* David S. Miller (davem@caip.rutgers.edu), 1995
*/
-#include <linux/config.h>
#include <linux/module.h>
#include <linux/string.h>
#include <linux/fs.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/random.h>
#include <linux/mount.h>
#include <linux/namei.h>
#include <linux/quotaops.h>
#include <linux/seq_file.h>
+#include <linux/log2.h>
#include <asm/uaccess.h>
static int ext3_load_journal(struct super_block *, struct ext3_super_block *,
unsigned long journal_devnum);
static int ext3_create_journal(struct super_block *, struct ext3_super_block *,
- int);
-static void ext3_commit_super (struct super_block * sb,
- struct ext3_super_block * es,
+ unsigned int);
+static int ext3_commit_super(struct super_block *sb,
+ struct ext3_super_block *es,
int sync);
static void ext3_mark_recovery_complete(struct super_block * sb,
struct ext3_super_block * es);
static const char *ext3_decode_error(struct super_block * sb, int errno,
char nbuf[16]);
static int ext3_remount (struct super_block * sb, int * flags, char * data);
-static int ext3_statfs (struct super_block * sb, struct kstatfs * buf);
-static void ext3_unlockfs(struct super_block *sb);
+static int ext3_statfs (struct dentry * dentry, struct kstatfs * buf);
+static int ext3_unfreeze(struct super_block *sb);
static void ext3_write_super (struct super_block * sb);
-static void ext3_write_super_lockfs(struct super_block *sb);
+static int ext3_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.
+ * appropriate.
*/
handle_t *ext3_journal_start_sb(struct super_block *sb, int nblocks)
{
* take the FS itself readonly cleanly. */
journal = EXT3_SB(sb)->s_journal;
if (is_journal_aborted(journal)) {
- ext3_abort(sb, __FUNCTION__,
+ ext3_abort(sb, __func__,
"Detected aborted journal");
return ERR_PTR(-EROFS);
}
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.
+ * appropriate.
*/
int __ext3_journal_stop(const char *where, handle_t *handle)
{
if (sb->s_flags & MS_RDONLY)
return;
- if (test_opt (sb, ERRORS_RO)) {
- printk (KERN_CRIT "Remounting filesystem read-only\n");
- sb->s_flags |= MS_RDONLY;
- } else {
+ if (!test_opt (sb, ERRORS_CONT)) {
journal_t *journal = EXT3_SB(sb)->s_journal;
EXT3_SB(sb)->s_mount_opt |= EXT3_MOUNT_ABORT;
if (journal)
journal_abort(journal, -EIO);
}
+ if (test_opt (sb, ERRORS_RO)) {
+ printk (KERN_CRIT "Remounting filesystem read-only\n");
+ sb->s_flags |= MS_RDONLY;
+ }
+ ext3_commit_super(sb, es, 1);
if (test_opt(sb, ERRORS_PANIC))
panic("EXT3-fs (device %s): panic forced after error\n",
sb->s_id);
- ext3_commit_super(sb, es, 1);
}
void ext3_error (struct super_block * sb, const char * function,
EXT3_SB(sb)->s_mount_state |= EXT3_ERROR_FS;
sb->s_flags |= MS_RDONLY;
EXT3_SB(sb)->s_mount_opt |= EXT3_MOUNT_ABORT;
- journal_abort(EXT3_SB(sb)->s_journal, -EIO);
+ if (EXT3_SB(sb)->s_journal)
+ journal_abort(EXT3_SB(sb)->s_journal, -EIO);
}
void ext3_warning (struct super_block * sb, const char * function,
if (le32_to_cpu(es->s_rev_level) > EXT3_GOOD_OLD_REV)
return;
- ext3_warning(sb, __FUNCTION__,
+ ext3_warning(sb, __func__,
"updating to rev %d because of new feature flag, "
"running e2fsck is recommended",
EXT3_DYNAMIC_REV);
static int ext3_blkdev_put(struct block_device *bdev)
{
bd_release(bdev);
- return blkdev_put(bdev);
+ return blkdev_put(bdev, FMODE_READ|FMODE_WRITE);
}
static int ext3_blkdev_remove(struct ext3_sb_info *sbi)
{
struct list_head *l;
- printk(KERN_ERR "sb orphan head is %d\n",
+ printk(KERN_ERR "sb orphan head is %d\n",
le32_to_cpu(sbi->s_es->s_last_orphan));
printk(KERN_ERR "sb_info orphan list:\n");
list_for_each(l, &sbi->s_orphan) {
struct inode *inode = orphan_list_entry(l);
printk(KERN_ERR " "
- "inode %s:%ld at %p: mode %o, nlink %d, next %d\n",
+ "inode %s:%lu at %p: mode %o, nlink %d, next %d\n",
inode->i_sb->s_id, inode->i_ino, inode,
- inode->i_mode, inode->i_nlink,
+ inode->i_mode, inode->i_nlink,
NEXT_ORPHAN(inode));
}
}
{
struct ext3_sb_info *sbi = EXT3_SB(sb);
struct ext3_super_block *es = sbi->s_es;
- int i;
+ int i, err;
ext3_xattr_put_super(sb);
- journal_destroy(sbi->s_journal);
+ err = journal_destroy(sbi->s_journal);
+ sbi->s_journal = NULL;
+ if (err < 0)
+ ext3_abort(sb, __func__, "Couldn't clean up the journal");
+
if (!(sb->s_flags & MS_RDONLY)) {
EXT3_CLEAR_INCOMPAT_FEATURE(sb, EXT3_FEATURE_INCOMPAT_RECOVER);
es->s_state = cpu_to_le16(sbi->s_mount_state);
dump_orphan_list(sb, sbi);
J_ASSERT(list_empty(&sbi->s_orphan));
- invalidate_bdev(sb->s_bdev, 0);
+ invalidate_bdev(sb->s_bdev);
if (sbi->journal_bdev && sbi->journal_bdev != sb->s_bdev) {
/*
* Invalidate the journal device's buffers. We don't want them
* hotswapped, and it breaks the `ro-after' testing code.
