#include <linux/seq_file.h>
#include <linux/proc_fs.h>
#include <linux/ctype.h>
-#include <linux/marker.h>
#include <linux/log2.h>
#include <linux/crc16.h>
#include <asm/uaccess.h>
#include "ext4_jbd2.h"
#include "xattr.h"
#include "acl.h"
+#include "mballoc.h"
-static int default_mb_history_length = 1000;
-
-module_param_named(default_mb_history_length, default_mb_history_length,
- int, 0644);
-MODULE_PARM_DESC(default_mb_history_length,
- "Default number of entries saved for mb_history");
+#define CREATE_TRACE_POINTS
+#include <trace/events/ext4.h>
struct proc_dir_entry *ext4_proc_root;
static struct kset *ext4_kset;
static int ext4_unfreeze(struct super_block *sb);
static void ext4_write_super(struct super_block *sb);
static int ext4_freeze(struct super_block *sb);
+static int ext4_get_sb(struct file_system_type *fs_type, int flags,
+ const char *dev_name, void *data, struct vfsmount *mnt);
+#if !defined(CONFIG_EXT3_FS) && !defined(CONFIG_EXT3_FS_MODULE) && defined(CONFIG_EXT4_USE_FOR_EXT23)
+static struct file_system_type ext3_fs_type = {
+ .owner = THIS_MODULE,
+ .name = "ext3",
+ .get_sb = ext4_get_sb,
+ .kill_sb = kill_block_super,
+ .fs_flags = FS_REQUIRES_DEV,
+};
+#define IS_EXT3_SB(sb) ((sb)->s_bdev->bd_holder == &ext3_fs_type)
+#else
+#define IS_EXT3_SB(sb) (0)
+#endif
ext4_fsblk_t ext4_block_bitmap(struct super_block *sb,
struct ext4_group_desc *bg)
bg->bg_itable_unused_hi = cpu_to_le16(count >> 16);
}
+
+/* Just increment the non-pointer handle value */
+static handle_t *ext4_get_nojournal(void)
+{
+ handle_t *handle = current->journal_info;
+ unsigned long ref_cnt = (unsigned long)handle;
+
+ BUG_ON(ref_cnt >= EXT4_NOJOURNAL_MAX_REF_COUNT);
+
+ ref_cnt++;
+ handle = (handle_t *)ref_cnt;
+
+ current->journal_info = handle;
+ return handle;
+}
+
+
+/* Decrement the non-pointer handle value */
+static void ext4_put_nojournal(handle_t *handle)
+{
+ unsigned long ref_cnt = (unsigned long)handle;
+
+ BUG_ON(ref_cnt == 0);
+
+ ref_cnt--;
+ handle = (handle_t *)ref_cnt;
+
+ current->journal_info = handle;
+}
+
/*
* Wrappers for jbd2_journal_start/end.
*
if (sb->s_flags & MS_RDONLY)
return ERR_PTR(-EROFS);
+ vfs_check_frozen(sb, SB_FREEZE_WRITE);
/* 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. */
}
return jbd2_journal_start(journal, nblocks);
}
- /*
- * We're not journaling, return the appropriate indication.
- */
- current->journal_info = EXT4_NOJOURNAL_HANDLE;
- return current->journal_info;
+ return ext4_get_nojournal();
}
/*
int rc;
if (!ext4_handle_valid(handle)) {
- /*
- * Do this here since we don't call jbd2_journal_stop() in
- * no-journal mode.
- */
- current->journal_info = NULL;
+ ext4_put_nojournal(handle);
return 0;
}
sb = handle->h_transaction->t_journal->j_private;
* write out the superblock safely.
*
* We'll just use the jbd2_journal_abort() error code to record an error in
- * the journal instead. On recovery, the journal will compain about
+ * the journal instead. On recovery, the journal will complain about
* that error until we've noted it down and cleared it.
*/
if (!test_opt(sb, ERRORS_CONT)) {
journal_t *journal = EXT4_SB(sb)->s_journal;
- EXT4_SB(sb)->s_mount_opt |= EXT4_MOUNT_ABORT;
+ EXT4_SB(sb)->s_mount_flags |= EXT4_MF_FS_ABORTED;
if (journal)
jbd2_journal_abort(journal, -EIO);
}
sb->s_id);
}
-void ext4_error(struct super_block *sb, const char *function,
+void __ext4_error(struct super_block *sb, const char *function,
const char *fmt, ...)
{
va_list args;
ext4_handle_error(sb);
}
+void ext4_error_inode(const char *function, struct inode *inode,
+ const char *fmt, ...)
+{
+ va_list args;
+
+ va_start(args, fmt);
+ printk(KERN_CRIT "EXT4-fs error (device %s): %s: inode #%lu: (comm %s) ",
+ inode->i_sb->s_id, function, inode->i_ino, current->comm);
+ vprintk(fmt, args);
+ printk("\n");
+ va_end(args);
+
+ ext4_handle_error(inode->i_sb);
+}
+
+void ext4_error_file(const char *function, struct file *file,
+ const char *fmt, ...)
+{
+ va_list args;
+ struct inode *inode = file->f_dentry->d_inode;
+ char pathname[80], *path;
+
+ va_start(args, fmt);
+ path = d_path(&(file->f_path), pathname, sizeof(pathname));
+ if (!path)
+ path = "(unknown)";
+ printk(KERN_CRIT
+ "EXT4-fs error (device %s): %s: inode #%lu (comm %s path %s): ",
+ inode->i_sb->s_id, function, inode->i_ino, current->comm, path);
+ vprintk(fmt, args);
+ printk("\n");
+ va_end(args);
+
+ ext4_handle_error(inode->i_sb);
+}
+
static const char *ext4_decode_error(struct super_block *sb, int errno,
char nbuf[16])
{
errstr = "Out of memory";
break;
case -EROFS:
- if (!sb || EXT4_SB(sb)->s_journal->j_flags & JBD2_ABORT)
+ if (!sb || (EXT4_SB(sb)->s_journal &&
+ EXT4_SB(sb)->s_journal->j_flags & JBD2_ABORT))
errstr = "Journal has aborted";
else
errstr = "Readonly filesystem";
ext4_msg(sb, KERN_CRIT, "Remounting filesystem read-only");
EXT4_SB(sb)->s_mount_state |= EXT4_ERROR_FS;
sb->s_flags |= MS_RDONLY;
- EXT4_SB(sb)->s_mount_opt |= EXT4_MOUNT_ABORT;
+ EXT4_SB(sb)->s_mount_flags |= EXT4_MF_FS_ABORTED;
if (EXT4_SB(sb)->s_journal)
jbd2_journal_abort(EXT4_SB(sb)->s_journal, -EIO);
}
va_end(args);
}
-void ext4_warning(struct super_block *sb, const char *function,
+void __ext4_warning(struct super_block *sb, const char *function,
const char *fmt, ...)
