page-writeback.c 29.2 KB
Newer Older
L
Linus Torvalds 已提交
1
/*
2
 * mm/page-writeback.c
L
Linus Torvalds 已提交
3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23
 *
 * Copyright (C) 2002, Linus Torvalds.
 *
 * Contains functions related to writing back dirty pages at the
 * address_space level.
 *
 * 10Apr2002	akpm@zip.com.au
 *		Initial version
 */

#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/spinlock.h>
#include <linux/fs.h>
#include <linux/mm.h>
#include <linux/swap.h>
#include <linux/slab.h>
#include <linux/pagemap.h>
#include <linux/writeback.h>
#include <linux/init.h>
#include <linux/backing-dev.h>
24
#include <linux/task_io_accounting_ops.h>
L
Linus Torvalds 已提交
25 26
#include <linux/blkdev.h>
#include <linux/mpage.h>
27
#include <linux/rmap.h>
L
Linus Torvalds 已提交
28 29 30 31 32 33
#include <linux/percpu.h>
#include <linux/notifier.h>
#include <linux/smp.h>
#include <linux/sysctl.h>
#include <linux/cpu.h>
#include <linux/syscalls.h>
34
#include <linux/buffer_head.h>
35
#include <linux/pagevec.h>
L
Linus Torvalds 已提交
36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51

/*
 * The maximum number of pages to writeout in a single bdflush/kupdate
 * operation.  We do this so we don't hold I_LOCK against an inode for
 * enormous amounts of time, which would block a userspace task which has
 * been forced to throttle against that inode.  Also, the code reevaluates
 * the dirty each time it has written this many pages.
 */
#define MAX_WRITEBACK_PAGES	1024

/*
 * After a CPU has dirtied this many pages, balance_dirty_pages_ratelimited
 * will look to see if it needs to force writeback or throttling.
 */
static long ratelimit_pages = 32;

52
static int dirty_exceeded __cacheline_aligned_in_smp;	/* Dirty mem may be over limit */
L
Linus Torvalds 已提交
53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69

/*
 * When balance_dirty_pages decides that the caller needs to perform some
 * non-background writeback, this is how many pages it will attempt to write.
 * It should be somewhat larger than RATELIMIT_PAGES to ensure that reasonably
 * large amounts of I/O are submitted.
 */
static inline long sync_writeback_pages(void)
{
	return ratelimit_pages + ratelimit_pages / 2;
}

/* The following parameters are exported via /proc/sys/vm */

/*
 * Start background writeback (via pdflush) at this percentage
 */
70
int dirty_background_ratio = 5;
L
Linus Torvalds 已提交
71 72 73 74

/*
 * The generator of dirty data starts writeback at this percentage
 */
75
int vm_dirty_ratio = 10;
L
Linus Torvalds 已提交
76 77

/*
78
 * The interval between `kupdate'-style writebacks, in jiffies
L
Linus Torvalds 已提交
79
 */
80
int dirty_writeback_interval = 5 * HZ;
L
Linus Torvalds 已提交
81 82

/*
83
 * The longest number of jiffies for which data is allowed to remain dirty
L
Linus Torvalds 已提交
84
 */
85
int dirty_expire_interval = 30 * HZ;
L
Linus Torvalds 已提交
86 87 88 89 90 91 92

/*
 * Flag that makes the machine dump writes/reads and block dirtyings.
 */
int block_dump;

/*
93 94
 * Flag that puts the machine in "laptop mode". Doubles as a timeout in jiffies:
 * a full sync is triggered after this time elapses without any disk activity.
L
Linus Torvalds 已提交
95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121
 */
int laptop_mode;

EXPORT_SYMBOL(laptop_mode);

/* End of sysctl-exported parameters */


static void background_writeout(unsigned long _min_pages);

/*
 * Work out the current dirty-memory clamping and background writeout
 * thresholds.
 *
 * The main aim here is to lower them aggressively if there is a lot of mapped
 * memory around.  To avoid stressing page reclaim with lots of unreclaimable
 * pages.  It is better to clamp down on writers than to start swapping, and
 * performing lots of scanning.
 *
 * We only allow 1/2 of the currently-unmapped memory to be dirtied.
 *
 * We don't permit the clamping level to fall below 5% - that is getting rather
 * excessive.
 *
 * We make sure that the background writeout level is below the adjusted
 * clamping level.
 */
122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159

static unsigned long highmem_dirtyable_memory(unsigned long total)
{
#ifdef CONFIG_HIGHMEM
	int node;
	unsigned long x = 0;

	for_each_online_node(node) {
		struct zone *z =
			&NODE_DATA(node)->node_zones[ZONE_HIGHMEM];

		x += zone_page_state(z, NR_FREE_PAGES)
			+ zone_page_state(z, NR_INACTIVE)
			+ zone_page_state(z, NR_ACTIVE);
	}
	/*
	 * Make sure that the number of highmem pages is never larger
	 * than the number of the total dirtyable memory. This can only
	 * occur in very strange VM situations but we want to make sure
	 * that this does not occur.
	 */
	return min(x, total);
#else
	return 0;
#endif
}

static unsigned long determine_dirtyable_memory(void)
{
	unsigned long x;

	x = global_page_state(NR_FREE_PAGES)
		+ global_page_state(NR_INACTIVE)
		+ global_page_state(NR_ACTIVE);
	x -= highmem_dirtyable_memory(x);
	return x + 1;	/* Ensure that we never return 0 */
}

