aboutsummaryrefslogtreecommitdiff
path: root/fs/ext4/super.c
diff options
context:
space:
mode:
Diffstat (limited to 'fs/ext4/super.c')
-rw-r--r--fs/ext4/super.c1003
1 files changed, 773 insertions, 230 deletions
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 26147746c272..f6a318f836b2 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -26,7 +26,6 @@
#include <linux/init.h>
#include <linux/blkdev.h>
#include <linux/parser.h>
-#include <linux/smp_lock.h>
#include <linux/buffer_head.h>
#include <linux/exportfs.h>
#include <linux/vfs.h>
@@ -41,6 +40,9 @@
#include <linux/crc16.h>
#include <asm/uaccess.h>
+#include <linux/kthread.h>
+#include <linux/freezer.h>
+
#include "ext4.h"
#include "ext4_jbd2.h"
#include "xattr.h"
@@ -50,8 +52,11 @@
#define CREATE_TRACE_POINTS
#include <trace/events/ext4.h>
-struct proc_dir_entry *ext4_proc_root;
+static struct proc_dir_entry *ext4_proc_root;
static struct kset *ext4_kset;
+struct ext4_lazy_init *ext4_li_info;
+struct mutex ext4_li_mtx;
+struct ext4_features *ext4_feat;
static int ext4_load_journal(struct super_block *, struct ext4_super_block *,
unsigned long journal_devnum);
@@ -68,14 +73,17 @@ static int ext4_statfs(struct dentry *dentry, struct kstatfs *buf);
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);
+static struct dentry *ext4_mount(struct file_system_type *fs_type, int flags,
+ const char *dev_name, void *data);
+static void ext4_destroy_lazyinit_thread(void);
+static void ext4_unregister_li_request(struct super_block *sb);
+static void ext4_clear_request_list(void);
#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,
+ .mount = ext4_mount,
.kill_sb = kill_block_super,
.fs_flags = FS_REQUIRES_DEV,
};
@@ -381,13 +389,14 @@ static void ext4_handle_error(struct super_block *sb)
void __ext4_error(struct super_block *sb, const char *function,
unsigned int line, const char *fmt, ...)
{
+ struct va_format vaf;
va_list args;
va_start(args, fmt);
- printk(KERN_CRIT "EXT4-fs error (device %s): %s:%d: comm %s: ",
- sb->s_id, function, line, current->comm);
- vprintk(fmt, args);
- printk("\n");
+ vaf.fmt = fmt;
+ vaf.va = &args;
+ printk(KERN_CRIT "EXT4-fs error (device %s): %s:%d: comm %s: %pV\n",
+ sb->s_id, function, line, current->comm, &vaf);
va_end(args);
ext4_handle_error(sb);
@@ -398,28 +407,31 @@ void ext4_error_inode(struct inode *inode, const char *function,
const char *fmt, ...)
{
va_list args;
+ struct va_format vaf;
struct ext4_super_block *es = EXT4_SB(inode->i_sb)->s_es;
es->s_last_error_ino = cpu_to_le32(inode->i_ino);
es->s_last_error_block = cpu_to_le64(block);
save_error_info(inode->i_sb, function, line);
va_start(args, fmt);
+ vaf.fmt = fmt;
+ vaf.va = &args;
printk(KERN_CRIT "EXT4-fs error (device %s): %s:%d: inode #%lu: ",
inode->i_sb->s_id, function, line, inode->i_ino);
if (block)
- printk("block %llu: ", block);
- printk("comm %s: ", current->comm);
- vprintk(fmt, args);
- printk("\n");
+ printk(KERN_CONT "block %llu: ", block);
+ printk(KERN_CONT "comm %s: %pV\n", current->comm, &vaf);
va_end(args);
ext4_handle_error(inode->i_sb);
}
void ext4_error_file(struct file *file, const char *function,
- unsigned int line, const char *fmt, ...)
+ unsigned int line, ext4_fsblk_t block,
+ const char *fmt, ...)
{
va_list args;
+ struct va_format vaf;
struct ext4_super_block *es;
struct inode *inode = file->f_dentry->d_inode;
char pathname[80], *path;
@@ -427,17 +439,18 @@ void ext4_error_file(struct file *file, const char *function,
es = EXT4_SB(inode->i_sb)->s_es;
es->s_last_error_ino = cpu_to_le32(inode->i_ino);
save_error_info(inode->i_sb, function, line);
- va_start(args, fmt);
path = d_path(&(file->f_path), pathname, sizeof(pathname));
- if (!path)
+ if (IS_ERR(path))
path = "(unknown)";
printk(KERN_CRIT
- "EXT4-fs error (device %s): %s:%d: inode #%lu "
- "(comm %s path %s): ",
- inode->i_sb->s_id, function, line, inode->i_ino,
- current->comm, path);
- vprintk(fmt, args);
- printk("\n");
+ "EXT4-fs error (device %s): %s:%d: inode #%lu: ",
+ inode->i_sb->s_id, function, line, inode->i_ino);
+ if (block)
+ printk(KERN_CONT "block %llu: ", block);
+ va_start(args, fmt);
+ vaf.fmt = fmt;
+ vaf.va = &args;
+ printk(KERN_CONT "comm %s: path %s: %pV\n", current->comm, path, &vaf);
va_end(args);
ext4_handle_error(inode->i_sb);
@@ -536,28 +549,29 @@ void __ext4_abort(struct super_block *sb, const char *function,
panic("EXT4-fs panic from previous error\n");
}
-void ext4_msg (struct super_block * sb, const char *prefix,
- const char *fmt, ...)
+void ext4_msg(struct super_block *sb, const char *prefix, const char *fmt, ...)
{
+ struct va_format vaf;
va_list args;
va_start(args, fmt);
- printk("%sEXT4-fs (%s): ", prefix, sb->s_id);
- vprintk(fmt, args);
- printk("\n");
+ vaf.fmt = fmt;
+ vaf.va = &args;
+ printk("%sEXT4-fs (%s): %pV\n", prefix, sb->s_id, &vaf);
va_end(args);
}
void __ext4_warning(struct super_block *sb, const char *function,
unsigned int line, const char *fmt, ...)
{
+ struct va_format vaf;
va_list args;
va_start(args, fmt);
- printk(KERN_WARNING "EXT4-fs warning (device %s): %s:%d: ",
- sb->s_id, function, line);
- vprintk(fmt, args);
- printk("\n");
+ vaf.fmt = fmt;
+ vaf.va = &args;
+ printk(KERN_WARNING "EXT4-fs warning (device %s): %s:%d: %pV\n",
+ sb->s_id, function, line, &vaf);
va_end(args);
}
@@ -568,21 +582,25 @@ void __ext4_grp_locked_error(const char *function, unsigned int line,
__releases(bitlock)
__acquires(bitlock)
{
+ struct va_format vaf;
va_list args;
struct ext4_super_block *es = EXT4_SB(sb)->s_es;
es->s_last_error_ino = cpu_to_le32(ino);
es->s_last_error_block = cpu_to_le64(block);
__save_error_info(sb, function, line);
+
va_start(args, fmt);
+
+ vaf.fmt = fmt;
+ vaf.va = &args;
printk(KERN_CRIT "EXT4-fs error (device %s): %s:%d: group %u",
sb->s_id, function, line, grp);
if (ino)
- printk("inode %lu: ", ino);
+ printk(KERN_CONT "inode %lu: ", ino);
if (block)
- printk("block %llu:", (unsigned long long) block);
- vprintk(fmt, args);
- printk("\n");
+ printk(KERN_CONT "block %llu:", (unsigned long long) block);
+ printk(KERN_CONT "%pV\n", &vaf);
va_end(args);
if (test_opt(sb, ERRORS_CONT)) {
@@ -640,7 +658,7 @@ static struct block_device *ext4_blkdev_get(dev_t dev, struct super_block *sb)
struct block_device *bdev;
char b[BDEVNAME_SIZE];
- bdev = open_by_devnum(dev, FMODE_READ|FMODE_WRITE);
+ bdev = blkdev_get_by_dev(dev, FMODE_READ|FMODE_WRITE|FMODE_EXCL, sb);
if (IS_ERR(bdev))
goto fail;
return bdev;
@@ -656,8 +674,7 @@ fail:
*/
static int ext4_blkdev_put(struct block_device *bdev)
{
- bd_release(bdev);
- return blkdev_put(bdev, FMODE_READ|FMODE_WRITE);
+ return blkdev_put(bdev, FMODE_READ|FMODE_WRITE|FMODE_EXCL);
}
static int ext4_blkdev_remove(struct ext4_sb_info *sbi)
@@ -702,13 +719,13 @@ static void ext4_put_super(struct super_block *sb)
struct ext4_super_block *es = sbi->s_es;
int i, err;
+ ext4_unregister_li_request(sb);
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_commit_super(sb, 1);
@@ -719,6 +736,7 @@ static void ext4_put_super(struct super_block *sb)
ext4_abort(sb, "Couldn't clean up the journal");
}
+ del_timer(&sbi->s_err_report);
ext4_release_system_zone(sb);
ext4_mb_release(sb);
ext4_ext_release(sb);
@@ -775,7 +793,6 @@ static void ext4_put_super(struct super_block *sb)
* Now that we are completely done shutting down the
* superblock, we need to actually destroy the kobject.
