shmem.c 58.3 KB
Newer Older
Linus Torvalds's avatar
Linus Torvalds committed
1 2 3 4 5 6 7 8
/*
 * Resizable virtual memory filesystem for Linux.
 *
 * Copyright (C) 2000 Linus Torvalds.
 *		 2000 Transmeta Corp.
 *		 2000-2001 Christoph Rohland
 *		 2000-2001 SAP AG
 *		 2002 Red Hat Inc.
9 10
 * Copyright (C) 2002-2005 Hugh Dickins.
 * Copyright (C) 2002-2005 VERITAS Software Corporation.
Linus Torvalds's avatar
Linus Torvalds committed
11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45
 * Copyright (C) 2004 Andi Kleen, SuSE Labs
 *
 * Extended attribute support for tmpfs:
 * Copyright (c) 2004, Luke Kenneth Casson Leighton <lkcl@lkcl.net>
 * Copyright (c) 2004 Red Hat, Inc., James Morris <jmorris@redhat.com>
 *
 * This file is released under the GPL.
 */

/*
 * This virtual memory filesystem is heavily based on the ramfs. It
 * extends ramfs by the ability to use swap and honor resource limits
 * which makes it a completely usable filesystem.
 */

#include <linux/module.h>
#include <linux/init.h>
#include <linux/fs.h>
#include <linux/mm.h>
#include <linux/mman.h>
#include <linux/file.h>
#include <linux/swap.h>
#include <linux/pagemap.h>
#include <linux/string.h>
#include <linux/slab.h>
#include <linux/backing-dev.h>
#include <linux/shmem_fs.h>
#include <linux/mount.h>
#include <linux/writeback.h>
#include <linux/vfs.h>
#include <linux/blkdev.h>
#include <linux/security.h>
#include <linux/swapops.h>
#include <linux/mempolicy.h>
#include <linux/namei.h>
46
#include <linux/ctype.h>
47
#include <linux/migrate.h>
48
#include <linux/highmem.h>
49

Linus Torvalds's avatar
Linus Torvalds committed
50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86
#include <asm/uaccess.h>
#include <asm/div64.h>
#include <asm/pgtable.h>

/* This magic number is used in glibc for posix shared memory */
#define TMPFS_MAGIC	0x01021994

#define ENTRIES_PER_PAGE (PAGE_CACHE_SIZE/sizeof(unsigned long))
#define ENTRIES_PER_PAGEPAGE (ENTRIES_PER_PAGE*ENTRIES_PER_PAGE)
#define BLOCKS_PER_PAGE  (PAGE_CACHE_SIZE/512)

#define SHMEM_MAX_INDEX  (SHMEM_NR_DIRECT + (ENTRIES_PER_PAGEPAGE/2) * (ENTRIES_PER_PAGE+1))
#define SHMEM_MAX_BYTES  ((unsigned long long)SHMEM_MAX_INDEX << PAGE_CACHE_SHIFT)

#define VM_ACCT(size)    (PAGE_CACHE_ALIGN(size) >> PAGE_SHIFT)

/* info->flags needs VM_flags to handle pagein/truncate races efficiently */
#define SHMEM_PAGEIN	 VM_READ
#define SHMEM_TRUNCATE	 VM_WRITE

/* Definition to limit shmem_truncate's steps between cond_rescheds */
#define LATENCY_LIMIT	 64

/* Pretend that each entry is of this size in directory's i_size */
#define BOGO_DIRENT_SIZE 20

/* Flag allocation requirements to shmem_getpage and shmem_swp_alloc */
enum sgp_type {
	SGP_QUICK,	/* don't try more than file page cache lookup */
	SGP_READ,	/* don't exceed i_size, don't allocate page */
	SGP_CACHE,	/* don't exceed i_size, may allocate page */
	SGP_WRITE,	/* may exceed i_size, may allocate page */
};

static int shmem_getpage(struct inode *inode, unsigned long idx,
			 struct page **pagep, enum sgp_type sgp, int *type);

Al Viro's avatar
Al Viro committed
87
static inline struct page *shmem_dir_alloc(gfp_t gfp_mask)
Linus Torvalds's avatar
Linus Torvalds committed
88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175
{
	/*
	 * The above definition of ENTRIES_PER_PAGE, and the use of
	 * BLOCKS_PER_PAGE on indirect pages, assume PAGE_CACHE_SIZE:
	 * might be reconsidered if it ever diverges from PAGE_SIZE.
	 */
	return alloc_pages(gfp_mask, PAGE_CACHE_SHIFT-PAGE_SHIFT);
}

static inline void shmem_dir_free(struct page *page)
{
	__free_pages(page, PAGE_CACHE_SHIFT-PAGE_SHIFT);
}

static struct page **shmem_dir_map(struct page *page)
{
	return (struct page **)kmap_atomic(page, KM_USER0);
}

static inline void shmem_dir_unmap(struct page **dir)
{
	kunmap_atomic(dir, KM_USER0);
}

static swp_entry_t *shmem_swp_map(struct page *page)
{
	return (swp_entry_t *)kmap_atomic(page, KM_USER1);
}

static inline void shmem_swp_balance_unmap(void)
{
	/*
	 * When passing a pointer to an i_direct entry, to code which
	 * also handles indirect entries and so will shmem_swp_unmap,
	 * we must arrange for the preempt count to remain in balance.
	 * What kmap_atomic of a lowmem page does depends on config
	 * and architecture, so pretend to kmap_atomic some lowmem page.
	 */
	(void) kmap_atomic(ZERO_PAGE(0), KM_USER1);
}

static inline void shmem_swp_unmap(swp_entry_t *entry)
{
	kunmap_atomic(entry, KM_USER1);
}

static inline struct shmem_sb_info *SHMEM_SB(struct super_block *sb)
{
	return sb->s_fs_info;
}

/*
 * shmem_file_setup pre-accounts the whole fixed size of a VM object,
 * for shared memory and for shared anonymous (/dev/zero) mappings
 * (unless MAP_NORESERVE and sysctl_overcommit_memory <= 1),
 * consistent with the pre-accounting of private mappings ...
 */
static inline int shmem_acct_size(unsigned long flags, loff_t size)
{
	return (flags & VM_ACCOUNT)?
		security_vm_enough_memory(VM_ACCT(size)): 0;
}

static inline void shmem_unacct_size(unsigned long flags, loff_t size)
{
	if (flags & VM_ACCOUNT)
		vm_unacct_memory(VM_ACCT(size));
}

/*
 * ... whereas tmpfs objects are accounted incrementally as
 * pages are allocated, in order to allow huge sparse files.
 * shmem_getpage reports shmem_acct_block failure as -ENOSPC not -ENOMEM,
 * so that a failure on a sparse tmpfs mapping will give SIGBUS not OOM.
 */
static inline int shmem_acct_block(unsigned long flags)
{
	return (flags & VM_ACCOUNT)?
		0: security_vm_enough_memory(VM_ACCT(PAGE_CACHE_SIZE));
}

static inline void shmem_unacct_blocks(unsigned long flags, long pages)
{
	if (!(flags & VM_ACCOUNT))
		vm_unacct_memory(pages * VM_ACCT(PAGE_CACHE_SIZE));
}

static struct super_operations shmem_ops;
176
static const struct address_space_operations shmem_aops;
Linus Torvalds's avatar
Linus Torvalds committed
177 178 179 180 181
static struct file_operations shmem_file_operations;
static struct inode_operations shmem_inode_operations;
static struct inode_operations shmem_dir_inode_operations;
static struct vm_operations_struct shmem_vm_ops;

