super.c 37.6 KB
Newer Older
L
Linus Torvalds 已提交
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20
/*
 *  linux/fs/ext2/super.c
 *
 * Copyright (C) 1992, 1993, 1994, 1995
 * Remy Card (card@masi.ibp.fr)
 * Laboratoire MASI - Institut Blaise Pascal
 * Universite Pierre et Marie Curie (Paris VI)
 *
 *  from
 *
 *  linux/fs/minix/inode.c
 *
 *  Copyright (C) 1991, 1992  Linus Torvalds
 *
 *  Big-endian to little-endian byte-swapping/bitmaps by
 *        David S. Miller (davem@caip.rutgers.edu), 1995
 */

#include <linux/module.h>
#include <linux/string.h>
21
#include <linux/fs.h>
L
Linus Torvalds 已提交
22 23 24 25 26 27
#include <linux/slab.h>
#include <linux/init.h>
#include <linux/blkdev.h>
#include <linux/parser.h>
#include <linux/random.h>
#include <linux/buffer_head.h>
28
#include <linux/exportfs.h>
L
Linus Torvalds 已提交
29 30
#include <linux/smp_lock.h>
#include <linux/vfs.h>
31 32
#include <linux/seq_file.h>
#include <linux/mount.h>
L
Linus Torvalds 已提交
33 34 35 36
#include <asm/uaccess.h>
#include "ext2.h"
#include "xattr.h"
#include "acl.h"
37
#include "xip.h"
L
Linus Torvalds 已提交
38 39 40 41

static void ext2_sync_super(struct super_block *sb,
			    struct ext2_super_block *es);
static int ext2_remount (struct super_block * sb, int * flags, char * data);
42
static int ext2_statfs (struct dentry * dentry, struct kstatfs * buf);
L
Linus Torvalds 已提交
43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138

void ext2_error (struct super_block * sb, const char * function,
		 const char * fmt, ...)
{
	va_list args;
	struct ext2_sb_info *sbi = EXT2_SB(sb);
	struct ext2_super_block *es = sbi->s_es;

	if (!(sb->s_flags & MS_RDONLY)) {
		sbi->s_mount_state |= EXT2_ERROR_FS;
		es->s_state =
			cpu_to_le16(le16_to_cpu(es->s_state) | EXT2_ERROR_FS);
		ext2_sync_super(sb, es);
	}

	va_start(args, fmt);
	printk(KERN_CRIT "EXT2-fs error (device %s): %s: ",sb->s_id, function);
	vprintk(fmt, args);
	printk("\n");
	va_end(args);

	if (test_opt(sb, ERRORS_PANIC))
		panic("EXT2-fs panic from previous error\n");
	if (test_opt(sb, ERRORS_RO)) {
		printk("Remounting filesystem read-only\n");
		sb->s_flags |= MS_RDONLY;
	}
}

void ext2_warning (struct super_block * sb, const char * function,
		   const char * fmt, ...)
{
	va_list args;

	va_start(args, fmt);
	printk(KERN_WARNING "EXT2-fs warning (device %s): %s: ",
	       sb->s_id, function);
	vprintk(fmt, args);
	printk("\n");
	va_end(args);
}

void ext2_update_dynamic_rev(struct super_block *sb)
{
	struct ext2_super_block *es = EXT2_SB(sb)->s_es;

	if (le32_to_cpu(es->s_rev_level) > EXT2_GOOD_OLD_REV)
		return;

	ext2_warning(sb, __FUNCTION__,
		     "updating to rev %d because of new feature flag, "
		     "running e2fsck is recommended",
		     EXT2_DYNAMIC_REV);

	es->s_first_ino = cpu_to_le32(EXT2_GOOD_OLD_FIRST_INO);
	es->s_inode_size = cpu_to_le16(EXT2_GOOD_OLD_INODE_SIZE);
	es->s_rev_level = cpu_to_le32(EXT2_DYNAMIC_REV);
	/* leave es->s_feature_*compat flags alone */
	/* es->s_uuid will be set by e2fsck if empty */

	/*
	 * The rest of the superblock fields should be zero, and if not it
	 * means they are likely already in use, so leave them alone.  We
	 * can leave it up to e2fsck to clean up any inconsistencies there.
	 */
}

static void ext2_put_super (struct super_block * sb)
{
	int db_count;
	int i;
	struct ext2_sb_info *sbi = EXT2_SB(sb);

	ext2_xattr_put_super(sb);
	if (!(sb->s_flags & MS_RDONLY)) {
		struct ext2_super_block *es = sbi->s_es;

		es->s_state = cpu_to_le16(sbi->s_mount_state);
		ext2_sync_super(sb, es);
	}
	db_count = sbi->s_gdb_count;
	for (i = 0; i < db_count; i++)
		if (sbi->s_group_desc[i])
			brelse (sbi->s_group_desc[i]);
	kfree(sbi->s_group_desc);
	kfree(sbi->s_debts);
	percpu_counter_destroy(&sbi->s_freeblocks_counter);
	percpu_counter_destroy(&sbi->s_freeinodes_counter);
	percpu_counter_destroy(&sbi->s_dirs_counter);
	brelse (sbi->s_sbh);
	sb->s_fs_info = NULL;
	kfree(sbi);

	return;
}

139
static struct kmem_cache * ext2_inode_cachep;
L
Linus Torvalds 已提交
140 141 142 143

static struct inode *ext2_alloc_inode(struct super_block *sb)
{
	struct ext2_inode_info *ei;
144
	ei = (struct ext2_inode_info *)kmem_cache_alloc(ext2_inode_cachep, GFP_KERNEL);
L
Linus Torvalds 已提交
145 146 147 148 149 150 151 152 153 154 155 156 157 158 159
	if (!ei)
		return NULL;
#ifdef CONFIG_EXT2_FS_POSIX_ACL
	ei->i_acl = EXT2_ACL_NOT_CACHED;
	ei->i_default_acl = EXT2_ACL_NOT_CACHED;
#endif
	ei->vfs_inode.i_version = 1;
	return &ei->vfs_inode;
}

static void ext2_destroy_inode(struct inode *inode)
{
	kmem_cache_free(ext2_inode_cachep, EXT2_I(inode));
}

160
static void init_once(struct kmem_cache * cachep, void *foo)
L
Linus Torvalds 已提交
161 162 163
{
	struct ext2_inode_info *ei = (struct ext2_inode_info *) foo;

C
Christoph Lameter 已提交
164
	rwlock_init(&ei->i_meta_lock);
L
Linus Torvalds 已提交
165
#ifdef CONFIG_EXT2_FS_XATTR
C
Christoph Lameter 已提交
166
	init_rwsem(&ei->xattr_sem);
L
Linus Torvalds 已提交
167
#endif
C
Christoph Lameter 已提交
168
	inode_init_once(&ei->vfs_inode);
L
Linus Torvalds 已提交
169
}
170

L
Linus Torvalds 已提交
171 172 173 174
static int init_inodecache(void)
{
	ext2_inode_cachep = kmem_cache_create("ext2_inode_cache",
					     sizeof(struct ext2_inode_info),
175 176
					     0, (SLAB_RECLAIM_ACCOUNT|
						SLAB_MEM_SPREAD),
177
					     init_once);
L
Linus Torvalds 已提交
178 179 180 181 182 183 184
	if (ext2_inode_cachep == NULL)
		return -ENOMEM;
	return 0;
}

static void destroy_inodecache(void)
{
185
	kmem_cache_destroy(ext2_inode_cachep);
L
Linus Torvalds 已提交
186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203
}

static void ext2_clear_inode(struct inode *inode)
{
#ifdef CONFIG_EXT2_FS_POSIX_ACL
	struct ext2_inode_info *ei = EXT2_I(inode);

	if (ei->i_acl && ei->i_acl != EXT2_ACL_NOT_CACHED) {
		posix_acl_release(ei->i_acl);
		ei->i_acl = EXT2_ACL_NOT_CACHED;
	}
	if (ei->i_default_acl && ei->i_default_acl != EXT2_ACL_NOT_CACHED) {
		posix_acl_release(ei->i_default_acl);
		ei->i_default_acl = EXT2_ACL_NOT_CACHED;
	}
#endif
}

