blk-cgroup.h 20.8 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
#include <linux/blkdev.h>
21
#include <linux/atomic.h>
22

23
24
25
/* Max limits for throttle policy */
#define THROTL_IOPS_MAX		UINT_MAX

Tejun Heo's avatar
Tejun Heo committed
26
27
#ifdef CONFIG_BLK_CGROUP

28
29
30
31
32
33
34
35
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,
36
37
};

38
39
struct blkcg_gq;

Tejun Heo's avatar
Tejun Heo committed
40
struct blkcg {
41
42
	struct cgroup_subsys_state	css;
	spinlock_t			lock;
43
44
45

	struct radix_tree_root		blkg_tree;
	struct blkcg_gq			*blkg_hint;
46
	struct hlist_head		blkg_list;
Tejun Heo's avatar
Tejun Heo committed
47

48
	struct blkcg_policy_data	*cpd[BLKCG_MAX_POLS];
49

Tejun Heo's avatar
Tejun Heo committed
50
	struct list_head		all_blkcgs_node;
51
52
53
#ifdef CONFIG_CGROUP_WRITEBACK
	struct list_head		cgwb_list;
#endif
54
55
};

56
57
58
59
/*
 * blkg_[rw]stat->aux_cnt is excluded for local stats but included for
 * recursive.  Used to carry stats of dead children.
 */
60
61
62
struct blkg_stat {
	struct u64_stats_sync		syncp;
	uint64_t			cnt;
63
	atomic64_t			aux_cnt;
64
65
66
67
68
};

struct blkg_rwstat {
	struct u64_stats_sync		syncp;
	uint64_t			cnt[BLKG_RWSTAT_NR];
69
	atomic64_t			aux_cnt[BLKG_RWSTAT_NR];
70
71
};

72
73
74
75
76
/*
 * 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.
 *
77
78
79
80
81
 * There can be multiple active blkcg policies and each blkg:policy pair is
 * represented by a blkg_policy_data which is allocated and freed by each
 * policy's pd_alloc/free_fn() methods.  A policy can allocate private data
 * area by allocating larger data structure which embeds blkg_policy_data
 * at the beginning.
82
 */
83
struct blkg_policy_data {
Tejun Heo's avatar
Tejun Heo committed
84
	/* the blkg and policy id this per-policy data belongs to */
Tejun Heo's avatar
Tejun Heo committed
85
	struct blkcg_gq			*blkg;
Tejun Heo's avatar
Tejun Heo committed
86
	int				plid;
87
88
};

89
/*
90
91
92
93
94
 * Policies that need to keep per-blkcg data which is independent from any
 * request_queue associated to it should implement cpd_alloc/free_fn()
 * methods.  A policy can allocate private data area by allocating larger
 * data structure which embeds blkcg_policy_data at the beginning.
 * cpd_init() is invoked to let each policy handle per-blkcg data.
95
96
 */
struct blkcg_policy_data {
97
98
	/* the blkcg and policy id this per-policy data belongs to */
	struct blkcg			*blkcg;
99
100
101
	int				plid;
};

Tejun Heo's avatar
Tejun Heo committed
102
103
/* association between a blk cgroup and a request queue */
struct blkcg_gq {
104
	/* Pointer to the associated request_queue */
105
106
107
	struct request_queue		*q;
	struct list_head		q_node;
	struct hlist_node		blkcg_node;
Tejun Heo's avatar
Tejun Heo committed
108
	struct blkcg			*blkcg;
109

110
111
112
113
114
115
	/*
	 * Each blkg gets congested separately and the congestion state is
	 * propagated to the matching bdi_writeback_congested.
	 */
	struct bdi_writeback_congested	*wb_congested;

116
117
118
	/* all non-root blkcg_gq's are guaranteed to have access to parent */
	struct blkcg_gq			*parent;

119
120
	/* request allocation list for this blkcg-q pair */
	struct request_list		rl;
121

