filemap.c 57.7 KB
Newer Older
Linus Torvalds's avatar
Linus Torvalds committed
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17
/*
 *	linux/mm/filemap.c
 *
 * Copyright (C) 1994-1999  Linus Torvalds
 */

/*
 * This file handles the generic file mmap semantics used by
 * most "normal" filesystems (but you don't /have/ to use this:
 * the NFS filesystem used to do this differently, for example)
 */
#include <linux/config.h>
#include <linux/module.h>
#include <linux/slab.h>
#include <linux/compiler.h>
#include <linux/fs.h>
#include <linux/aio.h>
18
#include <linux/capability.h>
Linus Torvalds's avatar
Linus Torvalds committed
19 20 21 22 23 24 25 26 27 28 29 30 31
#include <linux/kernel_stat.h>
#include <linux/mm.h>
#include <linux/swap.h>
#include <linux/mman.h>
#include <linux/pagemap.h>
#include <linux/file.h>
#include <linux/uio.h>
#include <linux/hash.h>
#include <linux/writeback.h>
#include <linux/pagevec.h>
#include <linux/blkdev.h>
#include <linux/security.h>
#include <linux/syscalls.h>
32
#include "filemap.h"
Linus Torvalds's avatar
Linus Torvalds committed
33 34 35 36 37 38 39 40
/*
 * FIXME: remove all knowledge of the buffer layer from the core VM
 */
#include <linux/buffer_head.h> /* for generic_osync_inode */

#include <asm/uaccess.h>
#include <asm/mman.h>

41 42 43 44
static ssize_t
generic_file_direct_IO(int rw, struct kiocb *iocb, const struct iovec *iov,
	loff_t offset, unsigned long nr_segs);

Linus Torvalds's avatar
Linus Torvalds committed
45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61
/*
 * Shared mappings implemented 30.11.1994. It's not fully working yet,
 * though.
 *
 * Shared mappings now work. 15.8.1995  Bruno.
 *
 * finished 'unifying' the page and buffer cache and SMP-threaded the
 * page-cache, 21.05.1999, Ingo Molnar <mingo@redhat.com>
 *
 * SMP-threaded pagemap-LRU 1999, Andrea Arcangeli <andrea@suse.de>
 */

/*
 * Lock ordering:
 *
 *  ->i_mmap_lock		(vmtruncate)
 *    ->private_lock		(__free_pte->__set_page_dirty_buffers)
62 63
 *      ->swap_lock		(exclusive_swap_page, others)
 *        ->mapping->tree_lock
Linus Torvalds's avatar
Linus Torvalds committed
64
 *
65
 *  ->i_mutex
Linus Torvalds's avatar
Linus Torvalds committed
66 67 68 69
 *    ->i_mmap_lock		(truncate->unmap_mapping_range)
 *
 *  ->mmap_sem
 *    ->i_mmap_lock
70
 *      ->page_table_lock or pte_lock	(various, mainly in memory.c)
Linus Torvalds's avatar
Linus Torvalds committed
71 72 73 74 75 76
 *        ->mapping->tree_lock	(arch-dependent flush_dcache_mmap_lock)
 *
 *  ->mmap_sem
 *    ->lock_page		(access_process_vm)
 *
 *  ->mmap_sem
77
 *    ->i_mutex			(msync)
Linus Torvalds's avatar
Linus Torvalds committed
78
 *
79
 *  ->i_mutex
Linus Torvalds's avatar
Linus Torvalds committed
80 81 82 83 84 85 86 87 88 89
 *    ->i_alloc_sem             (various)
 *
 *  ->inode_lock
 *    ->sb_lock			(fs/fs-writeback.c)
 *    ->mapping->tree_lock	(__sync_single_inode)
 *
 *  ->i_mmap_lock
 *    ->anon_vma.lock		(vma_adjust)
 *
 *  ->anon_vma.lock
90
 *    ->page_table_lock or pte_lock	(anon_vma_prepare and various)
Linus Torvalds's avatar
Linus Torvalds committed
91
 *
92
 *  ->page_table_lock or pte_lock
93
 *    ->swap_lock		(try_to_unmap_one)
Linus Torvalds's avatar
Linus Torvalds committed
94 95 96
 *    ->private_lock		(try_to_unmap_one)
 *    ->tree_lock		(try_to_unmap_one)
 *    ->zone.lru_lock		(follow_page->mark_page_accessed)
97
 *    ->zone.lru_lock		(check_pte_range->isolate_lru_page)
Linus Torvalds's avatar
Linus Torvalds committed
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
 *    ->private_lock		(page_remove_rmap->set_page_dirty)
 *    ->tree_lock		(page_remove_rmap->set_page_dirty)
 *    ->inode_lock		(page_remove_rmap->set_page_dirty)
 *    ->inode_lock		(zap_pte_range->set_page_dirty)
 *    ->private_lock		(zap_pte_range->__set_page_dirty_buffers)
 *
 *  ->task->proc_lock
 *    ->dcache_lock		(proc_pid_lookup)
 */

/*
 * Remove a page from the page cache and free it. Caller has to make
 * sure the page is locked and that nobody else uses it - or that usage
 * is safe.  The caller must hold a write_lock on the mapping's tree_lock.
 */
void __remove_from_page_cache(struct page *page)
{
	struct address_space *mapping = page->mapping;

	radix_tree_delete(&mapping->page_tree, page->index);
	page->mapping = NULL;
	mapping->nrpages--;
	pagecache_acct(-1);
}

void remove_from_page_cache(struct page *page)
{
	struct address_space *mapping = page->mapping;

127
	BUG_ON(!PageLocked(page));
Linus Torvalds's avatar
Linus Torvalds committed
128 129 130 131 132 133 134 135 136 137 138

	write_lock_irq(&mapping->tree_lock);
	__remove_from_page_cache(page);
	write_unlock_irq(&mapping->tree_lock);
}

static int sync_page(void *word)
{
	struct address_space *mapping;
	struct page *page;

139
	page = container_of((unsigned long *)word, struct page, flags);
Linus Torvalds's avatar
Linus Torvalds committed
140 141

	/*
142 143 144 145 146 147 148 149 150 151 152 153 154 155 156
	 * page_mapping() is being called without PG_locked held.
	 * Some knowledge of the state and use of the page is used to
	 * reduce the requirements down to a memory barrier.
	 * The danger here is of a stale page_mapping() return value
	 * indicating a struct address_space different from the one it's
	 * associated with when it is associated with one.
	 * After smp_mb(), it's either the correct page_mapping() for
	 * the page, or an old page_mapping() and the page's own
	 * page_mapping() has gone NULL.
	 * The ->sync_page() address_space operation must tolerate
	 * page_mapping() going NULL. By an amazing coincidence,
	 * this comes about because none of the users of the page
	 * in the ->sync_page() methods make essential use of the
	 * page_mapping(), merely passing the page down to the backing
	 * device's unplug functions when it's non-NULL, which in turn
157
	 * ignore it for all cases but swap, where only page_private(page) is
158 159 160
	 * of interest. When page_mapping() does go NULL, the entire
	 * call stack gracefully ignores the page and returns.
	 * -- wli
Linus Torvalds's avatar
Linus Torvalds committed
161 162 163 164 165 166 167 168 169 170 171 172
	 */
	smp_mb();
	mapping = page_mapping(page);
	if (mapping && mapping->a_ops && mapping->a_ops->sync_page)
		mapping->a_ops->sync_page(page);
	io_schedule();
	return 0;
}

/**
 * filemap_fdatawrite_range - start writeback against all of a mapping's
 * dirty pages that lie within the byte offsets <start, end>
173 174 175 176
 * @mapping:	address space structure to write
 * @start:	offset in bytes where the range starts
 * @end:	offset in bytes where the range ends
 * @sync_mode:	enable synchronous operation
Linus Torvalds's avatar
Linus Torvalds committed
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
 *
 * If sync_mode is WB_SYNC_ALL then this is a "data integrity" operation, as
 * opposed to a regular memory * cleansing writeback.  The difference between
 * these two operations is that if a dirty page/buffer is encountered, it must
 * be waited upon, and not just skipped over.
 */
static int __filemap_fdatawrite_range(struct address_space *mapping,
	loff_t start, loff_t end, int sync_mode)
{
	int ret;
	struct writeback_control wbc = {
		.sync_mode = sync_mode,
		.nr_to_write = mapping->nrpages * 2,
		.start = start,
		.end = end,
	};

	if (!mapping_cap_writeback_dirty(mapping))
		return 0;

	ret = do_writepages(mapping, &wbc);
	return ret;
}

static inline int __filemap_fdatawrite(struct address_space *mapping,
	int sync_mode)
{
	return __filemap_fdatawrite_range(mapping, 0, 0, sync_mode);
}

int filemap_fdatawrite(struct address_space *mapping)
{
	return __filemap_fdatawrite(mapping, WB_SYNC_ALL);
}
EXPORT_SYMBOL(filemap_fdatawrite);

static int filemap_fdatawrite_range(struct address_space *mapping,
	loff_t start, loff_t end)
{
	return __filemap_fdatawrite_range(mapping, start, end, WB_SYNC_ALL);
}

/*
 * This is a mostly non-blocking flush.  Not suitable for data-integrity
 * purposes - I/O may not be started against all dirty pages.
 */
int filemap_flush(struct address_space *mapping)
{
	return __filemap_fdatawrite(mapping, WB_SYNC_NONE);
}
EXPORT_SYMBOL(filemap_flush);

