1// SPDX-License-Identifier: GPL-2.0-only 2/* 3 * linux/fs/ext2/super.c 4 * 5 * Copyright (C) 1992, 1993, 1994, 1995 6 * Remy Card (card@masi.ibp.fr) 7 * Laboratoire MASI - Institut Blaise Pascal 8 * Universite Pierre et Marie Curie (Paris VI) 9 * 10 * from 11 * 12 * linux/fs/minix/inode.c 13 * 14 * Copyright (C) 1991, 1992 Linus Torvalds 15 * 16 * Big-endian to little-endian byte-swapping/bitmaps by 17 * David S. Miller (davem@caip.rutgers.edu), 1995 18 */ 19 20#include <linux/module.h> 21#include <linux/string.h> 22#include <linux/fs.h> 23#include <linux/slab.h> 24#include <linux/init.h> 25#include <linux/blkdev.h> 26#include <linux/parser.h> 27#include <linux/random.h> 28#include <linux/buffer_head.h> 29#include <linux/exportfs.h> 30#include <linux/vfs.h> 31#include <linux/seq_file.h> 32#include <linux/mount.h> 33#include <linux/log2.h> 34#include <linux/quotaops.h> 35#include <linux/uaccess.h> 36#include <linux/dax.h> 37#include <linux/iversion.h> 38#include "ext2.h" 39#include "xattr.h" 40#include "acl.h" 41 42static void ext2_write_super(struct super_block *sb); 43static int ext2_remount (struct super_block * sb, int * flags, char * data); 44static int ext2_statfs (struct dentry * dentry, struct kstatfs * buf); 45static int ext2_sync_fs(struct super_block *sb, int wait); 46static int ext2_freeze(struct super_block *sb); 47static int ext2_unfreeze(struct super_block *sb); 48 49void ext2_error(struct super_block *sb, const char *function, 50 const char *fmt, ...) 51{ 52 struct va_format vaf; 53 va_list args; 54 struct ext2_sb_info *sbi = EXT2_SB(sb); 55 struct ext2_super_block *es = sbi->s_es; 56 57 if (!sb_rdonly(sb)) { 58 spin_lock(&sbi->s_lock); 59 sbi->s_mount_state |= EXT2_ERROR_FS; 60 es->s_state |= cpu_to_le16(EXT2_ERROR_FS); 61 spin_unlock(&sbi->s_lock); 62 ext2_sync_super(sb, es, 1); 63 } 64 65 va_start(args, fmt); 66 67 vaf.fmt = fmt; 68 vaf.va = &args; 69 70 printk(KERN_CRIT "EXT2-fs (%s): error: %s: %pV\n", 71 sb->s_id, function, &vaf); 72 73 va_end(args); 74 75 if (test_opt(sb, ERRORS_PANIC)) 76 panic("EXT2-fs: panic from previous error\n"); 77 if (!sb_rdonly(sb) && test_opt(sb, ERRORS_RO)) { 78 ext2_msg(sb, KERN_CRIT, 79 "error: remounting filesystem read-only"); 80 sb->s_flags |= SB_RDONLY; 81 } 82} 83 84void ext2_msg(struct super_block *sb, const char *prefix, 85 const char *fmt, ...) 86{ 87 struct va_format vaf; 88 va_list args; 89 90 va_start(args, fmt); 91 92 vaf.fmt = fmt; 93 vaf.va = &args; 94 95 printk("%sEXT2-fs (%s): %pV\n", prefix, sb->s_id, &vaf); 96 97 va_end(args); 98} 99 100/* 101 * This must be called with sbi->s_lock held. 102 */ 103void ext2_update_dynamic_rev(struct super_block *sb) 104{ 105 struct ext2_super_block *es = EXT2_SB(sb)->s_es; 106 107 if (le32_to_cpu(es->s_rev_level) > EXT2_GOOD_OLD_REV) 108 return; 109 110 ext2_msg(sb, KERN_WARNING, 111 "warning: updating to rev %d because of " 112 "new feature flag, running e2fsck is recommended", 113 EXT2_DYNAMIC_REV); 114 115 es->s_first_ino = cpu_to_le32(EXT2_GOOD_OLD_FIRST_INO); 116 es->s_inode_size = cpu_to_le16(EXT2_GOOD_OLD_INODE_SIZE); 117 es->s_rev_level = cpu_to_le32(EXT2_DYNAMIC_REV); 118 /* leave es->s_feature_*compat flags alone */ 119 /* es->s_uuid will be set by e2fsck if empty */ 120 121 /* 122 * The rest of the superblock fields should be zero, and if not it 123 * means they are likely already in use, so leave them alone. We 124 * can leave it up to e2fsck to clean up any inconsistencies there. 125 */ 126} 127 128#ifdef CONFIG_QUOTA 129static int ext2_quota_off(struct super_block *sb, int type); 130 131static void ext2_quota_off_umount(struct super_block *sb) 132{ 133 int type; 134 135 for (type = 0; type < MAXQUOTAS; type++) 136 ext2_quota_off(sb, type); 137} 138#else 139static inline void ext2_quota_off_umount(struct super_block *sb) 140{ 141} 142#endif 143 144static void ext2_put_super (struct super_block * sb) 145{ 146 int db_count; 147 int i; 148 struct ext2_sb_info *sbi = EXT2_SB(sb); 149 150 ext2_quota_off_umount(sb); 151 152 ext2_xattr_destroy_cache(sbi->s_ea_block_cache); 153 sbi->s_ea_block_cache = NULL; 154 155 if (!sb_rdonly(sb)) { 156 struct ext2_super_block *es = sbi->s_es; 157 158 spin_lock(&sbi->s_lock); 159 es->s_state = cpu_to_le16(sbi->s_mount_state); 160 spin_unlock(&sbi->s_lock); 161 ext2_sync_super(sb, es, 1); 162 } 163 db_count = sbi->s_gdb_count; 164 for (i = 0; i < db_count; i++) 165 brelse(sbi->s_group_desc[i]); 166 kfree(sbi->s_group_desc); 167 kfree(sbi->s_debts); 168 percpu_counter_destroy(&sbi->s_freeblocks_counter); 169 percpu_counter_destroy(&sbi->s_freeinodes_counter); 170 percpu_counter_destroy(&sbi->s_dirs_counter); 171 brelse (sbi->s_sbh); 172 sb->s_fs_info = NULL; 173 kfree(sbi->s_blockgroup_lock); 174 fs_put_dax(sbi->s_daxdev); 175 kfree(sbi); 176} 177 178static struct kmem_cache * ext2_inode_cachep; 179 180static struct inode *ext2_alloc_inode(struct super_block *sb) 181{ 182 struct ext2_inode_info *ei; 183 ei = kmem_cache_alloc(ext2_inode_cachep, GFP_KERNEL); 184 if (!ei) 185 return NULL; 186 ei->i_block_alloc_info = NULL; 187 inode_set_iversion(&ei->vfs_inode, 1); 188#ifdef CONFIG_QUOTA 189 memset(&ei->i_dquot, 0, sizeof(ei->i_dquot)); 190#endif 191 192 return &ei->vfs_inode; 193} 194 195static void ext2_free_in_core_inode(struct inode *inode) 196{ 197 kmem_cache_free(ext2_inode_cachep, EXT2_I(inode)); 198} 199 200static void init_once(void *foo) 201{ 202 struct ext2_inode_info *ei = (struct ext2_inode_info *) foo; 203 204 rwlock_init(&ei->i_meta_lock); 205#ifdef CONFIG_EXT2_FS_XATTR 206 init_rwsem(&ei->xattr_sem); 207#endif 208 mutex_init(&ei->truncate_mutex); 209#ifdef CONFIG_FS_DAX 210 init_rwsem(&ei->dax_sem); 211#endif 212 inode_init_once(&ei->vfs_inode); 213} 214 215static int __init init_inodecache(void) 216{ 217 ext2_inode_cachep = kmem_cache_create_usercopy("ext2_inode_cache", 218 sizeof(struct ext2_inode_info), 0, 219 (SLAB_RECLAIM_ACCOUNT|SLAB_MEM_SPREAD| 220 SLAB_ACCOUNT), 221 offsetof(struct ext2_inode_info, i_data), 222 sizeof_field(struct ext2_inode_info, i_data), 223 init_once); 224 if (ext2_inode_cachep == NULL) 225 return -ENOMEM; 226 return 0; 227} 228 229static void destroy_inodecache(void) 230{ 231 /* 232 * Make sure all delayed rcu free inodes are flushed before we 233 * destroy cache. 