{
va_list args;
if (le32_to_cpu(es->s_rev_level) > EXT4_GOOD_OLD_REV)
return;
- ext4_warning(sb, __func__,
+ ext4_warning(sb,
"updating to rev %d because of new feature flag, "
"running e2fsck is recommended",
EXT4_DYNAMIC_REV);
struct ext4_super_block *es = sbi->s_es;
int i, err;
+ dquot_disable(sb, -1, DQUOT_USAGE_ENABLED | DQUOT_LIMITS_ENABLED);
+
+ flush_workqueue(sbi->dio_unwritten_wq);
+ destroy_workqueue(sbi->dio_unwritten_wq);
+
lock_super(sb);
+ lock_kernel();
if (sb->s_dirt)
- ext4_write_super(sb);
+ ext4_commit_super(sb, 1);
- ext4_release_system_zone(sb);
- ext4_mb_release(sb);
- ext4_ext_release(sb);
- ext4_xattr_put_super(sb);
if (sbi->s_journal) {
err = jbd2_journal_destroy(sbi->s_journal);
sbi->s_journal = NULL;
ext4_abort(sb, __func__,
"Couldn't clean up the journal");
}
+
+ ext4_release_system_zone(sb);
+ ext4_mb_release(sb);
+ ext4_ext_release(sb);
+ ext4_xattr_put_super(sb);
+
if (!(sb->s_flags & MS_RDONLY)) {
EXT4_CLEAR_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER);
es->s_state = cpu_to_le16(sbi->s_mount_state);
unlock_super(sb);
kobject_put(&sbi->s_kobj);
wait_for_completion(&sbi->s_kobj_unregister);
- lock_kernel();
kfree(sbi->s_blockgroup_lock);
kfree(sbi);
}
if (!ei)
return NULL;
-#ifdef CONFIG_EXT4_FS_POSIX_ACL
- ei->i_acl = EXT4_ACL_NOT_CACHED;
- ei->i_default_acl = EXT4_ACL_NOT_CACHED;
-#endif
ei->vfs_inode.i_version = 1;
ei->vfs_inode.i_data.writeback_index = 0;
memset(&ei->i_cached_extent, 0, sizeof(struct ext4_ext_cache));
ei->i_reserved_data_blocks = 0;
ei->i_reserved_meta_blocks = 0;
ei->i_allocated_meta_blocks = 0;
+ ei->i_da_metadata_calc_len = 0;
ei->i_delalloc_reserved_flag = 0;
spin_lock_init(&(ei->i_block_reservation_lock));
+#ifdef CONFIG_QUOTA
+ ei->i_reserved_quota = 0;
+#endif
+ INIT_LIST_HEAD(&ei->i_completed_io_list);
+ spin_lock_init(&ei->i_completed_io_lock);
+ ei->cur_aio_dio = NULL;
+ ei->i_sync_tid = 0;
+ ei->i_datasync_tid = 0;
return &ei->vfs_inode;
}
static void ext4_clear_inode(struct inode *inode)
{
-#ifdef CONFIG_EXT4_FS_POSIX_ACL
- if (EXT4_I(inode)->i_acl &&
- EXT4_I(inode)->i_acl != EXT4_ACL_NOT_CACHED) {
- posix_acl_release(EXT4_I(inode)->i_acl);
- EXT4_I(inode)->i_acl = EXT4_ACL_NOT_CACHED;
- }
- if (EXT4_I(inode)->i_default_acl &&
- EXT4_I(inode)->i_default_acl != EXT4_ACL_NOT_CACHED) {
- posix_acl_release(EXT4_I(inode)->i_default_acl);
- EXT4_I(inode)->i_default_acl = EXT4_ACL_NOT_CACHED;
- }
-#endif
+ dquot_drop(inode);
ext4_discard_preallocations(inode);
if (EXT4_JOURNAL(inode))
jbd2_journal_release_jbd_inode(EXT4_SB(inode->i_sb)->s_journal,
#if defined(CONFIG_QUOTA)
struct ext4_sb_info *sbi = EXT4_SB(sb);
- if (sbi->s_jquota_fmt)
- seq_printf(seq, ",jqfmt=%s",
- (sbi->s_jquota_fmt == QFMT_VFS_OLD) ? "vfsold" : "vfsv0");
+ if (sbi->s_jquota_fmt) {
+ char *fmtname = "";
+
+ switch (sbi->s_jquota_fmt) {
+ case QFMT_VFS_OLD:
+ fmtname = "vfsold";
+ break;
+ case QFMT_VFS_V0:
+ fmtname = "vfsv0";
+ break;
+ case QFMT_VFS_V1:
+ fmtname = "vfsv1";
+ break;
+ }
+ seq_printf(seq, ",jqfmt=%s", fmtname);
+ }
if (sbi->s_qf_names[USRQUOTA])
seq_printf(seq, ",usrjquota=%s", sbi->s_qf_names[USRQUOTA]);
if (sbi->s_qf_names[GRPQUOTA])
seq_printf(seq, ",grpjquota=%s", sbi->s_qf_names[GRPQUOTA]);
- if (sbi->s_mount_opt & EXT4_MOUNT_USRQUOTA)
+ if (test_opt(sb, USRQUOTA))
seq_puts(seq, ",usrquota");
- if (sbi->s_mount_opt & EXT4_MOUNT_GRPQUOTA)
+ if (test_opt(sb, GRPQUOTA))
seq_puts(seq, ",grpquota");
#endif
}
seq_puts(seq, test_opt(sb, BARRIER) ? "1" : "0");
if (test_opt(sb, JOURNAL_ASYNC_COMMIT))
seq_puts(seq, ",journal_async_commit");
+ else if (test_opt(sb, JOURNAL_CHECKSUM))
+ seq_puts(seq, ",journal_checksum");
if (test_opt(sb, NOBH))
seq_puts(seq, ",nobh");
if (test_opt(sb, I_VERSION))
if (test_opt(sb, NO_AUTO_DA_ALLOC))
seq_puts(seq, ",noauto_da_alloc");
+ if (test_opt(sb, DISCARD))
+ seq_puts(seq, ",discard");
+
+ if (test_opt(sb, NOLOAD))
+ seq_puts(seq, ",norecovery");
+
+ if (test_opt(sb, DIOREAD_NOLOCK))
+ seq_puts(seq, ",dioread_nolock");
+
ext4_show_quota_options(seq, sb);
return 0;
static int ext4_mark_dquot_dirty(struct dquot *dquot);
static int ext4_write_info(struct super_block *sb, int type);
static int ext4_quota_on(struct super_block *sb, int type, int format_id,
- char *path, int remount);
+ char *path);
static int ext4_quota_on_mount(struct super_block *sb, int type);
static ssize_t ext4_quota_read(struct super_block *sb, int type, char *data,
size_t len, loff_t off);
static ssize_t ext4_quota_write(struct super_block *sb, int type,
const char *data, size_t len, loff_t off);
-static struct dquot_operations ext4_quota_operations = {
- .initialize = dquot_initialize,
- .drop = dquot_drop,
- .alloc_space = dquot_alloc_space,
- .reserve_space = dquot_reserve_space,
- .claim_space = dquot_claim_space,
- .release_rsv = dquot_release_reserved_space,
+static const struct dquot_operations ext4_quota_operations = {
+#ifdef CONFIG_QUOTA
.get_reserved_space = ext4_get_reserved_space,
- .alloc_inode = dquot_alloc_inode,
- .free_space = dquot_free_space,
- .free_inode = dquot_free_inode,
- .transfer = dquot_transfer,
+#endif
.write_dquot = ext4_write_dquot,
.acquire_dquot = ext4_acquire_dquot,
.release_dquot = ext4_release_dquot,
.destroy_dquot = dquot_destroy,
};
-static struct quotactl_ops ext4_qctl_operations = {
+static const struct quotactl_ops ext4_qctl_operations = {
.quota_on = ext4_quota_on,
- .quota_off = vfs_quota_off,
- .quota_sync = vfs_quota_sync,
- .get_info = vfs_get_dqinfo,
- .set_info = vfs_set_dqinfo,
- .get_dqblk = vfs_get_dqblk,
- .set_dqblk = vfs_set_dqblk
+ .quota_off = dquot_quota_off,
+ .quota_sync = dquot_quota_sync,
+ .get_info = dquot_get_dqinfo,
+ .set_info = dquot_set_dqinfo,
+ .get_dqblk = dquot_get_dqblk,
+ .set_dqblk = dquot_set_dqblk
};
#endif
Opt_journal_update, Opt_journal_dev,
Opt_journal_checksum, Opt_journal_async_commit,
Opt_abort, Opt_data_journal, Opt_data_ordered, Opt_data_writeback,
- Opt_data_err_abort, Opt_data_err_ignore, Opt_mb_history_length,
+ 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_nobarrier, Opt_err, Opt_resize,
- Opt_usrquota, Opt_grpquota, Opt_i_version,
+ Opt_jqfmt_vfsold, Opt_jqfmt_vfsv0, Opt_jqfmt_vfsv1, Opt_quota,
+ Opt_noquota, Opt_ignore, Opt_barrier, Opt_nobarrier, Opt_err,
+ Opt_resize, Opt_usrquota, Opt_grpquota, Opt_i_version,
Opt_stripe, Opt_delalloc, Opt_nodelalloc,
Opt_block_validity, Opt_noblock_validity,
- Opt_inode_readahead_blks, Opt_journal_ioprio
+ Opt_inode_readahead_blks, Opt_journal_ioprio,
+ Opt_dioread_nolock, Opt_dioread_lock,