*/
sync_blockdev(sbi->journal_bdev);
- invalidate_bdev(sbi->journal_bdev, 0);
+ invalidate_bdev(sbi->journal_bdev);
ext3_blkdev_remove(sbi);
}
sb->s_fs_info = NULL;
+ kfree(sbi->s_blockgroup_lock);
kfree(sbi);
return;
}
-static kmem_cache_t *ext3_inode_cachep;
+static struct kmem_cache *ext3_inode_cachep;
/*
* Called inside transaction, so use GFP_NOFS
{
struct ext3_inode_info *ei;
- ei = kmem_cache_alloc(ext3_inode_cachep, SLAB_NOFS);
+ ei = kmem_cache_alloc(ext3_inode_cachep, GFP_NOFS);
if (!ei)
return NULL;
#ifdef CONFIG_EXT3_FS_POSIX_ACL
static void ext3_destroy_inode(struct inode *inode)
{
+ if (!list_empty(&(EXT3_I(inode)->i_orphan))) {
+ printk("EXT3 Inode %p: orphan list check failed!\n",
+ EXT3_I(inode));
+ print_hex_dump(KERN_INFO, "", DUMP_PREFIX_ADDRESS, 16, 4,
+ EXT3_I(inode), sizeof(struct ext3_inode_info),
+ false);
+ dump_stack();
+ }
kmem_cache_free(ext3_inode_cachep, EXT3_I(inode));
}
-static void init_once(void * foo, kmem_cache_t * cachep, unsigned long flags)
+static void init_once(void *foo)
{
struct ext3_inode_info *ei = (struct ext3_inode_info *) foo;
- if ((flags & (SLAB_CTOR_VERIFY|SLAB_CTOR_CONSTRUCTOR)) ==
- SLAB_CTOR_CONSTRUCTOR) {
- INIT_LIST_HEAD(&ei->i_orphan);
+ INIT_LIST_HEAD(&ei->i_orphan);
#ifdef CONFIG_EXT3_FS_XATTR
- init_rwsem(&ei->xattr_sem);
+ init_rwsem(&ei->xattr_sem);
#endif
- init_MUTEX(&ei->truncate_sem);
- inode_init_once(&ei->vfs_inode);
- }
+ mutex_init(&ei->truncate_mutex);
+ inode_init_once(&ei->vfs_inode);
}
-
+
static int init_inodecache(void)
{
ext3_inode_cachep = kmem_cache_create("ext3_inode_cache",
sizeof(struct ext3_inode_info),
- 0, SLAB_RECLAIM_ACCOUNT,
- init_once, NULL);
+ 0, (SLAB_RECLAIM_ACCOUNT|
+ SLAB_MEM_SPREAD),
+ init_once);
if (ext3_inode_cachep == NULL)
return -ENOMEM;
return 0;
static void destroy_inodecache(void)
{
- if (kmem_cache_destroy(ext3_inode_cachep))
- printk(KERN_INFO "ext3_inode_cache: not all structures were freed\n");
+ 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;
#ifdef CONFIG_EXT3_FS_POSIX_ACL
- if (EXT3_I(inode)->i_acl &&
- EXT3_I(inode)->i_acl != EXT3_ACL_NOT_CACHED) {
- posix_acl_release(EXT3_I(inode)->i_acl);
- EXT3_I(inode)->i_acl = EXT3_ACL_NOT_CACHED;
- }
- if (EXT3_I(inode)->i_default_acl &&
- EXT3_I(inode)->i_default_acl != EXT3_ACL_NOT_CACHED) {
- posix_acl_release(EXT3_I(inode)->i_default_acl);
- EXT3_I(inode)->i_default_acl = EXT3_ACL_NOT_CACHED;
- }
+ if (EXT3_I(inode)->i_acl &&
+ EXT3_I(inode)->i_acl != EXT3_ACL_NOT_CACHED) {
+ posix_acl_release(EXT3_I(inode)->i_acl);
+ EXT3_I(inode)->i_acl = EXT3_ACL_NOT_CACHED;
+ }
+ if (EXT3_I(inode)->i_default_acl &&
+ EXT3_I(inode)->i_default_acl != EXT3_ACL_NOT_CACHED) {
+ posix_acl_release(EXT3_I(inode)->i_default_acl);
+ EXT3_I(inode)->i_default_acl = EXT3_ACL_NOT_CACHED;
+ }
#endif
ext3_discard_reservation(inode);
EXT3_I(inode)->i_block_alloc_info = NULL;
- kfree(rsv);
+ if (unlikely(rsv))
+ kfree(rsv);
}
static inline void ext3_show_quota_options(struct seq_file *seq, struct super_block *sb)
#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 ext3_show_options(struct seq_file *seq, struct vfsmount *vfs)
{
struct super_block *sb = vfs->mnt_sb;
+ struct ext3_sb_info *sbi = EXT3_SB(sb);
+ struct ext3_super_block *es = sbi->s_es;
+ unsigned long def_mount_opts;
+
+ def_mount_opts = le32_to_cpu(es->s_default_mount_opts);
+
+ if (sbi->s_sb_block != 1)
+ seq_printf(seq, ",sb=%lu", sbi->s_sb_block);
+ if (test_opt(sb, MINIX_DF))
+ seq_puts(seq, ",minixdf");
+ if (test_opt(sb, GRPID))
+ seq_puts(seq, ",grpid");
+ if (!test_opt(sb, GRPID) && (def_mount_opts & EXT3_DEFM_BSDGROUPS))
+ seq_puts(seq, ",nogrpid");
+ if (sbi->s_resuid != EXT3_DEF_RESUID ||
+ le16_to_cpu(es->s_def_resuid) != EXT3_DEF_RESUID) {
+ seq_printf(seq, ",resuid=%u", sbi->s_resuid);
+ }
+ if (sbi->s_resgid != EXT3_DEF_RESGID ||
+ le16_to_cpu(es->s_def_resgid) != EXT3_DEF_RESGID) {
+ seq_printf(seq, ",resgid=%u", sbi->s_resgid);
+ }
+ if (test_opt(sb, ERRORS_RO)) {
+ int def_errors = le16_to_cpu(es->s_errors);
+
+ if (def_errors == EXT3_ERRORS_PANIC ||
+ def_errors == EXT3_ERRORS_CONTINUE) {
+ seq_puts(seq, ",errors=remount-ro");
+ }
+ }
+ if (test_opt(sb, ERRORS_CONT))
+ seq_puts(seq, ",errors=continue");
+ if (test_opt(sb, ERRORS_PANIC))
+ seq_puts(seq, ",errors=panic");
+ if (test_opt(sb, NO_UID32))
+ seq_puts(seq, ",nouid32");
+ if (test_opt(sb, DEBUG))
+ seq_puts(seq, ",debug");
+ if (test_opt(sb, OLDALLOC))
+ seq_puts(seq, ",oldalloc");
+#ifdef CONFIG_EXT3_FS_XATTR
+ if (test_opt(sb, XATTR_USER))
+ seq_puts(seq, ",user_xattr");
+ if (!test_opt(sb, XATTR_USER) &&
+ (def_mount_opts & EXT3_DEFM_XATTR_USER)) {
+ seq_puts(seq, ",nouser_xattr");
+ }
+#endif
+#ifdef CONFIG_EXT3_FS_POSIX_ACL
+ if (test_opt(sb, POSIX_ACL))
+ seq_puts(seq, ",acl");
+ if (!test_opt(sb, POSIX_ACL) && (def_mount_opts & EXT3_DEFM_ACL))
+ seq_puts(seq, ",noacl");
+#endif
+ if (!test_opt(sb, RESERVATION))
+ seq_puts(seq, ",noreservation");
+ if (sbi->s_commit_interval) {
+ seq_printf(seq, ",commit=%u",
+ (unsigned) (sbi->s_commit_interval / HZ));
+ }
+ if (test_opt(sb, BARRIER))
+ seq_puts(seq, ",barrier=1");
+ if (test_opt(sb, NOBH))
+ seq_puts(seq, ",nobh");
if (test_opt(sb, DATA_FLAGS) == EXT3_MOUNT_JOURNAL_DATA)
seq_puts(seq, ",data=journal");
else if (test_opt(sb, DATA_FLAGS) == EXT3_MOUNT_WRITEBACK_DATA)
seq_puts(seq, ",data=writeback");
+ if (test_opt(sb, DATA_ERR_ABORT))
+ seq_puts(seq, ",data_err=abort");
+
ext3_show_quota_options(seq, sb);
return 0;
}
+
+static struct inode *ext3_nfs_get_inode(struct super_block *sb,
+ u64 ino, u32 generation)
+{
+ struct inode *inode;
+
+ if (ino < EXT3_FIRST_INO(sb) && ino != EXT3_ROOT_INO)
+ return ERR_PTR(-ESTALE);
+ if (ino > le32_to_cpu(EXT3_SB(sb)->s_es->s_inodes_count))
+ return ERR_PTR(-ESTALE);
+
+ /* iget isn't really right if the inode is currently unallocated!!
+ *
+ * ext3_read_inode will return a bad_inode if the inode had been
+ * deleted, so we should be safe.
+ *
+ * Currently we don't know the generation for parent directory, so
+ * a generation of 0 means "accept any"
+ */
+ inode = ext3_iget(sb, ino);
+ if (IS_ERR(inode))
+ return ERR_CAST(inode);
+ if (generation && inode->i_generation != generation) {
+ iput(inode);
+ return ERR_PTR(-ESTALE);
+ }
+
+ return inode;
+}
+
+static struct dentry *ext3_fh_to_dentry(struct super_block *sb, struct fid *fid,
+ int fh_len, int fh_type)
+{
+ return generic_fh_to_dentry(sb, fid, fh_len, fh_type,
+ ext3_nfs_get_inode);
+}
+
+static struct dentry *ext3_fh_to_parent(struct super_block *sb, struct fid *fid,
+ int fh_len, int fh_type)
+{
+ return generic_fh_to_parent(sb, fid, fh_len, fh_type,
+ ext3_nfs_get_inode);
+}
+
+/*
+ * Try to release metadata pages (indirect blocks, directories) which are
+ * mapped via the block device. Since these pages could have journal heads
+ * which would prevent try_to_free_buffers() from freeing them, we must use
+ * jbd layer's try_to_free_buffers() function to release them.
