X-Git-Url: http://ftp.safe.ca/?a=blobdiff_plain;f=fs%2Fext3%2Fsuper.c;h=afa2b569da101094dee07e58fda0f40391f8e045;hb=d5aa407f59f5b83d2c50ec88f5bf56d40f1f8978;hp=580b8a6ca979a67b2412a9b8b2f16aaa4e232b92;hpb=a8f48a95619cbce8f85423480e7d0a1bf971a62b;p=safe%2Fjmp%2Flinux-2.6 diff --git a/fs/ext3/super.c b/fs/ext3/super.c index 580b8a6..afa2b56 100644 --- a/fs/ext3/super.c +++ b/fs/ext3/super.c @@ -29,12 +29,14 @@ #include #include #include +#include #include #include #include #include #include #include +#include #include @@ -42,12 +44,18 @@ #include "acl.h" #include "namei.h" +#ifdef CONFIG_EXT3_DEFAULTS_TO_ORDERED + #define EXT3_MOUNT_DEFAULT_DATA_MODE EXT3_MOUNT_ORDERED_DATA +#else + #define EXT3_MOUNT_DEFAULT_DATA_MODE EXT3_MOUNT_WRITEBACK_DATA +#endif + static int ext3_load_journal(struct super_block *, struct ext3_super_block *, unsigned long journal_devnum); static int ext3_create_journal(struct super_block *, struct ext3_super_block *, unsigned int); -static void ext3_commit_super (struct super_block * sb, - struct ext3_super_block * es, +static int ext3_commit_super(struct super_block *sb, + struct ext3_super_block *es, int sync); static void ext3_mark_recovery_complete(struct super_block * sb, struct ext3_super_block * es); @@ -58,9 +66,8 @@ static const char *ext3_decode_error(struct super_block * sb, int errno, char nbuf[16]); static int ext3_remount (struct super_block * sb, int * flags, char * data); static int ext3_statfs (struct dentry * dentry, struct kstatfs * buf); -static void ext3_unlockfs(struct super_block *sb); -static void ext3_write_super (struct super_block * sb); -static void ext3_write_super_lockfs(struct super_block *sb); +static int ext3_unfreeze(struct super_block *sb); +static int ext3_freeze(struct super_block *sb); /* * Wrappers for journal_start/end. @@ -82,7 +89,7 @@ handle_t *ext3_journal_start_sb(struct super_block *sb, int nblocks) * take the FS itself readonly cleanly. */ journal = EXT3_SB(sb)->s_journal; if (is_journal_aborted(journal)) { - ext3_abort(sb, __FUNCTION__, + ext3_abort(sb, __func__, "Detected aborted journal"); return ERR_PTR(-EROFS); } @@ -128,12 +135,24 @@ void ext3_journal_abort_handle(const char *caller, const char *err_fn, if (is_handle_aborted(handle)) return; - printk(KERN_ERR "%s: aborting transaction: %s in %s\n", - caller, errstr, err_fn); + printk(KERN_ERR "EXT3-fs: %s: aborting transaction: %s in %s\n", + caller, errstr, err_fn); journal_abort_handle(handle); } +void ext3_msg(struct super_block *sb, const char *prefix, + const char *fmt, ...) +{ + va_list args; + + va_start(args, fmt); + printk("%sEXT3-fs (%s): ", prefix, sb->s_id); + vprintk(fmt, args); + printk("\n"); + va_end(args); +} + /* Deal with the reporting of failure conditions on a filesystem such as * inconsistencies detected or read IO failures. * @@ -167,12 +186,13 @@ static void ext3_handle_error(struct super_block *sb) journal_abort(journal, -EIO); } if (test_opt (sb, ERRORS_RO)) { - printk (KERN_CRIT "Remounting filesystem read-only\n"); + ext3_msg(sb, KERN_CRIT, + "error: remounting filesystem read-only"); sb->s_flags |= MS_RDONLY; } ext3_commit_super(sb, es, 1); if (test_opt(sb, ERRORS_PANIC)) - panic("EXT3-fs (device %s): panic forced after error\n", + panic("EXT3-fs (%s): panic forced after error\n", sb->s_id); } @@ -240,8 +260,7 @@ void __ext3_std_error (struct super_block * sb, const char * function, return; errstr = ext3_decode_error(sb, errno, nbuf); - printk (KERN_CRIT "EXT3-fs error (device %s) in %s: %s\n", - sb->s_id, function, errstr); + ext3_msg(sb, KERN_CRIT, "error in %s: %s", function, errstr); ext3_handle_error(sb); } @@ -261,25 +280,25 @@ void ext3_abort (struct super_block * sb, const char * function, { va_list args; - printk (KERN_CRIT "ext3_abort called.\n"); - va_start(args, fmt); - printk(KERN_CRIT "EXT3-fs error (device %s): %s: ",sb->s_id, function); + printk(KERN_CRIT "EXT3-fs (%s): error: %s: ", sb->s_id, function); vprintk(fmt, args); printk("\n"); va_end(args); if (test_opt(sb, ERRORS_PANIC)) - panic("EXT3-fs panic from previous error\n"); + panic("EXT3-fs: panic from previous error\n"); if (sb->s_flags & MS_RDONLY) return; - printk(KERN_CRIT "Remounting filesystem read-only\n"); + ext3_msg(sb, KERN_CRIT, + "error: remounting filesystem read-only"); EXT3_SB(sb)->s_mount_state |= EXT3_ERROR_FS; sb->s_flags |= MS_RDONLY; EXT3_SB(sb)->s_mount_opt |= EXT3_MOUNT_ABORT; - journal_abort(EXT3_SB(sb)->s_journal, -EIO); + if (EXT3_SB(sb)->s_journal) + journal_abort(EXT3_SB(sb)->s_journal, -EIO); } void ext3_warning (struct super_block * sb, const char * function, @@ -288,7 +307,7 @@ void ext3_warning (struct super_block * sb, const char * function, va_list args; va_start(args, fmt); - printk(KERN_WARNING "EXT3-fs warning (device %s): %s: ", + printk(KERN_WARNING "EXT3-fs (%s): warning: %s: ", sb->s_id, function); vprintk(fmt, args); printk("\n"); @@ -302,10 +321,10 @@ void ext3_update_dynamic_rev(struct super_block *sb) if (le32_to_cpu(es->s_rev_level) > EXT3_GOOD_OLD_REV) return; - ext3_warning(sb, __FUNCTION__, - "updating to rev %d because of new feature flag, " - "running e2fsck is recommended", - EXT3_DYNAMIC_REV); + ext3_msg(sb, KERN_WARNING, + "warning: updating to rev %d because of " + "new feature flag, running e2fsck is recommended", + EXT3_DYNAMIC_REV); es->s_first_ino = cpu_to_le32(EXT3_GOOD_OLD_FIRST_INO); es->s_inode_size = cpu_to_le16(EXT3_GOOD_OLD_INODE_SIZE); @@ -323,7 +342,7 @@ void ext3_update_dynamic_rev(struct super_block *sb) /* * Open the external journal device */ -static struct block_device *ext3_blkdev_get(dev_t dev) +static struct block_device *ext3_blkdev_get(dev_t dev, struct super_block *sb) { struct block_device *bdev; char b[BDEVNAME_SIZE]; @@ -334,8 +353,9 @@ static struct block_device *ext3_blkdev_get(dev_t dev) return bdev; fail: - printk(KERN_ERR "EXT3: failed to open journal device %s: %ld\n", - __bdevname(dev, b), PTR_ERR(bdev)); + ext3_msg(sb, "error: failed to open journal device %s: %ld", + __bdevname(dev, b), PTR_ERR(bdev)); + return NULL; } @@ -345,7 +365,7 @@ fail: static int ext3_blkdev_put(struct block_device *bdev) { bd_release(bdev); - return blkdev_put(bdev); + return blkdev_put(bdev, FMODE_READ|FMODE_WRITE); } static int ext3_blkdev_remove(struct ext3_sb_info *sbi) @@ -370,13 +390,13 @@ static void dump_orphan_list(struct super_block *sb, struct ext3_sb_info *sbi) { struct list_head *l; - printk(KERN_ERR "sb orphan head is %d\n", + ext3_msg(sb, KERN_ERR, "error: sb orphan head is %d", le32_to_cpu(sbi->s_es->s_last_orphan)); - printk(KERN_ERR "sb_info orphan list:\n"); + ext3_msg(sb, KERN_ERR, "sb_info orphan list:"); list_for_each(l, &sbi->s_orphan) { struct inode *inode = orphan_list_entry(l); - printk(KERN_ERR " " + ext3_msg(sb, KERN_ERR, " " "inode %s:%lu at %p: mode %o, nlink %d, next %d\n", inode->i_sb->s_id, inode->i_ino, inode, inode->i_mode, inode->i_nlink, @@ -388,10 +408,16 @@ static void ext3_put_super (struct super_block * sb) { struct ext3_sb_info *sbi = EXT3_SB(sb); struct ext3_super_block *es = sbi->s_es; - int i; + int i, err; + + lock_kernel(); ext3_xattr_put_super(sb); - journal_destroy(sbi->s_journal); + err = journal_destroy(sbi->s_journal); + sbi->s_journal = NULL; + if (err < 0) + ext3_abort(sb, __func__, "Couldn't clean up the journal"); + if (!(sb->s_flags & MS_RDONLY)) { EXT3_CLEAR_INCOMPAT_FEATURE(sb, EXT3_FEATURE_INCOMPAT_RECOVER); es->s_state = cpu_to_le16(sbi->s_mount_state); @@ -420,7 +446,7 @@ static void ext3_put_super (struct super_block * sb) dump_orphan_list(sb, sbi); J_ASSERT(list_empty(&sbi->s_orphan)); - invalidate_bdev(sb->s_bdev, 0); + invalidate_bdev(sb->s_bdev); if (sbi->journal_bdev && sbi->journal_bdev != sb->s_bdev) { /* * Invalidate the journal device's buffers. We don't want them @@ -428,12 +454,14 @@ static void ext3_put_super (struct super_block * sb) * hotswapped, and it breaks the `ro-after' testing code. */ sync_blockdev(sbi->journal_bdev); - invalidate_bdev(sbi->journal_bdev, 0); + invalidate_bdev(sbi->journal_bdev); ext3_blkdev_remove(sbi); } sb->s_fs_info = NULL; + kfree(sbi->s_blockgroup_lock); kfree(sbi); - return; + + unlock_kernel(); } static struct kmem_cache *ext3_inode_cachep; @@ -448,33 +476,36 @@ static struct inode *ext3_alloc_inode(struct super_block *sb) ei = kmem_cache_alloc(ext3_inode_cachep, GFP_NOFS); if (!ei) return NULL; -#ifdef CONFIG_EXT3_FS_POSIX_ACL - ei->i_acl = EXT3_ACL_NOT_CACHED; - ei->i_default_acl = EXT3_ACL_NOT_CACHED; -#endif ei->i_block_alloc_info = NULL; ei->vfs_inode.i_version = 1; + atomic_set(&ei->i_datasync_tid, 0); + atomic_set(&ei->i_sync_tid, 0); return &ei->vfs_inode; } static void ext3_destroy_inode(struct inode *inode) { + if (!list_empty(&(EXT3_I(inode)->i_orphan))) { + printk("EXT3 Inode %p: orphan list check failed!