[mirror_ubuntu-artful-kernel.git] / block / blk-cgroup.c

/*
 * Common Block IO controller cgroup interface
 *
 * Based on ideas and code from CFQ, CFS and BFQ:
 * Copyright (C) 2003 Jens Axboe <axboe@kernel.dk>
 *
 * Copyright (C) 2008 Fabio Checconi <fabio@gandalf.sssup.it>
 *		      Paolo Valente <paolo.valente@unimore.it>
 *
 * Copyright (C) 2009 Vivek Goyal <vgoyal@redhat.com>
 * 	              Nauman Rafique <nauman@google.com>
 */
#include <linux/ioprio.h>
#include "blk-cgroup.h"

extern void cfq_unlink_blkio_group(void *, struct blkio_group *);

struct blkio_cgroup blkio_root_cgroup = { .weight = 2*BLKIO_WEIGHT_DEFAULT };

struct blkio_cgroup *cgroup_to_blkio_cgroup(struct cgroup *cgroup)
{
	return container_of(cgroup_subsys_state(cgroup, blkio_subsys_id),
			    struct blkio_cgroup, css);
}

void blkiocg_add_blkio_group(struct blkio_cgroup *blkcg,
				struct blkio_group *blkg, void *key)
{
	unsigned long flags;

	spin_lock_irqsave(&blkcg->lock, flags);
	rcu_assign_pointer(blkg->key, key);
	blkg->blkcg_id = css_id(&blkcg->css);
	hlist_add_head_rcu(&blkg->blkcg_node, &blkcg->blkg_list);
	spin_unlock_irqrestore(&blkcg->lock, flags);
#ifdef CONFIG_DEBUG_BLK_CGROUP
	/* Need to take css reference ? */
	cgroup_path(blkcg->css.cgroup, blkg->path, sizeof(blkg->path));
#endif
}

static void __blkiocg_del_blkio_group(struct blkio_group *blkg)
{
	hlist_del_init_rcu(&blkg->blkcg_node);
	blkg->blkcg_id = 0;
}

/*
 * returns 0 if blkio_group was still on cgroup list. Otherwise returns 1
 * indicating that blk_group was unhashed by the time we got to it.
 */
int blkiocg_del_blkio_group(struct blkio_group *blkg)
{
	struct blkio_cgroup *blkcg;
	unsigned long flags;
	struct cgroup_subsys_state *css;
	int ret = 1;

	rcu_read_lock();
	css = css_lookup(&blkio_subsys, blkg->blkcg_id);
	if (!css)
		goto out;

	blkcg = container_of(css, struct blkio_cgroup, css);
	spin_lock_irqsave(&blkcg->lock, flags);
	if (!hlist_unhashed(&blkg->blkcg_node)) {
		__blkiocg_del_blkio_group(blkg);
		ret = 0;
	}
	spin_unlock_irqrestore(&blkcg->lock, flags);
out:
	rcu_read_unlock();
	return ret;
}

/* called under rcu_read_lock(). */
struct blkio_group *blkiocg_lookup_group(struct blkio_cgroup *blkcg, void *key)
{
	struct blkio_group *blkg;
	struct hlist_node *n;
	void *__key;

	hlist_for_each_entry_rcu(blkg, n, &blkcg->blkg_list, blkcg_node) {
		__key = blkg->key;
		if (__key == key)
			return blkg;
	}

	return NULL;
}

#define SHOW_FUNCTION(__VAR)						\
static u64 blkiocg_##__VAR##_read(struct cgroup *cgroup,		\
				       struct cftype *cftype)		\
{									\
	struct blkio_cgroup *blkcg;					\
									\
	blkcg = cgroup_to_blkio_cgroup(cgroup);				\
	return (u64)blkcg->__VAR;					\
}

SHOW_FUNCTION(weight);
#undef SHOW_FUNCTION

static int
blkiocg_weight_write(struct cgroup *cgroup, struct cftype *cftype, u64 val)
{
	struct blkio_cgroup *blkcg;

	if (val < BLKIO_WEIGHT_MIN || val > BLKIO_WEIGHT_MAX)
		return -EINVAL;

	blkcg = cgroup_to_blkio_cgroup(cgroup);
	blkcg->weight = (unsigned int)val;
	return 0;
}

struct cftype blkio_files[] = {
	{
		.name = "weight",
		.read_u64 = blkiocg_weight_read,
		.write_u64 = blkiocg_weight_write,
	},
};

static int blkiocg_populate(struct cgroup_subsys *subsys, struct cgroup *cgroup)
{
	return cgroup_add_files(cgroup, subsys, blkio_files,
				ARRAY_SIZE(blkio_files));
}