Tejun Heo's avatar
Tejun Heo committed
122
	/* reference count */
123
	atomic_t			refcnt;
124

125
126
127
	/* is this blkg online? protected by both blkcg and q locks */
	bool				online;

128
	struct blkg_policy_data		*pd[BLKCG_MAX_POLS];
Tejun Heo's avatar
Tejun Heo committed
129

130
	struct rcu_head			rcu_head;
131
132
};

133
typedef struct blkcg_policy_data *(blkcg_pol_alloc_cpd_fn)(gfp_t gfp);
134
typedef void (blkcg_pol_init_cpd_fn)(struct blkcg_policy_data *cpd);
135
typedef void (blkcg_pol_free_cpd_fn)(struct blkcg_policy_data *cpd);
136
typedef struct blkg_policy_data *(blkcg_pol_alloc_pd_fn)(gfp_t gfp, int node);
137
138
139
typedef void (blkcg_pol_init_pd_fn)(struct blkg_policy_data *pd);
typedef void (blkcg_pol_online_pd_fn)(struct blkg_policy_data *pd);
typedef void (blkcg_pol_offline_pd_fn)(struct blkg_policy_data *pd);
140
typedef void (blkcg_pol_free_pd_fn)(struct blkg_policy_data *pd);
141
typedef void (blkcg_pol_reset_pd_stats_fn)(struct blkg_policy_data *pd);
142

Tejun Heo's avatar
Tejun Heo committed
143
struct blkcg_policy {
144
145
146
	int				plid;
	/* cgroup files for the policy */
	struct cftype			*cftypes;
147
148

	/* operations */
149
	blkcg_pol_alloc_cpd_fn		*cpd_alloc_fn;
150
	blkcg_pol_init_cpd_fn		*cpd_init_fn;
151
152
	blkcg_pol_free_cpd_fn		*cpd_free_fn;

153
	blkcg_pol_alloc_pd_fn		*pd_alloc_fn;
154
	blkcg_pol_init_pd_fn		*pd_init_fn;
155
156
	blkcg_pol_online_pd_fn		*pd_online_fn;
	blkcg_pol_offline_pd_fn		*pd_offline_fn;
157
	blkcg_pol_free_pd_fn		*pd_free_fn;
158
	blkcg_pol_reset_pd_stats_fn	*pd_reset_stats_fn;
159
160
};

Tejun Heo's avatar
Tejun Heo committed
161
extern struct blkcg blkcg_root;
Tejun Heo's avatar
Tejun Heo committed
162
extern struct cgroup_subsys_state * const blkcg_root_css;
163

Tejun Heo's avatar
Tejun Heo committed
164
165
struct blkcg_gq *blkg_lookup_slowpath(struct blkcg *blkcg,
				      struct request_queue *q, bool update_hint);
Tejun Heo's avatar
Tejun Heo committed
166
167
struct blkcg_gq *blkg_lookup_create(struct blkcg *blkcg,
				    struct request_queue *q);
168
169
170
int blkcg_init_queue(struct request_queue *q);
void blkcg_drain_queue(struct request_queue *q);
void blkcg_exit_queue(struct request_queue *q);
171

172
/* Blkio controller policy registration */
173
int blkcg_policy_register(struct blkcg_policy *pol);
Tejun Heo's avatar
Tejun Heo committed
174
void blkcg_policy_unregister(struct blkcg_policy *pol);
175
int blkcg_activate_policy(struct request_queue *q,
Tejun Heo's avatar
Tejun Heo committed
176
			  const struct blkcg_policy *pol);
177
void blkcg_deactivate_policy(struct request_queue *q,
Tejun Heo's avatar
Tejun Heo committed
178
			     const struct blkcg_policy *pol);
179

