* 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/mount.h>
#include <linux/namei.h>
#include <linux/quotaops.h>
+#include <linux/seq_file.h>
+
#include <asm/uaccess.h>
+
#include "xattr.h"
#include "acl.h"
+#include "namei.h"
-static int ext3_load_journal(struct super_block *, struct ext3_super_block *);
+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);
+ unsigned int);
static void ext3_commit_super (struct super_block * sb,
struct ext3_super_block * es,
int sync);
static void ext3_clear_journal_err(struct super_block * sb,
struct ext3_super_block * es);
static int ext3_sync_fs(struct super_block *sb, int wait);
+static const char *ext3_decode_error(struct super_block * sb, int errno,
+ char nbuf[16]);
+static int ext3_remount (struct super_block * sb, int * flags, char * data);
+static int ext3_statfs (struct dentry * dentry, struct kstatfs * buf);
+static void ext3_unlockfs(struct super_block *sb);
+static void ext3_write_super (struct super_block * sb);
+static void ext3_write_super_lockfs(struct super_block *sb);
-/*
+/*
* 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(struct inode *inode, int nblocks)
+handle_t *ext3_journal_start_sb(struct super_block *sb, int nblocks)
{
journal_t *journal;
- if (inode->i_sb->s_flags & MS_RDONLY)
+ if (sb->s_flags & MS_RDONLY)
return ERR_PTR(-EROFS);
/* Special case here: if the journal has aborted behind our
* backs (eg. EIO in the commit thread), then we still need to
* take the FS itself readonly cleanly. */
- journal = EXT3_JOURNAL(inode);
+ journal = EXT3_SB(sb)->s_journal;
if (is_journal_aborted(journal)) {
- ext3_abort(inode->i_sb, __FUNCTION__,
+ ext3_abort(sb, __FUNCTION__,
"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)
{
char nbuf[16];
const char *errstr = ext3_decode_error(NULL, err, nbuf);
- printk(KERN_ERR "%s: aborting transaction: %s in %s",
- caller, errstr, err_fn);
-
if (bh)
BUFFER_TRACE(bh, "abort");
- journal_abort_handle(handle);
+
if (!handle->h_err)
handle->h_err = err;
+
+ if (is_handle_aborted(handle))
+ return;
+
+ printk(KERN_ERR "%s: aborting transaction: %s in %s\n",
+ caller, errstr, err_fn);
+
+ journal_abort_handle(handle);
}
/* Deal with the reporting of failure conditions on a filesystem such as
if (sb->s_flags & MS_RDONLY)
return;
- if (test_opt (sb, ERRORS_PANIC))
- panic ("EXT3-fs (device %s): panic forced after error\n",
- sb->s_id);
- 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);
}
void ext3_error (struct super_block * sb, const char * function,
ext3_handle_error(sb);
}
-const char *ext3_decode_error(struct super_block * sb, int errno, char nbuf[16])
+static const char *ext3_decode_error(struct super_block * sb, int errno,
+ char nbuf[16])
{
char *errstr = NULL;
int errno)
{
char nbuf[16];
- const char *errstr = ext3_decode_error(sb, errno, nbuf);
+ const char *errstr;
+
+ /* Special case: if the error is EROFS, and we're not already
+ * inside a transaction, then there's really no point in logging
+ * an error. */
+ if (errno == -EROFS && journal_current_handle() == NULL &&
+ (sb->s_flags & MS_RDONLY))
+ return;
+ errstr = ext3_decode_error(sb, errno, nbuf);
printk (KERN_CRIT "EXT3-fs error (device %s) in %s: %s\n",
sb->s_id, function, errstr);
journal_abort(EXT3_SB(sb)->s_journal, -EIO);
}
-/* Deal with the reporting of failure conditions while running, such as
- * inconsistencies in operation or invalid system states.
- *
- * Use ext3_error() for cases of invalid filesystem states, as that will
- * record an error on disk and force a filesystem check on the next boot.
- */
-NORET_TYPE void ext3_panic (struct super_block * sb, const char * function,
- const char * fmt, ...)
-{
- 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");
- va_end(args);
-
- /* this is to prevent panic from syncing this filesystem */
- /* AKPM: is this sufficient? */
- sb->s_flags |= MS_RDONLY;
- panic ("EXT3-fs panic forced\n");
-}
-
void ext3_warning (struct super_block * sb, const char * function,
const char * fmt, ...)
