buffer.c 83.1 KB
Newer Older
Linus Torvalds's avatar
Linus Torvalds committed
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
/*
 *  linux/fs/buffer.c
 *
 *  Copyright (C) 1991, 1992, 2002  Linus Torvalds
 */

/*
 * Start bdflush() with kernel_thread not syscall - Paul Gortmaker, 12/95
 *
 * Removed a lot of unnecessary code and simplified things now that
 * the buffer cache isn't our primary cache - Andrew Tridgell 12/96
 *
 * Speed up hash, lru, and free list operations.  Use gfp() for allocating
 * hash table, use SLAB cache for buffer heads. SMP threading.  -DaveM
 *
 * Added 32k buffer block sizes - these are required older ARM systems. - RMK
 *
 * async buffer flushing, 1999 Andrea Arcangeli <andrea@suse.de>
 */

#include <linux/config.h>
#include <linux/kernel.h>
#include <linux/syscalls.h>
#include <linux/fs.h>
#include <linux/mm.h>
#include <linux/percpu.h>
#include <linux/slab.h>
#include <linux/smp_lock.h>
29
#include <linux/capability.h>
Linus Torvalds's avatar
Linus Torvalds committed
30 31 32 33 34 35 36 37 38 39 40 41 42 43
#include <linux/blkdev.h>
#include <linux/file.h>
#include <linux/quotaops.h>
#include <linux/highmem.h>
#include <linux/module.h>
#include <linux/writeback.h>
#include <linux/hash.h>
#include <linux/suspend.h>
#include <linux/buffer_head.h>
#include <linux/bio.h>
#include <linux/notifier.h>
#include <linux/cpu.h>
#include <linux/bitops.h>
#include <linux/mpage.h>
Ingo Molnar's avatar
Ingo Molnar committed
44
#include <linux/bit_spinlock.h>
Linus Torvalds's avatar
Linus Torvalds committed
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

static int fsync_buffers_list(spinlock_t *lock, struct list_head *list);
static void invalidate_bh_lrus(void);

#define BH_ENTRY(list) list_entry((list), struct buffer_head, b_assoc_buffers)

inline void
init_buffer(struct buffer_head *bh, bh_end_io_t *handler, void *private)
{
	bh->b_end_io = handler;
	bh->b_private = private;
}

static int sync_buffer(void *word)
{
	struct block_device *bd;
	struct buffer_head *bh
		= container_of(word, struct buffer_head, b_state);

	smp_mb();
	bd = bh->b_bdev;
	if (bd)
		blk_run_address_space(bd->bd_inode->i_mapping);
	io_schedule();
	return 0;
}

void fastcall __lock_buffer(struct buffer_head *bh)
{
	wait_on_bit_lock(&bh->b_state, BH_Lock, sync_buffer,
							TASK_UNINTERRUPTIBLE);
}
EXPORT_SYMBOL(__lock_buffer);

void fastcall unlock_buffer(struct buffer_head *bh)
{
	clear_buffer_locked(bh);
	smp_mb__after_clear_bit();
	wake_up_bit(&bh->b_state, BH_Lock);
}

/*
 * Block until a buffer comes unlocked.  This doesn't stop it
 * from becoming locked again - you have to lock it yourself
 * if you want to preserve its state.
 */
void __wait_on_buffer(struct buffer_head * bh)
{
	wait_on_bit(&bh->b_state, BH_Lock, sync_buffer, TASK_UNINTERRUPTIBLE);
}

static void
__clear_page_buffers(struct page *page)
{
	ClearPagePrivate(page);
100
	set_page_private(page, 0);
Linus Torvalds's avatar
Linus Torvalds committed
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
	page_cache_release(page);
}

static void buffer_io_error(struct buffer_head *bh)
{
	char b[BDEVNAME_SIZE];

	printk(KERN_ERR "Buffer I/O error on device %s, logical block %Lu\n",
			bdevname(bh->b_bdev, b),
			(unsigned long long)bh->b_blocknr);
}

/*
 * Default synchronous end-of-IO handler..  Just mark it up-to-date and
 * unlock the buffer. This is what ll_rw_block uses too.
 */
void end_buffer_read_sync(struct buffer_head *bh, int uptodate)
{
	if (uptodate) {
		set_buffer_uptodate(bh);
	} else {
		/* This happens, due to failed READA attempts. */
		clear_buffer_uptodate(bh);
	}
	unlock_buffer(bh);
	put_bh(bh);
}

void end_buffer_write_sync(struct buffer_head *bh, int uptodate)
{
	char b[BDEVNAME_SIZE];

	if (uptodate) {
		set_buffer_uptodate(bh);
	} else {
		if (!buffer_eopnotsupp(bh) && printk_ratelimit()) {
			buffer_io_error(bh);
			printk(KERN_WARNING "lost page write due to "
					"I/O error on %s\n",
				       bdevname(bh->b_bdev, b));
		}
		set_buffer_write_io_error(bh);
		clear_buffer_uptodate(bh);
	}
	unlock_buffer(bh);
	put_bh(bh);
}

/*
 * Write out and wait upon all the dirty data associated with a block
 * device via its mapping.  Does not take the superblock lock.
 */
int sync_blockdev(struct block_device *bdev)
{
	int ret = 0;

157 158
	if (bdev)
		ret = filemap_write_and_wait(bdev->bd_inode->i_mapping);
Linus Torvalds's avatar
Linus Torvalds committed
159 160 161 162
	return ret;
}
EXPORT_SYMBOL(sync_blockdev);

OGAWA Hirofumi's avatar
OGAWA Hirofumi committed
163
static void __fsync_super(struct super_block *sb)
Linus Torvalds's avatar
Linus Torvalds committed
164 165 166 167 168 169 170 171 172 173 174
{
	sync_inodes_sb(sb, 0);
	DQUOT_SYNC(sb);
	lock_super(sb);
	if (sb->s_dirt && sb->s_op->write_super)
		sb->s_op->write_super(sb);
	unlock_super(sb);
	if (sb->s_op->sync_fs)
		sb->s_op->sync_fs(sb, 1);
	sync_blockdev(sb->s_bdev);
	sync_inodes_sb(sb, 1);
OGAWA Hirofumi's avatar
OGAWA Hirofumi committed
175
}
Linus Torvalds's avatar
Linus Torvalds committed
176

OGAWA Hirofumi's avatar
OGAWA Hirofumi committed
177 178 179 180 181 182 183 184
/*
 * Write out and wait upon all dirty data associated with this
 * superblock.  Filesystem data as well as the underlying block
 * device.  Takes the superblock lock.
 */
int fsync_super(struct super_block *sb)
{
	__fsync_super(sb);
Linus Torvalds's avatar
Linus Torvalds committed
185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207
	return sync_blockdev(sb->s_bdev);
}

/*
 * Write out and wait upon all dirty data associated with this
 * device.   Filesystem data as well as the underlying block
 * device.  Takes the superblock lock.
 */
int fsync_bdev(struct block_device *bdev)
{
	struct super_block *sb = get_super(bdev);
	if (sb) {
		int res = fsync_super(sb);
		drop_super(sb);
		return res;
	}
	return sync_blockdev(bdev);
}

/**
 * freeze_bdev  --  lock a filesystem and force it into a consistent state
 * @bdev:	blockdevice to lock
 *
208
 * This takes the block device bd_mount_mutex to make sure no new mounts
Linus Torvalds's avatar
Linus Torvalds committed
209 210 211 212 213 214 215 216
 * happen on bdev until thaw_bdev() is called.
 * If a superblock is found on this device, we take the s_umount semaphore
 * on it to make sure nobody unmounts until the snapshot creation is done.
 */
struct super_block *freeze_bdev(struct block_device *bdev)
{
	struct super_block *sb;

