fs-writeback.c 22.4 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>
Jens Axboe's avatar
Jens Axboe committed
17
#include <linux/module.h>
Linus Torvalds's avatar
Linus Torvalds committed
18 19 20 21 22 23 24 25
#include <linux/spinlock.h>
#include <linux/sched.h>
#include <linux/fs.h>
#include <linux/mm.h>
#include <linux/writeback.h>
#include <linux/blkdev.h>
#include <linux/backing-dev.h>
#include <linux/buffer_head.h>
26
#include "internal.h"
Linus Torvalds's avatar
Linus Torvalds committed
27

28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66

/**
 * writeback_acquire - attempt to get exclusive writeback access to a device
 * @bdi: the device's backing_dev_info structure
 *
 * It is a waste of resources to have more than one pdflush thread blocked on
 * a single request queue.  Exclusion at the request_queue level is obtained
 * via a flag in the request_queue's backing_dev_info.state.
 *
 * Non-request_queue-backed address_spaces will share default_backing_dev_info,
 * unless they implement their own.  Which is somewhat inefficient, as this
 * may prevent concurrent writeback against multiple devices.
 */
static int writeback_acquire(struct backing_dev_info *bdi)
{
	return !test_and_set_bit(BDI_pdflush, &bdi->state);
}

/**
 * writeback_in_progress - determine whether there is writeback in progress
 * @bdi: the device's backing_dev_info structure.
 *
 * Determine whether there is writeback in progress against a backing device.
 */
int writeback_in_progress(struct backing_dev_info *bdi)
{
	return test_bit(BDI_pdflush, &bdi->state);
}

/**
 * writeback_release - relinquish exclusive writeback access against a device.
 * @bdi: the device's backing_dev_info structure
 */
static void writeback_release(struct backing_dev_info *bdi)
{
	BUG_ON(!writeback_in_progress(bdi));
	clear_bit(BDI_pdflush, &bdi->state);
}

Linus Torvalds's avatar
Linus Torvalds committed
67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130
/**
 *	__mark_inode_dirty -	internal function
 *	@inode: inode to mark
 *	@flags: what kind of dirty (i.e. I_DIRTY_SYNC)
 *	Mark an inode as dirty. Callers should use mark_inode_dirty or
 *  	mark_inode_dirty_sync.
 *
 * Put the inode on the super block's dirty list.
 *
 * CAREFUL! We mark it dirty unconditionally, but move it onto the
 * dirty list only if it is hashed or if it refers to a blockdev.
 * If it was not hashed, it will never be added to the dirty list
 * even if it is later hashed, as it will have been marked dirty already.
 *
 * In short, make sure you hash any inodes _before_ you start marking
 * them dirty.
 *
 * This function *must* be atomic for the I_DIRTY_PAGES case -
 * set_page_dirty() is called under spinlock in several places.
 *
 * Note that for blockdevs, inode->dirtied_when represents the dirtying time of
 * the block-special inode (/dev/hda1) itself.  And the ->dirtied_when field of
 * the kernel-internal blockdev inode represents the dirtying time of the
 * blockdev's pages.  This is why for I_DIRTY_PAGES we always use
 * page->mapping->host, so the page-dirtying time is recorded in the internal
 * blockdev inode.
 */
void __mark_inode_dirty(struct inode *inode, int flags)
{
	struct super_block *sb = inode->i_sb;

	/*
	 * Don't do this for I_DIRTY_PAGES - that doesn't actually
	 * dirty the inode itself
	 */
	if (flags & (I_DIRTY_SYNC | I_DIRTY_DATASYNC)) {
		if (sb->s_op->dirty_inode)
			sb->s_op->dirty_inode(inode);
	}

	/*
	 * make sure that changes are seen by all cpus before we test i_state
	 * -- mikulas
	 */
	smp_mb();

