#include <linux/freezer.h>
#include "ext4.h"
+#include "ext4_extents.h"
#include "ext4_jbd2.h"
#include "xattr.h"
#include "acl.h"
(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)
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.
brelse(sbi->s_group_desc[i]);
ext4_kvfree(sbi->s_group_desc);
ext4_kvfree(sbi->s_flex_groups);
- percpu_counter_destroy(&sbi->s_freeblocks_counter);
+ 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++)
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))
seq_puts(seq, ",user_xattr");
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);
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_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",
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;
}
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,
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;
}
}
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;
&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);
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",
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);
sbi->s_err_report.function = print_daily_error_info;
sbi->s_err_report.data = (unsigned long) sb;
- err = percpu_counter_init(&sbi->s_freeblocks_counter,
- ext4_count_free_blocks(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");
* 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:
/*
"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);
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;
del_timer(&sbi->s_err_report);
if (sbi->s_flex_groups)
ext4_kvfree(sbi->s_flex_groups);
- percpu_counter_destroy(&sbi->s_freeblocks_counter);
+ 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:
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));
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;
- 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 = max_t(s64, bfree, 0);
+ 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;
return err;
err = ext4_init_system_zone();
if (err)
- goto out7;
+ goto out6;
ext4_kset = kset_create_and_add("ext4", NULL, fs_kobj);
if (!ext4_kset)
- goto out6;
- ext4_proc_root = proc_mkdir("fs/ext4", NULL);
- if (!ext4_proc_root)
goto out5;
+ ext4_proc_root = proc_mkdir("fs/ext4", NULL);
err = ext4_init_feat_adverts();
if (err)
out3:
ext4_exit_feat_adverts();
out4:
- remove_proc_entry("fs/ext4", NULL);
-out5:
+ if (ext4_proc_root)
+ remove_proc_entry("fs/ext4", NULL);
kset_unregister(ext4_kset);
-out6:
+out5:
ext4_exit_system_zone();
-out7:
+out6:
ext4_exit_pageio();
return err;
}
git.openpandora.org / pandora-kernel.git / blobdiff