blk-cgroup.h 10.4 KB
Newer Older
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16
#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>
17
#include <linux/u64_stats_sync.h>
18
#include <linux/seq_file.h>
19
#include <linux/radix-tree.h>
20

21 22 23
/* Max limits for throttle policy */
#define THROTL_IOPS_MAX		UINT_MAX

24 25 26 27 28
/* CFQ specific, out here for blkcg->cfq_weight */
#define CFQ_WEIGHT_MIN		10
#define CFQ_WEIGHT_MAX		1000
#define CFQ_WEIGHT_DEFAULT	500

T
Tejun Heo 已提交
29 30
#ifdef CONFIG_BLK_CGROUP

31 32 33 34 35 36 37 38
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,
39 40
};

41 42
struct blkcg_gq;

T
Tejun Heo 已提交
43
struct blkcg {
44 45
	struct cgroup_subsys_state	css;
	spinlock_t			lock;
46 47 48

	struct radix_tree_root		blkg_tree;
	struct blkcg_gq			*blkg_hint;
49
	struct hlist_head		blkg_list;
T
Tejun Heo 已提交
50 51

	/* for policies to test whether associated blkcg has changed */
52
	uint64_t			id;
53

T
Tejun Heo 已提交
54
	/* TODO: per-policy storage in blkcg */
55
	unsigned int			cfq_weight;	/* belongs to cfq */
56 57
};

58 59 60 61 62 63 64 65 66 67
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];
};

68 69 70 71 72 73 74 75 76 77 78 79 80
/*
 * A blkcg_gq (blkg) is association between a block cgroup (blkcg) and a
 * request_queue (q).  This is used by blkcg policies which need to track
 * information per blkcg - q pair.
 *
 * There can be multiple active blkcg policies and each has its private
 * data on each blkg, the size of which is determined by
 * blkcg_policy->pd_size.  blkcg core allocates and frees such areas
 * together with blkg and invokes pd_init/exit_fn() methods.
 *
 * Such private data must embed struct blkg_policy_data (pd) at the
 * beginning and pd_size can't be smaller than pd.
 */
81 82
struct blkg_policy_data {
	/* the blkg this per-policy data belongs to */
T
Tejun Heo 已提交
83
	struct blkcg_gq			*blkg;
84

85
	/* used during policy activation */
86
	struct list_head		alloc_node;
87 88
};

T
Tejun Heo 已提交
89 90
/* association between a blk cgroup and a request queue */
struct blkcg_gq {
T
Tejun Heo 已提交
91
	/* Pointer to the associated request_queue */
92 93 94
	struct request_queue		*q;
	struct list_head		q_node;
	struct hlist_node		blkcg_node;
T
Tejun Heo 已提交
95
	struct blkcg			*blkcg;
T
Tejun Heo 已提交
96
	/* reference count */
97
	int				refcnt;
98

99
	struct blkg_policy_data		*pd[BLKCG_MAX_POLS];
T
Tejun Heo 已提交
100

101
	struct rcu_head			rcu_head;
102 103
};

T
Tejun Heo 已提交
104 105 106
typedef void (blkcg_pol_init_pd_fn)(struct blkcg_gq *blkg);
typedef void (blkcg_pol_exit_pd_fn)(struct blkcg_gq *blkg);
typedef void (blkcg_pol_reset_pd_stats_fn)(struct blkcg_gq *blkg);
107

T
Tejun Heo 已提交
108
struct blkcg_policy {
109 110
	int				plid;
	/* policy specific private data size */
111
	size_t				pd_size;
112 113
	/* cgroup files for the policy */
	struct cftype			*cftypes;
114 115 116 117 118

	/* operations */
	blkcg_pol_init_pd_fn		*pd_init_fn;
	blkcg_pol_exit_pd_fn		*pd_exit_fn;
	blkcg_pol_reset_pd_stats_fn	*pd_reset_stats_fn;
119 120
};

T
Tejun Heo 已提交
121
extern struct blkcg blkcg_root;
122

T
Tejun Heo 已提交
123 124 125 126 127
struct blkcg *cgroup_to_blkcg(struct cgroup *cgroup);
struct blkcg *bio_blkcg(struct bio *bio);
struct blkcg_gq *blkg_lookup(struct blkcg *blkcg, struct request_queue *q);
struct blkcg_gq *blkg_lookup_create(struct blkcg *blkcg,
				    struct request_queue *q);
128 129 130
int blkcg_init_queue(struct request_queue *q);
void blkcg_drain_queue(struct request_queue *q);
void blkcg_exit_queue(struct request_queue *q);
131

132
/* Blkio controller policy registration */
T
Tejun Heo 已提交
133 134
int blkcg_policy_register(struct blkcg_policy *pol);
void blkcg_policy_unregister(struct blkcg_policy *pol);
135
int blkcg_activate_policy(struct request_queue *q,
T
Tejun Heo 已提交
136
			  const struct blkcg_policy *pol);
137
void blkcg_deactivate_policy(struct request_queue *q,
T
Tejun Heo 已提交
138
			     const struct blkcg_policy *pol);
139

