buffer.c 83.0 KB
Newer Older
L
Linus Torvalds 已提交
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>
L
Linus Torvalds 已提交
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>
I
Ingo Molnar 已提交
44
#include <linux/bit_spinlock.h>
L
Linus Torvalds 已提交
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);
H
Hugh Dickins 已提交
100
	set_page_private(page, 0);
L
Linus Torvalds 已提交
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);
L
Linus Torvalds 已提交
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
	return ret;
}
EXPORT_SYMBOL(sync_blockdev);

/*
 * 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)
{
	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);

	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
 *
 * This takes the block device bd_mount_sem to make sure no new mounts
 * 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;

	down(&bdev->bd_mount_sem);
	sb = get_super(bdev);
	if (sb && !(sb->s_flags & MS_RDONLY)) {
		sb->s_frozen = SB_FREEZE_WRITE;
217
		smp_wmb();
L
Linus Torvalds 已提交
218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233

		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);

		sb->s_frozen = SB_FREEZE_TRANS;
234
		smp_wmb();
L
Linus Torvalds 已提交
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

		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;
262
		smp_wmb();
L
Linus Torvalds 已提交
263 264 265 266 267 268 269 270 271 272 273 274 275 276
		wake_up(&sb->s_wait_unfrozen);
		drop_super(sb);
	}

	up(&bdev->bd_mount_sem);
}
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)
{
277
	wakeup_pdflush(0);
L
Linus Torvalds 已提交
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
	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;
}

330
static long do_fsync(unsigned int fd, int datasync)
L
Linus Torvalds 已提交
331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346
{
	struct file * file;
	struct address_space *mapping;
	int ret, err;

	ret = -EBADF;
	file = fget(fd);
	if (!file)
		goto out;

	ret = -EINVAL;
	if (!file->f_op || !file->f_op->fsync) {
		/* Why?  We can still call filemap_fdatawrite */
		goto out_putf;
	}

347 348
	mapping = file->f_mapping;

L
Linus Torvalds 已提交
349 350 351 352 353 354 355
	current->flags |= PF_SYNCWRITE;
	ret = filemap_fdatawrite(mapping);

	/*
	 * We need to protect against concurrent writers,
	 * which could cause livelocks in fsync_buffers_list
	 */
356
	mutex_lock(&mapping->host->i_mutex);
357
	err = file->f_op->fsync(file, file->f_dentry, datasync);
L
Linus Torvalds 已提交
358 359
	if (!ret)
		ret = err;
360
	mutex_unlock(&mapping->host->i_mutex);
L
Linus Torvalds 已提交
361 362 363 364 365 366 367 368 369 370 371
	err = filemap_fdatawait(mapping);
	if (!ret)
		ret = err;
	current->flags &= ~PF_SYNCWRITE;

out_putf:
	fput(file);
out:
	return ret;
}

372
asmlinkage long sys_fsync(unsigned int fd)
L
Linus Torvalds 已提交
373
{
374 375
	return do_fsync(fd, 0);
}
L
Linus Torvalds 已提交
376

377 378 379
asmlinkage long sys_fdatasync(unsigned int fd)
{
	return do_fsync(fd, 1);
L
Linus Torvalds 已提交
380 381 382 383 384 385 386 387 388 389 390 391 392 393
}

/*
 * 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 *
394
__find_get_block_slow(struct block_device *bdev, sector_t block)
L
Linus Torvalds 已提交
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
{
	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",
			(unsigned long long)block, (unsigned long long)bh->b_blocknr);
		printk("b_state=0x%08lx, b_size=%u\n", bh->b_state, bh->b_size);
		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;

496
	wakeup_pdflush(1024);
L
Linus Torvalds 已提交
497 498 499
	yield();

	for_each_pgdat(pgdat) {
A
Al Viro 已提交
500
		zones = pgdat->node_zonelists[gfp_zone(GFP_NOFS)].zones;
L
Linus Torvalds 已提交
501
		if (*zones)
502
			try_to_free_pages(zones, GFP_NOFS);
L
Linus Torvalds 已提交
503 504 505 506 507 508 509 510 511 512
	}
}

/*
 * 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;
513
	struct buffer_head *first;
L
Linus Torvalds 已提交
514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534
	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.
	 */
535 536 537
	first = page_buffers(page);
	local_irq_save(flags);
	bit_spin_lock(BH_Uptodate_Lock, &first->b_state);
L
Linus Torvalds 已提交
538 539 540 541 542 543 544 545 546 547 548 549
	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);
550 551
	bit_spin_unlock(BH_Uptodate_Lock, &first->b_state);
	local_irq_restore(flags);
L
Linus Torvalds 已提交
552 553 554 555 556 557 558 559 560 561 562

	/*
	 * 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:
563 564
	bit_spin_unlock(BH_Uptodate_Lock, &first->b_state);
	local_irq_restore(flags);
L
Linus Torvalds 已提交
565 566 567 568 569 570 571 572 573 574 575
	return;
}

/*
 * Completion handler for block_write_full_page() - pages which are unlocked
 * during I/O, and which have PageWriteback cleared upon I/O completion.
 */
void end_buffer_async_write(struct buffer_head *bh, int uptodate)
{
	char b[BDEVNAME_SIZE];
	unsigned long flags;
576
	struct buffer_head *first;
L
Linus Torvalds 已提交
577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596
	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);
	}

597 598 599 600
	first = page_buffers(page);
	local_irq_save(flags);
	bit_spin_lock(BH_Uptodate_Lock, &first->b_state);

L
Linus Torvalds 已提交
601 602 603 604 605 606 607 608 609 610
	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;
	}
611 612
	bit_spin_unlock(BH_Uptodate_Lock, &first->b_state);
	local_irq_restore(flags);
L
Linus Torvalds 已提交
613 614 615 616
	end_page_writeback(page);
	return;

still_busy:
617 618
	bit_spin_unlock(BH_Uptodate_Lock, &first->b_state);
	local_irq_restore(flags);
L
Linus Torvalds 已提交
619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756
	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
757
 * @mapping: the mapping which wants those buffers written
L
Linus Torvalds 已提交
758 759 760 761
 *
 * Starts I/O against the buffers at mapping->private_list, and waits upon
 * that I/O.
 *
762 763 764
 * 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().
L
Linus Torvalds 已提交
765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915
 */
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 {
		if (mapping->assoc_mapping != buffer_mapping)
			BUG();
	}
	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);
	}
	
	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.
				 */
916
				ll_rw_block(SWRITE, 1, &bh);
L
Linus Torvalds 已提交
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 1019 1020 1021 1022 1023 1024
				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);
1025
		bh->b_private = NULL;
L
Linus Torvalds 已提交
1026 1027 1028 1029 1030
		bh->b_size = size;

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

1031
		init_buffer(bh, NULL, NULL);
L
Linus Torvalds 已提交
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 1116 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 1162 1163 1164 1165 1166 1167 1168
	}
	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;

	if (!PageLocked(page))
		BUG();

	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.
 */
1169
static int
L
Linus Torvalds 已提交
1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192
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;
}