234 */ 235 rcu_barrier(); 236 kmem_cache_destroy(ext2_inode_cachep); 237} 238 239static int ext2_show_options(struct seq_file *seq, struct dentry *root) 240{ 241 struct super_block *sb = root->d_sb; 242 struct ext2_sb_info *sbi = EXT2_SB(sb); 243 struct ext2_super_block *es = sbi->s_es; 244 unsigned long def_mount_opts; 245 246 spin_lock(&sbi->s_lock); 247 def_mount_opts = le32_to_cpu(es->s_default_mount_opts); 248 249 if (sbi->s_sb_block != 1) 250 seq_printf(seq, ",sb=%lu", sbi->s_sb_block); 251 if (test_opt(sb, MINIX_DF)) 252 seq_puts(seq, ",minixdf"); 253 if (test_opt(sb, GRPID)) 254 seq_puts(seq, ",grpid"); 255 if (!test_opt(sb, GRPID) && (def_mount_opts & EXT2_DEFM_BSDGROUPS)) 256 seq_puts(seq, ",nogrpid"); 257 if (!uid_eq(sbi->s_resuid, make_kuid(&init_user_ns, EXT2_DEF_RESUID)) || 258 le16_to_cpu(es->s_def_resuid) != EXT2_DEF_RESUID) { 259 seq_printf(seq, ",resuid=%u", 260 from_kuid_munged(&init_user_ns, sbi->s_resuid)); 261 } 262 if (!gid_eq(sbi->s_resgid, make_kgid(&init_user_ns, EXT2_DEF_RESGID)) || 263 le16_to_cpu(es->s_def_resgid) != EXT2_DEF_RESGID) { 264 seq_printf(seq, ",resgid=%u", 265 from_kgid_munged(&init_user_ns, sbi->s_resgid)); 266 } 267 if (test_opt(sb, ERRORS_RO)) { 268 int def_errors = le16_to_cpu(es->s_errors); 269 270 if (def_errors == EXT2_ERRORS_PANIC || 271 def_errors == EXT2_ERRORS_CONTINUE) { 272 seq_puts(seq, ",errors=remount-ro"); 273 } 274 } 275 if (test_opt(sb, ERRORS_CONT)) 276 seq_puts(seq, ",errors=continue"); 277 if (test_opt(sb, ERRORS_PANIC)) 278 seq_puts(seq, ",errors=panic"); 279 if (test_opt(sb, NO_UID32)) 280 seq_puts(seq, ",nouid32"); 281 if (test_opt(sb, DEBUG)) 282 seq_puts(seq, ",debug"); 283 if (test_opt(sb, OLDALLOC)) 284 seq_puts(seq, ",oldalloc"); 285 286#ifdef CONFIG_EXT2_FS_XATTR 287 if (test_opt(sb, XATTR_USER)) 288 seq_puts(seq, ",user_xattr"); 289 if (!test_opt(sb, XATTR_USER) && 290 (def_mount_opts & EXT2_DEFM_XATTR_USER)) { 291 seq_puts(seq, ",nouser_xattr"); 292 } 293#endif 294 295#ifdef CONFIG_EXT2_FS_POSIX_ACL 296 if (test_opt(sb, POSIX_ACL)) 297 seq_puts(seq, ",acl"); 298 if (!test_opt(sb, POSIX_ACL) && (def_mount_opts & EXT2_DEFM_ACL)) 299 seq_puts(seq, ",noacl"); 300#endif 301 302 if (test_opt(sb, NOBH)) 303 seq_puts(seq, ",nobh"); 304 305 if (test_opt(sb, USRQUOTA)) 306 seq_puts(seq, ",usrquota"); 307 308 if (test_opt(sb, GRPQUOTA)) 309 seq_puts(seq, ",grpquota"); 310 311 if (test_opt(sb, XIP)) 312 seq_puts(seq, ",xip"); 313 314 if (test_opt(sb, DAX)) 315 seq_puts(seq, ",dax"); 316 317 if (!test_opt(sb, RESERVATION)) 318 seq_puts(seq, ",noreservation"); 319 320 spin_unlock(&sbi->s_lock); 321 return 0; 322} 323 324#ifdef CONFIG_QUOTA 325static ssize_t ext2_quota_read(struct super_block *sb, int type, char *data, size_t len, loff_t off); 326static ssize_t ext2_quota_write(struct super_block *sb, int type, const char *data, size_t len, loff_t off); 327static int ext2_quota_on(struct super_block *sb, int type, int format_id, 328 const struct path *path); 329static struct dquot **ext2_get_dquots(struct inode *inode) 330{ 331 return EXT2_I(inode)->i_dquot; 332} 333 334static const struct quotactl_ops ext2_quotactl_ops = { 335 .quota_on = ext2_quota_on, 336 .quota_off = ext2_quota_off, 337 .quota_sync = dquot_quota_sync, 338 .get_state = dquot_get_state, 339 .set_info = dquot_set_dqinfo, 340 .get_dqblk = dquot_get_dqblk, 341 .set_dqblk = dquot_set_dqblk, 342 .get_nextdqblk = dquot_get_next_dqblk, 343}; 344#endif 345 346static const struct super_operations ext2_sops = { 347 .alloc_inode = ext2_alloc_inode, 348 .free_inode = ext2_free_in_core_inode, 349 .write_inode = ext2_write_inode, 350 .evict_inode = ext2_evict_inode, 351 .put_super = ext2_put_super, 352 .sync_fs = ext2_sync_fs, 353 .freeze_fs = ext2_freeze, 354 .unfreeze_fs = ext2_unfreeze, 355 .statfs = ext2_statfs, 356 .remount_fs = ext2_remount, 357 .show_options = ext2_show_options, 358#ifdef CONFIG_QUOTA 359 .quota_read = ext2_quota_read, 360 .quota_write = ext2_quota_write, 361 .get_dquots = ext2_get_dquots, 362#endif 363}; 364 365static struct inode *ext2_nfs_get_inode(struct super_block *sb, 366 u64 ino, u32 generation) 367{ 368 struct inode *inode; 369 370 if (ino < EXT2_FIRST_INO(sb) && ino != EXT2_ROOT_INO) 371 return ERR_PTR(-ESTALE); 372 if (ino > le32_to_cpu(EXT2_SB(sb)->s_es->s_inodes_count)) 373 return ERR_PTR(-ESTALE); 374 375 /* 376 * ext2_iget isn't quite right if the inode is currently unallocated! 377 * However ext2_iget currently does appropriate checks to handle stale 378 * inodes so everything is OK. 379 */ 380 inode = ext2_iget(sb, ino); 381 if (IS_ERR(inode)) 382 return ERR_CAST(inode); 383 if (generation && inode->i_generation != generation) { 384 /* we didn't find the right inode.. */ 385 iput(inode); 386 return ERR_PTR(-ESTALE); 387 } 388 return inode; 389} 390 391static struct dentry *ext2_fh_to_dentry(struct super_block *sb, struct fid *fid, 392 int fh_len, int fh_type) 393{ 394 return generic_fh_to_dentry(sb, fid, fh_len, fh_type, 395 ext2_nfs_get_inode); 396} 397 398static struct dentry *ext2_fh_to_parent(struct super_block *sb, struct fid *fid, 399 int fh_len, int fh_type) 400{ 401 return generic_fh_to_parent(sb, fid, fh_len, fh_type, 402 ext2_nfs_get_inode); 403} 404 405static const struct export_operations ext2_export_ops = { 406 .fh_to_dentry = ext2_fh_to_dentry, 407 .fh_to_parent = ext2_fh_to_parent, 408 .get_parent = ext2_get_parent, 409}; 410 411static unsigned long get_sb_block(void **data) 412{ 413 unsigned long sb_block; 414 char *options = (char *) *data; 415 416 if (!options || strncmp(options, "sb=", 3) != 0) 417 return 1; /* Default location */ 418 options += 3; 419 sb_block = simple_strtoul(options, &options, 0); 420 if (*options && *options != ',') { 421 printk("EXT2-fs: Invalid sb specification: %s\n", 422 (char *) *data); 423 return 1; 424 } 425 if (*options == ',') 426 options++; 427 *data = (void *) options; 428 return sb_block; 429} 430 431enum { 432 Opt_bsd_df, Opt_minix_df, Opt_grpid, Opt_nogrpid, 433 Opt_resgid, Opt_resuid, Opt_sb, Opt_err_cont, Opt_err_panic, 434 Opt_err_ro, Opt_nouid32, Opt_debug, 435 Opt_oldalloc, Opt_orlov, Opt_nobh, Opt_user_xattr, Opt_nouser_xattr, 436 