204 205
static int ext2_show_options(struct seq_file *seq, struct vfsmount *vfs)
{
M
Miklos Szeredi 已提交
206 207 208 209
	struct super_block *sb = vfs->mnt_sb;
	struct ext2_sb_info *sbi = EXT2_SB(sb);
	struct ext2_super_block *es = sbi->s_es;
	unsigned long def_mount_opts;
210

M
Miklos Szeredi 已提交
211 212 213 214 215 216 217
	def_mount_opts = le32_to_cpu(es->s_default_mount_opts);

	if (sbi->s_sb_block != 1)
		seq_printf(seq, ",sb=%lu", sbi->s_sb_block);
	if (test_opt(sb, MINIX_DF))
		seq_puts(seq, ",minixdf");
	if (test_opt(sb, GRPID))
218
		seq_puts(seq, ",grpid");
M
Miklos Szeredi 已提交
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
	if (!test_opt(sb, GRPID) && (def_mount_opts & EXT2_DEFM_BSDGROUPS))
		seq_puts(seq, ",nogrpid");
	if (sbi->s_resuid != EXT2_DEF_RESUID ||
	    le16_to_cpu(es->s_def_resuid) != EXT2_DEF_RESUID) {
		seq_printf(seq, ",resuid=%u", sbi->s_resuid);
	}
	if (sbi->s_resgid != EXT2_DEF_RESGID ||
	    le16_to_cpu(es->s_def_resgid) != EXT2_DEF_RESGID) {
		seq_printf(seq, ",resgid=%u", sbi->s_resgid);
	}
	if (test_opt(sb, ERRORS_CONT)) {
		int def_errors = le16_to_cpu(es->s_errors);

		if (def_errors == EXT2_ERRORS_PANIC ||
		    def_errors == EXT2_ERRORS_RO) {
			seq_puts(seq, ",errors=continue");
		}
	}
	if (test_opt(sb, ERRORS_RO))
		seq_puts(seq, ",errors=remount-ro");
	if (test_opt(sb, ERRORS_PANIC))
		seq_puts(seq, ",errors=panic");
	if (test_opt(sb, NO_UID32))
		seq_puts(seq, ",nouid32");
	if (test_opt(sb, DEBUG))
		seq_puts(seq, ",debug");
	if (test_opt(sb, OLDALLOC))
		seq_puts(seq, ",oldalloc");

#ifdef CONFIG_EXT2_FS_XATTR
	if (test_opt(sb, XATTR_USER))
		seq_puts(seq, ",user_xattr");
	if (!test_opt(sb, XATTR_USER) &&
	    (def_mount_opts & EXT2_DEFM_XATTR_USER)) {
		seq_puts(seq, ",nouser_xattr");
	}
#endif

#ifdef CONFIG_EXT2_FS_POSIX_ACL
	if (test_opt(sb, POSIX_ACL))
		seq_puts(seq, ",acl");
	if (!test_opt(sb, POSIX_ACL) && (def_mount_opts & EXT2_DEFM_ACL))
		seq_puts(seq, ",noacl");
#endif

	if (test_opt(sb, NOBH))
		seq_puts(seq, ",nobh");
266 267 268 269 270 271 272 273 274

#if defined(CONFIG_QUOTA)
	if (sbi->s_mount_opt & EXT2_MOUNT_USRQUOTA)
		seq_puts(seq, ",usrquota");

	if (sbi->s_mount_opt & EXT2_MOUNT_GRPQUOTA)
		seq_puts(seq, ",grpquota");
#endif

275 276 277 278 279
#if defined(CONFIG_EXT2_FS_XIP)
	if (sbi->s_mount_opt & EXT2_MOUNT_XIP)
		seq_puts(seq, ",xip");
#endif

280 281 282
	return 0;
}

L
Linus Torvalds 已提交
283 284 285 286 287
#ifdef CONFIG_QUOTA
static ssize_t ext2_quota_read(struct super_block *sb, int type, char *data, size_t len, loff_t off);
static ssize_t ext2_quota_write(struct super_block *sb, int type, const char *data, size_t len, loff_t off);
#endif

288
static const struct super_operations ext2_sops = {
L
Linus Torvalds 已提交
289 290 291 292
	.alloc_inode	= ext2_alloc_inode,
	.destroy_inode	= ext2_destroy_inode,
	.read_inode	= ext2_read_inode,
	.write_inode	= ext2_write_inode,
293
	.put_inode	= ext2_put_inode,
L
Linus Torvalds 已提交
294 295 296 297 298 299
	.delete_inode	= ext2_delete_inode,
	.put_super	= ext2_put_super,
	.write_super	= ext2_write_super,
	.statfs		= ext2_statfs,
	.remount_fs	= ext2_remount,
	.clear_inode	= ext2_clear_inode,
300
	.show_options	= ext2_show_options,
L
Linus Torvalds 已提交
301 302 303 304 305 306
#ifdef CONFIG_QUOTA
	.quota_read	= ext2_quota_read,
	.quota_write	= ext2_quota_write,
#endif
};

307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344
static struct dentry *ext2_get_dentry(struct super_block *sb, void *vobjp)
{
	__u32 *objp = vobjp;
	unsigned long ino = objp[0];
	__u32 generation = objp[1];
	struct inode *inode;
	struct dentry *result;

	if (ino < EXT2_FIRST_INO(sb) && ino != EXT2_ROOT_INO)
		return ERR_PTR(-ESTALE);
	if (ino > le32_to_cpu(EXT2_SB(sb)->s_es->s_inodes_count))
		return ERR_PTR(-ESTALE);

	/* iget isn't really right if the inode is currently unallocated!!
	 * ext2_read_inode currently does appropriate checks, but
	 * it might be "neater" to call ext2_get_inode first and check
	 * if the inode is valid.....
	 */
	inode = iget(sb, ino);
	if (inode == NULL)
		return ERR_PTR(-ENOMEM);
	if (is_bad_inode(inode) ||
	    (generation && inode->i_generation != generation)) {
		/* we didn't find the right inode.. */
		iput(inode);
		return ERR_PTR(-ESTALE);
	}
	/* now to find a dentry.
	 * If possible, get a well-connected one
	 */
	result = d_alloc_anon(inode);
	if (!result) {
		iput(inode);
		return ERR_PTR(-ENOMEM);
	}
	return result;
}

