filemap.c 63.8 KB
Newer Older
L
Linus Torvalds 已提交
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15
/*
 *	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/module.h>
#include <linux/slab.h>
#include <linux/compiler.h>
#include <linux/fs.h>
16
#include <linux/uaccess.h>
L
Linus Torvalds 已提交
17
#include <linux/aio.h>
18
#include <linux/capability.h>
L
Linus Torvalds 已提交
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 <linux/cpuset.h>
33
#include "filemap.h"
34 35
#include "internal.h"

L
Linus Torvalds 已提交
36 37 38 39 40 41 42
/*
 * FIXME: remove all knowledge of the buffer layer from the core VM
 */
#include <linux/buffer_head.h> /* for generic_osync_inode */

#include <asm/mman.h>

43 44 45 46
static ssize_t
generic_file_direct_IO(int rw, struct kiocb *iocb, const struct iovec *iov,
	loff_t offset, unsigned long nr_segs);

L
Linus Torvalds 已提交
47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63
/*
 * 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)
64 65
 *      ->swap_lock		(exclusive_swap_page, others)
 *        ->mapping->tree_lock
L
Linus Torvalds 已提交
66
 *
67
 *  ->i_mutex
L
Linus Torvalds 已提交
68 69 70 71
 *    ->i_mmap_lock		(truncate->unmap_mapping_range)
 *
 *  ->mmap_sem
 *    ->i_mmap_lock
72
 *      ->page_table_lock or pte_lock	(various, mainly in memory.c)
L
Linus Torvalds 已提交
73 74 75 76 77
 *        ->mapping->tree_lock	(arch-dependent flush_dcache_mmap_lock)
 *
 *  ->mmap_sem
 *    ->lock_page		(access_process_vm)
 *
78 79
 *  ->i_mutex			(generic_file_buffered_write)
 *    ->mmap_sem		(fault_in_pages_readable->do_page_fault)
L
Linus Torvalds 已提交
80
 *
81
 *  ->i_mutex
L
Linus Torvalds 已提交
82 83 84 85 86 87 88 89 90 91
 *    ->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
92
 *    ->page_table_lock or pte_lock	(anon_vma_prepare and various)
L
Linus Torvalds 已提交
93
 *
94
 *  ->page_table_lock or pte_lock
95
 *    ->swap_lock		(try_to_unmap_one)
L
Linus Torvalds 已提交
96 97 98
 *    ->private_lock		(try_to_unmap_one)
 *    ->tree_lock		(try_to_unmap_one)
 *    ->zone.lru_lock		(follow_page->mark_page_accessed)
99
 *    ->zone.lru_lock		(check_pte_range->isolate_lru_page)
L
Linus Torvalds 已提交
100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121
 *    ->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--;
122
	__dec_zone_page_state(page, NR_FILE_PAGES);
L
Linus Torvalds 已提交
123 124 125 126 127 128
}

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

M
Matt Mackall 已提交
129
	BUG_ON(!PageLocked(page));
L
Linus Torvalds 已提交
130 131 132 133 134 135 136 137 138 139 140

	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;

141
	page = container_of((unsigned long *)word, struct page, flags);
L
Linus Torvalds 已提交
142 143

	/*
144 145 146 147 148 149 150 151 152 153 154 155 156 157 158
	 * 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
H
Hugh Dickins 已提交
159
	 * ignore it for all cases but swap, where only page_private(page) is
160 161 162
	 * of interest. When page_mapping() does go NULL, the entire
	 * call stack gracefully ignores the page and returns.
	 * -- wli
L
Linus Torvalds 已提交
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;
}

/**
173
 * __filemap_fdatawrite_range - start writeback on mapping dirty pages in range
174 175
 * @mapping:	address space structure to write
 * @start:	offset in bytes where the range starts
176
 * @end:	offset in bytes where the range ends (inclusive)
177
 * @sync_mode:	enable synchronous operation
L
Linus Torvalds 已提交
178
 *
179 180 181
 * Start writeback against all of a mapping's dirty pages that lie
 * within the byte offsets <start, end> inclusive.
 *
L
Linus Torvalds 已提交
182
 * If sync_mode is WB_SYNC_ALL then this is a "data integrity" operation, as
183
 * opposed to a regular memory cleansing writeback.  The difference between
L
Linus Torvalds 已提交
184 185 186
 * these two operations is that if a dirty page/buffer is encountered, it must
 * be waited upon, and not just skipped over.
 */
187 188
int __filemap_fdatawrite_range(struct address_space *mapping, loff_t start,
				loff_t end, int sync_mode)
L
Linus Torvalds 已提交
189 190 191 192 193
{
	int ret;
	struct writeback_control wbc = {
		.sync_mode = sync_mode,
		.nr_to_write = mapping->nrpages * 2,
194 195
		.range_start = start,
		.range_end = end,
L
Linus Torvalds 已提交
196 197 198 199 200 201 202 203 204 205 206 207
	};

	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)
{
208
	return __filemap_fdatawrite_range(mapping, 0, LLONG_MAX, sync_mode);
L
Linus Torvalds 已提交
209 210 211 212 213 214 215 216
}

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

217 218
static int filemap_fdatawrite_range(struct address_space *mapping, loff_t start,
				loff_t end)
L
Linus Torvalds 已提交
219 220 221 222
{
	return __filemap_fdatawrite_range(mapping, start, end, WB_SYNC_ALL);
}