L
Linus Torvalds 已提交
160
static void
161 162
get_dirty_limits(long *pbackground, long *pdirty,
					struct address_space *mapping)
L
Linus Torvalds 已提交
163 164 165 166 167 168
{
	int background_ratio;		/* Percentages */
	int dirty_ratio;
	int unmapped_ratio;
	long background;
	long dirty;
169
	unsigned long available_memory = determine_dirtyable_memory();
L
Linus Torvalds 已提交
170 171
	struct task_struct *tsk;

172 173
	unmapped_ratio = 100 - ((global_page_state(NR_FILE_MAPPED) +
				global_page_state(NR_ANON_PAGES)) * 100) /
174
					available_memory;
L
Linus Torvalds 已提交
175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220

	dirty_ratio = vm_dirty_ratio;
	if (dirty_ratio > unmapped_ratio / 2)
		dirty_ratio = unmapped_ratio / 2;

	if (dirty_ratio < 5)
		dirty_ratio = 5;

	background_ratio = dirty_background_ratio;
	if (background_ratio >= dirty_ratio)
		background_ratio = dirty_ratio / 2;

	background = (background_ratio * available_memory) / 100;
	dirty = (dirty_ratio * available_memory) / 100;
	tsk = current;
	if (tsk->flags & PF_LESS_THROTTLE || rt_task(tsk)) {
		background += background / 4;
		dirty += dirty / 4;
	}
	*pbackground = background;
	*pdirty = dirty;
}

/*
 * balance_dirty_pages() must be called by processes which are generating dirty
 * data.  It looks at the number of dirty pages in the machine and will force
 * the caller to perform writeback if the system is over `vm_dirty_ratio'.
 * If we're over `background_thresh' then pdflush is woken to perform some
 * writeout.
 */
static void balance_dirty_pages(struct address_space *mapping)
{
	long nr_reclaimable;
	long background_thresh;
	long dirty_thresh;
	unsigned long pages_written = 0;
	unsigned long write_chunk = sync_writeback_pages();

	struct backing_dev_info *bdi = mapping->backing_dev_info;

	for (;;) {
		struct writeback_control wbc = {
			.bdi		= bdi,
			.sync_mode	= WB_SYNC_NONE,
			.older_than_this = NULL,
			.nr_to_write	= write_chunk,
221
			.range_cyclic	= 1,
L
Linus Torvalds 已提交
222 223
		};

224 225 226 227 228 229
		get_dirty_limits(&background_thresh, &dirty_thresh, mapping);
		nr_reclaimable = global_page_state(NR_FILE_DIRTY) +
					global_page_state(NR_UNSTABLE_NFS);
		if (nr_reclaimable + global_page_state(NR_WRITEBACK) <=
			dirty_thresh)
				break;
L
Linus Torvalds 已提交
230

231 232
		if (!dirty_exceeded)
			dirty_exceeded = 1;
L
Linus Torvalds 已提交
233 234 235 236 237 238 239 240 241

		/* Note: nr_reclaimable denotes nr_dirty + nr_unstable.
		 * Unstable writes are a feature of certain networked
		 * filesystems (i.e. NFS) in which data may have been
		 * written to the server's write cache, but has not yet
		 * been flushed to permanent storage.
		 */
		if (nr_reclaimable) {
			writeback_inodes(&wbc);
242 243 244 245 246 247 248 249
			get_dirty_limits(&background_thresh,
					 	&dirty_thresh, mapping);
			nr_reclaimable = global_page_state(NR_FILE_DIRTY) +
					global_page_state(NR_UNSTABLE_NFS);
			if (nr_reclaimable +
				global_page_state(NR_WRITEBACK)
					<= dirty_thresh)
						break;
L
Linus Torvalds 已提交
250 251 252 253
			pages_written += write_chunk - wbc.nr_to_write;
			if (pages_written >= write_chunk)
				break;		/* We've done our duty */
		}
254
		congestion_wait(WRITE, HZ/10);
L
Linus Torvalds 已提交
255 256
	}

257 258 259
	if (nr_reclaimable + global_page_state(NR_WRITEBACK)
		<= dirty_thresh && dirty_exceeded)
			dirty_exceeded = 0;
L
Linus Torvalds 已提交
260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276

	if (writeback_in_progress(bdi))
		return;		/* pdflush is already working this queue */

