#include <linux/ctype.h>
#include <linux/log2.h>
#include <linux/crc16.h>
+#include <linux/cleancache.h>
#include <asm/uaccess.h>
#include <linux/kthread.h>
#include <linux/freezer.h>
#include "ext4.h"
+#include "ext4_extents.h"
#include "ext4_jbd2.h"
#include "xattr.h"
#include "acl.h"
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 struct ext4_lazy_init *ext4_li_info;
+static struct mutex ext4_li_mtx;
+static struct ext4_features *ext4_feat;
static int ext4_load_journal(struct super_block *, struct ext4_super_block *,
unsigned long journal_devnum);
static int ext4_freeze(struct super_block *sb);
static struct dentry *ext4_mount(struct file_system_type *fs_type, int flags,
const char *dev_name, void *data);
+static inline int ext2_feature_set_ok(struct super_block *sb);
+static inline int ext3_feature_set_ok(struct super_block *sb);
+static int ext4_feature_set_ok(struct super_block *sb, int readonly);
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_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",
+ .mount = ext4_mount,
+ .kill_sb = kill_block_super,
+ .fs_flags = FS_REQUIRES_DEV,
+};
+#define IS_EXT2_SB(sb) ((sb)->s_bdev->bd_holder == &ext2_fs_type)
+#else
+#define IS_EXT2_SB(sb) (0)
+#endif
+
#if !defined(CONFIG_EXT3_FS) && !defined(CONFIG_EXT3_FS_MODULE) && defined(CONFIG_EXT4_USE_FOR_EXT23)
static struct file_system_type ext3_fs_type = {
#define IS_EXT3_SB(sb) (0)
#endif
+void *ext4_kvmalloc(size_t size, gfp_t flags)
+{
+ void *ret;
+
+ ret = kmalloc(size, flags);
+ if (!ret)
+ ret = __vmalloc(size, flags, PAGE_KERNEL);
+ return ret;
+}
+
+void *ext4_kvzalloc(size_t size, gfp_t flags)
+{
+ void *ret;
+
+ ret = kzalloc(size, flags);
+ if (!ret)
+ ret = __vmalloc(size, flags | __GFP_ZERO, PAGE_KERNEL);
+ return ret;
+}
+
+void ext4_kvfree(void *ptr)
+{
+ if (is_vmalloc_addr(ptr))
+ vfree(ptr);
+ else
+ kfree(ptr);
+
+}
+
ext4_fsblk_t ext4_block_bitmap(struct super_block *sb,
struct ext4_group_desc *bg)
{
(ext4_fsblk_t)le32_to_cpu(bg->bg_inode_table_hi) << 32 : 0);
}
-__u32 ext4_free_blks_count(struct super_block *sb,
- struct ext4_group_desc *bg)
+__u32 ext4_free_group_clusters(struct super_block *sb,
+ struct ext4_group_desc *bg)
{
return le16_to_cpu(bg->bg_free_blocks_count_lo) |
(EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT ?
bg->bg_inode_table_hi = cpu_to_le32(blk >> 32);
}
-void ext4_free_blks_set(struct super_block *sb,
- struct ext4_group_desc *bg, __u32 count)
+void ext4_free_group_clusters_set(struct super_block *sb,
+ struct ext4_group_desc *bg, __u32 count)
{
bg->bg_free_blocks_count_lo = cpu_to_le16((__u16)count);
if (EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT)
* journal_end calls result in the superblock being marked dirty, so
* that sync() will call the filesystem's write_super callback if
* appropriate.
+ *
+ * To avoid j_barrier hold in userspace when a user calls freeze(),
+ * ext4 prevents a new handle from being started by s_frozen, which
+ * is in an upper layer.
*/
handle_t *ext4_journal_start_sb(struct super_block *sb, int nblocks)
{
journal_t *journal;
+ handle_t *handle;
+ trace_ext4_journal_start(sb, nblocks, _RET_IP_);
if (sb->s_flags & MS_RDONLY)
return ERR_PTR(-EROFS);
- vfs_check_frozen(sb, SB_FREEZE_TRANS);
- /* Special case here: if the journal has aborted behind our
- * backs (eg. EIO in the commit thread), then we still need to
- * take the FS itself readonly cleanly. */
journal = EXT4_SB(sb)->s_journal;
- if (journal) {
- if (is_journal_aborted(journal)) {
- ext4_abort(sb, "Detected aborted journal");
- return ERR_PTR(-EROFS);
- }
- return jbd2_journal_start(journal, nblocks);
+ handle = ext4_journal_current_handle();
+
+ /*
+ * If a handle has been started, it should be allowed to
+ * finish, otherwise deadlock could happen between freeze
+ * and others(e.g. truncate) due to the restart of the
+ * journal handle if the filesystem is forzen and active
+ * handles are not stopped.
+ */
+ if (!handle)
+ vfs_check_frozen(sb, SB_FREEZE_TRANS);
+
+ if (!journal)
+ return ext4_get_nojournal();
+ /*
+ * 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.
+ */
+ if (is_journal_aborted(journal)) {
+ ext4_abort(sb, "Detected aborted journal");
+ return ERR_PTR(-EROFS);
}
- return ext4_get_nojournal();
+ return jbd2_journal_start(journal, nblocks);
}
/*
ext4_commit_super(sb, 1);
}
+/*
+ * The del_gendisk() function uninitializes the disk-specific data
+ * structures, including the bdi structure, without telling anyone
+ * else. Once this happens, any attempt to call mark_buffer_dirty()
+ * (for example, by ext4_commit_super), will cause a kernel OOPS.
+ * This is a kludge to prevent these oops until we can put in a proper
+ * hook in del_gendisk() to inform the VFS and file system layers.
+ */
+static int block_device_ejected(struct super_block *sb)
+{
+ struct inode *bd_inode = sb->s_bdev->bd_inode;
+ struct backing_dev_info *bdi = bd_inode->i_mapping->backing_dev_info;
+
+ return bdi->dev == NULL;
+}
+
/* Deal with the reporting of failure conditions on a filesystem such as
* inconsistencies detected or read IO failures.