+ Opt_discard, Opt_nodiscard,
};
static const match_table_t tokens = {
{Opt_acl, "acl"},
{Opt_noacl, "noacl"},
{Opt_noload, "noload"},
+ {Opt_noload, "norecovery"},
{Opt_nobh, "nobh"},
{Opt_bh, "bh"},
{Opt_commit, "commit=%u"},
{Opt_data_writeback, "data=writeback"},
{Opt_data_err_abort, "data_err=abort"},
{Opt_data_err_ignore, "data_err=ignore"},
- {Opt_mb_history_length, "mb_history_length=%u"},
{Opt_offusrjquota, "usrjquota="},
{Opt_usrjquota, "usrjquota=%s"},
{Opt_offgrpjquota, "grpjquota="},
{Opt_grpjquota, "grpjquota=%s"},
{Opt_jqfmt_vfsold, "jqfmt=vfsold"},
{Opt_jqfmt_vfsv0, "jqfmt=vfsv0"},
+ {Opt_jqfmt_vfsv1, "jqfmt=vfsv1"},
{Opt_grpquota, "grpquota"},
{Opt_noquota, "noquota"},
{Opt_quota, "quota"},
{Opt_auto_da_alloc, "auto_da_alloc=%u"},
{Opt_auto_da_alloc, "auto_da_alloc"},
{Opt_noauto_da_alloc, "noauto_da_alloc"},
+ {Opt_dioread_nolock, "dioread_nolock"},
+ {Opt_dioread_lock, "dioread_lock"},
+ {Opt_discard, "discard"},
+ {Opt_nodiscard, "nodiscard"},
{Opt_err, NULL},
};
}
#define DEFAULT_JOURNAL_IOPRIO (IOPRIO_PRIO_VALUE(IOPRIO_CLASS_BE, 3))
+static char deprecated_msg[] = "Mount option \"%s\" will be removed by %s\n"
+ "Contact linux-ext4@vger.kernel.org if you think we should keep it.\n";
+
+#ifdef CONFIG_QUOTA
+static int set_qf_name(struct super_block *sb, int qtype, substring_t *args)
+{
+ struct ext4_sb_info *sbi = EXT4_SB(sb);
+ char *qname;
+
+ if (sb_any_quota_loaded(sb) &&
+ !sbi->s_qf_names[qtype]) {
+ ext4_msg(sb, KERN_ERR,
+ "Cannot change journaled "
+ "quota options when quota turned on");
+ return 0;
+ }
+ qname = match_strdup(args);
+ if (!qname) {
+ ext4_msg(sb, KERN_ERR,
+ "Not enough memory for storing quotafile name");
+ return 0;
+ }
+ if (sbi->s_qf_names[qtype] &&
+ strcmp(sbi->s_qf_names[qtype], qname)) {
+ ext4_msg(sb, KERN_ERR,
+ "%s quota file already specified", QTYPE2NAME(qtype));
+ kfree(qname);
+ return 0;
+ }
+ sbi->s_qf_names[qtype] = qname;
+ if (strchr(sbi->s_qf_names[qtype], '/')) {
+ ext4_msg(sb, KERN_ERR,
+ "quotafile must be on filesystem root");
+ kfree(sbi->s_qf_names[qtype]);
+ sbi->s_qf_names[qtype] = NULL;
+ return 0;
+ }
+ set_opt(sbi->s_mount_opt, QUOTA);
+ return 1;
+}
+
+static int clear_qf_name(struct super_block *sb, int qtype)
+{
+
+ struct ext4_sb_info *sbi = EXT4_SB(sb);
+
+ if (sb_any_quota_loaded(sb) &&
+ sbi->s_qf_names[qtype]) {
+ ext4_msg(sb, KERN_ERR, "Cannot change journaled quota options"
+ " when quota turned on");
+ return 0;
+ }
+ /*
+ * The space will be released later when all options are confirmed
+ * to be correct
+ */
+ sbi->s_qf_names[qtype] = NULL;
+ return 1;
+}
+#endif
static int parse_options(char *options, struct super_block *sb,
unsigned long *journal_devnum,
int data_opt = 0;
int option;
#ifdef CONFIG_QUOTA
- int qtype, qfmt;
- char *qname;
+ int qfmt;
#endif
if (!options)
if (!*p)
continue;
+ /*
+ * Initialize args struct so we know whether arg was
+ * found; some options take optional arguments.
+ */
+ args[0].to = args[0].from = 0;
token = match_token(p, tokens, args);
switch (token) {
case Opt_bsd_df:
+ ext4_msg(sb, KERN_WARNING, deprecated_msg, p, "2.6.38");
clear_opt(sbi->s_mount_opt, MINIX_DF);
break;
case Opt_minix_df:
+ ext4_msg(sb, KERN_WARNING, deprecated_msg, p, "2.6.38");
set_opt(sbi->s_mount_opt, MINIX_DF);
+
break;
case Opt_grpid:
+ ext4_msg(sb, KERN_WARNING, deprecated_msg, p, "2.6.38");
set_opt(sbi->s_mount_opt, GRPID);
+
break;
case Opt_nogrpid:
+ ext4_msg(sb, KERN_WARNING, deprecated_msg, p, "2.6.38");
clear_opt(sbi->s_mount_opt, GRPID);
+
break;
case Opt_resuid:
if (match_int(&args[0], &option))
data_opt = EXT4_MOUNT_WRITEBACK_DATA;
datacheck:
if (is_remount) {
- if ((sbi->s_mount_opt & EXT4_MOUNT_DATA_FLAGS)
- != data_opt) {
+ if (test_opt(sb, DATA_FLAGS) != data_opt) {
ext4_msg(sb, KERN_ERR,
"Cannot change data mode on remount");
return 0;
}
} else {
- sbi->s_mount_opt &= ~EXT4_MOUNT_DATA_FLAGS;
+ clear_opt(sbi->s_mount_opt, DATA_FLAGS);
sbi->s_mount_opt |= data_opt;
}
break;
case Opt_data_err_ignore:
clear_opt(sbi->s_mount_opt, DATA_ERR_ABORT);
break;
- case Opt_mb_history_length:
- if (match_int(&args[0], &option))
- return 0;
- if (option < 0)
- return 0;
- sbi->s_mb_history_max = option;
- break;
#ifdef CONFIG_QUOTA
case Opt_usrjquota:
- qtype = USRQUOTA;
- goto set_qf_name;
- case Opt_grpjquota:
- qtype = GRPQUOTA;
-set_qf_name:
- if (sb_any_quota_loaded(sb) &&
- !sbi->s_qf_names[qtype]) {
- ext4_msg(sb, KERN_ERR,
- "Cannot change journaled "
- "quota options when quota turned on");
- return 0;
- }
- qname = match_strdup(&args[0]);
- if (!qname) {
- ext4_msg(sb, KERN_ERR,
- "Not enough memory for "
- "storing quotafile name");
+ if (!set_qf_name(sb, USRQUOTA, &args[0]))
return 0;
- }
- if (sbi->s_qf_names[qtype] &&
- strcmp(sbi->s_qf_names[qtype], qname)) {
- ext4_msg(sb, KERN_ERR,
- "%s quota file already "
- "specified", QTYPE2NAME(qtype));
- kfree(qname);
- return 0;
- }
- sbi->s_qf_names[qtype] = qname;
- if (strchr(sbi->s_qf_names[qtype], '/')) {
- ext4_msg(sb, KERN_ERR,
- "quotafile must be on "
- "filesystem root");
- kfree(sbi->s_qf_names[qtype]);
- sbi->s_qf_names[qtype] = NULL;
+ break;
+ case Opt_grpjquota:
+ if (!set_qf_name(sb, GRPQUOTA, &args[0]))
return 0;
- }
- set_opt(sbi->s_mount_opt, QUOTA);
break;
case Opt_offusrjquota:
- qtype = USRQUOTA;
- goto clear_qf_name;
+ if (!clear_qf_name(sb, USRQUOTA))
+ return 0;
+ break;
case Opt_offgrpjquota:
- qtype = GRPQUOTA;
-clear_qf_name:
- if (sb_any_quota_loaded(sb) &&
- sbi->s_qf_names[qtype]) {
- ext4_msg(sb, KERN_ERR, "Cannot change "
- "journaled quota options when "
- "quota turned on");
+ if (!clear_qf_name(sb, GRPQUOTA))
return 0;
- }
- /*
- * 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:
qfmt = QFMT_VFS_OLD;
goto set_qf_format;
case Opt_jqfmt_vfsv0:
qfmt = QFMT_VFS_V0;
+ goto set_qf_format;
+ case Opt_jqfmt_vfsv1:
+ qfmt = QFMT_VFS_V1;
set_qf_format:
if (sb_any_quota_loaded(sb) &&
sbi->s_jquota_fmt != qfmt) {
case Opt_offgrpjquota:
case Opt_jqfmt_vfsold:
case Opt_jqfmt_vfsv0:
+ case Opt_jqfmt_vfsv1:
ext4_msg(sb, KERN_ERR,
"journaled quota options not supported");
break;
break;
#endif
case Opt_abort:
- set_opt(sbi->s_mount_opt, ABORT);
+ sbi->s_mount_flags |= EXT4_MF_FS_ABORTED;
break;
case Opt_nobarrier:
clear_opt(sbi->s_mount_opt, BARRIER);
break;
case Opt_barrier:
- if (match_int(&args[0], &option)) {
- set_opt(sbi->s_mount_opt, BARRIER);
- break;
- }
+ if (args[0].from) {
+ if (match_int(&args[0], &option))
+ return 0;
+ } else
+ option = 1; /* No argument, default to 1 */