223 224 225 226
/**
 * filemap_flush - mostly a non-blocking flush
 * @mapping:	target address_space
 *
L
Linus Torvalds 已提交
227 228 229 230 231 232 233 234 235
 * 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);

236 237 238 239 240 241
/**
 * wait_on_page_writeback_range - wait for writeback to complete
 * @mapping:	target address_space
 * @start:	beginning page index
 * @end:	ending page index
 *
L
Linus Torvalds 已提交
242 243 244
 * Wait for writeback to complete against pages indexed by start->end
 * inclusive
 */
245
int wait_on_page_writeback_range(struct address_space *mapping,
L
Linus Torvalds 已提交
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
				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;
}

288 289 290 291 292 293 294
/**
 * sync_page_range - write and wait on all pages in the passed range
 * @inode:	target inode
 * @mapping:	target address_space
 * @pos:	beginning offset in pages to write
 * @count:	number of bytes to write
 *
L
Linus Torvalds 已提交
295 296 297 298
 * 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.
 *
299
 * We need to re-take i_mutex during the generic_osync_inode list walk because
L
Linus Torvalds 已提交
300 301 302
 * it is otherwise livelockable.
 */
int sync_page_range(struct inode *inode, struct address_space *mapping,
303
			loff_t pos, loff_t count)
L
Linus Torvalds 已提交
304 305 306 307 308 309 310 311 312
{
	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) {
313
		mutex_lock(&inode->i_mutex);
L
Linus Torvalds 已提交
314
		ret = generic_osync_inode(inode, mapping, OSYNC_METADATA);
315
		mutex_unlock(&inode->i_mutex);
L
Linus Torvalds 已提交
316 317 318 319 320 321 322
	}
	if (ret == 0)
		ret = wait_on_page_writeback_range(mapping, start, end);
	return ret;
}
EXPORT_SYMBOL(sync_page_range);

323 324 325 326 327 328 329
/**
 * sync_page_range_nolock
 * @inode:	target inode
 * @mapping:	target address_space
 * @pos:	beginning offset in pages to write
 * @count:	number of bytes to write
 *
330
 * Note: Holding i_mutex across sync_page_range_nolock() is not a good idea
L
Linus Torvalds 已提交
331 332 333
 * as it forces O_SYNC writers to different parts of the same file
 * to be serialised right until io completion.
 */
334 335
int sync_page_range_nolock(struct inode *inode, struct address_space *mapping,
			   loff_t pos, loff_t count)
L
Linus Torvalds 已提交
336 337 338 339 340 341 342 343 344 345 346 347 348 349
{
	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;
}
350
EXPORT_SYMBOL(sync_page_range_nolock);
L
Linus Torvalds 已提交
351 352

/**
353
 * filemap_fdatawait - wait for all under-writeback pages to complete
L
Linus Torvalds 已提交
354
 * @mapping: address space structure to wait for
355 356 357
 *
 * Walk the list of under-writeback pages of the given address space
 * and wait for all of them.
L
Linus Torvalds 已提交
358 359 360 361 362 363 364 365 366 367 368 369 370 371 372
 */
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)
{
373
	int err = 0;
L
Linus Torvalds 已提交
374 375

	if (mapping->nrpages) {
376 377 378 379 380 381 382 383 384 385 386 387
		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;
		}
L
Linus Torvalds 已提交
388
	}
389
	return err;
L
Linus Torvalds 已提交
390
}
391
EXPORT_SYMBOL(filemap_write_and_wait);
L
Linus Torvalds 已提交
392

393 394 395 396 397 398
/**
 * filemap_write_and_wait_range - write out & wait on a file range
 * @mapping:	the address_space for the pages
 * @lstart:	offset in bytes where the range starts
 * @lend:	offset in bytes where the range ends (inclusive)
 *
399 400 401 402 403
 * Write out and wait upon file offsets lstart->lend, inclusive.
 *
 * Note that `lend' is inclusive (describes the last byte to be written) so
 * that this function can be used to write to the very end-of-file (end = -1).
 */
L
Linus Torvalds 已提交
404 405 406
int filemap_write_and_wait_range(struct address_space *mapping,
				 loff_t lstart, loff_t lend)
{
407
	int err = 0;
L
Linus Torvalds 已提交
408 409

	if (mapping->nrpages) {
410 411 412 413 414 415 416 417 418 419
		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;
		}
L
Linus Torvalds 已提交
420
	}
421
	return err;
L
Linus Torvalds 已提交
422 423
}

424 425 426 427 428 429 430 431
/**
 * add_to_page_cache - add newly allocated pagecache pages
 * @page:	page to add
 * @mapping:	the page's address_space
 * @offset:	page index
 * @gfp_mask:	page allocation mode
 *
 * This function is used to add newly allocated pagecache pages;
L
Linus Torvalds 已提交
432 433 434 435 436 437
 * 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,
A
Al Viro 已提交
438
		pgoff_t offset, gfp_t gfp_mask)
L
Linus Torvalds 已提交
439 440 441 442 443 444 445 446 447 448 449 450
{
	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++;
451
			__inc_zone_page_state(page, NR_FILE_PAGES);
L
Linus Torvalds 已提交
452 453 454 455 456 457 458 459 460
		}
		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,
A
Al Viro 已提交
461
				pgoff_t offset, gfp_t gfp_mask)
L
Linus Torvalds 已提交
462 463 464 465 466 467 468
{
	int ret = add_to_page_cache(page, mapping, offset, gfp_mask);
	if (ret == 0)
		lru_cache_add(page);
	return ret;
}