static void blkiocg_destroy(struct cgroup_subsys *subsys, struct cgroup *cgroup)
{
	struct blkio_cgroup *blkcg = cgroup_to_blkio_cgroup(cgroup);
	unsigned long flags;
	struct blkio_group *blkg;
	void *key;

	rcu_read_lock();
remove_entry:
	spin_lock_irqsave(&blkcg->lock, flags);

	if (hlist_empty(&blkcg->blkg_list)) {
		spin_unlock_irqrestore(&blkcg->lock, flags);
		goto done;
	}

	blkg = hlist_entry(blkcg->blkg_list.first, struct blkio_group,
				blkcg_node);
	key = rcu_dereference(blkg->key);
	__blkiocg_del_blkio_group(blkg);

	spin_unlock_irqrestore(&blkcg->lock, flags);

	/*
	 * This blkio_group is being unlinked as associated cgroup is going
	 * away. Let all the IO controlling policies know about this event.
	 *
	 * Currently this is static call to one io controlling policy. Once
	 * we have more policies in place, we need some dynamic registration
	 * of callback function.
	 */
	cfq_unlink_blkio_group(key, blkg);
	goto remove_entry;
done:
	free_css_id(&blkio_subsys, &blkcg->css);
	rcu_read_unlock();
	kfree(blkcg);
}

static struct cgroup_subsys_state *
blkiocg_create(struct cgroup_subsys *subsys, struct cgroup *cgroup)
{
	struct blkio_cgroup *blkcg, *parent_blkcg;

	if (!cgroup->parent) {
		blkcg = &blkio_root_cgroup;
		goto done;
	}

	/* Currently we do not support hierarchy deeper than two level (0,1) */
	parent_blkcg = cgroup_to_blkio_cgroup(cgroup->parent);
	if (css_depth(&parent_blkcg->css) > 0)
		return ERR_PTR(-EINVAL);

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

	blkcg->weight = BLKIO_WEIGHT_DEFAULT;
done:
	spin_lock_init(&blkcg->lock);
	INIT_HLIST_HEAD(&blkcg->blkg_list);

	return &blkcg->css;
}

/*
 * We cannot support shared io contexts, as we have no mean to support
 * two tasks with the same ioc in two different groups without major rework
 * of the main cic data structures.  For now we allow a task to change
 * its cgroup only if it's the only owner of its ioc.
 */
static int blkiocg_can_attach(struct cgroup_subsys *subsys,
				struct cgroup *cgroup, struct task_struct *tsk,
				bool threadgroup)
{
	struct io_context *ioc;
	int ret = 0;

	/* task_lock() is needed to avoid races with exit_io_context() */
	task_lock(tsk);
	ioc = tsk->io_context;
	if (ioc && atomic_read(&ioc->nr_tasks) > 1)
		ret = -EINVAL;
	task_unlock(tsk);

	return ret;
}

static void blkiocg_attach(struct cgroup_subsys *subsys, struct cgroup *cgroup,
				struct cgroup *prev, struct task_struct *tsk,
				bool threadgroup)
{
	struct io_context *ioc;

	task_lock(tsk);
	ioc = tsk->io_context;
	if (ioc)
		ioc->cgroup_changed = 1;
	task_unlock(tsk);
}