A
Adrian Bunk 已提交
1193
static struct buffer_head *
L
Linus Torvalds 已提交
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 1238 1239 1240 1241 1242 1243 1244
__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
1245
 * @bh: the buffer_head to mark dirty
L
Linus Torvalds 已提交
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 1388 1389 1390 1391 1392 1393 1394
 *
 * 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.
 */
1395
static struct buffer_head *
L
Linus Torvalds 已提交
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 1430 1431 1432 1433 1434 1435 1436
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) {
1437
		bh = __find_get_block_slow(bdev, block);
L
Linus Torvalds 已提交
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 1470 1471 1472 1473 1474 1475 1476
		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);
A
Andrew Morton 已提交
1477 1478 1479 1480
	if (likely(bh)) {
		ll_rw_block(READA, 1, &bh);
		brelse(bh);
	}
L
Linus Torvalds 已提交
1481 1482 1483 1484 1485
}
EXPORT_SYMBOL(__breadahead);

/**
 *  __bread() - reads a specified block and returns the bh
1486
 *  @bdev: the block_device to read from
L
Linus Torvalds 已提交
1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497
 *  @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);

A
Andrew Morton 已提交
1498
	if (likely(bh) && !buffer_uptodate(bh))
L
Linus Torvalds 已提交
1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544
		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;
	if (offset >= PAGE_SIZE)
		BUG();
	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.
 */
1545
static void discard_buffer(struct buffer_head * bh)
L
Linus Torvalds 已提交
1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571
{
	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.
 */
A
Al Viro 已提交
1572
int try_to_release_page(struct page *page, gfp_t gfp_mask)
L
Linus Torvalds 已提交
1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 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 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637
{
	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.
 */
int block_invalidatepage(struct page *page, unsigned long offset)
{
	struct buffer_head *head, *bh, *next;
	unsigned int curr_off = 0;
	int ret = 1;

	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)
		ret = try_to_release_page(page, 0);
out:
	return ret;
}
EXPORT_SYMBOL(block_invalidatepage);

1638 1639 1640 1641 1642 1643 1644 1645 1646
int do_invalidatepage(struct page *page, unsigned long offset)
{
	int (*invalidatepage)(struct page *, unsigned long);
	invalidatepage = page->mapping->a_ops->invalidatepage;
	if (invalidatepage == NULL)
		invalidatepage = block_invalidatepage;
	return (*invalidatepage)(page, offset);
}

L
Linus Torvalds 已提交
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 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703
/*
 * 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();

1704
	old_bh = __find_get_block_slow(bdev, block);
L
Linus Torvalds 已提交
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 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744
	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;
1745
	struct buffer_head *bh, *head;
L
Linus Torvalds 已提交
1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766
	int nr_underway = 0;

	BUG_ON(!PageLocked(page));

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

	if (!page_has_buffers(page)) {
		create_empty_buffers(page, 1 << inode->i_blkbits,
					(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.
	 */

1767
	block = (sector_t)page->index << (PAGE_CACHE_SHIFT - inode->i_blkbits);
L
Linus Torvalds 已提交
1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 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 1832 1833 1834 1835 1836 1837 1838 1839
	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)) {
			err = get_block(inode, block, bh, 1);
			if (err)
				goto recover;
			if (buffer_new(bh)) {
				/* blockdev mappings never come here */
				clear_buffer_new(bh);
				unmap_underlying_metadata(bh->b_bdev,
							bh->b_blocknr);
			}
		}
		bh = bh->b_this_page;
		block++;
	} while (bh != head);

	do {
		if (!buffer_mapped(bh))
			continue;
		/*
		 * If it's a fully non-blocking write attempt and we cannot
		 * lock the buffer then redirty the page.  Note that this can
		 * potentially cause a busy-wait loop from pdflush and kswapd
		 * activity, but those code paths have their own higher-level
		 * throttling.
		 */
		if (wbc->sync_mode != WB_SYNC_NONE || !wbc->nonblocking) {
			lock_buffer(bh);
		} else if (test_set_buffer_locked(bh)) {
			redirty_page_for_writepage(wbc, page);
			continue;
		}
		if (test_clear_buffer_dirty(bh)) {
			mark_buffer_async_write(bh);
		} else {
			unlock_buffer(bh);
		}
	} while ((bh = bh->b_this_page) != head);

	/*
	 * The page and its buffers are protected by PageWriteback(), so we can
	 * drop the bh refcounts early.
	 */
	BUG_ON(PageWriteback(page));
	set_page_writeback(page);

	do {
		struct buffer_head *next = bh->b_this_page;
		if (buffer_async_write(bh)) {
			submit_bh(WRITE, bh);
			nr_underway++;
		}
		bh = next;
	} while (bh != head);
1840
	unlock_page(page);
L
Linus Torvalds 已提交
1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942

	err = 0;
done:
	if (nr_underway == 0) {
		/*
		 * The page was marked dirty, but the buffers were
		 * clean.  Someone wrote them back by hand with
		 * ll_rw_block/submit_bh.  A rare case.
		 */
		int uptodate = 1;
		do {
			if (!buffer_uptodate(bh)) {
				uptodate = 0;
				break;
			}
			bh = bh->b_this_page;
		} while (bh != head);
		if (uptodate)
			SetPageUptodate(page);
		end_page_writeback(page);
		/*
		 * The page and buffer_heads can be released at any time from
		 * here on.
		 */
		wbc->pages_skipped++;	/* We didn't write this page */
	}
	return err;

recover:
	/*
	 * ENOSPC, or some other error.  We may already have added some
	 * blocks to the file, so we need to write these out to avoid
	 * exposing stale data.
	 * The page is currently locked and not marked for writeback
	 */
	bh = head;
	/* Recovery: lock and submit the mapped buffers */
	do {
		if (buffer_mapped(bh) && buffer_dirty(bh)) {
			lock_buffer(bh);
			mark_buffer_async_write(bh);
		} else {
			/*
			 * The buffer may have been set dirty during
			 * attachment to a dirty page.
			 */
			clear_buffer_dirty(bh);
		}
	} while ((bh = bh->b_this_page) != head);
	SetPageError(page);
	BUG_ON(PageWriteback(page));
	set_page_writeback(page);
	unlock_page(page);
	do {
		struct buffer_head *next = bh->b_this_page;
		if (buffer_async_write(bh)) {
			clear_buffer_dirty(bh);
			submit_bh(WRITE, bh);
			nr_underway++;
		}
		bh = next;
	} while (bh != head);
	goto done;
}

static int __block_prepare_write(struct inode *inode, struct page *page,
		unsigned from, unsigned to, get_block_t *get_block)
{
	unsigned block_start, block_end;
	sector_t block;
	int err = 0;
	unsigned blocksize, bbits;
	struct buffer_head *bh, *head, *wait[2], **wait_bh=wait;

