X-Git-Url: http://ftp.safe.ca/?a=blobdiff_plain;f=fs%2Fext4%2Fsuper.c;h=fb940c22ab0da95960f3c5bb757d79ef5a6222a2;hb=3244fcb1ae03362e4aa8cb1a9039fbfd61661859;hp=157c64c9a4e773f134efe4b3292d3202fbf7118b;hpb=833f4077bf7c2dcff6e31526e03ec2ad91c88581;p=safe%2Fjmp%2Flinux-2.6 diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 157c64c..fb940c2 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -21,8 +21,6 @@ #include #include #include -#include -#include #include #include #include @@ -36,63 +34,69 @@ #include #include #include +#include +#include #include - +#include #include +#include "ext4.h" +#include "ext4_jbd2.h" #include "xattr.h" #include "acl.h" #include "namei.h" +#include "group.h" + +struct proc_dir_entry *ext4_proc_root; static int ext4_load_journal(struct super_block *, struct ext4_super_block *, unsigned long journal_devnum); static int ext4_create_journal(struct super_block *, struct ext4_super_block *, unsigned int); -static void ext4_commit_super (struct super_block * sb, - struct ext4_super_block * es, - int sync); -static void ext4_mark_recovery_complete(struct super_block * sb, - struct ext4_super_block * es); -static void ext4_clear_journal_err(struct super_block * sb, - struct ext4_super_block * es); +static void ext4_commit_super(struct super_block *sb, + struct ext4_super_block *es, int sync); +static void ext4_mark_recovery_complete(struct super_block *sb, + struct ext4_super_block *es); +static void ext4_clear_journal_err(struct super_block *sb, + struct ext4_super_block *es); static int ext4_sync_fs(struct super_block *sb, int wait); -static const char *ext4_decode_error(struct super_block * sb, int errno, +static const char *ext4_decode_error(struct super_block *sb, int errno, char nbuf[16]); -static int ext4_remount (struct super_block * sb, int * flags, char * data); -static int ext4_statfs (struct dentry * dentry, struct kstatfs * buf); +static int ext4_remount(struct super_block *sb, int *flags, char *data); +static int ext4_statfs(struct dentry *dentry, struct kstatfs *buf); static void ext4_unlockfs(struct super_block *sb); -static void ext4_write_super (struct super_block * sb); +static void ext4_write_super(struct super_block *sb); static void ext4_write_super_lockfs(struct super_block *sb); ext4_fsblk_t ext4_block_bitmap(struct super_block *sb, struct ext4_group_desc *bg) { - return le32_to_cpu(bg->bg_block_bitmap) | + return le32_to_cpu(bg->bg_block_bitmap_lo) | (EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT ? - (ext4_fsblk_t)le32_to_cpu(bg->bg_block_bitmap_hi) << 32 : 0); + (ext4_fsblk_t)le32_to_cpu(bg->bg_block_bitmap_hi) << 32 : 0); } ext4_fsblk_t ext4_inode_bitmap(struct super_block *sb, struct ext4_group_desc *bg) { - return le32_to_cpu(bg->bg_inode_bitmap) | + return le32_to_cpu(bg->bg_inode_bitmap_lo) | (EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT ? - (ext4_fsblk_t)le32_to_cpu(bg->bg_inode_bitmap_hi) << 32 : 0); + (ext4_fsblk_t)le32_to_cpu(bg->bg_inode_bitmap_hi) << 32 : 0); } ext4_fsblk_t ext4_inode_table(struct super_block *sb, struct ext4_group_desc *bg) { - return le32_to_cpu(bg->bg_inode_table) | + return le32_to_cpu(bg->bg_inode_table_lo) | (EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT ? - (ext4_fsblk_t)le32_to_cpu(bg->bg_inode_table_hi) << 32 : 0); + (ext4_fsblk_t)le32_to_cpu(bg->bg_inode_table_hi) << 32 : 0); } void ext4_block_bitmap_set(struct super_block *sb, struct ext4_group_desc *bg, ext4_fsblk_t blk) { - bg->bg_block_bitmap = cpu_to_le32((u32)blk); + bg->bg_block_bitmap_lo = cpu_to_le32((u32)blk); if (EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT) bg->bg_block_bitmap_hi = cpu_to_le32(blk >> 32); } @@ -100,7 +104,7 @@ void ext4_block_bitmap_set(struct super_block *sb, void ext4_inode_bitmap_set(struct super_block *sb, struct ext4_group_desc *bg, ext4_fsblk_t blk) { - bg->bg_inode_bitmap = cpu_to_le32((u32)blk); + bg->bg_inode_bitmap_lo = cpu_to_le32((u32)blk); if (EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT) bg->bg_inode_bitmap_hi = cpu_to_le32(blk >> 32); } @@ -108,7 +112,7 @@ void ext4_inode_bitmap_set(struct super_block *sb, void ext4_inode_table_set(struct super_block *sb, struct ext4_group_desc *bg, ext4_fsblk_t blk) { - bg->bg_inode_table = cpu_to_le32((u32)blk); + bg->bg_inode_table_lo = cpu_to_le32((u32)blk); if (EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT) bg->bg_inode_table_hi = cpu_to_le32(blk >> 32); } @@ -133,7 +137,7 @@ handle_t *ext4_journal_start_sb(struct super_block *sb, int nblocks) * take the FS itself readonly cleanly. */ journal = EXT4_SB(sb)->s_journal; if (is_journal_aborted(journal)) { - ext4_abort(sb, __FUNCTION__, + ext4_abort(sb, __func__, "Detected aborted journal"); return ERR_PTR(-EROFS); } @@ -210,15 +214,15 @@ static void ext4_handle_error(struct super_block *sb) if (sb->s_flags & MS_RDONLY) return; - if (!test_opt (sb, ERRORS_CONT)) { + if (!test_opt(sb, ERRORS_CONT)) { journal_t *journal = EXT4_SB(sb)->s_journal; EXT4_SB(sb)->s_mount_opt |= EXT4_MOUNT_ABORT; if (journal) jbd2_journal_abort(journal, -EIO); } - if (test_opt (sb, ERRORS_RO)) { - printk (KERN_CRIT "Remounting filesystem read-only\n"); + if (test_opt(sb, ERRORS_RO)) { + printk(KERN_CRIT "Remounting filesystem read-only\n"); sb->s_flags |= MS_RDONLY; } ext4_commit_super(sb, es, 1); @@ -227,13 +231,13 @@ static void ext4_handle_error(struct super_block *sb) sb->s_id); } -void ext4_error (struct super_block * sb, const char * function, - const char * fmt, ...) +void ext4_error(struct super_block *sb, const char *function, + const char *fmt, ...) { va_list args; va_start(args, fmt); - printk(KERN_CRIT "EXT4-fs error (device %s): %s: ",sb->s_id, function); + printk(KERN_CRIT "EXT4-fs error (device %s): %s: ", sb->s_id, function); vprintk(fmt, args); printk("\n"); va_end(args); @@ -241,7 +245,7 @@ void ext4_error (struct super_block * sb, const char * function, ext4_handle_error(sb); } -static const char *ext4_decode_error(struct super_block * sb, int errno, +static const char *ext4_decode_error(struct super_block *sb, int errno, char nbuf[16]) { char *errstr = NULL; @@ -277,8 +281,7 @@ static const char *ext4_decode_error(struct super_block * sb, int errno, /* __ext4_std_error decodes expected errors from journaling functions * automatically and invokes the appropriate error response. */ -void __ext4_std_error (struct super_block * sb, const char * function, - int errno) +void __ext4_std_error(struct super_block *sb, const char *function, int errno) { char nbuf[16]; const char *errstr; @@ -291,8 +294,8 @@ void __ext4_std_error (struct super_block * sb, const char * function, return; errstr = ext4_decode_error(sb, errno, nbuf); - printk (KERN_CRIT "EXT4-fs error (device %s) in %s: %s\n", - sb->s_id, function, errstr); + printk(KERN_CRIT "EXT4-fs error (device %s) in %s: %s\n", + sb->s_id, function, errstr); ext4_handle_error(sb); } @@ -307,15 +310,15 @@ void __ext4_std_error (struct super_block * sb, const char * function, * case we take the easy way out and panic immediately. */ -void ext4_abort (struct super_block * sb, const char * function, - const char * fmt, ...) +void ext4_abort(struct super_block *sb, const char *function, + const char *fmt, ...) { va_list args; - printk (KERN_CRIT "ext4_abort called.\n"); + printk(KERN_CRIT "ext4_abort called.\n"); va_start(args, fmt); - printk(KERN_CRIT "EXT4-fs error (device %s): %s: ",sb->s_id, function); + printk(KERN_CRIT "EXT4-fs error (device %s): %s: ", sb->s_id, function); vprintk(fmt, args); printk("\n"); va_end(args); @@ -333,8 +336,8 @@ void ext4_abort (struct super_block * sb, const char * function, jbd2_journal_abort(EXT4_SB(sb)->s_journal, -EIO); } -void ext4_warning (struct super_block * sb, const char * function, - const char * fmt, ...) +void ext4_warning(struct super_block *sb, const char *function, + const char *fmt, ...) { va_list args; @@ -353,7 +356,7 @@ void ext4_update_dynamic_rev(struct super_block *sb) if (le32_to_cpu(es->s_rev_level) > EXT4_GOOD_OLD_REV) return; - ext4_warning(sb, __FUNCTION__, + ext4_warning(sb, __func__, "updating to rev %d because of new feature flag, " "running e2fsck is recommended", EXT4_DYNAMIC_REV); @@ -371,6 +374,66 @@ void ext4_update_dynamic_rev(struct super_block *sb) */ } +int ext4_update_compat_feature(handle_t *handle, + struct super_block *sb, __u32 compat) +{ + int err = 0; + if (!EXT4_HAS_COMPAT_FEATURE(sb, compat)) { + err = ext4_journal_get_write_access(handle, + EXT4_SB(sb)->s_sbh); + if (err) + return err; + EXT4_SET_COMPAT_FEATURE(sb, compat); + sb->s_dirt = 1; + handle->h_sync = 1; + BUFFER_TRACE(EXT4_SB(sb)->s_sbh, + "call ext4_journal_dirty_met adata"); + err = ext4_journal_dirty_metadata(handle, + EXT4_SB(sb)->s_sbh); + } + return err; +} + +int ext4_update_rocompat_feature(handle_t *handle, + struct super_block *sb, __u32 rocompat) +{ + int err = 0; + if (!EXT4_HAS_RO_COMPAT_FEATURE(sb, rocompat)) { + err = ext4_journal_get_write_access(handle, + EXT4_SB(sb)->s_sbh); + if (err) + return err; + EXT4_SET_RO_COMPAT_FEATURE(sb, rocompat); + sb->s_dirt = 1; + handle->h_sync = 1; + BUFFER_TRACE(EXT4_SB(sb)->s_sbh, + "call ext4_journal_dirty_met adata"); + err = ext4_journal_dirty_metadata(handle, + EXT4_SB(sb)->s_sbh); + } + return err; +} + +int ext4_update_incompat_feature(handle_t *handle, + struct super_block *sb, __u32 incompat) +{ + int err = 0; + if (!EXT4_HAS_INCOMPAT_FEATURE(sb, incompat)) { + err = ext4_journal_get_write_access(handle, + EXT4_SB(sb)->s_sbh); + if (err) + return err; + EXT4_SET_INCOMPAT_FEATURE(sb, incompat); + sb->s_dirt = 1; + handle->h_sync = 1; + BUFFER_TRACE(EXT4_SB(sb)->s_sbh, + "call ext4_journal_dirty_met adata"); + err = ext4_journal_dirty_metadata(handle, + EXT4_SB(sb)->s_sbh); + } + return err; +} + /* * Open the external journal device */ @@ -435,29 +498,36 @@ static void dump_orphan_list(struct super_block *sb, struct ext4_sb_info *sbi) } } -static void ext4_put_super (struct super_block * sb) +static void ext4_put_super(struct super_block *sb) { struct ext4_sb_info *sbi = EXT4_SB(sb); struct ext4_super_block *es = sbi->s_es; int i; + ext4_mb_release(sb); ext4_ext_release(sb); ext4_xattr_put_super(sb); - jbd2_journal_destroy(sbi->s_journal); + if (jbd2_journal_destroy(sbi->s_journal) < 0) + ext4_abort(sb, __func__, "Couldn't clean up the journal"); + sbi->s_journal = NULL; if (!