+ */
+static int bdev_try_to_free_page(struct super_block *sb, struct page *page,
+ gfp_t wait)
+{
+ journal_t *journal = EXT3_SB(sb)->s_journal;
+
+ WARN_ON(PageChecked(page));
+ if (!page_has_buffers(page))
+ return 0;
+ if (journal)
+ return journal_try_to_free_buffers(journal, page,
+ wait & ~__GFP_WAIT);
+ return try_to_free_buffers(page);
+}
+
#ifdef CONFIG_QUOTA
#define QTYPE2NAME(t) ((t)==USRQUOTA?"user":"group")
#define QTYPE2MOPT(on, t) ((t)==USRQUOTA?((on)##USRJQUOTA):((on)##GRPJQUOTA))
static int ext3_release_dquot(struct dquot *dquot);
static int ext3_mark_dquot_dirty(struct dquot *dquot);
static int ext3_write_info(struct super_block *sb, int type);
-static int ext3_quota_on(struct super_block *sb, int type, int format_id, char *path);
+static int ext3_quota_on(struct super_block *sb, int type, int format_id,
+ char *path, int remount);
static int ext3_quota_on_mount(struct super_block *sb, int type);
static ssize_t ext3_quota_read(struct super_block *sb, int type, char *data,
size_t len, loff_t off);
.acquire_dquot = ext3_acquire_dquot,
.release_dquot = ext3_release_dquot,
.mark_dirty = ext3_mark_dquot_dirty,
- .write_info = ext3_write_info
+ .write_info = ext3_write_info,
+ .alloc_dquot = dquot_alloc,
+ .destroy_dquot = dquot_destroy,
};
static struct quotactl_ops ext3_qctl_operations = {
};
#endif
-static struct super_operations ext3_sops = {
+static const struct super_operations ext3_sops = {
.alloc_inode = ext3_alloc_inode,
.destroy_inode = ext3_destroy_inode,
- .read_inode = ext3_read_inode,
.write_inode = ext3_write_inode,
.dirty_inode = ext3_dirty_inode,
.delete_inode = ext3_delete_inode,
.put_super = ext3_put_super,
.write_super = ext3_write_super,
.sync_fs = ext3_sync_fs,
- .write_super_lockfs = ext3_write_super_lockfs,
- .unlockfs = ext3_unlockfs,
+ .freeze_fs = ext3_freeze,
+ .unfreeze_fs = ext3_unfreeze,
.statfs = ext3_statfs,
.remount_fs = ext3_remount,
.clear_inode = ext3_clear_inode,
.quota_read = ext3_quota_read,
.quota_write = ext3_quota_write,
#endif
+ .bdev_try_to_free_page = bdev_try_to_free_page,
};
-static struct export_operations ext3_export_ops = {
+static const struct export_operations ext3_export_ops = {
+ .fh_to_dentry = ext3_fh_to_dentry,
+ .fh_to_parent = ext3_fh_to_parent,
.get_parent = ext3_get_parent,
};
Opt_resgid, Opt_resuid, Opt_sb, Opt_err_cont, Opt_err_panic, Opt_err_ro,
Opt_nouid32, Opt_nocheck, Opt_debug, Opt_oldalloc, Opt_orlov,
Opt_user_xattr, Opt_nouser_xattr, Opt_acl, Opt_noacl,
- Opt_reservation, Opt_noreservation, Opt_noload, Opt_nobh,
+ Opt_reservation, Opt_noreservation, Opt_noload, Opt_nobh, Opt_bh,
Opt_commit, Opt_journal_update, Opt_journal_inum, Opt_journal_dev,
Opt_abort, Opt_data_journal, Opt_data_ordered, Opt_data_writeback,
+ Opt_data_err_abort, Opt_data_err_ignore,
Opt_usrjquota, Opt_grpjquota, Opt_offusrjquota, Opt_offgrpjquota,
Opt_jqfmt_vfsold, Opt_jqfmt_vfsv0, Opt_quota, Opt_noquota,
Opt_ignore, Opt_barrier, Opt_err, Opt_resize, Opt_usrquota,
Opt_grpquota
};
-static match_table_t tokens = {
+static const match_table_t tokens = {
{Opt_bsd_df, "bsddf"},
{Opt_minix_df, "minixdf"},
{Opt_grpid, "grpid"},
{Opt_noreservation, "noreservation"},
{Opt_noload, "noload"},
{Opt_nobh, "nobh"},
+ {Opt_bh, "bh"},
{Opt_commit, "commit=%u"},
{Opt_journal_update, "journal=update"},
{Opt_journal_inum, "journal=%u"},
{Opt_data_journal, "data=journal"},
{Opt_data_ordered, "data=ordered"},
{Opt_data_writeback, "data=writeback"},
+ {Opt_data_err_abort, "data_err=abort"},
+ {Opt_data_err_ignore, "data_err=ignore"},
{Opt_offusrjquota, "usrjquota="},
{Opt_usrjquota, "usrjquota=%s"},
{Opt_offgrpjquota, "grpjquota="},
{Opt_quota, "quota"},
{Opt_usrquota, "usrquota"},
{Opt_barrier, "barrier=%u"},
- {Opt_err, NULL},
{Opt_resize, "resize"},
+ {Opt_err, NULL},
};
-static unsigned long get_sb_block(void **data)
+static ext3_fsblk_t get_sb_block(void **data)
{
- unsigned long sb_block;
- char *options = (char *) *data;
+ ext3_fsblk_t sb_block;
+ char *options = (char *) *data;
if (!options || strncmp(options, "sb=", 3) != 0)
return 1; /* Default location */
options += 3;
+ /*todo: use simple_strtoll with >32bit ext3 */
sb_block = simple_strtoul(options, &options, 0);
if (*options && *options != ',') {
printk("EXT3-fs: Invalid sb specification: %s\n",
}
static int parse_options (char *options, struct super_block *sb,
- unsigned long *inum, unsigned long *journal_devnum,
- unsigned long *n_blocks_count, int is_remount)
+ unsigned int *inum, unsigned long *journal_devnum,
+ ext3_fsblk_t *n_blocks_count, int is_remount)
{
struct ext3_sb_info *sbi = EXT3_SB(sb);
char * p;
int data_opt = 0;
int option;
#ifdef CONFIG_QUOTA
- int qtype;
+ int qtype, qfmt;
char *qname;
#endif
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;
case Opt_grpjquota:
qtype = GRPQUOTA;
set_qf_name:
- if (sb_any_quota_enabled(sb)) {
+ if (sb_any_quota_loaded(sb) &&
+ !sbi->s_qf_names[qtype]) {
printk(KERN_ERR
- "EXT3-fs: Cannot change journalled "
+ "EXT3-fs: Cannot change journaled "
"quota options when quota turned on.\n");
return 0;
}
case Opt_offgrpjquota:
qtype = GRPQUOTA;
clear_qf_name:
- if (sb_any_quota_enabled(sb)) {
+ if (sb_any_quota_loaded(sb) &&
+ sbi->s_qf_names[qtype]) {
printk(KERN_ERR "EXT3-fs: Cannot change "
- "journalled quota options when "
+ "journaled quota options when "
"quota turned on.\n");
return 0;
}
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_loaded(sb) &&
+ sbi->s_jquota_fmt != qfmt) {
+ printk(KERN_ERR "EXT3-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:
set_opt(sbi->s_mount_opt, GRPQUOTA);
break;
case Opt_noquota:
- if (sb_any_quota_enabled(sb)) {