	/* avoid the locking if we can */
	if ((inode->i_state & flags) == flags)
		return;

	if (unlikely(block_dump)) {
		struct dentry *dentry = NULL;
		const char *name = "?";

		if (!list_empty(&inode->i_dentry)) {
			dentry = list_entry(inode->i_dentry.next,
					    struct dentry, d_alias);
			if (dentry && dentry->d_name.name)
				name = (const char *) dentry->d_name.name;
		}

		if (inode->i_ino || strcmp(inode->i_sb->s_id, "bdev"))
			printk(KERN_DEBUG
			       "%s(%d): dirtied inode %lu (%s) on %s\n",
131
			       current->comm, task_pid_nr(current), inode->i_ino,
Linus Torvalds's avatar
Linus Torvalds committed
132 133 134 135 136 137 138 139 140 141
			       name, inode->i_sb->s_id);
	}

	spin_lock(&inode_lock);
	if ((inode->i_state & flags) != flags) {
		const int was_dirty = inode->i_state & I_DIRTY;

		inode->i_state |= flags;

		/*
Joern Engel's avatar
Joern Engel committed
142
		 * If the inode is being synced, just update its dirty state.
Linus Torvalds's avatar
Linus Torvalds committed
143 144 145
		 * The unlocker will place the inode on the appropriate
		 * superblock list, based upon its state.
		 */
Joern Engel's avatar
Joern Engel committed
146
		if (inode->i_state & I_SYNC)
Linus Torvalds's avatar
Linus Torvalds committed
147 148 149 150 151 152 153 154 155 156 157 158 159 160
			goto out;

		/*
		 * Only add valid (hashed) inodes to the superblock's
		 * dirty list.  Add blockdev inodes as well.
		 */
		if (!S_ISBLK(inode->i_mode)) {
			if (hlist_unhashed(&inode->i_hash))
				goto out;
		}
		if (inode->i_state & (I_FREEING|I_CLEAR))
			goto out;

		/*
161
		 * If the inode was already on s_dirty/s_io/s_more_io, don't
Linus Torvalds's avatar
Linus Torvalds committed
162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181
		 * reposition it (that would break s_dirty time-ordering).
		 */
		if (!was_dirty) {
			inode->dirtied_when = jiffies;
			list_move(&inode->i_list, &sb->s_dirty);
		}
	}
out:
	spin_unlock(&inode_lock);
}

EXPORT_SYMBOL(__mark_inode_dirty);

static int write_inode(struct inode *inode, int sync)
{
	if (inode->i_sb->s_op->write_inode && !is_bad_inode(inode))
		return inode->i_sb->s_op->write_inode(inode, sync);
	return 0;
}

182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205
/*
 * 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
 * already the most-recently-dirtied inode on the s_dirty list.  If that is
 * the case then the inode must have been redirtied while it was being written
 * out and we don't reset its dirtied_when.
 */
static void redirty_tail(struct inode *inode)
{
	struct super_block *sb = inode->i_sb;

	if (!list_empty(&sb->s_dirty)) {
		struct inode *tail_inode;

		tail_inode = list_entry(sb->s_dirty.next, struct inode, i_list);
		if (!time_after_eq(inode->dirtied_when,
				tail_inode->dirtied_when))
			inode->dirtied_when = jiffies;
	}
	list_move(&inode->i_list, &sb->s_dirty);
}

206
/*
207
 * requeue inode for re-scanning after sb->s_io list is exhausted.
208
 */
209
static void requeue_io(struct inode *inode)
210
{
211
	list_move(&inode->i_list, &inode->i_sb->s_more_io);
212 213
}

Joern Engel's avatar
Joern Engel committed
214 215 216 217 218 219 220 221 222
static void inode_sync_complete(struct inode *inode)
{
	/*
	 * Prevent speculative execution through spin_unlock(&inode_lock);
	 */
	smp_mb();
	wake_up_bit(&inode->i_state, __I_SYNC);
}

223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249
/*
 * Move expired dirty inodes from @delaying_queue to @dispatch_queue.
 */
static void move_expired_inodes(struct list_head *delaying_queue,
			       struct list_head *dispatch_queue,
				unsigned long *older_than_this)
{
	while (!list_empty(delaying_queue)) {
		struct inode *inode = list_entry(delaying_queue->prev,
						struct inode, i_list);
		if (older_than_this &&
			time_after(inode->dirtied_when, *older_than_this))
			break;
		list_move(&inode->i_list, dispatch_queue);
	}
}