L
Linus Torvalds 已提交
345 346 347 348 349 350 351
/* Yes, most of these are left as NULL!!
 * A NULL value implies the default, which works with ext2-like file
 * systems, but can be improved upon.
 * Currently only get_parent is required.
 */
static struct export_operations ext2_export_ops = {
	.get_parent = ext2_get_parent,
352
	.get_dentry = ext2_get_dentry,
L
Linus Torvalds 已提交
353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376
};

static unsigned long get_sb_block(void **data)
{
	unsigned long 	sb_block;
	char 		*options = (char *) *data;

	if (!options || strncmp(options, "sb=", 3) != 0)
		return 1;	/* Default location */
	options += 3;
	sb_block = simple_strtoul(options, &options, 0);
	if (*options && *options != ',') {
		printk("EXT2-fs: Invalid sb specification: %s\n",
		       (char *) *data);
		return 1;
	}
	if (*options == ',')
		options++;
	*data = (void *) options;
	return sb_block;
}

enum {
	Opt_bsd_df, Opt_minix_df, Opt_grpid, Opt_nogrpid,
377
	Opt_resgid, Opt_resuid, Opt_sb, Opt_err_cont, Opt_err_panic,
A
Adrian Bunk 已提交
378
	Opt_err_ro, Opt_nouid32, Opt_nocheck, Opt_debug,
379 380 381
	Opt_oldalloc, Opt_orlov, Opt_nobh, Opt_user_xattr, Opt_nouser_xattr,
	Opt_acl, Opt_noacl, Opt_xip, Opt_ignore, Opt_err, Opt_quota,
	Opt_usrquota, Opt_grpquota
L
Linus Torvalds 已提交
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
};

static match_table_t tokens = {
	{Opt_bsd_df, "bsddf"},
	{Opt_minix_df, "minixdf"},
	{Opt_grpid, "grpid"},
	{Opt_grpid, "bsdgroups"},
	{Opt_nogrpid, "nogrpid"},
	{Opt_nogrpid, "sysvgroups"},
	{Opt_resgid, "resgid=%u"},
	{Opt_resuid, "resuid=%u"},
	{Opt_sb, "sb=%u"},
	{Opt_err_cont, "errors=continue"},
	{Opt_err_panic, "errors=panic"},
	{Opt_err_ro, "errors=remount-ro"},
	{Opt_nouid32, "nouid32"},
	{Opt_nocheck, "check=none"},
	{Opt_nocheck, "nocheck"},
	{Opt_debug, "debug"},
	{Opt_oldalloc, "oldalloc"},
	{Opt_orlov, "orlov"},
	{Opt_nobh, "nobh"},
	{Opt_user_xattr, "user_xattr"},
	{Opt_nouser_xattr, "nouser_xattr"},
	{Opt_acl, "acl"},
	{Opt_noacl, "noacl"},
408
	{Opt_xip, "xip"},
409
	{Opt_grpquota, "grpquota"},
L
Linus Torvalds 已提交
410
	{Opt_ignore, "noquota"},
411 412
	{Opt_quota, "quota"},
	{Opt_usrquota, "usrquota"},
L
Linus Torvalds 已提交
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
	{Opt_err, NULL}
};

static int parse_options (char * options,
			  struct ext2_sb_info *sbi)
{
	char * p;
	substring_t args[MAX_OPT_ARGS];
	int option;

	if (!options)
		return 1;

	while ((p = strsep (&options, ",")) != NULL) {
		int token;
		if (!*p)
			continue;

		token = match_token(p, tokens, args);
		switch (token) {
		case Opt_bsd_df:
			clear_opt (sbi->s_mount_opt, MINIX_DF);
			break;
		case Opt_minix_df:
			set_opt (sbi->s_mount_opt, MINIX_DF);
			break;
		case Opt_grpid:
			set_opt (sbi->s_mount_opt, GRPID);
			break;
		case Opt_nogrpid:
			clear_opt (sbi->s_mount_opt, GRPID);
			break;
		case Opt_resuid:
			if (match_int(&args[0], &option))
				return 0;
			sbi->s_resuid = option;
			break;
		case Opt_resgid:
			if (match_int(&args[0], &option))
				return 0;
			sbi->s_resgid = option;
			break;
		case Opt_sb:
			/* handled by get_sb_block() instead of here */
			/* *sb_block = match_int(&args[0]); */
			break;
		case Opt_err_panic:
V
Vasily Averin 已提交
460 461 462
			clear_opt (sbi->s_mount_opt, ERRORS_CONT);
			clear_opt (sbi->s_mount_opt, ERRORS_RO);
			set_opt (sbi->s_mount_opt, ERRORS_PANIC);
L
Linus Torvalds 已提交
463 464
			break;
		case Opt_err_ro:
V
Vasily Averin 已提交
465 466 467
			clear_opt (sbi->s_mount_opt, ERRORS_CONT);
			clear_opt (sbi->s_mount_opt, ERRORS_PANIC);
			set_opt (sbi->s_mount_opt, ERRORS_RO);
L
Linus Torvalds 已提交
468 469
			break;
		case Opt_err_cont:
V
Vasily Averin 已提交
470 471 472
			clear_opt (sbi->s_mount_opt, ERRORS_RO);
			clear_opt (sbi->s_mount_opt, ERRORS_PANIC);
			set_opt (sbi->s_mount_opt, ERRORS_CONT);
L
Linus Torvalds 已提交
473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517
			break;
		case Opt_nouid32:
			set_opt (sbi->s_mount_opt, NO_UID32);
			break;
		case Opt_nocheck:
			clear_opt (sbi->s_mount_opt, CHECK);
			break;
		case Opt_debug:
			set_opt (sbi->s_mount_opt, DEBUG);
			break;
		case Opt_oldalloc:
			set_opt (sbi->s_mount_opt, OLDALLOC);
			break;
		case Opt_orlov:
			clear_opt (sbi->s_mount_opt, OLDALLOC);
			break;
		case Opt_nobh:
			set_opt (sbi->s_mount_opt, NOBH);
			break;
#ifdef CONFIG_EXT2_FS_XATTR
		case Opt_user_xattr:
			set_opt (sbi->s_mount_opt, XATTR_USER);
			break;
		case Opt_nouser_xattr:
			clear_opt (sbi->s_mount_opt, XATTR_USER);
			break;
#else
		case Opt_user_xattr:
		case Opt_nouser_xattr:
			printk("EXT2 (no)user_xattr options not supported\n");
			break;
#endif
#ifdef CONFIG_EXT2_FS_POSIX_ACL
		case Opt_acl:
			set_opt(sbi->s_mount_opt, POSIX_ACL);
			break;
		case Opt_noacl:
			clear_opt(sbi->s_mount_opt, POSIX_ACL);
			break;
#else
		case Opt_acl:
		case Opt_noacl:
			printk("EXT2 (no)acl options not supported\n");
			break;
#endif
518 519 520 521 522 523 524
		case Opt_xip:
#ifdef CONFIG_EXT2_FS_XIP
			set_opt (sbi->s_mount_opt, XIP);
#else
			printk("EXT2 xip option not supported\n");
#endif
			break;
525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544

