[mirror_ubuntu-zesty-kernel.git] / block / blk-cgroup.h

#ifndef _BLK_CGROUP_H
#define _BLK_CGROUP_H
/*
 * 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/cgroup.h>
#include <linux/u64_stats_sync.h>

enum blkio_policy_id {
	BLKIO_POLICY_PROP = 0,		/* Proportional Bandwidth division */
	BLKIO_POLICY_THROTL,		/* Throttling */

	BLKIO_NR_POLICIES,
};

/* Max limits for throttle policy */
#define THROTL_IOPS_MAX		UINT_MAX

#ifdef CONFIG_BLK_CGROUP

/* cft->private [un]packing for stat printing */
#define BLKCG_STAT_PRIV(pol, off)	(((unsigned)(pol) << 16) | (off))
#define BLKCG_STAT_POL(prv)		((unsigned)(prv) >> 16)
#define BLKCG_STAT_OFF(prv)		((unsigned)(prv) & 0xffff)

enum blkg_rwstat_type {
	BLKG_RWSTAT_READ,
	BLKG_RWSTAT_WRITE,
	BLKG_RWSTAT_SYNC,
	BLKG_RWSTAT_ASYNC,

	BLKG_RWSTAT_NR,
	BLKG_RWSTAT_TOTAL = BLKG_RWSTAT_NR,
};

/* blkg state flags */
enum blkg_state_flags {
	BLKG_waiting = 0,
	BLKG_idling,
	BLKG_empty,
};

struct blkio_cgroup {
	struct cgroup_subsys_state css;
	unsigned int weight;
	spinlock_t lock;
	struct hlist_head blkg_list;

	/* for policies to test whether associated blkcg has changed */
	uint64_t id;
};

struct blkg_stat {
	struct u64_stats_sync		syncp;
	uint64_t			cnt;
};

struct blkg_rwstat {
	struct u64_stats_sync		syncp;
	uint64_t			cnt[BLKG_RWSTAT_NR];
};

struct blkio_group_stats {
	/* number of ios merged */
	struct blkg_rwstat		merged;
	/* total time spent on device in ns, may not be accurate w/ queueing */
	struct blkg_rwstat		service_time;
	/* total time spent waiting in scheduler queue in ns */
	struct blkg_rwstat		wait_time;
	/* number of IOs queued up */
	struct blkg_rwstat		queued;
	/* total disk time and nr sectors dispatched by this group */
	struct blkg_stat		time;
#ifdef CONFIG_DEBUG_BLK_CGROUP
	/* time not charged to this cgroup */
	struct blkg_stat		unaccounted_time;
	/* sum of number of ios queued across all samples */
	struct blkg_stat		avg_queue_size_sum;
	/* count of samples taken for average */
	struct blkg_stat		avg_queue_size_samples;
	/* how many times this group has been removed from service tree */
	struct blkg_stat		dequeue;
	/* total time spent waiting for it to be assigned a timeslice. */
	struct blkg_stat		group_wait_time;
	/* time spent idling for this blkio_group */
	struct blkg_stat		idle_time;
	/* total time with empty current active q with other requests queued */
	struct blkg_stat		empty_time;
	/* fields after this shouldn't be cleared on stat reset */
	uint64_t			start_group_wait_time;
	uint64_t			start_idle_time;
	uint64_t			start_empty_time;
	uint16_t			flags;
#endif
};

/* Per cpu blkio group stats */
struct blkio_group_stats_cpu {
	/* total bytes transferred */
	struct blkg_rwstat		service_bytes;
	/* total IOs serviced, post merge */
	struct blkg_rwstat		serviced;
	/* total sectors transferred */
	struct blkg_stat		sectors;
};

struct blkio_group_conf {
	unsigned int weight;
	u64 iops[2];
	u64 bps[2];
};

/* per-blkg per-policy data */
struct blkg_policy_data {
	/* the blkg this per-policy data belongs to */
	struct blkio_group *blkg;

	/* Configuration */
	struct blkio_group_conf conf;

	struct blkio_group_stats stats;
	/* Per cpu stats pointer */
	struct blkio_group_stats_cpu __percpu *stats_cpu;

	/* pol->pdata_size bytes of private data used by policy impl */
	char pdata[] __aligned(__alignof__(unsigned long long));
};

struct blkio_group {
	/* Pointer to the associated request_queue */
	struct request_queue *q;
	struct list_head q_node;
	struct hlist_node blkcg_node;
	struct blkio_cgroup *blkcg;
	/* Store cgroup path */
	char path[128];
	/* reference count */
	int refcnt;

	struct blkg_policy_data *pd[BLKIO_NR_POLICIES];

	/* List of blkg waiting for per cpu stats memory to be allocated */
	struct list_head alloc_node;
	struct rcu_head rcu_head;
};

typedef void (blkio_init_group_fn)(struct blkio_group *blkg);
typedef void (blkio_update_group_weight_fn)(struct request_queue *q,
			struct blkio_group *blkg, unsigned int weight);
typedef void (blkio_update_group_read_bps_fn)(struct request_queue *q,
			struct blkio_group *blkg, u64 read_bps);
typedef void (blkio_update_group_write_bps_fn)(struct request_queue *q,
			struct blkio_group *blkg, u64 write_bps);
typedef void (blkio_update_group_read_iops_fn)(struct request_queue *q,
			struct blkio_group *blkg, unsigned int read_iops);
typedef void (blkio_update_group_write_iops_fn)(struct request_queue *q,
			struct blkio_group *blkg, unsigned int write_iops);

