[linux-2.6-block.git] / net / sched / cls_cgroup.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/types.h>
#include <linux/string.h>
#include <linux/errno.h>
#include <linux/skbuff.h>
#include <linux/cgroup.h>
#include <net/rtnetlink.h>
#include <net/pkt_cls.h>

struct cgroup_cls_state
{
	struct cgroup_subsys_state css;
	u32 classid;
};

static inline struct cgroup_cls_state *cgrp_cls_state(struct cgroup *cgrp)
{
	return container_of(cgroup_subsys_state(cgrp, net_cls_subsys_id),
			    struct cgroup_cls_state, css);
}

static inline struct cgroup_cls_state *task_cls_state(struct task_struct *p)
{
	return container_of(task_subsys_state(p, net_cls_subsys_id),
			    struct cgroup_cls_state, css);
}

static struct cgroup_subsys_state *cgrp_create(struct cgroup_subsys *ss,
						 struct cgroup *cgrp)
{
	struct cgroup_cls_state *cs;

	if (!(cs = kzalloc(sizeof(*cs), GFP_KERNEL)))
		return ERR_PTR(-ENOMEM);

	if (cgrp->parent)
		cs->classid = cgrp_cls_state(cgrp->parent)->classid;

	return &cs->css;
}

static void cgrp_destroy(struct cgroup_subsys *ss, struct cgroup *cgrp)
{
	kfree(cgrp_cls_state(cgrp));
}

static u64 read_classid(struct cgroup *cgrp, struct cftype *cft)
{
	return cgrp_cls_state(cgrp)->classid;
}

static int write_classid(struct cgroup *cgrp, struct cftype *cft, u64 value)
{
	if (!cgroup_lock_live_group(cgrp))
		return -ENODEV;

	cgrp_cls_state(cgrp)->classid = (u32) value;

	cgroup_unlock();

	return 0;
}

static struct cftype ss_files[] = {
	{
		.name = "classid",
		.read_u64 = read_classid,
		.write_u64 = write_classid,
	},
};

static int cgrp_populate(struct cgroup_subsys *ss, struct cgroup *cgrp)
{
	return cgroup_add_files(cgrp, ss, ss_files, ARRAY_SIZE(ss_files));
}

struct cgroup_subsys net_cls_subsys = {
	.name		= "net_cls",
	.create		= cgrp_create,
	.destroy	= cgrp_destroy,
	.populate	= cgrp_populate,
	.subsys_id	= net_cls_subsys_id,
};

struct cls_cgroup_head
{
	u32			handle;
	struct tcf_exts		exts;
	struct tcf_ematch_tree	ematches;
};

static int cls_cgroup_classify(struct sk_buff *skb, struct tcf_proto *tp,
			       struct tcf_result *res)
{
	struct cls_cgroup_head *head = tp->root;
	u32 classid;

	/*
	 * 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 (softirq_count() != SOFTIRQ_OFFSET)
		return -1;

	rcu_read_lock();
	classid = task_cls_state(current)->classid;
	rcu_read_unlock();

	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 tcf_ext_map cgroup_ext_map = {
	.action = TCA_CGROUP_ACT,
	.police = TCA_CGROUP_POLICE,
};

static const struct nla_policy cgroup_policy[TCA_CGROUP_MAX + 1] = {
	[TCA_CGROUP_EMATCHES]	= { .type = NLA_NESTED },
};

static int cls_cgroup_change(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;

		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;

