mpage.c 20 KB
Newer Older
Linus Torvalds's avatar
Linus Torvalds committed
1 2 3 4 5 6 7 8
/*
 * fs/mpage.c
 *
 * Copyright (C) 2002, Linus Torvalds.
 *
 * Contains functions related to preparing and submitting BIOs which contain
 * multiple pagecache pages.
 *
9
 * 15May2002	Andrew Morton
Linus Torvalds's avatar
Linus Torvalds committed
10 11 12 13 14 15
 *		Initial version
 * 27Jun2002	axboe@suse.de
 *		use bio_add_page() to build bio's just the right size
 */

#include <linux/kernel.h>
16
#include <linux/export.h>
Linus Torvalds's avatar
Linus Torvalds committed
17 18
#include <linux/mm.h>
#include <linux/kdev_t.h>
19
#include <linux/gfp.h>
Linus Torvalds's avatar
Linus Torvalds committed
20 21 22 23 24 25 26 27 28 29
#include <linux/bio.h>
#include <linux/fs.h>
#include <linux/buffer_head.h>
#include <linux/blkdev.h>
#include <linux/highmem.h>
#include <linux/prefetch.h>
#include <linux/mpage.h>
#include <linux/writeback.h>
#include <linux/backing-dev.h>
#include <linux/pagevec.h>
30
#include <linux/cleancache.h>
Linus Torvalds's avatar
Linus Torvalds committed
31 32 33 34 35 36 37 38 39 40 41 42 43

/*
 * I/O completion handler for multipage BIOs.
 *
 * The mpage code never puts partial pages into a BIO (except for end-of-file).
 * If a page does not map to a contiguous run of blocks then it simply falls
 * back to block_read_full_page().
 *
 * Why is this?  If a page's completion depends on a number of different BIOs
 * which can complete in any order (or at the same time) then determining the
 * status of that page is hard.  See end_buffer_async_read() for the details.
 * There is no point in duplicating all that complexity.
 */
Hai Shan's avatar
Hai Shan committed
44
static void mpage_end_io(struct bio *bio, int err)
Linus Torvalds's avatar
Linus Torvalds committed
45 46 47 48 49 50 51 52 53
{
	const int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags);
	struct bio_vec *bvec = bio->bi_io_vec + bio->bi_vcnt - 1;

	do {
		struct page *page = bvec->bv_page;

		if (--bvec >= bio->bi_io_vec)
			prefetchw(&bvec->bv_page->flags);
Hai Shan's avatar
Hai Shan committed
54 55 56 57 58 59 60 61 62 63 64 65 66 67 68
		if (bio_data_dir(bio) == READ) {
			if (uptodate) {
				SetPageUptodate(page);
			} else {
				ClearPageUptodate(page);
				SetPageError(page);
			}
			unlock_page(page);
		} else { /* bio_data_dir(bio) == WRITE */
			if (!uptodate) {
				SetPageError(page);
				if (page->mapping)
					set_bit(AS_EIO, &page->mapping->flags);
			}
			end_page_writeback(page);
69
		}
Linus Torvalds's avatar
Linus Torvalds committed
70 71 72 73
	} while (bvec >= bio->bi_io_vec);
	bio_put(bio);
}

74
static struct bio *mpage_bio_submit(int rw, struct bio *bio)
Linus Torvalds's avatar
Linus Torvalds committed
75
{
Hai Shan's avatar
Hai Shan committed
76
	bio->bi_end_io = mpage_end_io;
Linus Torvalds's avatar
Linus Torvalds committed
77 78 79 80 81 82 83
	submit_bio(rw, bio);
	return NULL;
}

static struct bio *
mpage_alloc(struct block_device *bdev,
		sector_t first_sector, int nr_vecs,
84
		gfp_t gfp_flags)
Linus Torvalds's avatar
Linus Torvalds committed
85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144
{
	struct bio *bio;

	bio = bio_alloc(gfp_flags, nr_vecs);

	if (bio == NULL && (current->flags & PF_MEMALLOC)) {
		while (!bio && (nr_vecs /= 2))
			bio = bio_alloc(gfp_flags, nr_vecs);
	}

	if (bio) {
		bio->bi_bdev = bdev;
		bio->bi_sector = first_sector;
	}
	return bio;
}