struct blkio_policy_ops {
	blkio_init_group_fn *blkio_init_group_fn;
	blkio_update_group_weight_fn *blkio_update_group_weight_fn;
	blkio_update_group_read_bps_fn *blkio_update_group_read_bps_fn;
	blkio_update_group_write_bps_fn *blkio_update_group_write_bps_fn;
	blkio_update_group_read_iops_fn *blkio_update_group_read_iops_fn;
	blkio_update_group_write_iops_fn *blkio_update_group_write_iops_fn;
};

struct blkio_policy_type {
	struct list_head list;
	struct blkio_policy_ops ops;
	enum blkio_policy_id plid;
	size_t pdata_size;		/* policy specific private data size */
};

extern int blkcg_init_queue(struct request_queue *q);
extern void blkcg_drain_queue(struct request_queue *q);
extern void blkcg_exit_queue(struct request_queue *q);

/* Blkio controller policy registration */
extern void blkio_policy_register(struct blkio_policy_type *);
extern void blkio_policy_unregister(struct blkio_policy_type *);
extern void blkg_destroy_all(struct request_queue *q, bool destroy_root);
extern void update_root_blkg_pd(struct request_queue *q,
				enum blkio_policy_id plid);

/**
 * blkg_to_pdata - get policy private data
 * @blkg: blkg of interest
 * @pol: policy of interest
 *
 * Return pointer to private data associated with the @blkg-@pol pair.
 */
static inline void *blkg_to_pdata(struct blkio_group *blkg,
			      struct blkio_policy_type *pol)
{
	return blkg ? blkg->pd[pol->plid]->pdata : NULL;
}

/**
 * pdata_to_blkg - get blkg associated with policy private data
 * @pdata: policy private data of interest
 *
 * @pdata is policy private data.  Determine the blkg it's associated with.
 */
static inline struct blkio_group *pdata_to_blkg(void *pdata)
{
	if (pdata) {
		struct blkg_policy_data *pd =
			container_of(pdata, struct blkg_policy_data, pdata);
		return pd->blkg;
	}
	return NULL;
}

static inline char *blkg_path(struct blkio_group *blkg)
{
	return blkg->path;
}

/**
 * blkg_get - get a blkg reference
 * @blkg: blkg to get
 *
 * The caller should be holding queue_lock and an existing reference.
 */
static inline void blkg_get(struct blkio_group *blkg)
{
	lockdep_assert_held(blkg->q->queue_lock);
	WARN_ON_ONCE(!blkg->refcnt);
	blkg->refcnt++;
}

void __blkg_release(struct blkio_group *blkg);

/**
 * blkg_put - put a blkg reference
 * @blkg: blkg to put
 *
 * The caller should be holding queue_lock.
 */
static inline void blkg_put(struct blkio_group *blkg)
{
	lockdep_assert_held(blkg->q->queue_lock);
	WARN_ON_ONCE(blkg->refcnt <= 0);
	if (!--blkg->refcnt)
		__blkg_release(blkg);
}

/**
 * blkg_stat_add - add a value to a blkg_stat
 * @stat: target blkg_stat
 * @val: value to add
 *
 * Add @val to @stat.  The caller is responsible for synchronizing calls to
 * this function.
 */
static inline void blkg_stat_add(struct blkg_stat *stat, uint64_t val)
{
	u64_stats_update_begin(&stat->syncp);
	stat->cnt += val;
	u64_stats_update_end(&stat->syncp);
}

/**
 * blkg_stat_read - read the current value of a blkg_stat
 * @stat: blkg_stat to read
 *
 * Read the current value of @stat.  This function can be called without
 * synchroniztion and takes care of u64 atomicity.
 */
static inline uint64_t blkg_stat_read(struct blkg_stat *stat)
{
	unsigned int start;
	uint64_t v;

	do {
		start = u64_stats_fetch_begin(&stat->syncp);
		v = stat->cnt;
	} while (u64_stats_fetch_retry(&stat->syncp, start));

	return v;
}

/**
 * blkg_stat_reset - reset a blkg_stat
 * @stat: blkg_stat to reset
 */
static inline void blkg_stat_reset(struct blkg_stat *stat)
{
	stat->cnt = 0;
}

/**
 * blkg_rwstat_add - add a value to a blkg_rwstat
 * @rwstat: target blkg_rwstat
 * @rw: mask of REQ_{WRITE|SYNC}
 * @val: value to add
 *
 * Add @val to @rwstat.  The counters are chosen according to @rw.  The
 * caller is responsible for synchronizing calls to this function.
 */
static inline void blkg_rwstat_add(struct blkg_rwstat *rwstat,
				   int rw, uint64_t val)
{
	u64_stats_update_begin(&rwstat->syncp);

	if (rw & REQ_WRITE)
		rwstat->cnt[BLKG_RWSTAT_WRITE] += val;
	else
		rwstat->cnt[BLKG_RWSTAT_READ] += val;
	if (rw & REQ_SYNC)
		rwstat->cnt[BLKG_RWSTAT_SYNC] += val;
	else
		rwstat->cnt[BLKG_RWSTAT_ASYNC] += val;

	u64_stats_update_end(&rwstat->syncp);
}

/**
 * blkg_rwstat_read - read the current values of a blkg_rwstat
 * @rwstat: blkg_rwstat to read
 *
 * Read the current snapshot of @rwstat and return it as the return value.
 * This function can be called without synchronization and takes care of
 * u64 atomicity.
 */
static struct blkg_rwstat blkg_rwstat_read(struct blkg_rwstat *rwstat)
{
	unsigned int start;
	struct blkg_rwstat tmp;