	BUG_ON(!PageLocked(page));
	BUG_ON(from > PAGE_CACHE_SIZE);
	BUG_ON(to > PAGE_CACHE_SIZE);
	BUG_ON(from > to);

	blocksize = 1 << inode->i_blkbits;
	if (!page_has_buffers(page))
		create_empty_buffers(page, blocksize, 0);
	head = page_buffers(page);

	bbits = inode->i_blkbits;
	block = (sector_t)page->index << (PAGE_CACHE_SHIFT - bbits);

	for(bh = head, block_start = 0; bh != head || !block_start;
	    block++, block_start=block_end, bh = bh->b_this_page) {
		block_end = block_start + blocksize;
		if (block_end <= from || block_start >= to) {
			if (PageUptodate(page)) {
				if (!buffer_uptodate(bh))
					set_buffer_uptodate(bh);
			}
			continue;
		}
		if (buffer_new(bh))
			clear_buffer_new(bh);
		if (!buffer_mapped(bh)) {
			err = get_block(inode, block, bh, 1);
			if (err)
1943
				break;
L
Linus Torvalds 已提交
1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983
			if (buffer_new(bh)) {
				unmap_underlying_metadata(bh->b_bdev,
							bh->b_blocknr);
				if (PageUptodate(page)) {
					set_buffer_uptodate(bh);
					continue;
				}
				if (block_end > to || block_start < from) {
					void *kaddr;

					kaddr = kmap_atomic(page, KM_USER0);
					if (block_end > to)
						memset(kaddr+to, 0,
							block_end-to);
					if (block_start < from)
						memset(kaddr+block_start,
							0, from-block_start);
					flush_dcache_page(page);
					kunmap_atomic(kaddr, KM_USER0);
				}
				continue;
			}
		}
		if (PageUptodate(page)) {
			if (!buffer_uptodate(bh))
				set_buffer_uptodate(bh);
			continue; 
		}
		if (!buffer_uptodate(bh) && !buffer_delay(bh) &&
		     (block_start < from || block_end > to)) {
			ll_rw_block(READ, 1, &bh);
			*wait_bh++=bh;
		}
	}
	/*
	 * If we issued read requests - let them complete.
	 */
	while(wait_bh > wait) {
		wait_on_buffer(*--wait_bh);
		if (!buffer_uptodate(*wait_bh))
1984
			err = -EIO;
L
Linus Torvalds 已提交
1985
	}
1986 1987 1988 1989 1990 1991 1992 1993
	if (!err) {
		bh = head;
		do {
			if (buffer_new(bh))
				clear_buffer_new(bh);
		} while ((bh = bh->b_this_page) != head);
		return 0;
	}
1994
	/* Error case: */
L
Linus Torvalds 已提交
1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074
	/*
	 * Zero out any newly allocated blocks to avoid exposing stale
	 * data.  If BH_New is set, we know that the block was newly
	 * allocated in the above loop.
	 */
	bh = head;
	block_start = 0;
	do {
		block_end = block_start+blocksize;
		if (block_end <= from)
			goto next_bh;
		if (block_start >= to)
			break;
		if (buffer_new(bh)) {
			void *kaddr;

			clear_buffer_new(bh);
			kaddr = kmap_atomic(page, KM_USER0);
			memset(kaddr+block_start, 0, bh->b_size);
			kunmap_atomic(kaddr, KM_USER0);
			set_buffer_uptodate(bh);
			mark_buffer_dirty(bh);
		}
next_bh:
		block_start = block_end;
		bh = bh->b_this_page;
	} while (bh != head);
	return err;
}

static int __block_commit_write(struct inode *inode, struct page *page,
		unsigned from, unsigned to)
{
	unsigned block_start, block_end;
	int partial = 0;
	unsigned blocksize;
	struct buffer_head *bh, *head;

	blocksize = 1 << inode->i_blkbits;

	for(bh = head = page_buffers(page), block_start = 0;
	    bh != head || !block_start;
	    block_start=block_end, bh = bh->b_this_page) {
		block_end = block_start + blocksize;
		if (block_end <= from || block_start >= to) {
			if (!buffer_uptodate(bh))
				partial = 1;
		} else {
			set_buffer_uptodate(bh);
			mark_buffer_dirty(bh);
		}
	}

	/*
	 * If this is a partial write which happened to make all buffers
	 * uptodate then we can optimize away a bogus readpage() for
	 * the next read(). Here we 'discover' whether the page went
	 * uptodate as a result of this (potentially partial) write.
	 */
	if (!partial)
		SetPageUptodate(page);
	return 0;
}

/*
 * Generic "read page" function for block devices that have the normal
 * get_block functionality. This is most of the block device filesystems.
 * Reads the page asynchronously --- the unlock_buffer() and
 * set/clear_buffer_uptodate() functions propagate buffer state into the
 * page struct once IO has completed.
 */
int block_read_full_page(struct page *page, get_block_t *get_block)
{
	struct inode *inode = page->mapping->host;
	sector_t iblock, lblock;
	struct buffer_head *bh, *head, *arr[MAX_BUF_PER_PAGE];
	unsigned int blocksize;
	int nr, i;
	int fully_mapped = 1;

M
Matt Mackall 已提交
2075
	BUG_ON(!PageLocked(page));
L
Linus Torvalds 已提交
2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091
	blocksize = 1 << inode->i_blkbits;
	if (!page_has_buffers(page))
		create_empty_buffers(page, blocksize, 0);
	head = page_buffers(page);

	iblock = (sector_t)page->index << (PAGE_CACHE_SHIFT - inode->i_blkbits);
	lblock = (i_size_read(inode)+blocksize-1) >> inode->i_blkbits;
	bh = head;
	nr = 0;
	i = 0;

	do {
		if (buffer_uptodate(bh))
			continue;

		if (!buffer_mapped(bh)) {
2092 2093
			int err = 0;

L
Linus Torvalds 已提交
2094 2095
			fully_mapped = 0;
			if (iblock < lblock) {
2096 2097
				err = get_block(inode, iblock, bh, 0);
				if (err)
L
Linus Torvalds 已提交
2098 2099 2100 2101 2102 2103 2104
					SetPageError(page);
			}
			if (!buffer_mapped(bh)) {
				void *kaddr = kmap_atomic(page, KM_USER0);
				memset(kaddr + i * blocksize, 0, blocksize);
				flush_dcache_page(page);
				kunmap_atomic(kaddr, KM_USER0);
2105 2106
				if (!err)
					set_buffer_uptodate(bh);
L
Linus Torvalds 已提交
2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158
				continue;
			}
			/*
			 * get_block() might have updated the buffer
			 * synchronously
			 */
			if (buffer_uptodate(bh))
				continue;
		}
		arr[nr++] = bh;
	} while (i++, iblock++, (bh = bh->b_this_page) != head);

	if (fully_mapped)
		SetPageMappedToDisk(page);

	if (!nr) {
		/*
		 * All buffers are uptodate - we can set the page uptodate
		 * as well. But not if get_block() returned an error.
		 */
		if (!PageError(page))
			SetPageUptodate(page);
		unlock_page(page);
		return 0;
	}

	/* Stage two: lock the buffers */
	for (i = 0; i < nr; i++) {
		bh = arr[i];
		lock_buffer(bh);
		mark_buffer_async_read(bh);
	}

