redonkable/remarkable-linux
redonkable/remarkable-linux
1
0
Fork 0
Code Releases Activity

Merge branch 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4

Browse source 
* 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4: (50 commits)
  jbd2: sparse pointer use of zero as null
  jbd2: Use round-jiffies() function for the "5 second" ext4/jbd2 wakeup
  jbd2: Mark jbd2 slabs as SLAB_TEMPORARY
  jbd2: add lockdep support
  ext4: Use the ext4_ext_actual_len() helper function
  ext4: fix uniniatilized extent splitting error
  ext4: Check for return value from sb_set_blocksize
  ext4: Add stripe= option to /proc/mounts
  ext4: Enable the multiblock allocator by default
  ext4: Add multi block allocator for ext4
  ext4: Add new functions for searching extent tree
  ext4: Add ext4_find_next_bit()
  ext4: fix up EXT4FS_DEBUG builds
  ext4: Fix ext4_show_options to show the correct mount options.
  ext4: Add EXT4_IOC_MIGRATE ioctl
  ext4: Add inode version support in ext4
  vfs: Add 64 bit i_version support
  ext4: Add the journal checksum feature
  jbd2: jbd2 stats through procfs
  ext4: Take read lock during overwrite case.
  ...
This commit is contained in:
Linus Torvalds 2008-01-29 22:43:38 +11:00
parent 6b11d8179d 4019191be7
commit 8cd226ca3f
46 changed files with 7682 additions and 807 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

20
Documentation/filesystems/ext4.txt
View file

@ -86,9 +86,21 @@ Alex is working on a new set of patches right now.
When mounting an ext4 filesystem, the following option are accepted:
(*) == default
extents ext4 will use extents to address file data. The
extents (*) ext4 will use extents to address file data. The
file system will no longer be mountable by ext3.
noextents ext4 will not use extents for newly created files
journal_checksum Enable checksumming of the journal transactions.
This will allow the recovery code in e2fsck and the
kernel to detect corruption in the kernel. It is a
compatible change and will be ignored by older kernels.
journal_async_commit Commit block can be written to disk without waiting
for descriptor blocks. If enabled older kernels cannot
mount the device. This will enable 'journal_checksum'
internally.
journal=update Update the ext4 file system's journal to the current
format.
@ -196,6 +208,12 @@ nobh (a) cache disk block mapping information
"nobh" option tries to avoid associating buffer
heads (supported only for "writeback" mode).
mballoc (*) Use the multiple block allocator for block allocation
nomballoc disabled multiple block allocator for block allocation.
stripe=n Number of filesystem blocks that mballoc will try
to use for allocation size and alignment. For RAID5/6
systems this should be the number of data
disks * RAID chunk size in file system blocks.
Data Mode
---------

39
Documentation/filesystems/proc.txt
View file

@ -857,6 +857,45 @@ CPUs.
The "procs_blocked" line gives the number of processes currently blocked,
waiting for I/O to complete.
1.9 Ext4 file system parameters
------------------------------
Ext4 file system have one directory per partition under /proc/fs/ext4/
# ls /proc/fs/ext4/hdc/
group_prealloc max_to_scan mb_groups mb_history min_to_scan order2_req
stats stream_req
mb_groups:
This file gives the details of mutiblock allocator buddy cache of free blocks
mb_history:
Multiblock allocation history.
stats:
This file indicate whether the multiblock allocator should start collecting
statistics. The statistics are shown during unmount
group_prealloc:
The multiblock allocator normalize the block allocation request to
group_prealloc filesystem blocks if we don't have strip value set.
The stripe value can be specified at mount time or during mke2fs.
max_to_scan:
How long multiblock allocator can look for a best extent (in found extents)
min_to_scan:
How long multiblock allocator must look for a best extent
order2_req:
Multiblock allocator use 2^N search using buddies only for requests greater
than or equal to order2_req. The request size is specfied in file system
blocks. A value of 2 indicate only if the requests are greater than or equal
to 4 blocks.
stream_req:
Files smaller than stream_req are served by the stream allocator, whose
purpose is to pack requests as close each to other as possible to
produce smooth I/O traffic. Avalue of 16 indicate that file smaller than 16
filesystem block size will use group based preallocation.
------------------------------------------------------------------------------
Summary

1
fs/Kconfig
View file

@ -236,6 +236,7 @@ config JBD_DEBUG
config JBD2
tristate
select CRC32
help
This is a generic journaling layer for block devices that support
both 32-bit and 64-bit block numbers. It is currently used by

9
fs/afs/dir.c
View file

@ -546,11 +546,11 @@ static struct dentry *afs_lookup(struct inode *dir, struct dentry *dentry,
dentry->d_op = &afs_fs_dentry_operations;
d_add(dentry, inode);
_leave(" = 0 { vn=%u u=%u } -> { ino=%lu v=%lu }",
_leave(" = 0 { vn=%u u=%u } -> { ino=%lu v=%llu }",
fid.vnode,
fid.unique,
dentry->d_inode->i_ino,
dentry->d_inode->i_version);
(unsigned long long)dentry->d_inode->i_version);
return NULL;
}
@ -630,9 +630,10 @@ static int afs_d_revalidate(struct dentry *dentry, struct nameidata *nd)
* been deleted and replaced, and the original vnode ID has
* been reused */
if (fid.unique != vnode->fid.unique) {
_debug("%s: file deleted (uq %u -> %u I:%lu)",
_debug("%s: file deleted (uq %u -> %u I:%llu)",
dentry->d_name.name, fid.unique,
vnode->fid.unique, dentry->d_inode->i_version);
vnode->fid.unique,
(unsigned long long)dentry->d_inode->i_version);
spin_lock(&vnode->lock);
set_bit(AFS_VNODE_DELETED, &vnode->flags);
spin_unlock(&vnode->lock);

3
fs/afs/inode.c
View file

@ -301,7 +301,8 @@ int afs_getattr(struct vfsmount *mnt, struct dentry *dentry,
inode = dentry->d_inode;
_enter("{ ino=%lu v=%lu }", inode->i_ino, inode->i_version);
_enter("{ ino=%lu v=%llu }", inode->i_ino,
(unsigned long long)inode->i_version);
generic_fillattr(inode, stat);
return 0;

44
fs/buffer.c
View file

@ -3213,6 +3213,50 @@ static int buffer_cpu_notify(struct notifier_block *self,
return NOTIFY_OK;
}
/**
* bh_uptodate_or_lock: Test whether the buffer is uptodate
* @bh: struct buffer_head
*
* Return true if the buffer is up-to-date and false,
* with the buffer locked, if not.
*/
int bh_uptodate_or_lock(struct buffer_head *bh)
{
if (!buffer_uptodate(bh)) {
lock_buffer(bh);
if (!buffer_uptodate(bh))
return 0;
unlock_buffer(bh);
}
return 1;
}
EXPORT_SYMBOL(bh_uptodate_or_lock);
/**
* bh_submit_read: Submit a locked buffer for reading
* @bh: struct buffer_head
*
* Returns zero on success and -EIO on error.
*/
int bh_submit_read(struct buffer_head *bh)
{
BUG_ON(!buffer_locked(bh));
if (buffer_uptodate(bh)) {
unlock_buffer(bh);
return 0;
}
get_bh(bh);
bh->b_end_io = end_buffer_read_sync;
submit_bh(READ, bh);
wait_on_buffer(bh);
if (buffer_uptodate(bh))
return 0;
return -EIO;
}
EXPORT_SYMBOL(bh_submit_read);
void __init buffer_init(void)
{
int nrpages;

32
fs/ext2/super.c
View file

@ -680,11 +680,31 @@ static int ext2_check_descriptors (struct super_block * sb)
static loff_t ext2_max_size(int bits)
{
loff_t res = EXT2_NDIR_BLOCKS;
/* This constant is calculated to be the largest file size for a
* dense, 4k-blocksize file such that the total number of
int meta_blocks;
loff_t upper_limit;
/* This is calculated to be the largest file size for a
* dense, file such that the total number of
* sectors in the file, including data and all indirect blocks,
* does not exceed 2^32. */
const loff_t upper_limit = 0x1ff7fffd000LL;
* does not exceed 2^32 -1
* __u32 i_blocks representing the total number of
* 512 bytes blocks of the file
*/
upper_limit = (1LL << 32) - 1;
/* total blocks in file system block size */
upper_limit >>= (bits - 9);
/* indirect blocks */
meta_blocks = 1;
/* double indirect blocks */
meta_blocks += 1 + (1LL << (bits-2));
/* tripple indirect blocks */
meta_blocks += 1 + (1LL << (bits-2)) + (1LL << (2*(bits-2)));
upper_limit -= meta_blocks;
upper_limit <<= bits;
res += 1LL << (bits-2);
res += 1LL << (2*(bits-2));
@ -692,6 +712,10 @@ static loff_t ext2_max_size(int bits)
res <<= bits;
if (res > upper_limit)
res = upper_limit;
if (res > MAX_LFS_FILESIZE)
res = MAX_LFS_FILESIZE;
return res;
}

32
fs/ext3/super.c
View file

@ -1436,11 +1436,31 @@ static void ext3_orphan_cleanup (struct super_block * sb,
static loff_t ext3_max_size(int bits)
{
loff_t res = EXT3_NDIR_BLOCKS;
/* This constant is calculated to be the largest file size for a
* dense, 4k-blocksize file such that the total number of
int meta_blocks;
loff_t upper_limit;
/* This is calculated to be the largest file size for a
* dense, file such that the total number of
* sectors in the file, including data and all indirect blocks,
* does not exceed 2^32. */
const loff_t upper_limit = 0x1ff7fffd000LL;
* does not exceed 2^32 -1
* __u32 i_blocks representing the total number of
* 512 bytes blocks of the file
*/
upper_limit = (1LL << 32) - 1;
/* total blocks in file system block size */
upper_limit >>= (bits - 9);
/* indirect blocks */
meta_blocks = 1;
/* double indirect blocks */
meta_blocks += 1 + (1LL << (bits-2));
/* tripple indirect blocks */
meta_blocks += 1 + (1LL << (bits-2)) + (1LL << (2*(bits-2)));
upper_limit -= meta_blocks;
upper_limit <<= bits;
res += 1LL << (bits-2);
res += 1LL << (2*(bits-2));
@ -1448,6 +1468,10 @@ static loff_t ext3_max_size(int bits)
res <<= bits;
if (res > upper_limit)
res = upper_limit;
if (res > MAX_LFS_FILESIZE)
res = MAX_LFS_FILESIZE;
return res;
}

2
fs/ext4/Makefile
View file

@ -6,7 +6,7 @@ obj-$(CONFIG_EXT4DEV_FS) += ext4dev.o
ext4dev-y := balloc.o bitmap.o dir.o file.o fsync.o ialloc.o inode.o \
ioctl.o namei.o super.o symlink.o hash.o resize.o extents.o \
ext4_jbd2.o
ext4_jbd2.o migrate.o mballoc.o
ext4dev-$(CONFIG_EXT4DEV_FS_XATTR) += xattr.o xattr_user.o xattr_trusted.o
ext4dev-$(CONFIG_EXT4DEV_FS_POSIX_ACL) += acl.o

251
fs/ext4/balloc.c
View file

@ -29,7 +29,7 @@
* Calculate the block group number and offset, given a block number
*/
void ext4_get_group_no_and_offset(struct super_block *sb, ext4_fsblk_t blocknr,
unsigned long *blockgrpp, ext4_grpblk_t *offsetp)
ext4_group_t *blockgrpp, ext4_grpblk_t *offsetp)
{
struct ext4_super_block *es = EXT4_SB(sb)->s_es;
ext4_grpblk_t offset;
@ -46,7 +46,7 @@ void ext4_get_group_no_and_offset(struct super_block *sb, ext4_fsblk_t blocknr,
/* Initializes an uninitialized block bitmap if given, and returns the
* number of blocks free in the group. */
unsigned ext4_init_block_bitmap(struct super_block *sb, struct buffer_head *bh,
int block_group, struct ext4_group_desc *gdp)
ext4_group_t block_group, struct ext4_group_desc *gdp)
{
unsigned long start;
int bit, bit_max;
@ -60,7 +60,7 @@ unsigned ext4_init_block_bitmap(struct super_block *sb, struct buffer_head *bh,
* essentially implementing a per-group read-only flag. */
if (!ext4_group_desc_csum_verify(sbi, block_group, gdp)) {
ext4_error(sb, __FUNCTION__,
"Checksum bad for group %u\n", block_group);
"Checksum bad for group %lu\n", block_group);
gdp->bg_free_blocks_count = 0;
gdp->bg_free_inodes_count = 0;
gdp->bg_itable_unused = 0;
@ -153,7 +153,7 @@ unsigned ext4_init_block_bitmap(struct super_block *sb, struct buffer_head *bh,
* group descriptor
*/
struct ext4_group_desc * ext4_get_group_desc(struct super_block * sb,
unsigned int block_group,
ext4_group_t block_group,
struct buffer_head ** bh)
{
unsigned long group_desc;
@ -164,7 +164,7 @@ struct ext4_group_desc * ext4_get_group_desc(struct super_block * sb,
if (block_group >= sbi->s_groups_count) {
ext4_error (sb, "ext4_get_group_desc",
"block_group >= groups_count - "
"block_group = %d, groups_count = %lu",
"block_group = %lu, groups_count = %lu",
block_group, sbi->s_groups_count);
return NULL;
@ -176,7 +176,7 @@ struct ext4_group_desc * ext4_get_group_desc(struct super_block * sb,
if (!sbi->s_group_desc[group_desc]) {
ext4_error (sb, "ext4_get_group_desc",
"Group descriptor not loaded - "
"block_group = %d, group_desc = %lu, desc = %lu",
"block_group = %lu, group_desc = %lu, desc = %lu",
block_group, group_desc, offset);
return NULL;
}
@ -189,18 +189,70 @@ struct ext4_group_desc * ext4_get_group_desc(struct super_block * sb,
return desc;
}
static int ext4_valid_block_bitmap(struct super_block *sb,
struct ext4_group_desc *desc,
unsigned int block_group,
struct buffer_head *bh)
{
ext4_grpblk_t offset;
ext4_grpblk_t next_zero_bit;
ext4_fsblk_t bitmap_blk;
ext4_fsblk_t group_first_block;
if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_FLEX_BG)) {
/* with FLEX_BG, the inode/block bitmaps and itable
* blocks may not be in the group at all
* so the bitmap validation will be skipped for those groups
* or it has to also read the block group where the bitmaps
* are located to verify they are set.
*/
return 1;
}
group_first_block = ext4_group_first_block_no(sb, block_group);
/* check whether block bitmap block number is set */
bitmap_blk = ext4_block_bitmap(sb, desc);
offset = bitmap_blk - group_first_block;
if (!ext4_test_bit(offset, bh->b_data))
/* bad block bitmap */
goto err_out;
/* check whether the inode bitmap block number is set */
bitmap_blk = ext4_inode_bitmap(sb, desc);
offset = bitmap_blk - group_first_block;
if (!ext4_test_bit(offset, bh->b_data))
/* bad block bitmap */
goto err_out;
/* check whether the inode table block number is set */
bitmap_blk = ext4_inode_table(sb, desc);
offset = bitmap_blk - group_first_block;
next_zero_bit = ext4_find_next_zero_bit(bh->b_data,
offset + EXT4_SB(sb)->s_itb_per_group,
offset);
if (next_zero_bit >= offset + EXT4_SB(sb)->s_itb_per_group)
/* good bitmap for inode tables */
return 1;
err_out:
ext4_error(sb, __FUNCTION__,
"Invalid block bitmap - "
"block_group = %d, block = %llu",
block_group, bitmap_blk);
return 0;
}
/**
* read_block_bitmap()
* @sb: super block
* @block_group: given block group
*
* Read the bitmap for a given block_group, reading into the specified
* slot in the superblock's bitmap cache.
* Read the bitmap for a given block_group,and validate the
* bits for block/inode/inode tables are set in the bitmaps
*
* Return buffer_head on success or NULL in case of failure.
*/
struct buffer_head *
read_block_bitmap(struct super_block *sb, unsigned int block_group)
read_block_bitmap(struct super_block *sb, ext4_group_t block_group)
{
struct ext4_group_desc * desc;
struct buffer_head * bh = NULL;
@ -210,25 +262,36 @@ read_block_bitmap(struct super_block *sb, unsigned int block_group)
if (!desc)
return NULL;
bitmap_blk = ext4_block_bitmap(sb, desc);
if (desc->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT)) {
bh = sb_getblk(sb, bitmap_blk);
if (!buffer_uptodate(bh)) {
lock_buffer(bh);
if (!buffer_uptodate(bh)) {
ext4_init_block_bitmap(sb, bh, block_group,
desc);
set_buffer_uptodate(bh);
}
unlock_buffer(bh);
}
} else {
bh = sb_bread(sb, bitmap_blk);
}
if (!bh)
ext4_error (sb, __FUNCTION__,
bh = sb_getblk(sb, bitmap_blk);
if (unlikely(!bh)) {
ext4_error(sb, __FUNCTION__,
"Cannot read block bitmap - "
"block_group = %d, block_bitmap = %llu",
block_group, bitmap_blk);
(int)block_group, (unsigned long long)bitmap_blk);
return NULL;
}
if (bh_uptodate_or_lock(bh))
return bh;
if (desc->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT)) {
ext4_init_block_bitmap(sb, bh, block_group, desc);
set_buffer_uptodate(bh);
unlock_buffer(bh);
return bh;
}
if (bh_submit_read(bh) < 0) {
put_bh(bh);
ext4_error(sb, __FUNCTION__,
"Cannot read block bitmap - "
"block_group = %d, block_bitmap = %llu",
(int)block_group, (unsigned long long)bitmap_blk);
return NULL;
}
if (!ext4_valid_block_bitmap(sb, desc, block_group, bh)) {
put_bh(bh);
return NULL;
}
return bh;
}
/*
@ -320,7 +383,7 @@ restart:
*/
static int
goal_in_my_reservation(struct ext4_reserve_window *rsv, ext4_grpblk_t grp_goal,
unsigned int group, struct super_block * sb)
ext4_group_t group, struct super_block *sb)
{
ext4_fsblk_t group_first_block, group_last_block;
@ -463,7 +526,7 @@ static inline int rsv_is_empty(struct ext4_reserve_window *rsv)
* when setting the reservation window size through ioctl before the file
* is open for write (needs block allocation).
*
* Needs truncate_mutex protection prior to call this function.
* Needs down_write(i_data_sem) protection prior to call this function.
*/
void ext4_init_block_alloc_info(struct inode *inode)
{
@ -514,6 +577,8 @@ void ext4_discard_reservation(struct inode *inode)
struct ext4_reserve_window_node *rsv;
spinlock_t *rsv_lock = &EXT4_SB(inode->i_sb)->s_rsv_window_lock;
ext4_mb_discard_inode_preallocations(inode);
if (!block_i)
return;
@ -540,7 +605,7 @@ void ext4_free_blocks_sb(handle_t *handle, struct super_block *sb,
{
struct buffer_head *bitmap_bh = NULL;
struct buffer_head *gd_bh;
unsigned long block_group;
ext4_group_t block_group;
ext4_grpblk_t bit;
unsigned long i;
unsigned long overflow;
@ -587,11 +652,13 @@ do_more:
in_range(ext4_inode_bitmap(sb, desc), block, count) ||
in_range(block, ext4_inode_table(sb, desc), sbi->s_itb_per_group) ||
in_range(block + count - 1, ext4_inode_table(sb, desc),
sbi->s_itb_per_group))
sbi->s_itb_per_group)) {
ext4_error (sb, "ext4_free_blocks",
"Freeing blocks in system zones - "
"Block = %llu, count = %lu",
block, count);
goto error_return;
}
/*
* We are about to start releasing blocks in the bitmap,
@ -720,19 +787,29 @@ error_return:
* @inode: inode
* @block: start physical block to free
* @count: number of blocks to count
* @metadata: Are these metadata blocks
*/
void ext4_free_blocks(handle_t *handle, struct inode *inode,
ext4_fsblk_t block, unsigned long count)
ext4_fsblk_t block, unsigned long count,
int metadata)
{
struct super_block * sb;
unsigned long dquot_freed_blocks;
/* this isn't the right place to decide whether block is metadata
* inode.c/extents.c knows better, but for safety ... */
if (S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode) ||
ext4_should_journal_data(inode))
metadata = 1;
sb = inode->i_sb;
if (!sb) {
printk ("ext4_free_blocks: nonexistent device");
return;
}
ext4_free_blocks_sb(handle, sb, block, count, &dquot_freed_blocks);
if (!test_opt(sb, MBALLOC) || !EXT4_SB(sb)->s_group_info)
ext4_free_blocks_sb(handle, sb, block, count,
&dquot_freed_blocks);
else
ext4_mb_free_blocks(handle, inode, block, count,
metadata, &dquot_freed_blocks);
if (dquot_freed_blocks)
DQUOT_FREE_BLOCK(inode, dquot_freed_blocks);
return;
@ -920,9 +997,10 @@ claim_block(spinlock_t *lock, ext4_grpblk_t block, struct buffer_head *bh)
* ext4_journal_release_buffer(), else we'll run out of credits.
*/
static ext4_grpblk_t
ext4_try_to_allocate(struct super_block *sb, handle_t *handle, int group,
struct buffer_head *bitmap_bh, ext4_grpblk_t grp_goal,
unsigned long *count, struct ext4_reserve_window *my_rsv)
ext4_try_to_allocate(struct super_block *sb, handle_t *handle,
ext4_group_t group, struct buffer_head *bitmap_bh,
ext4_grpblk_t grp_goal, unsigned long *count,
struct ext4_reserve_window *my_rsv)
{
ext4_fsblk_t group_first_block;
ext4_grpblk_t start, end;
@ -1156,7 +1234,7 @@ static int find_next_reservable_window(
*/
static int alloc_new_reservation(struct ext4_reserve_window_node *my_rsv,
ext4_grpblk_t grp_goal, struct super_block *sb,
unsigned int group, struct buffer_head *bitmap_bh)
ext4_group_t group, struct buffer_head *bitmap_bh)
{
struct ext4_reserve_window_node *search_head;
ext4_fsblk_t group_first_block, group_end_block, start_block;
@ -1354,7 +1432,7 @@ static void try_to_extend_reservation(struct ext4_reserve_window_node *my_rsv,
*/
static ext4_grpblk_t
ext4_try_to_allocate_with_rsv(struct super_block *sb, handle_t *handle,
unsigned int group, struct buffer_head *bitmap_bh,
ext4_group_t group, struct buffer_head *bitmap_bh,
ext4_grpblk_t grp_goal,
struct ext4_reserve_window_node * my_rsv,
unsigned long *count, int *errp)
@ -1510,7 +1588,7 @@ int ext4_should_retry_alloc(struct super_block *sb, int *retries)
}
/**
* ext4_new_blocks() -- core block(s) allocation function
* ext4_new_blocks_old() -- core block(s) allocation function
* @handle: handle to this transaction
* @inode: file inode
* @goal: given target block(filesystem wide)
@ -1523,17 +1601,17 @@ int ext4_should_retry_alloc(struct super_block *sb, int *retries)
* any specific goal block.
*
*/
ext4_fsblk_t ext4_new_blocks(handle_t *handle, struct inode *inode,
ext4_fsblk_t ext4_new_blocks_old(handle_t *handle, struct inode *inode,
ext4_fsblk_t goal, unsigned long *count, int *errp)
{
struct buffer_head *bitmap_bh = NULL;
struct buffer_head *gdp_bh;
unsigned long group_no;
int goal_group;
ext4_group_t group_no;
ext4_group_t goal_group;
ext4_grpblk_t grp_target_blk; /* blockgroup relative goal block */
ext4_grpblk_t grp_alloc_blk; /* blockgroup-relative allocated block*/
ext4_fsblk_t ret_block; /* filesyetem-wide allocated block */
int bgi; /* blockgroup iteration index */
ext4_group_t bgi; /* blockgroup iteration index */
int fatal = 0, err;
int performed_allocation = 0;
ext4_grpblk_t free_blocks; /* number of free blocks in a group */
@ -1544,10 +1622,7 @@ ext4_fsblk_t ext4_new_blocks(handle_t *handle, struct inode *inode,
struct ext4_reserve_window_node *my_rsv = NULL;
struct ext4_block_alloc_info *block_i;
unsigned short windowsz = 0;
#ifdef EXT4FS_DEBUG
static int goal_hits, goal_attempts;
#endif
unsigned long ngroups;
ext4_group_t ngroups;
unsigned long num = *count;
*errp = -ENOSPC;
@ -1567,7 +1642,7 @@ ext4_fsblk_t ext4_new_blocks(handle_t *handle, struct inode *inode,
sbi = EXT4_SB(sb);
es = EXT4_SB(sb)->s_es;
ext4_debug("goal=%lu.\n", goal);
ext4_debug("goal=%llu.\n", goal);
/*
* Allocate a block from reservation only when
* filesystem is mounted with reservation(default,-o reservation), and
@ -1677,7 +1752,7 @@ retry_alloc:
allocated:
ext4_debug("using block group %d(%d)\n",
ext4_debug("using block group %lu(%d)\n",
group_no, gdp->bg_free_blocks_count);
BUFFER_TRACE(gdp_bh, "get_write_access");
@ -1692,11 +1767,13 @@ allocated:
in_range(ret_block, ext4_inode_table(sb, gdp),
EXT4_SB(sb)->s_itb_per_group) ||
in_range(ret_block + num - 1, ext4_inode_table(sb, gdp),
EXT4_SB(sb)->s_itb_per_group))
EXT4_SB(sb)->s_itb_per_group)) {
ext4_error(sb, "ext4_new_block",
"Allocating block in system zone - "
"blocks from %llu, length %lu",
ret_block, num);
goto out;
}
performed_allocation = 1;
@ -1743,9 +1820,6 @@ allocated:
* list of some description. We don't know in advance whether
* the caller wants to use it as metadata or data.
*/
ext4_debug("allocating block %lu. Goal hits %d of %d.\n",
ret_block, goal_hits, goal_attempts);
spin_lock(sb_bgl_lock(sbi, group_no));
if (gdp->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT))
gdp->bg_flags &= cpu_to_le16(~EXT4_BG_BLOCK_UNINIT);
@ -1787,13 +1861,46 @@ out:
}
ext4_fsblk_t ext4_new_block(handle_t *handle, struct inode *inode,
ext4_fsblk_t goal, int *errp)
ext4_fsblk_t goal, int *errp)
{
unsigned long count = 1;
struct ext4_allocation_request ar;
ext4_fsblk_t ret;
return ext4_new_blocks(handle, inode, goal, &count, errp);
if (!test_opt(inode->i_sb, MBALLOC)) {
unsigned long count = 1;
ret = ext4_new_blocks_old(handle, inode, goal, &count, errp);
return ret;
}
memset(&ar, 0, sizeof(ar));
ar.inode = inode;
ar.goal = goal;
ar.len = 1;
ret = ext4_mb_new_blocks(handle, &ar, errp);
return ret;
}
ext4_fsblk_t ext4_new_blocks(handle_t *handle, struct inode *inode,
ext4_fsblk_t goal, unsigned long *count, int *errp)
{
struct ext4_allocation_request ar;
ext4_fsblk_t ret;
if (!test_opt(inode->i_sb, MBALLOC)) {
ret = ext4_new_blocks_old(handle, inode, goal, count, errp);
return ret;
}
memset(&ar, 0, sizeof(ar));
ar.inode = inode;
ar.goal = goal;
ar.len = *count;
ret = ext4_mb_new_blocks(handle, &ar, errp);
*count = ar.len;
return ret;
}
/**
* ext4_count_free_blocks() -- count filesystem free blocks
* @sb: superblock
@ -1804,8 +1911,8 @@ ext4_fsblk_t ext4_count_free_blocks(struct super_block *sb)
{
ext4_fsblk_t desc_count;
struct ext4_group_desc *gdp;
int i;
unsigned long ngroups = EXT4_SB(sb)->s_groups_count;
ext4_group_t i;
ext4_group_t ngroups = EXT4_SB(sb)->s_groups_count;
#ifdef EXT4FS_DEBUG
struct ext4_super_block *es;
ext4_fsblk_t bitmap_count;
@ -1829,14 +1936,14 @@ ext4_fsblk_t ext4_count_free_blocks(struct super_block *sb)
continue;
x = ext4_count_free(bitmap_bh, sb->s_blocksize);
printk("group %d: stored = %d, counted = %lu\n",
printk(KERN_DEBUG "group %lu: stored = %d, counted = %lu\n",
i, le16_to_cpu(gdp->bg_free_blocks_count), x);
bitmap_count += x;
}
brelse(bitmap_bh);
printk("ext4_count_free_blocks: stored = %llu"
", computed = %llu, %llu\n",
EXT4_FREE_BLOCKS_COUNT(es),
ext4_free_blocks_count(es),
desc_count, bitmap_count);
return bitmap_count;
#else
@ -1853,7 +1960,7 @@ ext4_fsblk_t ext4_count_free_blocks(struct super_block *sb)
#endif
}
static inline int test_root(int a, int b)
static inline int test_root(ext4_group_t a, int b)
{
int num = b;
@ -1862,7 +1969,7 @@ static inline int test_root(int a, int b)
return num == a;
}
static int ext4_group_sparse(int group)
static int ext4_group_sparse(ext4_group_t group)
{
if (group <= 1)
return 1;
@ -1880,7 +1987,7 @@ static int ext4_group_sparse(int group)
* Return the number of blocks used by the superblock (primary or backup)
* in this group. Currently this will be only 0 or 1.
*/
int ext4_bg_has_super(struct super_block *sb, int group)
int ext4_bg_has_super(struct super_block *sb, ext4_group_t group)
{
if (EXT4_HAS_RO_COMPAT_FEATURE(sb,
EXT4_FEATURE_RO_COMPAT_SPARSE_SUPER) &&
@ -1889,18 +1996,20 @@ int ext4_bg_has_super(struct super_block *sb, int group)
return 1;
}
static unsigned long ext4_bg_num_gdb_meta(struct super_block *sb, int group)
static unsigned long ext4_bg_num_gdb_meta(struct super_block *sb,
ext4_group_t group)
{
unsigned long metagroup = group / EXT4_DESC_PER_BLOCK(sb);
unsigned long first = metagroup * EXT4_DESC_PER_BLOCK(sb);
unsigned long last = first + EXT4_DESC_PER_BLOCK(sb) - 1;
ext4_group_t first = metagroup * EXT4_DESC_PER_BLOCK(sb);
ext4_group_t last = first + EXT4_DESC_PER_BLOCK(sb) - 1;
if (group == first || group == first + 1 || group == last)
return 1;
return 0;
}
static unsigned long ext4_bg_num_gdb_nometa(struct super_block *sb, int group)
static unsigned long ext4_bg_num_gdb_nometa(struct super_block *sb,
ext4_group_t group)
{
if (EXT4_HAS_RO_COMPAT_FEATURE(sb,
EXT4_FEATURE_RO_COMPAT_SPARSE_SUPER) &&
@ -1918,7 +2027,7 @@ static unsigned long ext4_bg_num_gdb_nometa(struct super_block *sb, int group)
* (primary or backup) in this group. In the future there may be a
* different number of descriptor blocks in each group.
*/
unsigned long ext4_bg_num_gdb(struct super_block *sb, int group)
unsigned long ext4_bg_num_gdb(struct super_block *sb, ext4_group_t group)
{
unsigned long first_meta_bg =
le32_to_cpu(EXT4_SB(sb)->s_es->s_first_meta_bg);

14
fs/ext4/dir.c
View file

@ -67,7 +67,7 @@ int ext4_check_dir_entry (const char * function, struct inode * dir,
unsigned long offset)
{
const char * error_msg = NULL;
const int rlen = le16_to_cpu(de->rec_len);
const int rlen = ext4_rec_len_from_disk(de->rec_len);
if (rlen < EXT4_DIR_REC_LEN(1))
error_msg = "rec_len is smaller than minimal";
@ -124,7 +124,7 @@ static int ext4_readdir(struct file * filp,
offset = filp->f_pos & (sb->s_blocksize - 1);
while (!error && !stored && filp->f_pos < inode->i_size) {
unsigned long blk = filp->f_pos >> EXT4_BLOCK_SIZE_BITS(sb);
ext4_lblk_t blk = filp->f_pos >> EXT4_BLOCK_SIZE_BITS(sb);
struct buffer_head map_bh;
struct buffer_head *bh = NULL;
@ -172,10 +172,10 @@ revalidate:
* least that it is non-zero. A
* failure will be detected in the
* dirent test below. */
if (le16_to_cpu(de->rec_len) <
EXT4_DIR_REC_LEN(1))
if (ext4_rec_len_from_disk(de->rec_len)
< EXT4_DIR_REC_LEN(1))
break;
i += le16_to_cpu(de->rec_len);
i += ext4_rec_len_from_disk(de->rec_len);
}
offset = i;
filp->f_pos = (filp->f_pos & ~(sb->s_blocksize - 1))
@ -197,7 +197,7 @@ revalidate:
ret = stored;
goto out;
}
offset += le16_to_cpu(de->rec_len);
offset += ext4_rec_len_from_disk(de->rec_len);
if (le32_to_cpu(de->inode)) {
/* We might block in the next section
* if the data destination is
@ -219,7 +219,7 @@ revalidate:
goto revalidate;
stored ++;
}
filp->f_pos += le16_to_cpu(de->rec_len);
filp->f_pos += ext4_rec_len_from_disk(de->rec_len);
}
offset = 0;
brelse (bh);