Opt_acl, Opt_noacl, Opt_xip, Opt_dax, Opt_ignore, Opt_err, Opt_quota, 437 Opt_usrquota, Opt_grpquota, Opt_reservation, Opt_noreservation 438}; 439 440static const match_table_t tokens = { 441 {Opt_bsd_df, "bsddf"}, 442 {Opt_minix_df, "minixdf"}, 443 {Opt_grpid, "grpid"}, 444 {Opt_grpid, "bsdgroups"}, 445 {Opt_nogrpid, "nogrpid"}, 446 {Opt_nogrpid, "sysvgroups"}, 447 {Opt_resgid, "resgid=%u"}, 448 {Opt_resuid, "resuid=%u"}, 449 {Opt_sb, "sb=%u"}, 450 {Opt_err_cont, "errors=continue"}, 451 {Opt_err_panic, "errors=panic"}, 452 {Opt_err_ro, "errors=remount-ro"}, 453 {Opt_nouid32, "nouid32"}, 454 {Opt_debug, "debug"}, 455 {Opt_oldalloc, "oldalloc"}, 456 {Opt_orlov, "orlov"}, 457 {Opt_nobh, "nobh"}, 458 {Opt_user_xattr, "user_xattr"}, 459 {Opt_nouser_xattr, "nouser_xattr"}, 460 {Opt_acl, "acl"}, 461 {Opt_noacl, "noacl"}, 462 {Opt_xip, "xip"}, 463 {Opt_dax, "dax"}, 464 {Opt_grpquota, "grpquota"}, 465 {Opt_ignore, "noquota"}, 466 {Opt_quota, "quota"}, 467 {Opt_usrquota, "usrquota"}, 468 {Opt_reservation, "reservation"}, 469 {Opt_noreservation, "noreservation"}, 470 {Opt_err, NULL} 471}; 472 473static int parse_options(char *options, struct super_block *sb, 474 struct ext2_mount_options *opts) 475{ 476 char *p; 477 substring_t args[MAX_OPT_ARGS]; 478 int option; 479 kuid_t uid; 480 kgid_t gid; 481 482 if (!options) 483 return 1; 484 485 while ((p = strsep (&options, ",")) != NULL) { 486 int token; 487 if (!*p) 488 continue; 489 490 token = match_token(p, tokens, args); 491 switch (token) { 492 case Opt_bsd_df: 493 clear_opt (opts->s_mount_opt, MINIX_DF); 494 break; 495 case Opt_minix_df: 496 set_opt (opts->s_mount_opt, MINIX_DF); 497 break; 498 case Opt_grpid: 499 set_opt (opts->s_mount_opt, GRPID); 500 break; 501 case Opt_nogrpid: 502 clear_opt (opts->s_mount_opt, GRPID); 503 break; 504 case Opt_resuid: 505 if (match_int(&args[0], &option)) 506 return 0; 507 uid = make_kuid(current_user_ns(), option); 508 if (!uid_valid(uid)) { 509 ext2_msg(sb, KERN_ERR, "Invalid uid value %d", option); 510 return 0; 511 512 } 513 opts->s_resuid = uid; 514 break; 515 case Opt_resgid: 516 if (match_int(&args[0], &option)) 517 return 0; 518 gid = make_kgid(current_user_ns(), option); 519 if (!gid_valid(gid)) { 520 ext2_msg(sb, KERN_ERR, "Invalid gid value %d", option); 521 return 0; 522 } 523 opts->s_resgid = gid; 524 break; 525 case Opt_sb: 526 /* handled by get_sb_block() instead of here */ 527 /* *sb_block = match_int(&args[0]); */ 528 break; 529 case Opt_err_panic: 530 clear_opt (opts->s_mount_opt, ERRORS_CONT); 531 clear_opt (opts->s_mount_opt, ERRORS_RO); 532 set_opt (opts->s_mount_opt, ERRORS_PANIC); 533 break; 534 case Opt_err_ro: 535 clear_opt (opts->s_mount_opt, ERRORS_CONT); 536 clear_opt (opts->s_mount_opt, ERRORS_PANIC); 537 set_opt (opts->s_mount_opt, ERRORS_RO); 538 break; 539 case Opt_err_cont: 540 clear_opt (opts->s_mount_opt, ERRORS_RO); 541 clear_opt (opts->s_mount_opt, ERRORS_PANIC); 542 set_opt (opts->s_mount_opt, ERRORS_CONT); 543 break; 544 case Opt_nouid32: 545 set_opt (opts->s_mount_opt, NO_UID32); 546 break; 547 case Opt_debug: 548 set_opt (opts->s_mount_opt, DEBUG); 549 break; 550 case Opt_oldalloc: 551 set_opt (opts->s_mount_opt, OLDALLOC); 552 break; 553 case Opt_orlov: 554 clear_opt (opts->s_mount_opt, OLDALLOC); 555 break; 556 case Opt_nobh: 557 set_opt (opts->s_mount_opt, NOBH); 558 break; 559#ifdef CONFIG_EXT2_FS_XATTR 560 case Opt_user_xattr: 561 set_opt (opts->s_mount_opt, XATTR_USER); 562 break; 563 case Opt_nouser_xattr: 564 clear_opt (opts->s_mount_opt, XATTR_USER); 565 break; 566#else 567 case Opt_user_xattr: 568 case Opt_nouser_xattr: 569 ext2_msg(sb, KERN_INFO, "(no)user_xattr options" 570 "not supported"); 571 break; 572#endif 573#ifdef CONFIG_EXT2_FS_POSIX_ACL 574 case Opt_acl: 575 set_opt(opts->s_mount_opt, POSIX_ACL); 576 break; 577 case Opt_noacl: 578 clear_opt(opts->s_mount_opt, POSIX_ACL); 579 break; 580#else 581 case Opt_acl: 582 case Opt_noacl: 583 ext2_msg(sb, KERN_INFO, 584 "(no)acl options not supported"); 585 break; 586#endif 587 case Opt_xip: 588 ext2_msg(sb, KERN_INFO, "use dax instead of xip"); 589 set_opt(opts->s_mount_opt, XIP); 590 fallthrough; 591 case Opt_dax: 592#ifdef CONFIG_FS_DAX 593 ext2_msg(sb, KERN_WARNING, 594 "DAX enabled. Warning: EXPERIMENTAL, use at your own risk"); 595 set_opt(opts->s_mount_opt, DAX); 596#else 597 ext2_msg(sb, KERN_INFO, "dax option not supported"); 598#endif 599 break; 600 601#if defined(CONFIG_QUOTA) 602 case Opt_quota: 603 case Opt_usrquota: 604 set_opt(opts->s_mount_opt, USRQUOTA); 605 break; 606 607 case Opt_grpquota: 608 set_opt(opts->s_mount_opt, GRPQUOTA); 609 break; 610#else 611 case Opt_quota: 612 case Opt_usrquota: 613 case Opt_grpquota: 614 ext2_msg(sb, KERN_INFO, 615 "quota operations not supported"); 616 break; 617#endif 618 619 case Opt_reservation: 620 set_opt(opts->s_mount_opt, RESERVATION); 621 ext2_msg(sb, KERN_INFO, "reservations ON"); 622 break; 623 case Opt_noreservation: 624 clear_opt(opts->s_mount_opt, RESERVATION); 625 ext2_msg(sb, KERN_INFO, "reservations OFF"); 626 break; 627 case Opt_ignore: 628 break; 629 default: 630 return 0; 631 } 632 } 633 return 1; 634} 635 636static int ext2_setup_super (struct super_block * sb, 637 struct ext2_super_block * es, 638 int read_only) 639{ 640 int res = 0; 641 struct ext2_sb_info *sbi = EXT2_SB(sb); 642 643 if (le32_to_cpu(es->s_rev_level) > EXT2_MAX_SUPP_REV) { 644 ext2_msg(sb, KERN_ERR, 645 "error: revision level too high, " 646 "forcing read-only mode"); 647 res = SB_RDONLY; 648 } 649 if (read_only) 650 return res; 651 if (!