diff options
Diffstat (limited to 'fs/ext3/super.c')
| -rw-r--r-- | fs/ext3/super.c | 584 |
1 files changed, 345 insertions, 239 deletions
diff --git a/fs/ext3/super.c b/fs/ext3/super.c index 1bee604cc6c..08cdfe5461e 100644 --- a/fs/ext3/super.c +++ b/fs/ext3/super.c @@ -17,29 +17,23 @@ */ #include <linux/module.h> -#include <linux/string.h> -#include <linux/fs.h> -#include <linux/time.h> -#include <linux/jbd.h> -#include <linux/ext3_fs.h> -#include <linux/ext3_jbd.h> -#include <linux/slab.h> -#include <linux/init.h> #include <linux/blkdev.h> #include <linux/parser.h> -#include <linux/smp_lock.h> -#include <linux/buffer_head.h> #include <linux/exportfs.h> -#include <linux/vfs.h> +#include <linux/statfs.h> #include <linux/random.h> #include <linux/mount.h> -#include <linux/namei.h> #include <linux/quotaops.h> #include <linux/seq_file.h> #include <linux/log2.h> +#include <linux/cleancache.h> +#include <linux/namei.h> #include <asm/uaccess.h> +#define CREATE_TRACE_POINTS + +#include "ext3.h" #include "xattr.h" #include "acl.h" #include "namei.h" @@ -71,11 +65,6 @@ static int ext3_freeze(struct super_block *sb); /* * Wrappers for journal_start/end. - * - * The only special thing we need to do here is to make sure that all - * journal_end calls result in the superblock being marked dirty, so - * that sync() will call the filesystem's write_super callback if - * appropriate. */ handle_t *ext3_journal_start_sb(struct super_block *sb, int nblocks) { @@ -97,12 +86,6 @@ handle_t *ext3_journal_start_sb(struct super_block *sb, int nblocks) return journal_start(journal, nblocks); } -/* - * The only special thing we need to do here is to make sure that all - * journal_stop calls result in the superblock being marked dirty, so - * that sync() will call the filesystem's write_super callback if - * appropriate. - */ int __ext3_journal_stop(const char *where, handle_t *handle) { struct super_block *sb; @@ -144,12 +127,16 @@ void ext3_journal_abort_handle(const char *caller, const char *err_fn, void ext3_msg(struct super_block *sb, const char *prefix, const char *fmt, ...) { + struct va_format vaf; va_list args; va_start(args, fmt); - printk("%sEXT3-fs (%s): ", prefix, sb->s_id); - vprintk(fmt, args); - printk("\n"); + + vaf.fmt = fmt; + vaf.va = &args; + + printk("%sEXT3-fs (%s): %pV\n", prefix, sb->s_id, &vaf); + va_end(args); } @@ -188,6 +175,11 @@ static void ext3_handle_error(struct super_block *sb) if (test_opt (sb, ERRORS_RO)) { ext3_msg(sb, KERN_CRIT, "error: remounting filesystem read-only"); + /* + * Make sure updated value of ->s_mount_state will be visible + * before ->s_flags update. + */ + smp_wmb(); sb->s_flags |= MS_RDONLY; } ext3_commit_super(sb, es, 1); @@ -196,15 +188,20 @@ static void ext3_handle_error(struct super_block *sb) sb->s_id); } -void ext3_error (struct super_block * sb, const char * function, - const char * fmt, ...) +void ext3_error(struct super_block *sb, const char *function, + const char *fmt, ...) { + struct va_format vaf; va_list args; va_start(args, fmt); - printk(KERN_CRIT "EXT3-fs error (device %s): %s: ",sb->s_id, function); - vprintk(fmt, args); - printk("\n"); + + vaf.fmt = fmt; + vaf.va = &args; + + printk(KERN_CRIT "EXT3-fs error (device %s): %s: %pV\n", + sb->s_id, function, &vaf); + va_end(args); ext3_handle_error(sb); @@ -275,15 +272,20 @@ void __ext3_std_error (struct super_block * sb, const char * function, * case we take the easy way out and panic immediately. */ -void ext3_abort (struct super_block * sb, const char * function, - const char * fmt, ...) +void ext3_abort(struct super_block *sb, const char *function, + const char *fmt, ...) { + struct va_format vaf; va_list args; va_start(args, fmt); - printk(KERN_CRIT "EXT3-fs (%s): error: %s: ", sb->s_id, function); - vprintk(fmt, args); - printk("\n"); + + vaf.fmt = fmt; + vaf.va = &args; + + printk(KERN_CRIT "EXT3-fs (%s): error: %s: %pV\n", + sb->s_id, function, &vaf); + va_end(args); if (test_opt(sb, ERRORS_PANIC)) @@ -295,22 +297,32 @@ void ext3_abort (struct super_block * sb, const char * function, ext3_msg(sb, KERN_CRIT, "error: remounting filesystem read-only"); EXT3_SB(sb)->s_mount_state |= EXT3_ERROR_FS; - sb->s_flags |= MS_RDONLY; set_opt(EXT3_SB(sb)->s_mount_opt, ABORT); + /* + * Make sure updated value of ->s_mount_state will be visible + * before ->s_flags update. + */ + smp_wmb(); + sb->s_flags |= MS_RDONLY; + if (EXT3_SB(sb)->s_journal) journal_abort(EXT3_SB(sb)->s_journal, -EIO); } -void ext3_warning (struct super_block * sb, const char * function, - const char * fmt, ...) +void ext3_warning(struct super_block *sb, const char *function, + const char *fmt, ...) { + struct va_format vaf; va_list args; va_start(args, fmt); - printk(KERN_WARNING "EXT3-fs (%s): warning: %s: ", - sb->s_id, function); - vprintk(fmt, args); - printk("\n"); + + vaf.fmt = fmt; + vaf.va = &args; + + printk(KERN_WARNING "EXT3-fs (%s): warning: %s: %pV\n", + sb->s_id, function, &vaf); + va_end(args); } @@ -347,13 +359,13 @@ static struct block_device *ext3_blkdev_get(dev_t dev, struct super_block *sb) struct block_device *bdev; char b[BDEVNAME_SIZE]; - bdev = open_by_devnum(dev, FMODE_READ|FMODE_WRITE); + bdev = blkdev_get_by_dev(dev, FMODE_READ|FMODE_WRITE|FMODE_EXCL, sb); if (IS_ERR(bdev)) goto fail; return bdev; fail: - ext3_msg(sb, "error: failed to open journal device %s: %ld", + ext3_msg(sb, KERN_ERR, "error: failed to open journal device %s: %ld", __bdevname(dev, b), PTR_ERR(bdev)); return NULL; @@ -362,23 +374,19 @@ fail: /* * Release the journal device */ -static int ext3_blkdev_put(struct block_device *bdev) +static void ext3_blkdev_put(struct block_device *bdev) { - bd_release(bdev); - return blkdev_put(bdev, FMODE_READ|FMODE_WRITE); + blkdev_put(bdev, FMODE_READ|FMODE_WRITE|FMODE_EXCL); } -static int ext3_blkdev_remove(struct ext3_sb_info *sbi) +static void ext3_blkdev_remove(struct ext3_sb_info *sbi) { struct block_device *bdev; - int ret = -ENODEV; - bdev = sbi->journal_bdev; if (bdev) { - ret = ext3_blkdev_put(bdev); + ext3_blkdev_put(bdev); sbi->journal_bdev = NULL; } - return ret; } static inline struct inode *orphan_list_entry(struct list_head *l) @@ -410,8 +418,7 @@ static void ext3_put_super (struct super_block * sb) struct ext3_super_block *es = sbi->s_es; int i, err; - lock_kernel(); - + dquot_disable(sb, -1, DQUOT_USAGE_ENABLED | DQUOT_LIMITS_ENABLED); ext3_xattr_put_super(sb); err = journal_destroy(sbi->s_journal); sbi->s_journal = NULL; @@ -460,8 +467,6 @@ static void ext3_put_super (struct super_block * sb) sb->s_fs_info = NULL; kfree(sbi->s_blockgroup_lock); kfree(sbi); - - unlock_kernel(); } static struct kmem_cache *ext3_inode_cachep; @@ -483,6 +488,20 @@ static struct inode *ext3_alloc_inode(struct super_block *sb) return &ei->vfs_inode; } +static int ext3_drop_inode(struct inode *inode) +{ + int drop = generic_drop_inode(inode); + + trace_ext3_drop_inode(inode, drop); + return drop; +} + +static void ext3_i_callback(struct rcu_head *head) +{ + struct inode *inode = container_of(head, struct inode, i_rcu); + kmem_cache_free(ext3_inode_cachep, EXT3_I(inode)); +} + static void ext3_destroy_inode(struct inode *inode) { if (!list_empty(&(EXT3_I(inode)->i_orphan))) { @@ -493,7 +512,7 @@ static void ext3_destroy_inode(struct inode *inode) false); dump_stack(); } - kmem_cache_free(ext3_inode_cachep, EXT3_I(inode)); + call_rcu(&inode->i_rcu, ext3_i_callback); } static void init_once(void *foo) @@ -508,7 +527,7 @@ static void init_once(void *foo) inode_init_once(&ei->vfs_inode); } -static int init_inodecache(void) +static int __init init_inodecache(void) { ext3_inode_cachep = kmem_cache_create("ext3_inode_cache", sizeof(struct ext3_inode_info), @@ -522,20 +541,14 @@ static int init_inodecache(void) static void destroy_inodecache(void) { + /* + * Make sure all delayed rcu free inodes are flushed before we + * destroy cache. + */ + rcu_barrier(); kmem_cache_destroy(ext3_inode_cachep); } -static void ext3_clear_inode(struct inode *inode) -{ - struct ext3_block_alloc_info *rsv = EXT3_I(inode)->i_block_alloc_info; - - dquot_drop(inode); - ext3_discard_reservation(inode); - EXT3_I(inode)->i_block_alloc_info = NULL; - if (unlikely(rsv)) - kfree(rsv); -} - static inline void ext3_show_quota_options(struct seq_file *seq, struct super_block *sb) { #if defined(CONFIG_QUOTA) @@ -590,9 +603,9 @@ static char *data_mode_string(unsigned long mode) * - 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) +static int ext3_show_options(struct seq_file *seq, struct dentry *root) { - struct super_block *sb = vfs->mnt_sb; + struct super_block *sb = root->d_sb; struct ext3_sb_info *sbi = EXT3_SB(sb); struct ext3_super_block *es = sbi->s_es; unsigned long def_mount_opts; @@ -607,13 +620,15 @@ static int ext3_show_options(struct seq_file *seq, struct vfsmount *vfs) 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 || + if (!uid_eq(sbi->s_resuid, make_kuid(&init_user_ns, EXT3_DEF_RESUID)) || le16_to_cpu(es->s_def_resuid) != EXT3_DEF_RESUID) { - seq_printf(seq, ",resuid=%u", sbi->s_resuid); + seq_printf(seq, ",resuid=%u", + from_kuid_munged(&init_user_ns, sbi->s_resuid)); } - if (sbi->s_resgid != EXT3_DEF_RESGID || + if (!gid_eq(sbi->s_resgid, make_kgid(&init_user_ns, EXT3_DEF_RESGID)) || le16_to_cpu(es->s_def_resgid) != EXT3_DEF_RESGID) { - seq_printf(seq, ",resgid=%u", sbi->s_resgid); + seq_printf(seq, ",resgid=%u", + from_kgid_munged(&init_user_ns, sbi->s_resgid)); } if (test_opt(sb, ERRORS_RO)) { int def_errors = le16_to_cpu(es->s_errors); @@ -631,8 +646,6 @@ static int ext3_show_options(struct seq_file *seq, struct vfsmount *vfs) 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"); @@ -653,11 +666,12 @@ static int ext3_show_options(struct seq_file *seq, struct vfsmount *vfs) 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"); + /* + * Always display barrier state so it's clear what the status is. + */ + seq_puts(seq, ",barrier="); + seq_puts(seq, test_opt(sb, BARRIER) ? "1" : "0"); seq_printf(seq, ",data=%s", data_mode_string(test_opt(sb, DATA_FLAGS))); if (test_opt(sb, DATA_ERR_ABORT)) seq_puts(seq, ",data_err=abort"); @@ -744,7 +758,7 @@ 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, int remount); + struct path *path); 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); @@ -763,12 +777,12 @@ static const struct dquot_operations ext3_quota_operations = { static const struct quotactl_ops ext3_qctl_operations = { .quota_on = ext3_quota_on, - .quota_off = vfs_quota_off, - .quota_sync = vfs_quota_sync, - .get_info = vfs_get_dqinfo, - .set_info = vfs_set_dqinfo, - .get_dqblk = vfs_get_dqblk, - .set_dqblk = vfs_set_dqblk + .quota_off = dquot_quota_off, + .quota_sync = dquot_quota_sync, + .get_info = dquot_get_dqinfo, + .set_info = dquot_set_dqinfo, + .get_dqblk = dquot_get_dqblk, + .set_dqblk = dquot_set_dqblk }; #endif @@ -777,14 +791,14 @@ static const struct super_operations ext3_sops = { .destroy_inode = ext3_destroy_inode, .write_inode = ext3_write_inode, .dirty_inode = ext3_dirty_inode, - .delete_inode = ext3_delete_inode, + .drop_inode = ext3_drop_inode, + .evict_inode = ext3_evict_inode, .put_super = ext3_put_super, .sync_fs = ext3_sync_fs, .freeze_fs = ext3_freeze, .unfreeze_fs = ext3_unfreeze, .statfs = ext3_statfs, .remount_fs = ext3_remount, - .clear_inode = ext3_clear_inode, .show_options = ext3_show_options, #ifdef CONFIG_QUOTA .quota_read = ext3_quota_read, @@ -806,12 +820,13 @@ 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_path, 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_jqfmt_vfsv1, Opt_quota, - Opt_noquota, Opt_ignore, Opt_barrier, Opt_err, Opt_resize, - Opt_usrquota, Opt_grpquota + Opt_noquota, Opt_ignore, Opt_barrier, Opt_nobarrier, Opt_err, + Opt_resize, Opt_usrquota, Opt_grpquota }; static const match_table_t tokens = { @@ -847,6 +862,7 @@ static const match_table_t tokens = { {Opt_journal_update, "journal=update"}, {Opt_journal_inum, "journal=%u"}, {Opt_journal_dev, "journal_dev=%u"}, + {Opt_journal_path, "journal_path=%s"}, {Opt_abort, "abort"}, {Opt_data_journal, "data=journal"}, {Opt_data_ordered, "data=ordered"}, @@ -865,6 +881,8 @@ static const match_table_t tokens = { {Opt_quota, "quota"}, {Opt_usrquota, "usrquota"}, {Opt_barrier, "barrier=%u"}, + {Opt_barrier, "barrier"}, + {Opt_nobarrier, "nobarrier"}, {Opt_resize, "resize"}, {Opt_err, NULL}, }; @@ -880,7 +898,7 @@ static ext3_fsblk_t get_sb_block(void **data, struct super_block *sb) /*todo: use simple_strtoll with >32bit ext3 */ sb_block = simple_strtoul(options, &options, 0); if (*options && *options != ',') { - ext3_msg(sb, "error: invalid sb specification: %s", + ext3_msg(sb, KERN_ERR, "error: invalid sb specification: %s", (char *) *data); return 1; } @@ -909,21 +927,24 @@ static int set_qf_name(struct super_block *sb, int qtype, substring_t *args) "Not enough memory for storing quotafile name"); return 0; } - if (sbi->s_qf_names[qtype] && - strcmp(sbi->s_qf_names[qtype], qname)) { - ext3_msg(sb, KERN_ERR, - "%s quota file already specified", QTYPE2NAME(qtype)); + if (sbi->s_qf_names[qtype]) { + int same = !strcmp(sbi->s_qf_names[qtype], qname); + kfree(qname); - return 0; + if (!same) { + ext3_msg(sb, KERN_ERR, + "%s quota file already specified", + QTYPE2NAME(qtype)); + } + return same; } - sbi->s_qf_names[qtype] = qname; - if (strchr(sbi->s_qf_names[qtype], '/')) { + if (strchr(qname, '/')) { ext3_msg(sb, KERN_ERR, "quotafile must be on filesystem root"); - kfree(sbi->s_qf_names[qtype]); - sbi->s_qf_names[qtype] = NULL; + kfree(qname); return 0; } + sbi->s_qf_names[qtype] = qname; set_opt(sbi->s_mount_opt, QUOTA); return 1; } @@ -938,11 +959,10 @@ static int clear_qf_name(struct super_block *sb, int qtype) { " when quota turned on"); return 0; } - /* - * The space will be released later when all options are confirmed - * to be correct - */ - sbi->s_qf_names[qtype] = NULL; + if (sbi->s_qf_names[qtype]) { + kfree(sbi->s_qf_names[qtype]); + sbi->s_qf_names[qtype] = NULL; + } return 1; } #endif @@ -956,6 +976,13 @@ static int parse_options (char *options, struct super_block *sb, substring_t args[MAX_OPT_ARGS]; int data_opt = 0; int option; + kuid_t uid; + kgid_t gid; + char *journal_path; + struct inode *journal_inode; + struct path path; + int error; + #ifdef CONFIG_QUOTA int qfmt; #endif @@ -967,7 +994,11 @@ static int parse_options (char *options, struct super_block *sb, int token; if (!*p) continue; - + /* + * Initialize args struct so we know whether arg was + * found; some options take optional arguments. + */ + args[0].to = args[0].from = NULL; token = match_token(p, tokens, args); switch (token) { case Opt_bsd_df: @@ -985,12 +1016,23 @@ static int parse_options (char *options, struct super_block *sb, case Opt_resuid: if (match_int(&args[0], &option)) return 0; - sbi->s_resuid = option; + uid = make_kuid(current_user_ns(), option); + if (!uid_valid(uid)) { + ext3_msg(sb, KERN_ERR, "Invalid uid value %d", option); + return 0; + + } + sbi->s_resuid = uid; break; case Opt_resgid: if (match_int(&args[0], &option)) return 0; - sbi->s_resgid = option; + gid = make_kgid(current_user_ns(), option); + if (!gid_valid(gid)) { + ext3_msg(sb, KERN_ERR, "Invalid gid value %d", option); + return 0; + } + sbi->s_resgid = gid; break; case Opt_sb: /* handled by get_sb_block() instead of here */ @@ -1021,10 +1063,12 @@ static int parse_options (char *options, struct super_block *sb, set_opt (sbi->s_mount_opt, DEBUG); break; case Opt_oldalloc: - set_opt (sbi->s_mount_opt, OLDALLOC); + ext3_msg(sb, KERN_WARNING, + "Ignoring deprecated oldalloc option"); break; case Opt_orlov: - clear_opt (sbi->s_mount_opt, OLDALLOC); + ext3_msg(sb, KERN_WARNING, + "Ignoring deprecated orlov option"); break; #ifdef CONFIG_EXT3_FS_XATTR case Opt_user_xattr: @@ -1093,6 +1137,41 @@ static int parse_options (char *options, struct super_block *sb, return 0; *journal_devnum = option; break; + case Opt_journal_path: + if (is_remount) { + ext3_msg(sb, KERN_ERR, "error: cannot specify " + "journal on remount"); + return 0; + } + + journal_path = match_strdup(&args[0]); + if (!journal_path) { + ext3_msg(sb, KERN_ERR, "error: could not dup " + "journal device string"); + return 0; + } + + error = kern_path(journal_path, LOOKUP_FOLLOW, &path); + if (error) { + ext3_msg(sb, KERN_ERR, "error: could not find " + "journal device path: error %d", error); + kfree(journal_path); + return 0; + } + + journal_inode = path.dentry->d_inode; + if (!S_ISBLK(journal_inode->i_mode)) { + ext3_msg(sb, KERN_ERR, "error: journal path %s " + "is not a block device", journal_path); + path_put(&path); + kfree(journal_path); + return 0; + } + + *journal_devnum = new_encode_dev(journal_inode->i_rdev); + path_put(&path); + kfree(journal_path); + break; case Opt_noload: set_opt (sbi->s_mount_opt, NOLOAD); break; @@ -1215,9 +1294,15 @@ set_qf_format: case Opt_abort: set_opt(sbi->s_mount_opt, ABORT); break; + case Opt_nobarrier: + clear_opt(sbi->s_mount_opt, BARRIER); + break; case Opt_barrier: - if (match_int(&args[0], &option)) - return 0; + if (args[0].from) { + if (match_int(&args[0], &option)) + return 0; + } else + option = 1; /* No argument, default to 1 */ if (option) set_opt(sbi->s_mount_opt, BARRIER); else @@ -1237,10 +1322,12 @@ set_qf_format: *n_blocks_count = option; break; case Opt_nobh: - set_opt(sbi->s_mount_opt, NOBH); + ext3_msg(sb, KERN_WARNING, + "warning: ignoring deprecated nobh option"); break; case Opt_bh: - clear_opt(sbi->s_mount_opt, NOBH); + ext3_msg(sb, KERN_WARNING, + "warning: ignoring deprecated bh option"); break; default: ext3_msg(sb, KERN_ERR, @@ -1301,9 +1388,9 @@ static int ext3_setup_super(struct super_block *sb, struct ext3_super_block *es, 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 && + 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)) + le16_to_cpu(es->s_max_mnt_count)) ext3_msg(sb, KERN_WARNING, "warning: maximal mount count reached, " "running e2fsck is recommended"); @@ -1320,7 +1407,7 @@ static int ext3_setup_super(struct super_block *sb, struct ext3_super_block *es, valid forever! :) */ es->s_state &= cpu_to_le16(~EXT3_VALID_FS); #endif - if (!