#if defined(CONFIG_QUOTA)
		case Opt_quota:
		case Opt_usrquota:
			set_opt(sbi->s_mount_opt, USRQUOTA);
			break;

		case Opt_grpquota:
			set_opt(sbi->s_mount_opt, GRPQUOTA);
			break;
#else
		case Opt_quota:
		case Opt_usrquota:
		case Opt_grpquota:
			printk(KERN_ERR
				"EXT2-fs: quota operations not supported.\n");

			break;
#endif

L
Linus Torvalds 已提交
545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603
		case Opt_ignore:
			break;
		default:
			return 0;
		}
	}
	return 1;
}

static int ext2_setup_super (struct super_block * sb,
			      struct ext2_super_block * es,
			      int read_only)
{
	int res = 0;
	struct ext2_sb_info *sbi = EXT2_SB(sb);

	if (le32_to_cpu(es->s_rev_level) > EXT2_MAX_SUPP_REV) {
		printk ("EXT2-fs warning: revision level too high, "
			"forcing read-only mode\n");
		res = MS_RDONLY;
	}
	if (read_only)
		return res;
	if (!(sbi->s_mount_state & EXT2_VALID_FS))
		printk ("EXT2-fs warning: mounting unchecked fs, "
			"running e2fsck is recommended\n");
	else if ((sbi->s_mount_state & EXT2_ERROR_FS))
		printk ("EXT2-fs warning: mounting fs with errors, "
			"running e2fsck is recommended\n");
	else if ((__s16) le16_to_cpu(es->s_max_mnt_count) >= 0 &&
		 le16_to_cpu(es->s_mnt_count) >=
		 (unsigned short) (__s16) le16_to_cpu(es->s_max_mnt_count))
		printk ("EXT2-fs warning: maximal mount count reached, "
			"running e2fsck is recommended\n");
	else if (le32_to_cpu(es->s_checkinterval) &&
		(le32_to_cpu(es->s_lastcheck) + le32_to_cpu(es->s_checkinterval) <= get_seconds()))
		printk ("EXT2-fs warning: checktime reached, "
			"running e2fsck is recommended\n");
	if (!le16_to_cpu(es->s_max_mnt_count))
		es->s_max_mnt_count = cpu_to_le16(EXT2_DFL_MAX_MNT_COUNT);
	es->s_mnt_count=cpu_to_le16(le16_to_cpu(es->s_mnt_count) + 1);
	ext2_write_super(sb);
	if (test_opt (sb, DEBUG))
		printk ("[EXT II FS %s, %s, bs=%lu, fs=%lu, gc=%lu, "
			"bpg=%lu, ipg=%lu, mo=%04lx]\n",
			EXT2FS_VERSION, EXT2FS_DATE, sb->s_blocksize,
			sbi->s_frag_size,
			sbi->s_groups_count,
			EXT2_BLOCKS_PER_GROUP(sb),
			EXT2_INODES_PER_GROUP(sb),
			sbi->s_mount_opt);
	return res;
}

static int ext2_check_descriptors (struct super_block * sb)
{
	int i;
	int desc_block = 0;
	struct ext2_sb_info *sbi = EXT2_SB(sb);
E
Eric Sandeen 已提交
604 605
	unsigned long first_block = le32_to_cpu(sbi->s_es->s_first_data_block);
	unsigned long last_block;
L
Linus Torvalds 已提交
606 607 608 609 610 611
	struct ext2_group_desc * gdp = NULL;

	ext2_debug ("Checking group descriptors");

	for (i = 0; i < sbi->s_groups_count; i++)
	{
E
Eric Sandeen 已提交
612 613 614 615 616 617
		if (i == sbi->s_groups_count - 1)
			last_block = le32_to_cpu(sbi->s_es->s_blocks_count) - 1;
		else
			last_block = first_block +
				(EXT2_BLOCKS_PER_GROUP(sb) - 1);

L
Linus Torvalds 已提交
618 619
		if ((i % EXT2_DESC_PER_BLOCK(sb)) == 0)
			gdp = (struct ext2_group_desc *) sbi->s_group_desc[desc_block++]->b_data;
E
Eric Sandeen 已提交
620 621
		if (le32_to_cpu(gdp->bg_block_bitmap) < first_block ||
		    le32_to_cpu(gdp->bg_block_bitmap) > last_block)
L
Linus Torvalds 已提交
622 623 624 625 626 627 628
		{
			ext2_error (sb, "ext2_check_descriptors",
				    "Block bitmap for group %d"
				    " not in group (block %lu)!",
				    i, (unsigned long) le32_to_cpu(gdp->bg_block_bitmap));
			return 0;
		}
E
Eric Sandeen 已提交
629 630
		if (le32_to_cpu(gdp->bg_inode_bitmap) < first_block ||
		    le32_to_cpu(gdp->bg_inode_bitmap) > last_block)
L
Linus Torvalds 已提交
631 632 633 634 635 636 637
		{
			ext2_error (sb, "ext2_check_descriptors",
				    "Inode bitmap for group %d"
				    " not in group (block %lu)!",
				    i, (unsigned long) le32_to_cpu(gdp->bg_inode_bitmap));
			return 0;
		}
E
Eric Sandeen 已提交
638
		if (le32_to_cpu(gdp->bg_inode_table) < first_block ||
639
		    le32_to_cpu(gdp->bg_inode_table) + sbi->s_itb_per_group - 1 >
E
Eric Sandeen 已提交
640
		    last_block)
L
Linus Torvalds 已提交
641 642 643 644 645 646 647
		{
			ext2_error (sb, "ext2_check_descriptors",
				    "Inode table for group %d"
				    " not in group (block %lu)!",
				    i, (unsigned long) le32_to_cpu(gdp->bg_inode_table));
			return 0;
		}
E
Eric Sandeen 已提交
648
		first_block += EXT2_BLOCKS_PER_GROUP(sb);
L
Linus Torvalds 已提交
649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711
		gdp++;
	}
	return 1;
}

/*
 * Maximal file size.  There is a direct, and {,double-,triple-}indirect
 * block limit, and also a limit of (2^32 - 1) 512-byte sectors in i_blocks.
 * We need to be 1 filesystem block less than the 2^32 sector limit.
 */
static loff_t ext2_max_size(int bits)
{
	loff_t res = EXT2_NDIR_BLOCKS;
	/* This constant is calculated to be the largest file size for a
	 * dense, 4k-blocksize file such that the total number of
	 * sectors in the file, including data and all indirect blocks,
	 * does not exceed 2^32. */
	const loff_t upper_limit = 0x1ff7fffd000LL;

	res += 1LL << (bits-2);
	res += 1LL << (2*(bits-2));
	res += 1LL << (3*(bits-2));
	res <<= bits;
	if (res > upper_limit)
		res = upper_limit;
	return res;
}

static unsigned long descriptor_loc(struct super_block *sb,
				    unsigned long logic_sb_block,
				    int nr)
{
	struct ext2_sb_info *sbi = EXT2_SB(sb);
	unsigned long bg, first_data_block, first_meta_bg;
	int has_super = 0;
	
	first_data_block = le32_to_cpu(sbi->s_es->s_first_data_block);
	first_meta_bg = le32_to_cpu(sbi->s_es->s_first_meta_bg);

	if (!EXT2_HAS_INCOMPAT_FEATURE(sb, EXT2_FEATURE_INCOMPAT_META_BG) ||
	    nr < first_meta_bg)
		return (logic_sb_block + nr + 1);
	bg = sbi->s_desc_per_block * nr;
	if (ext2_bg_has_super(sb, bg))
		has_super = 1;
	return (first_data_block + has_super + (bg * sbi->s_blocks_per_group));
}

static int ext2_fill_super(struct super_block *sb, void *data, int silent)
{
	struct buffer_head * bh;
	struct ext2_sb_info * sbi;
	struct ext2_super_block * es;
	struct inode *root;
	unsigned long block;
	unsigned long sb_block = get_sb_block(&data);
	unsigned long logic_sb_block;
	unsigned long offset = 0;
	unsigned long def_mount_opts;
	int blocksize = BLOCK_SIZE;
	int db_count;
	int i, j;
	__le32 features;
712
	int err;
L
Linus Torvalds 已提交
713

714
	sbi = kzalloc(sizeof(*sbi), GFP_KERNEL);
L
Linus Torvalds 已提交
715 716 717
	if (!sbi)
		return -ENOMEM;
	sb->s_fs_info = sbi;
M
Miklos Szeredi 已提交
718
	sbi->s_sb_block = sb_block;
L
Linus Torvalds 已提交
719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766