\n", + EXT3_I(inode)); + print_hex_dump(KERN_INFO, "", DUMP_PREFIX_ADDRESS, 16, 4, + EXT3_I(inode), sizeof(struct ext3_inode_info), + false); + dump_stack(); + } kmem_cache_free(ext3_inode_cachep, EXT3_I(inode)); } -static void init_once(void * foo, struct kmem_cache * cachep, unsigned long flags) +static void init_once(void *foo) { struct ext3_inode_info *ei = (struct ext3_inode_info *) foo; - if ((flags & (SLAB_CTOR_VERIFY|SLAB_CTOR_CONSTRUCTOR)) == - SLAB_CTOR_CONSTRUCTOR) { - INIT_LIST_HEAD(&ei->i_orphan); + INIT_LIST_HEAD(&ei->i_orphan); #ifdef CONFIG_EXT3_FS_XATTR - init_rwsem(&ei->xattr_sem); + init_rwsem(&ei->xattr_sem); #endif - mutex_init(&ei->truncate_mutex); - inode_init_once(&ei->vfs_inode); - } + mutex_init(&ei->truncate_mutex); + inode_init_once(&ei->vfs_inode); } static int init_inodecache(void) @@ -483,7 +514,7 @@ static int init_inodecache(void) sizeof(struct ext3_inode_info), 0, (SLAB_RECLAIM_ACCOUNT| SLAB_MEM_SPREAD), - init_once, NULL); + init_once); if (ext3_inode_cachep == NULL) return -ENOMEM; return 0; @@ -497,18 +528,6 @@ static void destroy_inodecache(void) static void ext3_clear_inode(struct inode *inode) { struct ext3_block_alloc_info *rsv = EXT3_I(inode)->i_block_alloc_info; -#ifdef CONFIG_EXT3_FS_POSIX_ACL - if (EXT3_I(inode)->i_acl && - EXT3_I(inode)->i_acl != EXT3_ACL_NOT_CACHED) { - posix_acl_release(EXT3_I(inode)->i_acl); - EXT3_I(inode)->i_acl = EXT3_ACL_NOT_CACHED; - } - if (EXT3_I(inode)->i_default_acl && - EXT3_I(inode)->i_default_acl != EXT3_ACL_NOT_CACHED) { - posix_acl_release(EXT3_I(inode)->i_default_acl); - EXT3_I(inode)->i_default_acl = EXT3_ACL_NOT_CACHED; - } -#endif ext3_discard_reservation(inode); EXT3_I(inode)->i_block_alloc_info = NULL; if (unlikely(rsv)) @@ -520,9 +539,22 @@ static inline void ext3_show_quota_options(struct seq_file *seq, struct super_bl #if defined(CONFIG_QUOTA) struct ext3_sb_info *sbi = EXT3_SB(sb); - if (sbi->s_jquota_fmt) - seq_printf(seq, ",jqfmt=%s", - (sbi->s_jquota_fmt == QFMT_VFS_OLD) ? "vfsold": "vfsv0"); + if (sbi->s_jquota_fmt) { + char *fmtname = ""; + + switch (sbi->s_jquota_fmt) { + case QFMT_VFS_OLD: + fmtname = "vfsold"; + break; + case QFMT_VFS_V0: + fmtname = "vfsv0"; + break; + case QFMT_VFS_V1: + fmtname = "vfsv1"; + break; + } + seq_printf(seq, ",jqfmt=%s", fmtname); + } if (sbi->s_qf_names[USRQUOTA]) seq_printf(seq, ",usrjquota=%s", sbi->s_qf_names[USRQUOTA]); @@ -538,16 +570,99 @@ static inline void ext3_show_quota_options(struct seq_file *seq, struct super_bl #endif } +static char *data_mode_string(unsigned long mode) +{ + switch (mode) { + case EXT3_MOUNT_JOURNAL_DATA: + return "journal"; + case EXT3_MOUNT_ORDERED_DATA: + return "ordered"; + case EXT3_MOUNT_WRITEBACK_DATA: + return "writeback"; + } + return "unknown"; +} + +/* + * Show an option if + * - it's set to a non-default value OR + * - if the per-sb default is different from the global default + */ static int ext3_show_options(struct seq_file *seq, struct vfsmount *vfs) { struct super_block *sb = vfs->mnt_sb; + struct ext3_sb_info *sbi = EXT3_SB(sb); + struct ext3_super_block *es = sbi->s_es; + unsigned long def_mount_opts; - if (test_opt(sb, DATA_FLAGS) == EXT3_MOUNT_JOURNAL_DATA) - seq_puts(seq, ",data=journal"); - else if (test_opt(sb, DATA_FLAGS) == EXT3_MOUNT_ORDERED_DATA) - seq_puts(seq, ",data=ordered"); - else if (test_opt(sb, DATA_FLAGS) == EXT3_MOUNT_WRITEBACK_DATA) - seq_puts(seq, ",data=writeback"); + 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)) + seq_puts(seq, ",grpid"); + if (!test_opt(sb, GRPID) && (def_mount_opts & EXT3_DEFM_BSDGROUPS)) + seq_puts(seq, ",nogrpid"); + if (sbi->s_resuid != EXT3_DEF_RESUID || + le16_to_cpu(es->s_def_resuid) != EXT3_DEF_RESUID) { + seq_printf(seq, ",resuid=%u", sbi->s_resuid); + } + if (sbi->s_resgid != EXT3_DEF_RESGID || + le16_to_cpu(es->s_def_resgid) != EXT3_DEF_RESGID) { + seq_printf(seq, ",resgid=%u", sbi->s_resgid); + } + if (test_opt(sb, ERRORS_RO)) { + int def_errors = le16_to_cpu(es->s_errors); + + if (def_errors == EXT3_ERRORS_PANIC || + def_errors == EXT3_ERRORS_CONTINUE) { + seq_puts(seq, ",errors=remount-ro"); + } + } + if (test_opt(sb, ERRORS_CONT)) + seq_puts(seq, ",errors=continue"); + 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_EXT3_FS_XATTR + if (test_opt(sb, XATTR_USER)) + seq_puts(seq, ",user_xattr"); + if (!test_opt(sb, XATTR_USER) && + (def_mount_opts & EXT3_DEFM_XATTR_USER)) { + seq_puts(seq, ",nouser_xattr"); + } +#endif +#ifdef CONFIG_EXT3_FS_POSIX_ACL + if (test_opt(sb, POSIX_ACL)) + seq_puts(seq, ",acl"); + if (!test_opt(sb, POSIX_ACL) && (def_mount_opts & EXT3_DEFM_ACL)) + seq_puts(seq, ",noacl"); +#endif + if (!test_opt(sb, RESERVATION)) + seq_puts(seq, ",noreservation"); + if (sbi->s_commit_interval) { + seq_printf(seq, ",commit=%u", + (unsigned) (sbi->s_commit_interval / HZ)); + } + if (test_opt(sb, BARRIER)) + seq_puts(seq, ",barrier=1"); + if (test_opt(sb, NOBH)) + seq_puts(seq, ",nobh"); + + seq_printf(seq, ",data=%s", data_mode_string(sbi->s_mount_opt & + EXT3_MOUNT_DATA_FLAGS)); + if (test_opt(sb, DATA_ERR_ABORT)) + seq_puts(seq, ",data_err=abort"); + + if (test_opt(sb, NOLOAD)) + seq_puts(seq, ",norecovery"); ext3_show_quota_options(seq, sb); @@ -555,13 +670,10 @@ static int ext3_show_options(struct seq_file *seq, struct vfsmount *vfs) } -static struct dentry *ext3_get_dentry(struct super_block *sb, void *vobjp) +static struct inode *ext3_nfs_get_inode(struct super_block *sb, + u64 ino, u32 generation) { - __u32 *objp = vobjp; - unsigned long ino = objp[0]; - __u32 generation = objp[1]; struct inode *inode; - struct dentry *result; if (ino < EXT3_FIRST_INO(sb) && ino != EXT3_ROOT_INO) return ERR_PTR(-ESTALE); @@ -576,46 +688,71 @@ static struct dentry *ext3_get_dentry(struct super_block *sb, void *vobjp) * Currently we don't know the generation for parent directory, so * a generation of 0 means "accept any" */ - inode = iget(sb, ino); - if (inode == NULL) - return ERR_PTR(-ENOMEM); - if (is_bad_inode(inode) || - (generation && inode->i_generation != generation)) { + inode = ext3_iget(sb, ino); + if (IS_ERR(inode)) + return ERR_CAST(inode); + if (generation && inode->i_generation != generation) { 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; + + return inode; +} + +static struct dentry *ext3_fh_to_dentry(struct super_block *sb, struct fid *fid, + int fh_len, int fh_type) +{ + return generic_fh_to_dentry(sb, fid, fh_len, fh_type, + ext3_nfs_get_inode); +} + +static struct dentry *ext3_fh_to_parent(struct super_block *sb, struct fid *fid, + int fh_len, int fh_type) +{ + return generic_fh_to_parent(sb, fid, fh_len, fh_type, + ext3_nfs_get_inode); +} + +/* + * Try to release metadata pages (indirect blocks, directories) which are + * mapped via the block device. Since these pages could have journal heads + * which would prevent try_to_free_buffers() from freeing them, we must use + * jbd layer's try_to_free_buffers() function to release them. + */ +static int bdev_try_to_free_page(struct super_block *sb, struct page *page, + gfp_t wait) +{ + journal_t *journal = EXT3_SB(sb)->s_journal; + + WARN_ON(PageChecked(page)); + if (!page_has_buffers(page)) + return 0; + if (journal) + return journal_try_to_free_buffers(journal, page, + wait & ~__GFP_WAIT); + return try_to_free_buffers(page); } #ifdef CONFIG_QUOTA #define QTYPE2NAME(t) ((t)==USRQUOTA?"user":"group") #define QTYPE2MOPT(on, t) ((t)==USRQUOTA?((on)##USRJQUOTA):((on)##GRPJQUOTA)) -static int ext3_dquot_initialize(struct inode *inode, int type); -static int ext3_dquot_drop(struct inode *inode); static int ext3_write_dquot(struct dquot *dquot); static int ext3_acquire_dquot(struct dquot *dquot); static int ext3_release_dquot(struct dquot *dquot); static int ext3_mark_dquot_dirty(struct dquot *dquot); static int ext3_write_info(struct super_block *sb, int type); -static int ext3_quota_on(struct super_block *sb, int type, int format_id, char *path); +static int ext3_quota_on(struct super_block *sb, int type, int format_id, + char *path, int remount); static int ext3_quota_on_mount(struct super_block *sb, int type); static ssize_t ext3_quota_read(struct super_block *sb, int type, char *data, size_t len, loff_t off); static ssize_t ext3_quota_write(struct super_block *sb, int type, const char *data, size_t len, loff_t off); -static struct dquot_operations ext3_quota_operations = { - .initialize = ext3_dquot_initialize, - .drop = ext3_dquot_drop, +static const struct dquot_operations ext3_quota_operations = { + .initialize = dquot_initialize, + .drop = dquot_drop, .alloc_space = dquot_alloc_space, .alloc_inode = dquot_alloc_inode, .free_space = dquot_free_space, @@ -625,10 +762,12 @@ static struct dquot_operations ext3_quota_operations = { .acquire_dquot = ext3_acquire_dquot, .release_dquot = ext3_release_dquot, .mark_dirty = ext3_mark_dquot_dirty, - .write_info = ext3_write_info + .write_info = ext3_write_info, + .alloc_dquot = dquot_alloc, + .destroy_dquot = dquot_destroy, }; -static struct quotactl_ops ext3_qctl_operations = { +static const struct quotactl_ops ext3_qctl_operations = { .quota_on = ext3_quota_on, .quota_off = vfs_quota_off, .quota_sync = vfs_quota_sync, @@ -639,18 +778,16 @@ static struct quotactl_ops ext3_qctl_operations = { }; #endif -static struct super_operations ext3_sops = { +static const struct super_operations ext3_sops = { .alloc_inode = ext3_alloc_inode, .destroy_inode = ext3_destroy_inode, - .read_inode = ext3_read_inode, .write_inode = ext3_write_inode, .dirty_inode = ext3_dirty_inode, .delete_inode = ext3_delete_inode, .put_super = ext3_put_super, - .write_super = ext3_write_super, .sync_fs = ext3_sync_fs, - .write_super_lockfs = ext3_write_super_lockfs, - .unlockfs = ext3_unlockfs, + .freeze_fs = ext3_freeze, + .unfreeze_fs = ext3_unfreeze, .statfs = ext3_statfs, .remount_fs = ext3_remount, .clear_inode = ext3_clear_inode, @@ -659,11 +796,13 @@ static struct super_operations ext3_sops = { .quota_read = ext3_quota_read, .quota_write = ext3_quota_write, #endif + .bdev_try_to_free_page = bdev_try_to_free_page, }; -static struct export_operations ext3_export_ops = { +static const struct export_operations ext3_export_ops = { + .fh_to_dentry = ext3_fh_to_dentry, + .fh_to_parent = ext3_fh_to_parent, .get_parent = ext3_get_parent, - .get_dentry = ext3_get_dentry, }; enum { @@ -674,13 +813,14 @@ enum { Opt_reservation, Opt_noreservation, Opt_noload, Opt_nobh, Opt_bh, Opt_commit, Opt_journal_update, Opt_journal_inum, Opt_journal_dev, Opt_abort, Opt_data_journal, Opt_data_ordered, Opt_data_writeback, + Opt_data_err_abort, Opt_data_err_ignore, Opt_usrjquota, Opt_grpjquota, Opt_offusrjquota, Opt_offgrpjquota, - Opt_jqfmt_vfsold, Opt_jqfmt_vfsv0, Opt_quota, Opt_noquota, - Opt_ignore, Opt_barrier, Opt_err, Opt_resize, Opt_usrquota, - Opt_grpquota + Opt_jqfmt_vfsold, Opt_jqfmt_vfsv0, Opt_jqfmt_vfsv1, Opt_quota, + Opt_noquota, Opt_ignore, Opt_barrier, Opt_err, Opt_resize, + Opt_usrquota, Opt_grpquota }; -static match_table_t tokens = { +static const match_table_t tokens = { {Opt_bsd_df, "bsddf"}, {Opt_minix_df, "minixdf"}, {Opt_grpid, "grpid"}, @@ -706,6 +846,7 @@ static match_table_t tokens = { {Opt_reservation, "reservation"}, {Opt_noreservation, "noreservation"}, {Opt_noload, "noload"}, + {Opt_noload, "norecovery"}, {Opt_nobh, "nobh"}, {Opt_bh, "bh"}, {Opt_commit, "commit=%u"}, @@ -716,22 +857,25 @@ static match_table_t tokens = { {Opt_data_journal, "data=journal"}, {Opt_data_ordered, "data=ordered"}, {Opt_data_writeback, "data=writeback"}, + {Opt_data_err_abort, "data_err=abort"}, + {Opt_data_err_ignore, "data_err=ignore"}, {Opt_offusrjquota, "usrjquota="}, {Opt_usrjquota, "usrjquota=%s"}, {Opt_offgrpjquota, "grpjquota="}, {Opt_grpjquota, "grpjquota=%s"}, {Opt_jqfmt_vfsold, "jqfmt=vfsold"}, {Opt_jqfmt_vfsv0, "jqfmt=vfsv0"}, + {Opt_jqfmt_vfsv1, "jqfmt=vfsv1"}, {Opt_grpquota, "grpquota"}, {Opt_noquota, "noquota"}, {Opt_quota, "quota"}, {Opt_usrquota, "usrquota"}, {Opt_barrier, "barrier=%u"}, - {Opt_err, NULL}, {Opt_resize, "resize"}, + {Opt_err, NULL}, }; -static ext3_fsblk_t get_sb_block(void **data) +static ext3_fsblk_t get_sb_block(void **data, struct super_block *sb) { ext3_fsblk_t sb_block; char *options = (char *) *data; @@ -742,7 +886,7 @@ static ext3_fsblk_t get_sb_block(void **data) /*todo: use simple_strtoll with >32bit ext3 */ sb_block = simple_strtoul(options, &options, 0); if (*options && *options != ',') { - printk("EXT3-fs: Invalid sb specification: %s\n", + ext3_msg(sb, "error: invalid sb specification: %s", (char *) *data); return 1; } @@ -762,7 +906,7 @@ static int parse_options (char *options, struct super_block *sb, int data_opt = 0; int option; #ifdef CONFIG_QUOTA - int qtype; + int qtype, qfmt; char *qname; #endif @@ -842,7 +986,8 @@ static int parse_options (char *options, struct super_block *sb, #else case Opt_user_xattr: case Opt_nouser_xattr: - printk("EXT3 (no)user_xattr options not supported\n"); + ext3_msg(sb, KERN_INFO, + "(no)user_xattr options not supported"); break; #endif #ifdef CONFIG_EXT3_FS_POSIX_ACL @@ -855,7 +1000,8 @@ static int parse_options (char *options, struct super_block *sb, #else case Opt_acl: case Opt_noacl: - printk("EXT3 (no)acl options not supported\n"); + ext3_msg(sb, KERN_INFO, + "(no)acl options not supported"); break; #endif case Opt_reservation: @@ -871,16 +1017,16 @@ static int parse_options (char *options, struct super_block *sb, user to specify an existing inode to be the journal file. */ if (is_remount) { - printk(KERN_ERR "EXT3-fs: cannot specify " - "journal on remount\n"); + ext3_msg(sb, KERN_ERR, "error: cannot specify " + "journal on remount"); return 0; } set_opt (sbi->s_mount_opt, UPDATE_JOURNAL); break; case Opt_journal_inum: if (is_remount) { - printk(KERN_ERR "EXT3-fs: cannot specify " - "journal on remount\n"); + ext3_msg(sb, KERN_ERR, "error: cannot specify " + "journal on remount"); return 0; } if (match_int(&args[0], &option)) @@ -889,8 +1035,8 @@ static int parse_options (char *options, struct super_block *sb, break; case Opt_journal_dev: if (is_remount) { - printk(KERN_ERR "EXT3-fs: cannot specify " - "journal on remount\n"); + ext3_msg(sb, KERN_ERR, "error: cannot specify " + "journal on remount"); return 0; } if (match_int(&args[0], &option)) @@ -920,17 +1066,28 @@ static int parse_options (char *options, struct super_block *sb, datacheck: if (is_remount) { if ((sbi->s_mount_opt & EXT3_MOUNT_DATA_FLAGS) - != data_opt) { - printk(KERN_ERR - "EXT3-fs: cannot change data " - "mode on remount\n"); - return 0; - } + == data_opt) + break; + ext3_msg(sb, KERN_ERR, + "error: cannot change " + "data mode on remount. The filesystem " + "is mounted in data=%s mode and you " + "try to remount it in data=%s mode.", + data_mode_string(sbi->s_mount_opt & + EXT3_MOUNT_DATA_FLAGS), + data_mode_string(data_opt)); + return 0; } else { sbi->s_mount_opt &= ~EXT3_MOUNT_DATA_FLAGS; sbi->s_mount_opt |= data_opt; } break; + case Opt_data_err_abort: + set_opt(sbi->s_mount_opt, DATA_ERR_ABORT); + break; + case Opt_data_err_ignore: + clear_opt(sbi->s_mount_opt, DATA_ERR_ABORT); + break; #ifdef CONFIG_QUOTA case Opt_usrjquota: qtype = USRQUOTA; @@ -938,32 +1095,33 @@ static int parse_options (char *options, struct super_block *sb, case Opt_grpjquota: qtype = GRPQUOTA; set_qf_name: - if (sb_any_quota_enabled(sb)) { - printk(KERN_ERR - "EXT3-fs: Cannot change journalled " - "quota options when quota turned on.\n"); + if (sb_any_quota_loaded(sb) && + !sbi->s_qf_names[qtype]) { + ext3_msg(sb, KERN_ERR, + "error: cannot change journaled " + "quota options when quota turned on."); return 0; } qname = match_strdup(&args[0]); if (!qname) { - printk(KERN_ERR - "EXT3-fs: not enough memory for " - "storing quotafile name.\n"); + ext3_msg(sb, KERN_ERR, + "error: not enough memory for " + "storing quotafile name."); return 0; } if (sbi->s_qf_names[qtype] && strcmp(sbi->s_qf_names[qtype], qname)) { - printk(KERN_ERR - "EXT3-fs: %s quota file already " - "specified.\n", QTYPE2NAME(qtype)); + ext3_msg(sb, KERN_ERR, + "error: %s quota file already " + "specified.", QTYPE2NAME(qtype)); kfree(qname); return 0; } sbi->s_qf_names[qtype] = qname; if (strchr(sbi->s_qf_names[qtype], '/')) { - printk(KERN_ERR - "EXT3-fs: quotafile must be on " - "filesystem root.\n"); + ext3_msg(sb, KERN_ERR, + "error: quotafile must be on " + "filesystem root."); kfree(sbi->s_qf_names[qtype]); sbi->s_qf_names[qtype] = NULL; return 0; @@ -976,10 +1134,11 @@ set_qf_name: case Opt_offgrpjquota: qtype = GRPQUOTA; clear_qf_name: - if (sb_any_quota_enabled(sb)) { - printk(KERN_ERR "EXT3-fs: Cannot change " - "journalled quota options when " - "quota turned on.\n"); + if (sb_any_quota_loaded(sb) && + sbi->s_qf_names[qtype]) { + ext3_msg(sb, KERN_ERR, "error: cannot change " + "journaled quota options when " + "quota turned on."); return 0; } /* @@ -989,10 +1148,22 @@ clear_qf_name: sbi->s_qf_names[qtype] = NULL; break; case Opt_jqfmt_vfsold: - sbi->s_jquota_fmt = QFMT_VFS_OLD; - break; + qfmt = QFMT_VFS_OLD; + goto set_qf_format; case Opt_jqfmt_vfsv0: - sbi->s_jquota_fmt = QFMT_VFS_V0; + qfmt = QFMT_VFS_V0; + goto set_qf_format; + case Opt_jqfmt_vfsv1: + qfmt = QFMT_VFS_V1; +set_qf_format: + if (sb_any_quota_loaded(sb) && + sbi->s_jquota_fmt != qfmt) { + ext3_msg(sb, KERN_ERR, "error: cannot change " + "journaled quota options when " + "quota turned on."); + return 0; + } + sbi->s_jquota_fmt = qfmt; break; case Opt_quota: case Opt_usrquota: @@ -1004,9 +1175,9 @@ clear_qf_name: set_opt(sbi->s_mount_opt, GRPQUOTA); break; case Opt_noquota: - if (sb_any_quota_enabled(sb)) { - printk(KERN_ERR "EXT3-fs: Cannot change quota " - "options when quota turned on.\n"); + if (sb_any_quota_loaded(sb)) { + ext3_msg(sb, KERN_ERR, "error: cannot change " + "quota options when quota turned on."); return 0; } clear_opt(sbi->s_mount_opt, QUOTA); @@ -1017,15 +1188,19 @@ clear_qf_name: case Opt_quota: case Opt_usrquota: case Opt_grpquota: + ext3_msg(sb, KERN_ERR, + "error: quota options not supported."); + break; case Opt_usrjquota: case Opt_grpjquota: case Opt_offusrjquota: case Opt_offgrpjquota: case Opt_jqfmt_vfsold: case Opt_jqfmt_vfsv0: - printk(KERN_ERR - "EXT3-fs: journalled quota options not " - "supported.\n"); + case Opt_jqfmt_vfsv1: + ext3_msg(sb, KERN_ERR, + "error: journaled quota options not " + "supported."); break; case Opt_noquota: break; @@ -1045,8 +1220,9 @@ clear_qf_name: break; case Opt_resize: if (!is_remount) { - printk("EXT3-fs: resize option only available " - "for remount\n"); + ext3_msg(sb, KERN_ERR, + "error: resize option only available " + "for remount"); return 0; } if (match_int(&args[0], &option) != 0) @@ -1060,9 +1236,9 @@ clear_qf_name: clear_opt(sbi->s_mount_opt, NOBH); break; default: - printk (KERN_ERR - "EXT3-fs: Unrecognized mount option \"%s\" " - "or missing value\n", p); + ext3_msg(sb, KERN_ERR, + "error: unrecognized mount option \"%s\" " + "or missing value", p); return 0; } } @@ -1080,21 +1256,21 @@ clear_qf_name: (sbi->s_mount_opt & EXT3_MOUNT_GRPQUOTA)) || (sbi->s_qf_names[GRPQUOTA] && (sbi->s_mount_opt & EXT3_MOUNT_USRQUOTA))) { - printk(KERN_ERR "EXT3-fs: old and new quota " - "format mixing.