*/
- unlock_kernel();
unlock_super(sb);
kobject_put(&sbi->s_kobj);
wait_for_completion(&sbi->s_kobj_unregister);
@@ -801,32 +818,44 @@ static struct inode *ext4_alloc_inode(struct super_block *sb)
memset(&ei->i_cached_extent, 0, sizeof(struct ext4_ext_cache));
INIT_LIST_HEAD(&ei->i_prealloc_list);
spin_lock_init(&ei->i_prealloc_lock);
- /*
- * Note: We can be called before EXT4_SB(sb)->s_journal is set,
- * therefore it can be null here. Don't check it, just initialize
- * jinode.
- */
- jbd2_journal_init_jbd_inode(&ei->jinode, &ei->vfs_inode);
ei->i_reserved_data_blocks = 0;
ei->i_reserved_meta_blocks = 0;
ei->i_allocated_meta_blocks = 0;
ei->i_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
+ ei->jinode = NULL;
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;
+ atomic_set(&ei->i_ioend_count, 0);
+ atomic_set(&ei->i_aiodio_unwritten, 0);
return &ei->vfs_inode;
}
+static int ext4_drop_inode(struct inode *inode)
+{
+ int drop = generic_drop_inode(inode);
+
+ trace_ext4_drop_inode(inode, drop);
+ return drop;
+}
+
+static void ext4_i_callback(struct rcu_head *head)
+{
+ struct inode *inode = container_of(head, struct inode, i_rcu);
+ INIT_LIST_HEAD(&inode->i_dentry);
+ kmem_cache_free(ext4_inode_cachep, EXT4_I(inode));
+}
+
static void ext4_destroy_inode(struct inode *inode)
{
+ ext4_ioend_wait(inode);
if (!list_empty(&(EXT4_I(inode)->i_orphan))) {
ext4_msg(inode->i_sb, KERN_ERR,
"Inode %lu (%p): orphan list check failed!",
@@ -836,7 +865,7 @@ static void ext4_destroy_inode(struct inode *inode)
true);
dump_stack();
}
- kmem_cache_free(ext4_inode_cachep, EXT4_I(inode));
+ call_rcu(&inode->i_rcu, ext4_i_callback);
}
static void init_once(void *foo)
@@ -874,9 +903,12 @@ void ext4_clear_inode(struct inode *inode)
end_writeback(inode);
dquot_drop(inode);
ext4_discard_preallocations(inode);
- if (EXT4_JOURNAL(inode))
- jbd2_journal_release_jbd_inode(EXT4_SB(inode->i_sb)->s_journal,
- &EXT4_I(inode)->jinode);
+ if (EXT4_I(inode)->jinode) {
+ jbd2_journal_release_jbd_inode(EXT4_JOURNAL(inode),
+ EXT4_I(inode)->jinode);
+ jbd2_free_inode(EXT4_I(inode)->jinode);
+ EXT4_I(inode)->jinode = NULL;
+ }
}
static inline void ext4_show_quota_options(struct seq_file *seq,
@@ -1009,6 +1041,8 @@ static int ext4_show_options(struct seq_file *seq, struct vfsmount *vfs)
!(def_mount_opts & EXT4_DEFM_NODELALLOC))
seq_puts(seq, ",nodelalloc");
+ if (test_opt(sb, MBLK_IO_SUBMIT))
+ seq_puts(seq, ",mblk_io_submit");
if (sbi->s_stripe)
seq_printf(seq, ",stripe=%lu", sbi->s_stripe);
/*
@@ -1045,6 +1079,12 @@ static int ext4_show_options(struct seq_file *seq, struct vfsmount *vfs)
!(def_mount_opts & EXT4_DEFM_BLOCK_VALIDITY))
seq_puts(seq, ",block_validity");
+ if (!test_opt(sb, INIT_INODE_TABLE))
+ seq_puts(seq, ",noinit_inode_table");
+ else if (sbi->s_li_wait_mult)
+ seq_printf(seq, ",init_inode_table=%u",
+ (unsigned) sbi->s_li_wait_mult);
+
ext4_show_quota_options(seq, sb);
return 0;
@@ -1123,7 +1163,7 @@ static int ext4_release_dquot(struct dquot *dquot);
static int ext4_mark_dquot_dirty(struct dquot *dquot);
static int ext4_write_info(struct super_block *sb, int type);
static int ext4_quota_on(struct super_block *sb, int type, int format_id,
- char *path);
+ struct path *path);
static int ext4_quota_off(struct super_block *sb, int type);
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,
@@ -1160,6 +1200,7 @@ static const struct super_operations ext4_sops = {
.destroy_inode = ext4_destroy_inode,
.write_inode = ext4_write_inode,
.dirty_inode = ext4_dirty_inode,
+ .drop_inode = ext4_drop_inode,
.evict_inode = ext4_evict_inode,
.put_super = ext4_put_super,
.sync_fs = ext4_sync_fs,
@@ -1180,6 +1221,7 @@ static const struct super_operations ext4_nojournal_sops = {
.destroy_inode = ext4_destroy_inode,
.write_inode = ext4_write_inode,
.dirty_inode = ext4_dirty_inode,
+ .drop_inode = ext4_drop_inode,
.evict_inode = ext4_evict_inode,
.write_super = ext4_write_super,
.put_super = ext4_put_super,
@@ -1214,11 +1256,12 @@ enum {
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_stripe, Opt_delalloc, Opt_nodelalloc, Opt_mblk_io_submit,
+ Opt_nomblk_io_submit, Opt_block_validity, Opt_noblock_validity,
Opt_inode_readahead_blks, Opt_journal_ioprio,
Opt_dioread_nolock, Opt_dioread_lock,
Opt_discard, Opt_nodiscard,
+ Opt_init_inode_table, Opt_noinit_inode_table,
};
static const match_table_t tokens = {
@@ -1278,6 +1321,8 @@ static const match_table_t tokens = {
{Opt_resize, "resize"},
{Opt_delalloc, "delalloc"},
{Opt_nodelalloc, "nodelalloc"},
+ {Opt_mblk_io_submit, "mblk_io_submit"},
+ {Opt_nomblk_io_submit, "nomblk_io_submit"},
{Opt_block_validity, "block_validity"},
{Opt_noblock_validity, "noblock_validity"},
{Opt_inode_readahead_blks, "inode_readahead_blks=%u"},
@@ -1289,6 +1334,9 @@ static const match_table_t tokens = {
{Opt_dioread_lock, "dioread_lock"},
{Opt_discard, "discard"},
{Opt_nodiscard, "nodiscard"},
+ {Opt_init_inode_table, "init_itable=%u"},
+ {Opt_init_inode_table, "init_itable"},
+ {Opt_noinit_inode_table, "noinit_itable"},
{Opt_err, NULL},
};
@@ -1353,7 +1401,7 @@ static int set_qf_name(struct super_block *sb, int qtype, substring_t *args)
sbi->s_qf_names[qtype] = NULL;
return 0;
}
- set_opt(sbi->s_mount_opt, QUOTA);
+ set_opt(sb, QUOTA);
return 1;
}
@@ -1408,21 +1456,21 @@ static int parse_options(char *options, struct super_block *sb,
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);
+ clear_opt(sb, 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);
+ set_opt(sb, MINIX_DF);
break;
case Opt_grpid:
ext4_msg(sb, KERN_WARNING, deprecated_msg, p, "2.6.38");
- set_opt(sbi->s_mount_opt, GRPID);
+ set_opt(sb, GRPID);