	/*
	 * See what the current blocksize for the device is, and
	 * use that as the blocksize.  Otherwise (or if the blocksize
	 * is smaller than the default) use the default.
	 * This is important for devices that have a hardware
	 * sectorsize that is larger than the default.
	 */
	blocksize = sb_min_blocksize(sb, BLOCK_SIZE);
	if (!blocksize) {
		printk ("EXT2-fs: unable to set blocksize\n");
		goto failed_sbi;
	}

	/*
	 * If the superblock doesn't start on a hardware sector boundary,
	 * calculate the offset.  
	 */
	if (blocksize != BLOCK_SIZE) {
		logic_sb_block = (sb_block*BLOCK_SIZE) / blocksize;
		offset = (sb_block*BLOCK_SIZE) % blocksize;
	} else {
		logic_sb_block = sb_block;
	}

	if (!(bh = sb_bread(sb, logic_sb_block))) {
		printk ("EXT2-fs: unable to read superblock\n");
		goto failed_sbi;
	}
	/*
	 * Note: s_es must be initialized as soon as possible because
	 *       some ext2 macro-instructions depend on its value
	 */
	es = (struct ext2_super_block *) (((char *)bh->b_data) + offset);
	sbi->s_es = es;
	sb->s_magic = le16_to_cpu(es->s_magic);

	if (sb->s_magic != EXT2_SUPER_MAGIC)
		goto cantfind_ext2;

	/* Set defaults before we parse the mount options */
	def_mount_opts = le32_to_cpu(es->s_default_mount_opts);
	if (def_mount_opts & EXT2_DEFM_DEBUG)
		set_opt(sbi->s_mount_opt, DEBUG);
	if (def_mount_opts & EXT2_DEFM_BSDGROUPS)
		set_opt(sbi->s_mount_opt, GRPID);
	if (def_mount_opts & EXT2_DEFM_UID16)
		set_opt(sbi->s_mount_opt, NO_UID32);
767
#ifdef CONFIG_EXT2_FS_XATTR
L
Linus Torvalds 已提交
768 769
	if (def_mount_opts & EXT2_DEFM_XATTR_USER)
		set_opt(sbi->s_mount_opt, XATTR_USER);
770 771
#endif
#ifdef CONFIG_EXT2_FS_POSIX_ACL
L
Linus Torvalds 已提交
772 773
	if (def_mount_opts & EXT2_DEFM_ACL)
		set_opt(sbi->s_mount_opt, POSIX_ACL);
774
#endif
L
Linus Torvalds 已提交
775 776 777 778 779
	
	if (le16_to_cpu(sbi->s_es->s_errors) == EXT2_ERRORS_PANIC)
		set_opt(sbi->s_mount_opt, ERRORS_PANIC);
	else if (le16_to_cpu(sbi->s_es->s_errors) == EXT2_ERRORS_RO)
		set_opt(sbi->s_mount_opt, ERRORS_RO);
V
Vasily Averin 已提交
780 781
	else
		set_opt(sbi->s_mount_opt, ERRORS_CONT);
L
Linus Torvalds 已提交
782 783 784 785 786 787 788 789 790 791 792

	sbi->s_resuid = le16_to_cpu(es->s_def_resuid);
	sbi->s_resgid = le16_to_cpu(es->s_def_resgid);
	
	if (!parse_options ((char *) data, sbi))
		goto failed_mount;

	sb->s_flags = (sb->s_flags & ~MS_POSIXACL) |
		((EXT2_SB(sb)->s_mount_opt & EXT2_MOUNT_POSIX_ACL) ?
		 MS_POSIXACL : 0);

793 794 795
	ext2_xip_verify_sb(sb); /* see if bdev supports xip, unset
				    EXT2_MOUNT_XIP if not */

L
Linus Torvalds 已提交
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
	if (le32_to_cpu(es->s_rev_level) == EXT2_GOOD_OLD_REV &&
	    (EXT2_HAS_COMPAT_FEATURE(sb, ~0U) ||
	     EXT2_HAS_RO_COMPAT_FEATURE(sb, ~0U) ||
	     EXT2_HAS_INCOMPAT_FEATURE(sb, ~0U)))
		printk("EXT2-fs warning: feature flags set on rev 0 fs, "
		       "running e2fsck is recommended\n");
	/*
	 * Check feature flags regardless of the revision level, since we
	 * previously didn't change the revision level when setting the flags,
	 * so there is a chance incompat flags are set on a rev 0 filesystem.
	 */
	features = EXT2_HAS_INCOMPAT_FEATURE(sb, ~EXT2_FEATURE_INCOMPAT_SUPP);
	if (features) {
		printk("EXT2-fs: %s: couldn't mount because of "
		       "unsupported optional features (%x).\n",
		       sb->s_id, le32_to_cpu(features));
		goto failed_mount;
	}
	if (!(sb->s_flags & MS_RDONLY) &&
	    (features = EXT2_HAS_RO_COMPAT_FEATURE(sb, ~EXT2_FEATURE_RO_COMPAT_SUPP))){
		printk("EXT2-fs: %s: couldn't mount RDWR because of "
		       "unsupported optional features (%x).\n",
		       sb->s_id, le32_to_cpu(features));
		goto failed_mount;
	}

	blocksize = BLOCK_SIZE << le32_to_cpu(sbi->s_es->s_log_block_size);

824 825 826 827 828 829 830
	if ((ext2_use_xip(sb)) && ((blocksize != PAGE_SIZE) ||
				  (sb->s_blocksize != blocksize))) {
		if (!silent)
			printk("XIP: Unsupported blocksize\n");
		goto failed_mount;
	}

L
Linus Torvalds 已提交
831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885
	/* If the blocksize doesn't match, re-read the thing.. */
	if (sb->s_blocksize != blocksize) {
		brelse(bh);

		if (!sb_set_blocksize(sb, blocksize)) {
			printk(KERN_ERR "EXT2-fs: blocksize too small for device.\n");
			goto failed_sbi;
		}

		logic_sb_block = (sb_block*BLOCK_SIZE) / blocksize;
		offset = (sb_block*BLOCK_SIZE) % blocksize;
		bh = sb_bread(sb, logic_sb_block);
		if(!bh) {
			printk("EXT2-fs: Couldn't read superblock on "
			       "2nd try.\n");
			goto failed_sbi;
		}
		es = (struct ext2_super_block *) (((char *)bh->b_data) + offset);
		sbi->s_es = es;
		if (es->s_magic != cpu_to_le16(EXT2_SUPER_MAGIC)) {
			printk ("EXT2-fs: Magic mismatch, very weird !\n");
			goto failed_mount;
		}
	}

	sb->s_maxbytes = ext2_max_size(sb->s_blocksize_bits);

	if (le32_to_cpu(es->s_rev_level) == EXT2_GOOD_OLD_REV) {
		sbi->s_inode_size = EXT2_GOOD_OLD_INODE_SIZE;
		sbi->s_first_ino = EXT2_GOOD_OLD_FIRST_INO;
	} else {
		sbi->s_inode_size = le16_to_cpu(es->s_inode_size);
		sbi->s_first_ino = le32_to_cpu(es->s_first_ino);
		if ((sbi->s_inode_size < EXT2_GOOD_OLD_INODE_SIZE) ||
		    (sbi->s_inode_size & (sbi->s_inode_size - 1)) ||
		    (sbi->s_inode_size > blocksize)) {
			printk ("EXT2-fs: unsupported inode size: %d\n",
				sbi->s_inode_size);
			goto failed_mount;
		}
	}