	/*
	 * Stage 3: start the IO.  Check for uptodateness
	 * inside the buffer lock in case another process reading
	 * the underlying blockdev brought it uptodate (the sct fix).
	 */
	for (i = 0; i < nr; i++) {
		bh = arr[i];
		if (buffer_uptodate(bh))
			end_buffer_async_read(bh, 1);
		else
			submit_bh(READ, bh);
	}
	return 0;
}

/* utility function for filesystems that need to do work on expanding
 * truncates.  Uses prepare/commit_write to allow the filesystem to
 * deal with the hole.  
 */
2159 2160
static int __generic_cont_expand(struct inode *inode, loff_t size,
				 pgoff_t index, unsigned int offset)
L
Linus Torvalds 已提交
2161 2162 2163
{
	struct address_space *mapping = inode->i_mapping;
	struct page *page;
2164
	unsigned long limit;
L
Linus Torvalds 已提交
2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180
	int err;

	err = -EFBIG;
        limit = current->signal->rlim[RLIMIT_FSIZE].rlim_cur;
	if (limit != RLIM_INFINITY && size > (loff_t)limit) {
		send_sig(SIGXFSZ, current, 0);
		goto out;
	}
	if (size > inode->i_sb->s_maxbytes)
		goto out;

	err = -ENOMEM;
	page = grab_cache_page(mapping, index);
	if (!page)
		goto out;
	err = mapping->a_ops->prepare_write(NULL, page, offset, offset);
2181 2182 2183 2184 2185 2186 2187 2188 2189
	if (err) {
		/*
		 * ->prepare_write() may have instantiated a few blocks
		 * outside i_size.  Trim these off again.
		 */
		unlock_page(page);
		page_cache_release(page);
		vmtruncate(inode, inode->i_size);
		goto out;
L
Linus Torvalds 已提交
2190
	}
2191 2192 2193

	err = mapping->a_ops->commit_write(NULL, page, offset, offset);

L
Linus Torvalds 已提交
2194 2195 2196 2197 2198 2199 2200 2201
	unlock_page(page);
	page_cache_release(page);
	if (err > 0)
		err = 0;
out:
	return err;
}

2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231
int generic_cont_expand(struct inode *inode, loff_t size)
{
	pgoff_t index;
	unsigned int offset;

	offset = (size & (PAGE_CACHE_SIZE - 1)); /* Within page */

	/* ugh.  in prepare/commit_write, if from==to==start of block, we
	** skip the prepare.  make sure we never send an offset for the start
	** of a block
	*/
	if ((offset & (inode->i_sb->s_blocksize - 1)) == 0) {
		/* caller must handle this extra byte. */
		offset++;
	}
	index = size >> PAGE_CACHE_SHIFT;

	return __generic_cont_expand(inode, size, index, offset);
}

int generic_cont_expand_simple(struct inode *inode, loff_t size)
{
	loff_t pos = size - 1;
	pgoff_t index = pos >> PAGE_CACHE_SHIFT;
	unsigned int offset = (pos & (PAGE_CACHE_SIZE - 1)) + 1;

	/* prepare/commit_write can handle even if from==to==start of block. */
	return __generic_cont_expand(inode, size, index, offset);
}

L
Linus Torvalds 已提交
2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342
/*
 * For moronic filesystems that do not allow holes in file.
 * We may have to extend the file.
 */

int cont_prepare_write(struct page *page, unsigned offset,
		unsigned to, get_block_t *get_block, loff_t *bytes)
{
	struct address_space *mapping = page->mapping;
	struct inode *inode = mapping->host;
	struct page *new_page;
	pgoff_t pgpos;
	long status;
	unsigned zerofrom;
	unsigned blocksize = 1 << inode->i_blkbits;
	void *kaddr;

	while(page->index > (pgpos = *bytes>>PAGE_CACHE_SHIFT)) {
		status = -ENOMEM;
		new_page = grab_cache_page(mapping, pgpos);
		if (!new_page)
			goto out;
		/* we might sleep */
		if (*bytes>>PAGE_CACHE_SHIFT != pgpos) {
			unlock_page(new_page);
			page_cache_release(new_page);
			continue;
		}
		zerofrom = *bytes & ~PAGE_CACHE_MASK;
		if (zerofrom & (blocksize-1)) {
			*bytes |= (blocksize-1);
			(*bytes)++;
		}
		status = __block_prepare_write(inode, new_page, zerofrom,
						PAGE_CACHE_SIZE, get_block);
		if (status)
			goto out_unmap;
		kaddr = kmap_atomic(new_page, KM_USER0);
		memset(kaddr+zerofrom, 0, PAGE_CACHE_SIZE-zerofrom);
		flush_dcache_page(new_page);
		kunmap_atomic(kaddr, KM_USER0);
		generic_commit_write(NULL, new_page, zerofrom, PAGE_CACHE_SIZE);
		unlock_page(new_page);
		page_cache_release(new_page);
	}

	if (page->index < pgpos) {
		/* completely inside the area */
		zerofrom = offset;
	} else {
		/* page covers the boundary, find the boundary offset */
		zerofrom = *bytes & ~PAGE_CACHE_MASK;

		/* if we will expand the thing last block will be filled */
		if (to > zerofrom && (zerofrom & (blocksize-1))) {
			*bytes |= (blocksize-1);
			(*bytes)++;
		}

		/* starting below the boundary? Nothing to zero out */
		if (offset <= zerofrom)
			zerofrom = offset;
	}
	status = __block_prepare_write(inode, page, zerofrom, to, get_block);
	if (status)
		goto out1;
	if (zerofrom < offset) {
		kaddr = kmap_atomic(page, KM_USER0);
		memset(kaddr+zerofrom, 0, offset-zerofrom);
		flush_dcache_page(page);
		kunmap_atomic(kaddr, KM_USER0);
		__block_commit_write(inode, page, zerofrom, offset);
	}
	return 0;
out1:
	ClearPageUptodate(page);
	return status;

out_unmap:
	ClearPageUptodate(new_page);
	unlock_page(new_page);
	page_cache_release(new_page);
out:
	return status;
}

int block_prepare_write(struct page *page, unsigned from, unsigned to,
			get_block_t *get_block)
{
	struct inode *inode = page->mapping->host;
	int err = __block_prepare_write(inode, page, from, to, get_block);
	if (err)
		ClearPageUptodate(page);
	return err;
}

int block_commit_write(struct page *page, unsigned from, unsigned to)
{
	struct inode *inode = page->mapping->host;
	__block_commit_write(inode,page,from,to);
	return 0;
}

int generic_commit_write(struct file *file, struct page *page,
		unsigned from, unsigned to)
{
	struct inode *inode = page->mapping->host;
	loff_t pos = ((loff_t)page->index << PAGE_CACHE_SHIFT) + to;
	__block_commit_write(inode,page,from,to);
	/*
	 * No need to use i_size_read() here, the i_size
2343
	 * cannot change under us because we hold i_mutex.
L
Linus Torvalds 已提交
2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639
	 */
	if (pos > inode->i_size) {
		i_size_write(inode, pos);
		mark_inode_dirty(inode);
	}
	return 0;
}