\n"); + ext3_msg(sb, KERN_ERR, "error: old and new quota " + "format mixing."); return 0; } if (!sbi->s_jquota_fmt) { - printk(KERN_ERR "EXT3-fs: journalled quota format " - "not specified.\n"); + ext3_msg(sb, KERN_ERR, "error: journaled quota format " + "not specified."); return 0; } } else { if (sbi->s_jquota_fmt) { - printk(KERN_ERR "EXT3-fs: journalled quota format " - "specified with no journalling " - "enabled.\n"); + ext3_msg(sb, KERN_ERR, "error: journaled quota format " + "specified with no journaling " + "enabled."); return 0; } } @@ -1109,90 +1285,86 @@ static int ext3_setup_super(struct super_block *sb, struct ext3_super_block *es, int res = 0; if (le32_to_cpu(es->s_rev_level) > EXT3_MAX_SUPP_REV) { - printk (KERN_ERR "EXT3-fs warning: revision level too high, " - "forcing read-only mode\n"); + ext3_msg(sb, KERN_ERR, + "error: revision level too high, " + "forcing read-only mode"); res = MS_RDONLY; } if (read_only) return res; if (!(sbi->s_mount_state & EXT3_VALID_FS)) - printk (KERN_WARNING "EXT3-fs warning: mounting unchecked fs, " - "running e2fsck is recommended\n"); + ext3_msg(sb, KERN_WARNING, + "warning: mounting unchecked fs, " + "running e2fsck is recommended"); else if ((sbi->s_mount_state & EXT3_ERROR_FS)) - printk (KERN_WARNING - "EXT3-fs warning: mounting fs with errors, " - "running e2fsck is recommended\n"); + ext3_msg(sb, KERN_WARNING, + "warning: mounting fs with errors, " + "running e2fsck is recommended"); 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 (KERN_WARNING - "EXT3-fs warning: maximal mount count reached, " - "running e2fsck is recommended\n"); + ext3_msg(sb, KERN_WARNING, + "warning: maximal mount count reached, " + "running e2fsck is recommended"); else if (le32_to_cpu(es->s_checkinterval) && (le32_to_cpu(es->s_lastcheck) + le32_to_cpu(es->s_checkinterval) <= get_seconds())) - printk (KERN_WARNING - "EXT3-fs warning: checktime reached, " - "running e2fsck is recommended\n"); + ext3_msg(sb, KERN_WARNING, + "warning: checktime reached, " + "running e2fsck is recommended"); #if 0 /* @@@ We _will_ want to clear the valid bit if we find inconsistencies, to force a fsck at reboot. But for a plain journaled filesystem we can keep it set as valid forever! :) */ - es->s_state = cpu_to_le16(le16_to_cpu(es->s_state) & ~EXT3_VALID_FS); + es->s_state &= cpu_to_le16(~EXT3_VALID_FS); #endif if (!(__s16) le16_to_cpu(es->s_max_mnt_count)) es->s_max_mnt_count = cpu_to_le16(EXT3_DFL_MAX_MNT_COUNT); - es->s_mnt_count=cpu_to_le16(le16_to_cpu(es->s_mnt_count) + 1); + le16_add_cpu(&es->s_mnt_count, 1); es->s_mtime = cpu_to_le32(get_seconds()); ext3_update_dynamic_rev(sb); EXT3_SET_INCOMPAT_FEATURE(sb, EXT3_FEATURE_INCOMPAT_RECOVER); ext3_commit_super(sb, es, 1); if (test_opt(sb, DEBUG)) - printk(KERN_INFO "[EXT3 FS bs=%lu, gc=%lu, " - "bpg=%lu, ipg=%lu, mo=%04lx]\n", + ext3_msg(sb, KERN_INFO, "[bs=%lu, gc=%lu, " + "bpg=%lu, ipg=%lu, mo=%04lx]", sb->s_blocksize, sbi->s_groups_count, EXT3_BLOCKS_PER_GROUP(sb), EXT3_INODES_PER_GROUP(sb), sbi->s_mount_opt); - printk(KERN_INFO "EXT3 FS on %s, ", sb->s_id); if (EXT3_SB(sb)->s_journal->j_inode == NULL) { char b[BDEVNAME_SIZE]; - - printk("external journal on %s\n", + ext3_msg(sb, KERN_INFO, "using external journal on %s", bdevname(EXT3_SB(sb)->s_journal->j_dev, b)); } else { - printk("internal journal\n"); + ext3_msg(sb, KERN_INFO, "using internal journal"); } return res; } /* Called at mount-time, super-block is locked */ -static int ext3_check_descriptors (struct super_block * sb) +static int ext3_check_descriptors(struct super_block *sb) { struct ext3_sb_info *sbi = EXT3_SB(sb); - ext3_fsblk_t first_block = le32_to_cpu(sbi->s_es->s_first_data_block); - ext3_fsblk_t last_block; - struct ext3_group_desc * gdp = NULL; - int desc_block = 0; int i; ext3_debug ("Checking group descriptors"); - for (i = 0; i < sbi->s_groups_count; i++) - { + for (i = 0; i < sbi->s_groups_count; i++) { + struct ext3_group_desc *gdp = ext3_get_group_desc(sb, i, NULL); + ext3_fsblk_t first_block = ext3_group_first_block_no(sb, i); + ext3_fsblk_t last_block; + if (i == sbi->s_groups_count - 1) last_block = le32_to_cpu(sbi->s_es->s_blocks_count) - 1; else last_block = first_block + (EXT3_BLOCKS_PER_GROUP(sb) - 1); - if ((i % EXT3_DESC_PER_BLOCK(sb)) == 0) - gdp = (struct ext3_group_desc *) - sbi->s_group_desc[desc_block++]->b_data; if (le32_to_cpu(gdp->bg_block_bitmap) < first_block || le32_to_cpu(gdp->bg_block_bitmap) > last_block) { @@ -1214,7 +1386,7 @@ static int ext3_check_descriptors (struct super_block * sb) return 0; } if (le32_to_cpu(gdp->bg_inode_table) < first_block || - le32_to_cpu(gdp->bg_inode_table) + sbi->s_itb_per_group > + le32_to_cpu(gdp->bg_inode_table) + sbi->s_itb_per_group - 1 > last_block) { ext3_error (sb, "ext3_check_descriptors", @@ -1224,8 +1396,6 @@ static int ext3_check_descriptors (struct super_block * sb) le32_to_cpu(gdp->bg_inode_table)); return 0; } - first_block += EXT3_BLOCKS_PER_GROUP(sb); - gdp++; } sbi->s_es->s_free_blocks_count=cpu_to_le32(ext3_count_free_blocks(sb)); @@ -1265,8 +1435,8 @@ static void ext3_orphan_cleanup (struct super_block * sb, } if (bdev_read_only(sb->s_bdev)) { - printk(KERN_ERR "EXT3-fs: write access " - "unavailable, skipping orphan cleanup.\n"); + ext3_msg(sb, KERN_ERR, "error: write access " + "unavailable, skipping orphan cleanup."); return; } @@ -1280,8 +1450,7 @@ static void ext3_orphan_cleanup (struct super_block * sb, } if (s_flags & MS_RDONLY) { - printk(KERN_INFO "EXT3-fs: %s: orphan cleanup on readonly fs\n", - sb->s_id); + ext3_msg(sb, KERN_INFO, "orphan cleanup on readonly fs"); sb->s_flags &= ~MS_RDONLY; } #ifdef CONFIG_QUOTA @@ -1292,9 +1461,9 @@ static void ext3_orphan_cleanup (struct super_block * sb, if (EXT3_SB(sb)->s_qf_names[i]) { int ret = ext3_quota_on_mount(sb, i); if (ret < 0) - printk(KERN_ERR - "EXT3-fs: Cannot turn on journalled " - "quota: error %d\n", ret); + ext3_msg(sb, KERN_ERR, + "error: cannot turn on journaled " + "quota: %d", ret); } } #endif @@ -1302,18 +1471,18 @@ static void ext3_orphan_cleanup (struct super_block * sb, while (es->s_last_orphan) { struct inode *inode; - if (!(inode = - ext3_orphan_get(sb, le32_to_cpu(es->s_last_orphan)))) { + inode = ext3_orphan_get(sb, le32_to_cpu(es->s_last_orphan)); + if (IS_ERR(inode)) { es->s_last_orphan = 0; break; } list_add(&EXT3_I(inode)->i_orphan, &EXT3_SB(sb)->s_orphan); - DQUOT_INIT(inode); + vfs_dq_init(inode); if (inode->i_nlink) { printk(KERN_DEBUG "%s: truncating inode %lu to %Ld bytes\n", - __FUNCTION__, inode->i_ino, inode->i_size); + __func__, inode->i_ino, inode->i_size); jbd_debug(2, "truncating inode %lu to %Ld bytes\n", inode->i_ino, inode->i_size); ext3_truncate(inode); @@ -1321,7 +1490,7 @@ static void ext3_orphan_cleanup (struct super_block * sb, } else { printk(KERN_DEBUG "%s: deleting unreferenced inode %lu\n", - __FUNCTION__, inode->i_ino); + __func__, inode->i_ino); jbd_debug(2, "deleting unreferenced inode %lu\n", inode->i_ino); nr_orphans++; @@ -1332,23 +1501,21 @@ static void ext3_orphan_cleanup (struct super_block * sb, #define PLURAL(x) (x), ((x)==1) ? "" : "s" if (nr_orphans) - printk(KERN_INFO "EXT3-fs: %s: %d orphan inode%s deleted\n", - sb->s_id, PLURAL(nr_orphans)); + ext3_msg(sb, KERN_INFO, "%d orphan inode%s deleted", + PLURAL(nr_orphans)); if (nr_truncates) - printk(KERN_INFO "EXT3-fs: %s: %d truncate%s cleaned up\n", - sb->s_id, PLURAL(nr_truncates)); + ext3_msg(sb, KERN_INFO, "%d truncate%s cleaned up", + PLURAL(nr_truncates)); #ifdef CONFIG_QUOTA /* Turn quotas off */ for (i = 0; i < MAXQUOTAS; i++) { if (sb_dqopt(sb)->files[i]) - vfs_quota_off(sb, i); + vfs_quota_off(sb, i, 0); } #endif sb->s_flags = s_flags; /* Restore MS_RDONLY status */ } -#define log2(n) ffz(~(n)) - /* * 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. @@ -1357,11 +1524,31 @@ static void ext3_orphan_cleanup (struct super_block * sb, static loff_t ext3_max_size(int bits) { loff_t res = EXT3_NDIR_BLOCKS; - /* This constant is calculated to be the largest file size for a - * dense, 4k-blocksize file such that the total number of + int meta_blocks; + loff_t upper_limit; + + /* This is calculated to be the largest file size for a + * dense, 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; + * does not exceed 2^32 -1 + * __u32 i_blocks representing the total number of + * 512 bytes blocks of the file + */ + upper_limit = (1LL << 32) - 1; + + /* total blocks in file system block size */ + upper_limit >>= (bits - 9); + + + /* indirect blocks */ + meta_blocks = 1; + /* double indirect blocks */ + meta_blocks += 1 + (1LL << (bits-2)); + /* tripple indirect blocks */ + meta_blocks += 1 + (1LL << (bits-2)) + (1LL << (2*(bits-2))); + + upper_limit -= meta_blocks; + upper_limit <<= bits; res += 1LL << (bits-2); res += 1LL << (2*(bits-2)); @@ -1369,6 +1556,10 @@ static loff_t ext3_max_size(int bits) res <<= bits; if (res > upper_limit) res = upper_limit; + + if (res > MAX_LFS_FILESIZE) + res = MAX_LFS_FILESIZE; + return res; } @@ -1398,7 +1589,7 @@ static int ext3_fill_super (struct super_block *sb, void *data, int silent) struct ext3_super_block *es = NULL; struct ext3_sb_info *sbi; ext3_fsblk_t block; - ext3_fsblk_t sb_block = get_sb_block(&data); + ext3_fsblk_t sb_block = get_sb_block(&data, sb); ext3_fsblk_t logic_sb_block; unsigned long offset = 0; unsigned int journal_inum = 0; @@ -1410,21 +1601,31 @@ static int ext3_fill_super (struct super_block *sb, void *data, int silent) int db_count; int i; int needs_recovery; + int ret = -EINVAL; __le32 features; + int err; sbi = kzalloc(sizeof(*sbi), GFP_KERNEL); if (!sbi) return -ENOMEM; + + sbi->s_blockgroup_lock = + kzalloc(sizeof(struct blockgroup_lock), GFP_KERNEL); + if (!sbi->s_blockgroup_lock) { + kfree(sbi); + return -ENOMEM; + } sb->s_fs_info = sbi; sbi->s_mount_opt = 0; sbi->s_resuid = EXT3_DEF_RESUID; sbi->s_resgid = EXT3_DEF_RESGID; + sbi->s_sb_block = sb_block; unlock_kernel(); blocksize = sb_min_blocksize(sb, EXT3_MIN_BLOCK_SIZE); if (!blocksize) { - printk(KERN_ERR "EXT3-fs: unable to set blocksize\n"); + ext3_msg(sb, KERN_ERR, "error: unable to set blocksize"); goto out_fail; } @@ -1440,7 +1641,7 @@ static int ext3_fill_super (struct super_block *sb, void *data, int silent) } if (!