(sbi->s_mount_state & EXT2_VALID_FS)) 652 ext2_msg(sb, KERN_WARNING, 653 "warning: mounting unchecked fs, " 654 "running e2fsck is recommended"); 655 else if ((sbi->s_mount_state & EXT2_ERROR_FS)) 656 ext2_msg(sb, KERN_WARNING, 657 "warning: mounting fs with errors, " 658 "running e2fsck is recommended"); 659 else if ((__s16) le16_to_cpu(es->s_max_mnt_count) >= 0 && 660 le16_to_cpu(es->s_mnt_count) >= 661 (unsigned short) (__s16) le16_to_cpu(es->s_max_mnt_count)) 662 ext2_msg(sb, KERN_WARNING, 663 "warning: maximal mount count reached, " 664 "running e2fsck is recommended"); 665 else if (le32_to_cpu(es->s_checkinterval) && 666 (le32_to_cpu(es->s_lastcheck) + 667 le32_to_cpu(es->s_checkinterval) <= 668 ktime_get_real_seconds())) 669 ext2_msg(sb, KERN_WARNING, 670 "warning: checktime reached, " 671 "running e2fsck is recommended"); 672 if (!le16_to_cpu(es->s_max_mnt_count)) 673 es->s_max_mnt_count = cpu_to_le16(EXT2_DFL_MAX_MNT_COUNT); 674 le16_add_cpu(&es->s_mnt_count, 1); 675 if (test_opt (sb, DEBUG)) 676 ext2_msg(sb, KERN_INFO, "%s, %s, bs=%lu, gc=%lu, " 677 "bpg=%lu, ipg=%lu, mo=%04lx]", 678 EXT2FS_VERSION, EXT2FS_DATE, sb->s_blocksize, 679 sbi->s_groups_count, 680 EXT2_BLOCKS_PER_GROUP(sb), 681 EXT2_INODES_PER_GROUP(sb), 682 sbi->s_mount_opt); 683 return res; 684} 685 686static int ext2_check_descriptors(struct super_block *sb) 687{ 688 int i; 689 struct ext2_sb_info *sbi = EXT2_SB(sb); 690 691 ext2_debug ("Checking group descriptors"); 692 693 for (i = 0; i < sbi->s_groups_count; i++) { 694 struct ext2_group_desc *gdp = ext2_get_group_desc(sb, i, NULL); 695 ext2_fsblk_t first_block = ext2_group_first_block_no(sb, i); 696 ext2_fsblk_t last_block = ext2_group_last_block_no(sb, i); 697 698 if (le32_to_cpu(gdp->bg_block_bitmap) < first_block || 699 le32_to_cpu(gdp->bg_block_bitmap) > last_block) 700 { 701 ext2_error (sb, "ext2_check_descriptors", 702 "Block bitmap for group %d" 703 " not in group (block %lu)!", 704 i, (unsigned long) le32_to_cpu(gdp->bg_block_bitmap)); 705 return 0; 706 } 707 if (le32_to_cpu(gdp->bg_inode_bitmap) < first_block || 708 le32_to_cpu(gdp->bg_inode_bitmap) > last_block) 709 { 710 ext2_error (sb, "ext2_check_descriptors", 711 "Inode bitmap for group %d" 712 " not in group (block %lu)!", 713 i, (unsigned long) le32_to_cpu(gdp->bg_inode_bitmap)); 714 return 0; 715 } 716 if (le32_to_cpu(gdp->bg_inode_table) < first_block || 717 le32_to_cpu(gdp->bg_inode_table) + sbi->s_itb_per_group - 1 > 718 last_block) 719 { 720 ext2_error (sb, "ext2_check_descriptors", 721 "Inode table for group %d" 722 " not in group (block %lu)!", 723 i, (unsigned long) le32_to_cpu(gdp->bg_inode_table)); 724 return 0; 725 } 726 } 727 return 1; 728} 729 730/* 731 * Maximal file size. There is a direct, and {,double-,triple-}indirect 732 * block limit, and also a limit of (2^32 - 1) 512-byte sectors in i_blocks. 733 * We need to be 1 filesystem block less than the 2^32 sector limit. 734 */ 735static loff_t ext2_max_size(int bits) 736{ 737 loff_t res = EXT2_NDIR_BLOCKS; 738 int meta_blocks; 739 unsigned int upper_limit; 740 unsigned int ppb = 1 << (bits-2); 741 742 /* This is calculated to be the largest file size for a 743 * dense, file such that the total number of 744 * sectors in the file, including data and all indirect blocks, 745 * does not exceed 2^32 -1 746 * __u32 i_blocks representing the total number of 747 * 512 bytes blocks of the file 748 */ 749 upper_limit = (1LL << 32) - 1; 750 751 /* total blocks in file system block size */ 752 upper_limit >>= (bits - 9); 753 754 /* Compute how many blocks we can address by block tree */ 755 res += 1LL << (bits-2); 756 res += 1LL << (2*(bits-2)); 757 res += 1LL << (3*(bits-2)); 758 /* Compute how many metadata blocks are needed */ 759 meta_blocks = 1; 760 meta_blocks += 1 + ppb; 761 meta_blocks += 1 + ppb + ppb * ppb; 762 /* Does block tree limit file size? */ 763 if (res + meta_blocks <= upper_limit) 764 goto check_lfs; 765 766 res = upper_limit; 767 /* How many metadata blocks are needed for addressing upper_limit? */ 768 upper_limit -= EXT2_NDIR_BLOCKS; 769 /* indirect blocks */ 770 meta_blocks = 1; 771 upper_limit -= ppb; 772 /* double indirect blocks */ 773 if (upper_limit < ppb * ppb) { 774 meta_blocks += 1 + DIV_ROUND_UP(upper_limit, ppb); 775 res -= meta_blocks; 776 goto check_lfs; 777 } 778 meta_blocks += 1 + ppb; 779 upper_limit -= ppb * ppb; 780 /* tripple indirect blocks for the rest */ 781 meta_blocks += 1 + DIV_ROUND_UP(upper_limit, ppb) + 782 DIV_ROUND_UP(upper_limit, ppb*ppb); 783 res -= meta_blocks; 784check_lfs: 785 res <<= bits; 786 if (res > MAX_LFS_FILESIZE) 787 res = MAX_LFS_FILESIZE; 788 789 return res; 790} 791 792static unsigned long descriptor_loc(struct super_block *sb, 793 unsigned long logic_sb_block, 794 int nr) 795{ 796 struct ext2_sb_info *sbi = EXT2_SB(sb); 797 unsigned long bg, first_meta_bg; 798 799 first_meta_bg = le32_to_cpu(sbi->s_es->s_first_meta_bg); 800 801 if (!EXT2_HAS_INCOMPAT_FEATURE(sb, EXT2_FEATURE_INCOMPAT_META_BG) || 802 nr < first_meta_bg) 803 return (logic_sb_block + nr + 1); 804 bg = sbi->s_desc_per_block * nr; 805 806 return ext2_group_first_block_no(sb, bg) + ext2_bg_has_super(sb, bg); 807} 808 809static int ext2_fill_super(struct super_block *sb, void *data, int silent) 810{ 811 struct dax_device *dax_dev = fs_dax_get_by_bdev(sb->s_bdev); 812 struct buffer_head * bh; 813 struct ext2_sb_info * sbi; 814 struct ext2_super_block * es; 815 struct inode *root; 816 unsigned long block; 817 unsigned long sb_block = get_sb_block(&data); 818 unsigned long logic_sb_block; 819 unsigned long offset = 0; 820 unsigned long def_mount_opts; 821 long ret = -ENOMEM; 822 int blocksize = BLOCK_SIZE; 823 int db_count; 824 int i, j; 825 __le32 features; 826 int err; 827 struct ext2_mount_options opts; 828 829 sbi = kzalloc(sizeof(*sbi), GFP_KERNEL); 830 if (!sbi) 831 goto failed; 832 833 sbi->s_blockgroup_lock = 834 kzalloc(sizeof(struct blockgroup_lock), GFP_KERNEL); 835 if (!sbi->s_blockgroup_lock) { 836 kfree(sbi); 837 goto failed; 838 } 839 sb->s_fs_info = sbi; 840 sbi->s_sb_block = sb_block; 841 sbi->s_daxdev = dax_dev; 842 843 spin_lock_init(&sbi->s_lock); 844 ret = -EINVAL; 845 846 /* 847 * See what the current blocksize for the device is, and 848 * use that as the blocksize. Otherwise (or if the blocksize 849 * is smaller than the default) use the default. 850 * This is important for devices that have a hardware 851 * sectorsize that is larger than the default. 852 */ 853 blocksize = sb_min_blocksize(sb, BLOCK_SIZE); 854 if (!blocksize) { 855 ext2_msg(sb, KERN_ERR, "error: unable to set blocksize"); 856 goto failed_sbi; 857 } 858 859 /* 860 * If the superblock doesn't start on a hardware sector boundary, 861 * calculate the offset. 862 */ 863 if (blocksize != BLOCK_SIZE) { 864 logic_sb_block = (sb_block*BLOCK_SIZE) / blocksize; 865 offset = (sb_block*BLOCK_SIZE) % blocksize; 866 } else { 867 logic_sb_block = sb_block; 868 } 869 870 if (!