#include <linux/parser.h>
#include <linux/smp_lock.h>
#include <linux/buffer_head.h>
+#include <linux/exportfs.h>
#include <linux/vfs.h>
#include <linux/random.h>
#include <linux/mount.h>
#include <linux/namei.h>
#include <linux/quotaops.h>
#include <linux/seq_file.h>
+#include <linux/log2.h>
#include <asm/uaccess.h>
dump_orphan_list(sb, sbi);
J_ASSERT(list_empty(&sbi->s_orphan));
- invalidate_bdev(sb->s_bdev, 0);
+ invalidate_bdev(sb->s_bdev);
if (sbi->journal_bdev && sbi->journal_bdev != sb->s_bdev) {
/*
* Invalidate the journal device's buffers. We don't want them
* hotswapped, and it breaks the `ro-after' testing code.
*/
sync_blockdev(sbi->journal_bdev);
- invalidate_bdev(sbi->journal_bdev, 0);
+ invalidate_bdev(sbi->journal_bdev);
ext4_blkdev_remove(sbi);
}
sb->s_fs_info = NULL;
return;
}
-static kmem_cache_t *ext4_inode_cachep;
+static struct kmem_cache *ext4_inode_cachep;
/*
* Called inside transaction, so use GFP_NOFS
{
struct ext4_inode_info *ei;
- ei = kmem_cache_alloc(ext4_inode_cachep, SLAB_NOFS);
+ ei = kmem_cache_alloc(ext4_inode_cachep, GFP_NOFS);
if (!ei)
return NULL;
#ifdef CONFIG_EXT4DEV_FS_POSIX_ACL
static void ext4_destroy_inode(struct inode *inode)
{
+ if (!list_empty(&(EXT4_I(inode)->i_orphan))) {
+ printk("EXT4 Inode %p: orphan list check failed!\n",
+ EXT4_I(inode));
+ print_hex_dump(KERN_INFO, "", DUMP_PREFIX_ADDRESS, 16, 4,
+ EXT4_I(inode), sizeof(struct ext4_inode_info),
+ true);
+ dump_stack();
+ }
kmem_cache_free(ext4_inode_cachep, EXT4_I(inode));
}
-static void init_once(void * foo, kmem_cache_t * cachep, unsigned long flags)
+static void init_once(struct kmem_cache *cachep, void *foo)
{
struct ext4_inode_info *ei = (struct ext4_inode_info *) foo;
- if ((flags & (SLAB_CTOR_VERIFY|SLAB_CTOR_CONSTRUCTOR)) ==
- SLAB_CTOR_CONSTRUCTOR) {
- INIT_LIST_HEAD(&ei->i_orphan);
+ INIT_LIST_HEAD(&ei->i_orphan);
#ifdef CONFIG_EXT4DEV_FS_XATTR
- init_rwsem(&ei->xattr_sem);
+ init_rwsem(&ei->xattr_sem);
#endif
- mutex_init(&ei->truncate_mutex);
- inode_init_once(&ei->vfs_inode);
- }
+ mutex_init(&ei->truncate_mutex);
+ inode_init_once(&ei->vfs_inode);
}
static int init_inodecache(void)
sizeof(struct ext4_inode_info),
0, (SLAB_RECLAIM_ACCOUNT|
SLAB_MEM_SPREAD),
- init_once, NULL);
+ init_once);
if (ext4_inode_cachep == NULL)
return -ENOMEM;
return 0;
};
#endif
-static struct super_operations ext4_sops = {
+static const struct super_operations ext4_sops = {
.alloc_inode = ext4_alloc_inode,
.destroy_inode = ext4_destroy_inode,
.read_inode = ext4_read_inode,
Opt_usrjquota, Opt_grpjquota, Opt_offusrjquota, Opt_offgrpjquota,
Opt_jqfmt_vfsold, Opt_jqfmt_vfsv0, Opt_quota, Opt_noquota,
Opt_ignore, Opt_barrier, Opt_err, Opt_resize, Opt_usrquota,
- Opt_grpquota, Opt_extents,
+ Opt_grpquota, Opt_extents, Opt_noextents,
};
static match_table_t tokens = {
{Opt_usrquota, "usrquota"},
{Opt_barrier, "barrier=%u"},
{Opt_extents, "extents"},
+ {Opt_noextents, "noextents"},