(bh = sb_bread(sb, logic_sb_block))) { - printk (KERN_ERR "EXT3-fs: unable to read superblock\n"); + ext3_msg(sb, KERN_ERR, "error: unable to read superblock"); goto out_fail; } /* @@ -1461,10 +1662,14 @@ static int ext3_fill_super (struct super_block *sb, void *data, int silent) set_opt(sbi->s_mount_opt, GRPID); if (def_mount_opts & EXT3_DEFM_UID16) set_opt(sbi->s_mount_opt, NO_UID32); +#ifdef CONFIG_EXT3_FS_XATTR if (def_mount_opts & EXT3_DEFM_XATTR_USER) set_opt(sbi->s_mount_opt, XATTR_USER); +#endif +#ifdef CONFIG_EXT3_FS_POSIX_ACL if (def_mount_opts & EXT3_DEFM_ACL) set_opt(sbi->s_mount_opt, POSIX_ACL); +#endif if ((def_mount_opts & EXT3_DEFM_JMODE) == EXT3_DEFM_JMODE_DATA) sbi->s_mount_opt |= EXT3_MOUNT_JOURNAL_DATA; else if ((def_mount_opts & EXT3_DEFM_JMODE) == EXT3_DEFM_JMODE_ORDERED) @@ -1474,10 +1679,10 @@ static int ext3_fill_super (struct super_block *sb, void *data, int silent) if (le16_to_cpu(sbi->s_es->s_errors) == EXT3_ERRORS_PANIC) set_opt(sbi->s_mount_opt, ERRORS_PANIC); - else if (le16_to_cpu(sbi->s_es->s_errors) == EXT3_ERRORS_RO) - set_opt(sbi->s_mount_opt, ERRORS_RO); - else + else if (le16_to_cpu(sbi->s_es->s_errors) == EXT3_ERRORS_CONTINUE) set_opt(sbi->s_mount_opt, ERRORS_CONT); + else + set_opt(sbi->s_mount_opt, ERRORS_RO); sbi->s_resuid = le16_to_cpu(es->s_def_resuid); sbi->s_resgid = le16_to_cpu(es->s_def_resgid); @@ -1495,9 +1700,9 @@ static int ext3_fill_super (struct super_block *sb, void *data, int silent) (EXT3_HAS_COMPAT_FEATURE(sb, ~0U) || EXT3_HAS_RO_COMPAT_FEATURE(sb, ~0U) || EXT3_HAS_INCOMPAT_FEATURE(sb, ~0U))) - printk(KERN_WARNING - "EXT3-fs warning: feature flags set on rev 0 fs, " - "running e2fsck is recommended\n"); + ext3_msg(sb, KERN_WARNING, + "warning: feature flags set on rev 0 fs, " + "running e2fsck is recommended"); /* * Check feature flags regardless of the revision level, since we * previously didn't change the revision level when setting the flags, @@ -1505,55 +1710,60 @@ static int ext3_fill_super (struct super_block *sb, void *data, int silent) */ features = EXT3_HAS_INCOMPAT_FEATURE(sb, ~EXT3_FEATURE_INCOMPAT_SUPP); if (features) { - printk(KERN_ERR "EXT3-fs: %s: couldn't mount because of " - "unsupported optional features (%x).\n", - sb->s_id, le32_to_cpu(features)); + ext3_msg(sb, KERN_ERR, + "error: couldn't mount because of unsupported " + "optional features (%x)", le32_to_cpu(features)); goto failed_mount; } features = EXT3_HAS_RO_COMPAT_FEATURE(sb, ~EXT3_FEATURE_RO_COMPAT_SUPP); if (!(sb->s_flags & MS_RDONLY) && features) { - printk(KERN_ERR "EXT3-fs: %s: couldn't mount RDWR because of " - "unsupported optional features (%x).\n", - sb->s_id, le32_to_cpu(features)); + ext3_msg(sb, KERN_ERR, + "error: couldn't mount RDWR because of unsupported " + "optional features (%x)", le32_to_cpu(features)); goto failed_mount; } blocksize = BLOCK_SIZE << le32_to_cpu(es->s_log_block_size); if (blocksize < EXT3_MIN_BLOCK_SIZE || blocksize > EXT3_MAX_BLOCK_SIZE) { - printk(KERN_ERR - "EXT3-fs: Unsupported filesystem blocksize %d on %s.\n", - blocksize, sb->s_id); + ext3_msg(sb, KERN_ERR, + "error: couldn't mount because of unsupported " + "filesystem blocksize %d", blocksize); goto failed_mount; } - hblock = bdev_hardsect_size(sb->s_bdev); + hblock = bdev_logical_block_size(sb->s_bdev); if (sb->s_blocksize != blocksize) { /* * Make sure the blocksize for the filesystem is larger * than the hardware sectorsize for the machine. */ if (blocksize < hblock) { - printk(KERN_ERR "EXT3-fs: blocksize %d too small for " - "device blocksize %d.\n", blocksize, hblock); + ext3_msg(sb, KERN_ERR, + "error: fsblocksize %d too small for " + "hardware sectorsize %d", blocksize, hblock); goto failed_mount; } brelse (bh); - sb_set_blocksize(sb, blocksize); + if (!sb_set_blocksize(sb, blocksize)) { + ext3_msg(sb, KERN_ERR, + "error: bad blocksize %d", blocksize); + goto out_fail; + } logic_sb_block = (sb_block * EXT3_MIN_BLOCK_SIZE) / blocksize; offset = (sb_block * EXT3_MIN_BLOCK_SIZE) % blocksize; bh = sb_bread(sb, logic_sb_block); if (!bh) { - printk(KERN_ERR - "EXT3-fs: Can't read superblock on 2nd try.\n"); + ext3_msg(sb, KERN_ERR, + "error: can't read superblock on 2nd try"); goto failed_mount; } es = (struct ext3_super_block *)(((char *)bh->b_data) + offset); sbi->s_es = es; if (es->s_magic != cpu_to_le16(EXT3_SUPER_MAGIC)) { - printk (KERN_ERR - "EXT3-fs: Magic mismatch, very weird !\n"); + ext3_msg(sb, KERN_ERR, + "error: magic mismatch"); goto failed_mount; } } @@ -1567,10 +1777,10 @@ static int ext3_fill_super (struct super_block *sb, void *data, int silent) 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 < EXT3_GOOD_OLD_INODE_SIZE) || - (sbi->s_inode_size & (sbi->s_inode_size - 1)) || + (!is_power_of_2(sbi->s_inode_size)) || (sbi->s_inode_size > blocksize)) { - printk (KERN_ERR - "EXT3-fs: unsupported inode size: %d\n", + ext3_msg(sb, KERN_ERR, + "error: unsupported inode size: %d", sbi->s_inode_size); goto failed_mount; } @@ -1578,8 +1788,8 @@ static int ext3_fill_super (struct super_block *sb, void *data, int silent) sbi->s_frag_size = EXT3_MIN_FRAG_SIZE << le32_to_cpu(es->s_log_frag_size); if (blocksize != sbi->s_frag_size) { - printk(KERN_ERR - "EXT3-fs: fragsize %lu != blocksize %u (unsupported)\n", + ext3_msg(sb, KERN_ERR, + "error: fragsize %lu != blocksize %u (unsupported)", sbi->s_frag_size, blocksize); goto failed_mount; } @@ -1587,7 +1797,7 @@ static int ext3_fill_super (struct super_block *sb, void *data, int silent) 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 (EXT3_INODE_SIZE(sb) == 0) + if (EXT3_INODE_SIZE(sb) == 0 || EXT3_INODES_PER_GROUP(sb) == 0) goto cantfind_ext3; sbi->s_inodes_per_block = blocksize / EXT3_INODE_SIZE(sb); if (sbi->s_inodes_per_block == 0) @@ -1597,38 +1807,49 @@ static int ext3_fill_super (struct super_block *sb, void *data, int silent) sbi->s_desc_per_block = blocksize / sizeof(struct ext3_group_desc); sbi->s_sbh = bh; sbi->s_mount_state = le16_to_cpu(es->s_state); - sbi->s_addr_per_block_bits = log2(EXT3_ADDR_PER_BLOCK(sb)); - sbi->s_desc_per_block_bits = log2(EXT3_DESC_PER_BLOCK(sb)); + sbi->s_addr_per_block_bits = ilog2(EXT3_ADDR_PER_BLOCK(sb)); + sbi->s_desc_per_block_bits = ilog2(EXT3_DESC_PER_BLOCK(sb)); for (i=0; i < 4; i++) sbi->s_hash_seed[i] = le32_to_cpu(es->s_hash_seed[i]); sbi->s_def_hash_version = es->s_def_hash_version; + i = le32_to_cpu(es->s_flags); + if (i & EXT2_FLAGS_UNSIGNED_HASH) + sbi->s_hash_unsigned = 3; + else if ((i & EXT2_FLAGS_SIGNED_HASH) == 0) { +#ifdef __CHAR_UNSIGNED__ + es->s_flags |= cpu_to_le32(EXT2_FLAGS_UNSIGNED_HASH); + sbi->s_hash_unsigned = 3; +#else + es->s_flags |= cpu_to_le32(EXT2_FLAGS_SIGNED_HASH); +#endif + } if (sbi->s_blocks_per_group > blocksize * 8) { - printk (KERN_ERR - "EXT3-fs: #blocks per group too big: %lu\n", + ext3_msg(sb, KERN_ERR, + "#blocks per group too big: %lu", sbi->s_blocks_per_group); goto failed_mount; } if (sbi->s_frags_per_group > blocksize * 8) { - printk (KERN_ERR - "EXT3-fs: #fragments per group too big: %lu\n", + ext3_msg(sb, KERN_ERR, + "error: #fragments per group too big: %lu", sbi->s_frags_per_group); goto failed_mount; } if (sbi->s_inodes_per_group > blocksize * 8) { - printk (KERN_ERR - "EXT3-fs: #inodes per group too big: %lu\n", + ext3_msg(sb, KERN_ERR, + "error: #inodes per group too big: %lu", sbi->s_inodes_per_group); goto failed_mount; } if (le32_to_cpu(es->s_blocks_count) > (sector_t)(~0ULL) >> (sb->s_blocksize_bits - 9)) { - printk(KERN_ERR "EXT3-fs: filesystem on %s:" - " too large to mount safely\n", sb->s_id); + ext3_msg(sb, KERN_ERR, + "error: filesystem is too large to mount safely"); if (sizeof(sector_t) < 8) - printk(KERN_WARNING "EXT3-fs: CONFIG_LBD not " - "enabled\n"); + ext3_msg(sb, KERN_ERR, + "error: CONFIG_LBDAF not enabled"); goto failed_mount; } @@ -1642,36 +1863,46 @@ static int ext3_fill_super (struct super_block *sb, void *data, int silent) sbi->s_group_desc = kmalloc(db_count * sizeof (struct buffer_head *), GFP_KERNEL); if (sbi->s_group_desc == NULL) { - printk (KERN_ERR "EXT3-fs: not enough memory\n"); + ext3_msg(sb, KERN_ERR, + "error: not enough memory"); goto failed_mount; } - bgl_lock_init(&sbi->s_blockgroup_lock); + bgl_lock_init(sbi->s_blockgroup_lock); 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]) { - printk (KERN_ERR "EXT3-fs: " - "can't read group descriptor %d\n", i); + ext3_msg(sb, KERN_ERR, + "error: can't read group descriptor %d", i); db_count = i; goto failed_mount2; } } if (!ext3_check_descriptors (sb)) { - printk(KERN_ERR "EXT3-fs: group descriptors corrupted!