(bh = sb_bread(sb, logic_sb_block))) { 871 ext2_msg(sb, KERN_ERR, "error: unable to read superblock"); 872 goto failed_sbi; 873 } 874 /* 875 * Note: s_es must be initialized as soon as possible because 876 * some ext2 macro-instructions depend on its value 877 */ 878 es = (struct ext2_super_block *) (((char *)bh->b_data) + offset); 879 sbi->s_es = es; 880 sb->s_magic = le16_to_cpu(es->s_magic); 881 882 if (sb->s_magic != EXT2_SUPER_MAGIC) 883 goto cantfind_ext2; 884 885 opts.s_mount_opt = 0; 886 /* Set defaults before we parse the mount options */ 887 def_mount_opts = le32_to_cpu(es->s_default_mount_opts); 888 if (def_mount_opts & EXT2_DEFM_DEBUG) 889 set_opt(opts.s_mount_opt, DEBUG); 890 if (def_mount_opts & EXT2_DEFM_BSDGROUPS) 891 set_opt(opts.s_mount_opt, GRPID); 892 if (def_mount_opts & EXT2_DEFM_UID16) 893 set_opt(opts.s_mount_opt, NO_UID32); 894#ifdef CONFIG_EXT2_FS_XATTR 895 if (def_mount_opts & EXT2_DEFM_XATTR_USER) 896 set_opt(opts.s_mount_opt, XATTR_USER); 897#endif 898#ifdef CONFIG_EXT2_FS_POSIX_ACL 899 if (def_mount_opts & EXT2_DEFM_ACL) 900 set_opt(opts.s_mount_opt, POSIX_ACL); 901#endif 902 903 if (le16_to_cpu(sbi->s_es->s_errors) == EXT2_ERRORS_PANIC) 904 set_opt(opts.s_mount_opt, ERRORS_PANIC); 905 else if (le16_to_cpu(sbi->s_es->s_errors) == EXT2_ERRORS_CONTINUE) 906 set_opt(opts.s_mount_opt, ERRORS_CONT); 907 else 908 set_opt(opts.s_mount_opt, ERRORS_RO); 909 910 opts.s_resuid = make_kuid(&init_user_ns, le16_to_cpu(es->s_def_resuid)); 911 opts.s_resgid = make_kgid(&init_user_ns, le16_to_cpu(es->s_def_resgid)); 912 913 set_opt(opts.s_mount_opt, RESERVATION); 914 915 if (!parse_options((char *) data, sb, &opts)) 916 goto failed_mount; 917 918 sbi->s_mount_opt = opts.s_mount_opt; 919 sbi->s_resuid = opts.s_resuid; 920 sbi->s_resgid = opts.s_resgid; 921 922 sb->s_flags = (sb->s_flags & ~SB_POSIXACL) | 923 (test_opt(sb, POSIX_ACL) ? SB_POSIXACL : 0); 924 sb->s_iflags |= SB_I_CGROUPWB; 925 926 if (le32_to_cpu(es->s_rev_level) == EXT2_GOOD_OLD_REV && 927 (EXT2_HAS_COMPAT_FEATURE(sb, ~0U) || 928 EXT2_HAS_RO_COMPAT_FEATURE(sb, ~0U) || 929 EXT2_HAS_INCOMPAT_FEATURE(sb, ~0U))) 930 ext2_msg(sb, KERN_WARNING, 931 "warning: feature flags set on rev 0 fs, " 932 "running e2fsck is recommended"); 933 /* 934 * Check feature flags regardless of the revision level, since we 935 * previously didn't change the revision level when setting the flags, 936 * so there is a chance incompat flags are set on a rev 0 filesystem. 937 */ 938 features = EXT2_HAS_INCOMPAT_FEATURE(sb, ~EXT2_FEATURE_INCOMPAT_SUPP); 939 if (features) { 940 ext2_msg(sb, KERN_ERR, "error: couldn't mount because of " 941 "unsupported optional features (%x)", 942 le32_to_cpu(features)); 943 goto failed_mount; 944 } 945 if (!sb_rdonly(sb) && (features = EXT2_HAS_RO_COMPAT_FEATURE(sb, ~EXT2_FEATURE_RO_COMPAT_SUPP))){ 946 ext2_msg(sb, KERN_ERR, "error: couldn't mount RDWR because of " 947 "unsupported optional features (%x)", 948 le32_to_cpu(features)); 949 goto failed_mount; 950 } 951 952 if (le32_to_cpu(es->s_log_block_size) > 953 (EXT2_MAX_BLOCK_LOG_SIZE - BLOCK_SIZE_BITS)) { 954 ext2_msg(sb, KERN_ERR, 955 "Invalid log block size: %u", 956 le32_to_cpu(es->s_log_block_size)); 957 goto failed_mount; 958 } 959 blocksize = BLOCK_SIZE << le32_to_cpu(sbi->s_es->s_log_block_size); 960 961 if (test_opt(sb, DAX)) { 962 if (!bdev_dax_supported(sb->s_bdev, blocksize)) { 963 ext2_msg(sb, KERN_ERR, 964 "DAX unsupported by block device. Turning off DAX."); 965 clear_opt(sbi->s_mount_opt, DAX); 966 } 967 } 968 969 /* If the blocksize doesn't match, re-read the thing.. */ 970 if (sb->s_blocksize != blocksize) { 971 brelse(bh); 972 973 if (!sb_set_blocksize(sb, blocksize)) { 974 ext2_msg(sb, KERN_ERR, 975 "error: bad blocksize %d", blocksize); 976 goto failed_sbi; 977 } 978 979 logic_sb_block = (sb_block*BLOCK_SIZE) / blocksize; 980 offset = (sb_block*BLOCK_SIZE) % blocksize; 981 bh = sb_bread(sb, logic_sb_block); 982 if(!bh) { 983 ext2_msg(sb, KERN_ERR, "error: couldn't read" 984 "superblock on 2nd try"); 985 goto failed_sbi; 986 } 987 es = (struct ext2_super_block *) (((char *)bh->b_data) + offset); 988 sbi->s_es = es; 989 if (es->s_magic != cpu_to_le16(EXT2_SUPER_MAGIC)) { 990 ext2_msg(sb, KERN_ERR, "error: magic mismatch"); 991 goto failed_mount; 992 } 993 } 994 995 sb->s_maxbytes = ext2_max_size(sb->s_blocksize_bits); 996 sb->s_max_links = EXT2_LINK_MAX; 997 sb->s_time_min = S32_MIN; 998 sb->s_time_max = S32_MAX; 999 1000 if (le32_to_cpu(es->s_rev_level) == EXT2_GOOD_OLD_REV) { 1001 sbi->s_inode_size = EXT2_GOOD_OLD_INODE_SIZE; 1002 sbi->s_first_ino = EXT2_GOOD_OLD_FIRST_INO; 1003 } else { 1004 sbi->s_inode_size = le16_to_cpu(es->s_inode_size); 1005 sbi->s_first_ino = le32_to_cpu(es->s_first_ino); 1006 if ((sbi->s_inode_size < EXT2_GOOD_OLD_INODE_SIZE) || 1007 !is_power_of_2(sbi->s_inode_size) || 1008 (sbi->s_inode_size > blocksize)) { 1009 ext2_msg(sb, KERN_ERR, 1010 "error: unsupported inode size: %d", 1011 sbi->s_inode_size); 1012 goto failed_mount; 1013 } 1014 } 1015 1016 sbi->s_blocks_per_group = le32_to_cpu(es->s_blocks_per_group); 1017 sbi->s_inodes_per_group = le32_to_cpu(es->s_inodes_per_group); 1018 1019 sbi->s_inodes_per_block = sb->s_blocksize / EXT2_INODE_SIZE(sb); 1020 if (sbi->s_inodes_per_block == 0 || sbi->s_inodes_per_group == 0) 1021 goto cantfind_ext2; 1022 sbi->s_itb_per_group = sbi->s_inodes_per_group / 1023 sbi->s_inodes_per_block; 1024 sbi->s_desc_per_block = sb->s_blocksize / 1025 sizeof (struct ext2_group_desc); 1026 sbi->s_sbh = bh; 1027 sbi->s_mount_state = le16_to_cpu(es->s_state); 1028 sbi->s_addr_per_block_bits = 1029 ilog2 (EXT2_ADDR_PER_BLOCK(sb)); 1030 sbi->s_desc_per_block_bits = 1031 ilog2 (EXT2_DESC_PER_BLOCK(sb)); 1032 1033 if (sb->s_magic != EXT2_SUPER_MAGIC) 1034 goto cantfind_ext2; 1035 1036 if (sb->s_blocksize != bh->b_size) { 1037 if (!silent) 1038 ext2_msg(sb, KERN_ERR, "error: unsupported blocksize"); 1039 goto failed_mount; 1040 } 1041 1042 if (es->s_log_frag_size != es->s_log_block_size) { 1043 ext2_msg(sb, KERN_ERR, 1044 "error: fragsize log %u != blocksize log %u", 1045 le32_to_cpu(es->s_log_frag_size), sb->s_blocksize_bits); 1046 goto