217
	mutex_lock(&bdev->bd_mount_mutex);
Linus Torvalds's avatar
Linus Torvalds committed
218 219 220
	sb = get_super(bdev);
	if (sb && !(sb->s_flags & MS_RDONLY)) {
		sb->s_frozen = SB_FREEZE_WRITE;
221
		smp_wmb();
Linus Torvalds's avatar
Linus Torvalds committed
222

OGAWA Hirofumi's avatar
OGAWA Hirofumi committed
223
		__fsync_super(sb);
Linus Torvalds's avatar
Linus Torvalds committed
224 225

		sb->s_frozen = SB_FREEZE_TRANS;
226
		smp_wmb();
Linus Torvalds's avatar
Linus Torvalds committed
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

		sync_blockdev(sb->s_bdev);

		if (sb->s_op->write_super_lockfs)
			sb->s_op->write_super_lockfs(sb);
	}

	sync_blockdev(bdev);
	return sb;	/* thaw_bdev releases s->s_umount and bd_mount_sem */
}
EXPORT_SYMBOL(freeze_bdev);

/**
 * thaw_bdev  -- unlock filesystem
 * @bdev:	blockdevice to unlock
 * @sb:		associated superblock
 *
 * Unlocks the filesystem and marks it writeable again after freeze_bdev().
 */
void thaw_bdev(struct block_device *bdev, struct super_block *sb)
{
	if (sb) {
		BUG_ON(sb->s_bdev != bdev);

		if (sb->s_op->unlockfs)
			sb->s_op->unlockfs(sb);
		sb->s_frozen = SB_UNFROZEN;
254
		smp_wmb();
Linus Torvalds's avatar
Linus Torvalds committed
255 256 257 258
		wake_up(&sb->s_wait_unfrozen);
		drop_super(sb);
	}

259
	mutex_unlock(&bdev->bd_mount_mutex);
Linus Torvalds's avatar
Linus Torvalds committed
260 261 262 263 264 265 266 267 268
}
EXPORT_SYMBOL(thaw_bdev);

/*
 * sync everything.  Start out by waking pdflush, because that writes back
 * all queues in parallel.
 */
static void do_sync(unsigned long wait)
{
269
	wakeup_pdflush(0);
Linus Torvalds's avatar
Linus Torvalds committed
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
	sync_inodes(0);		/* All mappings, inodes and their blockdevs */
	DQUOT_SYNC(NULL);
	sync_supers();		/* Write the superblocks */
	sync_filesystems(0);	/* Start syncing the filesystems */
	sync_filesystems(wait);	/* Waitingly sync the filesystems */
	sync_inodes(wait);	/* Mappings, inodes and blockdevs, again. */
	if (!wait)
		printk("Emergency Sync complete\n");
	if (unlikely(laptop_mode))
		laptop_sync_completion();
}

asmlinkage long sys_sync(void)
{
	do_sync(1);
	return 0;
}

void emergency_sync(void)
{
	pdflush_operation(do_sync, 0);
}

/*
 * Generic function to fsync a file.
 *
 * filp may be NULL if called via the msync of a vma.
 */
 
int file_fsync(struct file *filp, struct dentry *dentry, int datasync)
{
	struct inode * inode = dentry->d_inode;
	struct super_block * sb;
	int ret, err;

	/* sync the inode to buffers */
	ret = write_inode_now(inode, 0);

	/* sync the superblock to buffers */
	sb = inode->i_sb;
	lock_super(sb);
	if (sb->s_op->write_super)
		sb->s_op->write_super(sb);
	unlock_super(sb);

	/* .. finally sync the buffers to disk */
	err = sync_blockdev(sb->s_bdev);
	if (!ret)
		ret = err;
	return ret;
}

322
long do_fsync(struct file *file, int datasync)
Linus Torvalds's avatar
Linus Torvalds committed
323
{
324 325 326
	int ret;
	int err;
	struct address_space *mapping = file->f_mapping;
Linus Torvalds's avatar
Linus Torvalds committed
327 328 329

	if (!file->f_op || !file->f_op->fsync) {
		/* Why?  We can still call filemap_fdatawrite */
330 331
		ret = -EINVAL;
		goto out;
Linus Torvalds's avatar
Linus Torvalds committed
332 333 334 335 336
	}

	ret = filemap_fdatawrite(mapping);

	/*
337 338
	 * We need to protect against concurrent writers, which could cause
	 * livelocks in fsync_buffers_list().
Linus Torvalds's avatar
Linus Torvalds committed
339
	 */
340
	mutex_lock(&mapping->host->i_mutex);
341
	err = file->f_op->fsync(file, file->f_dentry, datasync);
Linus Torvalds's avatar
Linus Torvalds committed
342 343
	if (!ret)
		ret = err;
344
	mutex_unlock(&mapping->host->i_mutex);
Linus Torvalds's avatar
Linus Torvalds committed
345 346 347 348 349 350 351
	err = filemap_fdatawait(mapping);
	if (!ret)
		ret = err;
out:
	return ret;
}

352 353 354 355 356 357 358 359 360 361 362 363 364
static long __do_fsync(unsigned int fd, int datasync)
{
	struct file *file;
	int ret = -EBADF;

	file = fget(fd);
	if (file) {
		ret = do_fsync(file, datasync);
		fput(file);
	}
	return ret;
}

365
asmlinkage long sys_fsync(unsigned int fd)
Linus Torvalds's avatar
Linus Torvalds committed
366
{
367
	return __do_fsync(fd, 0);
368
}
Linus Torvalds's avatar
Linus Torvalds committed
369

370 371
asmlinkage long sys_fdatasync(unsigned int fd)
{
372
	return __do_fsync(fd, 1);
Linus Torvalds's avatar
Linus Torvalds committed
373 374 375 376 377 378 379 380 381 382 383 384 385 386
}

/*
 * Various filesystems appear to want __find_get_block to be non-blocking.
 * But it's the page lock which protects the buffers.  To get around this,
 * we get exclusion from try_to_free_buffers with the blockdev mapping's
 * private_lock.
 *
 * Hack idea: for the blockdev mapping, i_bufferlist_lock contention
 * may be quite high.  This code could TryLock the page, and if that
 * succeeds, there is no need to take private_lock. (But if
 * private_lock is contended then so is mapping->tree_lock).
 */
static struct buffer_head *
387
__find_get_block_slow(struct block_device *bdev, sector_t block)
Linus Torvalds's avatar
Linus Torvalds committed
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
{
	struct inode *bd_inode = bdev->bd_inode;
	struct address_space *bd_mapping = bd_inode->i_mapping;
	struct buffer_head *ret = NULL;
	pgoff_t index;
	struct buffer_head *bh;
	struct buffer_head *head;
	struct page *page;
	int all_mapped = 1;

	index = block >> (PAGE_CACHE_SHIFT - bd_inode->i_blkbits);
	page = find_get_page(bd_mapping, index);
	if (!page)
		goto out;

	spin_lock(&bd_mapping->private_lock);
	if (!page_has_buffers(page))
		goto out_unlock;
	head = page_buffers(page);
	bh = head;
	do {
		if (bh->b_blocknr == block) {
			ret = bh;
			get_bh(bh);
			goto out_unlock;
		}
		if (!buffer_mapped(bh))
			all_mapped = 0;
		bh = bh->b_this_page;
	} while (bh != head);

	/* we might be here because some of the buffers on this page are
	 * not mapped.  This is due to various races between
	 * file io on the block device and getblk.  It gets dealt with
	 * elsewhere, don't buffer_error if we had some unmapped buffers
	 */
	if (all_mapped) {
		printk("__find_get_block_slow() failed. "
			"block=%llu, b_blocknr=%llu\n",
427 428 429 430
			(unsigned long long)block,
			(unsigned long long)bh->b_blocknr);
		printk("b_state=0x%08lx, b_size=%zu\n",
			bh->b_state, bh->b_size);
Linus Torvalds's avatar
Linus Torvalds committed
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
		printk("device blocksize: %d\n", 1 << bd_inode->i_blkbits);
	}
out_unlock:
	spin_unlock(&bd_mapping->private_lock);
	page_cache_release(page);
out:
	return ret;
}

/* If invalidate_buffers() will trash dirty buffers, it means some kind
   of fs corruption is going on. Trashing dirty data always imply losing
   information that was supposed to be just stored on the physical layer
   by the user.