\n"); + ext3_msg(sb, KERN_ERR, + "error: group descriptors corrupted"); 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); - percpu_counter_init(&sbi->s_freeblocks_counter, - ext3_count_free_blocks(sb)); - percpu_counter_init(&sbi->s_freeinodes_counter, - ext3_count_free_inodes(sb)); - percpu_counter_init(&sbi->s_dirs_counter, - ext3_count_dirs(sb)); + err = percpu_counter_init(&sbi->s_freeblocks_counter, + ext3_count_free_blocks(sb)); + if (!err) { + err = percpu_counter_init(&sbi->s_freeinodes_counter, + ext3_count_free_inodes(sb)); + } + if (!err) { + err = percpu_counter_init(&sbi->s_dirs_counter, + ext3_count_dirs(sb)); + } + if (err) { + ext3_msg(sb, KERN_ERR, "error: insufficient memory"); + goto failed_mount3; + } /* per fileystem reservation list head & lock */ spin_lock_init(&sbi->s_rsv_window_lock); @@ -1697,6 +1928,8 @@ static int ext3_fill_super (struct super_block *sb, void *data, int silent) sb->dq_op = &ext3_quota_operations; #endif INIT_LIST_HEAD(&sbi->s_orphan); /* unlinked but open files */ + mutex_init(&sbi->s_orphan_lock); + mutex_init(&sbi->s_resize_lock); sb->s_root = NULL; @@ -1717,9 +1950,9 @@ static int ext3_fill_super (struct super_block *sb, void *data, int silent) goto failed_mount3; } else { if (!silent) - printk (KERN_ERR - "ext3: No journal on filesystem on %s\n", - sb->s_id); + ext3_msg(sb, KERN_ERR, + "error: no journal found. " + "mounting ext3 over ext2?"); goto failed_mount3; } @@ -1732,7 +1965,7 @@ static int ext3_fill_super (struct super_block *sb, void *data, int silent) cope, else JOURNAL_DATA */ if (journal_check_available_features (sbi->s_journal, 0, 0, JFS_FEATURE_INCOMPAT_REVOKE)) - set_opt(sbi->s_mount_opt, ORDERED_DATA); + set_opt(sbi->s_mount_opt, DEFAULT_DATA_MODE); else set_opt(sbi->s_mount_opt, JOURNAL_DATA); break; @@ -1741,8 +1974,9 @@ static int ext3_fill_super (struct super_block *sb, void *data, int silent) case EXT3_MOUNT_WRITEBACK_DATA: if (!journal_check_available_features (sbi->s_journal, 0, 0, JFS_FEATURE_INCOMPAT_REVOKE)) { - printk(KERN_ERR "EXT3-fs: Journal does not support " - "requested data journaling mode\n"); + ext3_msg(sb, KERN_ERR, + "error: journal does not support " + "requested data journaling mode"); goto failed_mount4; } default: @@ -1751,8 +1985,9 @@ static int ext3_fill_super (struct super_block *sb, void *data, int silent) if (test_opt(sb, NOBH)) { if (!(test_opt(sb, DATA_FLAGS) == EXT3_MOUNT_WRITEBACK_DATA)) { - printk(KERN_WARNING "EXT3-fs: Ignoring nobh option - " - "its supported only with writeback mode\n"); + ext3_msg(sb, KERN_WARNING, + "warning: ignoring nobh option - " + "it is supported only with writeback mode"); clear_opt(sbi->s_mount_opt, NOBH); } } @@ -1761,36 +1996,34 @@ static int ext3_fill_super (struct super_block *sb, void *data, int silent) * so we can safely mount the rest of the filesystem now. */ - root = iget(sb, EXT3_ROOT_INO); - sb->s_root = d_alloc_root(root); - if (!sb->s_root) { - printk(KERN_ERR "EXT3-fs: get root inode failed\n"); - iput(root); + root = ext3_iget(sb, EXT3_ROOT_INO); + if (IS_ERR(root)) { + ext3_msg(sb, KERN_ERR, "error: get root inode failed"); + ret = PTR_ERR(root); goto failed_mount4; } if (!S_ISDIR(root->i_mode) || !root->i_blocks || !root->i_size) { - dput(sb->s_root); - sb->s_root = NULL; - printk(KERN_ERR "EXT3-fs: corrupt root inode, run e2fsck\n"); + iput(root); + ext3_msg(sb, KERN_ERR, "error: corrupt root inode, run e2fsck"); + goto failed_mount4; + } + sb->s_root = d_alloc_root(root); + if (!sb->s_root) { + ext3_msg(sb, KERN_ERR, "error: get root dentry failed"); + iput(root); + ret = -ENOMEM; goto failed_mount4; } ext3_setup_super (sb, es, sb->s_flags & MS_RDONLY); - /* - * akpm: core read_super() calls in here with the superblock locked. - * That deadlocks, because orphan cleanup needs to lock the superblock - * in numerous places. Here we just pop the lock - it's relatively - * harmless, because we are now ready to accept write_super() requests, - * and aviro says that's the only reason for hanging onto the - * superblock lock. - */ + EXT3_SB(sb)->s_mount_state |= EXT3_ORPHAN_FS; ext3_orphan_cleanup(sb, es); EXT3_SB(sb)->s_mount_state &= ~EXT3_ORPHAN_FS; if (needs_recovery) - printk (KERN_INFO "EXT3-fs: recovery complete.\n"); + ext3_msg(sb, KERN_INFO, "recovery complete"); ext3_mark_recovery_complete(sb, es); - printk (KERN_INFO "EXT3-fs: mounted filesystem with %s data mode.\n", + ext3_msg(sb, KERN_INFO, "mounted filesystem with %s data mode", test_opt(sb,DATA_FLAGS) == EXT3_MOUNT_JOURNAL_DATA ? "journal": test_opt(sb,DATA_FLAGS) == EXT3_MOUNT_ORDERED_DATA ? "ordered": "writeback"); @@ -1800,7 +2033,8 @@ static int ext3_fill_super (struct super_block *sb, void *data, int silent) cantfind_ext3: if (!silent) - printk(KERN_ERR "VFS: Can't find ext3 filesystem on dev %s.\n", + ext3_msg(sb, KERN_INFO, + "error: can't find ext3 filesystem on dev %s.", sb->s_id); goto failed_mount; @@ -1823,9 +2057,10 @@ failed_mount: brelse(bh); out_fail: sb->s_fs_info = NULL; + kfree(sbi->s_blockgroup_lock); kfree(sbi); lock_kernel(); - return -EINVAL; + return ret; } /* @@ -1848,6 +2083,10 @@ static void ext3_init_journal_params(struct super_block *sb, journal_t *journal) journal->j_flags |= JFS_BARRIER; else journal->j_flags &= ~JFS_BARRIER; + if (test_opt(sb, DATA_ERR_ABORT)) + journal->j_flags |= JFS_ABORT_ON_SYNCDATA_ERR; + else + journal->j_flags &= ~JFS_ABORT_ON_SYNCDATA_ERR; spin_unlock(&journal->j_state_lock); } @@ -1861,29 +2100,29 @@ static journal_t *ext3_get_journal(struct super_block *sb, * things happen if we iget() an unused inode, as the subsequent * iput() will try to delete it. */ - journal_inode = iget(sb, journal_inum); - if (!journal_inode) { - printk(KERN_ERR "EXT3-fs: no journal found.\n"); + journal_inode = ext3_iget(sb, journal_inum); + if (IS_ERR(journal_inode)) { + ext3_msg(sb, KERN_ERR, "error: no journal found"); return NULL; } if (!journal_inode->i_nlink) { make_bad_inode(journal_inode); iput(journal_inode); - printk(KERN_ERR "EXT3-fs: journal inode is deleted.\n"); + ext3_msg(sb, KERN_ERR, "error: journal inode is deleted"); return NULL; } jbd_debug(2, "Journal inode found at %p: %Ld bytes\n", journal_inode, journal_inode->i_size); - if (is_bad_inode(journal_inode) || !S_ISREG(journal_inode->i_mode)) { - printk(KERN_ERR "EXT3-fs: invalid journal inode.\n"); + if (!S_ISREG(journal_inode->i_mode)) { + ext3_msg(sb, KERN_ERR, "error: invalid journal inode"); iput(journal_inode); return NULL; } journal = journal_init_inode(journal_inode); if (!journal) { - printk(KERN_ERR "EXT3-fs: Could not load journal inode\n"); + ext3_msg(sb, KERN_ERR, "error: could not load journal inode"); iput(journal_inode); return NULL; } @@ -1905,22 +2144,22 @@ static journal_t *ext3_get_dev_journal(struct super_block *sb, struct ext3_super_block * es; struct block_device *bdev; - bdev = ext3_blkdev_get(j_dev); + bdev = ext3_blkdev_get(j_dev, sb); if (bdev == NULL) return NULL; if (bd_claim(bdev, sb)) { - printk(KERN_ERR - "EXT3: failed to claim external journal device.\n"); - blkdev_put(bdev); + ext3_msg(sb, KERN_ERR, + "error: failed to claim external journal device"); + blkdev_put(bdev, FMODE_READ|FMODE_WRITE); return NULL; } blocksize = sb->s_blocksize; - hblock = bdev_hardsect_size(bdev); + hblock = bdev_logical_block_size(bdev); if (blocksize < hblock) { - printk(KERN_ERR - "EXT3-fs: blocksize too small for journal device.\n"); + ext3_msg(sb, KERN_ERR, + "error: blocksize too small for journal device"); goto out_bdev; } @@ -1928,8 +2167,8 @@ static journal_t *ext3_get_dev_journal(struct super_block *sb, offset = EXT3_MIN_BLOCK_SIZE % blocksize; set_blocksize(bdev, blocksize); if (!(bh = __bread(bdev, sb_block, blocksize))) { - printk(KERN_ERR "EXT3-fs: couldn't read superblock of " - "external journal\n"); + ext3_msg(sb, KERN_ERR, "error: couldn't read superblock of " + "external journal"); goto out_bdev; } @@ -1937,14 +2176,14 @@ static journal_t *ext3_get_dev_journal(struct super_block *sb, if ((le16_to_cpu(es->s_magic) != EXT3_SUPER_MAGIC) || !