{
{
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));
}
}
-void ext3_put_super (struct super_block * sb)
+static void ext3_put_super (struct super_block * sb)
{
struct ext3_sb_info *sbi = EXT3_SB(sb);
struct ext3_super_block *es = sbi->s_es;
for (i = 0; i < sbi->s_gdb_count; i++)
brelse(sbi->s_group_desc[i]);
kfree(sbi->s_group_desc);
- kfree(sbi->s_debts);
+ percpu_counter_destroy(&sbi->s_freeblocks_counter);
+ percpu_counter_destroy(&sbi->s_freeinodes_counter);
+ percpu_counter_destroy(&sbi->s_dirs_counter);
brelse(sbi->s_sbh);
#ifdef CONFIG_QUOTA
- for (i = 0; i < MAXQUOTAS; i++) {
- if (sbi->s_qf_names[i])
- kfree(sbi->s_qf_names[i]);
- }
+ for (i = 0; i < MAXQUOTAS; i++)
+ kfree(sbi->s_qf_names[i]);
#endif
/* Debugging code just in case the in-memory inode orphan list
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
ei->i_acl = EXT3_ACL_NOT_CACHED;
ei->i_default_acl = EXT3_ACL_NOT_CACHED;
#endif
+ ei->i_block_alloc_info = NULL;
ei->vfs_inode.i_version = 1;
return &ei->vfs_inode;
}
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 kmem_cache * cachep, unsigned long flags)
{
struct ext3_inode_info *ei = (struct ext3_inode_info *) foo;
#ifdef CONFIG_EXT3_FS_XATTR
init_rwsem(&ei->xattr_sem);
#endif
- init_MUTEX(&ei->truncate_sem);
+ 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,
+ 0, (SLAB_RECLAIM_ACCOUNT|
+ SLAB_MEM_SPREAD),
init_once, NULL);
if (ext3_inode_cachep == NULL)
return -ENOMEM;
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);
}
-#ifdef CONFIG_EXT3_FS_POSIX_ACL
-
static void ext3_clear_inode(struct inode *inode)
{
- 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;
- }
+ struct ext3_block_alloc_info *rsv = EXT3_I(inode)->i_block_alloc_info;
+#ifdef CONFIG_EXT3_FS_POSIX_ACL
+ if (EXT3_I(inode)->i_acl &&
+ EXT3_I(inode)->i_acl != EXT3_ACL_NOT_CACHED) {
+ posix_acl_release(EXT3_I(inode)->i_acl);
+ EXT3_I(inode)->i_acl = EXT3_ACL_NOT_CACHED;
+ }
+ if (EXT3_I(inode)->i_default_acl &&
+ EXT3_I(inode)->i_default_acl != EXT3_ACL_NOT_CACHED) {
+ posix_acl_release(EXT3_I(inode)->i_default_acl);
+ EXT3_I(inode)->i_default_acl = EXT3_ACL_NOT_CACHED;
+ }
+#endif
+ ext3_discard_reservation(inode);
+ EXT3_I(inode)->i_block_alloc_info = NULL;
+ if (unlikely(rsv))
+ kfree(rsv);
}
-#else
-# define ext3_clear_inode NULL
+static inline void ext3_show_quota_options(struct seq_file *seq, struct super_block *sb)
+{
+#if defined(CONFIG_QUOTA)
+ struct ext3_sb_info *sbi = EXT3_SB(sb);
+
+ if (sbi->s_jquota_fmt)
+ seq_printf(seq, ",jqfmt=%s",
+ (sbi->s_jquota_fmt == QFMT_VFS_OLD) ? "vfsold": "vfsv0");
+
+ if (sbi->s_qf_names[USRQUOTA])
+ seq_printf(seq, ",usrjquota=%s", sbi->s_qf_names[USRQUOTA]);
+
+ if (sbi->s_qf_names[GRPQUOTA])
+ seq_printf(seq, ",grpjquota=%s", sbi->s_qf_names[GRPQUOTA]);
+
+ if (sbi->s_mount_opt & EXT3_MOUNT_USRQUOTA)
+ seq_puts(seq, ",usrquota");
+
+ if (sbi->s_mount_opt & EXT3_MOUNT_GRPQUOTA)
+ seq_puts(seq, ",grpquota");
#endif
+}
-#ifdef CONFIG_QUOTA
+static int ext3_show_options(struct seq_file *seq, struct vfsmount *vfs)
+{
+ struct super_block *sb = vfs->mnt_sb;
+
+ if (test_opt(sb, DATA_FLAGS) == EXT3_MOUNT_JOURNAL_DATA)
+ seq_puts(seq, ",data=journal");
+ else if (test_opt(sb, DATA_FLAGS) == EXT3_MOUNT_ORDERED_DATA)
+ seq_puts(seq, ",data=ordered");
+ else if (test_opt(sb, DATA_FLAGS) == EXT3_MOUNT_WRITEBACK_DATA)
+ seq_puts(seq, ",data=writeback");
+ ext3_show_quota_options(seq, sb);
+
+ return 0;
+}
+
+
+static struct dentry *ext3_get_dentry(struct super_block *sb, void *vobjp)
+{
+ __u32 *objp = vobjp;
+ unsigned long ino = objp[0];
+ __u32 generation = objp[1];
+ struct inode *inode;
+ struct dentry *result;
+
+ if (ino < EXT3_FIRST_INO(sb) && ino != EXT3_ROOT_INO)
+ return ERR_PTR(-ESTALE);
+ 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 = iget(sb, ino);
+ if (inode == NULL)
+ return ERR_PTR(-ENOMEM);
+ if (is_bad_inode(inode) ||
+ (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;
+}
+
+#ifdef CONFIG_QUOTA
#define QTYPE2NAME(t) ((t)==USRQUOTA?"user":"group")
#define QTYPE2MOPT(on, t) ((t)==USRQUOTA?((on)##USRJQUOTA):((on)##GRPJQUOTA))
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_mount(struct super_block *sb, int type);
-static int ext3_quota_off_mount(struct super_block *sb, int type);
+static ssize_t ext3_quota_read(struct super_block *sb, int type, char *data,
+ size_t len, loff_t off);
+static ssize_t ext3_quota_write(struct super_block *sb, int type,
+ const char *data, size_t len, loff_t off);
static struct dquot_operations ext3_quota_operations = {
.initialize = ext3_dquot_initialize,