	do {
		start = u64_stats_fetch_begin(&rwstat->syncp);
		tmp = *rwstat;
	} while (u64_stats_fetch_retry(&rwstat->syncp, start));

	return tmp;
}

/**
 * blkg_rwstat_sum - read the total count of a blkg_rwstat
 * @rwstat: blkg_rwstat to read
 *
 * Return the total count of @rwstat regardless of the IO direction.  This
 * function can be called without synchronization and takes care of u64
 * atomicity.
 */
static inline uint64_t blkg_rwstat_sum(struct blkg_rwstat *rwstat)
{
	struct blkg_rwstat tmp = blkg_rwstat_read(rwstat);

	return tmp.cnt[BLKG_RWSTAT_READ] + tmp.cnt[BLKG_RWSTAT_WRITE];
}

/**
 * blkg_rwstat_reset - reset a blkg_rwstat
 * @rwstat: blkg_rwstat to reset
 */
static inline void blkg_rwstat_reset(struct blkg_rwstat *rwstat)
{
	memset(rwstat->cnt, 0, sizeof(rwstat->cnt));
}

#else

struct blkio_group {
};

struct blkio_policy_type {
};

static inline int blkcg_init_queue(struct request_queue *q) { return 0; }
static inline void blkcg_drain_queue(struct request_queue *q) { }
static inline void blkcg_exit_queue(struct request_queue *q) { }
static inline void blkio_policy_register(struct blkio_policy_type *blkiop) { }
static inline void blkio_policy_unregister(struct blkio_policy_type *blkiop) { }
static inline void blkg_destroy_all(struct request_queue *q,
				    bool destory_root) { }
static inline void update_root_blkg_pd(struct request_queue *q,
				       enum blkio_policy_id plid) { }

static inline void *blkg_to_pdata(struct blkio_group *blkg,
				struct blkio_policy_type *pol) { return NULL; }
static inline struct blkio_group *pdata_to_blkg(void *pdata,
				struct blkio_policy_type *pol) { return NULL; }
static inline char *blkg_path(struct blkio_group *blkg) { return NULL; }
static inline void blkg_get(struct blkio_group *blkg) { }
static inline void blkg_put(struct blkio_group *blkg) { }

#endif

#define BLKIO_WEIGHT_MIN	10
#define BLKIO_WEIGHT_MAX	1000
#define BLKIO_WEIGHT_DEFAULT	500

#ifdef CONFIG_DEBUG_BLK_CGROUP
void blkiocg_update_avg_queue_size_stats(struct blkio_group *blkg,
					 struct blkio_policy_type *pol);
void blkiocg_update_dequeue_stats(struct blkio_group *blkg,
				  struct blkio_policy_type *pol,
				  unsigned long dequeue);
void blkiocg_update_set_idle_time_stats(struct blkio_group *blkg,
					struct blkio_policy_type *pol);
void blkiocg_update_idle_time_stats(struct blkio_group *blkg,
				    struct blkio_policy_type *pol);
void blkiocg_set_start_empty_time(struct blkio_group *blkg,
				  struct blkio_policy_type *pol);

#define BLKG_FLAG_FNS(name)						\
static inline void blkio_mark_blkg_##name(				\
		struct blkio_group_stats *stats)			\
{									\
	stats->flags |= (1 << BLKG_##name);				\
}									\
static inline void blkio_clear_blkg_##name(				\
		struct blkio_group_stats *stats)			\
{									\
	stats->flags &= ~(1 << BLKG_##name);				\
}									\
static inline int blkio_blkg_##name(struct blkio_group_stats *stats)	\
{									\
	return (stats->flags & (1 << BLKG_##name)) != 0;		\
}									\

BLKG_FLAG_FNS(waiting)
BLKG_FLAG_FNS(idling)
BLKG_FLAG_FNS(empty)
#undef BLKG_FLAG_FNS
#else
static inline void blkiocg_update_avg_queue_size_stats(struct blkio_group *blkg,
			struct blkio_policy_type *pol) { }
static inline void blkiocg_update_dequeue_stats(struct blkio_group *blkg,
			struct blkio_policy_type *pol, unsigned long dequeue) { }
static inline void blkiocg_update_set_idle_time_stats(struct blkio_group *blkg,
			struct blkio_policy_type *pol) { }
static inline void blkiocg_update_idle_time_stats(struct blkio_group *blkg,
			struct blkio_policy_type *pol) { }
static inline void blkiocg_set_start_empty_time(struct blkio_group *blkg,
			struct blkio_policy_type *pol) { }
#endif