(le32_to_cpu(es->s_feature_incompat) & EXT3_FEATURE_INCOMPAT_JOURNAL_DEV)) { - printk(KERN_ERR "EXT3-fs: external journal has " - "bad superblock\n"); + ext3_msg(sb, KERN_ERR, "error: external journal has " + "bad superblock"); brelse(bh); goto out_bdev; } if (memcmp(EXT3_SB(sb)->s_es->s_journal_uuid, es->s_uuid, 16)) { - printk(KERN_ERR "EXT3-fs: journal UUID does not match\n"); + ext3_msg(sb, KERN_ERR, "error: journal UUID does not match"); brelse(bh); goto out_bdev; } @@ -1956,19 +2195,21 @@ static journal_t *ext3_get_dev_journal(struct super_block *sb, journal = journal_init_dev(bdev, sb->s_bdev, start, len, blocksize); if (!journal) { - printk(KERN_ERR "EXT3-fs: failed to create device journal\n"); + ext3_msg(sb, KERN_ERR, + "error: failed to create device journal"); goto out_bdev; } journal->j_private = sb; ll_rw_block(READ, 1, &journal->j_sb_buffer); wait_on_buffer(journal->j_sb_buffer); if (!buffer_uptodate(journal->j_sb_buffer)) { - printk(KERN_ERR "EXT3-fs: I/O error on journal device\n"); + ext3_msg(sb, KERN_ERR, "I/O error on journal device"); goto out_journal; } if (be32_to_cpu(journal->j_superblock->s_nr_users) != 1) { - printk(KERN_ERR "EXT3-fs: External journal has more than one " - "user (unsupported) - %d\n", + ext3_msg(sb, KERN_ERR, + "error: external journal has more than one " + "user (unsupported) - %d", be32_to_cpu(journal->j_superblock->s_nr_users)); goto out_journal; } @@ -1994,8 +2235,8 @@ static int ext3_load_journal(struct super_block *sb, if (journal_devnum && journal_devnum != le32_to_cpu(es->s_journal_dev)) { - printk(KERN_INFO "EXT3-fs: external journal device major/minor " - "numbers have changed\n"); + ext3_msg(sb, KERN_INFO, "external journal device major/minor " + "numbers have changed"); journal_dev = new_decode_dev(journal_devnum); } else journal_dev = new_decode_dev(le32_to_cpu(es->s_journal_dev)); @@ -2010,21 +2251,21 @@ static int ext3_load_journal(struct super_block *sb, if (EXT3_HAS_INCOMPAT_FEATURE(sb, EXT3_FEATURE_INCOMPAT_RECOVER)) { if (sb->s_flags & MS_RDONLY) { - printk(KERN_INFO "EXT3-fs: INFO: recovery " - "required on readonly filesystem.\n"); + ext3_msg(sb, KERN_INFO, + "recovery required on readonly filesystem"); if (really_read_only) { - printk(KERN_ERR "EXT3-fs: write access " - "unavailable, cannot proceed.\n"); + ext3_msg(sb, KERN_ERR, "error: write access " + "unavailable, cannot proceed"); return -EROFS; } - printk (KERN_INFO "EXT3-fs: write access will " - "be enabled during recovery.\n"); + ext3_msg(sb, KERN_INFO, + "write access will be enabled during recovery"); } } if (journal_inum && journal_dev) { - printk(KERN_ERR "EXT3-fs: filesystem has both journal " - "and inode journals!\n"); + ext3_msg(sb, KERN_ERR, "error: filesystem has both journal " + "and inode journals"); return -EINVAL; } @@ -2039,7 +2280,7 @@ static int ext3_load_journal(struct super_block *sb, if (!really_read_only && test_opt(sb, UPDATE_JOURNAL)) { err = journal_update_format(journal); if (err) { - printk(KERN_ERR "EXT3-fs: error updating journal.\n"); + ext3_msg(sb, KERN_ERR, "error updating journal"); journal_destroy(journal); return err; } @@ -2051,7 +2292,7 @@ static int ext3_load_journal(struct super_block *sb, err = journal_load(journal); if (err) { - printk(KERN_ERR "EXT3-fs: error loading journal.\n"); + ext3_msg(sb, KERN_ERR, "error loading journal"); journal_destroy(journal); return err; } @@ -2062,7 +2303,6 @@ static int ext3_load_journal(struct super_block *sb, if (journal_devnum && journal_devnum != le32_to_cpu(es->s_journal_dev)) { es->s_journal_dev = cpu_to_le32(journal_devnum); - sb->s_dirt = 1; /* Make sure we flush the recovery flag to disk. */ ext3_commit_super(sb, es, 1); @@ -2071,26 +2311,30 @@ static int ext3_load_journal(struct super_block *sb, return 0; } -static int ext3_create_journal(struct super_block * sb, - struct ext3_super_block * es, +static int ext3_create_journal(struct super_block *sb, + struct ext3_super_block *es, unsigned int journal_inum) { journal_t *journal; + int err; if (sb->s_flags & MS_RDONLY) { - printk(KERN_ERR "EXT3-fs: readonly filesystem when trying to " - "create journal.\n"); + ext3_msg(sb, KERN_ERR, + "error: readonly filesystem when trying to " + "create journal"); return -EROFS; } - if (!(journal = ext3_get_journal(sb, journal_inum))) + journal = ext3_get_journal(sb, journal_inum); + if (!journal) return -EINVAL; - printk(KERN_INFO "EXT3-fs: creating new journal on inode %u\n", + ext3_msg(sb, KERN_INFO, "creating new journal on inode %u", journal_inum); - if (journal_create(journal)) { - printk(KERN_ERR "EXT3-fs: error creating journal.\n"); + err = journal_create(journal); + if (err) { + ext3_msg(sb, KERN_ERR, "error creating journal"); journal_destroy(journal); return -EIO; } @@ -2102,7 +2346,6 @@ static int ext3_create_journal(struct super_block * sb, EXT3_SET_COMPAT_FEATURE(sb, EXT3_FEATURE_COMPAT_HAS_JOURNAL); es->s_journal_inum = cpu_to_le32(journal_inum); - sb->s_dirt = 1; /* Make sure we flush the recovery flag to disk. */ ext3_commit_super(sb, es, 1); @@ -2110,21 +2353,34 @@ static int ext3_create_journal(struct super_block * sb, return 0; } -static void ext3_commit_super (struct super_block * sb, - struct ext3_super_block * es, +static int ext3_commit_super(struct super_block *sb, + struct ext3_super_block *es, int sync) { struct buffer_head *sbh = EXT3_SB(sb)->s_sbh; + int error = 0; if (!sbh) - return; - es->s_wtime = cpu_to_le32(get_seconds()); + return error; + /* + * If the file system is mounted read-only, don't update the + * superblock write time. This avoids updating the superblock + * write time when we are mounting the root file system + * read/only but we need to replay the journal; at that point, + * for people who are east of GMT and who make their clock + * tick in localtime for Windows bug-for-bug compatibility, + * the clock is set in the future, and this will cause e2fsck + * to complain and force a full file system check. + */ + if (!(sb->s_flags & MS_RDONLY)) + es->s_wtime = cpu_to_le32(get_seconds()); es->s_free_blocks_count = cpu_to_le32(ext3_count_free_blocks(sb)); es->s_free_inodes_count = cpu_to_le32(ext3_count_free_inodes(sb)); BUFFER_TRACE(sbh, "marking dirty"); mark_buffer_dirty(sbh); if (sync) - sync_dirty_buffer(sbh); + error = sync_dirty_buffer(sbh); + return error; } @@ -2139,13 +2395,16 @@ static void ext3_mark_recovery_complete(struct super_block * sb, journal_t *journal = EXT3_SB(sb)->s_journal; journal_lock_updates(journal); - journal_flush(journal); + if (journal_flush(journal) < 0) + goto out; + if (EXT3_HAS_INCOMPAT_FEATURE(sb, EXT3_FEATURE_INCOMPAT_RECOVER) && sb->s_flags & MS_RDONLY) { EXT3_CLEAR_INCOMPAT_FEATURE(sb, EXT3_FEATURE_INCOMPAT_RECOVER); - sb->s_dirt = 0; ext3_commit_super(sb, es, 1); } + +out: journal_unlock_updates(journal); } @@ -2154,8 +2413,8 @@ static void ext3_mark_recovery_complete(struct super_block * sb, * has recorded an error from a previous lifetime, move that error to the * main filesystem now. */ -static void ext3_clear_journal_err(struct super_block * sb, - struct ext3_super_block * es) +static void ext3_clear_journal_err(struct super_block *sb, + struct ext3_super_block *es) { journal_t *journal; int j_errno; @@ -2173,9 +2432,9 @@ static void ext3_clear_journal_err(struct super_block * sb, char nbuf[16]; errstr = ext3_decode_error(sb, j_errno, nbuf); - ext3_warning(sb, __FUNCTION__, "Filesystem error recorded " + ext3_warning(sb, __func__, "Filesystem error recorded " "from previous mount: %s", errstr); - ext3_warning(sb, __FUNCTION__, "Marking fs in need of " + ext3_warning(sb, __func__, "Marking fs in need of " "filesystem check."); EXT3_SB(sb)->s_mount_state |= EXT3_ERROR_FS; @@ -2199,32 +2458,14 @@ int ext3_force_commit(struct super_block *sb) return 0; journal = EXT3_SB(sb)->s_journal; - sb->s_dirt = 0; ret = ext3_journal_force_commit(journal); return ret; } -/* - * Ext3 always journals updates to the superblock itself, so we don't - * have to propagate any other updates to the superblock on disk at this - * point. Just start an async writeback to get the buffers on their way - * to the disk. - * - * This implicitly triggers the writebehind on sync(). - */ - -static void ext3_write_super (struct super_block * sb) -{ - if (mutex_trylock(&sb->s_lock) != 0) - BUG(); - sb->s_dirt = 0; -} - static int ext3_sync_fs(struct super_block *sb, int wait) { tid_t target; - sb->s_dirt = 0; if (journal_start_commit(EXT3_SB(sb)->s_journal, &target)) { if (wait) log_wait_commit(EXT3_SB(sb)->s_journal, target); @@ -2236,28 +2477,43 @@ static int ext3_sync_fs(struct super_block *sb, int wait) * LVM calls this function before a (read-only) snapshot is created. This * gives us a chance to flush the journal completely and mark the fs clean. */ -static void ext3_write_super_lockfs(struct super_block *sb) +static int ext3_freeze(struct super_block *sb) { - sb->s_dirt = 0; + int error = 0; + journal_t *journal; if (!(sb->s_flags & MS_RDONLY)) { - journal_t *journal = EXT3_SB(sb)->s_journal; + journal = EXT3_SB(sb)->s_journal; /* Now we set up the journal barrier. */ journal_lock_updates(journal); - journal_flush(journal); + + /* + * We don't want to clear needs_recovery flag when we failed + * to flush the journal. + */ + error = journal_flush(journal); + if (error < 0) + goto out; /* Journal blocked and flushed, clear needs_recovery flag. */ EXT3_CLEAR_INCOMPAT_FEATURE(sb, EXT3_FEATURE_INCOMPAT_RECOVER); - ext3_commit_super(sb, EXT3_SB(sb)->s_es, 1); + error = ext3_commit_super(sb, EXT3_SB(sb)->s_es, 1); + if (error) + goto out; } + return 0; + +out: + journal_unlock_updates(journal); + return error; } /* * Called by LVM after the snapshot is done. We need to reset the RECOVER * flag here, even though the filesystem is not technically dirty yet. */ -static void ext3_unlockfs(struct super_block *sb) +static int ext3_unfreeze(struct super_block *sb) { if (!