/*
 * support function for mpage_readpages.  The fs supplied get_block might
 * return an up to date buffer.  This is used to map that buffer into
 * the page, which allows readpage to avoid triggering a duplicate call
 * to get_block.
 *
 * The idea is to avoid adding buffers to pages that don't already have
 * them.  So when the buffer is up to date and the page size == block size,
 * this marks the page up to date instead of adding new buffers.
 */
static void 
map_buffer_to_page(struct page *page, struct buffer_head *bh, int page_block) 
{
	struct inode *inode = page->mapping->host;
	struct buffer_head *page_bh, *head;
	int block = 0;

	if (!page_has_buffers(page)) {
		/*
		 * don't make any buffers if there is only one buffer on
		 * the page and the page just needs to be set up to date
		 */
		if (inode->i_blkbits == PAGE_CACHE_SHIFT && 
		    buffer_uptodate(bh)) {
			SetPageUptodate(page);    
			return;
		}
		create_empty_buffers(page, 1 << inode->i_blkbits, 0);
	}
	head = page_buffers(page);
	page_bh = head;
	do {
		if (block == page_block) {
			page_bh->b_state = bh->b_state;
			page_bh->b_bdev = bh->b_bdev;
			page_bh->b_blocknr = bh->b_blocknr;
			break;
		}
		page_bh = page_bh->b_this_page;
		block++;
	} while (page_bh != head);
}

145 146 147 148 149 150 151 152 153
/*
 * This is the worker routine which does all the work of mapping the disk
 * blocks and constructs largest possible bios, submits them for IO if the
 * blocks are not contiguous on the disk.
 *
 * We pass a buffer_head back and forth and use its buffer_mapped() flag to
 * represent the validity of its disk mapping and to decide when to do the next
 * get_block() call.
 */
Linus Torvalds's avatar
Linus Torvalds committed
154 155
static struct bio *
do_mpage_readpage(struct bio *bio, struct page *page, unsigned nr_pages,
156 157
		sector_t *last_block_in_bio, struct buffer_head *map_bh,
		unsigned long *first_logical_block, get_block_t get_block)
Linus Torvalds's avatar
Linus Torvalds committed
158 159 160 161 162 163 164
{
	struct inode *inode = page->mapping->host;
	const unsigned blkbits = inode->i_blkbits;
	const unsigned blocks_per_page = PAGE_CACHE_SIZE >> blkbits;
	const unsigned blocksize = 1 << blkbits;
	sector_t block_in_file;
	sector_t last_block;
165
	sector_t last_block_in_file;
Linus Torvalds's avatar
Linus Torvalds committed
166 167 168 169 170 171
	sector_t blocks[MAX_BUF_PER_PAGE];
	unsigned page_block;
	unsigned first_hole = blocks_per_page;
	struct block_device *bdev = NULL;
	int length;
	int fully_mapped = 1;
172 173
	unsigned nblocks;
	unsigned relative_block;
Linus Torvalds's avatar
Linus Torvalds committed
174 175 176 177

	if (page_has_buffers(page))
		goto confused;

178
	block_in_file = (sector_t)page->index << (PAGE_CACHE_SHIFT - blkbits);
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
	last_block = block_in_file + nr_pages * blocks_per_page;
	last_block_in_file = (i_size_read(inode) + blocksize - 1) >> blkbits;
	if (last_block > last_block_in_file)
		last_block = last_block_in_file;
	page_block = 0;

	/*
	 * Map blocks using the result from the previous get_blocks call first.
	 */
	nblocks = map_bh->b_size >> blkbits;
	if (buffer_mapped(map_bh) && block_in_file > *first_logical_block &&
			block_in_file < (*first_logical_block + nblocks)) {
		unsigned map_offset = block_in_file - *first_logical_block;
		unsigned last = nblocks - map_offset;

		for (relative_block = 0; ; relative_block++) {
			if (relative_block == last) {
				clear_buffer_mapped(map_bh);
				break;
			}
			if (page_block == blocks_per_page)
				break;
			blocks[page_block] = map_bh->b_blocknr + map_offset +
						relative_block;
			page_block++;
			block_in_file++;
		}
		bdev = map_bh->b_bdev;
	}