469
#ifdef CONFIG_NUMA
470
struct page *__page_cache_alloc(gfp_t gfp)
471 472 473
{
	if (cpuset_do_page_mem_spread()) {
		int n = cpuset_mem_spread_node();
474
		return alloc_pages_node(n, gfp, 0);
475
	}
476
	return alloc_pages(gfp, 0);
477
}
478
EXPORT_SYMBOL(__page_cache_alloc);
479 480
#endif

481 482 483 484 485 486
static int __sleep_on_page_lock(void *word)
{
	io_schedule();
	return 0;
}

L
Linus Torvalds 已提交
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
/*
 * 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);

/**
520
 * unlock_page - unlock a locked page
L
Linus Torvalds 已提交
521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542
 * @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);

543 544 545
/**
 * end_page_writeback - end writeback against a page
 * @page: the page
L
Linus Torvalds 已提交
546 547 548 549 550 551 552 553 554 555 556 557
 */
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);

558 559 560
/**
 * __lock_page - get a lock on the page, assuming we need to sleep to get it
 * @page: the page to lock
L
Linus Torvalds 已提交
561
 *
562
 * Ugly. Running sync_page() in state TASK_UNINTERRUPTIBLE is scary.  If some
L
Linus Torvalds 已提交
563 564 565 566 567 568 569 570 571 572 573 574 575
 * 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);

576 577 578 579 580 581 582 583 584 585 586
/*
 * Variant of lock_page that does not require the caller to hold a reference
 * on the page's mapping.
 */
void fastcall __lock_page_nosync(struct page *page)
{
	DEFINE_WAIT_BIT(wait, &page->flags, PG_locked);
	__wait_on_bit_lock(page_waitqueue(page), &wait, __sleep_on_page_lock,
							TASK_UNINTERRUPTIBLE);
}

587 588 589 590 591
/**
 * find_get_page - find and get a page reference
 * @mapping: the address_space to search
 * @offset: the page index
 *
N
Nick Piggin 已提交
592 593
 * Is there a pagecache struct page at the given (mapping, offset) tuple?
 * If yes, increment its refcount and return it; if no, return NULL.
L
Linus Torvalds 已提交
594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609
 */
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);

/**
 * find_lock_page - locate, pin and lock a pagecache page
610 611
 * @mapping: the address_space to search
 * @offset: the page index
L
Linus Torvalds 已提交
612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629
 *
 * 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);
630
			__lock_page(page);
L
Linus Torvalds 已提交
631 632 633
			read_lock_irq(&mapping->tree_lock);

			/* Has the page been truncated while we slept? */
634 635
			if (unlikely(page->mapping != mapping ||
				     page->index != offset)) {
L
Linus Torvalds 已提交
636 637 638 639 640 641 642 643 644 645 646 647 648
				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
649 650 651
 * @mapping: the page's address_space
 * @index: the page's index into the mapping
 * @gfp_mask: page allocation mode
L
Linus Torvalds 已提交
652 653 654 655 656 657 658 659 660 661 662 663 664
 *
 * 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,
A
Al Viro 已提交
665
		unsigned long index, gfp_t gfp_mask)
L
Linus Torvalds 已提交
666 667 668 669 670 671 672
{
	struct page *page, *cached_page = NULL;
	int err;
repeat:
	page = find_lock_page(mapping, index);
	if (!page) {
		if (!cached_page) {
673 674
			cached_page =
				__page_cache_alloc(gfp_mask);
L
Linus Torvalds 已提交
675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722
			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;
}

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
/**
 * find_get_pages_contig - gang contiguous pagecache lookup
 * @mapping:	The address_space to search
 * @index:	The starting page index
 * @nr_pages:	The maximum number of pages
 * @pages:	Where the resulting pages are placed
 *
 * find_get_pages_contig() works exactly like find_get_pages(), except
 * that the returned number of pages are guaranteed to be contiguous.
 *
 * find_get_pages_contig() returns the number of pages which were found.
 */
unsigned find_get_pages_contig(struct address_space *mapping, pgoff_t index,
			       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, index, nr_pages);
	for (i = 0; i < ret; i++) {
		if (pages[i]->mapping == NULL || pages[i]->index != index)
			break;

		page_cache_get(pages[i]);
		index++;
	}
	read_unlock_irq(&mapping->tree_lock);
	return i;
}
754
EXPORT_SYMBOL(find_get_pages_contig);
755

756 757 758 759 760 761 762 763
/**
 * find_get_pages_tag - find and return pages that match @tag
 * @mapping:	the address_space to search
 * @index:	the starting page index
 * @tag:	the tag index
 * @nr_pages:	the maximum number of pages
 * @pages:	where the resulting pages are placed
 *
L
Linus Torvalds 已提交
764
 * Like find_get_pages, except we only return pages which are tagged with
765
 * @tag.   We update @index to index the next page for the traversal.
L
Linus Torvalds 已提交
766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782
 */
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;
}
783
EXPORT_SYMBOL(find_get_pages_tag);
L
Linus Torvalds 已提交
784

785 786 787 788 789
/**
 * grab_cache_page_nowait - returns locked page at given index in given cache
 * @mapping: target address_space
 * @index: the page index
 *
790
 * Same as grab_cache_page(), but do not wait if the page is unavailable.
L
Linus Torvalds 已提交
791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808
 * 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);

	if (page) {
		if (!TestSetPageLocked(page))
			return page;
		page_cache_release(page);
		return NULL;
	}
809 810
	page = __page_cache_alloc(mapping_gfp_mask(mapping) & ~__GFP_FS);
	if (page && add_to_page_cache_lru(page, mapping, index, GFP_KERNEL)) {
L
Linus Torvalds 已提交
811 812 813 814 815 816 817
		page_cache_release(page);
		page = NULL;
	}
	return page;
}
EXPORT_SYMBOL(grab_cache_page_nowait);

