backing-dev.h 14.0 KB
Newer Older
L
Linus Torvalds 已提交
1 2 3 4 5 6 7 8 9 10
/*
 * include/linux/backing-dev.h
 *
 * low-level device information and state which is propagated up through
 * to high-level code.
 */

#ifndef _LINUX_BACKING_DEV_H
#define _LINUX_BACKING_DEV_H

11
#include <linux/kernel.h>
12
#include <linux/fs.h>
13
#include <linux/sched.h>
T
Tejun Heo 已提交
14
#include <linux/blkdev.h>
15
#include <linux/writeback.h>
16
#include <linux/blk-cgroup.h>
17
#include <linux/backing-dev-defs.h>
18
#include <linux/slab.h>
19

M
Mikulas Patocka 已提交
20
int __must_check bdi_init(struct backing_dev_info *bdi);
21 22 23 24 25 26 27 28

static inline struct backing_dev_info *bdi_get(struct backing_dev_info *bdi)
{
	kref_get(&bdi->refcnt);
	return bdi;
}

void bdi_put(struct backing_dev_info *bdi);
29

30
__printf(3, 4)
31 32 33
int bdi_register(struct backing_dev_info *bdi, struct device *parent,
		const char *fmt, ...);
int bdi_register_dev(struct backing_dev_info *bdi, dev_t dev);
34
int bdi_register_owner(struct backing_dev_info *bdi, struct device *owner);
35 36
void bdi_unregister(struct backing_dev_info *bdi);

37
int __must_check bdi_setup_and_register(struct backing_dev_info *, char *);
38
void bdi_destroy(struct backing_dev_info *bdi);
39
struct backing_dev_info *bdi_alloc_node(gfp_t gfp_mask, int node_id);
40

41 42
void wb_start_writeback(struct bdi_writeback *wb, long nr_pages,
			bool range_cyclic, enum wb_reason reason);
43
void wb_start_background_writeback(struct bdi_writeback *wb);
44 45
void wb_workfn(struct work_struct *work);
void wb_wakeup_delayed(struct bdi_writeback *wb);
46

47
extern spinlock_t bdi_lock;
48 49
extern struct list_head bdi_list;

50 51
extern struct workqueue_struct *bdi_wq;

52
static inline bool wb_has_dirty_io(struct bdi_writeback *wb)
53
{
54
	return test_bit(WB_has_dirty_io, &wb->state);
55 56
}

57 58 59 60 61 62 63
static inline bool bdi_has_dirty_io(struct backing_dev_info *bdi)
{
	/*
	 * @bdi->tot_write_bandwidth is guaranteed to be > 0 if there are
	 * any dirty wbs.  See wb_update_write_bandwidth().
	 */
	return atomic_long_read(&bdi->tot_write_bandwidth);
64 65
}

66 67
static inline void __add_wb_stat(struct bdi_writeback *wb,
				 enum wb_stat_item item, s64 amount)
68
{
69
	__percpu_counter_add(&wb->stat[item], amount, WB_STAT_BATCH);
70 71
}

72 73
static inline void __inc_wb_stat(struct bdi_writeback *wb,
				 enum wb_stat_item item)
74
{
75
	__add_wb_stat(wb, item, 1);
76 77
}

78
static inline void inc_wb_stat(struct bdi_writeback *wb, enum wb_stat_item item)
79 80 81 82
{
	unsigned long flags;

	local_irq_save(flags);
83
	__inc_wb_stat(wb, item);
84 85 86
	local_irq_restore(flags);
}

87 88
static inline void __dec_wb_stat(struct bdi_writeback *wb,
				 enum wb_stat_item item)
89
{
90
	__add_wb_stat(wb, item, -1);
91 92
}

93
static inline void dec_wb_stat(struct bdi_writeback *wb, enum wb_stat_item item)
94 95 96 97
{
	unsigned long flags;

	local_irq_save(flags);
98
	__dec_wb_stat(wb, item);
99 100 101
	local_irq_restore(flags);
}

102
static inline s64 wb_stat(struct bdi_writeback *wb, enum wb_stat_item item)
103
{
104
	return percpu_counter_read_positive(&wb->stat[item]);
105 106
}