182
static struct backing_dev_info shmem_backing_dev_info  __read_mostly = {
Linus Torvalds's avatar
Linus Torvalds committed
183 184 185 186 187 188 189 190 191 192 193
	.ra_pages	= 0,	/* No readahead */
	.capabilities	= BDI_CAP_NO_ACCT_DIRTY | BDI_CAP_NO_WRITEBACK,
	.unplug_io_fn	= default_unplug_io_fn,
};

static LIST_HEAD(shmem_swaplist);
static DEFINE_SPINLOCK(shmem_swaplist_lock);

static void shmem_free_blocks(struct inode *inode, long pages)
{
	struct shmem_sb_info *sbinfo = SHMEM_SB(inode->i_sb);
194
	if (sbinfo->max_blocks) {
Linus Torvalds's avatar
Linus Torvalds committed
195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325
		spin_lock(&sbinfo->stat_lock);
		sbinfo->free_blocks += pages;
		inode->i_blocks -= pages*BLOCKS_PER_PAGE;
		spin_unlock(&sbinfo->stat_lock);
	}
}

/*
 * shmem_recalc_inode - recalculate the size of an inode
 *
 * @inode: inode to recalc
 *
 * We have to calculate the free blocks since the mm can drop
 * undirtied hole pages behind our back.
 *
 * But normally   info->alloced == inode->i_mapping->nrpages + info->swapped
 * So mm freed is info->alloced - (inode->i_mapping->nrpages + info->swapped)
 *
 * It has to be called with the spinlock held.
 */
static void shmem_recalc_inode(struct inode *inode)
{
	struct shmem_inode_info *info = SHMEM_I(inode);
	long freed;

	freed = info->alloced - info->swapped - inode->i_mapping->nrpages;
	if (freed > 0) {
		info->alloced -= freed;
		shmem_unacct_blocks(info->flags, freed);
		shmem_free_blocks(inode, freed);
	}
}

/*
 * shmem_swp_entry - find the swap vector position in the info structure
 *
 * @info:  info structure for the inode
 * @index: index of the page to find
 * @page:  optional page to add to the structure. Has to be preset to
 *         all zeros
 *
 * If there is no space allocated yet it will return NULL when
 * page is NULL, else it will use the page for the needed block,
 * setting it to NULL on return to indicate that it has been used.
 *
 * The swap vector is organized the following way:
 *
 * There are SHMEM_NR_DIRECT entries directly stored in the
 * shmem_inode_info structure. So small files do not need an addional
 * allocation.
 *
 * For pages with index > SHMEM_NR_DIRECT there is the pointer
 * i_indirect which points to a page which holds in the first half
 * doubly indirect blocks, in the second half triple indirect blocks:
 *
 * For an artificial ENTRIES_PER_PAGE = 4 this would lead to the
 * following layout (for SHMEM_NR_DIRECT == 16):
 *
 * i_indirect -> dir --> 16-19
 * 	      |	     +-> 20-23
 * 	      |
 * 	      +-->dir2 --> 24-27
 * 	      |	       +-> 28-31
 * 	      |	       +-> 32-35
 * 	      |	       +-> 36-39
 * 	      |
 * 	      +-->dir3 --> 40-43
 * 	       	       +-> 44-47
 * 	      	       +-> 48-51
 * 	      	       +-> 52-55
 */
static swp_entry_t *shmem_swp_entry(struct shmem_inode_info *info, unsigned long index, struct page **page)
{
	unsigned long offset;
	struct page **dir;
	struct page *subdir;

	if (index < SHMEM_NR_DIRECT) {
		shmem_swp_balance_unmap();
		return info->i_direct+index;
	}
	if (!info->i_indirect) {
		if (page) {
			info->i_indirect = *page;
			*page = NULL;
		}
		return NULL;			/* need another page */
	}

	index -= SHMEM_NR_DIRECT;
	offset = index % ENTRIES_PER_PAGE;
	index /= ENTRIES_PER_PAGE;
	dir = shmem_dir_map(info->i_indirect);

	if (index >= ENTRIES_PER_PAGE/2) {
		index -= ENTRIES_PER_PAGE/2;
		dir += ENTRIES_PER_PAGE/2 + index/ENTRIES_PER_PAGE;
		index %= ENTRIES_PER_PAGE;
		subdir = *dir;
		if (!subdir) {
			if (page) {
				*dir = *page;
				*page = NULL;
			}
			shmem_dir_unmap(dir);
			return NULL;		/* need another page */
		}
		shmem_dir_unmap(dir);
		dir = shmem_dir_map(subdir);
	}

	dir += index;
	subdir = *dir;
	if (!subdir) {
		if (!page || !(subdir = *page)) {
			shmem_dir_unmap(dir);
			return NULL;		/* need a page */
		}
		*dir = subdir;
		*page = NULL;
	}
	shmem_dir_unmap(dir);
	return shmem_swp_map(subdir) + offset;
}

static void shmem_swp_set(struct shmem_inode_info *info, swp_entry_t *entry, unsigned long value)
{
	long incdec = value? 1: -1;

	entry->val = value;
	info->swapped += incdec;
326 327 328 329
	if ((unsigned long)(entry - info->i_direct) >= SHMEM_NR_DIRECT) {
		struct page *page = kmap_atomic_to_page(entry);
		set_page_private(page, page_private(page) + incdec);
	}
Linus Torvalds's avatar
Linus Torvalds committed
330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358
}

/*
 * shmem_swp_alloc - get the position of the swap entry for the page.
 *                   If it does not exist allocate the entry.
 *
 * @info:	info structure for the inode
 * @index:	index of the page to find
 * @sgp:	check and recheck i_size? skip allocation?
 */
static swp_entry_t *shmem_swp_alloc(struct shmem_inode_info *info, unsigned long index, enum sgp_type sgp)
{
	struct inode *inode = &info->vfs_inode;
	struct shmem_sb_info *sbinfo = SHMEM_SB(inode->i_sb);
	struct page *page = NULL;
	swp_entry_t *entry;

	if (sgp != SGP_WRITE &&
	    ((loff_t) index << PAGE_CACHE_SHIFT) >= i_size_read(inode))
		return ERR_PTR(-EINVAL);

	while (!(entry = shmem_swp_entry(info, index, &page))) {
		if (sgp == SGP_READ)
			return shmem_swp_map(ZERO_PAGE(0));
		/*
		 * Test free_blocks against 1 not 0, since we have 1 data
		 * page (and perhaps indirect index pages) yet to allocate:
		 * a waste to allocate index if we cannot allocate data.
		 */
359
		if (sbinfo->max_blocks) {
Linus Torvalds's avatar
Linus Torvalds committed
360 361 362 363 364 365 366 367 368 369 370 371
			spin_lock(&sbinfo->stat_lock);
			if (sbinfo->free_blocks <= 1) {
				spin_unlock(&sbinfo->stat_lock);
				return ERR_PTR(-ENOSPC);
			}
			sbinfo->free_blocks--;
			inode->i_blocks += BLOCKS_PER_PAGE;
			spin_unlock(&sbinfo->stat_lock);
		}

		spin_unlock(&info->lock);
		page = shmem_dir_alloc(mapping_gfp_mask(inode->i_mapping) | __GFP_ZERO);
372 373
		if (page)
			set_page_private(page, 0);
Linus Torvalds's avatar
Linus Torvalds committed
374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461
		spin_lock(&info->lock);

		if (!page) {
			shmem_free_blocks(inode, 1);
			return ERR_PTR(-ENOMEM);
		}
		if (sgp != SGP_WRITE &&
		    ((loff_t) index << PAGE_CACHE_SHIFT) >= i_size_read(inode)) {
			entry = ERR_PTR(-EINVAL);
			break;
		}
		if (info->next_index <= index)
			info->next_index = index + 1;
	}
	if (page) {
		/* another task gave its page, or truncated the file */
		shmem_free_blocks(inode, 1);
		shmem_dir_free(page);
	}
	if (info->next_index <= index && !IS_ERR(entry))
		info->next_index = index + 1;
	return entry;
}