(sb->s_flags & MS_RDONLY)) { EXT4_CLEAR_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER); es->s_state = cpu_to_le16(sbi->s_mount_state); - BUFFER_TRACE(sbi->s_sbh, "marking dirty"); - mark_buffer_dirty(sbi->s_sbh); ext4_commit_super(sb, es, 1); } + if (sbi->s_proc) { + remove_proc_entry("inode_readahead_blks", sbi->s_proc); + remove_proc_entry(sb->s_id, ext4_proc_root); + } for (i = 0; i < sbi->s_gdb_count; i++) brelse(sbi->s_group_desc[i]); kfree(sbi->s_group_desc); + kfree(sbi->s_flex_groups); percpu_counter_destroy(&sbi->s_freeblocks_counter); percpu_counter_destroy(&sbi->s_freeinodes_counter); percpu_counter_destroy(&sbi->s_dirs_counter); + percpu_counter_destroy(&sbi->s_dirtyblocks_counter); brelse(sbi->s_sbh); #ifdef CONFIG_QUOTA for (i = 0; i < MAXQUOTAS; i++) @@ -500,13 +570,21 @@ static struct inode *ext4_alloc_inode(struct super_block *sb) ei = kmem_cache_alloc(ext4_inode_cachep, GFP_NOFS); if (!ei) return NULL; -#ifdef CONFIG_EXT4DEV_FS_POSIX_ACL +#ifdef CONFIG_EXT4_FS_POSIX_ACL ei->i_acl = EXT4_ACL_NOT_CACHED; ei->i_default_acl = EXT4_ACL_NOT_CACHED; #endif - ei->i_block_alloc_info = NULL; ei->vfs_inode.i_version = 1; + ei->vfs_inode.i_data.writeback_index = 0; memset(&ei->i_cached_extent, 0, sizeof(struct ext4_ext_cache)); + INIT_LIST_HEAD(&ei->i_prealloc_list); + spin_lock_init(&ei->i_prealloc_lock); + jbd2_journal_init_jbd_inode(&ei->jinode, &ei->vfs_inode); + ei->i_reserved_data_blocks = 0; + ei->i_reserved_meta_blocks = 0; + ei->i_allocated_meta_blocks = 0; + ei->i_delalloc_reserved_flag = 0; + spin_lock_init(&(ei->i_block_reservation_lock)); return &ei->vfs_inode; } @@ -523,15 +601,15 @@ static void ext4_destroy_inode(struct inode *inode) kmem_cache_free(ext4_inode_cachep, EXT4_I(inode)); } -static void init_once(void * foo, struct kmem_cache * cachep, unsigned long flags) +static void init_once(void *foo) { struct ext4_inode_info *ei = (struct ext4_inode_info *) foo; INIT_LIST_HEAD(&ei->i_orphan); -#ifdef CONFIG_EXT4DEV_FS_XATTR +#ifdef CONFIG_EXT4_FS_XATTR init_rwsem(&ei->xattr_sem); #endif - mutex_init(&ei->truncate_mutex); + init_rwsem(&ei->i_data_sem); inode_init_once(&ei->vfs_inode); } @@ -554,8 +632,7 @@ static void destroy_inodecache(void) static void ext4_clear_inode(struct inode *inode) { - struct ext4_block_alloc_info *rsv = EXT4_I(inode)->i_block_alloc_info; -#ifdef CONFIG_EXT4DEV_FS_POSIX_ACL +#ifdef CONFIG_EXT4_FS_POSIX_ACL if (EXT4_I(inode)->i_acl && EXT4_I(inode)->i_acl != EXT4_ACL_NOT_CACHED) { posix_acl_release(EXT4_I(inode)->i_acl); @@ -567,20 +644,20 @@ static void ext4_clear_inode(struct inode *inode) EXT4_I(inode)->i_default_acl = EXT4_ACL_NOT_CACHED; } #endif - ext4_discard_reservation(inode); - EXT4_I(inode)->i_block_alloc_info = NULL; - if (unlikely(rsv)) - kfree(rsv); + ext4_discard_preallocations(inode); + jbd2_journal_release_jbd_inode(EXT4_SB(inode->i_sb)->s_journal, + &EXT4_I(inode)->jinode); } -static inline void ext4_show_quota_options(struct seq_file *seq, struct super_block *sb) +static inline void ext4_show_quota_options(struct seq_file *seq, + struct super_block *sb) { #if defined(CONFIG_QUOTA) struct ext4_sb_info *sbi = EXT4_SB(sb); if (sbi->s_jquota_fmt) seq_printf(seq, ",jqfmt=%s", - (sbi->s_jquota_fmt == QFMT_VFS_OLD) ? "vfsold": "vfsv0"); + (sbi->s_jquota_fmt == QFMT_VFS_OLD) ? "vfsold" : "vfsv0"); if (sbi->s_qf_names[USRQUOTA]) seq_printf(seq, ",usrjquota=%s", sbi->s_qf_names[USRQUOTA]); @@ -596,10 +673,100 @@ static inline void ext4_show_quota_options(struct seq_file *seq, struct super_bl #endif } +/* + * 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 ext4_show_options(struct seq_file *seq, struct vfsmount *vfs) { + int def_errors; + unsigned long def_mount_opts; struct super_block *sb = vfs->mnt_sb; + struct ext4_sb_info *sbi = EXT4_SB(sb); + struct ext4_super_block *es = sbi->s_es; + def_mount_opts = le32_to_cpu(es->s_default_mount_opts); + def_errors = le16_to_cpu(es->s_errors); + + if (sbi->s_sb_block != 1) + seq_printf(seq, ",sb=%llu", sbi->s_sb_block); + if (test_opt(sb, MINIX_DF)) + seq_puts(seq, ",minixdf"); + if (test_opt(sb, GRPID) && !(def_mount_opts & EXT4_DEFM_BSDGROUPS)) + seq_puts(seq, ",grpid"); + if (!test_opt(sb, GRPID) && (def_mount_opts & EXT4_DEFM_BSDGROUPS)) + seq_puts(seq, ",nogrpid"); + if (sbi->s_resuid != EXT4_DEF_RESUID || + le16_to_cpu(es->s_def_resuid) != EXT4_DEF_RESUID) { + seq_printf(seq, ",resuid=%u", sbi->s_resuid); + } + if (sbi->s_resgid != EXT4_DEF_RESGID || + le16_to_cpu(es->s_def_resgid) != EXT4_DEF_RESGID) { + seq_printf(seq, ",resgid=%u", sbi->s_resgid); + } + if (test_opt(sb, ERRORS_RO)) { + if (def_errors == EXT4_ERRORS_PANIC || + def_errors == EXT4_ERRORS_CONTINUE) { + seq_puts(seq, ",errors=remount-ro"); + } + } + if (test_opt(sb, ERRORS_CONT) && def_errors != EXT4_ERRORS_CONTINUE) + seq_puts(seq, ",errors=continue"); + if (test_opt(sb, ERRORS_PANIC) && def_errors != EXT4_ERRORS_PANIC) + seq_puts(seq, ",errors=panic"); + if (test_opt(sb, NO_UID32) && !(def_mount_opts & EXT4_DEFM_UID16)) + seq_puts(seq, ",nouid32"); + if (test_opt(sb, DEBUG) && !(def_mount_opts & EXT4_DEFM_DEBUG)) + seq_puts(seq, ",debug"); + if (test_opt(sb, OLDALLOC)) + seq_puts(seq, ",oldalloc"); +#ifdef CONFIG_EXT4_FS_XATTR + if (test_opt(sb, XATTR_USER) && + !(def_mount_opts & EXT4_DEFM_XATTR_USER)) + seq_puts(seq, ",user_xattr"); + if (!test_opt(sb, XATTR_USER) && + (def_mount_opts & EXT4_DEFM_XATTR_USER)) { + seq_puts(seq, ",nouser_xattr"); + } +#endif +#ifdef CONFIG_EXT4_FS_POSIX_ACL + if (test_opt(sb, POSIX_ACL) && !(def_mount_opts & EXT4_DEFM_ACL)) + seq_puts(seq, ",acl"); + if (!test_opt(sb, POSIX_ACL) && (def_mount_opts & EXT4_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)); + } + /* + * We're changing the default of barrier mount option, so + * let's always display its mount state so it's clear what its + * status is. + */ + seq_puts(seq, ",barrier="); + seq_puts(seq, test_opt(sb, BARRIER) ? "1" : "0"); + if (test_opt(sb, JOURNAL_ASYNC_COMMIT)) + seq_puts(seq, ",journal_async_commit"); + if (test_opt(sb, NOBH)) + seq_puts(seq, ",nobh"); + if (!test_opt(sb, EXTENTS)) + seq_puts(seq, ",noextents"); + if (test_opt(sb, I_VERSION)) + seq_puts(seq, ",i_version"); + if (!test_opt(sb, DELALLOC)) + seq_puts(seq, ",nodelalloc"); + + + if (sbi->s_stripe) + seq_printf(seq, ",stripe=%lu", sbi->s_stripe); + /* + * journal mode get enabled in different ways + * So just print the value even if we didn't specify it + */ if (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA) seq_puts(seq, ",data=journal"); else if (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_ORDERED_DATA) @@ -607,19 +774,22 @@ static int ext4_show_options(struct seq_file *seq, struct vfsmount *vfs) else if (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_WRITEBACK_DATA) seq_puts(seq, ",data=writeback"); - ext4_show_quota_options(seq, sb); + if (sbi->s_inode_readahead_blks != EXT4_DEF_INODE_READAHEAD_BLKS) + seq_printf(seq, ",inode_readahead_blks=%u", + sbi->s_inode_readahead_blks); + if (test_opt(sb, DATA_ERR_ABORT)) + seq_puts(seq, ",data_err=abort"); + + ext4_show_quota_options(seq, sb); return 0; } -static struct dentry *ext4_get_dentry(struct super_block *sb, void *vobjp) +static struct inode *ext4_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 < EXT4_FIRST_INO(sb) && ino != EXT4_ROOT_INO) return ERR_PTR(-ESTALE); @@ -634,28 +804,34 @@ static struct dentry *ext4_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 = ext4_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 *ext4_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, + ext4_nfs_get_inode); +} + +static struct dentry *ext4_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, + ext4_nfs_get_inode); } #ifdef CONFIG_QUOTA -#define QTYPE2NAME(t) ((t)==USRQUOTA?"user":"group") -#define QTYPE2MOPT(on, t) ((t)==USRQUOTA?((on)##USRJQUOTA):((on)##GRPJQUOTA)) +#define QTYPE2NAME(t) ((t) == USRQUOTA ? "user" : "group") +#define QTYPE2MOPT(on, t) ((t) == USRQUOTA?((on)##USRJQUOTA):((on)##GRPJQUOTA)) static int ext4_dquot_initialize(struct inode *inode, int type); static int ext4_dquot_drop(struct inode *inode); @@ -664,7 +840,8 @@ static int ext4_acquire_dquot(struct dquot *dquot); static int ext4_release_dquot(struct dquot *dquot); static int ext4_mark_dquot_dirty(struct dquot *dquot); static int ext4_write_info(struct super_block *sb, int type); -static int ext4_quota_on(struct super_block *sb, int type, int format_id, char *path); +static int ext4_quota_on(struct super_block *sb, int type, int format_id, + char *path, int remount); static int ext4_quota_on_mount(struct super_block *sb, int type); static ssize_t ext4_quota_read(struct super_block *sb, int type, char *data, size_t len, loff_t off); @@ -700,7 +877,6 @@ static struct quotactl_ops ext4_qctl_operations = { static const struct super_operations ext4_sops = { .alloc_inode = ext4_alloc_inode, .destroy_inode = ext4_destroy_inode, - .read_inode = ext4_read_inode, .write_inode = ext4_write_inode, .dirty_inode = ext4_dirty_inode, .delete_inode = ext4_delete_inode, @@ -719,9 +895,10 @@ static const struct super_operations ext4_sops = { #endif }; -static struct export_operations ext4_export_ops = { +static const struct export_operations ext4_export_ops = { + .fh_to_dentry = ext4_fh_to_dentry, + .fh_to_parent = ext4_fh_to_parent, .get_parent = ext4_get_parent, - .get_dentry = ext4_get_dentry, }; enum { @@ -731,11 +908,15 @@ enum { Opt_user_xattr, Opt_nouser_xattr, Opt_acl, Opt_noacl, Opt_reservation, Opt_noreservation, Opt_noload, Opt_nobh, Opt_bh, Opt_commit, Opt_journal_update, Opt_journal_inum, Opt_journal_dev, + Opt_journal_checksum, Opt_journal_async_commit, 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_extents, Opt_noextents, + Opt_grpquota, Opt_extents, Opt_noextents, Opt_i_version, + Opt_mballoc, Opt_nomballoc, Opt_stripe, Opt_delalloc, Opt_nodelalloc, + Opt_inode_readahead_blks }; static match_table_t tokens = { @@ -770,10 +951,14 @@ static match_table_t tokens = { {Opt_journal_update, "journal=update"}, {Opt_journal_inum, "journal=%u"}, {Opt_journal_dev, "journal_dev=%u"}, + {Opt_journal_checksum, "journal_checksum"}, + {Opt_journal_async_commit, "journal_async_commit"}, {Opt_abort, "abort"}, {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="}, @@ -787,8 +972,15 @@ static match_table_t tokens = { {Opt_barrier, "barrier=%u"}, {Opt_extents, "extents"}, {Opt_noextents, "noextents"}, - {Opt_err, NULL}, + {Opt_i_version, "i_version"}, + {Opt_mballoc, "mballoc"}, + {Opt_nomballoc, "nomballoc"}, + {Opt_stripe, "stripe=%u"}, {Opt_resize, "resize"}, + {Opt_delalloc, "delalloc"}, + {Opt_nodelalloc, "nodelalloc"}, + {Opt_inode_readahead_blks, "inode_readahead_blks=%u"}, + {Opt_err, NULL}, }; static ext4_fsblk_t get_sb_block(void **data) @@ -802,7 +994,7 @@ static ext4_fsblk_t get_sb_block(void **data) /*todo: use simple_strtoll with >32bit ext4 */ sb_block = simple_strtoul(options, &options, 0); if (*options && *options != ',') { - printk("EXT4-fs: Invalid sb specification: %s\n", + printk(KERN_ERR "EXT4-fs: Invalid sb specification: %s\n", (char *) *data); return 1; } @@ -812,24 +1004,25 @@ static ext4_fsblk_t get_sb_block(void **data) return sb_block; } -static int parse_options (char *options, struct super_block *sb, - unsigned int *inum, unsigned long *journal_devnum, - ext4_fsblk_t *n_blocks_count, int is_remount) +static int parse_options(char *options, struct super_block *sb, + unsigned int *inum, unsigned long *journal_devnum, + ext4_fsblk_t *n_blocks_count, int is_remount) { struct ext4_sb_info *sbi = EXT4_SB(sb); - char * p; + char *p; substring_t args[MAX_OPT_ARGS]; int data_opt = 0; int option; #ifdef CONFIG_QUOTA - int qtype; + int qtype, qfmt; char *qname; #endif + ext4_fsblk_t last_block; if (!options) return 1; - while ((p = strsep (&options, ",")) != NULL) { + while ((p = strsep(&options, ",")) != NULL) { int token; if (!*p) continue; @@ -837,16 +1030,16 @@ static int parse_options (char *options, struct super_block *sb, token = match_token(p, tokens, args); switch (token) { case Opt_bsd_df: - clear_opt (sbi->s_mount_opt, MINIX_DF); + clear_opt(sbi->s_mount_opt, MINIX_DF); break; case Opt_minix_df: - set_opt (sbi->s_mount_opt, MINIX_DF); + set_opt(sbi->s_mount_opt, MINIX_DF); break; case Opt_grpid: - set_opt (sbi->s_mount_opt, GRPID); + set_opt(sbi->s_mount_opt, GRPID); break; case Opt_nogrpid: - clear_opt (sbi->s_mount_opt, GRPID); + clear_opt(sbi->s_mount_opt, GRPID); break; case Opt_resuid: if (match_int(&args[0], &option)) @@ -863,49 +1056,50 @@ static int parse_options (char *options, struct super_block *sb, /* *sb_block = match_int(&args[0]); */ break; case Opt_err_panic: - clear_opt (sbi->s_mount_opt, ERRORS_CONT); - clear_opt (sbi->s_mount_opt, ERRORS_RO); - set_opt (sbi->s_mount_opt, ERRORS_PANIC); + clear_opt(sbi->s_mount_opt, ERRORS_CONT); + clear_opt(sbi->s_mount_opt, ERRORS_RO); + set_opt(sbi->s_mount_opt, ERRORS_PANIC); break; case Opt_err_ro: - clear_opt (sbi->s_mount_opt, ERRORS_CONT); - clear_opt (sbi->s_mount_opt, ERRORS_PANIC); - set_opt (sbi->s_mount_opt, ERRORS_RO); + clear_opt(sbi->s_mount_opt, ERRORS_CONT); + clear_opt(sbi->s_mount_opt, ERRORS_PANIC); + set_opt(sbi->s_mount_opt, ERRORS_RO); break; case Opt_err_cont: - clear_opt (sbi->s_mount_opt, ERRORS_RO); - clear_opt (sbi->s_mount_opt, ERRORS_PANIC); - set_opt (sbi->s_mount_opt, ERRORS_CONT); + clear_opt(sbi->s_mount_opt, ERRORS_RO); + clear_opt(sbi->s_mount_opt, ERRORS_PANIC); + set_opt(sbi->s_mount_opt, ERRORS_CONT); break; case Opt_nouid32: - set_opt (sbi->s_mount_opt, NO_UID32); + set_opt(sbi->s_mount_opt, NO_UID32); break; case Opt_nocheck: - clear_opt (sbi->s_mount_opt, CHECK); + clear_opt(sbi->s_mount_opt, CHECK); break; case Opt_debug: - set_opt (sbi->s_mount_opt, DEBUG); + set_opt(sbi->s_mount_opt, DEBUG); break; case Opt_oldalloc: - set_opt (sbi->s_mount_opt, OLDALLOC); + set_opt(sbi->s_mount_opt, OLDALLOC); break; case Opt_orlov: - clear_opt (sbi->s_mount_opt, OLDALLOC); + clear_opt(sbi->s_mount_opt, OLDALLOC); break; -#ifdef CONFIG_EXT4DEV_FS_XATTR +#ifdef CONFIG_EXT4_FS_XATTR case Opt_user_xattr: - set_opt (sbi->s_mount_opt, XATTR_USER); + set_opt(sbi->s_mount_opt, XATTR_USER); break; case Opt_nouser_xattr: - clear_opt (sbi->s_mount_opt, XATTR_USER); + clear_opt(sbi->s_mount_opt, XATTR_USER); break; #else case Opt_user_xattr: case Opt_nouser_xattr: - printk("EXT4 (no)user_xattr options not supported\n"); + printk(KERN_ERR "EXT4 (no)user_xattr options " + "not supported\n"); break; #endif -#ifdef CONFIG_EXT4DEV_FS_POSIX_ACL +#ifdef CONFIG_EXT4_FS_POSIX_ACL case Opt_acl: set_opt(sbi->s_mount_opt, POSIX_ACL); break; @@ -915,7 +1109,8 @@ static int parse_options (char *options, struct super_block *sb, #else case Opt_acl: case Opt_noacl: - printk("EXT4 (no)acl options not supported\n"); + printk(KERN_ERR "EXT4 (no)acl options " + "not supported\n"); break; #endif case Opt_reservation: @@ -935,7 +1130,7 @@ static int parse_options (char *options, struct super_block *sb, "journal on remount\n"); return 0; } - set_opt (sbi->s_mount_opt, UPDATE_JOURNAL); + set_opt(sbi->s_mount_opt, UPDATE_JOURNAL); break; case Opt_journal_inum: if (is_remount) { @@ -957,8 +1152,15 @@ static int parse_options (char *options, struct super_block *sb, return 0; *journal_devnum = option; break; + case Opt_journal_checksum: + set_opt(sbi->s_mount_opt, JOURNAL_CHECKSUM); + break; + case Opt_journal_async_commit: + set_opt(sbi->s_mount_opt, JOURNAL_ASYNC_COMMIT); + set_opt(sbi->s_mount_opt, JOURNAL_CHECKSUM); + break; case Opt_noload: - set_opt (sbi->s_mount_opt, NOLOAD); + set_opt(sbi->s_mount_opt, NOLOAD); break; case Opt_commit: if (match_int(&args[0], &option)) @@ -966,7 +1168,7 @@ static int parse_options (char *options, struct super_block *sb, if (option < 0) return 0; if (option == 0) - option = JBD_DEFAULT_MAX_COMMIT_AGE; + option = JBD2_DEFAULT_MAX_COMMIT_AGE; sbi->s_commit_interval = HZ * option; break; case Opt_data_journal: @@ -991,6 +1193,12 @@ static int parse_options (char *options, struct super_block *sb, 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; @@ -998,10 +1206,12 @@ static int parse_options (char *options, struct super_block *sb, case Opt_grpjquota: qtype = GRPQUOTA; set_qf_name: - if (sb_any_quota_enabled(sb)) { + if ((sb_any_quota_enabled(sb) || + sb_any_quota_suspended(sb)) && + !sbi->s_qf_names[qtype]) { printk(KERN_ERR - "EXT4-fs: Cannot change journalled " - "quota options when quota turned on.\n"); + "EXT4-fs: Cannot change journaled " + "quota options when quota turned on.\n"); return 0; } qname = match_strdup(&args[0]); @@ -1036,9 +1246,11 @@ set_qf_name: case Opt_offgrpjquota: qtype = GRPQUOTA; clear_qf_name: - if (sb_any_quota_enabled(sb)) { + if ((sb_any_quota_enabled(sb) || + sb_any_quota_suspended(sb)) && + sbi->s_qf_names[qtype]) { printk(KERN_ERR "EXT4-fs: Cannot change " - "journalled quota options when " + "journaled quota options when " "quota turned on.\n"); return 0; } @@ -1049,10 +1261,20 @@ 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; +set_qf_format: + if ((sb_any_quota_enabled(sb) || + sb_any_quota_suspended(sb)) && + sbi->s_jquota_fmt != qfmt) { + printk(KERN_ERR "EXT4-fs: Cannot change " + "journaled quota options when " + "quota turned on.\n"); + return 0; + } + sbi->s_jquota_fmt = qfmt; break; case Opt_quota: case Opt_usrquota: @@ -1077,6 +1299,9 @@ clear_qf_name: case Opt_quota: case Opt_usrquota: case Opt_grpquota: + printk(KERN_ERR + "EXT4-fs: quota options not supported.\n"); + break; case Opt_usrjquota: case Opt_grpjquota: case Opt_offusrjquota: @@ -1084,7 +1309,7 @@ clear_qf_name: case Opt_jqfmt_vfsold: case Opt_jqfmt_vfsv0: printk(KERN_ERR - "EXT4-fs: journalled quota options not " + "EXT4-fs: journaled quota options not " "supported.\n"); break; case Opt_noquota: @@ -1120,15 +1345,60 @@ clear_qf_name: clear_opt(sbi->s_mount_opt, NOBH); break; case Opt_extents: - set_opt (sbi->s_mount_opt, EXTENTS); + if (!EXT4_HAS_INCOMPAT_FEATURE(sb, + EXT4_FEATURE_INCOMPAT_EXTENTS)) { + ext4_warning(sb, __func__, + "extents feature not enabled " + "on this filesystem, use tune2fs\n"); + return 0; + } + set_opt(sbi->s_mount_opt, EXTENTS); break; case Opt_noextents: - clear_opt (sbi->s_mount_opt, EXTENTS); + /* + * When e2fsprogs support resizing an already existing + * ext3 file system to greater than 2**32 we need to + * add support to block allocator to handle growing + * already existing block mapped inode so that blocks + * allocated for them fall within 2**32 + */ + last_block = ext4_blocks_count(sbi->s_es) - 1; + if (last_block > 0xffffffffULL) { + printk(KERN_ERR "EXT4-fs: Filesystem too " + "large to mount with " + "-o noextents options\n"); + return 0; + } + clear_opt(sbi->s_mount_opt, EXTENTS); + break; + case Opt_i_version: + set_opt(sbi->s_mount_opt, I_VERSION); + sb->s_flags |= MS_I_VERSION; + break; + case Opt_nodelalloc: + clear_opt(sbi->s_mount_opt, DELALLOC); + break; + case Opt_stripe: + if (match_int(&args[0], &option)) + return 0; + if (option < 0) + return 0; + sbi->s_stripe = option; + break; + case Opt_delalloc: + set_opt(sbi->s_mount_opt, DELALLOC); + break; + case Opt_inode_readahead_blks: + if (match_int(&args[0], &option)) + return 0; + if (option < 0 || option > (1 << 30)) + return 0; + sbi->s_inode_readahead_blks = option; break; default: - printk (KERN_ERR - "EXT4-fs: Unrecognized mount option \"%s\" " - "or missing value\n", p); + printk(KERN_ERR + "EXT4-fs: Unrecognized mount option \"%s\" " + "or missing value\n", p); return 0; } } @@ -1152,14 +1422,14 @@ clear_qf_name: } if (!sbi->s_jquota_fmt) { - printk(KERN_ERR "EXT4-fs: journalled quota format " + printk(KERN_ERR "EXT4-fs: journaled quota format " "not specified.