/*
 * nobh_prepare_write()'s prereads are special: the buffer_heads are freed
 * immediately, while under the page lock.  So it needs a special end_io
 * handler which does not touch the bh after unlocking it.
 *
 * Note: unlock_buffer() sort-of does touch the bh after unlocking it, but
 * a race there is benign: unlock_buffer() only use the bh's address for
 * hashing after unlocking the buffer, so it doesn't actually touch the bh
 * itself.
 */
static void end_buffer_read_nobh(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);
}

/*
 * On entry, the page is fully not uptodate.
 * On exit the page is fully uptodate in the areas outside (from,to)
 */
int nobh_prepare_write(struct page *page, unsigned from, unsigned to,
			get_block_t *get_block)
{
	struct inode *inode = page->mapping->host;
	const unsigned blkbits = inode->i_blkbits;
	const unsigned blocksize = 1 << blkbits;
	struct buffer_head map_bh;
	struct buffer_head *read_bh[MAX_BUF_PER_PAGE];
	unsigned block_in_page;
	unsigned block_start;
	sector_t block_in_file;
	char *kaddr;
	int nr_reads = 0;
	int i;
	int ret = 0;
	int is_mapped_to_disk = 1;
	int dirtied_it = 0;

	if (PageMappedToDisk(page))
		return 0;

	block_in_file = (sector_t)page->index << (PAGE_CACHE_SHIFT - blkbits);
	map_bh.b_page = page;

	/*
	 * We loop across all blocks in the page, whether or not they are
	 * part of the affected region.  This is so we can discover if the
	 * page is fully mapped-to-disk.
	 */
	for (block_start = 0, block_in_page = 0;
		  block_start < PAGE_CACHE_SIZE;
		  block_in_page++, block_start += blocksize) {
		unsigned block_end = block_start + blocksize;
		int create;

		map_bh.b_state = 0;
		create = 1;
		if (block_start >= to)
			create = 0;
		ret = get_block(inode, block_in_file + block_in_page,
					&map_bh, create);
		if (ret)
			goto failed;
		if (!buffer_mapped(&map_bh))
			is_mapped_to_disk = 0;
		if (buffer_new(&map_bh))
			unmap_underlying_metadata(map_bh.b_bdev,
							map_bh.b_blocknr);
		if (PageUptodate(page))
			continue;
		if (buffer_new(&map_bh) || !buffer_mapped(&map_bh)) {
			kaddr = kmap_atomic(page, KM_USER0);
			if (block_start < from) {
				memset(kaddr+block_start, 0, from-block_start);
				dirtied_it = 1;
			}
			if (block_end > to) {
				memset(kaddr + to, 0, block_end - to);
				dirtied_it = 1;
			}
			flush_dcache_page(page);
			kunmap_atomic(kaddr, KM_USER0);
			continue;
		}
		if (buffer_uptodate(&map_bh))
			continue;	/* reiserfs does this */
		if (block_start < from || block_end > to) {
			struct buffer_head *bh = alloc_buffer_head(GFP_NOFS);

			if (!bh) {
				ret = -ENOMEM;
				goto failed;
			}
			bh->b_state = map_bh.b_state;
			atomic_set(&bh->b_count, 0);
			bh->b_this_page = NULL;
			bh->b_page = page;
			bh->b_blocknr = map_bh.b_blocknr;
			bh->b_size = blocksize;
			bh->b_data = (char *)(long)block_start;
			bh->b_bdev = map_bh.b_bdev;
			bh->b_private = NULL;
			read_bh[nr_reads++] = bh;
		}
	}

	if (nr_reads) {
		struct buffer_head *bh;

		/*
		 * The page is locked, so these buffers are protected from
		 * any VM or truncate activity.  Hence we don't need to care
		 * for the buffer_head refcounts.
		 */
		for (i = 0; i < nr_reads; i++) {
			bh = read_bh[i];
			lock_buffer(bh);
			bh->b_end_io = end_buffer_read_nobh;
			submit_bh(READ, bh);
		}
		for (i = 0; i < nr_reads; i++) {
			bh = read_bh[i];
			wait_on_buffer(bh);
			if (!buffer_uptodate(bh))
				ret = -EIO;
			free_buffer_head(bh);
			read_bh[i] = NULL;
		}
		if (ret)
			goto failed;
	}

	if (is_mapped_to_disk)
		SetPageMappedToDisk(page);
	SetPageUptodate(page);

	/*
	 * Setting the page dirty here isn't necessary for the prepare_write
	 * function - commit_write will do that.  But if/when this function is
	 * used within the pagefault handler to ensure that all mmapped pages
	 * have backing space in the filesystem, we will need to dirty the page
	 * if its contents were altered.
	 */
	if (dirtied_it)
		set_page_dirty(page);

	return 0;

failed:
	for (i = 0; i < nr_reads; i++) {
		if (read_bh[i])
			free_buffer_head(read_bh[i]);
	}

	/*
	 * Error recovery is pretty slack.  Clear the page and mark it dirty
	 * so we'll later zero out any blocks which _were_ allocated.
	 */
	kaddr = kmap_atomic(page, KM_USER0);
	memset(kaddr, 0, PAGE_CACHE_SIZE);
	kunmap_atomic(kaddr, KM_USER0);
	SetPageUptodate(page);
	set_page_dirty(page);
	return ret;
}
EXPORT_SYMBOL(nobh_prepare_write);

int nobh_commit_write(struct file *file, struct page *page,
		unsigned from, unsigned to)
{
	struct inode *inode = page->mapping->host;
	loff_t pos = ((loff_t)page->index << PAGE_CACHE_SHIFT) + to;

	set_page_dirty(page);
	if (pos > inode->i_size) {
		i_size_write(inode, pos);
		mark_inode_dirty(inode);
	}
	return 0;
}
EXPORT_SYMBOL(nobh_commit_write);

/*
 * nobh_writepage() - based on block_full_write_page() except
 * that it tries to operate without attaching bufferheads to
 * the page.
 */
int nobh_writepage(struct page *page, get_block_t *get_block,
			struct writeback_control *wbc)
{
	struct inode * const inode = page->mapping->host;
	loff_t i_size = i_size_read(inode);
	const pgoff_t end_index = i_size >> PAGE_CACHE_SHIFT;
	unsigned offset;
	void *kaddr;
	int ret;

	/* Is the page fully inside i_size? */
	if (page->index < end_index)
		goto out;

	/* Is the page fully outside i_size? (truncate in progress) */
	offset = i_size & (PAGE_CACHE_SIZE-1);
	if (page->index >= end_index+1 || !offset) {
		/*
		 * The page may have dirty, unmapped buffers.  For example,
		 * they may have been added in ext3_writepage().  Make them
		 * freeable here, so the page does not leak.
		 */
#if 0
		/* Not really sure about this  - do we need this ? */
		if (page->mapping->a_ops->invalidatepage)
			page->mapping->a_ops->invalidatepage(page, offset);
#endif
		unlock_page(page);
		return 0; /* don't care */
	}