+ if (sb_any_quota_loaded(sb)) {
printk(KERN_ERR "EXT3-fs: Cannot change quota "
"options when quota turned on.\n");
return 0;
case Opt_quota:
case Opt_usrquota:
case Opt_grpquota:
+ printk(KERN_ERR
+ "EXT3-fs: quota options not supported.\n");
+ break;
case Opt_usrjquota:
case Opt_grpjquota:
case Opt_offusrjquota:
case Opt_jqfmt_vfsold:
case Opt_jqfmt_vfsv0:
printk(KERN_ERR
- "EXT3-fs: journalled quota options not "
+ "EXT3-fs: journaled quota options not "
"supported.\n");
break;
case Opt_noquota:
case Opt_nobh:
set_opt(sbi->s_mount_opt, NOBH);
break;
+ case Opt_bh:
+ clear_opt(sbi->s_mount_opt, NOBH);
+ break;
default:
printk (KERN_ERR
"EXT3-fs: Unrecognized mount option \"%s\" "
}
if (!sbi->s_jquota_fmt) {
- printk(KERN_ERR "EXT3-fs: journalled quota format "
+ printk(KERN_ERR "EXT3-fs: journaled quota format "
"not specified.\n");
return 0;
}
} else {
if (sbi->s_jquota_fmt) {
- printk(KERN_ERR "EXT3-fs: journalled quota format "
- "specified with no journalling "
+ printk(KERN_ERR "EXT3-fs: journaled quota format "
+ "specified with no journaling "
"enabled.\n");
return 0;
}
inconsistencies, to force a fsck at reboot. But for
a plain journaled filesystem we can keep it set as
valid forever! :) */
- es->s_state = cpu_to_le16(le16_to_cpu(es->s_state) & ~EXT3_VALID_FS);
+ es->s_state &= cpu_to_le16(~EXT3_VALID_FS);
#endif
if (!(__s16) le16_to_cpu(es->s_max_mnt_count))
es->s_max_mnt_count = cpu_to_le16(EXT3_DFL_MAX_MNT_COUNT);
- es->s_mnt_count=cpu_to_le16(le16_to_cpu(es->s_mnt_count) + 1);
+ le16_add_cpu(&es->s_mnt_count, 1);
es->s_mtime = cpu_to_le32(get_seconds());
ext3_update_dynamic_rev(sb);
EXT3_SET_INCOMPAT_FEATURE(sb, EXT3_FEATURE_INCOMPAT_RECOVER);
}
/* Called at mount-time, super-block is locked */
-static int ext3_check_descriptors (struct super_block * sb)
+static int ext3_check_descriptors(struct super_block *sb)
{
struct ext3_sb_info *sbi = EXT3_SB(sb);
- unsigned long block = le32_to_cpu(sbi->s_es->s_first_data_block);
- struct ext3_group_desc * gdp = NULL;
- int desc_block = 0;
int i;
ext3_debug ("Checking group descriptors");
- for (i = 0; i < sbi->s_groups_count; i++)
- {
- if ((i % EXT3_DESC_PER_BLOCK(sb)) == 0)
- gdp = (struct ext3_group_desc *)
- sbi->s_group_desc[desc_block++]->b_data;
- if (le32_to_cpu(gdp->bg_block_bitmap) < block ||
- le32_to_cpu(gdp->bg_block_bitmap) >=
- block + EXT3_BLOCKS_PER_GROUP(sb))
+ for (i = 0; i < sbi->s_groups_count; i++) {
+ struct ext3_group_desc *gdp = ext3_get_group_desc(sb, i, NULL);
+ ext3_fsblk_t first_block = ext3_group_first_block_no(sb, i);
+ ext3_fsblk_t last_block;
+
+ if (i == sbi->s_groups_count - 1)
+ last_block = le32_to_cpu(sbi->s_es->s_blocks_count) - 1;
+ else
+ last_block = first_block +
+ (EXT3_BLOCKS_PER_GROUP(sb) - 1);
+
+ if (le32_to_cpu(gdp->bg_block_bitmap) < first_block ||
+ le32_to_cpu(gdp->bg_block_bitmap) > last_block)
{
ext3_error (sb, "ext3_check_descriptors",
"Block bitmap for group %d"
le32_to_cpu(gdp->bg_block_bitmap));
return 0;
}
- if (le32_to_cpu(gdp->bg_inode_bitmap) < block ||
- le32_to_cpu(gdp->bg_inode_bitmap) >=
- block + EXT3_BLOCKS_PER_GROUP(sb))
+ if (le32_to_cpu(gdp->bg_inode_bitmap) < first_block ||
+ le32_to_cpu(gdp->bg_inode_bitmap) > last_block)
{
ext3_error (sb, "ext3_check_descriptors",
"Inode bitmap for group %d"
le32_to_cpu(gdp->bg_inode_bitmap));
return 0;
}
- if (le32_to_cpu(gdp->bg_inode_table) < block ||
- le32_to_cpu(gdp->bg_inode_table) + sbi->s_itb_per_group >=
- block + EXT3_BLOCKS_PER_GROUP(sb))
+ if (le32_to_cpu(gdp->bg_inode_table) < first_block ||
+ le32_to_cpu(gdp->bg_inode_table) + sbi->s_itb_per_group - 1 >
+ last_block)
{
ext3_error (sb, "ext3_check_descriptors",
"Inode table for group %d"
le32_to_cpu(gdp->bg_inode_table));
return 0;
}
- block += EXT3_BLOCKS_PER_GROUP(sb);
- gdp++;
}
sbi->s_es->s_free_blocks_count=cpu_to_le32(ext3_count_free_blocks(sb));
return;
}
+ if (bdev_read_only(sb->s_bdev)) {
+ printk(KERN_ERR "EXT3-fs: write access "
+ "unavailable, skipping orphan cleanup.\n");
+ return;
+ }
+
if (EXT3_SB(sb)->s_mount_state & EXT3_ERROR_FS) {
if (es->s_last_orphan)
jbd_debug(1, "Errors on filesystem, "
int ret = ext3_quota_on_mount(sb, i);
if (ret < 0)
printk(KERN_ERR
- "EXT3-fs: Cannot turn on journalled "
+ "EXT3-fs: Cannot turn on journaled "
"quota: error %d\n", ret);
}
}
while (es->s_last_orphan) {
struct inode *inode;
- if (!(inode =
- ext3_orphan_get(sb, le32_to_cpu(es->s_last_orphan)))) {
+ inode = ext3_orphan_get(sb, le32_to_cpu(es->s_last_orphan));
+ if (IS_ERR(inode)) {
es->s_last_orphan = 0;
break;
}
DQUOT_INIT(inode);
if (inode->i_nlink) {
printk(KERN_DEBUG
- "%s: truncating inode %ld to %Ld bytes\n",
- __FUNCTION__, inode->i_ino, inode->i_size);
- jbd_debug(2, "truncating inode %ld to %Ld bytes\n",
+ "%s: truncating inode %lu to %Ld bytes\n",
+ __func__, inode->i_ino, inode->i_size);
+ jbd_debug(2, "truncating inode %lu to %Ld bytes\n",
inode->i_ino, inode->i_size);
ext3_truncate(inode);
nr_truncates++;
} else {
printk(KERN_DEBUG
- "%s: deleting unreferenced inode %ld\n",
- __FUNCTION__, inode->i_ino);
- jbd_debug(2, "deleting unreferenced inode %ld\n",
+ "%s: deleting unreferenced inode %lu\n",
+ __func__, inode->i_ino);
+ jbd_debug(2, "deleting unreferenced inode %lu\n",
inode->i_ino);
nr_orphans++;
}
/* Turn quotas off */
for (i = 0; i < MAXQUOTAS; i++) {
if (sb_dqopt(sb)->files[i])
- vfs_quota_off(sb, i);
+ vfs_quota_off(sb, i, 0);
}
#endif
sb->s_flags = s_flags; /* Restore MS_RDONLY status */
}
-#define log2(n) ffz(~(n))
-
/*
* Maximal file size. There is a direct, and {,double-,triple-}indirect
* block limit, and also a limit of (2^32 - 1) 512-byte sectors in i_blocks.