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;
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 (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);
vaf.fmt = fmt;
vaf.va = &args;
- printk(KERN_CRIT "EXT4-fs error (device %s): %s:%d: group %u",
+ printk(KERN_CRIT "EXT4-fs error (device %s): %s:%d: group %u, ",
sb->s_id, function, line, grp);
if (ino)
printk(KERN_CONT "inode %lu: ", ino);
* filesystem will have already been marked read/only and the
* journal has been aborted. We return 1 as a hint to callers
* who might what to use the return value from
- * ext4_grp_locked_error() to distinguish beween the
+ * ext4_grp_locked_error() to distinguish between the
* ERRORS_CONT and ERRORS_RO case, and perhaps return more
* aggressively from the ext4 function in question, with a
* more appropriate error code.
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;
*/
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)
for (i = 0; i < sbi->s_gdb_count; i++)
brelse(sbi->s_group_desc[i]);
- kfree(sbi->s_group_desc);
- if (is_vmalloc_addr(sbi->s_flex_groups))
- vfree(sbi->s_flex_groups);
- else
- kfree(sbi->s_flex_groups);
- percpu_counter_destroy(&sbi->s_freeblocks_counter);
+ ext4_kvfree(sbi->s_group_desc);
+ ext4_kvfree(sbi->s_flex_groups);
+ percpu_counter_destroy(&sbi->s_freeclusters_counter);
percpu_counter_destroy(&sbi->s_freeinodes_counter);
percpu_counter_destroy(&sbi->s_dirs_counter);
- percpu_counter_destroy(&sbi->s_dirtyblocks_counter);
+ percpu_counter_destroy(&sbi->s_dirtyclusters_counter);
brelse(sbi->s_sbh);
#ifdef CONFIG_QUOTA
for (i = 0; i < MAXQUOTAS; i++)
invalidate_bdev(sbi->journal_bdev);
ext4_blkdev_remove(sbi);
}
+ if (sbi->s_mmp_tsk)
+ kthread_stop(sbi->s_mmp_tsk);
sb->s_fs_info = NULL;
/*
* Now that we are completely done shutting down the
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;
}
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!",
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)
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,
seq_puts(seq, ",nouid32");
if (test_opt(sb, DEBUG) && !(def_mount_opts & EXT4_DEFM_DEBUG))
seq_puts(seq, ",debug");
- if (test_opt(sb, OLDALLOC))
- seq_puts(seq, ",oldalloc");
#ifdef CONFIG_EXT4_FS_XATTR
- if (test_opt(sb, XATTR_USER) &&
- !(def_mount_opts & EXT4_DEFM_XATTR_USER))
+ if (test_opt(sb, XATTR_USER))
seq_puts(seq, ",user_xattr");
- if (!test_opt(sb, XATTR_USER) &&
- (def_mount_opts & EXT4_DEFM_XATTR_USER)) {
+ if (!test_opt(sb, XATTR_USER))
seq_puts(seq, ",nouser_xattr");
- }
#endif
#ifdef CONFIG_EXT4_FS_POSIX_ACL
if (test_opt(sb, POSIX_ACL) && !(def_mount_opts & EXT4_DEFM_ACL))
!(def_mount_opts & EXT4_DEFM_NODELALLOC))
seq_puts(seq, ",nodelalloc");
- if (test_opt(sb, MBLK_IO_SUBMIT))
- seq_puts(seq, ",mblk_io_submit");
+ if (!test_opt(sb, MBLK_IO_SUBMIT))
+ seq_puts(seq, ",nomblk_io_submit");
if (sbi->s_stripe)
seq_printf(seq, ",stripe=%lu", sbi->s_stripe);
/*
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",
+ seq_puts(seq, ",noinit_itable");
+ else if (sbi->s_li_wait_mult != EXT4_DEF_LI_WAIT_MULT)
+ seq_printf(seq, ",init_itable=%u",
(unsigned) sbi->s_li_wait_mult);
ext4_show_quota_options(seq, sb);
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,
const char *data, size_t len, loff_t off);
static const struct dquot_operations ext4_quota_operations = {
-#ifdef CONFIG_QUOTA
.get_reserved_space = ext4_get_reserved_space,
-#endif
.write_dquot = ext4_write_dquot,
.acquire_dquot = ext4_acquire_dquot,
.release_dquot = ext4_release_dquot,
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,
+ Opt_discard, Opt_nodiscard, Opt_init_itable, Opt_noinit_itable,
};
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_init_itable, "init_itable=%u"},
+ {Opt_init_itable, "init_itable"},
+ {Opt_noinit_itable, "noinit_itable"},
{Opt_err, NULL},
};
* Initialize args struct so we know whether arg was
* found; some options take optional arguments.