/*
 * Wait for writeback to complete against pages indexed by start->end
 * inclusive
 */
static int wait_on_page_writeback_range(struct address_space *mapping,
				pgoff_t start, pgoff_t end)
{
	struct pagevec pvec;
	int nr_pages;
	int ret = 0;
	pgoff_t index;

	if (end < start)
		return 0;

	pagevec_init(&pvec, 0);
	index = start;
	while ((index <= end) &&
			(nr_pages = pagevec_lookup_tag(&pvec, mapping, &index,
			PAGECACHE_TAG_WRITEBACK,
			min(end - index, (pgoff_t)PAGEVEC_SIZE-1) + 1)) != 0) {
		unsigned i;

		for (i = 0; i < nr_pages; i++) {
			struct page *page = pvec.pages[i];

			/* until radix tree lookup accepts end_index */
			if (page->index > end)
				continue;

			wait_on_page_writeback(page);
			if (PageError(page))
				ret = -EIO;
		}
		pagevec_release(&pvec);
		cond_resched();
	}

	/* Check for outstanding write errors */
	if (test_and_clear_bit(AS_ENOSPC, &mapping->flags))
		ret = -ENOSPC;
	if (test_and_clear_bit(AS_EIO, &mapping->flags))
		ret = -EIO;

	return ret;
}

/*
 * Write and wait upon all the pages in the passed range.  This is a "data
 * integrity" operation.  It waits upon in-flight writeout before starting and
 * waiting upon new writeout.  If there was an IO error, return it.
 *
281
 * We need to re-take i_mutex during the generic_osync_inode list walk because
Linus Torvalds's avatar
Linus Torvalds committed
282 283 284
 * it is otherwise livelockable.
 */
int sync_page_range(struct inode *inode, struct address_space *mapping,
285
			loff_t pos, loff_t count)
Linus Torvalds's avatar
Linus Torvalds committed
286 287 288 289 290 291 292 293 294
{
	pgoff_t start = pos >> PAGE_CACHE_SHIFT;
	pgoff_t end = (pos + count - 1) >> PAGE_CACHE_SHIFT;
	int ret;

	if (!mapping_cap_writeback_dirty(mapping) || !count)
		return 0;
	ret = filemap_fdatawrite_range(mapping, pos, pos + count - 1);
	if (ret == 0) {
295
		mutex_lock(&inode->i_mutex);
Linus Torvalds's avatar
Linus Torvalds committed
296
		ret = generic_osync_inode(inode, mapping, OSYNC_METADATA);
297
		mutex_unlock(&inode->i_mutex);
Linus Torvalds's avatar
Linus Torvalds committed
298 299 300 301 302 303 304 305
	}
	if (ret == 0)
		ret = wait_on_page_writeback_range(mapping, start, end);
	return ret;
}
EXPORT_SYMBOL(sync_page_range);

/*
306
 * Note: Holding i_mutex across sync_page_range_nolock is not a good idea
Linus Torvalds's avatar
Linus Torvalds committed
307 308 309
 * as it forces O_SYNC writers to different parts of the same file
 * to be serialised right until io completion.
 */
310 311
int sync_page_range_nolock(struct inode *inode, struct address_space *mapping,
			   loff_t pos, loff_t count)
Linus Torvalds's avatar
Linus Torvalds committed
312 313 314 315 316 317 318 319 320 321 322 323 324 325
{
	pgoff_t start = pos >> PAGE_CACHE_SHIFT;
	pgoff_t end = (pos + count - 1) >> PAGE_CACHE_SHIFT;
	int ret;

	if (!mapping_cap_writeback_dirty(mapping) || !count)
		return 0;
	ret = filemap_fdatawrite_range(mapping, pos, pos + count - 1);
	if (ret == 0)
		ret = generic_osync_inode(inode, mapping, OSYNC_METADATA);
	if (ret == 0)
		ret = wait_on_page_writeback_range(mapping, start, end);
	return ret;
}
326
EXPORT_SYMBOL(sync_page_range_nolock);
Linus Torvalds's avatar
Linus Torvalds committed
327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347

/**
 * filemap_fdatawait - walk the list of under-writeback pages of the given
 *     address space and wait for all of them.
 *
 * @mapping: address space structure to wait for
 */
int filemap_fdatawait(struct address_space *mapping)
{
	loff_t i_size = i_size_read(mapping->host);

	if (i_size == 0)
		return 0;

	return wait_on_page_writeback_range(mapping, 0,
				(i_size - 1) >> PAGE_CACHE_SHIFT);
}
EXPORT_SYMBOL(filemap_fdatawait);

int filemap_write_and_wait(struct address_space *mapping)
{
348
	int err = 0;
Linus Torvalds's avatar
Linus Torvalds committed
349 350

	if (mapping->nrpages) {
351 352 353 354 355 356 357 358 359 360 361 362
		err = filemap_fdatawrite(mapping);
		/*
		 * Even if the above returned error, the pages may be
		 * written partially (e.g. -ENOSPC), so we wait for it.
		 * But the -EIO is special case, it may indicate the worst
		 * thing (e.g. bug) happened, so we avoid waiting for it.
		 */
		if (err != -EIO) {
			int err2 = filemap_fdatawait(mapping);
			if (!err)
				err = err2;
		}
Linus Torvalds's avatar
Linus Torvalds committed
363
	}
364
	return err;
Linus Torvalds's avatar
Linus Torvalds committed
365
}
366
EXPORT_SYMBOL(filemap_write_and_wait);
Linus Torvalds's avatar
Linus Torvalds committed
367 368 369 370

int filemap_write_and_wait_range(struct address_space *mapping,
				 loff_t lstart, loff_t lend)
{
371
	int err = 0;
Linus Torvalds's avatar
Linus Torvalds committed
372 373

	if (mapping->nrpages) {
374 375 376 377 378 379 380 381 382 383
		err = __filemap_fdatawrite_range(mapping, lstart, lend,
						 WB_SYNC_ALL);
		/* See comment of filemap_write_and_wait() */
		if (err != -EIO) {
			int err2 = wait_on_page_writeback_range(mapping,
						lstart >> PAGE_CACHE_SHIFT,
						lend >> PAGE_CACHE_SHIFT);
			if (!err)
				err = err2;
		}
Linus Torvalds's avatar
Linus Torvalds committed
384
	}
385
	return err;
Linus Torvalds's avatar
Linus Torvalds committed
386 387 388 389 390 391 392 393 394 395
}

/*
 * This function is used to add newly allocated pagecache pages:
 * the page is new, so we can just run SetPageLocked() against it.
 * The other page state flags were set by rmqueue().
 *
 * This function does not add the page to the LRU.  The caller must do that.
 */
int add_to_page_cache(struct page *page, struct address_space *mapping,
396
		pgoff_t offset, gfp_t gfp_mask)
Linus Torvalds's avatar
Linus Torvalds committed
397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419
{
	int error = radix_tree_preload(gfp_mask & ~__GFP_HIGHMEM);

	if (error == 0) {
		write_lock_irq(&mapping->tree_lock);
		error = radix_tree_insert(&mapping->page_tree, offset, page);
		if (!error) {
			page_cache_get(page);
			SetPageLocked(page);
			page->mapping = mapping;
			page->index = offset;
			mapping->nrpages++;
			pagecache_acct(1);
		}
		write_unlock_irq(&mapping->tree_lock);
		radix_tree_preload_end();
	}
	return error;
}

EXPORT_SYMBOL(add_to_page_cache);

int add_to_page_cache_lru(struct page *page, struct address_space *mapping,
420
				pgoff_t offset, gfp_t gfp_mask)
Linus Torvalds's avatar
Linus Torvalds committed
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
{
	int ret = add_to_page_cache(page, mapping, offset, gfp_mask);
	if (ret == 0)
		lru_cache_add(page);
	return ret;
}

/*
 * In order to wait for pages to become available there must be
 * waitqueues associated with pages. By using a hash table of
 * waitqueues where the bucket discipline is to maintain all
 * waiters on the same queue and wake all when any of the pages
 * become available, and for the woken contexts to check to be
 * sure the appropriate page became available, this saves space
 * at a cost of "thundering herd" phenomena during rare hash
 * collisions.
 */
static wait_queue_head_t *page_waitqueue(struct page *page)
{
	const struct zone *zone = page_zone(page);

	return &zone->wait_table[hash_ptr(page, zone->wait_table_bits)];
}

static inline void wake_up_page(struct page *page, int bit)
{
	__wake_up_bit(page_waitqueue(page), &page->flags, bit);
}

void fastcall wait_on_page_bit(struct page *page, int bit_nr)
{
	DEFINE_WAIT_BIT(wait, &page->flags, bit_nr);

	if (test_bit(bit_nr, &page->flags))
		__wait_on_bit(page_waitqueue(page), &wait, sync_page,
							TASK_UNINTERRUPTIBLE);
}
EXPORT_SYMBOL(wait_on_page_bit);

/**
 * unlock_page() - unlock a locked page
 *
 * @page: the page
 *
 * Unlocks the page and wakes up sleepers in ___wait_on_page_locked().
 * Also wakes sleepers in wait_on_page_writeback() because the wakeup
 * mechananism between PageLocked pages and PageWriteback pages is shared.
 * But that's OK - sleepers in wait_on_page_writeback() just go back to sleep.
 *
 * The first mb is necessary to safely close the critical section opened by the
 * TestSetPageLocked(), the second mb is necessary to enforce ordering between
 * the clear_bit and the read of the waitqueue (to avoid SMP races with a
 * parallel wait_on_page_locked()).
 */
void fastcall unlock_page(struct page *page)
{
	smp_mb__before_clear_bit();
	if (!TestClearPageLocked(page))
		BUG();
	smp_mb__after_clear_bit(); 
	wake_up_page(page, PG_locked);
}
EXPORT_SYMBOL(unlock_page);