static loff_t ext3_max_size(int bits)
{
loff_t res = EXT3_NDIR_BLOCKS;
- /* This constant is calculated to be the largest file size for a
- * dense, 4k-blocksize file such that the total number of
+ int meta_blocks;
+ loff_t upper_limit;
+
+ /* This is calculated to be the largest file size for a
+ * dense, file such that the total number of
* sectors in the file, including data and all indirect blocks,
- * does not exceed 2^32. */
- const loff_t upper_limit = 0x1ff7fffd000LL;
+ * does not exceed 2^32 -1
+ * __u32 i_blocks representing the total number of
+ * 512 bytes blocks of the file
+ */
+ upper_limit = (1LL << 32) - 1;
+
+ /* total blocks in file system block size */
+ upper_limit >>= (bits - 9);
+
+
+ /* indirect blocks */
+ meta_blocks = 1;
+ /* double indirect blocks */
+ meta_blocks += 1 + (1LL << (bits-2));
+ /* tripple indirect blocks */
+ meta_blocks += 1 + (1LL << (bits-2)) + (1LL << (2*(bits-2)));
+
+ upper_limit -= meta_blocks;
+ upper_limit <<= bits;
res += 1LL << (bits-2);
res += 1LL << (2*(bits-2));
res <<= bits;
if (res > upper_limit)
res = upper_limit;
+
+ if (res > MAX_LFS_FILESIZE)
+ res = MAX_LFS_FILESIZE;
+
return res;
}
-static unsigned long descriptor_loc(struct super_block *sb,
- unsigned long logic_sb_block,
+static ext3_fsblk_t descriptor_loc(struct super_block *sb,
+ ext3_fsblk_t logic_sb_block,
int nr)
{
struct ext3_sb_info *sbi = EXT3_SB(sb);
- unsigned long bg, first_data_block, first_meta_bg;
+ unsigned long bg, first_meta_bg;
int has_super = 0;
- first_data_block = le32_to_cpu(sbi->s_es->s_first_data_block);
first_meta_bg = le32_to_cpu(sbi->s_es->s_first_meta_bg);
if (!EXT3_HAS_INCOMPAT_FEATURE(sb, EXT3_FEATURE_INCOMPAT_META_BG) ||
bg = sbi->s_desc_per_block * nr;
if (ext3_bg_has_super(sb, bg))
has_super = 1;
- return (first_data_block + has_super + (bg * sbi->s_blocks_per_group));
+ return (has_super + ext3_group_first_block_no(sb, bg));
}
struct buffer_head * bh;
struct ext3_super_block *es = NULL;
struct ext3_sb_info *sbi;
- unsigned long block;
- unsigned long sb_block = get_sb_block(&data);
- unsigned long logic_sb_block;
+ ext3_fsblk_t block;
+ ext3_fsblk_t sb_block = get_sb_block(&data);
+ ext3_fsblk_t logic_sb_block;
unsigned long offset = 0;
- unsigned long journal_inum = 0;
+ unsigned int journal_inum = 0;
unsigned long journal_devnum = 0;
unsigned long def_mount_opts;
struct inode *root;
int db_count;
int i;
int needs_recovery;
+ int ret = -EINVAL;
__le32 features;
+ int err;
- sbi = kmalloc(sizeof(*sbi), GFP_KERNEL);
+ sbi = kzalloc(sizeof(*sbi), GFP_KERNEL);
if (!sbi)
return -ENOMEM;
+
+ sbi->s_blockgroup_lock =
+ kzalloc(sizeof(struct blockgroup_lock), GFP_KERNEL);
+ if (!sbi->s_blockgroup_lock) {
+ kfree(sbi);
+ return -ENOMEM;
+ }
sb->s_fs_info = sbi;
- memset(sbi, 0, sizeof(*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();
set_opt(sbi->s_mount_opt, GRPID);
if (def_mount_opts & EXT3_DEFM_UID16)
set_opt(sbi->s_mount_opt, NO_UID32);
+#ifdef CONFIG_EXT3_FS_XATTR
if (def_mount_opts & EXT3_DEFM_XATTR_USER)
set_opt(sbi->s_mount_opt, XATTR_USER);
+#endif
+#ifdef CONFIG_EXT3_FS_POSIX_ACL
if (def_mount_opts & EXT3_DEFM_ACL)
set_opt(sbi->s_mount_opt, POSIX_ACL);
+#endif
if ((def_mount_opts & EXT3_DEFM_JMODE) == EXT3_DEFM_JMODE_DATA)
sbi->s_mount_opt |= EXT3_MOUNT_JOURNAL_DATA;
else if ((def_mount_opts & EXT3_DEFM_JMODE) == EXT3_DEFM_JMODE_ORDERED)
if (le16_to_cpu(sbi->s_es->s_errors) == EXT3_ERRORS_PANIC)
set_opt(sbi->s_mount_opt, ERRORS_PANIC);
- else if (le16_to_cpu(sbi->s_es->s_errors) == EXT3_ERRORS_RO)
+ else if (le16_to_cpu(sbi->s_es->s_errors) == EXT3_ERRORS_CONTINUE)
+ set_opt(sbi->s_mount_opt, ERRORS_CONT);
+ else
set_opt(sbi->s_mount_opt, ERRORS_RO);
sbi->s_resuid = le16_to_cpu(es->s_def_resuid);
(EXT3_HAS_COMPAT_FEATURE(sb, ~0U) ||
EXT3_HAS_RO_COMPAT_FEATURE(sb, ~0U) ||
EXT3_HAS_INCOMPAT_FEATURE(sb, ~0U)))
- printk(KERN_WARNING
+ printk(KERN_WARNING
"EXT3-fs warning: feature flags set on rev 0 fs, "
"running e2fsck is recommended\n");
/*
if (blocksize < EXT3_MIN_BLOCK_SIZE ||
blocksize > EXT3_MAX_BLOCK_SIZE) {
- printk(KERN_ERR
+ printk(KERN_ERR
"EXT3-fs: Unsupported filesystem blocksize %d on %s.\n",
blocksize, sb->s_id);
goto failed_mount;
}
brelse (bh);
- sb_set_blocksize(sb, blocksize);
+ if (!sb_set_blocksize(sb, blocksize)) {
+ printk(KERN_ERR "EXT3-fs: bad blocksize %d.\n",
+ blocksize);
+ goto out_fail;
+ }
logic_sb_block = (sb_block * EXT3_MIN_BLOCK_SIZE) / blocksize;
offset = (sb_block * EXT3_MIN_BLOCK_SIZE) % blocksize;
bh = sb_bread(sb, logic_sb_block);
if (!bh) {
- printk(KERN_ERR
+ printk(KERN_ERR
"EXT3-fs: Can't read superblock on 2nd try.\n");
goto failed_mount;
}
es = (struct ext3_super_block *)(((char *)bh->b_data) + offset);
sbi->s_es = es;
if (es->s_magic != cpu_to_le16(EXT3_SUPER_MAGIC)) {
- printk (KERN_ERR
+ printk (KERN_ERR
"EXT3-fs: Magic mismatch, very weird !\n");
goto failed_mount;
}
sbi->s_inode_size = le16_to_cpu(es->s_inode_size);
sbi->s_first_ino = le32_to_cpu(es->s_first_ino);
if ((sbi->s_inode_size < EXT3_GOOD_OLD_INODE_SIZE) ||
- (sbi->s_inode_size & (sbi->s_inode_size - 1)) ||
+ (!is_power_of_2(sbi->s_inode_size)) ||
(sbi->s_inode_size > blocksize)) {
printk (KERN_ERR
"EXT3-fs: unsupported inode size: %d\n",
sbi->s_blocks_per_group = le32_to_cpu(es->s_blocks_per_group);