818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841
/*
 * CD/DVDs are error prone. When a medium error occurs, the driver may fail
 * a _large_ part of the i/o request. Imagine the worst scenario:
 *
 *      ---R__________________________________________B__________
 *         ^ reading here                             ^ bad block(assume 4k)
 *
 * read(R) => miss => readahead(R...B) => media error => frustrating retries
 * => failing the whole request => read(R) => read(R+1) =>
 * readahead(R+1...B+1) => bang => read(R+2) => read(R+3) =>
 * readahead(R+3...B+2) => bang => read(R+3) => read(R+4) =>
 * readahead(R+4...B+3) => bang => read(R+4) => read(R+5) => ......
 *
 * It is going insane. Fix it by quickly scaling down the readahead size.
 */
static void shrink_readahead_size_eio(struct file *filp,
					struct file_ra_state *ra)
{
	if (!ra->ra_pages)
		return;

	ra->ra_pages /= 4;
}

842 843 844 845 846 847 848 849 850
/**
 * do_generic_mapping_read - generic file read routine
 * @mapping:	address_space to be read
 * @_ra:	file's readahead state
 * @filp:	the file to read
 * @ppos:	current file position
 * @desc:	read_descriptor
 * @actor:	read method
 *
L
Linus Torvalds 已提交
851
 * This is a generic file read routine, and uses the
852
 * mapping->a_ops->readpage() function for the actual low-level stuff.
L
Linus Torvalds 已提交
853 854 855 856
 *
 * This is really ugly. But the goto's actually try to clarify some
 * of the logic when it comes to error handling etc.
 *
857 858
 * Note the struct file* is only passed for the use of readpage.
 * It may be NULL.
L
Linus Torvalds 已提交
859 860 861 862 863 864 865 866 867 868 869 870 871 872 873
 */
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;
874
	unsigned int prev_offset;
L
Linus Torvalds 已提交
875 876 877 878 879 880 881 882
	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;
J
Jan Kara 已提交
883 884
	prev_index = ra.prev_index;
	prev_offset = ra.prev_offset;
L
Linus Torvalds 已提交
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
	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);

		/*
932 933
		 * When a sequential read accesses a page several times,
		 * only mark it as accessed the first time.
L
Linus Torvalds 已提交
934
		 */
935
		if (prev_index != index || offset != prev_offset)
L
Linus Torvalds 已提交
936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952
			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;
J
Jan Kara 已提交
953 954
		prev_offset = offset;
		ra.prev_offset = offset;
L
Linus Torvalds 已提交
955 956 957 958 959 960 961 962 963 964

		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);

N
Nick Piggin 已提交
965
		/* Did it get truncated before we got the lock? */
L
Linus Torvalds 已提交
966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981
		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);

982 983 984 985 986
		if (unlikely(error)) {
			if (error == AOP_TRUNCATED_PAGE) {
				page_cache_release(page);
				goto find_page;
			}
L
Linus Torvalds 已提交
987
			goto readpage_error;
988
		}
L
Linus Torvalds 已提交
989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002

		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;
1003
				shrink_readahead_size_eio(filp, &ra);
L
Linus Torvalds 已提交
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 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115
				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;
}

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
/*
 * Performs necessary checks before doing a write
 * @iov:	io vector request
 * @nr_segs:	number of segments in the iovec
 * @count:	number of bytes to write
 * @access_flags: type of access: %VERIFY_READ or %VERIFY_WRITE
 *
 * Adjust number of segments and amount of bytes to write (nr_segs should be
 * properly initialized first). Returns appropriate error code that caller
 * should return or zero in case that write should be allowed.
 */
int generic_segment_checks(const struct iovec *iov,
			unsigned long *nr_segs, size_t *count, int access_flags)
{
	unsigned long   seg;
	size_t cnt = 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.
		 */
		cnt += iv->iov_len;
		if (unlikely((ssize_t)(cnt|iv->iov_len) < 0))
			return -EINVAL;
		if (access_ok(access_flags, iv->iov_base, iv->iov_len))
			continue;
		if (seg == 0)
			return -EFAULT;
		*nr_segs = seg;
		cnt -= iv->iov_len;	/* This segment is no good */
		break;
	}
	*count = cnt;
	return 0;
}
EXPORT_SYMBOL(generic_segment_checks);

1155
/**
H
Henrik Kretzschmar 已提交
1156
 * generic_file_aio_read - generic filesystem read routine
1157 1158 1159
 * @iocb:	kernel I/O control block
 * @iov:	io vector request
 * @nr_segs:	number of segments in the iovec
H
Henrik Kretzschmar 已提交
1160
 * @pos:	current file position
1161
 *
L
Linus Torvalds 已提交
1162 1163 1164 1165
 * This is the "read()" routine for all filesystems
 * that can use the page cache directly.
 */
ssize_t
1166 1167
generic_file_aio_read(struct kiocb *iocb, const struct iovec *iov,
		unsigned long nr_segs, loff_t pos)
L
Linus Torvalds 已提交
1168 1169 1170 1171 1172
{
	struct file *filp = iocb->ki_filp;
	ssize_t retval;
	unsigned long seg;
	size_t count;
1173
	loff_t *ppos = &iocb->ki_pos;
L
Linus Torvalds 已提交
1174 1175

	count = 0;
1176 1177 1178
	retval = generic_segment_checks(iov, &nr_segs, &count, VERIFY_WRITE);
	if (retval)
		return retval;
L
Linus Torvalds 已提交
1179 1180 1181

