ext4: reimplement convert and split_unwritten

Reimplement ext4_ext_convert_to_initialized() and
ext4_split_unwritten_extents() using ext4_split_extent()

Signed-off-by: Yongqiang Yang <xiaoqiangnk@gmail.com>
Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
Tested-by: Allison Henderson <achender@linux.vnet.ibm.com>
This commit is contained in:
Yongqiang Yang 2011-05-03 12:25:07 -04:00 коммит произвёл Theodore Ts'o
Родитель 47ea3bb59c
Коммит 667eff35a1
1 изменённых файлов: 72 добавлений и 408 удалений

Просмотреть файл

@ -2757,17 +2757,13 @@ static int ext4_ext_convert_to_initialized(handle_t *handle,
struct ext4_map_blocks *map, struct ext4_map_blocks *map,
struct ext4_ext_path *path) struct ext4_ext_path *path)
{ {
struct ext4_extent *ex, newex, orig_ex; struct ext4_map_blocks split_map;
struct ext4_extent *ex1 = NULL; struct ext4_extent zero_ex;
struct ext4_extent *ex2 = NULL; struct ext4_extent *ex;
struct ext4_extent *ex3 = NULL;
struct ext4_extent_header *eh;
ext4_lblk_t ee_block, eof_block; ext4_lblk_t ee_block, eof_block;
unsigned int allocated, ee_len, depth; unsigned int allocated, ee_len, depth;
ext4_fsblk_t newblock;
int err = 0; int err = 0;
int ret = 0; int split_flag = 0;
int may_zeroout;
ext_debug("ext4_ext_convert_to_initialized: inode %lu, logical" ext_debug("ext4_ext_convert_to_initialized: inode %lu, logical"
"block %llu, max_blocks %u\n", inode->i_ino, "block %llu, max_blocks %u\n", inode->i_ino,
@ -2779,280 +2775,87 @@ static int ext4_ext_convert_to_initialized(handle_t *handle,
eof_block = map->m_lblk + map->m_len; eof_block = map->m_lblk + map->m_len;
depth = ext_depth(inode); depth = ext_depth(inode);
eh = path[depth].p_hdr;
ex = path[depth].p_ext; ex = path[depth].p_ext;
ee_block = le32_to_cpu(ex->ee_block); ee_block = le32_to_cpu(ex->ee_block);
ee_len = ext4_ext_get_actual_len(ex); ee_len = ext4_ext_get_actual_len(ex);
allocated = ee_len - (map->m_lblk - ee_block); allocated = ee_len - (map->m_lblk - ee_block);
newblock = map->m_lblk - ee_block + ext4_ext_pblock(ex);
ex2 = ex;
orig_ex.ee_block = ex->ee_block;
orig_ex.ee_len = cpu_to_le16(ee_len);
ext4_ext_store_pblock(&orig_ex, ext4_ext_pblock(ex));
WARN_ON(map->m_lblk < ee_block);
/* /*
* It is safe to convert extent to initialized via explicit * It is safe to convert extent to initialized via explicit
* zeroout only if extent is fully insde i_size or new_size. * zeroout only if extent is fully insde i_size or new_size.
*/ */
may_zeroout = ee_block + ee_len <= eof_block; split_flag |= ee_block + ee_len <= eof_block ? EXT4_EXT_MAY_ZEROOUT : 0;
err = ext4_ext_get_access(handle, inode, path + depth);
if (err)
goto out;
/* If extent has less than 2*EXT4_EXT_ZERO_LEN zerout directly */ /* If extent has less than 2*EXT4_EXT_ZERO_LEN zerout directly */
if (ee_len <= 2*EXT4_EXT_ZERO_LEN && may_zeroout) { if (ee_len <= 2*EXT4_EXT_ZERO_LEN &&
err = ext4_ext_zeroout(inode, &orig_ex); (EXT4_EXT_MAY_ZEROOUT & split_flag)) {
err = ext4_ext_zeroout(inode, ex);
if (err) if (err)
goto fix_extent_len;
/* update the extent length and mark as initialized */
ex->ee_block = orig_ex.ee_block;
ex->ee_len = orig_ex.ee_len;
ext4_ext_store_pblock(ex, ext4_ext_pblock(&orig_ex));
ext4_ext_dirty(handle, inode, path + depth);
/* zeroed the full extent */
return allocated;
}
/* ex1: ee_block to map->m_lblk - 1 : uninitialized */
if (map->m_lblk > ee_block) {
ex1 = ex;
ex1->ee_len = cpu_to_le16(map->m_lblk - ee_block);
ext4_ext_mark_uninitialized(ex1);
ex2 = &newex;
}
/*
* for sanity, update the length of the ex2 extent before
* we insert ex3, if ex1 is NULL. This is to avoid temporary
* overlap of blocks.