   Thus invalidate_buffers in general usage is not allwowed to trash
   dirty buffers. For example ioctl(FLSBLKBUF) expects dirty data to
   be preserved.  These buffers are simply skipped.
  
   We also skip buffers which are still in use.  For example this can
   happen if a userspace program is reading the block device.

   NOTE: In the case where the user removed a removable-media-disk even if
   there's still dirty data not synced on disk (due a bug in the device driver
   or due an error of the user), by not destroying the dirty buffers we could
   generate corruption also on the next media inserted, thus a parameter is
   necessary to handle this case in the most safe way possible (trying
   to not corrupt also the new disk inserted with the data belonging to
   the old now corrupted disk). Also for the ramdisk the natural thing
   to do in order to release the ramdisk memory is to destroy dirty buffers.

   These are two special cases. Normal usage imply the device driver
   to issue a sync on the device (without waiting I/O completion) and
   then an invalidate_buffers call that doesn't trash dirty buffers.

   For handling cache coherency with the blkdev pagecache the 'update' case
   is been introduced. It is needed to re-read from disk any pinned
   buffer. NOTE: re-reading from disk is destructive so we can do it only
   when we assume nobody is changing the buffercache under our I/O and when
   we think the disk contains more recent information than the buffercache.
   The update == 1 pass marks the buffers we need to update, the update == 2
   pass does the actual I/O. */
void invalidate_bdev(struct block_device *bdev, int destroy_dirty_buffers)
{
	invalidate_bh_lrus();
	/*
	 * FIXME: what about destroy_dirty_buffers?
	 * We really want to use invalidate_inode_pages2() for
	 * that, but not until that's cleaned up.
	 */
	invalidate_inode_pages(bdev->bd_inode->i_mapping);
}

/*
 * Kick pdflush then try to free up some ZONE_NORMAL memory.
 */
static void free_more_memory(void)
{
	struct zone **zones;
	pg_data_t *pgdat;

491
	wakeup_pdflush(1024);
Linus Torvalds's avatar
Linus Torvalds committed
492 493
	yield();

494
	for_each_online_pgdat(pgdat) {
Al Viro's avatar
Al Viro committed
495
		zones = pgdat->node_zonelists[gfp_zone(GFP_NOFS)].zones;
Linus Torvalds's avatar
Linus Torvalds committed
496
		if (*zones)
497
			try_to_free_pages(zones, GFP_NOFS);
Linus Torvalds's avatar
Linus Torvalds committed
498 499 500 501 502 503 504 505 506 507
	}
}

/*
 * I/O completion handler for block_read_full_page() - pages
 * which come unlocked at the end of I/O.
 */
static void end_buffer_async_read(struct buffer_head *bh, int uptodate)
{
	unsigned long flags;
508
	struct buffer_head *first;
Linus Torvalds's avatar
Linus Torvalds committed
509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529
	struct buffer_head *tmp;
	struct page *page;
	int page_uptodate = 1;

	BUG_ON(!buffer_async_read(bh));

	page = bh->b_page;
	if (uptodate) {
		set_buffer_uptodate(bh);
	} else {
		clear_buffer_uptodate(bh);
		if (printk_ratelimit())
			buffer_io_error(bh);
		SetPageError(page);
	}

	/*
	 * Be _very_ careful from here on. Bad things can happen if
	 * two buffer heads end IO at almost the same time and both
	 * decide that the page is now completely done.
	 */
530 531 532
	first = page_buffers(page);
	local_irq_save(flags);
	bit_spin_lock(BH_Uptodate_Lock, &first->b_state);
Linus Torvalds's avatar
Linus Torvalds committed
533 534 535 536 537 538 539 540 541 542 543 544
	clear_buffer_async_read(bh);
	unlock_buffer(bh);
	tmp = bh;
	do {
		if (!buffer_uptodate(tmp))
			page_uptodate = 0;
		if (buffer_async_read(tmp)) {
			BUG_ON(!buffer_locked(tmp));
			goto still_busy;
		}
		tmp = tmp->b_this_page;
	} while (tmp != bh);
545 546
	bit_spin_unlock(BH_Uptodate_Lock, &first->b_state);
	local_irq_restore(flags);
Linus Torvalds's avatar
Linus Torvalds committed
547 548 549 550 551 552 553 554 555 556 557

	/*
	 * If none of the buffers had errors and they are all
	 * uptodate then we can set the page uptodate.
	 */
	if (page_uptodate && !PageError(page))
		SetPageUptodate(page);
	unlock_page(page);
	return;

still_busy:
558 559
	bit_spin_unlock(BH_Uptodate_Lock, &first->b_state);
	local_irq_restore(flags);
Linus Torvalds's avatar
Linus Torvalds committed
560 561 562 563 564 565 566
	return;
}

/*
 * Completion handler for block_write_full_page() - pages which are unlocked
 * during I/O, and which have PageWriteback cleared upon I/O completion.
 */
Adrian Bunk's avatar
Adrian Bunk committed
567
static void end_buffer_async_write(struct buffer_head *bh, int uptodate)
Linus Torvalds's avatar
Linus Torvalds committed
568 569 570
{
	char b[BDEVNAME_SIZE];
	unsigned long flags;
571
	struct buffer_head *first;
Linus Torvalds's avatar
Linus Torvalds committed
572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591
	struct buffer_head *tmp;
	struct page *page;

	BUG_ON(!buffer_async_write(bh));

	page = bh->b_page;
	if (uptodate) {
		set_buffer_uptodate(bh);
	} else {
		if (printk_ratelimit()) {
			buffer_io_error(bh);
			printk(KERN_WARNING "lost page write due to "
					"I/O error on %s\n",
			       bdevname(bh->b_bdev, b));
		}
		set_bit(AS_EIO, &page->mapping->flags);
		clear_buffer_uptodate(bh);
		SetPageError(page);
	}

592 593 594 595
	first = page_buffers(page);
	local_irq_save(flags);
	bit_spin_lock(BH_Uptodate_Lock, &first->b_state);

Linus Torvalds's avatar
Linus Torvalds committed
596 597 598 599 600 601 602 603 604 605
	clear_buffer_async_write(bh);
	unlock_buffer(bh);
	tmp = bh->b_this_page;
	while (tmp != bh) {
		if (buffer_async_write(tmp)) {
			BUG_ON(!buffer_locked(tmp));
			goto still_busy;
		}
		tmp = tmp->b_this_page;
	}
606 607
	bit_spin_unlock(BH_Uptodate_Lock, &first->b_state);
	local_irq_restore(flags);
Linus Torvalds's avatar
Linus Torvalds committed
608 609 610 611
	end_page_writeback(page);
	return;

still_busy:
612 613
	bit_spin_unlock(BH_Uptodate_Lock, &first->b_state);
	local_irq_restore(flags);
Linus Torvalds's avatar
Linus Torvalds committed
614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751
	return;
}

/*
 * If a page's buffers are under async readin (end_buffer_async_read
 * completion) then there is a possibility that another thread of
 * control could lock one of the buffers after it has completed
 * but while some of the other buffers have not completed.  This
 * locked buffer would confuse end_buffer_async_read() into not unlocking
 * the page.  So the absence of BH_Async_Read tells end_buffer_async_read()
 * that this buffer is not under async I/O.
 *
 * The page comes unlocked when it has no locked buffer_async buffers
 * left.
 *
 * PageLocked prevents anyone starting new async I/O reads any of
 * the buffers.
 *
 * PageWriteback is used to prevent simultaneous writeout of the same
 * page.
 *
 * PageLocked prevents anyone from starting writeback of a page which is
 * under read I/O (PageWriteback is only ever set against a locked page).
 */
static void mark_buffer_async_read(struct buffer_head *bh)
{
	bh->b_end_io = end_buffer_async_read;
	set_buffer_async_read(bh);
}

void mark_buffer_async_write(struct buffer_head *bh)
{
	bh->b_end_io = end_buffer_async_write;
	set_buffer_async_write(bh);
}
EXPORT_SYMBOL(mark_buffer_async_write);