	/*
	 * In laptop mode, we wait until hitting the higher threshold before
	 * starting background writeout, and then write out all the way down
	 * to the lower threshold.  So slow writers cause minimal disk activity.
	 *
	 * In normal mode, we start background writeout at the lower
	 * background_thresh, to keep the amount of dirty memory low.
	 */
	if ((laptop_mode && pages_written) ||
	     (!laptop_mode && (nr_reclaimable > background_thresh)))
		pdflush_operation(background_writeout, 0);
}

277
void set_page_dirty_balance(struct page *page, int page_mkwrite)
P
Peter Zijlstra 已提交
278
{
279
	if (set_page_dirty(page) || page_mkwrite) {
P
Peter Zijlstra 已提交
280 281 282 283 284 285 286
		struct address_space *mapping = page_mapping(page);

		if (mapping)
			balance_dirty_pages_ratelimited(mapping);
	}
}

L
Linus Torvalds 已提交
287
/**
288
 * balance_dirty_pages_ratelimited_nr - balance dirty memory state
289
 * @mapping: address_space which was dirtied
290
 * @nr_pages_dirtied: number of pages which the caller has just dirtied
L
Linus Torvalds 已提交
291 292 293 294 295 296 297 298 299 300
 *
 * Processes which are dirtying memory should call in here once for each page
 * which was newly dirtied.  The function will periodically check the system's
 * dirty state and will initiate writeback if needed.
 *
 * On really big machines, get_writeback_state is expensive, so try to avoid
 * calling it too often (ratelimiting).  But once we're over the dirty memory
 * limit we decrease the ratelimiting by a lot, to prevent individual processes
 * from overshooting the limit by (ratelimit_pages) each.
 */
301 302
void balance_dirty_pages_ratelimited_nr(struct address_space *mapping,
					unsigned long nr_pages_dirtied)
L
Linus Torvalds 已提交
303
{
304 305 306
	static DEFINE_PER_CPU(unsigned long, ratelimits) = 0;
	unsigned long ratelimit;
	unsigned long *p;
L
Linus Torvalds 已提交
307 308 309 310 311 312 313 314 315

	ratelimit = ratelimit_pages;
	if (dirty_exceeded)
		ratelimit = 8;

	/*
	 * Check the rate limiting. Also, we do not want to throttle real-time
	 * tasks in balance_dirty_pages(). Period.
	 */
316 317 318 319 320 321
	preempt_disable();
	p =  &__get_cpu_var(ratelimits);
	*p += nr_pages_dirtied;
	if (unlikely(*p >= ratelimit)) {
		*p = 0;
		preempt_enable();
L
Linus Torvalds 已提交
322 323 324
		balance_dirty_pages(mapping);
		return;
	}
325
	preempt_enable();
L
Linus Torvalds 已提交
326
}
327
EXPORT_SYMBOL(balance_dirty_pages_ratelimited_nr);
L
Linus Torvalds 已提交
328

329
void throttle_vm_writeout(gfp_t gfp_mask)
L
Linus Torvalds 已提交
330 331 332 333
{
	long background_thresh;
	long dirty_thresh;

334 335 336 337 338 339 340 341 342 343
	if ((gfp_mask & (__GFP_FS|__GFP_IO)) != (__GFP_FS|__GFP_IO)) {
		/*
		 * The caller might hold locks which can prevent IO completion
		 * or progress in the filesystem.  So we cannot just sit here
		 * waiting for IO to complete.
		 */
		congestion_wait(WRITE, HZ/10);
		return;
	}

L
Linus Torvalds 已提交
344
        for ( ; ; ) {
345
		get_dirty_limits(&background_thresh, &dirty_thresh, NULL);
L
Linus Torvalds 已提交
346 347 348 349 350 351 352

                /*
                 * Boost the allowable dirty threshold a bit for page
                 * allocators so they don't get DoS'ed by heavy writers
                 */
                dirty_thresh += dirty_thresh / 10;      /* wheeee... */

353 354 355
                if (global_page_state(NR_UNSTABLE_NFS) +
			global_page_state(NR_WRITEBACK) <= dirty_thresh)
                        	break;
356
                congestion_wait(WRITE, HZ/10);
L
Linus Torvalds 已提交
357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372
        }
}

/*
 * writeback at least _min_pages, and keep writing until the amount of dirty
 * memory is less than the background threshold, or until we're all clean.
 */
static void background_writeout(unsigned long _min_pages)
{
	long min_pages = _min_pages;
	struct writeback_control wbc = {
		.bdi		= NULL,
		.sync_mode	= WB_SYNC_NONE,
		.older_than_this = NULL,
		.nr_to_write	= 0,
		.nonblocking	= 1,
373
		.range_cyclic	= 1,
L
Linus Torvalds 已提交
374 375 376 377 378 379
	};

	for ( ; ; ) {
		long background_thresh;
		long dirty_thresh;