{Opt_err, NULL},
{Opt_resize, "resize"},
};
case Opt_extents:
set_opt (sbi->s_mount_opt, EXTENTS);
break;
+ case Opt_noextents:
+ clear_opt (sbi->s_mount_opt, EXTENTS);
+ break;
default:
printk (KERN_ERR
"EXT4-fs: Unrecognized mount option \"%s\" "
}
inode_table = ext4_inode_table(sb, gdp);
if (inode_table < first_block ||
- inode_table + sbi->s_itb_per_group > last_block)
+ inode_table + sbi->s_itb_per_group - 1 > last_block)
{
ext4_error (sb, "ext4_check_descriptors",
"Inode table for group %d"
return;
}
+ if (bdev_read_only(sb->s_bdev)) {
+ printk(KERN_ERR "EXT4-fs: write access "
+ "unavailable, skipping orphan cleanup.\n");
+ return;
+ }
+
if (EXT4_SB(sb)->s_mount_state & EXT4_ERROR_FS) {
if (es->s_last_orphan)
jbd_debug(1, "Errors on filesystem, "
int needs_recovery;
__le32 features;
__u64 blocks_count;
+ int err;
sbi = kzalloc(sizeof(*sbi), GFP_KERNEL);
if (!sbi)
set_opt(sbi->s_mount_opt, GRPID);
if (def_mount_opts & EXT4_DEFM_UID16)
set_opt(sbi->s_mount_opt, NO_UID32);
+#ifdef CONFIG_EXT4DEV_FS_XATTR
if (def_mount_opts & EXT4_DEFM_XATTR_USER)
set_opt(sbi->s_mount_opt, XATTR_USER);
+#endif
+#ifdef CONFIG_EXT4DEV_FS_POSIX_ACL
if (def_mount_opts & EXT4_DEFM_ACL)
set_opt(sbi->s_mount_opt, POSIX_ACL);
+#endif
if ((def_mount_opts & EXT4_DEFM_JMODE) == EXT4_DEFM_JMODE_DATA)
sbi->s_mount_opt |= EXT4_MOUNT_JOURNAL_DATA;
else if ((def_mount_opts & EXT4_DEFM_JMODE) == EXT4_DEFM_JMODE_ORDERED)
set_opt(sbi->s_mount_opt, RESERVATION);
+ /*
+ * turn on extents feature by default in ext4 filesystem
+ * User -o noextents to turn it off
+ */
+ set_opt(sbi->s_mount_opt, EXTENTS);
+
if (!parse_options ((char *) data, sb, &journal_inum, &journal_devnum,
NULL, 0))
goto failed_mount;
sbi->s_inode_size = le16_to_cpu(es->s_inode_size);
sbi->s_first_ino = le32_to_cpu(es->s_first_ino);
if ((sbi->s_inode_size < EXT4_GOOD_OLD_INODE_SIZE) ||
- (sbi->s_inode_size & (sbi->s_inode_size - 1)) ||
+ (!is_power_of_2(sbi->s_inode_size)) ||
(sbi->s_inode_size > blocksize)) {
printk (KERN_ERR
"EXT4-fs: unsupported inode size: %d\n",
sbi->s_inode_size);
goto failed_mount;
}
+ if (sbi->s_inode_size > EXT4_GOOD_OLD_INODE_SIZE)
+ sb->s_time_gran = 1 << (EXT4_EPOCH_BITS - 2);
}
sbi->s_frag_size = EXT4_MIN_FRAG_SIZE <<
le32_to_cpu(es->s_log_frag_size);
get_random_bytes(&sbi->s_next_generation, sizeof(u32));
spin_lock_init(&sbi->s_next_gen_lock);
- percpu_counter_init(&sbi->s_freeblocks_counter,
- ext4_count_free_blocks(sb));
- percpu_counter_init(&sbi->s_freeinodes_counter,
- ext4_count_free_inodes(sb));
- percpu_counter_init(&sbi->s_dirs_counter,
- ext4_count_dirs(sb));
+ 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) {
+ printk(KERN_ERR "EXT4-fs: insufficient memory\n");
+ goto failed_mount3;
+ }
/* per fileystem reservation list head & lock */
spin_lock_init(&sbi->s_rsv_window_lock);
goto failed_mount3;
}
+ if (ext4_blocks_count(es) > 0xffffffffULL &&
+ !jbd2_journal_set_features(EXT4_SB(sb)->s_journal, 0, 0,