if (option)
set_opt(sbi->s_mount_opt, BARRIER);
else
set_opt(sbi->s_mount_opt,NO_AUTO_DA_ALLOC);
break;
case Opt_auto_da_alloc:
- if (match_int(&args[0], &option)) {
- clear_opt(sbi->s_mount_opt, NO_AUTO_DA_ALLOC);
- break;
- }
+ if (args[0].from) {
+ if (match_int(&args[0], &option))
+ return 0;
+ } else
+ option = 1; /* No argument, default to 1 */
if (option)
clear_opt(sbi->s_mount_opt, NO_AUTO_DA_ALLOC);
else
set_opt(sbi->s_mount_opt,NO_AUTO_DA_ALLOC);
break;
+ case Opt_discard:
+ set_opt(sbi->s_mount_opt, DISCARD);
+ break;
+ case Opt_nodiscard:
+ clear_opt(sbi->s_mount_opt, DISCARD);
+ break;
+ case Opt_dioread_nolock:
+ set_opt(sbi->s_mount_opt, DIOREAD_NOLOCK);
+ break;
+ case Opt_dioread_lock:
+ clear_opt(sbi->s_mount_opt, DIOREAD_NOLOCK);
+ break;
default:
ext4_msg(sb, KERN_ERR,
"Unrecognized mount option \"%s\" "
}
#ifdef CONFIG_QUOTA
if (sbi->s_qf_names[USRQUOTA] || sbi->s_qf_names[GRPQUOTA]) {
- if ((sbi->s_mount_opt & EXT4_MOUNT_USRQUOTA) &&
- sbi->s_qf_names[USRQUOTA])
+ if (test_opt(sb, USRQUOTA) && sbi->s_qf_names[USRQUOTA])
clear_opt(sbi->s_mount_opt, USRQUOTA);
- if ((sbi->s_mount_opt & EXT4_MOUNT_GRPQUOTA) &&
- sbi->s_qf_names[GRPQUOTA])
+ if (test_opt(sb, GRPQUOTA) && sbi->s_qf_names[GRPQUOTA])
clear_opt(sbi->s_mount_opt, GRPQUOTA);
- if ((sbi->s_qf_names[USRQUOTA] &&
- (sbi->s_mount_opt & EXT4_MOUNT_GRPQUOTA)) ||
- (sbi->s_qf_names[GRPQUOTA] &&
- (sbi->s_mount_opt & EXT4_MOUNT_USRQUOTA))) {
+ if (test_opt(sb, GRPQUOTA) || test_opt(sb, USRQUOTA)) {
ext4_msg(sb, KERN_ERR, "old and new quota "
"format mixing");
return 0;
ext4_commit_super(sb, 1);
if (test_opt(sb, DEBUG))
printk(KERN_INFO "[EXT4 FS bs=%lu, gc=%u, "
- "bpg=%lu, ipg=%lu, mo=%04lx]\n",
+ "bpg=%lu, ipg=%lu, mo=%04x]\n",
sb->s_blocksize,
sbi->s_groups_count,
EXT4_BLOCKS_PER_GROUP(sb),
EXT4_INODES_PER_GROUP(sb),
sbi->s_mount_opt);
- if (EXT4_SB(sb)->s_journal) {
- ext4_msg(sb, KERN_INFO, "%s journal on %s",
- EXT4_SB(sb)->s_journal->j_inode ? "internal" :
- "external", EXT4_SB(sb)->s_journal->j_devname);
- } else {
- ext4_msg(sb, KERN_INFO, "no journal");
- }
return res;
}
size_t size;
int i;
- if (!sbi->s_es->s_log_groups_per_flex) {
+ sbi->s_log_groups_per_flex = sbi->s_es->s_log_groups_per_flex;
+ groups_per_flex = 1 << sbi->s_log_groups_per_flex;
+
+ if (groups_per_flex < 2) {
sbi->s_log_groups_per_flex = 0;
return 1;
}
- sbi->s_log_groups_per_flex = sbi->s_es->s_log_groups_per_flex;
- groups_per_flex = 1 << sbi->s_log_groups_per_flex;
-
/* We allocate both existing and potentially added groups */
flex_group_count = ((sbi->s_groups_count + groups_per_flex - 1) +
((le16_to_cpu(sbi->s_es->s_reserved_gdt_blocks) + 1) <<
gdp = ext4_get_group_desc(sb, i, NULL);
flex_group = ext4_flex_group(sbi, i);
- atomic_set(&sbi->s_flex_groups[flex_group].free_inodes,
- ext4_free_inodes_count(sb, gdp));
- atomic_set(&sbi->s_flex_groups[flex_group].free_blocks,
- ext4_free_blks_count(sb, gdp));
- atomic_set(&sbi->s_flex_groups[flex_group].used_dirs,
- ext4_used_dirs_count(sb, gdp));
+ atomic_add(ext4_free_inodes_count(sb, gdp),
+ &sbi->s_flex_groups[flex_group].free_inodes);
+ atomic_add(ext4_free_blks_count(sb, gdp),
+ &sbi->s_flex_groups[flex_group].free_blocks);
+ atomic_add(ext4_used_dirs_count(sb, gdp),
+ &sbi->s_flex_groups[flex_group].used_dirs);
}
return 1;
}
list_add(&EXT4_I(inode)->i_orphan, &EXT4_SB(sb)->s_orphan);
- vfs_dq_init(inode);
+ dquot_initialize(inode);
if (inode->i_nlink) {
ext4_msg(sb, KERN_DEBUG,
"%s: truncating inode %lu to %lld bytes",
/* Turn quotas off */
for (i = 0; i < MAXQUOTAS; i++) {
if (sb_dqopt(sb)->files[i])
- vfs_quota_off(sb, i, 0);
+ dquot_quota_off(sb, i);
}
#endif
sb->s_flags = s_flags; /* Restore MS_RDONLY status */
/* small i_blocks in vfs inode? */
if (!has_huge_files || sizeof(blkcnt_t) < sizeof(u64)) {
/*
- * CONFIG_LBD is not enabled implies the inode
+ * CONFIG_LBDAF is not enabled implies the inode
* i_block represent total blocks in 512 bytes
* 32 == size of vfs inode i_blocks * 8
*/
if (!has_huge_files || sizeof(blkcnt_t) < sizeof(u64)) {
/*
- * !has_huge_files or CONFIG_LBD not enabled implies that
+ * !has_huge_files or CONFIG_LBDAF not enabled implies that
* the inode i_block field represents total file blocks in
* 2^32 512-byte sectors == size of vfs inode i_blocks * 8
*/
struct ext4_attr {
struct attribute attr;
ssize_t (*show)(struct ext4_attr *, struct ext4_sb_info *, char *);
- ssize_t (*store)(struct ext4_attr *, struct ext4_sb_info *,
+ ssize_t (*store)(struct ext4_attr *, struct ext4_sb_info *,
const char *, size_t);
int offset;
};
{
char *endp;
- while (*buf && isspace(*buf))
- buf++;
- *value = simple_strtoul(buf, &endp, 0);
- while (*endp && isspace(*endp))
- endp++;
+ *value = simple_strtoul(skip_spaces(buf), &endp, 0);
+ endp = skip_spaces(endp);
if (*endp || *value > max)
return -EINVAL;
struct super_block *sb = sbi->s_buddy_cache->i_sb;
return snprintf(buf, PAGE_SIZE, "%llu\n",
- sbi->s_kbytes_written +
+ (unsigned long long)(sbi->s_kbytes_written +
((part_stat_read(sb->s_bdev->bd_part, sectors[1]) -
- EXT4_SB(sb)->s_sectors_written_start) >> 1));
+ EXT4_SB(sb)->s_sectors_written_start) >> 1)));
}
static ssize_t inode_readahead_blks_store(struct ext4_attr *a,
EXT4_RO_ATTR(lifetime_write_kbytes);
EXT4_ATTR_OFFSET(inode_readahead_blks, 0644, sbi_ui_show,
inode_readahead_blks_store, s_inode_readahead_blks);
+EXT4_RW_ATTR_SBI_UI(inode_goal, s_inode_goal);
EXT4_RW_ATTR_SBI_UI(mb_stats, s_mb_stats);
EXT4_RW_ATTR_SBI_UI(mb_max_to_scan, s_mb_max_to_scan);
EXT4_RW_ATTR_SBI_UI(mb_min_to_scan, s_mb_min_to_scan);
EXT4_RW_ATTR_SBI_UI(mb_order2_req, s_mb_order2_reqs);
EXT4_RW_ATTR_SBI_UI(mb_stream_req, s_mb_stream_request);
EXT4_RW_ATTR_SBI_UI(mb_group_prealloc, s_mb_group_prealloc);
+EXT4_RW_ATTR_SBI_UI(max_writeback_mb_bump, s_max_writeback_mb_bump);
static struct attribute *ext4_attrs[] = {
ATTR_LIST(delayed_allocation_blocks),
ATTR_LIST(session_write_kbytes),
ATTR_LIST(lifetime_write_kbytes),
ATTR_LIST(inode_readahead_blks),
+ ATTR_LIST(inode_goal),
ATTR_LIST(mb_stats),
ATTR_LIST(mb_max_to_scan),
ATTR_LIST(mb_min_to_scan),
ATTR_LIST(mb_order2_req),
ATTR_LIST(mb_stream_req),
ATTR_LIST(mb_group_prealloc),
+ ATTR_LIST(max_writeback_mb_bump),
NULL,
};
}
-static struct sysfs_ops ext4_attr_ops = {
+static const struct sysfs_ops ext4_attr_ops = {
.show = ext4_attr_show,
.store = ext4_attr_store,
};
.release = ext4_sb_release,
};
+/*
+ * Check whether this filesystem can be mounted based on
+ * the features present and the RDONLY/RDWR mount requested.