break;
case Opt_nogrpid:
ext4_msg(sb, KERN_WARNING, deprecated_msg, p, "2.6.38");
- clear_opt(sbi->s_mount_opt, GRPID);
+ clear_opt(sb, GRPID);
break;
case Opt_resuid:
@@ -1440,38 +1488,38 @@ static int parse_options(char *options, struct super_block *sb,
/* *sb_block = match_int(&args[0]); */
break;
case Opt_err_panic:
- clear_opt(sbi->s_mount_opt, ERRORS_CONT);
- clear_opt(sbi->s_mount_opt, ERRORS_RO);
- set_opt(sbi->s_mount_opt, ERRORS_PANIC);
+ clear_opt(sb, ERRORS_CONT);
+ clear_opt(sb, ERRORS_RO);
+ set_opt(sb, ERRORS_PANIC);
break;
case Opt_err_ro:
- clear_opt(sbi->s_mount_opt, ERRORS_CONT);
- clear_opt(sbi->s_mount_opt, ERRORS_PANIC);
- set_opt(sbi->s_mount_opt, ERRORS_RO);
+ clear_opt(sb, ERRORS_CONT);
+ clear_opt(sb, ERRORS_PANIC);
+ set_opt(sb, ERRORS_RO);
break;
case Opt_err_cont:
- clear_opt(sbi->s_mount_opt, ERRORS_RO);
- clear_opt(sbi->s_mount_opt, ERRORS_PANIC);
- set_opt(sbi->s_mount_opt, ERRORS_CONT);
+ clear_opt(sb, ERRORS_RO);
+ clear_opt(sb, ERRORS_PANIC);
+ set_opt(sb, ERRORS_CONT);
break;
case Opt_nouid32:
- set_opt(sbi->s_mount_opt, NO_UID32);
+ set_opt(sb, NO_UID32);
break;
case Opt_debug:
- set_opt(sbi->s_mount_opt, DEBUG);
+ set_opt(sb, DEBUG);
break;
case Opt_oldalloc:
- set_opt(sbi->s_mount_opt, OLDALLOC);
+ set_opt(sb, OLDALLOC);
break;
case Opt_orlov:
- clear_opt(sbi->s_mount_opt, OLDALLOC);
+ clear_opt(sb, OLDALLOC);
break;
#ifdef CONFIG_EXT4_FS_XATTR
case Opt_user_xattr:
- set_opt(sbi->s_mount_opt, XATTR_USER);
+ set_opt(sb, XATTR_USER);
break;
case Opt_nouser_xattr:
- clear_opt(sbi->s_mount_opt, XATTR_USER);
+ clear_opt(sb, XATTR_USER);
break;
#else
case Opt_user_xattr:
@@ -1481,10 +1529,10 @@ static int parse_options(char *options, struct super_block *sb,
#endif
#ifdef CONFIG_EXT4_FS_POSIX_ACL
case Opt_acl:
- set_opt(sbi->s_mount_opt, POSIX_ACL);
+ set_opt(sb, POSIX_ACL);
break;
case Opt_noacl:
- clear_opt(sbi->s_mount_opt, POSIX_ACL);
+ clear_opt(sb, POSIX_ACL);
break;
#else
case Opt_acl:
@@ -1503,7 +1551,7 @@ static int parse_options(char *options, struct super_block *sb,
"Cannot specify journal on remount");
return 0;
}
- set_opt(sbi->s_mount_opt, UPDATE_JOURNAL);
+ set_opt(sb, UPDATE_JOURNAL);
break;
case Opt_journal_dev:
if (is_remount) {
@@ -1516,14 +1564,14 @@ static int parse_options(char *options, struct super_block *sb,
*journal_devnum = option;
break;
case Opt_journal_checksum:
- set_opt(sbi->s_mount_opt, JOURNAL_CHECKSUM);
+ set_opt(sb, JOURNAL_CHECKSUM);
break;
case Opt_journal_async_commit:
- set_opt(sbi->s_mount_opt, JOURNAL_ASYNC_COMMIT);
- set_opt(sbi->s_mount_opt, JOURNAL_CHECKSUM);
+ set_opt(sb, JOURNAL_ASYNC_COMMIT);
+ set_opt(sb, JOURNAL_CHECKSUM);
break;
case Opt_noload:
- set_opt(sbi->s_mount_opt, NOLOAD);
+ set_opt(sb, NOLOAD);
break;
case Opt_commit:
if (match_int(&args[0], &option))
@@ -1566,15 +1614,15 @@ static int parse_options(char *options, struct super_block *sb,
return 0;
}
} else {
- clear_opt(sbi->s_mount_opt, DATA_FLAGS);
+ clear_opt(sb, DATA_FLAGS);
sbi->s_mount_opt |= data_opt;
}
break;
case Opt_data_err_abort:
- set_opt(sbi->s_mount_opt, DATA_ERR_ABORT);
+ set_opt(sb, DATA_ERR_ABORT);
break;
case Opt_data_err_ignore:
- clear_opt(sbi->s_mount_opt, DATA_ERR_ABORT);
+ clear_opt(sb, DATA_ERR_ABORT);
break;
#ifdef CONFIG_QUOTA
case Opt_usrjquota:
@@ -1614,12 +1662,12 @@ set_qf_format:
break;
case Opt_quota:
case Opt_usrquota:
- set_opt(sbi->s_mount_opt, QUOTA);
- set_opt(sbi->s_mount_opt, USRQUOTA);
+ set_opt(sb, QUOTA);
+ set_opt(sb, USRQUOTA);
break;
case Opt_grpquota:
- set_opt(sbi->s_mount_opt, QUOTA);
- set_opt(sbi->s_mount_opt, GRPQUOTA);
+ set_opt(sb, QUOTA);
+ set_opt(sb, GRPQUOTA);
break;
case Opt_noquota:
if (sb_any_quota_loaded(sb)) {
@@ -1627,9 +1675,9 @@ set_qf_format:
"options when quota turned on");
return 0;
}
- clear_opt(sbi->s_mount_opt, QUOTA);
- clear_opt(sbi->s_mount_opt, USRQUOTA);
- clear_opt(sbi->s_mount_opt, GRPQUOTA);
+ clear_opt(sb, QUOTA);
+ clear_opt(sb, USRQUOTA);
+ clear_opt(sb, GRPQUOTA);
break;
#else
case Opt_quota:
@@ -1655,7 +1703,7 @@ set_qf_format:
sbi->s_mount_flags |= EXT4_MF_FS_ABORTED;
break;
case Opt_nobarrier:
- clear_opt(sbi->s_mount_opt, BARRIER);
+ clear_opt(sb, BARRIER);
break;
case Opt_barrier:
if (args[0].from) {
@@ -1664,9 +1712,9 @@ set_qf_format:
} else
option = 1; /* No argument, default to 1 */
if (option)
- set_opt(sbi->s_mount_opt, BARRIER);
+ set_opt(sb, BARRIER);
else
- clear_opt(sbi->s_mount_opt, BARRIER);
+ clear_opt(sb, BARRIER);
break;
case Opt_ignore:
break;
@@ -1690,11 +1738,17 @@ set_qf_format:
"Ignoring deprecated bh option");
break;
case Opt_i_version:
- set_opt(sbi->s_mount_opt, I_VERSION);
+ set_opt(sb, I_VERSION);
sb->s_flags |= MS_I_VERSION;
break;
case Opt_nodelalloc:
- clear_opt(sbi->s_mount_opt, DELALLOC);
+ clear_opt(sb, DELALLOC);
+ break;
+ case Opt_mblk_io_submit:
+ set_opt(sb, MBLK_IO_SUBMIT);
+ break;
+ case Opt_nomblk_io_submit:
+ clear_opt(sb, MBLK_IO_SUBMIT);
break;
case Opt_stripe:
if (match_int(&args[0], &option))
@@ -1704,13 +1758,13 @@ set_qf_format:
sbi->s_stripe = option;
break;
case Opt_delalloc:
- set_opt(sbi->s_mount_opt, DELALLOC);
+ set_opt(sb, DELALLOC);
break;
case Opt_block_validity:
- set_opt(sbi->s_mount_opt, BLOCK_VALIDITY);
+ set_opt(sb, BLOCK_VALIDITY);
break;
case Opt_noblock_validity:
- clear_opt(sbi->s_mount_opt, BLOCK_VALIDITY);
+ clear_opt(sb, BLOCK_VALIDITY);
break;
case Opt_inode_readahead_blks:
if (match_int(&args[0], &option))
@@ -1734,7 +1788,7 @@ set_qf_format:
option);
break;
case Opt_noauto_da_alloc:
- set_opt(sbi->s_mount_opt,NO_AUTO_DA_ALLOC);
+ set_opt(sb, NO_AUTO_DA_ALLOC);
break;
case Opt_auto_da_alloc:
if (args[0].from) {