\n"); return 0; } } else { if (sbi->s_jquota_fmt) { - printk(KERN_ERR "EXT4-fs: journalled quota format " - "specified with no journalling " + printk(KERN_ERR "EXT4-fs: journaled quota format " + "specified with no journaling " "enabled.\n"); return 0; } @@ -1175,42 +1445,42 @@ static int ext4_setup_super(struct super_block *sb, struct ext4_super_block *es, int res = 0; if (le32_to_cpu(es->s_rev_level) > EXT4_MAX_SUPP_REV) { - printk (KERN_ERR "EXT4-fs warning: revision level too high, " - "forcing read-only mode\n"); + printk(KERN_ERR "EXT4-fs warning: revision level too high, " + "forcing read-only mode\n"); res = MS_RDONLY; } if (read_only) return res; if (!(sbi->s_mount_state & EXT4_VALID_FS)) - printk (KERN_WARNING "EXT4-fs warning: mounting unchecked fs, " - "running e2fsck is recommended\n"); + printk(KERN_WARNING "EXT4-fs warning: mounting unchecked fs, " + "running e2fsck is recommended\n"); else if ((sbi->s_mount_state & EXT4_ERROR_FS)) - printk (KERN_WARNING - "EXT4-fs warning: mounting fs with errors, " - "running e2fsck is recommended\n"); + printk(KERN_WARNING + "EXT4-fs warning: mounting fs with errors, " + "running e2fsck is recommended\n"); else if ((__s16) le16_to_cpu(es->s_max_mnt_count) >= 0 && le16_to_cpu(es->s_mnt_count) >= (unsigned short) (__s16) le16_to_cpu(es->s_max_mnt_count)) - printk (KERN_WARNING - "EXT4-fs warning: maximal mount count reached, " - "running e2fsck is recommended\n"); + printk(KERN_WARNING + "EXT4-fs warning: maximal mount count reached, " + "running e2fsck is recommended\n"); else if (le32_to_cpu(es->s_checkinterval) && (le32_to_cpu(es->s_lastcheck) + le32_to_cpu(es->s_checkinterval) <= get_seconds())) - printk (KERN_WARNING - "EXT4-fs warning: checktime reached, " - "running e2fsck is recommended\n"); + printk(KERN_WARNING + "EXT4-fs warning: checktime reached, " + "running e2fsck is recommended\n"); #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) & ~EXT4_VALID_FS); + es->s_state &= cpu_to_le16(~EXT4_VALID_FS); #endif if (!(__s16) le16_to_cpu(es->s_max_mnt_count)) es->s_max_mnt_count = cpu_to_le16(EXT4_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()); ext4_update_dynamic_rev(sb); EXT4_SET_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER); @@ -1225,20 +1495,101 @@ static int ext4_setup_super(struct super_block *sb, struct ext4_super_block *es, EXT4_INODES_PER_GROUP(sb), sbi->s_mount_opt); - printk(KERN_INFO "EXT4 FS on %s, ", sb->s_id); - if (EXT4_SB(sb)->s_journal->j_inode == NULL) { - char b[BDEVNAME_SIZE]; + printk(KERN_INFO "EXT4 FS on %s, %s journal on %s\n", + sb->s_id, EXT4_SB(sb)->s_journal->j_inode ? "internal" : + "external", EXT4_SB(sb)->s_journal->j_devname); + return res; +} + +static int ext4_fill_flex_info(struct super_block *sb) +{ + struct ext4_sb_info *sbi = EXT4_SB(sb); + struct ext4_group_desc *gdp = NULL; + struct buffer_head *bh; + ext4_group_t flex_group_count; + ext4_group_t flex_group; + int groups_per_flex = 0; + __u64 block_bitmap = 0; + int i; - printk("external journal on %s\n", - bdevname(EXT4_SB(sb)->s_journal->j_dev, b)); - } else { - printk("internal journal\n"); + if (!sbi->s_es->s_log_groups_per_flex) { + sbi->s_log_groups_per_flex = 0; + return 1; } - return res; + + sbi->s_log_groups_per_flex = sbi->s_es->s_log_groups_per_flex; + groups_per_flex = 1 << sbi->s_log_groups_per_flex; + + /* We allocate both existing and potentially added groups */ + flex_group_count = ((sbi->s_groups_count + groups_per_flex - 1) + + ((sbi->s_es->s_reserved_gdt_blocks +1 ) << + EXT4_DESC_PER_BLOCK_BITS(sb))) / + groups_per_flex; + sbi->s_flex_groups = kzalloc(flex_group_count * + sizeof(struct flex_groups), GFP_KERNEL); + if (sbi->s_flex_groups == NULL) { + printk(KERN_ERR "EXT4-fs: not enough memory for " + "%lu flex groups\n", flex_group_count); + goto failed; + } + + gdp = ext4_get_group_desc(sb, 1, &bh); + block_bitmap = ext4_block_bitmap(sb, gdp) - 1; + + for (i = 0; i < sbi->s_groups_count; i++) { + gdp = ext4_get_group_desc(sb, i, &bh); + + flex_group = ext4_flex_group(sbi, i); + sbi->s_flex_groups[flex_group].free_inodes += + le16_to_cpu(gdp->bg_free_inodes_count); + sbi->s_flex_groups[flex_group].free_blocks += + le16_to_cpu(gdp->bg_free_blocks_count); + } + + return 1; +failed: + return 0; +} + +__le16 ext4_group_desc_csum(struct ext4_sb_info *sbi, __u32 block_group, + struct ext4_group_desc *gdp) +{ + __u16 crc = 0; + + if (sbi->s_es->s_feature_ro_compat & + cpu_to_le32(EXT4_FEATURE_RO_COMPAT_GDT_CSUM)) { + int offset = offsetof(struct ext4_group_desc, bg_checksum); + __le32 le_group = cpu_to_le32(block_group); + + crc = crc16(~0, sbi->s_es->s_uuid, sizeof(sbi->s_es->s_uuid)); + crc = crc16(crc, (__u8 *)&le_group, sizeof(le_group)); + crc = crc16(crc, (__u8 *)gdp, offset); + offset += sizeof(gdp->bg_checksum); /* skip checksum */ + /* for checksum of struct ext4_group_desc do the rest...*/ + if ((sbi->s_es->s_feature_incompat & + cpu_to_le32(EXT4_FEATURE_INCOMPAT_64BIT)) && + offset < le16_to_cpu(sbi->s_es->s_desc_size)) + crc = crc16(crc, (__u8 *)gdp + offset, + le16_to_cpu(sbi->s_es->s_desc_size) - + offset); + } + + return cpu_to_le16(crc); +} + +int ext4_group_desc_csum_verify(struct ext4_sb_info *sbi, __u32 block_group, + struct ext4_group_desc *gdp) +{ + if ((sbi->s_es->s_feature_ro_compat & + cpu_to_le32(EXT4_FEATURE_RO_COMPAT_GDT_CSUM)) && + (gdp->bg_checksum != ext4_group_desc_csum(sbi, block_group, gdp))) + return 0; + + return 1; } /* Called at mount-time, super-block is locked */ -static int ext4_check_descriptors (struct super_block * sb) +static int ext4_check_descriptors(struct super_block *sb) { struct ext4_sb_info *sbi = EXT4_SB(sb); ext4_fsblk_t first_block = le32_to_cpu(sbi->s_es->s_first_data_block); @@ -1246,62 +1597,66 @@ static int ext4_check_descriptors (struct super_block * sb) ext4_fsblk_t block_bitmap; ext4_fsblk_t inode_bitmap; ext4_fsblk_t inode_table; - struct ext4_group_desc * gdp = NULL; - int desc_block = 0; - int i; + int flexbg_flag = 0; + ext4_group_t i; + + if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_FLEX_BG)) + flexbg_flag = 1; + + ext4_debug("Checking group descriptors"); - ext4_debug ("Checking group descriptors"); + for (i = 0; i < sbi->s_groups_count; i++) { + struct ext4_group_desc *gdp = ext4_get_group_desc(sb, i, NULL); - for (i = 0; i < sbi->s_groups_count; i++) - { - if (i == sbi->s_groups_count - 1) + if (i == sbi->s_groups_count - 1 || flexbg_flag) last_block = ext4_blocks_count(sbi->s_es) - 1; else last_block = first_block + (EXT4_BLOCKS_PER_GROUP(sb) - 1); - if ((i % EXT4_DESC_PER_BLOCK(sb)) == 0) - gdp = (struct ext4_group_desc *) - sbi->s_group_desc[desc_block++]->b_data; block_bitmap = ext4_block_bitmap(sb, gdp); - if (block_bitmap < first_block || block_bitmap > last_block) - { - ext4_error (sb, "ext4_check_descriptors", - "Block bitmap for group %d" - " not in group (block %llu)!", - i, block_bitmap); + if (block_bitmap < first_block || block_bitmap > last_block) { + printk(KERN_ERR "EXT4-fs: ext4_check_descriptors: " + "Block bitmap for group %lu not in group " + "(block %llu)!", i, block_bitmap); return 0; } inode_bitmap = ext4_inode_bitmap(sb, gdp); - if (inode_bitmap < first_block || inode_bitmap > last_block) - { - ext4_error (sb, "ext4_check_descriptors", - "Inode bitmap for group %d" - " not in group (block %llu)!", - i, inode_bitmap); + if (inode_bitmap < first_block || inode_bitmap > last_block) { + printk(KERN_ERR "EXT4-fs: ext4_check_descriptors: " + "Inode bitmap for group %lu not in group " + "(block %llu)!", i, inode_bitmap); return 0; } inode_table = ext4_inode_table(sb, gdp); if (inode_table < first_block || - inode_table + sbi->s_itb_per_group - 1 > last_block) - { - ext4_error (sb, "ext4_check_descriptors", - "Inode table for group %d" - " not in group (block %llu)!", - i, inode_table); + inode_table + sbi->s_itb_per_group - 1 > last_block) { + printk(KERN_ERR "EXT4-fs: ext4_check_descriptors: " + "Inode table for group %lu not in group " + "(block %llu)!", i, inode_table); return 0; } - first_block += EXT4_BLOCKS_PER_GROUP(sb); - gdp = (struct ext4_group_desc *) - ((__u8 *)gdp + EXT4_DESC_SIZE(sb)); + spin_lock(sb_bgl_lock(sbi, i)); + if (!ext4_group_desc_csum_verify(sbi, i, gdp)) { + printk(KERN_ERR "EXT4-fs: ext4_check_descriptors: " + "Checksum for group %lu failed (%u!=%u)\n", + i, le16_to_cpu(ext4_group_desc_csum(sbi, i, + gdp)), le16_to_cpu(gdp->bg_checksum)); + if (!(sb->s_flags & MS_RDONLY)) { + spin_unlock(sb_bgl_lock(sbi, i)); + return 0; + } + } + spin_unlock(sb_bgl_lock(sbi, i)); + if (!flexbg_flag) + first_block += EXT4_BLOCKS_PER_GROUP(sb); } ext4_free_blocks_count_set(sbi->s_es, ext4_count_free_blocks(sb)); - sbi->s_es->s_free_inodes_count=cpu_to_le32(ext4_count_free_inodes(sb)); + sbi->s_es->s_free_inodes_count = cpu_to_le32(ext4_count_free_inodes(sb)); return 1; } - /* ext4_orphan_cleanup() walks a singly-linked list of inodes (starting at * the superblock) which were deleted from all directories, but held open by * a process at the time of a crash. We walk the list and try to delete these @@ -1319,8 +1674,8 @@ static int ext4_check_descriptors (struct super_block * sb) * e2fsck was run on this filesystem, and it must have already done the orphan * inode cleanup for us, so we can safely abort without any further action. */ -static void ext4_orphan_cleanup (struct super_block * sb, - struct ext4_super_block * es) +static void ext4_orphan_cleanup(struct super_block *sb, + struct ext4_super_block *es) { unsigned int s_flags = sb->s_flags; int nr_orphans = 0, nr_truncates = 0; @@ -1361,7 +1716,7 @@ static void ext4_orphan_cleanup (struct super_block * sb, int ret = ext4_quota_on_mount(sb, i); if (ret < 0) printk(KERN_ERR - "EXT4-fs: Cannot turn on journalled " + "EXT4-fs: Cannot turn on journaled " "quota: error %d\n", ret); } } @@ -1370,8 +1725,8 @@ static void ext4_orphan_cleanup (struct super_block * sb, while (es->s_last_orphan) { struct inode *inode; - if (!