fs-writeback.c 53 KB
Newer Older
Linus Torvalds's avatar
Linus Torvalds committed
1 2 3 4 5 6 7 8 9 10
/*
 * fs/fs-writeback.c
 *
 * Copyright (C) 2002, Linus Torvalds.
 *
 * Contains all the functions related to writing back and waiting
 * upon dirty inodes against superblocks, and writing back dirty
 * pages against inodes.  ie: data writeback.  Writeout of the
 * inode itself is not handled here.
 *
11
 * 10Apr2002	Andrew Morton
Linus Torvalds's avatar
Linus Torvalds committed
12 13 14 15 16
 *		Split out of fs/inode.c
 *		Additions for address_space-based writeback
 */

#include <linux/kernel.h>
17
#include <linux/export.h>
Linus Torvalds's avatar
Linus Torvalds committed
18
#include <linux/spinlock.h>
19
#include <linux/slab.h>
Linus Torvalds's avatar
Linus Torvalds committed
20 21 22
#include <linux/sched.h>
#include <linux/fs.h>
#include <linux/mm.h>
23
#include <linux/pagemap.h>
24
#include <linux/kthread.h>
Linus Torvalds's avatar
Linus Torvalds committed
25 26 27
#include <linux/writeback.h>
#include <linux/blkdev.h>
#include <linux/backing-dev.h>
28
#include <linux/tracepoint.h>
29
#include <linux/device.h>
30
#include <linux/memcontrol.h>
31
#include "internal.h"
Linus Torvalds's avatar
Linus Torvalds committed
32

33 34 35 36 37
/*
 * 4MB minimal write chunk size
 */
#define MIN_WRITEBACK_PAGES	(4096UL >> (PAGE_CACHE_SHIFT - 10))

38 39 40 41
struct wb_completion {
	atomic_t		cnt;
};

42 43 44
/*
 * Passed into wb_writeback(), essentially a subset of writeback_control
 */
45
struct wb_writeback_work {
46 47
	long nr_pages;
	struct super_block *sb;
48
	unsigned long *older_than_this;
49
	enum writeback_sync_modes sync_mode;
50
	unsigned int tagged_writepages:1;
51 52 53
	unsigned int for_kupdate:1;
	unsigned int range_cyclic:1;
	unsigned int for_background:1;
54
	unsigned int for_sync:1;	/* sync(2) WB_SYNC_ALL writeback */
55
	unsigned int auto_free:1;	/* free on completion */
56 57
	unsigned int single_wait:1;
	unsigned int single_done:1;
58
	enum wb_reason reason;		/* why was writeback initiated? */
59

60
	struct list_head list;		/* pending work list */
61
	struct wb_completion *done;	/* set if the caller waits */
62 63
};

64 65 66 67 68 69 70 71 72 73 74 75 76
/*
 * If one wants to wait for one or more wb_writeback_works, each work's
 * ->done should be set to a wb_completion defined using the following
 * macro.  Once all work items are issued with wb_queue_work(), the caller
 * can wait for the completion of all using wb_wait_for_completion().  Work
 * items which are waited upon aren't freed automatically on completion.
 */
#define DEFINE_WB_COMPLETION_ONSTACK(cmpl)				\
	struct wb_completion cmpl = {					\
		.cnt		= ATOMIC_INIT(1),			\
	}


77 78 79 80 81 82 83 84 85 86 87 88
/*
 * If an inode is constantly having its pages dirtied, but then the
 * updates stop dirtytime_expire_interval seconds in the past, it's
 * possible for the worst case time between when an inode has its
 * timestamps updated and when they finally get written out to be two
 * dirtytime_expire_intervals.  We set the default to 12 hours (in
 * seconds), which means most of the time inodes will have their
 * timestamps written to disk after 12 hours, but in the worst case a
 * few inodes might not their timestamps updated for 24 hours.
 */
unsigned int dirtytime_expire_interval = 12 * 60 * 60;

Nick Piggin's avatar
Nick Piggin committed
89 90 91 92 93
static inline struct inode *wb_inode(struct list_head *head)
{
	return list_entry(head, struct inode, i_wb_list);
}

94 95 96 97 98 99 100 101
/*
 * Include the creation of the trace points after defining the
 * wb_writeback_work structure and inline functions so that the definition
 * remains local to this file.
 */
#define CREATE_TRACE_POINTS
#include <trace/events/writeback.h>

102 103
EXPORT_TRACEPOINT_SYMBOL_GPL(wbc_writepage);

104 105 106 107 108 109
static bool wb_io_lists_populated(struct bdi_writeback *wb)
{
	if (wb_has_dirty_io(wb)) {
		return false;
	} else {
		set_bit(WB_has_dirty_io, &wb->state);
110
		WARN_ON_ONCE(!wb->avg_write_bandwidth);
111 112
		atomic_long_add(wb->avg_write_bandwidth,
				&wb->bdi->tot_write_bandwidth);
113 114 115 116 117 118 119
		return true;
	}
}

static void wb_io_lists_depopulated(struct bdi_writeback *wb)
{
	if (wb_has_dirty_io(wb) && list_empty(&wb->b_dirty) &&
120
	    list_empty(&wb->b_io) && list_empty(&wb->b_more_io)) {
121
		clear_bit(WB_has_dirty_io, &wb->state);
122 123
		WARN_ON_ONCE(atomic_long_sub_return(wb->avg_write_bandwidth,
					&wb->bdi->tot_write_bandwidth) < 0);
124
	}
125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169
}

/**
 * inode_wb_list_move_locked - move an inode onto a bdi_writeback IO list
 * @inode: inode to be moved
 * @wb: target bdi_writeback
 * @head: one of @wb->b_{dirty|io|more_io}
 *
 * Move @inode->i_wb_list to @list of @wb and set %WB_has_dirty_io.
 * Returns %true if @inode is the first occupant of the !dirty_time IO
 * lists; otherwise, %false.
 */
static bool inode_wb_list_move_locked(struct inode *inode,
				      struct bdi_writeback *wb,
				      struct list_head *head)
{
	assert_spin_locked(&wb->list_lock);

	list_move(&inode->i_wb_list, head);

