005-06-24 07:37:36 +04:00
|
|
|
goto out;
|
|
|
|
|
2008-10-17 02:24:51 +04:00
|
|
|
#ifdef CONFIG_MODULES
|
2006-11-10 03:36:36 +03:00
|
|
|
/* not found attempt to autoload module */
|
2009-08-13 17:44:51 +04:00
|
|
|
if (!ca && capable(CAP_NET_ADMIN)) {
|
2006-11-10 03:36:36 +03:00
|
|
|
rcu_read_unlock();
|
|
|
|
request_module("tcp_%s", name);
|
|
|
|
rcu_read_lock();
|
|
|
|
ca = tcp_ca_find(name);
|
|
|
|
}
|
|
|
|
#endif
|
2005-06-24 07:37:36 +04:00
|
|
|
if (!ca)
|
|
|
|
err = -ENOENT;
|
|
|
|
|
net: Allow userns root to control ipv4
Allow an unpriviled user who has created a user namespace, and then
created a network namespace to effectively use the new network
namespace, by reducing capable(CAP_NET_ADMIN) and
capable(CAP_NET_RAW) calls to be ns_capable(net->user_ns,
CAP_NET_ADMIN), or capable(net->user_ns, CAP_NET_RAW) calls.
Settings that merely control a single network device are allowed.
Either the network device is a logical network device where
restrictions make no difference or the network device is hardware NIC
that has been explicity moved from the initial network namespace.
In general policy and network stack state changes are allowed
while resource control is left unchanged.
Allow creating raw sockets.
Allow the SIOCSARP ioctl to control the arp cache.
Allow the SIOCSIFFLAG ioctl to allow setting network device flags.
Allow the SIOCSIFADDR ioctl to allow setting a netdevice ipv4 address.
Allow the SIOCSIFBRDADDR ioctl to allow setting a netdevice ipv4 broadcast address.
Allow the SIOCSIFDSTADDR ioctl to allow setting a netdevice ipv4 destination address.
Allow the SIOCSIFNETMASK ioctl to allow setting a netdevice ipv4 netmask.
Allow the SIOCADDRT and SIOCDELRT ioctls to allow adding and deleting ipv4 routes.
Allow the SIOCADDTUNNEL, SIOCCHGTUNNEL and SIOCDELTUNNEL ioctls for
adding, changing and deleting gre tunnels.
Allow the SIOCADDTUNNEL, SIOCCHGTUNNEL and SIOCDELTUNNEL ioctls for
adding, changing and deleting ipip tunnels.
Allow the SIOCADDTUNNEL, SIOCCHGTUNNEL and SIOCDELTUNNEL ioctls for
adding, changing and deleting ipsec virtual tunnel interfaces.
Allow setting the MRT_INIT, MRT_DONE, MRT_ADD_VIF, MRT_DEL_VIF, MRT_ADD_MFC,
MRT_DEL_MFC, MRT_ASSERT, MRT_PIM, MRT_TABLE socket options on multicast routing
sockets.
Allow setting and receiving IPOPT_CIPSO, IP_OPT_SEC, IP_OPT_SID and
arbitrary ip options.
Allow setting IP_SEC_POLICY/IP_XFRM_POLICY ipv4 socket option.
Allow setting the IP_TRANSPARENT ipv4 socket option.
Allow setting the TCP_REPAIR socket option.
Allow setting the TCP_CONGESTION socket option.