+ JBD2_FEATURE_INCOMPAT_64BIT)) {
+ printk(KERN_ERR "ext4: Failed to set 64-bit journal feature\n");
+ goto failed_mount4;
+ }
+
/* We have now updated the journal if required, so we can
* validate the data journaling mode. */
switch (test_opt(sb, DATA_FLAGS)) {
}
ext4_setup_super (sb, es, sb->s_flags & MS_RDONLY);
+
+ /* determine the minimum size of new large inodes, if present */
+ if (sbi->s_inode_size > EXT4_GOOD_OLD_INODE_SIZE) {
+ sbi->s_want_extra_isize = sizeof(struct ext4_inode) -
+ EXT4_GOOD_OLD_INODE_SIZE;
+ if (EXT4_HAS_RO_COMPAT_FEATURE(sb,
+ EXT4_FEATURE_RO_COMPAT_EXTRA_ISIZE)) {
+ if (sbi->s_want_extra_isize <
+ le16_to_cpu(es->s_want_extra_isize))
+ sbi->s_want_extra_isize =
+ le16_to_cpu(es->s_want_extra_isize);
+ if (sbi->s_want_extra_isize <
+ le16_to_cpu(es->s_min_extra_isize))
+ sbi->s_want_extra_isize =
+ le16_to_cpu(es->s_min_extra_isize);
+ }
+ }
+ /* Check if enough inode space is available */
+ if (EXT4_GOOD_OLD_INODE_SIZE + sbi->s_want_extra_isize >
+ sbi->s_inode_size) {
+ sbi->s_want_extra_isize = sizeof(struct ext4_inode) -
+ EXT4_GOOD_OLD_INODE_SIZE;
+ printk(KERN_INFO "EXT4-fs: required extra inode space not"
+ "available.\n");
+ }
+
/*
* akpm: core read_super() calls in here with the superblock locked.
* That deadlocks, because orphan cleanup needs to lock the superblock
if (bd_claim(bdev, sb)) {
printk(KERN_ERR
- "EXT4: failed to claim external journal device.\n");
+ "EXT4: failed to claim external journal device.\n");
blkdev_put(bdev);
return NULL;
}
unsigned int journal_inum)
{
journal_t *journal;
+ int err;
if (sb->s_flags & MS_RDONLY) {
printk(KERN_ERR "EXT4-fs: readonly filesystem when trying to "
return -EROFS;
}
- if (!(journal = ext4_get_journal(sb, journal_inum)))
+ journal = ext4_get_journal(sb, journal_inum);
+ if (!journal)
return -EINVAL;
printk(KERN_INFO "EXT4-fs: creating new journal on inode %u\n",
journal_inum);
- if (jbd2_journal_create(journal)) {
+ err = jbd2_journal_create(journal);
+ if (err) {
printk(KERN_ERR "EXT4-fs: error creating journal.\n");
jbd2_journal_destroy(journal);
return -EIO;
jbd2_journal_lock_updates(journal);
jbd2_journal_flush(journal);
+ lock_super(sb);
if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER) &&
sb->s_flags & MS_RDONLY) {
EXT4_CLEAR_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER);
sb->s_dirt = 0;
ext4_commit_super(sb, es, 1);
}
+ unlock_super(sb);
jbd2_journal_unlock_updates(journal);
}
(sbi->s_mount_state & EXT4_VALID_FS))
es->s_state = cpu_to_le16(sbi->s_mount_state);
+ /*
+ * We have to unlock super so that we can wait for
+ * transactions.
+ */
+ unlock_super(sb);
ext4_mark_recovery_complete(sb, es);
+ lock_super(sb);
} else {
__le32 ret;
if ((ret = EXT4_HAS_RO_COMPAT_FEATURE(sb,
err = -EROFS;
goto restore_opts;
}
+
+ /*
+ * If we have an unprocessed orphan list hanging
+ * around from a previously readonly bdev mount,
+ * require a full umount/remount for now.