	/* coalesce the iovecs and go direct-to-BIO for O_DIRECT */
	if (filp->f_flags & O_DIRECT) {
1182
		loff_t size;
L
Linus Torvalds 已提交
1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197
		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);
			if (retval > 0)
				*ppos = pos + retval;
		}
1198
		if (likely(retval != 0)) {
1199
			file_accessed(filp);
S
Steven Whitehouse 已提交
1200
			goto out;
1201
		}
L
Linus Torvalds 已提交
1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216
	}

	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;
1217 1218
			if (desc.error) {
				retval = retval ?: desc.error;
L
Linus Torvalds 已提交
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
				break;
			}
		}
	}
out:
	return retval;
}
EXPORT_SYMBOL(generic_file_aio_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;
}

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
1281 1282 1283 1284 1285 1286
static int FASTCALL(page_cache_read(struct file * file, unsigned long offset));
/**
 * page_cache_read - adds requested page to the page cache if not already there
 * @file:	file to read
 * @offset:	page index
 *
L
Linus Torvalds 已提交
1287 1288 1289 1290 1291 1292 1293
 * 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)
{
	struct address_space *mapping = file->f_mapping;
	struct page *page; 
1294
	int ret;
L
Linus Torvalds 已提交
1295

1296 1297 1298 1299 1300 1301 1302 1303 1304 1305
	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 */
L
Linus Torvalds 已提交
1306 1307 1308

		page_cache_release(page);

1309 1310 1311
	} while (ret == AOP_TRUNCATED_PAGE);
		
	return ret;
L
Linus Torvalds 已提交
1312 1313 1314 1315
}

#define MMAP_LOTSAMISS  (100)

1316 1317 1318 1319 1320 1321
/**
 * filemap_nopage - read in file data for page fault handling
 * @area:	the applicable vm_area
 * @address:	target address to read in
 * @type:	returned with VM_FAULT_{MINOR,MAJOR} if not %NULL
 *
L
Linus Torvalds 已提交
1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387
 * 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;
1388
			count_vm_event(PGMAJFAULT);
L
Linus Torvalds 已提交
1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428
		}
		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)
1429
		return NOPAGE_SIGBUS;
L
Linus Torvalds 已提交
1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452
	/* 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);

	/*
	 * 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;
1453
	return NOPAGE_SIGBUS;
L
Linus Torvalds 已提交
1454 1455 1456 1457

page_not_uptodate:
	if (!did_readaround) {
		majmin = VM_FAULT_MAJOR;
1458
		count_vm_event(PGMAJFAULT);
L
Linus Torvalds 已提交
1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481
	}

	/*
	 * 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);
1482 1483
	error = mapping->a_ops->readpage(file, page);
	if (!error) {
L
Linus Torvalds 已提交
1484 1485 1486
		wait_on_page_locked(page);
		if (PageUptodate(page))
			goto success;
1487 1488 1489
	} else if (error == AOP_TRUNCATED_PAGE) {
		page_cache_release(page);
		goto retry_find;
L
Linus Torvalds 已提交
1490 1491 1492 1493 1494 1495
	}

	/*
	 * Things didn't work out. Return zero to tell the
	 * mm layer so, possibly freeing the page cache page first.
	 */
1496
	shrink_readahead_size_eio(file, ra);
L
Linus Torvalds 已提交
1497
	page_cache_release(page);
1498
	return NOPAGE_SIGBUS;
L
Linus Torvalds 已提交
1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523
}
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.
	 */
1524 1525 1526 1527 1528
	if (!PageUptodate(page)) {
		if (nonblock) {
			page_cache_release(page);
			return NULL;
		}
L
Linus Torvalds 已提交
1529
		goto page_not_uptodate;
1530
	}
L
Linus Torvalds 已提交
1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559

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);

N
Nick Piggin 已提交
1560
	/* Did it get truncated while we waited for it? */
L
Linus Torvalds 已提交
1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571
	if (!page->mapping) {
		unlock_page(page);
		goto err;
	}

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

1572 1573
	error = mapping->a_ops->readpage(file, page);
	if (!error) {
L
Linus Torvalds 已提交
1574 1575 1576
		wait_on_page_locked(page);
		if (PageUptodate(page))
			goto success;
1577 1578 1579
	} else if (error == AOP_TRUNCATED_PAGE) {
		page_cache_release(page);
		goto retry_find;
L
Linus Torvalds 已提交
1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601
	}

	/*
	 * 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);
1602 1603
	error = mapping->a_ops->readpage(file, page);
	if (!error) {
L
Linus Torvalds 已提交
1604 1605 1606
		wait_on_page_locked(page);
		if (PageUptodate(page))
			goto success;
1607 1608 1609
	} else if (error == AOP_TRUNCATED_PAGE) {
		page_cache_release(page);
		goto retry_find;
L
Linus Torvalds 已提交
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
	}

	/*
	 * 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);
1644 1645 1646

	/* XXX: This is wrong, a filesystem I/O error may have happened. Fix that as
	 * done in shmem_populate calling shmem_getpage */
L
Linus Torvalds 已提交
1647 1648
	if (!page && !nonblock)
		return -ENOMEM;
1649