struct cgroup_subsys blkio_subsys = {
	.name = "blkio",
	.create = blkiocg_create,
	.can_attach = blkiocg_can_attach,
	.attach = blkiocg_attach,
	.destroy = blkiocg_destroy,
	.populate = blkiocg_populate,
	.subsys_id = blkio_subsys_id,
	.use_id = 1,
};
Commit	Line	Data
31e4c28d VG	1	/*
	2	* Common Block IO controller cgroup interface
	3	*
	4	* Based on ideas and code from CFQ, CFS and BFQ:
	5	* Copyright (C) 2003 Jens Axboe <axboe@kernel.dk>
	6	*
	7	* Copyright (C) 2008 Fabio Checconi <fabio@gandalf.sssup.it>
	8	* Paolo Valente <paolo.valente@unimore.it>
	9	*
	10	* Copyright (C) 2009 Vivek Goyal <vgoyal@redhat.com>
	11	* Nauman Rafique <nauman@google.com>
	12	*/
	13	#include <linux/ioprio.h>
	14	#include "blk-cgroup.h"
	15
b1c35769 VG	16	extern void cfq_unlink_blkio_group(void , struct blkio_group );
b1c35769 VG	17
31e4c28d VG	18	struct blkio_cgroup blkio_root_cgroup = { .weight = 2*BLKIO_WEIGHT_DEFAULT };
	19
	20	struct blkio_cgroup cgroup_to_blkio_cgroup(struct cgroup cgroup)
	21	{
	22	return container_of(cgroup_subsys_state(cgroup, blkio_subsys_id),
	23	struct blkio_cgroup, css);
	24	}
	25
	26	void blkiocg_add_blkio_group(struct blkio_cgroup *blkcg,
	27	struct blkio_group blkg, void key)
	28	{
	29	unsigned long flags;
	30
	31	spin_lock_irqsave(&blkcg->lock, flags);
	32	rcu_assign_pointer(blkg->key, key);
b1c35769	33	blkg->blkcg_id = css_id(&blkcg->css);
31e4c28d VG	34	hlist_add_head_rcu(&blkg->blkcg_node, &blkcg->blkg_list);
31e4c28d VG	35	spin_unlock_irqrestore(&blkcg->lock, flags);
2868ef7b VG	36	#ifdef CONFIG_DEBUG_BLK_CGROUP
	37	/* Need to take css reference ? */
	38	cgroup_path(blkcg->css.cgroup, blkg->path, sizeof(blkg->path));
	39	#endif
31e4c28d VG	40	}
31e4c28d VG	41
b1c35769 VG	42	static void __blkiocg_del_blkio_group(struct blkio_group *blkg)
	43	{
	44	hlist_del_init_rcu(&blkg->blkcg_node);
	45	blkg->blkcg_id = 0;
	46	}
	47
	48	/*
	49	* returns 0 if blkio_group was still on cgroup list. Otherwise returns 1
	50	* indicating that blk_group was unhashed by the time we got to it.
	51	*/
31e4c28d VG	52	int blkiocg_del_blkio_group(struct blkio_group *blkg)
31e4c28d VG	53	{
b1c35769 VG	54	struct blkio_cgroup *blkcg;
	55	unsigned long flags;
	56	struct cgroup_subsys_state *css;
	57	int ret = 1;
	58
	59	rcu_read_lock();
	60	css = css_lookup(&blkio_subsys, blkg->blkcg_id);
	61	if (!css)
	62	goto out;
	63
	64	blkcg = container_of(css, struct blkio_cgroup, css);
	65	spin_lock_irqsave(&blkcg->lock, flags);
	66	if (!hlist_unhashed(&blkg->blkcg_node)) {
	67	__blkiocg_del_blkio_group(blkg);
	68	ret = 0;
	69	}
	70	spin_unlock_irqrestore(&blkcg->lock, flags);
	71	out:
	72	rcu_read_unlock();
	73	return ret;
31e4c28d VG	74	}
	75
	76	/* called under rcu_read_lock(). */
	77	struct blkio_group blkiocg_lookup_group(struct blkio_cgroup blkcg, void *key)
	78	{
	79	struct blkio_group *blkg;
	80	struct hlist_node *n;
	81	void *__key;
	82
	83	hlist_for_each_entry_rcu(blkg, n, &blkcg->blkg_list, blkcg_node) {
	84	__key = blkg->key;
	85	if (__key == key)
	86	return blkg;
	87	}
	88
	89	return NULL;
	90	}
	91
	92	#define SHOW_FUNCTION(__VAR) \
	93	static u64 blkiocg_##__VAR##_read(struct cgroup *cgroup, \
	94	struct cftype *cftype) \
	95	{ \
	96	struct blkio_cgroup *blkcg; \
	97	\
	98	blkcg = cgroup_to_blkio_cgroup(cgroup); \
	99	return (u64)blkcg->__VAR; \
	100	}
	101
	102	SHOW_FUNCTION(weight);
	103	#undef SHOW_FUNCTION
	104
	105	static int
	106	blkiocg_weight_write(struct cgroup cgroup, struct cftype cftype, u64 val)
	107	{
	108	struct blkio_cgroup *blkcg;
	109
	110	if (val < BLKIO_WEIGHT_MIN \|\| val > BLKIO_WEIGHT_MAX)
	111	return -EINVAL;
	112
	113	blkcg = cgroup_to_blkio_cgroup(cgroup);
	114	blkcg->weight = (unsigned int)val;
	115	return 0;
	116	}