380 381 382
		get_dirty_limits(&background_thresh, &dirty_thresh, NULL);
		if (global_page_state(NR_FILE_DIRTY) +
			global_page_state(NR_UNSTABLE_NFS) < background_thresh
L
Linus Torvalds 已提交
383 384 385 386 387 388 389 390 391
				&& min_pages <= 0)
			break;
		wbc.encountered_congestion = 0;
		wbc.nr_to_write = MAX_WRITEBACK_PAGES;
		wbc.pages_skipped = 0;
		writeback_inodes(&wbc);
		min_pages -= MAX_WRITEBACK_PAGES - wbc.nr_to_write;
		if (wbc.nr_to_write > 0 || wbc.pages_skipped > 0) {
			/* Wrote less than expected */
392
			congestion_wait(WRITE, HZ/10);
L
Linus Torvalds 已提交
393 394 395 396 397 398 399 400 401 402 403
			if (!wbc.encountered_congestion)
				break;
		}
	}
}

/*
 * Start writeback of `nr_pages' pages.  If `nr_pages' is zero, write back
 * the whole world.  Returns 0 if a pdflush thread was dispatched.  Returns
 * -1 if all pdflush threads were busy.
 */
404
int wakeup_pdflush(long nr_pages)
L
Linus Torvalds 已提交
405
{
406 407 408
	if (nr_pages == 0)
		nr_pages = global_page_state(NR_FILE_DIRTY) +
				global_page_state(NR_UNSTABLE_NFS);
L
Linus Torvalds 已提交
409 410 411 412 413 414
	return pdflush_operation(background_writeout, nr_pages);
}

static void wb_timer_fn(unsigned long unused);
static void laptop_timer_fn(unsigned long unused);

415 416
static DEFINE_TIMER(wb_timer, wb_timer_fn, 0, 0);
static DEFINE_TIMER(laptop_mode_wb_timer, laptop_timer_fn, 0, 0);
L
Linus Torvalds 已提交
417 418 419 420 421 422 423 424 425

/*
 * Periodic writeback of "old" data.
 *
 * 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.
 *
426 427
 * Try to run once per dirty_writeback_interval.  But if a writeback event
 * takes longer than a dirty_writeback_interval interval, then leave a
L
Linus Torvalds 已提交
428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445
 * one-second gap.
 *
 * 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.
 */
static void wb_kupdate(unsigned long arg)
{
	unsigned long oldest_jif;
	unsigned long start_jif;
	unsigned long next_jif;
	long nr_to_write;
	struct writeback_control wbc = {
		.bdi		= NULL,
		.sync_mode	= WB_SYNC_NONE,
		.older_than_this = &oldest_jif,
		.nr_to_write	= 0,
		.nonblocking	= 1,
		.for_kupdate	= 1,
446
		.range_cyclic	= 1,
L
Linus Torvalds 已提交
447 448 449 450
	};

	sync_supers();

451
	oldest_jif = jiffies - dirty_expire_interval;
L
Linus Torvalds 已提交
452
	start_jif = jiffies;
453
	next_jif = start_jif + dirty_writeback_interval;
454 455
	nr_to_write = global_page_state(NR_FILE_DIRTY) +
			global_page_state(NR_UNSTABLE_NFS) +
L
Linus Torvalds 已提交
456 457 458 459 460 461 462
			(inodes_stat.nr_inodes - inodes_stat.nr_unused);
	while (nr_to_write > 0) {
		wbc.encountered_congestion = 0;
		wbc.nr_to_write = MAX_WRITEBACK_PAGES;
		writeback_inodes(&wbc);
		if (wbc.nr_to_write > 0) {
			if (wbc.encountered_congestion)
463
				congestion_wait(WRITE, HZ/10);
L
Linus Torvalds 已提交
464 465 466 467 468 469 470
			else
				break;	/* All the old data is written */
		}
		nr_to_write -= MAX_WRITEBACK_PAGES - wbc.nr_to_write;
	}
	if (time_before(next_jif, jiffies + HZ))
		next_jif = jiffies + HZ;
471
	if (dirty_writeback_interval)
L
Linus Torvalds 已提交
472 473 474 475 476 477 478
		mod_timer(&wb_timer, next_jif);
}

/*
 * sysctl handler for /proc/sys/vm/dirty_writeback_centisecs
 */
int dirty_writeback_centisecs_handler(ctl_table *table, int write,
479
	struct file *file, void __user *buffer, size_t *length, loff_t *ppos)
L
Linus Torvalds 已提交
480
{
481
	proc_dointvec_userhz_jiffies(table, write, file, buffer, length, ppos);
482 483 484
	if (dirty_writeback_interval)
		mod_timer(&wb_timer, jiffies + dirty_writeback_interval);
	else
L
Linus Torvalds 已提交
485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511
		del_timer(&wb_timer);
	return 0;
}

static void wb_timer_fn(unsigned long unused)
{
	if (pdflush_operation(wb_kupdate, 0) < 0)
		mod_timer(&wb_timer, jiffies + HZ); /* delay 1 second */
}

static void laptop_flush(unsigned long unused)
{
	sys_sync();
}

static void laptop_timer_fn(unsigned long unused)
{
	pdflush_operation(laptop_flush, 0);
}