/*
 * fs/buffer.c contains helper functions for buffer-backed address space's
 * fsync functions.  A common requirement for buffer-based filesystems is
 * that certain data from the backing blockdev needs to be written out for
 * a successful fsync().  For example, ext2 indirect blocks need to be
 * written back and waited upon before fsync() returns.
 *
 * The functions mark_buffer_inode_dirty(), fsync_inode_buffers(),
 * inode_has_buffers() and invalidate_inode_buffers() are provided for the
 * management of a list of dependent buffers at ->i_mapping->private_list.
 *
 * Locking is a little subtle: try_to_free_buffers() will remove buffers
 * from their controlling inode's queue when they are being freed.  But
 * try_to_free_buffers() will be operating against the *blockdev* mapping
 * at the time, not against the S_ISREG file which depends on those buffers.
 * So the locking for private_list is via the private_lock in the address_space
 * which backs the buffers.  Which is different from the address_space 
 * against which the buffers are listed.  So for a particular address_space,
 * mapping->private_lock does *not* protect mapping->private_list!  In fact,
 * mapping->private_list will always be protected by the backing blockdev's
 * ->private_lock.
 *
 * Which introduces a requirement: all buffers on an address_space's
 * ->private_list must be from the same address_space: the blockdev's.
 *
 * address_spaces which do not place buffers at ->private_list via these
 * utility functions are free to use private_lock and private_list for
 * whatever they want.  The only requirement is that list_empty(private_list)
 * be true at clear_inode() time.
 *
 * FIXME: clear_inode should not call invalidate_inode_buffers().  The
 * filesystems should do that.  invalidate_inode_buffers() should just go
 * BUG_ON(!list_empty).
 *
 * FIXME: mark_buffer_dirty_inode() is a data-plane operation.  It should
 * take an address_space, not an inode.  And it should be called
 * mark_buffer_dirty_fsync() to clearly define why those buffers are being
 * queued up.
 *
 * FIXME: mark_buffer_dirty_inode() doesn't need to add the buffer to the
 * list if it is already on a list.  Because if the buffer is on a list,
 * it *must* already be on the right one.  If not, the filesystem is being
 * silly.  This will save a ton of locking.  But first we have to ensure
 * that buffers are taken *off* the old inode's list when they are freed
 * (presumably in truncate).  That requires careful auditing of all
 * filesystems (do it inside bforget()).  It could also be done by bringing
 * b_inode back.
 */

/*
 * The buffer's backing address_space's private_lock must be held
 */
static inline void __remove_assoc_queue(struct buffer_head *bh)
{
	list_del_init(&bh->b_assoc_buffers);
}

int inode_has_buffers(struct inode *inode)
{
	return !list_empty(&inode->i_data.private_list);
}

/*
 * osync is designed to support O_SYNC io.  It waits synchronously for
 * all already-submitted IO to complete, but does not queue any new
 * writes to the disk.
 *
 * To do O_SYNC writes, just queue the buffer writes with ll_rw_block as
 * you dirty the buffers, and then use osync_inode_buffers to wait for
 * completion.  Any other dirty buffers which are not yet queued for
 * write will not be flushed to disk by the osync.
 */
static int osync_buffers_list(spinlock_t *lock, struct list_head *list)
{
	struct buffer_head *bh;
	struct list_head *p;
	int err = 0;

	spin_lock(lock);
repeat:
	list_for_each_prev(p, list) {
		bh = BH_ENTRY(p);
		if (buffer_locked(bh)) {
			get_bh(bh);
			spin_unlock(lock);
			wait_on_buffer(bh);
			if (!buffer_uptodate(bh))
				err = -EIO;
			brelse(bh);
			spin_lock(lock);
			goto repeat;
		}
	}
	spin_unlock(lock);
	return err;
}

/**
 * sync_mapping_buffers - write out and wait upon a mapping's "associated"
 *                        buffers
752
 * @mapping: the mapping which wants those buffers written
Linus Torvalds's avatar
Linus Torvalds committed
753 754 755 756
 *
 * Starts I/O against the buffers at mapping->private_list, and waits upon
 * that I/O.
 *
757 758 759
 * Basically, this is a convenience function for fsync().
 * @mapping is a file or directory which needs those buffers to be written for
 * a successful fsync().
Linus Torvalds's avatar
Linus Torvalds committed
760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798
 */
int sync_mapping_buffers(struct address_space *mapping)
{
	struct address_space *buffer_mapping = mapping->assoc_mapping;

	if (buffer_mapping == NULL || list_empty(&mapping->private_list))
		return 0;

	return fsync_buffers_list(&buffer_mapping->private_lock,
					&mapping->private_list);
}
EXPORT_SYMBOL(sync_mapping_buffers);

/*
 * Called when we've recently written block `bblock', and it is known that
 * `bblock' was for a buffer_boundary() buffer.  This means that the block at
 * `bblock + 1' is probably a dirty indirect block.  Hunt it down and, if it's
 * dirty, schedule it for IO.  So that indirects merge nicely with their data.
 */
void write_boundary_block(struct block_device *bdev,
			sector_t bblock, unsigned blocksize)
{
	struct buffer_head *bh = __find_get_block(bdev, bblock + 1, blocksize);
	if (bh) {
		if (buffer_dirty(bh))
			ll_rw_block(WRITE, 1, &bh);
		put_bh(bh);
	}
}

void mark_buffer_dirty_inode(struct buffer_head *bh, struct inode *inode)
{
	struct address_space *mapping = inode->i_mapping;
	struct address_space *buffer_mapping = bh->b_page->mapping;

	mark_buffer_dirty(bh);
	if (!mapping->assoc_mapping) {
		mapping->assoc_mapping = buffer_mapping;
	} else {
799
		BUG_ON(mapping->assoc_mapping != buffer_mapping);
Linus Torvalds's avatar
Linus Torvalds committed
800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861
	}
	if (list_empty(&bh->b_assoc_buffers)) {
		spin_lock(&buffer_mapping->private_lock);
		list_move_tail(&bh->b_assoc_buffers,
				&mapping->private_list);
		spin_unlock(&buffer_mapping->private_lock);
	}
}
EXPORT_SYMBOL(mark_buffer_dirty_inode);

/*
 * Add a page to the dirty page list.
 *
 * It is a sad fact of life that this function is called from several places
 * deeply under spinlocking.  It may not sleep.
 *
 * If the page has buffers, the uptodate buffers are set dirty, to preserve
 * dirty-state coherency between the page and the buffers.  It the page does
 * not have buffers then when they are later attached they will all be set
 * dirty.
 *
 * The buffers are dirtied before the page is dirtied.  There's a small race
 * window in which a writepage caller may see the page cleanness but not the
 * buffer dirtiness.  That's fine.  If this code were to set the page dirty
 * before the buffers, a concurrent writepage caller could clear the page dirty
 * bit, see a bunch of clean buffers and we'd end up with dirty buffers/clean
 * page on the dirty page list.
 *
 * We use private_lock to lock against try_to_free_buffers while using the
 * page's buffer list.  Also use this to protect against clean buffers being
 * added to the page after it was set dirty.
 *
 * FIXME: may need to call ->reservepage here as well.  That's rather up to the
 * address_space though.
 */
int __set_page_dirty_buffers(struct page *page)
{
	struct address_space * const mapping = page->mapping;

	spin_lock(&mapping->private_lock);
	if (page_has_buffers(page)) {
		struct buffer_head *head = page_buffers(page);
		struct buffer_head *bh = head;

		do {
			set_buffer_dirty(bh);
			bh = bh->b_this_page;
		} while (bh != head);
	}
	spin_unlock(&mapping->private_lock);

	if (!TestSetPageDirty(page)) {
		write_lock_irq(&mapping->tree_lock);
		if (page->mapping) {	/* Race with truncate? */
			if (mapping_cap_account_dirty(mapping))
				inc_page_state(nr_dirty);
			radix_tree_tag_set(&mapping->page_tree,
						page_index(page),
						PAGECACHE_TAG_DIRTY);
		}
		write_unlock_irq(&mapping->tree_lock);
		__mark_inode_dirty(mapping->host, I_DIRTY_PAGES);
862
		return 1;
Linus Torvalds's avatar
Linus Torvalds committed
863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909
	}
	return 0;
}
EXPORT_SYMBOL(__set_page_dirty_buffers);