*/
if (!ex1 && allocated > map->m_len)
ex2->ee_len = cpu_to_le16(map->m_len);
/* ex3: to ee_block + ee_len : uninitialised */
if (allocated > map->m_len) {
unsigned int newdepth;
/* If extent has less than EXT4_EXT_ZERO_LEN zerout directly */
if (allocated <= EXT4_EXT_ZERO_LEN && may_zeroout) {
/*
* map->m_lblk == ee_block is handled by the zerouout
* at the beginning.
* Mark first half uninitialized.
* Mark second half initialized and zero out the
* initialized extent
*/
ex->ee_block = orig_ex.ee_block;
ex->ee_len = cpu_to_le16(ee_len - allocated);
ext4_ext_mark_uninitialized(ex);
ext4_ext_store_pblock(ex, ext4_ext_pblock(&orig_ex));
ext4_ext_dirty(handle, inode, path + depth);
ex3 = &newex;
ex3->ee_block = cpu_to_le32(map->m_lblk);
ext4_ext_store_pblock(ex3, newblock);
ex3->ee_len = cpu_to_le16(allocated);
err = ext4_ext_insert_extent(handle, inode, path,
ex3, 0);
if (err == -ENOSPC) {
err = ext4_ext_zeroout(inode, &orig_ex);
if (err)
goto fix_extent_len;
ex->ee_block = orig_ex.ee_block;
ex->ee_len = orig_ex.ee_len;
ext4_ext_store_pblock(ex,
ext4_ext_pblock(&orig_ex));
ext4_ext_dirty(handle, inode, path + depth);
/* blocks available from map->m_lblk */
return allocated;
} else if (err)
goto fix_extent_len;
/*
* We need to zero out the second half because
* an fallocate request can update file size and
* converting the second half to initialized extent
* implies that we can leak some junk data to user
* space.
*/
err = ext4_ext_zeroout(inode, ex3);
if (err) {
/*
* We should actually mark the
* second half as uninit and return error
* Insert would have changed the extent
*/
depth = ext_depth(inode);
ext4_ext_drop_refs(path);
path = ext4_ext_find_extent(inode, map->m_lblk,
path);
if (IS_ERR(path)) {
err = PTR_ERR(path);
return err;
}
/* get the second half extent details */
ex = path[depth].p_ext;
err = ext4_ext_get_access(handle, inode,
path + depth);
if (err)
return err;
ext4_ext_mark_uninitialized(ex);
ext4_ext_dirty(handle, inode, path + depth);
return err;
}
/* zeroed the second half */
return allocated;
}
ex3 = &newex;
ex3->ee_block = cpu_to_le32(map->m_lblk + map->m_len);
ext4_ext_store_pblock(ex3, newblock + map->m_len);
ex3->ee_len = cpu_to_le16(allocated - map->m_len);
ext4_ext_mark_uninitialized(ex3);
err = ext4_ext_insert_extent(handle, inode, path, ex3, 0);
if (err == -ENOSPC && may_zeroout) {
err = ext4_ext_zeroout(inode, &orig_ex);
if (err)
goto fix_extent_len;
/* update the extent length and mark as initialized */
ex->ee_block = orig_ex.ee_block;
ex->ee_len = orig_ex.ee_len;
ext4_ext_store_pblock(ex, ext4_ext_pblock(&orig_ex));
ext4_ext_dirty(handle, inode, path + depth);
/* zeroed the full extent */
/* blocks available from map->m_lblk */
return allocated;
} else if (err)
goto fix_extent_len;
/*
* The depth, and hence eh & ex might change
* as part of the insert above.