/*
 * We've spun up the disk and we're in laptop mode: schedule writeback
 * of all dirty data a few seconds from now.  If the flush is already scheduled
 * then push it back - the user is still using the disk.
 */
void laptop_io_completion(void)
{
512
	mod_timer(&laptop_mode_wb_timer, jiffies + laptop_mode);
L
Linus Torvalds 已提交
513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541
}

/*
 * We're in laptop mode and we've just synced. The sync's writes will have
 * caused another writeback to be scheduled by laptop_io_completion.
 * Nothing needs to be written back anymore, so we unschedule the writeback.
 */
void laptop_sync_completion(void)
{
	del_timer(&laptop_mode_wb_timer);
}

/*
 * If ratelimit_pages is too high then we can get into dirty-data overload
 * if a large number of processes all perform writes at the same time.
 * If it is too low then SMP machines will call the (expensive)
 * get_writeback_state too often.
 *
 * Here we set ratelimit_pages to a level which ensures that when all CPUs are
 * dirtying in parallel, we cannot go more than 3% (1/32) over the dirty memory
 * thresholds before writeback cuts in.
 *
 * But the limit should not be set too high.  Because it also controls the
 * amount of memory which the balance_dirty_pages() caller has to write back.
 * If this is too large then the caller will block on the IO queue all the
 * time.  So limit it to four megabytes - the balance_dirty_pages() caller
 * will write six megabyte chunks, max.
 */

542
void writeback_set_ratelimit(void)
L
Linus Torvalds 已提交
543
{
544
	ratelimit_pages = vm_total_pages / (num_online_cpus() * 32);
L
Linus Torvalds 已提交
545 546 547 548 549 550
	if (ratelimit_pages < 16)
		ratelimit_pages = 16;
	if (ratelimit_pages * PAGE_CACHE_SIZE > 4096 * 1024)
		ratelimit_pages = (4096 * 1024) / PAGE_CACHE_SIZE;
}

551
static int __cpuinit
L
Linus Torvalds 已提交
552 553
ratelimit_handler(struct notifier_block *self, unsigned long u, void *v)
{
554
	writeback_set_ratelimit();
555
	return NOTIFY_DONE;
L
Linus Torvalds 已提交
556 557
}

558
static struct notifier_block __cpuinitdata ratelimit_nb = {
L
Linus Torvalds 已提交
559 560 561 562 563
	.notifier_call	= ratelimit_handler,
	.next		= NULL,
};

/*
564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579
 * Called early on to tune the page writeback dirty limits.
 *
 * We used to scale dirty pages according to how total memory
 * related to pages that could be allocated for buffers (by
 * comparing nr_free_buffer_pages() to vm_total_pages.
 *
 * However, that was when we used "dirty_ratio" to scale with
 * all memory, and we don't do that any more. "dirty_ratio"
 * is now applied to total non-HIGHPAGE memory (by subtracting
 * totalhigh_pages from vm_total_pages), and as such we can't
 * get into the old insane situation any more where we had
 * large amounts of dirty pages compared to a small amount of
 * non-HIGHMEM memory.
 *
 * But we might still want to scale the dirty_ratio by how
 * much memory the box has..
L
Linus Torvalds 已提交
580 581 582
 */
void __init page_writeback_init(void)
{
583
	mod_timer(&wb_timer, jiffies + dirty_writeback_interval);
584
	writeback_set_ratelimit();
L
Linus Torvalds 已提交
585 586 587
	register_cpu_notifier(&ratelimit_nb);
}

588
/**
589
 * write_cache_pages - walk the list of dirty pages of the given address space and write all of them.
590 591
 * @mapping: address space structure to write
 * @wbc: subtract the number of written pages from *@wbc->nr_to_write
592 593
 * @writepage: function called for each page
 * @data: data passed to writepage function
594
 *
595
 * If a page is already under I/O, write_cache_pages() skips it, even
596 597 598 599 600 601 602
 * if it's dirty.  This is desirable behaviour for memory-cleaning writeback,
 * but it is INCORRECT for data-integrity system calls such as fsync().  fsync()
 * and msync() need to guarantee that all the data which was dirty at the time
 * the call was made get new I/O started against them.  If wbc->sync_mode is
 * WB_SYNC_ALL then we were called for data integrity and we must wait for
 * existing IO to complete.
 */
603 604 605
int write_cache_pages(struct address_space *mapping,
		      struct writeback_control *wbc, writepage_t writepage,
		      void *data)
606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672
{
	struct backing_dev_info *bdi = mapping->backing_dev_info;
	int ret = 0;
	int done = 0;
	struct pagevec pvec;
	int nr_pages;
	pgoff_t index;
	pgoff_t end;		/* Inclusive */
	int scanned = 0;
	int range_whole = 0;