	sbi->s_frag_size = EXT2_MIN_FRAG_SIZE <<
				   le32_to_cpu(es->s_log_frag_size);
	if (sbi->s_frag_size == 0)
		goto cantfind_ext2;
	sbi->s_frags_per_block = sb->s_blocksize / sbi->s_frag_size;

	sbi->s_blocks_per_group = le32_to_cpu(es->s_blocks_per_group);
	sbi->s_frags_per_group = le32_to_cpu(es->s_frags_per_group);
	sbi->s_inodes_per_group = le32_to_cpu(es->s_inodes_per_group);

	if (EXT2_INODE_SIZE(sb) == 0)
		goto cantfind_ext2;
	sbi->s_inodes_per_block = sb->s_blocksize / EXT2_INODE_SIZE(sb);
886
	if (sbi->s_inodes_per_block == 0 || sbi->s_inodes_per_group == 0)
L
Linus Torvalds 已提交
887 888 889 890 891 892 893 894
		goto cantfind_ext2;
	sbi->s_itb_per_group = sbi->s_inodes_per_group /
					sbi->s_inodes_per_block;
	sbi->s_desc_per_block = sb->s_blocksize /
					sizeof (struct ext2_group_desc);
	sbi->s_sbh = bh;
	sbi->s_mount_state = le16_to_cpu(es->s_state);
	sbi->s_addr_per_block_bits =
895
		ilog2 (EXT2_ADDR_PER_BLOCK(sb));
L
Linus Torvalds 已提交
896
	sbi->s_desc_per_block_bits =
897
		ilog2 (EXT2_DESC_PER_BLOCK(sb));
L
Linus Torvalds 已提交
898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932

	if (sb->s_magic != EXT2_SUPER_MAGIC)
		goto cantfind_ext2;

	if (sb->s_blocksize != bh->b_size) {
		if (!silent)
			printk ("VFS: Unsupported blocksize on dev "
				"%s.\n", sb->s_id);
		goto failed_mount;
	}

	if (sb->s_blocksize != sbi->s_frag_size) {
		printk ("EXT2-fs: fragsize %lu != blocksize %lu (not supported yet)\n",
			sbi->s_frag_size, sb->s_blocksize);
		goto failed_mount;
	}

	if (sbi->s_blocks_per_group > sb->s_blocksize * 8) {
		printk ("EXT2-fs: #blocks per group too big: %lu\n",
			sbi->s_blocks_per_group);
		goto failed_mount;
	}
	if (sbi->s_frags_per_group > sb->s_blocksize * 8) {
		printk ("EXT2-fs: #fragments per group too big: %lu\n",
			sbi->s_frags_per_group);
		goto failed_mount;
	}
	if (sbi->s_inodes_per_group > sb->s_blocksize * 8) {
		printk ("EXT2-fs: #inodes per group too big: %lu\n",
			sbi->s_inodes_per_group);
		goto failed_mount;
	}

	if (EXT2_BLOCKS_PER_GROUP(sb) == 0)
		goto cantfind_ext2;
E
Eric Sandeen 已提交
933 934 935
 	sbi->s_groups_count = ((le32_to_cpu(es->s_blocks_count) -
 				le32_to_cpu(es->s_first_data_block) - 1)
 					/ EXT2_BLOCKS_PER_GROUP(sb)) + 1;
L
Linus Torvalds 已提交
936 937 938 939 940 941 942 943
	db_count = (sbi->s_groups_count + EXT2_DESC_PER_BLOCK(sb) - 1) /
		   EXT2_DESC_PER_BLOCK(sb);
	sbi->s_group_desc = kmalloc (db_count * sizeof (struct buffer_head *), GFP_KERNEL);
	if (sbi->s_group_desc == NULL) {
		printk ("EXT2-fs: not enough memory\n");
		goto failed_mount;
	}
	bgl_lock_init(&sbi->s_blockgroup_lock);
944
	sbi->s_debts = kcalloc(sbi->s_groups_count, sizeof(*sbi->s_debts), GFP_KERNEL);
L
Linus Torvalds 已提交
945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965
	if (!sbi->s_debts) {
		printk ("EXT2-fs: not enough memory\n");
		goto failed_mount_group_desc;
	}
	for (i = 0; i < db_count; i++) {
		block = descriptor_loc(sb, logic_sb_block, i);
		sbi->s_group_desc[i] = sb_bread(sb, block);
		if (!sbi->s_group_desc[i]) {
			for (j = 0; j < i; j++)
				brelse (sbi->s_group_desc[j]);
			printk ("EXT2-fs: unable to read group descriptors\n");
			goto failed_mount_group_desc;
		}
	}
	if (!ext2_check_descriptors (sb)) {
		printk ("EXT2-fs: group descriptors corrupted!\n");
		goto failed_mount2;
	}
	sbi->s_gdb_count = db_count;
	get_random_bytes(&sbi->s_next_generation, sizeof(u32));
	spin_lock_init(&sbi->s_next_gen_lock);
966

967
	err = percpu_counter_init(&sbi->s_freeblocks_counter,
968
				ext2_count_free_blocks(sb));
969 970
	if (!err) {
		err = percpu_counter_init(&sbi->s_freeinodes_counter,
971
				ext2_count_free_inodes(sb));
972 973 974
	}
	if (!err) {
		err = percpu_counter_init(&sbi->s_dirs_counter,
975
				ext2_count_dirs(sb));
976 977 978 979 980
	}
	if (err) {
		printk(KERN_ERR "EXT2-fs: insufficient memory\n");
		goto failed_mount3;
	}
L
Linus Torvalds 已提交
981 982 983 984 985 986 987 988 989 990 991
	/*
	 * set up enough so that it can read an inode
	 */
	sb->s_op = &ext2_sops;
	sb->s_export_op = &ext2_export_ops;
	sb->s_xattr = ext2_xattr_handlers;
	root = iget(sb, EXT2_ROOT_INO);
	sb->s_root = d_alloc_root(root);
	if (!sb->s_root) {
		iput(root);
		printk(KERN_ERR "EXT2-fs: get root inode failed\n");
992
		goto failed_mount3;
L
Linus Torvalds 已提交
993 994 995 996 997
	}
	if (!S_ISDIR(root->i_mode) || !root->i_blocks || !root->i_size) {
		dput(sb->s_root);
		sb->s_root = NULL;
		printk(KERN_ERR "EXT2-fs: corrupt root inode, run e2fsck\n");
998
		goto failed_mount3;
L
Linus Torvalds 已提交
999 1000 1001
	}
	if (EXT2_HAS_COMPAT_FEATURE(sb, EXT3_FEATURE_COMPAT_HAS_JOURNAL))
		ext2_warning(sb, __FUNCTION__,
1002
			"mounting ext3 filesystem as ext2");
L
Linus Torvalds 已提交
1003 1004 1005 1006 1007 1008 1009 1010
	ext2_setup_super (sb, es, sb->s_flags & MS_RDONLY);
	return 0;

cantfind_ext2:
	if (!silent)
		printk("VFS: Can't find an ext2 filesystem on dev %s.\n",
		       sb->s_id);
	goto failed_mount;
1011 1012 1013 1014
failed_mount3:
	percpu_counter_destroy(&sbi->s_freeblocks_counter);
	percpu_counter_destroy(&sbi->s_freeinodes_counter);
	percpu_counter_destroy(&sbi->s_dirs_counter);
L
Linus Torvalds 已提交
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
failed_mount2:
	for (i = 0; i < db_count; i++)
		brelse(sbi->s_group_desc[i]);
failed_mount_group_desc:
	kfree(sbi->s_group_desc);
	kfree(sbi->s_debts);
failed_mount:
	brelse(bh);
failed_sbi:
	sb->s_fs_info = NULL;
	kfree(sbi);
	return -EINVAL;
}

static void ext2_commit_super (struct super_block * sb,
			       struct ext2_super_block * es)
{
	es->s_wtime = cpu_to_le32(get_seconds());
	mark_buffer_dirty(EXT2_SB(sb)->s_sbh);
	sb->s_dirt = 0;
}

static void ext2_sync_super(struct super_block *sb, struct ext2_super_block *es)
{
	es->s_free_blocks_count = cpu_to_le32(ext2_count_free_blocks(sb));
	es->s_free_inodes_count = cpu_to_le32(ext2_count_free_inodes(sb));
	es->s_wtime = cpu_to_le32(get_seconds());
	mark_buffer_dirty(EXT2_SB(sb)->s_sbh);
	sync_dirty_buffer(EXT2_SB(sb)->s_sbh);
	sb->s_dirt = 0;
}