/*
 * End writeback against a page.
 */
void end_page_writeback(struct page *page)
{
	if (!TestClearPageReclaim(page) || rotate_reclaimable_page(page)) {
		if (!test_clear_page_writeback(page))
			BUG();
	}
	smp_mb__after_clear_bit();
	wake_up_page(page, PG_writeback);
}
EXPORT_SYMBOL(end_page_writeback);

/*
 * Get a lock on the page, assuming we need to sleep to get it.
 *
 * Ugly: running sync_page() in state TASK_UNINTERRUPTIBLE is scary.  If some
 * random driver's requestfn sets TASK_RUNNING, we could busywait.  However
 * chances are that on the second loop, the block layer's plug list is empty,
 * so sync_page() will then return in state TASK_UNINTERRUPTIBLE.
 */
void fastcall __lock_page(struct page *page)
{
	DEFINE_WAIT_BIT(wait, &page->flags, PG_locked);

	__wait_on_bit_lock(page_waitqueue(page), &wait, sync_page,
							TASK_UNINTERRUPTIBLE);
}
EXPORT_SYMBOL(__lock_page);

/*
 * a rather lightweight function, finding and getting a reference to a
 * hashed page atomically.
 */
struct page * find_get_page(struct address_space *mapping, unsigned long offset)
{
	struct page *page;

	read_lock_irq(&mapping->tree_lock);
	page = radix_tree_lookup(&mapping->page_tree, offset);
	if (page)
		page_cache_get(page);
	read_unlock_irq(&mapping->tree_lock);
	return page;
}

EXPORT_SYMBOL(find_get_page);

/*
 * Same as above, but trylock it instead of incrementing the count.
 */
struct page *find_trylock_page(struct address_space *mapping, unsigned long offset)
{
	struct page *page;

	read_lock_irq(&mapping->tree_lock);
	page = radix_tree_lookup(&mapping->page_tree, offset);
	if (page && TestSetPageLocked(page))
		page = NULL;
	read_unlock_irq(&mapping->tree_lock);
	return page;
}

EXPORT_SYMBOL(find_trylock_page);

/**
 * find_lock_page - locate, pin and lock a pagecache page
 *
554 555
 * @mapping: the address_space to search
 * @offset: the page index
Linus Torvalds's avatar
Linus Torvalds committed
556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573
 *
 * Locates the desired pagecache page, locks it, increments its reference
 * count and returns its address.
 *
 * Returns zero if the page was not present. find_lock_page() may sleep.
 */
struct page *find_lock_page(struct address_space *mapping,
				unsigned long offset)
{
	struct page *page;

	read_lock_irq(&mapping->tree_lock);
repeat:
	page = radix_tree_lookup(&mapping->page_tree, offset);
	if (page) {
		page_cache_get(page);
		if (TestSetPageLocked(page)) {
			read_unlock_irq(&mapping->tree_lock);
574
			__lock_page(page);
Linus Torvalds's avatar
Linus Torvalds committed
575 576 577
			read_lock_irq(&mapping->tree_lock);

			/* Has the page been truncated while we slept? */
578 579
			if (unlikely(page->mapping != mapping ||
				     page->index != offset)) {
Linus Torvalds's avatar
Linus Torvalds committed
580 581 582 583 584 585 586 587 588 589 590 591 592 593 594
				unlock_page(page);
				page_cache_release(page);
				goto repeat;
			}
		}
	}
	read_unlock_irq(&mapping->tree_lock);
	return page;
}

EXPORT_SYMBOL(find_lock_page);

/**
 * find_or_create_page - locate or add a pagecache page
 *
595 596 597
 * @mapping: the page's address_space
 * @index: the page's index into the mapping
 * @gfp_mask: page allocation mode
Linus Torvalds's avatar
Linus Torvalds committed
598 599 600 601 602 603 604 605 606 607 608 609 610
 *
 * Locates a page in the pagecache.  If the page is not present, a new page
 * is allocated using @gfp_mask and is added to the pagecache and to the VM's
 * LRU list.  The returned page is locked and has its reference count
 * incremented.
 *
 * find_or_create_page() may sleep, even if @gfp_flags specifies an atomic
 * allocation!
 *
 * find_or_create_page() returns the desired page's address, or zero on
 * memory exhaustion.
 */
struct page *find_or_create_page(struct address_space *mapping,
611
		unsigned long index, gfp_t gfp_mask)
Linus Torvalds's avatar
Linus Torvalds committed
612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702
{
	struct page *page, *cached_page = NULL;
	int err;
repeat:
	page = find_lock_page(mapping, index);
	if (!page) {
		if (!cached_page) {
			cached_page = alloc_page(gfp_mask);
			if (!cached_page)
				return NULL;
		}
		err = add_to_page_cache_lru(cached_page, mapping,
					index, gfp_mask);
		if (!err) {
			page = cached_page;
			cached_page = NULL;
		} else if (err == -EEXIST)
			goto repeat;
	}
	if (cached_page)
		page_cache_release(cached_page);
	return page;
}

EXPORT_SYMBOL(find_or_create_page);

/**
 * find_get_pages - gang pagecache lookup
 * @mapping:	The address_space to search
 * @start:	The starting page index
 * @nr_pages:	The maximum number of pages
 * @pages:	Where the resulting pages are placed
 *
 * find_get_pages() will search for and return a group of up to
 * @nr_pages pages in the mapping.  The pages are placed at @pages.
 * find_get_pages() takes a reference against the returned pages.
 *
 * The search returns a group of mapping-contiguous pages with ascending
 * indexes.  There may be holes in the indices due to not-present pages.
 *
 * find_get_pages() returns the number of pages which were found.
 */
unsigned find_get_pages(struct address_space *mapping, pgoff_t start,
			    unsigned int nr_pages, struct page **pages)
{
	unsigned int i;
	unsigned int ret;

	read_lock_irq(&mapping->tree_lock);
	ret = radix_tree_gang_lookup(&mapping->page_tree,
				(void **)pages, start, nr_pages);
	for (i = 0; i < ret; i++)
		page_cache_get(pages[i]);
	read_unlock_irq(&mapping->tree_lock);
	return ret;
}

/*
 * Like find_get_pages, except we only return pages which are tagged with
 * `tag'.   We update *index to index the next page for the traversal.
 */
unsigned find_get_pages_tag(struct address_space *mapping, pgoff_t *index,
			int tag, unsigned int nr_pages, struct page **pages)
{
	unsigned int i;
	unsigned int ret;

	read_lock_irq(&mapping->tree_lock);
	ret = radix_tree_gang_lookup_tag(&mapping->page_tree,
				(void **)pages, *index, nr_pages, tag);
	for (i = 0; i < ret; i++)
		page_cache_get(pages[i]);
	if (ret)
		*index = pages[ret - 1]->index + 1;
	read_unlock_irq(&mapping->tree_lock);
	return ret;
}

/*
 * Same as grab_cache_page, but do not wait if the page is unavailable.
 * This is intended for speculative data generators, where the data can
 * be regenerated if the page couldn't be grabbed.  This routine should
 * be safe to call while holding the lock for another page.
 *
 * Clear __GFP_FS when allocating the page to avoid recursion into the fs
 * and deadlock against the caller's locked page.
 */
struct page *
grab_cache_page_nowait(struct address_space *mapping, unsigned long index)
{
	struct page *page = find_get_page(mapping, index);
703
	gfp_t gfp_mask;
Linus Torvalds's avatar
Linus Torvalds committed
704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850

	if (page) {
		if (!TestSetPageLocked(page))
			return page;
		page_cache_release(page);
		return NULL;
	}
	gfp_mask = mapping_gfp_mask(mapping) & ~__GFP_FS;
	page = alloc_pages(gfp_mask, 0);
	if (page && add_to_page_cache_lru(page, mapping, index, gfp_mask)) {
		page_cache_release(page);
		page = NULL;
	}
	return page;
}

EXPORT_SYMBOL(grab_cache_page_nowait);

/*
 * This is a generic file read routine, and uses the
 * mapping->a_ops->readpage() function for the actual low-level
 * stuff.
 *
 * This is really ugly. But the goto's actually try to clarify some
 * of the logic when it comes to error handling etc.
 *
 * Note the struct file* is only passed for the use of readpage.  It may be
 * NULL.
 */
void do_generic_mapping_read(struct address_space *mapping,
			     struct file_ra_state *_ra,
			     struct file *filp,
			     loff_t *ppos,
			     read_descriptor_t *desc,
			     read_actor_t actor)
{
	struct inode *inode = mapping->host;
	unsigned long index;
	unsigned long end_index;
	unsigned long offset;
	unsigned long last_index;
	unsigned long next_index;
	unsigned long prev_index;
	loff_t isize;
	struct page *cached_page;
	int error;
	struct file_ra_state ra = *_ra;

	cached_page = NULL;
	index = *ppos >> PAGE_CACHE_SHIFT;
	next_index = index;
	prev_index = ra.prev_page;
	last_index = (*ppos + desc->count + PAGE_CACHE_SIZE-1) >> PAGE_CACHE_SHIFT;
	offset = *ppos & ~PAGE_CACHE_MASK;

	isize = i_size_read(inode);
	if (!isize)
		goto out;

	end_index = (isize - 1) >> PAGE_CACHE_SHIFT;
	for (;;) {
		struct page *page;
		unsigned long nr, ret;