/*
 * Write out and wait upon a list of buffers.
 *
 * We have conflicting pressures: we want to make sure that all
 * initially dirty buffers get waited on, but that any subsequently
 * dirtied buffers don't.  After all, we don't want fsync to last
 * forever if somebody is actively writing to the file.
 *
 * Do this in two main stages: first we copy dirty buffers to a
 * temporary inode list, queueing the writes as we go.  Then we clean
 * up, waiting for those writes to complete.
 * 
 * During this second stage, any subsequent updates to the file may end
 * up refiling the buffer on the original inode's dirty list again, so
 * there is a chance we will end up with a buffer queued for write but
 * not yet completed on that list.  So, as a final cleanup we go through
 * the osync code to catch these locked, dirty buffers without requeuing
 * any newly dirty buffers for write.
 */
static int fsync_buffers_list(spinlock_t *lock, struct list_head *list)
{
	struct buffer_head *bh;
	struct list_head tmp;
	int err = 0, err2;

	INIT_LIST_HEAD(&tmp);

	spin_lock(lock);
	while (!list_empty(list)) {
		bh = BH_ENTRY(list->next);
		list_del_init(&bh->b_assoc_buffers);
		if (buffer_dirty(bh) || buffer_locked(bh)) {
			list_add(&bh->b_assoc_buffers, &tmp);
			if (buffer_dirty(bh)) {
				get_bh(bh);
				spin_unlock(lock);
				/*
				 * Ensure any pending I/O completes so that
				 * ll_rw_block() actually writes the current
				 * contents - it is a noop if I/O is still in
				 * flight on potentially older contents.
				 */
910
				ll_rw_block(SWRITE, 1, &bh);
Linus Torvalds's avatar
Linus Torvalds committed
911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018
				brelse(bh);
				spin_lock(lock);
			}
		}
	}

	while (!list_empty(&tmp)) {
		bh = BH_ENTRY(tmp.prev);
		__remove_assoc_queue(bh);
		get_bh(bh);
		spin_unlock(lock);
		wait_on_buffer(bh);
		if (!buffer_uptodate(bh))
			err = -EIO;
		brelse(bh);
		spin_lock(lock);
	}
	
	spin_unlock(lock);
	err2 = osync_buffers_list(lock, list);
	if (err)
		return err;
	else
		return err2;
}

/*
 * Invalidate any and all dirty buffers on a given inode.  We are
 * probably unmounting the fs, but that doesn't mean we have already
 * done a sync().  Just drop the buffers from the inode list.
 *
 * NOTE: we take the inode's blockdev's mapping's private_lock.  Which
 * assumes that all the buffers are against the blockdev.  Not true
 * for reiserfs.
 */
void invalidate_inode_buffers(struct inode *inode)
{
	if (inode_has_buffers(inode)) {
		struct address_space *mapping = &inode->i_data;
		struct list_head *list = &mapping->private_list;
		struct address_space *buffer_mapping = mapping->assoc_mapping;

		spin_lock(&buffer_mapping->private_lock);
		while (!list_empty(list))
			__remove_assoc_queue(BH_ENTRY(list->next));
		spin_unlock(&buffer_mapping->private_lock);
	}
}

/*
 * Remove any clean buffers from the inode's buffer list.  This is called
 * when we're trying to free the inode itself.  Those buffers can pin it.
 *
 * Returns true if all buffers were removed.
 */
int remove_inode_buffers(struct inode *inode)
{
	int ret = 1;

	if (inode_has_buffers(inode)) {
		struct address_space *mapping = &inode->i_data;
		struct list_head *list = &mapping->private_list;
		struct address_space *buffer_mapping = mapping->assoc_mapping;

		spin_lock(&buffer_mapping->private_lock);
		while (!list_empty(list)) {
			struct buffer_head *bh = BH_ENTRY(list->next);
			if (buffer_dirty(bh)) {
				ret = 0;
				break;
			}
			__remove_assoc_queue(bh);
		}
		spin_unlock(&buffer_mapping->private_lock);
	}
	return ret;
}

/*
 * Create the appropriate buffers when given a page for data area and
 * the size of each buffer.. Use the bh->b_this_page linked list to
 * follow the buffers created.  Return NULL if unable to create more
 * buffers.
 *
 * The retry flag is used to differentiate async IO (paging, swapping)
 * which may not fail from ordinary buffer allocations.
 */
struct buffer_head *alloc_page_buffers(struct page *page, unsigned long size,
		int retry)
{
	struct buffer_head *bh, *head;
	long offset;

try_again:
	head = NULL;
	offset = PAGE_SIZE;
	while ((offset -= size) >= 0) {
		bh = alloc_buffer_head(GFP_NOFS);
		if (!bh)
			goto no_grow;

		bh->b_bdev = NULL;
		bh->b_this_page = head;
		bh->b_blocknr = -1;
		head = bh;

		bh->b_state = 0;
		atomic_set(&bh->b_count, 0);
1019
		bh->b_private = NULL;
Linus Torvalds's avatar
Linus Torvalds committed
1020 1021 1022 1023 1024
		bh->b_size = size;

		/* Link the buffer to its page */
		set_bh_page(bh, page, offset);

1025
		init_buffer(bh, NULL, NULL);
Linus Torvalds's avatar
Linus Torvalds committed
1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115
	}
	return head;
/*
 * In case anything failed, we just free everything we got.
 */
no_grow:
	if (head) {
		do {
			bh = head;
			head = head->b_this_page;
			free_buffer_head(bh);
		} while (head);
	}

	/*
	 * Return failure for non-async IO requests.  Async IO requests
	 * are not allowed to fail, so we have to wait until buffer heads
	 * become available.  But we don't want tasks sleeping with 
	 * partially complete buffers, so all were released above.
	 */
	if (!retry)
		return NULL;

	/* We're _really_ low on memory. Now we just
	 * wait for old buffer heads to become free due to
	 * finishing IO.  Since this is an async request and
	 * the reserve list is empty, we're sure there are 
	 * async buffer heads in use.
	 */
	free_more_memory();
	goto try_again;
}
EXPORT_SYMBOL_GPL(alloc_page_buffers);

static inline void
link_dev_buffers(struct page *page, struct buffer_head *head)
{
	struct buffer_head *bh, *tail;

	bh = head;
	do {
		tail = bh;
		bh = bh->b_this_page;
	} while (bh);
	tail->b_this_page = head;
	attach_page_buffers(page, head);
}

/*
 * Initialise the state of a blockdev page's buffers.
 */ 
static void
init_page_buffers(struct page *page, struct block_device *bdev,
			sector_t block, int size)
{
	struct buffer_head *head = page_buffers(page);
	struct buffer_head *bh = head;
	int uptodate = PageUptodate(page);

	do {
		if (!buffer_mapped(bh)) {
			init_buffer(bh, NULL, NULL);
			bh->b_bdev = bdev;
			bh->b_blocknr = block;
			if (uptodate)
				set_buffer_uptodate(bh);
			set_buffer_mapped(bh);
		}
		block++;
		bh = bh->b_this_page;
	} while (bh != head);
}