	err = tcf_exts_validate(tp, tb, tca[TCA_RATE], &e, &cgroup_ext_map);
	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, &cgroup_ext_map) < 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, &cgroup_ext_map) < 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");
Commit	Line	Data
f4009237 TG	1	/*
	2	* net/sched/cls_cgroup.c Control Group Classifier
	3	*
	4	* This program is free software; you can redistribute it and/or
	5	* modify it under the terms of the GNU General Public License
	6	* as published by the Free Software Foundation; either version
	7	* 2 of the License, or (at your option) any later version.
	8	*
	9	* Authors: Thomas Graf <tgraf@suug.ch>
	10	*/
	11
	12	#include <linux/module.h>
	13	#include <linux/types.h>
	14	#include <linux/string.h>
	15	#include <linux/errno.h>
	16	#include <linux/skbuff.h>
	17	#include <linux/cgroup.h>
	18	#include <net/rtnetlink.h>
	19	#include <net/pkt_cls.h>
	20
	21	struct cgroup_cls_state
	22	{
	23	struct cgroup_subsys_state css;
	24	u32 classid;
	25	};
	26
8e8ba854	27	static inline struct cgroup_cls_state cgrp_cls_state(struct cgroup cgrp)
f4009237	28	{
8e8ba854 LZ	29	return container_of(cgroup_subsys_state(cgrp, net_cls_subsys_id),
	30	struct cgroup_cls_state, css);
	31	}
	32
	33	static inline struct cgroup_cls_state task_cls_state(struct task_struct p)
	34	{
	35	return container_of(task_subsys_state(p, net_cls_subsys_id),
	36	struct cgroup_cls_state, css);
f4009237 TG	37	}
	38
	39	static struct cgroup_subsys_state cgrp_create(struct cgroup_subsys ss,
	40	struct cgroup *cgrp)
	41	{
	42	struct cgroup_cls_state *cs;
	43
	44	if (!(cs = kzalloc(sizeof(*cs), GFP_KERNEL)))
	45	return ERR_PTR(-ENOMEM);
	46
	47	if (cgrp->parent)
8e8ba854	48	cs->classid = cgrp_cls_state(cgrp->parent)->classid;
f4009237 TG	49
	50	return &cs->css;
	51	}
	52
	53	static void cgrp_destroy(struct cgroup_subsys ss, struct cgroup cgrp)
	54	{
8e8ba854	55	kfree(cgrp_cls_state(cgrp));
f4009237 TG	56	}
	57
	58	static u64 read_classid(struct cgroup cgrp, struct cftype cft)
	59	{
8e8ba854	60	return cgrp_cls_state(cgrp)->classid;
f4009237 TG	61	}
	62
	63	static int write_classid(struct cgroup cgrp, struct cftype cft, u64 value)
	64	{
	65	if (!cgroup_lock_live_group(cgrp))
	66	return -ENODEV;
	67
8e8ba854	68	cgrp_cls_state(cgrp)->classid = (u32) value;
f4009237 TG	69
	70	cgroup_unlock();
	71
	72	return 0;
	73	}
	74
	75	static struct cftype ss_files[] = {
	76	{
	77	.name = "classid",
	78	.read_u64 = read_classid,
	79	.write_u64 = write_classid,
	80	},
	81	};
	82
	83	static int cgrp_populate(struct cgroup_subsys ss, struct cgroup cgrp)
	84	{
	85	return cgroup_add_files(cgrp, ss, ss_files, ARRAY_SIZE(ss_files));
	86	}
	87
	88	struct cgroup_subsys net_cls_subsys = {
	89	.name = "net_cls",
	90	.create = cgrp_create,
	91	.destroy = cgrp_destroy,
	92	.populate = cgrp_populate,
	93	.subsys_id = net_cls_subsys_id,
	94	};
	95
	96	struct cls_cgroup_head
	97	{
	98	u32 handle;
	99	struct tcf_exts exts;
	100	struct tcf_ematch_tree ematches;
	101	};
	102
	103	static int cls_cgroup_classify(struct sk_buff skb, struct tcf_proto tp,
	104	struct tcf_result *res)
	105	{
	106	struct cls_cgroup_head *head = tp->root;
e65fcfd6	107	u32 classid;
f4009237 TG	108
	109	/*
	110	* Due to the nature of the classifier it is required to ignore all
	111	* packets originating from softirq context as accessing `current'
	112	* would lead to false results.
	113	*
	114	* This test assumes that all callers of dev_queue_xmit() explicitely
	115	* disable bh. Knowing this, it is possible to detect softirq based
	116	* calls by looking at the number of nested bh disable calls because
	117	* softirqs always disables bh.
	118	*/
	119	if (softirq_count() != SOFTIRQ_OFFSET)
	120	return -1;
	121
	122	rcu_read_lock();
e65fcfd6	123	classid = task_cls_state(current)->classid;
f4009237 TG	124	rcu_read_unlock();
f4009237 TG	125
e65fcfd6 PM	126	if (!classid)
	127	return -1;
	128
	129	if (!tcf_em_tree_match(skb, &head->ematches, NULL))
	130	return -1;
	131
	132	res->classid = classid;
	133	res->class = 0;