/*
 * Queue all expired dirty inodes for io, eldest first.
 */
static void queue_io(struct super_block *sb,
				unsigned long *older_than_this)
{
	list_splice_init(&sb->s_more_io, sb->s_io.prev);
	move_expired_inodes(&sb->s_dirty, &sb->s_io, older_than_this);
}

250 251 252 253 254 255 256 257
int sb_has_dirty_inodes(struct super_block *sb)
{
	return !list_empty(&sb->s_dirty) ||
	       !list_empty(&sb->s_io) ||
	       !list_empty(&sb->s_more_io);
}
EXPORT_SYMBOL(sb_has_dirty_inodes);

Linus Torvalds's avatar
Linus Torvalds committed
258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275
/*
 * Write a single inode's dirty pages and inode data out to disk.
 * If `wait' is set, wait on the writeout.
 *
 * The whole writeout design is quite complex and fragile.  We want to avoid
 * starvation of particular inodes when others are being redirtied, prevent
 * livelocks, etc.
 *
 * Called under inode_lock.
 */
static int
__sync_single_inode(struct inode *inode, struct writeback_control *wbc)
{
	unsigned dirty;
	struct address_space *mapping = inode->i_mapping;
	int wait = wbc->sync_mode == WB_SYNC_ALL;
	int ret;

Joern Engel's avatar
Joern Engel committed
276
	BUG_ON(inode->i_state & I_SYNC);
Linus Torvalds's avatar
Linus Torvalds committed
277

Joern Engel's avatar
Joern Engel committed
278
	/* Set I_SYNC, reset I_DIRTY */
Linus Torvalds's avatar
Linus Torvalds committed
279
	dirty = inode->i_state & I_DIRTY;
Joern Engel's avatar
Joern Engel committed
280
	inode->i_state |= I_SYNC;
Linus Torvalds's avatar
Linus Torvalds committed
281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300
	inode->i_state &= ~I_DIRTY;

	spin_unlock(&inode_lock);

	ret = do_writepages(mapping, wbc);

	/* Don't write the inode if only I_DIRTY_PAGES was set */
	if (dirty & (I_DIRTY_SYNC | I_DIRTY_DATASYNC)) {
		int err = write_inode(inode, wait);
		if (ret == 0)
			ret = err;
	}

	if (wait) {
		int err = filemap_fdatawait(mapping);
		if (ret == 0)
			ret = err;
	}