/*
 * Create the page-cache page that contains the requested block.
 *
 * This is user purely for blockdev mappings.
 */
static struct page *
grow_dev_page(struct block_device *bdev, sector_t block,
		pgoff_t index, int size)
{
	struct inode *inode = bdev->bd_inode;
	struct page *page;
	struct buffer_head *bh;

	page = find_or_create_page(inode->i_mapping, index, GFP_NOFS);
	if (!page)
		return NULL;

1116
	BUG_ON(!PageLocked(page));
Linus Torvalds's avatar
Linus Torvalds committed
1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161

	if (page_has_buffers(page)) {
		bh = page_buffers(page);
		if (bh->b_size == size) {
			init_page_buffers(page, bdev, block, size);
			return page;
		}
		if (!try_to_free_buffers(page))
			goto failed;
	}

	/*
	 * Allocate some buffers for this page
	 */
	bh = alloc_page_buffers(page, size, 0);
	if (!bh)
		goto failed;

	/*
	 * Link the page to the buffers and initialise them.  Take the
	 * lock to be atomic wrt __find_get_block(), which does not
	 * run under the page lock.
	 */
	spin_lock(&inode->i_mapping->private_lock);
	link_dev_buffers(page, bh);
	init_page_buffers(page, bdev, block, size);
	spin_unlock(&inode->i_mapping->private_lock);
	return page;

failed:
	BUG();
	unlock_page(page);
	page_cache_release(page);
	return NULL;
}

/*
 * Create buffers for the specified block device block's page.  If
 * that page was dirty, the buffers are set dirty also.
 *
 * Except that's a bug.  Attaching dirty buffers to a dirty
 * blockdev's page can result in filesystem corruption, because
 * some of those buffers may be aliases of filesystem data.
 * grow_dev_page() will go BUG() if this happens.
 */
1162
static int
Linus Torvalds's avatar
Linus Torvalds committed
1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185
grow_buffers(struct block_device *bdev, sector_t block, int size)
{
	struct page *page;
	pgoff_t index;
	int sizebits;

	sizebits = -1;
	do {
		sizebits++;
	} while ((size << sizebits) < PAGE_SIZE);

	index = block >> sizebits;
	block = index << sizebits;

	/* Create a page with the proper size buffers.. */
	page = grow_dev_page(bdev, block, index, size);
	if (!page)
		return 0;
	unlock_page(page);
	page_cache_release(page);
	return 1;
}

Adrian Bunk's avatar
Adrian Bunk committed
1186
static struct buffer_head *
Linus Torvalds's avatar
Linus Torvalds committed
1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237
__getblk_slow(struct block_device *bdev, sector_t block, int size)
{
	/* Size must be multiple of hard sectorsize */
	if (unlikely(size & (bdev_hardsect_size(bdev)-1) ||
			(size < 512 || size > PAGE_SIZE))) {
		printk(KERN_ERR "getblk(): invalid block size %d requested\n",
					size);
		printk(KERN_ERR "hardsect size: %d\n",
					bdev_hardsect_size(bdev));

		dump_stack();
		return NULL;
	}

	for (;;) {
		struct buffer_head * bh;

		bh = __find_get_block(bdev, block, size);
		if (bh)
			return bh;

		if (!grow_buffers(bdev, block, size))
			free_more_memory();
	}
}

/*
 * The relationship between dirty buffers and dirty pages:
 *
 * Whenever a page has any dirty buffers, the page's dirty bit is set, and
 * the page is tagged dirty in its radix tree.
 *
 * At all times, the dirtiness of the buffers represents the dirtiness of
 * subsections of the page.  If the page has buffers, the page dirty bit is
 * merely a hint about the true dirty state.
 *
 * When a page is set dirty in its entirety, all its buffers are marked dirty
 * (if the page has buffers).
 *
 * When a buffer is marked dirty, its page is dirtied, but the page's other
 * buffers are not.
 *
 * Also.  When blockdev buffers are explicitly read with bread(), they
 * individually become uptodate.  But their backing page remains not
 * uptodate - even if all of its buffers are uptodate.  A subsequent
 * block_read_full_page() against that page will discover all the uptodate
 * buffers, will set the page uptodate and will perform no I/O.
 */

/**
 * mark_buffer_dirty - mark a buffer_head as needing writeout
1238
 * @bh: the buffer_head to mark dirty
Linus Torvalds's avatar
Linus Torvalds committed
1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387
 *
 * mark_buffer_dirty() will set the dirty bit against the buffer, then set its
 * backing page dirty, then tag the page as dirty in its address_space's radix
 * tree and then attach the address_space's inode to its superblock's dirty
 * inode list.
 *
 * mark_buffer_dirty() is atomic.  It takes bh->b_page->mapping->private_lock,
 * mapping->tree_lock and the global inode_lock.
 */
void fastcall mark_buffer_dirty(struct buffer_head *bh)
{
	if (!buffer_dirty(bh) && !test_set_buffer_dirty(bh))
		__set_page_dirty_nobuffers(bh->b_page);
}

/*
 * Decrement a buffer_head's reference count.  If all buffers against a page
 * have zero reference count, are clean and unlocked, and if the page is clean
 * and unlocked then try_to_free_buffers() may strip the buffers from the page
 * in preparation for freeing it (sometimes, rarely, buffers are removed from
 * a page but it ends up not being freed, and buffers may later be reattached).
 */
void __brelse(struct buffer_head * buf)
{
	if (atomic_read(&buf->b_count)) {
		put_bh(buf);
		return;
	}
	printk(KERN_ERR "VFS: brelse: Trying to free free buffer\n");
	WARN_ON(1);
}

/*
 * bforget() is like brelse(), except it discards any
 * potentially dirty data.
 */
void __bforget(struct buffer_head *bh)
{
	clear_buffer_dirty(bh);
	if (!list_empty(&bh->b_assoc_buffers)) {
		struct address_space *buffer_mapping = bh->b_page->mapping;

		spin_lock(&buffer_mapping->private_lock);
		list_del_init(&bh->b_assoc_buffers);
		spin_unlock(&buffer_mapping->private_lock);
	}
	__brelse(bh);
}

static struct buffer_head *__bread_slow(struct buffer_head *bh)
{
	lock_buffer(bh);
	if (buffer_uptodate(bh)) {
		unlock_buffer(bh);
		return bh;
	} else {
		get_bh(bh);
		bh->b_end_io = end_buffer_read_sync;
		submit_bh(READ, bh);
		wait_on_buffer(bh);
		if (buffer_uptodate(bh))
			return bh;
	}
	brelse(bh);
	return NULL;
}

/*
 * Per-cpu buffer LRU implementation.  To reduce the cost of __find_get_block().
 * The bhs[] array is sorted - newest buffer is at bhs[0].  Buffers have their
 * refcount elevated by one when they're in an LRU.  A buffer can only appear
 * once in a particular CPU's LRU.  A single buffer can be present in multiple
 * CPU's LRUs at the same time.
 *
 * This is a transparent caching front-end to sb_bread(), sb_getblk() and
 * sb_find_get_block().
 *
 * The LRUs themselves only need locking against invalidate_bh_lrus.  We use
 * a local interrupt disable for that.
 */

#define BH_LRU_SIZE	8

struct bh_lru {
	struct buffer_head *bhs[BH_LRU_SIZE];
};

static DEFINE_PER_CPU(struct bh_lru, bh_lrus) = {{ NULL }};