107 108
static inline s64 __wb_stat_sum(struct bdi_writeback *wb,
				enum wb_stat_item item)
109
{
110
	return percpu_counter_sum_positive(&wb->stat[item]);
111 112
}

113
static inline s64 wb_stat_sum(struct bdi_writeback *wb, enum wb_stat_item item)
P
Peter Zijlstra 已提交
114
{
115 116 117 118
	s64 sum;
	unsigned long flags;

	local_irq_save(flags);
119
	sum = __wb_stat_sum(wb, item);
120 121 122
	local_irq_restore(flags);

	return sum;
P
Peter Zijlstra 已提交
123 124
}

125
extern void wb_writeout_inc(struct bdi_writeback *wb);
126

127 128 129
/*
 * maximal error of a stat counter.
 */
130
static inline unsigned long wb_stat_error(struct bdi_writeback *wb)
P
Peter Zijlstra 已提交
131
{
132
#ifdef CONFIG_SMP
133
	return nr_cpu_ids * WB_STAT_BATCH;
134 135 136
#else
	return 1;
#endif
P
Peter Zijlstra 已提交
137
}
L
Linus Torvalds 已提交
138

139
int bdi_set_min_ratio(struct backing_dev_info *bdi, unsigned int min_ratio);
140
int bdi_set_max_ratio(struct backing_dev_info *bdi, unsigned int max_ratio);
141

L
Linus Torvalds 已提交
142 143
/*
 * Flags in backing_dev_info::capability
144 145 146 147 148 149 150 151 152 153 154 155
 *
 * The first three flags control whether dirty pages will contribute to the
 * VM's accounting and whether writepages() should be called for dirty pages
 * (something that would not, for example, be appropriate for ramfs)
 *
 * WARNING: these flags are closely related and should not normally be
 * used separately.  The BDI_CAP_NO_ACCT_AND_WRITEBACK combines these
 * three flags into a single convenience macro.
 *
 * BDI_CAP_NO_ACCT_DIRTY:  Dirty pages shouldn't contribute to accounting
 * BDI_CAP_NO_WRITEBACK:   Don't write pages back
 * BDI_CAP_NO_ACCT_WB:     Don't automatically account writeback pages
156
 * BDI_CAP_STRICTLIMIT:    Keep number of dirty pages below bdi threshold.
157 158
 *
 * BDI_CAP_CGROUP_WRITEBACK: Supports cgroup-aware writeback.
L
Linus Torvalds 已提交
159
 */
160 161
#define BDI_CAP_NO_ACCT_DIRTY	0x00000001
#define BDI_CAP_NO_WRITEBACK	0x00000002
162 163 164
#define BDI_CAP_NO_ACCT_WB	0x00000004
#define BDI_CAP_STABLE_WRITES	0x00000008
#define BDI_CAP_STRICTLIMIT	0x00000010
165
#define BDI_CAP_CGROUP_WRITEBACK 0x00000020
L
Linus Torvalds 已提交
166

167 168 169
#define BDI_CAP_NO_ACCT_AND_WRITEBACK \
	(BDI_CAP_NO_WRITEBACK | BDI_CAP_NO_ACCT_DIRTY | BDI_CAP_NO_ACCT_WB)

J
Jörn Engel 已提交
170
extern struct backing_dev_info noop_backing_dev_info;
L
Linus Torvalds 已提交
171

172 173 174 175 176 177 178 179
/**
 * writeback_in_progress - determine whether there is writeback in progress
 * @wb: bdi_writeback of interest
 *
 * Determine whether there is writeback waiting to be handled against a
 * bdi_writeback.
 */
static inline bool writeback_in_progress(struct bdi_writeback *wb)
L
Linus Torvalds 已提交
180
{
181
	return test_bit(WB_writeback_running, &wb->state);
L
Linus Torvalds 已提交
182 183
}

T
Tejun Heo 已提交
184
static inline struct backing_dev_info *inode_to_bdi(struct inode *inode)
L
Linus Torvalds 已提交
185
{
T
Tejun Heo 已提交
186
	struct super_block *sb;
L
Linus Torvalds 已提交
187