@@ -1743,21 +1797,35 @@ set_qf_format:
} else
option = 1; /* No argument, default to 1 */
if (option)
- clear_opt(sbi->s_mount_opt, NO_AUTO_DA_ALLOC);
+ clear_opt(sb, NO_AUTO_DA_ALLOC);
else
- set_opt(sbi->s_mount_opt,NO_AUTO_DA_ALLOC);
+ set_opt(sb,NO_AUTO_DA_ALLOC);
break;
case Opt_discard:
- set_opt(sbi->s_mount_opt, DISCARD);
+ set_opt(sb, DISCARD);
break;
case Opt_nodiscard:
- clear_opt(sbi->s_mount_opt, DISCARD);
+ clear_opt(sb, DISCARD);
break;
case Opt_dioread_nolock:
- set_opt(sbi->s_mount_opt, DIOREAD_NOLOCK);
+ set_opt(sb, DIOREAD_NOLOCK);
break;
case Opt_dioread_lock:
- clear_opt(sbi->s_mount_opt, DIOREAD_NOLOCK);
+ clear_opt(sb, DIOREAD_NOLOCK);
+ break;
+ case Opt_init_inode_table:
+ set_opt(sb, INIT_INODE_TABLE);
+ if (args[0].from) {
+ if (match_int(&args[0], &option))
+ return 0;
+ } else
+ option = EXT4_DEF_LI_WAIT_MULT;
+ if (option < 0)
+ return 0;
+ sbi->s_li_wait_mult = option;
+ break;
+ case Opt_noinit_inode_table:
+ clear_opt(sb, INIT_INODE_TABLE);
break;
default:
ext4_msg(sb, KERN_ERR,
@@ -1769,10 +1837,10 @@ set_qf_format:
#ifdef CONFIG_QUOTA
if (sbi->s_qf_names[USRQUOTA] || sbi->s_qf_names[GRPQUOTA]) {
if (test_opt(sb, USRQUOTA) && sbi->s_qf_names[USRQUOTA])
- clear_opt(sbi->s_mount_opt, USRQUOTA);
+ clear_opt(sb, USRQUOTA);
if (test_opt(sb, GRPQUOTA) && sbi->s_qf_names[GRPQUOTA])
- clear_opt(sbi->s_mount_opt, GRPQUOTA);
+ clear_opt(sb, GRPQUOTA);
if (test_opt(sb, GRPQUOTA) || test_opt(sb, USRQUOTA)) {
ext4_msg(sb, KERN_ERR, "old and new quota "
@@ -1842,12 +1910,12 @@ static int ext4_setup_super(struct super_block *sb, struct ext4_super_block *es,
ext4_commit_super(sb, 1);
if (test_opt(sb, DEBUG))
printk(KERN_INFO "[EXT4 FS bs=%lu, gc=%u, "
- "bpg=%lu, ipg=%lu, mo=%04x]\n",
+ "bpg=%lu, ipg=%lu, mo=%04x, mo2=%04x]\n",
sb->s_blocksize,
sbi->s_groups_count,
EXT4_BLOCKS_PER_GROUP(sb),
EXT4_INODES_PER_GROUP(sb),
- sbi->s_mount_opt);
+ sbi->s_mount_opt, sbi->s_mount_opt2);
return res;
}
@@ -1877,14 +1945,13 @@ static int ext4_fill_flex_info(struct super_block *sb)
size = flex_group_count * sizeof(struct flex_groups);
sbi->s_flex_groups = kzalloc(size, GFP_KERNEL);
if (sbi->s_flex_groups == NULL) {
- sbi->s_flex_groups = vmalloc(size);
- if (sbi->s_flex_groups)
- memset(sbi->s_flex_groups, 0, size);
- }
- if (sbi->s_flex_groups == NULL) {
- ext4_msg(sb, KERN_ERR, "not enough memory for "
- "%u flex groups", flex_group_count);
- goto failed;
+ sbi->s_flex_groups = vzalloc(size);
+ if (sbi->s_flex_groups == NULL) {
+ ext4_msg(sb, KERN_ERR,
+ "not enough memory for %u flex groups",
+ flex_group_count);
+ goto failed;
+ }
}
for (i = 0; i < sbi->s_groups_count; i++) {
@@ -1942,7 +2009,8 @@ int ext4_group_desc_csum_verify(struct ext4_sb_info *sbi, __u32 block_group,
}
/* Called at mount-time, super-block is locked */
-static int ext4_check_descriptors(struct super_block *sb)
+static int ext4_check_descriptors(struct super_block *sb,
+ ext4_group_t *first_not_zeroed)
{
struct ext4_sb_info *sbi = EXT4_SB(sb);
ext4_fsblk_t first_block = le32_to_cpu(sbi->s_es->s_first_data_block);
@@ -1951,7 +2019,7 @@ static int ext4_check_descriptors(struct super_block *sb)
ext4_fsblk_t inode_bitmap;
ext4_fsblk_t inode_table;
int flexbg_flag = 0;
- ext4_group_t i;
+ ext4_group_t i, grp = sbi->s_groups_count;
if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_FLEX_BG))
flexbg_flag = 1;
@@ -1967,6 +2035,10 @@ static int ext4_check_descriptors(struct super_block *sb)
last_block = first_block +
(EXT4_BLOCKS_PER_GROUP(sb) - 1);
+ if ((grp == sbi->s_groups_count) &&
+ !(gdp->bg_flags & cpu_to_le16(EXT4_BG_INODE_ZEROED)))
+ grp = i;
+
block_bitmap = ext4_block_bitmap(sb, gdp);
if (block_bitmap < first_block || block_bitmap > last_block) {
ext4_msg(sb, KERN_ERR, "ext4_check_descriptors: "
@@ -2004,6 +2076,8 @@ static int ext4_check_descriptors(struct super_block *sb)
if (!flexbg_flag)
first_block += EXT4_BLOCKS_PER_GROUP(sb);
}
+ if (NULL != first_not_zeroed)
+ *first_not_zeroed = grp;
ext4_free_blocks_count_set(sbi->s_es, ext4_count_free_blocks(sb));
sbi->s_es->s_free_inodes_count =cpu_to_le32(ext4_count_free_inodes(sb));
@@ -2376,6 +2450,7 @@ static struct ext4_attr ext4_attr_##_name = { \
#define EXT4_ATTR(name, mode, show, store) \
static struct ext4_attr ext4_attr_##name = __ATTR(name, mode, show, store)
+#define EXT4_INFO_ATTR(name) EXT4_ATTR(name, 0444, NULL, NULL)
#define EXT4_RO_ATTR(name) EXT4_ATTR(name, 0444, name##_show, NULL)
#define EXT4_RW_ATTR(name) EXT4_ATTR(name, 0644, name##_show, name##_store)
#define EXT4_RW_ATTR_SBI_UI(name, elname) \
@@ -2412,6 +2487,16 @@ static struct attribute *ext4_attrs[] = {
NULL,
};
+/* Features this copy of ext4 supports */
+EXT4_INFO_ATTR(lazy_itable_init);
+EXT4_INFO_ATTR(batched_discard);
+
+static struct attribute *ext4_feat_attrs[] = {
+ ATTR_LIST(lazy_itable_init),
+ ATTR_LIST(batched_discard),
+ NULL,
+};
+
static ssize_t ext4_attr_show(struct kobject *kobj,
struct attribute *attr, char *buf)
{
@@ -2440,7 +2525,6 @@ static void ext4_sb_release(struct kobject *kobj)
complete(&sbi->s_kobj_unregister);
}
-
static const struct sysfs_ops ext4_attr_ops = {
.show = ext4_attr_show,
.store = ext4_attr_store,
@@ -2452,6 +2536,17 @@ static struct kobj_type ext4_ktype = {
.release = ext4_sb_release,
};
+static void ext4_feat_release(struct kobject *kobj)
+{
+ complete(&ext4_feat->f_kobj_unregister);
+}
+
+static struct kobj_type ext4_feat_ktype = {
+ .default_attrs = ext4_feat_attrs,
+ .sysfs_ops = &ext4_attr_ops,
+ .release = ext4_feat_release,
+};
+
/*
* Check whether this filesystem can be mounted based on
* the features present and the RDONLY/RDWR mount requested.
