kernel_optimize_test/net/sched/cls_cgroup.c
David S. Miller 855404efae Merge git://git.kernel.org/pub/scm/linux/kernel/git/pablo/nf-next
Pablo Neira Ayuso says:

====================
netfilter/IPVS updates for net-next

The following patchset contains Netfilter updates for your net-next tree,
they are:

* Add full port randomization support. Some crazy researchers found a way
  to reconstruct the secure ephemeral ports that are allocated in random mode
  by sending off-path bursts of UDP packets to overrun the socket buffer of
  the DNS resolver to trigger retransmissions, then if the timing for the
  DNS resolution done by a client is larger than usual, then they conclude
  that the port that received the burst of UDP packets is the one that was
  opened. It seems a bit aggressive method to me but it seems to work for
  them. As a result, Daniel Borkmann and Hannes Frederic Sowa came up with a
  new NAT mode to fully randomize ports using prandom.

* Add a new classifier to x_tables based on the socket net_cls set via
  cgroups. These includes two patches to prepare the field as requested by
  Zefan Li. Also from Daniel Borkmann.

* Use prandom instead of get_random_bytes in several locations of the
  netfilter code, from Florian Westphal.

* Allow to use the CTA_MARK_MASK in ctnetlink when mangling the conntrack
  mark, also from Florian Westphal.

* Fix compilation warning due to unused variable in IPVS, from Geert
  Uytterhoeven.

* Add support for UID/GID via nfnetlink_queue, from Valentina Giusti.

* Add IPComp extension to x_tables, from Fan Du.
====================

Signed-off-by: David S. Miller <davem@davemloft.net>
2014-01-05 20:18:50 -05:00

223 lines
4.9 KiB
C

/*
* 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 <linux/slab.h>
#include <linux/skbuff.h>
#include <linux/rcupdate.h>
#include <net/rtnetlink.h>
#include <net/pkt_cls.h>
#include <net/sock.h>
#include <net/cls_cgroup.h>
struct cls_cgroup_head {
u32 handle;
struct tcf_exts exts;
struct tcf_ematch_tree ematches;
};
static int cls_cgroup_classify(struct sk_buff *skb, const struct tcf_proto *tp,
struct tcf_result *res)
{
struct cls_cgroup_head *head = tp->root;
u32 classid;
rcu_read_lock();
classid = task_cls_state(current)->classid;
rcu_read_unlock();
/*
* 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.
*/
if (in_serving_softirq()) {
/* If there is an sk_classid we'll use that. */
if (!skb->sk)
return -1;
classid = skb->sk->sk_classid;
}
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);
}
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 },
};
static int cls_cgroup_change(struct net *net, struct sk_buff *in_skb,
struct tcf_proto *tp, unsigned long base,
u32 handle, struct nlattr **tca,
unsigned long *arg)
{
struct nlattr *tb[TCA_CGROUP_MAX + 1];
struct cls_cgroup_head *head = tp->root;
struct tcf_ematch_tree t;
struct tcf_exts e;
int err;
if (!tca[TCA_OPTIONS])
return -EINVAL;
if (head == NULL) {
if (!handle)
return -EINVAL;
head = kzalloc(sizeof(*head), GFP_KERNEL);
if (head == NULL)
return -ENOBUFS;
tcf_exts_init(&head->exts, TCA_CGROUP_ACT, TCA_CGROUP_POLICE);
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;
tcf_exts_init(&e, TCA_CGROUP_ACT, TCA_CGROUP_POLICE);
err = tcf_exts_validate(net, tp, tb, tca[TCA_RATE], &e);
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)
{
struct cls_cgroup_head *head = tp->root;
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++;
}
static int cls_cgroup_dump(struct tcf_proto *tp, unsigned long fh,
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;
if (tcf_exts_dump(skb, &head->exts) < 0 ||
tcf_em_tree_dump(skb, &head->ematches, TCA_CGROUP_EMATCHES) < 0)
goto nla_put_failure;
nla_nest_end(skb, nest);
if (tcf_exts_dump_stats(skb, &head->exts) < 0)
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)
{
return register_tcf_proto_ops(&cls_cgroup_ops);
}
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");