	/*
	 * Then do more get_blocks calls until we are done with this page.
	 */
	map_bh->b_page = page;
	while (page_block < blocks_per_page) {
		map_bh->b_state = 0;
		map_bh->b_size = 0;
Linus Torvalds's avatar
Linus Torvalds committed
216 217

		if (block_in_file < last_block) {
218 219
			map_bh->b_size = (last_block-block_in_file) << blkbits;
			if (get_block(inode, block_in_file, map_bh, 0))
Linus Torvalds's avatar
Linus Torvalds committed
220
				goto confused;
221
			*first_logical_block = block_in_file;
Linus Torvalds's avatar
Linus Torvalds committed
222 223
		}

224
		if (!buffer_mapped(map_bh)) {
Linus Torvalds's avatar
Linus Torvalds committed
225 226 227
			fully_mapped = 0;
			if (first_hole == blocks_per_page)
				first_hole = page_block;
228 229
			page_block++;
			block_in_file++;
Linus Torvalds's avatar
Linus Torvalds committed
230 231 232 233 234 235 236 237 238
			continue;
		}

		/* some filesystems will copy data into the page during
		 * the get_block call, in which case we don't want to
		 * read it again.  map_buffer_to_page copies the data
		 * we just collected from get_block into the page's buffers
		 * so readpage doesn't have to repeat the get_block call
		 */
239 240
		if (buffer_uptodate(map_bh)) {
			map_buffer_to_page(page, map_bh, page_block);
Linus Torvalds's avatar
Linus Torvalds committed
241 242 243 244 245 246 247
			goto confused;
		}
	
		if (first_hole != blocks_per_page)
			goto confused;		/* hole -> non-hole */

		/* Contiguous blocks? */
248
		if (page_block && blocks[page_block-1] != map_bh->b_blocknr-1)
Linus Torvalds's avatar
Linus Torvalds committed
249
			goto confused;
250 251 252 253 254 255 256 257 258 259 260 261
		nblocks = map_bh->b_size >> blkbits;
		for (relative_block = 0; ; relative_block++) {
			if (relative_block == nblocks) {
				clear_buffer_mapped(map_bh);
				break;
			} else if (page_block == blocks_per_page)
				break;
			blocks[page_block] = map_bh->b_blocknr+relative_block;
			page_block++;
			block_in_file++;
		}
		bdev = map_bh->b_bdev;
Linus Torvalds's avatar
Linus Torvalds committed
262 263 264
	}

	if (first_hole != blocks_per_page) {
265
		zero_user_segment(page, first_hole << blkbits, PAGE_CACHE_SIZE);
Linus Torvalds's avatar
Linus Torvalds committed
266 267 268 269 270 271 272 273 274
		if (first_hole == 0) {
			SetPageUptodate(page);
			unlock_page(page);
			goto out;
		}
	} else if (fully_mapped) {
		SetPageMappedToDisk(page);
	}

275 276 277 278 279 280
	if (fully_mapped && blocks_per_page == 1 && !PageUptodate(page) &&
	    cleancache_get_page(page) == 0) {
		SetPageUptodate(page);
		goto confused;
	}

Linus Torvalds's avatar
Linus Torvalds committed
281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301
	/*
	 * This page will go to BIO.  Do we need to send this BIO off first?
	 */
	if (bio && (*last_block_in_bio != blocks[0] - 1))
		bio = mpage_bio_submit(READ, bio);

alloc_new:
	if (bio == NULL) {
		bio = mpage_alloc(bdev, blocks[0] << (blkbits - 9),
			  	min_t(int, nr_pages, bio_get_nr_vecs(bdev)),
				GFP_KERNEL);
		if (bio == NULL)
			goto confused;
	}

	length = first_hole << blkbits;
	if (bio_add_page(bio, page, length, 0) < length) {
		bio = mpage_bio_submit(READ, bio);
		goto alloc_new;
	}