.read_inode = ext3_read_inode,
.write_inode = ext3_write_inode,
.dirty_inode = ext3_dirty_inode,
- .put_inode = ext3_put_inode,
.delete_inode = ext3_delete_inode,
.put_super = ext3_put_super,
.write_super = ext3_write_super,
.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,
+ .quota_write = ext3_quota_write,
+#endif
};
-struct dentry *ext3_get_parent(struct dentry *child);
static struct export_operations ext3_export_ops = {
.get_parent = ext3_get_parent,
+ .get_dentry = ext3_get_dentry,
};
enum {
Opt_bsd_df, Opt_minix_df, Opt_grpid, Opt_nogrpid,
Opt_resgid, Opt_resuid, Opt_sb, Opt_err_cont, Opt_err_panic, Opt_err_ro,
- Opt_nouid32, Opt_check, Opt_nocheck, Opt_debug, Opt_oldalloc, Opt_orlov,
- Opt_user_xattr, Opt_nouser_xattr, Opt_acl, Opt_noacl, Opt_noload,
- Opt_commit, Opt_journal_update, Opt_journal_inum,
+ 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_bh,
+ Opt_commit, Opt_journal_update, Opt_journal_inum, Opt_journal_dev,
Opt_abort, Opt_data_journal, Opt_data_ordered, Opt_data_writeback,
Opt_usrjquota, Opt_grpjquota, Opt_offusrjquota, Opt_offgrpjquota,
- Opt_jqfmt_vfsold, Opt_jqfmt_vfsv0,
- Opt_tagxid, Opt_barrier, Opt_ignore, Opt_err,
+ Opt_jqfmt_vfsold, Opt_jqfmt_vfsv0, Opt_quota, Opt_noquota,
+ Opt_ignore, Opt_barrier, Opt_err, Opt_resize, Opt_usrquota,
+ Opt_grpquota, Opt_tag, Opt_notag, Opt_tagid
};
static match_table_t tokens = {
{Opt_nouid32, "nouid32"},
{Opt_nocheck, "nocheck"},
{Opt_nocheck, "check=none"},
- {Opt_check, "check"},
{Opt_debug, "debug"},
{Opt_oldalloc, "oldalloc"},
{Opt_orlov, "orlov"},
{Opt_nouser_xattr, "nouser_xattr"},
{Opt_acl, "acl"},
{Opt_noacl, "noacl"},
+ {Opt_reservation, "reservation"},
+ {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_journal_dev, "journal_dev=%u"},
{Opt_abort, "abort"},
{Opt_data_journal, "data=journal"},
{Opt_data_ordered, "data=ordered"},
{Opt_grpjquota, "grpjquota=%s"},
{Opt_jqfmt_vfsold, "jqfmt=vfsold"},
{Opt_jqfmt_vfsv0, "jqfmt=vfsv0"},
- {Opt_tagxid, "tagxid"},
- {Opt_ignore, "grpquota"},
- {Opt_ignore, "noquota"},
- {Opt_ignore, "quota"},
- {Opt_ignore, "usrquota"},
+ {Opt_grpquota, "grpquota"},
+ {Opt_noquota, "noquota"},
+ {Opt_quota, "quota"},
+ {Opt_usrquota, "usrquota"},
{Opt_barrier, "barrier=%u"},
- {Opt_err, NULL}
+ {Opt_tag, "tag"},
+ {Opt_notag, "notag"},
+ {Opt_tagid, "tagid=%u"},
+ {Opt_tag, "tagxid"},
+ {Opt_err, NULL},
+ {Opt_resize, "resize"},
};
-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",
return sb_block;
}
-static int parse_options (char * options, struct super_block *sb,
- unsigned long * inum, int is_remount)
+static int parse_options (char *options, struct super_block *sb,
+ 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 option;
#ifdef CONFIG_QUOTA
int qtype;
+ char *qname;
#endif
if (!options)
case Opt_nouid32:
set_opt (sbi->s_mount_opt, NO_UID32);
break;
-#ifndef CONFIG_INOXID_NONE
- case Opt_tagxid:
- if (is_remount) {
- printk(KERN_ERR "EXT3-fs: cannot specify "
- "tagxid on remount\n");
- return 0;
- }
- set_opt (sbi->s_mount_opt, TAG_XID);
+#ifndef CONFIG_TAGGING_NONE
+ case Opt_tag:
+ set_opt (sbi->s_mount_opt, TAGGED);
+ break;
+ case Opt_notag:
+ clear_opt (sbi->s_mount_opt, TAGGED);
break;
#endif
- case Opt_check:
-#ifdef CONFIG_EXT3_CHECK
- set_opt (sbi->s_mount_opt, CHECK);
-#else
- printk(KERN_ERR
- "EXT3 Check option not supported\n");
-#endif
+#ifdef CONFIG_PROPAGATE
+ case Opt_tagid:
+ /* use args[0] */
+ set_opt (sbi->s_mount_opt, TAGGED);
break;
+#endif
case Opt_nocheck:
clear_opt (sbi->s_mount_opt, CHECK);
break;
printk("EXT3 (no)acl options not supported\n");
break;
#endif
+ case Opt_reservation:
+ set_opt(sbi->s_mount_opt, RESERVATION);
+ break;
+ case Opt_noreservation:
+ clear_opt(sbi->s_mount_opt, RESERVATION);
+ break;
case Opt_journal_update:
/* @@@ FIXME */
/* Eventually we will want to be able to create
return 0;
*inum = option;
break;
+ case Opt_journal_dev:
+ if (is_remount) {
+ printk(KERN_ERR "EXT3-fs: cannot specify "
+ "journal on remount\n");
+ return 0;
+ }
+ if (match_int(&args[0], &option))
+ return 0;
+ *journal_devnum = option;
+ break;
case Opt_noload:
set_opt (sbi->s_mount_opt, NOLOAD);
break;
"quota options when quota turned on.\n");
return 0;
}
- if (sbi->s_qf_names[qtype]) {
+ qname = match_strdup(&args[0]);
+ if (!qname) {
printk(KERN_ERR
- "EXT3-fs: %s quota file already "
- "specified.\n", QTYPE2NAME(qtype));
+ "EXT3-fs: not enough memory for "
+ "storing quotafile name.\n");
return 0;
}
- sbi->s_qf_names[qtype] = match_strdup(&args[0]);
- if (!sbi->s_qf_names[qtype]) {
+ if (sbi->s_qf_names[qtype] &&
