• Andrew Morton's avatar
    [PATCH] fix writeback for dirty ramdisk blockdev inodes · 71a1f72c
    Andrew Morton authored
    Once the blockdev inode for /dev/ram0 is dirtied we have a memory-backed
    inode on the blockdev superblock's s_dirty list.
    
    sync_sb_inodes() sees the memory-backed inode on the superblock and assumes
    that all the other inodes on the superblock are also memory-backed.  This is
    not true for the blockdev superblock!  We forget to write out dirty pages
    against the following blockdevs.
    
    Fix this by just leaving the inode dirty and moving on to inspect the other
    blockdev inodes on sb->s_io.
    
    (This is a little inefficient: an alternative is to leave dirtied
    memory-backed inodes on inode_in_use, so nobody ever even considers them for
    writeout.  But that introduces an inconsistency and is a bit kludgey).
    71a1f72c
fs-writeback.c 16.5 KB
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 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 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576
/*
 * 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.
 *
 * 10Apr2002	akpm@zip.com.au
 *		Split out of fs/inode.c
 *		Additions for address_space-based writeback
 */

#include <linux/kernel.h>
#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>

extern struct super_block *blockdev_superblock;

/**
 *	__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.
 */
void __mark_inode_dirty(struct inode *inode, int flags)
{
	struct super_block *sb = inode->i_sb;

	if (!sb)
		return;		/* swapper_space */

	/*
	 * 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;

	spin_lock(&inode_lock);
	if ((inode->i_state & flags) != flags) {
		const int was_dirty = inode->i_state & I_DIRTY;
		struct address_space *mapping = inode->i_mapping;

		inode->i_state |= flags;

		/*
		 * If the inode is locked, just update its dirty state. 
		 * The unlocker will place the inode on the appropriate
		 * superblock list, based upon its state.
		 */
		if (inode->i_state & I_LOCK)
			goto out;

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

		/*
		 * If the inode was already on s_dirty or s_io, don't
		 * reposition it (that would break s_dirty time-ordering).
		 */
		if (!was_dirty) {
			mapping->dirtied_when = jiffies|1; /* 0 is special */
			list_move(&inode->i_list, &sb->s_dirty);
		}
	}
out:
	spin_unlock(&inode_lock);
}

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

/*
 * 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.
 *
 * So what we do is to move all pages which are to be written from dirty_pages
 * onto io_pages.  And keep on writing io_pages until it's empty.  Refusing to
 * move more pages onto io_pages until io_pages is empty.  Once that point has
 * been reached, we are ready to take another pass across the inode's dirty
 * pages.
 *
 * Called under inode_lock.
 */
static void
__sync_single_inode(struct inode *inode, struct writeback_control *wbc)
{
	unsigned dirty;
	struct address_space *mapping = inode->i_mapping;
	struct super_block *sb = inode->i_sb;
	int wait = wbc->sync_mode == WB_SYNC_ALL;

	BUG_ON(inode->i_state & I_LOCK);

	/* Set I_LOCK, reset I_DIRTY */
	dirty = inode->i_state & I_DIRTY;
	inode->i_state |= I_LOCK;
	inode->i_state &= ~I_DIRTY;

	/*
	 * smp_rmb(); note: if you remove write_lock below, you must add this.
	 * mark_inode_dirty doesn't take spinlock, make sure that inode is not
	 * read speculatively by this cpu before &= ~I_DIRTY  -- mikulas
	 */

	spin_lock(&mapping->page_lock);
	if (wait || !wbc->for_kupdate || list_empty(&mapping->io_pages))
		list_splice_init(&mapping->dirty_pages, &mapping->io_pages);
	spin_unlock(&mapping->page_lock);
	spin_unlock(&inode_lock);

	do_writepages(mapping, wbc);