		/* nr is the maximum number of bytes to copy from this page */
		nr = PAGE_CACHE_SIZE;
		if (index >= end_index) {
			if (index > end_index)
				goto out;
			nr = ((isize - 1) & ~PAGE_CACHE_MASK) + 1;
			if (nr <= offset) {
				goto out;
			}
		}
		nr = nr - offset;

		cond_resched();
		if (index == next_index)
			next_index = page_cache_readahead(mapping, &ra, filp,
					index, last_index - index);

find_page:
		page = find_get_page(mapping, index);
		if (unlikely(page == NULL)) {
			handle_ra_miss(mapping, &ra, index);
			goto no_cached_page;
		}
		if (!PageUptodate(page))
			goto page_not_up_to_date;
page_ok:

		/* If users can be writing to this page using arbitrary
		 * virtual addresses, take care about potential aliasing
		 * before reading the page on the kernel side.
		 */
		if (mapping_writably_mapped(mapping))
			flush_dcache_page(page);

		/*
		 * When (part of) the same page is read multiple times
		 * in succession, only mark it as accessed the first time.
		 */
		if (prev_index != index)
			mark_page_accessed(page);
		prev_index = index;

		/*
		 * Ok, we have the page, and it's up-to-date, so
		 * now we can copy it to user space...
		 *
		 * The actor routine returns how many bytes were actually used..
		 * NOTE! This may not be the same as how much of a user buffer
		 * we filled up (we may be padding etc), so we can only update
		 * "pos" here (the actor routine has to update the user buffer
		 * pointers and the remaining count).
		 */
		ret = actor(desc, page, offset, nr);
		offset += ret;
		index += offset >> PAGE_CACHE_SHIFT;
		offset &= ~PAGE_CACHE_MASK;

		page_cache_release(page);
		if (ret == nr && desc->count)
			continue;
		goto out;

page_not_up_to_date:
		/* Get exclusive access to the page ... */
		lock_page(page);

		/* Did it get unhashed before we got the lock? */
		if (!page->mapping) {
			unlock_page(page);
			page_cache_release(page);
			continue;
		}

		/* Did somebody else fill it already? */
		if (PageUptodate(page)) {
			unlock_page(page);
			goto page_ok;
		}

readpage:
		/* Start the actual read. The read will unlock the page. */
		error = mapping->a_ops->readpage(filp, page);

851 852 853 854 855
		if (unlikely(error)) {
			if (error == AOP_TRUNCATED_PAGE) {
				page_cache_release(page);
				goto find_page;
			}
Linus Torvalds's avatar
Linus Torvalds committed
856
			goto readpage_error;
857
		}
Linus Torvalds's avatar
Linus Torvalds committed
858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032

		if (!PageUptodate(page)) {
			lock_page(page);
			if (!PageUptodate(page)) {
				if (page->mapping == NULL) {
					/*
					 * invalidate_inode_pages got it
					 */
					unlock_page(page);
					page_cache_release(page);
					goto find_page;
				}
				unlock_page(page);
				error = -EIO;
				goto readpage_error;
			}
			unlock_page(page);
		}

		/*
		 * i_size must be checked after we have done ->readpage.
		 *
		 * Checking i_size after the readpage allows us to calculate
		 * the correct value for "nr", which means the zero-filled
		 * part of the page is not copied back to userspace (unless
		 * another truncate extends the file - this is desired though).
		 */
		isize = i_size_read(inode);
		end_index = (isize - 1) >> PAGE_CACHE_SHIFT;
		if (unlikely(!isize || index > end_index)) {
			page_cache_release(page);
			goto out;
		}

		/* nr is the maximum number of bytes to copy from this page */
		nr = PAGE_CACHE_SIZE;
		if (index == end_index) {
			nr = ((isize - 1) & ~PAGE_CACHE_MASK) + 1;
			if (nr <= offset) {
				page_cache_release(page);
				goto out;
			}
		}
		nr = nr - offset;
		goto page_ok;

readpage_error:
		/* UHHUH! A synchronous read error occurred. Report it */
		desc->error = error;
		page_cache_release(page);
		goto out;

no_cached_page:
		/*
		 * Ok, it wasn't cached, so we need to create a new
		 * page..
		 */
		if (!cached_page) {
			cached_page = page_cache_alloc_cold(mapping);
			if (!cached_page) {
				desc->error = -ENOMEM;
				goto out;
			}
		}
		error = add_to_page_cache_lru(cached_page, mapping,
						index, GFP_KERNEL);
		if (error) {
			if (error == -EEXIST)
				goto find_page;
			desc->error = error;
			goto out;
		}
		page = cached_page;
		cached_page = NULL;
		goto readpage;
	}

out:
	*_ra = ra;

	*ppos = ((loff_t) index << PAGE_CACHE_SHIFT) + offset;
	if (cached_page)
		page_cache_release(cached_page);
	if (filp)
		file_accessed(filp);
}

EXPORT_SYMBOL(do_generic_mapping_read);

int file_read_actor(read_descriptor_t *desc, struct page *page,
			unsigned long offset, unsigned long size)
{
	char *kaddr;
	unsigned long left, count = desc->count;

	if (size > count)
		size = count;

	/*
	 * Faults on the destination of a read are common, so do it before
	 * taking the kmap.
	 */
	if (!fault_in_pages_writeable(desc->arg.buf, size)) {
		kaddr = kmap_atomic(page, KM_USER0);
		left = __copy_to_user_inatomic(desc->arg.buf,
						kaddr + offset, size);
		kunmap_atomic(kaddr, KM_USER0);
		if (left == 0)
			goto success;
	}

	/* Do it the slow way */
	kaddr = kmap(page);
	left = __copy_to_user(desc->arg.buf, kaddr + offset, size);
	kunmap(page);

	if (left) {
		size -= left;
		desc->error = -EFAULT;
	}
success:
	desc->count = count - size;
	desc->written += size;
	desc->arg.buf += size;
	return size;
}

/*
 * This is the "read()" routine for all filesystems
 * that can use the page cache directly.
 */
ssize_t
__generic_file_aio_read(struct kiocb *iocb, const struct iovec *iov,
		unsigned long nr_segs, loff_t *ppos)
{
	struct file *filp = iocb->ki_filp;
	ssize_t retval;
	unsigned long seg;
	size_t count;

	count = 0;
	for (seg = 0; seg < nr_segs; seg++) {
		const struct iovec *iv = &iov[seg];

		/*
		 * If any segment has a negative length, or the cumulative
		 * length ever wraps negative then return -EINVAL.
		 */
		count += iv->iov_len;
		if (unlikely((ssize_t)(count|iv->iov_len) < 0))
			return -EINVAL;
		if (access_ok(VERIFY_WRITE, iv->iov_base, iv->iov_len))
			continue;
		if (seg == 0)
			return -EFAULT;
		nr_segs = seg;
		count -= iv->iov_len;	/* This segment is no good */
		break;
	}

	/* coalesce the iovecs and go direct-to-BIO for O_DIRECT */
	if (filp->f_flags & O_DIRECT) {
		loff_t pos = *ppos, size;
		struct address_space *mapping;
		struct inode *inode;

		mapping = filp->f_mapping;
		inode = mapping->host;
		retval = 0;
		if (!count)
			goto out; /* skip atime */
		size = i_size_read(inode);
		if (pos < size) {
			retval = generic_file_direct_IO(READ, iocb,
						iov, pos, nr_segs);
1033
			if (retval > 0 && !is_sync_kiocb(iocb))
Linus Torvalds's avatar
Linus Torvalds committed
1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054
				retval = -EIOCBQUEUED;
			if (retval > 0)
				*ppos = pos + retval;
		}
		file_accessed(filp);
		goto out;
	}

	retval = 0;
	if (count) {
		for (seg = 0; seg < nr_segs; seg++) {
			read_descriptor_t desc;

			desc.written = 0;
			desc.arg.buf = iov[seg].iov_base;
			desc.count = iov[seg].iov_len;
			if (desc.count == 0)
				continue;
			desc.error = 0;
			do_generic_file_read(filp,ppos,&desc,file_read_actor);
			retval += desc.written;
1055 1056
			if (desc.error) {
				retval = retval ?: desc.error;
Linus Torvalds's avatar
Linus Torvalds committed
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 1169 1170 1171 1172 1173 1174 1175 1176
				break;
			}
		}
	}
out:
	return retval;
}

EXPORT_SYMBOL(__generic_file_aio_read);

ssize_t
generic_file_aio_read(struct kiocb *iocb, char __user *buf, size_t count, loff_t pos)
{
	struct iovec local_iov = { .iov_base = buf, .iov_len = count };

	BUG_ON(iocb->ki_pos != pos);
	return __generic_file_aio_read(iocb, &local_iov, 1, &iocb->ki_pos);
}

EXPORT_SYMBOL(generic_file_aio_read);

ssize_t
generic_file_read(struct file *filp, char __user *buf, size_t count, loff_t *ppos)
{
	struct iovec local_iov = { .iov_base = buf, .iov_len = count };
	struct kiocb kiocb;
	ssize_t ret;

	init_sync_kiocb(&kiocb, filp);
	ret = __generic_file_aio_read(&kiocb, &local_iov, 1, ppos);
	if (-EIOCBQUEUED == ret)
		ret = wait_on_sync_kiocb(&kiocb);
	return ret;
}

EXPORT_SYMBOL(generic_file_read);

int file_send_actor(read_descriptor_t * desc, struct page *page, unsigned long offset, unsigned long size)
{
	ssize_t written;
	unsigned long count = desc->count;
	struct file *file = desc->arg.data;

	if (size > count)
		size = count;

	written = file->f_op->sendpage(file, page, offset,
				       size, &file->f_pos, size<count);
	if (written < 0) {
		desc->error = written;
		written = 0;
	}
	desc->count = count - written;
	desc->written += written;
	return written;
}

ssize_t generic_file_sendfile(struct file *in_file, loff_t *ppos,
			 size_t count, read_actor_t actor, void *target)
{
	read_descriptor_t desc;

	if (!count)
		return 0;

	desc.written = 0;
	desc.count = count;
	desc.arg.data = target;
	desc.error = 0;

	do_generic_file_read(in_file, ppos, &desc, actor);
	if (desc.written)
		return desc.written;
	return desc.error;
}