(inode = - ext4_orphan_get(sb, le32_to_cpu(es->s_last_orphan)))) { + inode = ext4_orphan_get(sb, le32_to_cpu(es->s_last_orphan)); + if (IS_ERR(inode)) { es->s_last_orphan = 0; break; } @@ -1380,16 +1735,16 @@ static void ext4_orphan_cleanup (struct super_block * sb, DQUOT_INIT(inode); if (inode->i_nlink) { printk(KERN_DEBUG - "%s: truncating inode %lu to %Ld bytes\n", - __FUNCTION__, inode->i_ino, inode->i_size); - jbd_debug(2, "truncating inode %lu to %Ld bytes\n", + "%s: truncating inode %lu to %lld bytes\n", + __func__, inode->i_ino, inode->i_size); + jbd_debug(2, "truncating inode %lu to %lld bytes\n", inode->i_ino, inode->i_size); ext4_truncate(inode); nr_truncates++; } 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++; @@ -1397,7 +1752,7 @@ static void ext4_orphan_cleanup (struct super_block * sb, iput(inode); /* The delete magic happens here! */ } -#define PLURAL(x) (x), ((x)==1) ? "" : "s" +#define PLURAL(x) (x), ((x) == 1) ? "" : "s" if (nr_orphans) printk(KERN_INFO "EXT4-fs: %s: %d orphan inode%s deleted\n", @@ -1409,27 +1764,100 @@ static void ext4_orphan_cleanup (struct super_block * sb, /* 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 */ } +/* + * Maximal extent format file size. + * Resulting logical blkno at s_maxbytes must fit in our on-disk + * extent format containers, within a sector_t, and within i_blocks + * in the vfs. ext4 inode has 48 bits of i_block in fsblock units, + * so that won't be a limiting factor. + * + * Note, this does *not* consider any metadata overhead for vfs i_blocks. + */ +static loff_t ext4_max_size(int blkbits) +{ + loff_t res; + loff_t upper_limit = MAX_LFS_FILESIZE; + + /* small i_blocks in vfs inode? */ + if (sizeof(blkcnt_t) < sizeof(u64)) { + /* + * CONFIG_LSF is not enabled implies the inode + * i_block represent total blocks in 512 bytes + * 32 == size of vfs inode i_blocks * 8 + */ + upper_limit = (1LL << 32) - 1; + + /* total blocks in file system block size */ + upper_limit >>= (blkbits - 9); + upper_limit <<= blkbits; + } + + /* 32-bit extent-start container, ee_block */ + res = 1LL << 32; + res <<= blkbits; + res -= 1; + + /* Sanity check against vm- & vfs- imposed limits */ + if (res > upper_limit) + res = upper_limit; -#define log2(n) ffz(~(n)) + return res; +} /* - * Maximal file size. There is a direct, and {,double-,triple-}indirect - * block limit, and also a limit of (2^32 - 1) 512-byte sectors in i_blocks. - * We need to be 1 filesystem block less than the 2^32 sector limit. + * Maximal bitmap file size. There is a direct, and {,double-,triple-}indirect + * block limit, and also a limit of (2^48 - 1) 512-byte sectors in i_blocks. + * We need to be 1 filesystem block less than the 2^48 sector limit. */ -static loff_t ext4_max_size(int bits) +static loff_t ext4_max_bitmap_size(int bits) { loff_t res = EXT4_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, bitmapped 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 2^48 -1 + * __u32 i_blocks_lo and _u16 i_blocks_high representing the + * total number of 512 bytes blocks of the file + */ + + if (sizeof(blkcnt_t) < sizeof(u64)) { + /* + * CONFIG_LSF is not enabled implies the inode + * i_block represent total blocks in 512 bytes + * 32 == size of vfs inode i_blocks * 8 + */ + upper_limit = (1LL << 32) - 1; + + /* total blocks in file system block size */ + upper_limit >>= (bits - 9); + + } else { + /* + * We use 48 bit ext4_inode i_blocks + * With EXT4_HUGE_FILE_FL set the i_blocks + * represent total number of blocks in + * file system block size + */ + upper_limit = (1LL << 48) - 1; + + } + + /* 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)); @@ -1437,6 +1865,10 @@ static loff_t ext4_max_size(int bits) res <<= bits; if (res > upper_limit) res = upper_limit; + + if (res > MAX_LFS_FILESIZE) + res = MAX_LFS_FILESIZE; + return res; } @@ -1444,7 +1876,7 @@ static ext4_fsblk_t descriptor_loc(struct super_block *sb, ext4_fsblk_t logical_sb_block, int nr) { struct ext4_sb_info *sbi = EXT4_SB(sb); - unsigned long bg, first_meta_bg; + ext4_group_t bg, first_meta_bg; int has_super = 0; first_meta_bg = le32_to_cpu(sbi->s_es->s_first_meta_bg); @@ -1458,10 +1890,41 @@ static ext4_fsblk_t descriptor_loc(struct super_block *sb, return (has_super + ext4_group_first_block_no(sb, bg)); } +/** + * ext4_get_stripe_size: Get the stripe size. + * @sbi: In memory super block info + * + * If we have specified it via mount option, then + * use the mount option value. If the value specified at mount time is + * greater than the blocks per group use the super block value. + * If the super block value is greater than blocks per group return 0. + * Allocator needs it be less than blocks per group. + * + */ +static unsigned long ext4_get_stripe_size(struct ext4_sb_info *sbi) +{ + unsigned long stride = le16_to_cpu(sbi->s_es->s_raid_stride); + unsigned long stripe_width = + le32_to_cpu(sbi->s_es->s_raid_stripe_width); + + if (sbi->s_stripe && sbi->s_stripe <= sbi->s_blocks_per_group) + return sbi->s_stripe; + + if (stripe_width <= sbi->s_blocks_per_group) + return stripe_width; + + if (stride <= sbi->s_blocks_per_group) + return stride; + + return 0; +} + +static int ext4_fill_super(struct super_block *sb, void *data, int silent) + __releases(kernel_lock) + __acquires(kernel_lock) -static int ext4_fill_super (struct super_block *sb, void *data, int silent) { - struct buffer_head * bh; + struct buffer_head *bh; struct ext4_super_block *es = NULL; struct ext4_sb_info *sbi; ext4_fsblk_t block; @@ -1472,8 +1935,9 @@ static int ext4_fill_super (struct super_block *sb, void *data, int silent) unsigned long journal_devnum = 0; unsigned long def_mount_opts; struct inode *root; + char *cp; + int ret = -EINVAL; int blocksize; - int hblock; int db_count; int i; int needs_recovery; @@ -1488,9 +1952,15 @@ static int ext4_fill_super (struct super_block *sb, void *data, int silent) sbi->s_mount_opt = 0; sbi->s_resuid = EXT4_DEF_RESUID; sbi->s_resgid = EXT4_DEF_RESGID; + sbi->s_inode_readahead_blks = EXT4_DEF_INODE_READAHEAD_BLKS; + sbi->s_sb_block = sb_block; unlock_kernel(); + /* Cleanup superblock name */ + for (cp = sb->s_id; (cp = strchr(cp, '/'));) + *cp = '!'; + blocksize = sb_min_blocksize(sb, EXT4_MIN_BLOCK_SIZE); if (!blocksize) { printk(KERN_ERR "EXT4-fs: unable to set blocksize\n"); @@ -1509,7 +1979,7 @@ static int ext4_fill_super (struct super_block *sb, void *data, int silent) } if (!(bh = sb_bread(sb, logical_sb_block))) { - printk (KERN_ERR "EXT4-fs: unable to read superblock\n"); + printk(KERN_ERR "EXT4-fs: unable to read superblock\n"); goto out_fail; } /* @@ -1530,11 +2000,11 @@ static int ext4_fill_super (struct super_block *sb, void *data, int silent) set_opt(sbi->s_mount_opt, GRPID); if (def_mount_opts & EXT4_DEFM_UID16) set_opt(sbi->s_mount_opt, NO_UID32); -#ifdef CONFIG_EXT4DEV_FS_XATTR +#ifdef CONFIG_EXT4_FS_XATTR if (def_mount_opts & EXT4_DEFM_XATTR_USER) set_opt(sbi->s_mount_opt, XATTR_USER); #endif -#ifdef CONFIG_EXT4DEV_FS_POSIX_ACL +#ifdef CONFIG_EXT4_FS_POSIX_ACL if (def_mount_opts & EXT4_DEFM_ACL) set_opt(sbi->s_mount_opt, POSIX_ACL); #endif @@ -1547,24 +2017,38 @@ static int ext4_fill_super (struct super_block *sb, void *data, int silent) if (le16_to_cpu(sbi->s_es->s_errors) == EXT4_ERRORS_PANIC) set_opt(sbi->s_mount_opt, ERRORS_PANIC); - else if (le16_to_cpu(sbi->s_es->s_errors) == EXT4_ERRORS_RO) - set_opt(sbi->s_mount_opt, ERRORS_RO); - else + else if (le16_to_cpu(sbi->s_es->s_errors) == EXT4_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); set_opt(sbi->s_mount_opt, RESERVATION); + set_opt(sbi->s_mount_opt, BARRIER); /* * turn on extents feature by default in ext4 filesystem - * User -o noextents to turn it off + * only if feature flag already set by mkfs or tune2fs. + * Use -o noextents to turn it off */ - set_opt(sbi->s_mount_opt, EXTENTS); + if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_EXTENTS)) + set_opt(sbi->s_mount_opt, EXTENTS); + else + ext4_warning(sb, __func__, + "extents feature not enabled on this filesystem, " + "use tune2fs.\n"); - if (!parse_options ((char *) data, sb, &journal_inum, &journal_devnum, - NULL, 0)) + /* + * enable delayed allocation by default + * Use -o nodelalloc to turn it off + */ + set_opt(sbi->s_mount_opt, DELALLOC); + + + if (!parse_options((char *) data, sb, &journal_inum, &journal_devnum, + NULL, 0)) goto failed_mount; sb->s_flags = (sb->s_flags & ~MS_POSIXACL) | @@ -1577,6 +2061,7 @@ static int ext4_fill_super (struct super_block *sb, void *data, int silent) printk(KERN_WARNING "EXT4-fs warning: feature flags set on rev 0 fs, " "running e2fsck is recommended\n"); + /* * Check feature flags regardless of the revision level, since we * previously didn't change the revision level when setting the flags, @@ -1596,6 +2081,19 @@ static int ext4_fill_super (struct super_block *sb, void *data, int silent) sb->s_id, le32_to_cpu(features)); goto failed_mount; } + if (EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_HUGE_FILE)) { + /* + * Large file size enabled file system can only be + * mount if kernel is build with CONFIG_LSF + */ + if (sizeof(root->i_blocks) < sizeof(u64) && + !(sb->s_flags & MS_RDONLY)) { + printk(KERN_ERR "EXT4-fs: %s: Filesystem with huge " + "files cannot be mounted read-write " + "without CONFIG_LSF.\n", sb->s_id); + goto failed_mount; + } + } blocksize = BLOCK_SIZE << le32_to_cpu(es->s_log_block_size); if (blocksize < EXT4_MIN_BLOCK_SIZE || @@ -1606,20 +2104,16 @@ static int ext4_fill_super (struct super_block *sb, void *data, int silent) goto failed_mount; } - hblock = bdev_hardsect_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 "EXT4-fs: blocksize %d too small for " - "device blocksize %d.