+ strcmp(sbi->s_qf_names[qtype], qname)) {
printk(KERN_ERR
- "EXT3-fs: not enough memory for "
- "storing quotafile name.\n");
+ "EXT3-fs: %s quota file already "
+ "specified.\n", QTYPE2NAME(qtype));
+ kfree(qname);
return 0;
}
+ sbi->s_qf_names[qtype] = qname;
if (strchr(sbi->s_qf_names[qtype], '/')) {
printk(KERN_ERR
"EXT3-fs: quotafile must be on "
sbi->s_qf_names[qtype] = NULL;
return 0;
}
+ set_opt(sbi->s_mount_opt, QUOTA);
break;
case Opt_offusrjquota:
qtype = USRQUOTA;
"quota turned on.\n");
return 0;
}
- if (sbi->s_qf_names[qtype]) {
- kfree(sbi->s_qf_names[qtype]);
- sbi->s_qf_names[qtype] = NULL;
- }
+ /*
+ * The space will be released later when all options
+ * are confirmed to be correct
+ */
+ sbi->s_qf_names[qtype] = NULL;
break;
case Opt_jqfmt_vfsold:
sbi->s_jquota_fmt = QFMT_VFS_OLD;
case Opt_jqfmt_vfsv0:
sbi->s_jquota_fmt = QFMT_VFS_V0;
break;
+ case Opt_quota:
+ case Opt_usrquota:
+ set_opt(sbi->s_mount_opt, QUOTA);
+ set_opt(sbi->s_mount_opt, USRQUOTA);
+ break;
+ case Opt_grpquota:
+ set_opt(sbi->s_mount_opt, QUOTA);
+ set_opt(sbi->s_mount_opt, GRPQUOTA);
+ break;
+ case Opt_noquota:
+ if (sb_any_quota_enabled(sb)) {
+ printk(KERN_ERR "EXT3-fs: Cannot change quota "
+ "options when quota turned on.\n");
+ return 0;
+ }
+ clear_opt(sbi->s_mount_opt, QUOTA);
+ clear_opt(sbi->s_mount_opt, USRQUOTA);
+ clear_opt(sbi->s_mount_opt, GRPQUOTA);
+ break;
#else
+ case Opt_quota:
+ case Opt_usrquota:
+ case Opt_grpquota:
case Opt_usrjquota:
case Opt_grpjquota:
case Opt_offusrjquota:
"EXT3-fs: journalled quota options not "
"supported.\n");
break;
+ case Opt_noquota:
+ break;
#endif
case Opt_abort:
set_opt(sbi->s_mount_opt, ABORT);
break;
case Opt_ignore:
break;
+ case Opt_resize:
+ if (!is_remount) {
+ printk("EXT3-fs: resize option only available "
+ "for remount\n");
+ return 0;
+ }
+ if (match_int(&args[0], &option) != 0)
+ return 0;
+ *n_blocks_count = option;
+ break;
+ 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\" "
}
}
#ifdef CONFIG_QUOTA
- if (!sbi->s_jquota_fmt && (sbi->s_qf_names[USRQUOTA] ||
- sbi->s_qf_names[GRPQUOTA])) {
- printk(KERN_ERR
- "EXT3-fs: journalled quota format not specified.\n");
- return 0;
+ if (sbi->s_qf_names[USRQUOTA] || sbi->s_qf_names[GRPQUOTA]) {
+ if ((sbi->s_mount_opt & EXT3_MOUNT_USRQUOTA) &&
+ sbi->s_qf_names[USRQUOTA])
+ clear_opt(sbi->s_mount_opt, USRQUOTA);
+
+ if ((sbi->s_mount_opt & EXT3_MOUNT_GRPQUOTA) &&
+ sbi->s_qf_names[GRPQUOTA])
+ clear_opt(sbi->s_mount_opt, GRPQUOTA);
+
+ if ((sbi->s_qf_names[USRQUOTA] &&
+ (sbi->s_mount_opt & EXT3_MOUNT_GRPQUOTA)) ||
+ (sbi->s_qf_names[GRPQUOTA] &&
+ (sbi->s_mount_opt & EXT3_MOUNT_USRQUOTA))) {
+ printk(KERN_ERR "EXT3-fs: old and new quota "
+ "format mixing.\n");
+ return 0;
+ }
+
+ if (!sbi->s_jquota_fmt) {
+ printk(KERN_ERR "EXT3-fs: journalled 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 "
+ "enabled.\n");
+ return 0;
+ }
}
#endif
-
return 1;
}
} else {
printk("internal journal\n");
}
-#ifdef CONFIG_EXT3_CHECK
- if (test_opt (sb, CHECK)) {
- ext3_check_blocks_bitmap (sb);
- ext3_check_inodes_bitmap (sb);
- }
-#endif
return res;
}
+/* Called at mount-time, super-block is locked */
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);
+ ext3_fsblk_t first_block = le32_to_cpu(sbi->s_es->s_first_data_block);
+ ext3_fsblk_t last_block;
struct ext3_group_desc * gdp = NULL;
int desc_block = 0;
int i;
for (i = 0; i < sbi->s_groups_count; i++)
{
+ if (i == sbi->s_groups_count - 1)
+ last_block = le32_to_cpu(sbi->s_es->s_blocks_count) - 1;
+ else
+ last_block = first_block +
+ (EXT3_BLOCKS_PER_GROUP(sb) - 1);
+
if ((i % EXT3_DESC_PER_BLOCK(sb)) == 0)
gdp = (struct ext3_group_desc *)
sbi->s_group_desc[desc_block++]->b_data;
- if (le32_to_cpu(gdp->bg_block_bitmap) < block ||
- le32_to_cpu(gdp->bg_block_bitmap) >=
- block + EXT3_BLOCKS_PER_GROUP(sb))
+ 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 >
+ 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);
+ first_block += EXT3_BLOCKS_PER_GROUP(sb);
gdp++;
}
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, "
DQUOT_INIT(inode);
if (inode->i_nlink) {
printk(KERN_DEBUG
- "%s: truncating inode %ld to %Ld bytes\n",
+ "%s: truncating inode %lu to %Ld bytes\n",
__FUNCTION__, inode->i_ino, inode->i_size);
- jbd_debug(2, "truncating inode %ld to %Ld bytes\n",
+ 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",
+ "%s: deleting unreferenced inode %lu\n",
__FUNCTION__, inode->i_ino);
- jbd_debug(2, "deleting unreferenced inode %ld\n",
+ 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])
- ext3_quota_off_mount(sb, i);