	/* Don't write the inode if only I_DIRTY_PAGES was set */
	if (dirty & (I_DIRTY_SYNC | I_DIRTY_DATASYNC))
		write_inode(inode, wait);

	if (wait)
		filemap_fdatawait(mapping);

	spin_lock(&inode_lock);
	inode->i_state &= ~I_LOCK;
	if (!(inode->i_state & I_FREEING)) {
		if (!list_empty(&mapping->io_pages)) {
		 	/* Needs more writeback */
			inode->i_state |= I_DIRTY_PAGES;
		} else if (!list_empty(&mapping->dirty_pages)) {
			/* Redirtied */
			inode->i_state |= I_DIRTY_PAGES;
			mapping->dirtied_when = jiffies|1;
			list_move(&inode->i_list, &sb->s_dirty);
		} else if (inode->i_state & I_DIRTY) {
			/* Redirtied */
			mapping->dirtied_when = jiffies|1;
			list_move(&inode->i_list, &sb->s_dirty);
		} else if (atomic_read(&inode->i_count)) {
			mapping->dirtied_when = 0;
			list_move(&inode->i_list, &inode_in_use);
		} else {
			mapping->dirtied_when = 0;
			list_move(&inode->i_list, &inode_unused);
		}
	}
	wake_up_inode(inode);
}

/*
 * Write out an inode's dirty pages.  Called under inode_lock.
 */
static void
__writeback_single_inode(struct inode *inode,
			struct writeback_control *wbc)
{
	if ((wbc->sync_mode != WB_SYNC_ALL) && (inode->i_state & I_LOCK)) {
		list_move(&inode->i_list, &inode->i_sb->s_dirty);
		return;
	}

	/*
	 * It's a data-integrity sync.  We must wait.
	 */
	while (inode->i_state & I_LOCK) {
		__iget(inode);
		spin_unlock(&inode_lock);
		__wait_on_inode(inode);
		iput(inode);
		spin_lock(&inode_lock);
	}
	__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 mappings 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().
 *
 * Called under inode_lock.
 *
 * 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
 * throttled threads: we don't want them all piling up on __wait_on_inode.
 */
static void
sync_sb_inodes(struct super_block *sb, struct writeback_control *wbc)
{
	const unsigned long start = jiffies;	/* livelock avoidance */

	if (!wbc->for_kupdate || list_empty(&sb->s_io))
		list_splice_init(&sb->s_dirty, &sb->s_io);

	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;

		if (bdi->memory_backed) {
			if (sb == blockdev_superblock) {
				/*
				 * Dirty memory-backed blockdev: the ramdisk
				 * driver does this.
				 */
				list_move(&inode->i_list, &sb->s_dirty);
				continue;
			}
			/*
			 * Assume that all inodes on this superblock are memory
			 * backed.  Skip the superblock.
			 */
			break;
		}

		if (wbc->nonblocking && bdi_write_congested(bdi)) {
			wbc->encountered_congestion = 1;
			if (sb != blockdev_superblock)
				break;		/* Skip a congested fs */
			list_move(&inode->i_list, &sb->s_dirty);
			continue;		/* Skip a congested blockdev */
		}

		if (wbc->bdi && bdi != wbc->bdi) {
			if (sb != blockdev_superblock)
				break;		/* fs has the wrong queue */
			list_move(&inode->i_list, &sb->s_dirty);
			continue;		/* blockdev has wrong queue */
		}

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

		/* Was this inode dirtied too recently? */
		if (wbc->older_than_this && time_after(mapping->dirtied_when,
						*wbc->older_than_this))
			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);
		__writeback_single_inode(inode, wbc);
		if (wbc->sync_mode == WB_SYNC_HOLD) {
			mapping->dirtied_when = jiffies|1;
			list_move(&inode->i_list, &sb->s_dirty);
		}
		if (current_is_pdflush())
			writeback_release(bdi);
		spin_unlock(&inode_lock);
		iput(inode);
		spin_lock(&inode_lock);
		if (wbc->nr_to_write <= 0)
			break;
	}
	return;		/* Leave any unwritten inodes on s_io */
}