481
fs/ext4/extents.c
View file

@ -61,7 +61,7 @@ static ext4_fsblk_t ext_pblock(struct ext4_extent *ex)
* idx_pblock:
* combine low and high parts of a leaf physical block number into ext4_fsblk_t
*/
static ext4_fsblk_t idx_pblock(struct ext4_extent_idx *ix)
ext4_fsblk_t idx_pblock(struct ext4_extent_idx *ix)
{
ext4_fsblk_t block;
@ -75,7 +75,7 @@ static ext4_fsblk_t idx_pblock(struct ext4_extent_idx *ix)
* stores a large physical block number into an extent struct,
* breaking it into parts
*/
static void ext4_ext_store_pblock(struct ext4_extent *ex, ext4_fsblk_t pb)
void ext4_ext_store_pblock(struct ext4_extent *ex, ext4_fsblk_t pb)
{
ex->ee_start_lo = cpu_to_le32((unsigned long) (pb & 0xffffffff));
ex->ee_start_hi = cpu_to_le16((unsigned long) ((pb >> 31) >> 1) & 0xffff);
@ -144,7 +144,7 @@ static int ext4_ext_dirty(handle_t *handle, struct inode *inode,
static ext4_fsblk_t ext4_ext_find_goal(struct inode *inode,
struct ext4_ext_path *path,
ext4_fsblk_t block)
ext4_lblk_t block)
{
struct ext4_inode_info *ei = EXT4_I(inode);
ext4_fsblk_t bg_start;
@ -367,13 +367,14 @@ static void ext4_ext_drop_refs(struct ext4_ext_path *path)
* the header must be checked before calling this
*/
static void
ext4_ext_binsearch_idx(struct inode *inode, struct ext4_ext_path *path, int block)
ext4_ext_binsearch_idx(struct inode *inode,
struct ext4_ext_path *path, ext4_lblk_t block)
{
struct ext4_extent_header *eh = path->p_hdr;
struct ext4_extent_idx *r, *l, *m;
ext_debug("binsearch for %d(idx): ", block);
ext_debug("binsearch for %u(idx): ", block);
l = EXT_FIRST_INDEX(eh) + 1;
r = EXT_LAST_INDEX(eh);
@ -425,7 +426,8 @@ ext4_ext_binsearch_idx(struct inode *inode, struct ext4_ext_path *path, int bloc
* the header must be checked before calling this
*/
static void
ext4_ext_binsearch(struct inode *inode, struct ext4_ext_path *path, int block)
ext4_ext_binsearch(struct inode *inode,
struct ext4_ext_path *path, ext4_lblk_t block)
{
struct ext4_extent_header *eh = path->p_hdr;
struct ext4_extent *r, *l, *m;
@ -438,7 +440,7 @@ ext4_ext_binsearch(struct inode *inode, struct ext4_ext_path *path, int block)
return;
}
ext_debug("binsearch for %d: ", block);
ext_debug("binsearch for %u: ", block);
l = EXT_FIRST_EXTENT(eh) + 1;
r = EXT_LAST_EXTENT(eh);
@ -494,7 +496,8 @@ int ext4_ext_tree_init(handle_t *handle, struct inode *inode)
}
struct ext4_ext_path *
ext4_ext_find_extent(struct inode *inode, int block, struct ext4_ext_path *path)
ext4_ext_find_extent(struct inode *inode, ext4_lblk_t block,
struct ext4_ext_path *path)
{
struct ext4_extent_header *eh;
struct buffer_head *bh;
@ -763,7 +766,7 @@ static int ext4_ext_split(handle_t *handle, struct inode *inode,
while (k--) {
oldblock = newblock;
newblock = ablocks[--a];
bh = sb_getblk(inode->i_sb, (ext4_fsblk_t)newblock);
bh = sb_getblk(inode->i_sb, newblock);
if (!bh) {
err = -EIO;
goto cleanup;
@ -783,9 +786,8 @@ static int ext4_ext_split(handle_t *handle, struct inode *inode,
fidx->ei_block = border;
ext4_idx_store_pblock(fidx, oldblock);
ext_debug("int.index at %d (block %llu): %lu -> %llu\n", i,
newblock, (unsigned long) le32_to_cpu(border),
oldblock);
ext_debug("int.index at %d (block %llu): %u -> %llu\n",
i, newblock, le32_to_cpu(border), oldblock);
/* copy indexes */
m = 0;
path[i].p_idx++;
@ -851,7 +853,7 @@ cleanup:
for (i = 0; i < depth; i++) {
if (!ablocks[i])
continue;
ext4_free_blocks(handle, inode, ablocks[i], 1);
ext4_free_blocks(handle, inode, ablocks[i], 1, 1);
}
}
kfree(ablocks);
@ -979,8 +981,8 @@ repeat:
/* refill path */
ext4_ext_drop_refs(path);
path = ext4_ext_find_extent(inode,
le32_to_cpu(newext->ee_block),
path);
(ext4_lblk_t)le32_to_cpu(newext->ee_block),
path);
if (IS_ERR(path))
err = PTR_ERR(path);
} else {
@ -992,8 +994,8 @@ repeat:
/* refill path */
ext4_ext_drop_refs(path);
path = ext4_ext_find_extent(inode,
le32_to_cpu(newext->ee_block),
path);
(ext4_lblk_t)le32_to_cpu(newext->ee_block),
path);
if (IS_ERR(path)) {
err = PTR_ERR(path);
goto out;
@ -1014,6 +1016,150 @@ out:
return err;
}
/*
* search the closest allocated block to the left for *logical
* and returns it at @logical + it's physical address at @phys
* if *logical is the smallest allocated block, the function
* returns 0 at @phys
* return value contains 0 (success) or error code
*/
int
ext4_ext_search_left(struct inode *inode, struct ext4_ext_path *path,
ext4_lblk_t *logical, ext4_fsblk_t *phys)
{
struct ext4_extent_idx *ix;
struct ext4_extent *ex;
int depth, ee_len;
BUG_ON(path == NULL);
depth = path->p_depth;
*phys = 0;
if (depth == 0 && path->p_ext == NULL)
return 0;
/* usually extent in the path covers blocks smaller
* then *logical, but it can be that extent is the
* first one in the file */
ex = path[depth].p_ext;
ee_len = ext4_ext_get_actual_len(ex);
if (*logical < le32_to_cpu(ex->ee_block)) {
BUG_ON(EXT_FIRST_EXTENT(path[depth].p_hdr) != ex);
while (--depth >= 0) {
ix = path[depth].p_idx;
BUG_ON(ix != EXT_FIRST_INDEX(path[depth].p_hdr));
}
return 0;
}
BUG_ON(*logical < (le32_to_cpu(ex->ee_block) + ee_len));
*logical = le32_to_cpu(ex->ee_block) + ee_len - 1;
*phys = ext_pblock(ex) + ee_len - 1;
return 0;
}
/*
* search the closest allocated block to the right for *logical
* and returns it at @logical + it's physical address at @phys
* if *logical is the smallest allocated block, the function
* returns 0 at @phys
* return value contains 0 (success) or error code
*/
int
ext4_ext_search_right(struct inode *inode, struct ext4_ext_path *path,
ext4_lblk_t *logical, ext4_fsblk_t *phys)
{
struct buffer_head *bh = NULL;
struct ext4_extent_header *eh;
struct ext4_extent_idx *ix;
struct ext4_extent *ex;
ext4_fsblk_t block;
int depth, ee_len;
BUG_ON(path == NULL);
depth = path->p_depth;
*phys = 0;
if (depth == 0 && path->p_ext == NULL)
return 0;
/* usually extent in the path covers blocks smaller
* then *logical, but it can be that extent is the
* first one in the file */
ex = path[depth].p_ext;
ee_len = ext4_ext_get_actual_len(ex);
if (*logical < le32_to_cpu(ex->ee_block)) {
BUG_ON(EXT_FIRST_EXTENT(path[depth].p_hdr) != ex);
while (--depth >= 0) {
ix = path[depth].p_idx;
BUG_ON(ix != EXT_FIRST_INDEX(path[depth].p_hdr));
}
*logical = le32_to_cpu(ex->ee_block);
*phys = ext_pblock(ex);
return 0;
}
BUG_ON(*logical < (le32_to_cpu(ex->ee_block) + ee_len));
if (ex != EXT_LAST_EXTENT(path[depth].p_hdr)) {
/* next allocated block in this leaf */
ex++;
*logical = le32_to_cpu(ex->ee_block);
*phys = ext_pblock(ex);
return 0;
}
/* go up and search for index to the right */
while (--depth >= 0) {
ix = path[depth].p_idx;
if (ix != EXT_LAST_INDEX(path[depth].p_hdr))
break;
}
if (depth < 0) {
/* we've gone up to the root and
* found no index to the right */
return 0;
}
/* we've found index to the right, let's
* follow it and find the closest allocated
* block to the right */
ix++;
block = idx_pblock(ix);
while (++depth < path->p_depth) {
bh = sb_bread(inode->i_sb, block);
if (bh == NULL)
return -EIO;
eh = ext_block_hdr(bh);
if (ext4_ext_check_header(inode, eh, depth)) {
put_bh(bh);
return -EIO;
}
ix = EXT_FIRST_INDEX(eh);
block = idx_pblock(ix);
put_bh(bh);
}
bh = sb_bread(inode->i_sb, block);
if (bh == NULL)
return -EIO;
eh = ext_block_hdr(bh);
if (ext4_ext_check_header(inode, eh, path->p_depth - depth)) {
put_bh(bh);
return -EIO;
}
ex = EXT_FIRST_EXTENT(eh);
*logical = le32_to_cpu(ex->ee_block);
*phys = ext_pblock(ex);
put_bh(bh);
return 0;
}
/*
* ext4_ext_next_allocated_block:
* returns allocated block in subsequent extent or EXT_MAX_BLOCK.
@ -1021,7 +1167,7 @@ out:
* allocated block. Thus, index entries have to be consistent
* with leaves.
*/
static unsigned long
static ext4_lblk_t
ext4_ext_next_allocated_block(struct ext4_ext_path *path)
{
int depth;
@ -1054,7 +1200,7 @@ ext4_ext_next_allocated_block(struct ext4_ext_path *path)
* ext4_ext_next_leaf_block:
* returns first allocated block from next leaf or EXT_MAX_BLOCK
*/
static unsigned ext4_ext_next_leaf_block(struct inode *inode,
static ext4_lblk_t ext4_ext_next_leaf_block(struct inode *inode,
struct ext4_ext_path *path)
{
int depth;
@ -1072,7 +1218,8 @@ static unsigned ext4_ext_next_leaf_block(struct inode *inode,
while (depth >= 0) {
if (path[depth].p_idx !=
EXT_LAST_INDEX(path[depth].p_hdr))
return le32_to_cpu(path[depth].p_idx[1].ei_block);
return (ext4_lblk_t)
le32_to_cpu(path[depth].p_idx[1].ei_block);
depth--;
}
@ -1085,7 +1232,7 @@ static unsigned ext4_ext_next_leaf_block(struct inode *inode,
* then we have to correct all indexes above.
* TODO: do we need to correct tree in all cases?
*/
int ext4_ext_correct_indexes(handle_t *handle, struct inode *inode,
static int ext4_ext_correct_indexes(handle_t *handle, struct inode *inode,
struct ext4_ext_path *path)
{
struct ext4_extent_header *eh;
@ -1171,7 +1318,7 @@ ext4_can_extents_be_merged(struct inode *inode, struct ext4_extent *ex1,
if (ext1_ee_len + ext2_ee_len > max_len)
return 0;
#ifdef AGGRESSIVE_TEST
if (le16_to_cpu(ex1->ee_len) >= 4)
if (ext1_ee_len >= 4)
return 0;
#endif
@ -1239,7 +1386,7 @@ unsigned int ext4_ext_check_overlap(struct inode *inode,
struct ext4_extent *newext,
struct ext4_ext_path *path)
{
unsigned long b1, b2;
ext4_lblk_t b1, b2;
unsigned int depth, len1;
unsigned int ret = 0;
@ -1260,7 +1407,7 @@ unsigned int ext4_ext_check_overlap(struct inode *inode,
goto out;
}
/* check for wrap through zero */
/* check for wrap through zero on extent logical start block*/
if (b1 + len1 < b1) {
len1 = EXT_MAX_BLOCK - b1;
newext->ee_len = cpu_to_le16(len1);
@ -1290,7 +1437,8 @@ int ext4_ext_insert_extent(handle_t *handle, struct inode *inode,
struct ext4_extent *ex, *fex;
struct ext4_extent *nearex; /* nearest extent */
struct ext4_ext_path *npath = NULL;
int depth, len, err, next;
int depth, len, err;
ext4_lblk_t next;
unsigned uninitialized = 0;
BUG_ON(ext4_ext_get_actual_len(newext) == 0);
@ -1435,114 +1583,8 @@ cleanup:
return err;
}
int ext4_ext_walk_space(struct inode *inode, unsigned long block,
unsigned long num, ext_prepare_callback func,
void *cbdata)
{
struct ext4_ext_path *path = NULL;
struct ext4_ext_cache cbex;
struct ext4_extent *ex;
unsigned long next, start = 0, end = 0;
unsigned long last = block + num;
int depth, exists, err = 0;
BUG_ON(func == NULL);
BUG_ON(inode == NULL);
while (block < last && block != EXT_MAX_BLOCK) {
num = last - block;
/* find extent for this block */
path = ext4_ext_find_extent(inode, block, path);
if (IS_ERR(path)) {
err = PTR_ERR(path);
path = NULL;
break;
}
depth = ext_depth(inode);
BUG_ON(path[depth].p_hdr == NULL);
ex = path[depth].p_ext;
next = ext4_ext_next_allocated_block(path);
exists = 0;
if (!ex) {
/* there is no extent yet, so try to allocate
* all requested space */
start = block;
end = block + num;
} else if (le32_to_cpu(ex->ee_block) > block) {
/* need to allocate space before found extent */
start = block;
end = le32_to_cpu(ex->ee_block);
if (block + num < end)
end = block + num;
} else if (block >= le32_to_cpu(ex->ee_block)
+ ext4_ext_get_actual_len(ex)) {
/* need to allocate space after found extent */
start = block;
end = block + num;
if (end >= next)
end = next;
} else if (block >= le32_to_cpu(ex->ee_block)) {
/*
* some part of requested space is covered
* by found extent
*/
start = block;
end = le32_to_cpu(ex->ee_block)
+ ext4_ext_get_actual_len(ex);
if (block + num < end)
end = block + num;
exists = 1;
} else {
BUG();
}
BUG_ON(end <= start);
if (!exists) {
cbex.ec_block = start;
cbex.ec_len = end - start;
cbex.ec_start = 0;
cbex.ec_type = EXT4_EXT_CACHE_GAP;
} else {
cbex.ec_block = le32_to_cpu(ex->ee_block);
cbex.ec_len = ext4_ext_get_actual_len(ex);
cbex.ec_start = ext_pblock(ex);
cbex.ec_type = EXT4_EXT_CACHE_EXTENT;
}
BUG_ON(cbex.ec_len == 0);
err = func(inode, path, &cbex, cbdata);
ext4_ext_drop_refs(path);
if (err < 0)
break;
if (err == EXT_REPEAT)
continue;
else if (err == EXT_BREAK) {
err = 0;
break;
}
if (ext_depth(inode) != depth) {
/* depth was changed. we have to realloc path */
kfree(path);
path = NULL;
}
block = cbex.ec_block + cbex.ec_len;
}
if (path) {
ext4_ext_drop_refs(path);
kfree(path);
}
return err;
}
static void
ext4_ext_put_in_cache(struct inode *inode, __u32 block,
ext4_ext_put_in_cache(struct inode *inode, ext4_lblk_t block,
__u32 len, ext4_fsblk_t start, int type)
{
struct ext4_ext_cache *cex;
@ -1561,10 +1603,11 @@ ext4_ext_put_in_cache(struct inode *inode, __u32 block,
*/
static void
ext4_ext_put_gap_in_cache(struct inode *inode, struct ext4_ext_path *path,
unsigned long block)
ext4_lblk_t block)
{
int depth = ext_depth(inode);
unsigned long lblock, len;
unsigned long len;
ext4_lblk_t lblock;
struct ext4_extent *ex;
ex = path[depth].p_ext;
@ -1576,32 +1619,34 @@ ext4_ext_put_gap_in_cache(struct inode *inode, struct ext4_ext_path *path,
} else if (block < le32_to_cpu(ex->ee_block)) {
lblock = block;
len = le32_to_cpu(ex->ee_block) - block;
ext_debug("cache gap(before): %lu [%lu:%lu]",
(unsigned long) block,
(unsigned long) le32_to_cpu(ex->ee_block),
(unsigned long) ext4_ext_get_actual_len(ex));
ext_debug("cache gap(before): %u [%u:%u]",
block,
le32_to_cpu(ex->ee_block),
ext4_ext_get_actual_len(ex));
} else if (block >= le32_to_cpu(ex->ee_block)
+ ext4_ext_get_actual_len(ex)) {
ext4_lblk_t next;
lblock = le32_to_cpu(ex->ee_block)
+ ext4_ext_get_actual_len(ex);
len = ext4_ext_next_allocated_block(path);
ext_debug("cache gap(after): [%lu:%lu] %lu",
(unsigned long) le32_to_cpu(ex->ee_block),
(unsigned long) ext4_ext_get_actual_len(ex),
(unsigned long) block);
BUG_ON(len == lblock);
len = len - lblock;
next = ext4_ext_next_allocated_block(path);
ext_debug("cache gap(after): [%u:%u] %u",
le32_to_cpu(ex->ee_block),
ext4_ext_get_actual_len(ex),
block);
BUG_ON(next == lblock);
len = next - lblock;
} else {
lblock = len = 0;
BUG();
}
ext_debug(" -> %lu:%lu\n", (unsigned long) lblock, len);
ext_debug(" -> %u:%lu\n", lblock, len);
ext4_ext_put_in_cache(inode, lblock, len, 0, EXT4_EXT_CACHE_GAP);
}
static int
ext4_ext_in_cache(struct inode *inode, unsigned long block,
ext4_ext_in_cache(struct inode *inode, ext4_lblk_t block,
struct ext4_extent *ex)
{
struct ext4_ext_cache *cex;
@ -1618,11 +1663,9 @@ ext4_ext_in_cache(struct inode *inode, unsigned long block,
ex->ee_block = cpu_to_le32(cex->ec_block);
ext4_ext_store_pblock(ex, cex->ec_start);
ex->ee_len = cpu_to_le16(cex->ec_len);
ext_debug("%lu cached by %lu:%lu:%llu\n",
(unsigned long) block,
(unsigned long) cex->ec_block,
(unsigned long) cex->ec_len,
cex->ec_start);
ext_debug("%u cached by %u:%u:%llu\n",
block,
cex->ec_block, cex->ec_len, cex->ec_start);
return cex->ec_type;
}
@ -1636,7 +1679,7 @@ ext4_ext_in_cache(struct inode *inode, unsigned long block,
* It's used in truncate case only, thus all requests are for
* last index in the block only.
*/
int ext4_ext_rm_idx(handle_t *handle, struct inode *inode,
static int ext4_ext_rm_idx(handle_t *handle, struct inode *inode,
struct ext4_ext_path *path)
{
struct buffer_head *bh;
@ -1657,7 +1700,7 @@ int ext4_ext_rm_idx(handle_t *handle, struct inode *inode,
ext_debug("index is empty, remove it, free block %llu\n", leaf);
bh = sb_find_get_block(inode->i_sb, leaf);
ext4_forget(handle, 1, inode, bh, leaf);
ext4_free_blocks(handle, inode, leaf, 1);
ext4_free_blocks(handle, inode, leaf, 1, 1);
return err;
}
@ -1666,7 +1709,7 @@ int ext4_ext_rm_idx(handle_t *handle, struct inode *inode,
* This routine returns max. credits that the extent tree can consume.
* It should be OK for low-performance paths like ->writepage()
* To allow many writing processes to fit into a single transaction,
* the caller should calculate credits under truncate_mutex and
* the caller should calculate credits under i_data_sem and
* pass the actual path.
*/
int ext4_ext_calc_credits_for_insert(struct inode *inode,
@ -1714,12 +1757,14 @@ int ext4_ext_calc_credits_for_insert(struct inode *inode,
static int ext4_remove_blocks(handle_t *handle, struct inode *inode,
struct ext4_extent *ex,
unsigned long from, unsigned long to)
ext4_lblk_t from, ext4_lblk_t to)
{
struct buffer_head *bh;
unsigned short ee_len = ext4_ext_get_actual_len(ex);
int i;
int i, metadata = 0;
if (S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode))
metadata = 1;
#ifdef EXTENTS_STATS
{
struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
@ -1738,42 +1783,45 @@ static int ext4_remove_blocks(handle_t *handle, struct inode *inode,
if (from >= le32_to_cpu(ex->ee_block)
&& to == le32_to_cpu(ex->ee_block) + ee_len - 1) {
/* tail removal */
unsigned long num;
ext4_lblk_t num;
ext4_fsblk_t start;
num = le32_to_cpu(ex->ee_block) + ee_len - from;
start = ext_pblock(ex) + ee_len - num;
ext_debug("free last %lu blocks starting %llu\n", num, start);
ext_debug("free last %u blocks starting %llu\n", num, start);
for (i = 0; i < num; i++) {
bh = sb_find_get_block(inode->i_sb, start + i);
ext4_forget(handle, 0, inode, bh, start + i);
}
ext4_free_blocks(handle, inode, start, num);
ext4_free_blocks(handle, inode, start, num, metadata);
} else if (from == le32_to_cpu(ex->ee_block)
&& to <= le32_to_cpu(ex->ee_block) + ee_len - 1) {
printk("strange request: removal %lu-%lu from %u:%u\n",
printk(KERN_INFO "strange request: removal %u-%u from %u:%u\n",
from, to, le32_to_cpu(ex->ee_block), ee_len);
} else {
printk("strange request: removal(2) %lu-%lu from %u:%u\n",
from, to, le32_to_cpu(ex->ee_block), ee_len);
printk(KERN_INFO "strange request: removal(2) "
"%u-%u from %u:%u\n",
from, to, le32_to_cpu(ex->ee_block), ee_len);
}
return 0;
}
static int
ext4_ext_rm_leaf(handle_t *handle, struct inode *inode,
struct ext4_ext_path *path, unsigned long start)
struct ext4_ext_path *path, ext4_lblk_t start)
{
int err = 0, correct_index = 0;
int depth = ext_depth(inode), credits;
struct ext4_extent_header *eh;
unsigned a, b, block, num;
unsigned long ex_ee_block;
ext4_lblk_t a, b, block;
unsigned num;
ext4_lblk_t ex_ee_block;
unsigned short ex_ee_len;
unsigned uninitialized = 0;
struct ext4_extent *ex;
/* the header must be checked already in ext4_ext_remove_space() */
ext_debug("truncate since %lu in leaf\n", start);
ext_debug("truncate since %u in leaf\n", start);
if (!path[depth].p_hdr)
path[depth].p_hdr = ext_block_hdr(path[depth].p_bh);
eh = path[depth].p_hdr;
@ -1904,7 +1952,7 @@ ext4_ext_more_to_rm(struct ext4_ext_path *path)
return 1;
}
int ext4_ext_remove_space(struct inode *inode, unsigned long start)
static int ext4_ext_remove_space(struct inode *inode, ext4_lblk_t start)
{
struct super_block *sb = inode->i_sb;
int depth = ext_depth(inode);
@ -1912,7 +1960,7 @@ int ext4_ext_remove_space(struct inode *inode, unsigned long start)
handle_t *handle;
int i = 0, err = 0;
ext_debug("truncate since %lu\n", start);
ext_debug("truncate since %u\n", start);
/* probably first extent we're gonna free will be last in block */
handle = ext4_journal_start(inode, depth + 1);
@ -2094,17 +2142,19 @@ void ext4_ext_release(struct super_block *sb)
* b> Splits in two extents: Write is happening at either end of the extent
* c> Splits in three extents: Somone is writing in middle of the extent
*/
int ext4_ext_convert_to_initialized(handle_t *handle, struct inode *inode,
struct ext4_ext_path *path,
ext4_fsblk_t iblock,
unsigned long max_blocks)
static int ext4_ext_convert_to_initialized(handle_t *handle,
struct inode *inode,
struct ext4_ext_path *path,
ext4_lblk_t iblock,
unsigned long max_blocks)
{
struct ext4_extent *ex, newex;
struct ext4_extent *ex1 = NULL;
struct ext4_extent *ex2 = NULL;
struct ext4_extent *ex3 = NULL;
struct ext4_extent_header *eh;
unsigned int allocated, ee_block, ee_len, depth;
ext4_lblk_t ee_block;
unsigned int allocated, ee_len, depth;
ext4_fsblk_t newblock;
int err = 0;
int ret = 0;
@ -2225,8 +2275,13 @@ out:
return err ? err : allocated;
}
/*
* Need to be called with
* down_read(&EXT4_I(inode)->i_data_sem) if not allocating file system block
* (ie, create is zero). Otherwise down_write(&EXT4_I(inode)->i_data_sem)
*/
int ext4_ext_get_blocks(handle_t *handle, struct inode *inode,
ext4_fsblk_t iblock,
ext4_lblk_t iblock,
unsigned long max_blocks, struct buffer_head *bh_result,
int create, int extend_disksize)
{
@ -2236,11 +2291,11 @@ int ext4_ext_get_blocks(handle_t *handle, struct inode *inode,
ext4_fsblk_t goal, newblock;
int err = 0, depth, ret;
unsigned long allocated = 0;
struct ext4_allocation_request ar;
__clear_bit(BH_New, &bh_result->b_state);
ext_debug("blocks %d/%lu requested for inode %u\n", (int) iblock,
max_blocks, (unsigned) inode->i_ino);
mutex_lock(&EXT4_I(inode)->truncate_mutex);
ext_debug("blocks %u/%lu requested for inode %u\n",
iblock, max_blocks, inode->i_ino);
/* check in cache */
goal = ext4_ext_in_cache(inode, iblock, &newex);
@ -2260,7 +2315,7 @@ int ext4_ext_get_blocks(handle_t *handle, struct inode *inode,
- le32_to_cpu(newex.ee_block)
+ ext_pblock(&newex);
/* number of remaining blocks in the extent */
allocated = le16_to_cpu(newex.ee_len) -
allocated = ext4_ext_get_actual_len(&newex) -
(iblock - le32_to_cpu(newex.ee_block));
goto out;
} else {
@ -2288,7 +2343,7 @@ int ext4_ext_get_blocks(handle_t *handle, struct inode *inode,
ex = path[depth].p_ext;
if (ex) {
unsigned long ee_block = le32_to_cpu(ex->ee_block);
ext4_lblk_t ee_block = le32_to_cpu(ex->ee_block);
ext4_fsblk_t ee_start = ext_pblock(ex);
unsigned short ee_len;
@ -2302,7 +2357,7 @@ int ext4_ext_get_blocks(handle_t *handle, struct inode *inode,
newblock = iblock - ee_block + ee_start;
/* number of remaining blocks in the extent */
allocated = ee_len - (iblock - ee_block);
ext_debug("%d fit into %lu:%d -> %llu\n", (int) iblock,
ext_debug("%u fit into %lu:%d -> %llu\n", iblock,
ee_block, ee_len, newblock);
/* Do not put uninitialized extent in the cache */
@ -2320,9 +2375,10 @@ int ext4_ext_get_blocks(handle_t *handle, struct inode *inode,
ret = ext4_ext_convert_to_initialized(handle, inode,
path, iblock,
max_blocks);
if (ret <= 0)
if (ret <= 0) {
err = ret;
goto out2;
else
} else
allocated = ret;
goto outnew;
}
@ -2347,8 +2403,15 @@ int ext4_ext_get_blocks(handle_t *handle, struct inode *inode,
if (S_ISREG(inode->i_mode) && (!EXT4_I(inode)->i_block_alloc_info))
ext4_init_block_alloc_info(inode);
/* allocate new block */
goal = ext4_ext_find_goal(inode, path, iblock);
/* find neighbour allocated blocks */
ar.lleft = iblock;
err = ext4_ext_search_left(inode, path, &ar.lleft, &ar.pleft);
if (err)
goto out2;
ar.lright = iblock;
err = ext4_ext_search_right(inode, path, &ar.lright, &ar.pright);
if (err)
goto out2;
/*
* See if request is beyond maximum number of blocks we can have in
@ -2368,10 +2431,21 @@ int ext4_ext_get_blocks(handle_t *handle, struct inode *inode,
newex.ee_len = cpu_to_le16(max_blocks);
err = ext4_ext_check_overlap(inode, &newex, path);
if (err)
allocated = le16_to_cpu(newex.ee_len);
allocated = ext4_ext_get_actual_len(&newex);
else
allocated = max_blocks;
newblock = ext4_new_blocks(handle, inode, goal, &allocated, &err);
/* allocate new block */
ar.inode = inode;
ar.goal = ext4_ext_find_goal(inode, path, iblock);
ar.logical = iblock;
ar.len = allocated;
if (S_ISREG(inode->i_mode))
ar.flags = EXT4_MB_HINT_DATA;
else
/* disable in-core preallocation for non-regular files */
ar.flags = 0;
newblock = ext4_mb_new_blocks(handle, &ar, &err);
if (!newblock)
goto out2;
ext_debug("allocate new block: goal %llu, found %llu/%lu\n",
@ -2379,14 +2453,17 @@ int ext4_ext_get_blocks(handle_t *handle, struct inode *inode,
/* try to insert new extent into found leaf and return */
ext4_ext_store_pblock(&newex, newblock);
newex.ee_len = cpu_to_le16(allocated);
newex.ee_len = cpu_to_le16(ar.len);
if (create == EXT4_CREATE_UNINITIALIZED_EXT) /* Mark uninitialized */
ext4_ext_mark_uninitialized(&newex);
err = ext4_ext_insert_extent(handle, inode, path, &newex);
if (err) {
/* free data blocks we just allocated */
/* not a good idea to call discard here directly,
* but otherwise we'd need to call it every free() */
ext4_mb_discard_inode_preallocations(inode);
ext4_free_blocks(handle, inode, ext_pblock(&newex),
le16_to_cpu(newex.ee_len));
ext4_ext_get_actual_len(&newex), 0);
goto out2;
}
@ -2395,6 +2472,7 @@ int ext4_ext_get_blocks(handle_t *handle, struct inode *inode,
/* previous routine could use block we allocated */
newblock = ext_pblock(&newex);
allocated = ext4_ext_get_actual_len(&newex);
outnew:
__set_bit(BH_New, &bh_result->b_state);
@ -2414,8 +2492,6 @@ out2:
ext4_ext_drop_refs(path);
kfree(path);
}
mutex_unlock(&EXT4_I(inode)->truncate_mutex);
return err ? err : allocated;
}
@ -2423,7 +2499,7 @@ void ext4_ext_truncate(struct inode * inode, struct page *page)
{
struct address_space *mapping = inode->i_mapping;
struct super_block *sb = inode->i_sb;
unsigned long last_block;
ext4_lblk_t last_block;
handle_t *handle;
int err = 0;
@ -2445,9 +2521,11 @@ void ext4_ext_truncate(struct inode * inode, struct page *page)
if (page)
ext4_block_truncate_page(handle, page, mapping, inode->i_size);
mutex_lock(&EXT4_I(inode)->truncate_mutex);
down_write(&EXT4_I(inode)->i_data_sem);
ext4_ext_invalidate_cache(inode);
ext4_mb_discard_inode_preallocations(inode);
/*
* TODO: optimization is possible here.
* Probably we need not scan at all,
@ -2481,7 +2559,7 @@ out_stop:
if (inode->i_nlink)
ext4_orphan_del(handle, inode);
mutex_unlock(&EXT4_I(inode)->truncate_mutex);
up_write(&EXT4_I(inode)->i_data_sem);
ext4_journal_stop(handle);
}
@ -2516,7 +2594,8 @@ int ext4_ext_writepage_trans_blocks(struct inode *inode, int num)
long ext4_fallocate(struct inode *inode, int mode, loff_t offset, loff_t len)
{
handle_t *handle;
ext4_fsblk_t block, max_blocks;
ext4_lblk_t block;
unsigned long max_blocks;
ext4_fsblk_t nblocks = 0;
int ret = 0;
int ret2 = 0;
@ -2544,6 +2623,7 @@ long ext4_fallocate(struct inode *inode, int mode, loff_t offset, loff_t len)
* modify 1 super block, 1 block bitmap and 1 group descriptor.
*/
credits = EXT4_DATA_TRANS_BLOCKS(inode->i_sb) + 3;
down_write((&EXT4_I(inode)->i_data_sem));
retry:
while (ret >= 0 && ret < max_blocks) {
block = block + ret;
@ -2557,12 +2637,12 @@ retry:
ret = ext4_ext_get_blocks(handle, inode, block,
max_blocks, &map_bh,
EXT4_CREATE_UNINITIALIZED_EXT, 0);
WARN_ON(!ret);
if (!ret) {
WARN_ON(ret <= 0);
if (ret <= 0) {
ext4_error(inode->i_sb, "ext4_fallocate",
"ext4_ext_get_blocks returned 0! inode#%lu"
", block=%llu, max_blocks=%llu",
inode->i_ino, block, max_blocks);
"ext4_ext_get_blocks returned error: "
"inode#%lu, block=%u, max_blocks=%lu",
inode->i_ino, block, max_blocks);
ret = -EIO;
ext4_mark_inode_dirty(handle, inode);
ret2 = ext4_journal_stop(handle);
@ -2600,6 +2680,7 @@ retry:
if (ret == -ENOSPC && ext4_should_retry_alloc(inode->i_sb, &retries))
goto retry;
up_write((&EXT4_I(inode)->i_data_sem));
/*
* Time to update the file size.
* Update only when preallocation was requested beyond the file size.