@@ -2542,6 +2637,368 @@ static void print_daily_error_info(unsigned long arg)
mod_timer(&sbi->s_err_report, jiffies + 24*60*60*HZ); /* Once a day */
}
+static void ext4_lazyinode_timeout(unsigned long data)
+{
+ struct task_struct *p = (struct task_struct *)data;
+ wake_up_process(p);
+}
+
+/* Find next suitable group and run ext4_init_inode_table */
+static int ext4_run_li_request(struct ext4_li_request *elr)
+{
+ struct ext4_group_desc *gdp = NULL;
+ ext4_group_t group, ngroups;
+ struct super_block *sb;
+ unsigned long timeout = 0;
+ int ret = 0;
+
+ sb = elr->lr_super;
+ ngroups = EXT4_SB(sb)->s_groups_count;
+
+ for (group = elr->lr_next_group; group < ngroups; group++) {
+ gdp = ext4_get_group_desc(sb, group, NULL);
+ if (!gdp) {
+ ret = 1;
+ break;
+ }
+
+ if (!(gdp->bg_flags & cpu_to_le16(EXT4_BG_INODE_ZEROED)))
+ break;
+ }
+
+ if (group == ngroups)
+ ret = 1;
+
+ if (!ret) {
+ timeout = jiffies;
+ ret = ext4_init_inode_table(sb, group,
+ elr->lr_timeout ? 0 : 1);
+ if (elr->lr_timeout == 0) {
+ timeout = jiffies - timeout;
+ if (elr->lr_sbi->s_li_wait_mult)
+ timeout *= elr->lr_sbi->s_li_wait_mult;
+ else
+ timeout *= 20;
+ elr->lr_timeout = timeout;
+ }
+ elr->lr_next_sched = jiffies + elr->lr_timeout;
+ elr->lr_next_group = group + 1;
+ }
+
+ return ret;
+}
+
+/*
+ * Remove lr_request from the list_request and free the
+ * request tructure. Should be called with li_list_mtx held
+ */
+static void ext4_remove_li_request(struct ext4_li_request *elr)
+{
+ struct ext4_sb_info *sbi;
+
+ if (!elr)
+ return;
+
+ sbi = elr->lr_sbi;
+
+ list_del(&elr->lr_request);
+ sbi->s_li_request = NULL;
+ kfree(elr);
+}
+
+static void ext4_unregister_li_request(struct super_block *sb)
+{
+ struct ext4_li_request *elr = EXT4_SB(sb)->s_li_request;
+
+ if (!ext4_li_info)
+ return;
+
+ mutex_lock(&ext4_li_info->li_list_mtx);
+ ext4_remove_li_request(elr);
+ mutex_unlock(&ext4_li_info->li_list_mtx);
+}
+
+static struct task_struct *ext4_lazyinit_task;
+
+/*
+ * This is the function where ext4lazyinit thread lives. It walks
+ * through the request list searching for next scheduled filesystem.
+ * When such a fs is found, run the lazy initialization request
+ * (ext4_rn_li_request) and keep track of the time spend in this
+ * function. Based on that time we compute next schedule time of
+ * the request. When walking through the list is complete, compute
+ * next waking time and put itself into sleep.
+ */
+static int ext4_lazyinit_thread(void *arg)
+{
+ struct ext4_lazy_init *eli = (struct ext4_lazy_init *)arg;
+ struct list_head *pos, *n;
+ struct ext4_li_request *elr;
+ unsigned long next_wakeup;
+ DEFINE_WAIT(wait);
+
+ BUG_ON(NULL == eli);
+
+ eli->li_timer.data = (unsigned long)current;
+ eli->li_timer.function = ext4_lazyinode_timeout;
+
+ eli->li_task = current;
+ wake_up(&eli->li_wait_task);
+
+cont_thread:
+ while (true) {
+ next_wakeup = MAX_JIFFY_OFFSET;
+
+ mutex_lock(&eli->li_list_mtx);
+ if (list_empty(&eli->li_request_list)) {
+ mutex_unlock(&eli->li_list_mtx);
+ goto exit_thread;
+ }
+
+ list_for_each_safe(pos, n, &eli->li_request_list) {
+ elr = list_entry(pos, struct ext4_li_request,
+ lr_request);
+
+ if (time_after_eq(jiffies, elr->lr_next_sched)) {
+ if (ext4_run_li_request(elr) != 0) {
+ /* error, remove the lazy_init job */
+ ext4_remove_li_request(elr);
+ continue;
+ }
+ }
+
+ if (time_before(elr->lr_next_sched, next_wakeup))
+ next_wakeup = elr->lr_next_sched;
+ }
+ mutex_unlock(&eli->li_list_mtx);
+
+ if (freezing(current))
+ refrigerator();
+
+ if ((time_after_eq(jiffies, next_wakeup)) ||
+ (MAX_JIFFY_OFFSET == next_wakeup)) {
+ cond_resched();
+ continue;
+ }
+
+ eli->li_timer.expires = next_wakeup;
+ add_timer(&eli->li_timer);
+ prepare_to_wait(&eli->li_wait_daemon, &wait,
+ TASK_INTERRUPTIBLE);
+ if (time_before(jiffies, next_wakeup))
+ schedule();
+ finish_wait(&eli->li_wait_daemon, &wait);
+ if (kthread_should_stop()) {
+ ext4_clear_request_list();
+ goto exit_thread;
+ }
+ }
+
+exit_thread:
+ /*
+ * It looks like the request list is empty, but we need
+ * to check it under the li_list_mtx lock, to prevent any
+ * additions into it, and of course we should lock ext4_li_mtx
+ * to atomically free the list and ext4_li_info, because at
+ * this point another ext4 filesystem could be registering
+ * new one.
+ */
+ mutex_lock(&ext4_li_mtx);
+ mutex_lock(&eli->li_list_mtx);
+ if (!list_empty(&eli->li_request_list)) {
+ mutex_unlock(&eli->li_list_mtx);
+ mutex_unlock(&ext4_li_mtx);
+ goto cont_thread;
+ }
+ mutex_unlock(&eli->li_list_mtx);
+ del_timer_sync(&ext4_li_info->li_timer);
+ eli->li_task = NULL;
+ wake_up(&eli->li_wait_task);
+
+ kfree(ext4_li_info);
+ ext4_lazyinit_task = NULL;
+ ext4_li_info = NULL;
+ mutex_unlock(&ext4_li_mtx);
+
+ return 0;
+}
+
+static void ext4_clear_request_list(void)
+{
+ struct list_head *pos, *n;
+ struct ext4_li_request *elr;
+
+ mutex_lock(&ext4_li_info->li_list_mtx);
+ list_for_each_safe(pos, n, &ext4_li_info->li_request_list) {
+ elr = list_entry(pos, struct ext4_li_request,
+ lr_request);
+ ext4_remove_li_request(elr);
+ }
+ mutex_unlock(&ext4_li_info->li_list_mtx);
+}
+
+static int ext4_run_lazyinit_thread(void)
+{
+ ext4_lazyinit_task = kthread_run(ext4_lazyinit_thread,
+ ext4_li_info, "ext4lazyinit");
+ if (IS_ERR(ext4_lazyinit_task)) {
+ int err = PTR_ERR(ext4_lazyinit_task);
+ ext4_clear_request_list();
+ del_timer_sync(&ext4_li_info->li_timer);
+ kfree(ext4_li_info);
+ ext4_li_info = NULL;
+ printk(KERN_CRIT "EXT4: error %d creating inode table "
+ "initialization thread\n",
+ err);
+ return err;
+ }
+ ext4_li_info->li_state |= EXT4_LAZYINIT_RUNNING;
+
+ wait_event(ext4_li_info->li_wait_task, ext4_li_info->li_task != NULL);
+ return 0;
+}
+
+/*
+ * Check whether it make sense to run itable init. thread or not.