/*
 * shmem_free_swp - free some swap entries in a directory
 *
 * @dir:   pointer to the directory
 * @edir:  pointer after last entry of the directory
 */
static int shmem_free_swp(swp_entry_t *dir, swp_entry_t *edir)
{
	swp_entry_t *ptr;
	int freed = 0;

	for (ptr = dir; ptr < edir; ptr++) {
		if (ptr->val) {
			free_swap_and_cache(*ptr);
			*ptr = (swp_entry_t){0};
			freed++;
		}
	}
	return freed;
}

static int shmem_map_and_free_swp(struct page *subdir,
		int offset, int limit, struct page ***dir)
{
	swp_entry_t *ptr;
	int freed = 0;

	ptr = shmem_swp_map(subdir);
	for (; offset < limit; offset += LATENCY_LIMIT) {
		int size = limit - offset;
		if (size > LATENCY_LIMIT)
			size = LATENCY_LIMIT;
		freed += shmem_free_swp(ptr+offset, ptr+offset+size);
		if (need_resched()) {
			shmem_swp_unmap(ptr);
			if (*dir) {
				shmem_dir_unmap(*dir);
				*dir = NULL;
			}
			cond_resched();
			ptr = shmem_swp_map(subdir);
		}
	}
	shmem_swp_unmap(ptr);
	return freed;
}

static void shmem_free_pages(struct list_head *next)
{
	struct page *page;
	int freed = 0;

	do {
		page = container_of(next, struct page, lru);
		next = next->next;
		shmem_dir_free(page);
		freed++;
		if (freed >= LATENCY_LIMIT) {
			cond_resched();
			freed = 0;
		}
	} while (next);
}

462
static void shmem_truncate_range(struct inode *inode, loff_t start, loff_t end)
Linus Torvalds's avatar
Linus Torvalds committed
463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479
{
	struct shmem_inode_info *info = SHMEM_I(inode);
	unsigned long idx;
	unsigned long size;
	unsigned long limit;
	unsigned long stage;
	unsigned long diroff;
	struct page **dir;
	struct page *topdir;
	struct page *middir;
	struct page *subdir;
	swp_entry_t *ptr;
	LIST_HEAD(pages_to_free);
	long nr_pages_to_free = 0;
	long nr_swaps_freed = 0;
	int offset;
	int freed;
480
	int punch_hole = 0;
Linus Torvalds's avatar
Linus Torvalds committed
481 482

	inode->i_ctime = inode->i_mtime = CURRENT_TIME;
483
	idx = (start + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
Linus Torvalds's avatar
Linus Torvalds committed
484 485 486 487 488
	if (idx >= info->next_index)
		return;

	spin_lock(&info->lock);
	info->flags |= SHMEM_TRUNCATE;
489 490 491 492 493 494 495 496 497 498
	if (likely(end == (loff_t) -1)) {
		limit = info->next_index;
		info->next_index = idx;
	} else {
		limit = (end + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
		if (limit > info->next_index)
			limit = info->next_index;
		punch_hole = 1;
	}

Linus Torvalds's avatar
Linus Torvalds committed
499
	topdir = info->i_indirect;
500
	if (topdir && idx <= SHMEM_NR_DIRECT && !punch_hole) {
Linus Torvalds's avatar
Linus Torvalds committed
501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572
		info->i_indirect = NULL;
		nr_pages_to_free++;
		list_add(&topdir->lru, &pages_to_free);
	}
	spin_unlock(&info->lock);

	if (info->swapped && idx < SHMEM_NR_DIRECT) {
		ptr = info->i_direct;
		size = limit;
		if (size > SHMEM_NR_DIRECT)
			size = SHMEM_NR_DIRECT;
		nr_swaps_freed = shmem_free_swp(ptr+idx, ptr+size);
	}
	if (!topdir)
		goto done2;

	BUG_ON(limit <= SHMEM_NR_DIRECT);
	limit -= SHMEM_NR_DIRECT;
	idx = (idx > SHMEM_NR_DIRECT)? (idx - SHMEM_NR_DIRECT): 0;
	offset = idx % ENTRIES_PER_PAGE;
	idx -= offset;

	dir = shmem_dir_map(topdir);
	stage = ENTRIES_PER_PAGEPAGE/2;
	if (idx < ENTRIES_PER_PAGEPAGE/2) {
		middir = topdir;
		diroff = idx/ENTRIES_PER_PAGE;
	} else {
		dir += ENTRIES_PER_PAGE/2;
		dir += (idx - ENTRIES_PER_PAGEPAGE/2)/ENTRIES_PER_PAGEPAGE;
		while (stage <= idx)
			stage += ENTRIES_PER_PAGEPAGE;
		middir = *dir;
		if (*dir) {
			diroff = ((idx - ENTRIES_PER_PAGEPAGE/2) %
				ENTRIES_PER_PAGEPAGE) / ENTRIES_PER_PAGE;
			if (!diroff && !offset) {
				*dir = NULL;
				nr_pages_to_free++;
				list_add(&middir->lru, &pages_to_free);
			}
			shmem_dir_unmap(dir);
			dir = shmem_dir_map(middir);
		} else {
			diroff = 0;
			offset = 0;
			idx = stage;
		}
	}

	for (; idx < limit; idx += ENTRIES_PER_PAGE, diroff++) {
		if (unlikely(idx == stage)) {
			shmem_dir_unmap(dir);
			dir = shmem_dir_map(topdir) +
			    ENTRIES_PER_PAGE/2 + idx/ENTRIES_PER_PAGEPAGE;
			while (!*dir) {
				dir++;
				idx += ENTRIES_PER_PAGEPAGE;
				if (idx >= limit)
					goto done1;
			}
			stage = idx + ENTRIES_PER_PAGEPAGE;
			middir = *dir;
			*dir = NULL;
			nr_pages_to_free++;
			list_add(&middir->lru, &pages_to_free);
			shmem_dir_unmap(dir);
			cond_resched();
			dir = shmem_dir_map(middir);
			diroff = 0;
		}
		subdir = dir[diroff];
573
		if (subdir && page_private(subdir)) {
Linus Torvalds's avatar
Linus Torvalds committed
574 575 576 577 578 579 580 581 582 583
			size = limit - idx;
			if (size > ENTRIES_PER_PAGE)
				size = ENTRIES_PER_PAGE;
			freed = shmem_map_and_free_swp(subdir,
						offset, size, &dir);
			if (!dir)
				dir = shmem_dir_map(middir);
			nr_swaps_freed += freed;
			if (offset)
				spin_lock(&info->lock);
584
			set_page_private(subdir, page_private(subdir) - freed);
Linus Torvalds's avatar
Linus Torvalds committed
585 586
			if (offset)
				spin_unlock(&info->lock);
587 588
			if (!punch_hole)
				BUG_ON(page_private(subdir) > offset);
Linus Torvalds's avatar
Linus Torvalds committed
589 590 591
		}
		if (offset)
			offset = 0;
592
		else if (subdir && !page_private(subdir)) {
Linus Torvalds's avatar
Linus Torvalds committed
593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608
			dir[diroff] = NULL;
			nr_pages_to_free++;
			list_add(&subdir->lru, &pages_to_free);
		}
	}
done1:
	shmem_dir_unmap(dir);
done2:
	if (inode->i_mapping->nrpages && (info->flags & SHMEM_PAGEIN)) {
		/*
		 * Call truncate_inode_pages again: racing shmem_unuse_inode
		 * may have swizzled a page in from swap since vmtruncate or
		 * generic_delete_inode did it, before we lowered next_index.
		 * Also, though shmem_getpage checks i_size before adding to
		 * cache, no recheck after: so fix the narrow window there too.
		 */
609
		truncate_inode_pages_range(inode->i_mapping, start, end);
Linus Torvalds's avatar
Linus Torvalds committed
610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628
	}

	spin_lock(&info->lock);
	info->flags &= ~SHMEM_TRUNCATE;
	info->swapped -= nr_swaps_freed;
	if (nr_pages_to_free)
		shmem_free_blocks(inode, nr_pages_to_free);
	shmem_recalc_inode(inode);
	spin_unlock(&info->lock);