Tejun Heo's avatar
Tejun Heo committed
180
void blkcg_print_blkgs(struct seq_file *sf, struct blkcg *blkcg,
181
182
		       u64 (*prfill)(struct seq_file *,
				     struct blkg_policy_data *, int),
Tejun Heo's avatar
Tejun Heo committed
183
		       const struct blkcg_policy *pol, int data,
184
		       bool show_total);
185
186
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,
187
			 const struct blkg_rwstat *rwstat);
188
189
190
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);
191

192
193
194
195
u64 blkg_stat_recursive_sum(struct blkg_policy_data *pd, int off);
struct blkg_rwstat blkg_rwstat_recursive_sum(struct blkg_policy_data *pd,
					     int off);

196
struct blkg_conf_ctx {
197
	struct gendisk			*disk;
Tejun Heo's avatar
Tejun Heo committed
198
	struct blkcg_gq			*blkg;
199
	u64				v;
200
201
};

Tejun Heo's avatar
Tejun Heo committed
202
203
int blkg_conf_prep(struct blkcg *blkcg, const struct blkcg_policy *pol,
		   const char *input, struct blkg_conf_ctx *ctx);
204
205
206
void blkg_conf_finish(struct blkg_conf_ctx *ctx);


207
208
209
210
211
static inline struct blkcg *css_to_blkcg(struct cgroup_subsys_state *css)
{
	return css ? container_of(css, struct blkcg, css) : NULL;
}

212
213
static inline struct blkcg *task_blkcg(struct task_struct *tsk)
{
214
	return css_to_blkcg(task_css(tsk, blkio_cgrp_id));
215
216
217
218
219
}

static inline struct blkcg *bio_blkcg(struct bio *bio)
{
	if (bio && bio->bi_css)
220
		return css_to_blkcg(bio->bi_css);
221
222
223
	return task_blkcg(current);
}

224
225
226
227
228
229
static inline struct cgroup_subsys_state *
task_get_blkcg_css(struct task_struct *task)
{
	return task_get_css(task, blkio_cgrp_id);
}

230
231
232
233
234
235
236
237
/**
 * blkcg_parent - get the parent of a blkcg
 * @blkcg: blkcg of interest
 *
 * Return the parent blkcg of @blkcg.  Can be called anytime.
 */
static inline struct blkcg *blkcg_parent(struct blkcg *blkcg)
{
Tejun Heo's avatar
Tejun Heo committed
238
	return css_to_blkcg(blkcg->css.parent);
239
240
}

Tejun Heo's avatar
Tejun Heo committed
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
/**
 * __blkg_lookup - internal version of blkg_lookup()
 * @blkcg: blkcg of interest
 * @q: request_queue of interest
 * @update_hint: whether to update lookup hint with the result or not
 *
 * This is internal version and shouldn't be used by policy
 * implementations.  Looks up blkgs for the @blkcg - @q pair regardless of
 * @q's bypass state.  If @update_hint is %true, the caller should be
 * holding @q->queue_lock and lookup hint is updated on success.
 */
static inline struct blkcg_gq *__blkg_lookup(struct blkcg *blkcg,
					     struct request_queue *q,
					     bool update_hint)
{
	struct blkcg_gq *blkg;

258
259
260
	if (blkcg == &blkcg_root)
		return q->root_blkg;

Tejun Heo's avatar
Tejun Heo committed
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
	blkg = rcu_dereference(blkcg->blkg_hint);
	if (blkg && blkg->q == q)
		return blkg;

	return blkg_lookup_slowpath(blkcg, q, update_hint);
}

/**
 * blkg_lookup - lookup blkg for the specified blkcg - q pair
 * @blkcg: blkcg of interest
 * @q: request_queue of interest
 *
 * Lookup blkg for the @blkcg - @q pair.  This function should be called
 * under RCU read lock and is guaranteed to return %NULL if @q is bypassing
 * - see blk_queue_bypass_start() for details.
 */
static inline struct blkcg_gq *blkg_lookup(struct blkcg *blkcg,
					   struct request_queue *q)
{
	WARN_ON_ONCE(!rcu_read_lock_held());

	if (unlikely(blk_queue_bypass(q)))
		return NULL;
	return __blkg_lookup(blkcg, q, false);
}