+ * Returns 1 if this filesystem can be mounted as requested,
+ * 0 if it cannot be.
+ */
+static int ext4_feature_set_ok(struct super_block *sb, int readonly)
+{
+ if (EXT4_HAS_INCOMPAT_FEATURE(sb, ~EXT4_FEATURE_INCOMPAT_SUPP)) {
+ ext4_msg(sb, KERN_ERR,
+ "Couldn't mount because of "
+ "unsupported optional features (%x)",
+ (le32_to_cpu(EXT4_SB(sb)->s_es->s_feature_incompat) &
+ ~EXT4_FEATURE_INCOMPAT_SUPP));
+ return 0;
+ }
+
+ if (readonly)
+ return 1;
+
+ /* Check that feature set is OK for a read-write mount */
+ if (EXT4_HAS_RO_COMPAT_FEATURE(sb, ~EXT4_FEATURE_RO_COMPAT_SUPP)) {
+ ext4_msg(sb, KERN_ERR, "couldn't mount RDWR because of "
+ "unsupported optional features (%x)",
+ (le32_to_cpu(EXT4_SB(sb)->s_es->s_feature_ro_compat) &
+ ~EXT4_FEATURE_RO_COMPAT_SUPP));
+ return 0;
+ }
+ /*
+ * Large file size enabled file system can only be mounted
+ * read-write on 32-bit systems if kernel is built with CONFIG_LBDAF
+ */
+ if (EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_HUGE_FILE)) {
+ if (sizeof(blkcnt_t) < sizeof(u64)) {
+ ext4_msg(sb, KERN_ERR, "Filesystem with huge files "
+ "cannot be mounted RDWR without "
+ "CONFIG_LBDAF");
+ return 0;
+ }
+ }
+ return 1;
+}
+
static int ext4_fill_super(struct super_block *sb, void *data, int silent)
__releases(kernel_lock)
__acquires(kernel_lock)
{
+ char *orig_data = kstrdup(data, GFP_KERNEL);
struct buffer_head *bh;
struct ext4_super_block *es = NULL;
struct ext4_sb_info *sbi;
unsigned int db_count;
unsigned int i;
int needs_recovery, has_huge_files;
- int features;
__u64 blocks_count;
int err;
unsigned int journal_ioprio = DEFAULT_JOURNAL_IOPRIO;
def_mount_opts = le32_to_cpu(es->s_default_mount_opts);
if (def_mount_opts & EXT4_DEFM_DEBUG)
set_opt(sbi->s_mount_opt, DEBUG);
- if (def_mount_opts & EXT4_DEFM_BSDGROUPS)
+ if (def_mount_opts & EXT4_DEFM_BSDGROUPS) {
+ ext4_msg(sb, KERN_WARNING, deprecated_msg, "bsdgroups",
+ "2.6.38");
set_opt(sbi->s_mount_opt, GRPID);
+ }
if (def_mount_opts & EXT4_DEFM_UID16)
set_opt(sbi->s_mount_opt, NO_UID32);
#ifdef CONFIG_EXT4_FS_XATTR
set_opt(sbi->s_mount_opt, POSIX_ACL);
#endif
if ((def_mount_opts & EXT4_DEFM_JMODE) == EXT4_DEFM_JMODE_DATA)
- sbi->s_mount_opt |= EXT4_MOUNT_JOURNAL_DATA;
+ set_opt(sbi->s_mount_opt, JOURNAL_DATA);
else if ((def_mount_opts & EXT4_DEFM_JMODE) == EXT4_DEFM_JMODE_ORDERED)
- sbi->s_mount_opt |= EXT4_MOUNT_ORDERED_DATA;
+ set_opt(sbi->s_mount_opt, ORDERED_DATA);
else if ((def_mount_opts & EXT4_DEFM_JMODE) == EXT4_DEFM_JMODE_WBACK)
- sbi->s_mount_opt |= EXT4_MOUNT_WRITEBACK_DATA;
+ set_opt(sbi->s_mount_opt, WRITEBACK_DATA);
if (le16_to_cpu(sbi->s_es->s_errors) == EXT4_ERRORS_PANIC)
set_opt(sbi->s_mount_opt, ERRORS_PANIC);
sbi->s_commit_interval = JBD2_DEFAULT_MAX_COMMIT_AGE * HZ;
sbi->s_min_batch_time = EXT4_DEF_MIN_BATCH_TIME;
sbi->s_max_batch_time = EXT4_DEF_MAX_BATCH_TIME;
- sbi->s_mb_history_max = default_mb_history_length;
set_opt(sbi->s_mount_opt, BARRIER);
* enable delayed allocation by default
* Use -o nodelalloc to turn it off
*/
- set_opt(sbi->s_mount_opt, DELALLOC);
+ if (!IS_EXT3_SB(sb))
+ set_opt(sbi->s_mount_opt, DELALLOC);
if (!parse_options((char *) data, sb, &journal_devnum,
&journal_ioprio, NULL, 0))
goto failed_mount;
sb->s_flags = (sb->s_flags & ~MS_POSIXACL) |
- ((sbi->s_mount_opt & EXT4_MOUNT_POSIX_ACL) ? MS_POSIXACL : 0);
+ (test_opt(sb, POSIX_ACL) ? MS_POSIXACL : 0);
if (le32_to_cpu(es->s_rev_level) == EXT4_GOOD_OLD_REV &&
(EXT4_HAS_COMPAT_FEATURE(sb, ~0U) ||
* previously didn't change the revision level when setting the flags,
* so there is a chance incompat flags are set on a rev 0 filesystem.
*/
- features = EXT4_HAS_INCOMPAT_FEATURE(sb, ~EXT4_FEATURE_INCOMPAT_SUPP);
- if (features) {
- ext4_msg(sb, KERN_ERR,
- "Couldn't mount because of "
- "unsupported optional features (%x)",
- (le32_to_cpu(EXT4_SB(sb)->s_es->s_feature_incompat) &
- ~EXT4_FEATURE_INCOMPAT_SUPP));
- goto failed_mount;
- }
- features = EXT4_HAS_RO_COMPAT_FEATURE(sb, ~EXT4_FEATURE_RO_COMPAT_SUPP);
- if (!(sb->s_flags & MS_RDONLY) && features) {
- ext4_msg(sb, KERN_ERR,
- "Couldn't mount RDWR because of "
- "unsupported optional features (%x)",
- (le32_to_cpu(EXT4_SB(sb)->s_es->s_feature_ro_compat) &
- ~EXT4_FEATURE_RO_COMPAT_SUPP));
+ if (!ext4_feature_set_ok(sb, (sb->s_flags & MS_RDONLY)))
goto failed_mount;
- }
- has_huge_files = EXT4_HAS_RO_COMPAT_FEATURE(sb,
- EXT4_FEATURE_RO_COMPAT_HUGE_FILE);
- if (has_huge_files) {
- /*
- * Large file size enabled file system can only be
- * mount if kernel is build with CONFIG_LBD
- */
- if (sizeof(root->i_blocks) < sizeof(u64) &&
- !(sb->s_flags & MS_RDONLY)) {
- ext4_msg(sb, KERN_ERR, "Filesystem with huge "
- "files cannot be mounted read-write "
- "without CONFIG_LBD");
- goto failed_mount;
- }
- }
+
blocksize = BLOCK_SIZE << le32_to_cpu(es->s_log_block_size);
if (blocksize < EXT4_MIN_BLOCK_SIZE ||
}
}
+ has_huge_files = EXT4_HAS_RO_COMPAT_FEATURE(sb,
+ EXT4_FEATURE_RO_COMPAT_HUGE_FILE);
sbi->s_bitmap_maxbytes = ext4_max_bitmap_size(sb->s_blocksize_bits,
has_huge_files);
sb->s_maxbytes = ext4_max_size(sb->s_blocksize_bits, has_huge_files);
goto failed_mount;
}
- if (ext4_blocks_count(es) >
- (sector_t)(~0ULL) >> (sb->s_blocksize_bits - 9)) {
+ /*
+ * Test whether we have more sectors than will fit in sector_t,
+ * and whether the max offset is addressable by the page cache.