*/
- args[0].to = args[0].from = 0;
+ args[0].to = args[0].from = NULL;
token = match_token(p, tokens, args);
switch (token) {
case Opt_bsd_df:
set_opt(sb, DEBUG);
break;
case Opt_oldalloc:
- set_opt(sb, OLDALLOC);
+ ext4_msg(sb, KERN_WARNING,
+ "Ignoring deprecated oldalloc option");
break;
case Opt_orlov:
- clear_opt(sb, OLDALLOC);
+ ext4_msg(sb, KERN_WARNING,
+ "Ignoring deprecated orlov option");
break;
#ifdef CONFIG_EXT4_FS_XATTR
case Opt_user_xattr:
data_opt = EXT4_MOUNT_WRITEBACK_DATA;
datacheck:
if (is_remount) {
- if (test_opt(sb, DATA_FLAGS) != data_opt) {
+ if (!sbi->s_journal)
+ ext4_msg(sb, KERN_WARNING, "Remounting file system with no journal so ignoring journalled data option");
+ else if (test_opt(sb, DATA_FLAGS) != data_opt) {
ext4_msg(sb, KERN_ERR,
"Cannot change data mode on remount");
return 0;
break;
case Opt_nodelalloc:
clear_opt(sb, DELALLOC);
+ clear_opt2(sb, EXPLICIT_DELALLOC);
break;
case Opt_mblk_io_submit:
set_opt(sb, MBLK_IO_SUBMIT);
break;
case Opt_delalloc:
set_opt(sb, DELALLOC);
+ set_opt2(sb, EXPLICIT_DELALLOC);
break;
case Opt_block_validity:
set_opt(sb, BLOCK_VALIDITY);
return 0;
if (option < 0 || option > (1 << 30))
return 0;
- if (!is_power_of_2(option)) {
+ if (option && !is_power_of_2(option)) {
ext4_msg(sb, KERN_ERR,
"EXT4-fs: inode_readahead_blks"
" must be a power of 2");
case Opt_dioread_lock:
clear_opt(sb, DIOREAD_NOLOCK);
break;
- case Opt_init_inode_table:
+ case Opt_init_itable:
set_opt(sb, INIT_INODE_TABLE);
if (args[0].from) {
if (match_int(&args[0], &option))
return 0;
sbi->s_li_wait_mult = option;
break;
- case Opt_noinit_inode_table:
+ case Opt_noinit_itable:
clear_opt(sb, INIT_INODE_TABLE);
break;
default:
res = MS_RDONLY;
}
if (read_only)
- return res;
+ goto done;
if (!(sbi->s_mount_state & EXT4_VALID_FS))
ext4_msg(sb, KERN_WARNING, "warning: mounting unchecked fs, "
"running e2fsck is recommended");
ext4_msg(sb, KERN_WARNING,
"warning: mounting fs with errors, "
"running e2fsck is recommended");
- else if ((__s16) le16_to_cpu(es->s_max_mnt_count) >= 0 &&
+ else if ((__s16) le16_to_cpu(es->s_max_mnt_count) > 0 &&
le16_to_cpu(es->s_mnt_count) >=
(unsigned short) (__s16) le16_to_cpu(es->s_max_mnt_count))
ext4_msg(sb, KERN_WARNING,
EXT4_SET_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER);
ext4_commit_super(sb, 1);
+done:
if (test_opt(sb, DEBUG))
printk(KERN_INFO "[EXT4 FS bs=%lu, gc=%u, "
"bpg=%lu, ipg=%lu, mo=%04x, mo2=%04x]\n",
EXT4_INODES_PER_GROUP(sb),
sbi->s_mount_opt, sbi->s_mount_opt2);
+ cleancache_init_fs(sb);
return res;
}
struct ext4_group_desc *gdp = NULL;
ext4_group_t flex_group_count;
ext4_group_t flex_group;
- int groups_per_flex = 0;
+ unsigned int groups_per_flex = 0;
size_t size;
int i;
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) {
+ if (sbi->s_log_groups_per_flex < 1 || sbi->s_log_groups_per_flex > 31) {
sbi->s_log_groups_per_flex = 0;
return 1;
}
+ 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) <<
EXT4_DESC_PER_BLOCK_BITS(sb))) / groups_per_flex;
size = flex_group_count * sizeof(struct flex_groups);
- sbi->s_flex_groups = kzalloc(size, GFP_KERNEL);
+ sbi->s_flex_groups = ext4_kvzalloc(size, GFP_KERNEL);
if (sbi->s_flex_groups == NULL) {
- 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;
- }
+ 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++) {
flex_group = ext4_flex_group(sbi, i);
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_free_group_clusters(sb, gdp),
+ &sbi->s_flex_groups[flex_group].free_clusters);
atomic_add(ext4_used_dirs_count(sb, gdp),
&sbi->s_flex_groups[flex_group].used_dirs);
}
if (NULL != first_not_zeroed)
*first_not_zeroed = grp;
- ext4_free_blocks_count_set(sbi->s_es, ext4_count_free_blocks(sb));
+ ext4_free_blocks_count_set(sbi->s_es,
+ EXT4_C2B(sbi, ext4_count_free_clusters(sb)));
sbi->s_es->s_free_inodes_count =cpu_to_le32(ext4_count_free_inodes(sb));
return 1;
}
return;
}
+ /* Check if feature set would not allow a r/w mount */
+ if (!ext4_feature_set_ok(sb, 0)) {
+ ext4_msg(sb, KERN_INFO, "Skipping orphan cleanup due to "
+ "unknown ROCOMPAT features");
+ return;
+ }
+
if (EXT4_SB(sb)->s_mount_state & EXT4_ERROR_FS) {
if (es->s_last_orphan)
jbd_debug(1, "Errors on filesystem, "
* in the vfs. ext4 inode has 48 bits of i_block in fsblock units,
* so that won't be a limiting factor.
*
+ * However there is other limiting factor. We do store extents in the form
+ * of starting block and length, hence the resulting length of the extent
+ * covering maximum file size must fit into on-disk format containers as
+ * well. Given that length is always by 1 unit bigger than max unit (because
+ * we count 0 as well) we have to lower the s_maxbytes by one fs block.
+ *
* Note, this does *not* consider any metadata overhead for vfs i_blocks.
*/
static loff_t ext4_max_size(int blkbits, int has_huge_files)
upper_limit <<= blkbits;
}
- /* 32-bit extent-start container, ee_block */
- res = 1LL << 32;
+ /*
+ * 32-bit extent-start container, ee_block. We lower the maxbytes
+ * by one fs block, so ee_len can cover the extent of maximum file
+ * size
+ */
+ res = (1LL << 32) - 1;
res <<= blkbits;
- res -= 1;
/* Sanity check against vm- & vfs- imposed limits */
if (res > upper_limit)
unsigned long stride = le16_to_cpu(sbi->s_es->s_raid_stride);
unsigned long stripe_width =
le32_to_cpu(sbi->s_es->s_raid_stripe_width);
+ int ret;
if (sbi->s_stripe && sbi->s_stripe <= sbi->s_blocks_per_group)
- return sbi->s_stripe;
-
- if (stripe_width <= sbi->s_blocks_per_group)
- return stripe_width;
+ ret = sbi->s_stripe;
+ else if (stripe_width <= sbi->s_blocks_per_group)
+ ret = stripe_width;
+ else if (stride <= sbi->s_blocks_per_group)
+ ret = stride;
+ else
+ ret = 0;
- if (stride <= sbi->s_blocks_per_group)
- return stride;
+ /*
+ * If the stripe width is 1, this makes no sense and
+ * we set it to 0 to turn off stripe handling code.