+ vfs_quota_off(sb, i);
}
#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
+ * sectors in the file, including data and all indirect blocks,
+ * does not exceed 2^32. */
+ const loff_t upper_limit = 0x1ff7fffd000LL;
+
res += 1LL << (bits-2);
res += 1LL << (2*(bits-2));
res += 1LL << (3*(bits-2));
res <<= bits;
- if (res > (512LL << 32) - (1 << bits))
- res = (512LL << 32) - (1 << bits);
+ if (res > upper_limit)
+ res = upper_limit;
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 blocksize;
int needs_recovery;
__le32 features;
- sbi = kmalloc(sizeof(*sbi), GFP_KERNEL);
+ sbi = kzalloc(sizeof(*sbi), GFP_KERNEL);
if (!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;
+ unlock_kernel();
+
blocksize = sb_min_blocksize(sb, EXT3_MIN_BLOCK_SIZE);
if (!blocksize) {
printk(KERN_ERR "EXT3-fs: unable to set blocksize\n");
es = (struct ext3_super_block *) (((char *)bh->b_data) + offset);
sbi->s_es = es;
sb->s_magic = le16_to_cpu(es->s_magic);
- if (sb->s_magic != EXT3_SUPER_MAGIC) {
- if (!silent)
- printk(KERN_ERR
- "VFS: Can't find ext3 filesystem on dev %s.\n",
- sb->s_id);
- goto failed_mount;
- }
+ if (sb->s_magic != EXT3_SUPER_MAGIC)
+ goto cantfind_ext3;
/* Set defaults before we parse the mount options */
def_mount_opts = le32_to_cpu(es->s_default_mount_opts);
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)
set_opt(sbi->s_mount_opt, ERRORS_PANIC);
else if (le16_to_cpu(sbi->s_es->s_errors) == EXT3_ERRORS_RO)
set_opt(sbi->s_mount_opt, ERRORS_RO);
+ else
+ set_opt(sbi->s_mount_opt, ERRORS_CONT);
sbi->s_resuid = le16_to_cpu(es->s_def_resuid);
sbi->s_resgid = le16_to_cpu(es->s_def_resgid);
- if (!parse_options ((char *) data, sb, &journal_inum, 0))
+ set_opt(sbi->s_mount_opt, RESERVATION);
+
+ if (!parse_options ((char *) data, sb, &journal_inum, &journal_devnum,
+ NULL, 0))
goto failed_mount;
- if (EXT3_SB(sb)->s_mount_opt & EXT3_MOUNT_TAG_XID)
- sb->s_flags |= MS_TAGXID;
- sb->s_flags |= MS_ONE_SECOND;
+ if (EXT3_SB(sb)->s_mount_opt & EXT3_MOUNT_TAGGED)
+ sb->s_flags |= MS_TAGGED;
+
sb->s_flags = (sb->s_flags & ~MS_POSIXACL) |
((sbi->s_mount_opt & EXT3_MOUNT_POSIX_ACL) ? MS_POSIXACL : 0);
(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;
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_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)
+ goto cantfind_ext3;
sbi->s_inodes_per_block = blocksize / EXT3_INODE_SIZE(sb);
- sbi->s_itb_per_group = sbi->s_inodes_per_group /sbi->s_inodes_per_block;
+ if (sbi->s_inodes_per_block == 0)
+ goto cantfind_ext3;
+ sbi->s_itb_per_group = sbi->s_inodes_per_group /
+ sbi->s_inodes_per_block;
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;
goto failed_mount;
}
- 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);
+ 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) - 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 *),
printk (KERN_ERR "EXT3-fs: not enough memory\n");
goto failed_mount;
}
- sbi->s_debts = kmalloc(sbi->s_groups_count * sizeof(u8),
- GFP_KERNEL);
- if (!sbi->s_debts) {
- printk("EXT3-fs: not enough memory to allocate s_bgi\n");
- goto failed_mount2;
- }
- memset(sbi->s_debts, 0, sbi->s_groups_count * sizeof(u8));
- 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);
for (i = 0; i < db_count; 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);
+
+ percpu_counter_init(&sbi->s_freeblocks_counter,
+ ext3_count_free_blocks(sb));
+ percpu_counter_init(&sbi->s_freeinodes_counter,
+ ext3_count_free_inodes(sb));
+ percpu_counter_init(&sbi->s_dirs_counter,
+ ext3_count_dirs(sb));
+
+ /* 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 = EXT3_RESERVE_WINDOW_NOT_ALLOCATED;
+ sbi->s_rsv_window_head.rsv_end = EXT3_RESERVE_WINDOW_NOT_ALLOCATED;
+ sbi->s_rsv_window_head.rsv_alloc_hit = 0;
+ sbi->s_rsv_window_head.rsv_goal_size = 0;
+ ext3_rsv_window_add(sb, &sbi->s_rsv_window_head);
+
/*
* set up enough so that it can read an inode
*/
sb->s_op = &ext3_sops;
sb->s_export_op = &ext3_export_ops;
+ sb->s_xattr = ext3_xattr_handlers;
#ifdef CONFIG_QUOTA
sb->s_qcop = &ext3_qctl_operations;
sb->dq_op = &ext3_quota_operations;
*/
if (!test_opt(sb, NOLOAD) &&
EXT3_HAS_COMPAT_FEATURE(sb, EXT3_FEATURE_COMPAT_HAS_JOURNAL)) {
- if (ext3_load_journal(sb, es))
- goto failed_mount2;
+ if (ext3_load_journal(sb, es, journal_devnum))
+ 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 (!(test_opt(sb, DATA_FLAGS) == EXT3_MOUNT_WRITEBACK_DATA)) {
+ printk(KERN_WARNING "EXT3-fs: Ignoring nobh option - "
+ "its supported only with writeback mode\n");
+ 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.