#ifdef CONFIG_BLK_CGROUP
extern struct blkio_cgroup blkio_root_cgroup;
extern struct blkio_cgroup *cgroup_to_blkio_cgroup(struct cgroup *cgroup);
extern struct blkio_cgroup *bio_blkio_cgroup(struct bio *bio);
extern struct blkio_group *blkg_lookup(struct blkio_cgroup *blkcg,
				       struct request_queue *q);
struct blkio_group *blkg_lookup_create(struct blkio_cgroup *blkcg,
				       struct request_queue *q,
				       bool for_root);
void blkiocg_update_timeslice_used(struct blkio_group *blkg,
				   struct blkio_policy_type *pol,
				   unsigned long time,
				   unsigned long unaccounted_time);
void blkiocg_update_dispatch_stats(struct blkio_group *blkg,
				   struct blkio_policy_type *pol,
				   uint64_t bytes, bool direction, bool sync);
void blkiocg_update_completion_stats(struct blkio_group *blkg,
				     struct blkio_policy_type *pol,
				     uint64_t start_time,
				     uint64_t io_start_time, bool direction,
				     bool sync);
void blkiocg_update_io_merged_stats(struct blkio_group *blkg,
				    struct blkio_policy_type *pol,
				    bool direction, bool sync);
void blkiocg_update_io_add_stats(struct blkio_group *blkg,
				 struct blkio_policy_type *pol,
				 struct blkio_group *curr_blkg, bool direction,
				 bool sync);
void blkiocg_update_io_remove_stats(struct blkio_group *blkg,
				    struct blkio_policy_type *pol,
				    bool direction, bool sync);
#else
struct cgroup;
static inline struct blkio_cgroup *
cgroup_to_blkio_cgroup(struct cgroup *cgroup) { return NULL; }
static inline struct blkio_cgroup *
bio_blkio_cgroup(struct bio *bio) { return NULL; }