T
Tejun Heo 已提交
188 189 190 191 192 193
	if (!inode)
		return &noop_backing_dev_info;

	sb = inode->i_sb;
#ifdef CONFIG_BLOCK
	if (sb_is_blkdev_sb(sb))
194
		return I_BDEV(inode)->bd_bdi;
T
Tejun Heo 已提交
195 196
#endif
	return sb->s_bdi;
L
Linus Torvalds 已提交
197 198
}

199
static inline int wb_congested(struct bdi_writeback *wb, int cong_bits)
L
Linus Torvalds 已提交
200
{
201
	struct backing_dev_info *bdi = wb->bdi;
L
Linus Torvalds 已提交
202

203 204 205
	if (bdi->congested_fn)
		return bdi->congested_fn(bdi->congested_data, cong_bits);
	return wb->congested->state & cong_bits;
L
Linus Torvalds 已提交
206
}
207

208
long congestion_wait(int sync, long timeout);
M
Mel Gorman 已提交
209
long wait_iff_congested(struct pglist_data *pgdat, int sync, long timeout);
210 211
int pdflush_proc_obsolete(struct ctl_table *table, int write,
		void __user *buffer, size_t *lenp, loff_t *ppos);
L
Linus Torvalds 已提交
212

213 214 215 216 217
static inline bool bdi_cap_stable_pages_required(struct backing_dev_info *bdi)
{
	return bdi->capabilities & BDI_CAP_STABLE_WRITES;
}

218 219 220 221 222 223 224 225 226
static inline bool bdi_cap_writeback_dirty(struct backing_dev_info *bdi)
{
	return !(bdi->capabilities & BDI_CAP_NO_WRITEBACK);
}

static inline bool bdi_cap_account_dirty(struct backing_dev_info *bdi)
{
	return !(bdi->capabilities & BDI_CAP_NO_ACCT_DIRTY);
}
L
Linus Torvalds 已提交
227

228 229 230 231 232 233
static inline bool bdi_cap_account_writeback(struct backing_dev_info *bdi)
{
	/* Paranoia: BDI_CAP_NO_WRITEBACK implies BDI_CAP_NO_ACCT_WB */
	return !(bdi->capabilities & (BDI_CAP_NO_ACCT_WB |
				      BDI_CAP_NO_WRITEBACK));
}
L
Linus Torvalds 已提交
234

235 236
static inline bool mapping_cap_writeback_dirty(struct address_space *mapping)
{
237
	return bdi_cap_writeback_dirty(inode_to_bdi(mapping->host));
238
}
L
Linus Torvalds 已提交
239

240 241
static inline bool mapping_cap_account_dirty(struct address_space *mapping)
{
242
	return bdi_cap_account_dirty(inode_to_bdi(mapping->host));
243
}
L
Linus Torvalds 已提交
244

245 246 247 248 249 250
static inline int bdi_sched_wait(void *word)
{
	schedule();
	return 0;
}

251 252
#ifdef CONFIG_CGROUP_WRITEBACK

253 254 255 256 257 258 259 260
struct bdi_writeback_congested *
wb_congested_get_create(struct backing_dev_info *bdi, int blkcg_id, gfp_t gfp);
void wb_congested_put(struct bdi_writeback_congested *congested);
struct bdi_writeback *wb_get_create(struct backing_dev_info *bdi,
				    struct cgroup_subsys_state *memcg_css,
				    gfp_t gfp);
void wb_memcg_offline(struct mem_cgroup *memcg);
void wb_blkcg_offline(struct blkcg *blkcg);
261
int inode_congested(struct inode *inode, int cong_bits);
262

263 264 265 266 267
/**
 * inode_cgwb_enabled - test whether cgroup writeback is enabled on an inode
 * @inode: inode of interest
 *
 * cgroup writeback requires support from both the bdi and filesystem.
268 269 270 271 272
 * Also, both memcg and iocg have to be on the default hierarchy.  Test
 * whether all conditions are met.
 *
 * Note that the test result may change dynamically on the same inode
 * depending on how memcg and iocg are configured.
273 274 275 276 277
 */
static inline bool inode_cgwb_enabled(struct inode *inode)
{
	struct backing_dev_info *bdi = inode_to_bdi(inode);