	if (wbc->nonblocking && bdi_write_congested(bdi)) {
		wbc->encountered_congestion = 1;
		return 0;
	}

	pagevec_init(&pvec, 0);
	if (wbc->range_cyclic) {
		index = mapping->writeback_index; /* Start from prev offset */
		end = -1;
	} else {
		index = wbc->range_start >> PAGE_CACHE_SHIFT;
		end = wbc->range_end >> PAGE_CACHE_SHIFT;
		if (wbc->range_start == 0 && wbc->range_end == LLONG_MAX)
			range_whole = 1;
		scanned = 1;
	}
retry:
	while (!done && (index <= end) &&
	       (nr_pages = pagevec_lookup_tag(&pvec, mapping, &index,
					      PAGECACHE_TAG_DIRTY,
					      min(end - index, (pgoff_t)PAGEVEC_SIZE-1) + 1))) {
		unsigned i;

		scanned = 1;
		for (i = 0; i < nr_pages; i++) {
			struct page *page = pvec.pages[i];

			/*
			 * At this point we hold neither mapping->tree_lock nor
			 * lock on the page itself: the page may be truncated or
			 * invalidated (changing page->mapping to NULL), or even
			 * swizzled back from swapper_space to tmpfs file
			 * mapping
			 */
			lock_page(page);

			if (unlikely(page->mapping != mapping)) {
				unlock_page(page);
				continue;
			}

			if (!wbc->range_cyclic && page->index > end) {
				done = 1;
				unlock_page(page);
				continue;
			}

			if (wbc->sync_mode != WB_SYNC_NONE)
				wait_on_page_writeback(page);

			if (PageWriteback(page) ||
			    !clear_page_dirty_for_io(page)) {
				unlock_page(page);
				continue;
			}

673
			ret = (*writepage)(page, wbc, data);
674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699

			if (unlikely(ret == AOP_WRITEPAGE_ACTIVATE))
				unlock_page(page);
			if (ret || (--(wbc->nr_to_write) <= 0))
				done = 1;
			if (wbc->nonblocking && bdi_write_congested(bdi)) {
				wbc->encountered_congestion = 1;
				done = 1;
			}
		}
		pagevec_release(&pvec);
		cond_resched();
	}
	if (!scanned && !done) {
		/*
		 * We hit the last page and there is more work to be done: wrap
		 * back to the start of the file
		 */
		scanned = 1;
		index = 0;
		goto retry;
	}
	if (wbc->range_cyclic || (range_whole && wbc->nr_to_write > 0))
		mapping->writeback_index = index;
	return ret;
}
700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731
EXPORT_SYMBOL(write_cache_pages);

/*
 * Function used by generic_writepages to call the real writepage
 * function and set the mapping flags on error
 */
static int __writepage(struct page *page, struct writeback_control *wbc,
		       void *data)
{
	struct address_space *mapping = data;
	int ret = mapping->a_ops->writepage(page, wbc);
	mapping_set_error(mapping, ret);
	return ret;
}

/**
 * generic_writepages - walk the list of dirty pages of the given address space and writepage() all of them.
 * @mapping: address space structure to write
 * @wbc: subtract the number of written pages from *@wbc->nr_to_write
 *
 * This is a library function, which implements the writepages()
 * address_space_operation.
 */
int generic_writepages(struct address_space *mapping,
		       struct writeback_control *wbc)
{
	/* deal with chardevs and other special file */
	if (!mapping->a_ops->writepage)
		return 0;

	return write_cache_pages(mapping, wbc, __writepage, mapping);
}
732 733 734

EXPORT_SYMBOL(generic_writepages);

L
Linus Torvalds 已提交
735 736
int do_writepages(struct address_space *mapping, struct writeback_control *wbc)
{
737 738
	int ret;

L
Linus Torvalds 已提交
739 740
	if (wbc->nr_to_write <= 0)
		return 0;
741
	wbc->for_writepages = 1;
L
Linus Torvalds 已提交
742
	if (mapping->a_ops->writepages)
743
		ret = mapping->a_ops->writepages(mapping, wbc);
744 745 746 747
	else
		ret = generic_writepages(mapping, wbc);
	wbc->for_writepages = 0;
	return ret;
L
Linus Torvalds 已提交
748 749 750 751
}

/**
 * write_one_page - write out a single page and optionally wait on I/O
752 753
 * @page: the page to write
 * @wait: if true, wait on writeout
L
Linus Torvalds 已提交
754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788
 *
 * The page must be locked by the caller and will be unlocked upon return.
 *
 * write_one_page() returns a negative error code if I/O failed.
 */
int write_one_page(struct page *page, int wait)
{
	struct address_space *mapping = page->mapping;
	int ret = 0;
	struct writeback_control wbc = {
		.sync_mode = WB_SYNC_ALL,
		.nr_to_write = 1,
	};