+ */
+ if (ret <= 1)
+ ret = 0;
- return 0;
+ return ret;
}
/* sysfs supprt */
char *buf)
{
return snprintf(buf, PAGE_SIZE, "%llu\n",
- (s64) percpu_counter_sum(&sbi->s_dirtyblocks_counter));
+ (s64) EXT4_C2B(sbi,
+ percpu_counter_sum(&sbi->s_dirtyclusters_counter)));
}
static ssize_t session_write_kbytes_show(struct ext4_attr *a,
if (parse_strtoul(buf, 0x40000000, &t))
return -EINVAL;
- if (!is_power_of_2(t))
+ if (t && !is_power_of_2(t))
return -EINVAL;
sbi->s_inode_readahead_blks = t;
return 0;
}
}
+ if (EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_BIGALLOC) &&
+ !EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_EXTENTS)) {
+ ext4_msg(sb, KERN_ERR,
+ "Can't support bigalloc feature without "
+ "extents feature\n");
+ return 0;
+ }
return 1;
}
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)
{
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;
+ timeout = (jiffies - timeout) *
+ elr->lr_sbi->s_li_wait_mult;
elr->lr_timeout = timeout;
}
elr->lr_next_sched = jiffies + elr->lr_timeout;
/*
* Remove lr_request from the list_request and free the
- * request tructure. Should be called with li_list_mtx held
+ * request structure. Should be called with li_list_mtx held
*/
static void ext4_remove_li_request(struct ext4_li_request *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)
+ mutex_lock(&ext4_li_mtx);
+ if (!ext4_li_info) {
+ mutex_unlock(&ext4_li_mtx);
return;
+ }
mutex_lock(&ext4_li_info->li_list_mtx);
- ext4_remove_li_request(elr);
+ ext4_remove_li_request(EXT4_SB(sb)->s_li_request);
mutex_unlock(&ext4_li_info->li_list_mtx);
+ mutex_unlock(&ext4_li_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.
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);
+ unsigned long next_wakeup, cur;
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;
if (freezing(current))
refrigerator();
- if ((time_after_eq(jiffies, next_wakeup)) ||
+ cur = jiffies;
+ if ((time_after_eq(cur, 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);
+ schedule_timeout_interruptible(next_wakeup - cur);
+
+ if (kthread_should_stop()) {
+ ext4_clear_request_list();
+ goto exit_thread;
+ }
}
exit_thread:
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_li_info = NULL;
mutex_unlock(&ext4_li_mtx);
static int ext4_run_lazyinit_thread(void)
{
- struct task_struct *t;
-
- t = kthread_run(ext4_lazyinit_thread, ext4_li_info, "ext4lazyinit");
- if (IS_ERR(t)) {
- int err = PTR_ERR(t);
+ 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 "
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;
}
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;
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;
+ int ret = 0;
- if (sbi->s_li_request != NULL)
+ if (sbi->s_li_request != NULL) {
+ /*
+ * Reset timeout so it can be computed again, because
+ * s_li_wait_mult might have changed.
+ */
+ sbi->s_li_request->lr_timeout = 0;
return 0;
+ }
if (first_not_zeroed == ngroups ||
(sb->s_flags & MS_RDONLY) ||
- !test_opt(sb, INIT_INODE_TABLE)) {
- sbi->s_li_request = NULL;
+ !test_opt(sb, INIT_INODE_TABLE))
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)
mutex_unlock(&ext4_li_info->li_list_mtx);
sbi->s_li_request = elr;
+ /*
+ * set elr to NULL here since it has been inserted to
+ * the request_list and the removal and free of it is
+ * handled by ext4_clear_request_list from now on.
+ */
+ elr = NULL;
if (!(ext4_li_info->li_state & EXT4_LAZYINIT_RUNNING)) {
ret = ext4_run_lazyinit_thread();
* If thread exited earlier
* there's nothing to be done.
*/
- if (!ext4_li_info)
+ if (!ext4_li_info || !ext4_lazyinit_task)
return;
- ext4_clear_request_list();
-
- while (ext4_li_info->li_task) {
- wake_up(&ext4_li_info->li_wait_daemon);
- wait_event(ext4_li_info->li_wait_task,
- ext4_li_info->li_task == NULL);
- }
+ kthread_stop(ext4_lazyinit_task);
}
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;
char *cp;
const char *descr;
int ret = -ENOMEM;
- int blocksize;
+ int blocksize, clustersize;
unsigned int db_count;
unsigned int i;
- int needs_recovery, has_huge_files;
+ int needs_recovery, has_huge_files, has_bigalloc;
__u64 blocks_count;
int err;
unsigned int journal_ioprio = DEFAULT_JOURNAL_IOPRIO;
}
if (def_mount_opts & EXT4_DEFM_UID16)
set_opt(sb, NO_UID32);
+ /* xattr user namespace & acls are now defaulted on */
#ifdef CONFIG_EXT4_FS_XATTR
- if (def_mount_opts & EXT4_DEFM_XATTR_USER)
- set_opt(sb, XATTR_USER);
+ set_opt(sb, XATTR_USER);
#endif
#ifdef CONFIG_EXT4_FS_POSIX_ACL
- if (def_mount_opts & EXT4_DEFM_ACL)
- set_opt(sb, POSIX_ACL);
+ set_opt(sb, POSIX_ACL);
#endif
+ set_opt(sb, MBLK_IO_SUBMIT);
if ((def_mount_opts & EXT4_DEFM_JMODE) == EXT4_DEFM_JMODE_DATA)
set_opt(sb, JOURNAL_DATA);
else if ((def_mount_opts & EXT4_DEFM_JMODE) == EXT4_DEFM_JMODE_ORDERED)
((def_mount_opts & EXT4_DEFM_NODELALLOC) == 0))
set_opt(sb, DELALLOC);
+ /*
+ * set default s_li_wait_mult for lazyinit, for the case there is
+ * no mount option specified.