failed_mount; 1047 } 1048 1049 if (sbi->s_blocks_per_group > sb->s_blocksize * 8) { 1050 ext2_msg(sb, KERN_ERR, 1051 "error: #blocks per group too big: %lu", 1052 sbi->s_blocks_per_group); 1053 goto failed_mount; 1054 } 1055 if (sbi->s_inodes_per_group < sbi->s_inodes_per_block || 1056 sbi->s_inodes_per_group > sb->s_blocksize * 8) { 1057 ext2_msg(sb, KERN_ERR, 1058 "error: invalid #inodes per group: %lu", 1059 sbi->s_inodes_per_group); 1060 goto failed_mount; 1061 } 1062 1063 if (EXT2_BLOCKS_PER_GROUP(sb) == 0) 1064 goto cantfind_ext2; 1065 sbi->s_groups_count = ((le32_to_cpu(es->s_blocks_count) - 1066 le32_to_cpu(es->s_first_data_block) - 1) 1067 / EXT2_BLOCKS_PER_GROUP(sb)) + 1; 1068 if ((u64)sbi->s_groups_count * sbi->s_inodes_per_group != 1069 le32_to_cpu(es->s_inodes_count)) { 1070 ext2_msg(sb, KERN_ERR, "error: invalid #inodes: %u vs computed %llu", 1071 le32_to_cpu(es->s_inodes_count), 1072 (u64)sbi->s_groups_count * sbi->s_inodes_per_group); 1073 goto failed_mount; 1074 } 1075 db_count = (sbi->s_groups_count + EXT2_DESC_PER_BLOCK(sb) - 1) / 1076 EXT2_DESC_PER_BLOCK(sb); 1077 sbi->s_group_desc = kmalloc_array (db_count, 1078 sizeof(struct buffer_head *), 1079 GFP_KERNEL); 1080 if (sbi->s_group_desc == NULL) { 1081 ret = -ENOMEM; 1082 ext2_msg(sb, KERN_ERR, "error: not enough memory"); 1083 goto failed_mount; 1084 } 1085 bgl_lock_init(sbi->s_blockgroup_lock); 1086 sbi->s_debts = kcalloc(sbi->s_groups_count, sizeof(*sbi->s_debts), GFP_KERNEL); 1087 if (!sbi->s_debts) { 1088 ret = -ENOMEM; 1089 ext2_msg(sb, KERN_ERR, "error: not enough memory"); 1090 goto failed_mount_group_desc; 1091 } 1092 for (i = 0; i < db_count; i++) { 1093 block = descriptor_loc(sb, logic_sb_block, i); 1094 sbi->s_group_desc[i] = sb_bread(sb, block); 1095 if (!sbi->s_group_desc[i]) { 1096 for (j = 0; j < i; j++) 1097 brelse (sbi->s_group_desc[j]); 1098 ext2_msg(sb, KERN_ERR, 1099 "error: unable to read group descriptors"); 1100 goto failed_mount_group_desc; 1101 } 1102 } 1103 if (!ext2_check_descriptors (sb)) { 1104 ext2_msg(sb, KERN_ERR, "group descriptors corrupted"); 1105 goto failed_mount2; 1106 } 1107 sbi->s_gdb_count = db_count; 1108 get_random_bytes(&sbi->s_next_generation, sizeof(u32)); 1109 spin_lock_init(&sbi->s_next_gen_lock); 1110 1111 /* per fileystem reservation list head & lock */ 1112 spin_lock_init(&sbi->s_rsv_window_lock); 1113 sbi->s_rsv_window_root = RB_ROOT; 1114 /* 1115 * Add a single, static dummy reservation to the start of the 1116 * reservation window list --- it gives us a placeholder for 1117 * append-at-start-of-list which makes the allocation logic 1118 * _much_ simpler. 1119 */ 1120 sbi->s_rsv_window_head.rsv_start = EXT2_RESERVE_WINDOW_NOT_ALLOCATED; 1121 sbi->s_rsv_window_head.rsv_end = EXT2_RESERVE_WINDOW_NOT_ALLOCATED; 1122 sbi->s_rsv_window_head.rsv_alloc_hit = 0; 1123 sbi->s_rsv_window_head.rsv_goal_size = 0; 1124 ext2_rsv_window_add(sb, &sbi->s_rsv_window_head); 1125 1126 err = percpu_counter_init(&sbi->s_freeblocks_counter, 1127 ext2_count_free_blocks(sb), GFP_KERNEL); 1128 if (!err) { 1129 err = percpu_counter_init(&sbi->s_freeinodes_counter, 1130 ext2_count_free_inodes(sb), GFP_KERNEL); 1131 } 1132 if (!err) { 1133 err = percpu_counter_init(&sbi->s_dirs_counter, 1134 ext2_count_dirs(sb), GFP_KERNEL); 1135 } 1136 if (err) { 1137 ret = err; 1138 ext2_msg(sb, KERN_ERR, "error: insufficient memory"); 1139 goto failed_mount3; 1140 } 1141 1142#ifdef CONFIG_EXT2_FS_XATTR 1143 sbi->s_ea_block_cache = ext2_xattr_create_cache(); 1144 if (!sbi->s_ea_block_cache) { 1145 ret = -ENOMEM; 1146 ext2_msg(sb, KERN_ERR, "Failed to create ea_block_cache"); 1147 goto failed_mount3; 1148 } 1149#endif 1150 /* 1151 * set up enough so that it can read an inode 1152 */ 1153 sb->s_op = &ext2_sops; 1154 sb->s_export_op = &ext2_export_ops; 1155 sb->s_xattr = ext2_xattr_handlers; 1156 1157#ifdef CONFIG_QUOTA 1158 sb->dq_op = &dquot_operations; 1159 sb->s_qcop = &ext2_quotactl_ops; 1160 sb->s_quota_types = QTYPE_MASK_USR | QTYPE_MASK_GRP; 1161#endif 1162 1163 root = ext2_iget(sb, EXT2_ROOT_INO); 1164 if (IS_ERR(root)) { 1165 ret = PTR_ERR(root); 1166 goto failed_mount3; 1167 } 1168 if (!S_ISDIR(root->i_mode) || !root->i_blocks || !root->i_size) { 1169 iput(root); 1170 ext2_msg(sb, KERN_ERR, "error: corrupt root inode, run e2fsck"); 1171 goto failed_mount3; 1172 } 1173 1174 sb->s_root = d_make_root(root); 1175 if (!sb->s_root) { 1176 ext2_msg(sb, KERN_ERR, "error: get root inode failed"); 1177 ret = -ENOMEM; 1178 goto failed_mount3; 1179 } 1180 if (EXT2_HAS_COMPAT_FEATURE(sb, EXT3_FEATURE_COMPAT_HAS_JOURNAL)) 1181 ext2_msg(sb, KERN_WARNING, 1182 "warning: mounting ext3 filesystem as ext2"); 1183 if (ext2_setup_super (sb, es, sb_rdonly(sb))) 1184 sb->s_flags |= SB_RDONLY; 1185 ext2_write_super(sb); 1186 return 0; 1187 1188cantfind_ext2: 1189 if (!silent) 1190 ext2_msg(sb, KERN_ERR, 1191 "error: can't find an ext2 filesystem on dev %s.", 1192 sb->s_id); 1193 goto failed_mount; 1194failed_mount3: 1195 ext2_xattr_destroy_cache(sbi->s_ea_block_cache); 1196 percpu_counter_destroy(&sbi->s_freeblocks_counter); 1197 percpu_counter_destroy(&sbi->s_freeinodes_counter); 1198 percpu_counter_destroy(&sbi->s_dirs_counter); 1199failed_mount2: 1200 for (i = 0; i < db_count; i++) 1201 brelse(sbi->s_group_desc[i]); 1202failed_mount_group_desc: 1203 kfree(sbi->s_group_desc); 1204 kfree(sbi->s_debts); 1205failed_mount: 1206 brelse(bh); 1207failed_sbi: 1208 sb->s_fs_info = NULL; 1209 kfree(sbi->s_blockgroup_lock); 1210 kfree(sbi); 1211failed: 1212 fs_put_dax(dax_dev); 1213 return ret; 1214} 1215 1216static void ext2_clear_super_error(struct super_block *sb) 1217{ 1218 struct buffer_head *sbh = EXT2_SB(sb)->s_sbh; 1219 1220 if (buffer_write_io_error(sbh)) { 1221 /* 1222 * Oh, dear. A previous attempt to write the 1223 * superblock failed. This could happen because the 1224 * USB device was yanked out. Or it could happen to 1225 * be a transient write error and maybe the block will 1226 * be remapped. Nothing we can do but to retry the 1227 * write and hope for the best. 1228 */ 1229 ext2_msg(sb, KERN_ERR, 1230 "previous I/O error to superblock detected"); 1231 clear_buffer_write_io_error(sbh); 1232 set_buffer_uptodate(sbh); 1233 } 1234} 1235 1236void ext2_sync_super(struct super_block *sb, struct ext2_super_block *es, 1237 int wait) 1238{ 1239 ext2_clear_super_error(sb); 1240 spin_lock(&EXT2_SB(sb)->s_lock); 1241 es->s_free_blocks_count = cpu_to_le32(ext2_count_free_blocks(sb)); 1242 es->s_free_inodes_count = cpu_to_le32(ext2_count_free_inodes(sb)); 1243 es->s_wtime = cpu_to_le32(ktime_get_real_seconds()); 1244 /* unlock before we do IO */ 1245 spin_unlock(&EXT2_SB(sb)->s_lock); 1246 mark_buffer_dirty(EXT2_SB(sb)->s_sbh); 1247 if (wait) 1248 sync_dirty_buffer(EXT2_SB(sb)->s_sbh); 1249} 1250 1251/* 1252 * In the second extended file system, it is not necessary to 1253 * write the super block since we use a mapping of the 1254 * disk super block in a buffer. 