page.c 14.6 KB
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587
/*
 * page.c - buffer/page management specific to NILFS
 *
 * Copyright (C) 2005-2008 Nippon Telegraph and Telephone Corporation.
 *
 * This program is free software; you can redistribute it and/or modify
 * it under the terms of the GNU General Public License as published by
 * the Free Software Foundation; either version 2 of the License, or
 * (at your option) any later version.
 *
 * This program is distributed in the hope that it will be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 * GNU General Public License for more details.
 *
 * You should have received a copy of the GNU General Public License
 * along with this program; if not, write to the Free Software
 * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
 *
 * Written by Ryusuke Konishi <ryusuke@osrg.net>,
 *            Seiji Kihara <kihara@osrg.net>.
 */

#include <linux/pagemap.h>
#include <linux/writeback.h>
#include <linux/swap.h>
#include <linux/bitops.h>
#include <linux/page-flags.h>
#include <linux/list.h>
#include <linux/highmem.h>
#include <linux/pagevec.h>
#include <linux/gfp.h>
#include "nilfs.h"
#include "page.h"
#include "mdt.h"


#define NILFS_BUFFER_INHERENT_BITS  \
	((1UL << BH_Uptodate) | (1UL << BH_Mapped) | (1UL << BH_NILFS_Node) | \
	 (1UL << BH_NILFS_Volatile) | (1UL << BH_NILFS_Checked))

static struct buffer_head *
__nilfs_get_page_block(struct page *page, unsigned long block, pgoff_t index,
		       int blkbits, unsigned long b_state)

{
	unsigned long first_block;
	struct buffer_head *bh;

	if (!page_has_buffers(page))
		create_empty_buffers(page, 1 << blkbits, b_state);

	first_block = (unsigned long)index << (PAGE_CACHE_SHIFT - blkbits);
	bh = nilfs_page_get_nth_block(page, block - first_block);

	touch_buffer(bh);
	wait_on_buffer(bh);
	return bh;
}

struct buffer_head *nilfs_grab_buffer(struct inode *inode,
				      struct address_space *mapping,
				      unsigned long blkoff,
				      unsigned long b_state)
{
	int blkbits = inode->i_blkbits;
	pgoff_t index = blkoff >> (PAGE_CACHE_SHIFT - blkbits);
	struct page *page;
	struct buffer_head *bh;

	page = grab_cache_page(mapping, index);
	if (unlikely(!page))
		return NULL;

	bh = __nilfs_get_page_block(page, blkoff, index, blkbits, b_state);
	if (unlikely(!bh)) {
		unlock_page(page);
		page_cache_release(page);
		return NULL;
	}
	return bh;
}

/**
 * nilfs_forget_buffer - discard dirty state
 * @inode: owner inode of the buffer
 * @bh: buffer head of the buffer to be discarded
 */
void nilfs_forget_buffer(struct buffer_head *bh)
{
	struct page *page = bh->b_page;

	lock_buffer(bh);
	clear_buffer_nilfs_volatile(bh);
	clear_buffer_nilfs_checked(bh);
	clear_buffer_nilfs_redirected(bh);
	clear_buffer_async_write(bh);
	clear_buffer_dirty(bh);
	if (nilfs_page_buffers_clean(page))
		__nilfs_clear_page_dirty(page);

	clear_buffer_uptodate(bh);
	clear_buffer_mapped(bh);
	bh->b_blocknr = -1;
	ClearPageUptodate(page);
	ClearPageMappedToDisk(page);
	unlock_buffer(bh);
	brelse(bh);
}

/**
 * nilfs_copy_buffer -- copy buffer data and flags
 * @dbh: destination buffer
 * @sbh: source buffer
 */
void nilfs_copy_buffer(struct buffer_head *dbh, struct buffer_head *sbh)
{
	void *kaddr0, *kaddr1;
	unsigned long bits;
	struct page *spage = sbh->b_page, *dpage = dbh->b_page;
	struct buffer_head *bh;

	kaddr0 = kmap_atomic(spage);
	kaddr1 = kmap_atomic(dpage);
	memcpy(kaddr1 + bh_offset(dbh), kaddr0 + bh_offset(sbh), sbh->b_size);
	kunmap_atomic(kaddr1);
	kunmap_atomic(kaddr0);

	dbh->b_state = sbh->b_state & NILFS_BUFFER_INHERENT_BITS;
	dbh->b_blocknr = sbh->b_blocknr;
	dbh->b_bdev = sbh->b_bdev;

	bh = dbh;
	bits = sbh->b_state & ((1UL << BH_Uptodate) | (1UL << BH_Mapped));
	while ((bh = bh->b_this_page) != dbh) {
		lock_buffer(bh);
		bits &= bh->b_state;
		unlock_buffer(bh);
	}
	if (bits & (1UL << BH_Uptodate))
		SetPageUptodate(dpage);
	else
		ClearPageUptodate(dpage);
	if (bits & (1UL << BH_Mapped))
		SetPageMappedToDisk(dpage);
	else
		ClearPageMappedToDisk(dpage);
}