302 303 304 305
	relative_block = block_in_file - *first_logical_block;
	nblocks = map_bh->b_size >> blkbits;
	if ((buffer_boundary(map_bh) && relative_block == nblocks) ||
	    (first_hole != blocks_per_page))
Linus Torvalds's avatar
Linus Torvalds committed
306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321
		bio = mpage_bio_submit(READ, bio);
	else
		*last_block_in_bio = blocks[blocks_per_page - 1];
out:
	return bio;

confused:
	if (bio)
		bio = mpage_bio_submit(READ, bio);
	if (!PageUptodate(page))
	        block_read_full_page(page, get_block);
	else
		unlock_page(page);
	goto out;
}

322
/**
323
 * mpage_readpages - populate an address space with some pages & start reads against them
324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353
 * @mapping: the address_space
 * @pages: The address of a list_head which contains the target pages.  These
 *   pages have their ->index populated and are otherwise uninitialised.
 *   The page at @pages->prev has the lowest file offset, and reads should be
 *   issued in @pages->prev to @pages->next order.
 * @nr_pages: The number of pages at *@pages
 * @get_block: The filesystem's block mapper function.
 *
 * This function walks the pages and the blocks within each page, building and
 * emitting large BIOs.
 *
 * If anything unusual happens, such as:
 *
 * - encountering a page which has buffers
 * - encountering a page which has a non-hole after a hole
 * - encountering a page with non-contiguous blocks
 *
 * then this code just gives up and calls the buffer_head-based read function.
 * It does handle a page which has holes at the end - that is a common case:
 * the end-of-file on blocksize < PAGE_CACHE_SIZE setups.
 *
 * BH_Boundary explanation:
 *
 * There is a problem.  The mpage read code assembles several pages, gets all
 * their disk mappings, and then submits them all.  That's fine, but obtaining
 * the disk mappings may require I/O.  Reads of indirect blocks, for example.
 *
 * So an mpage read of the first 16 blocks of an ext2 file will cause I/O to be
 * submitted in the following order:
 * 	12 0 1 2 3 4 5 6 7 8 9 10 11 13 14 15 16
354
 *
355 356 357 358 359 360 361 362 363 364
 * because the indirect block has to be read to get the mappings of blocks
 * 13,14,15,16.  Obviously, this impacts performance.
 *
 * So what we do it to allow the filesystem's get_block() function to set
 * BH_Boundary when it maps block 11.  BH_Boundary says: mapping of the block
 * after this one will require I/O against a block which is probably close to
 * this one.  So you should push what I/O you have currently accumulated.
 *
 * This all causes the disk requests to be issued in the correct order.
 */
Linus Torvalds's avatar
Linus Torvalds committed
365 366 367 368 369 370 371
int
mpage_readpages(struct address_space *mapping, struct list_head *pages,
				unsigned nr_pages, get_block_t get_block)
{
	struct bio *bio = NULL;
	unsigned page_idx;
	sector_t last_block_in_bio = 0;
372 373
	struct buffer_head map_bh;
	unsigned long first_logical_block = 0;
Linus Torvalds's avatar
Linus Torvalds committed
374

375 376
	map_bh.b_state = 0;
	map_bh.b_size = 0;
Linus Torvalds's avatar
Linus Torvalds committed
377 378 379 380 381
	for (page_idx = 0; page_idx < nr_pages; page_idx++) {
		struct page *page = list_entry(pages->prev, struct page, lru);

		prefetchw(&page->flags);
		list_del(&page->lru);
Nick Piggin's avatar
Nick Piggin committed
382
		if (!add_to_page_cache_lru(page, mapping,
Linus Torvalds's avatar
Linus Torvalds committed
383 384 385
					page->index, GFP_KERNEL)) {
			bio = do_mpage_readpage(bio, page,
					nr_pages - page_idx,
386 387 388
					&last_block_in_bio, &map_bh,
					&first_logical_block,
					get_block);
Linus Torvalds's avatar
Linus Torvalds committed
389
		}
Nick Piggin's avatar
Nick Piggin committed
390
		page_cache_release(page);
Linus Torvalds's avatar
Linus Torvalds committed
391 392 393 394 395 396 397 398 399 400 401 402 403 404 405
	}
	BUG_ON(!list_empty(pages));
	if (bio)
		mpage_bio_submit(READ, bio);
	return 0;
}
EXPORT_SYMBOL(mpage_readpages);