	/* dirty_time doesn't count as dirty_io until expiration */
	if (head != &wb->b_dirty_time)
		return wb_io_lists_populated(wb);

	wb_io_lists_depopulated(wb);
	return false;
}

/**
 * inode_wb_list_del_locked - remove an inode from its bdi_writeback IO list
 * @inode: inode to be removed
 * @wb: bdi_writeback @inode is being removed from
 *
 * Remove @inode which may be on one of @wb->b_{dirty|io|more_io} lists and
 * clear %WB_has_dirty_io if all are empty afterwards.
 */
static void inode_wb_list_del_locked(struct inode *inode,
				     struct bdi_writeback *wb)
{
	assert_spin_locked(&wb->list_lock);

	list_del_init(&inode->i_wb_list);
	wb_io_lists_depopulated(wb);
}

170
static void wb_wakeup(struct bdi_writeback *wb)
Jan Kara's avatar
Jan Kara committed
171
{
172 173 174 175
	spin_lock_bh(&wb->work_lock);
	if (test_bit(WB_registered, &wb->state))
		mod_delayed_work(bdi_wq, &wb->dwork, 0);
	spin_unlock_bh(&wb->work_lock);
Jan Kara's avatar
Jan Kara committed
176 177
}

178 179
static void wb_queue_work(struct bdi_writeback *wb,
			  struct wb_writeback_work *work)
180
{
181
	trace_writeback_queue(wb->bdi, work);
182

183
	spin_lock_bh(&wb->work_lock);
184 185 186
	if (!test_bit(WB_registered, &wb->state)) {
		if (work->single_wait)
			work->single_done = 1;
Jan Kara's avatar
Jan Kara committed
187
		goto out_unlock;
188
	}
189 190
	if (work->done)
		atomic_inc(&work->done->cnt);
191 192
	list_add_tail(&work->list, &wb->work_list);
	mod_delayed_work(bdi_wq, &wb->dwork, 0);
Jan Kara's avatar
Jan Kara committed
193
out_unlock:
194
	spin_unlock_bh(&wb->work_lock);
Linus Torvalds's avatar
Linus Torvalds committed
195 196
}

197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214
/**
 * wb_wait_for_completion - wait for completion of bdi_writeback_works
 * @bdi: bdi work items were issued to
 * @done: target wb_completion
 *
 * Wait for one or more work items issued to @bdi with their ->done field
 * set to @done, which should have been defined with
 * DEFINE_WB_COMPLETION_ONSTACK().  This function returns after all such
 * work items are completed.  Work items which are waited upon aren't freed
 * automatically on completion.
 */
static void wb_wait_for_completion(struct backing_dev_info *bdi,
				   struct wb_completion *done)
{
	atomic_dec(&done->cnt);		/* put down the initial count */
	wait_event(bdi->wb_waitq, !atomic_read(&done->cnt));
}

215 216
#ifdef CONFIG_CGROUP_WRITEBACK

217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246
void __inode_attach_wb(struct inode *inode, struct page *page)
{
	struct backing_dev_info *bdi = inode_to_bdi(inode);
	struct bdi_writeback *wb = NULL;

	if (inode_cgwb_enabled(inode)) {
		struct cgroup_subsys_state *memcg_css;

		if (page) {
			memcg_css = mem_cgroup_css_from_page(page);
			wb = wb_get_create(bdi, memcg_css, GFP_ATOMIC);
		} else {
			/* must pin memcg_css, see wb_get_create() */
			memcg_css = task_get_css(current, memory_cgrp_id);
			wb = wb_get_create(bdi, memcg_css, GFP_ATOMIC);
			css_put(memcg_css);
		}
	}

	if (!wb)
		wb = &bdi->wb;

	/*
	 * There may be multiple instances of this function racing to
	 * update the same inode.  Use cmpxchg() to tell the winner.
	 */
	if (unlikely(cmpxchg(&inode->i_wb, NULL, wb)))
		wb_put(wb);
}

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
/**
 * wbc_attach_and_unlock_inode - associate wbc with target inode and unlock it
 * @wbc: writeback_control of interest
 * @inode: target inode
 *
 * @inode is locked and about to be written back under the control of @wbc.
 * Record @inode's writeback context into @wbc and unlock the i_lock.  On
 * writeback completion, wbc_detach_inode() should be called.  This is used
 * to track the cgroup writeback context.
 */
void wbc_attach_and_unlock_inode(struct writeback_control *wbc,
				 struct inode *inode)
{
	wbc->wb = inode_to_wb(inode);
	wb_get(wbc->wb);
	spin_unlock(&inode->i_lock);
}

/**
 * wbc_detach_inode - disassociate wbc from its target inode
 * @wbc: writeback_control of interest
 *
 * To be called after a writeback attempt of an inode finishes and undoes
 * wbc_attach_and_unlock_inode().  Can be called under any context.
 */
void wbc_detach_inode(struct writeback_control *wbc)
{
	wb_put(wbc->wb);
	wbc->wb = NULL;
}

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
/**
 * inode_congested - test whether an inode is congested
 * @inode: inode to test for congestion
 * @cong_bits: mask of WB_[a]sync_congested bits to test
 *
 * Tests whether @inode is congested.  @cong_bits is the mask of congestion
 * bits to test and the return value is the mask of set bits.
 *
 * If cgroup writeback is enabled for @inode, the congestion state is
 * determined by whether the cgwb (cgroup bdi_writeback) for the blkcg
 * associated with @inode is congested; otherwise, the root wb's congestion
 * state is used.
 */
int inode_congested(struct inode *inode, int cong_bits)
{
	if (inode) {
		struct bdi_writeback *wb = inode_to_wb(inode);
		if (wb)
			return wb_congested(wb, cong_bits);
	}

	return wb_congested(&inode_to_bdi(inode)->wb, cong_bits);
}
EXPORT_SYMBOL_GPL(inode_congested);