	134	return tcf_exts_exec(skb, &head->exts, res);
f4009237 TG	135	}
	136
	137	static unsigned long cls_cgroup_get(struct tcf_proto *tp, u32 handle)
	138	{
	139	return 0UL;
	140	}
	141
	142	static void cls_cgroup_put(struct tcf_proto *tp, unsigned long f)
	143	{
	144	}
	145
	146	static int cls_cgroup_init(struct tcf_proto *tp)
	147	{
	148	return 0;
	149	}
	150
	151	static const struct tcf_ext_map cgroup_ext_map = {
	152	.action = TCA_CGROUP_ACT,
	153	.police = TCA_CGROUP_POLICE,
	154	};
	155
	156	static const struct nla_policy cgroup_policy[TCA_CGROUP_MAX + 1] = {
	157	[TCA_CGROUP_EMATCHES] = { .type = NLA_NESTED },
	158	};
	159
	160	static int cls_cgroup_change(struct tcf_proto *tp, unsigned long base,
	161	u32 handle, struct nlattr **tca,
	162	unsigned long *arg)
	163	{
	164	struct nlattr *tb[TCA_CGROUP_MAX+1];
	165	struct cls_cgroup_head *head = tp->root;
	166	struct tcf_ematch_tree t;
	167	struct tcf_exts e;
	168	int err;
	169
52ea3a56 MU	170	if (!tca[TCA_OPTIONS])
	171	return -EINVAL;
	172
f4009237 TG	173	if (head == NULL) {
	174	if (!handle)
	175	return -EINVAL;
	176
	177	head = kzalloc(sizeof(*head), GFP_KERNEL);
	178	if (head == NULL)
	179	return -ENOBUFS;
	180
	181	head->handle = handle;
	182
	183	tcf_tree_lock(tp);
	184	tp->root = head;
	185	tcf_tree_unlock(tp);
	186	}
	187
	188	if (handle != head->handle)
	189	return -ENOENT;
	190
	191	err = nla_parse_nested(tb, TCA_CGROUP_MAX, tca[TCA_OPTIONS],
	192	cgroup_policy);
	193	if (err < 0)
	194	return err;
	195
	196	err = tcf_exts_validate(tp, tb, tca[TCA_RATE], &e, &cgroup_ext_map);
	197	if (err < 0)
	198	return err;
	199
	200	err = tcf_em_tree_validate(tp, tb[TCA_CGROUP_EMATCHES], &t);
	201	if (err < 0)
	202	return err;
	203
	204	tcf_exts_change(tp, &head->exts, &e);
	205	tcf_em_tree_change(tp, &head->ematches, &t);
	206
	207	return 0;
	208	}
	209
	210	static void cls_cgroup_destroy(struct tcf_proto *tp)
	211	{
47a1a1d4	212	struct cls_cgroup_head *head = tp->root;
f4009237 TG	213
	214	if (head) {
	215	tcf_exts_destroy(tp, &head->exts);
	216	tcf_em_tree_destroy(tp, &head->ematches);
	217	kfree(head);
	218	}
	219	}
	220
	221	static int cls_cgroup_delete(struct tcf_proto *tp, unsigned long arg)
	222	{
	223	return -EOPNOTSUPP;
	224	}
	225
	226	static void cls_cgroup_walk(struct tcf_proto tp, struct tcf_walker arg)
	227	{
	228	struct cls_cgroup_head *head = tp->root;
	229
	230	if (arg->count < arg->skip)
	231	goto skip;
	232
	233	if (arg->fn(tp, (unsigned long) head, arg) < 0) {
	234	arg->stop = 1;
	235	return;
	236	}
	237	skip:
	238	arg->count++;
	239	}
	240
	241	static int cls_cgroup_dump(struct tcf_proto *tp, unsigned long fh,
	242	struct sk_buff skb, struct tcmsg t)
	243	{
	244	struct cls_cgroup_head *head = tp->root;
	245	unsigned char *b = skb_tail_pointer(skb);
	246	struct nlattr *nest;
	247
	248	t->tcm_handle = head->handle;
	249
	250	nest = nla_nest_start(skb, TCA_OPTIONS);
	251	if (nest == NULL)
	252	goto nla_put_failure;
	253
	254	if (tcf_exts_dump(skb, &head->exts, &cgroup_ext_map) < 0 \|\|
	255	tcf_em_tree_dump(skb, &head->ematches, TCA_CGROUP_EMATCHES) < 0)
	256	goto nla_put_failure;
	257
	258	nla_nest_end(skb, nest);
	259
	260	if (tcf_exts_dump_stats(skb, &head->exts, &cgroup_ext_map) < 0)
	261	goto nla_put_failure;
	262
	263	return skb->len;
	264
	265	nla_put_failure:
	266	nlmsg_trim(skb, b);
	267	return -1;
	268	}
	269
	270	static struct tcf_proto_ops cls_cgroup_ops __read_mostly = {
	271	.kind = "cgroup",
	272	.init = cls_cgroup_init,
	273	.change = cls_cgroup_change,
	274	.classify = cls_cgroup_classify,
	275	.destroy = cls_cgroup_destroy,
	276	.get = cls_cgroup_get,
277	.put = cls_cgroup_put,
278	.delete = cls_cgroup_delete,
279	.walk = cls_cgroup_walk,
280	.dump = cls_cgroup_dump,
281	.owner = THIS_MODULE,
282	};
283
284	static int __init init_cgroup_cls(void)
285	{
286	return register_tcf_proto_ops(&cls_cgroup_ops);
287	}
288
289	static void __exit exit_cgroup_cls(void)
290	{
291	unregister_tcf_proto_ops(&cls_cgroup_ops);
292	}
293
294	module_init(init_cgroup_cls);
295	module_exit(exit_cgroup_cls);
296	MODULE_LICENSE("GPL");