T
Tejun Heo 已提交
140
void blkcg_print_blkgs(struct seq_file *sf, struct blkcg *blkcg,
141 142
		       u64 (*prfill)(struct seq_file *,
				     struct blkg_policy_data *, int),
T
Tejun Heo 已提交
143
		       const struct blkcg_policy *pol, int data,
144
		       bool show_total);
145 146
u64 __blkg_prfill_u64(struct seq_file *sf, struct blkg_policy_data *pd, u64 v);
u64 __blkg_prfill_rwstat(struct seq_file *sf, struct blkg_policy_data *pd,
147
			 const struct blkg_rwstat *rwstat);
148 149 150
u64 blkg_prfill_stat(struct seq_file *sf, struct blkg_policy_data *pd, int off);
u64 blkg_prfill_rwstat(struct seq_file *sf, struct blkg_policy_data *pd,
		       int off);
151 152

struct blkg_conf_ctx {
153
	struct gendisk			*disk;
T
Tejun Heo 已提交
154
	struct blkcg_gq			*blkg;
155
	u64				v;
156 157
};

T
Tejun Heo 已提交
158 159
int blkg_conf_prep(struct blkcg *blkcg, const struct blkcg_policy *pol,
		   const char *input, struct blkg_conf_ctx *ctx);
160 161 162
void blkg_conf_finish(struct blkg_conf_ctx *ctx);


163 164 165 166 167 168 169
/**
 * 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.
 */
170 171
static inline struct blkg_policy_data *blkg_to_pd(struct blkcg_gq *blkg,
						  struct blkcg_policy *pol)
172
{
173
	return blkg ? blkg->pd[pol->plid] : NULL;
174 175 176 177
}

/**
 * pdata_to_blkg - get blkg associated with policy private data
178
 * @pd: policy private data of interest
179
 *
180
 * @pd is policy private data.  Determine the blkg it's associated with.
181
 */
182
static inline struct blkcg_gq *pd_to_blkg(struct blkg_policy_data *pd)
183
{
184
	return pd ? pd->blkg : NULL;
185 186
}

T
Tejun Heo 已提交
187 188 189 190 191 192 193 194
/**
 * blkg_path - format cgroup path of blkg
 * @blkg: blkg of interest
 * @buf: target buffer
 * @buflen: target buffer length
 *
 * Format the path of the cgroup of @blkg into @buf.
 */
T
Tejun Heo 已提交
195
static inline int blkg_path(struct blkcg_gq *blkg, char *buf, int buflen)
196
{
T
Tejun Heo 已提交
197 198 199 200 201 202 203 204
	int ret;

	rcu_read_lock();
	ret = cgroup_path(blkg->blkcg->css.cgroup, buf, buflen);
	rcu_read_unlock();
	if (ret)
		strncpy(buf, "<unavailable>", buflen);
	return ret;
205 206
}

T
Tejun Heo 已提交
207 208 209 210 211 212
/**
 * blkg_get - get a blkg reference
 * @blkg: blkg to get
 *
 * The caller should be holding queue_lock and an existing reference.
 */
T
Tejun Heo 已提交
213
static inline void blkg_get(struct blkcg_gq *blkg)
T
Tejun Heo 已提交
214 215 216 217 218 219
{
	lockdep_assert_held(blkg->q->queue_lock);
	WARN_ON_ONCE(!blkg->refcnt);
	blkg->refcnt++;
}

T
Tejun Heo 已提交
220
void __blkg_release(struct blkcg_gq *blkg);
T
Tejun Heo 已提交
221 222 223 224 225 226 227

/**
 * blkg_put - put a blkg reference
 * @blkg: blkg to put
 *
 * The caller should be holding queue_lock.
 */
T
Tejun Heo 已提交
228
static inline void blkg_put(struct blkcg_gq *blkg)
T
Tejun Heo 已提交
229 230 231 232 233 234 235
{
	lockdep_assert_held(blkg->q->queue_lock);
	WARN_ON_ONCE(blkg->refcnt <= 0);
	if (!--blkg->refcnt)
		__blkg_release(blkg);
}

236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313
/**
 * 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.
 */
314
static inline struct blkg_rwstat blkg_rwstat_read(struct blkg_rwstat *rwstat)
315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350
{
	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));
}

351 352 353
#else	/* CONFIG_BLK_CGROUP */

struct cgroup;
354

355 356 357
struct blkg_policy_data {
};

T
Tejun Heo 已提交
358
struct blkcg_gq {
359 360
};

T
Tejun Heo 已提交
361
struct blkcg_policy {
362 363
};

T
Tejun Heo 已提交
364 365 366
static inline struct blkcg *cgroup_to_blkcg(struct cgroup *cgroup) { return NULL; }
static inline struct blkcg *bio_blkcg(struct bio *bio) { return NULL; }
static inline struct blkcg_gq *blkg_lookup(struct blkcg *blkcg, void *key) { return NULL; }
367 368 369
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) { }
T
Tejun Heo 已提交
370 371
static inline int blkcg_policy_register(struct blkcg_policy *pol) { return 0; }
static inline void blkcg_policy_unregister(struct blkcg_policy *pol) { }
372
static inline int blkcg_activate_policy(struct request_queue *q,
T
Tejun Heo 已提交
373
					const struct blkcg_policy *pol) { return 0; }
374
static inline void blkcg_deactivate_policy(struct request_queue *q,
T
Tejun Heo 已提交
375 376
					   const struct blkcg_policy *pol) { }

377 378 379
static inline struct blkg_policy_data *blkg_to_pd(struct blkcg_gq *blkg,
						  struct blkcg_policy *pol) { return NULL; }
static inline struct blkcg_gq *pd_to_blkg(struct blkg_policy_data *pd) { return NULL; }
T
Tejun Heo 已提交
380 381 382
static inline char *blkg_path(struct blkcg_gq *blkg) { return NULL; }
static inline void blkg_get(struct blkcg_gq *blkg) { }
static inline void blkg_put(struct blkcg_gq *blkg) { }
383

384 385
#endif	/* CONFIG_BLK_CGROUP */
#endif	/* _BLK_CGROUP_H */