23
fs/ext4/file.c
View file

@ -37,9 +37,9 @@ static int ext4_release_file (struct inode * inode, struct file * filp)
if ((filp->f_mode & FMODE_WRITE) &&
(atomic_read(&inode->i_writecount) == 1))
{
mutex_lock(&EXT4_I(inode)->truncate_mutex);
down_write(&EXT4_I(inode)->i_data_sem);
ext4_discard_reservation(inode);
mutex_unlock(&EXT4_I(inode)->truncate_mutex);
up_write(&EXT4_I(inode)->i_data_sem);
}
if (is_dx(inode) && filp->private_data)
ext4_htree_free_dir_info(filp->private_data);
@ -56,8 +56,25 @@ ext4_file_write(struct kiocb *iocb, const struct iovec *iov,
ssize_t ret;
int err;
ret = generic_file_aio_write(iocb, iov, nr_segs, pos);
/*
* If we have encountered a bitmap-format file, the size limit
* is smaller than s_maxbytes, which is for extent-mapped files.
*/
if (!(EXT4_I(inode)->i_flags & EXT4_EXTENTS_FL)) {
struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
size_t length = iov_length(iov, nr_segs);
if (pos > sbi->s_bitmap_maxbytes)
return -EFBIG;
if (pos + length > sbi->s_bitmap_maxbytes) {
nr_segs = iov_shorten((struct iovec *)iov, nr_segs,
sbi->s_bitmap_maxbytes - pos);
}
}
ret = generic_file_aio_write(iocb, iov, nr_segs, pos);
/*
* Skip flushing if there was an error, or if nothing was written.
*/

8
fs/ext4/group.h
View file

@ -14,14 +14,16 @@ extern __le16 ext4_group_desc_csum(struct ext4_sb_info *sbi, __u32 group,
extern int ext4_group_desc_csum_verify(struct ext4_sb_info *sbi, __u32 group,
struct ext4_group_desc *gdp);
struct buffer_head *read_block_bitmap(struct super_block *sb,
unsigned int block_group);
ext4_group_t block_group);
extern unsigned ext4_init_block_bitmap(struct super_block *sb,
struct buffer_head *bh, int group,
struct buffer_head *bh,
ext4_group_t group,
struct ext4_group_desc *desc);
#define ext4_free_blocks_after_init(sb, group, desc) \
ext4_init_block_bitmap(sb, NULL, group, desc)
extern unsigned ext4_init_inode_bitmap(struct super_block *sb,
struct buffer_head *bh, int group,
struct buffer_head *bh,
ext4_group_t group,
struct ext4_group_desc *desc);
extern void mark_bitmap_end(int start_bit, int end_bit, char *bitmap);
#endif /* _LINUX_EXT4_GROUP_H */

141
fs/ext4/ialloc.c
View file

@ -64,8 +64,8 @@ void mark_bitmap_end(int start_bit, int end_bit, char *bitmap)
}
/* Initializes an uninitialized inode bitmap */
unsigned ext4_init_inode_bitmap(struct super_block *sb,
struct buffer_head *bh, int block_group,
unsigned ext4_init_inode_bitmap(struct super_block *sb, struct buffer_head *bh,
ext4_group_t block_group,
struct ext4_group_desc *gdp)
{
struct ext4_sb_info *sbi = EXT4_SB(sb);
@ -75,7 +75,7 @@ unsigned ext4_init_inode_bitmap(struct super_block *sb,
/* If checksum is bad mark all blocks and inodes use to prevent
* allocation, essentially implementing a per-group read-only flag. */
if (!ext4_group_desc_csum_verify(sbi, block_group, gdp)) {
ext4_error(sb, __FUNCTION__, "Checksum bad for group %u\n",
ext4_error(sb, __FUNCTION__, "Checksum bad for group %lu\n",
block_group);
gdp->bg_free_blocks_count = 0;
gdp->bg_free_inodes_count = 0;
@ -98,7 +98,7 @@ unsigned ext4_init_inode_bitmap(struct super_block *sb,
* Return buffer_head of bitmap on success or NULL.
*/
static struct buffer_head *
read_inode_bitmap(struct super_block * sb, unsigned long block_group)
read_inode_bitmap(struct super_block *sb, ext4_group_t block_group)
{
struct ext4_group_desc *desc;
struct buffer_head *bh = NULL;
@ -152,7 +152,7 @@ void ext4_free_inode (handle_t *handle, struct inode * inode)
unsigned long ino;
struct buffer_head *bitmap_bh = NULL;
struct buffer_head *bh2;
unsigned long block_group;
ext4_group_t block_group;
unsigned long bit;
struct ext4_group_desc * gdp;
struct ext4_super_block * es;
@ -260,12 +260,14 @@ error_return:
* For other inodes, search forward from the parent directory\'s block
* group to find a free inode.
*/
static int find_group_dir(struct super_block *sb, struct inode *parent)
static int find_group_dir(struct super_block *sb, struct inode *parent,
ext4_group_t *best_group)
{
int ngroups = EXT4_SB(sb)->s_groups_count;
ext4_group_t ngroups = EXT4_SB(sb)->s_groups_count;
unsigned int freei, avefreei;
struct ext4_group_desc *desc, *best_desc = NULL;
int group, best_group = -1;
ext4_group_t group;
int ret = -1;
freei = percpu_counter_read_positive(&EXT4_SB(sb)->s_freeinodes_counter);
avefreei = freei / ngroups;
@ -279,11 +281,12 @@ static int find_group_dir(struct super_block *sb, struct inode *parent)
if (!best_desc ||
(le16_to_cpu(desc->bg_free_blocks_count) >
le16_to_cpu(best_desc->bg_free_blocks_count))) {
best_group = group;
*best_group = group;
best_desc = desc;
ret = 0;
}
}
return best_group;
return ret;
}
/*
@ -314,12 +317,13 @@ static int find_group_dir(struct super_block *sb, struct inode *parent)
#define INODE_COST 64
#define BLOCK_COST 256
static int find_group_orlov(struct super_block *sb, struct inode *parent)
static int find_group_orlov(struct super_block *sb, struct inode *parent,
ext4_group_t *group)
{
int parent_group = EXT4_I(parent)->i_block_group;
ext4_group_t parent_group = EXT4_I(parent)->i_block_group;
struct ext4_sb_info *sbi = EXT4_SB(sb);
struct ext4_super_block *es = sbi->s_es;
int ngroups = sbi->s_groups_count;
ext4_group_t ngroups = sbi->s_groups_count;
int inodes_per_group = EXT4_INODES_PER_GROUP(sb);
unsigned int freei, avefreei;
ext4_fsblk_t freeb, avefreeb;
@ -327,7 +331,7 @@ static int find_group_orlov(struct super_block *sb, struct inode *parent)
unsigned int ndirs;
int max_debt, max_dirs, min_inodes;
ext4_grpblk_t min_blocks;
int group = -1, i;
ext4_group_t i;
struct ext4_group_desc *desc;
freei = percpu_counter_read_positive(&sbi->s_freeinodes_counter);
@ -340,13 +344,14 @@ static int find_group_orlov(struct super_block *sb, struct inode *parent)
if ((parent == sb->s_root->d_inode) ||
(EXT4_I(parent)->i_flags & EXT4_TOPDIR_FL)) {
int best_ndir = inodes_per_group;
int best_group = -1;
ext4_group_t grp;
int ret = -1;
get_random_bytes(&group, sizeof(group));
parent_group = (unsigned)group % ngroups;
get_random_bytes(&grp, sizeof(grp));
parent_group = (unsigned)grp % ngroups;
for (i = 0; i < ngroups; i++) {
group = (parent_group + i) % ngroups;
desc = ext4_get_group_desc (sb, group, NULL);
grp = (parent_group + i) % ngroups;
desc = ext4_get_group_desc(sb, grp, NULL);
if (!desc || !desc->bg_free_inodes_count)
continue;
if (le16_to_cpu(desc->bg_used_dirs_count) >= best_ndir)
@ -355,11 +360,12 @@ static int find_group_orlov(struct super_block *sb, struct inode *parent)
continue;
if (le16_to_cpu(desc->bg_free_blocks_count) < avefreeb)
continue;
best_group = group;
*group = grp;
ret = 0;
best_ndir = le16_to_cpu(desc->bg_used_dirs_count);
}
if (best_group >= 0)
return best_group;
if (ret == 0)
return ret;
goto fallback;
}
@ -380,8 +386,8 @@ static int find_group_orlov(struct super_block *sb, struct inode *parent)
max_debt = 1;
for (i = 0; i < ngroups; i++) {
group = (parent_group + i) % ngroups;
desc = ext4_get_group_desc (sb, group, NULL);
*group = (parent_group + i) % ngroups;
desc = ext4_get_group_desc(sb, *group, NULL);
if (!desc || !desc->bg_free_inodes_count)
continue;
if (le16_to_cpu(desc->bg_used_dirs_count) >= max_dirs)
@ -390,17 +396,16 @@ static int find_group_orlov(struct super_block *sb, struct inode *parent)
continue;
if (le16_to_cpu(desc->bg_free_blocks_count) < min_blocks)
continue;
return group;
return 0;
}
fallback:
for (i = 0; i < ngroups; i++) {
group = (parent_group + i) % ngroups;
desc = ext4_get_group_desc (sb, group, NULL);
if (!desc || !desc->bg_free_inodes_count)
continue;
if (le16_to_cpu(desc->bg_free_inodes_count) >= avefreei)
return group;
*group = (parent_group + i) % ngroups;
desc = ext4_get_group_desc(sb, *group, NULL);
if (desc && desc->bg_free_inodes_count &&
le16_to_cpu(desc->bg_free_inodes_count) >= avefreei)
return 0;
}
if (avefreei) {
@ -415,21 +420,22 @@ fallback:
return -1;
}
static int find_group_other(struct super_block *sb, struct inode *parent)
static int find_group_other(struct super_block *sb, struct inode *parent,
ext4_group_t *group)
{
int parent_group = EXT4_I(parent)->i_block_group;
int ngroups = EXT4_SB(sb)->s_groups_count;
ext4_group_t parent_group = EXT4_I(parent)->i_block_group;
ext4_group_t ngroups = EXT4_SB(sb)->s_groups_count;
struct ext4_group_desc *desc;
int group, i;
ext4_group_t i;
/*
* Try to place the inode in its parent directory
*/
group = parent_group;
desc = ext4_get_group_desc (sb, group, NULL);
*group = parent_group;
desc = ext4_get_group_desc(sb, *group, NULL);
if (desc && le16_to_cpu(desc->bg_free_inodes_count) &&
le16_to_cpu(desc->bg_free_blocks_count))
return group;
return 0;
/*
* We're going to place this inode in a different blockgroup from its
@ -440,33 +446,33 @@ static int find_group_other(struct super_block *sb, struct inode *parent)
*
* So add our directory's i_ino into the starting point for the hash.
*/
group = (group + parent->i_ino) % ngroups;
*group = (*group + parent->i_ino) % ngroups;
/*
* Use a quadratic hash to find a group with a free inode and some free
* blocks.
*/
for (i = 1; i < ngroups; i <<= 1) {
group += i;
if (group >= ngroups)
group -= ngroups;
desc = ext4_get_group_desc (sb, group, NULL);
*group += i;
if (*group >= ngroups)
*group -= ngroups;
desc = ext4_get_group_desc(sb, *group, NULL);
if (desc && le16_to_cpu(desc->bg_free_inodes_count) &&
le16_to_cpu(desc->bg_free_blocks_count))
return group;
return 0;
}
/*
* That failed: try linear search for a free inode, even if that group
* has no free blocks.
*/
group = parent_group;
*group = parent_group;
for (i = 0; i < ngroups; i++) {
if (++group >= ngroups)
group = 0;
desc = ext4_get_group_desc (sb, group, NULL);
if (++*group >= ngroups)
*group = 0;
desc = ext4_get_group_desc(sb, *group, NULL);
if (desc && le16_to_cpu(desc->bg_free_inodes_count))
return group;
return 0;
}
return -1;
@ -487,16 +493,17 @@ struct inode *ext4_new_inode(handle_t *handle, struct inode * dir, int mode)
struct super_block *sb;
struct buffer_head *bitmap_bh = NULL;
struct buffer_head *bh2;
int group;
ext4_group_t group = 0;
unsigned long ino = 0;
struct inode * inode;
struct ext4_group_desc * gdp = NULL;
struct ext4_super_block * es;
struct ext4_inode_info *ei;
struct ext4_sb_info *sbi;
int err = 0;
int ret2, err = 0;
struct inode *ret;
int i, free = 0;
ext4_group_t i;
int free = 0;
/* Cannot create files in a deleted directory */
if (!dir || !dir->i_nlink)
@ -512,14 +519,14 @@ struct inode *ext4_new_inode(handle_t *handle, struct inode * dir, int mode)
es = sbi->s_es;
if (S_ISDIR(mode)) {
if (test_opt (sb, OLDALLOC))
group = find_group_dir(sb, dir);
ret2 = find_group_dir(sb, dir, &group);
else
group = find_group_orlov(sb, dir);
ret2 = find_group_orlov(sb, dir, &group);
} else
group = find_group_other(sb, dir);
ret2 = find_group_other(sb, dir, &group);
err = -ENOSPC;
if (group == -1)
if (ret2 == -1)
goto out;
for (i = 0; i < sbi->s_groups_count; i++) {
@ -583,7 +590,7 @@ got:
ino > EXT4_INODES_PER_GROUP(sb)) {
ext4_error(sb, __FUNCTION__,
"reserved inode or inode > inodes count - "
"block_group = %d, inode=%lu", group,
"block_group = %lu, inode=%lu", group,
ino + group * EXT4_INODES_PER_GROUP(sb));
err = -EIO;
goto fail;
@ -702,7 +709,6 @@ got:
if (!S_ISDIR(mode))
ei->i_flags &= ~EXT4_DIRSYNC_FL;
ei->i_file_acl = 0;
ei->i_dir_acl = 0;
ei->i_dtime = 0;
ei->i_block_alloc_info = NULL;
ei->i_block_group = group;
@ -741,13 +747,10 @@ got:
if (test_opt(sb, EXTENTS)) {
EXT4_I(inode)->i_flags |= EXT4_EXTENTS_FL;
ext4_ext_tree_init(handle, inode);
if (!EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_EXTENTS)) {
err = ext4_journal_get_write_access(handle, EXT4_SB(sb)->s_sbh);
if (err) goto fail;
EXT4_SET_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_EXTENTS);
BUFFER_TRACE(EXT4_SB(sb)->s_sbh, "call ext4_journal_dirty_metadata");
err = ext4_journal_dirty_metadata(handle, EXT4_SB(sb)->s_sbh);
}
err = ext4_update_incompat_feature(handle, sb,
EXT4_FEATURE_INCOMPAT_EXTENTS);
if (err)
goto fail;
}
ext4_debug("allocating inode %lu\n", inode->i_ino);
@ -777,7 +780,7 @@ fail_drop:
struct inode *ext4_orphan_get(struct super_block *sb, unsigned long ino)
{
unsigned long max_ino = le32_to_cpu(EXT4_SB(sb)->s_es->s_inodes_count);
unsigned long block_group;
ext4_group_t block_group;
int bit;
struct buffer_head *bitmap_bh = NULL;
struct inode *inode = NULL;
@ -833,7 +836,7 @@ unsigned long ext4_count_free_inodes (struct super_block * sb)
{
unsigned long desc_count;
struct ext4_group_desc *gdp;
int i;
ext4_group_t i;
#ifdef EXT4FS_DEBUG
struct ext4_super_block *es;
unsigned long bitmap_count, x;
@ -854,7 +857,7 @@ unsigned long ext4_count_free_inodes (struct super_block * sb)
continue;
x = ext4_count_free(bitmap_bh, EXT4_INODES_PER_GROUP(sb) / 8);
printk("group %d: stored = %d, counted = %lu\n",
printk(KERN_DEBUG "group %lu: stored = %d, counted = %lu\n",
i, le16_to_cpu(gdp->bg_free_inodes_count), x);
bitmap_count += x;
}
@ -879,7 +882,7 @@ unsigned long ext4_count_free_inodes (struct super_block * sb)
unsigned long ext4_count_dirs (struct super_block * sb)
{
unsigned long count = 0;
int i;
ext4_group_t i;
for (i = 0; i < EXT4_SB(sb)->s_groups_count; i++) {
struct ext4_group_desc *gdp = ext4_get_group_desc (sb, i, NULL);

360
fs/ext4/inode.c
View file

@ -105,7 +105,7 @@ int ext4_forget(handle_t *handle, int is_metadata, struct inode *inode,
*/
static unsigned long blocks_for_truncate(struct inode *inode)
{
unsigned long needed;
ext4_lblk_t needed;
needed = inode->i_blocks >> (inode->i_sb->s_blocksize_bits - 9);
@ -243,13 +243,6 @@ static inline void add_chain(Indirect *p, struct buffer_head *bh, __le32 *v)
p->bh = bh;
}
static int verify_chain(Indirect *from, Indirect *to)
{
while (from <= to && from->key == *from->p)
from++;
return (from > to);
}
/**
* ext4_block_to_path - parse the block number into array of offsets
* @inode: inode in question (we are only interested in its superblock)
@ -282,7 +275,8 @@ static int verify_chain(Indirect *from, Indirect *to)
*/
static int ext4_block_to_path(struct inode *inode,
long i_block, int offsets[4], int *boundary)
ext4_lblk_t i_block,
ext4_lblk_t offsets[4], int *boundary)
{
int ptrs = EXT4_ADDR_PER_BLOCK(inode->i_sb);
int ptrs_bits = EXT4_ADDR_PER_BLOCK_BITS(inode->i_sb);
@ -313,7 +307,10 @@ static int ext4_block_to_path(struct inode *inode,
offsets[n++] = i_block & (ptrs - 1);
final = ptrs;
} else {
ext4_warning(inode->i_sb, "ext4_block_to_path", "block > big");
ext4_warning(inode->i_sb, "ext4_block_to_path",
"block %lu > max",
i_block + direct_blocks +
indirect_blocks + double_blocks);
}
if (boundary)
*boundary = final - 1 - (i_block & (ptrs - 1));
@ -344,12 +341,14 @@ static int ext4_block_to_path(struct inode *inode,
* (pointer to last triple returned, *@err == 0)
* or when it gets an IO error reading an indirect block
* (ditto, *@err == -EIO)
* or when it notices that chain had been changed while it was reading
* (ditto, *@err == -EAGAIN)
* or when it reads all @depth-1 indirect blocks successfully and finds
* the whole chain, all way to the data (returns %NULL, *err == 0).
*
* Need to be called with
* down_read(&EXT4_I(inode)->i_data_sem)
*/
static Indirect *ext4_get_branch(struct inode *inode, int depth, int *offsets,
static Indirect *ext4_get_branch(struct inode *inode, int depth,
ext4_lblk_t *offsets,
Indirect chain[4], int *err)
{
struct super_block *sb = inode->i_sb;
@ -365,9 +364,6 @@ static Indirect *ext4_get_branch(struct inode *inode, int depth, int *offsets,
bh = sb_bread(sb, le32_to_cpu(p->key));
if (!bh)
goto failure;
/* Reader: pointers */
if (!verify_chain(chain, p))
goto changed;
add_chain(++p, bh, (__le32*)bh->b_data + *++offsets);
/* Reader: end */
if (!p->key)
@ -375,10 +371,6 @@ static Indirect *ext4_get_branch(struct inode *inode, int depth, int *offsets,
}
return NULL;
changed:
brelse(bh);
*err = -EAGAIN;
goto no_block;
failure:
*err = -EIO;
no_block:
@ -445,7 +437,7 @@ static ext4_fsblk_t ext4_find_near(struct inode *inode, Indirect *ind)
* stores it in *@goal and returns zero.
*/
static ext4_fsblk_t ext4_find_goal(struct inode *inode, long block,
static ext4_fsblk_t ext4_find_goal(struct inode *inode, ext4_lblk_t block,
Indirect chain[4], Indirect *partial)
{
struct ext4_block_alloc_info *block_i;
@ -559,7 +551,7 @@ static int ext4_alloc_blocks(handle_t *handle, struct inode *inode,
return ret;
failed_out:
for (i = 0; i <index; i++)
ext4_free_blocks(handle, inode, new_blocks[i], 1);
ext4_free_blocks(handle, inode, new_blocks[i], 1, 0);
return ret;
}
@ -590,7 +582,7 @@ failed_out:
*/
static int ext4_alloc_branch(handle_t *handle, struct inode *inode,
int indirect_blks, int *blks, ext4_fsblk_t goal,
int *offsets, Indirect *branch)
ext4_lblk_t *offsets, Indirect *branch)
{
int blocksize = inode->i_sb->s_blocksize;
int i, n = 0;
@ -658,9 +650,9 @@ failed:
ext4_journal_forget(handle, branch[i].bh);
}
for (i = 0; i <indirect_blks; i++)
ext4_free_blocks(handle, inode, new_blocks[i], 1);
ext4_free_blocks(handle, inode, new_blocks[i], 1, 0);
ext4_free_blocks(handle, inode, new_blocks[i], num);
ext4_free_blocks(handle, inode, new_blocks[i], num, 0);
return err;
}
@ -680,7 +672,7 @@ failed:
* chain to new block and return 0.
*/
static int ext4_splice_branch(handle_t *handle, struct inode *inode,
long block, Indirect *where, int num, int blks)
ext4_lblk_t block, Indirect *where, int num, int blks)
{
int i;
int err = 0;
@ -757,9 +749,10 @@ err_out:
for (i = 1; i <= num; i++) {
BUFFER_TRACE(where[i].bh, "call jbd2_journal_forget");
ext4_journal_forget(handle, where[i].bh);
ext4_free_blocks(handle,inode,le32_to_cpu(where[i-1].key),1);
ext4_free_blocks(handle, inode,
le32_to_cpu(where[i-1].key), 1, 0);
}
ext4_free_blocks(handle, inode, le32_to_cpu(where[num].key), blks);
ext4_free_blocks(handle, inode, le32_to_cpu(where[num].key), blks, 0);
return err;
}
@ -782,14 +775,19 @@ err_out:
* return > 0, # of blocks mapped or allocated.
* return = 0, if plain lookup failed.
* return < 0, error case.
*
*
* Need to be called with
* down_read(&EXT4_I(inode)->i_data_sem) if not allocating file system block
* (ie, create is zero). Otherwise down_write(&EXT4_I(inode)->i_data_sem)
*/
int ext4_get_blocks_handle(handle_t *handle, struct inode *inode,
sector_t iblock, unsigned long maxblocks,
ext4_lblk_t iblock, unsigned long maxblocks,
struct buffer_head *bh_result,
int create, int extend_disksize)
{
int err = -EIO;
int offsets[4];
ext4_lblk_t offsets[4];
Indirect chain[4];
Indirect *partial;
ext4_fsblk_t goal;
@ -803,7 +801,8 @@ int ext4_get_blocks_handle(handle_t *handle, struct inode *inode,
J_ASSERT(!(EXT4_I(inode)->i_flags & EXT4_EXTENTS_FL));
J_ASSERT(handle != NULL || create == 0);
depth = ext4_block_to_path(inode,iblock,offsets,&blocks_to_boundary);
depth = ext4_block_to_path(inode, iblock, offsets,
&blocks_to_boundary);
if (depth == 0)
goto out;
@ -819,18 +818,6 @@ int ext4_get_blocks_handle(handle_t *handle, struct inode *inode,
while (count < maxblocks && count <= blocks_to_boundary) {
ext4_fsblk_t blk;
if (!verify_chain(chain, partial)) {
/*
* Indirect block might be removed by
* truncate while we were reading it.
* Handling of that case: forget what we've
* got now. Flag the err as EAGAIN, so it
* will reread.
*/
err = -EAGAIN;
count = 0;
break;
}
blk = le32_to_cpu(*(chain[depth-1].p + count));
if (blk == first_block + count)
@ -838,44 +825,13 @@ int ext4_get_blocks_handle(handle_t *handle, struct inode *inode,
else
break;
}
if (err != -EAGAIN)
goto got_it;
goto got_it;
}
/* Next simple case - plain lookup or failed read of indirect block */
if (!create || err == -EIO)
goto cleanup;
mutex_lock(&ei->truncate_mutex);
/*
* If the indirect block is missing while we are reading
* the chain(ext4_get_branch() returns -EAGAIN err), or
* if the chain has been changed after we grab the semaphore,
* (either because another process truncated this branch, or
* another get_block allocated this branch) re-grab the chain to see if
* the request block has been allocated or not.
*
* Since we already block the truncate/other get_block
* at this point, we will have the current copy of the chain when we
* splice the branch into the tree.
*/
if (err == -EAGAIN || !verify_chain(chain, partial)) {
while (partial > chain) {
brelse(partial->bh);
partial--;
}
partial = ext4_get_branch(inode, depth, offsets, chain, &err);
if (!partial) {
count++;
mutex_unlock(&ei->truncate_mutex);
if (err)
goto cleanup;
clear_buffer_new(bh_result);
goto got_it;
}
}
/*
* Okay, we need to do block allocation. Lazily initialize the block
* allocation info here if necessary
@ -911,13 +867,12 @@ int ext4_get_blocks_handle(handle_t *handle, struct inode *inode,
err = ext4_splice_branch(handle, inode, iblock,
partial, indirect_blks, count);
/*
* i_disksize growing is protected by truncate_mutex. Don't forget to
* i_disksize growing is protected by i_data_sem. Don't forget to
* protect it if you're about to implement concurrent
* ext4_get_block() -bzzz
*/
if (!err && extend_disksize && inode->i_size > ei->i_disksize)
ei->i_disksize = inode->i_size;
mutex_unlock(&ei->truncate_mutex);
if (err)
goto cleanup;
@ -942,6 +897,47 @@ out:
#define DIO_CREDITS (EXT4_RESERVE_TRANS_BLOCKS + 32)
int ext4_get_blocks_wrap(handle_t *handle, struct inode *inode, sector_t block,
unsigned long max_blocks, struct buffer_head *bh,
int create, int extend_disksize)
{
int retval;
/*
* Try to see if we can get the block without requesting
* for new file system block.
*/
down_read((&EXT4_I(inode)->i_data_sem));
if (EXT4_I(inode)->i_flags & EXT4_EXTENTS_FL) {
retval = ext4_ext_get_blocks(handle, inode, block, max_blocks,
bh, 0, 0);
} else {
retval = ext4_get_blocks_handle(handle,
inode, block, max_blocks, bh, 0, 0);
}
up_read((&EXT4_I(inode)->i_data_sem));
if (!create || (retval > 0))
return retval;
/*
* We need to allocate new blocks which will result
* in i_data update
*/
down_write((&EXT4_I(inode)->i_data_sem));
/*
* We need to check for EXT4 here because migrate
* could have changed the inode type in between
*/
if (EXT4_I(inode)->i_flags & EXT4_EXTENTS_FL) {
retval = ext4_ext_get_blocks(handle, inode, block, max_blocks,
bh, create, extend_disksize);
} else {
retval = ext4_get_blocks_handle(handle, inode, block,
max_blocks, bh, create, extend_disksize);
}
up_write((&EXT4_I(inode)->i_data_sem));
return retval;
}
static int ext4_get_block(struct inode *inode, sector_t iblock,
struct buffer_head *bh_result, int create)
{
@ -996,7 +992,7 @@ get_block:
* `handle' can be NULL if create is zero
*/
struct buffer_head *ext4_getblk(handle_t *handle, struct inode *inode,
long block, int create, int *errp)
ext4_lblk_t block, int create, int *errp)
{
struct buffer_head dummy;
int fatal = 0, err;
@ -1063,7 +1059,7 @@ err:
}
struct buffer_head *ext4_bread(handle_t *handle, struct inode *inode,
int block, int create, int *err)
ext4_lblk_t block, int create, int *err)
{
struct buffer_head * bh;
@ -1446,7 +1442,7 @@ static int jbd2_journal_dirty_data_fn(handle_t *handle, struct buffer_head *bh)
* ext4_file_write() -> generic_file_write() -> __alloc_pages() -> ...
*
* Same applies to ext4_get_block(). We will deadlock on various things like
* lock_journal and i_truncate_mutex.
* lock_journal and i_data_sem
*
* Setting PF_MEMALLOC here doesn't work - too many internal memory
* allocations fail.
@ -1828,7 +1824,8 @@ int ext4_block_truncate_page(handle_t *handle, struct page *page,
{
ext4_fsblk_t index = from >> PAGE_CACHE_SHIFT;
unsigned offset = from & (PAGE_CACHE_SIZE-1);
unsigned blocksize, iblock, length, pos;
unsigned blocksize, length, pos;
ext4_lblk_t iblock;
struct inode *inode = mapping->host;
struct buffer_head *bh;
int err = 0;
@ -1964,7 +1961,7 @@ static inline int all_zeroes(__le32 *p, __le32 *q)
* (no partially truncated stuff there). */
static Indirect *ext4_find_shared(struct inode *inode, int depth,
int offsets[4], Indirect chain[4], __le32 *top)
ext4_lblk_t offsets[4], Indirect chain[4], __le32 *top)
{
Indirect *partial, *p;
int k, err;
@ -2048,15 +2045,15 @@ static void ext4_clear_blocks(handle_t *handle, struct inode *inode,
for (p = first; p < last; p++) {
u32 nr = le32_to_cpu(*p);
if (nr) {
struct buffer_head *bh;
struct buffer_head *tbh;
*p = 0;
bh = sb_find_get_block(inode->i_sb, nr);
ext4_forget(handle, 0, inode, bh, nr);
tbh = sb_find_get_block(inode->i_sb, nr);
ext4_forget(handle, 0, inode, tbh, nr);
}
}
ext4_free_blocks(handle, inode, block_to_free, count);
ext4_free_blocks(handle, inode, block_to_free, count, 0);
}
/**
@ -2229,7 +2226,7 @@ static void ext4_free_branches(handle_t *handle, struct inode *inode,
ext4_journal_test_restart(handle, inode);
}
ext4_free_blocks(handle, inode, nr, 1);
ext4_free_blocks(handle, inode, nr, 1, 1);
if (parent_bh) {
/*
@ -2289,12 +2286,12 @@ void ext4_truncate(struct inode *inode)
__le32 *i_data = ei->i_data;
int addr_per_block = EXT4_ADDR_PER_BLOCK(inode->i_sb);
struct address_space *mapping = inode->i_mapping;
int offsets[4];
ext4_lblk_t offsets[4];
Indirect chain[4];
Indirect *partial;
__le32 nr = 0;
int n;
long last_block;
ext4_lblk_t last_block;
unsigned blocksize = inode->i_sb->s_blocksize;
struct page *page;
@ -2320,8 +2317,10 @@ void ext4_truncate(struct inode *inode)
return;
}
if (EXT4_I(inode)->i_flags & EXT4_EXTENTS_FL)
return ext4_ext_truncate(inode, page);
if (EXT4_I(inode)->i_flags & EXT4_EXTENTS_FL) {
ext4_ext_truncate(inode, page);
return;
}
handle = start_transaction(inode);
if (IS_ERR(handle)) {
@ -2369,7 +2368,7 @@ void ext4_truncate(struct inode *inode)
* From here we block out all ext4_get_block() callers who want to
* modify the block allocation tree.
*/
mutex_lock(&ei->truncate_mutex);
down_write(&ei->i_data_sem);
if (n == 1) { /* direct blocks */
ext4_free_data(handle, inode, NULL, i_data+offsets[0],
@ -2433,7 +2432,7 @@ do_indirects:
ext4_discard_reservation(inode);
mutex_unlock(&ei->truncate_mutex);
up_write(&ei->i_data_sem);
inode->i_mtime = inode->i_ctime = ext4_current_time(inode);
ext4_mark_inode_dirty(handle, inode);
@ -2460,7 +2459,8 @@ out_stop:
static ext4_fsblk_t ext4_get_inode_block(struct super_block *sb,
unsigned long ino, struct ext4_iloc *iloc)
{
unsigned long desc, group_desc, block_group;
unsigned long desc, group_desc;
ext4_group_t block_group;
unsigned long offset;
ext4_fsblk_t block;
struct buffer_head *bh;
@ -2547,7 +2547,7 @@ static int __ext4_get_inode_loc(struct inode *inode,
struct ext4_group_desc *desc;
int inodes_per_buffer;
int inode_offset, i;
int block_group;
ext4_group_t block_group;
int start;
block_group = (inode->i_ino - 1) /
@ -2660,6 +2660,28 @@ void ext4_get_inode_flags(struct ext4_inode_info *ei)
if (flags & S_DIRSYNC)
ei->i_flags |= EXT4_DIRSYNC_FL;
}
static blkcnt_t ext4_inode_blocks(struct ext4_inode *raw_inode,
struct ext4_inode_info *ei)
{
blkcnt_t i_blocks ;
struct inode *inode = &(ei->vfs_inode);
struct super_block *sb = inode->i_sb;
if (EXT4_HAS_RO_COMPAT_FEATURE(sb,
EXT4_FEATURE_RO_COMPAT_HUGE_FILE)) {
/* we are using combined 48 bit field */
i_blocks = ((u64)le16_to_cpu(raw_inode->i_blocks_high)) << 32 |
le32_to_cpu(raw_inode->i_blocks_lo);
if (ei->i_flags & EXT4_HUGE_FILE_FL) {
/* i_blocks represent file system block size */
return i_blocks << (inode->i_blkbits - 9);
} else {
return i_blocks;
}
} else {
return le32_to_cpu(raw_inode->i_blocks_lo);
}
}
void ext4_read_inode(struct inode * inode)
{
@ -2687,7 +2709,6 @@ void ext4_read_inode(struct inode * inode)
inode->i_gid |= le16_to_cpu(raw_inode->i_gid_high) << 16;
}
inode->i_nlink = le16_to_cpu(raw_inode->i_links_count);
inode->i_size = le32_to_cpu(raw_inode->i_size);
ei->i_state = 0;
ei->i_dir_start_lookup = 0;
@ -2709,19 +2730,15 @@ void ext4_read_inode(struct inode * inode)
* recovery code: that's fine, we're about to complete
* the process of deleting those. */
}
inode->i_blocks = le32_to_cpu(raw_inode->i_blocks);
ei->i_flags = le32_to_cpu(raw_inode->i_flags);
ei->i_file_acl = le32_to_cpu(raw_inode->i_file_acl);
inode->i_blocks = ext4_inode_blocks(raw_inode, ei);
ei->i_file_acl = le32_to_cpu(raw_inode->i_file_acl_lo);
if (EXT4_SB(inode->i_sb)->s_es->s_creator_os !=
cpu_to_le32(EXT4_OS_HURD))
cpu_to_le32(EXT4_OS_HURD)) {
ei->i_file_acl |=
((__u64)le16_to_cpu(raw_inode->i_file_acl_high)) << 32;
if (!S_ISREG(inode->i_mode)) {
ei->i_dir_acl = le32_to_cpu(raw_inode->i_dir_acl);
} else {
inode->i_size |=
((__u64)le32_to_cpu(raw_inode->i_size_high)) << 32;
}
inode->i_size = ext4_isize(raw_inode);
ei->i_disksize = inode->i_size;
inode->i_generation = le32_to_cpu(raw_inode->i_generation);
ei->i_block_group = iloc.block_group;
@ -2765,6 +2782,13 @@ void ext4_read_inode(struct inode * inode)
EXT4_INODE_GET_XTIME(i_atime, inode, raw_inode);
EXT4_EINODE_GET_XTIME(i_crtime, ei, raw_inode);
inode->i_version = le32_to_cpu(raw_inode->i_disk_version);
if (EXT4_INODE_SIZE(inode->i_sb) > EXT4_GOOD_OLD_INODE_SIZE) {
if (EXT4_FITS_IN_INODE(raw_inode, ei, i_version_hi))
inode->i_version |=
(__u64)(le32_to_cpu(raw_inode->i_version_hi)) << 32;
}
if (S_ISREG(inode->i_mode)) {
inode->i_op = &ext4_file_inode_operations;
inode->i_fop = &ext4_file_operations;
@ -2797,6 +2821,55 @@ bad_inode:
return;
}
static int ext4_inode_blocks_set(handle_t *handle,
struct ext4_inode *raw_inode,
struct ext4_inode_info *ei)
{
struct inode *inode = &(ei->vfs_inode);
u64 i_blocks = inode->i_blocks;
struct super_block *sb = inode->i_sb;
int err = 0;
if (i_blocks <= ~0U) {
/*
* i_blocks can be represnted in a 32 bit variable
* as multiple of 512 bytes
*/
raw_inode->i_blocks_lo = cpu_to_le32(i_blocks);
raw_inode->i_blocks_high = 0;
ei->i_flags &= ~EXT4_HUGE_FILE_FL;
} else if (i_blocks <= 0xffffffffffffULL) {
/*
* i_blocks can be represented in a 48 bit variable
* as multiple of 512 bytes
*/
err = ext4_update_rocompat_feature(handle, sb,
EXT4_FEATURE_RO_COMPAT_HUGE_FILE);
if (err)
goto err_out;
/* i_block is stored in the split 48 bit fields */
raw_inode->i_blocks_lo = cpu_to_le32(i_blocks);
raw_inode->i_blocks_high = cpu_to_le16(i_blocks >> 32);
ei->i_flags &= ~EXT4_HUGE_FILE_FL;
} else {
/*
* i_blocks should be represented in a 48 bit variable
* as multiple of file system block size
*/
err = ext4_update_rocompat_feature(handle, sb,
EXT4_FEATURE_RO_COMPAT_HUGE_FILE);
if (err)
goto err_out;
ei->i_flags |= EXT4_HUGE_FILE_FL;
/* i_block is stored in file system block size */
i_blocks = i_blocks >> (inode->i_blkbits - 9);
raw_inode->i_blocks_lo = cpu_to_le32(i_blocks);
raw_inode->i_blocks_high = cpu_to_le16(i_blocks >> 32);
}
err_out:
return err;
}
/*
* Post the struct inode info into an on-disk inode location in the
* buffer-cache. This gobbles the caller's reference to the
@ -2845,47 +2918,42 @@ static int ext4_do_update_inode(handle_t *handle,
raw_inode->i_gid_high = 0;
}
raw_inode->i_links_count = cpu_to_le16(inode->i_nlink);
raw_inode->i_size = cpu_to_le32(ei->i_disksize);
EXT4_INODE_SET_XTIME(i_ctime, inode, raw_inode);
EXT4_INODE_SET_XTIME(i_mtime, inode, raw_inode);
EXT4_INODE_SET_XTIME(i_atime, inode, raw_inode);
EXT4_EINODE_SET_XTIME(i_crtime, ei, raw_inode);
raw_inode->i_blocks = cpu_to_le32(inode->i_blocks);
if (ext4_inode_blocks_set(handle, raw_inode, ei))
goto out_brelse;
raw_inode->i_dtime = cpu_to_le32(ei->i_dtime);
raw_inode->i_flags = cpu_to_le32(ei->i_flags);
if (EXT4_SB(inode->i_sb)->s_es->s_creator_os !=
cpu_to_le32(EXT4_OS_HURD))
raw_inode->i_file_acl_high =
cpu_to_le16(ei->i_file_acl >> 32);
raw_inode->i_file_acl = cpu_to_le32(ei->i_file_acl);
if (!S_ISREG(inode->i_mode)) {
raw_inode->i_dir_acl = cpu_to_le32(ei->i_dir_acl);
} else {
raw_inode->i_size_high =
cpu_to_le32(ei->i_disksize >> 32);
if (ei->i_disksize > 0x7fffffffULL) {
struct super_block *sb = inode->i_sb;
if (!EXT4_HAS_RO_COMPAT_FEATURE(sb,
EXT4_FEATURE_RO_COMPAT_LARGE_FILE) ||
EXT4_SB(sb)->s_es->s_rev_level ==
cpu_to_le32(EXT4_GOOD_OLD_REV)) {
/* If this is the first large file
* created, add a flag to the superblock.
*/
err = ext4_journal_get_write_access(handle,
EXT4_SB(sb)->s_sbh);
if (err)
goto out_brelse;
ext4_update_dynamic_rev(sb);
EXT4_SET_RO_COMPAT_FEATURE(sb,
raw_inode->i_file_acl_lo = cpu_to_le32(ei->i_file_acl);
ext4_isize_set(raw_inode, ei->i_disksize);
if (ei->i_disksize > 0x7fffffffULL) {
struct super_block *sb = inode->i_sb;
if (!EXT4_HAS_RO_COMPAT_FEATURE(sb,
EXT4_FEATURE_RO_COMPAT_LARGE_FILE) ||
EXT4_SB(sb)->s_es->s_rev_level ==
cpu_to_le32(EXT4_GOOD_OLD_REV)) {
/* If this is the first large file
* created, add a flag to the superblock.
*/
err = ext4_journal_get_write_access(handle,
EXT4_SB(sb)->s_sbh);
if (err)
goto out_brelse;
ext4_update_dynamic_rev(sb);
EXT4_SET_RO_COMPAT_FEATURE(sb,
EXT4_FEATURE_RO_COMPAT_LARGE_FILE);
sb->s_dirt = 1;
handle->h_sync = 1;
err = ext4_journal_dirty_metadata(handle,
EXT4_SB(sb)->s_sbh);
}
sb->s_dirt = 1;
handle->h_sync = 1;
err = ext4_journal_dirty_metadata(handle,
EXT4_SB(sb)->s_sbh);
}
}
raw_inode->i_generation = cpu_to_le32(inode->i_generation);
@ -2903,8 +2971,14 @@ static int ext4_do_update_inode(handle_t *handle,
} else for (block = 0; block < EXT4_N_BLOCKS; block++)
raw_inode->i_block[block] = ei->i_data[block];
if (ei->i_extra_isize)
raw_inode->i_disk_version = cpu_to_le32(inode->i_version);
if (ei->i_extra_isize) {
if (EXT4_FITS_IN_INODE(raw_inode, ei, i_version_hi))
raw_inode->i_version_hi =
cpu_to_le32(inode->i_version >> 32);
raw_inode->i_extra_isize = cpu_to_le16(ei->i_extra_isize);
}
BUFFER_TRACE(bh, "call ext4_journal_dirty_metadata");
rc = ext4_journal_dirty_metadata(handle, bh);
@ -3024,6 +3098,17 @@ int ext4_setattr(struct dentry *dentry, struct iattr *attr)
ext4_journal_stop(handle);
}
if (attr->ia_valid & ATTR_SIZE) {
if (!(EXT4_I(inode)->i_flags & EXT4_EXTENTS_FL)) {
struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
if (attr->ia_size > sbi->s_bitmap_maxbytes) {
error = -EFBIG;
goto err_out;
}
}
}
if (S_ISREG(inode->i_mode) &&
attr->ia_valid & ATTR_SIZE && attr->ia_size < inode->i_size) {
handle_t *handle;
@ -3120,6 +3205,9 @@ int ext4_mark_iloc_dirty(handle_t *handle,
{
int err = 0;
if (test_opt(inode->i_sb, I_VERSION))
inode_inc_iversion(inode);
/* the do_update_inode consumes one bh->b_count */
get_bh(iloc->bh);
@ -3158,8 +3246,10 @@ ext4_reserve_inode_write(handle_t *handle, struct inode *inode,
* Expand an inode by new_extra_isize bytes.
* Returns 0 on success or negative error number on failure.
*/
int ext4_expand_extra_isize(struct inode *inode, unsigned int new_extra_isize,
struct ext4_iloc iloc, handle_t *handle)
static int ext4_expand_extra_isize(struct inode *inode,
unsigned int new_extra_isize,
struct ext4_iloc iloc,
handle_t *handle)
{
struct ext4_inode *raw_inode;
struct ext4_xattr_ibody_header *header;