(__s16) le16_to_cpu(es->s_max_mnt_count)) + if (!le16_to_cpu(es->s_max_mnt_count)) es->s_max_mnt_count = cpu_to_le16(EXT3_DFL_MAX_MNT_COUNT); le16_add_cpu(&es->s_mnt_count, 1); es->s_mtime = cpu_to_le32(get_seconds()); @@ -1344,6 +1431,7 @@ static int ext3_setup_super(struct super_block *sb, struct ext3_super_block *es, } else { ext3_msg(sb, KERN_INFO, "using internal journal"); } + cleancache_init_fs(sb); return res; } @@ -1441,11 +1529,20 @@ static void ext3_orphan_cleanup (struct super_block * sb, return; } + /* Check if feature set allows readwrite operations */ + if (EXT3_HAS_RO_COMPAT_FEATURE(sb, ~EXT3_FEATURE_RO_COMPAT_SUPP)) { + ext3_msg(sb, KERN_INFO, "Skipping orphan cleanup due to " + "unknown ROCOMPAT features"); + return; + } + if (EXT3_SB(sb)->s_mount_state & EXT3_ERROR_FS) { - if (es->s_last_orphan) + /* don't clear list on RO mount w/ errors */ + if (es->s_last_orphan && !(s_flags & MS_RDONLY)) { jbd_debug(1, "Errors on filesystem, " "clearing orphan list.\n"); - es->s_last_orphan = 0; + es->s_last_orphan = 0; + } jbd_debug(1, "Skipping orphan recovery on fs with errors.\n"); return; } @@ -1511,7 +1608,7 @@ static void ext3_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, 0); + dquot_quota_off(sb, i); } #endif sb->s_flags = s_flags; /* Restore MS_RDONLY status */ @@ -1617,13 +1714,8 @@ static int ext3_fill_super (struct super_block *sb, void *data, int silent) 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) { ext3_msg(sb, KERN_ERR, "error: unable to set blocksize"); @@ -1649,7 +1741,7 @@ static int ext3_fill_super (struct super_block *sb, void *data, int silent) * Note: s_es must be initialized as soon as possible because * some ext3 macro-instructions depend on its value */ - es = (struct ext3_super_block *) (((char *)bh->b_data) + offset); + es = (struct ext3_super_block *) (bh->b_data + offset); sbi->s_es = es; sb->s_magic = le16_to_cpu(es->s_magic); if (sb->s_magic != EXT3_SUPER_MAGIC) @@ -1685,9 +1777,11 @@ static int ext3_fill_super (struct super_block *sb, void *data, int silent) 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); + sbi->s_resuid = make_kuid(&init_user_ns, le16_to_cpu(es->s_def_resuid)); + sbi->s_resgid = make_kgid(&init_user_ns, le16_to_cpu(es->s_def_resgid)); + /* enable barriers by default */ + set_opt(sbi->s_mount_opt, BARRIER); set_opt(sbi->s_mount_opt, RESERVATION); if (!parse_options ((char *) data, sb, &journal_inum, &journal_devnum, @@ -1760,7 +1854,7 @@ static int ext3_fill_super (struct super_block *sb, void *data, int silent) "error: can't read superblock on 2nd try"); goto failed_mount; } - es = (struct ext3_super_block *)(((char *)bh->b_data) + offset); + es = (struct ext3_super_block *)(bh->b_data + offset); sbi->s_es = es; if (es->s_magic != cpu_to_le16(EXT3_SUPER_MAGIC)) { ext3_msg(sb, KERN_ERR, @@ -1844,13 +1938,15 @@ static int ext3_fill_super (struct super_block *sb, void *data, int silent) goto failed_mount; } - if (le32_to_cpu(es->s_blocks_count) > - (sector_t)(~0ULL) >> (sb->s_blocksize_bits - 9)) { + err = generic_check_addressable(sb->s_blocksize_bits, + le32_to_cpu(es->s_blocks_count)); + if (err) { ext3_msg(sb, KERN_ERR, "error: filesystem is too large to mount safely"); if (sizeof(sector_t) < 8) ext3_msg(sb, KERN_ERR, "error: CONFIG_LBDAF not enabled"); + ret = err; goto failed_mount; } @@ -1859,13 +1955,13 @@ static int ext3_fill_super (struct super_block *sb, void *data, int silent) sbi->s_groups_count = ((le32_to_cpu(es->s_blocks_count) - le32_to_cpu(es->s_first_data_block) - 1) / EXT3_BLOCKS_PER_GROUP(sb)) + 1; - db_count = (sbi->s_groups_count + EXT3_DESC_PER_BLOCK(sb) - 1) / - EXT3_DESC_PER_BLOCK(sb); + db_count = DIV_ROUND_UP(sbi->s_groups_count, EXT3_DESC_PER_BLOCK(sb)); sbi->s_group_desc = kmalloc(db_count * sizeof (struct buffer_head *), GFP_KERNEL); if (sbi->s_group_desc == NULL) { ext3_msg(sb, KERN_ERR, "error: not enough memory"); + ret = -ENOMEM; goto failed_mount; } @@ -1890,21 +1986,6 @@ static int ext3_fill_super (struct super_block *sb, void *data, int