/*
 * This isn't called much at all
 */
int mpage_readpage(struct page *page, get_block_t get_block)
{
	struct bio *bio = NULL;
	sector_t last_block_in_bio = 0;
406 407
	struct buffer_head map_bh;
	unsigned long first_logical_block = 0;
Linus Torvalds's avatar
Linus Torvalds committed
408

409 410
	map_bh.b_state = 0;
	map_bh.b_size = 0;
411 412
	bio = do_mpage_readpage(bio, page, 1, &last_block_in_bio,
			&map_bh, &first_logical_block, get_block);
Linus Torvalds's avatar
Linus Torvalds committed
413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434
	if (bio)
		mpage_bio_submit(READ, bio);
	return 0;
}
EXPORT_SYMBOL(mpage_readpage);

/*
 * Writing is not so simple.
 *
 * If the page has buffers then they will be used for obtaining the disk
 * mapping.  We only support pages which are fully mapped-and-dirty, with a
 * special case for pages which are unmapped at the end: end-of-file.
 *
 * If the page has no buffers (preferred) then the page is mapped here.
 *
 * If all blocks are found to be contiguous then the page can go into the
 * BIO.  Otherwise fall back to the mapping's writepage().
 * 
 * FIXME: This code wants an estimate of how many pages are still to be
 * written, so it can intelligently allocate a suitably-sized BIO.  For now,
 * just allocate full-size (16-page) BIOs.
 */
435

436 437 438 439 440 441 442 443
struct mpage_data {
	struct bio *bio;
	sector_t last_block_in_bio;
	get_block_t *get_block;
	unsigned use_writepage;
};

static int __mpage_writepage(struct page *page, struct writeback_control *wbc,
444
		      void *data)
Linus Torvalds's avatar
Linus Torvalds committed
445
{
446 447
	struct mpage_data *mpd = data;
	struct bio *bio = mpd->bio;
Linus Torvalds's avatar
Linus Torvalds committed
448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464
	struct address_space *mapping = page->mapping;
	struct inode *inode = page->mapping->host;
	const unsigned blkbits = inode->i_blkbits;
	unsigned long end_index;
	const unsigned blocks_per_page = PAGE_CACHE_SIZE >> blkbits;
	sector_t last_block;
	sector_t block_in_file;
	sector_t blocks[MAX_BUF_PER_PAGE];
	unsigned page_block;
	unsigned first_unmapped = blocks_per_page;
	struct block_device *bdev = NULL;
	int boundary = 0;
	sector_t boundary_block = 0;
	struct block_device *boundary_bdev = NULL;
	int length;
	struct buffer_head map_bh;
	loff_t i_size = i_size_read(inode);
465
	int ret = 0;
Linus Torvalds's avatar
Linus Torvalds committed
466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520

	if (page_has_buffers(page)) {
		struct buffer_head *head = page_buffers(page);
		struct buffer_head *bh = head;

		/* If they're all mapped and dirty, do it */
		page_block = 0;
		do {
			BUG_ON(buffer_locked(bh));
			if (!buffer_mapped(bh)) {
				/*
				 * unmapped dirty buffers are created by
				 * __set_page_dirty_buffers -> mmapped data
				 */
				if (buffer_dirty(bh))
					goto confused;
				if (first_unmapped == blocks_per_page)
					first_unmapped = page_block;
				continue;
			}

			if (first_unmapped != blocks_per_page)
				goto confused;	/* hole -> non-hole */

			if (!buffer_dirty(bh) || !buffer_uptodate(bh))
				goto confused;
			if (page_block) {
				if (bh->b_blocknr != blocks[page_block-1] + 1)
					goto confused;
			}
			blocks[page_block++] = bh->b_blocknr;
			boundary = buffer_boundary(bh);
			if (boundary) {
				boundary_block = bh->b_blocknr;
				boundary_bdev = bh->b_bdev;
			}
			bdev = bh->b_bdev;
		} while ((bh = bh->b_this_page) != head);

		if (first_unmapped)
			goto page_is_mapped;