L
Linus Torvalds 已提交
1650 1651 1652 1653 1654 1655
	if (page) {
		err = install_page(mm, vma, addr, page, prot);
		if (err) {
			page_cache_release(page);
			return err;
		}
1656
	} else if (vma->vm_flags & VM_NONLINEAR) {
1657 1658 1659
		/* 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. */
L
Linus Torvalds 已提交
1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672
		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;
}
1673
EXPORT_SYMBOL(filemap_populate);
L
Linus Torvalds 已提交
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

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);

1716
static struct page *__read_cache_page(struct address_space *mapping,
L
Linus Torvalds 已提交
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
				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;
}

1753 1754 1755
/*
 * Same as read_cache_page, but don't wait for page to become unlocked
 * after submitting it to the filler.
L
Linus Torvalds 已提交
1756
 */
1757
struct page *read_cache_page_async(struct address_space *mapping,
L
Linus Torvalds 已提交
1758 1759 1760 1761 1762 1763 1764 1765 1766 1767
				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))
1768
		return page;
L
Linus Torvalds 已提交
1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784
	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);
1785
		return ERR_PTR(err);
L
Linus Torvalds 已提交
1786
	}
1787
out:
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
	mark_page_accessed(page);
	return page;
}
EXPORT_SYMBOL(read_cache_page_async);

/**
 * read_cache_page - read into page cache, fill it if needed
 * @mapping:	the page's address_space
 * @index:	the page index
 * @filler:	function to perform the read
 * @data:	destination for read data
 *
 * Read into the page cache. If a page already exists, and PageUptodate() is
 * not set, try to fill the page then wait for it to become unlocked.
 *
 * If the page does not get brought uptodate, return -EIO.
 */
struct page *read_cache_page(struct address_space *mapping,
				unsigned long index,
				int (*filler)(void *,struct page*),
				void *data)
{
	struct page *page;

	page = read_cache_page_async(mapping, index, filler, data);
	if (IS_ERR(page))
		goto out;
	wait_on_page_locked(page);
	if (!PageUptodate(page)) {
		page_cache_release(page);
		page = ERR_PTR(-EIO);
	}
L
Linus Torvalds 已提交
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
 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
 */
1865
int should_remove_suid(struct dentry *dentry)
L
Linus Torvalds 已提交
1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880
{
	mode_t mode = dentry->d_inode->i_mode;
	int kill = 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;

1881 1882
	if (unlikely(kill && !capable(CAP_FSETID)))
		return kill;
L
Linus Torvalds 已提交
1883

1884 1885
	return 0;
}
M
Mark Fasheh 已提交
1886
EXPORT_SYMBOL(should_remove_suid);
1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903

int __remove_suid(struct dentry *dentry, int kill)
{
	struct iattr newattrs;

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

int remove_suid(struct dentry *dentry)
{
	int kill = should_remove_suid(dentry);

	if (unlikely(kill))
		return __remove_suid(dentry, kill);

	return 0;
L
Linus Torvalds 已提交
1904 1905 1906
}
EXPORT_SYMBOL(remove_suid);

1907
size_t
1908
__filemap_copy_from_user_iovec_inatomic(char *vaddr,
L
Linus Torvalds 已提交
1909 1910 1911 1912 1913 1914 1915 1916 1917
			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;
1918
		left = __copy_from_user_inatomic_nocache(vaddr, buf, copy);
L
Linus Torvalds 已提交
1919 1920 1921 1922 1923
		copied += copy;
		bytes -= copy;
		vaddr += copy;
		iov++;

1924
		if (unlikely(left))
L
Linus Torvalds 已提交
1925 1926 1927 1928 1929 1930 1931 1932
			break;
	}
	return copied - left;
}

/*
 * Performs necessary checks before doing a write
 *
1933
 * Can adjust writing position or amount of bytes to write.
L
Linus Torvalds 已提交
1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993
 * 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 {
1994
#ifdef CONFIG_BLOCK
L
Linus Torvalds 已提交
1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005
		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;
2006 2007 2008
#else
		return -EPERM;
#endif
L
Linus Torvalds 已提交
2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039
	}
	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.
2040
	 * i_mutex is held, which protects generic_osync_inode() from
2041
	 * livelocking.  AIO O_DIRECT ops attempt to sync metadata here.
L
Linus Torvalds 已提交
2042
	 */
2043 2044
	if ((written >= 0 || written == -EIOCBQUEUED) &&
	    ((file->f_flags & O_SYNC) || IS_SYNC(inode))) {
2045 2046 2047 2048
		int err = generic_osync_inode(inode, mapping, OSYNC_METADATA);
		if (err < 0)
			written = err;
	}
L
Linus Torvalds 已提交
2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059
	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;
2060
	const struct address_space_operations *a_ops = mapping->a_ops;
L
Linus Torvalds 已提交
2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079
	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);
2080
		buf = cur_iov->iov_base + iov_base;
L
Linus Torvalds 已提交
2081 2082 2083 2084 2085 2086 2087 2088 2089 2090
	}

	do {
		unsigned long index;
		unsigned long offset;
		size_t copied;

		offset = (pos & (PAGE_CACHE_SIZE -1)); /* Within page */
		index = pos >> PAGE_CACHE_SHIFT;
		bytes = PAGE_CACHE_SIZE - offset;
2091 2092 2093 2094