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2012-11-16 07:03:05 +04:00
|
|
|
else if (!((ca->flags & TCP_CONG_NON_RESTRICTED) ||
|
|
|
|
ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)))
|
2006-11-10 03:35:15 +03:00
|
|
|
err = -EPERM;
|
|
|
|
|
2005-06-24 07:37:36 +04:00
|
|
|
else if (!try_module_get(ca->owner))
|
|
|
|
err = -EBUSY;
|
|
|
|
|
|
|
|
else {
|
2005-08-10 11:03:31 +04:00
|
|
|
tcp_cleanup_congestion_control(sk);
|
|
|
|
icsk->icsk_ca_ops = ca;
|
2007-04-24 09:32:11 +04:00
|
|
|
|
|
|
|
if (sk->sk_state != TCP_CLOSE && icsk->icsk_ca_ops->init)
|
2005-08-10 11:03:31 +04:00
|
|
|
icsk->icsk_ca_ops->init(sk);
|
2005-06-24 07:37:36 +04:00
|
|
|
}
|
|
|
|
out:
|
|
|
|
rcu_read_unlock();
|
|
|
|
return err;
|
|
|
|
}
|
|
|
|
|
[TCP]: Uninline tcp_is_cwnd_limited
net/ipv4/tcp_cong.c:
tcp_reno_cong_avoid | -65
1 function changed, 65 bytes removed, diff: -65
net/ipv4/arp.c:
arp_ignore | -5
1 function changed, 5 bytes removed, diff: -5
net/ipv4/tcp_bic.c:
bictcp_cong_avoid | -57
1 function changed, 57 bytes removed, diff: -57
net/ipv4/tcp_cubic.c:
bictcp_cong_avoid | -61
1 function changed, 61 bytes removed, diff: -61
net/ipv4/tcp_highspeed.c:
hstcp_cong_avoid | -63
1 function changed, 63 bytes removed, diff: -63
net/ipv4/tcp_hybla.c:
hybla_cong_avoid | -85
1 function changed, 85 bytes removed, diff: -85
net/ipv4/tcp_htcp.c:
htcp_cong_avoid | -57
1 function changed, 57 bytes removed, diff: -57
net/ipv4/tcp_veno.c:
tcp_veno_cong_avoid | -52
1 function changed, 52 bytes removed, diff: -52
net/ipv4/tcp_scalable.c:
tcp_scalable_cong_avoid | -61
1 function changed, 61 bytes removed, diff: -61
net/ipv4/tcp_yeah.c:
tcp_yeah_cong_avoid | -75
1 function changed, 75 bytes removed, diff: -75
net/ipv4/tcp_illinois.c:
tcp_illinois_cong_avoid | -54
1 function changed, 54 bytes removed, diff: -54
net/dccp/ccids/ccid3.c:
ccid3_update_send_interval | -7
ccid3_hc_tx_packet_recv | +7
2 functions changed, 7 bytes added, 7 bytes removed, diff: +0
net/ipv4/tcp_cong.c:
tcp_is_cwnd_limited | +88
1 function changed, 88 bytes added, diff: +88
built-in.o:
14 functions changed, 95 bytes added, 642 bytes removed, diff: -547
...Again some gcc artifacts visible as well.
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@helsinki.fi>
Signed-off-by: David S. Miller <davem@davemloft.net>
2008-01-12 14:19:12 +03:00
|
|
|
/* RFC2861 Check whether we are limited by application or congestion window
|
|
|
|
* This is the inverse of cwnd check in tcp_tso_should_defer
|
|
|
|
*/
|
2012-05-17 03:15:34 +04:00
|
|
|
bool tcp_is_cwnd_limited(const struct sock *sk, u32 in_flight)
|
[TCP]: Uninline tcp_is_cwnd_limited
net/ipv4/tcp_cong.c:
tcp_reno_cong_avoid | -65
1 function changed, 65 bytes removed, diff: -65
net/ipv4/arp.c:
arp_ignore | -5
1 function changed, 5 bytes removed, diff: -5
net/ipv4/tcp_bic.c:
bictcp_cong_avoid | -57
1 function changed, 57 bytes removed, diff: -57
net/ipv4/tcp_cubic.c:
bictcp_cong_avoid | -61
1 function changed, 61 bytes removed, diff: -61
net/ipv4/tcp_highspeed.c:
hstcp_cong_avoid | -63
1 function changed, 63 bytes removed, diff: -63
net/ipv4/tcp_hybla.c:
hybla_cong_avoid | -85
1 function changed, 85 bytes removed, diff: -85
net/ipv4/tcp_htcp.c:
htcp_cong_avoid | -57
1 function changed, 57 bytes removed, diff: -57
net/ipv4/tcp_veno.c:
tcp_veno_cong_avoid | -52
1 function changed, 52 bytes removed, diff: -52
net/ipv4/tcp_scalable.c:
tcp_scalable_cong_avoid | -61
1 function changed, 61 bytes removed, diff: -61
net/ipv4/tcp_yeah.c:
tcp_yeah_cong_avoid | -75
1 function changed, 75 bytes removed, diff: -75
net/ipv4/tcp_illinois.c:
tcp_illinois_cong_avoid | -54
1 function changed, 54 bytes removed, diff: -54
net/dccp/ccids/ccid3.c:
ccid3_update_send_interval | -7
ccid3_hc_tx_packet_recv | +7
2 functions changed, 7 bytes added, 7 bytes removed, diff: +0
net/ipv4/tcp_cong.c:
tcp_is_cwnd_limited | +88
1 function changed, 88 bytes added, diff: +88
built-in.o:
14 functions changed, 95 bytes added, 642 bytes removed, diff: -547
...Again some gcc artifacts visible as well.