\n", blocksize, hblock); + + /* Validate the filesystem blocksize */ + if (!sb_set_blocksize(sb, blocksize)) { + printk(KERN_ERR "EXT4-fs: bad block size %d.\n", + blocksize); goto failed_mount; } - brelse (bh); - sb_set_blocksize(sb, blocksize); + brelse(bh); logical_sb_block = sb_block * EXT4_MIN_BLOCK_SIZE; offset = do_div(logical_sb_block, blocksize); bh = sb_bread(sb, logical_sb_block); @@ -1631,12 +2125,13 @@ static int ext4_fill_super (struct super_block *sb, void *data, int silent) es = (struct ext4_super_block *)(((char *)bh->b_data) + offset); sbi->s_es = es; if (es->s_magic != cpu_to_le16(EXT4_SUPER_MAGIC)) { - printk (KERN_ERR - "EXT4-fs: Magic mismatch, very weird !\n"); + printk(KERN_ERR + "EXT4-fs: Magic mismatch, very weird !\n"); goto failed_mount; } } + sbi->s_bitmap_maxbytes = ext4_max_bitmap_size(sb->s_blocksize_bits); sb->s_maxbytes = ext4_max_size(sb->s_blocksize_bits); if (le32_to_cpu(es->s_rev_level) == EXT4_GOOD_OLD_REV) { @@ -1648,27 +2143,19 @@ static int ext4_fill_super (struct super_block *sb, void *data, int silent) if ((sbi->s_inode_size < EXT4_GOOD_OLD_INODE_SIZE) || (!is_power_of_2(sbi->s_inode_size)) || (sbi->s_inode_size > blocksize)) { - printk (KERN_ERR - "EXT4-fs: unsupported inode size: %d\n", - sbi->s_inode_size); + printk(KERN_ERR + "EXT4-fs: unsupported inode size: %d\n", + sbi->s_inode_size); goto failed_mount; } if (sbi->s_inode_size > EXT4_GOOD_OLD_INODE_SIZE) sb->s_time_gran = 1 << (EXT4_EPOCH_BITS - 2); } - sbi->s_frag_size = EXT4_MIN_FRAG_SIZE << - le32_to_cpu(es->s_log_frag_size); - if (blocksize != sbi->s_frag_size) { - printk(KERN_ERR - "EXT4-fs: fragsize %lu != blocksize %u (unsupported)\n", - sbi->s_frag_size, blocksize); - goto failed_mount; - } sbi->s_desc_size = le16_to_cpu(es->s_desc_size); if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_64BIT)) { if (sbi->s_desc_size < EXT4_MIN_DESC_SIZE_64BIT || sbi->s_desc_size > EXT4_MAX_DESC_SIZE || - sbi->s_desc_size & (sbi->s_desc_size - 1)) { + !is_power_of_2(sbi->s_desc_size)) { printk(KERN_ERR "EXT4-fs: unsupported descriptor size %lu\n", sbi->s_desc_size); @@ -1677,9 +2164,8 @@ static int ext4_fill_super (struct super_block *sb, void *data, int silent) } else sbi->s_desc_size = EXT4_MIN_DESC_SIZE; sbi->s_blocks_per_group = le32_to_cpu(es->s_blocks_per_group); - sbi->s_frags_per_group = le32_to_cpu(es->s_frags_per_group); sbi->s_inodes_per_group = le32_to_cpu(es->s_inodes_per_group); - if (EXT4_INODE_SIZE(sb) == 0) + if (EXT4_INODE_SIZE(sb) == 0 || EXT4_INODES_PER_GROUP(sb) == 0) goto cantfind_ext4; sbi->s_inodes_per_block = blocksize / EXT4_INODE_SIZE(sb); if (sbi->s_inodes_per_block == 0) @@ -1689,28 +2175,22 @@ static int ext4_fill_super (struct super_block *sb, void *data, int silent) sbi->s_desc_per_block = blocksize / EXT4_DESC_SIZE(sb); sbi->s_sbh = bh; sbi->s_mount_state = le16_to_cpu(es->s_state); - sbi->s_addr_per_block_bits = log2(EXT4_ADDR_PER_BLOCK(sb)); - sbi->s_desc_per_block_bits = log2(EXT4_DESC_PER_BLOCK(sb)); - for (i=0; i < 4; i++) + sbi->s_addr_per_block_bits = ilog2(EXT4_ADDR_PER_BLOCK(sb)); + sbi->s_desc_per_block_bits = ilog2(EXT4_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; if (sbi->s_blocks_per_group > blocksize * 8) { - printk (KERN_ERR - "EXT4-fs: #blocks per group too big: %lu\n", - sbi->s_blocks_per_group); - goto failed_mount; - } - if (sbi->s_frags_per_group > blocksize * 8) { - printk (KERN_ERR - "EXT4-fs: #fragments per group too big: %lu\n", - sbi->s_frags_per_group); + printk(KERN_ERR + "EXT4-fs: #blocks per group too big: %lu\n", + sbi->s_blocks_per_group); goto failed_mount; } if (sbi->s_inodes_per_group > blocksize * 8) { - printk (KERN_ERR - "EXT4-fs: #inodes per group too big: %lu\n", - sbi->s_inodes_per_group); + printk(KERN_ERR + "EXT4-fs: #inodes per group too big: %lu\n", + sbi->s_inodes_per_group); goto failed_mount; } @@ -1726,6 +2206,17 @@ static int ext4_fill_super (struct super_block *sb, void *data, int silent) if (EXT4_BLOCKS_PER_GROUP(sb) == 0) goto cantfind_ext4; + + /* ensure blocks_count calculation below doesn't sign-extend */ + if (ext4_blocks_count(es) + EXT4_BLOCKS_PER_GROUP(sb) < + le32_to_cpu(es->s_first_data_block) + 1) { + printk(KERN_WARNING "EXT4-fs: bad geometry: block count %llu, " + "first data block %u, blocks per group %lu\n", + ext4_blocks_count(es), + le32_to_cpu(es->s_first_data_block), + EXT4_BLOCKS_PER_GROUP(sb)); + goto failed_mount; + } blocks_count = (ext4_blocks_count(es) - le32_to_cpu(es->s_first_data_block) + EXT4_BLOCKS_PER_GROUP(sb) - 1); @@ -1733,29 +2224,47 @@ static int ext4_fill_super (struct super_block *sb, void *data, int silent) sbi->s_groups_count = blocks_count; db_count = (sbi->s_groups_count + EXT4_DESC_PER_BLOCK(sb) - 1) / EXT4_DESC_PER_BLOCK(sb); - sbi->s_group_desc = kmalloc(db_count * sizeof (struct buffer_head *), + sbi->s_group_desc = kmalloc(db_count * sizeof(struct buffer_head *), GFP_KERNEL); if (sbi->s_group_desc == NULL) { - printk (KERN_ERR "EXT4-fs: not enough memory\n"); + printk(KERN_ERR "EXT4-fs: not enough memory\n"); goto failed_mount; } +#ifdef CONFIG_PROC_FS + if (ext4_proc_root) + sbi->s_proc = proc_mkdir(sb->s_id, ext4_proc_root); + + if (sbi->s_proc) + proc_create_data("inode_readahead_blks", 0644, sbi->s_proc, + &ext4_ui_proc_fops, + &sbi->s_inode_readahead_blks); +#endif + bgl_lock_init(&sbi->s_blockgroup_lock); for (i = 0; i < db_count; i++) { block = descriptor_loc(sb, logical_sb_block, i); sbi->s_group_desc[i] = sb_bread(sb, block); if (!sbi->s_group_desc[i]) { - printk (KERN_ERR "EXT4-fs: " - "can't read group descriptor %d\n", i); + printk(KERN_ERR "EXT4-fs: " + "can't read group descriptor %d\n", i); db_count = i; goto failed_mount2; } } - if (!ext4_check_descriptors (sb)) { + if (!ext4_check_descriptors(sb)) { printk(KERN_ERR "EXT4-fs: group descriptors corrupted!\n"); goto failed_mount2; } + if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_FLEX_BG)) + if (!ext4_fill_flex_info(sb)) { + printk(KERN_ERR + "EXT4-fs: unable to initialize " + "flex_bg meta info!\n"); + goto failed_mount2; + } + sbi->s_gdb_count = db_count; get_random_bytes(&sbi->s_next_generation, sizeof(u32)); spin_lock_init(&sbi->s_next_gen_lock); @@ -1770,23 +2279,15 @@ static int ext4_fill_super (struct super_block *sb, void *data, int silent) err = percpu_counter_init(&sbi->s_dirs_counter, ext4_count_dirs(sb)); } + if (!err) { + err = percpu_counter_init(&sbi->s_dirtyblocks_counter, 0); + } if (err) { printk(KERN_ERR "EXT4-fs: insufficient memory\n"); goto failed_mount3; } - /* per fileystem reservation list head & lock */ - spin_lock_init(&sbi->s_rsv_window_lock); - sbi->s_rsv_window_root = RB_ROOT; - /* Add a single, static dummy reservation to the start of the - * reservation window list --- it gives us a placeholder for - * append-at-start-of-list which makes the allocation logic - * _much_ simpler. */ - sbi->s_rsv_window_head.rsv_start = EXT4_RESERVE_WINDOW_NOT_ALLOCATED; - sbi->s_rsv_window_head.rsv_end = EXT4_RESERVE_WINDOW_NOT_ALLOCATED; - sbi->s_rsv_window_head.rsv_alloc_hit = 0; - sbi->s_rsv_window_head.rsv_goal_size = 0; - ext4_rsv_window_add(sb, &sbi->s_rsv_window_head); + sbi->s_stripe = ext4_get_stripe_size(sbi); /* * set up enough so that it can read an inode @@ -1814,14 +2315,37 @@ static int ext4_fill_super (struct super_block *sb, void *data, int silent) EXT4_HAS_COMPAT_FEATURE(sb, EXT4_FEATURE_COMPAT_HAS_JOURNAL)) { if (ext4_load_journal(sb, es, journal_devnum)) goto failed_mount3; + if (!(sb->s_flags & MS_RDONLY) && + EXT4_SB(sb)->s_journal->j_failed_commit) { + printk(KERN_CRIT "EXT4-fs error (device %s): " + "ext4_fill_super: Journal transaction " + "%u is corrupt\n", sb->s_id, + EXT4_SB(sb)->s_journal->j_failed_commit); + if (test_opt(sb, ERRORS_RO)) { + printk(KERN_CRIT + "Mounting filesystem read-only\n"); + sb->s_flags |= MS_RDONLY; + EXT4_SB(sb)->s_mount_state |= EXT4_ERROR_FS; + es->s_state |= cpu_to_le16(EXT4_ERROR_FS); + } + if (test_opt(sb, ERRORS_PANIC)) { + EXT4_SB(sb)->s_mount_state |= EXT4_ERROR_FS; + es->s_state |= cpu_to_le16(EXT4_ERROR_FS); + ext4_commit_super(sb, es, 1); + printk(KERN_CRIT + "EXT4-fs (device %s): mount failed\n", + sb->s_id); + goto failed_mount4; + } + } } else if (journal_inum) { if (ext4_create_journal(sb, es, journal_inum)) goto failed_mount3; } else { if (!silent) - printk (KERN_ERR - "ext4: No journal on filesystem on %s\n", - sb->s_id); + printk(KERN_ERR + "ext4: No journal on filesystem on %s\n", + sb->s_id); goto failed_mount3; } @@ -1832,6 +2356,21 @@ static int ext4_fill_super (struct super_block *sb, void *data, int silent) goto failed_mount4; } + if (test_opt(sb, JOURNAL_ASYNC_COMMIT)) { + jbd2_journal_set_features(sbi->s_journal, + JBD2_FEATURE_COMPAT_CHECKSUM, 0, + JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT); + } else if (test_opt(sb, JOURNAL_CHECKSUM)) { + jbd2_journal_set_features(sbi->s_journal, + JBD2_FEATURE_COMPAT_CHECKSUM, 0, 0); + jbd2_journal_clear_features(sbi->s_journal, 0, 0, + JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT); + } else { + jbd2_journal_clear_features(sbi->s_journal, + JBD2_FEATURE_COMPAT_CHECKSUM, 0, + JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT); + } + /* We have now updated the journal if required, so we can * validate the data journaling mode. */ switch (test_opt(sb, DATA_FLAGS)) { @@ -1871,21 +2410,26 @@ static int ext4_fill_super (struct super_block *sb, void *data, int silent) * so we can safely mount the rest of the filesystem now. */ - root = iget(sb, EXT4_ROOT_INO); - sb->s_root = d_alloc_root(root); - if (!sb->s_root) { + root = ext4_iget(sb, EXT4_ROOT_INO); + if (IS_ERR(root)) { printk(KERN_ERR "EXT4-fs: get root inode failed\n"); - iput(root); + 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; + iput(root); printk(KERN_ERR "EXT4-fs: corrupt root inode, run e2fsck\n"); goto failed_mount4; } + sb->s_root = d_alloc_root(root); + if (!sb->s_root) { + printk(KERN_ERR "EXT4-fs: get root dentry failed\n"); + iput(root); + ret = -ENOMEM; + goto failed_mount4; + } - ext4_setup_super (sb, es, sb->s_flags & MS_RDONLY); + ext4_setup_super(sb, es, sb->s_flags & MS_RDONLY); /* determine the minimum size of new large inodes, if present */ if (sbi->s_inode_size > EXT4_GOOD_OLD_INODE_SIZE) { @@ -1924,14 +2468,27 @@ static int ext4_fill_super (struct super_block *sb, void *data, int silent) ext4_orphan_cleanup(sb, es); EXT4_SB(sb)->s_mount_state &= ~EXT4_ORPHAN_FS; if (needs_recovery) - printk (KERN_INFO "EXT4-fs: recovery complete.