#ifdef CONFIG_SMP
#define bh_lru_lock()	local_irq_disable()
#define bh_lru_unlock()	local_irq_enable()
#else
#define bh_lru_lock()	preempt_disable()
#define bh_lru_unlock()	preempt_enable()
#endif

static inline void check_irqs_on(void)
{
#ifdef irqs_disabled
	BUG_ON(irqs_disabled());
#endif
}

/*
 * The LRU management algorithm is dopey-but-simple.  Sorry.
 */
static void bh_lru_install(struct buffer_head *bh)
{
	struct buffer_head *evictee = NULL;
	struct bh_lru *lru;

	check_irqs_on();
	bh_lru_lock();
	lru = &__get_cpu_var(bh_lrus);
	if (lru->bhs[0] != bh) {
		struct buffer_head *bhs[BH_LRU_SIZE];
		int in;
		int out = 0;

		get_bh(bh);
		bhs[out++] = bh;
		for (in = 0; in < BH_LRU_SIZE; in++) {
			struct buffer_head *bh2 = lru->bhs[in];

			if (bh2 == bh) {
				__brelse(bh2);
			} else {
				if (out >= BH_LRU_SIZE) {
					BUG_ON(evictee != NULL);
					evictee = bh2;
				} else {
					bhs[out++] = bh2;
				}
			}
		}
		while (out < BH_LRU_SIZE)
			bhs[out++] = NULL;
		memcpy(lru->bhs, bhs, sizeof(bhs));
	}
	bh_lru_unlock();

	if (evictee)
		__brelse(evictee);
}

/*
 * Look up the bh in this cpu's LRU.  If it's there, move it to the head.
 */
1388
static struct buffer_head *
Linus Torvalds's avatar
Linus Torvalds committed
1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429
lookup_bh_lru(struct block_device *bdev, sector_t block, int size)
{
	struct buffer_head *ret = NULL;
	struct bh_lru *lru;
	int i;

	check_irqs_on();
	bh_lru_lock();
	lru = &__get_cpu_var(bh_lrus);
	for (i = 0; i < BH_LRU_SIZE; i++) {
		struct buffer_head *bh = lru->bhs[i];

		if (bh && bh->b_bdev == bdev &&
				bh->b_blocknr == block && bh->b_size == size) {
			if (i) {
				while (i) {
					lru->bhs[i] = lru->bhs[i - 1];
					i--;
				}
				lru->bhs[0] = bh;
			}
			get_bh(bh);
			ret = bh;
			break;
		}
	}
	bh_lru_unlock();
	return ret;
}

/*
 * Perform a pagecache lookup for the matching buffer.  If it's there, refresh
 * it in the LRU and mark it as accessed.  If it is not present then return
 * NULL
 */
struct buffer_head *
__find_get_block(struct block_device *bdev, sector_t block, int size)
{
	struct buffer_head *bh = lookup_bh_lru(bdev, block, size);

	if (bh == NULL) {
1430
		bh = __find_get_block_slow(bdev, block);
Linus Torvalds's avatar
Linus Torvalds committed
1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469
		if (bh)
			bh_lru_install(bh);
	}
	if (bh)
		touch_buffer(bh);
	return bh;
}
EXPORT_SYMBOL(__find_get_block);

/*
 * __getblk will locate (and, if necessary, create) the buffer_head
 * which corresponds to the passed block_device, block and size. The
 * returned buffer has its reference count incremented.
 *
 * __getblk() cannot fail - it just keeps trying.  If you pass it an
 * illegal block number, __getblk() will happily return a buffer_head
 * which represents the non-existent block.  Very weird.
 *
 * __getblk() will lock up the machine if grow_dev_page's try_to_free_buffers()
 * attempt is failing.  FIXME, perhaps?
 */
struct buffer_head *
__getblk(struct block_device *bdev, sector_t block, int size)
{
	struct buffer_head *bh = __find_get_block(bdev, block, size);

	might_sleep();
	if (bh == NULL)
		bh = __getblk_slow(bdev, block, size);
	return bh;
}
EXPORT_SYMBOL(__getblk);

/*
 * Do async read-ahead on a buffer..
 */
void __breadahead(struct block_device *bdev, sector_t block, int size)
{
	struct buffer_head *bh = __getblk(bdev, block, size);
Andrew Morton's avatar
Andrew Morton committed
1470 1471 1472 1473
	if (likely(bh)) {
		ll_rw_block(READA, 1, &bh);
		brelse(bh);
	}
Linus Torvalds's avatar
Linus Torvalds committed
1474 1475 1476 1477 1478
}
EXPORT_SYMBOL(__breadahead);

/**
 *  __bread() - reads a specified block and returns the bh
1479
 *  @bdev: the block_device to read from
Linus Torvalds's avatar
Linus Torvalds committed
1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490
 *  @block: number of block
 *  @size: size (in bytes) to read
 * 
 *  Reads a specified block, and returns buffer head that contains it.
 *  It returns NULL if the block was unreadable.
 */
struct buffer_head *
__bread(struct block_device *bdev, sector_t block, int size)
{
	struct buffer_head *bh = __getblk(bdev, block, size);

Andrew Morton's avatar
Andrew Morton committed
1491
	if (likely(bh) && !buffer_uptodate(bh))
Linus Torvalds's avatar
Linus Torvalds committed
1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522
		bh = __bread_slow(bh);
	return bh;
}
EXPORT_SYMBOL(__bread);

/*
 * invalidate_bh_lrus() is called rarely - but not only at unmount.
 * This doesn't race because it runs in each cpu either in irq
 * or with preempt disabled.
 */
static void invalidate_bh_lru(void *arg)
{
	struct bh_lru *b = &get_cpu_var(bh_lrus);
	int i;

	for (i = 0; i < BH_LRU_SIZE; i++) {
		brelse(b->bhs[i]);
		b->bhs[i] = NULL;
	}
	put_cpu_var(bh_lrus);
}
	
static void invalidate_bh_lrus(void)
{
	on_each_cpu(invalidate_bh_lru, NULL, 1, 1);
}

void set_bh_page(struct buffer_head *bh,
		struct page *page, unsigned long offset)
{
	bh->b_page = page;
1523
	BUG_ON(offset >= PAGE_SIZE);
Linus Torvalds's avatar
Linus Torvalds committed
1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536
	if (PageHighMem(page))
		/*
		 * This catches illegal uses and preserves the offset:
		 */
		bh->b_data = (char *)(0 + offset);
	else
		bh->b_data = page_address(page) + offset;
}
EXPORT_SYMBOL(set_bh_page);

/*
 * Called when truncating a buffer on a page completely.
 */
1537
static void discard_buffer(struct buffer_head * bh)
Linus Torvalds's avatar
Linus Torvalds committed
1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563
{
	lock_buffer(bh);
	clear_buffer_dirty(bh);
	bh->b_bdev = NULL;
	clear_buffer_mapped(bh);
	clear_buffer_req(bh);
	clear_buffer_new(bh);
	clear_buffer_delay(bh);
	unlock_buffer(bh);
}

/**
 * try_to_release_page() - release old fs-specific metadata on a page
 *
 * @page: the page which the kernel is trying to free
 * @gfp_mask: memory allocation flags (and I/O mode)
 *
 * The address_space is to try to release any data against the page
 * (presumably at page->private).  If the release was successful, return `1'.
 * Otherwise return zero.
 *
 * The @gfp_mask argument specifies whether I/O may be performed to release
 * this page (__GFP_IO), and whether the call may block (__GFP_WAIT).
 *
 * NOTE: @gfp_mask may go away, and this function may become non-blocking.
 */
Al Viro's avatar
Al Viro committed
1564
int try_to_release_page(struct page *page, gfp_t gfp_mask)
Linus Torvalds's avatar
Linus Torvalds committed
1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592
{
	struct address_space * const mapping = page->mapping;

	BUG_ON(!PageLocked(page));
	if (PageWriteback(page))
		return 0;
	
	if (mapping && mapping->a_ops->releasepage)
		return mapping->a_ops->releasepage(page, gfp_mask);
	return try_to_free_buffers(page);
}
EXPORT_SYMBOL(try_to_release_page);