	/*
	 * Empty swap vector directory pages to be freed?
	 */
	if (!list_empty(&pages_to_free)) {
		pages_to_free.prev->next = NULL;
		shmem_free_pages(pages_to_free.next);
	}
}

629 630 631 632 633
static void shmem_truncate(struct inode *inode)
{
	shmem_truncate_range(inode, inode->i_size, (loff_t)-1);
}

Linus Torvalds's avatar
Linus Torvalds committed
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
static int shmem_notify_change(struct dentry *dentry, struct iattr *attr)
{
	struct inode *inode = dentry->d_inode;
	struct page *page = NULL;
	int error;

	if (attr->ia_valid & ATTR_SIZE) {
		if (attr->ia_size < inode->i_size) {
			/*
			 * If truncating down to a partial page, then
			 * if that page is already allocated, hold it
			 * in memory until the truncation is over, so
			 * truncate_partial_page cannnot miss it were
			 * it assigned to swap.
			 */
			if (attr->ia_size & (PAGE_CACHE_SIZE-1)) {
				(void) shmem_getpage(inode,
					attr->ia_size>>PAGE_CACHE_SHIFT,
						&page, SGP_READ, NULL);
			}
			/*
			 * Reset SHMEM_PAGEIN flag so that shmem_truncate can
			 * detect if any pages might have been added to cache
			 * after truncate_inode_pages.  But we needn't bother
			 * if it's being fully truncated to zero-length: the
			 * nrpages check is efficient enough in that case.
			 */
			if (attr->ia_size) {
				struct shmem_inode_info *info = SHMEM_I(inode);
				spin_lock(&info->lock);
				info->flags &= ~SHMEM_PAGEIN;
				spin_unlock(&info->lock);
			}
		}
	}

	error = inode_change_ok(inode, attr);
	if (!error)
		error = inode_setattr(inode, attr);
	if (page)
		page_cache_release(page);
	return error;
}

static void shmem_delete_inode(struct inode *inode)
{
	struct shmem_sb_info *sbinfo = SHMEM_SB(inode->i_sb);
	struct shmem_inode_info *info = SHMEM_I(inode);

	if (inode->i_op->truncate == shmem_truncate) {
684
		truncate_inode_pages(inode->i_mapping, 0);
Linus Torvalds's avatar
Linus Torvalds committed
685 686 687 688 689 690 691 692 693
		shmem_unacct_size(info->flags, inode->i_size);
		inode->i_size = 0;
		shmem_truncate(inode);
		if (!list_empty(&info->swaplist)) {
			spin_lock(&shmem_swaplist_lock);
			list_del_init(&info->swaplist);
			spin_unlock(&shmem_swaplist_lock);
		}
	}
694 695
	BUG_ON(inode->i_blocks);
	if (sbinfo->max_inodes) {
Linus Torvalds's avatar
Linus Torvalds committed
696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760
		spin_lock(&sbinfo->stat_lock);
		sbinfo->free_inodes++;
		spin_unlock(&sbinfo->stat_lock);
	}
	clear_inode(inode);
}

static inline int shmem_find_swp(swp_entry_t entry, swp_entry_t *dir, swp_entry_t *edir)
{
	swp_entry_t *ptr;

	for (ptr = dir; ptr < edir; ptr++) {
		if (ptr->val == entry.val)
			return ptr - dir;
	}
	return -1;
}

static int shmem_unuse_inode(struct shmem_inode_info *info, swp_entry_t entry, struct page *page)
{
	struct inode *inode;
	unsigned long idx;
	unsigned long size;
	unsigned long limit;
	unsigned long stage;
	struct page **dir;
	struct page *subdir;
	swp_entry_t *ptr;
	int offset;

	idx = 0;
	ptr = info->i_direct;
	spin_lock(&info->lock);
	limit = info->next_index;
	size = limit;
	if (size > SHMEM_NR_DIRECT)
		size = SHMEM_NR_DIRECT;
	offset = shmem_find_swp(entry, ptr, ptr+size);
	if (offset >= 0) {
		shmem_swp_balance_unmap();
		goto found;
	}
	if (!info->i_indirect)
		goto lost2;

	dir = shmem_dir_map(info->i_indirect);
	stage = SHMEM_NR_DIRECT + ENTRIES_PER_PAGEPAGE/2;

	for (idx = SHMEM_NR_DIRECT; idx < limit; idx += ENTRIES_PER_PAGE, dir++) {
		if (unlikely(idx == stage)) {
			shmem_dir_unmap(dir-1);
			dir = shmem_dir_map(info->i_indirect) +
			    ENTRIES_PER_PAGE/2 + idx/ENTRIES_PER_PAGEPAGE;
			while (!*dir) {
				dir++;
				idx += ENTRIES_PER_PAGEPAGE;
				if (idx >= limit)
					goto lost1;
			}
			stage = idx + ENTRIES_PER_PAGEPAGE;
			subdir = *dir;
			shmem_dir_unmap(dir);
			dir = shmem_dir_map(subdir);
		}
		subdir = *dir;
761
		if (subdir && page_private(subdir)) {
Linus Torvalds's avatar
Linus Torvalds committed
762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874
			ptr = shmem_swp_map(subdir);
			size = limit - idx;
			if (size > ENTRIES_PER_PAGE)
				size = ENTRIES_PER_PAGE;
			offset = shmem_find_swp(entry, ptr, ptr+size);
			if (offset >= 0) {
				shmem_dir_unmap(dir);
				goto found;
			}
			shmem_swp_unmap(ptr);
		}
	}
lost1:
	shmem_dir_unmap(dir-1);
lost2:
	spin_unlock(&info->lock);
	return 0;
found:
	idx += offset;
	inode = &info->vfs_inode;
	if (move_from_swap_cache(page, idx, inode->i_mapping) == 0) {
		info->flags |= SHMEM_PAGEIN;
		shmem_swp_set(info, ptr + offset, 0);
	}
	shmem_swp_unmap(ptr);
	spin_unlock(&info->lock);
	/*
	 * Decrement swap count even when the entry is left behind:
	 * try_to_unuse will skip over mms, then reincrement count.
	 */
	swap_free(entry);
	return 1;
}

/*
 * shmem_unuse() search for an eventually swapped out shmem page.
 */
int shmem_unuse(swp_entry_t entry, struct page *page)
{
	struct list_head *p, *next;
	struct shmem_inode_info *info;
	int found = 0;

	spin_lock(&shmem_swaplist_lock);
	list_for_each_safe(p, next, &shmem_swaplist) {
		info = list_entry(p, struct shmem_inode_info, swaplist);
		if (!info->swapped)
			list_del_init(&info->swaplist);
		else if (shmem_unuse_inode(info, entry, page)) {
			/* move head to start search for next from here */
			list_move_tail(&shmem_swaplist, &info->swaplist);
			found = 1;
			break;
		}
	}
	spin_unlock(&shmem_swaplist_lock);
	return found;
}

/*
 * Move the page from the page cache to the swap cache.
 */
static int shmem_writepage(struct page *page, struct writeback_control *wbc)
{
	struct shmem_inode_info *info;
	swp_entry_t *entry, swap;
	struct address_space *mapping;
	unsigned long index;
	struct inode *inode;

	BUG_ON(!PageLocked(page));
	BUG_ON(page_mapped(page));

	mapping = page->mapping;
	index = page->index;
	inode = mapping->host;
	info = SHMEM_I(inode);
	if (info->flags & VM_LOCKED)
		goto redirty;
	swap = get_swap_page();
	if (!swap.val)
		goto redirty;

	spin_lock(&info->lock);
	shmem_recalc_inode(inode);
	if (index >= info->next_index) {
		BUG_ON(!(info->flags & SHMEM_TRUNCATE));
		goto unlock;
	}
	entry = shmem_swp_entry(info, index, NULL);
	BUG_ON(!entry);
	BUG_ON(entry->val);

	if (move_to_swap_cache(page, swap) == 0) {
		shmem_swp_set(info, entry, swap.val);
		shmem_swp_unmap(entry);
		spin_unlock(&info->lock);
		if (list_empty(&info->swaplist)) {
			spin_lock(&shmem_swaplist_lock);
			/* move instead of add in case we're racing */
			list_move_tail(&info->swaplist, &shmem_swaplist);
			spin_unlock(&shmem_swaplist_lock);
		}
		unlock_page(page);
		return 0;
	}

	shmem_swp_unmap(entry);
unlock:
	spin_unlock(&info->lock);
	swap_free(swap);
redirty:
	set_page_dirty(page);
875
	return AOP_WRITEPAGE_ACTIVATE;	/* Return with the page locked */
Linus Torvalds's avatar
Linus Torvalds committed
876 877 878
}