static inline struct blkio_group *blkg_lookup(struct blkio_cgroup *blkcg,
					      void *key) { return NULL; }
static inline void blkiocg_update_timeslice_used(struct blkio_group *blkg,
			struct blkio_policy_type *pol, unsigned long time,
			unsigned long unaccounted_time) { }
static inline void blkiocg_update_dispatch_stats(struct blkio_group *blkg,
			struct blkio_policy_type *pol, uint64_t bytes,
			bool direction, bool sync) { }
static inline void blkiocg_update_completion_stats(struct blkio_group *blkg,
			struct blkio_policy_type *pol, uint64_t start_time,
			uint64_t io_start_time, bool direction, bool sync) { }
static inline void blkiocg_update_io_merged_stats(struct blkio_group *blkg,
			struct blkio_policy_type *pol, bool direction,
			bool sync) { }
static inline void blkiocg_update_io_add_stats(struct blkio_group *blkg,
			struct blkio_policy_type *pol,
			struct blkio_group *curr_blkg, bool direction,
			bool sync) { }
static inline void blkiocg_update_io_remove_stats(struct blkio_group *blkg,
			struct blkio_policy_type *pol, bool direction,
			bool sync) { }
#endif
#endif /* _BLK_CGROUP_H */
Commit	Line	Data
31e4c28d VG	1	#ifndef _BLK_CGROUP_H
	2	#define _BLK_CGROUP_H
	3	/*
	4	* Common Block IO controller cgroup interface
	5	*
	6	* Based on ideas and code from CFQ, CFS and BFQ:
	7	* Copyright (C) 2003 Jens Axboe <axboe@kernel.dk>
	8	*
	9	* Copyright (C) 2008 Fabio Checconi <fabio@gandalf.sssup.it>
	10	* Paolo Valente <paolo.valente@unimore.it>
	11	*
	12	* Copyright (C) 2009 Vivek Goyal <vgoyal@redhat.com>
	13	* Nauman Rafique <nauman@google.com>
	14	*/
	15
	16	#include <linux/cgroup.h>
575969a0	17	#include <linux/u64_stats_sync.h>
31e4c28d	18
062a644d VG	19	enum blkio_policy_id {
062a644d VG	20	BLKIO_POLICY_PROP = 0, /* Proportional Bandwidth division */
4c9eefa1	21	BLKIO_POLICY_THROTL, /* Throttling */
035d10b2 TH	22
035d10b2 TH	23	BLKIO_NR_POLICIES,
062a644d VG	24	};
062a644d VG	25
9355aede VG	26	/* Max limits for throttle policy */
	27	#define THROTL_IOPS_MAX UINT_MAX
	28
32e380ae	29	#ifdef CONFIG_BLK_CGROUP
2f5ea477	30
d3d32e69 TH	31	/* cft->private [un]packing for stat printing */
	32	#define BLKCG_STAT_PRIV(pol, off) (((unsigned)(pol) << 16) \| (off))
	33	#define BLKCG_STAT_POL(prv) ((unsigned)(prv) >> 16)
	34	#define BLKCG_STAT_OFF(prv) ((unsigned)(prv) & 0xffff)
2aa4a152	35
edcb0722 TH	36	enum blkg_rwstat_type {
	37	BLKG_RWSTAT_READ,
	38	BLKG_RWSTAT_WRITE,
	39	BLKG_RWSTAT_SYNC,
	40	BLKG_RWSTAT_ASYNC,
	41
	42	BLKG_RWSTAT_NR,
	43	BLKG_RWSTAT_TOTAL = BLKG_RWSTAT_NR,
303a3acb DS	44	};
303a3acb DS	45
812df48d DS	46	/* blkg state flags */
	47	enum blkg_state_flags {
	48	BLKG_waiting = 0,
	49	BLKG_idling,
	50	BLKG_empty,
	51	};
	52
31e4c28d VG	53	struct blkio_cgroup {
	54	struct cgroup_subsys_state css;
	55	unsigned int weight;
	56	spinlock_t lock;
	57	struct hlist_head blkg_list;
9a9e8a26 TH	58
	59	/* for policies to test whether associated blkcg has changed */
	60	uint64_t id;
31e4c28d VG	61	};
31e4c28d VG	62
edcb0722 TH	63	struct blkg_stat {
	64	struct u64_stats_sync syncp;
	65	uint64_t cnt;
	66	};
	67
	68	struct blkg_rwstat {
	69	struct u64_stats_sync syncp;
	70	uint64_t cnt[BLKG_RWSTAT_NR];
	71	};
	72
303a3acb	73	struct blkio_group_stats {
edcb0722 TH	74	/* number of ios merged */
	75	struct blkg_rwstat merged;
	76	/* total time spent on device in ns, may not be accurate w/ queueing */
	77	struct blkg_rwstat service_time;
	78	/* total time spent waiting in scheduler queue in ns */
	79	struct blkg_rwstat wait_time;
	80	/* number of IOs queued up */
	81	struct blkg_rwstat queued;
303a3acb	82	/* total disk time and nr sectors dispatched by this group */
edcb0722	83	struct blkg_stat time;
303a3acb	84	#ifdef CONFIG_DEBUG_BLK_CGROUP
edcb0722 TH	85	/* time not charged to this cgroup */
	86	struct blkg_stat unaccounted_time;
	87	/* sum of number of ios queued across all samples */
	88	struct blkg_stat avg_queue_size_sum;
	89	/* count of samples taken for average */
	90	struct blkg_stat avg_queue_size_samples;
	91	/* how many times this group has been removed from service tree */
	92	struct blkg_stat dequeue;
	93	/* total time spent waiting for it to be assigned a timeslice. */
	94	struct blkg_stat group_wait_time;
	95	/* time spent idling for this blkio_group */
	96	struct blkg_stat idle_time;
	97	/* total time with empty current active q with other requests queued */
	98	struct blkg_stat empty_time;
997a026c	99	/* fields after this shouldn't be cleared on stat reset */
edcb0722 TH	100	uint64_t start_group_wait_time;
	101	uint64_t start_idle_time;
	102	uint64_t start_empty_time;
	103	uint16_t flags;
303a3acb DS	104	#endif
	105	};
	106
5624a4e4 VG	107	/* Per cpu blkio group stats */
5624a4e4 VG	108	struct blkio_group_stats_cpu {
edcb0722 TH	109	/* total bytes transferred */
	110	struct blkg_rwstat service_bytes;
	111	/* total IOs serviced, post merge */
	112	struct blkg_rwstat serviced;
	113	/* total sectors transferred */
	114	struct blkg_stat sectors;
5624a4e4 VG	115	};
5624a4e4 VG	116
e56da7e2 TH	117	struct blkio_group_conf {
e56da7e2 TH	118	unsigned int weight;