sbi->s_frags_per_group = le32_to_cpu(es->s_frags_per_group);
sbi->s_inodes_per_group = le32_to_cpu(es->s_inodes_per_group);
- if (EXT3_INODE_SIZE(sb) == 0)
+ if (EXT3_INODE_SIZE(sb) == 0 || EXT3_INODES_PER_GROUP(sb) == 0)
goto cantfind_ext3;
sbi->s_inodes_per_block = blocksize / EXT3_INODE_SIZE(sb);
if (sbi->s_inodes_per_block == 0)
sbi->s_desc_per_block = blocksize / sizeof(struct ext3_group_desc);
sbi->s_sbh = bh;
sbi->s_mount_state = le16_to_cpu(es->s_state);
- sbi->s_addr_per_block_bits = log2(EXT3_ADDR_PER_BLOCK(sb));
- sbi->s_desc_per_block_bits = log2(EXT3_DESC_PER_BLOCK(sb));
+ sbi->s_addr_per_block_bits = ilog2(EXT3_ADDR_PER_BLOCK(sb));
+ sbi->s_desc_per_block_bits = ilog2(EXT3_DESC_PER_BLOCK(sb));
for (i=0; i < 4; i++)
sbi->s_hash_seed[i] = le32_to_cpu(es->s_hash_seed[i]);
sbi->s_def_hash_version = es->s_def_hash_version;
+ i = le32_to_cpu(es->s_flags);
+ if (i & EXT2_FLAGS_UNSIGNED_HASH)
+ sbi->s_hash_unsigned = 3;
+ else if ((i & EXT2_FLAGS_SIGNED_HASH) == 0) {
+#ifdef __CHAR_UNSIGNED__
+ es->s_flags |= cpu_to_le32(EXT2_FLAGS_UNSIGNED_HASH);
+ sbi->s_hash_unsigned = 3;
+#else
+ es->s_flags |= cpu_to_le32(EXT2_FLAGS_SIGNED_HASH);
+#endif
+ sb->s_dirt = 1;
+ }
if (sbi->s_blocks_per_group > blocksize * 8) {
printk (KERN_ERR
goto failed_mount;
}
+ if (le32_to_cpu(es->s_blocks_count) >
+ (sector_t)(~0ULL) >> (sb->s_blocksize_bits - 9)) {
+ printk(KERN_ERR "EXT3-fs: filesystem on %s:"
+ " too large to mount safely\n", sb->s_id);
+ if (sizeof(sector_t) < 8)
+ printk(KERN_WARNING "EXT3-fs: CONFIG_LBD not "
+ "enabled\n");
+ goto failed_mount;
+ }
+
if (EXT3_BLOCKS_PER_GROUP(sb) == 0)
goto cantfind_ext3;
- sbi->s_groups_count = (le32_to_cpu(es->s_blocks_count) -
- le32_to_cpu(es->s_first_data_block) +
- EXT3_BLOCKS_PER_GROUP(sb) - 1) /
- EXT3_BLOCKS_PER_GROUP(sb);
+ 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);
sbi->s_group_desc = kmalloc(db_count * sizeof (struct buffer_head *),
goto failed_mount;
}
- percpu_counter_init(&sbi->s_freeblocks_counter);
- percpu_counter_init(&sbi->s_freeinodes_counter);
- percpu_counter_init(&sbi->s_dirs_counter);
- bgl_lock_init(&sbi->s_blockgroup_lock);
+ bgl_lock_init(sbi->s_blockgroup_lock);
for (i = 0; i < db_count; i++) {
block = descriptor_loc(sb, logic_sb_block, i);
}
}
if (!ext3_check_descriptors (sb)) {
- printk (KERN_ERR "EXT3-fs: group descriptors corrupted !\n");
+ printk(KERN_ERR "EXT3-fs: group descriptors corrupted!\n");
goto failed_mount2;
}
sbi->s_gdb_count = db_count;
get_random_bytes(&sbi->s_next_generation, sizeof(u32));
spin_lock_init(&sbi->s_next_gen_lock);
+
+ 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) {
+ printk(KERN_ERR "EXT3-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;
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_mount2;
+ goto failed_mount3;
} else if (journal_inum) {
if (ext3_create_journal(sb, es, journal_inum))
- goto failed_mount2;
+ goto failed_mount3;
} else {
if (!silent)
printk (KERN_ERR
"ext3: No journal on filesystem on %s\n",
sb->s_id);
- goto failed_mount2;
+ goto failed_mount3;
}
/* We have now updated the journal if required, so we can
(sbi->s_journal, 0, 0, JFS_FEATURE_INCOMPAT_REVOKE)) {
printk(KERN_ERR "EXT3-fs: Journal does not support "
"requested data journaling mode\n");
- goto failed_mount3;
+ goto failed_mount4;
}
default:
break;
}
if (test_opt(sb, NOBH)) {
- if (sb->s_blocksize_bits != PAGE_CACHE_SHIFT) {
- printk(KERN_WARNING "EXT3-fs: Ignoring nobh option "
- "since filesystem blocksize doesn't match "
- "pagesize\n");
- clear_opt(sbi->s_mount_opt, NOBH);
- }
if (!(test_opt(sb, DATA_FLAGS) == EXT3_MOUNT_WRITEBACK_DATA)) {
printk(KERN_WARNING "EXT3-fs: Ignoring nobh option - "
"its supported only with writeback mode\n");
* so we can safely mount the rest of the filesystem now.
*/
- root = iget(sb, EXT3_ROOT_INO);
- sb->s_root = d_alloc_root(root);
- if (!sb->s_root) {
+ root = ext3_iget(sb, EXT3_ROOT_INO);
+ if (IS_ERR(root)) {
printk(KERN_ERR "EXT3-fs: get root inode failed\n");
- iput(root);
- goto failed_mount3;
+ 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 "EXT3-fs: corrupt root inode, run e2fsck\n");
- goto failed_mount3;
+ goto failed_mount4;
+ }
+ sb->s_root = d_alloc_root(root);
+ if (!sb->s_root) {
+ printk(KERN_ERR "EXT3-fs: get root dentry failed\n");
+ iput(root);
+ ret = -ENOMEM;
+ goto failed_mount4;
}
ext3_setup_super (sb, es, sb->s_flags & MS_RDONLY);
test_opt(sb,DATA_FLAGS) == EXT3_MOUNT_ORDERED_DATA ? "ordered":
"writeback");
- percpu_counter_mod(&sbi->s_freeblocks_counter,
- ext3_count_free_blocks(sb));
- percpu_counter_mod(&sbi->s_freeinodes_counter,
- ext3_count_free_inodes(sb));
- percpu_counter_mod(&sbi->s_dirs_counter,
- ext3_count_dirs(sb));
-
lock_kernel();
return 0;
sb->s_id);
goto failed_mount;
-failed_mount3:
+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);
failed_mount2:
for (i = 0; i < db_count; i++)
brelse(sbi->s_group_desc[i]);
sb->s_fs_info = NULL;
kfree(sbi);
lock_kernel();
- return -EINVAL;
+ return ret;
}
/*
* Setup any per-fs journal parameters now. We'll do this both on
* initial mount, once the journal has been initialised but before we've
- * done any recovery; and again on any subsequent remount.
+ * done any recovery; and again on any subsequent remount.