		/*
		 * Page has buffers, but they are all unmapped. The page was
		 * created by pagein or read over a hole which was handled by
		 * block_read_full_page().  If this address_space is also
		 * using mpage_readpages then this can rarely happen.
		 */
		goto confused;
	}

	/*
	 * The page has no buffers: map it to disk
	 */
	BUG_ON(!PageUptodate(page));
521
	block_in_file = (sector_t)page->index << (PAGE_CACHE_SHIFT - blkbits);
Linus Torvalds's avatar
Linus Torvalds committed
522 523 524 525 526
	last_block = (i_size - 1) >> blkbits;
	map_bh.b_page = page;
	for (page_block = 0; page_block < blocks_per_page; ) {

		map_bh.b_state = 0;
527
		map_bh.b_size = 1 << blkbits;
528
		if (mpd->get_block(inode, block_in_file, &map_bh, 1))
Linus Torvalds's avatar
Linus Torvalds committed
529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556
			goto confused;
		if (buffer_new(&map_bh))
			unmap_underlying_metadata(map_bh.b_bdev,
						map_bh.b_blocknr);
		if (buffer_boundary(&map_bh)) {
			boundary_block = map_bh.b_blocknr;
			boundary_bdev = map_bh.b_bdev;
		}
		if (page_block) {
			if (map_bh.b_blocknr != blocks[page_block-1] + 1)
				goto confused;
		}
		blocks[page_block++] = map_bh.b_blocknr;
		boundary = buffer_boundary(&map_bh);
		bdev = map_bh.b_bdev;
		if (block_in_file == last_block)
			break;
		block_in_file++;
	}
	BUG_ON(page_block == 0);

	first_unmapped = page_block;

page_is_mapped:
	end_index = i_size >> PAGE_CACHE_SHIFT;
	if (page->index >= end_index) {
		/*
		 * The page straddles i_size.  It must be zeroed out on each
557
		 * and every writepage invocation because it may be mmapped.
Linus Torvalds's avatar
Linus Torvalds committed
558 559 560 561 562 563 564 565 566
		 * "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."
		 */
		unsigned offset = i_size & (PAGE_CACHE_SIZE - 1);

		if (page->index > end_index || !offset)
			goto confused;
567
		zero_user_segment(page, offset, PAGE_CACHE_SIZE);
Linus Torvalds's avatar
Linus Torvalds committed
568 569 570 571 572
	}

	/*
	 * This page will go to BIO.  Do we need to send this BIO off first?
	 */
573
	if (bio && mpd->last_block_in_bio != blocks[0] - 1)
Linus Torvalds's avatar
Linus Torvalds committed
574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629
		bio = mpage_bio_submit(WRITE, bio);

alloc_new:
	if (bio == NULL) {
		bio = mpage_alloc(bdev, blocks[0] << (blkbits - 9),
				bio_get_nr_vecs(bdev), GFP_NOFS|__GFP_HIGH);
		if (bio == NULL)
			goto confused;
	}

	/*
	 * Must try to add the page before marking the buffer clean or
	 * the confused fail path above (OOM) will be very confused when
	 * it finds all bh marked clean (i.e. it will not write anything)
	 */
	length = first_unmapped << blkbits;
	if (bio_add_page(bio, page, length, 0) < length) {
		bio = mpage_bio_submit(WRITE, bio);
		goto alloc_new;
	}

	/*
	 * OK, we have our BIO, so we can now mark the buffers clean.  Make
	 * sure to only clean buffers which we know we'll be writing.
	 */
	if (page_has_buffers(page)) {
		struct buffer_head *head = page_buffers(page);
		struct buffer_head *bh = head;
		unsigned buffer_counter = 0;

		do {
			if (buffer_counter++ == first_unmapped)
				break;
			clear_buffer_dirty(bh);
			bh = bh->b_this_page;
		} while (bh != head);