278 279
	return cgroup_subsys_on_dfl(memory_cgrp_subsys) &&
		cgroup_subsys_on_dfl(io_cgrp_subsys) &&
280
		bdi_cap_account_dirty(bdi) &&
281
		(bdi->capabilities & BDI_CAP_CGROUP_WRITEBACK) &&
282
		(inode->i_sb->s_iflags & SB_I_CGROUPWB);
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
/**
 * wb_find_current - find wb for %current on a bdi
 * @bdi: bdi of interest
 *
 * Find the wb of @bdi which matches both the memcg and blkcg of %current.
 * Must be called under rcu_read_lock() which protects the returend wb.
 * NULL if not found.
 */
static inline struct bdi_writeback *wb_find_current(struct backing_dev_info *bdi)
{
	struct cgroup_subsys_state *memcg_css;
	struct bdi_writeback *wb;

	memcg_css = task_css(current, memory_cgrp_id);
	if (!memcg_css->parent)
		return &bdi->wb;

	wb = radix_tree_lookup(&bdi->cgwb_tree, memcg_css->id);

	/*
	 * %current's blkcg equals the effective blkcg of its memcg.  No
	 * need to use the relatively expensive cgroup_get_e_css().
	 */
308
	if (likely(wb && wb->blkcg_css == task_css(current, io_cgrp_id)))
309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342
		return wb;
	return NULL;
}

/**
 * wb_get_create_current - get or create wb for %current on a bdi
 * @bdi: bdi of interest
 * @gfp: allocation mask
 *
 * Equivalent to wb_get_create() on %current's memcg.  This function is
 * called from a relatively hot path and optimizes the common cases using
 * wb_find_current().
 */
static inline struct bdi_writeback *
wb_get_create_current(struct backing_dev_info *bdi, gfp_t gfp)
{
	struct bdi_writeback *wb;

	rcu_read_lock();
	wb = wb_find_current(bdi);
	if (wb && unlikely(!wb_tryget(wb)))
		wb = NULL;
	rcu_read_unlock();

	if (unlikely(!wb)) {
		struct cgroup_subsys_state *memcg_css;

		memcg_css = task_get_css(current, memory_cgrp_id);
		wb = wb_get_create(bdi, memcg_css, gfp);
		css_put(memcg_css);
	}
	return wb;
}

343 344 345 346 347 348 349 350 351 352 353 354
/**
 * inode_to_wb_is_valid - test whether an inode has a wb associated
 * @inode: inode of interest
 *
 * Returns %true if @inode has a wb associated.  May be called without any
 * locking.
 */
static inline bool inode_to_wb_is_valid(struct inode *inode)
{
	return inode->i_wb;
}

355 356 357 358
/**
 * inode_to_wb - determine the wb of an inode
 * @inode: inode of interest
 *
359 360 361
 * Returns the wb @inode is currently associated with.  The caller must be
 * holding either @inode->i_lock, @inode->i_mapping->tree_lock, or the
 * associated wb's list_lock.
362 363 364
 */
static inline struct bdi_writeback *inode_to_wb(struct inode *inode)
{
365 366 367 368 369 370
#ifdef CONFIG_LOCKDEP
	WARN_ON_ONCE(debug_locks &&
		     (!lockdep_is_held(&inode->i_lock) &&
		      !lockdep_is_held(&inode->i_mapping->tree_lock) &&
		      !lockdep_is_held(&inode->i_wb->list_lock)));
#endif
371 372 373
	return inode->i_wb;
}

374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401
/**
 * unlocked_inode_to_wb_begin - begin unlocked inode wb access transaction
 * @inode: target inode
 * @lockedp: temp bool output param, to be passed to the end function
 *
 * The caller wants to access the wb associated with @inode but isn't
 * holding inode->i_lock, mapping->tree_lock or wb->list_lock.  This
 * function determines the wb associated with @inode and ensures that the
 * association doesn't change until the transaction is finished with
 * unlocked_inode_to_wb_end().
 *
 * The caller must call unlocked_inode_to_wb_end() with *@lockdep
 * afterwards and can't sleep during transaction.  IRQ may or may not be
 * disabled on return.
 */
static inline struct bdi_writeback *
unlocked_inode_to_wb_begin(struct inode *inode, bool *lockedp)
{
	rcu_read_lock();