c4682aec	119	u64 iops[2];
e56da7e2 TH	120	u64 bps[2];
	121	};
	122
0381411e TH	123	/* per-blkg per-policy data */
	124	struct blkg_policy_data {
	125	/* the blkg this per-policy data belongs to */
	126	struct blkio_group *blkg;
	127
549d3aa8 TH	128	/* Configuration */
	129	struct blkio_group_conf conf;
	130
	131	struct blkio_group_stats stats;
	132	/* Per cpu stats pointer */
	133	struct blkio_group_stats_cpu __percpu *stats_cpu;
	134
0381411e TH	135	/* pol->pdata_size bytes of private data used by policy impl */
	136	char pdata[] __aligned(__alignof__(unsigned long long));
	137	};
	138
31e4c28d	139	struct blkio_group {
c875f4d0 TH	140	/* Pointer to the associated request_queue */
c875f4d0 TH	141	struct request_queue *q;
e8989fae	142	struct list_head q_node;
31e4c28d	143	struct hlist_node blkcg_node;
7ee9c562	144	struct blkio_cgroup *blkcg;
2868ef7b VG	145	/* Store cgroup path */
2868ef7b VG	146	char path[128];
1adaf3dd TH	147	/* reference count */
1adaf3dd TH	148	int refcnt;
22084190	149
549d3aa8	150	struct blkg_policy_data *pd[BLKIO_NR_POLICIES];
1adaf3dd	151
1cd9e039 VG	152	/* List of blkg waiting for per cpu stats memory to be allocated */
1cd9e039 VG	153	struct list_head alloc_node;
1adaf3dd	154	struct rcu_head rcu_head;
31e4c28d VG	155	};
31e4c28d VG	156
0381411e	157	typedef void (blkio_init_group_fn)(struct blkio_group *blkg);
ca32aefc	158	typedef void (blkio_update_group_weight_fn)(struct request_queue *q,
fe071437	159	struct blkio_group *blkg, unsigned int weight);
ca32aefc	160	typedef void (blkio_update_group_read_bps_fn)(struct request_queue *q,
fe071437	161	struct blkio_group *blkg, u64 read_bps);
ca32aefc	162	typedef void (blkio_update_group_write_bps_fn)(struct request_queue *q,
fe071437	163	struct blkio_group *blkg, u64 write_bps);
ca32aefc	164	typedef void (blkio_update_group_read_iops_fn)(struct request_queue *q,
fe071437	165	struct blkio_group *blkg, unsigned int read_iops);
ca32aefc	166	typedef void (blkio_update_group_write_iops_fn)(struct request_queue *q,
fe071437	167	struct blkio_group *blkg, unsigned int write_iops);
3e252066 VG	168
3e252066 VG	169	struct blkio_policy_ops {
0381411e	170	blkio_init_group_fn *blkio_init_group_fn;
3e252066	171	blkio_update_group_weight_fn *blkio_update_group_weight_fn;
4c9eefa1 VG	172	blkio_update_group_read_bps_fn *blkio_update_group_read_bps_fn;
4c9eefa1 VG	173	blkio_update_group_write_bps_fn *blkio_update_group_write_bps_fn;
7702e8f4 VG	174	blkio_update_group_read_iops_fn *blkio_update_group_read_iops_fn;
7702e8f4 VG	175	blkio_update_group_write_iops_fn *blkio_update_group_write_iops_fn;
3e252066 VG	176	};
	177
	178	struct blkio_policy_type {
	179	struct list_head list;
	180	struct blkio_policy_ops ops;
062a644d	181	enum blkio_policy_id plid;
0381411e	182	size_t pdata_size; /* policy specific private data size */
3e252066 VG	183	};
3e252066 VG	184
5efd6113 TH	185	extern int blkcg_init_queue(struct request_queue *q);
	186	extern void blkcg_drain_queue(struct request_queue *q);
	187	extern void blkcg_exit_queue(struct request_queue *q);
	188
3e252066 VG	189	/* Blkio controller policy registration */
	190	extern void blkio_policy_register(struct blkio_policy_type *);
	191	extern void blkio_policy_unregister(struct blkio_policy_type *);
e8989fae TH	192	extern void blkg_destroy_all(struct request_queue *q, bool destroy_root);
	193	extern void update_root_blkg_pd(struct request_queue *q,
	194	enum blkio_policy_id plid);
3e252066	195
0381411e TH	196	/**
	197	* blkg_to_pdata - get policy private data
	198	* @blkg: blkg of interest
	199	* @pol: policy of interest
	200	*
	201	* Return pointer to private data associated with the @blkg-@pol pair.
	202	*/
	203	static inline void blkg_to_pdata(struct blkio_group blkg,
	204	struct blkio_policy_type *pol)
	205	{
549d3aa8	206	return blkg ? blkg->pd[pol->plid]->pdata : NULL;
0381411e TH	207	}
	208
	209	/**
	210	* pdata_to_blkg - get blkg associated with policy private data
	211	* @pdata: policy private data of interest
0381411e	212	*
aaec55a0	213	* @pdata is policy private data. Determine the blkg it's associated with.
0381411e	214	*/
aaec55a0	215	static inline struct blkio_group pdata_to_blkg(void pdata)
0381411e TH	216	{
	217	if (pdata) {
	218	struct blkg_policy_data *pd =
	219	container_of(pdata, struct blkg_policy_data, pdata);
	220	return pd->blkg;
	221	}
	222	return NULL;
	223	}
	224
afc24d49 VG	225	static inline char blkg_path(struct blkio_group blkg)
	226	{
	227	return blkg->path;
	228	}
	229
1adaf3dd TH	230	/**
	231	* blkg_get - get a blkg reference
	232	* @blkg: blkg to get
	233	*
	234	* The caller should be holding queue_lock and an existing reference.
	235	*/
	236	static inline void blkg_get(struct blkio_group *blkg)
	237	{
	238	lockdep_assert_held(blkg->q->queue_lock);
	239	WARN_ON_ONCE(!blkg->refcnt);
	240	blkg->refcnt++;
	241	}
	242
	243	void __blkg_release(struct blkio_group *blkg);
	244
	245	/**
	246	* blkg_put - put a blkg reference
	247	* @blkg: blkg to put
	248	*
	249	* The caller should be holding queue_lock.
	250	*/
	251	static inline void blkg_put(struct blkio_group *blkg)