(sb->s_flags & MS_RDONLY)) { lock_super(sb); @@ -2267,6 +2523,7 @@ static void ext3_unlockfs(struct super_block *sb) unlock_super(sb); journal_unlock_updates(EXT3_SB(sb)->s_journal); } + return 0; } static int ext3_remount (struct super_block * sb, int * flags, char * data) @@ -2281,7 +2538,10 @@ static int ext3_remount (struct super_block * sb, int * flags, char * data) int i; #endif + lock_kernel(); + /* Store the original options */ + lock_super(sb); old_sb_flags = sb->s_flags; old_opts.s_mount_opt = sbi->s_mount_opt; old_opts.s_resuid = sbi->s_resuid; @@ -2302,7 +2562,7 @@ static int ext3_remount (struct super_block * sb, int * flags, char * data) } if (sbi->s_mount_opt & EXT3_MOUNT_ABORT) - ext3_abort(sb, __FUNCTION__, "Abort forced by user"); + ext3_abort(sb, __func__, "Abort forced by user"); sb->s_flags = (sb->s_flags & ~MS_POSIXACL) | ((sbi->s_mount_opt & EXT3_MOUNT_POSIX_ACL) ? MS_POSIXACL : 0); @@ -2339,13 +2599,28 @@ static int ext3_remount (struct super_block * sb, int * flags, char * data) __le32 ret; if ((ret = EXT3_HAS_RO_COMPAT_FEATURE(sb, ~EXT3_FEATURE_RO_COMPAT_SUPP))) { - printk(KERN_WARNING "EXT3-fs: %s: couldn't " - "remount RDWR because of unsupported " - "optional features (%x).\n", - sb->s_id, le32_to_cpu(ret)); + ext3_msg(sb, KERN_WARNING, + "warning: couldn't remount RDWR " + "because of unsupported optional " + "features (%x)", le32_to_cpu(ret)); err = -EROFS; goto restore_opts; } + + /* + * If we have an unprocessed orphan list hanging + * around from a previously readonly bdev mount, + * require a full umount/remount for now. + */ + if (es->s_last_orphan) { + ext3_msg(sb, KERN_WARNING, "warning: couldn't " + "remount RDWR because of unprocessed " + "orphan inode list. Please " + "umount/remount instead."); + err = -EINVAL; + goto restore_opts; + } + /* * Mounting a RDONLY partition read-write, so reread * and store the current valid flag. (It may have @@ -2367,6 +2642,8 @@ static int ext3_remount (struct super_block * sb, int * flags, char * data) old_opts.s_qf_names[i] != sbi->s_qf_names[i]) kfree(old_opts.s_qf_names[i]); #endif + unlock_super(sb); + unlock_kernel(); return 0; restore_opts: sb->s_flags = old_sb_flags; @@ -2383,6 +2660,8 @@ restore_opts: sbi->s_qf_names[i] = old_opts.s_qf_names[i]; } #endif + unlock_super(sb); + unlock_kernel(); return err; } @@ -2391,19 +2670,19 @@ static int ext3_statfs (struct dentry * dentry, struct kstatfs * buf) struct super_block *sb = dentry->d_sb; struct ext3_sb_info *sbi = EXT3_SB(sb); struct ext3_super_block *es = sbi->s_es; - ext3_fsblk_t overhead; - int i; u64 fsid; - if (test_opt (sb, MINIX_DF)) - overhead = 0; - else { - unsigned long ngroups; - ngroups = EXT3_SB(sb)->s_groups_count; + if (test_opt(sb, MINIX_DF)) { + sbi->s_overhead_last = 0; + } else if (sbi->s_blocks_last != le32_to_cpu(es->s_blocks_count)) { + unsigned long ngroups = sbi->s_groups_count, i; + ext3_fsblk_t overhead = 0; smp_rmb(); /* - * Compute the overhead (FS structures) + * 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. */ /* @@ -2427,18 +2706,21 @@ static int ext3_statfs (struct dentry * dentry, struct kstatfs * buf) * Every block group has an inode bitmap, a block * bitmap, and an inode table. */ - overhead += (ngroups * (2 + EXT3_SB(sb)->s_itb_per_group)); + overhead += ngroups * (2 + sbi->s_itb_per_group); + sbi->s_overhead_last = overhead; + smp_wmb(); + sbi->s_blocks_last = le32_to_cpu(es->s_blocks_count); } buf->f_type = EXT3_SUPER_MAGIC; buf->f_bsize = sb->s_blocksize; - buf->f_blocks = le32_to_cpu(es->s_blocks_count) - overhead; - buf->f_bfree = percpu_counter_sum(&sbi->s_freeblocks_counter); + buf->f_blocks = le32_to_cpu(es->s_blocks_count) - sbi->s_overhead_last; + buf->f_bfree = percpu_counter_sum_positive(&sbi->s_freeblocks_counter); 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)) buf->f_bavail = 0; buf->f_files = le32_to_cpu(es->s_inodes_count); - buf->f_ffree = percpu_counter_sum(&sbi->s_freeinodes_counter); + buf->f_ffree = percpu_counter_sum_positive(&sbi->s_freeinodes_counter); buf->f_namelen = EXT3_NAME_LEN; fsid = le64_to_cpup((void *)es->s_uuid) ^ le64_to_cpup((void *)es->s_uuid + sizeof(u64)); @@ -2452,7 +2734,7 @@ static int ext3_statfs (struct dentry * dentry, struct kstatfs * buf) * Process 1 Process 2 * ext3_create() quota_sync() * journal_start() write_dquot() - * DQUOT_INIT() down(dqio_mutex) + * vfs_dq_init() down(dqio_mutex) * down(dqio_mutex) journal_start() * */ @@ -2464,38 +2746,6 @@ static inline struct inode *dquot_to_inode(struct dquot *dquot) return sb_dqopt(dquot->dq_sb)->files[dquot->dq_type]; } -static int ext3_dquot_initialize(struct inode *inode, int type) -{ - handle_t *handle; - int ret, err; - - /* We may create quota structure so we need to reserve enough blocks */ - handle = ext3_journal_start(inode, 2*EXT3_QUOTA_INIT_BLOCKS(inode->i_sb)); - if (IS_ERR(handle)) - return PTR_ERR(handle); - ret = dquot_initialize(inode, type); - err = ext3_journal_stop(handle); - if (!ret) - ret = err; - return ret; -} - -static int ext3_dquot_drop(struct inode *inode) -{ - handle_t *handle; - int ret, err; - - /* We may delete quota structure so we need to reserve enough blocks */ - handle = ext3_journal_start(inode, 2*EXT3_QUOTA_DEL_BLOCKS(inode->i_sb)); - if (IS_ERR(handle)) - return PTR_ERR(handle); - ret = dquot_drop(inode); - err = ext3_journal_stop(handle); - if (!ret) - ret = err; - return ret; -} - static int ext3_write_dquot(struct dquot *dquot) { int ret, err; @@ -2537,8 +2787,11 @@ static int ext3_release_dquot(struct dquot *dquot) handle = ext3_journal_start(dquot_to_inode(dquot), EXT3_QUOTA_DEL_BLOCKS(dquot->dq_sb)); - if (IS_ERR(handle)) + if (IS_ERR(handle)) { + /* Release dquot anyway to avoid endless cycle in dqput() */ + dquot_release(dquot); return PTR_ERR(handle); + } ret = dquot_release(dquot); err = ext3_journal_stop(handle); if (!ret) @@ -2548,7 +2801,7 @@ static int ext3_release_dquot(struct dquot *dquot) static int ext3_mark_dquot_dirty(struct dquot *dquot) { - /* Are we journalling quotas? */ + /* Are we journaling quotas? */ if (EXT3_SB(dquot->dq_sb)->s_qf_names[USRQUOTA] || EXT3_SB(dquot->dq_sb)->s_qf_names[GRPQUOTA]) { dquot_mark_dquot_dirty(dquot); @@ -2588,32 +2841,56 @@ static int ext3_quota_on_mount(struct super_block *sb, int type) * Standard function to be called on quota_on */ static int ext3_quota_on(struct super_block *sb, int type, int format_id, - char *path) + char *name, int remount) { int err; - struct nameidata nd; + struct path path; if (!test_opt(sb, QUOTA)) return -EINVAL; - /* Not journalling quota? */ - if (!EXT3_SB(sb)->s_qf_names[USRQUOTA] && - !EXT3_SB(sb)->s_qf_names[GRPQUOTA]) - return vfs_quota_on(sb, type, format_id, path); - err = path_lookup(path, LOOKUP_FOLLOW, &nd); + /* When remounting, no checks are needed and in fact, name is NULL */ + if (remount) + return vfs_quota_on(sb, type, format_id, name, remount); + + err = kern_path(name, LOOKUP_FOLLOW, &path); if (err) return err; + /* Quotafile not on the same filesystem? */ - if (nd.mnt->mnt_sb != sb) { - path_release(&nd); + if (path.mnt->mnt_sb != sb) { + path_put(&path); return -EXDEV; } - /* Quotafile not of fs root? */ - if (nd.dentry->d_parent->d_inode != sb->s_root->d_inode) - printk(KERN_WARNING - "EXT3-fs: Quota file not on filesystem root. " - "Journalled quota will not work.\n"); - path_release(&nd); - return vfs_quota_on(sb, type, format_id, path); + /* Journaling quota? */ + if (EXT3_SB(sb)->s_qf_names[type]) { + /* Quotafile not of fs root? */ + if (path.dentry->d_parent != sb->s_root) + ext3_msg(sb, KERN_WARNING, + "warning: Quota file not on filesystem root. " + "Journaled quota will not work."); + } + + /* + * When we journal data on quota file, we have to flush journal to see + * all updates to the file when we bypass pagecache... + */ + if (ext3_should_journal_data(path.dentry->d_inode)) { + /* + * We don't need to lock updates but journal_flush() could + * otherwise be livelocked... + */ + journal_lock_updates(EXT3_SB(sb)->s_journal); + err = journal_flush(EXT3_SB(sb)->s_journal); + journal_unlock_updates(EXT3_SB(sb)->s_journal); + if (err) { + path_put(&path); + return err; + } + } + + err = vfs_quota_on_path(sb, type, format_id, &path); + path_put(&path); + return err; } /* Read data from quotafile - avoid pagecache and such because we cannot afford @@ -2671,6 +2948,13 @@ static ssize_t ext3_quota_write(struct super_block *sb, int type, struct buffer_head *bh; handle_t *handle = journal_current_handle(); + if (!handle) { + ext3_msg(sb, KERN_WARNING, + "warning: quota write (off=%llu, len=%llu)" + " cancelled because transaction is not started.", + (unsigned long long)off, (unsigned long long)len); + return -EIO; + } mutex_lock_nested(&inode->i_mutex, I_MUTEX_QUOTA); while (towrite > 0) { tocopy = sb->s_blocksize - offset < towrite ? @@ -2705,8 +2989,10 @@ static ssize_t ext3_quota_write(struct super_block *sb, int type, blk++; } out: - if (len == towrite) + if (len == towrite) { + mutex_unlock(&inode->i_mutex); return err; + } if (inode->i_size < off+len-towrite) { i_size_write(inode, off+len-towrite); EXT3_I(inode)->i_disksize = inode->i_size;