1255 * 1256 * However, this function is still used to set the fs valid 1257 * flags to 0. We need to set this flag to 0 since the fs 1258 * may have been checked while mounted and e2fsck may have 1259 * set s_state to EXT2_VALID_FS after some corrections. 1260 */ 1261static int ext2_sync_fs(struct super_block *sb, int wait) 1262{ 1263 struct ext2_sb_info *sbi = EXT2_SB(sb); 1264 struct ext2_super_block *es = EXT2_SB(sb)->s_es; 1265 1266 /* 1267 * Write quota structures to quota file, sync_blockdev() will write 1268 * them to disk later 1269 */ 1270 dquot_writeback_dquots(sb, -1); 1271 1272 spin_lock(&sbi->s_lock); 1273 if (es->s_state & cpu_to_le16(EXT2_VALID_FS)) { 1274 ext2_debug("setting valid to 0\n"); 1275 es->s_state &= cpu_to_le16(~EXT2_VALID_FS); 1276 } 1277 spin_unlock(&sbi->s_lock); 1278 ext2_sync_super(sb, es, wait); 1279 return 0; 1280} 1281 1282static int ext2_freeze(struct super_block *sb) 1283{ 1284 struct ext2_sb_info *sbi = EXT2_SB(sb); 1285 1286 /* 1287 * Open but unlinked files present? Keep EXT2_VALID_FS flag cleared 1288 * because we have unattached inodes and thus filesystem is not fully 1289 * consistent. 1290 */ 1291 if (atomic_long_read(&sb->s_remove_count)) { 1292 ext2_sync_fs(sb, 1); 1293 return 0; 1294 } 1295 /* Set EXT2_FS_VALID flag */ 1296 spin_lock(&sbi->s_lock); 1297 sbi->s_es->s_state = cpu_to_le16(sbi->s_mount_state); 1298 spin_unlock(&sbi->s_lock); 1299 ext2_sync_super(sb, sbi->s_es, 1); 1300 1301 return 0; 1302} 1303 1304static int ext2_unfreeze(struct super_block *sb) 1305{ 1306 /* Just write sb to clear EXT2_VALID_FS flag */ 1307 ext2_write_super(sb); 1308 1309 return 0; 1310} 1311 1312static void ext2_write_super(struct super_block *sb) 1313{ 1314 if (!sb_rdonly(sb)) 1315 ext2_sync_fs(sb, 1); 1316} 1317 1318static int ext2_remount (struct super_block * sb, int * flags, char * data) 1319{ 1320 struct ext2_sb_info * sbi = EXT2_SB(sb); 1321 struct ext2_super_block * es; 1322 struct ext2_mount_options new_opts; 1323 int err; 1324 1325 sync_filesystem(sb); 1326 1327 spin_lock(&sbi->s_lock); 1328 new_opts.s_mount_opt = sbi->s_mount_opt; 1329 new_opts.s_resuid = sbi->s_resuid; 1330 new_opts.s_resgid = sbi->s_resgid; 1331 spin_unlock(&sbi->s_lock); 1332 1333 if (!parse_options(data, sb, &new_opts)) 1334 return -EINVAL; 1335 1336 spin_lock(&sbi->s_lock); 1337 es = sbi->s_es; 1338 if ((sbi->s_mount_opt ^ new_opts.s_mount_opt) & EXT2_MOUNT_DAX) { 1339 ext2_msg(sb, KERN_WARNING, "warning: refusing change of " 1340 "dax flag with busy inodes while remounting"); 1341 new_opts.s_mount_opt ^= EXT2_MOUNT_DAX; 1342 } 1343 if ((bool)(*flags & SB_RDONLY) == sb_rdonly(sb)) 1344 goto out_set; 1345 if (*flags & SB_RDONLY) { 1346 if (le16_to_cpu(es->s_state) & EXT2_VALID_FS || 1347 !(sbi->s_mount_state & EXT2_VALID_FS)) 1348 goto out_set; 1349 1350 /* 1351 * OK, we are remounting a valid rw partition rdonly, so set 1352 * the rdonly flag and then mark the partition as valid again. 1353 */ 1354 es->s_state = cpu_to_le16(sbi->s_mount_state); 1355 es->s_mtime = cpu_to_le32(ktime_get_real_seconds()); 1356 spin_unlock(&sbi->s_lock); 1357 1358 err = dquot_suspend(sb, -1); 1359 if (err < 0) 1360 return err; 1361 1362 ext2_sync_super(sb, es, 1); 1363 } else { 1364 __le32 ret = EXT2_HAS_RO_COMPAT_FEATURE(sb, 1365 ~EXT2_FEATURE_RO_COMPAT_SUPP); 1366 if (ret) { 1367 spin_unlock(&sbi->s_lock); 1368 ext2_msg(sb, KERN_WARNING, 1369 "warning: couldn't remount RDWR because of " 1370 "unsupported optional features (%x).", 1371 le32_to_cpu(ret)); 1372 return -EROFS; 1373 } 1374 /* 1375 * Mounting a RDONLY partition read-write, so reread and 1376 * store the current valid flag. (It may have been changed 1377 * by e2fsck since we originally mounted the partition.) 1378 */ 1379 sbi->s_mount_state = le16_to_cpu(es->s_state); 1380 if (!ext2_setup_super (sb, es, 0)) 1381 sb->s_flags &= ~SB_RDONLY; 1382 spin_unlock(&sbi->s_lock); 1383 1384 ext2_write_super(sb); 1385 1386 dquot_resume(sb, -1); 1387 } 1388 1389 spin_lock(&sbi->s_lock); 1390out_set: 1391 sbi->s_mount_opt = new_opts.s_mount_opt; 1392 sbi->s_resuid = new_opts.s_resuid; 1393 sbi->s_resgid = new_opts.s_resgid; 1394 sb->s_flags = (sb->s_flags & ~SB_POSIXACL) | 1395 (test_opt(sb, POSIX_ACL) ? SB_POSIXACL : 0); 1396 spin_unlock(&sbi->s_lock); 1397 1398 return 0; 1399} 1400 1401static int ext2_statfs (struct dentry * dentry, struct kstatfs * buf) 1402{ 1403 struct super_block *sb = dentry->d_sb; 1404 struct ext2_sb_info *sbi = EXT2_SB(sb); 1405 struct ext2_super_block *es = sbi->s_es; 1406 u64 fsid; 1407 1408 spin_lock(&sbi->s_lock); 1409 1410 if (test_opt (sb, MINIX_DF)) 1411 sbi->s_overhead_last = 0; 1412 else if (sbi->s_blocks_last != le32_to_cpu(es->s_blocks_count)) { 1413 unsigned long i, overhead = 0; 1414 smp_rmb(); 1415 1416 /* 1417 * Compute the overhead (FS structures). This is constant 1418 * for a given filesystem unless the number of block groups 1419 * changes so we cache the previous value until it does. 1420 */ 1421 1422 /* 1423 * All of the blocks before first_data_block are 1424 * overhead 1425 */ 1426 overhead = le32_to_cpu(es->s_first_data_block); 1427 1428 /* 1429 * Add the overhead attributed to the superblock and 1430 * block group descriptors. If the sparse superblocks 1431 * feature is turned on, then not all groups have this. 1432 */ 1433 for (i = 0; i < sbi->s_groups_count; i++) 1434 overhead += ext2_bg_has_super(sb, i) + 1435 ext2_bg_num_gdb(sb, i); 1436 1437 /* 1438 * Every block group has an inode bitmap, a block 1439 * bitmap, and an inode table. 