	252	{
	253	lockdep_assert_held(blkg->q->queue_lock);
	254	WARN_ON_ONCE(blkg->refcnt <= 0);
	255	if (!--blkg->refcnt)
	256	__blkg_release(blkg);
	257	}
	258
edcb0722 TH	259	/**
	260	* blkg_stat_add - add a value to a blkg_stat
	261	* @stat: target blkg_stat
	262	* @val: value to add
	263	*
	264	* Add @val to @stat. The caller is responsible for synchronizing calls to
	265	* this function.
	266	*/
	267	static inline void blkg_stat_add(struct blkg_stat *stat, uint64_t val)
	268	{
	269	u64_stats_update_begin(&stat->syncp);
	270	stat->cnt += val;
	271	u64_stats_update_end(&stat->syncp);
	272	}
	273
	274	/**
	275	* blkg_stat_read - read the current value of a blkg_stat
	276	* @stat: blkg_stat to read
	277	*
	278	* Read the current value of @stat. This function can be called without
	279	* synchroniztion and takes care of u64 atomicity.
	280	*/
	281	static inline uint64_t blkg_stat_read(struct blkg_stat *stat)
	282	{
	283	unsigned int start;
	284	uint64_t v;
	285
	286	do {
	287	start = u64_stats_fetch_begin(&stat->syncp);
	288	v = stat->cnt;
	289	} while (u64_stats_fetch_retry(&stat->syncp, start));
	290
	291	return v;
	292	}
	293
	294	/**
	295	* blkg_stat_reset - reset a blkg_stat
	296	* @stat: blkg_stat to reset
	297	*/
	298	static inline void blkg_stat_reset(struct blkg_stat *stat)
	299	{
	300	stat->cnt = 0;
	301	}
	302
	303	/**
	304	* blkg_rwstat_add - add a value to a blkg_rwstat
	305	* @rwstat: target blkg_rwstat
	306	* @rw: mask of REQ_{WRITE\|SYNC}
	307	* @val: value to add
	308	*
	309	* Add @val to @rwstat. The counters are chosen according to @rw. The
	310	* caller is responsible for synchronizing calls to this function.
	311	*/
	312	static inline void blkg_rwstat_add(struct blkg_rwstat *rwstat,
	313	int rw, uint64_t val)
	314	{
	315	u64_stats_update_begin(&rwstat->syncp);
	316
	317	if (rw & REQ_WRITE)
	318	rwstat->cnt[BLKG_RWSTAT_WRITE] += val;
	319	else
	320	rwstat->cnt[BLKG_RWSTAT_READ] += val;
	321	if (rw & REQ_SYNC)
	322	rwstat->cnt[BLKG_RWSTAT_SYNC] += val;
323	else
324	rwstat->cnt[BLKG_RWSTAT_ASYNC] += val;
325
326	u64_stats_update_end(&rwstat->syncp);
327	}
328
329	/**
330	* blkg_rwstat_read - read the current values of a blkg_rwstat
331	* @rwstat: blkg_rwstat to read
332	*
333	* Read the current snapshot of @rwstat and return it as the return value.
334	* This function can be called without synchronization and takes care of
335	* u64 atomicity.
336	*/
337	static struct blkg_rwstat blkg_rwstat_read(struct blkg_rwstat *rwstat)
338	{
339	unsigned int start;
340	struct blkg_rwstat tmp;
341
342	do {
343	start = u64_stats_fetch_begin(&rwstat->syncp);
344	tmp = *rwstat;
345	} while (u64_stats_fetch_retry(&rwstat->syncp, start));
346
347	return tmp;
348	}
349
350	/**
351	* blkg_rwstat_sum - read the total count of a blkg_rwstat
352	* @rwstat: blkg_rwstat to read
353	*
354	* Return the total count of @rwstat regardless of the IO direction. This
355	* function can be called without synchronization and takes care of u64
356	* atomicity.
357	*/
358	static inline uint64_t blkg_rwstat_sum(struct blkg_rwstat *rwstat)
359	{
360	struct blkg_rwstat tmp = blkg_rwstat_read(rwstat);
361
362	return tmp.cnt[BLKG_RWSTAT_READ] + tmp.cnt[BLKG_RWSTAT_WRITE];
363	}
364
365	/**
366	* blkg_rwstat_reset - reset a blkg_rwstat
367	* @rwstat: blkg_rwstat to reset
368	*/
369	static inline void blkg_rwstat_reset(struct blkg_rwstat *rwstat)
370	{
371	memset(rwstat->cnt, 0, sizeof(rwstat->cnt));
372	}
373
2f5ea477 JA	374	#else
	375
	376	struct blkio_group {
	377	};
	378
3e252066 VG	379	struct blkio_policy_type {
	380	};
	381
5efd6113 TH	382	static inline int blkcg_init_queue(struct request_queue *q) { return 0; }
	383	static inline void blkcg_drain_queue(struct request_queue *q) { }
	384	static inline void blkcg_exit_queue(struct request_queue *q) { }
3e252066 VG	385	static inline void blkio_policy_register(struct blkio_policy_type *blkiop) { }
3e252066 VG	386	static inline void blkio_policy_unregister(struct blkio_policy_type *blkiop) { }
03aa264a	387	static inline void blkg_destroy_all(struct request_queue *q,
03aa264a	388	bool destory_root) { }
e8989fae TH	389	static inline void update_root_blkg_pd(struct request_queue *q,
e8989fae TH	390	enum blkio_policy_id plid) { }
3e252066	391
0381411e TH	392	static inline void blkg_to_pdata(struct blkio_group blkg,
	393	struct blkio_policy_type *pol) { return NULL; }
	394	static inline struct blkio_group pdata_to_blkg(void pdata,
	395	struct blkio_policy_type *pol) { return NULL; }
afc24d49	396	static inline char blkg_path(struct blkio_group blkg) { return NULL; }
1adaf3dd TH	397	static inline void blkg_get(struct blkio_group *blkg) { }
1adaf3dd TH	398	static inline void blkg_put(struct blkio_group *blkg) { }
afc24d49	399
2f5ea477 JA	400	#endif
2f5ea477 JA	401
df457f84	402	#define BLKIO_WEIGHT_MIN 10
31e4c28d VG	403	#define BLKIO_WEIGHT_MAX 1000
	404	#define BLKIO_WEIGHT_DEFAULT 500
	405
2868ef7b	406	#ifdef CONFIG_DEBUG_BLK_CGROUP
c1768268 TH	407	void blkiocg_update_avg_queue_size_stats(struct blkio_group *blkg,
c1768268 TH	408	struct blkio_policy_type *pol);