	spin_lock(&inode_lock);
Joern Engel's avatar
Joern Engel committed
301
	inode->i_state &= ~I_SYNC;
Linus Torvalds's avatar
Linus Torvalds committed
302 303 304 305 306 307
	if (!(inode->i_state & I_FREEING)) {
		if (!(inode->i_state & I_DIRTY) &&
		    mapping_tagged(mapping, PAGECACHE_TAG_DIRTY)) {
			/*
			 * We didn't write back all the pages.  nfs_writepages()
			 * sometimes bales out without doing anything. Redirty
308
			 * the inode; Move it from s_io onto s_more_io/s_dirty.
309 310 311 312 313 314 315 316 317
			 */
			/*
			 * akpm: if the caller was the kupdate function we put
			 * this inode at the head of s_dirty so it gets first
			 * consideration.  Otherwise, move it to the tail, for
			 * the reasons described there.  I'm not really sure
			 * how much sense this makes.  Presumably I had a good
			 * reasons for doing it this way, and I'd rather not
			 * muck with it at present.
Linus Torvalds's avatar
Linus Torvalds committed
318 319 320
			 */
			if (wbc->for_kupdate) {
				/*
321 322 323
				 * For the kupdate function we move the inode
				 * to s_more_io so it will get more writeout as
				 * soon as the queue becomes uncongested.
Linus Torvalds's avatar
Linus Torvalds committed
324 325
				 */
				inode->i_state |= I_DIRTY_PAGES;
326 327 328 329 330 331 332 333 334 335 336
				if (wbc->nr_to_write <= 0) {
					/*
					 * slice used up: queue for next turn
					 */
					requeue_io(inode);
				} else {
					/*
					 * somehow blocked: retry later
					 */
					redirty_tail(inode);
				}
Linus Torvalds's avatar
Linus Torvalds committed
337 338 339 340 341 342 343 344 345
			} else {
				/*
				 * Otherwise fully redirty the inode so that
				 * other inodes on this superblock will get some
				 * writeout.  Otherwise heavy writing to one
				 * file would indefinitely suspend writeout of
				 * all the other files.
				 */
				inode->i_state |= I_DIRTY_PAGES;
346
				redirty_tail(inode);
Linus Torvalds's avatar
Linus Torvalds committed
347 348 349 350 351 352
			}
		} else if (inode->i_state & I_DIRTY) {
			/*
			 * Someone redirtied the inode while were writing back
			 * the pages.
			 */
353
			redirty_tail(inode);
Linus Torvalds's avatar
Linus Torvalds committed
354 355 356 357 358 359 360 361 362 363 364 365
		} else if (atomic_read(&inode->i_count)) {
			/*
			 * The inode is clean, inuse
			 */
			list_move(&inode->i_list, &inode_in_use);
		} else {
			/*
			 * The inode is clean, unused
			 */
			list_move(&inode->i_list, &inode_unused);
		}
	}
Joern Engel's avatar
Joern Engel committed
366
	inode_sync_complete(inode);
Linus Torvalds's avatar
Linus Torvalds committed
367 368 369 370
	return ret;
}

/*
371 372 373
 * Write out an inode's dirty pages.  Called under inode_lock.  Either the
 * caller has ref on the inode (either via __iget or via syscall against an fd)
 * or the inode has I_WILL_FREE set (via generic_forget_inode)
Linus Torvalds's avatar
Linus Torvalds committed
374 375
 */
static int
376
__writeback_single_inode(struct inode *inode, struct writeback_control *wbc)
Linus Torvalds's avatar
Linus Torvalds committed
377 378 379
{
	wait_queue_head_t *wqh;

380
	if (!atomic_read(&inode->i_count))
381
		WARN_ON(!(inode->i_state & (I_WILL_FREE|I_FREEING)));
382 383 384
	else
		WARN_ON(inode->i_state & I_WILL_FREE);

Joern Engel's avatar
Joern Engel committed
385
	if ((wbc->sync_mode != WB_SYNC_ALL) && (inode->i_state & I_SYNC)) {
386 387
		/*
		 * We're skipping this inode because it's locked, and we're not
388 389 390 391
		 * doing writeback-for-data-integrity.  Move it to s_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 s_io.
392
		 */
393
		requeue_io(inode);
394
		return 0;
Linus Torvalds's avatar
Linus Torvalds committed
395 396 397 398 399
	}

	/*
	 * It's a data-integrity sync.  We must wait.
	 */
Joern Engel's avatar
Joern Engel committed
400 401
	if (inode->i_state & I_SYNC) {
		DEFINE_WAIT_BIT(wq, &inode->i_state, __I_SYNC);
Linus Torvalds's avatar
Linus Torvalds committed
402

Joern Engel's avatar
Joern Engel committed
403
		wqh = bit_waitqueue(&inode->i_state, __I_SYNC);
Linus Torvalds's avatar
Linus Torvalds committed
404 405 406 407 408
		do {
			spin_unlock(&inode_lock);
			__wait_on_bit(wqh, &wq, inode_wait,
							TASK_UNINTERRUPTIBLE);
			spin_lock(&inode_lock);
Joern Engel's avatar
Joern Engel committed
409
		} while (inode->i_state & I_SYNC);
Linus Torvalds's avatar
Linus Torvalds committed
410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439
	}
	return __sync_single_inode(inode, wbc);
}