/*
 * In the second extended file system, it is not necessary to
 * write the super block since we use a mapping of the
 * disk super block in a buffer.
 *
 * However, this function is still used to set the fs valid
 * flags to 0.  We need to set this flag to 0 since the fs
 * may have been checked while mounted and e2fsck may have
 * set s_state to EXT2_VALID_FS after some corrections.
 */

void ext2_write_super (struct super_block * sb)
{
	struct ext2_super_block * es;
	lock_kernel();
	if (!(sb->s_flags & MS_RDONLY)) {
		es = EXT2_SB(sb)->s_es;

		if (le16_to_cpu(es->s_state) & EXT2_VALID_FS) {
			ext2_debug ("setting valid to 0\n");
			es->s_state = cpu_to_le16(le16_to_cpu(es->s_state) &
						  ~EXT2_VALID_FS);
			es->s_free_blocks_count = cpu_to_le32(ext2_count_free_blocks(sb));
			es->s_free_inodes_count = cpu_to_le32(ext2_count_free_inodes(sb));
			es->s_mtime = cpu_to_le32(get_seconds());
			ext2_sync_super(sb, es);
		} else
			ext2_commit_super (sb, es);
	}
	sb->s_dirt = 0;
	unlock_kernel();
}

static int ext2_remount (struct super_block * sb, int * flags, char * data)
{
	struct ext2_sb_info * sbi = EXT2_SB(sb);
	struct ext2_super_block * es;
1084
	unsigned long old_mount_opt = sbi->s_mount_opt;
1085 1086 1087 1088 1089 1090 1091 1092 1093
	struct ext2_mount_options old_opts;
	unsigned long old_sb_flags;
	int err;

	/* Store the old options */
	old_sb_flags = sb->s_flags;
	old_opts.s_mount_opt = sbi->s_mount_opt;
	old_opts.s_resuid = sbi->s_resuid;
	old_opts.s_resgid = sbi->s_resgid;
L
Linus Torvalds 已提交
1094 1095 1096 1097

	/*
	 * Allow the "check" option to be passed as a remount option.
	 */
1098 1099 1100 1101
	if (!parse_options (data, sbi)) {
		err = -EINVAL;
		goto restore_opts;
	}
L
Linus Torvalds 已提交
1102 1103 1104 1105

	sb->s_flags = (sb->s_flags & ~MS_POSIXACL) |
		((sbi->s_mount_opt & EXT2_MOUNT_POSIX_ACL) ? MS_POSIXACL : 0);

1106 1107 1108 1109 1110
	ext2_xip_verify_sb(sb); /* see if bdev supports xip, unset
				    EXT2_MOUNT_XIP if not */

	if ((ext2_use_xip(sb)) && (sb->s_blocksize != PAGE_SIZE)) {
		printk("XIP: Unsupported blocksize\n");
1111
		err = -EINVAL;
1112 1113 1114
		goto restore_opts;
	}

L
Linus Torvalds 已提交
1115
	es = sbi->s_es;
1116 1117 1118 1119 1120
	if (((sbi->s_mount_opt & EXT2_MOUNT_XIP) !=
	    (old_mount_opt & EXT2_MOUNT_XIP)) &&
	    invalidate_inodes(sb))
		ext2_warning(sb, __FUNCTION__, "busy inodes while remounting "\
			     "xip remain in cache (no functional problem)");
L
Linus Torvalds 已提交
1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139
	if ((*flags & MS_RDONLY) == (sb->s_flags & MS_RDONLY))
		return 0;
	if (*flags & MS_RDONLY) {
		if (le16_to_cpu(es->s_state) & EXT2_VALID_FS ||
		    !(sbi->s_mount_state & EXT2_VALID_FS))
			return 0;
		/*
		 * OK, we are remounting a valid rw partition rdonly, so set
		 * the rdonly flag and then mark the partition as valid again.
		 */
		es->s_state = cpu_to_le16(sbi->s_mount_state);
		es->s_mtime = cpu_to_le32(get_seconds());
	} else {
		__le32 ret = EXT2_HAS_RO_COMPAT_FEATURE(sb,
					       ~EXT2_FEATURE_RO_COMPAT_SUPP);
		if (ret) {
			printk("EXT2-fs: %s: couldn't remount RDWR because of "
			       "unsupported optional features (%x).\n",
			       sb->s_id, le32_to_cpu(ret));
1140 1141
			err = -EROFS;
			goto restore_opts;
L
Linus Torvalds 已提交
1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153
		}
		/*
		 * Mounting a RDONLY partition read-write, so reread and
		 * store the current valid flag.  (It may have been changed
		 * by e2fsck since we originally mounted the partition.)
		 */
		sbi->s_mount_state = le16_to_cpu(es->s_state);
		if (!ext2_setup_super (sb, es, 0))
			sb->s_flags &= ~MS_RDONLY;
	}
	ext2_sync_super(sb, es);
	return 0;
1154 1155 1156 1157 1158 1159
restore_opts:
	sbi->s_mount_opt = old_opts.s_mount_opt;
	sbi->s_resuid = old_opts.s_resuid;
	sbi->s_resgid = old_opts.s_resgid;
	sb->s_flags = old_sb_flags;
	return err;
L
Linus Torvalds 已提交
1160 1161
}

1162
static int ext2_statfs (struct dentry * dentry, struct kstatfs * buf)
L
Linus Torvalds 已提交
1163
{
1164
	struct super_block *sb = dentry->d_sb;
L
Linus Torvalds 已提交
1165
	struct ext2_sb_info *sbi = EXT2_SB(sb);
P
Pekka Enberg 已提交
1166 1167
	struct ext2_super_block *es = sbi->s_es;
	u64 fsid;
L
Linus Torvalds 已提交
1168 1169

	if (test_opt (sb, MINIX_DF))
B
Badari Pulavarty 已提交
1170 1171 1172 1173 1174
		sbi->s_overhead_last = 0;
	else if (sbi->s_blocks_last != le32_to_cpu(es->s_blocks_count)) {
		unsigned long i, overhead = 0;
		smp_rmb();

L
Linus Torvalds 已提交
1175
		/*
B
Badari Pulavarty 已提交
1176 1177 1178
		 * Compute the overhead (FS structures). This is constant
		 * for a given filesystem unless the number of block groups
		 * changes so we cache the previous value until it does.
L
Linus Torvalds 已提交
1179 1180 1181 1182 1183 1184
		 */