/**
 * nilfs_page_buffers_clean - check if a page has dirty buffers or not.
 * @page: page to be checked
 *
 * nilfs_page_buffers_clean() returns zero if the page has dirty buffers.
 * Otherwise, it returns non-zero value.
 */
int nilfs_page_buffers_clean(struct page *page)
{
	struct buffer_head *bh, *head;

	bh = head = page_buffers(page);
	do {
		if (buffer_dirty(bh))
			return 0;
		bh = bh->b_this_page;
	} while (bh != head);
	return 1;
}

void nilfs_page_bug(struct page *page)
{
	struct address_space *m;
	unsigned long ino;

	if (unlikely(!page)) {
		printk(KERN_CRIT "NILFS_PAGE_BUG(NULL)\n");
		return;
	}

	m = page->mapping;
	ino = m ? m->host->i_ino : 0;

	printk(KERN_CRIT "NILFS_PAGE_BUG(%p): cnt=%d index#=%llu flags=0x%lx "
	       "mapping=%p ino=%lu\n",
	       page, atomic_read(&page->_count),
	       (unsigned long long)page->index, page->flags, m, ino);

	if (page_has_buffers(page)) {
		struct buffer_head *bh, *head;
		int i = 0;

		bh = head = page_buffers(page);
		do {
			printk(KERN_CRIT
			       " BH[%d] %p: cnt=%d block#=%llu state=0x%lx\n",
			       i++, bh, atomic_read(&bh->b_count),
			       (unsigned long long)bh->b_blocknr, bh->b_state);
			bh = bh->b_this_page;
		} while (bh != head);
	}
}

/**
 * nilfs_copy_page -- copy the page with buffers
 * @dst: destination page
 * @src: source page
 * @copy_dirty: flag whether to copy dirty states on the page's buffer heads.
 *
 * This function is for both data pages and btnode pages.  The dirty flag
 * should be treated by caller.  The page must not be under i/o.
 * Both src and dst page must be locked
 */
static void nilfs_copy_page(struct page *dst, struct page *src, int copy_dirty)
{
	struct buffer_head *dbh, *dbufs, *sbh, *sbufs;
	unsigned long mask = NILFS_BUFFER_INHERENT_BITS;

	BUG_ON(PageWriteback(dst));

	sbh = sbufs = page_buffers(src);
	if (!page_has_buffers(dst))
		create_empty_buffers(dst, sbh->b_size, 0);

	if (copy_dirty)
		mask |= (1UL << BH_Dirty);

	dbh = dbufs = page_buffers(dst);
	do {
		lock_buffer(sbh);
		lock_buffer(dbh);
		dbh->b_state = sbh->b_state & mask;
		dbh->b_blocknr = sbh->b_blocknr;
		dbh->b_bdev = sbh->b_bdev;
		sbh = sbh->b_this_page;
		dbh = dbh->b_this_page;
	} while (dbh != dbufs);

	copy_highpage(dst, src);

	if (PageUptodate(src) && !PageUptodate(dst))
		SetPageUptodate(dst);
	else if (!PageUptodate(src) && PageUptodate(dst))
		ClearPageUptodate(dst);
	if (PageMappedToDisk(src) && !PageMappedToDisk(dst))
		SetPageMappedToDisk(dst);
	else if (!PageMappedToDisk(src) && PageMappedToDisk(dst))
		ClearPageMappedToDisk(dst);

	do {
		unlock_buffer(sbh);
		unlock_buffer(dbh);
		sbh = sbh->b_this_page;
		dbh = dbh->b_this_page;
	} while (dbh != dbufs);
}

int nilfs_copy_dirty_pages(struct address_space *dmap,
			   struct address_space *smap)
{
	struct pagevec pvec;
	unsigned int i;
	pgoff_t index = 0;
	int err = 0;

	pagevec_init(&pvec, 0);
repeat:
	if (!pagevec_lookup_tag(&pvec, smap, &index, PAGECACHE_TAG_DIRTY,
				PAGEVEC_SIZE))
		return 0;

	for (i = 0; i < pagevec_count(&pvec); i++) {
		struct page *page = pvec.pages[i], *dpage;

		lock_page(page);
		if (unlikely(!PageDirty(page)))
			NILFS_PAGE_BUG(page, "inconsistent dirty state");