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@helsinki.fi>
Signed-off-by: David S. Miller <davem@davemloft.net>
2008-01-12 14:19:12 +03:00
|
|
|
{
|
|
|
|
const struct tcp_sock *tp = tcp_sk(sk);
|
|
|
|
u32 left;
|
|
|
|
|
|
|
|
if (in_flight >= tp->snd_cwnd)
|
2012-05-17 03:15:34 +04:00
|
|
|
return true;
|
[TCP]: Uninline tcp_is_cwnd_limited
net/ipv4/tcp_cong.c:
tcp_reno_cong_avoid | -65
1 function changed, 65 bytes removed, diff: -65
net/ipv4/arp.c:
arp_ignore | -5
1 function changed, 5 bytes removed, diff: -5
net/ipv4/tcp_bic.c:
bictcp_cong_avoid | -57
1 function changed, 57 bytes removed, diff: -57
net/ipv4/tcp_cubic.c:
bictcp_cong_avoid | -61
1 function changed, 61 bytes removed, diff: -61
net/ipv4/tcp_highspeed.c:
hstcp_cong_avoid | -63
1 function changed, 63 bytes removed, diff: -63
net/ipv4/tcp_hybla.c:
hybla_cong_avoid | -85
1 function changed, 85 bytes removed, diff: -85
net/ipv4/tcp_htcp.c:
htcp_cong_avoid | -57
1 function changed, 57 bytes removed, diff: -57
net/ipv4/tcp_veno.c:
tcp_veno_cong_avoid | -52
1 function changed, 52 bytes removed, diff: -52
net/ipv4/tcp_scalable.c:
tcp_scalable_cong_avoid | -61
1 function changed, 61 bytes removed, diff: -61
net/ipv4/tcp_yeah.c:
tcp_yeah_cong_avoid | -75
1 function changed, 75 bytes removed, diff: -75
net/ipv4/tcp_illinois.c:
tcp_illinois_cong_avoid | -54
1 function changed, 54 bytes removed, diff: -54
net/dccp/ccids/ccid3.c:
ccid3_update_send_interval | -7
ccid3_hc_tx_packet_recv | +7
2 functions changed, 7 bytes added, 7 bytes removed, diff: +0
net/ipv4/tcp_cong.c:
tcp_is_cwnd_limited | +88
1 function changed, 88 bytes added, diff: +88
built-in.o:
14 functions changed, 95 bytes added, 642 bytes removed, diff: -547
...Again some gcc artifacts visible as well.