#ifdef CONFIG_NUMA
879
static inline int shmem_parse_mpol(char *value, int *policy, nodemask_t *policy_nodes)
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
{
	char *nodelist = strchr(value, ':');
	int err = 1;

	if (nodelist) {
		/* NUL-terminate policy string */
		*nodelist++ = '\0';
		if (nodelist_parse(nodelist, *policy_nodes))
			goto out;
	}
	if (!strcmp(value, "default")) {
		*policy = MPOL_DEFAULT;
		/* Don't allow a nodelist */
		if (!nodelist)
			err = 0;
	} else if (!strcmp(value, "prefer")) {
		*policy = MPOL_PREFERRED;
		/* Insist on a nodelist of one node only */
		if (nodelist) {
			char *rest = nodelist;
			while (isdigit(*rest))
				rest++;
			if (!*rest)
				err = 0;
		}
	} else if (!strcmp(value, "bind")) {
		*policy = MPOL_BIND;
		/* Insist on a nodelist */
		if (nodelist)
			err = 0;
	} else if (!strcmp(value, "interleave")) {
		*policy = MPOL_INTERLEAVE;
		/* Default to nodes online if no nodelist */
		if (!nodelist)
			*policy_nodes = node_online_map;
		err = 0;
	}
out:
	/* Restore string for error message */
	if (nodelist)
		*--nodelist = ':';
	return err;
}

Linus Torvalds's avatar
Linus Torvalds committed
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
static struct page *shmem_swapin_async(struct shared_policy *p,
				       swp_entry_t entry, unsigned long idx)
{
	struct page *page;
	struct vm_area_struct pvma;

	/* Create a pseudo vma that just contains the policy */
	memset(&pvma, 0, sizeof(struct vm_area_struct));
	pvma.vm_end = PAGE_SIZE;
	pvma.vm_pgoff = idx;
	pvma.vm_policy = mpol_shared_policy_lookup(p, idx);
	page = read_swap_cache_async(entry, &pvma, 0);
	mpol_free(pvma.vm_policy);
	return page;
}

struct page *shmem_swapin(struct shmem_inode_info *info, swp_entry_t entry,
			  unsigned long idx)
{
	struct shared_policy *p = &info->policy;
	int i, num;
	struct page *page;
	unsigned long offset;

	num = valid_swaphandles(entry, &offset);
	for (i = 0; i < num; offset++, i++) {
		page = shmem_swapin_async(p,
				swp_entry(swp_type(entry), offset), idx);
		if (!page)
			break;
		page_cache_release(page);
	}
	lru_add_drain();	/* Push any new pages onto the LRU now */
	return shmem_swapin_async(p, entry, idx);
}

static struct page *
Al Viro's avatar
Al Viro committed
961
shmem_alloc_page(gfp_t gfp, struct shmem_inode_info *info,
Linus Torvalds's avatar
Linus Torvalds committed
962 963 964 965 966 967 968 969 970 971 972 973 974 975
		 unsigned long idx)
{
	struct vm_area_struct pvma;
	struct page *page;

	memset(&pvma, 0, sizeof(struct vm_area_struct));
	pvma.vm_policy = mpol_shared_policy_lookup(&info->policy, idx);
	pvma.vm_pgoff = idx;
	pvma.vm_end = PAGE_SIZE;
	page = alloc_page_vma(gfp | __GFP_ZERO, &pvma, 0);
	mpol_free(pvma.vm_policy);
	return page;
}
#else
976 977 978 979 980
static inline int shmem_parse_mpol(char *value, int *policy, nodemask_t *policy_nodes)
{
	return 1;
}

Linus Torvalds's avatar
Linus Torvalds committed
981 982 983 984 985 986 987 988
static inline struct page *
shmem_swapin(struct shmem_inode_info *info,swp_entry_t entry,unsigned long idx)
{
	swapin_readahead(entry, 0, NULL);
	return read_swap_cache_async(entry, NULL, 0);
}

static inline struct page *
989
shmem_alloc_page(gfp_t gfp,struct shmem_inode_info *info, unsigned long idx)
Linus Torvalds's avatar
Linus Torvalds committed
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 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049
{
	return alloc_page(gfp | __GFP_ZERO);
}
#endif

/*
 * shmem_getpage - either get the page from swap or allocate a new one
 *
 * If we allocate a new one we do not mark it dirty. That's up to the
 * vm. If we swap it in we mark it dirty since we also free the swap
 * entry since a page cannot live in both the swap and page cache
 */
static int shmem_getpage(struct inode *inode, unsigned long idx,
			struct page **pagep, enum sgp_type sgp, int *type)
{
	struct address_space *mapping = inode->i_mapping;
	struct shmem_inode_info *info = SHMEM_I(inode);
	struct shmem_sb_info *sbinfo;
	struct page *filepage = *pagep;
	struct page *swappage;
	swp_entry_t *entry;
	swp_entry_t swap;
	int error;

	if (idx >= SHMEM_MAX_INDEX)
		return -EFBIG;
	/*
	 * Normally, filepage is NULL on entry, and either found
	 * uptodate immediately, or allocated and zeroed, or read
	 * in under swappage, which is then assigned to filepage.
	 * But shmem_prepare_write passes in a locked filepage,
	 * which may be found not uptodate by other callers too,
	 * and may need to be copied from the swappage read in.
	 */
repeat:
	if (!filepage)
		filepage = find_lock_page(mapping, idx);
	if (filepage && PageUptodate(filepage))
		goto done;
	error = 0;
	if (sgp == SGP_QUICK)
		goto failed;

	spin_lock(&info->lock);
	shmem_recalc_inode(inode);
	entry = shmem_swp_alloc(info, idx, sgp);
	if (IS_ERR(entry)) {
		spin_unlock(&info->lock);
		error = PTR_ERR(entry);
		goto failed;
	}
	swap = *entry;

	if (swap.val) {
		/* Look it up and read it in.. */
		swappage = lookup_swap_cache(swap);
		if (!swappage) {
			shmem_swp_unmap(entry);
			/* here we actually do the io */
			if (type && *type == VM_FAULT_MINOR) {
1050
				__count_vm_event(PGMAJFAULT);
Linus Torvalds's avatar
Linus Torvalds committed
1051 1052
				*type = VM_FAULT_MAJOR;
			}
1053
			spin_unlock(&info->lock);
Linus Torvalds's avatar
Linus Torvalds committed
1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145
			swappage = shmem_swapin(info, swap, idx);
			if (!swappage) {
				spin_lock(&info->lock);
				entry = shmem_swp_alloc(info, idx, sgp);
				if (IS_ERR(entry))
					error = PTR_ERR(entry);
				else {
					if (entry->val == swap.val)
						error = -ENOMEM;
					shmem_swp_unmap(entry);
				}
				spin_unlock(&info->lock);
				if (error)
					goto failed;
				goto repeat;
			}
			wait_on_page_locked(swappage);
			page_cache_release(swappage);
			goto repeat;
		}

