2008-11-08 09:56:00 +03:00
|
|
|
/*
|
|
|
|
* net/sched/cls_cgroup.c Control Group Classifier
|
|
|
|
*
|
|
|
|
* 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.
|
|
|
|
*
|
|
|
|
* Authors: Thomas Graf <tgraf@suug.ch>
|
|
|
|
*/
|
|
|
|
|
|
|
|
#include <linux/module.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/slab.h>
|
2008-11-08 09:56:00 +03:00
|
|
|
#include <linux/skbuff.h>
|
cls_cgroup: Store classid in struct sock
Up until now cls_cgroup has relied on fetching the classid out of
the current executing thread. This runs into trouble when a packet
processing is delayed in which case it may execute out of another
thread's context.
Furthermore, even when a packet is not delayed we may fail to
classify it if soft IRQs have been disabled, because this scenario
is indistinguishable from one where a packet unrelated to the
current thread is processed by a real soft IRQ.
In fact, the current semantics is inherently broken, as a single
skb may be constructed out of the writes of two different tasks.
A different manifestation of this problem is when the TCP stack
transmits in response of an incoming ACK. This is currently
unclassified.
As we already have a concept of packet ownership for accounting
purposes in the skb->sk pointer, this is a natural place to store
the classid in a persistent manner.
This patch adds the cls_cgroup classid in struct sock, filling up
an existing hole on 64-bit :)
The value is set at socket creation time. So all sockets created
via socket(2) automatically gains the ID of the thread creating it.
Whenever another process touches the socket by either reading or
writing to it, we will change the socket classid to that of the
process if it has a valid (non-zero) classid.
For sockets created on inbound connections through accept(2), we
inherit the classid of the original listening socket through
sk_clone, possibly preceding the actual accept(2) call.
In order to minimise risks, I have not made this the authoritative
classid. For now it is only used as a backup when we execute
with soft IRQs disabled. Once we're completely happy with its
semantics we can use it as the sole classid.
Footnote: I have rearranged the error path on cls_group module
creation. If we didn't do this, then there is a window where
someone could create a tc rule using cls_group before the cgroup
subsystem has been registered.
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
2010-05-24 11:12:34 +04:00
|
|
|
#include <linux/rcupdate.h>
|
2008-11-08 09:56:00 +03:00
|
|
|
#include <net/rtnetlink.h>
|
|
|
|
#include <net/pkt_cls.h>
|
cls_cgroup: Store classid in struct sock
Up until now cls_cgroup has relied on fetching the classid out of
the current executing thread. This runs into trouble when a packet
processing is delayed in which case it may execute out of another
thread's context.
Furthermore, even when a packet is not delayed we may fail to
classify it if soft IRQs have been disabled, because this scenario
is indistinguishable from one where a packet unrelated to the
current thread is processed by a real soft IRQ.
In fact, the current semantics is inherently broken, as a single
skb may be constructed out of the writes of two different tasks.
A different manifestation of this problem is when the TCP stack
transmits in response of an incoming ACK. This is currently
unclassified.
As we already have a concept of packet ownership for accounting
purposes in the skb->sk pointer, this is a natural place to store
the classid in a persistent manner.
This patch adds the cls_cgroup classid in struct sock, filling up
an existing hole on 64-bit :)
The value is set at socket creation time. So all sockets created
via socket(2) automatically gains the ID of the thread creating it.
Whenever another process touches the socket by either reading or
writing to it, we will change the socket classid to that of the
process if it has a valid (non-zero) classid.
For sockets created on inbound connections through accept(2), we
inherit the classid of the original listening socket through
sk_clone, possibly preceding the actual accept(2) call.
In order to minimise risks, I have not made this the authoritative
classid. For now it is only used as a backup when we execute
with soft IRQs disabled. Once we're completely happy with its
semantics we can use it as the sole classid.
Footnote: I have rearranged the error path on cls_group module
creation. If we didn't do this, then there is a window where
someone could create a tc rule using cls_group before the cgroup
subsystem has been registered.