7
fs/ext4/ioctl.c
View file

@ -199,7 +199,7 @@ flags_err:
* need to allocate reservation structure for this inode
* before set the window size
*/
mutex_lock(&ei->truncate_mutex);
down_write(&ei->i_data_sem);
if (!ei->i_block_alloc_info)
ext4_init_block_alloc_info(inode);
@ -207,7 +207,7 @@ flags_err:
struct ext4_reserve_window_node *rsv = &ei->i_block_alloc_info->rsv_window_node;
rsv->rsv_goal_size = rsv_window_size;
}
mutex_unlock(&ei->truncate_mutex);
up_write(&ei->i_data_sem);
return 0;
}
case EXT4_IOC_GROUP_EXTEND: {
@ -254,6 +254,9 @@ flags_err:
return err;
}
case EXT4_IOC_MIGRATE:
return ext4_ext_migrate(inode, filp, cmd, arg);
default:
return -ENOTTY;
}

4552
fs/ext4/mballoc.c Normal file
View file

File diff suppressed because it is too large Load diff

560
fs/ext4/migrate.c Normal file
View file

@ -0,0 +1,560 @@
/*
* Copyright IBM Corporation, 2007
* Author Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
*
* This program is free software; you can redistribute it and/or modify it
* under the terms of version 2.1 of the GNU Lesser General Public License
* as published by the Free Software Foundation.
*
* This program is distributed in the hope that it would be useful, but
* WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
*
*/
#include <linux/module.h>
#include <linux/ext4_jbd2.h>
#include <linux/ext4_fs_extents.h>
/*
* The contiguous blocks details which can be
* represented by a single extent
*/
struct list_blocks_struct {
ext4_lblk_t first_block, last_block;
ext4_fsblk_t first_pblock, last_pblock;
};
static int finish_range(handle_t *handle, struct inode *inode,
struct list_blocks_struct *lb)
{
int retval = 0, needed;
struct ext4_extent newext;
struct ext4_ext_path *path;
if (lb->first_pblock == 0)
return 0;
/* Add the extent to temp inode*/
newext.ee_block = cpu_to_le32(lb->first_block);
newext.ee_len = cpu_to_le16(lb->last_block - lb->first_block + 1);
ext4_ext_store_pblock(&newext, lb->first_pblock);
path = ext4_ext_find_extent(inode, lb->first_block, NULL);
if (IS_ERR(path)) {
retval = PTR_ERR(path);
goto err_out;
}
/*
* Calculate the credit needed to inserting this extent
* Since we are doing this in loop we may accumalate extra
* credit. But below we try to not accumalate too much
* of them by restarting the journal.
*/
needed = ext4_ext_calc_credits_for_insert(inode, path);
/*
* Make sure the credit we accumalated is not really high
*/
if (needed && handle->h_buffer_credits >= EXT4_RESERVE_TRANS_BLOCKS) {
retval = ext4_journal_restart(handle, needed);
if (retval)
goto err_out;
}
if (needed) {
retval = ext4_journal_extend(handle, needed);
if (retval != 0) {
/*
* IF not able to extend the journal restart the journal
*/
retval = ext4_journal_restart(handle, needed);
if (retval)
goto err_out;
}
}
retval = ext4_ext_insert_extent(handle, inode, path, &newext);
err_out:
lb->first_pblock = 0;
return retval;
}
static int update_extent_range(handle_t *handle, struct inode *inode,
ext4_fsblk_t pblock, ext4_lblk_t blk_num,
struct list_blocks_struct *lb)
{
int retval;
/*
* See if we can add on to the existing range (if it exists)
*/
if (lb->first_pblock &&
(lb->last_pblock+1 == pblock) &&
(lb->last_block+1 == blk_num)) {
lb->last_pblock = pblock;
lb->last_block = blk_num;
return 0;
}
/*
* Start a new range.
*/
retval = finish_range(handle, inode, lb);
lb->first_pblock = lb->last_pblock = pblock;
lb->first_block = lb->last_block = blk_num;
return retval;
}
static int update_ind_extent_range(handle_t *handle, struct inode *inode,
ext4_fsblk_t pblock, ext4_lblk_t *blk_nump,
struct list_blocks_struct *lb)
{
struct buffer_head *bh;
__le32 *i_data;
int i, retval = 0;
ext4_lblk_t blk_count = *blk_nump;
unsigned long max_entries = inode->i_sb->s_blocksize >> 2;
if (!pblock) {
/* Only update the file block number */
*blk_nump += max_entries;
return 0;
}
bh = sb_bread(inode->i_sb, pblock);
if (!bh)
return -EIO;
i_data = (__le32 *)bh->b_data;
for (i = 0; i < max_entries; i++, blk_count++) {
if (i_data[i]) {
retval = update_extent_range(handle, inode,
le32_to_cpu(i_data[i]),
blk_count, lb);
if (retval)
break;
}
}
/* Update the file block number */
*blk_nump = blk_count;
put_bh(bh);
return retval;
}
static int update_dind_extent_range(handle_t *handle, struct inode *inode,
ext4_fsblk_t pblock, ext4_lblk_t *blk_nump,
struct list_blocks_struct *lb)
{
struct buffer_head *bh;
__le32 *i_data;
int i, retval = 0;
ext4_lblk_t blk_count = *blk_nump;
unsigned long max_entries = inode->i_sb->s_blocksize >> 2;
if (!pblock) {
/* Only update the file block number */
*blk_nump += max_entries * max_entries;
return 0;
}
bh = sb_bread(inode->i_sb, pblock);
if (!bh)
return -EIO;
i_data = (__le32 *)bh->b_data;
for (i = 0; i < max_entries; i++) {
if (i_data[i]) {
retval = update_ind_extent_range(handle, inode,
le32_to_cpu(i_data[i]),
&blk_count, lb);
if (retval)
break;
} else {
/* Only update the file block number */
blk_count += max_entries;
}
}
/* Update the file block number */
*blk_nump = blk_count;
put_bh(bh);
return retval;
}
static int update_tind_extent_range(handle_t *handle, struct inode *inode,
ext4_fsblk_t pblock, ext4_lblk_t *blk_nump,
struct list_blocks_struct *lb)
{
struct buffer_head *bh;
__le32 *i_data;
int i, retval = 0;
ext4_lblk_t blk_count = *blk_nump;
unsigned long max_entries = inode->i_sb->s_blocksize >> 2;
if (!pblock) {
/* Only update the file block number */
*blk_nump += max_entries * max_entries * max_entries;
return 0;
}
bh = sb_bread(inode->i_sb, pblock);
if (!bh)
return -EIO;
i_data = (__le32 *)bh->b_data;
for (i = 0; i < max_entries; i++) {
if (i_data[i]) {
retval = update_dind_extent_range(handle, inode,
le32_to_cpu(i_data[i]),
&blk_count, lb);
if (retval)
break;
} else
/* Only update the file block number */
blk_count += max_entries * max_entries;
}
/* Update the file block number */
*blk_nump = blk_count;
put_bh(bh);
return retval;
}
static int free_dind_blocks(handle_t *handle,
struct inode *inode, __le32 i_data)
{
int i;
__le32 *tmp_idata;
struct buffer_head *bh;
unsigned long max_entries = inode->i_sb->s_blocksize >> 2;
bh = sb_bread(inode->i_sb, le32_to_cpu(i_data));
if (!bh)
return -EIO;
tmp_idata = (__le32 *)bh->b_data;
for (i = 0; i < max_entries; i++) {
if (tmp_idata[i])
ext4_free_blocks(handle, inode,
le32_to_cpu(tmp_idata[i]), 1, 1);
}
put_bh(bh);
ext4_free_blocks(handle, inode, le32_to_cpu(i_data), 1, 1);
return 0;
}
static int free_tind_blocks(handle_t *handle,
struct inode *inode, __le32 i_data)
{
int i, retval = 0;
__le32 *tmp_idata;
struct buffer_head *bh;
unsigned long max_entries = inode->i_sb->s_blocksize >> 2;
bh = sb_bread(inode->i_sb, le32_to_cpu(i_data));
if (!bh)
return -EIO;
tmp_idata = (__le32 *)bh->b_data;
for (i = 0; i < max_entries; i++) {
if (tmp_idata[i]) {
retval = free_dind_blocks(handle,
inode, tmp_idata[i]);
if (retval) {
put_bh(bh);
return retval;
}
}
}
put_bh(bh);
ext4_free_blocks(handle, inode, le32_to_cpu(i_data), 1, 1);
return 0;
}
static int free_ind_block(handle_t *handle, struct inode *inode)
{
int retval;
struct ext4_inode_info *ei = EXT4_I(inode);
if (ei->i_data[EXT4_IND_BLOCK])
ext4_free_blocks(handle, inode,
le32_to_cpu(ei->i_data[EXT4_IND_BLOCK]), 1, 1);
if (ei->i_data[EXT4_DIND_BLOCK]) {
retval = free_dind_blocks(handle, inode,
ei->i_data[EXT4_DIND_BLOCK]);
if (retval)
return retval;
}
if (ei->i_data[EXT4_TIND_BLOCK]) {
retval = free_tind_blocks(handle, inode,
ei->i_data[EXT4_TIND_BLOCK]);
if (retval)
return retval;
}
return 0;
}
static int ext4_ext_swap_inode_data(handle_t *handle, struct inode *inode,
struct inode *tmp_inode, int retval)
{
struct ext4_inode_info *ei = EXT4_I(inode);
struct ext4_inode_info *tmp_ei = EXT4_I(tmp_inode);
retval = free_ind_block(handle, inode);
if (retval)
goto err_out;
/*
* One credit accounted for writing the
* i_data field of the original inode
*/
retval = ext4_journal_extend(handle, 1);
if (retval != 0) {
retval = ext4_journal_restart(handle, 1);
if (retval)
goto err_out;
}
/*
* We have the extent map build with the tmp inode.
* Now copy the i_data across
*/
ei->i_flags |= EXT4_EXTENTS_FL;
memcpy(ei->i_data, tmp_ei->i_data, sizeof(ei->i_data));
/*
* Update i_blocks with the new blocks that got
* allocated while adding extents for extent index
* blocks.
*
* While converting to extents we need not
* update the orignal inode i_blocks for extent blocks
* via quota APIs. The quota update happened via tmp_inode already.
*/
spin_lock(&inode->i_lock);
inode->i_blocks += tmp_inode->i_blocks;
spin_unlock(&inode->i_lock);
ext4_mark_inode_dirty(handle, inode);
err_out:
return retval;
}
static int free_ext_idx(handle_t *handle, struct inode *inode,
struct ext4_extent_idx *ix)
{
int i, retval = 0;
ext4_fsblk_t block;
struct buffer_head *bh;
struct ext4_extent_header *eh;
block = idx_pblock(ix);
bh = sb_bread(inode->i_sb, block);
if (!bh)
return -EIO;
eh = (struct ext4_extent_header *)bh->b_data;
if (eh->eh_depth != 0) {
ix = EXT_FIRST_INDEX(eh);
for (i = 0; i < le16_to_cpu(eh->eh_entries); i++, ix++) {
retval = free_ext_idx(handle, inode, ix);
if (retval)
break;
}
}
put_bh(bh);
ext4_free_blocks(handle, inode, block, 1, 1);
return retval;
}
/*
* Free the extent meta data blocks only
*/
static int free_ext_block(handle_t *handle, struct inode *inode)
{
int i, retval = 0;
struct ext4_inode_info *ei = EXT4_I(inode);
struct ext4_extent_header *eh = (struct ext4_extent_header *)ei->i_data;
struct ext4_extent_idx *ix;
if (eh->eh_depth == 0)
/*
* No extra blocks allocated for extent meta data
*/
return 0;
ix = EXT_FIRST_INDEX(eh);
for (i = 0; i < le16_to_cpu(eh->eh_entries); i++, ix++) {
retval = free_ext_idx(handle, inode, ix);
if (retval)
return retval;
}
return retval;
}
int ext4_ext_migrate(struct inode *inode, struct file *filp,
unsigned int cmd, unsigned long arg)
{
handle_t *handle;
int retval = 0, i;
__le32 *i_data;
ext4_lblk_t blk_count = 0;
struct ext4_inode_info *ei;
struct inode *tmp_inode = NULL;
struct list_blocks_struct lb;
unsigned long max_entries;
if (!test_opt(inode->i_sb, EXTENTS))
/*
* if mounted with noextents we don't allow the migrate
*/
return -EINVAL;
if ((EXT4_I(inode)->i_flags & EXT4_EXTENTS_FL))
return -EINVAL;
down_write(&EXT4_I(inode)->i_data_sem);
handle = ext4_journal_start(inode,
EXT4_DATA_TRANS_BLOCKS(inode->i_sb) +
EXT4_INDEX_EXTRA_TRANS_BLOCKS + 3 +
2 * EXT4_QUOTA_INIT_BLOCKS(inode->i_sb)
+ 1);
if (IS_ERR(handle)) {
retval = PTR_ERR(handle);
goto err_out;
}
tmp_inode = ext4_new_inode(handle,
inode->i_sb->s_root->d_inode,
S_IFREG);
if (IS_ERR(tmp_inode)) {
retval = -ENOMEM;
ext4_journal_stop(handle);
tmp_inode = NULL;
goto err_out;
}
i_size_write(tmp_inode, i_size_read(inode));
/*
* We don't want the inode to be reclaimed
* if we got interrupted in between. We have
* this tmp inode carrying reference to the
* data blocks of the original file. We set
* the i_nlink to zero at the last stage after
* switching the original file to extent format
*/
tmp_inode->i_nlink = 1;
ext4_ext_tree_init(handle, tmp_inode);
ext4_orphan_add(handle, tmp_inode);
ext4_journal_stop(handle);
ei = EXT4_I(inode);
i_data = ei->i_data;
memset(&lb, 0, sizeof(lb));
/* 32 bit block address 4 bytes */
max_entries = inode->i_sb->s_blocksize >> 2;
/*
* start with one credit accounted for
* superblock modification.
*
* For the tmp_inode we already have commited the
* trascation that created the inode. Later as and
* when we add extents we extent the journal
*/
handle = ext4_journal_start(inode, 1);
for (i = 0; i < EXT4_NDIR_BLOCKS; i++, blk_count++) {
if (i_data[i]) {
retval = update_extent_range(handle, tmp_inode,
le32_to_cpu(i_data[i]),
blk_count, &lb);
if (retval)
goto err_out;
}
}
if (i_data[EXT4_IND_BLOCK]) {
retval = update_ind_extent_range(handle, tmp_inode,
le32_to_cpu(i_data[EXT4_IND_BLOCK]),
&blk_count, &lb);
if (retval)
goto err_out;
} else
blk_count += max_entries;
if (i_data[EXT4_DIND_BLOCK]) {
retval = update_dind_extent_range(handle, tmp_inode,
le32_to_cpu(i_data[EXT4_DIND_BLOCK]),
&blk_count, &lb);
if (retval)
goto err_out;
} else
blk_count += max_entries * max_entries;
if (i_data[EXT4_TIND_BLOCK]) {
retval = update_tind_extent_range(handle, tmp_inode,
le32_to_cpu(i_data[EXT4_TIND_BLOCK]),
&blk_count, &lb);
if (retval)
goto err_out;
}
/*
* Build the last extent
*/
retval = finish_range(handle, tmp_inode, &lb);
err_out:
/*
* We are either freeing extent information or indirect
* blocks. During this we touch superblock, group descriptor
* and block bitmap. Later we mark the tmp_inode dirty
* via ext4_ext_tree_init. So allocate a credit of 4
* We may update quota (user and group).
*
* FIXME!! we may be touching bitmaps in different block groups.
*/
if (ext4_journal_extend(handle,
4 + 2*EXT4_QUOTA_TRANS_BLOCKS(inode->i_sb)) != 0)
ext4_journal_restart(handle,
4 + 2*EXT4_QUOTA_TRANS_BLOCKS(inode->i_sb));
if (retval)
/*
* Failure case delete the extent information with the
* tmp_inode
*/
free_ext_block(handle, tmp_inode);
else
retval = ext4_ext_swap_inode_data(handle, inode,
tmp_inode, retval);
/*
* Mark the tmp_inode as of size zero
*/
i_size_write(tmp_inode, 0);
/*
* set the i_blocks count to zero
* so that the ext4_delete_inode does the
* right job
*
* We don't need to take the i_lock because
* the inode is not visible to user space.
*/
tmp_inode->i_blocks = 0;
/* Reset the extent details */
ext4_ext_tree_init(handle, tmp_inode);
/*
* Set the i_nlink to zero so that
* generic_drop_inode really deletes the
* inode
*/
tmp_inode->i_nlink = 0;
ext4_journal_stop(handle);
up_write(&EXT4_I(inode)->i_data_sem);
if (tmp_inode)
iput(tmp_inode);
return retval;
}