		/*
		 * we cannot drop the bh if the page is not uptodate
		 * or a concurrent readpage would fail to serialize with the bh
		 * and it would read from disk before we reach the platter.
		 */
		if (buffer_heads_over_limit && PageUptodate(page))
			try_to_free_buffers(page);
	}

	BUG_ON(PageWriteback(page));
	set_page_writeback(page);
	unlock_page(page);
	if (boundary || (first_unmapped != blocks_per_page)) {
		bio = mpage_bio_submit(WRITE, bio);
		if (boundary_block) {
			write_boundary_block(boundary_bdev,
					boundary_block, 1 << blkbits);
		}
	} else {
630
		mpd->last_block_in_bio = blocks[blocks_per_page - 1];
Linus Torvalds's avatar
Linus Torvalds committed
631 632 633 634 635 636 637
	}
	goto out;

confused:
	if (bio)
		bio = mpage_bio_submit(WRITE, bio);

638 639
	if (mpd->use_writepage) {
		ret = mapping->a_ops->writepage(page, wbc);
Linus Torvalds's avatar
Linus Torvalds committed
640
	} else {
641
		ret = -EAGAIN;
Linus Torvalds's avatar
Linus Torvalds committed
642 643 644 645 646
		goto out;
	}
	/*
	 * The caller has a ref on the inode, so *mapping is stable
	 */
647
	mapping_set_error(mapping, ret);
Linus Torvalds's avatar
Linus Torvalds committed
648
out:
649 650
	mpd->bio = bio;
	return ret;
Linus Torvalds's avatar
Linus Torvalds committed
651 652 653
}

/**
654
 * mpage_writepages - walk the list of dirty pages of the given address space & writepage() all of them
Linus Torvalds's avatar
Linus Torvalds committed
655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675
 * @mapping: address space structure to write
 * @wbc: subtract the number of written pages from *@wbc->nr_to_write
 * @get_block: the filesystem's block mapper function.
 *             If this is NULL then use a_ops->writepage.  Otherwise, go
 *             direct-to-BIO.
 *
 * This is a library function, which implements the writepages()
 * address_space_operation.
 *
 * If a page is already under I/O, generic_writepages() skips it, even
 * if it's dirty.  This is desirable behaviour for memory-cleaning writeback,
 * but it is INCORRECT for data-integrity system calls such as fsync().  fsync()
 * and msync() need to guarantee that all the data which was dirty at the time
 * the call was made get new I/O started against them.  If wbc->sync_mode is
 * WB_SYNC_ALL then we were called for data integrity and we must wait for
 * existing IO to complete.
 */
int
mpage_writepages(struct address_space *mapping,
		struct writeback_control *wbc, get_block_t get_block)
{
676
	struct blk_plug plug;
677 678
	int ret;

679 680
	blk_start_plug(&plug);

681 682 683 684 685 686 687 688 689 690 691 692 693
	if (!get_block)
		ret = generic_writepages(mapping, wbc);
	else {
		struct mpage_data mpd = {
			.bio = NULL,
			.last_block_in_bio = 0,
			.get_block = get_block,
			.use_writepage = 1,
		};

		ret = write_cache_pages(mapping, wbc, __mpage_writepage, &mpd);
		if (mpd.bio)
			mpage_bio_submit(WRITE, mpd.bio);
Linus Torvalds's avatar
Linus Torvalds committed
694
	}
695
	blk_finish_plug(&plug);
Linus Torvalds's avatar
Linus Torvalds committed
696 697 698 699 700 701 702
	return ret;
}
EXPORT_SYMBOL(mpage_writepages);

int mpage_writepage(struct page *page, get_block_t get_block,
	struct writeback_control *wbc)
{
703 704 705 706 707 708 709 710 711
	struct mpage_data mpd = {
		.bio = NULL,
		.last_block_in_bio = 0,
		.get_block = get_block,
		.use_writepage = 0,
	};
	int ret = __mpage_writepage(page, wbc, &mpd);
	if (mpd.bio)
		mpage_bio_submit(WRITE, mpd.bio);
Linus Torvalds's avatar
Linus Torvalds committed
712 713 714
	return ret;
}
EXPORT_SYMBOL(mpage_writepage);