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
2010-05-24 11:12:34 +04:00
|
|
|
#include <net/sock.h>
|
|
|
|
#include <net/cls_cgroup.h>
|
2008-11-08 09:56:00 +03:00
|
|
|
|
2011-01-19 22:26:56 +03:00
|
|
|
struct cls_cgroup_head {
|
2008-11-08 09:56:00 +03:00
|
|
|
u32 handle;
|
|
|
|
struct tcf_exts exts;
|
|
|
|
struct tcf_ematch_tree ematches;
|
|
|
|
};
|
|
|
|
|
2011-07-06 03:25:42 +04:00
|
|
|
static int cls_cgroup_classify(struct sk_buff *skb, const struct tcf_proto *tp,
|
2008-11-08 09:56:00 +03:00
|
|
|
struct tcf_result *res)
|
|
|
|
{
|
|
|
|
struct cls_cgroup_head *head = tp->root;
|
2009-05-27 07:47:02 +04:00
|
|
|
u32 classid;
|
2008-11-08 09:56:00 +03:00
|
|
|
|
cls_cgroup: Store classid in struct sock
Up until now cls_cgroup has relied on fetching the classid out of
the current executing thread. This runs into trouble when a packet
processing is delayed in which case it may execute out of another
thread's context.
Furthermore, even when a packet is not delayed we may fail to
classify it if soft IRQs have been disabled, because this scenario
is indistinguishable from one where a packet unrelated to the
current thread is processed by a real soft IRQ.
In fact, the current semantics is inherently broken, as a single
skb may be constructed out of the writes of two different tasks.
A different manifestation of this problem is when the TCP stack
transmits in response of an incoming ACK. This is currently
unclassified.
As we already have a concept of packet ownership for accounting
purposes in the skb->sk pointer, this is a natural place to store
the classid in a persistent manner.
This patch adds the cls_cgroup classid in struct sock, filling up
an existing hole on 64-bit :)
The value is set at socket creation time. So all sockets created
via socket(2) automatically gains the ID of the thread creating it.
Whenever another process touches the socket by either reading or
writing to it, we will change the socket classid to that of the
process if it has a valid (non-zero) classid.
For sockets created on inbound connections through accept(2), we
inherit the classid of the original listening socket through
sk_clone, possibly preceding the actual accept(2) call.
In order to minimise risks, I have not made this the authoritative
classid. For now it is only used as a backup when we execute
with soft IRQs disabled. Once we're completely happy with its
semantics we can use it as the sole classid.
Footnote: I have rearranged the error path on cls_group module
creation. If we didn't do this, then there is a window where
someone could create a tc rule using cls_group before the cgroup
subsystem has been registered.
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
2010-05-24 11:12:34 +04:00
|
|
|
rcu_read_lock();
|
|
|
|
classid = task_cls_state(current)->classid;
|
|
|
|
rcu_read_unlock();
|
|
|
|
|
2008-11-08 09:56:00 +03:00
|
|
|
/*
|
|
|
|
* Due to the nature of the classifier it is required to ignore all
|
|
|
|
* packets originating from softirq context as accessing `current'
|
|
|
|
* would lead to false results.
|
|
|
|
*
|
|
|
|
* This test assumes that all callers of dev_queue_xmit() explicitely
|
|
|
|
* disable bh. Knowing this, it is possible to detect softirq based
|
|
|
|
* calls by looking at the number of nested bh disable calls because
|
|
|
|
* softirqs always disables bh.
|
|
|
|
*/
|
2010-10-05 04:03:16 +04:00
|
|
|
if (in_serving_softirq()) {
|
cls_cgroup: Store classid in struct sock
Up until now cls_cgroup has relied on fetching the classid out of
the current executing thread. This runs into trouble when a packet
processing is delayed in which case it may execute out of another
thread's context.
Furthermore, even when a packet is not delayed we may fail to
classify it if soft IRQs have been disabled, because this scenario
is indistinguishable from one where a packet unrelated to the
current thread is processed by a real soft IRQ.
In fact, the current semantics is inherently broken, as a single
skb may be constructed out of the writes of two different tasks.
A different manifestation of this problem is when the TCP stack
transmits in response of an incoming ACK. This is currently
unclassified.
As we already have a concept of packet ownership for accounting
purposes in the skb->sk pointer, this is a natural place to store
the classid in a persistent manner.
This patch adds the cls_cgroup classid in struct sock, filling up
an existing hole on 64-bit :)
The value is set at socket creation time. So all sockets created
via socket(2) automatically gains the ID of the thread creating it.
Whenever another process touches the socket by either reading or
writing to it, we will change the socket classid to that of the
process if it has a valid (non-zero) classid.
For sockets created on inbound connections through accept(2), we
inherit the classid of the original listening socket through
sk_clone, possibly preceding the actual accept(2) call.
In order to minimise risks, I have not made this the authoritative
classid. For now it is only used as a backup when we execute
with soft IRQs disabled. Once we're completely happy with its
semantics we can use it as the sole classid.
Footnote: I have rearranged the error path on cls_group module
creation. If we didn't do this, then there is a window where
someone could create a tc rule using cls_group before the cgroup
subsystem has been registered.