303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328
/**
 * wb_wait_for_single_work - wait for completion of a single bdi_writeback_work
 * @bdi: bdi the work item was issued to
 * @work: work item to wait for
 *
 * Wait for the completion of @work which was issued to one of @bdi's
 * bdi_writeback's.  The caller must have set @work->single_wait before
 * issuing it.  This wait operates independently fo
 * wb_wait_for_completion() and also disables automatic freeing of @work.
 */
static void wb_wait_for_single_work(struct backing_dev_info *bdi,
				    struct wb_writeback_work *work)
{
	if (WARN_ON_ONCE(!work->single_wait))
		return;

	wait_event(bdi->wb_waitq, work->single_done);

	/*
	 * Paired with smp_wmb() in wb_do_writeback() and ensures that all
	 * modifications to @work prior to assertion of ->single_done is
	 * visible to the caller once this function returns.
	 */
	smp_rmb();
}

329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356
/**
 * wb_split_bdi_pages - split nr_pages to write according to bandwidth
 * @wb: target bdi_writeback to split @nr_pages to
 * @nr_pages: number of pages to write for the whole bdi
 *
 * Split @wb's portion of @nr_pages according to @wb's write bandwidth in
 * relation to the total write bandwidth of all wb's w/ dirty inodes on
 * @wb->bdi.
 */
static long wb_split_bdi_pages(struct bdi_writeback *wb, long nr_pages)
{
	unsigned long this_bw = wb->avg_write_bandwidth;
	unsigned long tot_bw = atomic_long_read(&wb->bdi->tot_write_bandwidth);

	if (nr_pages == LONG_MAX)
		return LONG_MAX;

	/*
	 * This may be called on clean wb's and proportional distribution
	 * may not make sense, just use the original @nr_pages in those
	 * cases.  In general, we wanna err on the side of writing more.
	 */
	if (!tot_bw || this_bw >= tot_bw)
		return nr_pages;
	else
		return DIV_ROUND_UP_ULL((u64)nr_pages * this_bw, tot_bw);
}

357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430
/**
 * wb_clone_and_queue_work - clone a wb_writeback_work and issue it to a wb
 * @wb: target bdi_writeback
 * @base_work: source wb_writeback_work
 *
 * Try to make a clone of @base_work and issue it to @wb.  If cloning
 * succeeds, %true is returned; otherwise, @base_work is issued directly
 * and %false is returned.  In the latter case, the caller is required to
 * wait for @base_work's completion using wb_wait_for_single_work().
 *
 * A clone is auto-freed on completion.  @base_work never is.
 */
static bool wb_clone_and_queue_work(struct bdi_writeback *wb,
				    struct wb_writeback_work *base_work)
{
	struct wb_writeback_work *work;

	work = kmalloc(sizeof(*work), GFP_ATOMIC);
	if (work) {
		*work = *base_work;
		work->auto_free = 1;
		work->single_wait = 0;
	} else {
		work = base_work;
		work->auto_free = 0;
		work->single_wait = 1;
	}
	work->single_done = 0;
	wb_queue_work(wb, work);
	return work != base_work;
}

/**
 * bdi_split_work_to_wbs - split a wb_writeback_work to all wb's of a bdi
 * @bdi: target backing_dev_info
 * @base_work: wb_writeback_work to issue
 * @skip_if_busy: skip wb's which already have writeback in progress
 *
 * Split and issue @base_work to all wb's (bdi_writeback's) of @bdi which
 * have dirty inodes.  If @base_work->nr_page isn't %LONG_MAX, it's
 * distributed to the busy wbs according to each wb's proportion in the
 * total active write bandwidth of @bdi.
 */
static void bdi_split_work_to_wbs(struct backing_dev_info *bdi,
				  struct wb_writeback_work *base_work,
				  bool skip_if_busy)
{
	long nr_pages = base_work->nr_pages;
	int next_blkcg_id = 0;
	struct bdi_writeback *wb;
	struct wb_iter iter;

	might_sleep();

	if (!bdi_has_dirty_io(bdi))
		return;
restart:
	rcu_read_lock();
	bdi_for_each_wb(wb, bdi, &iter, next_blkcg_id) {
		if (!wb_has_dirty_io(wb) ||
		    (skip_if_busy && writeback_in_progress(wb)))
			continue;

		base_work->nr_pages = wb_split_bdi_pages(wb, nr_pages);
		if (!wb_clone_and_queue_work(wb, base_work)) {
			next_blkcg_id = wb->blkcg_css->id + 1;
			rcu_read_unlock();
			wb_wait_for_single_work(bdi, base_work);
			goto restart;
		}
	}
	rcu_read_unlock();
}

431 432 433 434 435 436 437
#else	/* CONFIG_CGROUP_WRITEBACK */

static long wb_split_bdi_pages(struct bdi_writeback *wb, long nr_pages)
{
	return nr_pages;
}

438 439 440 441 442 443 444 445 446 447 448 449 450 451 452
static void bdi_split_work_to_wbs(struct backing_dev_info *bdi,
				  struct wb_writeback_work *base_work,
				  bool skip_if_busy)
{
	might_sleep();

	if (bdi_has_dirty_io(bdi) &&
	    (!skip_if_busy || !writeback_in_progress(&bdi->wb))) {
		base_work->auto_free = 0;
		base_work->single_wait = 0;
		base_work->single_done = 0;
		wb_queue_work(&bdi->wb, base_work);
	}
}

453 454
#endif	/* CONFIG_CGROUP_WRITEBACK */

455 456
void wb_start_writeback(struct bdi_writeback *wb, long nr_pages,
			bool range_cyclic, enum wb_reason reason)
457
{
458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477
	struct wb_writeback_work *work;

	if (!wb_has_dirty_io(wb))
		return;