EXPORT_SYMBOL(generic_file_sendfile);

static ssize_t
do_readahead(struct address_space *mapping, struct file *filp,
	     unsigned long index, unsigned long nr)
{
	if (!mapping || !mapping->a_ops || !mapping->a_ops->readpage)
		return -EINVAL;

	force_page_cache_readahead(mapping, filp, index,
					max_sane_readahead(nr));
	return 0;
}

asmlinkage ssize_t sys_readahead(int fd, loff_t offset, size_t count)
{
	ssize_t ret;
	struct file *file;

	ret = -EBADF;
	file = fget(fd);
	if (file) {
		if (file->f_mode & FMODE_READ) {
			struct address_space *mapping = file->f_mapping;
			unsigned long start = offset >> PAGE_CACHE_SHIFT;
			unsigned long end = (offset + count - 1) >> PAGE_CACHE_SHIFT;
			unsigned long len = end - start + 1;
			ret = do_readahead(mapping, file, start, len);
		}
		fput(file);
	}
	return ret;
}

#ifdef CONFIG_MMU
/*
 * This adds the requested page to the page cache if it isn't already there,
 * and schedules an I/O to read in its contents from disk.
 */
static int FASTCALL(page_cache_read(struct file * file, unsigned long offset));
static int fastcall page_cache_read(struct file * file, unsigned long offset)
{
	struct address_space *mapping = file->f_mapping;
	struct page *page; 
1177
	int ret;
Linus Torvalds's avatar
Linus Torvalds committed
1178

1179 1180 1181 1182 1183 1184 1185 1186 1187 1188
	do {
		page = page_cache_alloc_cold(mapping);
		if (!page)
			return -ENOMEM;

		ret = add_to_page_cache_lru(page, mapping, offset, GFP_KERNEL);
		if (ret == 0)
			ret = mapping->a_ops->readpage(file, page);
		else if (ret == -EEXIST)
			ret = 0; /* losing race to add is OK */
Linus Torvalds's avatar
Linus Torvalds committed
1189 1190 1191

		page_cache_release(page);

1192 1193 1194
	} while (ret == AOP_TRUNCATED_PAGE);
		
	return ret;
Linus Torvalds's avatar
Linus Torvalds committed
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 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353
}

#define MMAP_LOTSAMISS  (100)

/*
 * filemap_nopage() is invoked via the vma operations vector for a
 * mapped memory region to read in file data during a page fault.
 *
 * The goto's are kind of ugly, but this streamlines the normal case of having
 * it in the page cache, and handles the special cases reasonably without
 * having a lot of duplicated code.
 */
struct page *filemap_nopage(struct vm_area_struct *area,
				unsigned long address, int *type)
{
	int error;
	struct file *file = area->vm_file;
	struct address_space *mapping = file->f_mapping;
	struct file_ra_state *ra = &file->f_ra;
	struct inode *inode = mapping->host;
	struct page *page;
	unsigned long size, pgoff;
	int did_readaround = 0, majmin = VM_FAULT_MINOR;

	pgoff = ((address-area->vm_start) >> PAGE_CACHE_SHIFT) + area->vm_pgoff;

retry_all:
	size = (i_size_read(inode) + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
	if (pgoff >= size)
		goto outside_data_content;

	/* If we don't want any read-ahead, don't bother */
	if (VM_RandomReadHint(area))
		goto no_cached_page;

	/*
	 * The readahead code wants to be told about each and every page
	 * so it can build and shrink its windows appropriately
	 *
	 * For sequential accesses, we use the generic readahead logic.
	 */
	if (VM_SequentialReadHint(area))
		page_cache_readahead(mapping, ra, file, pgoff, 1);

	/*
	 * Do we have something in the page cache already?
	 */
retry_find:
	page = find_get_page(mapping, pgoff);
	if (!page) {
		unsigned long ra_pages;

		if (VM_SequentialReadHint(area)) {
			handle_ra_miss(mapping, ra, pgoff);
			goto no_cached_page;
		}
		ra->mmap_miss++;

		/*
		 * Do we miss much more than hit in this file? If so,
		 * stop bothering with read-ahead. It will only hurt.
		 */
		if (ra->mmap_miss > ra->mmap_hit + MMAP_LOTSAMISS)
			goto no_cached_page;

		/*
		 * To keep the pgmajfault counter straight, we need to
		 * check did_readaround, as this is an inner loop.
		 */
		if (!did_readaround) {
			majmin = VM_FAULT_MAJOR;
			inc_page_state(pgmajfault);
		}
		did_readaround = 1;
		ra_pages = max_sane_readahead(file->f_ra.ra_pages);
		if (ra_pages) {
			pgoff_t start = 0;

			if (pgoff > ra_pages / 2)
				start = pgoff - ra_pages / 2;
			do_page_cache_readahead(mapping, file, start, ra_pages);
		}
		page = find_get_page(mapping, pgoff);
		if (!page)
			goto no_cached_page;
	}

	if (!did_readaround)
		ra->mmap_hit++;

	/*
	 * Ok, found a page in the page cache, now we need to check
	 * that it's up-to-date.
	 */
	if (!PageUptodate(page))
		goto page_not_uptodate;

success:
	/*
	 * Found the page and have a reference on it.
	 */
	mark_page_accessed(page);
	if (type)
		*type = majmin;
	return page;

outside_data_content:
	/*
	 * An external ptracer can access pages that normally aren't
	 * accessible..
	 */
	if (area->vm_mm == current->mm)
		return NULL;
	/* Fall through to the non-read-ahead case */
no_cached_page:
	/*
	 * We're only likely to ever get here if MADV_RANDOM is in
	 * effect.
	 */
	error = page_cache_read(file, pgoff);
	grab_swap_token();

	/*
	 * The page we want has now been added to the page cache.
	 * In the unlikely event that someone removed it in the
	 * meantime, we'll just come back here and read it again.
	 */
	if (error >= 0)
		goto retry_find;

	/*
	 * An error return from page_cache_read can result if the
	 * system is low on memory, or a problem occurs while trying
	 * to schedule I/O.
	 */
	if (error == -ENOMEM)
		return NOPAGE_OOM;
	return NULL;

page_not_uptodate:
	if (!did_readaround) {
		majmin = VM_FAULT_MAJOR;
		inc_page_state(pgmajfault);
	}
	lock_page(page);

	/* Did it get unhashed while we waited for it? */
	if (!page->mapping) {
		unlock_page(page);
		page_cache_release(page);
		goto retry_all;
	}

	/* Did somebody else get it up-to-date? */
	if (PageUptodate(page)) {
		unlock_page(page);
		goto success;
	}

1354 1355
	error = mapping->a_ops->readpage(file, page);
	if (!error) {
Linus Torvalds's avatar
Linus Torvalds committed
1356 1357 1358
		wait_on_page_locked(page);
		if (PageUptodate(page))
			goto success;
1359 1360 1361
	} else if (error == AOP_TRUNCATED_PAGE) {
		page_cache_release(page);
		goto retry_find;
Linus Torvalds's avatar
Linus Torvalds committed
1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384
	}

	/*
	 * Umm, take care of errors if the page isn't up-to-date.
	 * Try to re-read it _once_. We do this synchronously,
	 * because there really aren't any performance issues here
	 * and we need to check for errors.
	 */
	lock_page(page);

	/* Somebody truncated the page on us? */
	if (!page->mapping) {
		unlock_page(page);
		page_cache_release(page);
		goto retry_all;
	}

	/* Somebody else successfully read it in? */
	if (PageUptodate(page)) {
		unlock_page(page);
		goto success;
	}
	ClearPageError(page);
1385 1386
	error = mapping->a_ops->readpage(file, page);
	if (!error) {
Linus Torvalds's avatar
Linus Torvalds committed
1387 1388 1389
		wait_on_page_locked(page);
		if (PageUptodate(page))
			goto success;
1390 1391 1392
	} else if (error == AOP_TRUNCATED_PAGE) {
		page_cache_release(page);
		goto retry_find;
Linus Torvalds's avatar
Linus Torvalds committed
1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426
	}

	/*
	 * Things didn't work out. Return zero to tell the
	 * mm layer so, possibly freeing the page cache page first.
	 */
	page_cache_release(page);
	return NULL;
}

EXPORT_SYMBOL(filemap_nopage);

static struct page * filemap_getpage(struct file *file, unsigned long pgoff,
					int nonblock)
{
	struct address_space *mapping = file->f_mapping;
	struct page *page;
	int error;

	/*
	 * Do we have something in the page cache already?
	 */
retry_find:
	page = find_get_page(mapping, pgoff);
	if (!page) {
		if (nonblock)
			return NULL;
		goto no_cached_page;
	}

	/*
	 * Ok, found a page in the page cache, now we need to check
	 * that it's up-to-date.
	 */
1427 1428 1429 1430 1431
	if (!PageUptodate(page)) {
		if (nonblock) {
			page_cache_release(page);
			return NULL;
		}
Linus Torvalds's avatar
Linus Torvalds committed
1432
		goto page_not_uptodate;
1433
	}
Linus Torvalds's avatar
Linus Torvalds committed
1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474

success:
	/*
	 * Found the page and have a reference on it.
	 */
	mark_page_accessed(page);
	return page;

no_cached_page:
	error = page_cache_read(file, pgoff);