	/*
	 * The page straddles i_size.  It must be zeroed out on each and every
	 * writepage invocation because it may be mmapped.  "A file is mapped
	 * in multiples of the page size.  For a file that is not a multiple of
	 * the  page size, the remaining memory is zeroed when mapped, and
	 * writes to that region are not written out to the file."
	 */
	kaddr = kmap_atomic(page, KM_USER0);
	memset(kaddr + offset, 0, PAGE_CACHE_SIZE - offset);
	flush_dcache_page(page);
	kunmap_atomic(kaddr, KM_USER0);
out:
	ret = mpage_writepage(page, get_block, wbc);
	if (ret == -EAGAIN)
		ret = __block_write_full_page(inode, page, get_block, wbc);
	return ret;
}
EXPORT_SYMBOL(nobh_writepage);

/*
 * This function assumes that ->prepare_write() uses nobh_prepare_write().
 */
int nobh_truncate_page(struct address_space *mapping, loff_t from)
{
	struct inode *inode = mapping->host;
	unsigned blocksize = 1 << inode->i_blkbits;
	pgoff_t index = from >> PAGE_CACHE_SHIFT;
	unsigned offset = from & (PAGE_CACHE_SIZE-1);
	unsigned to;
	struct page *page;
	struct address_space_operations *a_ops = mapping->a_ops;
	char *kaddr;
	int ret = 0;

	if ((offset & (blocksize - 1)) == 0)
		goto out;

	ret = -ENOMEM;
	page = grab_cache_page(mapping, index);
	if (!page)
		goto out;

	to = (offset + blocksize) & ~(blocksize - 1);
	ret = a_ops->prepare_write(NULL, page, offset, to);
	if (ret == 0) {
		kaddr = kmap_atomic(page, KM_USER0);
		memset(kaddr + offset, 0, PAGE_CACHE_SIZE - offset);
		flush_dcache_page(page);
		kunmap_atomic(kaddr, KM_USER0);
		set_page_dirty(page);
	}
	unlock_page(page);
	page_cache_release(page);
out:
	return ret;
}
EXPORT_SYMBOL(nobh_truncate_page);

int block_truncate_page(struct address_space *mapping,
			loff_t from, get_block_t *get_block)
{
	pgoff_t index = from >> PAGE_CACHE_SHIFT;
	unsigned offset = from & (PAGE_CACHE_SIZE-1);
	unsigned blocksize;
2640
	sector_t iblock;
L
Linus Torvalds 已提交
2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655
	unsigned length, pos;
	struct inode *inode = mapping->host;
	struct page *page;
	struct buffer_head *bh;
	void *kaddr;
	int err;

	blocksize = 1 << inode->i_blkbits;
	length = offset & (blocksize - 1);

	/* Block boundary? Nothing to do */
	if (!length)
		return 0;

	length = blocksize - length;
2656
	iblock = (sector_t)index << (PAGE_CACHE_SHIFT - inode->i_blkbits);
L
Linus Torvalds 已提交
2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736
	
	page = grab_cache_page(mapping, index);
	err = -ENOMEM;
	if (!page)
		goto out;

	if (!page_has_buffers(page))
		create_empty_buffers(page, blocksize, 0);

	/* Find the buffer that contains "offset" */
	bh = page_buffers(page);
	pos = blocksize;
	while (offset >= pos) {
		bh = bh->b_this_page;
		iblock++;
		pos += blocksize;
	}

	err = 0;
	if (!buffer_mapped(bh)) {
		err = get_block(inode, iblock, bh, 0);
		if (err)
			goto unlock;
		/* unmapped? It's a hole - nothing to do */
		if (!buffer_mapped(bh))
			goto unlock;
	}

	/* Ok, it's mapped. Make sure it's up-to-date */
	if (PageUptodate(page))
		set_buffer_uptodate(bh);

	if (!buffer_uptodate(bh) && !buffer_delay(bh)) {
		err = -EIO;
		ll_rw_block(READ, 1, &bh);
		wait_on_buffer(bh);
		/* Uhhuh. Read error. Complain and punt. */
		if (!buffer_uptodate(bh))
			goto unlock;
	}

	kaddr = kmap_atomic(page, KM_USER0);
	memset(kaddr + offset, 0, length);
	flush_dcache_page(page);
	kunmap_atomic(kaddr, KM_USER0);

	mark_buffer_dirty(bh);
	err = 0;

unlock:
	unlock_page(page);
	page_cache_release(page);
out:
	return err;
}

/*
 * The generic ->writepage function for buffer-backed address_spaces
 */
int block_write_full_page(struct page *page, get_block_t *get_block,
			struct writeback_control *wbc)
{
	struct inode * const inode = page->mapping->host;
	loff_t i_size = i_size_read(inode);
	const pgoff_t end_index = i_size >> PAGE_CACHE_SHIFT;
	unsigned offset;
	void *kaddr;

	/* Is the page fully inside i_size? */
	if (page->index < end_index)
		return __block_write_full_page(inode, page, get_block, wbc);

	/* Is the page fully outside i_size? (truncate in progress) */
	offset = i_size & (PAGE_CACHE_SIZE-1);
	if (page->index >= end_index+1 || !offset) {
		/*
		 * The page may have dirty, unmapped buffers.  For example,
		 * they may have been added in ext3_writepage().  Make them
		 * freeable here, so the page does not leak.
		 */
2737
		do_invalidatepage(page, 0);
L
Linus Torvalds 已提交
2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833
		unlock_page(page);
		return 0; /* don't care */
	}

	/*
	 * The page straddles i_size.  It must be zeroed out on each and every
	 * writepage invokation because it may be mmapped.  "A file is mapped
	 * in multiples of the page size.  For a file that is not a multiple of
	 * the  page size, the remaining memory is zeroed when mapped, and
	 * writes to that region are not written out to the file."
	 */
	kaddr = kmap_atomic(page, KM_USER0);
	memset(kaddr + offset, 0, PAGE_CACHE_SIZE - offset);
	flush_dcache_page(page);
	kunmap_atomic(kaddr, KM_USER0);
	return __block_write_full_page(inode, page, get_block, wbc);
}

sector_t generic_block_bmap(struct address_space *mapping, sector_t block,
			    get_block_t *get_block)
{
	struct buffer_head tmp;
	struct inode *inode = mapping->host;
	tmp.b_state = 0;
	tmp.b_blocknr = 0;
	get_block(inode, block, &tmp, 0);
	return tmp.b_blocknr;
}

static int end_bio_bh_io_sync(struct bio *bio, unsigned int bytes_done, int err)
{
	struct buffer_head *bh = bio->bi_private;

	if (bio->bi_size)
		return 1;

	if (err == -EOPNOTSUPP) {
		set_bit(BIO_EOPNOTSUPP, &bio->bi_flags);
		set_bit(BH_Eopnotsupp, &bh->b_state);
	}

	bh->b_end_io(bh, test_bit(BIO_UPTODATE, &bio->bi_flags));
	bio_put(bio);
	return 0;
}

int submit_bh(int rw, struct buffer_head * bh)
{
	struct bio *bio;
	int ret = 0;

	BUG_ON(!buffer_locked(bh));
	BUG_ON(!buffer_mapped(bh));
	BUG_ON(!bh->b_end_io);

	if (buffer_ordered(bh) && (rw == WRITE))
		rw = WRITE_BARRIER;