9195291e	409	void blkiocg_update_dequeue_stats(struct blkio_group *blkg,
c1768268 TH	410	struct blkio_policy_type *pol,
	411	unsigned long dequeue);
	412	void blkiocg_update_set_idle_time_stats(struct blkio_group *blkg,
	413	struct blkio_policy_type *pol);
	414	void blkiocg_update_idle_time_stats(struct blkio_group *blkg,
	415	struct blkio_policy_type *pol);
	416	void blkiocg_set_start_empty_time(struct blkio_group *blkg,
	417	struct blkio_policy_type *pol);
812df48d DS	418
	419	#define BLKG_FLAG_FNS(name) \
	420	static inline void blkio_mark_blkg_##name( \
	421	struct blkio_group_stats *stats) \
	422	{ \
	423	stats->flags \|= (1 << BLKG_##name); \
	424	} \
	425	static inline void blkio_clear_blkg_##name( \
	426	struct blkio_group_stats *stats) \
	427	{ \
	428	stats->flags &= ~(1 << BLKG_##name); \
	429	} \
	430	static inline int blkio_blkg_##name(struct blkio_group_stats *stats) \
	431	{ \
	432	return (stats->flags & (1 << BLKG_##name)) != 0; \
	433	} \
	434
	435	BLKG_FLAG_FNS(waiting)
	436	BLKG_FLAG_FNS(idling)
	437	BLKG_FLAG_FNS(empty)
	438	#undef BLKG_FLAG_FNS
2868ef7b	439	#else
c1768268 TH	440	static inline void blkiocg_update_avg_queue_size_stats(struct blkio_group *blkg,
c1768268 TH	441	struct blkio_policy_type *pol) { }
9195291e	442	static inline void blkiocg_update_dequeue_stats(struct blkio_group *blkg,
c1768268 TH	443	struct blkio_policy_type *pol, unsigned long dequeue) { }
	444	static inline void blkiocg_update_set_idle_time_stats(struct blkio_group *blkg,
	445	struct blkio_policy_type *pol) { }
	446	static inline void blkiocg_update_idle_time_stats(struct blkio_group *blkg,
	447	struct blkio_policy_type *pol) { }
	448	static inline void blkiocg_set_start_empty_time(struct blkio_group *blkg,
	449	struct blkio_policy_type *pol) { }
2868ef7b VG	450	#endif
2868ef7b VG	451
32e380ae	452	#ifdef CONFIG_BLK_CGROUP
31e4c28d VG	453	extern struct blkio_cgroup blkio_root_cgroup;
31e4c28d VG	454	extern struct blkio_cgroup cgroup_to_blkio_cgroup(struct cgroup cgroup);
4f85cb96	455	extern struct blkio_cgroup bio_blkio_cgroup(struct bio bio);
cd1604fa	456	extern struct blkio_group blkg_lookup(struct blkio_cgroup blkcg,
e8989fae	457	struct request_queue *q);
cd1604fa TH	458	struct blkio_group blkg_lookup_create(struct blkio_cgroup blkcg,
cd1604fa TH	459	struct request_queue *q,
cd1604fa	460	bool for_root);
303a3acb	461	void blkiocg_update_timeslice_used(struct blkio_group *blkg,
c1768268 TH	462	struct blkio_policy_type *pol,
	463	unsigned long time,
	464	unsigned long unaccounted_time);
	465	void blkiocg_update_dispatch_stats(struct blkio_group *blkg,
	466	struct blkio_policy_type *pol,
	467	uint64_t bytes, bool direction, bool sync);
84c124da	468	void blkiocg_update_completion_stats(struct blkio_group *blkg,
c1768268 TH	469	struct blkio_policy_type *pol,
	470	uint64_t start_time,
	471	uint64_t io_start_time, bool direction,
	472	bool sync);
	473	void blkiocg_update_io_merged_stats(struct blkio_group *blkg,
	474	struct blkio_policy_type *pol,
	475	bool direction, bool sync);
a11cdaa7	476	void blkiocg_update_io_add_stats(struct blkio_group *blkg,
c1768268 TH	477	struct blkio_policy_type *pol,
	478	struct blkio_group *curr_blkg, bool direction,
	479	bool sync);
a11cdaa7	480	void blkiocg_update_io_remove_stats(struct blkio_group *blkg,
c1768268 TH	481	struct blkio_policy_type *pol,
c1768268 TH	482	bool direction, bool sync);
31e4c28d	483	#else
2f5ea477	484	struct cgroup;
31e4c28d VG	485	static inline struct blkio_cgroup *
31e4c28d VG	486	cgroup_to_blkio_cgroup(struct cgroup *cgroup) { return NULL; }
70087dc3	487	static inline struct blkio_cgroup *
4f85cb96	488	bio_blkio_cgroup(struct bio *bio) { return NULL; }
31e4c28d	489
cd1604fa TH	490	static inline struct blkio_group blkg_lookup(struct blkio_cgroup blkcg,
cd1604fa TH	491	void *key) { return NULL; }
303a3acb	492	static inline void blkiocg_update_timeslice_used(struct blkio_group *blkg,
c1768268 TH	493	struct blkio_policy_type *pol, unsigned long time,
c1768268 TH	494	unsigned long unaccounted_time) { }
84c124da	495	static inline void blkiocg_update_dispatch_stats(struct blkio_group *blkg,
c1768268 TH	496	struct blkio_policy_type *pol, uint64_t bytes,
c1768268 TH	497	bool direction, bool sync) { }
84c124da	498	static inline void blkiocg_update_completion_stats(struct blkio_group *blkg,
c1768268 TH	499	struct blkio_policy_type *pol, uint64_t start_time,
c1768268 TH	500	uint64_t io_start_time, bool direction, bool sync) { }
812d4026	501	static inline void blkiocg_update_io_merged_stats(struct blkio_group *blkg,
c1768268 TH	502	struct blkio_policy_type *pol, bool direction,
c1768268 TH	503	bool sync) { }
a11cdaa7	504	static inline void blkiocg_update_io_add_stats(struct blkio_group *blkg,
c1768268 TH	505	struct blkio_policy_type *pol,
	506	struct blkio_group *curr_blkg, bool direction,
	507	bool sync) { }
a11cdaa7	508	static inline void blkiocg_update_io_remove_stats(struct blkio_group *blkg,
c1768268 TH	509	struct blkio_policy_type *pol, bool direction,
c1768268 TH	510	bool sync) { }
31e4c28d VG	511	#endif
31e4c28d VG	512	#endif /* _BLK_CGROUP_H */