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@helsinki.fi>
Signed-off-by: David S. Miller <davem@davemloft.net>
2008-01-12 14:19:12 +03:00
|
|
|
|
|
|
|
left = tp->snd_cwnd - in_flight;
|
2008-04-29 14:13:02 +04:00
|
|
|
if (sk_can_gso(sk) &&
|
2008-04-29 14:13:52 +04:00
|
|
|
left * sysctl_tcp_tso_win_divisor < tp->snd_cwnd &&
|
2014-02-23 10:25:57 +04:00
|
|
|
left < tp->xmit_size_goal_segs)
|
2012-05-17 03:15:34 +04:00
|
|
|
return true;
|
2011-11-21 21:15:14 +04:00
|
|
|
return left <= tcp_max_tso_deferred_mss(tp);
|
[TCP]: Uninline tcp_is_cwnd_limited
net/ipv4/tcp_cong.c:
tcp_reno_cong_avoid | -65
1 function changed, 65 bytes removed, diff: -65
net/ipv4/arp.c:
arp_ignore | -5
1 function changed, 5 bytes removed, diff: -5
net/ipv4/tcp_bic.c:
bictcp_cong_avoid | -57
1 function changed, 57 bytes removed, diff: -57
net/ipv4/tcp_cubic.c:
bictcp_cong_avoid | -61
1 function changed, 61 bytes removed, diff: -61
net/ipv4/tcp_highspeed.c:
hstcp_cong_avoid | -63
1 function changed, 63 bytes removed, diff: -63
net/ipv4/tcp_hybla.c:
hybla_cong_avoid | -85
1 function changed, 85 bytes removed, diff: -85
net/ipv4/tcp_htcp.c:
htcp_cong_avoid | -57
1 function changed, 57 bytes removed, diff: -57
net/ipv4/tcp_veno.c:
tcp_veno_cong_avoid | -52
1 function changed, 52 bytes removed, diff: -52
net/ipv4/tcp_scalable.c:
tcp_scalable_cong_avoid | -61
1 function changed, 61 bytes removed, diff: -61
net/ipv4/tcp_yeah.c:
tcp_yeah_cong_avoid | -75
1 function changed, 75 bytes removed, diff: -75
net/ipv4/tcp_illinois.c:
tcp_illinois_cong_avoid | -54
1 function changed, 54 bytes removed, diff: -54
net/dccp/ccids/ccid3.c:
ccid3_update_send_interval | -7
ccid3_hc_tx_packet_recv | +7
2 functions changed, 7 bytes added, 7 bytes removed, diff: +0
net/ipv4/tcp_cong.c:
tcp_is_cwnd_limited | +88
1 function changed, 88 bytes added, diff: +88
built-in.o:
14 functions changed, 95 bytes added, 642 bytes removed, diff: -547
...Again some gcc artifacts visible as well.
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@helsinki.fi>
Signed-off-by: David S. Miller <davem@davemloft.net>
2008-01-12 14:19:12 +03:00
|
|
|
}
|
|
|
|
EXPORT_SYMBOL_GPL(tcp_is_cwnd_limited);
|
2006-01-04 03:03:49 +03:00
|
|
|
|
2013-10-31 22:07:31 +04:00
|
|
|
/* Slow start is used when congestion window is no greater than the slow start
|
|
|
|
* threshold. We base on RFC2581 and also handle stretch ACKs properly.
|
|
|
|
* We do not implement RFC3465 Appropriate Byte Counting (ABC) per se but
|
|
|
|
* something better;) a packet is only considered (s)acked in its entirety to
|
|
|
|
* defend the ACK attacks described in the RFC. Slow start processes a stretch
|
|
|
|
* ACK of degree N as if N acks of degree 1 are received back to back except
|
|
|
|
* ABC caps N to 2. Slow start exits when cwnd grows over ssthresh and
|
|
|
|
* returns the leftover acks to adjust cwnd in congestion avoidance mode.
|
2006-01-04 03:03:49 +03:00
|
|
|
*/
|
2013-10-31 22:07:31 +04:00
|
|
|
int tcp_slow_start(struct tcp_sock *tp, u32 acked)
|
2006-01-04 03:03:49 +03:00
|
|
|
{
|
2013-10-31 22:07:31 +04:00
|
|
|
u32 cwnd = tp->snd_cwnd + acked;
|
2007-05-17 11:04:18 +04:00
|
|
|
|
2013-10-31 22:07:31 +04:00
|
|
|
if (cwnd > tp->snd_ssthresh)
|
|
|
|
cwnd = tp->snd_ssthresh + 1;
|
|
|
|
acked -= cwnd - tp->snd_cwnd;
|
|
|
|
tp->snd_cwnd = min(cwnd, tp->snd_cwnd_clamp);
|
|
|
|
return acked;
|
2006-01-04 03:03:49 +03:00
|
|
|
}
|
|
|
|
EXPORT_SYMBOL_GPL(tcp_slow_start);
|
|
|
|
|
2009-02-28 07:44:37 +03:00
|
|
|
/* In theory this is tp->snd_cwnd += 1 / tp->snd_cwnd (or alternative w) */
|
|
|
|
void tcp_cong_avoid_ai(struct tcp_sock *tp, u32 w)
|
|
|
|
{
|
|
|
|
if (tp->snd_cwnd_cnt >= w) {
|
|
|
|
if (tp->snd_cwnd < tp->snd_cwnd_clamp)
|
|
|
|
tp->snd_cwnd++;
|
|
|
|
tp->snd_cwnd_cnt = 0;
|
|
|
|
} else {
|
|
|
|
tp->snd_cwnd_cnt++;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
EXPORT_SYMBOL_GPL(tcp_cong_avoid_ai);
|
|
|
|
|
2005-06-23 23:19:55 +04:00
|
|
|
/*
|
|
|
|
* TCP Reno congestion control
|
|
|
|
* This is special case used for fallback as well.