if (!sb->s_root) {
printk(KERN_ERR "EXT3-fs: get root inode failed\n");
iput(root);
- goto failed_mount3;
+ goto failed_mount4;
}
if (!S_ISDIR(root->i_mode) || !root->i_blocks || !root->i_size) {
dput(sb->s_root);
sb->s_root = NULL;
printk(KERN_ERR "EXT3-fs: corrupt root inode, run e2fsck\n");
- goto failed_mount3;
+ 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;
-failed_mount3:
+cantfind_ext3:
+ if (!silent)
+ printk(KERN_ERR "VFS: Can't find ext3 filesystem on dev %s.\n",
+ 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);
failed_mount2:
- kfree(sbi->s_debts);
for (i = 0; i < db_count; i++)
brelse(sbi->s_group_desc[i]);
kfree(sbi->s_group_desc);
failed_mount:
#ifdef CONFIG_QUOTA
- for (i = 0; i < MAXQUOTAS; i++) {
- if (sbi->s_qf_names[i])
- kfree(sbi->s_qf_names[i]);
- }
+ for (i = 0; i < MAXQUOTAS; i++)
+ kfree(sbi->s_qf_names[i]);
#endif
ext3_blkdev_remove(sbi);
brelse(bh);
out_fail:
sb->s_fs_info = NULL;
kfree(sbi);
+ lock_kernel();
return -EINVAL;
}
/*
* 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)
{
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;
{
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;
return NULL;
}
-static int ext3_load_journal(struct super_block * sb,
- struct ext3_super_block * es)
+static int ext3_load_journal(struct super_block *sb,
+ struct ext3_super_block *es,
+ unsigned long journal_devnum)
{
journal_t *journal;
- int journal_inum = le32_to_cpu(es->s_journal_inum);
- dev_t journal_dev = new_decode_dev(le32_to_cpu(es->s_journal_dev));
+ unsigned int journal_inum = le32_to_cpu(es->s_journal_inum);
+ dev_t journal_dev;
int err = 0;
int really_read_only;
+ if (journal_devnum &&
+ journal_devnum != le32_to_cpu(es->s_journal_dev)) {
+ printk(KERN_INFO "EXT3-fs: external journal device major/minor "
+ "numbers have changed\n");
+ journal_dev = new_decode_dev(journal_devnum);
+ } else
+ journal_dev = new_decode_dev(le32_to_cpu(es->s_journal_dev));
+
really_read_only = bdev_read_only(sb->s_bdev);
/*
EXT3_SB(sb)->s_journal = journal;
ext3_clear_journal_err(sb, es);
+
+ if (journal_devnum &&
+ journal_devnum != le32_to_cpu(es->s_journal_dev)) {
+ es->s_journal_dev = cpu_to_le32(journal_devnum);
+ sb->s_dirt = 1;
+
+ /* Make sure we flush the recovery flag to disk. */
+ ext3_commit_super(sb, es, 1);
+ }
+
return 0;
}
static int ext3_create_journal(struct super_block * sb,
struct ext3_super_block * es,
- int journal_inum)
+ unsigned int journal_inum)
{
journal_t *journal;
if (!(journal = ext3_get_journal(sb, journal_inum)))
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)) {
* This implicitly triggers the writebehind on sync().
*/
-void ext3_write_super (struct super_block * sb)
+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.
*/
-void ext3_write_super_lockfs(struct super_block *sb)
+static void ext3_write_super_lockfs(struct super_block *sb)
{
sb->s_dirt = 0;
* 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.
*/
-void ext3_unlockfs(struct super_block *sb)
+static void ext3_unlockfs(struct super_block *sb)
{
if (!(sb->s_flags & MS_RDONLY)) {
lock_super(sb);
}
}
-int ext3_remount (struct super_block * sb, int * flags, char * data)
+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 tmp;
+ ext3_fsblk_t n_blocks_count = 0;
+ unsigned long old_sb_flags;
+ struct ext3_mount_options old_opts;
+ int err;
+#ifdef CONFIG_QUOTA
+ int i;
+#endif
+
+ /* Store the original options */
+ old_sb_flags = sb->s_flags;
+ old_opts.s_mount_opt = sbi->s_mount_opt;
+ old_opts.s_resuid = sbi->s_resuid;
+ old_opts.s_resgid = sbi->s_resgid;
+ old_opts.s_commit_interval = sbi->s_commit_interval;
+#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];
+#endif
/*
* Allow the "check" option to be passed as a remount option.