		/* We have to do this with page locked to prevent races */
		if (TestSetPageLocked(swappage)) {
			shmem_swp_unmap(entry);
			spin_unlock(&info->lock);
			wait_on_page_locked(swappage);
			page_cache_release(swappage);
			goto repeat;
		}
		if (PageWriteback(swappage)) {
			shmem_swp_unmap(entry);
			spin_unlock(&info->lock);
			wait_on_page_writeback(swappage);
			unlock_page(swappage);
			page_cache_release(swappage);
			goto repeat;
		}
		if (!PageUptodate(swappage)) {
			shmem_swp_unmap(entry);
			spin_unlock(&info->lock);
			unlock_page(swappage);
			page_cache_release(swappage);
			error = -EIO;
			goto failed;
		}

		if (filepage) {
			shmem_swp_set(info, entry, 0);
			shmem_swp_unmap(entry);
			delete_from_swap_cache(swappage);
			spin_unlock(&info->lock);
			copy_highpage(filepage, swappage);
			unlock_page(swappage);
			page_cache_release(swappage);
			flush_dcache_page(filepage);
			SetPageUptodate(filepage);
			set_page_dirty(filepage);
			swap_free(swap);
		} else if (!(error = move_from_swap_cache(
				swappage, idx, mapping))) {
			info->flags |= SHMEM_PAGEIN;
			shmem_swp_set(info, entry, 0);
			shmem_swp_unmap(entry);
			spin_unlock(&info->lock);
			filepage = swappage;
			swap_free(swap);
		} else {
			shmem_swp_unmap(entry);
			spin_unlock(&info->lock);
			unlock_page(swappage);
			page_cache_release(swappage);
			if (error == -ENOMEM) {
				/* let kswapd refresh zone for GFP_ATOMICs */
				blk_congestion_wait(WRITE, HZ/50);
			}
			goto repeat;
		}
	} else if (sgp == SGP_READ && !filepage) {
		shmem_swp_unmap(entry);
		filepage = find_get_page(mapping, idx);
		if (filepage &&
		    (!PageUptodate(filepage) || TestSetPageLocked(filepage))) {
			spin_unlock(&info->lock);
			wait_on_page_locked(filepage);
			page_cache_release(filepage);
			filepage = NULL;
			goto repeat;
		}
		spin_unlock(&info->lock);
	} else {
		shmem_swp_unmap(entry);
		sbinfo = SHMEM_SB(inode->i_sb);
1146
		if (sbinfo->max_blocks) {
Linus Torvalds's avatar
Linus Torvalds committed
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 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260
			spin_lock(&sbinfo->stat_lock);
			if (sbinfo->free_blocks == 0 ||
			    shmem_acct_block(info->flags)) {
				spin_unlock(&sbinfo->stat_lock);
				spin_unlock(&info->lock);
				error = -ENOSPC;
				goto failed;
			}
			sbinfo->free_blocks--;
			inode->i_blocks += BLOCKS_PER_PAGE;
			spin_unlock(&sbinfo->stat_lock);
		} else if (shmem_acct_block(info->flags)) {
			spin_unlock(&info->lock);
			error = -ENOSPC;
			goto failed;
		}

		if (!filepage) {
			spin_unlock(&info->lock);
			filepage = shmem_alloc_page(mapping_gfp_mask(mapping),
						    info,
						    idx);
			if (!filepage) {
				shmem_unacct_blocks(info->flags, 1);
				shmem_free_blocks(inode, 1);
				error = -ENOMEM;
				goto failed;
			}

			spin_lock(&info->lock);
			entry = shmem_swp_alloc(info, idx, sgp);
			if (IS_ERR(entry))
				error = PTR_ERR(entry);
			else {
				swap = *entry;
				shmem_swp_unmap(entry);
			}
			if (error || swap.val || 0 != add_to_page_cache_lru(
					filepage, mapping, idx, GFP_ATOMIC)) {
				spin_unlock(&info->lock);
				page_cache_release(filepage);
				shmem_unacct_blocks(info->flags, 1);
				shmem_free_blocks(inode, 1);
				filepage = NULL;
				if (error)
					goto failed;
				goto repeat;
			}
			info->flags |= SHMEM_PAGEIN;
		}

		info->alloced++;
		spin_unlock(&info->lock);
		flush_dcache_page(filepage);
		SetPageUptodate(filepage);
	}
done:
	if (*pagep != filepage) {
		unlock_page(filepage);
		*pagep = filepage;
	}
	return 0;

failed:
	if (*pagep != filepage) {
		unlock_page(filepage);
		page_cache_release(filepage);
	}
	return error;
}

struct page *shmem_nopage(struct vm_area_struct *vma, unsigned long address, int *type)
{
	struct inode *inode = vma->vm_file->f_dentry->d_inode;
	struct page *page = NULL;
	unsigned long idx;
	int error;

	idx = (address - vma->vm_start) >> PAGE_SHIFT;
	idx += vma->vm_pgoff;
	idx >>= PAGE_CACHE_SHIFT - PAGE_SHIFT;
	if (((loff_t) idx << PAGE_CACHE_SHIFT) >= i_size_read(inode))
		return NOPAGE_SIGBUS;

	error = shmem_getpage(inode, idx, &page, SGP_CACHE, type);
	if (error)
		return (error == -ENOMEM)? NOPAGE_OOM: NOPAGE_SIGBUS;

	mark_page_accessed(page);
	return page;
}

static int shmem_populate(struct vm_area_struct *vma,
	unsigned long addr, unsigned long len,
	pgprot_t prot, unsigned long pgoff, int nonblock)
{
	struct inode *inode = vma->vm_file->f_dentry->d_inode;
	struct mm_struct *mm = vma->vm_mm;
	enum sgp_type sgp = nonblock? SGP_QUICK: SGP_CACHE;
	unsigned long size;

	size = (i_size_read(inode) + PAGE_SIZE - 1) >> PAGE_SHIFT;
	if (pgoff >= size || pgoff + (len >> PAGE_SHIFT) > size)
		return -EINVAL;

	while ((long) len > 0) {
		struct page *page = NULL;
		int err;
		/*
		 * Will need changing if PAGE_CACHE_SIZE != PAGE_SIZE
		 */
		err = shmem_getpage(inode, pgoff, &page, sgp, NULL);
		if (err)
			return err;
1261
		/* Page may still be null, but only if nonblock was set. */
Linus Torvalds's avatar
Linus Torvalds committed
1262 1263 1264 1265 1266 1267 1268
		if (page) {
			mark_page_accessed(page);
			err = install_page(mm, vma, addr, page, prot);
			if (err) {
				page_cache_release(page);
				return err;
			}
1269
		} else if (vma->vm_flags & VM_NONLINEAR) {
1270 1271 1272
			/* 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
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
    			err = install_file_pte(mm, vma, addr, pgoff, prot);
			if (err)
	    			return err;
		}

		len -= PAGE_SIZE;
		addr += PAGE_SIZE;
		pgoff++;
	}
	return 0;
}

#ifdef CONFIG_NUMA
int shmem_set_policy(struct vm_area_struct *vma, struct mempolicy *new)
{
	struct inode *i = vma->vm_file->f_dentry->d_inode;
	return mpol_set_shared_policy(&SHMEM_I(i)->policy, vma, new);
}

struct mempolicy *
shmem_get_policy(struct vm_area_struct *vma, unsigned long addr)
{
	struct inode *i = vma->vm_file->f_dentry->d_inode;
	unsigned long idx;

	idx = ((addr - vma->vm_start) >> PAGE_SHIFT) + vma->vm_pgoff;
	return mpol_shared_policy_lookup(&SHMEM_I(i)->policy, idx);
}
#endif

int shmem_lock(struct file *file, int lock, struct user_struct *user)
{
	struct inode *inode = file->f_dentry->d_inode;
	struct shmem_inode_info *info = SHMEM_I(inode);
	int retval = -ENOMEM;

	spin_lock(&info->lock);
	if (lock && !(info->flags & VM_LOCKED)) {
		if (!user_shm_lock(inode->i_size, user))
			goto out_nomem;
		info->flags |= VM_LOCKED;
	}
	if (!lock && (info->flags & VM_LOCKED) && user) {
		user_shm_unlock(inode->i_size, user);
		info->flags &= ~VM_LOCKED;
	}
	retval = 0;
out_nomem:
	spin_unlock(&info->lock);
	return retval;
}