+ */
+ sbi->s_li_wait_mult = EXT4_DEF_LI_WAIT_MULT;
+
if (!parse_options((char *) sbi->s_es->s_mount_opts, sb,
&journal_devnum, &journal_ioprio, NULL, 0)) {
ext4_msg(sb, KERN_WARNING,
&journal_ioprio, NULL, 0))
goto failed_mount;
+ if (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA) {
+ printk_once(KERN_WARNING "EXT4-fs: Warning: mounting "
+ "with data=journal disables delayed "
+ "allocation and O_DIRECT support!\n");
+ if (test_opt2(sb, EXPLICIT_DELALLOC)) {
+ ext4_msg(sb, KERN_ERR, "can't mount with "
+ "both data=journal and delalloc");
+ goto failed_mount;
+ }
+ if (test_opt(sb, DIOREAD_NOLOCK)) {
+ ext4_msg(sb, KERN_ERR, "can't mount with "
+ "both data=journal and delalloc");
+ goto failed_mount;
+ }
+ if (test_opt(sb, DELALLOC))
+ clear_opt(sb, DELALLOC);
+ }
+
+ blocksize = BLOCK_SIZE << le32_to_cpu(es->s_log_block_size);
+ if (test_opt(sb, DIOREAD_NOLOCK)) {
+ if (blocksize < PAGE_SIZE) {
+ ext4_msg(sb, KERN_ERR, "can't mount with "
+ "dioread_nolock if block size != PAGE_SIZE");
+ goto failed_mount;
+ }
+ }
+
sb->s_flags = (sb->s_flags & ~MS_POSIXACL) |
(test_opt(sb, POSIX_ACL) ? MS_POSIXACL : 0);
"feature flags set on rev 0 fs, "
"running e2fsck is recommended");
+ if (IS_EXT2_SB(sb)) {
+ if (ext2_feature_set_ok(sb))
+ ext4_msg(sb, KERN_INFO, "mounting ext2 file system "
+ "using the ext4 subsystem");
+ else {
+ ext4_msg(sb, KERN_ERR, "couldn't mount as ext2 due "
+ "to feature incompatibilities");
+ goto failed_mount;
+ }
+ }
+
+ if (IS_EXT3_SB(sb)) {
+ if (ext3_feature_set_ok(sb))
+ ext4_msg(sb, KERN_INFO, "mounting ext3 file system "
+ "using the ext4 subsystem");
+ else {
+ ext4_msg(sb, KERN_ERR, "couldn't mount as ext3 due "
+ "to feature incompatibilities");
+ goto failed_mount;
+ }
+ }
+
/*
* Check feature flags regardless of the revision level, since we
* previously didn't change the revision level when setting the flags,
if (!ext4_feature_set_ok(sb, (sb->s_flags & MS_RDONLY)))
goto failed_mount;
- blocksize = BLOCK_SIZE << le32_to_cpu(es->s_log_block_size);
-
if (blocksize < EXT4_MIN_BLOCK_SIZE ||
blocksize > EXT4_MAX_BLOCK_SIZE) {
ext4_msg(sb, KERN_ERR,
sb->s_dirt = 1;
}
- if (sbi->s_blocks_per_group > blocksize * 8) {
- ext4_msg(sb, KERN_ERR,
- "#blocks per group too big: %lu",
- sbi->s_blocks_per_group);
- goto failed_mount;
+ /* Handle clustersize */
+ clustersize = BLOCK_SIZE << le32_to_cpu(es->s_log_cluster_size);
+ has_bigalloc = EXT4_HAS_RO_COMPAT_FEATURE(sb,
+ EXT4_FEATURE_RO_COMPAT_BIGALLOC);
+ if (has_bigalloc) {
+ if (clustersize < blocksize) {
+ ext4_msg(sb, KERN_ERR,
+ "cluster size (%d) smaller than "
+ "block size (%d)", clustersize, blocksize);
+ goto failed_mount;
+ }
+ sbi->s_cluster_bits = le32_to_cpu(es->s_log_cluster_size) -
+ le32_to_cpu(es->s_log_block_size);
+ sbi->s_clusters_per_group =
+ le32_to_cpu(es->s_clusters_per_group);
+ if (sbi->s_clusters_per_group > blocksize * 8) {
+ ext4_msg(sb, KERN_ERR,
+ "#clusters per group too big: %lu",
+ sbi->s_clusters_per_group);
+ goto failed_mount;
+ }
+ if (sbi->s_blocks_per_group !=
+ (sbi->s_clusters_per_group * (clustersize / blocksize))) {
+ ext4_msg(sb, KERN_ERR, "blocks per group (%lu) and "
+ "clusters per group (%lu) inconsistent",
+ sbi->s_blocks_per_group,
+ sbi->s_clusters_per_group);
+ goto failed_mount;
+ }
+ } else {
+ if (clustersize != blocksize) {
+ ext4_warning(sb, "fragment/cluster size (%d) != "
+ "block size (%d)", clustersize,
+ blocksize);
+ clustersize = blocksize;
+ }
+ if (sbi->s_blocks_per_group > blocksize * 8) {
+ ext4_msg(sb, KERN_ERR,
+ "#blocks per group too big: %lu",
+ sbi->s_blocks_per_group);
+ goto failed_mount;
+ }
+ sbi->s_clusters_per_group = sbi->s_blocks_per_group;
+ sbi->s_cluster_bits = 0;
}
+ sbi->s_cluster_ratio = clustersize / blocksize;
+
if (sbi->s_inodes_per_group > blocksize * 8) {
ext4_msg(sb, KERN_ERR,
"#inodes per group too big: %lu",
(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 *),
- GFP_KERNEL);
+ sbi->s_group_desc = ext4_kvmalloc(db_count *
+ sizeof(struct buffer_head *),
+ GFP_KERNEL);
if (sbi->s_group_desc == NULL) {
ext4_msg(sb, KERN_ERR, "not enough memory");
goto failed_mount;
}
-#ifdef CONFIG_PROC_FS
if (ext4_proc_root)
sbi->s_proc = proc_mkdir(sb->s_id, ext4_proc_root);
-#endif
bgl_lock_init(sbi->s_blockgroup_lock);