|
|
|
|
*/
|
|
|
|
/* This is Jacobson's slow start and congestion avoidance.
|
|
|
|
* SIGCOMM '88, p. 328.
|
|
|
|
*/
|
2013-10-31 22:07:31 +04:00
|
|
|
void tcp_reno_cong_avoid(struct sock *sk, u32 ack, u32 acked, u32 in_flight)
|
2005-06-23 23:19:55 +04:00
|
|
|
{
|
2005-08-10 11:03:31 +04:00
|
|
|
struct tcp_sock *tp = tcp_sk(sk);
|
|
|
|
|
2005-11-11 03:53:30 +03:00
|
|
|
if (!tcp_is_cwnd_limited(sk, in_flight))
|
2005-06-23 23:19:55 +04:00
|
|
|
return;
|
|
|
|
|
2005-11-11 04:07:24 +03:00
|
|
|
/* In "safe" area, increase. */
|
2007-02-09 17:24:47 +03:00
|
|
|
if (tp->snd_cwnd <= tp->snd_ssthresh)
|
2013-10-31 22:07:31 +04:00
|
|
|
tcp_slow_start(tp, acked);
|
2007-02-09 17:24:47 +03:00
|
|
|
/* In dangerous area, increase slowly. */
|
2013-02-05 11:25:17 +04:00
|
|
|
else
|
2009-02-28 07:44:37 +03:00
|
|
|
tcp_cong_avoid_ai(tp, tp->snd_cwnd);
|
2005-06-23 23:19:55 +04:00
|
|
|
}
|
|
|
|
EXPORT_SYMBOL_GPL(tcp_reno_cong_avoid);
|
|
|
|
|
|
|
|
/* Slow start threshold is half the congestion window (min 2) */
|
2005-08-10 11:03:31 +04:00
|
|
|
u32 tcp_reno_ssthresh(struct sock *sk)
|
2005-06-23 23:19:55 +04:00
|
|
|
{
|
2005-08-10 11:03:31 +04:00
|
|
|
const struct tcp_sock *tp = tcp_sk(sk);
|
2005-06-23 23:19:55 +04:00
|
|
|
return max(tp->snd_cwnd >> 1U, 2U);
|
|
|
|
}
|
|
|
|
EXPORT_SYMBOL_GPL(tcp_reno_ssthresh);
|
|
|
|
|
|
|
|
struct tcp_congestion_ops tcp_reno = {
|
2007-04-24 09:26:16 +04:00
|
|
|
.flags = TCP_CONG_NON_RESTRICTED,
|
2005-06-23 23:19:55 +04:00
|
|
|
.name = "reno",
|
|
|
|
.owner = THIS_MODULE,
|
|
|
|
.ssthresh = tcp_reno_ssthresh,
|
|
|
|
.cong_avoid = tcp_reno_cong_avoid,
|
|
|
|
};
|
|
|
|
|
2005-06-24 07:37:36 +04:00
|
|
|
/* Initial congestion control used (until SYN)
|
|
|
|
* really reno under another name so we can tell difference
|
|
|
|
* during tcp_set_default_congestion_control
|
|
|
|
*/
|
|
|
|
struct tcp_congestion_ops tcp_init_congestion_ops = {
|
|
|
|
.name = "",
|
|
|
|
.owner = THIS_MODULE,
|
|
|
|
.ssthresh = tcp_reno_ssthresh,
|
|
|
|
.cong_avoid = tcp_reno_cong_avoid,
|
|
|
|
};
|
|
|
|
EXPORT_SYMBOL_GPL(tcp_init_congestion_ops);
|