	/*
	 * Paired with store_release in inode_switch_wb_work_fn() and
	 * ensures that we see the new wb if we see cleared I_WB_SWITCH.
	 */
	*lockedp = smp_load_acquire(&inode->i_state) & I_WB_SWITCH;

	if (unlikely(*lockedp))
		spin_lock_irq(&inode->i_mapping->tree_lock);
402 403 404 405 406 407

	/*
	 * Protected by either !I_WB_SWITCH + rcu_read_lock() or tree_lock.
	 * inode_to_wb() will bark.  Deref directly.
	 */
	return inode->i_wb;
408 409 410 411 412 413 414 415 416 417 418 419 420 421 422
}

/**
 * unlocked_inode_to_wb_end - end inode wb access transaction
 * @inode: target inode
 * @locked: *@lockedp from unlocked_inode_to_wb_begin()
 */
static inline void unlocked_inode_to_wb_end(struct inode *inode, bool locked)
{
	if (unlikely(locked))
		spin_unlock_irq(&inode->i_mapping->tree_lock);

	rcu_read_unlock();
}

423 424 425 426 427 428 429
#else	/* CONFIG_CGROUP_WRITEBACK */

static inline bool inode_cgwb_enabled(struct inode *inode)
{
	return false;
}

430 431 432
static inline struct bdi_writeback_congested *
wb_congested_get_create(struct backing_dev_info *bdi, int blkcg_id, gfp_t gfp)
{
433 434
	atomic_inc(&bdi->wb_congested->refcnt);
	return bdi->wb_congested;
435 436 437 438
}

static inline void wb_congested_put(struct bdi_writeback_congested *congested)
{
439 440
	if (atomic_dec_and_test(&congested->refcnt))
		kfree(congested);
441 442 443 444 445 446 447 448 449 450 451 452 453
}

static inline struct bdi_writeback *wb_find_current(struct backing_dev_info *bdi)
{
	return &bdi->wb;
}

static inline struct bdi_writeback *
wb_get_create_current(struct backing_dev_info *bdi, gfp_t gfp)
{
	return &bdi->wb;
}

454 455 456 457 458
static inline bool inode_to_wb_is_valid(struct inode *inode)
{
	return true;
}

459 460 461 462 463
static inline struct bdi_writeback *inode_to_wb(struct inode *inode)
{
	return &inode_to_bdi(inode)->wb;
}

464 465 466 467 468 469 470 471 472 473
static inline struct bdi_writeback *
unlocked_inode_to_wb_begin(struct inode *inode, bool *lockedp)
{
	return inode_to_wb(inode);
}

static inline void unlocked_inode_to_wb_end(struct inode *inode, bool locked)
{
}

474 475 476 477 478 479 480 481
static inline void wb_memcg_offline(struct mem_cgroup *memcg)
{
}

static inline void wb_blkcg_offline(struct blkcg *blkcg)
{
}

482 483 484 485 486
static inline int inode_congested(struct inode *inode, int cong_bits)
{
	return wb_congested(&inode_to_bdi(inode)->wb, cong_bits);
}

487 488
#endif	/* CONFIG_CGROUP_WRITEBACK */

489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504
static inline int inode_read_congested(struct inode *inode)
{
	return inode_congested(inode, 1 << WB_sync_congested);
}

static inline int inode_write_congested(struct inode *inode)
{
	return inode_congested(inode, 1 << WB_async_congested);
}

static inline int inode_rw_congested(struct inode *inode)
{
	return inode_congested(inode, (1 << WB_sync_congested) |
				      (1 << WB_async_congested));
}

505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525
static inline int bdi_congested(struct backing_dev_info *bdi, int cong_bits)
{
	return wb_congested(&bdi->wb, cong_bits);
}

static inline int bdi_read_congested(struct backing_dev_info *bdi)
{
	return bdi_congested(bdi, 1 << WB_sync_congested);
}

static inline int bdi_write_congested(struct backing_dev_info *bdi)
{
	return bdi_congested(bdi, 1 << WB_async_congested);
}

static inline int bdi_rw_congested(struct backing_dev_info *bdi)
{
	return bdi_congested(bdi, (1 << WB_sync_congested) |
				  (1 << WB_async_congested));
}

526
#endif	/* _LINUX_BACKING_DEV_H */