+ */
+ if ((ext4_blocks_count(es) >
+ (sector_t)(~0ULL) >> (sb->s_blocksize_bits - 9)) ||
+ (ext4_blocks_count(es) >
+ (pgoff_t)(~0ULL) >> (PAGE_CACHE_SHIFT - sb->s_blocksize_bits))) {
ext4_msg(sb, KERN_ERR, "filesystem"
- " too large to mount safely");
+ " too large to mount safely on this system");
if (sizeof(sector_t) < 8)
- ext4_msg(sb, KERN_WARNING, "CONFIG_LBD not enabled");
+ ext4_msg(sb, KERN_WARNING, "CONFIG_LBDAF not enabled");
+ ret = -EFBIG;
goto failed_mount;
}
goto failed_mount;
}
sbi->s_groups_count = blocks_count;
+ sbi->s_blockfile_groups = min_t(ext4_group_t, sbi->s_groups_count,
+ (EXT4_MAX_BLOCK_FILE_PHYS / EXT4_BLOCKS_PER_GROUP(sb)));
db_count = (sbi->s_groups_count + EXT4_DESC_PER_BLOCK(sb) - 1) /
EXT4_DESC_PER_BLOCK(sb);
sbi->s_group_desc = kmalloc(db_count * sizeof(struct buffer_head *),
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,
- ext4_count_free_blocks(sb));
- if (!err) {
- err = percpu_counter_init(&sbi->s_freeinodes_counter,
- ext4_count_free_inodes(sb));
- }
- if (!err) {
- err = percpu_counter_init(&sbi->s_dirs_counter,
- ext4_count_dirs(sb));
- }
- if (!err) {
- err = percpu_counter_init(&sbi->s_dirtyblocks_counter, 0);
- }
- if (err) {
- ext4_msg(sb, KERN_ERR, "insufficient memory");
- goto failed_mount3;
- }
-
sbi->s_stripe = ext4_get_stripe_size(sbi);
+ sbi->s_max_writeback_mb_bump = 128;
/*
* set up enough so that it can read an inode
EXT4_HAS_COMPAT_FEATURE(sb, EXT4_FEATURE_COMPAT_HAS_JOURNAL)) {
if (ext4_load_journal(sb, es, journal_devnum))
goto failed_mount3;
- if (!(sb->s_flags & MS_RDONLY) &&
- EXT4_SB(sb)->s_journal->j_failed_commit) {
- ext4_msg(sb, KERN_CRIT, "error: "
- "ext4_fill_super: Journal transaction "
- "%u is corrupt",
- EXT4_SB(sb)->s_journal->j_failed_commit);
- if (test_opt(sb, ERRORS_RO)) {
- ext4_msg(sb, KERN_CRIT,
- "Mounting filesystem read-only");
- sb->s_flags |= MS_RDONLY;
- EXT4_SB(sb)->s_mount_state |= EXT4_ERROR_FS;
- es->s_state |= cpu_to_le16(EXT4_ERROR_FS);
- }
- if (test_opt(sb, ERRORS_PANIC)) {
- EXT4_SB(sb)->s_mount_state |= EXT4_ERROR_FS;
- es->s_state |= cpu_to_le16(EXT4_ERROR_FS);
- ext4_commit_super(sb, 1);
- goto failed_mount4;
- }
- }
} else if (test_opt(sb, NOLOAD) && !(sb->s_flags & MS_RDONLY) &&
EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER)) {
ext4_msg(sb, KERN_ERR, "required journal recovery "
"suppressed and not mounted read-only");
- goto failed_mount4;
+ goto failed_mount_wq;
} else {
clear_opt(sbi->s_mount_opt, DATA_FLAGS);
set_opt(sbi->s_mount_opt, WRITEBACK_DATA);
!jbd2_journal_set_features(EXT4_SB(sb)->s_journal, 0, 0,
JBD2_FEATURE_INCOMPAT_64BIT)) {
ext4_msg(sb, KERN_ERR, "Failed to set 64-bit journal feature");
- goto failed_mount4;
+ goto failed_mount_wq;
}
if (test_opt(sb, JOURNAL_ASYNC_COMMIT)) {
(sbi->s_journal, 0, 0, JBD2_FEATURE_INCOMPAT_REVOKE)) {
ext4_msg(sb, KERN_ERR, "Journal does not support "
"requested data journaling mode");
- goto failed_mount4;
+ goto failed_mount_wq;
}
default:
break;
set_task_ioprio(sbi->s_journal->j_task, journal_ioprio);
no_journal:
-
+ err = percpu_counter_init(&sbi->s_freeblocks_counter,
+ ext4_count_free_blocks(sb));
+ if (!err)
+ err = percpu_counter_init(&sbi->s_freeinodes_counter,
+ ext4_count_free_inodes(sb));
+ if (!err)
+ err = percpu_counter_init(&sbi->s_dirs_counter,
+ ext4_count_dirs(sb));
+ if (!err)
+ err = percpu_counter_init(&sbi->s_dirtyblocks_counter, 0);
+ if (err) {
+ ext4_msg(sb, KERN_ERR, "insufficient memory");
+ goto failed_mount_wq;
+ }
if (test_opt(sb, NOBH)) {
if (!(test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_WRITEBACK_DATA)) {
ext4_msg(sb, KERN_WARNING, "Ignoring nobh option - "
"its supported only with writeback mode");
clear_opt(sbi->s_mount_opt, NOBH);
}
+ if (test_opt(sb, DIOREAD_NOLOCK)) {
+ ext4_msg(sb, KERN_WARNING, "dioread_nolock option is "
+ "not supported with nobh mode");
+ goto failed_mount_wq;
+ }
+ }
+ EXT4_SB(sb)->dio_unwritten_wq = create_workqueue("ext4-dio-unwritten");
+ if (!EXT4_SB(sb)->dio_unwritten_wq) {
+ printk(KERN_ERR "EXT4-fs: failed to create DIO workqueue\n");
+ goto failed_mount_wq;
}
+
/*
* The jbd2_journal_load will have done any necessary log recovery,
* so we can safely mount the rest of the filesystem now.