135
fs/ext4/namei.c
View file

@ -51,7 +51,7 @@
static struct buffer_head *ext4_append(handle_t *handle,
struct inode *inode,
u32 *block, int *err)
ext4_lblk_t *block, int *err)
{
struct buffer_head *bh;
@ -144,8 +144,8 @@ struct dx_map_entry
u16 size;
};
static inline unsigned dx_get_block (struct dx_entry *entry);
static void dx_set_block (struct dx_entry *entry, unsigned value);
static inline ext4_lblk_t dx_get_block(struct dx_entry *entry);
static void dx_set_block(struct dx_entry *entry, ext4_lblk_t value);
static inline unsigned dx_get_hash (struct dx_entry *entry);
static void dx_set_hash (struct dx_entry *entry, unsigned value);
static unsigned dx_get_count (struct dx_entry *entries);
@ -166,7 +166,8 @@ static void dx_sort_map(struct dx_map_entry *map, unsigned count);
static struct ext4_dir_entry_2 *dx_move_dirents (char *from, char *to,
struct dx_map_entry *offsets, int count);
static struct ext4_dir_entry_2* dx_pack_dirents (char *base, int size);
static void dx_insert_block (struct dx_frame *frame, u32 hash, u32 block);
static void dx_insert_block(struct dx_frame *frame,
u32 hash, ext4_lblk_t block);
static int ext4_htree_next_block(struct inode *dir, __u32 hash,
struct dx_frame *frame,
struct dx_frame *frames,
@ -181,12 +182,12 @@ static int ext4_dx_add_entry(handle_t *handle, struct dentry *dentry,
* Mask them off for now.
*/
static inline unsigned dx_get_block (struct dx_entry *entry)
static inline ext4_lblk_t dx_get_block(struct dx_entry *entry)
{
return le32_to_cpu(entry->block) & 0x00ffffff;
}
static inline void dx_set_block (struct dx_entry *entry, unsigned value)
static inline void dx_set_block(struct dx_entry *entry, ext4_lblk_t value)
{
entry->block = cpu_to_le32(value);
}
@ -243,8 +244,8 @@ static void dx_show_index (char * label, struct dx_entry *entries)
int i, n = dx_get_count (entries);
printk("%s index ", label);
for (i = 0; i < n; i++) {
printk("%x->%u ", i? dx_get_hash(entries + i) :
0, dx_get_block(entries + i));
printk("%x->%lu ", i? dx_get_hash(entries + i) :
0, (unsigned long)dx_get_block(entries + i));
}
printk("\n");
}
@ -280,7 +281,7 @@ static struct stats dx_show_leaf(struct dx_hash_info *hinfo, struct ext4_dir_ent
space += EXT4_DIR_REC_LEN(de->name_len);
names++;
}
de = (struct ext4_dir_entry_2 *) ((char *) de + le16_to_cpu(de->rec_len));
de = ext4_next_entry(de);
}
printk("(%i)\n", names);
return (struct stats) { names, space, 1 };
@ -297,7 +298,8 @@ struct stats dx_show_entries(struct dx_hash_info *hinfo, struct inode *dir,
printk("%i indexed blocks...\n", count);
for (i = 0; i < count; i++, entries++)
{
u32 block = dx_get_block(entries), hash = i? dx_get_hash(entries): 0;
ext4_lblk_t block = dx_get_block(entries);
ext4_lblk_t hash = i ? dx_get_hash(entries): 0;
u32 range = i < count - 1? (dx_get_hash(entries + 1) - hash): ~hash;
struct stats stats;
printk("%s%3u:%03u hash %8x/%8x ",levels?"":" ", i, block, hash, range);
@ -551,7 +553,8 @@ static int ext4_htree_next_block(struct inode *dir, __u32 hash,
*/
static inline struct ext4_dir_entry_2 *ext4_next_entry(struct ext4_dir_entry_2 *p)
{
return (struct ext4_dir_entry_2 *)((char*)p + le16_to_cpu(p->rec_len));
return (struct ext4_dir_entry_2 *)((char *)p +
ext4_rec_len_from_disk(p->rec_len));
}
/*
@ -560,7 +563,7 @@ static inline struct ext4_dir_entry_2 *ext4_next_entry(struct ext4_dir_entry_2 *
* into the tree. If there is an error it is returned in err.
*/
static int htree_dirblock_to_tree(struct file *dir_file,
struct inode *dir, int block,
struct inode *dir, ext4_lblk_t block,
struct dx_hash_info *hinfo,
__u32 start_hash, __u32 start_minor_hash)
{
@ -568,7 +571,8 @@ static int htree_dirblock_to_tree(struct file *dir_file,
struct ext4_dir_entry_2 *de, *top;
int err, count = 0;
dxtrace(printk("In htree dirblock_to_tree: block %d\n", block));
dxtrace(printk(KERN_INFO "In htree dirblock_to_tree: block %lu\n",
(unsigned long)block));
if (!(bh = ext4_bread (NULL, dir, block, 0, &err)))
return err;
@ -620,9 +624,9 @@ int ext4_htree_fill_tree(struct file *dir_file, __u32 start_hash,
struct ext4_dir_entry_2 *de;
struct dx_frame frames[2], *frame;
struct inode *dir;
int block, err;
ext4_lblk_t block;
int count = 0;
int ret;
int ret, err;
__u32 hashval;
dxtrace(printk("In htree_fill_tree, start hash: %x:%x\n", start_hash,
@ -720,7 +724,7 @@ static int dx_make_map (struct ext4_dir_entry_2 *de, int size,
cond_resched();
}
/* XXX: do we need to check rec_len == 0 case? -Chris */
de = (struct ext4_dir_entry_2 *) ((char *) de + le16_to_cpu(de->rec_len));
de = ext4_next_entry(de);
}
return count;
}
@ -752,7 +756,7 @@ static void dx_sort_map (struct dx_map_entry *map, unsigned count)
} while(more);
}
static void dx_insert_block(struct dx_frame *frame, u32 hash, u32 block)
static void dx_insert_block(struct dx_frame *frame, u32 hash, ext4_lblk_t block)
{
struct dx_entry *entries = frame->entries;
struct dx_entry *old = frame->at, *new = old + 1;
@ -820,7 +824,7 @@ static inline int search_dirblock(struct buffer_head * bh,
return 1;
}
/* prevent looping on a bad block */
de_len = le16_to_cpu(de->rec_len);
de_len = ext4_rec_len_from_disk(de->rec_len);
if (de_len <= 0)
return -1;
offset += de_len;
@ -847,23 +851,20 @@ static struct buffer_head * ext4_find_entry (struct dentry *dentry,
struct super_block * sb;
struct buffer_head * bh_use[NAMEI_RA_SIZE];
struct buffer_head * bh, *ret = NULL;
unsigned long start, block, b;
ext4_lblk_t start, block, b;
int ra_max = 0; /* Number of bh's in the readahead
buffer, bh_use[] */
int ra_ptr = 0; /* Current index into readahead
buffer */
int num = 0;
int nblocks, i, err;
ext4_lblk_t nblocks;
int i, err;
struct inode *dir = dentry->d_parent->d_inode;
int namelen;
const u8 *name;
unsigned blocksize;
*res_dir = NULL;
sb = dir->i_sb;
blocksize = sb->s_blocksize;
namelen = dentry->d_name.len;
name = dentry->d_name.name;
if (namelen > EXT4_NAME_LEN)
return NULL;
if (is_dx(dir)) {
@ -914,7 +915,8 @@ restart:
if (!buffer_uptodate(bh)) {
/* read error, skip block & hope for the best */
ext4_error(sb, __FUNCTION__, "reading directory #%lu "
"offset %lu", dir->i_ino, block);
"offset %lu", dir->i_ino,
(unsigned long)block);
brelse(bh);
goto next;
}
@ -961,7 +963,7 @@ static struct buffer_head * ext4_dx_find_entry(struct dentry *dentry,
struct dx_frame frames[2], *frame;
struct ext4_dir_entry_2 *de, *top;
struct buffer_head *bh;
unsigned long block;
ext4_lblk_t block;
int retval;
int namelen = dentry->d_name.len;
const u8 *name = dentry->d_name.name;
@ -1128,7 +1130,7 @@ dx_move_dirents(char *from, char *to, struct dx_map_entry *map, int count)
rec_len = EXT4_DIR_REC_LEN(de->name_len);
memcpy (to, de, rec_len);
((struct ext4_dir_entry_2 *) to)->rec_len =
cpu_to_le16(rec_len);
ext4_rec_len_to_disk(rec_len);
de->inode = 0;
map++;
to += rec_len;
@ -1147,13 +1149,12 @@ static struct ext4_dir_entry_2* dx_pack_dirents(char *base, int size)
prev = to = de;
while ((char*)de < base + size) {
next = (struct ext4_dir_entry_2 *) ((char *) de +
le16_to_cpu(de->rec_len));
next = ext4_next_entry(de);
if (de->inode && de->name_len) {
rec_len = EXT4_DIR_REC_LEN(de->name_len);
if (de > to)
memmove(to, de, rec_len);
to->rec_len = cpu_to_le16(rec_len);
to->rec_len = ext4_rec_len_to_disk(rec_len);
prev = to;
to = (struct ext4_dir_entry_2 *) (((char *) to) + rec_len);
}
@ -1174,7 +1175,7 @@ static struct ext4_dir_entry_2 *do_split(handle_t *handle, struct inode *dir,
unsigned blocksize = dir->i_sb->s_blocksize;
unsigned count, continued;
struct buffer_head *bh2;
u32 newblock;
ext4_lblk_t newblock;
u32 hash2;
struct dx_map_entry *map;
char *data1 = (*bh)->b_data, *data2;
@ -1221,14 +1222,15 @@ static struct ext4_dir_entry_2 *do_split(handle_t *handle, struct inode *dir,
split = count - move;
hash2 = map[split].hash;
continued = hash2 == map[split - 1].hash;
dxtrace(printk("Split block %i at %x, %i/%i\n",
dx_get_block(frame->at), hash2, split, count-split));
dxtrace(printk(KERN_INFO "Split block %lu at %x, %i/%i\n",
(unsigned long)dx_get_block(frame->at),
hash2, split, count-split));
/* Fancy dance to stay within two buffers */
de2 = dx_move_dirents(data1, data2, map + split, count - split);
de = dx_pack_dirents(data1,blocksize);
de->rec_len = cpu_to_le16(data1 + blocksize - (char *) de);
de2->rec_len = cpu_to_le16(data2 + blocksize - (char *) de2);
de->rec_len = ext4_rec_len_to_disk(data1 + blocksize - (char *) de);
de2->rec_len = ext4_rec_len_to_disk(data2 + blocksize - (char *) de2);
dxtrace(dx_show_leaf (hinfo, (struct ext4_dir_entry_2 *) data1, blocksize, 1));
dxtrace(dx_show_leaf (hinfo, (struct ext4_dir_entry_2 *) data2, blocksize, 1));
@ -1297,7 +1299,7 @@ static int add_dirent_to_buf(handle_t *handle, struct dentry *dentry,
return -EEXIST;
}
nlen = EXT4_DIR_REC_LEN(de->name_len);
rlen = le16_to_cpu(de->rec_len);
rlen = ext4_rec_len_from_disk(de->rec_len);
if ((de->inode? rlen - nlen: rlen) >= reclen)
break;
de = (struct ext4_dir_entry_2 *)((char *)de + rlen);
@ -1316,11 +1318,11 @@ static int add_dirent_to_buf(handle_t *handle, struct dentry *dentry,
/* By now the buffer is marked for journaling */
nlen = EXT4_DIR_REC_LEN(de->name_len);
rlen = le16_to_cpu(de->rec_len);
rlen = ext4_rec_len_from_disk(de->rec_len);
if (de->inode) {
struct ext4_dir_entry_2 *de1 = (struct ext4_dir_entry_2 *)((char *)de + nlen);
de1->rec_len = cpu_to_le16(rlen - nlen);
de->rec_len = cpu_to_le16(nlen);
de1->rec_len = ext4_rec_len_to_disk(rlen - nlen);
de->rec_len = ext4_rec_len_to_disk(nlen);
de = de1;
}
de->file_type = EXT4_FT_UNKNOWN;
@ -1374,7 +1376,7 @@ static int make_indexed_dir(handle_t *handle, struct dentry *dentry,
int retval;
unsigned blocksize;
struct dx_hash_info hinfo;
u32 block;
ext4_lblk_t block;
struct fake_dirent *fde;
blocksize = dir->i_sb->s_blocksize;
@ -1397,17 +1399,18 @@ static int make_indexed_dir(handle_t *handle, struct dentry *dentry,
/* The 0th block becomes the root, move the dirents out */
fde = &root->dotdot;
de = (struct ext4_dir_entry_2 *)((char *)fde + le16_to_cpu(fde->rec_len));
de = (struct ext4_dir_entry_2 *)((char *)fde +
ext4_rec_len_from_disk(fde->rec_len));
len = ((char *) root) + blocksize - (char *) de;
memcpy (data1, de, len);
de = (struct ext4_dir_entry_2 *) data1;
top = data1 + len;
while ((char *)(de2=(void*)de+le16_to_cpu(de->rec_len)) < top)
while ((char *)(de2 = ext4_next_entry(de)) < top)
de = de2;
de->rec_len = cpu_to_le16(data1 + blocksize - (char *) de);
de->rec_len = ext4_rec_len_to_disk(data1 + blocksize - (char *) de);
/* Initialize the root; the dot dirents already exist */
de = (struct ext4_dir_entry_2 *) (&root->dotdot);
de->rec_len = cpu_to_le16(blocksize - EXT4_DIR_REC_LEN(2));
de->rec_len = ext4_rec_len_to_disk(blocksize - EXT4_DIR_REC_LEN(2));
memset (&root->info, 0, sizeof(root->info));
root->info.info_length = sizeof(root->info);
root->info.hash_version = EXT4_SB(dir->i_sb)->s_def_hash_version;
@ -1454,7 +1457,7 @@ static int ext4_add_entry (handle_t *handle, struct dentry *dentry,
int retval;
int dx_fallback=0;
unsigned blocksize;
u32 block, blocks;
ext4_lblk_t block, blocks;
sb = dir->i_sb;
blocksize = sb->s_blocksize;
@ -1487,7 +1490,7 @@ static int ext4_add_entry (handle_t *handle, struct dentry *dentry,
return retval;
de = (struct ext4_dir_entry_2 *) bh->b_data;
de->inode = 0;
de->rec_len = cpu_to_le16(blocksize);
de->rec_len = ext4_rec_len_to_disk(blocksize);
return add_dirent_to_buf(handle, dentry, inode, de, bh);
}
@ -1531,7 +1534,7 @@ static int ext4_dx_add_entry(handle_t *handle, struct dentry *dentry,
dx_get_count(entries), dx_get_limit(entries)));
/* Need to split index? */
if (dx_get_count(entries) == dx_get_limit(entries)) {
u32 newblock;
ext4_lblk_t newblock;
unsigned icount = dx_get_count(entries);
int levels = frame - frames;
struct dx_entry *entries2;
@ -1550,7 +1553,7 @@ static int ext4_dx_add_entry(handle_t *handle, struct dentry *dentry,
goto cleanup;
node2 = (struct dx_node *)(bh2->b_data);
entries2 = node2->entries;
node2->fake.rec_len = cpu_to_le16(sb->s_blocksize);
node2->fake.rec_len = ext4_rec_len_to_disk(sb->s_blocksize);
node2->fake.inode = 0;
BUFFER_TRACE(frame->bh, "get_write_access");
err = ext4_journal_get_write_access(handle, frame->bh);
@ -1648,9 +1651,9 @@ static int ext4_delete_entry (handle_t *handle,
BUFFER_TRACE(bh, "get_write_access");
ext4_journal_get_write_access(handle, bh);
if (pde)
pde->rec_len =
cpu_to_le16(le16_to_cpu(pde->rec_len) +
le16_to_cpu(de->rec_len));
pde->rec_len = ext4_rec_len_to_disk(
ext4_rec_len_from_disk(pde->rec_len) +
ext4_rec_len_from_disk(de->rec_len));
else
de->inode = 0;
dir->i_version++;
@ -1658,10 +1661,9 @@ static int ext4_delete_entry (handle_t *handle,
ext4_journal_dirty_metadata(handle, bh);
return 0;
}
i += le16_to_cpu(de->rec_len);
i += ext4_rec_len_from_disk(de->rec_len);
pde = de;
de = (struct ext4_dir_entry_2 *)
((char *) de + le16_to_cpu(de->rec_len));
de = ext4_next_entry(de);
}
return -ENOENT;
}
@ -1824,13 +1826,13 @@ retry:
de = (struct ext4_dir_entry_2 *) dir_block->b_data;
de->inode = cpu_to_le32(inode->i_ino);
de->name_len = 1;
de->rec_len = cpu_to_le16(EXT4_DIR_REC_LEN(de->name_len));
de->rec_len = ext4_rec_len_to_disk(EXT4_DIR_REC_LEN(de->name_len));
strcpy (de->name, ".");
ext4_set_de_type(dir->i_sb, de, S_IFDIR);
de = (struct ext4_dir_entry_2 *)
((char *) de + le16_to_cpu(de->rec_len));
de = ext4_next_entry(de);
de->inode = cpu_to_le32(dir->i_ino);
de->rec_len = cpu_to_le16(inode->i_sb->s_blocksize-EXT4_DIR_REC_LEN(1));
de->rec_len = ext4_rec_len_to_disk(inode->i_sb->s_blocksize -
EXT4_DIR_REC_LEN(1));
de->name_len = 2;
strcpy (de->name, "..");
ext4_set_de_type(dir->i_sb, de, S_IFDIR);
@ -1882,8 +1884,7 @@ static int empty_dir (struct inode * inode)
return 1;
}
de = (struct ext4_dir_entry_2 *) bh->b_data;
de1 = (struct ext4_dir_entry_2 *)
((char *) de + le16_to_cpu(de->rec_len));
de1 = ext4_next_entry(de);
if (le32_to_cpu(de->inode) != inode->i_ino ||
!le32_to_cpu(de1->inode) ||
strcmp (".", de->name) ||
@ -1894,9 +1895,9 @@ static int empty_dir (struct inode * inode)
brelse (bh);
return 1;
}
offset = le16_to_cpu(de->rec_len) + le16_to_cpu(de1->rec_len);
de = (struct ext4_dir_entry_2 *)
((char *) de1 + le16_to_cpu(de1->rec_len));
offset = ext4_rec_len_from_disk(de->rec_len) +
ext4_rec_len_from_disk(de1->rec_len);
de = ext4_next_entry(de1);
while (offset < inode->i_size ) {
if (!bh ||
(void *) de >= (void *) (bh->b_data+sb->s_blocksize)) {
@ -1925,9 +1926,8 @@ static int empty_dir (struct inode * inode)
brelse (bh);
return 0;
}
offset += le16_to_cpu(de->rec_len);
de = (struct ext4_dir_entry_2 *)
((char *) de + le16_to_cpu(de->rec_len));
offset += ext4_rec_len_from_disk(de->rec_len);
de = ext4_next_entry(de);
}
brelse (bh);
return 1;
@ -2282,8 +2282,7 @@ retry:
}
#define PARENT_INO(buffer) \
((struct ext4_dir_entry_2 *) ((char *) buffer + \
le16_to_cpu(((struct ext4_dir_entry_2 *) buffer)->rec_len)))->inode
(ext4_next_entry((struct ext4_dir_entry_2 *)(buffer))->inode)
/*
* Anybody can rename anything with this: the permission checks are left to the

28
fs/ext4/resize.c
View file

@ -28,7 +28,7 @@ static int verify_group_input(struct super_block *sb,
struct ext4_super_block *es = sbi->s_es;
ext4_fsblk_t start = ext4_blocks_count(es);
ext4_fsblk_t end = start + input->blocks_count;
unsigned group = input->group;
ext4_group_t group = input->group;
ext4_fsblk_t itend = input->inode_table + sbi->s_itb_per_group;
unsigned overhead = ext4_bg_has_super(sb, group) ?
(1 + ext4_bg_num_gdb(sb, group) +
@ -206,7 +206,7 @@ static int setup_new_group_blocks(struct super_block *sb,
}
if (ext4_bg_has_super(sb, input->group)) {
ext4_debug("mark backup superblock %#04lx (+0)\n", start);
ext4_debug("mark backup superblock %#04llx (+0)\n", start);
ext4_set_bit(0, bh->b_data);
}
@ -215,7 +215,7 @@ static int setup_new_group_blocks(struct super_block *sb,
i < gdblocks; i++, block++, bit++) {
struct buffer_head *gdb;
ext4_debug("update backup group %#04lx (+%d)\n", block, bit);
ext4_debug("update backup group %#04llx (+%d)\n", block, bit);
if ((err = extend_or_restart_transaction(handle, 1, bh)))
goto exit_bh;
@ -243,7 +243,7 @@ static int setup_new_group_blocks(struct super_block *sb,
i < reserved_gdb; i++, block++, bit++) {
struct buffer_head *gdb;
ext4_debug("clear reserved block %#04lx (+%d)\n", block, bit);
ext4_debug("clear reserved block %#04llx (+%d)\n", block, bit);
if ((err = extend_or_restart_transaction(handle, 1, bh)))
goto exit_bh;
@ -256,10 +256,10 @@ static int setup_new_group_blocks(struct super_block *sb,
ext4_set_bit(bit, bh->b_data);
brelse(gdb);
}
ext4_debug("mark block bitmap %#04x (+%ld)\n", input->block_bitmap,
ext4_debug("mark block bitmap %#04llx (+%llu)\n", input->block_bitmap,
input->block_bitmap - start);
ext4_set_bit(input->block_bitmap - start, bh->b_data);
ext4_debug("mark inode bitmap %#04x (+%ld)\n", input->inode_bitmap,
ext4_debug("mark inode bitmap %#04llx (+%llu)\n", input->inode_bitmap,
input->inode_bitmap - start);
ext4_set_bit(input->inode_bitmap - start, bh->b_data);
@ -268,7 +268,7 @@ static int setup_new_group_blocks(struct super_block *sb,
i < sbi->s_itb_per_group; i++, bit++, block++) {
struct buffer_head *it;
ext4_debug("clear inode block %#04lx (+%d)\n", block, bit);
ext4_debug("clear inode block %#04llx (+%d)\n", block, bit);
if ((err = extend_or_restart_transaction(handle, 1, bh)))
goto exit_bh;
@ -291,7 +291,7 @@ static int setup_new_group_blocks(struct super_block *sb,
brelse(bh);
/* Mark unused entries in inode bitmap used */
ext4_debug("clear inode bitmap %#04x (+%ld)\n",
ext4_debug("clear inode bitmap %#04llx (+%llu)\n",
input->inode_bitmap, input->inode_bitmap - start);
if (IS_ERR(bh = bclean(handle, sb, input->inode_bitmap))) {
err = PTR_ERR(bh);
@ -357,7 +357,7 @@ static int verify_reserved_gdb(struct super_block *sb,
struct buffer_head *primary)
{
const ext4_fsblk_t blk = primary->b_blocknr;
const unsigned long end = EXT4_SB(sb)->s_groups_count;
const ext4_group_t end = EXT4_SB(sb)->s_groups_count;
unsigned three = 1;
unsigned five = 5;
unsigned seven = 7;
@ -656,12 +656,12 @@ static void update_backups(struct super_block *sb,
int blk_off, char *data, int size)
{
struct ext4_sb_info *sbi = EXT4_SB(sb);
const unsigned long last = sbi->s_groups_count;
const ext4_group_t last = sbi->s_groups_count;
const int bpg = EXT4_BLOCKS_PER_GROUP(sb);
unsigned three = 1;
unsigned five = 5;
unsigned seven = 7;
unsigned group;
ext4_group_t group;
int rest = sb->s_blocksize - size;
handle_t *handle;
int err = 0, err2;
@ -716,7 +716,7 @@ static void update_backups(struct super_block *sb,
exit_err:
if (err) {
ext4_warning(sb, __FUNCTION__,
"can't update backup for group %d (err %d), "
"can't update backup for group %lu (err %d), "
"forcing fsck on next reboot", group, err);
sbi->s_mount_state &= ~EXT4_VALID_FS;
sbi->s_es->s_state &= cpu_to_le16(~EXT4_VALID_FS);
@ -952,7 +952,7 @@ int ext4_group_extend(struct super_block *sb, struct ext4_super_block *es,
ext4_fsblk_t n_blocks_count)
{
ext4_fsblk_t o_blocks_count;
unsigned long o_groups_count;
ext4_group_t o_groups_count;
ext4_grpblk_t last;
ext4_grpblk_t add;
struct buffer_head * bh;
@ -1054,7 +1054,7 @@ int ext4_group_extend(struct super_block *sb, struct ext4_super_block *es,
ext4_journal_dirty_metadata(handle, EXT4_SB(sb)->s_sbh);
sb->s_dirt = 1;
unlock_super(sb);
ext4_debug("freeing blocks %lu through %llu\n", o_blocks_count,
ext4_debug("freeing blocks %llu through %llu\n", o_blocks_count,
o_blocks_count + add);
ext4_free_blocks_sb(handle, sb, o_blocks_count, add, &freed_blocks);
ext4_debug("freed blocks %llu through %llu\n", o_blocks_count,

379
fs/ext4/super.c
View file

@ -373,6 +373,66 @@ void ext4_update_dynamic_rev(struct super_block *sb)
*/
}
int ext4_update_compat_feature(handle_t *handle,
struct super_block *sb, __u32 compat)
{
int err = 0;
if (!EXT4_HAS_COMPAT_FEATURE(sb, compat)) {
err = ext4_journal_get_write_access(handle,
EXT4_SB(sb)->s_sbh);
if (err)
return err;
EXT4_SET_COMPAT_FEATURE(sb, compat);
sb->s_dirt = 1;
handle->h_sync = 1;
BUFFER_TRACE(EXT4_SB(sb)->s_sbh,
"call ext4_journal_dirty_met adata");
err = ext4_journal_dirty_metadata(handle,
EXT4_SB(sb)->s_sbh);
}
return err;
}
int ext4_update_rocompat_feature(handle_t *handle,
struct super_block *sb, __u32 rocompat)
{
int err = 0;
if (!EXT4_HAS_RO_COMPAT_FEATURE(sb, rocompat)) {
err = ext4_journal_get_write_access(handle,
EXT4_SB(sb)->s_sbh);
if (err)
return err;
EXT4_SET_RO_COMPAT_FEATURE(sb, rocompat);
sb->s_dirt = 1;
handle->h_sync = 1;
BUFFER_TRACE(EXT4_SB(sb)->s_sbh,
"call ext4_journal_dirty_met adata");
err = ext4_journal_dirty_metadata(handle,
EXT4_SB(sb)->s_sbh);
}
return err;
}
int ext4_update_incompat_feature(handle_t *handle,
struct super_block *sb, __u32 incompat)
{
int err = 0;
if (!EXT4_HAS_INCOMPAT_FEATURE(sb, incompat)) {
err = ext4_journal_get_write_access(handle,
EXT4_SB(sb)->s_sbh);
if (err)
return err;
EXT4_SET_INCOMPAT_FEATURE(sb, incompat);
sb->s_dirt = 1;
handle->h_sync = 1;
BUFFER_TRACE(EXT4_SB(sb)->s_sbh,
"call ext4_journal_dirty_met adata");
err = ext4_journal_dirty_metadata(handle,
EXT4_SB(sb)->s_sbh);
}
return err;
}
/*
* Open the external journal device
*/
@ -443,6 +503,7 @@ static void ext4_put_super (struct super_block * sb)
struct ext4_super_block *es = sbi->s_es;
int i;
ext4_mb_release(sb);
ext4_ext_release(sb);
ext4_xattr_put_super(sb);
jbd2_journal_destroy(sbi->s_journal);
@ -509,6 +570,8 @@ static struct inode *ext4_alloc_inode(struct super_block *sb)
ei->i_block_alloc_info = NULL;
ei->vfs_inode.i_version = 1;
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);
return &ei->vfs_inode;
}
@ -533,7 +596,7 @@ static void init_once(struct kmem_cache *cachep, void *foo)
#ifdef CONFIG_EXT4DEV_FS_XATTR
init_rwsem(&ei->xattr_sem);
#endif
mutex_init(&ei->truncate_mutex);
init_rwsem(&ei->i_data_sem);
inode_init_once(&ei->vfs_inode);
}
@ -605,18 +668,20 @@ static inline void ext4_show_quota_options(struct seq_file *seq, struct super_bl
*/
static int ext4_show_options(struct seq_file *seq, struct vfsmount *vfs)
{
int def_errors;
unsigned long def_mount_opts;
struct super_block *sb = vfs->mnt_sb;
struct ext4_sb_info *sbi = EXT4_SB(sb);
struct ext4_super_block *es = sbi->s_es;
unsigned long def_mount_opts;
def_mount_opts = le32_to_cpu(es->s_default_mount_opts);
def_errors = le16_to_cpu(es->s_errors);
if (sbi->s_sb_block != 1)
seq_printf(seq, ",sb=%llu", sbi->s_sb_block);
if (test_opt(sb, MINIX_DF))
seq_puts(seq, ",minixdf");
if (test_opt(sb, GRPID))
if (test_opt(sb, GRPID) && !(def_mount_opts & EXT4_DEFM_BSDGROUPS))
seq_puts(seq, ",grpid");
if (!test_opt(sb, GRPID) && (def_mount_opts & EXT4_DEFM_BSDGROUPS))
seq_puts(seq, ",nogrpid");
@ -628,34 +693,33 @@ static int ext4_show_options(struct seq_file *seq, struct vfsmount *vfs)
le16_to_cpu(es->s_def_resgid) != EXT4_DEF_RESGID) {
seq_printf(seq, ",resgid=%u", sbi->s_resgid);
}
if (test_opt(sb, ERRORS_CONT)) {
int def_errors = le16_to_cpu(es->s_errors);
if (test_opt(sb, ERRORS_RO)) {
if (def_errors == EXT4_ERRORS_PANIC ||
def_errors == EXT4_ERRORS_RO) {
seq_puts(seq, ",errors=continue");
def_errors == EXT4_ERRORS_CONTINUE) {
seq_puts(seq, ",errors=remount-ro");
}
}
if (test_opt(sb, ERRORS_RO))
seq_puts(seq, ",errors=remount-ro");
if (test_opt(sb, ERRORS_PANIC))
if (test_opt(sb, ERRORS_CONT) && def_errors != EXT4_ERRORS_CONTINUE)
seq_puts(seq, ",errors=continue");
if (test_opt(sb, ERRORS_PANIC) && def_errors != EXT4_ERRORS_PANIC)
seq_puts(seq, ",errors=panic");
if (test_opt(sb, NO_UID32))
if (test_opt(sb, NO_UID32) && !(def_mount_opts & EXT4_DEFM_UID16))
seq_puts(seq, ",nouid32");
if (test_opt(sb, DEBUG))
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))
#ifdef CONFIG_EXT4DEV_FS_XATTR
if (test_opt(sb, XATTR_USER) &&
!(def_mount_opts & EXT4_DEFM_XATTR_USER))
seq_puts(seq, ",user_xattr");
if (!test_opt(sb, XATTR_USER) &&
(def_mount_opts & EXT4_DEFM_XATTR_USER)) {
seq_puts(seq, ",nouser_xattr");
}
#endif
#ifdef CONFIG_EXT4_FS_POSIX_ACL
if (test_opt(sb, POSIX_ACL))
#ifdef CONFIG_EXT4DEV_FS_POSIX_ACL
if (test_opt(sb, POSIX_ACL) && !(def_mount_opts & EXT4_DEFM_ACL))
seq_puts(seq, ",acl");
if (!test_opt(sb, POSIX_ACL) && (def_mount_opts & EXT4_DEFM_ACL))
seq_puts(seq, ",noacl");
@ -672,7 +736,17 @@ static int ext4_show_options(struct seq_file *seq, struct vfsmount *vfs)
seq_puts(seq, ",nobh");
if (!test_opt(sb, EXTENTS))
seq_puts(seq, ",noextents");
if (!test_opt(sb, MBALLOC))
seq_puts(seq, ",nomballoc");
if (test_opt(sb, I_VERSION))
seq_puts(seq, ",i_version");
if (sbi->s_stripe)
seq_printf(seq, ",stripe=%lu", sbi->s_stripe);
/*
* journal mode get enabled in different ways
* So just print the value even if we didn't specify it
*/
if (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA)
seq_puts(seq, ",data=journal");
else if (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_ORDERED_DATA)
@ -681,7 +755,6 @@ static int ext4_show_options(struct seq_file *seq, struct vfsmount *vfs)
seq_puts(seq, ",data=writeback");
ext4_show_quota_options(seq, sb);
return 0;
}
@ -809,11 +882,13 @@ enum {
Opt_user_xattr, Opt_nouser_xattr, Opt_acl, Opt_noacl,
Opt_reservation, Opt_noreservation, Opt_noload, Opt_nobh, Opt_bh,
Opt_commit, Opt_journal_update, Opt_journal_inum, Opt_journal_dev,
Opt_journal_checksum, Opt_journal_async_commit,
Opt_abort, Opt_data_journal, Opt_data_ordered, Opt_data_writeback,
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_noextents,
Opt_grpquota, Opt_extents, Opt_noextents, Opt_i_version,
Opt_mballoc, Opt_nomballoc, Opt_stripe,
};
static match_table_t tokens = {
@ -848,6 +923,8 @@ static match_table_t tokens = {
{Opt_journal_update, "journal=update"},
{Opt_journal_inum, "journal=%u"},
{Opt_journal_dev, "journal_dev=%u"},
{Opt_journal_checksum, "journal_checksum"},
{Opt_journal_async_commit, "journal_async_commit"},
{Opt_abort, "abort"},
{Opt_data_journal, "data=journal"},
{Opt_data_ordered, "data=ordered"},
@ -865,6 +942,10 @@ static match_table_t tokens = {
{Opt_barrier, "barrier=%u"},
{Opt_extents, "extents"},
{Opt_noextents, "noextents"},
{Opt_i_version, "i_version"},
{Opt_mballoc, "mballoc"},
{Opt_nomballoc, "nomballoc"},
{Opt_stripe, "stripe=%u"},
{Opt_err, NULL},
{Opt_resize, "resize"},
};
@ -1035,6 +1116,13 @@ static int parse_options (char *options, struct super_block *sb,
return 0;
*journal_devnum = option;
break;
case Opt_journal_checksum:
set_opt(sbi->s_mount_opt, 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);
break;
case Opt_noload:
set_opt (sbi->s_mount_opt, NOLOAD);
break;
@ -1203,6 +1291,23 @@ clear_qf_name:
case Opt_noextents:
clear_opt (sbi->s_mount_opt, EXTENTS);
break;
case Opt_i_version:
set_opt(sbi->s_mount_opt, I_VERSION);
sb->s_flags |= MS_I_VERSION;
break;
case Opt_mballoc:
set_opt(sbi->s_mount_opt, MBALLOC);
break;
case Opt_nomballoc:
clear_opt(sbi->s_mount_opt, MBALLOC);
break;
case Opt_stripe:
if (match_int(&args[0], &option))
return 0;
if (option < 0)
return 0;
sbi->s_stripe = option;
break;
default:
printk (KERN_ERR
"EXT4-fs: Unrecognized mount option \"%s\" "
@ -1364,7 +1469,7 @@ static int ext4_check_descriptors (struct super_block * sb)
struct ext4_group_desc * gdp = NULL;
int desc_block = 0;
int flexbg_flag = 0;
int i;
ext4_group_t i;
if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_FLEX_BG))
flexbg_flag = 1;
@ -1386,7 +1491,7 @@ static int ext4_check_descriptors (struct super_block * sb)
if (block_bitmap < first_block || block_bitmap > last_block)
{
ext4_error (sb, "ext4_check_descriptors",
"Block bitmap for group %d"
"Block bitmap for group %lu"
" not in group (block %llu)!",
i, block_bitmap);
return 0;
@ -1395,7 +1500,7 @@ static int ext4_check_descriptors (struct super_block * sb)
if (inode_bitmap < first_block || inode_bitmap > last_block)
{
ext4_error (sb, "ext4_check_descriptors",
"Inode bitmap for group %d"
"Inode bitmap for group %lu"
" not in group (block %llu)!",
i, inode_bitmap);
return 0;
@ -1405,17 +1510,16 @@ static int ext4_check_descriptors (struct super_block * sb)
inode_table + sbi->s_itb_per_group - 1 > last_block)
{
ext4_error (sb, "ext4_check_descriptors",
"Inode table for group %d"
"Inode table for group %lu"
" not in group (block %llu)!",
i, inode_table);
return 0;
}
if (!ext4_group_desc_csum_verify(sbi, i, gdp)) {
ext4_error(sb, __FUNCTION__,
"Checksum for group %d failed (%u!=%u)\n", i,
le16_to_cpu(ext4_group_desc_csum(sbi, i,
gdp)),
le16_to_cpu(gdp->bg_checksum));
"Checksum for group %lu failed (%u!=%u)\n",
i, le16_to_cpu(ext4_group_desc_csum(sbi, i,
gdp)), le16_to_cpu(gdp->bg_checksum));
return 0;
}
if (!flexbg_flag)
@ -1429,7 +1533,6 @@ static int ext4_check_descriptors (struct super_block * sb)
return 1;
}
/* ext4_orphan_cleanup() walks a singly-linked list of inodes (starting at
* the superblock) which were deleted from all directories, but held open by
* a process at the time of a crash. We walk the list and try to delete these
@ -1542,20 +1645,95 @@ static void ext4_orphan_cleanup (struct super_block * sb,
#endif
sb->s_flags = s_flags; /* Restore MS_RDONLY status */
}
/*
* Maximal extent format file size.
* Resulting logical blkno at s_maxbytes must fit in our on-disk
* extent format containers, within a sector_t, and within i_blocks
* in the vfs. ext4 inode has 48 bits of i_block in fsblock units,
* so that won't be a limiting factor.
*
* Note, this does *not* consider any metadata overhead for vfs i_blocks.
*/
static loff_t ext4_max_size(int blkbits)
{
loff_t res;
loff_t upper_limit = MAX_LFS_FILESIZE;
/* small i_blocks in vfs inode? */
if (sizeof(blkcnt_t) < sizeof(u64)) {
/*
* CONFIG_LSF is not enabled implies the inode
* i_block represent total blocks in 512 bytes
* 32 == size of vfs inode i_blocks * 8
*/
upper_limit = (1LL << 32) - 1;
/* total blocks in file system block size */
upper_limit >>= (blkbits - 9);
upper_limit <<= blkbits;
}
/* 32-bit extent-start container, ee_block */
res = 1LL << 32;
res <<= blkbits;
res -= 1;
/* Sanity check against vm- & vfs- imposed limits */
if (res > upper_limit)
res = upper_limit;
return res;
}
/*
* Maximal file size. There is a direct, and {,double-,triple-}indirect
* block limit, and also a limit of (2^32 - 1) 512-byte sectors in i_blocks.
* We need to be 1 filesystem block less than the 2^32 sector limit.
* Maximal bitmap file size. There is a direct, and {,double-,triple-}indirect
* block limit, and also a limit of (2^48 - 1) 512-byte sectors in i_blocks.
* We need to be 1 filesystem block less than the 2^48 sector limit.
*/
static loff_t ext4_max_size(int bits)
static loff_t ext4_max_bitmap_size(int bits)
{
loff_t res = EXT4_NDIR_BLOCKS;
/* This constant is calculated to be the largest file size for a
* dense, 4k-blocksize file such that the total number of
int meta_blocks;
loff_t upper_limit;
/* This is calculated to be the largest file size for a
* dense, bitmapped file such that the total number of
* sectors in the file, including data and all indirect blocks,
* does not exceed 2^32. */
const loff_t upper_limit = 0x1ff7fffd000LL;
* does not exceed 2^48 -1
* __u32 i_blocks_lo and _u16 i_blocks_high representing the
* total number of 512 bytes blocks of the file
*/
if (sizeof(blkcnt_t) < sizeof(u64)) {
/*
* CONFIG_LSF is not enabled implies the inode
* i_block represent total blocks in 512 bytes
* 32 == size of vfs inode i_blocks * 8
*/
upper_limit = (1LL << 32) - 1;
/* total blocks in file system block size */
upper_limit >>= (bits - 9);
} else {
/*
* We use 48 bit ext4_inode i_blocks
* With EXT4_HUGE_FILE_FL set the i_blocks
* represent total number of blocks in
* file system block size
*/
upper_limit = (1LL << 48) - 1;
}
/* indirect blocks */
meta_blocks = 1;
/* double indirect blocks */
meta_blocks += 1 + (1LL << (bits-2));
/* tripple indirect blocks */
meta_blocks += 1 + (1LL << (bits-2)) + (1LL << (2*(bits-2)));
upper_limit -= meta_blocks;
upper_limit <<= bits;
res += 1LL << (bits-2);
res += 1LL << (2*(bits-2));
@ -1563,6 +1741,10 @@ static loff_t ext4_max_size(int bits)
res <<= bits;
if (res > upper_limit)
res = upper_limit;
if (res > MAX_LFS_FILESIZE)
res = MAX_LFS_FILESIZE;
return res;
}
@ -1570,7 +1752,7 @@ static ext4_fsblk_t descriptor_loc(struct super_block *sb,
ext4_fsblk_t logical_sb_block, int nr)
{
struct ext4_sb_info *sbi = EXT4_SB(sb);
unsigned long bg, first_meta_bg;
ext4_group_t bg, first_meta_bg;
int has_super = 0;
first_meta_bg = le32_to_cpu(sbi->s_es->s_first_meta_bg);
@ -1584,8 +1766,39 @@ static ext4_fsblk_t descriptor_loc(struct super_block *sb,
return (has_super + ext4_group_first_block_no(sb, bg));
}
/**
* ext4_get_stripe_size: Get the stripe size.
* @sbi: In memory super block info
*
* If we have specified it via mount option, then
* use the mount option value. If the value specified at mount time is
* greater than the blocks per group use the super block value.
* If the super block value is greater than blocks per group return 0.
* Allocator needs it be less than blocks per group.
*
*/
static unsigned long ext4_get_stripe_size(struct ext4_sb_info *sbi)
{
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);
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;
if (stride <= sbi->s_blocks_per_group)
return stride;
return 0;
}
static int ext4_fill_super (struct super_block *sb, void *data, int silent)
__releases(kernel_sem)
__acquires(kernel_sem)
{
struct buffer_head * bh;
struct ext4_super_block *es = NULL;
@ -1599,7 +1812,6 @@ static int ext4_fill_super (struct super_block *sb, void *data, int silent)
unsigned long def_mount_opts;
struct inode *root;
int blocksize;
int hblock;
int db_count;
int i;
int needs_recovery;
@ -1624,6 +1836,11 @@ static int ext4_fill_super (struct super_block *sb, void *data, int silent)
goto out_fail;
}
if (!sb_set_blocksize(sb, blocksize)) {
printk(KERN_ERR "EXT4-fs: bad blocksize %d.\n", blocksize);
goto out_fail;
}
/*
* The ext4 superblock will not be buffer aligned for other than 1kB
* block sizes. We need to calculate the offset from buffer start.
@ -1674,10 +1891,10 @@ static int ext4_fill_super (struct super_block *sb, void *data, int silent)
if (le16_to_cpu(sbi->s_es->s_errors) == EXT4_ERRORS_PANIC)
set_opt(sbi->s_mount_opt, ERRORS_PANIC);
else if (le16_to_cpu(sbi->s_es->s_errors) == EXT4_ERRORS_RO)
set_opt(sbi->s_mount_opt, ERRORS_RO);
else
else if (le16_to_cpu(sbi->s_es->s_errors) == EXT4_ERRORS_CONTINUE)
set_opt(sbi->s_mount_opt, ERRORS_CONT);
else
set_opt(sbi->s_mount_opt, ERRORS_RO);
sbi->s_resuid = le16_to_cpu(es->s_def_resuid);
sbi->s_resgid = le16_to_cpu(es->s_def_resgid);
@ -1689,6 +1906,11 @@ static int ext4_fill_super (struct super_block *sb, void *data, int silent)
* User -o noextents to turn it off
*/
set_opt(sbi->s_mount_opt, EXTENTS);
/*
* turn on mballoc feature by default in ext4 filesystem
* User -o nomballoc to turn it off
*/
set_opt(sbi->s_mount_opt, MBALLOC);
if (!parse_options ((char *) data, sb, &journal_inum, &journal_devnum,
NULL, 0))
@ -1723,6 +1945,19 @@ static int ext4_fill_super (struct super_block *sb, void *data, int silent)
sb->s_id, le32_to_cpu(features));
goto failed_mount;
}
if (EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_HUGE_FILE)) {
/*
* Large file size enabled file system can only be
* mount if kernel is build with CONFIG_LSF
*/
if (sizeof(root->i_blocks) < sizeof(u64) &&
!(sb->s_flags & MS_RDONLY)) {
printk(KERN_ERR "EXT4-fs: %s: Filesystem with huge "
"files cannot be mounted read-write "
"without CONFIG_LSF.\n", sb->s_id);
goto failed_mount;
}
}
blocksize = BLOCK_SIZE << le32_to_cpu(es->s_log_block_size);
if (blocksize < EXT4_MIN_BLOCK_SIZE ||
@ -1733,20 +1968,16 @@ static int ext4_fill_super (struct super_block *sb, void *data, int silent)
goto failed_mount;
}
hblock = bdev_hardsect_size(sb->s_bdev);
if (sb->s_blocksize != blocksize) {
/*
* Make sure the blocksize for the filesystem is larger
* than the hardware sectorsize for the machine.
*/
if (blocksize < hblock) {
printk(KERN_ERR "EXT4-fs: blocksize %d too small for "
"device blocksize %d.\n", blocksize, hblock);
/* Validate the filesystem blocksize */
if (!sb_set_blocksize(sb, blocksize)) {
printk(KERN_ERR "EXT4-fs: bad block size %d.\n",
blocksize);
goto failed_mount;
}
brelse (bh);
sb_set_blocksize(sb, blocksize);
logical_sb_block = sb_block * EXT4_MIN_BLOCK_SIZE;
offset = do_div(logical_sb_block, blocksize);
bh = sb_bread(sb, logical_sb_block);
@ -1764,6 +1995,7 @@ static int ext4_fill_super (struct super_block *sb, void *data, int silent)
}
}
sbi->s_bitmap_maxbytes = ext4_max_bitmap_size(sb->s_blocksize_bits);
sb->s_maxbytes = ext4_max_size(sb->s_blocksize_bits);
if (le32_to_cpu(es->s_rev_level) == EXT4_GOOD_OLD_REV) {
@ -1838,6 +2070,17 @@ static int ext4_fill_super (struct super_block *sb, void *data, int silent)
if (EXT4_BLOCKS_PER_GROUP(sb) == 0)
goto cantfind_ext4;
/* ensure blocks_count calculation below doesn't sign-extend */
if (ext4_blocks_count(es) + EXT4_BLOCKS_PER_GROUP(sb) <
le32_to_cpu(es->s_first_data_block) + 1) {
printk(KERN_WARNING "EXT4-fs: bad geometry: block count %llu, "
"first data block %u, blocks per group %lu\n",
ext4_blocks_count(es),
le32_to_cpu(es->s_first_data_block),
EXT4_BLOCKS_PER_GROUP(sb));
goto failed_mount;
}
blocks_count = (ext4_blocks_count(es) -
le32_to_cpu(es->s_first_data_block) +
EXT4_BLOCKS_PER_GROUP(sb) - 1);
@ -1900,6 +2143,8 @@ static int ext4_fill_super (struct super_block *sb, void *data, int silent)
sbi->s_rsv_window_head.rsv_goal_size = 0;
ext4_rsv_window_add(sb, &sbi->s_rsv_window_head);
sbi->s_stripe = ext4_get_stripe_size(sbi);
/*
* set up enough so that it can read an inode
*/
@ -1944,6 +2189,21 @@ static int ext4_fill_super (struct super_block *sb, void *data, int silent)
goto failed_mount4;
}
if (test_opt(sb, JOURNAL_ASYNC_COMMIT)) {
jbd2_journal_set_features(sbi->s_journal,
JBD2_FEATURE_COMPAT_CHECKSUM, 0,
JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT);
} else if (test_opt(sb, JOURNAL_CHECKSUM)) {
jbd2_journal_set_features(sbi->s_journal,
JBD2_FEATURE_COMPAT_CHECKSUM, 0, 0);
jbd2_journal_clear_features(sbi->s_journal, 0, 0,
JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT);
} else {
jbd2_journal_clear_features(sbi->s_journal,
JBD2_FEATURE_COMPAT_CHECKSUM, 0,
JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT);
}
/* We have now updated the journal if required, so we can
* validate the data journaling mode. */
switch (test_opt(sb, DATA_FLAGS)) {
@ -2044,6 +2304,7 @@ static int ext4_fill_super (struct super_block *sb, void *data, int silent)
"writeback");
ext4_ext_init(sb);
ext4_mb_init(sb, needs_recovery);
lock_kernel();
return 0;
@ -2673,7 +2934,7 @@ static int ext4_statfs (struct dentry * dentry, struct kstatfs * buf)
if (test_opt(sb, MINIX_DF)) {
sbi->s_overhead_last = 0;
} else if (sbi->s_blocks_last != ext4_blocks_count(es)) {
unsigned long ngroups = sbi->s_groups_count, i;
ext4_group_t ngroups = sbi->s_groups_count, i;
ext4_fsblk_t overhead = 0;
smp_rmb();
@ -2909,7 +3170,7 @@ static ssize_t ext4_quota_read(struct super_block *sb, int type, char *data,
size_t len, loff_t off)
{
struct inode *inode = sb_dqopt(sb)->files[type];
sector_t blk = off >> EXT4_BLOCK_SIZE_BITS(sb);
ext4_lblk_t blk = off >> EXT4_BLOCK_SIZE_BITS(sb);
int err = 0;
int offset = off & (sb->s_blocksize - 1);
int tocopy;
@ -2947,7 +3208,7 @@ static ssize_t ext4_quota_write(struct super_block *sb, int type,
const char *data, size_t len, loff_t off)
{
struct inode *inode = sb_dqopt(sb)->files[type];
sector_t blk = off >> EXT4_BLOCK_SIZE_BITS(sb);
ext4_lblk_t blk = off >> EXT4_BLOCK_SIZE_BITS(sb);
int err = 0;
int offset = off & (sb->s_blocksize - 1);
int tocopy;
@ -3002,7 +3263,6 @@ out:
i_size_write(inode, off+len-towrite);
EXT4_I(inode)->i_disksize = inode->i_size;
}
inode->i_version++;
inode->i_mtime = inode->i_ctime = CURRENT_TIME;
ext4_mark_inode_dirty(handle, inode);
mutex_unlock(&inode->i_mutex);
@ -3027,9 +3287,15 @@ static struct file_system_type ext4dev_fs_type = {
static int __init init_ext4_fs(void)
{
int err = init_ext4_xattr();
int err;
err = init_ext4_mballoc();
if (err)
return err;
err = init_ext4_xattr();
if (err)
goto out2;
err = init_inodecache();
if (err)
goto out1;
@ -3041,6 +3307,8 @@ out:
destroy_inodecache();
out1:
exit_ext4_xattr();
out2:
exit_ext4_mballoc();
return err;
}
@ -3049,6 +3317,7 @@ static void __exit exit_ext4_fs(void)
unregister_filesystem(&ext4dev_fs_type);
destroy_inodecache();
exit_ext4_xattr();
exit_ext4_mballoc();
}
MODULE_AUTHOR("Remy Card, Stephen Tweedie, Andrew Morton, Andreas Dilger, Theodore Ts'o and others");