1325
int shmem_mmap(struct file *file, struct vm_area_struct *vma)
Linus Torvalds's avatar
Linus Torvalds committed
1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338
{
	file_accessed(file);
	vma->vm_ops = &shmem_vm_ops;
	return 0;
}

static struct inode *
shmem_get_inode(struct super_block *sb, int mode, dev_t dev)
{
	struct inode *inode;
	struct shmem_inode_info *info;
	struct shmem_sb_info *sbinfo = SHMEM_SB(sb);

1339
	if (sbinfo->max_inodes) {
Linus Torvalds's avatar
Linus Torvalds committed
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
		spin_lock(&sbinfo->stat_lock);
		if (!sbinfo->free_inodes) {
			spin_unlock(&sbinfo->stat_lock);
			return NULL;
		}
		sbinfo->free_inodes--;
		spin_unlock(&sbinfo->stat_lock);
	}

	inode = new_inode(sb);
	if (inode) {
		inode->i_mode = mode;
		inode->i_uid = current->fsuid;
		inode->i_gid = current->fsgid;
		inode->i_blocks = 0;
		inode->i_mapping->a_ops = &shmem_aops;
		inode->i_mapping->backing_dev_info = &shmem_backing_dev_info;
		inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME;
		info = SHMEM_I(inode);
		memset(info, 0, (char *)inode - (char *)info);
		spin_lock_init(&info->lock);
		INIT_LIST_HEAD(&info->swaplist);

		switch (mode & S_IFMT) {
		default:
			init_special_inode(inode, mode, dev);
			break;
		case S_IFREG:
			inode->i_op = &shmem_inode_operations;
			inode->i_fop = &shmem_file_operations;
1370 1371
			mpol_shared_policy_init(&info->policy, sbinfo->policy,
							&sbinfo->policy_nodes);
Linus Torvalds's avatar
Linus Torvalds committed
1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384
			break;
		case S_IFDIR:
			inode->i_nlink++;
			/* Some things misbehave if size == 0 on a directory */
			inode->i_size = 2 * BOGO_DIRENT_SIZE;
			inode->i_op = &shmem_dir_inode_operations;
			inode->i_fop = &simple_dir_operations;
			break;
		case S_IFLNK:
			/*
			 * Must not load anything in the rbtree,
			 * mpol_free_shared_policy will not be called.
			 */
1385 1386
			mpol_shared_policy_init(&info->policy, MPOL_DEFAULT,
						NULL);
Linus Torvalds's avatar
Linus Torvalds committed
1387 1388
			break;
		}
1389
	} else if (sbinfo->max_inodes) {
Linus Torvalds's avatar
Linus Torvalds committed
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
		spin_lock(&sbinfo->stat_lock);
		sbinfo->free_inodes++;
		spin_unlock(&sbinfo->stat_lock);
	}
	return inode;
}

#ifdef CONFIG_TMPFS
static struct inode_operations shmem_symlink_inode_operations;
static struct inode_operations shmem_symlink_inline_operations;

/*
 * Normally tmpfs makes no use of shmem_prepare_write, but it
 * lets a tmpfs file be used read-write below the loop driver.
 */
static int
shmem_prepare_write(struct file *file, struct page *page, unsigned offset, unsigned to)
{
	struct inode *inode = page->mapping->host;
	return shmem_getpage(inode, page->index, &page, SGP_WRITE, NULL);
}

static ssize_t
shmem_file_write(struct file *file, const char __user *buf, size_t count, loff_t *ppos)
{
	struct inode	*inode = file->f_dentry->d_inode;
	loff_t		pos;
	unsigned long	written;
	ssize_t		err;

	if ((ssize_t) count < 0)
		return -EINVAL;

	if (!access_ok(VERIFY_READ, buf, count))
		return -EFAULT;

1426
	mutex_lock(&inode->i_mutex);
Linus Torvalds's avatar
Linus Torvalds committed
1427 1428 1429 1430 1431 1432 1433 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 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510

	pos = *ppos;
	written = 0;

	err = generic_write_checks(file, &pos, &count, 0);
	if (err || !count)
		goto out;

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

	inode->i_ctime = inode->i_mtime = CURRENT_TIME;

	do {
		struct page *page = NULL;
		unsigned long bytes, index, offset;
		char *kaddr;
		int left;

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

		/*
		 * We don't hold page lock across copy from user -
		 * what would it guard against? - so no deadlock here.
		 * But it still may be a good idea to prefault below.
		 */

		err = shmem_getpage(inode, index, &page, SGP_WRITE, NULL);
		if (err)
			break;

		left = bytes;
		if (PageHighMem(page)) {
			volatile unsigned char dummy;
			__get_user(dummy, buf);
			__get_user(dummy, buf + bytes - 1);

			kaddr = kmap_atomic(page, KM_USER0);
			left = __copy_from_user_inatomic(kaddr + offset,
							buf, bytes);
			kunmap_atomic(kaddr, KM_USER0);
		}
		if (left) {
			kaddr = kmap(page);
			left = __copy_from_user(kaddr + offset, buf, bytes);
			kunmap(page);
		}

		written += bytes;
		count -= bytes;
		pos += bytes;
		buf += bytes;
		if (pos > inode->i_size)
			i_size_write(inode, pos);

		flush_dcache_page(page);
		set_page_dirty(page);
		mark_page_accessed(page);
		page_cache_release(page);

		if (left) {
			pos -= left;
			written -= left;
			err = -EFAULT;
			break;
		}

		/*
		 * Our dirty pages are not counted in nr_dirty,
		 * and we do not attempt to balance dirty pages.
		 */

		cond_resched();
	} while (count);

	*ppos = pos;
	if (written)
		err = written;
out:
1511
	mutex_unlock(&inode->i_mutex);
Linus Torvalds's avatar
Linus Torvalds committed
1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546
	return err;
}

static void do_shmem_file_read(struct file *filp, loff_t *ppos, read_descriptor_t *desc, read_actor_t actor)
{
	struct inode *inode = filp->f_dentry->d_inode;
	struct address_space *mapping = inode->i_mapping;
	unsigned long index, offset;

	index = *ppos >> PAGE_CACHE_SHIFT;
	offset = *ppos & ~PAGE_CACHE_MASK;

	for (;;) {
		struct page *page = NULL;
		unsigned long end_index, nr, ret;
		loff_t i_size = i_size_read(inode);

		end_index = i_size >> PAGE_CACHE_SHIFT;
		if (index > end_index)
			break;
		if (index == end_index) {
			nr = i_size & ~PAGE_CACHE_MASK;
			if (nr <= offset)
				break;
		}

		desc->error = shmem_getpage(inode, index, &page, SGP_READ, NULL);
		if (desc->error) {
			if (desc->error == -EINVAL)
				desc->error = 0;
			break;
		}

		/*
		 * We must evaluate after, since reads (unlike writes)
1547
		 * are called without i_mutex protection against truncate
Linus Torvalds's avatar
Linus Torvalds committed
1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574
		 */
		nr = PAGE_CACHE_SIZE;
		i_size = i_size_read(inode);
		end_index = i_size >> PAGE_CACHE_SHIFT;
		if (index == end_index) {
			nr = i_size & ~PAGE_CACHE_MASK;
			if (nr <= offset) {
				if (page)
					page_cache_release(page);
				break;
			}
		}
		nr -= offset;

		if (page) {
			/*
			 * 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);
			/*
			 * Mark the page accessed if we read the beginning.
			 */
			if (!offset)
				mark_page_accessed(page);
Nick Piggin's avatar
Nick Piggin committed
1575
		} else {
Linus Torvalds's avatar
Linus Torvalds committed
1576
			page = ZERO_PAGE(0);
Nick Piggin's avatar
Nick Piggin committed
1577 1578
			page_cache_get(page);
		}
Linus Torvalds's avatar
Linus Torvalds committed
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