287
288
289
290
291
292
293
/**
 * 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.
 */
294
295
static inline struct blkg_policy_data *blkg_to_pd(struct blkcg_gq *blkg,
						  struct blkcg_policy *pol)
296
{
297
	return blkg ? blkg->pd[pol->plid] : NULL;
298
299
}

300
301
302
static inline struct blkcg_policy_data *blkcg_to_cpd(struct blkcg *blkcg,
						     struct blkcg_policy *pol)
{
303
	return blkcg ? blkcg->cpd[pol->plid] : NULL;
304
305
}

306
307
/**
 * pdata_to_blkg - get blkg associated with policy private data
308
 * @pd: policy private data of interest
309
 *
310
 * @pd is policy private data.  Determine the blkg it's associated with.
311
 */
312
static inline struct blkcg_gq *pd_to_blkg(struct blkg_policy_data *pd)
313
{
314
	return pd ? pd->blkg : NULL;
315
316
}

317
318
319
320
321
static inline struct blkcg *cpd_to_blkcg(struct blkcg_policy_data *cpd)
{
	return cpd ? cpd->blkcg : NULL;
}

Tejun Heo's avatar
Tejun Heo committed
322
323
324
325
326
327
328
329
/**
 * 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.
 */
Tejun Heo's avatar
Tejun Heo committed
330
static inline int blkg_path(struct blkcg_gq *blkg, char *buf, int buflen)
331
{
Tejun Heo's avatar
Tejun Heo committed
332
	char *p;
Tejun Heo's avatar
Tejun Heo committed
333

Tejun Heo's avatar
Tejun Heo committed
334
335
	p = cgroup_path(blkg->blkcg->css.cgroup, buf, buflen);
	if (!p) {
Tejun Heo's avatar
Tejun Heo committed
336
		strncpy(buf, "<unavailable>", buflen);
Tejun Heo's avatar
Tejun Heo committed
337
338
339
340
341
		return -ENAMETOOLONG;
	}

	memmove(buf, p, buf + buflen - p);
	return 0;
342
343
}

Tejun Heo's avatar
Tejun Heo committed
344
345
346
347
/**
 * blkg_get - get a blkg reference
 * @blkg: blkg to get
 *
348
 * The caller should be holding an existing reference.
Tejun Heo's avatar
Tejun Heo committed
349
 */
Tejun Heo's avatar
Tejun Heo committed
350
static inline void blkg_get(struct blkcg_gq *blkg)
Tejun Heo's avatar
Tejun Heo committed
351
{
352
353
	WARN_ON_ONCE(atomic_read(&blkg->refcnt) <= 0);
	atomic_inc(&blkg->refcnt);
Tejun Heo's avatar
Tejun Heo committed
354
355
}

356
void __blkg_release_rcu(struct rcu_head *rcu);
Tejun Heo's avatar
Tejun Heo committed
357
358
359
360
361

/**
 * blkg_put - put a blkg reference
 * @blkg: blkg to put
 */
Tejun Heo's avatar
Tejun Heo committed
362
static inline void blkg_put(struct blkcg_gq *blkg)
Tejun Heo's avatar
Tejun Heo committed
363
{
364
365
	WARN_ON_ONCE(atomic_read(&blkg->refcnt) <= 0);
	if (atomic_dec_and_test(&blkg->refcnt))
366
		call_rcu(&blkg->rcu_head, __blkg_release_rcu);
Tejun Heo's avatar
Tejun Heo committed
367
368
}