		/* Limit the size of the copy to the caller's write size */
		bytes = min(bytes, count);

2095 2096 2097 2098
		/* We only need to worry about prefaulting when writes are from
		 * user-space.  NFSd uses vfs_writev with several non-aligned
		 * segments in the vector, and limiting to one segment a time is
		 * a noticeable performance for re-write
2099
		 */
2100 2101 2102 2103 2104 2105 2106
		if (!segment_eq(get_fs(), KERNEL_DS)) {
			/*
			 * Limit the size of the copy to that of the current
			 * segment, because fault_in_pages_readable() doesn't
			 * know how to walk segments.
			 */
			bytes = min(bytes, cur_iov->iov_len - iov_base);
L
Linus Torvalds 已提交
2107

2108 2109 2110 2111 2112 2113 2114 2115
			/*
			 * 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.
			 */
			fault_in_pages_readable(buf, bytes);
		}
L
Linus Torvalds 已提交
2116 2117 2118 2119 2120 2121
		page = __grab_cache_page(mapping,index,&cached_page,&lru_pvec);
		if (!page) {
			status = -ENOMEM;
			break;
		}

2122 2123 2124 2125 2126 2127
		if (unlikely(bytes == 0)) {
			status = 0;
			copied = 0;
			goto zero_length_segment;
		}

L
Linus Torvalds 已提交
2128 2129 2130
		status = a_ops->prepare_write(file, page, offset, offset+bytes);
		if (unlikely(status)) {
			loff_t isize = i_size_read(inode);
2131 2132 2133 2134 2135 2136

			if (status != AOP_TRUNCATED_PAGE)
				unlock_page(page);
			page_cache_release(page);
			if (status == AOP_TRUNCATED_PAGE)
				continue;
L
Linus Torvalds 已提交
2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152
			/*
			 * 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);
2153 2154 2155 2156
		if (status == AOP_TRUNCATED_PAGE) {
			page_cache_release(page);
			continue;
		}
2157 2158
zero_length_segment:
		if (likely(copied >= 0)) {
L
Linus Torvalds 已提交
2159 2160 2161 2162 2163 2164 2165 2166
			if (!status)
				status = copied;

			if (status >= 0) {
				written += status;
				count -= status;
				pos += status;
				buf += status;
2167
				if (unlikely(nr_segs > 1)) {
L
Linus Torvalds 已提交
2168 2169
					filemap_set_next_iovec(&cur_iov,
							&iov_base, status);
2170 2171 2172
					if (count)
						buf = cur_iov->iov_base +
							iov_base;
2173 2174
				} else {
					iov_base += status;
2175
				}
L
Linus Torvalds 已提交
2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217
			}
		}
		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);

2218
static ssize_t
L
Linus Torvalds 已提交
2219 2220 2221 2222
__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;
2223
	struct address_space * mapping = file->f_mapping;
L
Linus Torvalds 已提交
2224 2225 2226 2227 2228 2229 2230 2231
	size_t ocount;		/* original count */
	size_t count;		/* after file limit checks */
	struct inode 	*inode = mapping->host;
	loff_t		pos;
	ssize_t		written;
	ssize_t		err;

	ocount = 0;
2232 2233 2234
	err = generic_segment_checks(iov, &nr_segs, &ocount, VERIFY_READ);
	if (err)
		return err;
L
Linus Torvalds 已提交
2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251

	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;

2252
	err = remove_suid(file->f_path.dentry);
L
Linus Torvalds 已提交
2253 2254 2255
	if (err)
		goto out;

2256
	file_update_time(file);
L
Linus Torvalds 已提交
2257 2258 2259

	/* coalesce the iovecs and go direct-to-BIO for O_DIRECT */
	if (unlikely(file->f_flags & O_DIRECT)) {
2260 2261 2262 2263 2264
		loff_t endbyte;
		ssize_t written_buffered;

		written = generic_file_direct_write(iocb, iov, &nr_segs, pos,
							ppos, count, ocount);
L
Linus Torvalds 已提交
2265 2266 2267 2268 2269 2270 2271 2272
		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;
2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286
		written_buffered = generic_file_buffered_write(iocb, iov,
						nr_segs, pos, ppos, count,
						written);
		/*
		 * If generic_file_buffered_write() retuned a synchronous error
		 * then we want to return the number of bytes which were
		 * direct-written, or the error code if that was zero.  Note
		 * that this differs from normal direct-io semantics, which
		 * will return -EFOO even if some bytes were written.
		 */
		if (written_buffered < 0) {
			err = written_buffered;
			goto out;
		}
L
Linus Torvalds 已提交
2287

2288 2289 2290 2291 2292 2293
		/*
		 * We need to ensure that the page cache pages are written to
		 * disk and invalidated to preserve the expected O_DIRECT
		 * semantics.
		 */
		endbyte = pos + written_buffered - written - 1;
M
Mark Fasheh 已提交
2294 2295 2296 2297
		err = do_sync_mapping_range(file->f_mapping, pos, endbyte,
					    SYNC_FILE_RANGE_WAIT_BEFORE|
					    SYNC_FILE_RANGE_WRITE|
					    SYNC_FILE_RANGE_WAIT_AFTER);
2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312
		if (err == 0) {
			written = written_buffered;
			invalidate_mapping_pages(mapping,
						 pos >> PAGE_CACHE_SHIFT,
						 endbyte >> PAGE_CACHE_SHIFT);
		} else {
			/*
			 * We don't know how much we wrote, so just return
			 * the number of bytes which were direct-written
			 */
		}
	} else {
		written = generic_file_buffered_write(iocb, iov, nr_segs,
				pos, ppos, count, written);
	}
L
Linus Torvalds 已提交
2313 2314 2315 2316 2317
out:
	current->backing_dev_info = NULL;
	return written ? written : err;
}