*/
- if (!parse_options(data, sb, &tmp, 1))
- return -EINVAL;
+ if (!parse_options(data, sb, NULL, NULL, &n_blocks_count, 1)) {
+ err = -EINVAL;
+ goto restore_opts;
+ }
if (sbi->s_mount_opt & EXT3_MOUNT_ABORT)
ext3_abort(sb, __FUNCTION__, "Abort forced by user");
+ if ((sbi->s_mount_opt & EXT3_MOUNT_TAGGED) &&
+ !(sb->s_flags & MS_TAGGED)) {
+ printk("EXT3-fs: %s: tagging not permitted on remount.\n",
+ sb->s_id);
+ return -EINVAL;
+ }
sb->s_flags = (sb->s_flags & ~MS_POSIXACL) |
((sbi->s_mount_opt & EXT3_MOUNT_POSIX_ACL) ? MS_POSIXACL : 0);
ext3_init_journal_params(sb, sbi->s_journal);
- if ((*flags & MS_RDONLY) != (sb->s_flags & MS_RDONLY)) {
- if (sbi->s_mount_opt & EXT3_MOUNT_ABORT)
- return -EROFS;
+ if ((*flags & MS_RDONLY) != (sb->s_flags & MS_RDONLY) ||
+ n_blocks_count > le32_to_cpu(es->s_blocks_count)) {
+ if (sbi->s_mount_opt & EXT3_MOUNT_ABORT) {
+ err = -EROFS;
+ goto restore_opts;
+ }
if (*flags & MS_RDONLY) {
/*
"remount RDWR because of unsupported "
"optional features (%x).\n",
sb->s_id, le32_to_cpu(ret));
- return -EROFS;
+ err = -EROFS;
+ goto restore_opts;
}
/*
* Mounting a RDONLY partition read-write, so reread
*/
ext3_clear_journal_err(sb, es);
sbi->s_mount_state = le16_to_cpu(es->s_state);
+ 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;
}
}
+#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]);
+#endif
return 0;
+restore_opts:
+ sb->s_flags = old_sb_flags;
+ sbi->s_mount_opt = old_opts.s_mount_opt;
+ sbi->s_resuid = old_opts.s_resuid;
+ sbi->s_resgid = old_opts.s_resgid;
+ sbi->s_commit_interval = old_opts.s_commit_interval;
+#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]);
+ sbi->s_qf_names[i] = old_opts.s_qf_names[i];
+ }
+#endif
+ return err;
}
-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;
+ struct super_block *sb = dentry->d_sb;
+ struct ext3_sb_info *sbi = EXT3_SB(sb);
+ struct ext3_super_block *es = sbi->s_es;
+ ext3_fsblk_t overhead;
int i;
+ u64 fsid;
if (test_opt (sb, MINIX_DF))
overhead = 0;
else {
+ unsigned long ngroups;
+ ngroups = EXT3_SB(sb)->s_groups_count;
+ smp_rmb();
+
/*
* Compute the overhead (FS structures)
*/
* block group descriptors. If the sparse superblocks
* feature is turned on, then not all groups have this.
*/
- for (i = 0; i < EXT3_SB(sb)->s_groups_count; i++)
+ for (i = 0; i < ngroups; i++) {
overhead += ext3_bg_has_super(sb, i) +
ext3_bg_num_gdb(sb, i);
+ cond_resched();
+ }
/*
* Every block group has an inode bitmap, a block
* bitmap, and an inode table.
*/
- overhead += (EXT3_SB(sb)->s_groups_count *
- (2 + EXT3_SB(sb)->s_itb_per_group));
+ overhead += (ngroups * (2 + EXT3_SB(sb)->s_itb_per_group));
}
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_bfree = percpu_counter_sum(&sbi->s_freeblocks_counter);
buf->f_bavail = buf->f_bfree - le32_to_cpu(es->s_r_blocks_count);
if (buf->f_bfree < le32_to_cpu(es->s_r_blocks_count))
buf->f_bavail = 0;
buf->f_files = le32_to_cpu(es->s_inodes_count);
- buf->f_ffree = ext3_count_free_inodes (sb);
+ buf->f_ffree = percpu_counter_sum(&sbi->s_freeinodes_counter);
buf->f_namelen = EXT3_NAME_LEN;
+ fsid = le64_to_cpup((void *)es->s_uuid) ^
+ le64_to_cpup((void *)es->s_uuid + sizeof(u64));
+ 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()
*
*/
static inline struct inode *dquot_to_inode(struct dquot *dquot)
{
- return sb_dqopt(dquot->dq_sb)->files[dquot->dq_type]->f_dentry->d_inode;
+ return sb_dqopt(dquot->dq_sb)->files[dquot->dq_type];
}
static int ext3_dquot_initialize(struct inode *inode, int type)
int ret, err;
/* We may create quota structure so we need to reserve enough blocks */
- handle = ext3_journal_start(inode, 2*EXT3_QUOTA_INIT_BLOCKS);
+ handle = ext3_journal_start(inode, 2*EXT3_QUOTA_INIT_BLOCKS(inode->i_sb));
if (IS_ERR(handle))
return PTR_ERR(handle);
ret = dquot_initialize(inode, type);
int ret, err;
/* We may delete quota structure so we need to reserve enough blocks */
- handle = ext3_journal_start(inode, 2*EXT3_QUOTA_INIT_BLOCKS);
+ handle = ext3_journal_start(inode, 2*EXT3_QUOTA_DEL_BLOCKS(inode->i_sb));
if (IS_ERR(handle))
return PTR_ERR(handle);
ret = dquot_drop(inode);
{
int ret, err;
handle_t *handle;
+ struct inode *inode;
- handle = ext3_journal_start(dquot_to_inode(dquot),
- EXT3_QUOTA_TRANS_BLOCKS);
+ inode = dquot_to_inode(dquot);