369
370
371
/**
 * blkg_for_each_descendant_pre - pre-order walk of a blkg's descendants
 * @d_blkg: loop cursor pointing to the current descendant
372
 * @pos_css: used for iteration
373
374
375
376
377
 * @p_blkg: target blkg to walk descendants of
 *
 * Walk @c_blkg through the descendants of @p_blkg.  Must be used with RCU
 * read locked.  If called under either blkcg or queue lock, the iteration
 * is guaranteed to include all and only online blkgs.  The caller may
378
 * update @pos_css by calling css_rightmost_descendant() to skip subtree.
379
 * @p_blkg is included in the iteration and the first node to be visited.
380
 */
381
382
383
#define blkg_for_each_descendant_pre(d_blkg, pos_css, p_blkg)		\
	css_for_each_descendant_pre((pos_css), &(p_blkg)->blkcg->css)	\
		if (((d_blkg) = __blkg_lookup(css_to_blkcg(pos_css),	\
384
385
					      (p_blkg)->q, false)))

386
387
388
/**
 * blkg_for_each_descendant_post - post-order walk of a blkg's descendants
 * @d_blkg: loop cursor pointing to the current descendant
389
 * @pos_css: used for iteration
390
391
392
 * @p_blkg: target blkg to walk descendants of
 *
 * Similar to blkg_for_each_descendant_pre() but performs post-order
393
394
 * traversal instead.  Synchronization rules are the same.  @p_blkg is
 * included in the iteration and the last node to be visited.
395
 */
396
397
398
#define blkg_for_each_descendant_post(d_blkg, pos_css, p_blkg)		\
	css_for_each_descendant_post((pos_css), &(p_blkg)->blkcg->css)	\
		if (((d_blkg) = __blkg_lookup(css_to_blkcg(pos_css),	\
399
400
					      (p_blkg)->q, false)))

401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
/**
 * blk_get_rl - get request_list to use
 * @q: request_queue of interest
 * @bio: bio which will be attached to the allocated request (may be %NULL)
 *
 * The caller wants to allocate a request from @q to use for @bio.  Find
 * the request_list to use and obtain a reference on it.  Should be called
 * under queue_lock.  This function is guaranteed to return non-%NULL
 * request_list.
 */
static inline struct request_list *blk_get_rl(struct request_queue *q,
					      struct bio *bio)
{
	struct blkcg *blkcg;
	struct blkcg_gq *blkg;

	rcu_read_lock();

	blkcg = bio_blkcg(bio);

	/* bypass blkg lookup and use @q->root_rl directly for root */
	if (blkcg == &blkcg_root)
		goto root_rl;

	/*
	 * Try to use blkg->rl.  blkg lookup may fail under memory pressure
	 * or if either the blkcg or queue is going away.  Fall back to
	 * root_rl in such cases.
	 */
430
431
	blkg = blkg_lookup(blkcg, q);
	if (unlikely(!blkg))
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
		goto root_rl;

	blkg_get(blkg);
	rcu_read_unlock();
	return &blkg->rl;
root_rl:
	rcu_read_unlock();
	return &q->root_rl;
}

/**
 * blk_put_rl - put request_list
 * @rl: request_list to put
 *
 * Put the reference acquired by blk_get_rl().  Should be called under
 * queue_lock.
 */
static inline void blk_put_rl(struct request_list *rl)
{
451
	if (rl->blkg->blkcg != &blkcg_root)
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
		blkg_put(rl->blkg);
}

/**
 * blk_rq_set_rl - associate a request with a request_list
 * @rq: request of interest
 * @rl: target request_list
 *
 * Associate @rq with @rl so that accounting and freeing can know the
 * request_list @rq came from.
 */
static inline void blk_rq_set_rl(struct request *rq, struct request_list *rl)
{
	rq->rl = rl;
}