	/*
	 * This is WB_SYNC_NONE writeback, so if allocation fails just
	 * wakeup the thread for old dirty data writeback
	 */
	work = kzalloc(sizeof(*work), GFP_ATOMIC);
	if (!work) {
		trace_writeback_nowork(wb->bdi);
		wb_wakeup(wb);
		return;
	}

	work->sync_mode	= WB_SYNC_NONE;
	work->nr_pages	= nr_pages;
	work->range_cyclic = range_cyclic;
	work->reason	= reason;
478
	work->auto_free	= 1;
479 480

	wb_queue_work(wb, work);
481
}
482

483
/**
484 485
 * wb_start_background_writeback - start background writeback
 * @wb: bdi_writback to write from
486 487
 *
 * Description:
488
 *   This makes sure WB_SYNC_NONE background writeback happens. When
489
 *   this function returns, it is only guaranteed that for given wb
490 491
 *   some IO is happening if we are over background dirty threshold.
 *   Caller need not hold sb s_umount semaphore.
492
 */
493
void wb_start_background_writeback(struct bdi_writeback *wb)
494
{
495 496 497 498
	/*
	 * We just wake up the flusher thread. It will perform background
	 * writeback as soon as there is no other work to do.
	 */
499 500
	trace_writeback_wake_background(wb->bdi);
	wb_wakeup(wb);
Linus Torvalds's avatar
Linus Torvalds committed
501 502
}

503 504 505 506 507
/*
 * Remove the inode from the writeback list it is on.
 */
void inode_wb_list_del(struct inode *inode)
{
508
	struct bdi_writeback *wb = inode_to_wb(inode);
509

510
	spin_lock(&wb->list_lock);
511
	inode_wb_list_del_locked(inode, wb);
512
	spin_unlock(&wb->list_lock);
513 514
}

515 516 517 518 519
/*
 * Redirty an inode: set its when-it-was dirtied timestamp and move it to the
 * furthest end of its superblock's dirty-inode list.
 *
 * Before stamping the inode's ->dirtied_when, we check to see whether it is
520
 * already the most-recently-dirtied inode on the b_dirty list.  If that is
521 522 523
 * the case then the inode must have been redirtied while it was being written
 * out and we don't reset its dirtied_when.
 */
524
static void redirty_tail(struct inode *inode, struct bdi_writeback *wb)
525
{
526
	if (!list_empty(&wb->b_dirty)) {
527
		struct inode *tail;
528

Nick Piggin's avatar
Nick Piggin committed
529
		tail = wb_inode(wb->b_dirty.next);
530
		if (time_before(inode->dirtied_when, tail->dirtied_when))
531 532
			inode->dirtied_when = jiffies;
	}
533
	inode_wb_list_move_locked(inode, wb, &wb->b_dirty);
534 535
}

536
/*
537
 * requeue inode for re-scanning after bdi->b_io list is exhausted.
538
 */
539
static void requeue_io(struct inode *inode, struct bdi_writeback *wb)
540
{
541
	inode_wb_list_move_locked(inode, wb, &wb->b_more_io);
542 543
}

Joern Engel's avatar
Joern Engel committed
544 545
static void inode_sync_complete(struct inode *inode)
{
546
	inode->i_state &= ~I_SYNC;
547 548
	/* If inode is clean an unused, put it into LRU now... */
	inode_add_lru(inode);
549
	/* Waiters must see I_SYNC cleared before being woken up */
Joern Engel's avatar
Joern Engel committed
550 551 552 553
	smp_mb();
	wake_up_bit(&inode->i_state, __I_SYNC);
}

554 555 556 557 558 559 560 561
static bool inode_dirtied_after(struct inode *inode, unsigned long t)
{
	bool ret = time_after(inode->dirtied_when, t);
#ifndef CONFIG_64BIT
	/*
	 * For inodes being constantly redirtied, dirtied_when can get stuck.
	 * It _appears_ to be in the future, but is actually in distant past.
	 * This test is necessary to prevent such wrapped-around relative times
562
	 * from permanently stopping the whole bdi writeback.
563 564 565 566 567 568
	 */
	ret = ret && time_before_eq(inode->dirtied_when, jiffies);
#endif
	return ret;
}

569 570
#define EXPIRE_DIRTY_ATIME 0x0001

571
/*
572
 * Move expired (dirtied before work->older_than_this) dirty inodes from
Jan Kara's avatar
Jan Kara committed
573
 * @delaying_queue to @dispatch_queue.
574
 */
575
static int move_expired_inodes(struct list_head *delaying_queue,
576
			       struct list_head *dispatch_queue,
577
			       int flags,
578
			       struct wb_writeback_work *work)
579
{
580 581
	unsigned long *older_than_this = NULL;
	unsigned long expire_time;
582 583
	LIST_HEAD(tmp);
	struct list_head *pos, *node;
584
	struct super_block *sb = NULL;
585
	struct inode *inode;
586
	int do_sb_sort = 0;
587
	int moved = 0;
588

589 590
	if ((flags & EXPIRE_DIRTY_ATIME) == 0)
		older_than_this = work->older_than_this;
591 592
	else if (!work->for_sync) {
		expire_time = jiffies - (dirtytime_expire_interval * HZ);
593 594
		older_than_this = &expire_time;
	}
595
	while (!list_empty(delaying_queue)) {
Nick Piggin's avatar
Nick Piggin committed
596
		inode = wb_inode(delaying_queue->prev);
597 598
		if (older_than_this &&
		    inode_dirtied_after(inode, *older_than_this))
599
			break;
600 601
		list_move(&inode->i_wb_list, &tmp);
		moved++;
602 603
		if (flags & EXPIRE_DIRTY_ATIME)
			set_bit(__I_DIRTY_TIME_EXPIRED, &inode->i_state);
604 605
		if (sb_is_blkdev_sb(inode->i_sb))
			continue;
606 607 608
		if (sb && sb != inode->i_sb)
			do_sb_sort = 1;
		sb = inode->i_sb;
609 610
	}