/*
 * Write out a superblock's list of dirty inodes.  A wait will be performed
 * upon no inodes, all inodes or the final one, depending upon sync_mode.
 *
 * If older_than_this is non-NULL, then only write out inodes which
 * had their first dirtying at a time earlier than *older_than_this.
 *
 * If we're a pdlfush thread, then implement pdflush collision avoidance
 * against the entire list.
 *
 * WB_SYNC_HOLD is a hack for sys_sync(): reattach the inode to sb->s_dirty so
 * that it can be located for waiting on in __writeback_single_inode().
 *
 * If `bdi' is non-zero then we're being asked to writeback a specific queue.
 * This function assumes that the blockdev superblock's inodes are backed by
 * a variety of queues, so all inodes are searched.  For other superblocks,
 * assume that all inodes are backed by the same queue.
 *
 * FIXME: this linear search could get expensive with many fileystems.  But
 * how to fix?  We need to go from an address_space to all inodes which share
 * a queue with that address_space.  (Easy: have a global "dirty superblocks"
 * list).
 *
 * The inodes to be written are parked on sb->s_io.  They are moved back onto
 * sb->s_dirty as they are selected for writing.  This way, none can be missed
 * on the writer throttling path, and we get decent balancing between many
Joern Engel's avatar
Joern Engel committed
440
 * throttled threads: we don't want them all piling up on inode_sync_wait.
Linus Torvalds's avatar
Linus Torvalds committed
441
 */
442 443
void generic_sync_sb_inodes(struct super_block *sb,
				struct writeback_control *wbc)
Linus Torvalds's avatar
Linus Torvalds committed
444 445 446
{
	const unsigned long start = jiffies;	/* livelock avoidance */

447
	spin_lock(&inode_lock);
Linus Torvalds's avatar
Linus Torvalds committed
448
	if (!wbc->for_kupdate || list_empty(&sb->s_io))
449
		queue_io(sb, wbc->older_than_this);
Linus Torvalds's avatar
Linus Torvalds committed
450 451 452 453 454 455 456 457 458

	while (!list_empty(&sb->s_io)) {
		struct inode *inode = list_entry(sb->s_io.prev,
						struct inode, i_list);
		struct address_space *mapping = inode->i_mapping;
		struct backing_dev_info *bdi = mapping->backing_dev_info;
		long pages_skipped;

		if (!bdi_cap_writeback_dirty(bdi)) {
459
			redirty_tail(inode);
460
			if (sb_is_blkdev_sb(sb)) {
Linus Torvalds's avatar
Linus Torvalds committed
461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476
				/*
				 * Dirty memory-backed blockdev: the ramdisk
				 * driver does this.  Skip just this inode
				 */
				continue;
			}
			/*
			 * Dirty memory-backed inode against a filesystem other
			 * than the kernel-internal bdev filesystem.  Skip the
			 * entire superblock.
			 */
			break;
		}

		if (wbc->nonblocking && bdi_write_congested(bdi)) {
			wbc->encountered_congestion = 1;
477
			if (!sb_is_blkdev_sb(sb))
Linus Torvalds's avatar
Linus Torvalds committed
478
				break;		/* Skip a congested fs */
479
			requeue_io(inode);
Linus Torvalds's avatar
Linus Torvalds committed
480 481 482 483
			continue;		/* Skip a congested blockdev */
		}

		if (wbc->bdi && bdi != wbc->bdi) {
484
			if (!sb_is_blkdev_sb(sb))
Linus Torvalds's avatar
Linus Torvalds committed
485
				break;		/* fs has the wrong queue */
486
			requeue_io(inode);
Linus Torvalds's avatar
Linus Torvalds committed
487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512
			continue;		/* blockdev has wrong queue */
		}

		/* Was this inode dirtied after sync_sb_inodes was called? */
		if (time_after(inode->dirtied_when, start))
			break;

		/* Is another pdflush already flushing this queue? */
		if (current_is_pdflush() && !writeback_acquire(bdi))
			break;