silent) get_random_bytes(&sbi->s_next_generation, sizeof(u32)); spin_lock_init(&sbi->s_next_gen_lock); - 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); sbi->s_rsv_window_root = RB_ROOT; @@ -1928,6 +2009,7 @@ static int ext3_fill_super (struct super_block *sb, void *data, int silent) sb->s_qcop = &ext3_qctl_operations; sb->dq_op = &ext3_quota_operations; #endif + memcpy(sb->s_uuid, es->s_uuid, sizeof(es->s_uuid)); INIT_LIST_HEAD(&sbi->s_orphan); /* unlinked but open files */ mutex_init(&sbi->s_orphan_lock); mutex_init(&sbi->s_resize_lock); @@ -1945,15 +2027,30 @@ static int ext3_fill_super (struct super_block *sb, void *data, int silent) if (!test_opt(sb, NOLOAD) && EXT3_HAS_COMPAT_FEATURE(sb, EXT3_FEATURE_COMPAT_HAS_JOURNAL)) { if (ext3_load_journal(sb, es, journal_devnum)) - goto failed_mount3; + goto failed_mount2; } else if (journal_inum) { if (ext3_create_journal(sb, es, journal_inum)) - goto failed_mount3; + goto failed_mount2; } else { if (!silent) ext3_msg(sb, KERN_ERR, "error: no journal found. " "mounting ext3 over ext2?"); + goto failed_mount2; + } + 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"); + ret = err; goto failed_mount3; } @@ -1978,20 +2075,12 @@ static int ext3_fill_super (struct super_block *sb, void *data, int silent) ext3_msg(sb, KERN_ERR, "error: journal does not support " "requested data journaling mode"); - goto failed_mount4; + goto failed_mount3; } default: break; } - if (test_opt(sb, NOBH)) { - if (!(test_opt(sb, DATA_FLAGS) == EXT3_MOUNT_WRITEBACK_DATA)) { - ext3_msg(sb, KERN_WARNING, - "warning: ignoring nobh option - " - "it is supported only with writeback mode"); - clear_opt(sbi->s_mount_opt, NOBH); - } - } /* * The journal_load will have done any necessary log recovery, * so we can safely mount the rest of the filesystem now. @@ -2001,35 +2090,35 @@ static int ext3_fill_super (struct super_block *sb, void *data, int silent) if (IS_ERR(root)) { ext3_msg(sb, KERN_ERR, "error: get root inode failed"); ret = PTR_ERR(root); - goto failed_mount4; + goto failed_mount3; } if (!S_ISDIR(root->i_mode) || !root->i_blocks || !root->i_size) { iput(root); ext3_msg(sb, KERN_ERR, "error: corrupt root inode, run e2fsck"); - goto failed_mount4; + goto failed_mount3; } - sb->s_root = d_alloc_root(root); + sb->s_root = d_make_root(root); if (!sb->s_root) { ext3_msg(sb, KERN_ERR, "error: get root dentry failed"); - iput(root); ret = -ENOMEM; - goto failed_mount4; + goto failed_mount3; } - ext3_setup_super (sb, es, sb->s_flags & MS_RDONLY); + if (ext3_setup_super(sb, es, sb->s_flags & MS_RDONLY)) + sb->s_flags |= MS_RDONLY; 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) + if (needs_recovery) { + ext3_mark_recovery_complete(sb, es); ext3_msg(sb, KERN_INFO, "recovery complete"); - ext3_mark_recovery_complete(sb, es); + } 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"); - lock_kernel(); return 0; cantfind_ext3: @@ -2039,12 +2128,11 @@ cantfind_ext3: sb->s_id); goto failed_mount; -failed_mount4: - journal_destroy(sbi->s_journal); failed_mount3: percpu_counter_destroy(&sbi->s_freeblocks_counter); percpu_counter_destroy(&sbi->s_freeinodes_counter); percpu_counter_destroy(&sbi->s_dirs_counter); + journal_destroy(sbi->s_journal); failed_mount2: for (i = 0; i < db_count; i++) brelse(sbi->s_group_desc[i]); @@ -2060,7 +2148,6 @@ out_fail: sb->s_fs_info = NULL; kfree(sbi->s_blockgroup_lock); kfree(sbi); - lock_kernel(); return ret; } @@ -2149,13 +2236,6 @@ static journal_t *ext3_get_dev_journal(struct super_block *sb, if (bdev == NULL) return NULL; - if (bd_claim(bdev, sb)) { - 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_logical_block_size(bdev); if (blocksize < hblock) { @@ -2173,7 +2253,7 @@ static journal_t *ext3_get_dev_journal(struct super_block *sb, goto out_bdev; } - es = (struct ext3_super_block *) (((char *)bh->b_data) + offset); + es = (struct ext3_super_block *) (bh->b_data + offset); if ((le16_to_cpu(es->s_magic) != EXT3_SUPER_MAGIC) || !(le32_to_cpu(es->s_feature_incompat) & EXT3_FEATURE_INCOMPAT_JOURNAL_DEV)) { @@ -2201,11 +2281,11 @@ static journal_t *ext3_get_dev_journal(struct super_block *sb, 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)) { - ext3_msg(sb, KERN_ERR, "I/O error on journal device"); - goto out_journal; + if (!bh_uptodate_or_lock(journal->j_sb_buffer)) { + if (bh_submit_read(journal->j_sb_buffer)) { + 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) { ext3_msg(sb, KERN_ERR, @@ -2278,6 +2358,9 @@ static int ext3_load_journal(struct super_block *sb, return -EINVAL; } + if (!