	BUG_ON(!PageLocked(page));

	if (wait)
		wait_on_page_writeback(page);

	if (clear_page_dirty_for_io(page)) {
		page_cache_get(page);
		ret = mapping->a_ops->writepage(page, &wbc);
		if (ret == 0 && wait) {
			wait_on_page_writeback(page);
			if (PageError(page))
				ret = -EIO;
		}
		page_cache_release(page);
	} else {
		unlock_page(page);
	}
	return ret;
}
EXPORT_SYMBOL(write_one_page);

789 790 791 792 793 794 795 796 797 798
/*
 * For address_spaces which do not use buffers nor write back.
 */
int __set_page_dirty_no_writeback(struct page *page)
{
	if (!PageDirty(page))
		SetPageDirty(page);
	return 0;
}

L
Linus Torvalds 已提交
799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819
/*
 * For address_spaces which do not use buffers.  Just tag the page as dirty in
 * its radix tree.
 *
 * This is also used when a single buffer is being dirtied: we want to set the
 * page dirty in that case, but not all the buffers.  This is a "bottom-up"
 * dirtying, whereas __set_page_dirty_buffers() is a "top-down" dirtying.
 *
 * Most callers have locked the page, which pins the address_space in memory.
 * But zap_pte_range() does not lock the page, however in that case the
 * mapping is pinned by the vma's ->vm_file reference.
 *
 * We take care to handle the case where the page was truncated from the
 * mapping by re-checking page_mapping() insode tree_lock.
 */
int __set_page_dirty_nobuffers(struct page *page)
{
	if (!TestSetPageDirty(page)) {
		struct address_space *mapping = page_mapping(page);
		struct address_space *mapping2;

820 821 822 823 824 825 826
		if (!mapping)
			return 1;

		write_lock_irq(&mapping->tree_lock);
		mapping2 = page_mapping(page);
		if (mapping2) { /* Race with truncate? */
			BUG_ON(mapping2 != mapping);
827
			WARN_ON_ONCE(!PagePrivate(page) && !PageUptodate(page));
828
			if (mapping_cap_account_dirty(mapping)) {
829
				__inc_zone_page_state(page, NR_FILE_DIRTY);
830 831
				task_io_account_write(PAGE_CACHE_SIZE);
			}
832 833 834 835 836 837 838
			radix_tree_tag_set(&mapping->page_tree,
				page_index(page), PAGECACHE_TAG_DIRTY);
		}
		write_unlock_irq(&mapping->tree_lock);
		if (mapping->host) {
			/* !PageAnon && !swapper_space */
			__mark_inode_dirty(mapping->host, I_DIRTY_PAGES);
L
Linus Torvalds 已提交
839
		}
840
		return 1;
L
Linus Torvalds 已提交
841
	}
842
	return 0;
L
Linus Torvalds 已提交
843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867
}
EXPORT_SYMBOL(__set_page_dirty_nobuffers);

/*
 * When a writepage implementation decides that it doesn't want to write this
 * page for some reason, it should redirty the locked page via
 * redirty_page_for_writepage() and it should then unlock the page and return 0
 */
int redirty_page_for_writepage(struct writeback_control *wbc, struct page *page)
{
	wbc->pages_skipped++;
	return __set_page_dirty_nobuffers(page);
}
EXPORT_SYMBOL(redirty_page_for_writepage);

/*
 * If the mapping doesn't provide a set_page_dirty a_op, then
 * just fall through and assume that it wants buffer_heads.
 */
int fastcall set_page_dirty(struct page *page)
{
	struct address_space *mapping = page_mapping(page);

	if (likely(mapping)) {
		int (*spd)(struct page *) = mapping->a_ops->set_page_dirty;
868 869 870 871 872
#ifdef CONFIG_BLOCK
		if (!spd)
			spd = __set_page_dirty_buffers;
#endif
		return (*spd)(page);
L
Linus Torvalds 已提交
873
	}
874 875 876 877
	if (!PageDirty(page)) {
		if (!TestSetPageDirty(page))
			return 1;
	}
L
Linus Torvalds 已提交
878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895
	return 0;
}
EXPORT_SYMBOL(set_page_dirty);

/*
 * set_page_dirty() is racy if the caller has no reference against
 * page->mapping->host, and if the page is unlocked.  This is because another
 * CPU could truncate the page off the mapping and then free the mapping.
 *
 * Usually, the page _is_ locked, or the caller is a user-space process which
 * holds a reference on the inode by having an open file.
 *
 * In other cases, the page should be locked before running set_page_dirty().
 */
int set_page_dirty_lock(struct page *page)
{
	int ret;

896
	lock_page_nosync(page);
L
Linus Torvalds 已提交
897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920
	ret = set_page_dirty(page);
	unlock_page(page);
	return ret;
}
EXPORT_SYMBOL(set_page_dirty_lock);