+ * If there is at least one uninitialized inode table, return
+ * corresponding group number, else the loop goes through all
+ * groups and return total number of groups.
+ */
+static ext4_group_t ext4_has_uninit_itable(struct super_block *sb)
+{
+ ext4_group_t group, ngroups = EXT4_SB(sb)->s_groups_count;
+ struct ext4_group_desc *gdp = NULL;
+
+ for (group = 0; group < ngroups; group++) {
+ gdp = ext4_get_group_desc(sb, group, NULL);
+ if (!gdp)
+ continue;
+
+ if (!(gdp->bg_flags & cpu_to_le16(EXT4_BG_INODE_ZEROED)))
+ break;
+ }
+
+ return group;
+}
+
+static int ext4_li_info_new(void)
+{
+ struct ext4_lazy_init *eli = NULL;
+
+ eli = kzalloc(sizeof(*eli), GFP_KERNEL);
+ if (!eli)
+ return -ENOMEM;
+
+ eli->li_task = NULL;
+ INIT_LIST_HEAD(&eli->li_request_list);
+ mutex_init(&eli->li_list_mtx);
+
+ init_waitqueue_head(&eli->li_wait_daemon);
+ init_waitqueue_head(&eli->li_wait_task);
+ init_timer(&eli->li_timer);
+ eli->li_state |= EXT4_LAZYINIT_QUIT;
+
+ ext4_li_info = eli;
+
+ return 0;
+}
+
+static struct ext4_li_request *ext4_li_request_new(struct super_block *sb,
+ ext4_group_t start)
+{
+ struct ext4_sb_info *sbi = EXT4_SB(sb);
+ struct ext4_li_request *elr;
+ unsigned long rnd;
+
+ elr = kzalloc(sizeof(*elr), GFP_KERNEL);
+ if (!elr)
+ return NULL;
+
+ elr->lr_super = sb;
+ elr->lr_sbi = sbi;
+ elr->lr_next_group = start;
+
+ /*
+ * Randomize first schedule time of the request to
+ * spread the inode table initialization requests
+ * better.
+ */
+ get_random_bytes(&rnd, sizeof(rnd));
+ elr->lr_next_sched = jiffies + (unsigned long)rnd %
+ (EXT4_DEF_LI_MAX_START_DELAY * HZ);
+
+ return elr;
+}
+
+static int ext4_register_li_request(struct super_block *sb,
+ ext4_group_t first_not_zeroed)
+{
+ struct ext4_sb_info *sbi = EXT4_SB(sb);
+ struct ext4_li_request *elr;
+ ext4_group_t ngroups = EXT4_SB(sb)->s_groups_count;
+ int ret = 0;
+
+ if (sbi->s_li_request != NULL)
+ return 0;
+
+ if (first_not_zeroed == ngroups ||
+ (sb->s_flags & MS_RDONLY) ||
+ !test_opt(sb, INIT_INODE_TABLE)) {
+ sbi->s_li_request = NULL;
+ return 0;
+ }
+
+ if (first_not_zeroed == ngroups) {
+ sbi->s_li_request = NULL;
+ return 0;
+ }
+
+ elr = ext4_li_request_new(sb, first_not_zeroed);
+ if (!elr)
+ return -ENOMEM;
+
+ mutex_lock(&ext4_li_mtx);
+
+ if (NULL == ext4_li_info) {
+ ret = ext4_li_info_new();
+ if (ret)
+ goto out;
+ }
+
+ mutex_lock(&ext4_li_info->li_list_mtx);
+ list_add(&elr->lr_request, &ext4_li_info->li_request_list);
+ mutex_unlock(&ext4_li_info->li_list_mtx);
+
+ sbi->s_li_request = elr;
+
+ if (!(ext4_li_info->li_state & EXT4_LAZYINIT_RUNNING)) {
+ ret = ext4_run_lazyinit_thread();
+ if (ret)
+ goto out;
+ }
+out:
+ mutex_unlock(&ext4_li_mtx);
+ if (ret)
+ kfree(elr);
+ return ret;
+}
+
+/*
+ * We do not need to lock anything since this is called on
+ * module unload.
+ */
+static void ext4_destroy_lazyinit_thread(void)
+{
+ /*
+ * If thread exited earlier
+ * there's nothing to be done.
+ */
+ if (!ext4_li_info || !ext4_lazyinit_task)
+ return;
+
+ kthread_stop(ext4_lazyinit_task);
+}
+
static int ext4_fill_super(struct super_block *sb, void *data, int silent)
__releases(kernel_lock)
__acquires(kernel_lock)
@@ -2567,6 +3024,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
__u64 blocks_count;
int err;
unsigned int journal_ioprio = DEFAULT_JOURNAL_IOPRIO;
+ ext4_group_t first_not_zeroed;
sbi = kzalloc(sizeof(*sbi), GFP_KERNEL);
if (!sbi)
@@ -2588,8 +3046,6 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
sbi->s_sectors_written_start =
part_stat_read(sb->s_bdev->bd_part, sectors[1]);
- unlock_kernel();
-
/* Cleanup superblock name */
for (cp = sb->s_id; (cp = strchr(cp, '/'));)
*cp = '!';
@@ -2629,40 +3085,41 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
/* Set defaults before we parse the mount options */
def_mount_opts = le32_to_cpu(es->s_default_mount_opts);
+ set_opt(sb, INIT_INODE_TABLE);
if (def_mount_opts & EXT4_DEFM_DEBUG)
- set_opt(sbi->s_mount_opt, DEBUG);
+ set_opt(sb, DEBUG);
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);
+ set_opt(sb, GRPID);
}
if (def_mount_opts & EXT4_DEFM_UID16)
- set_opt(sbi->s_mount_opt, NO_UID32);
+ set_opt(sb, NO_UID32);
#ifdef CONFIG_EXT4_FS_XATTR
if (def_mount_opts & EXT4_DEFM_XATTR_USER)
- set_opt(sbi->s_mount_opt, XATTR_USER);
+ set_opt(sb, XATTR_USER);
#endif
#ifdef CONFIG_EXT4_FS_POSIX_ACL
if (def_mount_opts & EXT4_DEFM_ACL)
- set_opt(sbi->s_mount_opt, POSIX_ACL);
+ set_opt(sb, POSIX_ACL);
#endif
if ((def_mount_opts & EXT4_DEFM_JMODE) == EXT4_DEFM_JMODE_DATA)
- set_opt(sbi->s_mount_opt, JOURNAL_DATA);
+ set_opt(sb, JOURNAL_DATA);
else if ((def_mount_opts & EXT4_DEFM_JMODE) == EXT4_DEFM_JMODE_ORDERED)
- set_opt(sbi->s_mount_opt, ORDERED_DATA);
+ set_opt(sb, ORDERED_DATA);
else if ((def_mount_opts & EXT4_DEFM_JMODE) == EXT4_DEFM_JMODE_WBACK)
- set_opt(sbi->s_mount_opt, WRITEBACK_DATA);
+ set_opt(sb, WRITEBACK_DATA);
if (le16_to_cpu(sbi->s_es->s_errors) == EXT4_ERRORS_PANIC)
- set_opt(sbi->s_mount_opt, ERRORS_PANIC);
+ set_opt(sb, ERRORS_PANIC);
else if (le16_to_cpu(sbi->s_es->s_errors) == EXT4_ERRORS_CONTINUE)
- set_opt(sbi->s_mount_opt, ERRORS_CONT);
+ set_opt(sb, ERRORS_CONT);
else
- set_opt(sbi->s_mount_opt, ERRORS_RO);
+ set_opt(sb, ERRORS_RO);
if (def_mount_opts & EXT4_DEFM_BLOCK_VALIDITY)
- set_opt(sbi->s_mount_opt, BLOCK_VALIDITY);
+ set_opt(sb, BLOCK_VALIDITY);
if (def_mount_opts & EXT4_DEFM_DISCARD)
- set_opt(sbi->s_mount_opt, DISCARD);
+ set_opt(sb, DISCARD);
sbi->s_resuid = le16_to_cpu(es->s_def_resuid);
sbi->s_resgid = le16_to_cpu(es->s_def_resgid);
@@ -2671,7 +3128,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
sbi->s_max_batch_time = EXT4_DEF_MAX_BATCH_TIME;
if ((def_mount_opts & EXT4_DEFM_NOBARRIER) == 0)
- set_opt(sbi->s_mount_opt, BARRIER);
+ set_opt(sb, BARRIER);
/*
* enable delayed allocation by default
@@ -2679,7 +3136,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
*/
if (!IS_EXT3_SB(sb) &&
((def_mount_opts & EXT4_DEFM_NODELALLOC) == 0))
- set_opt(sbi->s_mount_opt, DELALLOC);
+ set_opt(sb, DELALLOC);
if (!parse_options((char *) sbi->s_es->s_mount_opts, sb,
&journal_devnum, &journal_ioprio, NULL, 0)) {
@@ -2831,15 +3288,14 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
* 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))) {
+ err = generic_check_addressable(sb->s_blocksize_bits,
+ ext4_blocks_count(es));
+ if (err) {
ext4_msg(sb, KERN_ERR, "filesystem"
" too large to mount safely on this system");
if (sizeof(sector_t) < 8)
ext4_msg(sb, KERN_WARNING, "CONFIG_LBDAF not enabled");
- ret = -EFBIG;
+ ret = err;
goto failed_mount;
}
@@ -2908,7 +3364,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
goto failed_mount2;
}
}
- if (!ext4_check_descriptors(sb)) {
+ if (!ext4_check_descriptors(sb, &first_not_zeroed)) {
ext4_msg(sb, KERN_ERR, "group descriptors corrupted!");
goto failed_mount2;
}
@@ -2924,6 +3380,24 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