		dpage = grab_cache_page(dmap, page->index);
		if (unlikely(!dpage)) {
			/* No empty page is added to the page cache */
			err = -ENOMEM;
			unlock_page(page);
			break;
		}
		if (unlikely(!page_has_buffers(page)))
			NILFS_PAGE_BUG(page,
				       "found empty page in dat page cache");

		nilfs_copy_page(dpage, page, 1);
		__set_page_dirty_nobuffers(dpage);

		unlock_page(dpage);
		page_cache_release(dpage);
		unlock_page(page);
	}
	pagevec_release(&pvec);
	cond_resched();

	if (likely(!err))
		goto repeat;
	return err;
}

/**
 * nilfs_copy_back_pages -- copy back pages to original cache from shadow cache
 * @dmap: destination page cache
 * @smap: source page cache
 *
 * No pages must no be added to the cache during this process.
 * This must be ensured by the caller.
 */
void nilfs_copy_back_pages(struct address_space *dmap,
			   struct address_space *smap)
{
	struct pagevec pvec;
	unsigned int i, n;
	pgoff_t index = 0;
	int err;

	pagevec_init(&pvec, 0);
repeat:
	n = pagevec_lookup(&pvec, smap, index, PAGEVEC_SIZE);
	if (!n)
		return;
	index = pvec.pages[n - 1]->index + 1;

	for (i = 0; i < pagevec_count(&pvec); i++) {
		struct page *page = pvec.pages[i], *dpage;
		pgoff_t offset = page->index;

		lock_page(page);
		dpage = find_lock_page(dmap, offset);
		if (dpage) {
			/* override existing page on the destination cache */
			WARN_ON(PageDirty(dpage));
			nilfs_copy_page(dpage, page, 0);
			unlock_page(dpage);
			page_cache_release(dpage);
		} else {
			struct page *page2;

			/* move the page to the destination cache */
			spin_lock_irq(&smap->tree_lock);
			page2 = radix_tree_delete(&smap->page_tree, offset);
			WARN_ON(page2 != page);

			smap->nrpages--;
			spin_unlock_irq(&smap->tree_lock);

			spin_lock_irq(&dmap->tree_lock);
			err = radix_tree_insert(&dmap->page_tree, offset, page);
			if (unlikely(err < 0)) {
				WARN_ON(err == -EEXIST);
				page->mapping = NULL;
				page_cache_release(page); /* for cache */
			} else {
				page->mapping = dmap;
				dmap->nrpages++;
				if (PageDirty(page))
					radix_tree_tag_set(&dmap->page_tree,
							   offset,
							   PAGECACHE_TAG_DIRTY);
			}
			spin_unlock_irq(&dmap->tree_lock);
		}
		unlock_page(page);
	}
	pagevec_release(&pvec);
	cond_resched();

	goto repeat;
}

/**
 * nilfs_clear_dirty_pages - discard dirty pages in address space
 * @mapping: address space with dirty pages for discarding
 * @silent: suppress [true] or print [false] warning messages
 */
void nilfs_clear_dirty_pages(struct address_space *mapping, bool silent)
{
	struct pagevec pvec;
	unsigned int i;
	pgoff_t index = 0;

	pagevec_init(&pvec, 0);

	while (pagevec_lookup_tag(&pvec, mapping, &index, PAGECACHE_TAG_DIRTY,
				  PAGEVEC_SIZE)) {
		for (i = 0; i < pagevec_count(&pvec); i++) {
			struct page *page = pvec.pages[i];

			lock_page(page);
			nilfs_clear_dirty_page(page, silent);
			unlock_page(page);
		}
		pagevec_release(&pvec);
		cond_resched();
	}
}

/**
 * nilfs_clear_dirty_page - discard dirty page
 * @page: dirty page that will be discarded
 * @silent: suppress [true] or print [false] warning messages
 */
void nilfs_clear_dirty_page(struct page *page, bool silent)
{
	struct inode *inode = page->mapping->host;
	struct super_block *sb = inode->i_sb;

	BUG_ON(!PageLocked(page));

	if (!silent) {
		nilfs_warning(sb, __func__,
				"discard page: offset %lld, ino %lu",
				page_offset(page), inode->i_ino);
	}

	ClearPageUptodate(page);
	ClearPageMappedToDisk(page);