/*
 * Clear a page's dirty flag, while caring for dirty memory accounting.
 * Returns true if the page was previously dirty.
 *
 * This is for preparing to put the page under writeout.  We leave the page
 * tagged as dirty in the radix tree so that a concurrent write-for-sync
 * can discover it via a PAGECACHE_TAG_DIRTY walk.  The ->writepage
 * implementation will run either set_page_writeback() or set_page_dirty(),
 * at which stage we bring the page's dirty flag and radix-tree dirty tag
 * back into sync.
 *
 * This incoherency between the page's dirty flag and radix-tree tag is
 * unfortunate, but it only exists while the page is locked.
 */
int clear_page_dirty_for_io(struct page *page)
{
	struct address_space *mapping = page_mapping(page);

921 922
	BUG_ON(!PageLocked(page));

923
	ClearPageReclaim(page);
924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951
	if (mapping && mapping_cap_account_dirty(mapping)) {
		/*
		 * Yes, Virginia, this is indeed insane.
		 *
		 * We use this sequence to make sure that
		 *  (a) we account for dirty stats properly
		 *  (b) we tell the low-level filesystem to
		 *      mark the whole page dirty if it was
		 *      dirty in a pagetable. Only to then
		 *  (c) clean the page again and return 1 to
		 *      cause the writeback.
		 *
		 * This way we avoid all nasty races with the
		 * dirty bit in multiple places and clearing
		 * them concurrently from different threads.
		 *
		 * Note! Normally the "set_page_dirty(page)"
		 * has no effect on the actual dirty bit - since
		 * that will already usually be set. But we
		 * need the side effects, and it can help us
		 * avoid races.
		 *
		 * We basically use the page "master dirty bit"
		 * as a serialization point for all the different
		 * threads doing their things.
		 */
		if (page_mkclean(page))
			set_page_dirty(page);
952 953 954 955 956 957 958 959 960 961
		/*
		 * We carefully synchronise fault handlers against
		 * installing a dirty pte and marking the page dirty
		 * at this point. We do this by having them hold the
		 * page lock at some point after installing their
		 * pte, but before marking the page dirty.
		 * Pages are always locked coming in here, so we get
		 * the desired exclusion. See mm/memory.c:do_wp_page()
		 * for more comments.
		 */
962
		if (TestClearPageDirty(page)) {
963
			dec_zone_page_state(page, NR_FILE_DIRTY);
964
			return 1;
L
Linus Torvalds 已提交
965
		}
966
		return 0;
L
Linus Torvalds 已提交
967
	}
968
	return TestClearPageDirty(page);
L
Linus Torvalds 已提交
969
}
970
EXPORT_SYMBOL(clear_page_dirty_for_io);
L
Linus Torvalds 已提交
971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989

int test_clear_page_writeback(struct page *page)
{
	struct address_space *mapping = page_mapping(page);
	int ret;

	if (mapping) {
		unsigned long flags;

		write_lock_irqsave(&mapping->tree_lock, flags);
		ret = TestClearPageWriteback(page);
		if (ret)
			radix_tree_tag_clear(&mapping->page_tree,
						page_index(page),
						PAGECACHE_TAG_WRITEBACK);
		write_unlock_irqrestore(&mapping->tree_lock, flags);
	} else {
		ret = TestClearPageWriteback(page);
	}
990 991
	if (ret)
		dec_zone_page_state(page, NR_WRITEBACK);
L
Linus Torvalds 已提交
992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016
	return ret;
}

int test_set_page_writeback(struct page *page)
{
	struct address_space *mapping = page_mapping(page);
	int ret;

	if (mapping) {
		unsigned long flags;

		write_lock_irqsave(&mapping->tree_lock, flags);
		ret = TestSetPageWriteback(page);
		if (!ret)
			radix_tree_tag_set(&mapping->page_tree,
						page_index(page),
						PAGECACHE_TAG_WRITEBACK);
		if (!PageDirty(page))
			radix_tree_tag_clear(&mapping->page_tree,
						page_index(page),
						PAGECACHE_TAG_DIRTY);
		write_unlock_irqrestore(&mapping->tree_lock, flags);
	} else {
		ret = TestSetPageWriteback(page);
	}
1017 1018
	if (!ret)
		inc_zone_page_state(page, NR_WRITEBACK);
L
Linus Torvalds 已提交
1019 1020 1021 1022 1023 1024
	return ret;

}
EXPORT_SYMBOL(test_set_page_writeback);

/*
N
Nick Piggin 已提交
1025
 * Return true if any of the pages in the mapping are marked with the
L
Linus Torvalds 已提交
1026 1027 1028 1029 1030
 * passed tag.
 */
int mapping_tagged(struct address_space *mapping, int tag)
{
	int ret;
N
Nick Piggin 已提交
1031
	rcu_read_lock();
L
Linus Torvalds 已提交
1032
	ret = radix_tree_tagged(&mapping->page_tree, tag);
N
Nick Piggin 已提交
1033
	rcu_read_unlock();
L
Linus Torvalds 已提交
1034 1035 1036
	return ret;
}
EXPORT_SYMBOL(mapping_tagged);