	/*
	 * The page we want has now been added to the page cache.
	 * In the unlikely event that someone removed it in the
	 * meantime, we'll just come back here and read it again.
	 */
	if (error >= 0)
		goto retry_find;

	/*
	 * An error return from page_cache_read can result if the
	 * system is low on memory, or a problem occurs while trying
	 * to schedule I/O.
	 */
	return NULL;

page_not_uptodate:
	lock_page(page);

	/* Did it get unhashed while we waited for it? */
	if (!page->mapping) {
		unlock_page(page);
		goto err;
	}

	/* Did somebody else get it up-to-date? */
	if (PageUptodate(page)) {
		unlock_page(page);
		goto success;
	}

1475 1476
	error = mapping->a_ops->readpage(file, page);
	if (!error) {
Linus Torvalds's avatar
Linus Torvalds committed
1477 1478 1479
		wait_on_page_locked(page);
		if (PageUptodate(page))
			goto success;
1480 1481 1482
	} else if (error == AOP_TRUNCATED_PAGE) {
		page_cache_release(page);
		goto retry_find;
Linus Torvalds's avatar
Linus Torvalds committed
1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504
	}

	/*
	 * Umm, take care of errors if the page isn't up-to-date.
	 * Try to re-read it _once_. We do this synchronously,
	 * because there really aren't any performance issues here
	 * and we need to check for errors.
	 */
	lock_page(page);

	/* Somebody truncated the page on us? */
	if (!page->mapping) {
		unlock_page(page);
		goto err;
	}
	/* Somebody else successfully read it in? */
	if (PageUptodate(page)) {
		unlock_page(page);
		goto success;
	}

	ClearPageError(page);
1505 1506
	error = mapping->a_ops->readpage(file, page);
	if (!error) {
Linus Torvalds's avatar
Linus Torvalds committed
1507 1508 1509
		wait_on_page_locked(page);
		if (PageUptodate(page))
			goto success;
1510 1511 1512
	} else if (error == AOP_TRUNCATED_PAGE) {
		page_cache_release(page);
		goto retry_find;
Linus Torvalds's avatar
Linus Torvalds committed
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 1545 1546
	}

	/*
	 * Things didn't work out. Return zero to tell the
	 * mm layer so, possibly freeing the page cache page first.
	 */
err:
	page_cache_release(page);

	return NULL;
}

int filemap_populate(struct vm_area_struct *vma, unsigned long addr,
		unsigned long len, pgprot_t prot, unsigned long pgoff,
		int nonblock)
{
	struct file *file = vma->vm_file;
	struct address_space *mapping = file->f_mapping;
	struct inode *inode = mapping->host;
	unsigned long size;
	struct mm_struct *mm = vma->vm_mm;
	struct page *page;
	int err;

	if (!nonblock)
		force_page_cache_readahead(mapping, vma->vm_file,
					pgoff, len >> PAGE_CACHE_SHIFT);

repeat:
	size = (i_size_read(inode) + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
	if (pgoff + (len >> PAGE_CACHE_SHIFT) > size)
		return -EINVAL;

	page = filemap_getpage(file, pgoff, nonblock);
1547 1548 1549

	/* XXX: This is wrong, a filesystem I/O error may have happened. Fix that as
	 * done in shmem_populate calling shmem_getpage */
Linus Torvalds's avatar
Linus Torvalds committed
1550 1551
	if (!page && !nonblock)
		return -ENOMEM;
1552

Linus Torvalds's avatar
Linus Torvalds committed
1553 1554 1555 1556 1557 1558
	if (page) {
		err = install_page(mm, vma, addr, page, prot);
		if (err) {
			page_cache_release(page);
			return err;
		}
1559
	} else if (vma->vm_flags & VM_NONLINEAR) {
1560 1561 1562
		/* No page was found just because we can't read it in now (being
		 * here implies nonblock != 0), but the page may exist, so set
		 * the PTE to fault it in later. */
Linus Torvalds's avatar
Linus Torvalds committed
1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575
		err = install_file_pte(mm, vma, addr, pgoff, prot);
		if (err)
			return err;
	}

	len -= PAGE_SIZE;
	addr += PAGE_SIZE;
	pgoff++;
	if (len)
		goto repeat;

	return 0;
}
1576
EXPORT_SYMBOL(filemap_populate);
Linus Torvalds's avatar
Linus Torvalds committed
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 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763

struct vm_operations_struct generic_file_vm_ops = {
	.nopage		= filemap_nopage,
	.populate	= filemap_populate,
};

/* This is used for a general mmap of a disk file */

int generic_file_mmap(struct file * file, struct vm_area_struct * vma)
{
	struct address_space *mapping = file->f_mapping;

	if (!mapping->a_ops->readpage)
		return -ENOEXEC;
	file_accessed(file);
	vma->vm_ops = &generic_file_vm_ops;
	return 0;
}

/*
 * This is for filesystems which do not implement ->writepage.
 */
int generic_file_readonly_mmap(struct file *file, struct vm_area_struct *vma)
{
	if ((vma->vm_flags & VM_SHARED) && (vma->vm_flags & VM_MAYWRITE))
		return -EINVAL;
	return generic_file_mmap(file, vma);
}
#else
int generic_file_mmap(struct file * file, struct vm_area_struct * vma)
{
	return -ENOSYS;
}
int generic_file_readonly_mmap(struct file * file, struct vm_area_struct * vma)
{
	return -ENOSYS;
}
#endif /* CONFIG_MMU */

EXPORT_SYMBOL(generic_file_mmap);
EXPORT_SYMBOL(generic_file_readonly_mmap);

static inline struct page *__read_cache_page(struct address_space *mapping,
				unsigned long index,
				int (*filler)(void *,struct page*),
				void *data)
{
	struct page *page, *cached_page = NULL;
	int err;
repeat:
	page = find_get_page(mapping, index);
	if (!page) {
		if (!cached_page) {
			cached_page = page_cache_alloc_cold(mapping);
			if (!cached_page)
				return ERR_PTR(-ENOMEM);
		}
		err = add_to_page_cache_lru(cached_page, mapping,
					index, GFP_KERNEL);
		if (err == -EEXIST)
			goto repeat;
		if (err < 0) {
			/* Presumably ENOMEM for radix tree node */
			page_cache_release(cached_page);
			return ERR_PTR(err);
		}
		page = cached_page;
		cached_page = NULL;
		err = filler(data, page);
		if (err < 0) {
			page_cache_release(page);
			page = ERR_PTR(err);
		}
	}
	if (cached_page)
		page_cache_release(cached_page);
	return page;
}

/*
 * Read into the page cache. If a page already exists,
 * and PageUptodate() is not set, try to fill the page.
 */
struct page *read_cache_page(struct address_space *mapping,
				unsigned long index,
				int (*filler)(void *,struct page*),
				void *data)
{
	struct page *page;
	int err;

retry:
	page = __read_cache_page(mapping, index, filler, data);
	if (IS_ERR(page))
		goto out;
	mark_page_accessed(page);
	if (PageUptodate(page))
		goto out;

	lock_page(page);
	if (!page->mapping) {
		unlock_page(page);
		page_cache_release(page);
		goto retry;
	}
	if (PageUptodate(page)) {
		unlock_page(page);
		goto out;
	}
	err = filler(data, page);
	if (err < 0) {
		page_cache_release(page);
		page = ERR_PTR(err);
	}
 out:
	return page;
}

EXPORT_SYMBOL(read_cache_page);

/*
 * If the page was newly created, increment its refcount and add it to the
 * caller's lru-buffering pagevec.  This function is specifically for
 * generic_file_write().
 */
static inline struct page *
__grab_cache_page(struct address_space *mapping, unsigned long index,
			struct page **cached_page, struct pagevec *lru_pvec)
{
	int err;
	struct page *page;
repeat:
	page = find_lock_page(mapping, index);
	if (!page) {
		if (!*cached_page) {
			*cached_page = page_cache_alloc(mapping);
			if (!*cached_page)
				return NULL;
		}
		err = add_to_page_cache(*cached_page, mapping,
					index, GFP_KERNEL);
		if (err == -EEXIST)
			goto repeat;
		if (err == 0) {
			page = *cached_page;
			page_cache_get(page);
			if (!pagevec_add(lru_pvec, page))
				__pagevec_lru_add(lru_pvec);
			*cached_page = NULL;
		}
	}
	return page;
}

/*
 * The logic we want is
 *
 *	if suid or (sgid and xgrp)
 *		remove privs
 */
int remove_suid(struct dentry *dentry)
{
	mode_t mode = dentry->d_inode->i_mode;
	int kill = 0;
	int result = 0;

	/* suid always must be killed */
	if (unlikely(mode & S_ISUID))
		kill = ATTR_KILL_SUID;

	/*
	 * sgid without any exec bits is just a mandatory locking mark; leave
	 * it alone.  If some exec bits are set, it's a real sgid; kill it.
	 */
	if (unlikely((mode & S_ISGID) && (mode & S_IXGRP)))
		kill |= ATTR_KILL_SGID;

	if (unlikely(kill && !capable(CAP_FSETID))) {
		struct iattr newattrs;

		newattrs.ia_valid = ATTR_FORCE | kill;
		result = notify_change(dentry, &newattrs);
	}
	return result;
}
EXPORT_SYMBOL(remove_suid);