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
2010-05-24 11:12:34 +04:00
|
|
|
/* If there is an sk_classid we'll use that. */
|
|
|
|
if (!skb->sk)
|
|
|
|
return -1;
|
|
|
|
classid = skb->sk->sk_classid;
|
|
|
|
}
|
2008-11-08 09:56:00 +03:00
|
|
|
|
2009-05-27 07:47:02 +04:00
|
|
|
if (!classid)
|
|
|
|
return -1;
|
|
|
|
|
|
|
|
if (!tcf_em_tree_match(skb, &head->ematches, NULL))
|
|
|
|
return -1;
|
|
|
|
|
|
|
|
res->classid = classid;
|
|
|
|
res->class = 0;
|
|
|
|
return tcf_exts_exec(skb, &head->exts, res);
|
2008-11-08 09:56:00 +03:00
|
|
|
}
|
|
|
|
|
|
|
|
static unsigned long cls_cgroup_get(struct tcf_proto *tp, u32 handle)
|
|
|
|
{
|
|
|
|
return 0UL;
|
|
|
|
}
|
|
|
|
|
|
|
|
static void cls_cgroup_put(struct tcf_proto *tp, unsigned long f)
|
|
|
|
{
|
|
|
|
}
|
|
|
|
|
|
|
|
static int cls_cgroup_init(struct tcf_proto *tp)
|
|
|
|
{
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
static const struct nla_policy cgroup_policy[TCA_CGROUP_MAX + 1] = {
|
|
|
|
[TCA_CGROUP_EMATCHES] = { .type = NLA_NESTED },
|
|
|
|
};
|
|
|
|
|
2013-01-14 09:15:39 +04:00
|
|
|
static int cls_cgroup_change(struct net *net, struct sk_buff *in_skb,
|
2012-05-25 23:42:45 +04:00
|
|
|
struct tcf_proto *tp, unsigned long base,
|
2008-11-08 09:56:00 +03:00
|
|
|
u32 handle, struct nlattr **tca,
|
|
|
|
unsigned long *arg)
|
|
|
|
{
|
2011-01-19 22:26:56 +03:00
|
|
|
struct nlattr *tb[TCA_CGROUP_MAX + 1];
|
2008-11-08 09:56:00 +03:00
|
|
|
struct cls_cgroup_head *head = tp->root;
|
|
|
|
struct tcf_ematch_tree t;
|
|
|
|
struct tcf_exts e;
|
|
|
|
int err;
|
|
|
|
|
2009-06-09 15:03:09 +04:00
|
|
|
if (!tca[TCA_OPTIONS])
|
|
|
|
return -EINVAL;
|
|
|
|
|
2008-11-08 09:56:00 +03:00
|
|
|
if (head == NULL) {
|
|
|
|
if (!handle)
|
|
|
|
return -EINVAL;
|
|
|
|
|
|
|
|
head = kzalloc(sizeof(*head), GFP_KERNEL);
|
|
|
|
if (head == NULL)
|
|
|
|
return -ENOBUFS;
|
|
|
|
|
2013-12-16 08:15:07 +04:00
|
|
|
tcf_exts_init(&head->exts, TCA_CGROUP_ACT, TCA_CGROUP_POLICE);
|
2008-11-08 09:56:00 +03:00
|
|
|
head->handle = handle;
|
|
|
|
|
|
|
|
tcf_tree_lock(tp);
|
|
|
|
tp->root = head;
|
|
|
|
tcf_tree_unlock(tp);
|
|
|
|
}
|
|
|
|
|
|
|
|
if (handle != head->handle)
|
|
|
|
return -ENOENT;
|
|
|
|
|
|
|
|
err = nla_parse_nested(tb, TCA_CGROUP_MAX, tca[TCA_OPTIONS],
|
|
|
|
cgroup_policy);
|
|
|
|
if (err < 0)
|
|
|
|
return err;
|
|
|
|
|
2013-12-16 08:15:07 +04:00
|
|
|
tcf_exts_init(&e, TCA_CGROUP_ACT, TCA_CGROUP_POLICE);
|
|
|
|
err = tcf_exts_validate(net, tp, tb, tca[TCA_RATE], &e);
|
2008-11-08 09:56:00 +03:00
|
|
|
if (err < 0)
|
|
|
|
return err;
|
|
|
|
|
|
|
|
err = tcf_em_tree_validate(tp, tb[TCA_CGROUP_EMATCHES], &t);
|
|
|
|
if (err < 0)
|
|
|
|
return err;
|
|
|
|
|
|
|
|
tcf_exts_change(tp, &head->exts, &e);
|
|
|
|
tcf_em_tree_change(tp, &head->ematches, &t);
|