(journal->j_flags & JFS_BARRIER)) + printk(KERN_INFO "EXT3-fs: barriers not enabled\n"); + if (!really_read_only && test_opt(sb, UPDATE_JOURNAL)) { err = journal_update_format(journal); if (err) { @@ -2301,7 +2384,7 @@ static int ext3_load_journal(struct super_block *sb, EXT3_SB(sb)->s_journal = journal; ext3_clear_journal_err(sb, es); - if (journal_devnum && + if (!really_read_only && journal_devnum && journal_devnum != le32_to_cpu(es->s_journal_dev)) { es->s_journal_dev = cpu_to_le32(journal_devnum); @@ -2363,6 +2446,21 @@ static int ext3_commit_super(struct super_block *sb, if (!sbh) return error; + + 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. + */ + ext3_msg(sb, KERN_ERR, "previous I/O error to " + "superblock detected"); + clear_buffer_write_io_error(sbh); + set_buffer_uptodate(sbh); + } /* * If the file system is mounted read-only, don't update the * superblock write time. This avoids updating the superblock @@ -2379,8 +2477,15 @@ static int ext3_commit_super(struct super_block *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) + if (sync) { error = sync_dirty_buffer(sbh); + if (buffer_write_io_error(sbh)) { + ext3_msg(sb, KERN_ERR, "I/O error while writing " + "superblock"); + clear_buffer_write_io_error(sbh); + set_buffer_uptodate(sbh); + } + } return error; } @@ -2467,6 +2572,12 @@ static int ext3_sync_fs(struct super_block *sb, int wait) { tid_t target; + trace_ext3_sync_fs(sb, wait); + /* + * Writeback quota in non-journalled quota case - journalled quota has + * no dirty dquots + */ + dquot_writeback_dquots(sb, -1); if (journal_start_commit(EXT3_SB(sb)->s_journal, &target)) { if (wait) log_wait_commit(EXT3_SB(sb)->s_journal, target); @@ -2517,11 +2628,9 @@ out: static int ext3_unfreeze(struct super_block *sb) { if (!(sb->s_flags & MS_RDONLY)) { - lock_super(sb); /* Reser the needs_recovery flag before the fs is unlocked. */ EXT3_SET_INCOMPAT_FEATURE(sb, EXT3_FEATURE_INCOMPAT_RECOVER); ext3_commit_super(sb, EXT3_SB(sb)->s_es, 1); - unlock_super(sb); journal_unlock_updates(EXT3_SB(sb)->s_journal); } return 0; @@ -2534,15 +2643,15 @@ static int ext3_remount (struct super_block * sb, int * flags, char * data) ext3_fsblk_t n_blocks_count = 0; unsigned long old_sb_flags; struct ext3_mount_options old_opts; + int enable_quota = 0; int err; #ifdef CONFIG_QUOTA int i; #endif - lock_kernel(); + sync_filesystem(sb); /* 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; @@ -2551,7 +2660,18 @@ static int ext3_remount (struct super_block * sb, int * flags, char * data) #ifdef CONFIG_QUOTA old_opts.s_jquota_fmt = sbi->s_jquota_fmt; for (i = 0; i < MAXQUOTAS; i++) - old_opts.s_qf_names[i] = sbi->s_qf_names[i]; + if (sbi->s_qf_names[i]) { + old_opts.s_qf_names[i] = kstrdup(sbi->s_qf_names[i], + GFP_KERNEL); + if (!old_opts.s_qf_names[i]) { + int j; + + for (j = 0; j < i; j++) + kfree(old_opts.s_qf_names[j]); + return -ENOMEM; + } + } else + old_opts.s_qf_names[i] = NULL; #endif /* @@ -2580,6 +2700,10 @@ static int ext3_remount (struct super_block * sb, int * flags, char * data) } if (*flags & MS_RDONLY) { + err = dquot_suspend(sb, -1); + if (err < 0) + goto restore_opts; + /* * First of all, the unconditional stuff we have to do * to disable replay of the journal when we next remount @@ -2611,13 +2735,13 @@ static int ext3_remount (struct super_block * sb, int * flags, char * data) /* * If we have an unprocessed orphan list hanging * around from a previously readonly bdev mount, - * require a full umount/remount for now. + * require a full umount & mount 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."); + "umount & mount instead."); err = -EINVAL; goto restore_opts; } @@ -2634,17 +2758,16 @@ static int ext3_remount (struct super_block * sb, int * flags, char * data) goto restore_opts; if (!ext3_setup_super (sb, es, 0)) sb->s_flags &= ~MS_RDONLY; + enable_quota = 1; } } #ifdef CONFIG_QUOTA /* Release old quota file names */ for (i = 0; i < MAXQUOTAS; i++) - if (old_opts.s_qf_names[i] && - old_opts.s_qf_names[i] != sbi->s_qf_names[i]) - kfree(old_opts.s_qf_names[i]); + kfree(old_opts.s_qf_names[i]); #endif - unlock_super(sb); - unlock_kernel(); + if (enable_quota) + dquot_resume(sb, -1); return 0; restore_opts: sb->s_flags = old_sb_flags; @@ -2655,14 +2778,10 @@ restore_opts: #ifdef CONFIG_QUOTA