	/*
	 * Only clear out a write error when rewriting, should this
	 * include WRITE_SYNC as well?
	 */
	if (test_set_buffer_req(bh) && (rw == WRITE || rw == WRITE_BARRIER))
		clear_buffer_write_io_error(bh);

	/*
	 * from here on down, it's all bio -- do the initial mapping,
	 * submit_bio -> generic_make_request may further map this bio around
	 */
	bio = bio_alloc(GFP_NOIO, 1);

	bio->bi_sector = bh->b_blocknr * (bh->b_size >> 9);
	bio->bi_bdev = bh->b_bdev;
	bio->bi_io_vec[0].bv_page = bh->b_page;
	bio->bi_io_vec[0].bv_len = bh->b_size;
	bio->bi_io_vec[0].bv_offset = bh_offset(bh);

	bio->bi_vcnt = 1;
	bio->bi_idx = 0;
	bio->bi_size = bh->b_size;

	bio->bi_end_io = end_bio_bh_io_sync;
	bio->bi_private = bh;

	bio_get(bio);
	submit_bio(rw, bio);

	if (bio_flagged(bio, BIO_EOPNOTSUPP))
		ret = -EOPNOTSUPP;

	bio_put(bio);
	return ret;
}

/**
 * ll_rw_block: low-level access to block devices (DEPRECATED)
2834
 * @rw: whether to %READ or %WRITE or %SWRITE or maybe %READA (readahead)
L
Linus Torvalds 已提交
2835 2836 2837
 * @nr: number of &struct buffer_heads in the array
 * @bhs: array of pointers to &struct buffer_head
 *
2838 2839 2840 2841 2842
 * ll_rw_block() takes an array of pointers to &struct buffer_heads, and
 * requests an I/O operation on them, either a %READ or a %WRITE.  The third
 * %SWRITE is like %WRITE only we make sure that the *current* data in buffers
 * are sent to disk. The fourth %READA option is described in the documentation
 * for generic_make_request() which ll_rw_block() calls.
L
Linus Torvalds 已提交
2843 2844
 *
 * This function drops any buffer that it cannot get a lock on (with the
2845 2846 2847 2848 2849
 * BH_Lock state bit) unless SWRITE is required, any buffer that appears to be
 * clean when doing a write request, and any buffer that appears to be
 * up-to-date when doing read request.  Further it marks as clean buffers that
 * are processed for writing (the buffer cache won't assume that they are
 * actually clean until the buffer gets unlocked).
L
Linus Torvalds 已提交
2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864
 *
 * ll_rw_block sets b_end_io to simple completion handler that marks
 * the buffer up-to-date (if approriate), unlocks the buffer and wakes
 * any waiters. 
 *
 * All of the buffers must be for the same device, and must also be a
 * multiple of the current approved size for the device.
 */
void ll_rw_block(int rw, int nr, struct buffer_head *bhs[])
{
	int i;

	for (i = 0; i < nr; i++) {
		struct buffer_head *bh = bhs[i];

2865 2866 2867
		if (rw == SWRITE)
			lock_buffer(bh);
		else if (test_set_buffer_locked(bh))
L
Linus Torvalds 已提交
2868 2869
			continue;

2870
		if (rw == WRITE || rw == SWRITE) {
L
Linus Torvalds 已提交
2871
			if (test_clear_buffer_dirty(bh)) {
2872
				bh->b_end_io = end_buffer_write_sync;
2873
				get_bh(bh);
L
Linus Torvalds 已提交
2874 2875 2876 2877 2878
				submit_bh(WRITE, bh);
				continue;
			}
		} else {
			if (!buffer_uptodate(bh)) {
2879
				bh->b_end_io = end_buffer_read_sync;
2880
				get_bh(bh);
L
Linus Torvalds 已提交
2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950
				submit_bh(rw, bh);
				continue;
			}
		}
		unlock_buffer(bh);
	}
}

/*
 * For a data-integrity writeout, we need to wait upon any in-progress I/O
 * and then start new I/O and then wait upon it.  The caller must have a ref on
 * the buffer_head.
 */
int sync_dirty_buffer(struct buffer_head *bh)
{
	int ret = 0;

	WARN_ON(atomic_read(&bh->b_count) < 1);
	lock_buffer(bh);
	if (test_clear_buffer_dirty(bh)) {
		get_bh(bh);
		bh->b_end_io = end_buffer_write_sync;
		ret = submit_bh(WRITE, bh);
		wait_on_buffer(bh);
		if (buffer_eopnotsupp(bh)) {
			clear_buffer_eopnotsupp(bh);
			ret = -EOPNOTSUPP;
		}
		if (!ret && !buffer_uptodate(bh))
			ret = -EIO;
	} else {
		unlock_buffer(bh);
	}
	return ret;
}

/*
 * try_to_free_buffers() checks if all the buffers on this particular page
 * are unused, and releases them if so.
 *
 * Exclusion against try_to_free_buffers may be obtained by either
 * locking the page or by holding its mapping's private_lock.
 *
 * If the page is dirty but all the buffers are clean then we need to
 * be sure to mark the page clean as well.  This is because the page
 * may be against a block device, and a later reattachment of buffers
 * to a dirty page will set *all* buffers dirty.  Which would corrupt
 * filesystem data on the same device.
 *
 * The same applies to regular filesystem pages: if all the buffers are
 * clean then we set the page clean and proceed.  To do that, we require
 * total exclusion from __set_page_dirty_buffers().  That is obtained with
 * private_lock.
 *
 * try_to_free_buffers() is non-blocking.
 */
static inline int buffer_busy(struct buffer_head *bh)
{
	return atomic_read(&bh->b_count) |
		(bh->b_state & ((1 << BH_Dirty) | (1 << BH_Lock)));
}

static int
drop_buffers(struct page *page, struct buffer_head **buffers_to_free)
{
	struct buffer_head *head = page_buffers(page);
	struct buffer_head *bh;

	bh = head;
	do {
A
akpm@osdl.org 已提交
2951
		if (buffer_write_io_error(bh) && page->mapping)
L
Linus Torvalds 已提交
2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085
			set_bit(AS_EIO, &page->mapping->flags);
		if (buffer_busy(bh))
			goto failed;
		bh = bh->b_this_page;
	} while (bh != head);

	do {
		struct buffer_head *next = bh->b_this_page;

		if (!list_empty(&bh->b_assoc_buffers))
			__remove_assoc_queue(bh);
		bh = next;
	} while (bh != head);
	*buffers_to_free = head;
	__clear_page_buffers(page);
	return 1;
failed:
	return 0;
}

int try_to_free_buffers(struct page *page)
{
	struct address_space * const mapping = page->mapping;
	struct buffer_head *buffers_to_free = NULL;
	int ret = 0;