+ handle = ext3_journal_start(inode,
+ EXT3_QUOTA_TRANS_BLOCKS(dquot->dq_sb));
if (IS_ERR(handle))
return PTR_ERR(handle);
ret = dquot_commit(dquot);
handle_t *handle;
handle = ext3_journal_start(dquot_to_inode(dquot),
- EXT3_QUOTA_INIT_BLOCKS);
+ EXT3_QUOTA_INIT_BLOCKS(dquot->dq_sb));
if (IS_ERR(handle))
return PTR_ERR(handle);
ret = dquot_acquire(dquot);
handle_t *handle;
handle = ext3_journal_start(dquot_to_inode(dquot),
- EXT3_QUOTA_INIT_BLOCKS);
+ EXT3_QUOTA_DEL_BLOCKS(dquot->dq_sb));
if (IS_ERR(handle))
return PTR_ERR(handle);
ret = dquot_release(dquot);
*/
static int ext3_quota_on_mount(struct super_block *sb, int type)
{
- int err;
- struct dentry *dentry;
- struct qstr name = { .name = EXT3_SB(sb)->s_qf_names[type],
- .hash = 0,
- .len = strlen(EXT3_SB(sb)->s_qf_names[type])};
-
- dentry = lookup_hash(&name, sb->s_root);
- if (IS_ERR(dentry))
- return PTR_ERR(dentry);
- err = vfs_quota_on_mount(type, EXT3_SB(sb)->s_jquota_fmt, dentry);
- if (err)
- dput(dentry);
- /* We keep the dentry reference if everything went ok - we drop it
- * on quota_off time */
- return err;
-}
-
-/* Turn quotas off during mount time */
-static int ext3_quota_off_mount(struct super_block *sb, int type)
-{
- int err;
- struct dentry *dentry;
-
- dentry = sb_dqopt(sb)->files[type]->f_dentry;
- err = vfs_quota_off_mount(sb, type);
- /* We invalidate dentry - it has at least wrong hash... */
- d_invalidate(dentry);
- dput(dentry);
- return err;
+ return vfs_quota_on_mount(sb, EXT3_SB(sb)->s_qf_names[type],
+ EXT3_SB(sb)->s_jquota_fmt, type);
}
/*
int err;
struct nameidata nd;
+ 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])
if (err)
return err;
/* Quotafile not on the same filesystem? */
- if (nd.mnt->mnt_sb != sb)
+ if (nd.mnt->mnt_sb != sb) {
+ path_release(&nd);
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");
- if (!ext3_should_journal_data(nd.dentry->d_inode))
- printk(KERN_WARNING "EXT3-fs: Quota file does not have "
- "data-journalling. Journalled quota will not work.\n");
path_release(&nd);
return vfs_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)
+ * 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)
+{
+ struct inode *inode = sb_dqopt(sb)->files[type];
+ sector_t blk = off >> EXT3_BLOCK_SIZE_BITS(sb);
+ int err = 0;
+ int offset = off & (sb->s_blocksize - 1);
+ int tocopy;
+ size_t toread;
+ struct buffer_head *bh;
+ loff_t i_size = i_size_read(inode);
+
+ if (off > i_size)
+ return 0;
+ if (off+len > i_size)
+ len = i_size-off;
+ toread = len;
+ while (toread > 0) {
+ tocopy = sb->s_blocksize - offset < toread ?
+ sb->s_blocksize - offset : toread;
+ bh = ext3_bread(NULL, inode, blk, 0, &err);
+ if (err)
+ return err;
+ if (!bh) /* A hole? */
+ memset(data, 0, tocopy);
+ else
+ memcpy(data, bh->b_data+offset, tocopy);
+ brelse(bh);
+ offset = 0;
+ toread -= tocopy;
+ data += tocopy;
+ blk++;
+ }
+ return len;
+}
+
+/* Write to quotafile (we know the transaction is already started and has
+ * enough credits) */
+static ssize_t ext3_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 >> EXT3_BLOCK_SIZE_BITS(sb);
+ int err = 0;
+ int offset = off & (sb->s_blocksize - 1);
+ int tocopy;
+ int journal_quota = EXT3_SB(sb)->s_qf_names[type] != NULL;
+ size_t towrite = len;
+ struct buffer_head *bh;
+ handle_t *handle = journal_current_handle();
+
+ mutex_lock_nested(&inode->i_mutex, I_MUTEX_QUOTA);
+ while (towrite > 0) {
+ tocopy = sb->s_blocksize - offset < towrite ?
+ sb->s_blocksize - offset : towrite;
+ bh = ext3_bread(handle, inode, blk, 1, &err);
+ if (!bh)
+ goto out;
+ if (journal_quota) {
+ err = ext3_journal_get_write_access(handle, bh);
+ if (err) {
+ brelse(bh);
+ goto out;
+ }
+ }
+ lock_buffer(bh);
+ memcpy(bh->b_data+offset, data, tocopy);
+ flush_dcache_page(bh->b_page);
+ unlock_buffer(bh);
+ if (journal_quota)
+ err = ext3_journal_dirty_metadata(handle, bh);
+ else {
+ /* Always do at least ordered writes for quotas */
+ err = ext3_journal_dirty_data(handle, bh);
+ mark_buffer_dirty(bh);
+ }
+ brelse(bh);
+ if (err)
+ goto out;
+ offset = 0;
+ towrite -= tocopy;
+ data += tocopy;
+ blk++;
+ }
+out:
+ if (len == towrite)
+ 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);
+ 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;
}
git://git.onelab.eu / linux-2.6.git / blobdiff