		/*
		 * 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)
			break;

		cond_resched();
	}

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

static ssize_t shmem_file_read(struct file *filp, char __user *buf, size_t count, loff_t *ppos)
{
	read_descriptor_t desc;

	if ((ssize_t) count < 0)
		return -EINVAL;
	if (!access_ok(VERIFY_WRITE, buf, count))
		return -EFAULT;
	if (!count)
		return 0;

	desc.written = 0;
	desc.count = count;
	desc.arg.buf = buf;
	desc.error = 0;

	do_shmem_file_read(filp, ppos, &desc, file_read_actor);
	if (desc.written)
		return desc.written;
	return desc.error;
}

static ssize_t shmem_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_shmem_file_read(in_file, ppos, &desc, actor);
	if (desc.written)
		return desc.written;
	return desc.error;
}

1647
static int shmem_statfs(struct dentry *dentry, struct kstatfs *buf)
Linus Torvalds's avatar
Linus Torvalds committed
1648
{
1649
	struct shmem_sb_info *sbinfo = SHMEM_SB(dentry->d_sb);
Linus Torvalds's avatar
Linus Torvalds committed
1650 1651 1652 1653

	buf->f_type = TMPFS_MAGIC;
	buf->f_bsize = PAGE_CACHE_SIZE;
	buf->f_namelen = NAME_MAX;
1654 1655
	spin_lock(&sbinfo->stat_lock);
	if (sbinfo->max_blocks) {
Linus Torvalds's avatar
Linus Torvalds committed
1656 1657
		buf->f_blocks = sbinfo->max_blocks;
		buf->f_bavail = buf->f_bfree = sbinfo->free_blocks;
1658 1659
	}
	if (sbinfo->max_inodes) {
Linus Torvalds's avatar
Linus Torvalds committed
1660 1661 1662 1663
		buf->f_files = sbinfo->max_inodes;
		buf->f_ffree = sbinfo->free_inodes;
	}
	/* else leave those fields 0 like simple_statfs */
1664
	spin_unlock(&sbinfo->stat_lock);
Linus Torvalds's avatar
Linus Torvalds committed
1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677
	return 0;
}

/*
 * File creation. Allocate an inode, and we're done..
 */
static int
shmem_mknod(struct inode *dir, struct dentry *dentry, int mode, dev_t dev)
{
	struct inode *inode = shmem_get_inode(dir->i_sb, mode, dev);
	int error = -ENOSPC;

	if (inode) {
1678 1679 1680 1681 1682 1683 1684 1685 1686
		error = security_inode_init_security(inode, dir, NULL, NULL,
						     NULL);
		if (error) {
			if (error != -EOPNOTSUPP) {
				iput(inode);
				return error;
			}
			error = 0;
		}
Linus Torvalds's avatar
Linus Torvalds committed
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
		if (dir->i_mode & S_ISGID) {
			inode->i_gid = dir->i_gid;
			if (S_ISDIR(mode))
				inode->i_mode |= S_ISGID;
		}
		dir->i_size += BOGO_DIRENT_SIZE;
		dir->i_ctime = dir->i_mtime = CURRENT_TIME;
		d_instantiate(dentry, inode);
		dget(dentry); /* Extra count - pin the dentry in core */
	}
	return error;
}

static int shmem_mkdir(struct inode *dir, struct dentry *dentry, int mode)
{
	int error;

	if ((error = shmem_mknod(dir, dentry, mode | S_IFDIR, 0)))
		return error;
	dir->i_nlink++;
	return 0;
}

static int shmem_create(struct inode *dir, struct dentry *dentry, int mode,
		struct nameidata *nd)
{
	return shmem_mknod(dir, dentry, mode | S_IFREG, 0);
}

/*
 * Link a file..
 */
static int shmem_link(struct dentry *old_dentry, struct inode *dir, struct dentry *dentry)
{
	struct inode *inode = old_dentry->d_inode;
	struct shmem_sb_info *sbinfo = SHMEM_SB(inode->i_sb);

	/*
	 * No ordinary (disk based) filesystem counts links as inodes;
	 * but each new link needs a new dentry, pinning lowmem, and
	 * tmpfs dentries cannot be pruned until they are unlinked.
	 */
1729
	if (sbinfo->max_inodes) {
Linus Torvalds's avatar
Linus Torvalds committed
1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753
		spin_lock(&sbinfo->stat_lock);
		if (!sbinfo->free_inodes) {
			spin_unlock(&sbinfo->stat_lock);
			return -ENOSPC;
		}
		sbinfo->free_inodes--;
		spin_unlock(&sbinfo->stat_lock);
	}

	dir->i_size += BOGO_DIRENT_SIZE;
	inode->i_ctime = dir->i_ctime = dir->i_mtime = CURRENT_TIME;
	inode->i_nlink++;
	atomic_inc(&inode->i_count);	/* New dentry reference */
	dget(dentry);		/* Extra pinning count for the created dentry */
	d_instantiate(dentry, inode);
	return 0;
}

static int shmem_unlink(struct inode *dir, struct dentry *dentry)
{
	struct inode *inode = dentry->d_inode;

	if (inode->i_nlink > 1 && !S_ISDIR(inode->i_mode)) {
		struct shmem_sb_info *sbinfo = SHMEM_SB(inode->i_sb);
1754
		if (sbinfo->max_inodes) {
Linus Torvalds's avatar
Linus Torvalds committed
1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772
			spin_lock(&sbinfo->stat_lock);
			sbinfo->free_inodes++;
			spin_unlock(&sbinfo->stat_lock);
		}
	}

	dir->i_size -= BOGO_DIRENT_SIZE;
	inode->i_ctime = dir->i_ctime = dir->i_mtime = CURRENT_TIME;
	inode->i_nlink--;
	dput(dentry);	/* Undo the count from "create" - this does all the work */
	return 0;
}

static int shmem_rmdir(struct inode *dir, struct dentry *dentry)
{
	if (!simple_empty(dentry))
		return -ENOTEMPTY;

1773
	dentry->d_inode->i_nlink--;
Linus Torvalds's avatar
Linus Torvalds committed
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
	dir->i_nlink--;
	return shmem_unlink(dir, dentry);
}

/*
 * The VFS layer already does all the dentry stuff for rename,
 * we just have to decrement the usage count for the target if
 * it exists so that the VFS layer correctly free's it when it
 * gets overwritten.
 */
static int shmem_rename(struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry)
{
	struct inode *inode = old_dentry->d_inode;
	int they_are_dirs = S_ISDIR(inode->i_mode);

	if (!simple_empty(new_dentry))
		return -ENOTEMPTY;

	if (new_dentry->d_inode) {
		(void) shmem_unlink(new_dir, new_dentry);
		if (they_are_dirs)
			old_dir->i_nlink--;
	} else if (they_are_dirs) {
		old_dir->i_nlink--;
		new_dir->i_nlink++;
	}

	old_dir->i_size -= BOGO_DIRENT_SIZE;
	new_dir->i_size += BOGO_DIRENT_SIZE;
	old_dir->i_ctime = old_dir->i_mtime =
	new_dir->i_ctime = new_dir->i_mtime =
	inode->i_ctime = CURRENT_TIME;
	return 0;
}

static int shmem_symlink(struct inode *dir, struct dentry *dentry, const char *symname)
{
	int error;
	int len;
	struct inode *inode;
	struct page *page = NULL;
	char *kaddr;
	struct shmem_inode_info *info;

	len = strlen(symname) + 1;
	if (len > PAGE_CACHE_SIZE)
		return -ENAMETOOLONG;

	inode = shmem_get_inode(dir->i_sb, S_IFLNK|S_IRWXUGO, 0);
	if (!inode)
		return -ENOSPC;

1826 1827 1828 1829 1830 1831 1832 1833 1834 1835
	error = security_inode_init_security(inode, dir, NULL, NULL,
					     NULL);
	if (error) {
		if (error != -EOPNOTSUPP) {