/**
 * blk_rq_rl - return the request_list a request came from
 * @rq: request of interest
 *
 * Return the request_list @rq is allocated from.
 */
static inline struct request_list *blk_rq_rl(struct request *rq)
{
	return rq->rl;
}

struct request_list *__blk_queue_next_rl(struct request_list *rl,
					 struct request_queue *q);
/**
 * blk_queue_for_each_rl - iterate through all request_lists of a request_queue
 *
 * Should be used under queue_lock.
 */
#define blk_queue_for_each_rl(rl, q)	\
	for ((rl) = &(q)->root_rl; (rl); (rl) = __blk_queue_next_rl((rl), (q)))

489
490
491
static inline void blkg_stat_init(struct blkg_stat *stat)
{
	u64_stats_init(&stat->syncp);
492
	atomic64_set(&stat->aux_cnt, 0);
493
494
}

495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
/**
 * 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
 *
514
515
516
 * Read the current value of @stat.  The returned value doesn't include the
 * aux count.  This function can be called without synchroniztion and takes
 * care of u64 atomicity.
517
518
519
520
521
522
523
 */
static inline uint64_t blkg_stat_read(struct blkg_stat *stat)
{
	unsigned int start;
	uint64_t v;

	do {
524
		start = u64_stats_fetch_begin_irq(&stat->syncp);
525
		v = stat->cnt;
526
	} while (u64_stats_fetch_retry_irq(&stat->syncp, start));
527
528
529
530
531
532
533
534
535
536
537

	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;
538
	atomic64_set(&stat->aux_cnt, 0);
539
540
}

541
/**
542
 * blkg_stat_add_aux - add a blkg_stat into another's aux count
543
544
545
 * @to: the destination blkg_stat
 * @from: the source
 *
546
 * Add @from's count including the aux one to @to's aux count.
547
 */
548
549
static inline void blkg_stat_add_aux(struct blkg_stat *to,
				     struct blkg_stat *from)
550
{
551
552
	atomic64_add(blkg_stat_read(from) + atomic64_read(&from->aux_cnt),
		     &to->aux_cnt);
553
554
}

555
556
static inline void blkg_rwstat_init(struct blkg_rwstat *rwstat)
{
557
558
	int i;

559
	u64_stats_init(&rwstat->syncp);
560
561
562

	for (i = 0; i < BLKG_RWSTAT_NR; i++)
		atomic64_set(&rwstat->aux_cnt[i], 0);
563
564
}

565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
/**
 * 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.
 */
599
static inline struct blkg_rwstat blkg_rwstat_read(struct blkg_rwstat *rwstat)
600
601
602
603
604
{
	unsigned int start;
	struct blkg_rwstat tmp;

	do {
605
		start = u64_stats_fetch_begin_irq(&rwstat->syncp);
606
		tmp = *rwstat;
607
	} while (u64_stats_fetch_retry_irq(&rwstat->syncp, start));
608
609
610
611
612

	return tmp;
}

/**
613
 * blkg_rwstat_total - read the total count of a blkg_rwstat
614
615
616
617
618
619
 * @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.
 */
620
static inline uint64_t blkg_rwstat_total(struct blkg_rwstat *rwstat)
621
622
623
624
625
626
627
628
629
630
631
632
{
	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)
{
633
634
	int i;

635
	memset(rwstat->cnt, 0, sizeof(rwstat->cnt));
636
637
638

	for (i = 0; i < BLKG_RWSTAT_NR; i++)
		atomic64_set(&rwstat->aux_cnt[i], 0);
639
640
}

641
/**
642
 * blkg_rwstat_add_aux - add a blkg_rwstat into another's aux count
643
644
645
 * @to: the destination blkg_rwstat
 * @from: the source
 *
646
 * Add @from's count including the aux one to @to's aux count.
647
 */
648
649
static inline void blkg_rwstat_add_aux(struct blkg_rwstat *to,
				       struct blkg_rwstat *from)
650
651
652
653
654
{
	struct blkg_rwstat v = blkg_rwstat_read(from);
	int i;

	for (i = 0; i < BLKG_RWSTAT_NR; i++)
655
656
		atomic64_add(v.cnt[i] + atomic64_read(&from->aux_cnt[i]),
			     &to->aux_cnt[i]);
657
658
}