		BUG_ON(inode->i_state & I_FREEING);
		__iget(inode);
		pages_skipped = wbc->pages_skipped;
		__writeback_single_inode(inode, wbc);
		if (wbc->sync_mode == WB_SYNC_HOLD) {
			inode->dirtied_when = jiffies;
			list_move(&inode->i_list, &sb->s_dirty);
		}
		if (current_is_pdflush())
			writeback_release(bdi);
		if (wbc->pages_skipped != pages_skipped) {
			/*
			 * writeback is not making progress due to locked
			 * buffers.  Skip this inode for now.
			 */
513
			redirty_tail(inode);
Linus Torvalds's avatar
Linus Torvalds committed
514 515 516
		}
		spin_unlock(&inode_lock);
		iput(inode);
517
		cond_resched();
Linus Torvalds's avatar
Linus Torvalds committed
518
		spin_lock(&inode_lock);
519 520
		if (wbc->nr_to_write <= 0) {
			wbc->more_io = 1;
Linus Torvalds's avatar
Linus Torvalds committed
521
			break;
522 523 524
		}
		if (!list_empty(&sb->s_more_io))
			wbc->more_io = 1;
Linus Torvalds's avatar
Linus Torvalds committed
525
	}
526
	spin_unlock(&inode_lock);
Linus Torvalds's avatar
Linus Torvalds committed
527 528
	return;		/* Leave any unwritten inodes on s_io */
}
529 530 531 532 533 534 535
EXPORT_SYMBOL_GPL(generic_sync_sb_inodes);

static void sync_sb_inodes(struct super_block *sb,
				struct writeback_control *wbc)
{
	generic_sync_sb_inodes(sb, wbc);
}
Linus Torvalds's avatar
Linus Torvalds committed
536 537 538 539 540 541 542

/*
 * Start writeback of dirty pagecache data against all unlocked inodes.
 *
 * Note:
 * We don't need to grab a reference to superblock here. If it has non-empty
 * ->s_dirty it's hadn't been killed yet and kill_super() won't proceed
543
 * past sync_inodes_sb() until the ->s_dirty/s_io/s_more_io lists are all
Linus Torvalds's avatar
Linus Torvalds committed
544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563
 * empty. Since __sync_single_inode() regains inode_lock before it finally moves
 * inode from superblock lists we are OK.
 *
 * If `older_than_this' is non-zero then only flush inodes which have a
 * flushtime older than *older_than_this.
 *
 * If `bdi' is non-zero then we will scan the first inode against each
 * superblock until we find the matching ones.  One group will be the dirty
 * inodes against a filesystem.  Then when we hit the dummy blockdev superblock,
 * sync_sb_inodes will seekout the blockdev which matches `bdi'.  Maybe not
 * super-efficient but we're about to do a ton of I/O...
 */
void
writeback_inodes(struct writeback_control *wbc)
{
	struct super_block *sb;

	might_sleep();
	spin_lock(&sb_lock);
restart:
564
	list_for_each_entry_reverse(sb, &super_blocks, s_list) {
565
		if (sb_has_dirty_inodes(sb)) {
Linus Torvalds's avatar
Linus Torvalds committed
566 567 568 569 570 571 572 573 574
			/* we're making our own get_super here */
			sb->s_count++;
			spin_unlock(&sb_lock);
			/*
			 * If we can't get the readlock, there's no sense in
			 * waiting around, most of the time the FS is going to
			 * be unmounted by the time it is released.
			 */
			if (down_read_trylock(&sb->s_umount)) {
575
				if (sb->s_root)
Linus Torvalds's avatar
Linus Torvalds committed
576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603
					sync_sb_inodes(sb, wbc);
				up_read(&sb->s_umount);
			}
			spin_lock(&sb_lock);
			if (__put_super_and_need_restart(sb))
				goto restart;
		}
		if (wbc->nr_to_write <= 0)
			break;
	}
	spin_unlock(&sb_lock);
}