"available");
}
- if (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA) {
+ if (test_opt(sb, DELALLOC) &&
+ (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA)) {
ext4_msg(sb, KERN_WARNING, "Ignoring delalloc option - "
"requested data journaling mode");
clear_opt(sbi->s_mount_opt, DELALLOC);
- } else if (test_opt(sb, DELALLOC))
- ext4_msg(sb, KERN_INFO, "delayed allocation enabled");
+ }
+ if (test_opt(sb, DIOREAD_NOLOCK)) {
+ if (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA) {
+ ext4_msg(sb, KERN_WARNING, "Ignoring dioread_nolock "
+ "option - requested data journaling mode");
+ clear_opt(sbi->s_mount_opt, DIOREAD_NOLOCK);
+ }
+ if (sb->s_blocksize < PAGE_SIZE) {
+ ext4_msg(sb, KERN_WARNING, "Ignoring dioread_nolock "
+ "option - block size is too small");
+ clear_opt(sbi->s_mount_opt, DIOREAD_NOLOCK);
+ }
+ }
err = ext4_setup_system_zone(sb);
if (err) {
ext4_msg(sb, KERN_ERR, "failed to initialize system "
- "zone (%d)\n", err);
+ "zone (%d)", err);
goto failed_mount4;
}
} else
descr = "out journal";
- ext4_msg(sb, KERN_INFO, "mounted filesystem with%s", descr);
+ ext4_msg(sb, KERN_INFO, "mounted filesystem with%s. "
+ "Opts: %s", descr, orig_data);
lock_kernel();
+ kfree(orig_data);
return 0;
cantfind_ext4:
failed_mount4:
ext4_msg(sb, KERN_ERR, "mount failed");
+ destroy_workqueue(EXT4_SB(sb)->dio_unwritten_wq);
+failed_mount_wq:
ext4_release_system_zone(sb);
if (sbi->s_journal) {
jbd2_journal_destroy(sbi->s_journal);
sbi->s_journal = NULL;
}
+ percpu_counter_destroy(&sbi->s_freeblocks_counter);
+ percpu_counter_destroy(&sbi->s_freeinodes_counter);
+ percpu_counter_destroy(&sbi->s_dirs_counter);
+ percpu_counter_destroy(&sbi->s_dirtyblocks_counter);
failed_mount3:
if (sbi->s_flex_groups) {
if (is_vmalloc_addr(sbi->s_flex_groups))
else
kfree(sbi->s_flex_groups);
}
- percpu_counter_destroy(&sbi->s_freeblocks_counter);
- percpu_counter_destroy(&sbi->s_freeinodes_counter);
- percpu_counter_destroy(&sbi->s_dirs_counter);
- percpu_counter_destroy(&sbi->s_dirtyblocks_counter);
failed_mount2:
for (i = 0; i < db_count; i++)
brelse(sbi->s_group_desc[i]);
kfree(sbi->s_blockgroup_lock);
kfree(sbi);
lock_kernel();
+ kfree(orig_data);
return ret;
}
return -EINVAL;
}
- if (journal->j_flags & JBD2_BARRIER)
- ext4_msg(sb, KERN_INFO, "barriers enabled");
- else
+ if (!(journal->j_flags & JBD2_BARRIER))
ext4_msg(sb, KERN_INFO, "barriers disabled");
if (!really_read_only && test_opt(sb, UPDATE_JOURNAL)) {
clear_buffer_write_io_error(sbh);
set_buffer_uptodate(sbh);
}
- es->s_wtime = cpu_to_le32(get_seconds());
+ /*
+ * If the file system is mounted read-only, don't update the
+ * superblock write time. This avoids updating the superblock
+ * write time when we are mounting the root file system
+ * read/only but we need to replay the journal; at that point,
+ * for people who are east of GMT and who make their clock
+ * tick in localtime for Windows bug-for-bug compatibility,
+ * the clock is set in the future, and this will cause e2fsck
+ * to complain and force a full file system check.
+ */
+ if (!(sb->s_flags & MS_RDONLY))
+ es->s_wtime = cpu_to_le32(get_seconds());
es->s_kbytes_written =
- cpu_to_le64(EXT4_SB(sb)->s_kbytes_written +
+ cpu_to_le64(EXT4_SB(sb)->s_kbytes_written +
((part_stat_read(sb->s_bdev->bd_part, sectors[1]) -
EXT4_SB(sb)->s_sectors_written_start) >> 1));
ext4_free_blocks_count_set(es, percpu_counter_sum_positive(
char nbuf[16];
errstr = ext4_decode_error(sb, j_errno, nbuf);
- ext4_warning(sb, __func__, "Filesystem error recorded "
+ ext4_warning(sb, "Filesystem error recorded "
"from previous mount: %s", errstr);
- ext4_warning(sb, __func__, "Marking fs in need of "
- "filesystem check.");
+ ext4_warning(sb, "Marking fs in need of filesystem check.");
EXT4_SB(sb)->s_mount_state |= EXT4_ERROR_FS;
es->s_state |= cpu_to_le16(EXT4_ERROR_FS);
return 0;
journal = EXT4_SB(sb)->s_journal;
- if (journal)
+ if (journal) {
+ vfs_check_frozen(sb, SB_FREEZE_WRITE);
ret = ext4_journal_force_commit(journal);
+ }
return ret;
}
static void ext4_write_super(struct super_block *sb)
{
+ lock_super(sb);
ext4_commit_super(sb, 1);
+ unlock_super(sb);
}
static int ext4_sync_fs(struct super_block *sb, int wait)
{
int ret = 0;
tid_t target;
+ struct ext4_sb_info *sbi = EXT4_SB(sb);
- trace_mark(ext4_sync_fs, "dev %s wait %d", sb->s_id, wait);
- if (jbd2_journal_start_commit(EXT4_SB(sb)->s_journal, &target)) {
+ trace_ext4_sync_fs(sb, wait);
+ flush_workqueue(sbi->dio_unwritten_wq);
+ if (jbd2_journal_start_commit(sbi->s_journal, &target)) {
if (wait)
- jbd2_log_wait_commit(EXT4_SB(sb)->s_journal, target);
+ jbd2_log_wait_commit(sbi->s_journal, target);
}
return ret;
}
* the journal.
*/
error = jbd2_journal_flush(journal);
- if (error < 0) {
- out:
- jbd2_journal_unlock_updates(journal);
- return error;
- }
+ if (error < 0)
+ goto out;
/* Journal blocked and flushed, clear needs_recovery flag. */
EXT4_CLEAR_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER);
error = ext4_commit_super(sb, 1);
- if (error)
- goto out;
- return 0;
+out:
+ /* we rely on s_frozen to stop further updates */
+ jbd2_journal_unlock_updates(EXT4_SB(sb)->s_journal);
+ return error;
}
/*
EXT4_SET_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER);
ext4_commit_super(sb, 1);
unlock_super(sb);
- jbd2_journal_unlock_updates(EXT4_SB(sb)->s_journal);
return 0;
}
ext4_fsblk_t n_blocks_count = 0;
unsigned long old_sb_flags;
struct ext4_mount_options old_opts;
+ int enable_quota = 0;
ext4_group_t g;
unsigned int journal_ioprio = DEFAULT_JOURNAL_IOPRIO;
int err;
#ifdef CONFIG_QUOTA
int i;
#endif
+ char *orig_data = kstrdup(data, GFP_KERNEL);
+
+ lock_kernel();
/* Store the original options */
+ lock_super(sb);
old_sb_flags = sb->s_flags;
old_opts.s_mount_opt = sbi->s_mount_opt;
old_opts.s_resuid = sbi->s_resuid;
goto restore_opts;
}
- if (sbi->s_mount_opt & EXT4_MOUNT_ABORT)
+ if (sbi->s_mount_flags & EXT4_MF_FS_ABORTED)
ext4_abort(sb, __func__, "Abort forced by user");
sb->s_flags = (sb->s_flags & ~MS_POSIXACL) |
- ((sbi->s_mount_opt & EXT4_MOUNT_POSIX_ACL) ? MS_POSIXACL : 0);
+ (test_opt(sb, POSIX_ACL) ? MS_POSIXACL : 0);
es = sbi->s_es;
if ((*flags & MS_RDONLY) != (sb->s_flags & MS_RDONLY) ||
n_blocks_count > ext4_blocks_count(es)) {
- if (sbi->s_mount_opt & EXT4_MOUNT_ABORT) {
+ if (sbi->s_mount_flags & EXT4_MF_FS_ABORTED) {
err = -EROFS;
goto restore_opts;
}
if (*flags & MS_RDONLY) {
+ err = dquot_suspend(sb, -1);
+ if (err < 0)
+ goto restore_opts;
+
/*
* First of all, the unconditional stuff we have to do
* to disable replay of the journal when we next remount
if (sbi->s_journal)
ext4_mark_recovery_complete(sb, es);
} else {
- int ret;
- if ((ret = EXT4_HAS_RO_COMPAT_FEATURE(sb,
- ~EXT4_FEATURE_RO_COMPAT_SUPP))) {
- ext4_msg(sb, KERN_WARNING, "couldn't "
- "remount RDWR because of unsupported "
- "optional features (%x)",
- (le32_to_cpu(sbi->s_es->s_feature_ro_compat) &
- ~EXT4_FEATURE_RO_COMPAT_SUPP));
+ /* Make sure we can mount this feature set readwrite */
+ if (!ext4_feature_set_ok(sb, 0)) {
err = -EROFS;
goto restore_opts;
}
-
/*
* Make sure the group descriptor checksums
* are sane. If they aren't, refuse to remount r/w.