611 612 613
	/* just one sb in list, splice to dispatch_queue and we're done */
	if (!do_sb_sort) {
		list_splice(&tmp, dispatch_queue);
614
		goto out;
615 616
	}

617 618
	/* Move inodes from one superblock together */
	while (!list_empty(&tmp)) {
Nick Piggin's avatar
Nick Piggin committed
619
		sb = wb_inode(tmp.prev)->i_sb;
620
		list_for_each_prev_safe(pos, node, &tmp) {
Nick Piggin's avatar
Nick Piggin committed
621
			inode = wb_inode(pos);
622
			if (inode->i_sb == sb)
Nick Piggin's avatar
Nick Piggin committed
623
				list_move(&inode->i_wb_list, dispatch_queue);
624
		}
625
	}
626 627
out:
	return moved;
628 629 630 631
}

/*
 * Queue all expired dirty inodes for io, eldest first.
632 633 634 635 636 637 638 639
 * Before
 *         newly dirtied     b_dirty    b_io    b_more_io
 *         =============>    gf         edc     BA
 * After
 *         newly dirtied     b_dirty    b_io    b_more_io
 *         =============>    g          fBAedc
 *                                           |
 *                                           +--> dequeue for IO
640
 */
641
static void queue_io(struct bdi_writeback *wb, struct wb_writeback_work *work)
642
{
643
	int moved;
644

645
	assert_spin_locked(&wb->list_lock);
646
	list_splice_init(&wb->b_more_io, &wb->b_io);
647 648 649
	moved = move_expired_inodes(&wb->b_dirty, &wb->b_io, 0, work);
	moved += move_expired_inodes(&wb->b_dirty_time, &wb->b_io,
				     EXPIRE_DIRTY_ATIME, work);
650 651
	if (moved)
		wb_io_lists_populated(wb);
652
	trace_writeback_queue_io(wb, work, moved);
653 654
}

655
static int write_inode(struct inode *inode, struct writeback_control *wbc)
656
{
Tejun Heo's avatar
Tejun Heo committed
657 658 659 660 661 662 663 664
	int ret;

	if (inode->i_sb->s_op->write_inode && !is_bad_inode(inode)) {
		trace_writeback_write_inode_start(inode, wbc);
		ret = inode->i_sb->s_op->write_inode(inode, wbc);
		trace_writeback_write_inode(inode, wbc);
		return ret;
	}
665
	return 0;
666 667
}

Linus Torvalds's avatar
Linus Torvalds committed
668
/*
669 670
 * Wait for writeback on an inode to complete. Called with i_lock held.
 * Caller must make sure inode cannot go away when we drop i_lock.
671
 */
672 673 674
static void __inode_wait_for_writeback(struct inode *inode)
	__releases(inode->i_lock)
	__acquires(inode->i_lock)
675 676 677 678 679
{
	DEFINE_WAIT_BIT(wq, &inode->i_state, __I_SYNC);
	wait_queue_head_t *wqh;

	wqh = bit_waitqueue(&inode->i_state, __I_SYNC);
680 681
	while (inode->i_state & I_SYNC) {
		spin_unlock(&inode->i_lock);
682 683
		__wait_on_bit(wqh, &wq, bit_wait,
			      TASK_UNINTERRUPTIBLE);
684
		spin_lock(&inode->i_lock);
685
	}
686 687
}

688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717
/*
 * Wait for writeback on an inode to complete. Caller must have inode pinned.
 */
void inode_wait_for_writeback(struct inode *inode)
{
	spin_lock(&inode->i_lock);
	__inode_wait_for_writeback(inode);
	spin_unlock(&inode->i_lock);
}

/*
 * Sleep until I_SYNC is cleared. This function must be called with i_lock
 * held and drops it. It is aimed for callers not holding any inode reference
 * so once i_lock is dropped, inode can go away.
 */
static void inode_sleep_on_writeback(struct inode *inode)
	__releases(inode->i_lock)
{
	DEFINE_WAIT(wait);
	wait_queue_head_t *wqh = bit_waitqueue(&inode->i_state, __I_SYNC);
	int sleep;

	prepare_to_wait(wqh, &wait, TASK_UNINTERRUPTIBLE);
	sleep = inode->i_state & I_SYNC;
	spin_unlock(&inode->i_lock);
	if (sleep)
		schedule();
	finish_wait(wqh, &wait);
}

718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740
/*
 * Find proper writeback list for the inode depending on its current state and
 * possibly also change of its state while we were doing writeback.  Here we
 * handle things such as livelock prevention or fairness of writeback among
 * inodes. This function can be called only by flusher thread - noone else
 * processes all inodes in writeback lists and requeueing inodes behind flusher
 * thread's back can have unexpected consequences.
 */
static void requeue_inode(struct inode *inode, struct bdi_writeback *wb,
			  struct writeback_control *wbc)
{
	if (inode->i_state & I_FREEING)
		return;

	/*
	 * Sync livelock prevention. Each inode is tagged and synced in one
	 * shot. If still dirty, it will be redirty_tail()'ed below.  Update
	 * the dirty time to prevent enqueue and sync it again.
	 */
	if ((inode->i_state & I_DIRTY) &&
	    (wbc->sync_mode == WB_SYNC_ALL || wbc->tagged_writepages))
		inode->dirtied_when = jiffies;

741 742 743 744 745 746 747 748 749
	if (wbc->pages_skipped) {
		/*
		 * writeback is not making progress due to locked
		 * buffers. Skip this inode for now.
		 */
		redirty_tail(inode, wb);
		return;
	}