659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
#ifdef CONFIG_BLK_DEV_THROTTLING
extern bool blk_throtl_bio(struct request_queue *q, struct blkcg_gq *blkg,
			   struct bio *bio);
#else
static inline bool blk_throtl_bio(struct request_queue *q, struct blkcg_gq *blkg,
				  struct bio *bio) { return false; }
#endif

static inline bool blkcg_bio_issue_check(struct request_queue *q,
					 struct bio *bio)
{
	struct blkcg *blkcg;
	struct blkcg_gq *blkg;
	bool throtl = false;

	rcu_read_lock();
	blkcg = bio_blkcg(bio);

	blkg = blkg_lookup(blkcg, q);
	if (unlikely(!blkg)) {
		spin_lock_irq(q->queue_lock);
		blkg = blkg_lookup_create(blkcg, q);
		if (IS_ERR(blkg))
			blkg = NULL;
		spin_unlock_irq(q->queue_lock);
	}

	throtl = blk_throtl_bio(q, blkg, bio);

	rcu_read_unlock();
	return !throtl;
}

692
693
#else	/* CONFIG_BLK_CGROUP */

694
695
struct blkcg {
};
696

697
698
699
struct blkg_policy_data {
};

700
701
702
struct blkcg_policy_data {
};

Tejun Heo's avatar
Tejun Heo committed
703
struct blkcg_gq {
704
705
};

Tejun Heo's avatar
Tejun Heo committed
706
struct blkcg_policy {
707
708
};

Tejun Heo's avatar
Tejun Heo committed
709
710
#define blkcg_root_css	((struct cgroup_subsys_state *)ERR_PTR(-EINVAL))

711
712
713
714
715
716
static inline struct cgroup_subsys_state *
task_get_blkcg_css(struct task_struct *task)
{
	return NULL;
}

717
718
#ifdef CONFIG_BLOCK

Tejun Heo's avatar
Tejun Heo committed
719
static inline struct blkcg_gq *blkg_lookup(struct blkcg *blkcg, void *key) { return NULL; }
720
721
722
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) { }
723
static inline int blkcg_policy_register(struct blkcg_policy *pol) { return 0; }
Tejun Heo's avatar
Tejun Heo committed
724
static inline void blkcg_policy_unregister(struct blkcg_policy *pol) { }
725
static inline int blkcg_activate_policy(struct request_queue *q,
Tejun Heo's avatar
Tejun Heo committed
726
					const struct blkcg_policy *pol) { return 0; }
727
static inline void blkcg_deactivate_policy(struct request_queue *q,
Tejun Heo's avatar
Tejun Heo committed
728
729
					   const struct blkcg_policy *pol) { }

730
static inline struct blkcg *bio_blkcg(struct bio *bio) { return NULL; }
731

732
733
734
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; }
Tejun Heo's avatar
Tejun Heo committed
735
736
737
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) { }
738

739
740
741
742
743
744
static inline struct request_list *blk_get_rl(struct request_queue *q,
					      struct bio *bio) { return &q->root_rl; }
static inline void blk_put_rl(struct request_list *rl) { }
static inline void blk_rq_set_rl(struct request *rq, struct request_list *rl) { }
static inline struct request_list *blk_rq_rl(struct request *rq) { return &rq->q->root_rl; }

745
746
747
static inline bool blkcg_bio_issue_check(struct request_queue *q,
					 struct bio *bio) { return true; }

748
749
750
#define blk_queue_for_each_rl(rl, q)	\
	for ((rl) = &(q)->root_rl; (rl); (rl) = NULL)

751
#endif	/* CONFIG_BLOCK */
752
753
#endif	/* CONFIG_BLK_CGROUP */
#endif	/* _BLK_CGROUP_H */