1764
size_t
Linus Torvalds's avatar
Linus Torvalds committed
1765 1766 1767 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 1840 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
__filemap_copy_from_user_iovec(char *vaddr, 
			const struct iovec *iov, size_t base, size_t bytes)
{
	size_t copied = 0, left = 0;

	while (bytes) {
		char __user *buf = iov->iov_base + base;
		int copy = min(bytes, iov->iov_len - base);

		base = 0;
		left = __copy_from_user_inatomic(vaddr, buf, copy);
		copied += copy;
		bytes -= copy;
		vaddr += copy;
		iov++;

		if (unlikely(left)) {
			/* zero the rest of the target like __copy_from_user */
			if (bytes)
				memset(vaddr, 0, bytes);
			break;
		}
	}
	return copied - left;
}

/*
 * Performs necessary checks before doing a write
 *
 * Can adjust writing position aor amount of bytes to write.
 * Returns appropriate error code that caller should return or
 * zero in case that write should be allowed.
 */
inline int generic_write_checks(struct file *file, loff_t *pos, size_t *count, int isblk)
{
	struct inode *inode = file->f_mapping->host;
	unsigned long limit = current->signal->rlim[RLIMIT_FSIZE].rlim_cur;

        if (unlikely(*pos < 0))
                return -EINVAL;

	if (!isblk) {
		/* FIXME: this is for backwards compatibility with 2.4 */
		if (file->f_flags & O_APPEND)
                        *pos = i_size_read(inode);

		if (limit != RLIM_INFINITY) {
			if (*pos >= limit) {
				send_sig(SIGXFSZ, current, 0);
				return -EFBIG;
			}
			if (*count > limit - (typeof(limit))*pos) {
				*count = limit - (typeof(limit))*pos;
			}
		}
	}

	/*
	 * LFS rule
	 */
	if (unlikely(*pos + *count > MAX_NON_LFS &&
				!(file->f_flags & O_LARGEFILE))) {
		if (*pos >= MAX_NON_LFS) {
			send_sig(SIGXFSZ, current, 0);
			return -EFBIG;
		}
		if (*count > MAX_NON_LFS - (unsigned long)*pos) {
			*count = MAX_NON_LFS - (unsigned long)*pos;
		}
	}

	/*
	 * Are we about to exceed the fs block limit ?
	 *
	 * If we have written data it becomes a short write.  If we have
	 * exceeded without writing data we send a signal and return EFBIG.
	 * Linus frestrict idea will clean these up nicely..
	 */
	if (likely(!isblk)) {
		if (unlikely(*pos >= inode->i_sb->s_maxbytes)) {
			if (*count || *pos > inode->i_sb->s_maxbytes) {
				send_sig(SIGXFSZ, current, 0);
				return -EFBIG;
			}
			/* zero-length writes at ->s_maxbytes are OK */
		}

		if (unlikely(*pos + *count > inode->i_sb->s_maxbytes))
			*count = inode->i_sb->s_maxbytes - *pos;
	} else {
		loff_t isize;
		if (bdev_read_only(I_BDEV(inode)))
			return -EPERM;
		isize = i_size_read(inode);
		if (*pos >= isize) {
			if (*count || *pos > isize)
				return -ENOSPC;
		}

		if (*pos + *count > isize)
			*count = isize - *pos;
	}
	return 0;
}
EXPORT_SYMBOL(generic_write_checks);

ssize_t
generic_file_direct_write(struct kiocb *iocb, const struct iovec *iov,
		unsigned long *nr_segs, loff_t pos, loff_t *ppos,
		size_t count, size_t ocount)
{
	struct file	*file = iocb->ki_filp;
	struct address_space *mapping = file->f_mapping;
	struct inode	*inode = mapping->host;
	ssize_t		written;

	if (count != ocount)
		*nr_segs = iov_shorten((struct iovec *)iov, *nr_segs, count);

	written = generic_file_direct_IO(WRITE, iocb, iov, pos, *nr_segs);
	if (written > 0) {
		loff_t end = pos + written;
		if (end > i_size_read(inode) && !S_ISBLK(inode->i_mode)) {
			i_size_write(inode,  end);
			mark_inode_dirty(inode);
		}
		*ppos = end;
	}

	/*
	 * Sync the fs metadata but not the minor inode changes and
	 * of course not the data as we did direct DMA for the IO.
1897
	 * i_mutex is held, which protects generic_osync_inode() from
Linus Torvalds's avatar
Linus Torvalds committed
1898 1899
	 * livelocking.
	 */
1900 1901 1902 1903 1904
	if (written >= 0 && ((file->f_flags & O_SYNC) || IS_SYNC(inode))) {
		int err = generic_osync_inode(inode, mapping, OSYNC_METADATA);
		if (err < 0)
			written = err;
	}
Linus Torvalds's avatar
Linus Torvalds committed
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
	if (written == count && !is_sync_kiocb(iocb))
		written = -EIOCBQUEUED;
	return written;
}
EXPORT_SYMBOL(generic_file_direct_write);

ssize_t
generic_file_buffered_write(struct kiocb *iocb, const struct iovec *iov,
		unsigned long nr_segs, loff_t pos, loff_t *ppos,
		size_t count, ssize_t written)
{
	struct file *file = iocb->ki_filp;
	struct address_space * mapping = file->f_mapping;
	struct address_space_operations *a_ops = mapping->a_ops;
	struct inode 	*inode = mapping->host;
	long		status = 0;
	struct page	*page;
	struct page	*cached_page = NULL;
	size_t		bytes;
	struct pagevec	lru_pvec;
	const struct iovec *cur_iov = iov; /* current iovec */
	size_t		iov_base = 0;	   /* offset in the current iovec */
	char __user	*buf;

	pagevec_init(&lru_pvec, 0);

	/*
	 * handle partial DIO write.  Adjust cur_iov if needed.
	 */
	if (likely(nr_segs == 1))
		buf = iov->iov_base + written;
	else {
		filemap_set_next_iovec(&cur_iov, &iov_base, written);
1938
		buf = cur_iov->iov_base + iov_base;
Linus Torvalds's avatar
Linus Torvalds committed
1939 1940 1941 1942 1943
	}

	do {
		unsigned long index;
		unsigned long offset;
1944
		unsigned long maxlen;
Linus Torvalds's avatar
Linus Torvalds committed
1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958
		size_t copied;

		offset = (pos & (PAGE_CACHE_SIZE -1)); /* Within page */
		index = pos >> PAGE_CACHE_SHIFT;
		bytes = PAGE_CACHE_SIZE - offset;
		if (bytes > count)
			bytes = count;

		/*
		 * Bring in the user page that we will copy from _first_.
		 * Otherwise there's a nasty deadlock on copying from the
		 * same page as we're writing to, without it being marked
		 * up-to-date.
		 */
1959 1960 1961 1962
		maxlen = cur_iov->iov_len - iov_base;
		if (maxlen > bytes)
			maxlen = bytes;
		fault_in_pages_readable(buf, maxlen);
Linus Torvalds's avatar
Linus Torvalds committed
1963 1964 1965 1966 1967 1968 1969 1970 1971 1972

		page = __grab_cache_page(mapping,index,&cached_page,&lru_pvec);
		if (!page) {
			status = -ENOMEM;
			break;
		}

		status = a_ops->prepare_write(file, page, offset, offset+bytes);
		if (unlikely(status)) {
			loff_t isize = i_size_read(inode);
1973 1974 1975 1976 1977 1978

			if (status != AOP_TRUNCATED_PAGE)
				unlock_page(page);
			page_cache_release(page);
			if (status == AOP_TRUNCATED_PAGE)
				continue;
Linus Torvalds's avatar
Linus Torvalds committed
1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994
			/*
			 * prepare_write() may have instantiated a few blocks
			 * outside i_size.  Trim these off again.
			 */
			if (pos + bytes > isize)
				vmtruncate(inode, isize);
			break;
		}
		if (likely(nr_segs == 1))
			copied = filemap_copy_from_user(page, offset,
							buf, bytes);
		else
			copied = filemap_copy_from_user_iovec(page, offset,
						cur_iov, iov_base, bytes);
		flush_dcache_page(page);
		status = a_ops->commit_write(file, page, offset, offset+bytes);
1995 1996 1997 1998
		if (status == AOP_TRUNCATED_PAGE) {
			page_cache_release(page);
			continue;
		}
Linus Torvalds's avatar
Linus Torvalds committed
1999 2000 2001 2002 2003 2004 2005 2006 2007
		if (likely(copied > 0)) {
			if (!status)
				status = copied;

			if (status >= 0) {
				written += status;
				count -= status;
				pos += status;
				buf += status;
2008
				if (unlikely(nr_segs > 1)) {
Linus Torvalds's avatar
Linus Torvalds committed
2009 2010
					filemap_set_next_iovec(&cur_iov,
							&iov_base, status);
2011 2012 2013
					if (count)
						buf = cur_iov->iov_base +
							iov_base;
2014 2015
				} else {
					iov_base += status;
2016
				}
Linus Torvalds's avatar
Linus Torvalds committed
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
			}
		}
		if (unlikely(copied != bytes))
			if (status >= 0)
				status = -EFAULT;
		unlock_page(page);
		mark_page_accessed(page);
		page_cache_release(page);
		if (status < 0)
			break;
		balance_dirty_pages_ratelimited(mapping);
		cond_resched();
	} while (count);
	*ppos = pos;

	if (cached_page)
		page_cache_release(cached_page);

	/*
	 * For now, when the user asks for O_SYNC, we'll actually give O_DSYNC
	 */
	if (likely(status >= 0)) {
		if (unlikely((file->f_flags & O_SYNC) || IS_SYNC(inode))) {
			if (!a_ops->writepage || !is_sync_kiocb(iocb))
				status = generic_osync_inode(inode, mapping,
						OSYNC_METADATA|OSYNC_DATA);
		}
  	}
	