750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774
	if (mapping_tagged(inode->i_mapping, PAGECACHE_TAG_DIRTY)) {
		/*
		 * We didn't write back all the pages.  nfs_writepages()
		 * sometimes bales out without doing anything.
		 */
		if (wbc->nr_to_write <= 0) {
			/* Slice used up. Queue for next turn. */
			requeue_io(inode, wb);
		} else {
			/*
			 * Writeback blocked by something other than
			 * congestion. Delay the inode for some time to
			 * avoid spinning on the CPU (100% iowait)
			 * retrying writeback of the dirty page/inode
			 * that cannot be performed immediately.
			 */
			redirty_tail(inode, wb);
		}
	} else if (inode->i_state & I_DIRTY) {
		/*
		 * Filesystems can dirty the inode during writeback operations,
		 * such as delayed allocation during submission or metadata
		 * updates after data IO completion.
		 */
		redirty_tail(inode, wb);
775
	} else if (inode->i_state & I_DIRTY_TIME) {
776
		inode->dirtied_when = jiffies;
777
		inode_wb_list_move_locked(inode, wb, &wb->b_dirty_time);
778 779
	} else {
		/* The inode is clean. Remove from writeback lists. */
780
		inode_wb_list_del_locked(inode, wb);
781 782 783
	}
}

784
/*
785 786 787
 * Write out an inode and its dirty pages. Do not update the writeback list
 * linkage. That is left to the caller. The caller is also responsible for
 * setting I_SYNC flag and calling inode_sync_complete() to clear it.
Linus Torvalds's avatar
Linus Torvalds committed
788 789
 */
static int
790
__writeback_single_inode(struct inode *inode, struct writeback_control *wbc)
Linus Torvalds's avatar
Linus Torvalds committed
791 792
{
	struct address_space *mapping = inode->i_mapping;
793
	long nr_to_write = wbc->nr_to_write;
794
	unsigned dirty;
Linus Torvalds's avatar
Linus Torvalds committed
795 796
	int ret;

797
	WARN_ON(!(inode->i_state & I_SYNC));
Linus Torvalds's avatar
Linus Torvalds committed
798

Tejun Heo's avatar
Tejun Heo committed
799 800
	trace_writeback_single_inode_start(inode, wbc, nr_to_write);

Linus Torvalds's avatar
Linus Torvalds committed
801 802
	ret = do_writepages(mapping, wbc);

803 804 805
	/*
	 * Make sure to wait on the data before writing out the metadata.
	 * This is important for filesystems that modify metadata on data
806 807 808
	 * I/O completion. We don't do it for sync(2) writeback because it has a
	 * separate, external IO completion path and ->sync_fs for guaranteeing
	 * inode metadata is written back correctly.
809
	 */
810
	if (wbc->sync_mode == WB_SYNC_ALL && !wbc->for_sync) {
811
		int err = filemap_fdatawait(mapping);
Linus Torvalds's avatar
Linus Torvalds committed
812 813 814 815
		if (ret == 0)
			ret = err;
	}

816 817 818 819 820
	/*
	 * Some filesystems may redirty the inode during the writeback
	 * due to delalloc, clear dirty metadata flags right before
	 * write_inode()
	 */
821
	spin_lock(&inode->i_lock);
822

823
	dirty = inode->i_state & I_DIRTY;
824 825 826 827 828 829 830 831 832 833 834
	if (inode->i_state & I_DIRTY_TIME) {
		if ((dirty & (I_DIRTY_SYNC | I_DIRTY_DATASYNC)) ||
		    unlikely(inode->i_state & I_DIRTY_TIME_EXPIRED) ||
		    unlikely(time_after(jiffies,
					(inode->dirtied_time_when +
					 dirtytime_expire_interval * HZ)))) {
			dirty |= I_DIRTY_TIME | I_DIRTY_TIME_EXPIRED;
			trace_writeback_lazytime(inode);
		}
	} else
		inode->i_state &= ~I_DIRTY_TIME_EXPIRED;
835
	inode->i_state &= ~dirty;
836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852

	/*
	 * Paired with smp_mb() in __mark_inode_dirty().  This allows
	 * __mark_inode_dirty() to test i_state without grabbing i_lock -
	 * either they see the I_DIRTY bits cleared or we see the dirtied
	 * inode.
	 *
	 * I_DIRTY_PAGES is always cleared together above even if @mapping
	 * still has dirty pages.  The flag is reinstated after smp_mb() if
	 * necessary.  This guarantees that either __mark_inode_dirty()
	 * sees clear I_DIRTY_PAGES or we see PAGECACHE_TAG_DIRTY.
	 */
	smp_mb();

	if (mapping_tagged(mapping, PAGECACHE_TAG_DIRTY))
		inode->i_state |= I_DIRTY_PAGES;

853
	spin_unlock(&inode->i_lock);
854

855 856
	if (dirty & I_DIRTY_TIME)
		mark_inode_dirty_sync(inode);
857
	/* Don't write the inode if only I_DIRTY_PAGES was set */
858
	if (dirty & ~I_DIRTY_PAGES) {
859
		int err = write_inode(inode, wbc);
Linus Torvalds's avatar
Linus Torvalds committed
860 861 862
		if (ret == 0)
			ret = err;
	}
863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890
	trace_writeback_single_inode(inode, wbc, nr_to_write);
	return ret;
}