/**
 * block_invalidatepage - invalidate part of all of a buffer-backed page
 *
 * @page: the page which is affected
 * @offset: the index of the truncation point
 *
 * block_invalidatepage() is called when all or part of the page has become
 * invalidatedby a truncate operation.
 *
 * block_invalidatepage() does not have to release all buffers, but it must
 * ensure that no dirty buffer is left outside @offset and that no I/O
 * is underway against any of the blocks which are outside the truncation
 * point.  Because the caller is about to free (and possibly reuse) those
 * blocks on-disk.
 */
1593
void block_invalidatepage(struct page *page, unsigned long offset)
Linus Torvalds's avatar
Linus Torvalds committed
1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622
{
	struct buffer_head *head, *bh, *next;
	unsigned int curr_off = 0;

	BUG_ON(!PageLocked(page));
	if (!page_has_buffers(page))
		goto out;

	head = page_buffers(page);
	bh = head;
	do {
		unsigned int next_off = curr_off + bh->b_size;
		next = bh->b_this_page;

		/*
		 * is this block fully invalidated?
		 */
		if (offset <= curr_off)
			discard_buffer(bh);
		curr_off = next_off;
		bh = next;
	} while (bh != head);

	/*
	 * We release buffers only if the entire page is being invalidated.
	 * The get_block cached value has been unconditionally invalidated,
	 * so real IO is not possible anymore.
	 */
	if (offset == 0)
1623
		try_to_release_page(page, 0);
Linus Torvalds's avatar
Linus Torvalds committed
1624
out:
1625
	return;
Linus Torvalds's avatar
Linus Torvalds committed
1626 1627 1628
}
EXPORT_SYMBOL(block_invalidatepage);

1629
void do_invalidatepage(struct page *page, unsigned long offset)
1630
{
1631 1632 1633 1634
	void (*invalidatepage)(struct page *, unsigned long);
	invalidatepage = page->mapping->a_ops->invalidatepage ? :
		block_invalidatepage;
	(*invalidatepage)(page, offset);
1635 1636
}

Linus Torvalds's avatar
Linus Torvalds committed
1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693
/*
 * We attach and possibly dirty the buffers atomically wrt
 * __set_page_dirty_buffers() via private_lock.  try_to_free_buffers
 * is already excluded via the page lock.
 */
void create_empty_buffers(struct page *page,
			unsigned long blocksize, unsigned long b_state)
{
	struct buffer_head *bh, *head, *tail;

	head = alloc_page_buffers(page, blocksize, 1);
	bh = head;
	do {
		bh->b_state |= b_state;
		tail = bh;
		bh = bh->b_this_page;
	} while (bh);
	tail->b_this_page = head;

	spin_lock(&page->mapping->private_lock);
	if (PageUptodate(page) || PageDirty(page)) {
		bh = head;
		do {
			if (PageDirty(page))
				set_buffer_dirty(bh);
			if (PageUptodate(page))
				set_buffer_uptodate(bh);
			bh = bh->b_this_page;
		} while (bh != head);
	}
	attach_page_buffers(page, head);
	spin_unlock(&page->mapping->private_lock);
}
EXPORT_SYMBOL(create_empty_buffers);

/*
 * We are taking a block for data and we don't want any output from any
 * buffer-cache aliases starting from return from that function and
 * until the moment when something will explicitly mark the buffer
 * dirty (hopefully that will not happen until we will free that block ;-)
 * We don't even need to mark it not-uptodate - nobody can expect
 * anything from a newly allocated buffer anyway. We used to used
 * unmap_buffer() for such invalidation, but that was wrong. We definitely
 * don't want to mark the alias unmapped, for example - it would confuse
 * anyone who might pick it with bread() afterwards...
 *
 * Also..  Note that bforget() doesn't lock the buffer.  So there can
 * be writeout I/O going on against recently-freed buffers.  We don't
 * wait on that I/O in bforget() - it's more efficient to wait on the I/O
 * only if we really need to.  That happens here.
 */
void unmap_underlying_metadata(struct block_device *bdev, sector_t block)
{
	struct buffer_head *old_bh;

	might_sleep();

1694
	old_bh = __find_get_block_slow(bdev, block);
Linus Torvalds's avatar
Linus Torvalds committed
1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734
	if (old_bh) {
		clear_buffer_dirty(old_bh);
		wait_on_buffer(old_bh);
		clear_buffer_req(old_bh);
		__brelse(old_bh);
	}
}
EXPORT_SYMBOL(unmap_underlying_metadata);

/*
 * NOTE! All mapped/uptodate combinations are valid:
 *
 *	Mapped	Uptodate	Meaning
 *
 *	No	No		"unknown" - must do get_block()
 *	No	Yes		"hole" - zero-filled
 *	Yes	No		"allocated" - allocated on disk, not read in
 *	Yes	Yes		"valid" - allocated and up-to-date in memory.
 *
 * "Dirty" is valid only with the last case (mapped+uptodate).
 */

/*
 * While block_write_full_page is writing back the dirty buffers under
 * the page lock, whoever dirtied the buffers may decide to clean them
 * again at any time.  We handle that by only looking at the buffer
 * state inside lock_buffer().
 *
 * If block_write_full_page() is called for regular writeback
 * (wbc->sync_mode == WB_SYNC_NONE) then it will redirty a page which has a
 * locked buffer.   This only can happen if someone has written the buffer
 * directly, with submit_bh().  At the address_space level PageWriteback
 * prevents this contention from occurring.
 */
static int __block_write_full_page(struct inode *inode, struct page *page,
			get_block_t *get_block, struct writeback_control *wbc)
{
	int err;
	sector_t block;
	sector_t last_block;
1735
	struct buffer_head *bh, *head;
1736
	const unsigned blocksize = 1 << inode->i_blkbits;
Linus Torvalds's avatar
Linus Torvalds committed
1737 1738 1739 1740 1741 1742 1743
	int nr_underway = 0;

	BUG_ON(!PageLocked(page));

	last_block = (i_size_read(inode) - 1) >> inode->i_blkbits;

	if (!page_has_buffers(page)) {
1744
		create_empty_buffers(page, blocksize,
Linus Torvalds's avatar
Linus Torvalds committed
1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757
					(1 << BH_Dirty)|(1 << BH_Uptodate));
	}

	/*
	 * Be very careful.  We have no exclusion from __set_page_dirty_buffers
	 * here, and the (potentially unmapped) buffers may become dirty at
	 * any time.  If a buffer becomes dirty here after we've inspected it
	 * then we just miss that fact, and the page stays dirty.
	 *
	 * Buffers outside i_size may be dirtied by __set_page_dirty_buffers;
	 * handle that here by just cleaning them.
	 */

1758
	block = (sector_t)page->index << (PAGE_CACHE_SHIFT - inode->i_blkbits);
Linus Torvalds's avatar
Linus Torvalds committed
1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778
	head = page_buffers(page);
	bh = head;

	/*
	 * Get all the dirty buffers mapped to disk addresses and
	 * handle any aliases from the underlying blockdev's mapping.
	 */
	do {
		if (block > last_block) {
			/*
			 * mapped buffers outside i_size will occur, because
			 * this page can be outside i_size when there is a
			 * truncate in progress.
			 */
			/*
			 * The buffer was zeroed by block_write_full_page()
			 */
			clear_buffer_dirty(bh);
			set_buffer_uptodate(bh);
		} else if (!buffer_mapped(bh) && buffer_dirty(bh)) {
1779
			WARN_ON(bh->b_size != blocksize);
Linus Torvalds's avatar
Linus Torvalds committed
1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831
			err = get_block(inode, block, bh, 1);
			if (err)
				goto recover;
			if (buffer_new(bh)) {
				/* blockdev mappings never come here */