sbi->s_jquota_fmt = old_opts.s_jquota_fmt; for (i = 0; i < MAXQUOTAS; i++) { - if (sbi->s_qf_names[i] && - old_opts.s_qf_names[i] != sbi->s_qf_names[i]) - kfree(sbi->s_qf_names[i]); + kfree(sbi->s_qf_names[i]); sbi->s_qf_names[i] = old_opts.s_qf_names[i]; } #endif - unlock_super(sb); - unlock_kernel(); return err; } @@ -2708,6 +2827,10 @@ static int ext3_statfs (struct dentry * dentry, struct kstatfs * buf) * bitmap, and an inode table. */ overhead += ngroups * (2 + sbi->s_itb_per_group); + + /* Add the journal blocks as well */ + overhead += sbi->s_journal->j_maxlen; + sbi->s_overhead_last = overhead; smp_wmb(); sbi->s_blocks_last = le32_to_cpu(es->s_blocks_count); @@ -2744,7 +2867,7 @@ static int ext3_statfs (struct dentry * dentry, struct kstatfs * buf) static inline struct inode *dquot_to_inode(struct dquot *dquot) { - return sb_dqopt(dquot->dq_sb)->files[dquot->dq_type]; + return sb_dqopt(dquot->dq_sb)->files[dquot->dq_id.type]; } static int ext3_write_dquot(struct dquot *dquot) @@ -2834,38 +2957,28 @@ static int ext3_write_info(struct super_block *sb, int type) */ static int ext3_quota_on_mount(struct super_block *sb, int type) { - return vfs_quota_on_mount(sb, EXT3_SB(sb)->s_qf_names[type], - EXT3_SB(sb)->s_jquota_fmt, type); + return dquot_quota_on_mount(sb, EXT3_SB(sb)->s_qf_names[type], + EXT3_SB(sb)->s_jquota_fmt, type); } /* * Standard function to be called on quota_on */ static int ext3_quota_on(struct super_block *sb, int type, int format_id, - char *name, int remount) + struct path *path) { int err; - struct path path; if (!test_opt(sb, QUOTA)) return -EINVAL; - /* 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 (path.mnt->mnt_sb != sb) { - path_put(&path); + if (path->dentry->d_sb != sb) return -EXDEV; - } /* Journaling quota? */ if (EXT3_SB(sb)->s_qf_names[type]) { /* Quotafile not of fs root? */ - if (path.dentry->d_parent != sb->s_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."); @@ -2875,7 +2988,7 @@ static int ext3_quota_on(struct super_block *sb, int type, int format_id, * 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)) { + if (ext3_should_journal_data(path->dentry->d_inode)) { /* * We don't need to lock updates but journal_flush() could * otherwise be livelocked... @@ -2883,20 +2996,16 @@ static int ext3_quota_on(struct super_block *sb, int type, int format_id, 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); + if (err) return err; - } } - err = vfs_quota_on_path(sb, type, format_id, &path); - path_put(&path); - return err; + return dquot_quota_on(sb, type, format_id, path); } /* Read data from quotafile - avoid pagecache and such because we cannot afford * acquiring the locks... As quota files are never truncated and quota code - * itself serializes the operations (and noone else should touch the files) + * itself serializes the operations (and no one else should touch the files) * we don't have to be afraid of races */ static ssize_t ext3_quota_read(struct super_block *sb, int type, char *data, size_t len, loff_t off) @@ -2965,7 +3074,6 @@ static ssize_t ext3_quota_write(struct super_block *sb, int type, (unsigned long long)off, (unsigned long long)len); return -EIO; } - mutex_lock_nested(&inode->i_mutex, I_MUTEX_QUOTA); bh = ext3_bread(handle, inode, blk, 1, &err); if (!bh) goto out; @@ -2989,10 +3097,8 @@ static ssize_t ext3_quota_write(struct super_block *sb, int type, } brelse(bh); out: - if (err) { - mutex_unlock(&inode->i_mutex); + if (err) return err; - } if (inode->i_size < off + len) { i_size_write(inode, off + len); EXT3_I(inode)->i_disksize = inode->i_size; @@ -3000,25 +3106,25 @@ out: inode->i_version++; inode->i_mtime = inode->i_ctime = CURRENT_TIME; ext3_mark_inode_dirty(handle, inode); - mutex_unlock(&inode->i_mutex); return len; } #endif -static int ext3_get_sb(struct file_system_type *fs_type, - int flags, const char *dev_name, void *data, struct vfsmount *mnt) +static struct dentry *ext3_mount(struct file_system_type *fs_type, + int flags, const char *dev_name, void *data) { - return get_sb_bdev(fs_type, flags, dev_name, data, ext3_fill_super, mnt); + return mount_bdev(fs_type, flags, dev_name, data, ext3_fill_super); } static struct file_system_type ext3_fs_type = { .owner = THIS_MODULE, .name = "ext3", - .get_sb = ext3_get_sb, + .mount = ext3_mount, .kill_sb = kill_block_super, .fs_flags = FS_REQUIRES_DEV, }; +MODULE_ALIAS_FS("ext3"); static int __init init_ext3_fs(void) { |