/*
 * Write out an inode's dirty pages. Either the caller has an active reference
 * on the inode or the inode has I_WILL_FREE set.
 *
 * This function is designed to be called for writing back one inode which
 * we go e.g. from filesystem. Flusher thread uses __writeback_single_inode()
 * and does more profound writeback list handling in writeback_sb_inodes().
 */
static int
writeback_single_inode(struct inode *inode, struct bdi_writeback *wb,
		       struct writeback_control *wbc)
{
	int ret = 0;

	spin_lock(&inode->i_lock);
	if (!atomic_read(&inode->i_count))
		WARN_ON(!(inode->i_state & (I_WILL_FREE|I_FREEING)));
	else
		WARN_ON(inode->i_state & I_WILL_FREE);

	if (inode->i_state & I_SYNC) {
		if (wbc->sync_mode != WB_SYNC_ALL)
			goto out;
		/*
891 892 893
		 * It's a data-integrity sync. We must wait. Since callers hold
		 * inode reference or inode has I_WILL_FREE set, it cannot go
		 * away under us.
894
		 */
895
		__inode_wait_for_writeback(inode);
896 897 898
	}
	WARN_ON(inode->i_state & I_SYNC);
	/*
899 900 901 902 903 904
	 * Skip inode if it is clean and we have no outstanding writeback in
	 * WB_SYNC_ALL mode. We don't want to mess with writeback lists in this
	 * function since flusher thread may be doing for example sync in
	 * parallel and if we move the inode, it could get skipped. So here we
	 * make sure inode is on some writeback list and leave it there unless
	 * we have completely cleaned the inode.
905
	 */
906
	if (!(inode->i_state & I_DIRTY_ALL) &&
907 908
	    (wbc->sync_mode != WB_SYNC_ALL ||
	     !mapping_tagged(inode->i_mapping, PAGECACHE_TAG_WRITEBACK)))
909 910
		goto out;
	inode->i_state |= I_SYNC;
911
	wbc_attach_and_unlock_inode(wbc, inode);
912

913
	ret = __writeback_single_inode(inode, wbc);
Linus Torvalds's avatar
Linus Torvalds committed
914

915
	wbc_detach_inode(wbc);
916
	spin_lock(&wb->list_lock);
917
	spin_lock(&inode->i_lock);
918 919 920 921
	/*
	 * If inode is clean, remove it from writeback lists. Otherwise don't
	 * touch it. See comment above for explanation.
	 */
922
	if (!(inode->i_state & I_DIRTY_ALL))
923
		inode_wb_list_del_locked(inode, wb);
924
	spin_unlock(&wb->list_lock);
Joern Engel's avatar
Joern Engel committed
925
	inode_sync_complete(inode);
926 927
out:
	spin_unlock(&inode->i_lock);
Linus Torvalds's avatar
Linus Torvalds committed
928 929 930
	return ret;
}

931
static long writeback_chunk_size(struct bdi_writeback *wb,
932
				 struct wb_writeback_work *work)
933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950
{
	long pages;

	/*
	 * WB_SYNC_ALL mode does livelock avoidance by syncing dirty
	 * inodes/pages in one big loop. Setting wbc.nr_to_write=LONG_MAX
	 * here avoids calling into writeback_inodes_wb() more than once.
	 *
	 * The intended call sequence for WB_SYNC_ALL writeback is:
	 *
	 *      wb_writeback()
	 *          writeback_sb_inodes()       <== called only once
	 *              write_cache_pages()     <== called once for each inode
	 *                   (quickly) tag currently dirty pages
	 *                   (maybe slowly) sync all tagged pages
	 */
	if (work->sync_mode == WB_SYNC_ALL || work->tagged_writepages)
		pages = LONG_MAX;
951
	else {
952
		pages = min(wb->avg_write_bandwidth / 2,
953
			    global_wb_domain.dirty_limit / DIRTY_SCOPE);
954 955 956 957
		pages = min(pages, work->nr_pages);
		pages = round_down(pages + MIN_WRITEBACK_PAGES,
				   MIN_WRITEBACK_PAGES);
	}
958 959 960 961

	return pages;
}

962 963
/*
 * Write a portion of b_io inodes which belong to @sb.
964
 *
965
 * Return the number of pages and/or inodes written.
966
 */
967 968 969
static long writeback_sb_inodes(struct super_block *sb,
				struct bdi_writeback *wb,
				struct wb_writeback_work *work)
Linus Torvalds's avatar
Linus Torvalds committed
970
{
971 972 973 974 975
	struct writeback_control wbc = {
		.sync_mode		= work->sync_mode,
		.tagged_writepages	= work->tagged_writepages,
		.for_kupdate		= work->for_kupdate,
		.for_background		= work->for_background,
976
		.for_sync		= work->for_sync,
977 978 979 980 981 982 983 984
		.range_cyclic		= work->range_cyclic,
		.range_start		= 0,
		.range_end		= LLONG_MAX,
	};
	unsigned long start_time = jiffies;
	long write_chunk;
	long wrote = 0;  /* count both pages and inodes */

985
	while (!list_empty(&wb->b_io)) {
Nick Piggin's avatar
Nick Piggin committed
986
		struct inode *inode = wb_inode(wb->b_io.prev);
987 988

		if (inode->i_sb != sb) {
989
			if (work->sb) {
990 991 992 993 994
				/*
				 * We only want to write back data for this
				 * superblock, move all inodes not belonging
				 * to it back onto the dirty list.
				 */
995
				redirty_tail(inode, wb);
996 997 998 999 1000 1001 1002 1003
				continue;
			}

			/*
			 * The inode belongs to a different superblock.
			 * Bounce back to the caller to unpin this and
			 * pin the next superblock.
			 */
1004
			break;
1005 1006
		}

1007
		/*
1008 1009
		 * Don't bother with new inodes or inodes being freed, first
		 * kind does not need periodic writeout yet, and for the latter
1010 1011
		 * kind writeout is handled by the freer.
		 */
1012
		spin_lock(&inode->i_lock);
1013
		if (inode->i_state & (I_NEW | I_FREEING | I_WILL_FREE)) {
1014
			spin_unlock(&inode->i_lock);
1015
			redirty_tail(inode, wb);
1016 1017
			continue;
		}
1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032
		if ((inode->i_state & I_SYNC) && wbc.sync_mode != WB_SYNC_ALL) {
			/*
			 * If this inode is locked for writeback and we are not
			 * doing writeback-for-data-integrity, move it to
			 * b_more_io so that writeback can proceed with the
			 * other inodes on s_io.
			 *
			 * We'll have another go at writing back this inode
			 * when we completed a full scan of b_io.
			 */
			spin_unlock(&inode->i_lock);
			requeue_io(inode, wb);
			trace_writeback_sb_inodes_requeue(inode);
			continue;
		}
1033 1034
		spin_unlock(&wb->list_lock);