4
fs/ext4/xattr.c
View file

@ -480,7 +480,7 @@ ext4_xattr_release_block(handle_t *handle, struct inode *inode,
ea_bdebug(bh, "refcount now=0; freeing");
if (ce)
mb_cache_entry_free(ce);
ext4_free_blocks(handle, inode, bh->b_blocknr, 1);
ext4_free_blocks(handle, inode, bh->b_blocknr, 1, 1);
get_bh(bh);
ext4_forget(handle, 1, inode, bh, bh->b_blocknr);
} else {
@ -821,7 +821,7 @@ inserted:
new_bh = sb_getblk(sb, block);
if (!new_bh) {
getblk_failed:
ext4_free_blocks(handle, inode, block, 1);
ext4_free_blocks(handle, inode, block, 1, 1);
error = -EIO;
goto cleanup;
}

5
fs/inode.c
View file

@ -1276,6 +1276,11 @@ void file_update_time(struct file *file)
sync_it = 1;
}
if (IS_I_VERSION(inode)) {
inode_inc_iversion(inode);
sync_it = 1;
}
if (sync_it)
mark_inode_dirty_sync(inode);
}

22
fs/jbd2/checkpoint.c
View file

@ -232,7 +232,8 @@ __flush_batch(journal_t *journal, struct buffer_head **bhs, int *batch_count)
* Called under jbd_lock_bh_state(jh2bh(jh)), and drops it
*/
static int __process_buffer(journal_t *journal, struct journal_head *jh,
struct buffer_head **bhs, int *batch_count)
struct buffer_head **bhs, int *batch_count,
transaction_t *transaction)
{
struct buffer_head *bh = jh2bh(jh);
int ret = 0;
@ -250,6 +251,7 @@ static int __process_buffer(journal_t *journal, struct journal_head *jh,
transaction_t *t = jh->b_transaction;
tid_t tid = t->t_tid;
transaction->t_chp_stats.cs_forced_to_close++;
spin_unlock(&journal->j_list_lock);
jbd_unlock_bh_state(bh);
jbd2_log_start_commit(journal, tid);
@ -279,6 +281,7 @@ static int __process_buffer(journal_t *journal, struct journal_head *jh,
bhs[*batch_count] = bh;
__buffer_relink_io(jh);
jbd_unlock_bh_state(bh);
transaction->t_chp_stats.cs_written++;
(*batch_count)++;
if (*batch_count == NR_BATCH) {
spin_unlock(&journal->j_list_lock);
@ -322,6 +325,8 @@ int jbd2_log_do_checkpoint(journal_t *journal)
if (!journal->j_checkpoint_transactions)
goto out;
transaction = journal->j_checkpoint_transactions;
if (transaction->t_chp_stats.cs_chp_time == 0)
transaction->t_chp_stats.cs_chp_time = jiffies;
this_tid = transaction->t_tid;
restart:
/*
@ -346,7 +351,8 @@ restart:
retry = 1;
break;
}
retry = __process_buffer(journal, jh, bhs,&batch_count);
retry = __process_buffer(journal, jh, bhs, &batch_count,
transaction);
if (!retry && lock_need_resched(&journal->j_list_lock)){
spin_unlock(&journal->j_list_lock);
retry = 1;
@ -602,15 +608,15 @@ int __jbd2_journal_remove_checkpoint(struct journal_head *jh)
/*
* There is one special case to worry about: if we have just pulled the
* buffer off a committing transaction's forget list, then even if the
* checkpoint list is empty, the transaction obviously cannot be
* dropped!
* buffer off a running or committing transaction's checkpoing list,
* then even if the checkpoint list is empty, the transaction obviously
* cannot be dropped!
*
* The locking here around j_committing_transaction is a bit sleazy.
* The locking here around t_state is a bit sleazy.
* See the comment at the end of jbd2_journal_commit_transaction().
*/
if (transaction == journal->j_committing_transaction) {
JBUFFER_TRACE(jh, "belongs to committing transaction");
if (transaction->t_state != T_FINISHED) {
JBUFFER_TRACE(jh, "belongs to running/committing transaction");
goto out;
}

257
fs/jbd2/commit.c
View file

@ -20,6 +20,8 @@
#include <linux/slab.h>
#include <linux/mm.h>
#include <linux/pagemap.h>
#include <linux/jiffies.h>
#include <linux/crc32.h>
/*
* Default IO end handler for temporary BJ_IO buffer_heads.
@ -92,19 +94,23 @@ static int inverted_lock(journal_t *journal, struct buffer_head *bh)
return 1;
}
/* Done it all: now write the commit record. We should have
/*
* Done it all: now submit the commit record. We should have
* cleaned up our previous buffers by now, so if we are in abort
* mode we can now just skip the rest of the journal write
* entirely.
*
* Returns 1 if the journal needs to be aborted or 0 on success
*/
static int journal_write_commit_record(journal_t *journal,
transaction_t *commit_transaction)
static int journal_submit_commit_record(journal_t *journal,
transaction_t *commit_transaction,
struct buffer_head **cbh,
__u32 crc32_sum)
{
struct journal_head *descriptor;
struct commit_header *tmp;
struct buffer_head *bh;
int i, ret;
int ret;
int barrier_done = 0;
if (is_journal_aborted(journal))
@ -116,21 +122,33 @@ static int journal_write_commit_record(journal_t *journal,
bh = jh2bh(descriptor);
/* AKPM: buglet - add `i' to tmp! */
for (i = 0; i < bh->b_size; i += 512) {
journal_header_t *tmp = (journal_header_t*)bh->b_data;
tmp->h_magic = cpu_to_be32(JBD2_MAGIC_NUMBER);
tmp->h_blocktype = cpu_to_be32(JBD2_COMMIT_BLOCK);
tmp->h_sequence = cpu_to_be32(commit_transaction->t_tid);
tmp = (struct commit_header *)bh->b_data;
tmp->h_magic = cpu_to_be32(JBD2_MAGIC_NUMBER);
tmp->h_blocktype = cpu_to_be32(JBD2_COMMIT_BLOCK);
tmp->h_sequence = cpu_to_be32(commit_transaction->t_tid);
if (JBD2_HAS_COMPAT_FEATURE(journal,
JBD2_FEATURE_COMPAT_CHECKSUM)) {
tmp->h_chksum_type = JBD2_CRC32_CHKSUM;
tmp->h_chksum_size = JBD2_CRC32_CHKSUM_SIZE;
tmp->h_chksum[0] = cpu_to_be32(crc32_sum);
}
JBUFFER_TRACE(descriptor, "write commit block");
JBUFFER_TRACE(descriptor, "submit commit block");
lock_buffer(bh);
set_buffer_dirty(bh);
if (journal->j_flags & JBD2_BARRIER) {
set_buffer_uptodate(bh);
bh->b_end_io = journal_end_buffer_io_sync;
if (journal->j_flags & JBD2_BARRIER &&
!JBD2_HAS_COMPAT_FEATURE(journal,
JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT)) {
set_buffer_ordered(bh);
barrier_done = 1;
}
ret = sync_dirty_buffer(bh);
ret = submit_bh(WRITE, bh);
/* is it possible for another commit to fail at roughly
* the same time as this one? If so, we don't want to
* trust the barrier flag in the super, but instead want
@ -151,14 +169,72 @@ static int journal_write_commit_record(journal_t *journal,
clear_buffer_ordered(bh);
set_buffer_uptodate(bh);
set_buffer_dirty(bh);
ret = sync_dirty_buffer(bh);
ret = submit_bh(WRITE, bh);
}
put_bh(bh); /* One for getblk() */
jbd2_journal_put_journal_head(descriptor);
return (ret == -EIO);
*cbh = bh;
return ret;
}
/*
* This function along with journal_submit_commit_record
* allows to write the commit record asynchronously.
*/
static int journal_wait_on_commit_record(struct buffer_head *bh)
{
int ret = 0;
clear_buffer_dirty(bh);
wait_on_buffer(bh);
if (unlikely(!buffer_uptodate(bh)))
ret = -EIO;
put_bh(bh); /* One for getblk() */
jbd2_journal_put_journal_head(bh2jh(bh));
return ret;
}
/*
* Wait for all submitted IO to complete.
*/
static int journal_wait_on_locked_list(journal_t *journal,
transaction_t *commit_transaction)
{
int ret = 0;
struct journal_head *jh;
while (commit_transaction->t_locked_list) {
struct buffer_head *bh;
jh = commit_transaction->t_locked_list->b_tprev;
bh = jh2bh(jh);
get_bh(bh);
if (buffer_locked(bh)) {
spin_unlock(&journal->j_list_lock);
wait_on_buffer(bh);
if (unlikely(!buffer_uptodate(bh)))
ret = -EIO;
spin_lock(&journal->j_list_lock);
}
if (!inverted_lock(journal, bh)) {
put_bh(bh);
spin_lock(&journal->j_list_lock);
continue;
}
if (buffer_jbd(bh) && jh->b_jlist == BJ_Locked) {
__jbd2_journal_unfile_buffer(jh);
jbd_unlock_bh_state(bh);
jbd2_journal_remove_journal_head(bh);
put_bh(bh);
} else {
jbd_unlock_bh_state(bh);
}
put_bh(bh);
cond_resched_lock(&journal->j_list_lock);
}
return ret;
}
static void journal_do_submit_data(struct buffer_head **wbuf, int bufs)
{
int i;
@ -274,7 +350,21 @@ write_out_data:
journal_do_submit_data(wbuf, bufs);
}
static inline void write_tag_block(int tag_bytes, journal_block_tag_t *tag,
static __u32 jbd2_checksum_data(__u32 crc32_sum, struct buffer_head *bh)
{
struct page *page = bh->b_page;
char *addr;
__u32 checksum;
addr = kmap_atomic(page, KM_USER0);
checksum = crc32_be(crc32_sum,
(void *)(addr + offset_in_page(bh->b_data)), bh->b_size);
kunmap_atomic(addr, KM_USER0);
return checksum;
}
static void write_tag_block(int tag_bytes, journal_block_tag_t *tag,
unsigned long long block)
{
tag->t_blocknr = cpu_to_be32(block & (u32)~0);
@ -290,6 +380,7 @@ static inline void write_tag_block(int tag_bytes, journal_block_tag_t *tag,
*/
void jbd2_journal_commit_transaction(journal_t *journal)
{
struct transaction_stats_s stats;
transaction_t *commit_transaction;
struct journal_head *jh, *new_jh, *descriptor;
struct buffer_head **wbuf = journal->j_wbuf;
@ -305,6 +396,8 @@ void jbd2_journal_commit_transaction(journal_t *journal)
int tag_flag;
int i;
int tag_bytes = journal_tag_bytes(journal);
struct buffer_head *cbh = NULL; /* For transactional checksums */
__u32 crc32_sum = ~0;
/*
* First job: lock down the current transaction and wait for
@ -337,6 +430,11 @@ void jbd2_journal_commit_transaction(journal_t *journal)
spin_lock(&journal->j_state_lock);
commit_transaction->t_state = T_LOCKED;
stats.u.run.rs_wait = commit_transaction->t_max_wait;
stats.u.run.rs_locked = jiffies;
stats.u.run.rs_running = jbd2_time_diff(commit_transaction->t_start,
stats.u.run.rs_locked);
spin_lock(&commit_transaction->t_handle_lock);
while (commit_transaction->t_updates) {
DEFINE_WAIT(wait);
@ -407,6 +505,10 @@ void jbd2_journal_commit_transaction(journal_t *journal)
*/
jbd2_journal_switch_revoke_table(journal);
stats.u.run.rs_flushing = jiffies;
stats.u.run.rs_locked = jbd2_time_diff(stats.u.run.rs_locked,
stats.u.run.rs_flushing);
commit_transaction->t_state = T_FLUSH;
journal->j_committing_transaction = commit_transaction;
journal->j_running_transaction = NULL;
@ -440,38 +542,15 @@ void jbd2_journal_commit_transaction(journal_t *journal)
journal_submit_data_buffers(journal, commit_transaction);
/*
* Wait for all previously submitted IO to complete.
* Wait for all previously submitted IO to complete if commit
* record is to be written synchronously.
*/
spin_lock(&journal->j_list_lock);
while (commit_transaction->t_locked_list) {
struct buffer_head *bh;
if (!JBD2_HAS_INCOMPAT_FEATURE(journal,
JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT))
err = journal_wait_on_locked_list(journal,
commit_transaction);
jh = commit_transaction->t_locked_list->b_tprev;
bh = jh2bh(jh);
get_bh(bh);
if (buffer_locked(bh)) {
spin_unlock(&journal->j_list_lock);
wait_on_buffer(bh);
if (unlikely(!buffer_uptodate(bh)))
err = -EIO;
spin_lock(&journal->j_list_lock);
}
if (!inverted_lock(journal, bh)) {
put_bh(bh);
spin_lock(&journal->j_list_lock);
continue;
}
if (buffer_jbd(bh) && jh->b_jlist == BJ_Locked) {
__jbd2_journal_unfile_buffer(jh);
jbd_unlock_bh_state(bh);
jbd2_journal_remove_journal_head(bh);
put_bh(bh);
} else {
jbd_unlock_bh_state(bh);
}
put_bh(bh);
cond_resched_lock(&journal->j_list_lock);
}
spin_unlock(&journal->j_list_lock);
if (err)
@ -498,6 +577,12 @@ void jbd2_journal_commit_transaction(journal_t *journal)
*/
commit_transaction->t_state = T_COMMIT;
stats.u.run.rs_logging = jiffies;
stats.u.run.rs_flushing = jbd2_time_diff(stats.u.run.rs_flushing,
stats.u.run.rs_logging);
stats.u.run.rs_blocks = commit_transaction->t_outstanding_credits;
stats.u.run.rs_blocks_logged = 0;
descriptor = NULL;
bufs = 0;
while (commit_transaction->t_buffers) {
@ -639,6 +724,15 @@ void jbd2_journal_commit_transaction(journal_t *journal)
start_journal_io:
for (i = 0; i < bufs; i++) {
struct buffer_head *bh = wbuf[i];
/*
* Compute checksum.
*/
if (JBD2_HAS_COMPAT_FEATURE(journal,
JBD2_FEATURE_COMPAT_CHECKSUM)) {
crc32_sum =
jbd2_checksum_data(crc32_sum, bh);
}
lock_buffer(bh);
clear_buffer_dirty(bh);
set_buffer_uptodate(bh);
@ -646,6 +740,7 @@ start_journal_io:
submit_bh(WRITE, bh);
}
cond_resched();
stats.u.run.rs_blocks_logged += bufs;
/* Force a new descriptor to be generated next
time round the loop. */
@ -654,6 +749,23 @@ start_journal_io:
}
}
/* Done it all: now write the commit record asynchronously. */
if (JBD2_HAS_INCOMPAT_FEATURE(journal,
JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT)) {
err = journal_submit_commit_record(journal, commit_transaction,
&cbh, crc32_sum);
if (err)
__jbd2_journal_abort_hard(journal);
spin_lock(&journal->j_list_lock);
err = journal_wait_on_locked_list(journal,
commit_transaction);
spin_unlock(&journal->j_list_lock);
if (err)
__jbd2_journal_abort_hard(journal);
}
/* Lo and behold: we have just managed to send a transaction to
the log. Before we can commit it, wait for the IO so far to
complete. Control buffers being written are on the
@ -753,8 +865,14 @@ wait_for_iobuf:
jbd_debug(3, "JBD: commit phase 6\n");
if (journal_write_commit_record(journal, commit_transaction))
err = -EIO;
if (!JBD2_HAS_INCOMPAT_FEATURE(journal,
JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT)) {
err = journal_submit_commit_record(journal, commit_transaction,
&cbh, crc32_sum);
if (err)
__jbd2_journal_abort_hard(journal);
}
err = journal_wait_on_commit_record(cbh);
if (err)
jbd2_journal_abort(journal, err);
@ -816,6 +934,7 @@ restart_loop:
cp_transaction = jh->b_cp_transaction;
if (cp_transaction) {
JBUFFER_TRACE(jh, "remove from old cp transaction");
cp_transaction->t_chp_stats.cs_dropped++;
__jbd2_journal_remove_checkpoint(jh);
}
@ -867,10 +986,10 @@ restart_loop:
}
spin_unlock(&journal->j_list_lock);
/*
* This is a bit sleazy. We borrow j_list_lock to protect
* journal->j_committing_transaction in __jbd2_journal_remove_checkpoint.
* Really, __jbd2_journal_remove_checkpoint should be using j_state_lock but
* it's a bit hassle to hold that across __jbd2_journal_remove_checkpoint
* This is a bit sleazy. We use j_list_lock to protect transition
* of a transaction into T_FINISHED state and calling
* __jbd2_journal_drop_transaction(). Otherwise we could race with
* other checkpointing code processing the transaction...
*/
spin_lock(&journal->j_state_lock);
spin_lock(&journal->j_list_lock);
@ -890,6 +1009,36 @@ restart_loop:
J_ASSERT(commit_transaction->t_state == T_COMMIT);
commit_transaction->t_start = jiffies;
stats.u.run.rs_logging = jbd2_time_diff(stats.u.run.rs_logging,
commit_transaction->t_start);
/*
* File the transaction for history
*/
stats.ts_type = JBD2_STATS_RUN;
stats.ts_tid = commit_transaction->t_tid;
stats.u.run.rs_handle_count = commit_transaction->t_handle_count;
spin_lock(&journal->j_history_lock);
memcpy(journal->j_history + journal->j_history_cur, &stats,
sizeof(stats));
if (++journal->j_history_cur == journal->j_history_max)
journal->j_history_cur = 0;
/*
* Calculate overall stats
*/
journal->j_stats.ts_tid++;
journal->j_stats.u.run.rs_wait += stats.u.run.rs_wait;
journal->j_stats.u.run.rs_running += stats.u.run.rs_running;
journal->j_stats.u.run.rs_locked += stats.u.run.rs_locked;
journal->j_stats.u.run.rs_flushing += stats.u.run.rs_flushing;
journal->j_stats.u.run.rs_logging += stats.u.run.rs_logging;
journal->j_stats.u.run.rs_handle_count += stats.u.run.rs_handle_count;
journal->j_stats.u.run.rs_blocks += stats.u.run.rs_blocks;
journal->j_stats.u.run.rs_blocks_logged += stats.u.run.rs_blocks_logged;
spin_unlock(&journal->j_history_lock);
commit_transaction->t_state = T_FINISHED;
J_ASSERT(commit_transaction == journal->j_committing_transaction);
journal->j_commit_sequence = commit_transaction->t_tid;