get_random_bytes(&sbi->s_next_generation, sizeof(u32));
spin_lock_init(&sbi->s_next_gen_lock);
+ err = percpu_counter_init(&sbi->s_freeblocks_counter,
+ 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;
@@ -2965,8 +3439,8 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
"suppressed and not mounted read-only");
goto failed_mount_wq;
} else {
- clear_opt(sbi->s_mount_opt, DATA_FLAGS);
- set_opt(sbi->s_mount_opt, WRITEBACK_DATA);
+ clear_opt(sb, DATA_FLAGS);
+ set_opt(sb, WRITEBACK_DATA);
sbi->s_journal = NULL;
needs_recovery = 0;
goto no_journal;
@@ -3004,9 +3478,9 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
*/
if (jbd2_journal_check_available_features
(sbi->s_journal, 0, 0, JBD2_FEATURE_INCOMPAT_REVOKE))
- set_opt(sbi->s_mount_opt, ORDERED_DATA);
+ set_opt(sb, ORDERED_DATA);
else
- set_opt(sbi->s_mount_opt, JOURNAL_DATA);
+ set_opt(sb, JOURNAL_DATA);
break;
case EXT4_MOUNT_ORDERED_DATA:
@@ -3022,22 +3496,19 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
}
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;
- }
+ /*
+ * The journal may have updated the bg summary counts, so we
+ * need to update the global counters.
+ */
+ percpu_counter_set(&sbi->s_freeblocks_counter,
+ ext4_count_free_blocks(sb));
+ percpu_counter_set(&sbi->s_freeinodes_counter,
+ ext4_count_free_inodes(sb));
+ percpu_counter_set(&sbi->s_dirs_counter,
+ ext4_count_dirs(sb));
+ percpu_counter_set(&sbi->s_dirtyblocks_counter, 0);
+no_journal:
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");
@@ -3099,18 +3570,18 @@ no_journal:
(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);
+ clear_opt(sb, DELALLOC);
}
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);
+ clear_opt(sb, 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);
+ clear_opt(sb, DIOREAD_NOLOCK);
}
}
@@ -3129,6 +3600,10 @@ no_journal:
goto failed_mount4;
}
+ err = ext4_register_li_request(sb, first_not_zeroed);
+ if (err)
+ goto failed_mount4;
+
sbi->s_kobj.kset = ext4_kset;
init_completion(&sbi->s_kobj_unregister);
err = kobject_init_and_add(&sbi->s_kobj, &ext4_ktype, NULL,
@@ -3166,7 +3641,6 @@ no_journal:
if (es->s_error_count)
mod_timer(&sbi->s_err_report, jiffies + 300*HZ); /* 5 minutes */
- lock_kernel();
kfree(orig_data);
return 0;
@@ -3184,10 +3658,6 @@ failed_mount_wq:
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))
@@ -3195,6 +3665,10 @@ failed_mount3:
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]);
@@ -3213,7 +3687,6 @@ out_fail:
sb->s_fs_info = NULL;
kfree(sbi->s_blockgroup_lock);
kfree(sbi);
- lock_kernel();
out_free_orig:
kfree(orig_data);
return ret;
@@ -3306,13 +3779,6 @@ static journal_t *ext4_get_dev_journal(struct super_block *sb,
if (bdev == NULL)
return NULL;
- if (bd_claim(bdev, sb)) {
- ext4_msg(sb, KERN_ERR,
- "failed to claim external journal device");
- blkdev_put(bdev, FMODE_READ|FMODE_WRITE);
- return NULL;
- }
-
blocksize = sb->s_blocksize;
hblock = bdev_logical_block_size(bdev);
if (blocksize < hblock) {
@@ -3470,7 +3936,7 @@ static int ext4_load_journal(struct super_block *sb,
EXT4_SB(sb)->s_journal = journal;
ext4_clear_journal_err(sb, es);
- if (journal_devnum &&
+ if (!really_read_only && journal_devnum &&
journal_devnum != le32_to_cpu(es->s_journal_dev)) {
es->s_journal_dev = cpu_to_le32(journal_devnum);
@@ -3524,9 +3990,10 @@ static int ext4_commit_super(struct super_block *sb, int sync)
es->s_kbytes_written =
cpu_to_le64(EXT4_SB(sb)->s_kbytes_written);
ext4_free_blocks_count_set(es, percpu_counter_sum_positive(
- &EXT4_SB(sb)->s_freeblocks_counter));
- es->s_free_inodes_count = cpu_to_le32(percpu_counter_sum_positive(
- &EXT4_SB(sb)->s_freeinodes_counter));
+ &EXT4_SB(sb)->s_freeblocks_counter));
+ es->s_free_inodes_count =
+ cpu_to_le32(percpu_counter_sum_positive(
+ &EXT4_SB(sb)->s_freeinodes_counter));
sb->s_dirt = 0;
BUFFER_TRACE(sbh, "marking dirty");
mark_buffer_dirty(sbh);
@@ -3706,6 +4173,22 @@ static int ext4_unfreeze(struct super_block *sb)
return 0;
}
+/*
+ * Structure to save mount options for ext4_remount's benefit
+ */
+struct ext4_mount_options {
+ unsigned long s_mount_opt;
+ unsigned long s_mount_opt2;
+ uid_t s_resuid;
+ gid_t s_resgid;
+ unsigned long s_commit_interval;
+ u32 s_min_batch_time, s_max_batch_time;
+#ifdef CONFIG_QUOTA
+ int s_jquota_fmt;
+ char *s_qf_names[MAXQUOTAS];
+#endif
+};
+
static int ext4_remount(struct super_block *sb, int *flags, char *data)
{
struct ext4_super_block *es;
@@ -3722,12 +4205,11 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data)
#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_mount_opt2 = sbi->s_mount_opt2;
old_opts.s_resuid = sbi->s_resuid;
old_opts.s_resgid = sbi->s_resgid;
old_opts.s_commit_interval = sbi->s_commit_interval;
@@ -3846,6 +4328,19 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data)
enable_quota = 1;
}
}
+
+ /*
+ * Reinitialize lazy itable initialization thread based on
+ * current settings
+ */
+ if ((sb->s_flags & MS_RDONLY) || !test_opt(sb, INIT_INODE_TABLE))
+ ext4_unregister_li_request(sb);
+ else {
+ ext4_group_t first_not_zeroed;
+ first_not_zeroed = ext4_has_uninit_itable(sb);
+ ext4_register_li_request(sb, first_not_zeroed);
+ }
+
ext4_setup_system_zone(sb);
if (sbi->s_journal == NULL)
ext4_commit_super(sb, 1);
@@ -3858,7 +4353,6 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data)
kfree(old_opts.s_qf_names[i]);
#endif
unlock_super(sb);
- unlock_kernel();
if (enable_quota)
dquot_resume(sb, -1);
@@ -3869,6 +4363,7 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data)
restore_opts:
sb->s_flags = old_sb_flags;
sbi->s_mount_opt = old_opts.s_mount_opt;
+ sbi->s_mount_opt2 = old_opts.s_mount_opt2;
sbi->s_resuid = old_opts.s_resuid;
sbi->s_resgid = old_opts.s_resgid;
sbi->s_commit_interval = old_opts.s_commit_interval;
@@ -3884,7 +4379,6 @@ restore_opts:
}
#endif
unlock_super(sb);
- unlock_kernel();
kfree(orig_data);
return err;
}
@@ -4066,27 +4560,20 @@ static int ext4_quota_on_mount(struct super_block *sb, int type)
* Standard function to be called on quota_on
*/
static int ext4_quota_on(struct super_block *sb, int type, int format_id,
- char *name)
+ struct path *path)
{
int err;
- struct path path;
if (!test_opt(sb, QUOTA))
return -EINVAL;
- err = kern_path(name, LOOKUP_FOLLOW, &path);
- if (err)
- return err;
-
/* Quotafile not on the same filesystem? */
- if (path.mnt->mnt_sb != sb) {
- path_put(&path);
+ if (path->mnt->mnt_sb != sb)
return -EXDEV;
- }
/* Journaling quota? */
if (EXT4_SB(sb)->s_qf_names[type]) {
/* Quotafile not in fs root? */
- if (path.dentry->d_parent != sb->s_root)
+ if (path->dentry->d_parent != sb->s_root)
ext4_msg(sb, KERN_WARNING,
"Quota file not on filesystem root. "
"Journaled quota will not work");
@@ -4097,7 +4584,7 @@ static int ext4_quota_on(struct super_block *sb, int type, int format_id,
* all updates to the file when we bypass pagecache...