*/
static void ext3_init_journal_params(struct super_block *sb, journal_t *journal)
{
journal->j_flags |= JFS_BARRIER;
else
journal->j_flags &= ~JFS_BARRIER;
+ if (test_opt(sb, DATA_ERR_ABORT))
+ journal->j_flags |= JFS_ABORT_ON_SYNCDATA_ERR;
+ else
+ journal->j_flags &= ~JFS_ABORT_ON_SYNCDATA_ERR;
spin_unlock(&journal->j_state_lock);
}
-static journal_t *ext3_get_journal(struct super_block *sb, int journal_inum)
+static journal_t *ext3_get_journal(struct super_block *sb,
+ unsigned int journal_inum)
{
struct inode *journal_inode;
journal_t *journal;
* 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 = ext3_iget(sb, journal_inum);
+ if (IS_ERR(journal_inode)) {
printk(KERN_ERR "EXT3-fs: no journal found.\n");
return NULL;
}
jbd_debug(2, "Journal inode found at %p: %Ld bytes\n",
journal_inode, journal_inode->i_size);
- if (is_bad_inode(journal_inode) || !S_ISREG(journal_inode->i_mode)) {
+ if (!S_ISREG(journal_inode->i_mode)) {
printk(KERN_ERR "EXT3-fs: invalid journal inode.\n");
iput(journal_inode);
return NULL;
{
struct buffer_head * bh;
journal_t *journal;
- int start;
- int len;
+ ext3_fsblk_t start;
+ ext3_fsblk_t len;
int hblock, blocksize;
- unsigned long sb_block;
+ ext3_fsblk_t sb_block;
unsigned long offset;
struct ext3_super_block * es;
struct block_device *bdev;
if (bd_claim(bdev, sb)) {
printk(KERN_ERR
"EXT3: failed to claim external journal device.\n");
- blkdev_put(bdev);
+ blkdev_put(bdev, FMODE_READ|FMODE_WRITE);
return NULL;
}
unsigned long journal_devnum)
{
journal_t *journal;
- int journal_inum = le32_to_cpu(es->s_journal_inum);
+ unsigned int journal_inum = le32_to_cpu(es->s_journal_inum);
dev_t journal_dev;
int err = 0;
int really_read_only;
static int ext3_create_journal(struct super_block * sb,
struct ext3_super_block * es,
- int journal_inum)
+ unsigned int journal_inum)
{
journal_t *journal;
+ int err;
if (sb->s_flags & MS_RDONLY) {
printk(KERN_ERR "EXT3-fs: readonly filesystem when trying to "
return -EROFS;
}
- if (!(journal = ext3_get_journal(sb, journal_inum)))
+ journal = ext3_get_journal(sb, journal_inum);
+ if (!journal)
return -EINVAL;
- printk(KERN_INFO "EXT3-fs: creating new journal on inode %d\n",
+ printk(KERN_INFO "EXT3-fs: creating new journal on inode %u\n",
journal_inum);
- if (journal_create(journal)) {
+ err = journal_create(journal);
+ if (err) {
printk(KERN_ERR "EXT3-fs: error creating journal.\n");
journal_destroy(journal);
return -EIO;
return 0;
}
-static void ext3_commit_super (struct super_block * sb,
- struct ext3_super_block * es,
+static int ext3_commit_super(struct super_block *sb,
+ struct ext3_super_block *es,
int sync)
{
struct buffer_head *sbh = EXT3_SB(sb)->s_sbh;
+ int error = 0;
if (!sbh)
- return;
+ return error;
es->s_wtime = cpu_to_le32(get_seconds());
es->s_free_blocks_count = cpu_to_le32(ext3_count_free_blocks(sb));
es->s_free_inodes_count = cpu_to_le32(ext3_count_free_inodes(sb));
BUFFER_TRACE(sbh, "marking dirty");
mark_buffer_dirty(sbh);
if (sync)
- sync_dirty_buffer(sbh);
+ error = sync_dirty_buffer(sbh);
+ return error;
}
journal_t *journal = EXT3_SB(sb)->s_journal;
journal_lock_updates(journal);
- journal_flush(journal);
+ if (journal_flush(journal) < 0)
+ goto out;
+
+ lock_super(sb);
if (EXT3_HAS_INCOMPAT_FEATURE(sb, EXT3_FEATURE_INCOMPAT_RECOVER) &&
sb->s_flags & MS_RDONLY) {
EXT3_CLEAR_INCOMPAT_FEATURE(sb, EXT3_FEATURE_INCOMPAT_RECOVER);
sb->s_dirt = 0;
ext3_commit_super(sb, es, 1);
}
+ unlock_super(sb);
+
+out:
journal_unlock_updates(journal);
}
char nbuf[16];
errstr = ext3_decode_error(sb, j_errno, nbuf);
- ext3_warning(sb, __FUNCTION__, "Filesystem error recorded "
+ ext3_warning(sb, __func__, "Filesystem error recorded "
"from previous mount: %s", errstr);
- ext3_warning(sb, __FUNCTION__, "Marking fs in need of "
+ ext3_warning(sb, __func__, "Marking fs in need of "
"filesystem check.");
EXT3_SB(sb)->s_mount_state |= EXT3_ERROR_FS;
/*
* Ext3 always journals updates to the superblock itself, so we don't
* have to propagate any other updates to the superblock on disk at this
- * point. Just start an async writeback to get the buffers on their way
- * to the disk.
- *
- * This implicitly triggers the writebehind on sync().
+ * point. (We can probably nuke this function altogether, and remove
+ * any mention to sb->s_dirt in all of fs/ext3; eventual cleanup...)
*/
-
static void ext3_write_super (struct super_block * sb)
{
- if (down_trylock(&sb->s_lock) == 0)
+ if (mutex_trylock(&sb->s_lock) != 0)
BUG();
sb->s_dirt = 0;
}
* LVM calls this function before a (read-only) snapshot is created. This
* gives us a chance to flush the journal completely and mark the fs clean.
*/
-static void ext3_write_super_lockfs(struct super_block *sb)
+static int ext3_freeze(struct super_block *sb)
{
+ int error = 0;
+ journal_t *journal;
sb->s_dirt = 0;
if (!(sb->s_flags & MS_RDONLY)) {
- journal_t *journal = EXT3_SB(sb)->s_journal;
+ journal = EXT3_SB(sb)->s_journal;
/* Now we set up the journal barrier. */
journal_lock_updates(journal);
- journal_flush(journal);
+
+ /*
+ * We don't want to clear needs_recovery flag when we failed
+ * to flush the journal.
+ */
+ error = journal_flush(journal);
+ if (error < 0)
+ goto out;
/* Journal blocked and flushed, clear needs_recovery flag. */
EXT3_CLEAR_INCOMPAT_FEATURE(sb, EXT3_FEATURE_INCOMPAT_RECOVER);
- ext3_commit_super(sb, EXT3_SB(sb)->s_es, 1);
+ error = ext3_commit_super(sb, EXT3_SB(sb)->s_es, 1);
+ if (error)
+ goto out;
}
+ return 0;
+
+out:
+ journal_unlock_updates(journal);
+ return error;
}
/*
* Called by LVM after the snapshot is done. We need to reset the RECOVER
* flag here, even though the filesystem is not technically dirty yet.
*/
-static void ext3_unlockfs(struct super_block *sb)
+static int ext3_unfreeze(struct super_block *sb)
{
if (!(sb->s_flags & MS_RDONLY)) {
lock_super(sb);
unlock_super(sb);
journal_unlock_updates(EXT3_SB(sb)->s_journal);
}
+ return 0;
}
static int ext3_remount (struct super_block * sb, int * flags, char * data)
{
struct ext3_super_block * es;
struct ext3_sb_info *sbi = EXT3_SB(sb);
- unsigned long n_blocks_count = 0;
+ ext3_fsblk_t n_blocks_count = 0;
unsigned long old_sb_flags;
struct ext3_mount_options old_opts;
int err;
}
if (sbi->s_mount_opt & EXT3_MOUNT_ABORT)
- ext3_abort(sb, __FUNCTION__, "Abort forced by user");
+ ext3_abort(sb, __func__, "Abort forced by user");
sb->s_flags = (sb->s_flags & ~MS_POSIXACL) |
((sbi->s_mount_opt & EXT3_MOUNT_POSIX_ACL) ? MS_POSIXACL : 0);
(sbi->s_mount_state & EXT3_VALID_FS))
es->s_state = cpu_to_le16(sbi->s_mount_state);
+ /*
+ * We have to unlock super so that we can wait for
+ * transactions.
+ */
+ unlock_super(sb);
ext3_mark_recovery_complete(sb, es);
+ lock_super(sb);
} else {
__le32 ret;
if ((ret = EXT3_HAS_RO_COMPAT_FEATURE(sb,
err = -EROFS;
goto restore_opts;
}
+
+ /*
+ * If we have an unprocessed orphan list hanging
+ * around from a previously readonly bdev mount,
+ * require a full umount/remount for now.
+ */
+ if (es->s_last_orphan) {
+ printk(KERN_WARNING "EXT3-fs: %s: couldn't "
+ "remount RDWR because of unprocessed "
+ "orphan inode list. Please "
+ "umount/remount instead.\n",
+ sb->s_id);
+ err = -EINVAL;
+ goto restore_opts;
+ }
+
/*
* Mounting a RDONLY partition read-write, so reread
* and store the current valid flag. (It may have
*/
ext3_clear_journal_err(sb, es);
sbi->s_mount_state = le16_to_cpu(es->s_state);
- if ((ret = ext3_group_extend(sb, es, n_blocks_count))) {
- err = ret;
+ if ((err = ext3_group_extend(sb, es, n_blocks_count)))
goto restore_opts;
- }
if (!ext3_setup_super (sb, es, 0))
sb->s_flags &= ~MS_RDONLY;
}
return err;
}
-static int ext3_statfs (struct super_block * sb, struct kstatfs * buf)
+static int ext3_statfs (struct dentry * dentry, struct kstatfs * buf)
{
- struct ext3_super_block *es = EXT3_SB(sb)->s_es;
- unsigned long overhead;
- int i;
+ struct super_block *sb = dentry->d_sb;
+ struct ext3_sb_info *sbi = EXT3_SB(sb);
+ struct ext3_super_block *es = sbi->s_es;
+ u64 fsid;
- if (test_opt (sb, MINIX_DF))
- overhead = 0;
- else {
- unsigned long ngroups;
- ngroups = EXT3_SB(sb)->s_groups_count;
+ if (test_opt(sb, MINIX_DF)) {
+ sbi->s_overhead_last = 0;
+ } else if (sbi->s_blocks_last != le32_to_cpu(es->s_blocks_count)) {
+ unsigned long ngroups = sbi->s_groups_count, i;
+ ext3_fsblk_t overhead = 0;
smp_rmb();
/*
- * Compute the overhead (FS structures)
+ * Compute the overhead (FS structures). This is constant
+ * for a given filesystem unless the number of block groups
+ * changes so we cache the previous value until it does.