368
fs/jbd2/journal.c
View file

@ -36,6 +36,7 @@
#include <linux/poison.h>
#include <linux/proc_fs.h>
#include <linux/debugfs.h>
#include <linux/seq_file.h>
#include <asm/uaccess.h>
#include <asm/page.h>
@ -640,6 +641,312 @@ struct journal_head *jbd2_journal_get_descriptor_buffer(journal_t *journal)
return jbd2_journal_add_journal_head(bh);
}
struct jbd2_stats_proc_session {
journal_t *journal;
struct transaction_stats_s *stats;
int start;
int max;
};
static void *jbd2_history_skip_empty(struct jbd2_stats_proc_session *s,
struct transaction_stats_s *ts,
int first)
{
if (ts == s->stats + s->max)
ts = s->stats;
if (!first && ts == s->stats + s->start)
return NULL;
while (ts->ts_type == 0) {
ts++;
if (ts == s->stats + s->max)
ts = s->stats;
if (ts == s->stats + s->start)
return NULL;
}
return ts;
}
static void *jbd2_seq_history_start(struct seq_file *seq, loff_t *pos)
{
struct jbd2_stats_proc_session *s = seq->private;
struct transaction_stats_s *ts;
int l = *pos;
if (l == 0)
return SEQ_START_TOKEN;
ts = jbd2_history_skip_empty(s, s->stats + s->start, 1);
if (!ts)
return NULL;
l--;
while (l) {
ts = jbd2_history_skip_empty(s, ++ts, 0);
if (!ts)
break;
l--;
}
return ts;
}
static void *jbd2_seq_history_next(struct seq_file *seq, void *v, loff_t *pos)
{
struct jbd2_stats_proc_session *s = seq->private;
struct transaction_stats_s *ts = v;
++*pos;
if (v == SEQ_START_TOKEN)
return jbd2_history_skip_empty(s, s->stats + s->start, 1);
else
return jbd2_history_skip_empty(s, ++ts, 0);
}
static int jbd2_seq_history_show(struct seq_file *seq, void *v)
{
struct transaction_stats_s *ts = v;
if (v == SEQ_START_TOKEN) {
seq_printf(seq, "%-4s %-5s %-5s %-5s %-5s %-5s %-5s %-6s %-5s "
"%-5s %-5s %-5s %-5s %-5s\n", "R/C", "tid",
"wait", "run", "lock", "flush", "log", "hndls",
"block", "inlog", "ctime", "write", "drop",
"close");
return 0;
}
if (ts->ts_type == JBD2_STATS_RUN)
seq_printf(seq, "%-4s %-5lu %-5u %-5u %-5u %-5u %-5u "
"%-6lu %-5lu %-5lu\n", "R", ts->ts_tid,
jiffies_to_msecs(ts->u.run.rs_wait),
jiffies_to_msecs(ts->u.run.rs_running),
jiffies_to_msecs(ts->u.run.rs_locked),
jiffies_to_msecs(ts->u.run.rs_flushing),
jiffies_to_msecs(ts->u.run.rs_logging),
ts->u.run.rs_handle_count,
ts->u.run.rs_blocks,
ts->u.run.rs_blocks_logged);
else if (ts->ts_type == JBD2_STATS_CHECKPOINT)
seq_printf(seq, "%-4s %-5lu %48s %-5u %-5lu %-5lu %-5lu\n",
"C", ts->ts_tid, " ",
jiffies_to_msecs(ts->u.chp.cs_chp_time),
ts->u.chp.cs_written, ts->u.chp.cs_dropped,
ts->u.chp.cs_forced_to_close);
else
J_ASSERT(0);
return 0;
}
static void jbd2_seq_history_stop(struct seq_file *seq, void *v)
{
}
static struct seq_operations jbd2_seq_history_ops = {
.start = jbd2_seq_history_start,
.next = jbd2_seq_history_next,
.stop = jbd2_seq_history_stop,
.show = jbd2_seq_history_show,
};
static int jbd2_seq_history_open(struct inode *inode, struct file *file)
{
journal_t *journal = PDE(inode)->data;
struct jbd2_stats_proc_session *s;
int rc, size;
s = kmalloc(sizeof(*s), GFP_KERNEL);
if (s == NULL)
return -ENOMEM;
size = sizeof(struct transaction_stats_s) * journal->j_history_max;
s->stats = kmalloc(size, GFP_KERNEL);
if (s->stats == NULL) {
kfree(s);
return -ENOMEM;
}
spin_lock(&journal->j_history_lock);
memcpy(s->stats, journal->j_history, size);
s->max = journal->j_history_max;
s->start = journal->j_history_cur % s->max;
spin_unlock(&journal->j_history_lock);
rc = seq_open(file, &jbd2_seq_history_ops);
if (rc == 0) {
struct seq_file *m = file->private_data;
m->private = s;
} else {
kfree(s->stats);
kfree(s);
}
return rc;
}
static int jbd2_seq_history_release(struct inode *inode, struct file *file)
{
struct seq_file *seq = file->private_data;
struct jbd2_stats_proc_session *s = seq->private;
kfree(s->stats);
kfree(s);
return seq_release(inode, file);
}
static struct file_operations jbd2_seq_history_fops = {
.owner = THIS_MODULE,
.open = jbd2_seq_history_open,
.read = seq_read,
.llseek = seq_lseek,
.release = jbd2_seq_history_release,
};
static void *jbd2_seq_info_start(struct seq_file *seq, loff_t *pos)
{
return *pos ? NULL : SEQ_START_TOKEN;
}
static void *jbd2_seq_info_next(struct seq_file *seq, void *v, loff_t *pos)
{
return NULL;
}
static int jbd2_seq_info_show(struct seq_file *seq, void *v)
{
struct jbd2_stats_proc_session *s = seq->private;
if (v != SEQ_START_TOKEN)
return 0;
seq_printf(seq, "%lu transaction, each upto %u blocks\n",
s->stats->ts_tid,
s->journal->j_max_transaction_buffers);
if (s->stats->ts_tid == 0)
return 0;
seq_printf(seq, "average: \n %ums waiting for transaction\n",
jiffies_to_msecs(s->stats->u.run.rs_wait / s->stats->ts_tid));
seq_printf(seq, " %ums running transaction\n",
jiffies_to_msecs(s->stats->u.run.rs_running / s->stats->ts_tid));
seq_printf(seq, " %ums transaction was being locked\n",
jiffies_to_msecs(s->stats->u.run.rs_locked / s->stats->ts_tid));
seq_printf(seq, " %ums flushing data (in ordered mode)\n",
jiffies_to_msecs(s->stats->u.run.rs_flushing / s->stats->ts_tid));
seq_printf(seq, " %ums logging transaction\n",
jiffies_to_msecs(s->stats->u.run.rs_logging / s->stats->ts_tid));
seq_printf(seq, " %lu handles per transaction\n",
s->stats->u.run.rs_handle_count / s->stats->ts_tid);
seq_printf(seq, " %lu blocks per transaction\n",
s->stats->u.run.rs_blocks / s->stats->ts_tid);
seq_printf(seq, " %lu logged blocks per transaction\n",
s->stats->u.run.rs_blocks_logged / s->stats->ts_tid);
return 0;
}
static void jbd2_seq_info_stop(struct seq_file *seq, void *v)
{
}
static struct seq_operations jbd2_seq_info_ops = {
.start = jbd2_seq_info_start,
.next = jbd2_seq_info_next,
.stop = jbd2_seq_info_stop,
.show = jbd2_seq_info_show,
};
static int jbd2_seq_info_open(struct inode *inode, struct file *file)
{
journal_t *journal = PDE(inode)->data;
struct jbd2_stats_proc_session *s;
int rc, size;
s = kmalloc(sizeof(*s), GFP_KERNEL);
if (s == NULL)
return -ENOMEM;
size = sizeof(struct transaction_stats_s);
s->stats = kmalloc(size, GFP_KERNEL);
if (s->stats == NULL) {
kfree(s);
return -ENOMEM;
}
spin_lock(&journal->j_history_lock);
memcpy(s->stats, &journal->j_stats, size);
s->journal = journal;
spin_unlock(&journal->j_history_lock);
rc = seq_open(file, &jbd2_seq_info_ops);
if (rc == 0) {
struct seq_file *m = file->private_data;
m->private = s;
} else {
kfree(s->stats);
kfree(s);
}
return rc;
}
static int jbd2_seq_info_release(struct inode *inode, struct file *file)
{
struct seq_file *seq = file->private_data;
struct jbd2_stats_proc_session *s = seq->private;
kfree(s->stats);
kfree(s);
return seq_release(inode, file);
}
static struct file_operations jbd2_seq_info_fops = {
.owner = THIS_MODULE,
.open = jbd2_seq_info_open,
.read = seq_read,
.llseek = seq_lseek,
.release = jbd2_seq_info_release,
};
static struct proc_dir_entry *proc_jbd2_stats;
static void jbd2_stats_proc_init(journal_t *journal)
{
char name[BDEVNAME_SIZE];
snprintf(name, sizeof(name) - 1, "%s", bdevname(journal->j_dev, name));
journal->j_proc_entry = proc_mkdir(name, proc_jbd2_stats);
if (journal->j_proc_entry) {
struct proc_dir_entry *p;
p = create_proc_entry("history", S_IRUGO,
journal->j_proc_entry);
if (p) {
p->proc_fops = &jbd2_seq_history_fops;
p->data = journal;
p = create_proc_entry("info", S_IRUGO,
journal->j_proc_entry);
if (p) {
p->proc_fops = &jbd2_seq_info_fops;
p->data = journal;
}
}
}
}
static void jbd2_stats_proc_exit(journal_t *journal)
{
char name[BDEVNAME_SIZE];
snprintf(name, sizeof(name) - 1, "%s", bdevname(journal->j_dev, name));
remove_proc_entry("info", journal->j_proc_entry);
remove_proc_entry("history", journal->j_proc_entry);
remove_proc_entry(name, proc_jbd2_stats);
}
static void journal_init_stats(journal_t *journal)
{
int size;
if (!proc_jbd2_stats)
return;
journal->j_history_max = 100;
size = sizeof(struct transaction_stats_s) * journal->j_history_max;
journal->j_history = kzalloc(size, GFP_KERNEL);
if (!journal->j_history) {
journal->j_history_max = 0;
return;
}
spin_lock_init(&journal->j_history_lock);
}
/*
* Management for journal control blocks: functions to create and
* destroy journal_t structures, and to initialise and read existing
@ -681,6 +988,9 @@ static journal_t * journal_init_common (void)
kfree(journal);
goto fail;
}
journal_init_stats(journal);
return journal;
fail:
return NULL;
@ -735,6 +1045,7 @@ journal_t * jbd2_journal_init_dev(struct block_device *bdev,
journal->j_fs_dev = fs_dev;
journal->j_blk_offset = start;
journal->j_maxlen = len;
jbd2_stats_proc_init(journal);
bh = __getblk(journal->j_dev, start, journal->j_blocksize);
J_ASSERT(bh != NULL);
@ -773,6 +1084,7 @@ journal_t * jbd2_journal_init_inode (struct inode *inode)
journal->j_maxlen = inode->i_size >> inode->i_sb->s_blocksize_bits;
journal->j_blocksize = inode->i_sb->s_blocksize;
jbd2_stats_proc_init(journal);
/* journal descriptor can store up to n blocks -bzzz */
n = journal->j_blocksize / sizeof(journal_block_tag_t);
@ -1153,6 +1465,8 @@ void jbd2_journal_destroy(journal_t *journal)
brelse(journal->j_sb_buffer);
}
if (journal->j_proc_entry)
jbd2_stats_proc_exit(journal);
if (journal->j_inode)
iput(journal->j_inode);
if (journal->j_revoke)
@ -1264,6 +1578,32 @@ int jbd2_journal_set_features (journal_t *journal, unsigned long compat,
return 1;
}
/*
* jbd2_journal_clear_features () - Clear a given journal feature in the
* superblock
* @journal: Journal to act on.
* @compat: bitmask of compatible features
* @ro: bitmask of features that force read-only mount
* @incompat: bitmask of incompatible features
*
* Clear a given journal feature as present on the
* superblock.
*/
void jbd2_journal_clear_features(journal_t *journal, unsigned long compat,
unsigned long ro, unsigned long incompat)
{
journal_superblock_t *sb;
jbd_debug(1, "Clear features 0x%lx/0x%lx/0x%lx\n",
compat, ro, incompat);
sb = journal->j_superblock;
sb->s_feature_compat &= ~cpu_to_be32(compat);
sb->s_feature_ro_compat &= ~cpu_to_be32(ro);
sb->s_feature_incompat &= ~cpu_to_be32(incompat);
}
EXPORT_SYMBOL(jbd2_journal_clear_features);
/**
* int jbd2_journal_update_format () - Update on-disk journal structure.
@ -1633,7 +1973,7 @@ static int journal_init_jbd2_journal_head_cache(void)
jbd2_journal_head_cache = kmem_cache_create("jbd2_journal_head",
sizeof(struct journal_head),
0, /* offset */
0, /* flags */
SLAB_TEMPORARY, /* flags */
NULL); /* ctor */
retval = 0;
if (jbd2_journal_head_cache == 0) {
@ -1900,6 +2240,28 @@ static void __exit jbd2_remove_debugfs_entry(void)
#endif
#ifdef CONFIG_PROC_FS
#define JBD2_STATS_PROC_NAME "fs/jbd2"
static void __init jbd2_create_jbd_stats_proc_entry(void)
{
proc_jbd2_stats = proc_mkdir(JBD2_STATS_PROC_NAME, NULL);
}
static void __exit jbd2_remove_jbd_stats_proc_entry(void)
{
if (proc_jbd2_stats)
remove_proc_entry(JBD2_STATS_PROC_NAME, NULL);
}
#else
#define jbd2_create_jbd_stats_proc_entry() do {} while (0)
#define jbd2_remove_jbd_stats_proc_entry() do {} while (0)
#endif
struct kmem_cache *jbd2_handle_cache;
static int __init journal_init_handle_cache(void)
@ -1907,7 +2269,7 @@ static int __init journal_init_handle_cache(void)
jbd2_handle_cache = kmem_cache_create("jbd2_journal_handle",
sizeof(handle_t),
0, /* offset */
0, /* flags */
SLAB_TEMPORARY, /* flags */
NULL); /* ctor */
if (jbd2_handle_cache == NULL) {
printk(KERN_EMERG "JBD: failed to create handle cache\n");
@ -1955,6 +2317,7 @@ static int __init journal_init(void)
if (ret != 0)
jbd2_journal_destroy_caches();
jbd2_create_debugfs_entry();
jbd2_create_jbd_stats_proc_entry();
return ret;
}
@ -1966,6 +2329,7 @@ static void __exit journal_exit(void)
printk(KERN_EMERG "JBD: leaked %d journal_heads!\n", n);
#endif
jbd2_remove_debugfs_entry();
jbd2_remove_jbd_stats_proc_entry();
jbd2_journal_destroy_caches();
}

151
fs/jbd2/recovery.c
View file

@ -21,6 +21,7 @@
#include <linux/jbd2.h>
#include <linux/errno.h>
#include <linux/slab.h>
#include <linux/crc32.h>
#endif
/*
@ -316,6 +317,37 @@ static inline unsigned long long read_tag_block(int tag_bytes, journal_block_tag
return block;
}
/*
* calc_chksums calculates the checksums for the blocks described in the
* descriptor block.
*/
static int calc_chksums(journal_t *journal, struct buffer_head *bh,
unsigned long *next_log_block, __u32 *crc32_sum)
{
int i, num_blks, err;
unsigned long io_block;
struct buffer_head *obh;
num_blks = count_tags(journal, bh);
/* Calculate checksum of the descriptor block. */
*crc32_sum = crc32_be(*crc32_sum, (void *)bh->b_data, bh->b_size);
for (i = 0; i < num_blks; i++) {
io_block = (*next_log_block)++;
wrap(journal, *next_log_block);
err = jread(&obh, journal, io_block);
if (err) {
printk(KERN_ERR "JBD: IO error %d recovering block "
"%lu in log\n", err, io_block);
return 1;
} else {
*crc32_sum = crc32_be(*crc32_sum, (void *)obh->b_data,
obh->b_size);
}
}
return 0;
}
static int do_one_pass(journal_t *journal,
struct recovery_info *info, enum passtype pass)
{
@ -328,6 +360,7 @@ static int do_one_pass(journal_t *journal,
unsigned int sequence;
int blocktype;
int tag_bytes = journal_tag_bytes(journal);
__u32 crc32_sum = ~0; /* Transactional Checksums */
/* Precompute the maximum metadata descriptors in a descriptor block */
int MAX_BLOCKS_PER_DESC;
@ -419,12 +452,26 @@ static int do_one_pass(journal_t *journal,
switch(blocktype) {
case JBD2_DESCRIPTOR_BLOCK:
/* If it is a valid descriptor block, replay it
* in pass REPLAY; otherwise, just skip over the
* blocks it describes. */
* in pass REPLAY; if journal_checksums enabled, then
* calculate checksums in PASS_SCAN, otherwise,
* just skip over the blocks it describes. */
if (pass != PASS_REPLAY) {
if (pass == PASS_SCAN &&
JBD2_HAS_COMPAT_FEATURE(journal,
JBD2_FEATURE_COMPAT_CHECKSUM) &&
!info->end_transaction) {
if (calc_chksums(journal, bh,
&next_log_block,
&crc32_sum)) {
put_bh(bh);
break;
}
put_bh(bh);
continue;
}
next_log_block += count_tags(journal, bh);
wrap(journal, next_log_block);
brelse(bh);
put_bh(bh);
continue;
}
@ -516,9 +563,96 @@ static int do_one_pass(journal_t *journal,
continue;
case JBD2_COMMIT_BLOCK:
/* Found an expected commit block: not much to
* do other than move on to the next sequence
/* How to differentiate between interrupted commit
* and journal corruption ?
*
* {nth transaction}
* Checksum Verification Failed
* |
* ____________________
* | |
* async_commit sync_commit
* | |
* | GO TO NEXT "Journal Corruption"
* | TRANSACTION
* |
* {(n+1)th transanction}
* |
* _______|______________
* | |
* Commit block found Commit block not found
* | |
* "Journal Corruption" |
* _____________|_________
* | |
* nth trans corrupt OR nth trans
* and (n+1)th interrupted interrupted
* before commit block
* could reach the disk.
* (Cannot find the difference in above
* mentioned conditions. Hence assume
* "Interrupted Commit".)
*/
/* Found an expected commit block: if checksums
* are present verify them in PASS_SCAN; else not
* much to do other than move on to the next sequence
* number. */
if (pass == PASS_SCAN &&
JBD2_HAS_COMPAT_FEATURE(journal,
JBD2_FEATURE_COMPAT_CHECKSUM)) {
int chksum_err, chksum_seen;
struct commit_header *cbh =
(struct commit_header *)bh->b_data;
unsigned found_chksum =
be32_to_cpu(cbh->h_chksum[0]);
chksum_err = chksum_seen = 0;
if (info->end_transaction) {
printk(KERN_ERR "JBD: Transaction %u "
"found to be corrupt.\n",
next_commit_ID - 1);
brelse(bh);
break;
}
if (crc32_sum == found_chksum &&
cbh->h_chksum_type == JBD2_CRC32_CHKSUM &&
cbh->h_chksum_size ==
JBD2_CRC32_CHKSUM_SIZE)
chksum_seen = 1;
else if (!(cbh->h_chksum_type == 0 &&
cbh->h_chksum_size == 0 &&
found_chksum == 0 &&
!chksum_seen))
/*
* If fs is mounted using an old kernel and then
* kernel with journal_chksum is used then we
* get a situation where the journal flag has
* checksum flag set but checksums are not
* present i.e chksum = 0, in the individual
* commit blocks.
* Hence to avoid checksum failures, in this
* situation, this extra check is added.
*/
chksum_err = 1;
if (chksum_err) {
info->end_transaction = next_commit_ID;
if (!JBD2_HAS_COMPAT_FEATURE(journal,
JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT)){
printk(KERN_ERR
"JBD: Transaction %u "
"found to be corrupt.\n",
next_commit_ID);
brelse(bh);
break;
}
}
crc32_sum = ~0;
}
brelse(bh);
next_commit_ID++;
continue;
@ -554,9 +688,10 @@ static int do_one_pass(journal_t *journal,
* transaction marks the end of the valid log.
*/
if (pass == PASS_SCAN)
info->end_transaction = next_commit_ID;
else {
if (pass == PASS_SCAN) {
if (!info->end_transaction)
info->end_transaction = next_commit_ID;
} else {
/* It's really bad news if different passes end up at
* different places (but possible due to IO errors). */
if (info->end_transaction != next_commit_ID) {

6
fs/jbd2/revoke.c
View file

@ -171,13 +171,15 @@ int __init jbd2_journal_init_revoke_caches(void)
{
jbd2_revoke_record_cache = kmem_cache_create("jbd2_revoke_record",
sizeof(struct jbd2_revoke_record_s),
0, SLAB_HWCACHE_ALIGN, NULL);
0,
SLAB_HWCACHE_ALIGN|SLAB_TEMPORARY,
NULL);
if (jbd2_revoke_record_cache == 0)
return -ENOMEM;
jbd2_revoke_table_cache = kmem_cache_create("jbd2_revoke_table",
sizeof(struct jbd2_revoke_table_s),
0, 0, NULL);
0, SLAB_TEMPORARY, NULL);
if (jbd2_revoke_table_cache == 0) {
kmem_cache_destroy(jbd2_revoke_record_cache);
jbd2_revoke_record_cache = NULL;

34
fs/jbd2/transaction.c
View file

@ -54,11 +54,13 @@ jbd2_get_transaction(journal_t *journal, transaction_t *transaction)
spin_lock_init(&transaction->t_handle_lock);
/* Set up the commit timer for the new transaction. */
journal->j_commit_timer.expires = transaction->t_expires;
journal->j_commit_timer.expires = round_jiffies(transaction->t_expires);
add_timer(&journal->j_commit_timer);
J_ASSERT(journal->j_running_transaction == NULL);
journal->j_running_transaction = transaction;
transaction->t_max_wait = 0;
transaction->t_start = jiffies;
return transaction;
}
@ -85,6 +87,7 @@ static int start_this_handle(journal_t *journal, handle_t *handle)
int nblocks = handle->h_buffer_credits;
transaction_t *new_transaction = NULL;
int ret = 0;
unsigned long ts = jiffies;
if (nblocks > journal->j_max_transaction_buffers) {
printk(KERN_ERR "JBD: %s wants too many credits (%d > %d)\n",
@ -217,6 +220,12 @@ repeat_locked:
/* OK, account for the buffers that this operation expects to
* use and add the handle to the running transaction. */
if (time_after(transaction->t_start, ts)) {
ts = jbd2_time_diff(ts, transaction->t_start);
if (ts > transaction->t_max_wait)
transaction->t_max_wait = ts;
}
handle->h_transaction = transaction;
transaction->t_outstanding_credits += nblocks;
transaction->t_updates++;
@ -232,6 +241,8 @@ out:
return ret;
}
static struct lock_class_key jbd2_handle_key;
/* Allocate a new handle. This should probably be in a slab... */
static handle_t *new_handle(int nblocks)
{
@ -242,6 +253,9 @@ static handle_t *new_handle(int nblocks)
handle->h_buffer_credits = nblocks;
handle->h_ref = 1;
lockdep_init_map(&handle->h_lockdep_map, "jbd2_handle",
&jbd2_handle_key, 0);
return handle;
}
@ -284,7 +298,11 @@ handle_t *jbd2_journal_start(journal_t *journal, int nblocks)
jbd2_free_handle(handle);
current->journal_info = NULL;
handle = ERR_PTR(err);
goto out;
}
lock_acquire(&handle->h_lockdep_map, 0, 0, 0, 2, _THIS_IP_);
out:
return handle;
}
@ -1164,7 +1182,7 @@ int jbd2_journal_dirty_metadata(handle_t *handle, struct buffer_head *bh)
}
/* That test should have eliminated the following case: */
J_ASSERT_JH(jh, jh->b_frozen_data == 0);
J_ASSERT_JH(jh, jh->b_frozen_data == NULL);
JBUFFER_TRACE(jh, "file as BJ_Metadata");
spin_lock(&journal->j_list_lock);
@ -1410,6 +1428,8 @@ int jbd2_journal_stop(handle_t *handle)
spin_unlock(&journal->j_state_lock);
}
lock_release(&handle->h_lockdep_map, 1, _THIS_IP_);
jbd2_free_handle(handle);
return err;
}
@ -1512,7 +1532,7 @@ void __jbd2_journal_temp_unlink_buffer(struct journal_head *jh)
J_ASSERT_JH(jh, jh->b_jlist < BJ_Types);
if (jh->b_jlist != BJ_None)
J_ASSERT_JH(jh, transaction != 0);
J_ASSERT_JH(jh, transaction != NULL);
switch (jh->b_jlist) {
case BJ_None:
@ -1581,11 +1601,11 @@ __journal_try_to_free_buffer(journal_t *journal, struct buffer_head *bh)
if (buffer_locked(bh) || buffer_dirty(bh))
goto out;
if (jh->b_next_transaction != 0)
if (jh->b_next_transaction != NULL)
goto out;
spin_lock(&journal->j_list_lock);
if (jh->b_transaction != 0 && jh->b_cp_transaction == 0) {
if (jh->b_transaction != NULL && jh->b_cp_transaction == NULL) {
if (jh->b_jlist == BJ_SyncData || jh->b_jlist == BJ_Locked) {
/* A written-back ordered data buffer */
JBUFFER_TRACE(jh, "release data");
@ -1593,7 +1613,7 @@ __journal_try_to_free_buffer(journal_t *journal, struct buffer_head *bh)
jbd2_journal_remove_journal_head(bh);
__brelse(bh);
}
} else if (jh->b_cp_transaction != 0 && jh->b_transaction == 0) {
} else if (jh->b_cp_transaction != NULL && jh->b_transaction == NULL) {
/* written-back checkpointed metadata buffer */
if (jh->b_jlist == BJ_None) {
JBUFFER_TRACE(jh, "remove from checkpoint list");
@ -1953,7 +1973,7 @@ void __jbd2_journal_file_buffer(struct journal_head *jh,
J_ASSERT_JH(jh, jh->b_jlist < BJ_Types);
J_ASSERT_JH(jh, jh->b_transaction == transaction ||
jh->b_transaction == 0);
jh->b_transaction == NULL);
if (jh->b_transaction && jh->b_jlist == jlist)
return;

1
fs/read_write.c
View file

@ -446,6 +446,7 @@ unsigned long iov_shorten(struct iovec *iov, unsigned long nr_segs, size_t to)
}
return seg;
}
EXPORT_SYMBOL(iov_shorten);
ssize_t do_sync_readv_writev(struct file *filp, const struct iovec *iov,
unsigned long nr_segs, size_t len, loff_t *ppos, iov_fn_t fn)

2
include/asm-arm/bitops.h
View file

@ -310,6 +310,8 @@ static inline int constant_fls(int x)
_find_first_zero_bit_le(p,sz)
#define ext2_find_next_zero_bit(p,sz,off) \
_find_next_zero_bit_le(p,sz,off)
#define ext2_find_next_bit(p, sz, off) \
_find_next_bit_le(p, sz, off)
/*
* Minix is defined to use little-endian byte ordering.

2
include/asm-generic/bitops/ext2-non-atomic.h
View file

@ -14,5 +14,7 @@
generic_find_first_zero_le_bit((unsigned long *)(addr), (size))
#define ext2_find_next_zero_bit(addr, size, off) \
generic_find_next_zero_le_bit((unsigned long *)(addr), (size), (off))
#define ext2_find_next_bit(addr, size, off) \
generic_find_next_le_bit((unsigned long *)(addr), (size), (off))
#endif /* _ASM_GENERIC_BITOPS_EXT2_NON_ATOMIC_H_ */

4
include/asm-generic/bitops/le.h
View file

@ -20,6 +20,8 @@
#define generic___test_and_clear_le_bit(nr, addr) __test_and_clear_bit(nr, addr)
#define generic_find_next_zero_le_bit(addr, size, offset) find_next_zero_bit(addr, size, offset)
#define generic_find_next_le_bit(addr, size, offset) \
find_next_bit(addr, size, offset)
#elif defined(__BIG_ENDIAN)
@ -42,6 +44,8 @@
extern unsigned long generic_find_next_zero_le_bit(const unsigned long *addr,
unsigned long size, unsigned long offset);
extern unsigned long generic_find_next_le_bit(const unsigned long *addr,
unsigned long size, unsigned long offset);
#else
#error "Please fix <asm/byteorder.h>"

2
include/asm-m68k/bitops.h
View file

@ -410,6 +410,8 @@ static inline int ext2_find_next_zero_bit(const void *vaddr, unsigned size,
res = ext2_find_first_zero_bit (p, size - 32 * (p - addr));
return (p - addr) * 32 + res;
}
#define ext2_find_next_bit(addr, size, off) \
generic_find_next_le_bit((unsigned long *)(addr), (size), (off))
#endif /* __KERNEL__ */

2
include/asm-m68knommu/bitops.h
View file

@ -294,6 +294,8 @@ found_middle:
return result + ffz(__swab32(tmp));
}
#define ext2_find_next_bit(addr, size, off) \
generic_find_next_le_bit((unsigned long *)(addr), (size), (off))
#include <asm-generic/bitops/minix.h>
#endif /* __KERNEL__ */

4
include/asm-powerpc/bitops.h
View file

@ -359,6 +359,8 @@ static __inline__ int test_le_bit(unsigned long nr,
unsigned long generic_find_next_zero_le_bit(const unsigned long *addr,
unsigned long size, unsigned long offset);
unsigned long generic_find_next_le_bit(const unsigned long *addr,
unsigned long size, unsigned long offset);
/* Bitmap functions for the ext2 filesystem */
#define ext2_set_bit(nr,addr) \
@ -378,6 +380,8 @@ unsigned long generic_find_next_zero_le_bit(const unsigned long *addr,
#define ext2_find_next_zero_bit(addr, size, off) \
generic_find_next_zero_le_bit((unsigned long*)addr, size, off)
#define ext2_find_next_bit(addr, size, off) \
generic_find_next_le_bit((unsigned long *)addr, size, off)
/* Bitmap functions for the minix filesystem. */
#define minix_test_and_set_bit(nr,addr) \

2
include/asm-s390/bitops.h
View file

@ -772,6 +772,8 @@ static inline int sched_find_first_bit(unsigned long *b)
test_and_clear_bit((nr)^(__BITOPS_WORDSIZE - 8), (unsigned long *)addr)
#define ext2_test_bit(nr, addr) \
test_bit((nr)^(__BITOPS_WORDSIZE - 8), (unsigned long *)addr)
#define ext2_find_next_bit(addr, size, off) \
generic_find_next_le_bit((unsigned long *)(addr), (size), (off))
#ifndef __s390x__

2
include/linux/buffer_head.h
View file

@ -192,6 +192,8 @@ int sync_dirty_buffer(struct buffer_head *bh);
int submit_bh(int, struct buffer_head *);
void write_boundary_block(struct block_device *bdev,
sector_t bblock, unsigned blocksize);
int bh_uptodate_or_lock(struct buffer_head *bh);
int bh_submit_read(struct buffer_head *bh);
extern int buffer_heads_over_limit;