|
|
|
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
static void cls_cgroup_destroy(struct tcf_proto *tp)
|
|
|
|
{
|
2008-11-19 11:03:09 +03:00
|
|
|
struct cls_cgroup_head *head = tp->root;
|
2008-11-08 09:56:00 +03:00
|
|
|
|
|
|
|
if (head) {
|
|
|
|
tcf_exts_destroy(tp, &head->exts);
|
|
|
|
tcf_em_tree_destroy(tp, &head->ematches);
|
|
|
|
kfree(head);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
static int cls_cgroup_delete(struct tcf_proto *tp, unsigned long arg)
|
|
|
|
{
|
|
|
|
return -EOPNOTSUPP;
|
|
|
|
}
|
|
|
|
|
|
|
|
static void cls_cgroup_walk(struct tcf_proto *tp, struct tcf_walker *arg)
|
|
|
|
{
|
|
|
|
struct cls_cgroup_head *head = tp->root;
|
|
|
|
|
|
|
|
if (arg->count < arg->skip)
|
|
|
|
goto skip;
|
|
|
|
|
|
|
|
if (arg->fn(tp, (unsigned long) head, arg) < 0) {
|
|
|
|
arg->stop = 1;
|
|
|
|
return;
|
|
|
|
}
|
|
|
|
skip:
|
|
|
|
arg->count++;
|
|
|
|
}
|
|
|
|
|
2014-01-10 04:14:01 +04:00
|
|
|
static int cls_cgroup_dump(struct net *net, struct tcf_proto *tp, unsigned long fh,
|
2008-11-08 09:56:00 +03:00
|
|
|
struct sk_buff *skb, struct tcmsg *t)
|
|
|
|
{
|
|
|
|
struct cls_cgroup_head *head = tp->root;
|
|
|
|
unsigned char *b = skb_tail_pointer(skb);
|
|
|
|
struct nlattr *nest;
|
|
|
|
|
|
|
|
t->tcm_handle = head->handle;
|
|
|
|
|
|
|
|
nest = nla_nest_start(skb, TCA_OPTIONS);
|
|
|
|
if (nest == NULL)
|
|
|
|
goto nla_put_failure;
|
|
|
|
|
2013-12-16 08:15:07 +04:00
|
|
|
if (tcf_exts_dump(skb, &head->exts) < 0 ||
|
2008-11-08 09:56:00 +03:00
|
|
|
tcf_em_tree_dump(skb, &head->ematches, TCA_CGROUP_EMATCHES) < 0)
|
|
|
|
goto nla_put_failure;
|
|
|
|
|
|
|
|
nla_nest_end(skb, nest);
|
|
|
|
|
2013-12-16 08:15:07 +04:00
|
|
|
if (tcf_exts_dump_stats(skb, &head->exts) < 0)
|
2008-11-08 09:56:00 +03:00
|
|
|
goto nla_put_failure;
|
|
|
|
|
|
|
|
return skb->len;
|
|
|
|
|
|
|
|
nla_put_failure:
|
|
|
|
nlmsg_trim(skb, b);
|
|
|
|
return -1;
|
|
|
|
}
|
|
|
|
|
|
|
|
static struct tcf_proto_ops cls_cgroup_ops __read_mostly = {
|
|
|
|
.kind = "cgroup",
|
|
|
|
.init = cls_cgroup_init,
|
|
|
|
.change = cls_cgroup_change,
|
|
|
|
.classify = cls_cgroup_classify,
|
|
|
|
.destroy = cls_cgroup_destroy,
|
|
|
|
.get = cls_cgroup_get,
|
|
|
|
.put = cls_cgroup_put,
|
|
|
|
.delete = cls_cgroup_delete,
|
|
|
|
.walk = cls_cgroup_walk,
|
|
|
|
.dump = cls_cgroup_dump,
|
|
|
|
.owner = THIS_MODULE,
|
|
|
|
};
|
|
|
|
|
|
|
|
static int __init init_cgroup_cls(void)
|
|
|
|
{
|
2013-12-29 21:27:10 +04:00
|
|
|
return register_tcf_proto_ops(&cls_cgroup_ops);
|
2008-11-08 09:56:00 +03:00
|
|
|
}
|
|
|
|
|
|
|
|
static void __exit exit_cgroup_cls(void)
|
|
|
|
{
|
|
|
|
unregister_tcf_proto_ops(&cls_cgroup_ops);
|
|
|
|
}
|
|
|
|
|
|
|
|
module_init(init_cgroup_cls);
|
|
|
|
module_exit(exit_cgroup_cls);
|
|
|
|
MODULE_LICENSE("GPL");
|