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));
+ init_timer(&sbi->s_err_report);
+ sbi->s_err_report.function = print_daily_error_info;
+ sbi->s_err_report.data = (unsigned long) sb;
+
+ err = percpu_counter_init(&sbi->s_freeclusters_counter,
+ ext4_count_free_clusters(sb));
if (!err) {
err = percpu_counter_init(&sbi->s_freeinodes_counter,
ext4_count_free_inodes(sb));
ext4_count_dirs(sb));
}
if (!err) {
- err = percpu_counter_init(&sbi->s_dirtyblocks_counter, 0);
+ err = percpu_counter_init(&sbi->s_dirtyclusters_counter, 0);
}
if (err) {
ext4_msg(sb, KERN_ERR, "insufficient memory");
sb->s_qcop = &ext4_qctl_operations;
sb->dq_op = &ext4_quota_operations;
#endif
+ memcpy(sb->s_uuid, es->s_uuid, sizeof(es->s_uuid));
+
INIT_LIST_HEAD(&sbi->s_orphan); /* unlinked but open files */
mutex_init(&sbi->s_orphan_lock);
- mutex_init(&sbi->s_resize_lock);
+ sbi->s_resize_flags = 0;
sb->s_root = NULL;
EXT4_HAS_INCOMPAT_FEATURE(sb,
EXT4_FEATURE_INCOMPAT_RECOVER));
+ if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_MMP) &&
+ !(sb->s_flags & MS_RDONLY))
+ if (ext4_multi_mount_protect(sb, le64_to_cpu(es->s_mmp_block)))
+ goto failed_mount3;
+
/*
* The first inode we look at is the journal inode. Don't try
* root first: it may be modified in the journal!
goto failed_mount_wq;
} else {
clear_opt(sb, DATA_FLAGS);
- set_opt(sb, WRITEBACK_DATA);
sbi->s_journal = NULL;
needs_recovery = 0;
goto no_journal;
* 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_freeclusters_counter,
+ ext4_count_free_clusters(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);
+ percpu_counter_set(&sbi->s_dirtyclusters_counter, 0);
no_journal:
- EXT4_SB(sb)->dio_unwritten_wq = create_workqueue("ext4-dio-unwritten");
+ /*
+ * The maximum number of concurrent works can be high and
+ * concurrency isn't really necessary. Limit it to 1.
+ */
+ EXT4_SB(sb)->dio_unwritten_wq =
+ alloc_workqueue("ext4-dio-unwritten", WQ_MEM_RECLAIM | WQ_UNBOUND, 1);
if (!EXT4_SB(sb)->dio_unwritten_wq) {
printk(KERN_ERR "EXT4-fs: failed to create DIO workqueue\n");
goto failed_mount_wq;
if (IS_ERR(root)) {
ext4_msg(sb, KERN_ERR, "get root inode failed");
ret = PTR_ERR(root);
+ root = NULL;
goto failed_mount4;
}
if (!S_ISDIR(root->i_mode) || !root->i_blocks || !root->i_size) {
- iput(root);
ext4_msg(sb, KERN_ERR, "corrupt root inode, run e2fsck");
goto failed_mount4;
}
sb->s_root = d_alloc_root(root);
if (!sb->s_root) {
ext4_msg(sb, KERN_ERR, "get root dentry failed");
- iput(root);
ret = -ENOMEM;
goto failed_mount4;
}
"available");
}
- 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(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(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(sb, DIOREAD_NOLOCK);
- }
- }
-
err = ext4_setup_system_zone(sb);
if (err) {
ext4_msg(sb, KERN_ERR, "failed to initialize system "
if (err) {
ext4_msg(sb, KERN_ERR, "failed to initialize mballoc (%d)",
err);
- goto failed_mount4;
+ goto failed_mount5;
}
err = ext4_register_li_request(sb, first_not_zeroed);
if (err)
- goto failed_mount4;
+ goto failed_mount6;
sbi->s_kobj.kset = ext4_kset;
init_completion(&sbi->s_kobj_unregister);
err = kobject_init_and_add(&sbi->s_kobj, &ext4_ktype, NULL,
"%s", sb->s_id);
- if (err) {
- ext4_mb_release(sb);
- ext4_ext_release(sb);
- goto failed_mount4;
- };
+ if (err)
+ goto failed_mount7;
EXT4_SB(sb)->s_mount_state |= EXT4_ORPHAN_FS;
ext4_orphan_cleanup(sb, es);
"Opts: %s%s%s", descr, sbi->s_es->s_mount_opts,
*sbi->s_es->s_mount_opts ? "; " : "", orig_data);
- init_timer(&sbi->s_err_report);
- sbi->s_err_report.function = print_daily_error_info;
- sbi->s_err_report.data = (unsigned long) sb;
if (es->s_error_count)
mod_timer(&sbi->s_err_report, jiffies + 300*HZ); /* 5 minutes */
ext4_msg(sb, KERN_ERR, "VFS: Can't find ext4 filesystem");
goto failed_mount;
+failed_mount7:
+ ext4_unregister_li_request(sb);
+failed_mount6:
+ ext4_ext_release(sb);
+failed_mount5:
+ ext4_mb_release(sb);
+ ext4_release_system_zone(sb);
failed_mount4:
+ iput(root);
+ sb->s_root = NULL;
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;
}
failed_mount3:
- if (sbi->s_flex_groups) {
- if (is_vmalloc_addr(sbi->s_flex_groups))
- vfree(sbi->s_flex_groups);
- else
- kfree(sbi->s_flex_groups);
- }