		/*
		 * All of the blocks before first_data_block are
		 * overhead
		 */
P
Pekka Enberg 已提交
1185
		overhead = le32_to_cpu(es->s_first_data_block);
L
Linus Torvalds 已提交
1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201

		/*
		 * Add the overhead attributed to the superblock and
		 * block group descriptors.  If the sparse superblocks
		 * feature is turned on, then not all groups have this.
		 */
		for (i = 0; i < sbi->s_groups_count; i++)
			overhead += ext2_bg_has_super(sb, i) +
				ext2_bg_num_gdb(sb, i);

		/*
		 * Every block group has an inode bitmap, a block
		 * bitmap, and an inode table.
		 */
		overhead += (sbi->s_groups_count *
			     (2 + sbi->s_itb_per_group));
B
Badari Pulavarty 已提交
1202 1203 1204
		sbi->s_overhead_last = overhead;
		smp_wmb();
		sbi->s_blocks_last = le32_to_cpu(es->s_blocks_count);
L
Linus Torvalds 已提交
1205 1206 1207 1208
	}

	buf->f_type = EXT2_SUPER_MAGIC;
	buf->f_bsize = sb->s_blocksize;
B
Badari Pulavarty 已提交
1209
	buf->f_blocks = le32_to_cpu(es->s_blocks_count) - sbi->s_overhead_last;
L
Linus Torvalds 已提交
1210
	buf->f_bfree = ext2_count_free_blocks(sb);
B
Badari Pulavarty 已提交
1211
	es->s_free_blocks_count = cpu_to_le32(buf->f_bfree);
P
Pekka Enberg 已提交
1212 1213
	buf->f_bavail = buf->f_bfree - le32_to_cpu(es->s_r_blocks_count);
	if (buf->f_bfree < le32_to_cpu(es->s_r_blocks_count))
L
Linus Torvalds 已提交
1214
		buf->f_bavail = 0;
P
Pekka Enberg 已提交
1215 1216
	buf->f_files = le32_to_cpu(es->s_inodes_count);
	buf->f_ffree = ext2_count_free_inodes(sb);
B
Badari Pulavarty 已提交
1217
	es->s_free_inodes_count = cpu_to_le32(buf->f_ffree);
L
Linus Torvalds 已提交
1218
	buf->f_namelen = EXT2_NAME_LEN;
P
Pekka Enberg 已提交
1219 1220 1221 1222
	fsid = le64_to_cpup((void *)es->s_uuid) ^
	       le64_to_cpup((void *)es->s_uuid + sizeof(u64));
	buf->f_fsid.val[0] = fsid & 0xFFFFFFFFUL;
	buf->f_fsid.val[1] = (fsid >> 32) & 0xFFFFFFFFUL;
L
Linus Torvalds 已提交
1223 1224 1225
	return 0;
}

1226 1227
static int ext2_get_sb(struct file_system_type *fs_type,
	int flags, const char *dev_name, void *data, struct vfsmount *mnt)
L
Linus Torvalds 已提交
1228
{
1229
	return get_sb_bdev(fs_type, flags, dev_name, data, ext2_fill_super, mnt);
L
Linus Torvalds 已提交
1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293
}

#ifdef CONFIG_QUOTA

/* Read data from quotafile - avoid pagecache and such because we cannot afford
 * acquiring the locks... As quota files are never truncated and quota code
 * itself serializes the operations (and noone else should touch the files)
 * we don't have to be afraid of races */
static ssize_t ext2_quota_read(struct super_block *sb, int type, char *data,
			       size_t len, loff_t off)
{
	struct inode *inode = sb_dqopt(sb)->files[type];
	sector_t blk = off >> EXT2_BLOCK_SIZE_BITS(sb);
	int err = 0;
	int offset = off & (sb->s_blocksize - 1);
	int tocopy;
	size_t toread;
	struct buffer_head tmp_bh;
	struct buffer_head *bh;
	loff_t i_size = i_size_read(inode);

	if (off > i_size)
		return 0;
	if (off+len > i_size)
		len = i_size-off;
	toread = len;
	while (toread > 0) {
		tocopy = sb->s_blocksize - offset < toread ?
				sb->s_blocksize - offset : toread;

		tmp_bh.b_state = 0;
		err = ext2_get_block(inode, blk, &tmp_bh, 0);
		if (err)
			return err;
		if (!buffer_mapped(&tmp_bh))	/* A hole? */
			memset(data, 0, tocopy);
		else {
			bh = sb_bread(sb, tmp_bh.b_blocknr);
			if (!bh)
				return -EIO;
			memcpy(data, bh->b_data+offset, tocopy);
			brelse(bh);
		}
		offset = 0;
		toread -= tocopy;
		data += tocopy;
		blk++;
	}
	return len;
}

/* Write to quotafile */
static ssize_t ext2_quota_write(struct super_block *sb, int type,
				const char *data, size_t len, loff_t off)
{
	struct inode *inode = sb_dqopt(sb)->files[type];
	sector_t blk = off >> EXT2_BLOCK_SIZE_BITS(sb);
	int err = 0;
	int offset = off & (sb->s_blocksize - 1);
	int tocopy;
	size_t towrite = len;
	struct buffer_head tmp_bh;
	struct buffer_head *bh;

1294
	mutex_lock_nested(&inode->i_mutex, I_MUTEX_QUOTA);
L
Linus Torvalds 已提交
1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330
	while (towrite > 0) {
		tocopy = sb->s_blocksize - offset < towrite ?
				sb->s_blocksize - offset : towrite;

		tmp_bh.b_state = 0;
		err = ext2_get_block(inode, blk, &tmp_bh, 1);
		if (err)
			goto out;
		if (offset || tocopy != EXT2_BLOCK_SIZE(sb))
			bh = sb_bread(sb, tmp_bh.b_blocknr);
		else
			bh = sb_getblk(sb, tmp_bh.b_blocknr);
		if (!bh) {
			err = -EIO;
			goto out;
		}
		lock_buffer(bh);
		memcpy(bh->b_data+offset, data, tocopy);
		flush_dcache_page(bh->b_page);
		set_buffer_uptodate(bh);
		mark_buffer_dirty(bh);
		unlock_buffer(bh);
		brelse(bh);
		offset = 0;
		towrite -= tocopy;
		data += tocopy;
		blk++;
	}
out:
	if (len == towrite)
		return err;
	if (inode->i_size < off+len-towrite)
		i_size_write(inode, off+len-towrite);
	inode->i_version++;
	inode->i_mtime = inode->i_ctime = CURRENT_TIME;
	mark_inode_dirty(inode);
1331
	mutex_unlock(&inode->i_mutex);
L
Linus Torvalds 已提交
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
	return len - towrite;
}

#endif

static struct file_system_type ext2_fs_type = {
	.owner		= THIS_MODULE,
	.name		= "ext2",
	.get_sb		= ext2_get_sb,
	.kill_sb	= kill_block_super,
	.fs_flags	= FS_REQUIRES_DEV,
};

static int __init init_ext2_fs(void)
{
	int err = init_ext2_xattr();
	if (err)
		return err;
	err = init_inodecache();
	if (err)
		goto out1;
        err = register_filesystem(&ext2_fs_type);
	if (err)
		goto out;
	return 0;
out:
	destroy_inodecache();
out1:
	exit_ext2_xattr();
	return err;
}

static void __exit exit_ext2_fs(void)
{
	unregister_filesystem(&ext2_fs_type);
	destroy_inodecache();
	exit_ext2_xattr();
}

module_init(init_ext2_fs)
module_exit(exit_ext2_fs)