1035 1036 1037 1038 1039
		/*
		 * We already requeued the inode if it had I_SYNC set and we
		 * are doing WB_SYNC_NONE writeback. So this catches only the
		 * WB_SYNC_ALL case.
		 */
1040 1041 1042 1043
		if (inode->i_state & I_SYNC) {
			/* Wait for I_SYNC. This function drops i_lock... */
			inode_sleep_on_writeback(inode);
			/* Inode may be gone, start again */
1044
			spin_lock(&wb->list_lock);
1045 1046
			continue;
		}
1047
		inode->i_state |= I_SYNC;
1048
		wbc_attach_and_unlock_inode(&wbc, inode);
1049

1050
		write_chunk = writeback_chunk_size(wb, work);
1051 1052
		wbc.nr_to_write = write_chunk;
		wbc.pages_skipped = 0;
1053

1054 1055 1056 1057
		/*
		 * We use I_SYNC to pin the inode in memory. While it is set
		 * evict_inode() will wait so the inode cannot be freed.
		 */
1058
		__writeback_single_inode(inode, &wbc);
1059

1060
		wbc_detach_inode(&wbc);
1061 1062
		work->nr_pages -= write_chunk - wbc.nr_to_write;
		wrote += write_chunk - wbc.nr_to_write;
1063 1064
		spin_lock(&wb->list_lock);
		spin_lock(&inode->i_lock);
1065
		if (!(inode->i_state & I_DIRTY_ALL))
1066
			wrote++;
1067 1068
		requeue_inode(inode, wb, &wbc);
		inode_sync_complete(inode);
1069
		spin_unlock(&inode->i_lock);
1070
		cond_resched_lock(&wb->list_lock);
1071 1072 1073 1074 1075 1076 1077 1078 1079
		/*
		 * bail out to wb_writeback() often enough to check
		 * background threshold and other termination conditions.
		 */
		if (wrote) {
			if (time_is_before_jiffies(start_time + HZ / 10UL))
				break;
			if (work->nr_pages <= 0)
				break;
1080
		}
Linus Torvalds's avatar
Linus Torvalds committed
1081
	}
1082
	return wrote;
1083 1084
}

1085 1086
static long __writeback_inodes_wb(struct bdi_writeback *wb,
				  struct wb_writeback_work *work)
1087
{
1088 1089
	unsigned long start_time = jiffies;
	long wrote = 0;
Nick Piggin's avatar
Nick Piggin committed
1090

1091
	while (!list_empty(&wb->b_io)) {
Nick Piggin's avatar
Nick Piggin committed
1092
		struct inode *inode = wb_inode(wb->b_io.prev);
1093
		struct super_block *sb = inode->i_sb;
1094

1095
		if (!trylock_super(sb)) {
1096
			/*
1097
			 * trylock_super() may fail consistently due to
1098 1099 1100 1101
			 * s_umount being grabbed by someone else. Don't use
			 * requeue_io() to avoid busy retrying the inode/sb.
			 */
			redirty_tail(inode, wb);
1102
			continue;
1103
		}
1104
		wrote += writeback_sb_inodes(sb, wb, work);
1105
		up_read(&sb->s_umount);
1106

1107 1108 1109 1110 1111 1112 1113
		/* refer to the same tests at the end of writeback_sb_inodes */
		if (wrote) {
			if (time_is_before_jiffies(start_time + HZ / 10UL))
				break;
			if (work->nr_pages <= 0)
				break;
		}
1114
	}
1115
	/* Leave any unwritten inodes on b_io */
1116
	return wrote;
1117 1118
}

1119
static long writeback_inodes_wb(struct bdi_writeback *wb, long nr_pages,
1120
				enum wb_reason reason)
1121
{
1122 1123 1124 1125
	struct wb_writeback_work work = {
		.nr_pages	= nr_pages,
		.sync_mode	= WB_SYNC_NONE,
		.range_cyclic	= 1,
1126
		.reason		= reason,
1127
	};
1128

1129
	spin_lock(&wb->list_lock);
1130
	if (list_empty(&wb->b_io))
1131
		queue_io(wb, &work);
1132
	__writeback_inodes_wb(wb, &work);
1133
	spin_unlock(&wb->list_lock);
1134

1135 1136
	return nr_pages - work.nr_pages;
}
1137 1138 1139

/*
 * Explicit flushing or periodic writeback of "old" data.
1140
 *
1141 1142 1143 1144
 * Define "old": the first time one of an inode's pages is dirtied, we mark the
 * dirtying-time in the inode's address_space.  So this periodic writeback code
 * just walks the superblock inode list, writing back any inodes which are
 * older than a specific point in time.
1145
 *
1146 1147 1148
 * Try to run once per dirty_writeback_interval.  But if a writeback event
 * takes longer than a dirty_writeback_interval interval, then leave a
 * one-second gap.
1149
 *
1150 1151
 * older_than_this takes precedence over nr_to_write.  So we'll only write back
 * all dirty pages if they are all attached to "old" mappings.
1152
 */
1153
static long wb_writeback(struct bdi_writeback *wb,
1154
			 struct wb_writeback_work *work)
1155
{
1156
	unsigned long wb_start = jiffies;
1157
	long nr_pages = work->nr_pages;
1158
	unsigned long oldest_jif;
Jan Kara's avatar
Jan Kara committed
1159
	struct inode *inode;
1160
	long progress;
1161

1162 1163
	oldest_jif = jiffies;
	work->older_than_this = &oldest_jif;
Nick Piggin's avatar
Nick Piggin committed
1164