	117
	118	struct cftype blkio_files[] = {
	119	{
	120	.name = "weight",
	121	.read_u64 = blkiocg_weight_read,
	122	.write_u64 = blkiocg_weight_write,
	123	},
	124	};
	125
	126	static int blkiocg_populate(struct cgroup_subsys subsys, struct cgroup cgroup)
	127	{
	128	return cgroup_add_files(cgroup, subsys, blkio_files,
	129	ARRAY_SIZE(blkio_files));
	130	}
	131
	132	static void blkiocg_destroy(struct cgroup_subsys subsys, struct cgroup cgroup)
	133	{
	134	struct blkio_cgroup *blkcg = cgroup_to_blkio_cgroup(cgroup);
b1c35769 VG	135	unsigned long flags;
	136	struct blkio_group *blkg;
	137	void *key;
	138
	139	rcu_read_lock();
	140	remove_entry:
	141	spin_lock_irqsave(&blkcg->lock, flags);
	142
	143	if (hlist_empty(&blkcg->blkg_list)) {
	144	spin_unlock_irqrestore(&blkcg->lock, flags);
	145	goto done;
	146	}
	147
	148	blkg = hlist_entry(blkcg->blkg_list.first, struct blkio_group,
	149	blkcg_node);
	150	key = rcu_dereference(blkg->key);
	151	__blkiocg_del_blkio_group(blkg);
31e4c28d	152
b1c35769 VG	153	spin_unlock_irqrestore(&blkcg->lock, flags);
	154
	155	/*
	156	* This blkio_group is being unlinked as associated cgroup is going
	157	* away. Let all the IO controlling policies know about this event.
	158	*
	159	* Currently this is static call to one io controlling policy. Once
	160	* we have more policies in place, we need some dynamic registration
	161	* of callback function.
	162	*/
	163	cfq_unlink_blkio_group(key, blkg);
	164	goto remove_entry;
	165	done:
31e4c28d	166	free_css_id(&blkio_subsys, &blkcg->css);
b1c35769	167	rcu_read_unlock();
31e4c28d VG	168	kfree(blkcg);
	169	}
	170
	171	static struct cgroup_subsys_state *
	172	blkiocg_create(struct cgroup_subsys subsys, struct cgroup cgroup)
	173	{
	174	struct blkio_cgroup blkcg, parent_blkcg;
	175
	176	if (!cgroup->parent) {
	177	blkcg = &blkio_root_cgroup;
	178	goto done;
	179	}
	180
	181	/* Currently we do not support hierarchy deeper than two level (0,1) */
	182	parent_blkcg = cgroup_to_blkio_cgroup(cgroup->parent);
	183	if (css_depth(&parent_blkcg->css) > 0)
	184	return ERR_PTR(-EINVAL);
	185
	186	blkcg = kzalloc(sizeof(*blkcg), GFP_KERNEL);
	187	if (!blkcg)
	188	return ERR_PTR(-ENOMEM);
	189
	190	blkcg->weight = BLKIO_WEIGHT_DEFAULT;
	191	done:
	192	spin_lock_init(&blkcg->lock);
	193	INIT_HLIST_HEAD(&blkcg->blkg_list);
	194
	195	return &blkcg->css;
	196	}
	197
	198	/*
	199	* We cannot support shared io contexts, as we have no mean to support
	200	* two tasks with the same ioc in two different groups without major rework
	201	* of the main cic data structures. For now we allow a task to change
	202	* its cgroup only if it's the only owner of its ioc.
	203	*/
	204	static int blkiocg_can_attach(struct cgroup_subsys *subsys,
	205	struct cgroup cgroup, struct task_struct tsk,
	206	bool threadgroup)
	207	{
	208	struct io_context *ioc;
	209	int ret = 0;
	210
	211	/* task_lock() is needed to avoid races with exit_io_context() */
	212	task_lock(tsk);
	213	ioc = tsk->io_context;
	214	if (ioc && atomic_read(&ioc->nr_tasks) > 1)
	215	ret = -EINVAL;
	216	task_unlock(tsk);
	217
	218	return ret;
	219	}
	220
	221	static void blkiocg_attach(struct cgroup_subsys subsys, struct cgroup cgroup,
	222	struct cgroup prev, struct task_struct tsk,
	223	bool threadgroup)
	224	{
	225	struct io_context *ioc;
	226
	227	task_lock(tsk);
	228	ioc = tsk->io_context;
	229	if (ioc)
	230	ioc->cgroup_changed = 1;
	231	task_unlock(tsk);
232	}
233
234	struct cgroup_subsys blkio_subsys = {
235	.name = "blkio",
236	.create = blkiocg_create,
237	.can_attach = blkiocg_can_attach,
238	.attach = blkiocg_attach,
239	.destroy = blkiocg_destroy,
240	.populate = blkiocg_populate,
241	.subsys_id = blkio_subsys_id,
242	.use_id = 1,
243	};