/*
 * 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
 * past sync_inodes_sb() until both the ->s_dirty and ->s_io lists are
 * 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;

	spin_lock(&inode_lock);
	spin_lock(&sb_lock);
	sb = sb_entry(super_blocks.prev);
	for (; sb != sb_entry(&super_blocks); sb = sb_entry(sb->s_list.prev)) {
		if (!list_empty(&sb->s_dirty) || !list_empty(&sb->s_io)) {
			spin_unlock(&sb_lock);
			sync_sb_inodes(sb, wbc);
			spin_lock(&sb_lock);
		}
		if (wbc->nr_to_write <= 0)
			break;
	}
	spin_unlock(&sb_lock);
	spin_unlock(&inode_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().
 */
void sync_inodes_sb(struct super_block *sb, int wait)
{
	struct page_state ps;
	struct writeback_control wbc = {
		.bdi		= NULL,
		.sync_mode	= wait ? WB_SYNC_ALL : WB_SYNC_HOLD,
		.older_than_this = NULL,
		.nr_to_write	= 0,
	};

	get_page_state(&ps);
	wbc.nr_to_write = ps.nr_dirty + ps.nr_unstable +
		(ps.nr_dirty + ps.nr_unstable) / 4;
	spin_lock(&inode_lock);
	sync_sb_inodes(sb, &wbc);
	spin_unlock(&inode_lock);
}

/*
 * Rather lame livelock avoidance.
 */
static void set_sb_syncing(int val)
{
	struct super_block *sb;
	spin_lock(&sb_lock);
	sb = sb_entry(super_blocks.prev);
	for (; sb != sb_entry(&super_blocks); sb = sb_entry(sb->s_list.prev)) {
		sb->s_syncing = val;
	}
	spin_unlock(&sb_lock);
}

/*
 * Find a superblock with inodes that need to be synced
 */
static struct super_block *get_super_to_sync(void)
{
	struct super_block *sb;
restart:
	spin_lock(&sb_lock);
	sb = sb_entry(super_blocks.prev);
	for (; sb != sb_entry(&super_blocks); sb = sb_entry(sb->s_list.prev)) {
		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) {
			drop_super(sb);
			goto restart;
		}
		return sb;
	}
	spin_unlock(&sb_lock);
	return NULL;
}

/**
 * sync_inodes
 *
 * 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.
 */
void sync_inodes(int wait)
{
	struct super_block *sb;

	set_sb_syncing(0);
	while ((sb = get_super_to_sync()) != NULL) {
		sync_inodes_sb(sb, 0);
		sync_blockdev(sb->s_bdev);
		drop_super(sb);
	}
	if (wait) {
		set_sb_syncing(0);
		while ((sb = get_super_to_sync()) != NULL) {
			sync_inodes_sb(sb, 1);
			sync_blockdev(sb->s_bdev);
			drop_super(sb);
		}
	}
}

/**
 *	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.
 */
 
void write_inode_now(struct inode *inode, int sync)
{
	struct writeback_control wbc = {
		.nr_to_write = LONG_MAX,
		.sync_mode = WB_SYNC_ALL,
	};

	spin_lock(&inode_lock);
	__writeback_single_inode(inode, &wbc);
	spin_unlock(&inode_lock);
	if (sync)
		wait_on_inode(inode);
}

/**
 * generic_osync_inode - flush all dirty data for a given inode to disk
 * @inode: inode to write
 * @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
 * written and waited upon:
 *
 *    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, int what)
{
	int err = 0;
	int need_write_inode_now = 0;
	int err2;

	if (what & OSYNC_DATA)
		err = filemap_fdatawrite(inode->i_mapping);
	if (what & (OSYNC_METADATA|OSYNC_DATA)) {
		err2 = sync_mapping_buffers(inode->i_mapping);
		if (!err)
			err = err2;
	}
	if (what & OSYNC_DATA) {
		err2 = filemap_fdatawait(inode->i_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)
		write_inode_now(inode, 1);
	else
		wait_on_inode(inode);

	return err;
}

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