	BUG_ON(!PageLocked(page));
	if (PageWriteback(page))
		return 0;

	if (mapping == NULL) {		/* can this still happen? */
		ret = drop_buffers(page, &buffers_to_free);
		goto out;
	}

	spin_lock(&mapping->private_lock);
	ret = drop_buffers(page, &buffers_to_free);
	if (ret) {
		/*
		 * If the filesystem writes its buffers by hand (eg ext3)
		 * then we can have clean buffers against a dirty page.  We
		 * clean the page here; otherwise later reattachment of buffers
		 * could encounter a non-uptodate page, which is unresolvable.
		 * This only applies in the rare case where try_to_free_buffers
		 * succeeds but the page is not freed.
		 */
		clear_page_dirty(page);
	}
	spin_unlock(&mapping->private_lock);
out:
	if (buffers_to_free) {
		struct buffer_head *bh = buffers_to_free;

		do {
			struct buffer_head *next = bh->b_this_page;
			free_buffer_head(bh);
			bh = next;
		} while (bh != buffers_to_free);
	}
	return ret;
}
EXPORT_SYMBOL(try_to_free_buffers);

int block_sync_page(struct page *page)
{
	struct address_space *mapping;

	smp_mb();
	mapping = page_mapping(page);
	if (mapping)
		blk_run_backing_dev(mapping->backing_dev_info, page);
	return 0;
}

/*
 * There are no bdflush tunables left.  But distributions are
 * still running obsolete flush daemons, so we terminate them here.
 *
 * Use of bdflush() is deprecated and will be removed in a future kernel.
 * The `pdflush' kernel threads fully replace bdflush daemons and this call.
 */
asmlinkage long sys_bdflush(int func, long data)
{
	static int msg_count;

	if (!capable(CAP_SYS_ADMIN))
		return -EPERM;

	if (msg_count < 5) {
		msg_count++;
		printk(KERN_INFO
			"warning: process `%s' used the obsolete bdflush"
			" system call\n", current->comm);
		printk(KERN_INFO "Fix your initscripts?\n");
	}

	if (func == 1)
		do_exit(0);
	return 0;
}

/*
 * Buffer-head allocation
 */
static kmem_cache_t *bh_cachep;

/*
 * Once the number of bh's in the machine exceeds this level, we start
 * stripping them in writeback.
 */
static int max_buffer_heads;

int buffer_heads_over_limit;

struct bh_accounting {
	int nr;			/* Number of live bh's */
	int ratelimit;		/* Limit cacheline bouncing */
};

static DEFINE_PER_CPU(struct bh_accounting, bh_accounting) = {0, 0};

static void recalc_bh_state(void)
{
	int i;
	int tot = 0;

	if (__get_cpu_var(bh_accounting).ratelimit++ < 4096)
		return;
	__get_cpu_var(bh_accounting).ratelimit = 0;
	for_each_cpu(i)
		tot += per_cpu(bh_accounting, i).nr;
	buffer_heads_over_limit = (tot > max_buffer_heads);
}
	
A
Al Viro 已提交
3086
struct buffer_head *alloc_buffer_head(gfp_t gfp_flags)
L
Linus Torvalds 已提交
3087 3088 3089
{
	struct buffer_head *ret = kmem_cache_alloc(bh_cachep, gfp_flags);
	if (ret) {
3090
		get_cpu_var(bh_accounting).nr++;
L
Linus Torvalds 已提交
3091
		recalc_bh_state();
3092
		put_cpu_var(bh_accounting);
L
Linus Torvalds 已提交
3093 3094 3095 3096 3097 3098 3099 3100 3101
	}
	return ret;
}
EXPORT_SYMBOL(alloc_buffer_head);

void free_buffer_head(struct buffer_head *bh)
{
	BUG_ON(!list_empty(&bh->b_assoc_buffers));
	kmem_cache_free(bh_cachep, bh);
3102
	get_cpu_var(bh_accounting).nr--;
L
Linus Torvalds 已提交
3103
	recalc_bh_state();
3104
	put_cpu_var(bh_accounting);
L
Linus Torvalds 已提交
3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146
}
EXPORT_SYMBOL(free_buffer_head);

static void
init_buffer_head(void *data, kmem_cache_t *cachep, unsigned long flags)
{
	if ((flags & (SLAB_CTOR_VERIFY|SLAB_CTOR_CONSTRUCTOR)) ==
			    SLAB_CTOR_CONSTRUCTOR) {
		struct buffer_head * bh = (struct buffer_head *)data;

		memset(bh, 0, sizeof(*bh));
		INIT_LIST_HEAD(&bh->b_assoc_buffers);
	}
}

#ifdef CONFIG_HOTPLUG_CPU
static void buffer_exit_cpu(int cpu)
{
	int i;
	struct bh_lru *b = &per_cpu(bh_lrus, cpu);

	for (i = 0; i < BH_LRU_SIZE; i++) {
		brelse(b->bhs[i]);
		b->bhs[i] = NULL;
	}
}

static int buffer_cpu_notify(struct notifier_block *self,
			      unsigned long action, void *hcpu)
{
	if (action == CPU_DEAD)
		buffer_exit_cpu((unsigned long)hcpu);
	return NOTIFY_OK;
}
#endif /* CONFIG_HOTPLUG_CPU */

void __init buffer_init(void)
{
	int nrpages;

	bh_cachep = kmem_cache_create("buffer_head",
			sizeof(struct buffer_head), 0,
3147
			SLAB_RECLAIM_ACCOUNT|SLAB_PANIC, init_buffer_head, NULL);
L
Linus Torvalds 已提交
3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174

	/*
	 * Limit the bh occupancy to 10% of ZONE_NORMAL
	 */
	nrpages = (nr_free_buffer_pages() * 10) / 100;
	max_buffer_heads = nrpages * (PAGE_SIZE / sizeof(struct buffer_head));
	hotcpu_notifier(buffer_cpu_notify, 0);
}

EXPORT_SYMBOL(__bforget);
EXPORT_SYMBOL(__brelse);
EXPORT_SYMBOL(__wait_on_buffer);
EXPORT_SYMBOL(block_commit_write);
EXPORT_SYMBOL(block_prepare_write);
EXPORT_SYMBOL(block_read_full_page);
EXPORT_SYMBOL(block_sync_page);
EXPORT_SYMBOL(block_truncate_page);
EXPORT_SYMBOL(block_write_full_page);
EXPORT_SYMBOL(cont_prepare_write);
EXPORT_SYMBOL(end_buffer_async_write);
EXPORT_SYMBOL(end_buffer_read_sync);
EXPORT_SYMBOL(end_buffer_write_sync);
EXPORT_SYMBOL(file_fsync);
EXPORT_SYMBOL(fsync_bdev);
EXPORT_SYMBOL(generic_block_bmap);
EXPORT_SYMBOL(generic_commit_write);
EXPORT_SYMBOL(generic_cont_expand);
3175
EXPORT_SYMBOL(generic_cont_expand_simple);
L
Linus Torvalds 已提交
3176 3177 3178 3179 3180 3181 3182
EXPORT_SYMBOL(init_buffer);
EXPORT_SYMBOL(invalidate_bdev);
EXPORT_SYMBOL(ll_rw_block);
EXPORT_SYMBOL(mark_buffer_dirty);
EXPORT_SYMBOL(submit_bh);
EXPORT_SYMBOL(sync_dirty_buffer);
EXPORT_SYMBOL(unlock_buffer);