1440 */ 1441 overhead += (sbi->s_groups_count * 1442 (2 + sbi->s_itb_per_group)); 1443 sbi->s_overhead_last = overhead; 1444 smp_wmb(); 1445 sbi->s_blocks_last = le32_to_cpu(es->s_blocks_count); 1446 } 1447 1448 buf->f_type = EXT2_SUPER_MAGIC; 1449 buf->f_bsize = sb->s_blocksize; 1450 buf->f_blocks = le32_to_cpu(es->s_blocks_count) - sbi->s_overhead_last; 1451 buf->f_bfree = ext2_count_free_blocks(sb); 1452 es->s_free_blocks_count = cpu_to_le32(buf->f_bfree); 1453 buf->f_bavail = buf->f_bfree - le32_to_cpu(es->s_r_blocks_count); 1454 if (buf->f_bfree < le32_to_cpu(es->s_r_blocks_count)) 1455 buf->f_bavail = 0; 1456 buf->f_files = le32_to_cpu(es->s_inodes_count); 1457 buf->f_ffree = ext2_count_free_inodes(sb); 1458 es->s_free_inodes_count = cpu_to_le32(buf->f_ffree); 1459 buf->f_namelen = EXT2_NAME_LEN; 1460 fsid = le64_to_cpup((void *)es->s_uuid) ^ 1461 le64_to_cpup((void *)es->s_uuid + sizeof(u64)); 1462 buf->f_fsid = u64_to_fsid(fsid); 1463 spin_unlock(&sbi->s_lock); 1464 return 0; 1465} 1466 1467static struct dentry *ext2_mount(struct file_system_type *fs_type, 1468 int flags, const char *dev_name, void *data) 1469{ 1470 return mount_bdev(fs_type, flags, dev_name, data, ext2_fill_super); 1471} 1472 1473#ifdef CONFIG_QUOTA 1474 1475/* Read data from quotafile - avoid pagecache and such because we cannot afford 1476 * acquiring the locks... As quota files are never truncated and quota code 1477 * itself serializes the operations (and no one else should touch the files) 1478 * we don't have to be afraid of races */ 1479static ssize_t ext2_quota_read(struct super_block *sb, int type, char *data, 1480 size_t len, loff_t off) 1481{ 1482 struct inode *inode = sb_dqopt(sb)->files[type]; 1483 sector_t blk = off >> EXT2_BLOCK_SIZE_BITS(sb); 1484 int err = 0; 1485 int offset = off & (sb->s_blocksize - 1); 1486 int tocopy; 1487 size_t toread; 1488 struct buffer_head tmp_bh; 1489 struct buffer_head *bh; 1490 loff_t i_size = i_size_read(inode); 1491 1492 if (off > i_size) 1493 return 0; 1494 if (off+len > i_size) 1495 len = i_size-off; 1496 toread = len; 1497 while (toread > 0) { 1498 tocopy = sb->s_blocksize - offset < toread ? 1499 sb->s_blocksize - offset : toread; 1500 1501 tmp_bh.b_state = 0; 1502 tmp_bh.b_size = sb->s_blocksize; 1503 err = ext2_get_block(inode, blk, &tmp_bh, 0); 1504 if (err < 0) 1505 return err; 1506 if (!buffer_mapped(&tmp_bh)) /* A hole? */ 1507 memset(data, 0, tocopy); 1508 else { 1509 bh = sb_bread(sb, tmp_bh.b_blocknr); 1510 if (!bh) 1511 return -EIO; 1512 memcpy(data, bh->b_data+offset, tocopy); 1513 brelse(bh); 1514 } 1515 offset = 0; 1516 toread -= tocopy; 1517 data += tocopy; 1518 blk++; 1519 } 1520 return len; 1521} 1522 1523/* Write to quotafile */ 1524static ssize_t ext2_quota_write(struct super_block *sb, int type, 1525 const char *data, size_t len, loff_t off) 1526{ 1527 struct inode *inode = sb_dqopt(sb)->files[type]; 1528 sector_t blk = off >> EXT2_BLOCK_SIZE_BITS(sb); 1529 int err = 0; 1530 int offset = off & (sb->s_blocksize - 1); 1531 int tocopy; 1532 size_t towrite = len; 1533 struct buffer_head tmp_bh; 1534 struct buffer_head *bh; 1535 1536 while (towrite > 0) { 1537 tocopy = sb->s_blocksize - offset < towrite ? 1538 sb->s_blocksize - offset : towrite; 1539 1540 tmp_bh.b_state = 0; 1541 tmp_bh.b_size = sb->s_blocksize; 1542 err = ext2_get_block(inode, blk, &tmp_bh, 1); 1543 if (err < 0) 1544 goto out; 1545 if (offset || tocopy != EXT2_BLOCK_SIZE(sb)) 1546 bh = sb_bread(sb, tmp_bh.b_blocknr); 1547 else 1548 bh = sb_getblk(sb, tmp_bh.b_blocknr); 1549 if (unlikely(!bh)) { 1550 err = -EIO; 1551 goto out; 1552 } 1553 lock_buffer(bh); 1554 memcpy(bh->b_data+offset, data, tocopy); 1555 flush_dcache_page(bh->b_page); 1556 set_buffer_uptodate(bh); 1557 mark_buffer_dirty(bh); 1558 unlock_buffer(bh); 1559 brelse(bh); 1560 offset = 0; 1561 towrite -= tocopy; 1562 data += tocopy; 1563 blk++; 1564 } 1565out: 1566 if (len == towrite) 1567 return err; 1568 if (inode->i_size < off+len-towrite) 1569 i_size_write(inode, off+len-towrite); 1570 inode_inc_iversion(inode); 1571 inode->i_mtime = inode->i_ctime = current_time(inode); 1572 mark_inode_dirty(inode); 1573 return len - towrite; 1574} 1575 1576static int ext2_quota_on(struct super_block *sb, int type, int format_id, 1577 const struct path *path) 1578{ 1579 int err; 1580 struct inode *inode; 1581 1582 err = dquot_quota_on(sb, type, format_id, path); 1583 if (err) 1584 return err; 1585 1586 inode = d_inode(path->dentry); 1587 inode_lock(inode); 1588 EXT2_I(inode)->i_flags |= EXT2_NOATIME_FL | EXT2_IMMUTABLE_FL; 1589 inode_set_flags(inode, S_NOATIME | S_IMMUTABLE, 1590 S_NOATIME | S_IMMUTABLE); 1591 inode_unlock(inode); 1592 mark_inode_dirty(inode); 1593 1594 return 0; 1595} 1596 1597static int ext2_quota_off(struct super_block *sb, int type) 1598{ 1599 struct inode *inode = sb_dqopt(sb)->files[type]; 1600 int err; 1601 1602 if (!inode || !igrab(inode)) 1603 goto out; 1604 1605 err = dquot_quota_off(sb, type); 1606 if (err) 1607 goto out_put; 1608 1609 inode_lock(inode); 1610 EXT2_I(inode)->i_flags &= ~(EXT2_NOATIME_FL | EXT2_IMMUTABLE_FL); 1611 inode_set_flags(inode, 0, S_NOATIME | S_IMMUTABLE); 1612 inode_unlock(inode); 1613 mark_inode_dirty(inode); 1614out_put: 1615 iput(inode); 1616 return err; 1617out: 1618 return dquot_quota_off(sb, type); 1619} 1620 1621#endif 1622 1623static struct file_system_type ext2_fs_type = { 1624 .owner = THIS_MODULE, 1625 .name = "ext2", 1626 .mount = ext2_mount, 1627 .kill_sb = kill_block_super, 1628 .fs_flags = FS_REQUIRES_DEV, 1629}; 1630MODULE_ALIAS_FS("ext2"); 1631 1632static int __init init_ext2_fs(void) 1633{ 1634 int err; 1635 1636 err = init_inodecache(); 1637 if (err) 1638 return err; 1639 err = register_filesystem(&ext2_fs_type); 1640 if (err) 1641 goto out; 1642 return 0; 1643out: 1644 destroy_inodecache(); 1645 return err; 1646} 1647 1648static void __exit exit_ext2_fs(void) 1649{ 1650 unregister_filesystem(&ext2_fs_type); 1651 destroy_inodecache(); 1652} 1653 1654MODULE_AUTHOR("Remy Card and others"); 1655MODULE_DESCRIPTION("Second Extended Filesystem"); 1656MODULE_LICENSE("GPL"); 1657module_init(init_ext2_fs) 1658module_exit(exit_ext2_fs) 1659