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

		bh = head = page_buffers(page);
		do {
			lock_buffer(bh);
			if (!silent) {
				nilfs_warning(sb, __func__,
					"discard block %llu, size %zu",
					(u64)bh->b_blocknr, bh->b_size);
			}
			clear_buffer_async_write(bh);
			clear_buffer_dirty(bh);
			clear_buffer_nilfs_volatile(bh);
			clear_buffer_nilfs_checked(bh);
			clear_buffer_nilfs_redirected(bh);
			clear_buffer_uptodate(bh);
			clear_buffer_mapped(bh);
			unlock_buffer(bh);
		} while (bh = bh->b_this_page, bh != head);
	}

	__nilfs_clear_page_dirty(page);
}

unsigned nilfs_page_count_clean_buffers(struct page *page,
					unsigned from, unsigned to)
{
	unsigned block_start, block_end;
	struct buffer_head *bh, *head;
	unsigned nc = 0;

	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 + bh->b_size;
		if (block_end > from && block_start < to && !buffer_dirty(bh))
			nc++;
	}
	return nc;
}

void nilfs_mapping_init(struct address_space *mapping, struct inode *inode,
			struct backing_dev_info *bdi)
{
	mapping->host = inode;
	mapping->flags = 0;
	mapping_set_gfp_mask(mapping, GFP_NOFS);
	mapping->private_data = NULL;
	mapping->backing_dev_info = bdi;
	mapping->a_ops = &empty_aops;
}

/*
 * NILFS2 needs clear_page_dirty() in the following two cases:
 *
 * 1) For B-tree node pages and data pages of the dat/gcdat, NILFS2 clears
 *    page dirty flags when it copies back pages from the shadow cache
 *    (gcdat->{i_mapping,i_btnode_cache}) to its original cache
 *    (dat->{i_mapping,i_btnode_cache}).
 *
 * 2) Some B-tree operations like insertion or deletion may dispose buffers
 *    in dirty state, and this needs to cancel the dirty state of their pages.
 */
int __nilfs_clear_page_dirty(struct page *page)
{
	struct address_space *mapping = page->mapping;

	if (mapping) {
		spin_lock_irq(&mapping->tree_lock);
		if (test_bit(PG_dirty, &page->flags)) {
			radix_tree_tag_clear(&mapping->page_tree,
					     page_index(page),
					     PAGECACHE_TAG_DIRTY);
			spin_unlock_irq(&mapping->tree_lock);
			return clear_page_dirty_for_io(page);
		}
		spin_unlock_irq(&mapping->tree_lock);
		return 0;
	}
	return TestClearPageDirty(page);
}

/**
 * nilfs_find_uncommitted_extent - find extent of uncommitted data
 * @inode: inode
 * @start_blk: start block offset (in)
 * @blkoff: start offset of the found extent (out)
 *
 * This function searches an extent of buffers marked "delayed" which
 * starts from a block offset equal to or larger than @start_blk.  If
 * such an extent was found, this will store the start offset in
 * @blkoff and return its length in blocks.  Otherwise, zero is
 * returned.
 */
unsigned long nilfs_find_uncommitted_extent(struct inode *inode,
					    sector_t start_blk,
					    sector_t *blkoff)
{
	unsigned int i;
	pgoff_t index;
	unsigned int nblocks_in_page;
	unsigned long length = 0;
	sector_t b;
	struct pagevec pvec;
	struct page *page;

	if (inode->i_mapping->nrpages == 0)
		return 0;

	index = start_blk >> (PAGE_CACHE_SHIFT - inode->i_blkbits);
	nblocks_in_page = 1U << (PAGE_CACHE_SHIFT - inode->i_blkbits);

	pagevec_init(&pvec, 0);

repeat:
	pvec.nr = find_get_pages_contig(inode->i_mapping, index, PAGEVEC_SIZE,
					pvec.pages);
	if (pvec.nr == 0)
		return length;

	if (length > 0 && pvec.pages[0]->index > index)
		goto out;

	b = pvec.pages[0]->index << (PAGE_CACHE_SHIFT - inode->i_blkbits);
	i = 0;
	do {
		page = pvec.pages[i];

		lock_page(page);
		if (page_has_buffers(page)) {
			struct buffer_head *bh, *head;

			bh = head = page_buffers(page);
			do {
				if (b < start_blk)
					continue;
				if (buffer_delay(bh)) {
					if (length == 0)
						*blkoff = b;
					length++;
				} else if (length > 0) {
					goto out_locked;
				}
			} while (++b, bh = bh->b_this_page, bh != head);
		} else {
			if (length > 0)
				goto out_locked;

			b += nblocks_in_page;
		}
		unlock_page(page);

	} while (++i < pagevec_count(&pvec));

	index = page->index + 1;
	pagevec_release(&pvec);
	cond_resched();
	goto repeat;

out_locked:
	unlock_page(page);
out:
	pagevec_release(&pvec);
	return length;
}