- percpu_counter_destroy(&sbi->s_freeblocks_counter);
+ del_timer(&sbi->s_err_report);
+ if (sbi->s_flex_groups)
+ ext4_kvfree(sbi->s_flex_groups);
+ percpu_counter_destroy(&sbi->s_freeclusters_counter);
percpu_counter_destroy(&sbi->s_freeinodes_counter);
percpu_counter_destroy(&sbi->s_dirs_counter);
- percpu_counter_destroy(&sbi->s_dirtyblocks_counter);
+ percpu_counter_destroy(&sbi->s_dirtyclusters_counter);
+ if (sbi->s_mmp_tsk)
+ kthread_stop(sbi->s_mmp_tsk);
failed_mount2:
for (i = 0; i < db_count; i++)
brelse(sbi->s_group_desc[i]);
- kfree(sbi->s_group_desc);
+ ext4_kvfree(sbi->s_group_desc);
failed_mount:
if (sbi->s_proc) {
remove_proc_entry(sb->s_id, ext4_proc_root);
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) {
struct buffer_head *sbh = EXT4_SB(sb)->s_sbh;
int error = 0;
- if (!sbh)
+ if (!sbh || block_device_ejected(sb))
return error;
if (buffer_write_io_error(sbh)) {
/*
else
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));
+ ext4_free_blocks_count_set(es,
+ EXT4_C2B(EXT4_SB(sb), percpu_counter_sum_positive(
+ &EXT4_SB(sb)->s_freeclusters_counter)));
es->s_free_inodes_count =
cpu_to_le32(percpu_counter_sum_positive(
&EXT4_SB(sb)->s_freeinodes_counter));
/*
* LVM calls this function before a (read-only) snapshot is created. This
* gives us a chance to flush the journal completely and mark the fs clean.
+ *
+ * Note that only this function cannot bring a filesystem to be in a clean
+ * state independently, because ext4 prevents a new handle from being started
+ * by @sb->s_frozen, which stays in an upper layer. It thus needs help from
+ * the upper layer.
*/
static int ext4_freeze(struct super_block *sb)
{
int enable_quota = 0;
ext4_group_t g;
unsigned int journal_ioprio = DEFAULT_JOURNAL_IOPRIO;
- int err;
+ int err = 0;
#ifdef CONFIG_QUOTA
int i;
#endif
goto restore_opts;
if (!ext4_setup_super(sb, es, 0))
sb->s_flags &= ~MS_RDONLY;
+ if (EXT4_HAS_INCOMPAT_FEATURE(sb,
+ EXT4_FEATURE_INCOMPAT_MMP))
+ if (ext4_multi_mount_protect(sb,
+ le64_to_cpu(es->s_mmp_block))) {
+ err = -EROFS;
+ goto restore_opts;
+ }
enable_quota = 1;
}
}
return err;
}
+/*
+ * Note: calculating the overhead so we can be compatible with
+ * historical BSD practice is quite difficult in the face of
+ * clusters/bigalloc. This is because multiple metadata blocks from
+ * different block group can end up in the same allocation cluster.
+ * Calculating the exact overhead in the face of clustered allocation
+ * requires either O(all block bitmaps) in memory or O(number of block
+ * groups**2) in time. We will still calculate the superblock for
+ * older file systems --- and if we come across with a bigalloc file
+ * system with zero in s_overhead_clusters the estimate will be close to
+ * correct especially for very large cluster sizes --- but for newer
+ * file systems, it's better to calculate this figure once at mkfs
+ * time, and store it in the superblock. If the superblock value is
+ * present (even for non-bigalloc file systems), we will use it.
+ */
static int ext4_statfs(struct dentry *dentry, struct kstatfs *buf)
{
struct super_block *sb = dentry->d_sb;
struct ext4_sb_info *sbi = EXT4_SB(sb);
struct ext4_super_block *es = sbi->s_es;
+ struct ext4_group_desc *gdp;
u64 fsid;
+ s64 bfree;
if (test_opt(sb, MINIX_DF)) {
sbi->s_overhead_last = 0;
+ } else if (es->s_overhead_clusters) {
+ sbi->s_overhead_last = le32_to_cpu(es->s_overhead_clusters);
} else if (sbi->s_blocks_last != ext4_blocks_count(es)) {
ext4_group_t i, ngroups = ext4_get_groups_count(sb);
ext4_fsblk_t overhead = 0;
* All of the blocks before first_data_block are
* overhead
*/
- overhead = le32_to_cpu(es->s_first_data_block);
+ overhead = EXT4_B2C(sbi, le32_to_cpu(es->s_first_data_block));
/*
- * Add the overhead attributed to the superblock and
- * block group descriptors. If the sparse superblocks
- * feature is turned on, then not all groups have this.
+ * Add the overhead found in each block group
*/
for (i = 0; i < ngroups; i++) {
- overhead += ext4_bg_has_super(sb, i) +
- ext4_bg_num_gdb(sb, i);
+ gdp = ext4_get_group_desc(sb, i, NULL);
+ overhead += ext4_num_overhead_clusters(sb, i, gdp);
cond_resched();
}
-
- /*
- * Every block group has an inode bitmap, a block
- * bitmap, and an inode table.