*/
if (EXT4_SB(sb)->s_journal &&
- ext4_should_journal_data(path.dentry->d_inode)) {
+ ext4_should_journal_data(path->dentry->d_inode)) {
/*
* We don't need to lock updates but journal_flush() could
* otherwise be livelocked...
@@ -4105,25 +4592,19 @@ static int ext4_quota_on(struct super_block *sb, int type, int format_id,
jbd2_journal_lock_updates(EXT4_SB(sb)->s_journal);
err = jbd2_journal_flush(EXT4_SB(sb)->s_journal);
jbd2_journal_unlock_updates(EXT4_SB(sb)->s_journal);
- if (err) {
- path_put(&path);
+ if (err)
return err;
- }
}
- err = dquot_quota_on_path(sb, type, format_id, &path);
- path_put(&path);
- return err;
+ return dquot_quota_on(sb, type, format_id, path);
}
static int ext4_quota_off(struct super_block *sb, int type)
{
- /* Force all delayed allocation blocks to be allocated */
- if (test_opt(sb, DELALLOC)) {
- down_read(&sb->s_umount);
+ /* Force all delayed allocation blocks to be allocated.
+ * Caller already holds s_umount sem */
+ if (test_opt(sb, DELALLOC))
sync_filesystem(sb);
- up_read(&sb->s_umount);
- }
return dquot_quota_off(sb, type);
}
@@ -4229,17 +4710,17 @@ out:
#endif
-static int ext4_get_sb(struct file_system_type *fs_type, int flags,
- const char *dev_name, void *data, struct vfsmount *mnt)
+static struct dentry *ext4_mount(struct file_system_type *fs_type, int flags,
+ const char *dev_name, void *data)
{
- return get_sb_bdev(fs_type, flags, dev_name, data, ext4_fill_super,mnt);
+ return mount_bdev(fs_type, flags, dev_name, data, ext4_fill_super);
}
#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 = "ext2",
- .get_sb = ext4_get_sb,
+ .mount = ext4_mount,
.kill_sb = kill_block_super,
.fs_flags = FS_REQUIRES_DEV,
};
@@ -4284,28 +4765,79 @@ static inline void unregister_as_ext3(void) { }
static struct file_system_type ext4_fs_type = {
.owner = THIS_MODULE,
.name = "ext4",
- .get_sb = ext4_get_sb,
+ .mount = ext4_mount,
.kill_sb = kill_block_super,
.fs_flags = FS_REQUIRES_DEV,
};
-static int __init init_ext4_fs(void)
+static int __init ext4_init_feat_adverts(void)
{
- int err;
+ struct ext4_features *ef;
+ int ret = -ENOMEM;
+
+ ef = kzalloc(sizeof(struct ext4_features), GFP_KERNEL);
+ if (!ef)
+ goto out;
+
+ ef->f_kobj.kset = ext4_kset;
+ init_completion(&ef->f_kobj_unregister);
+ ret = kobject_init_and_add(&ef->f_kobj, &ext4_feat_ktype, NULL,
+ "features");
+ if (ret) {
+ kfree(ef);
+ goto out;
+ }
+
+ ext4_feat = ef;
+ ret = 0;
+out:
+ return ret;
+}
+
+static void ext4_exit_feat_adverts(void)
+{
+ kobject_put(&ext4_feat->f_kobj);
+ wait_for_completion(&ext4_feat->f_kobj_unregister);
+ kfree(ext4_feat);
+}
+
+/* Shared across all ext4 file systems */
+wait_queue_head_t ext4__ioend_wq[EXT4_WQ_HASH_SZ];
+struct mutex ext4__aio_mutex[EXT4_WQ_HASH_SZ];
+
+static int __init ext4_init_fs(void)
+{
+ int i, err;
ext4_check_flag_values();
- err = init_ext4_system_zone();
+
+ for (i = 0; i < EXT4_WQ_HASH_SZ; i++) {
+ mutex_init(&ext4__aio_mutex[i]);
+ init_waitqueue_head(&ext4__ioend_wq[i]);
+ }
+
+ err = ext4_init_pageio();
if (err)
return err;
+ err = ext4_init_system_zone();
+ if (err)
+ goto out7;
ext4_kset = kset_create_and_add("ext4", NULL, fs_kobj);
if (!ext4_kset)
- goto out4;
+ goto out6;
ext4_proc_root = proc_mkdir("fs/ext4", NULL);
- err = init_ext4_mballoc();
+ if (!ext4_proc_root)
+ goto out5;
+
+ err = ext4_init_feat_adverts();
+ if (err)
+ goto out4;
+
+ err = ext4_init_mballoc();
if (err)
goto out3;
- err = init_ext4_xattr();
+ err = ext4_init_xattr();
if (err)
goto out2;
err = init_inodecache();
@@ -4316,38 +4848,49 @@ static int __init init_ext4_fs(void)
err = register_filesystem(&ext4_fs_type);
if (err)
goto out;
+
+ ext4_li_info = NULL;
+ mutex_init(&ext4_li_mtx);
return 0;
out:
unregister_as_ext2();
unregister_as_ext3();
destroy_inodecache();
out1:
- exit_ext4_xattr();
+ ext4_exit_xattr();
out2:
- exit_ext4_mballoc();
+ ext4_exit_mballoc();
out3:
+ ext4_exit_feat_adverts();
+out4:
remove_proc_entry("fs/ext4", NULL);
+out5:
kset_unregister(ext4_kset);
-out4:
- exit_ext4_system_zone();
+out6:
+ ext4_exit_system_zone();
+out7:
+ ext4_exit_pageio();
return err;
}
-static void __exit exit_ext4_fs(void)
+static void __exit ext4_exit_fs(void)
{
+ ext4_destroy_lazyinit_thread();
unregister_as_ext2();
unregister_as_ext3();
unregister_filesystem(&ext4_fs_type);
destroy_inodecache();
- exit_ext4_xattr();
- exit_ext4_mballoc();
+ ext4_exit_xattr();
+ ext4_exit_mballoc();
+ ext4_exit_feat_adverts();
remove_proc_entry("fs/ext4", NULL);
kset_unregister(ext4_kset);
- exit_ext4_system_zone();
+ ext4_exit_system_zone();
+ ext4_exit_pageio();
}
MODULE_AUTHOR("Remy Card, Stephen Tweedie, Andrew Morton, Andreas Dilger, Theodore Ts'o and others");
MODULE_DESCRIPTION("Fourth Extended Filesystem");
MODULE_LICENSE("GPL");
-module_init(init_ext4_fs)
-module_exit(exit_ext4_fs)
+module_init(ext4_init_fs)
+module_exit(ext4_exit_fs)
Powered by cgit, Gruvboxed by Blaster4385.