\n"); + printk(KERN_INFO "EXT4-fs: recovery complete.\n"); ext4_mark_recovery_complete(sb, es); - printk (KERN_INFO "EXT4-fs: mounted filesystem with %s data mode.\n", - test_opt(sb,DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA ? "journal": - test_opt(sb,DATA_FLAGS) == EXT4_MOUNT_ORDERED_DATA ? "ordered": - "writeback"); + printk(KERN_INFO "EXT4-fs: mounted filesystem with %s data mode.\n", + test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA ? "journal": + test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_ORDERED_DATA ? "ordered": + "writeback"); + + if (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA) { + printk(KERN_WARNING "EXT4-fs: Ignoring delalloc option - " + "requested data journaling mode\n"); + clear_opt(sbi->s_mount_opt, DELALLOC); + } else if (test_opt(sb, DELALLOC)) + printk(KERN_INFO "EXT4-fs: delayed allocation enabled\n"); ext4_ext_init(sb); + err = ext4_mb_init(sb, needs_recovery); + if (err) { + printk(KERN_ERR "EXT4-fs: failed to initalize mballoc (%d)\n", + err); + goto failed_mount4; + } lock_kernel(); return 0; @@ -1944,15 +2501,21 @@ cantfind_ext4: failed_mount4: jbd2_journal_destroy(sbi->s_journal); + sbi->s_journal = NULL; failed_mount3: percpu_counter_destroy(&sbi->s_freeblocks_counter); percpu_counter_destroy(&sbi->s_freeinodes_counter); percpu_counter_destroy(&sbi->s_dirs_counter); + percpu_counter_destroy(&sbi->s_dirtyblocks_counter); failed_mount2: for (i = 0; i < db_count; i++) brelse(sbi->s_group_desc[i]); kfree(sbi->s_group_desc); failed_mount: + if (sbi->s_proc) { + remove_proc_entry("inode_readahead_blks", sbi->s_proc); + remove_proc_entry(sb->s_id, ext4_proc_root); + } #ifdef CONFIG_QUOTA for (i = 0; i < MAXQUOTAS; i++) kfree(sbi->s_qf_names[i]); @@ -1963,7 +2526,7 @@ out_fail: sb->s_fs_info = NULL; kfree(sbi); lock_kernel(); - return -EINVAL; + return ret; } /* @@ -1986,6 +2549,10 @@ static void ext4_init_journal_params(struct super_block *sb, journal_t *journal) journal->j_flags |= JBD2_BARRIER; else journal->j_flags &= ~JBD2_BARRIER; + if (test_opt(sb, DATA_ERR_ABORT)) + journal->j_flags |= JBD2_ABORT_ON_SYNCDATA_ERR; + else + journal->j_flags &= ~JBD2_ABORT_ON_SYNCDATA_ERR; spin_unlock(&journal->j_state_lock); } @@ -1999,8 +2566,8 @@ static journal_t *ext4_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) { + journal_inode = ext4_iget(sb, journal_inum); + if (IS_ERR(journal_inode)) { printk(KERN_ERR "EXT4-fs: no journal found.\n"); return NULL; } @@ -2011,9 +2578,9 @@ static journal_t *ext4_get_journal(struct super_block *sb, return NULL; } - jbd_debug(2, "Journal inode found at %p: %Ld bytes\n", + jbd_debug(2, "Journal inode found at %p: %lld bytes\n", journal_inode, journal_inode->i_size); - if (is_bad_inode(journal_inode) || !S_ISREG(journal_inode->i_mode)) { + if (!S_ISREG(journal_inode->i_mode)) { printk(KERN_ERR "EXT4-fs: invalid journal inode.\n"); iput(journal_inode); return NULL; @@ -2033,14 +2600,14 @@ static journal_t *ext4_get_journal(struct super_block *sb, static journal_t *ext4_get_dev_journal(struct super_block *sb, dev_t j_dev) { - struct buffer_head * bh; + struct buffer_head *bh; journal_t *journal; ext4_fsblk_t start; ext4_fsblk_t len; int hblock, blocksize; ext4_fsblk_t sb_block; unsigned long offset; - struct ext4_super_block * es; + struct ext4_super_block *es; struct block_device *bdev; bdev = ext4_blkdev_get(j_dev); @@ -2155,8 +2722,8 @@ static int ext4_load_journal(struct super_block *sb, "unavailable, cannot proceed.\n"); return -EROFS; } - printk (KERN_INFO "EXT4-fs: write access will " - "be enabled during recovery.\n"); + printk(KERN_INFO "EXT4-fs: write access will " + "be enabled during recovery.\n"); } } @@ -2174,6 +2741,11 @@ static int ext4_load_journal(struct super_block *sb, return -EINVAL; } + if (journal->j_flags & JBD2_BARRIER) + printk(KERN_INFO "EXT4-fs: barriers enabled\n"); + else + printk(KERN_INFO "EXT4-fs: barriers disabled\n"); + if (!really_read_only && test_opt(sb, UPDATE_JOURNAL)) { err = jbd2_journal_update_format(journal); if (err) { @@ -2209,8 +2781,8 @@ static int ext4_load_journal(struct super_block *sb, return 0; } -static int ext4_create_journal(struct super_block * sb, - struct ext4_super_block * es, +static int ext4_create_journal(struct super_block *sb, + struct ext4_super_block *es, unsigned int journal_inum) { journal_t *journal; @@ -2251,21 +2823,41 @@ static int ext4_create_journal(struct super_block * sb, return 0; } -static void ext4_commit_super (struct super_block * sb, - struct ext4_super_block * es, - int sync) +static void ext4_commit_super(struct super_block *sb, + struct ext4_super_block *es, int sync) { struct buffer_head *sbh = EXT4_SB(sb)->s_sbh; if (!sbh) return; + if (buffer_write_io_error(sbh)) { + /* + * Oh, dear. A previous attempt to write the + * superblock failed. This could happen because the + * USB device was yanked out. Or it could happen to + * be a transient write error and maybe the block will + * be remapped. Nothing we can do but to retry the + * write and hope for the best. + */ + printk(KERN_ERR "ext4: previous I/O error to " + "superblock detected for %s.\n", sb->s_id); + clear_buffer_write_io_error(sbh); + set_buffer_uptodate(sbh); + } es->s_wtime = cpu_to_le32(get_seconds()); ext4_free_blocks_count_set(es, ext4_count_free_blocks(sb)); es->s_free_inodes_count = cpu_to_le32(ext4_count_free_inodes(sb)); BUFFER_TRACE(sbh, "marking dirty"); mark_buffer_dirty(sbh); - if (sync) + if (sync) { sync_dirty_buffer(sbh); + if (buffer_write_io_error(sbh)) { + printk(KERN_ERR "ext4: I/O error while writing " + "superblock for %s.\n", sb->s_id); + clear_buffer_write_io_error(sbh); + set_buffer_uptodate(sbh); + } + } } @@ -2274,13 +2866,15 @@ static void ext4_commit_super (struct super_block * sb, * remounting) the filesystem readonly, then we will end up with a * consistent fs on disk. Record that fact. */ -static void ext4_mark_recovery_complete(struct super_block * sb, - struct ext4_super_block * es) +static void ext4_mark_recovery_complete(struct super_block *sb, + struct ext4_super_block *es) { journal_t *journal = EXT4_SB(sb)->s_journal; jbd2_journal_lock_updates(journal); - jbd2_journal_flush(journal); + if (jbd2_journal_flush(journal) < 0) + goto out; + lock_super(sb); if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER) && sb->s_flags & MS_RDONLY) { @@ -2289,6 +2883,8 @@ static void ext4_mark_recovery_complete(struct super_block * sb, ext4_commit_super(sb, es, 1); } unlock_super(sb); + +out: jbd2_journal_unlock_updates(journal); } @@ -2297,8 +2893,8 @@ static void ext4_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 ext4_clear_journal_err(struct super_block * sb, - struct ext4_super_block * es) +static void ext4_clear_journal_err(struct super_block *sb, + struct ext4_super_block *es) { journal_t *journal; int j_errno; @@ -2316,14 +2912,14 @@ static void ext4_clear_journal_err(struct super_block * sb, char nbuf[16]; errstr = ext4_decode_error(sb, j_errno, nbuf); - ext4_warning(sb, __FUNCTION__, "Filesystem error recorded " + ext4_warning(sb, __func__, "Filesystem error recorded " "from previous mount: %s", errstr); - ext4_warning(sb, __FUNCTION__, "Marking fs in need of " + ext4_warning(sb, __func__, "Marking fs in need of " "filesystem check."); EXT4_SB(sb)->s_mount_state |= EXT4_ERROR_FS; es->s_state |= cpu_to_le16(EXT4_ERROR_FS); - ext4_commit_super (sb, es, 1); + ext4_commit_super(sb, es, 1); jbd2_journal_clear_err(journal); } @@ -2356,7 +2952,7 @@ int ext4_force_commit(struct super_block *sb) * This implicitly triggers the writebehind on sync(). */ -static void ext4_write_super (struct super_block * sb) +static void ext4_write_super(struct super_block *sb) { if (mutex_trylock(&sb->s_lock) != 0) BUG(); @@ -2367,6 +2963,7 @@ static int ext4_sync_fs(struct super_block *sb, int wait) { tid_t target; + trace_mark(ext4_sync_fs, "dev %s wait %d", sb->s_id, wait); sb->s_dirt = 0; if (jbd2_journal_start_commit(EXT4_SB(sb)->s_journal, &target)) { if (wait) @@ -2388,7 +2985,13 @@ static void ext4_write_super_lockfs(struct super_block *sb) /* Now we set up the journal barrier. */ jbd2_journal_lock_updates(journal); - jbd2_journal_flush(journal); + + /* + * We don't want to clear needs_recovery flag when we failed + * to flush the journal. + */ + if (jbd2_journal_flush(journal) < 0) + return; /* Journal blocked and flushed, clear needs_recovery flag. */ EXT4_CLEAR_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER); @@ -2412,13 +3015,14 @@ static void ext4_unlockfs(struct super_block *sb) } } -static int ext4_remount (struct super_block * sb, int * flags, char * data) +static int ext4_remount(struct super_block *sb, int *flags, char *data) { - struct ext4_super_block * es; + struct ext4_super_block *es; struct ext4_sb_info *sbi = EXT4_SB(sb); ext4_fsblk_t n_blocks_count = 0; unsigned long old_sb_flags; struct ext4_mount_options old_opts; + ext4_group_t g; int err; #ifdef CONFIG_QUOTA int i; @@ -2445,7 +3049,7 @@ static int ext4_remount (struct super_block * sb, int * flags, char * data) } if (sbi->s_mount_opt & EXT4_MOUNT_ABORT) - ext4_abort(sb, __FUNCTION__, "Abort forced by user"); + ext4_abort(sb, __func__, "Abort forced by user"); sb->s_flags = (sb->s_flags & ~MS_POSIXACL) | ((sbi->s_mount_opt & EXT4_MOUNT_POSIX_ACL) ? MS_POSIXACL : 0); @@ -2497,6 +3101,26 @@ static int ext4_remount (struct super_block * sb, int * flags, char * data) } /* + * Make sure the group descriptor checksums + * are sane. If they aren't, refuse to + * remount r/w. + */ + for (g = 0; g < sbi->s_groups_count; g++) { + struct ext4_group_desc *gdp = + ext4_get_group_desc(sb, g, NULL); + + if (!ext4_group_desc_csum_verify(sbi, g, gdp)) { + printk(KERN_ERR + "EXT4-fs: ext4_remount: " + "Checksum for group %lu failed (%u!