/*
 * writeback and wait upon the filesystem's dirty inodes.  The caller will
 * do this in two passes - one to write, and one to wait.  WB_SYNC_HOLD is
 * used to park the written inodes on sb->s_dirty for the wait pass.
 *
 * A finite limit is set on the number of pages which will be written.
 * To prevent infinite livelock of sys_sync().
 *
 * We add in the number of potentially dirty inodes, because each inode write
 * can dirty pagecache in the underlying blockdev.
 */
void sync_inodes_sb(struct super_block *sb, int wait)
{
	struct writeback_control wbc = {
		.sync_mode	= wait ? WB_SYNC_ALL : WB_SYNC_HOLD,
604 605
		.range_start	= 0,
		.range_end	= LLONG_MAX,
Linus Torvalds's avatar
Linus Torvalds committed
606
	};
607
	unsigned long nr_dirty = global_page_state(NR_FILE_DIRTY);
608
	unsigned long nr_unstable = global_page_state(NR_UNSTABLE_NFS);
Linus Torvalds's avatar
Linus Torvalds committed
609 610 611 612 613 614 615 616 617 618 619 620 621 622 623

	wbc.nr_to_write = nr_dirty + nr_unstable +
			(inodes_stat.nr_inodes - inodes_stat.nr_unused) +
			nr_dirty + nr_unstable;
	wbc.nr_to_write += wbc.nr_to_write / 2;		/* Bit more for luck */
	sync_sb_inodes(sb, &wbc);
}

/*
 * Rather lame livelock avoidance.
 */
static void set_sb_syncing(int val)
{
	struct super_block *sb;
	spin_lock(&sb_lock);
624
	list_for_each_entry_reverse(sb, &super_blocks, s_list)
Linus Torvalds's avatar
Linus Torvalds committed
625 626 627 628 629
		sb->s_syncing = val;
	spin_unlock(&sb_lock);
}

/**
630 631
 * sync_inodes - writes all inodes to disk
 * @wait: wait for completion
Linus Torvalds's avatar
Linus Torvalds committed
632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647
 *
 * sync_inodes() goes through each super block's dirty inode list, writes the
 * inodes out, waits on the writeout and puts the inodes back on the normal
 * list.
 *
 * This is for sys_sync().  fsync_dev() uses the same algorithm.  The subtle
 * part of the sync functions is that the blockdev "superblock" is processed
 * last.  This is because the write_inode() function of a typical fs will
 * perform no I/O, but will mark buffers in the blockdev mapping as dirty.
 * What we want to do is to perform all that dirtying first, and then write
 * back all those inode blocks via the blockdev mapping in one sweep.  So the
 * additional (somewhat redundant) sync_blockdev() calls here are to make
 * sure that really happens.  Because if we call sync_inodes_sb(wait=1) with
 * outstanding dirty inodes, the writeback goes block-at-a-time within the
 * filesystem's write_inode().  This is extremely slow.
 */
648
static void __sync_inodes(int wait)
Linus Torvalds's avatar
Linus Torvalds committed
649 650 651
{
	struct super_block *sb;

652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668
	spin_lock(&sb_lock);
restart:
	list_for_each_entry(sb, &super_blocks, s_list) {
		if (sb->s_syncing)
			continue;
		sb->s_syncing = 1;
		sb->s_count++;
		spin_unlock(&sb_lock);
		down_read(&sb->s_umount);
		if (sb->s_root) {
			sync_inodes_sb(sb, wait);
			sync_blockdev(sb->s_bdev);
		}
		up_read(&sb->s_umount);
		spin_lock(&sb_lock);
		if (__put_super_and_need_restart(sb))
			goto restart;
Linus Torvalds's avatar
Linus Torvalds committed
669
	}
670 671 672 673 674 675 676 677
	spin_unlock(&sb_lock);
}

void sync_inodes(int wait)
{
	set_sb_syncing(0);
	__sync_inodes(0);

Linus Torvalds's avatar
Linus Torvalds committed
678 679
	if (wait) {
		set_sb_syncing(0);
680
		__sync_inodes(1);
Linus Torvalds's avatar
Linus Torvalds committed
681 682 683 684
	}
}