- */
- overhead += ngroups * (2 + sbi->s_itb_per_group);
sbi->s_overhead_last = overhead;
smp_wmb();
sbi->s_blocks_last = ext4_blocks_count(es);
buf->f_type = EXT4_SUPER_MAGIC;
buf->f_bsize = sb->s_blocksize;
- 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);
+ buf->f_blocks = (ext4_blocks_count(es) -
+ EXT4_C2B(sbi, sbi->s_overhead_last));
+ bfree = percpu_counter_sum_positive(&sbi->s_freeclusters_counter) -
+ percpu_counter_sum_positive(&sbi->s_dirtyclusters_counter);
+ /* prevent underflow in case that few free space is available */
+ buf->f_bfree = EXT4_C2B(sbi, max_t(s64, bfree, 0));
buf->f_bavail = buf->f_bfree - ext4_r_blocks_count(es);
if (buf->f_bfree < ext4_r_blocks_count(es))
buf->f_bavail = 0;
* 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");
* 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...
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)
{
+ struct inode *inode = sb_dqopt(sb)->files[type];
+ handle_t *handle;
+
/* Force all delayed allocation blocks to be allocated.
* Caller already holds s_umount sem */
if (test_opt(sb, DELALLOC))
sync_filesystem(sb);
+ if (!inode)
+ goto out;
+
+ /* Update modification times of quota files when userspace can
+ * start looking at them */
+ handle = ext4_journal_start(inode, 1);
+ if (IS_ERR(handle))
+ goto out;
+ inode->i_mtime = inode->i_ctime = CURRENT_TIME;
+ ext4_mark_inode_dirty(handle, inode);
+ ext4_journal_stop(handle);
+
+out:
return dquot_quota_off(sb, type);
}
/* Read data from quotafile - avoid pagecache and such because we cannot afford
* acquiring the locks... As quota files are never truncated and quota code
- * itself serializes the operations (and noone else should touch the files)
+ * itself serializes the operations (and no one else should touch the files)
* we don't have to be afraid of races */
static ssize_t ext4_quota_read(struct super_block *sb, int type, char *data,
size_t len, loff_t off)
if (inode->i_size < off + len) {
i_size_write(inode, off + len);
EXT4_I(inode)->i_disksize = inode->i_size;
+ ext4_mark_inode_dirty(handle, inode);
}
- inode->i_mtime = inode->i_ctime = CURRENT_TIME;
- ext4_mark_inode_dirty(handle, inode);
mutex_unlock(&inode->i_mutex);
return len;
}
}
#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",
- .mount = ext4_mount,
- .kill_sb = kill_block_super,
- .fs_flags = FS_REQUIRES_DEV,
-};
-
static inline void register_as_ext2(void)
{
int err = register_filesystem(&ext2_fs_type);
{
unregister_filesystem(&ext2_fs_type);
}
+
+static inline int ext2_feature_set_ok(struct super_block *sb)
+{
+ if (EXT4_HAS_INCOMPAT_FEATURE(sb, ~EXT2_FEATURE_INCOMPAT_SUPP))
+ return 0;
+ if (sb->s_flags & MS_RDONLY)
+ return 1;
+ if (EXT4_HAS_RO_COMPAT_FEATURE(sb, ~EXT2_FEATURE_RO_COMPAT_SUPP))
+ return 0;
+ return 1;
+}
MODULE_ALIAS("ext2");
#else
static inline void register_as_ext2(void) { }
static inline void unregister_as_ext2(void) { }
+static inline int ext2_feature_set_ok(struct super_block *sb) { return 0; }
#endif
#if !defined(CONFIG_EXT3_FS) && !defined(CONFIG_EXT3_FS_MODULE) && defined(CONFIG_EXT4_USE_FOR_EXT23)
{
unregister_filesystem(&ext3_fs_type);
}
+
+static inline int ext3_feature_set_ok(struct super_block *sb)
+{
+ if (EXT4_HAS_INCOMPAT_FEATURE(sb, ~EXT3_FEATURE_INCOMPAT_SUPP))
+ return 0;
+ if (!EXT4_HAS_COMPAT_FEATURE(sb, EXT4_FEATURE_COMPAT_HAS_JOURNAL))
+ return 0;
+ if (sb->s_flags & MS_RDONLY)
+ return 1;
+ if (EXT4_HAS_RO_COMPAT_FEATURE(sb, ~EXT3_FEATURE_RO_COMPAT_SUPP))
+ return 0;
+ return 1;
+}
MODULE_ALIAS("ext3");
#else
static inline void register_as_ext3(void) { }
static inline void unregister_as_ext3(void) { }
+static inline int ext3_feature_set_ok(struct super_block *sb) { return 0; }
#endif
static struct file_system_type ext4_fs_type = {
.fs_flags = FS_REQUIRES_DEV,
};
-int __init ext4_init_feat_adverts(void)
+static int __init ext4_init_feat_adverts(void)
{
struct ext4_features *ef;
int ret = -ENOMEM;
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 err;
+ int i, err;
ext4_check_flag_values();
+
+ 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 out5;
+ goto out6;
ext4_kset = kset_create_and_add("ext4", NULL, fs_kobj);
if (!ext4_kset)
- goto out4;
+ goto out5;
ext4_proc_root = proc_mkdir("fs/ext4", NULL);
err = ext4_init_feat_adverts();
+ if (err)
+ goto out4;
err = ext4_init_mballoc();
if (err)
err = init_inodecache();
if (err)
goto out1;
- register_as_ext2();
register_as_ext3();
+ register_as_ext2();
err = register_filesystem(&ext4_fs_type);
if (err)
goto out;
out2:
ext4_exit_mballoc();
out3:
- kfree(ext4_feat);
- remove_proc_entry("fs/ext4", NULL);
- kset_unregister(ext4_kset);
+ ext4_exit_feat_adverts();
out4:
- ext4_exit_system_zone();
+ if (ext4_proc_root)
+ remove_proc_entry("fs/ext4", NULL);
+ kset_unregister(ext4_kset);
out5:
+ ext4_exit_system_zone();
+out6:
ext4_exit_pageio();
return err;
}
destroy_inodecache();
ext4_exit_xattr();
ext4_exit_mballoc();
+ ext4_exit_feat_adverts();
remove_proc_entry("fs/ext4", NULL);
kset_unregister(ext4_kset);
ext4_exit_system_zone();