+ */
+ if (es->s_last_orphan) {
+ printk(KERN_WARNING "EXT4-fs: %s: couldn't "
+ "remount RDWR because of unprocessed "
+ "orphan inode list. Please "
+ "umount/remount instead.\n",
+ sb->s_id);
+ err = -EINVAL;
+ goto restore_opts;
+ }
+
/*
* Mounting a RDONLY partition read-write, so reread
* and store the current valid flag. (It may have
struct super_block *sb = dentry->d_sb;
struct ext4_sb_info *sbi = EXT4_SB(sb);
struct ext4_super_block *es = sbi->s_es;
- ext4_fsblk_t overhead;
- int i;
+ u64 fsid;
- if (test_opt (sb, MINIX_DF))
- overhead = 0;
- else {
- unsigned long ngroups;
- ngroups = EXT4_SB(sb)->s_groups_count;
+ if (test_opt(sb, MINIX_DF)) {
+ sbi->s_overhead_last = 0;
+ } else if (sbi->s_blocks_last != le32_to_cpu(es->s_blocks_count)) {
+ unsigned long ngroups = sbi->s_groups_count, i;
+ ext4_fsblk_t overhead = 0;
smp_rmb();
/*
- * Compute the overhead (FS structures)
+ * Compute the overhead (FS structures). This is constant
+ * for a given filesystem unless the number of block groups
+ * changes so we cache the previous value until it does.
*/
/*
* Every block group has an inode bitmap, a block
* bitmap, and an inode table.
*/
- overhead += (ngroups * (2 + EXT4_SB(sb)->s_itb_per_group));
+ overhead += ngroups * (2 + sbi->s_itb_per_group);
+ sbi->s_overhead_last = overhead;
+ smp_wmb();
+ sbi->s_blocks_last = le32_to_cpu(es->s_blocks_count);
}
buf->f_type = EXT4_SUPER_MAGIC;
buf->f_bsize = sb->s_blocksize;
- buf->f_blocks = ext4_blocks_count(es) - overhead;
- buf->f_bfree = percpu_counter_sum(&sbi->s_freeblocks_counter);
+ buf->f_blocks = ext4_blocks_count(es) - sbi->s_overhead_last;
+ buf->f_bfree = percpu_counter_sum_positive(&sbi->s_freeblocks_counter);
+ es->s_free_blocks_count = cpu_to_le32(buf->f_bfree);
buf->f_bavail = buf->f_bfree - ext4_r_blocks_count(es);
if (buf->f_bfree < ext4_r_blocks_count(es))
buf->f_bavail = 0;
buf->f_files = le32_to_cpu(es->s_inodes_count);
- buf->f_ffree = percpu_counter_sum(&sbi->s_freeinodes_counter);
+ buf->f_ffree = percpu_counter_sum_positive(&sbi->s_freeinodes_counter);
+ es->s_free_inodes_count = cpu_to_le32(buf->f_ffree);
buf->f_namelen = EXT4_NAME_LEN;
+ fsid = le64_to_cpup((void *)es->s_uuid) ^
+ le64_to_cpup((void *)es->s_uuid + sizeof(u64));
+ buf->f_fsid.val[0] = fsid & 0xFFFFFFFFUL;
+ buf->f_fsid.val[1] = (fsid >> 32) & 0xFFFFFFFFUL;
return 0;
}
handle = ext4_journal_start(dquot_to_inode(dquot),
EXT4_QUOTA_DEL_BLOCKS(dquot->dq_sb));
- if (IS_ERR(handle))
+ if (IS_ERR(handle)) {
+ /* Release dquot anyway to avoid endless cycle in dqput() */
+ dquot_release(dquot);
return PTR_ERR(handle);
+ }
ret = dquot_release(dquot);
err = ext4_journal_stop(handle);
if (!ret)
struct buffer_head *bh;
handle_t *handle = journal_current_handle();
+ if (!handle) {
+ printk(KERN_WARNING "EXT4-fs: Quota write (off=%Lu, len=%Lu)"
+ " cancelled because transaction is not started.\n",
+ (unsigned long long)off, (unsigned long long)len);
+ return -EIO;
+ }
mutex_lock_nested(&inode->i_mutex, I_MUTEX_QUOTA);
while (towrite > 0) {
tocopy = sb->s_blocksize - offset < towrite ?