	/*
	 * If we get here for O_DIRECT writes then we must have fallen through
	 * to buffered writes (block instantiation inside i_size).  So we sync
	 * the file data here, to try to honour O_DIRECT expectations.
	 */
	if (unlikely(file->f_flags & O_DIRECT) && written)
		status = filemap_write_and_wait(mapping);

	pagevec_lru_add(&lru_pvec);
	return written ? written : status;
}
EXPORT_SYMBOL(generic_file_buffered_write);

2059
static ssize_t
Linus Torvalds's avatar
Linus Torvalds committed
2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112
__generic_file_aio_write_nolock(struct kiocb *iocb, const struct iovec *iov,
				unsigned long nr_segs, loff_t *ppos)
{
	struct file *file = iocb->ki_filp;
	struct address_space * mapping = file->f_mapping;
	size_t ocount;		/* original count */
	size_t count;		/* after file limit checks */
	struct inode 	*inode = mapping->host;
	unsigned long	seg;
	loff_t		pos;
	ssize_t		written;
	ssize_t		err;

	ocount = 0;
	for (seg = 0; seg < nr_segs; seg++) {
		const struct iovec *iv = &iov[seg];

		/*
		 * If any segment has a negative length, or the cumulative
		 * length ever wraps negative then return -EINVAL.
		 */
		ocount += iv->iov_len;
		if (unlikely((ssize_t)(ocount|iv->iov_len) < 0))
			return -EINVAL;
		if (access_ok(VERIFY_READ, iv->iov_base, iv->iov_len))
			continue;
		if (seg == 0)
			return -EFAULT;
		nr_segs = seg;
		ocount -= iv->iov_len;	/* This segment is no good */
		break;
	}

	count = ocount;
	pos = *ppos;

	vfs_check_frozen(inode->i_sb, SB_FREEZE_WRITE);

	/* We can write back this queue in page reclaim */
	current->backing_dev_info = mapping->backing_dev_info;
	written = 0;

	err = generic_write_checks(file, &pos, &count, S_ISBLK(inode->i_mode));
	if (err)
		goto out;

	if (count == 0)
		goto out;

	err = remove_suid(file->f_dentry);
	if (err)
		goto out;

2113
	file_update_time(file);
Linus Torvalds's avatar
Linus Torvalds committed
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

	/* coalesce the iovecs and go direct-to-BIO for O_DIRECT */
	if (unlikely(file->f_flags & O_DIRECT)) {
		written = generic_file_direct_write(iocb, iov,
				&nr_segs, pos, ppos, count, ocount);
		if (written < 0 || written == count)
			goto out;
		/*
		 * direct-io write to a hole: fall through to buffered I/O
		 * for completing the rest of the request.
		 */
		pos += written;
		count -= written;
	}

	written = generic_file_buffered_write(iocb, iov, nr_segs,
			pos, ppos, count, written);
out:
	current->backing_dev_info = NULL;
	return written ? written : err;
}
EXPORT_SYMBOL(generic_file_aio_write_nolock);

ssize_t
generic_file_aio_write_nolock(struct kiocb *iocb, const struct iovec *iov,
				unsigned long nr_segs, loff_t *ppos)
{
	struct file *file = iocb->ki_filp;
	struct address_space *mapping = file->f_mapping;
	struct inode *inode = mapping->host;
	ssize_t ret;
	loff_t pos = *ppos;

	ret = __generic_file_aio_write_nolock(iocb, iov, nr_segs, ppos);

	if (ret > 0 && ((file->f_flags & O_SYNC) || IS_SYNC(inode))) {
		int err;

		err = sync_page_range_nolock(inode, mapping, pos, ret);
		if (err < 0)
			ret = err;
	}
	return ret;
}

2159
static ssize_t
Linus Torvalds's avatar
Linus Torvalds committed
2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199
__generic_file_write_nolock(struct file *file, const struct iovec *iov,
				unsigned long nr_segs, loff_t *ppos)
{
	struct kiocb kiocb;
	ssize_t ret;

	init_sync_kiocb(&kiocb, file);
	ret = __generic_file_aio_write_nolock(&kiocb, iov, nr_segs, ppos);
	if (ret == -EIOCBQUEUED)
		ret = wait_on_sync_kiocb(&kiocb);
	return ret;
}

ssize_t
generic_file_write_nolock(struct file *file, const struct iovec *iov,
				unsigned long nr_segs, loff_t *ppos)
{
	struct kiocb kiocb;
	ssize_t ret;

	init_sync_kiocb(&kiocb, file);
	ret = generic_file_aio_write_nolock(&kiocb, iov, nr_segs, ppos);
	if (-EIOCBQUEUED == ret)
		ret = wait_on_sync_kiocb(&kiocb);
	return ret;
}
EXPORT_SYMBOL(generic_file_write_nolock);

ssize_t generic_file_aio_write(struct kiocb *iocb, const char __user *buf,
			       size_t count, loff_t pos)
{
	struct file *file = iocb->ki_filp;
	struct address_space *mapping = file->f_mapping;
	struct inode *inode = mapping->host;
	ssize_t ret;
	struct iovec local_iov = { .iov_base = (void __user *)buf,
					.iov_len = count };

	BUG_ON(iocb->ki_pos != pos);

2200
	mutex_lock(&inode->i_mutex);
Linus Torvalds's avatar
Linus Torvalds committed
2201 2202
	ret = __generic_file_aio_write_nolock(iocb, &local_iov, 1,
						&iocb->ki_pos);
2203
	mutex_unlock(&inode->i_mutex);
Linus Torvalds's avatar
Linus Torvalds committed
2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224

	if (ret > 0 && ((file->f_flags & O_SYNC) || IS_SYNC(inode))) {
		ssize_t err;

		err = sync_page_range(inode, mapping, pos, ret);
		if (err < 0)
			ret = err;
	}
	return ret;
}
EXPORT_SYMBOL(generic_file_aio_write);

ssize_t generic_file_write(struct file *file, const char __user *buf,
			   size_t count, loff_t *ppos)
{
	struct address_space *mapping = file->f_mapping;
	struct inode *inode = mapping->host;
	ssize_t	ret;
	struct iovec local_iov = { .iov_base = (void __user *)buf,
					.iov_len = count };

2225
	mutex_lock(&inode->i_mutex);
Linus Torvalds's avatar
Linus Torvalds committed
2226
	ret = __generic_file_write_nolock(file, &local_iov, 1, ppos);
2227
	mutex_unlock(&inode->i_mutex);
Linus Torvalds's avatar
Linus Torvalds committed
2228 2229 2230 2231 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

	if (ret > 0 && ((file->f_flags & O_SYNC) || IS_SYNC(inode))) {
		ssize_t err;

		err = sync_page_range(inode, mapping, *ppos - ret, ret);
		if (err < 0)
			ret = err;
	}
	return ret;
}
EXPORT_SYMBOL(generic_file_write);

ssize_t generic_file_readv(struct file *filp, const struct iovec *iov,
			unsigned long nr_segs, loff_t *ppos)
{
	struct kiocb kiocb;
	ssize_t ret;

	init_sync_kiocb(&kiocb, filp);
	ret = __generic_file_aio_read(&kiocb, iov, nr_segs, ppos);
	if (-EIOCBQUEUED == ret)
		ret = wait_on_sync_kiocb(&kiocb);
	return ret;
}
EXPORT_SYMBOL(generic_file_readv);

ssize_t generic_file_writev(struct file *file, const struct iovec *iov,
			unsigned long nr_segs, loff_t *ppos)
{
	struct address_space *mapping = file->f_mapping;
	struct inode *inode = mapping->host;
	ssize_t ret;

2261
	mutex_lock(&inode->i_mutex);
Linus Torvalds's avatar
Linus Torvalds committed
2262
	ret = __generic_file_write_nolock(file, iov, nr_segs, ppos);
2263
	mutex_unlock(&inode->i_mutex);
Linus Torvalds's avatar
Linus Torvalds committed
2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276

	if (ret > 0 && ((file->f_flags & O_SYNC) || IS_SYNC(inode))) {
		int err;

		err = sync_page_range(inode, mapping, *ppos - ret, ret);
		if (err < 0)
			ret = err;
	}
	return ret;
}
EXPORT_SYMBOL(generic_file_writev);

/*
2277
 * Called under i_mutex for writes to S_ISREG files.   Returns -EIO if something
Linus Torvalds's avatar
Linus Torvalds committed
2278 2279
 * went wrong during pagecache shootdown.
 */
2280
static ssize_t
Linus Torvalds's avatar
Linus Torvalds committed
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
generic_file_direct_IO(int rw, struct kiocb *iocb, const struct iovec *iov,
	loff_t offset, unsigned long nr_segs)
{
	struct file *file = iocb->ki_filp;
	struct address_space *mapping = file->f_mapping;
	ssize_t retval;
	size_t write_len = 0;

	/*
	 * If it's a write, unmap all mmappings of the file up-front.  This
	 * will cause any pte dirty bits to be propagated into the pageframes
	 * for the subsequent filemap_write_and_wait().
	 */
	if (rw == WRITE) {
		write_len = iov_length(iov, nr_segs);
	       	if (mapping_mapped(mapping))
			unmap_mapping_range(mapping, offset, write_len, 0);
	}

	retval = filemap_write_and_wait(mapping);
	if (retval == 0) {
		retval = mapping->a_ops->direct_IO(rw, iocb, iov,
						offset, nr_segs);
		if (rw == WRITE && mapping->nrpages) {
			pgoff_t end = (offset + write_len - 1)
						>> PAGE_CACHE_SHIFT;
			int err = invalidate_inode_pages2_range(mapping,
					offset >> PAGE_CACHE_SHIFT, end);
			if (err)
				retval = err;
		}
	}
	return retval;
}