2318 2319
ssize_t generic_file_aio_write_nolock(struct kiocb *iocb,
		const struct iovec *iov, unsigned long nr_segs, loff_t pos)
L
Linus Torvalds 已提交
2320 2321 2322 2323 2324 2325
{
	struct file *file = iocb->ki_filp;
	struct address_space *mapping = file->f_mapping;
	struct inode *inode = mapping->host;
	ssize_t ret;

2326 2327 2328 2329
	BUG_ON(iocb->ki_pos != pos);

	ret = __generic_file_aio_write_nolock(iocb, iov, nr_segs,
			&iocb->ki_pos);
L
Linus Torvalds 已提交
2330 2331

	if (ret > 0 && ((file->f_flags & O_SYNC) || IS_SYNC(inode))) {
2332
		ssize_t err;
L
Linus Torvalds 已提交
2333 2334 2335 2336 2337 2338 2339

		err = sync_page_range_nolock(inode, mapping, pos, ret);
		if (err < 0)
			ret = err;
	}
	return ret;
}
2340
EXPORT_SYMBOL(generic_file_aio_write_nolock);
L
Linus Torvalds 已提交
2341

2342 2343
ssize_t generic_file_aio_write(struct kiocb *iocb, const struct iovec *iov,
		unsigned long nr_segs, loff_t pos)
L
Linus Torvalds 已提交
2344 2345 2346 2347 2348 2349 2350 2351
{
	struct file *file = iocb->ki_filp;
	struct address_space *mapping = file->f_mapping;
	struct inode *inode = mapping->host;
	ssize_t ret;

	BUG_ON(iocb->ki_pos != pos);

2352
	mutex_lock(&inode->i_mutex);
2353 2354
	ret = __generic_file_aio_write_nolock(iocb, iov, nr_segs,
			&iocb->ki_pos);
2355
	mutex_unlock(&inode->i_mutex);
L
Linus Torvalds 已提交
2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368

	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);

/*
2369
 * Called under i_mutex for writes to S_ISREG files.   Returns -EIO if something
L
Linus Torvalds 已提交
2370 2371
 * went wrong during pagecache shootdown.
 */
2372
static ssize_t
L
Linus Torvalds 已提交
2373 2374 2375 2376 2377 2378
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;
2379 2380
	size_t write_len;
	pgoff_t end = 0; /* silence gcc */
L
Linus Torvalds 已提交
2381 2382 2383 2384 2385 2386 2387 2388

	/*
	 * 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);
2389
		end = (offset + write_len - 1) >> PAGE_CACHE_SHIFT;
L
Linus Torvalds 已提交
2390 2391 2392 2393 2394
	       	if (mapping_mapped(mapping))
			unmap_mapping_range(mapping, offset, write_len, 0);
	}

	retval = filemap_write_and_wait(mapping);
2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405
	if (retval)
		goto out;

	/*
	 * After a write we want buffered reads to be sure to go to disk to get
	 * the new data.  We invalidate clean cached page from the region we're
	 * about to write.  We do this *before* the write so that we can return
	 * -EIO without clobbering -EIOCBQUEUED from ->direct_IO().
	 */
	if (rw == WRITE && mapping->nrpages) {
		retval = invalidate_inode_pages2_range(mapping,
L
Linus Torvalds 已提交
2406
					offset >> PAGE_CACHE_SHIFT, end);
2407 2408
		if (retval)
			goto out;
L
Linus Torvalds 已提交
2409
	}
2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428

	retval = mapping->a_ops->direct_IO(rw, iocb, iov, offset, nr_segs);
	if (retval)
		goto out;

	/*
	 * Finally, try again to invalidate clean pages which might have been
	 * faulted in by get_user_pages() if the source of the write was an
	 * mmap()ed region of the file we're writing.  That's a pretty crazy
	 * thing to do, so we don't support it 100%.  If this invalidation
	 * fails and we have -EIOCBQUEUED we ignore the failure.
	 */
	if (rw == WRITE && mapping->nrpages) {
		int err = invalidate_inode_pages2_range(mapping,
					      offset >> PAGE_CACHE_SHIFT, end);
		if (err && retval >= 0)
			retval = err;
	}
out:
L
Linus Torvalds 已提交
2429 2430
	return retval;
}
2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460

/**
 * try_to_release_page() - release old fs-specific metadata on a page
 *
 * @page: the page which the kernel is trying to free
 * @gfp_mask: memory allocation flags (and I/O mode)
 *
 * The address_space is to try to release any data against the page
 * (presumably at page->private).  If the release was successful, return `1'.
 * Otherwise return zero.
 *
 * The @gfp_mask argument specifies whether I/O may be performed to release
 * this page (__GFP_IO), and whether the call may block (__GFP_WAIT).
 *
 * NOTE: @gfp_mask may go away, and this function may become non-blocking.
 */
int try_to_release_page(struct page *page, gfp_t gfp_mask)
{
	struct address_space * const mapping = page->mapping;

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

	if (mapping && mapping->a_ops->releasepage)
		return mapping->a_ops->releasepage(page, gfp_mask);
	return try_to_free_buffers(page);
}

EXPORT_SYMBOL(try_to_release_page);