/**
685 686 687 688 689 690
 * write_inode_now	-	write an inode to disk
 * @inode: inode to write to disk
 * @sync: whether the write should be synchronous or not
 *
 * This function commits an inode to disk immediately if it is dirty. This is
 * primarily needed by knfsd.
Linus Torvalds's avatar
Linus Torvalds committed
691
 *
692
 * The caller must either have a ref on the inode or must have set I_WILL_FREE.
Linus Torvalds's avatar
Linus Torvalds committed
693 694 695 696 697 698
 */
int write_inode_now(struct inode *inode, int sync)
{
	int ret;
	struct writeback_control wbc = {
		.nr_to_write = LONG_MAX,
699
		.sync_mode = sync ? WB_SYNC_ALL : WB_SYNC_NONE,
700 701
		.range_start = 0,
		.range_end = LLONG_MAX,
Linus Torvalds's avatar
Linus Torvalds committed
702 703 704
	};

	if (!mapping_cap_writeback_dirty(inode->i_mapping))
705
		wbc.nr_to_write = 0;
Linus Torvalds's avatar
Linus Torvalds committed
706 707 708 709 710 711

	might_sleep();
	spin_lock(&inode_lock);
	ret = __writeback_single_inode(inode, &wbc);
	spin_unlock(&inode_lock);
	if (sync)
Joern Engel's avatar
Joern Engel committed
712
		inode_sync_wait(inode);
Linus Torvalds's avatar
Linus Torvalds committed
713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741
	return ret;
}
EXPORT_SYMBOL(write_inode_now);

/**
 * sync_inode - write an inode and its pages to disk.
 * @inode: the inode to sync
 * @wbc: controls the writeback mode
 *
 * sync_inode() will write an inode and its pages to disk.  It will also
 * correctly update the inode on its superblock's dirty inode lists and will
 * update inode->i_state.
 *
 * The caller must have a ref on the inode.
 */
int sync_inode(struct inode *inode, struct writeback_control *wbc)
{
	int ret;

	spin_lock(&inode_lock);
	ret = __writeback_single_inode(inode, wbc);
	spin_unlock(&inode_lock);
	return ret;
}
EXPORT_SYMBOL(sync_inode);

/**
 * generic_osync_inode - flush all dirty data for a given inode to disk
 * @inode: inode to write
742
 * @mapping: the address_space that should be flushed
Linus Torvalds's avatar
Linus Torvalds committed
743 744 745 746 747 748
 * @what:  what to write and wait upon
 *
 * This can be called by file_write functions for files which have the
 * O_SYNC flag set, to flush dirty writes to disk.
 *
 * @what is a bitmask, specifying which part of the inode's data should be
749
 * written and waited upon.
Linus Torvalds's avatar
Linus Torvalds committed
750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786
 *
 *    OSYNC_DATA:     i_mapping's dirty data
 *    OSYNC_METADATA: the buffers at i_mapping->private_list
 *    OSYNC_INODE:    the inode itself
 */

int generic_osync_inode(struct inode *inode, struct address_space *mapping, int what)
{
	int err = 0;
	int need_write_inode_now = 0;
	int err2;

	if (what & OSYNC_DATA)
		err = filemap_fdatawrite(mapping);
	if (what & (OSYNC_METADATA|OSYNC_DATA)) {
		err2 = sync_mapping_buffers(mapping);
		if (!err)
			err = err2;
	}
	if (what & OSYNC_DATA) {
		err2 = filemap_fdatawait(mapping);
		if (!err)
			err = err2;
	}

	spin_lock(&inode_lock);
	if ((inode->i_state & I_DIRTY) &&
	    ((what & OSYNC_INODE) || (inode->i_state & I_DIRTY_DATASYNC)))
		need_write_inode_now = 1;
	spin_unlock(&inode_lock);

	if (need_write_inode_now) {
		err2 = write_inode_now(inode, 1);
		if (!err)
			err = err2;
	}
	else
Joern Engel's avatar
Joern Engel committed
787
		inode_sync_wait(inode);
Linus Torvalds's avatar
Linus Torvalds committed
788 789 790 791

	return err;
}
EXPORT_SYMBOL(generic_osync_inode);