=%u)\n", + g, le16_to_cpu(ext4_group_desc_csum(sbi, g, gdp)), + le16_to_cpu(gdp->bg_checksum)); + err = -EINVAL; + 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. @@ -2521,7 +3145,7 @@ static int ext4_remount (struct super_block * sb, int * flags, char * data) sbi->s_mount_state = le16_to_cpu(es->s_state); if ((err = ext4_group_extend(sb, es, n_blocks_count))) goto restore_opts; - if (!ext4_setup_super (sb, es, 0)) + if (!ext4_setup_super(sb, es, 0)) sb->s_flags &= ~MS_RDONLY; } } @@ -2551,7 +3175,7 @@ restore_opts: return err; } -static int ext4_statfs (struct dentry * dentry, struct kstatfs * buf) +static int ext4_statfs(struct dentry *dentry, struct kstatfs *buf) { struct super_block *sb = dentry->d_sb; struct ext4_sb_info *sbi = EXT4_SB(sb); @@ -2560,8 +3184,8 @@ static int ext4_statfs (struct dentry * dentry, struct kstatfs * buf) 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; + } else if (sbi->s_blocks_last != ext4_blocks_count(es)) { + ext4_group_t ngroups = sbi->s_groups_count, i; ext4_fsblk_t overhead = 0; smp_rmb(); @@ -2595,14 +3219,15 @@ static int ext4_statfs (struct dentry * dentry, struct kstatfs * buf) 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); + sbi->s_blocks_last = ext4_blocks_count(es); } buf->f_type = EXT4_SUPER_MAGIC; buf->f_bsize = sb->s_blocksize; buf->f_blocks = ext4_blocks_count(es) - sbi->s_overhead_last; - buf->f_bfree = percpu_counter_sum_positive(&sbi->s_freeblocks_counter); - es->s_free_blocks_count = cpu_to_le32(buf->f_bfree); + buf->f_bfree = percpu_counter_sum_positive(&sbi->s_freeblocks_counter) - + percpu_counter_sum_positive(&sbi->s_dirtyblocks_counter); + ext4_free_blocks_count_set(es, buf->f_bfree); buf->f_bavail = buf->f_bfree - ext4_r_blocks_count(es); if (buf->f_bfree < ext4_r_blocks_count(es)) buf->f_bavail = 0; @@ -2657,8 +3282,14 @@ static int ext4_dquot_drop(struct inode *inode) /* We may delete quota structure so we need to reserve enough blocks */ handle = ext4_journal_start(inode, 2*EXT4_QUOTA_DEL_BLOCKS(inode->i_sb)); - if (IS_ERR(handle)) + if (IS_ERR(handle)) { + /* + * We call dquot_drop() anyway to at least release references + * to quota structures so that umount does not hang. + */ + dquot_drop(inode); return PTR_ERR(handle); + } ret = dquot_drop(inode); err = ext4_journal_stop(handle); if (!ret) @@ -2721,7 +3352,7 @@ static int ext4_release_dquot(struct dquot *dquot) static int ext4_mark_dquot_dirty(struct dquot *dquot) { - /* Are we journalling quotas? */ + /* Are we journaling quotas? */ if (EXT4_SB(dquot->dq_sb)->s_qf_names[USRQUOTA] || EXT4_SB(dquot->dq_sb)->s_qf_names[GRPQUOTA]) { dquot_mark_dquot_dirty(dquot); @@ -2761,32 +3392,56 @@ static int ext4_quota_on_mount(struct super_block *sb, int type) * Standard function to be called on quota_on */ static int ext4_quota_on(struct super_block *sb, int type, int format_id, - char *path) + char *path, int remount) { int err; struct nameidata nd; if (!test_opt(sb, QUOTA)) return -EINVAL; - /* Not journalling quota? */ - if (!EXT4_SB(sb)->s_qf_names[USRQUOTA] && - !EXT4_SB(sb)->s_qf_names[GRPQUOTA]) - return vfs_quota_on(sb, type, format_id, path); + /* When remounting, no checks are needed and in fact, path is NULL */ + if (remount) + return vfs_quota_on(sb, type, format_id, path, remount); + err = path_lookup(path, LOOKUP_FOLLOW, &nd); if (err) return err; + /* Quotafile not on the same filesystem? */ - if (nd.mnt->mnt_sb != sb) { - path_release(&nd); + if (nd.path.mnt->mnt_sb != sb) { + path_put(&nd.path); return -EXDEV; } - /* Quotafile not of fs root? */ - if (nd.dentry->d_parent->d_inode != sb->s_root->d_inode) - printk(KERN_WARNING - "EXT4-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 (EXT4_SB(sb)->s_qf_names[type]) { + /* Quotafile not in fs root? */ + if (nd.path.dentry->d_parent->d_inode != sb->s_root->d_inode) + printk(KERN_WARNING + "EXT4-fs: Quota file not on filesystem root. " + "Journaled quota will not work.\n"); + } + + /* + * When we journal data on quota file, we have to flush journal to see + * all updates to the file when we bypass pagecache... + */ + if (ext4_should_journal_data(nd.path.dentry->d_inode)) { + /* + * We don't need to lock updates but journal_flush() could + * otherwise be livelocked... + */ + jbd2_journal_lock_updates(EXT4_SB(sb)->s_journal); + err = jbd2_journal_flush(EXT4_SB(sb)->s_journal); + jbd2_journal_unlock_updates(EXT4_SB(sb)->s_journal); + if (err) { + path_put(&nd.path); + return err; + } + } + + err = vfs_quota_on_path(sb, type, format_id, &nd.path); + path_put(&nd.path); + return err; } /* Read data from quotafile - avoid pagecache and such because we cannot afford @@ -2797,7 +3452,7 @@ static ssize_t ext4_quota_read(struct super_block *sb, int type, char *data, size_t len, loff_t off) { struct inode *inode = sb_dqopt(sb)->files[type]; - sector_t blk = off >> EXT4_BLOCK_SIZE_BITS(sb); + ext4_lblk_t blk = off >> EXT4_BLOCK_SIZE_BITS(sb); int err = 0; int offset = off & (sb->s_blocksize - 1); int tocopy; @@ -2835,7 +3490,7 @@ static ssize_t ext4_quota_write(struct super_block *sb, int type, const char *data, size_t len, loff_t off) { struct inode *inode = sb_dqopt(sb)->files[type]; - sector_t blk = off >> EXT4_BLOCK_SIZE_BITS(sb); + ext4_lblk_t blk = off >> EXT4_BLOCK_SIZE_BITS(sb); int err = 0; int offset = off & (sb->s_blocksize - 1); int tocopy; @@ -2845,7 +3500,7 @@ static ssize_t ext4_quota_write(struct super_block *sb, int type, handle_t *handle = journal_current_handle(); if (!handle) { - printk(KERN_WARNING "EXT4-fs: Quota write (off=%Lu, len=%Lu)" + printk(KERN_WARNING "EXT4-fs: Quota write (off=%llu, len=%llu)" " cancelled because transaction is not started.\n", (unsigned long long)off, (unsigned long long)len); return -EIO; @@ -2872,7 +3527,7 @@ static ssize_t ext4_quota_write(struct super_block *sb, int type, err = ext4_journal_dirty_metadata(handle, bh); else { /* Always do at least ordered writes for quotas */ - err = ext4_journal_dirty_data(handle, bh); + err = ext4_jbd2_file_inode(handle, inode); mark_buffer_dirty(bh); } brelse(bh); @@ -2884,13 +3539,14 @@ static ssize_t ext4_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); EXT4_I(inode)->i_disksize = inode->i_size; } - inode->i_version++; inode->i_mtime = inode->i_ctime = CURRENT_TIME; ext4_mark_inode_dirty(handle, inode); mutex_unlock(&inode->i_mutex); @@ -2905,38 +3561,122 @@ static int ext4_get_sb(struct file_system_type *fs_type, return get_sb_bdev(fs_type, flags, dev_name, data, ext4_fill_super, mnt); } +#ifdef CONFIG_PROC_FS +static int ext4_ui_proc_show(struct seq_file *m, void *v) +{ + unsigned int *p = m->private; + + seq_printf(m, "%u\n", *p); + return 0; +} + +static int ext4_ui_proc_open(struct inode *inode, struct file *file) +{ + return single_open(file, ext4_ui_proc_show, PDE(inode)->data); +} + +static ssize_t ext4_ui_proc_write(struct file *file, const char __user *buf, + size_t cnt, loff_t *ppos) +{ + unsigned int *p = PDE(file->f_path.dentry->d_inode)->data; + char str[32]; + unsigned long value; + + if (cnt >= sizeof(str)) + return -EINVAL; + if (copy_from_user(str, buf, cnt)) + return -EFAULT; + value = simple_strtol(str, NULL, 0); + if (value < 0) + return -ERANGE; + *p = value; + return cnt; +} + +const struct file_operations ext4_ui_proc_fops = { + .owner = THIS_MODULE, + .open = ext4_ui_proc_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, + .write = ext4_ui_proc_write, +}; +#endif + +static struct file_system_type ext4_fs_type = { + .owner = THIS_MODULE, + .name = "ext4", + .get_sb = ext4_get_sb, + .kill_sb = kill_block_super, + .fs_flags = FS_REQUIRES_DEV, +}; + +#ifdef CONFIG_EXT4DEV_COMPAT +static int ext4dev_get_sb(struct file_system_type *fs_type, + int flags, const char *dev_name, void *data, struct vfsmount *mnt) +{ + printk(KERN_WARNING "EXT4-fs: Update your userspace programs " + "to mount using ext4\n"); + printk(KERN_WARNING "EXT4-fs: ext4dev backwards compatibility " + "will go away by 2.6.31\n"); + return get_sb_bdev(fs_type, flags, dev_name, data, ext4_fill_super, mnt); +} + static struct file_system_type ext4dev_fs_type = { .owner = THIS_MODULE, .name = "ext4dev", - .get_sb = ext4_get_sb, + .get_sb = ext4dev_get_sb, .kill_sb = kill_block_super, .fs_flags = FS_REQUIRES_DEV, }; +MODULE_ALIAS("ext4dev"); +#endif static int __init init_ext4_fs(void) { - int err = init_ext4_xattr(); + int err; + + ext4_proc_root = proc_mkdir("fs/ext4", NULL); + err = init_ext4_mballoc(); if (err) return err; + + err = init_ext4_xattr(); + if (err) + goto out2; err = init_inodecache(); if (err) goto out1; - err = register_filesystem(&ext4dev_fs_type); + err = register_filesystem(&ext4_fs_type); if (err) goto out; +#ifdef CONFIG_EXT4DEV_COMPAT + err = register_filesystem(&ext4dev_fs_type); + if (err) { + unregister_filesystem(&ext4_fs_type); + goto out; + } +#endif return 0; out: destroy_inodecache(); out1: exit_ext4_xattr(); +out2: + exit_ext4_mballoc(); return err; } static void __exit exit_ext4_fs(void) { + unregister_filesystem(&ext4_fs_type); +#ifdef CONFIG_EXT4DEV_COMPAT unregister_filesystem(&ext4dev_fs_type); +#endif destroy_inodecache(); exit_ext4_xattr(); + exit_ext4_mballoc(); + remove_proc_entry("fs/ext4", NULL); } MODULE_AUTHOR("Remy Card, Stephen Tweedie, Andrew Morton, Andreas Dilger, Theodore Ts'o and others");