goto restore_opts;
if (!ext4_setup_super(sb, es, 0))
sb->s_flags &= ~MS_RDONLY;
+ enable_quota = 1;
}
}
ext4_setup_system_zone(sb);
old_opts.s_qf_names[i] != sbi->s_qf_names[i])
kfree(old_opts.s_qf_names[i]);
#endif
+ unlock_super(sb);
+ unlock_kernel();
+ if (enable_quota)
+ dquot_resume(sb, -1);
+
+ ext4_msg(sb, KERN_INFO, "re-mounted. Opts: %s", orig_data);
+ kfree(orig_data);
return 0;
restore_opts:
sbi->s_qf_names[i] = old_opts.s_qf_names[i];
}
#endif
+ unlock_super(sb);
+ unlock_kernel();
+ kfree(orig_data);
return err;
}
buf->f_blocks = ext4_blocks_count(es) - sbi->s_overhead_last;
buf->f_bfree = percpu_counter_sum_positive(&sbi->s_freeblocks_counter) -
percpu_counter_sum_positive(&sbi->s_dirtyblocks_counter);
- ext4_free_blocks_count_set(es, buf->f_bfree);
buf->f_bavail = buf->f_bfree - ext4_r_blocks_count(es);
if (buf->f_bfree < ext4_r_blocks_count(es))
buf->f_bavail = 0;
buf->f_files = le32_to_cpu(es->s_inodes_count);
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 = EXT4_NAME_LEN;
fsid = le64_to_cpup((void *)es->s_uuid) ^
le64_to_cpup((void *)es->s_uuid + sizeof(u64));
* Process 1 Process 2
* ext4_create() quota_sync()
* jbd2_journal_start() write_dquot()
- * vfs_dq_init() down(dqio_mutex)
+ * dquot_initialize() down(dqio_mutex)
* down(dqio_mutex) jbd2_journal_start()
*
*/
*/
static int ext4_quota_on_mount(struct super_block *sb, int type)
{
- return vfs_quota_on_mount(sb, EXT4_SB(sb)->s_qf_names[type],
- EXT4_SB(sb)->s_jquota_fmt, type);
+ return dquot_quota_on_mount(sb, EXT4_SB(sb)->s_qf_names[type],
+ EXT4_SB(sb)->s_jquota_fmt, type);
}
/*
* Standard function to be called on quota_on
*/
static int ext4_quota_on(struct super_block *sb, int type, int format_id,
- char *name, int remount)
+ char *name)
{
int err;
struct path path;
if (!test_opt(sb, QUOTA))
return -EINVAL;
- /* When remounting, no checks are needed and in fact, name is NULL */
- if (remount)
- return vfs_quota_on(sb, type, format_id, name, remount);
err = kern_path(name, LOOKUP_FOLLOW, &path);
if (err)
}
}
- err = vfs_quota_on_path(sb, type, format_id, &path);
+ err = dquot_quota_on_path(sb, type, format_id, &path);
path_put(&path);
return err;
}
ext4_lblk_t blk = off >> EXT4_BLOCK_SIZE_BITS(sb);
int err = 0;
int offset = off & (sb->s_blocksize - 1);
- int tocopy;
int journal_quota = EXT4_SB(sb)->s_qf_names[type] != NULL;
- size_t towrite = len;
struct buffer_head *bh;
handle_t *handle = journal_current_handle();
(unsigned long long)off, (unsigned long long)len);
return -EIO;
}
+ /*
+ * Since we account only one data block in transaction credits,
+ * then it is impossible to cross a block boundary.
+ */
+ if (sb->s_blocksize - offset < len) {
+ ext4_msg(sb, KERN_WARNING, "Quota write (off=%llu, len=%llu)"
+ " cancelled because not block aligned",
+ (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;
- bh = ext4_bread(handle, inode, blk, 1, &err);
- if (!bh)
+ bh = ext4_bread(handle, inode, blk, 1, &err);
+ if (!bh)
+ goto out;
+ if (journal_quota) {
+ err = ext4_journal_get_write_access(handle, bh);
+ if (err) {
+ brelse(bh);
goto out;
- if (journal_quota) {
- err = ext4_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 = ext4_handle_dirty_metadata(handle, NULL, bh);
- else {
- /* Always do at least ordered writes for quotas */
- err = ext4_jbd2_file_inode(handle, inode);
- mark_buffer_dirty(bh);
}
- brelse(bh);
- if (err)
- goto out;
- offset = 0;
- towrite -= tocopy;
- data += tocopy;
- blk++;
}
+ lock_buffer(bh);
+ memcpy(bh->b_data+offset, data, len);
+ flush_dcache_page(bh->b_page);
+ unlock_buffer(bh);
+ if (journal_quota)
+ err = ext4_handle_dirty_metadata(handle, NULL, bh);
+ else {
+ /* Always do at least ordered writes for quotas */
+ err = ext4_jbd2_file_inode(handle, inode);
+ mark_buffer_dirty(bh);
+ }
+ brelse(bh);
out:
- if (len == towrite) {
+ if (err) {
mutex_unlock(&inode->i_mutex);
return err;
}
- if (inode->i_size < off+len-towrite) {
- i_size_write(inode, off+len-towrite);
+ if (inode->i_size < off + len) {
+ i_size_write(inode, off + len);
EXT4_I(inode)->i_disksize = inode->i_size;
}
inode->i_mtime = inode->i_ctime = CURRENT_TIME;
ext4_mark_inode_dirty(handle, inode);
mutex_unlock(&inode->i_mutex);
- return len - towrite;
+ return len;
}
#endif
return get_sb_bdev(fs_type, flags, dev_name, data, ext4_fill_super,mnt);
}
-static struct file_system_type ext4_fs_type = {
+#if !defined(CONFIG_EXT2_FS) && !defined(CONFIG_EXT2_FS_MODULE) && defined(CONFIG_EXT4_USE_FOR_EXT23)
+static struct file_system_type ext2_fs_type = {
.owner = THIS_MODULE,
- .name = "ext4",
+ .name = "ext2",
.get_sb = ext4_get_sb,
.kill_sb = kill_block_super,
.fs_flags = FS_REQUIRES_DEV,
};
-#ifdef CONFIG_EXT4DEV_COMPAT
-static int ext4dev_get_sb(struct file_system_type *fs_type, int flags,
- const char *dev_name, void *data,struct vfsmount *mnt)
+static inline void register_as_ext2(void)
{
- printk(KERN_WARNING "EXT4-fs (%s): Update your userspace programs "
- "to mount using ext4\n", dev_name);
- printk(KERN_WARNING "EXT4-fs (%s): ext4dev backwards compatibility "
- "will go away by 2.6.31\n", dev_name);
- return get_sb_bdev(fs_type, flags, dev_name, data, ext4_fill_super,mnt);
+ int err = register_filesystem(&ext2_fs_type);
+ if (err)
+ printk(KERN_WARNING
+ "EXT4-fs: Unable to register as ext2 (%d)\n", err);
+}
+
+static inline void unregister_as_ext2(void)
+{
+ unregister_filesystem(&ext2_fs_type);
}
+MODULE_ALIAS("ext2");
+#else
+static inline void register_as_ext2(void) { }
+static inline void unregister_as_ext2(void) { }
+#endif
-static struct file_system_type ext4dev_fs_type = {
+#if !defined(CONFIG_EXT3_FS) && !defined(CONFIG_EXT3_FS_MODULE) && defined(CONFIG_EXT4_USE_FOR_EXT23)
+static inline void register_as_ext3(void)
+{
+ int err = register_filesystem(&ext3_fs_type);
+ if (err)
+ printk(KERN_WARNING
+ "EXT4-fs: Unable to register as ext3 (%d)\n", err);
+}
+
+static inline void unregister_as_ext3(void)
+{
+ unregister_filesystem(&ext3_fs_type);
+}
+MODULE_ALIAS("ext3");
+#else
+static inline void register_as_ext3(void) { }
+static inline void unregister_as_ext3(void) { }
+#endif
+
+static struct file_system_type ext4_fs_type = {
.owner = THIS_MODULE,
- .name = "ext4dev",
- .get_sb = ext4dev_get_sb,
+ .name = "ext4",
+ .get_sb = ext4_get_sb,
.kill_sb = kill_block_super,
.fs_flags = FS_REQUIRES_DEV,
};
-MODULE_ALIAS("ext4dev");
-#endif
static int __init init_ext4_fs(void)
{
int err;
+ ext4_check_flag_values();
err = init_ext4_system_zone();
if (err)
return err;
err = init_inodecache();
if (err)
goto out1;
+ register_as_ext2();
+ register_as_ext3();
err = register_filesystem(&ext4_fs_type);
if (err)
goto out;
-#ifdef CONFIG_EXT4DEV_COMPAT
- err = register_filesystem(&ext4dev_fs_type);
- if (err) {
- unregister_filesystem(&ext4_fs_type);
- goto out;
- }
-#endif
return 0;
out:
+ unregister_as_ext2();
+ unregister_as_ext3();
destroy_inodecache();
out1:
exit_ext4_xattr();
static void __exit exit_ext4_fs(void)
{
+ unregister_as_ext2();
+ unregister_as_ext3();
unregister_filesystem(&ext4_fs_type);
-#ifdef CONFIG_EXT4DEV_COMPAT
- unregister_filesystem(&ext4dev_fs_type);
-#endif
destroy_inodecache();
exit_ext4_xattr();
exit_ext4_mballoc();