198
include/linux/ext4_fs.h
View file

@ -20,6 +20,8 @@
#include <linux/blkdev.h>
#include <linux/magic.h>
#include <linux/ext4_fs_i.h>
/*
* The second extended filesystem constants/structures
*/
@ -51,6 +53,50 @@
#define ext4_debug(f, a...) do {} while (0)
#endif
#define EXT4_MULTIBLOCK_ALLOCATOR 1
/* prefer goal again. length */
#define EXT4_MB_HINT_MERGE 1
/* blocks already reserved */
#define EXT4_MB_HINT_RESERVED 2
/* metadata is being allocated */
#define EXT4_MB_HINT_METADATA 4
/* first blocks in the file */
#define EXT4_MB_HINT_FIRST 8
/* search for the best chunk */
#define EXT4_MB_HINT_BEST 16
/* data is being allocated */
#define EXT4_MB_HINT_DATA 32
/* don't preallocate (for tails) */
#define EXT4_MB_HINT_NOPREALLOC 64
/* allocate for locality group */
#define EXT4_MB_HINT_GROUP_ALLOC 128
/* allocate goal blocks or none */
#define EXT4_MB_HINT_GOAL_ONLY 256
/* goal is meaningful */
#define EXT4_MB_HINT_TRY_GOAL 512
struct ext4_allocation_request {
/* target inode for block we're allocating */
struct inode *inode;
/* logical block in target inode */
ext4_lblk_t logical;
/* phys. target (a hint) */
ext4_fsblk_t goal;
/* the closest logical allocated block to the left */
ext4_lblk_t lleft;
/* phys. block for ^^^ */
ext4_fsblk_t pleft;
/* the closest logical allocated block to the right */
ext4_lblk_t lright;
/* phys. block for ^^^ */
ext4_fsblk_t pright;
/* how many blocks we want to allocate */
unsigned long len;
/* flags. see above EXT4_MB_HINT_* */
unsigned long flags;
};
/*
* Special inodes numbers
*/
@ -73,8 +119,8 @@
* Macro-instructions used to manage several block sizes
*/
#define EXT4_MIN_BLOCK_SIZE 1024
#define EXT4_MAX_BLOCK_SIZE 4096
#define EXT4_MIN_BLOCK_LOG_SIZE 10
#define EXT4_MAX_BLOCK_SIZE 65536
#define EXT4_MIN_BLOCK_LOG_SIZE 10
#ifdef __KERNEL__
# define EXT4_BLOCK_SIZE(s) ((s)->s_blocksize)
#else
@ -118,6 +164,11 @@ struct ext4_group_desc
__le32 bg_block_bitmap_hi; /* Blocks bitmap block MSB */
__le32 bg_inode_bitmap_hi; /* Inodes bitmap block MSB */
__le32 bg_inode_table_hi; /* Inodes table block MSB */
__le16 bg_free_blocks_count_hi;/* Free blocks count MSB */
__le16 bg_free_inodes_count_hi;/* Free inodes count MSB */
__le16 bg_used_dirs_count_hi; /* Directories count MSB */
__le16 bg_itable_unused_hi; /* Unused inodes count MSB */
__u32 bg_reserved2[3];
};
#define EXT4_BG_INODE_UNINIT 0x0001 /* Inode table/bitmap not in use */
@ -178,8 +229,9 @@ struct ext4_group_desc
#define EXT4_NOTAIL_FL 0x00008000 /* file tail should not be merged */
#define EXT4_DIRSYNC_FL 0x00010000 /* dirsync behaviour (directories only) */
#define EXT4_TOPDIR_FL 0x00020000 /* Top of directory hierarchies*/
#define EXT4_RESERVED_FL 0x80000000 /* reserved for ext4 lib */
#define EXT4_HUGE_FILE_FL 0x00040000 /* Set to each huge file */
#define EXT4_EXTENTS_FL 0x00080000 /* Inode uses extents */
#define EXT4_RESERVED_FL 0x80000000 /* reserved for ext4 lib */
#define EXT4_FL_USER_VISIBLE 0x000BDFFF /* User visible flags */
#define EXT4_FL_USER_MODIFIABLE 0x000380FF /* User modifiable flags */
@ -237,6 +289,7 @@ struct ext4_new_group_data {
#endif
#define EXT4_IOC_GETRSVSZ _IOR('f', 5, long)
#define EXT4_IOC_SETRSVSZ _IOW('f', 6, long)
#define EXT4_IOC_MIGRATE _IO('f', 7)
/*
* ioctl commands in 32 bit emulation
@ -275,18 +328,18 @@ struct ext4_mount_options {
struct ext4_inode {
__le16 i_mode; /* File mode */
__le16 i_uid; /* Low 16 bits of Owner Uid */
__le32 i_size; /* Size in bytes */
__le32 i_size_lo; /* Size in bytes */
__le32 i_atime; /* Access time */
__le32 i_ctime; /* Inode Change time */
__le32 i_mtime; /* Modification time */
__le32 i_dtime; /* Deletion Time */
__le16 i_gid; /* Low 16 bits of Group Id */
__le16 i_links_count; /* Links count */
__le32 i_blocks; /* Blocks count */
__le32 i_blocks_lo; /* Blocks count */
__le32 i_flags; /* File flags */
union {
struct {
__u32 l_i_reserved1;
__le32 l_i_version;
} linux1;
struct {
__u32 h_i_translator;
@ -297,12 +350,12 @@ struct ext4_inode {
} osd1; /* OS dependent 1 */
__le32 i_block[EXT4_N_BLOCKS];/* Pointers to blocks */
__le32 i_generation; /* File version (for NFS) */
__le32 i_file_acl; /* File ACL */
__le32 i_dir_acl; /* Directory ACL */
__le32 i_file_acl_lo; /* File ACL */
__le32 i_size_high;
__le32 i_obso_faddr; /* Obsoleted fragment address */
union {
struct {
__le16 l_i_reserved1; /* Obsoleted fragment number/size which are removed in ext4 */
__le16 l_i_blocks_high; /* were l_i_reserved1 */
__le16 l_i_file_acl_high;
__le16 l_i_uid_high; /* these 2 fields */
__le16 l_i_gid_high; /* were reserved2[0] */
@ -328,9 +381,9 @@ struct ext4_inode {
__le32 i_atime_extra; /* extra Access time (nsec << 2 | epoch) */
__le32 i_crtime; /* File Creation time */
__le32 i_crtime_extra; /* extra FileCreationtime (nsec << 2 | epoch) */
__le32 i_version_hi; /* high 32 bits for 64-bit version */
};
#define i_size_high i_dir_acl
#define EXT4_EPOCH_BITS 2
#define EXT4_EPOCH_MASK ((1 << EXT4_EPOCH_BITS) - 1)
@ -402,9 +455,12 @@ do { \
raw_inode->xtime ## _extra); \
} while (0)
#define i_disk_version osd1.linux1.l_i_version
#if defined(__KERNEL__) || defined(__linux__)
#define i_reserved1 osd1.linux1.l_i_reserved1
#define i_file_acl_high osd2.linux2.l_i_file_acl_high
#define i_blocks_high osd2.linux2.l_i_blocks_high
#define i_uid_low i_uid
#define i_gid_low i_gid
#define i_uid_high osd2.linux2.l_i_uid_high
@ -461,7 +517,10 @@ do { \
#define EXT4_MOUNT_USRQUOTA 0x100000 /* "old" user quota */
#define EXT4_MOUNT_GRPQUOTA 0x200000 /* "old" group quota */
#define EXT4_MOUNT_EXTENTS 0x400000 /* Extents support */
#define EXT4_MOUNT_JOURNAL_CHECKSUM 0x800000 /* Journal checksums */
#define EXT4_MOUNT_JOURNAL_ASYNC_COMMIT 0x1000000 /* Journal Async Commit */
#define EXT4_MOUNT_I_VERSION 0x2000000 /* i_version support */
#define EXT4_MOUNT_MBALLOC 0x4000000 /* Buddy allocation support */
/* Compatibility, for having both ext2_fs.h and ext4_fs.h included at once */
#ifndef _LINUX_EXT2_FS_H
#define clear_opt(o, opt) o &= ~EXT4_MOUNT_##opt
@ -481,6 +540,7 @@ do { \
#define ext4_test_bit ext2_test_bit
#define ext4_find_first_zero_bit ext2_find_first_zero_bit
#define ext4_find_next_zero_bit ext2_find_next_zero_bit
#define ext4_find_next_bit ext2_find_next_bit
/*
* Maximal mount counts between two filesystem checks
@ -671,6 +731,7 @@ static inline int ext4_valid_inum(struct super_block *sb, unsigned long ino)
#define EXT4_FEATURE_RO_COMPAT_SPARSE_SUPER 0x0001
#define EXT4_FEATURE_RO_COMPAT_LARGE_FILE 0x0002
#define EXT4_FEATURE_RO_COMPAT_BTREE_DIR 0x0004
#define EXT4_FEATURE_RO_COMPAT_HUGE_FILE 0x0008
#define EXT4_FEATURE_RO_COMPAT_GDT_CSUM 0x0010
#define EXT4_FEATURE_RO_COMPAT_DIR_NLINK 0x0020
#define EXT4_FEATURE_RO_COMPAT_EXTRA_ISIZE 0x0040
@ -682,6 +743,7 @@ static inline int ext4_valid_inum(struct super_block *sb, unsigned long ino)
#define EXT4_FEATURE_INCOMPAT_META_BG 0x0010
#define EXT4_FEATURE_INCOMPAT_EXTENTS 0x0040 /* extents support */
#define EXT4_FEATURE_INCOMPAT_64BIT 0x0080
#define EXT4_FEATURE_INCOMPAT_MMP 0x0100
#define EXT4_FEATURE_INCOMPAT_FLEX_BG 0x0200
#define EXT4_FEATURE_COMPAT_SUPP EXT2_FEATURE_COMPAT_EXT_ATTR
@ -696,7 +758,8 @@ static inline int ext4_valid_inum(struct super_block *sb, unsigned long ino)
EXT4_FEATURE_RO_COMPAT_GDT_CSUM| \
EXT4_FEATURE_RO_COMPAT_DIR_NLINK | \
EXT4_FEATURE_RO_COMPAT_EXTRA_ISIZE | \
EXT4_FEATURE_RO_COMPAT_BTREE_DIR)
EXT4_FEATURE_RO_COMPAT_BTREE_DIR |\
EXT4_FEATURE_RO_COMPAT_HUGE_FILE)
/*
* Default values for user and/or group using reserved blocks
@ -767,6 +830,26 @@ struct ext4_dir_entry_2 {
#define EXT4_DIR_ROUND (EXT4_DIR_PAD - 1)
#define EXT4_DIR_REC_LEN(name_len) (((name_len) + 8 + EXT4_DIR_ROUND) & \
~EXT4_DIR_ROUND)
#define EXT4_MAX_REC_LEN ((1<<16)-1)
static inline unsigned ext4_rec_len_from_disk(__le16 dlen)
{
unsigned len = le16_to_cpu(dlen);
if (len == EXT4_MAX_REC_LEN)
return 1 << 16;
return len;
}
static inline __le16 ext4_rec_len_to_disk(unsigned len)
{
if (len == (1 << 16))
return cpu_to_le16(EXT4_MAX_REC_LEN);
else if (len > (1 << 16))
BUG();
return cpu_to_le16(len);
}
/*
* Hash Tree Directory indexing
* (c) Daniel Phillips, 2001
@ -810,7 +893,7 @@ struct ext4_iloc
{
struct buffer_head *bh;
unsigned long offset;
unsigned long block_group;
ext4_group_t block_group;
};
static inline struct ext4_inode *ext4_raw_inode(struct ext4_iloc *iloc)
@ -835,7 +918,7 @@ struct dir_private_info {
/* calculate the first block number of the group */
static inline ext4_fsblk_t
ext4_group_first_block_no(struct super_block *sb, unsigned long group_no)
ext4_group_first_block_no(struct super_block *sb, ext4_group_t group_no)
{
return group_no * (ext4_fsblk_t)EXT4_BLOCKS_PER_GROUP(sb) +
le32_to_cpu(EXT4_SB(sb)->s_es->s_first_data_block);
@ -866,21 +949,24 @@ extern unsigned int ext4_block_group(struct super_block *sb,
ext4_fsblk_t blocknr);
extern ext4_grpblk_t ext4_block_group_offset(struct super_block *sb,
ext4_fsblk_t blocknr);
extern int ext4_bg_has_super(struct super_block *sb, int group);
extern unsigned long ext4_bg_num_gdb(struct super_block *sb, int group);
extern int ext4_bg_has_super(struct super_block *sb, ext4_group_t group);
extern unsigned long ext4_bg_num_gdb(struct super_block *sb,
ext4_group_t group);
extern ext4_fsblk_t ext4_new_block (handle_t *handle, struct inode *inode,
ext4_fsblk_t goal, int *errp);
extern ext4_fsblk_t ext4_new_blocks (handle_t *handle, struct inode *inode,
ext4_fsblk_t goal, unsigned long *count, int *errp);
extern ext4_fsblk_t ext4_new_blocks_old(handle_t *handle, struct inode *inode,
ext4_fsblk_t goal, unsigned long *count, int *errp);
extern void ext4_free_blocks (handle_t *handle, struct inode *inode,
ext4_fsblk_t block, unsigned long count);
ext4_fsblk_t block, unsigned long count, int metadata);
extern void ext4_free_blocks_sb (handle_t *handle, struct super_block *sb,
ext4_fsblk_t block, unsigned long count,
unsigned long *pdquot_freed_blocks);
extern ext4_fsblk_t ext4_count_free_blocks (struct super_block *);
extern void ext4_check_blocks_bitmap (struct super_block *);
extern struct ext4_group_desc * ext4_get_group_desc(struct super_block * sb,
unsigned int block_group,
ext4_group_t block_group,
struct buffer_head ** bh);
extern int ext4_should_retry_alloc(struct super_block *sb, int *retries);
extern void ext4_init_block_alloc_info(struct inode *);
@ -911,15 +997,32 @@ extern unsigned long ext4_count_dirs (struct super_block *);
extern void ext4_check_inodes_bitmap (struct super_block *);
extern unsigned long ext4_count_free (struct buffer_head *, unsigned);
/* mballoc.c */
extern long ext4_mb_stats;
extern long ext4_mb_max_to_scan;
extern int ext4_mb_init(struct super_block *, int);
extern int ext4_mb_release(struct super_block *);
extern ext4_fsblk_t ext4_mb_new_blocks(handle_t *,
struct ext4_allocation_request *, int *);
extern int ext4_mb_reserve_blocks(struct super_block *, int);
extern void ext4_mb_discard_inode_preallocations(struct inode *);
extern int __init init_ext4_mballoc(void);
extern void exit_ext4_mballoc(void);
extern void ext4_mb_free_blocks(handle_t *, struct inode *,
unsigned long, unsigned long, int, unsigned long *);
/* inode.c */
int ext4_forget(handle_t *handle, int is_metadata, struct inode *inode,
struct buffer_head *bh, ext4_fsblk_t blocknr);
struct buffer_head * ext4_getblk (handle_t *, struct inode *, long, int, int *);
struct buffer_head * ext4_bread (handle_t *, struct inode *, int, int, int *);
struct buffer_head *ext4_getblk(handle_t *, struct inode *,
ext4_lblk_t, int, int *);
struct buffer_head *ext4_bread(handle_t *, struct inode *,
ext4_lblk_t, int, int *);
int ext4_get_blocks_handle(handle_t *handle, struct inode *inode,
sector_t iblock, unsigned long maxblocks, struct buffer_head *bh_result,
int create, int extend_disksize);
ext4_lblk_t iblock, unsigned long maxblocks,
struct buffer_head *bh_result,
int create, int extend_disksize);
extern void ext4_read_inode (struct inode *);
extern int ext4_write_inode (struct inode *, int);
@ -943,6 +1046,9 @@ extern int ext4_ioctl (struct inode *, struct file *, unsigned int,
unsigned long);
extern long ext4_compat_ioctl (struct file *, unsigned int, unsigned long);
/* migrate.c */
extern int ext4_ext_migrate(struct inode *, struct file *, unsigned int,
unsigned long);
/* namei.c */
extern int ext4_orphan_add(handle_t *, struct inode *);
extern int ext4_orphan_del(handle_t *, struct inode *);
@ -965,6 +1071,12 @@ extern void ext4_abort (struct super_block *, const char *, const char *, ...)
extern void ext4_warning (struct super_block *, const char *, const char *, ...)
__attribute__ ((format (printf, 3, 4)));
extern void ext4_update_dynamic_rev (struct super_block *sb);
extern int ext4_update_compat_feature(handle_t *handle, struct super_block *sb,
__u32 compat);
extern int ext4_update_rocompat_feature(handle_t *handle,
struct super_block *sb, __u32 rocompat);
extern int ext4_update_incompat_feature(handle_t *handle,
struct super_block *sb, __u32 incompat);
extern ext4_fsblk_t ext4_block_bitmap(struct super_block *sb,
struct ext4_group_desc *bg);
extern ext4_fsblk_t ext4_inode_bitmap(struct super_block *sb,
@ -1017,6 +1129,29 @@ static inline void ext4_r_blocks_count_set(struct ext4_super_block *es,
es->s_r_blocks_count_hi = cpu_to_le32(blk >> 32);
}
static inline loff_t ext4_isize(struct ext4_inode *raw_inode)
{
return ((loff_t)le32_to_cpu(raw_inode->i_size_high) << 32) |
le32_to_cpu(raw_inode->i_size_lo);
}
static inline void ext4_isize_set(struct ext4_inode *raw_inode, loff_t i_size)
{
raw_inode->i_size_lo = cpu_to_le32(i_size);
raw_inode->i_size_high = cpu_to_le32(i_size >> 32);
}
static inline
struct ext4_group_info *ext4_get_group_info(struct super_block *sb,
ext4_group_t group)
{
struct ext4_group_info ***grp_info;
long indexv, indexh;
grp_info = EXT4_SB(sb)->s_group_info;
indexv = group >> (EXT4_DESC_PER_BLOCK_BITS(sb));
indexh = group & ((EXT4_DESC_PER_BLOCK(sb)) - 1);
return grp_info[indexv][indexh];
}
#define ext4_std_error(sb, errno) \
@ -1048,7 +1183,7 @@ extern const struct inode_operations ext4_fast_symlink_inode_operations;
extern int ext4_ext_tree_init(handle_t *handle, struct inode *);
extern int ext4_ext_writepage_trans_blocks(struct inode *, int);
extern int ext4_ext_get_blocks(handle_t *handle, struct inode *inode,
ext4_fsblk_t iblock,
ext4_lblk_t iblock,
unsigned long max_blocks, struct buffer_head *bh_result,
int create, int extend_disksize);
extern void ext4_ext_truncate(struct inode *, struct page *);
@ -1056,19 +1191,10 @@ extern void ext4_ext_init(struct super_block *);
extern void ext4_ext_release(struct super_block *);
extern long ext4_fallocate(struct inode *inode, int mode, loff_t offset,
loff_t len);
static inline int
ext4_get_blocks_wrap(handle_t *handle, struct inode *inode, sector_t block,
unsigned long max_blocks, struct buffer_head *bh,
int create, int extend_disksize)
{
if (EXT4_I(inode)->i_flags & EXT4_EXTENTS_FL)
return ext4_ext_get_blocks(handle, inode, block, max_blocks,
bh, create, extend_disksize);
return ext4_get_blocks_handle(handle, inode, block, max_blocks, bh,
create, extend_disksize);
}
extern int ext4_get_blocks_wrap(handle_t *handle, struct inode *inode,
sector_t block, unsigned long max_blocks,
struct buffer_head *bh, int create,
int extend_disksize);
#endif /* __KERNEL__ */
#endif /* _LINUX_EXT4_FS_H */

25
include/linux/ext4_fs_extents.h
View file

@ -124,20 +124,6 @@ struct ext4_ext_path {
#define EXT4_EXT_CACHE_GAP 1
#define EXT4_EXT_CACHE_EXTENT 2
/*
* to be called by ext4_ext_walk_space()
* negative retcode - error
* positive retcode - signal for ext4_ext_walk_space(), see below
* callback must return valid extent (passed or newly created)
*/
typedef int (*ext_prepare_callback)(struct inode *, struct ext4_ext_path *,
struct ext4_ext_cache *,
void *);
#define EXT_CONTINUE 0
#define EXT_BREAK 1
#define EXT_REPEAT 2
#define EXT_MAX_BLOCK 0xffffffff
@ -226,6 +212,8 @@ static inline int ext4_ext_get_actual_len(struct ext4_extent *ext)
(le16_to_cpu(ext->ee_len) - EXT_INIT_MAX_LEN));
}
extern ext4_fsblk_t idx_pblock(struct ext4_extent_idx *);
extern void ext4_ext_store_pblock(struct ext4_extent *, ext4_fsblk_t);
extern int ext4_extent_tree_init(handle_t *, struct inode *);
extern int ext4_ext_calc_credits_for_insert(struct inode *, struct ext4_ext_path *);
extern int ext4_ext_try_to_merge(struct inode *inode,
@ -233,8 +221,11 @@ extern int ext4_ext_try_to_merge(struct inode *inode,
struct ext4_extent *);
extern unsigned int ext4_ext_check_overlap(struct inode *, struct ext4_extent *, struct ext4_ext_path *);
extern int ext4_ext_insert_extent(handle_t *, struct inode *, struct ext4_ext_path *, struct ext4_extent *);
extern int ext4_ext_walk_space(struct inode *, unsigned long, unsigned long, ext_prepare_callback, void *);
extern struct ext4_ext_path * ext4_ext_find_extent(struct inode *, int, struct ext4_ext_path *);
extern struct ext4_ext_path *ext4_ext_find_extent(struct inode *, ext4_lblk_t,
struct ext4_ext_path *);
extern int ext4_ext_search_left(struct inode *, struct ext4_ext_path *,
ext4_lblk_t *, ext4_fsblk_t *);
extern int ext4_ext_search_right(struct inode *, struct ext4_ext_path *,
ext4_lblk_t *, ext4_fsblk_t *);
#endif /* _LINUX_EXT4_EXTENTS */

25
include/linux/ext4_fs_i.h
View file

@ -27,6 +27,12 @@ typedef int ext4_grpblk_t;
/* data type for filesystem-wide blocks number */
typedef unsigned long long ext4_fsblk_t;
/* data type for file logical block number */
typedef __u32 ext4_lblk_t;
/* data type for block group number */
typedef unsigned long ext4_group_t;
struct ext4_reserve_window {
ext4_fsblk_t _rsv_start; /* First byte reserved */
ext4_fsblk_t _rsv_end; /* Last byte reserved or 0 */
@ -48,7 +54,7 @@ struct ext4_block_alloc_info {
* most-recently-allocated block in this file.
* We use this for detecting linearly ascending allocation requests.
*/
__u32 last_alloc_logical_block;
ext4_lblk_t last_alloc_logical_block;
/*
* Was i_next_alloc_goal in ext4_inode_info
* is the *physical* companion to i_next_alloc_block.
@ -67,7 +73,7 @@ struct ext4_block_alloc_info {
*/
struct ext4_ext_cache {
ext4_fsblk_t ec_start;
__u32 ec_block;
ext4_lblk_t ec_block;
__u32 ec_len; /* must be 32bit to return holes */
__u32 ec_type;
};
@ -79,7 +85,6 @@ struct ext4_inode_info {
__le32 i_data[15]; /* unconverted */
__u32 i_flags;
ext4_fsblk_t i_file_acl;
__u32 i_dir_acl;
__u32 i_dtime;
/*
@ -89,13 +94,13 @@ struct ext4_inode_info {
* place a file's data blocks near its inode block, and new inodes
* near to their parent directory's inode.
*/
__u32 i_block_group;
ext4_group_t i_block_group;
__u32 i_state; /* Dynamic state flags for ext4 */
/* block reservation info */
struct ext4_block_alloc_info *i_block_alloc_info;
__u32 i_dir_start_lookup;
ext4_lblk_t i_dir_start_lookup;
#ifdef CONFIG_EXT4DEV_FS_XATTR
/*
* Extended attributes can be read independently of the main file
@ -134,16 +139,16 @@ struct ext4_inode_info {
__u16 i_extra_isize;
/*
* truncate_mutex is for serialising ext4_truncate() against
* i_data_sem is for serialising ext4_truncate() against
* ext4_getblock(). In the 2.4 ext2 design, great chunks of inode's
* data tree are chopped off during truncate. We can't do that in
* ext4 because whenever we perform intermediate commits during
* truncate, the inode and all the metadata blocks *must* be in a
* consistent state which allows truncation of the orphans to restart
* during recovery. Hence we must fix the get_block-vs-truncate race
* by other means, so we have truncate_mutex.
* by other means, so we have i_data_sem.
*/
struct mutex truncate_mutex;
struct rw_semaphore i_data_sem;
struct inode vfs_inode;
unsigned long i_ext_generation;
@ -153,6 +158,10 @@ struct ext4_inode_info {
* struct timespec i_{a,c,m}time in the generic inode.
*/
struct timespec i_crtime;
/* mballoc */
struct list_head i_prealloc_list;
spinlock_t i_prealloc_lock;
};
#endif /* _LINUX_EXT4_FS_I */

55
include/linux/ext4_fs_sb.h
View file

@ -35,9 +35,10 @@ struct ext4_sb_info {
unsigned long s_itb_per_group; /* Number of inode table blocks per group */
unsigned long s_gdb_count; /* Number of group descriptor blocks */
unsigned long s_desc_per_block; /* Number of group descriptors per block */
unsigned long s_groups_count; /* Number of groups in the fs */
ext4_group_t s_groups_count; /* Number of groups in the fs */
unsigned long s_overhead_last; /* Last calculated overhead */
unsigned long s_blocks_last; /* Last seen block count */
loff_t s_bitmap_maxbytes; /* max bytes for bitmap files */
struct buffer_head * s_sbh; /* Buffer containing the super block */
struct ext4_super_block * s_es; /* Pointer to the super block in the buffer */
struct buffer_head ** s_group_desc;
@ -90,6 +91,58 @@ struct ext4_sb_info {
unsigned long s_ext_blocks;
unsigned long s_ext_extents;
#endif
/* for buddy allocator */
struct ext4_group_info ***s_group_info;
struct inode *s_buddy_cache;
long s_blocks_reserved;
spinlock_t s_reserve_lock;
struct list_head s_active_transaction;
struct list_head s_closed_transaction;
struct list_head s_committed_transaction;
spinlock_t s_md_lock;
tid_t s_last_transaction;
unsigned short *s_mb_offsets, *s_mb_maxs;
/* tunables */
unsigned long s_stripe;
unsigned long s_mb_stream_request;
unsigned long s_mb_max_to_scan;
unsigned long s_mb_min_to_scan;
unsigned long s_mb_stats;
unsigned long s_mb_order2_reqs;
unsigned long s_mb_group_prealloc;
/* where last allocation was done - for stream allocation */
unsigned long s_mb_last_group;
unsigned long s_mb_last_start;
/* history to debug policy */
struct ext4_mb_history *s_mb_history;
int s_mb_history_cur;
int s_mb_history_max;
int s_mb_history_num;
struct proc_dir_entry *s_mb_proc;
spinlock_t s_mb_history_lock;
int s_mb_history_filter;
/* stats for buddy allocator */
spinlock_t s_mb_pa_lock;
atomic_t s_bal_reqs; /* number of reqs with len > 1 */
atomic_t s_bal_success; /* we found long enough chunks */
atomic_t s_bal_allocated; /* in blocks */
atomic_t s_bal_ex_scanned; /* total extents scanned */
atomic_t s_bal_goals; /* goal hits */
atomic_t s_bal_breaks; /* too long searches */
atomic_t s_bal_2orders; /* 2^order hits */
spinlock_t s_bal_lock;
unsigned long s_mb_buddies_generated;
unsigned long long s_mb_generation_time;
atomic_t s_mb_lost_chunks;
atomic_t s_mb_preallocated;
atomic_t s_mb_discarded;
/* locality groups */
struct ext4_locality_group *s_locality_groups;
};
#endif /* _LINUX_EXT4_FS_SB */

19
include/linux/fs.h
View file

@ -124,6 +124,7 @@ extern int dir_notify_enable;
#define MS_SHARED (1<<20) /* change to shared */
#define MS_RELATIME (1<<21) /* Update atime relative to mtime/ctime. */
#define MS_KERNMOUNT (1<<22) /* this is a kern_mount call */
#define MS_I_VERSION (1<<23) /* Update inode I_version field */
#define MS_ACTIVE (1<<30)
#define MS_NOUSER (1<<31)
@ -173,6 +174,7 @@ extern int dir_notify_enable;
((inode)->i_flags & (S_SYNC|S_DIRSYNC)))
#define IS_MANDLOCK(inode) __IS_FLG(inode, MS_MANDLOCK)
#define IS_NOATIME(inode) __IS_FLG(inode, MS_RDONLY|MS_NOATIME)
#define IS_I_VERSION(inode) __IS_FLG(inode, MS_I_VERSION)
#define IS_NOQUOTA(inode) ((inode)->i_flags & S_NOQUOTA)
#define IS_APPEND(inode) ((inode)->i_flags & S_APPEND)
@ -599,7 +601,7 @@ struct inode {
uid_t i_uid;
gid_t i_gid;
dev_t i_rdev;
unsigned long i_version;
u64 i_version;
loff_t i_size;
#ifdef __NEED_I_SIZE_ORDERED
seqcount_t i_size_seqcount;
@ -1394,6 +1396,21 @@ static inline void inode_dec_link_count(struct inode *inode)
mark_inode_dirty(inode);
}
/**
* inode_inc_iversion - increments i_version
* @inode: inode that need to be updated
*
* Every time the inode is modified, the i_version field will be incremented.
* The filesystem has to be mounted with i_version flag
*/
static inline void inode_inc_iversion(struct inode *inode)
{
spin_lock(&inode->i_lock);
inode->i_version++;
spin_unlock(&inode->i_lock);
}
extern void touch_atime(struct vfsmount *mnt, struct dentry *dentry);
static inline void file_accessed(struct file *file)
{

135
include/linux/jbd2.h
View file

@ -149,6 +149,28 @@ typedef struct journal_header_s
__be32 h_sequence;
} journal_header_t;
/*
* Checksum types.
*/
#define JBD2_CRC32_CHKSUM 1
#define JBD2_MD5_CHKSUM 2
#define JBD2_SHA1_CHKSUM 3
#define JBD2_CRC32_CHKSUM_SIZE 4
#define JBD2_CHECKSUM_BYTES (32 / sizeof(u32))
/*
* Commit block header for storing transactional checksums:
*/
struct commit_header {
__be32 h_magic;
__be32 h_blocktype;
__be32 h_sequence;
unsigned char h_chksum_type;
unsigned char h_chksum_size;
unsigned char h_padding[2];
__be32 h_chksum[JBD2_CHECKSUM_BYTES];
};
/*
* The block tag: used to describe a single buffer in the journal.
@ -242,31 +264,25 @@ typedef struct journal_superblock_s
((j)->j_format_version >= 2 && \
((j)->j_superblock->s_feature_incompat & cpu_to_be32((mask))))
#define JBD2_FEATURE_INCOMPAT_REVOKE 0x00000001
#define JBD2_FEATURE_INCOMPAT_64BIT 0x00000002
#define JBD2_FEATURE_COMPAT_CHECKSUM 0x00000001
#define JBD2_FEATURE_INCOMPAT_REVOKE 0x00000001
#define JBD2_FEATURE_INCOMPAT_64BIT 0x00000002
#define JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT 0x00000004
/* Features known to this kernel version: */
#define JBD2_KNOWN_COMPAT_FEATURES 0
#define JBD2_KNOWN_COMPAT_FEATURES JBD2_FEATURE_COMPAT_CHECKSUM
#define JBD2_KNOWN_ROCOMPAT_FEATURES 0
#define JBD2_KNOWN_INCOMPAT_FEATURES (JBD2_FEATURE_INCOMPAT_REVOKE | \
JBD2_FEATURE_INCOMPAT_64BIT)
JBD2_FEATURE_INCOMPAT_64BIT | \
JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT)
#ifdef __KERNEL__
#include <linux/fs.h>
#include <linux/sched.h>
#define JBD2_ASSERTIONS
#ifdef JBD2_ASSERTIONS
#define J_ASSERT(assert) \
do { \
if (!(assert)) { \
printk (KERN_EMERG \
"Assertion failure in %s() at %s:%d: \"%s\"\n", \
__FUNCTION__, __FILE__, __LINE__, # assert); \
BUG(); \
} \
} while (0)
#define J_ASSERT(assert) BUG_ON(!(assert))
#if defined(CONFIG_BUFFER_DEBUG)
void buffer_assertion_failure(struct buffer_head *bh);
@ -282,10 +298,6 @@ void buffer_assertion_failure(struct buffer_head *bh);
#define J_ASSERT_JH(jh, expr) J_ASSERT(expr)
#endif
#else
#define J_ASSERT(assert) do { } while (0)
#endif /* JBD2_ASSERTIONS */
#if defined(JBD2_PARANOID_IOFAIL)
#define J_EXPECT(expr, why...) J_ASSERT(expr)
#define J_EXPECT_BH(bh, expr, why...) J_ASSERT_BH(bh, expr)
@ -406,9 +418,23 @@ struct handle_s
unsigned int h_sync: 1; /* sync-on-close */
unsigned int h_jdata: 1; /* force data journaling */
unsigned int h_aborted: 1; /* fatal error on handle */
#ifdef CONFIG_DEBUG_LOCK_ALLOC
struct lockdep_map h_lockdep_map;
#endif
};
/*
* Some stats for checkpoint phase
*/
struct transaction_chp_stats_s {
unsigned long cs_chp_time;
unsigned long cs_forced_to_close;
unsigned long cs_written;
unsigned long cs_dropped;
};
/* The transaction_t type is the guts of the journaling mechanism. It
* tracks a compound transaction through its various states:
*
@ -456,6 +482,8 @@ struct transaction_s
/*
* Transaction's current state
* [no locking - only kjournald2 alters this]
* [j_list_lock] guards transition of a transaction into T_FINISHED
* state and subsequent call of __jbd2_journal_drop_transaction()
* FIXME: needs barriers
* KLUDGE: [use j_state_lock]
*/
@ -543,6 +571,21 @@ struct transaction_s
*/
spinlock_t t_handle_lock;
/*
* Longest time some handle had to wait for running transaction
*/
unsigned long t_max_wait;
/*
* When transaction started
*/
unsigned long t_start;
/*
* Checkpointing stats [j_checkpoint_sem]
*/
struct transaction_chp_stats_s t_chp_stats;
/*
* Number of outstanding updates running on this transaction
* [t_handle_lock]
@ -574,6 +617,39 @@ struct transaction_s
};
struct transaction_run_stats_s {
unsigned long rs_wait;
unsigned long rs_running;
unsigned long rs_locked;
unsigned long rs_flushing;
unsigned long rs_logging;
unsigned long rs_handle_count;
unsigned long rs_blocks;
unsigned long rs_blocks_logged;
};
struct transaction_stats_s {
int ts_type;
unsigned long ts_tid;
union {
struct transaction_run_stats_s run;
struct transaction_chp_stats_s chp;
} u;
};
#define JBD2_STATS_RUN 1
#define JBD2_STATS_CHECKPOINT 2
static inline unsigned long
jbd2_time_diff(unsigned long start, unsigned long end)
{
if (end >= start)
return end - start;
return end + (MAX_JIFFY_OFFSET - start);
}
/**
* struct journal_s - The journal_s type is the concrete type associated with
* journal_t.
@ -635,6 +711,12 @@ struct transaction_s
* @j_wbufsize: maximum number of buffer_heads allowed in j_wbuf, the
* number that will fit in j_blocksize
* @j_last_sync_writer: most recent pid which did a synchronous write
* @j_history: Buffer storing the transactions statistics history
* @j_history_max: Maximum number of transactions in the statistics history
* @j_history_cur: Current number of transactions in the statistics history
* @j_history_lock: Protect the transactions statistics history
* @j_proc_entry: procfs entry for the jbd statistics directory
* @j_stats: Overall statistics
* @j_private: An opaque pointer to fs-private information.
*/
@ -826,6 +908,19 @@ struct journal_s
pid_t j_last_sync_writer;
/*
* Journal statistics
*/
struct transaction_stats_s *j_history;
int j_history_max;
int j_history_cur;
/*
* Protect the transactions statistics history
*/
spinlock_t j_history_lock;
struct proc_dir_entry *j_proc_entry;
struct transaction_stats_s j_stats;
/*
* An opaque pointer to fs-private information. ext3 puts its
* superblock pointer here
@ -932,6 +1027,8 @@ extern int jbd2_journal_check_available_features
(journal_t *, unsigned long, unsigned long, unsigned long);
extern int jbd2_journal_set_features
(journal_t *, unsigned long, unsigned long, unsigned long);
extern void jbd2_journal_clear_features
(journal_t *, unsigned long, unsigned long, unsigned long);
extern int jbd2_journal_create (journal_t *);
extern int jbd2_journal_load (journal_t *journal);
extern void jbd2_journal_destroy (journal_t *);

43
lib/find_next_bit.c
View file

@ -178,4 +178,47 @@ found_middle_swap:
EXPORT_SYMBOL(generic_find_next_zero_le_bit);
unsigned long generic_find_next_le_bit(const unsigned long *addr, unsigned
long size, unsigned long offset)
{
const unsigned long *p = addr + BITOP_WORD(offset);
unsigned long result = offset & ~(BITS_PER_LONG - 1);
unsigned long tmp;
if (offset >= size)
return size;
size -= result;
offset &= (BITS_PER_LONG - 1UL);
if (offset) {
tmp = ext2_swabp(p++);
tmp &= (~0UL << offset);
if (size < BITS_PER_LONG)
goto found_first;
if (tmp)
goto found_middle;
size -= BITS_PER_LONG;
result += BITS_PER_LONG;
}
while (size & ~(BITS_PER_LONG - 1)) {
tmp = *(p++);
if (tmp)
goto found_middle_swap;
result += BITS_PER_LONG;
size -= BITS_PER_LONG;
}
if (!size)
return result;
tmp = ext2_swabp(p);
found_first:
tmp &= (~0UL >> (BITS_PER_LONG - size));
if (tmp == 0UL) /* Are any bits set? */
return result + size; /* Nope. */
found_middle:
return result + __ffs(tmp);
found_middle_swap:
return result + __ffs(ext2_swab(tmp));
}
EXPORT_SYMBOL(generic_find_next_le_bit);
#endif /* __BIG_ENDIAN */