*/
/*
* Every block group has an inode bitmap, a block
* bitmap, and an inode table.
*/
- overhead += (ngroups * (2 + EXT3_SB(sb)->s_itb_per_group));
+ overhead += ngroups * (2 + sbi->s_itb_per_group);
+ sbi->s_overhead_last = overhead;
+ smp_wmb();
+ sbi->s_blocks_last = le32_to_cpu(es->s_blocks_count);
}
buf->f_type = EXT3_SUPER_MAGIC;
buf->f_bsize = sb->s_blocksize;
- buf->f_blocks = le32_to_cpu(es->s_blocks_count) - overhead;
- buf->f_bfree = ext3_count_free_blocks (sb);
+ buf->f_blocks = le32_to_cpu(es->s_blocks_count) - sbi->s_overhead_last;
+ buf->f_bfree = percpu_counter_sum_positive(&sbi->s_freeblocks_counter);
+ es->s_free_blocks_count = cpu_to_le32(buf->f_bfree);
buf->f_bavail = buf->f_bfree - le32_to_cpu(es->s_r_blocks_count);
if (buf->f_bfree < le32_to_cpu(es->s_r_blocks_count))
buf->f_bavail = 0;
buf->f_files = le32_to_cpu(es->s_inodes_count);
- buf->f_ffree = ext3_count_free_inodes (sb);
+ buf->f_ffree = percpu_counter_sum_positive(&sbi->s_freeinodes_counter);
+ es->s_free_inodes_count = cpu_to_le32(buf->f_ffree);
buf->f_namelen = EXT3_NAME_LEN;
+ fsid = le64_to_cpup((void *)es->s_uuid) ^
+ le64_to_cpup((void *)es->s_uuid + sizeof(u64));
+ buf->f_fsid.val[0] = fsid & 0xFFFFFFFFUL;
+ buf->f_fsid.val[1] = (fsid >> 32) & 0xFFFFFFFFUL;
return 0;
}
* Process 1 Process 2
* ext3_create() quota_sync()
* journal_start() write_dquot()
- * DQUOT_INIT() down(dqio_sem)
- * down(dqio_sem) journal_start()
+ * DQUOT_INIT() down(dqio_mutex)
+ * down(dqio_mutex) journal_start()
*
*/
/* We may delete quota structure so we need to reserve enough blocks */
handle = ext3_journal_start(inode, 2*EXT3_QUOTA_DEL_BLOCKS(inode->i_sb));
- if (IS_ERR(handle))
+ 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 = ext3_journal_stop(handle);
if (!ret)
handle = ext3_journal_start(dquot_to_inode(dquot),
EXT3_QUOTA_DEL_BLOCKS(dquot->dq_sb));
- if (IS_ERR(handle))
+ if (IS_ERR(handle)) {
+ /* Release dquot anyway to avoid endless cycle in dqput() */
+ dquot_release(dquot);
return PTR_ERR(handle);
+ }
ret = dquot_release(dquot);
err = ext3_journal_stop(handle);
if (!ret)
static int ext3_mark_dquot_dirty(struct dquot *dquot)
{
- /* Are we journalling quotas? */
+ /* Are we journaling quotas? */
if (EXT3_SB(dquot->dq_sb)->s_qf_names[USRQUOTA] ||
EXT3_SB(dquot->dq_sb)->s_qf_names[GRPQUOTA]) {
dquot_mark_dquot_dirty(dquot);
* Standard function to be called on quota_on
*/
static int ext3_quota_on(struct super_block *sb, int type, int format_id,
- char *path)
+ char *name, int remount)
{
int err;
- struct nameidata nd;
+ struct path path;
if (!test_opt(sb, QUOTA))
return -EINVAL;
- /* Not journalling quota? */
- if (!EXT3_SB(sb)->s_qf_names[USRQUOTA] &&
- !EXT3_SB(sb)->s_qf_names[GRPQUOTA])
- return vfs_quota_on(sb, type, format_id, path);
- err = path_lookup(path, LOOKUP_FOLLOW, &nd);
+ /* When remounting, no checks are needed and in fact, name is NULL */
+ if (remount)
+ return vfs_quota_on(sb, type, format_id, name, remount);
+
+ err = kern_path(name, LOOKUP_FOLLOW, &path);
if (err)
return err;
+
/* Quotafile not on the same filesystem? */
- if (nd.mnt->mnt_sb != sb) {
- path_release(&nd);
+ if (path.mnt->mnt_sb != sb) {
+ path_put(&path);
return -EXDEV;
}
- /* Quotafile not of fs root? */
- if (nd.dentry->d_parent->d_inode != sb->s_root->d_inode)
- printk(KERN_WARNING
- "EXT3-fs: Quota file not on filesystem root. "
- "Journalled quota will not work.\n");
- path_release(&nd);
- return vfs_quota_on(sb, type, format_id, path);
+ /* Journaling quota? */
+ if (EXT3_SB(sb)->s_qf_names[type]) {
+ /* Quotafile not of fs root? */
+ if (path.dentry->d_parent != sb->s_root)
+ printk(KERN_WARNING
+ "EXT3-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 (ext3_should_journal_data(path.dentry->d_inode)) {
+ /*
+ * We don't need to lock updates but journal_flush() could
+ * otherwise be livelocked...
+ */
+ journal_lock_updates(EXT3_SB(sb)->s_journal);
+ err = journal_flush(EXT3_SB(sb)->s_journal);
+ journal_unlock_updates(EXT3_SB(sb)->s_journal);
+ if (err) {
+ path_put(&path);
+ return err;
+ }
+ }
+
+ err = vfs_quota_on_path(sb, type, format_id, &path);
+ path_put(&path);
+ return err;
}
/* Read data from quotafile - avoid pagecache and such because we cannot afford
struct buffer_head *bh;
handle_t *handle = journal_current_handle();
- down(&inode->i_sem);
+ if (!handle) {
+ printk(KERN_WARNING "EXT3-fs: Quota write (off=%Lu, len=%Lu)"
+ " cancelled because transaction is not started.\n",
+ (unsigned long long)off, (unsigned long long)len);
+ return -EIO;
+ }
+ mutex_lock_nested(&inode->i_mutex, I_MUTEX_QUOTA);
while (towrite > 0) {
tocopy = sb->s_blocksize - offset < towrite ?
sb->s_blocksize - offset : towrite;
blk++;
}
out:
- if (len == towrite)
+ if (len == towrite) {
+ mutex_unlock(&inode->i_mutex);
return err;
+ }
if (inode->i_size < off+len-towrite) {
i_size_write(inode, off+len-towrite);
EXT3_I(inode)->i_disksize = inode->i_size;
inode->i_version++;
inode->i_mtime = inode->i_ctime = CURRENT_TIME;
ext3_mark_inode_dirty(handle, inode);
- up(&inode->i_sem);
+ mutex_unlock(&inode->i_mutex);
return len - towrite;
}
#endif
-static struct super_block *ext3_get_sb(struct file_system_type *fs_type,
- int flags, const char *dev_name, void *data)
+static int ext3_get_sb(struct file_system_type *fs_type,
+ int flags, const char *dev_name, void *data, struct vfsmount *mnt)
{
- return get_sb_bdev(fs_type, flags, dev_name, data, ext3_fill_super);
+ return get_sb_bdev(fs_type, flags, dev_name, data, ext3_fill_super, mnt);
}
static struct file_system_type ext3_fs_type = {
out:
destroy_inodecache();
out1:
- exit_ext3_xattr();
+ exit_ext3_xattr();
return err;
}