*/
newdepth = ext_depth(inode);
/*
* update the extent length after successful insert of the
* split extent
*/
ee_len -= ext4_ext_get_actual_len(ex3);
orig_ex.ee_len = cpu_to_le16(ee_len);
may_zeroout = ee_block + ee_len <= eof_block;
depth = newdepth;
ext4_ext_drop_refs(path);
path = ext4_ext_find_extent(inode, map->m_lblk, path);
if (IS_ERR(path)) {
err = PTR_ERR(path);
goto out; goto out;
}
eh = path[depth].p_hdr;
ex = path[depth].p_ext;
if (ex2 != &newex)
ex2 = ex;
err = ext4_ext_get_access(handle, inode, path + depth); err = ext4_ext_get_access(handle, inode, path + depth);
if (err) if (err)
goto out; goto out;
ext4_ext_mark_initialized(ex);
allocated = map->m_len; ext4_ext_try_to_merge(inode, path, ex);
err = ext4_ext_dirty(handle, inode, path + depth);
/* If extent has less than EXT4_EXT_ZERO_LEN and we are trying goto out;
* to insert a extent in the middle zerout directly
* otherwise give the extent a chance to merge to left
*/
if (le16_to_cpu(orig_ex.ee_len) <= EXT4_EXT_ZERO_LEN &&
map->m_lblk != ee_block && may_zeroout) {
err = ext4_ext_zeroout(inode, &orig_ex);
if (err)
goto fix_extent_len;
/* update the extent length and mark as initialized */
ex->ee_block = orig_ex.ee_block;
ex->ee_len = orig_ex.ee_len;
ext4_ext_store_pblock(ex, ext4_ext_pblock(&orig_ex));
ext4_ext_dirty(handle, inode, path + depth);
/* zero out the first half */
/* blocks available from map->m_lblk */
return allocated;
}
} }
/* /*
* If there was a change of depth as part of the * four cases:
* insertion of ex3 above, we need to update the length * 1. split the extent into three extents.
* of the ex1 extent again here * 2. split the extent into two extents, zeroout the first half.
* 3. split the extent into two extents, zeroout the second half.
* 4. split the extent into two extents with out zeroout.
*/ */
if (ex1 && ex1 != ex) { split_map.m_lblk = map->m_lblk;
ex1 = ex; split_map.m_len = map->m_len;
ex1->ee_len = cpu_to_le16(map->m_lblk - ee_block);
ext4_ext_mark_uninitialized(ex1); if (allocated > map->m_len) {
ex2 = &newex; if (allocated <= EXT4_EXT_ZERO_LEN &&
} (EXT4_EXT_MAY_ZEROOUT & split_flag)) {
/* ex2: map->m_lblk to map->m_lblk + maxblocks-1 : initialised */ /* case 3 */
ex2->ee_block = cpu_to_le32(map->m_lblk); zero_ex.ee_block =
ext4_ext_store_pblock(ex2, newblock); cpu_to_le32(map->m_lblk + map->m_len);
ex2->ee_len = cpu_to_le16(allocated); zero_ex.ee_len = cpu_to_le16(allocated - map->m_len);
if (ex2 != ex) ext4_ext_store_pblock(&zero_ex,
goto insert; ext4_ext_pblock(ex) + map->m_lblk - ee_block);
/* err = ext4_ext_zeroout(inode, &zero_ex);
* New (initialized) extent starts from the first block
* in the current extent. i.e., ex2 == ex
* We have to see if it can be merged with the extent
* on the left.
*/
if (ex2 > EXT_FIRST_EXTENT(eh)) {
/*
* To merge left, pass "ex2 - 1" to try_to_merge(),
* since it merges towards right _only_.
*/
ret = ext4_ext_try_to_merge(inode, path, ex2 - 1);
if (ret) {
err = ext4_ext_correct_indexes(handle, inode, path);
if (err) if (err)
goto out; goto out;
depth = ext_depth(inode); split_map.m_lblk = map->m_lblk;
ex2--; split_map.m_len = allocated;
} else if ((map->m_lblk - ee_block + map->m_len <
EXT4_EXT_ZERO_LEN) &&
(EXT4_EXT_MAY_ZEROOUT & split_flag)) {
/* case 2 */
if (map->m_lblk != ee_block) {
zero_ex.ee_block = ex->ee_block;
zero_ex.ee_len = cpu_to_le16(map->m_lblk -
ee_block);
ext4_ext_store_pblock(&zero_ex,
ext4_ext_pblock(ex));
err = ext4_ext_zeroout(inode, &zero_ex);
if (err)
goto out;
}
allocated = map->m_lblk - ee_block + map->m_len;
split_map.m_lblk = ee_block;
split_map.m_len = allocated;
} }
} }
/*
* Try to Merge towards right. This might be required allocated = ext4_split_extent(handle, inode, path,
* only when the whole extent is being written to. &split_map, split_flag, 0);
* i.e. ex2 == ex and ex3 == NULL. if (allocated < 0)
*/ err = allocated;
if (!ex3) {
ret = ext4_ext_try_to_merge(inode, path, ex2);
if (ret) {
err = ext4_ext_correct_indexes(handle, inode, path);
if (err)
goto out;
}
}
/* Mark modified extent as dirty */
err = ext4_ext_dirty(handle, inode, path + depth);
goto out;
insert:
err = ext4_ext_insert_extent(handle, inode, path, &newex, 0);
if (err == -ENOSPC && may_zeroout) {
err = ext4_ext_zeroout(inode, &orig_ex);
if (err)
goto fix_extent_len;
/* update the extent length and mark as initialized */
ex->ee_block = orig_ex.ee_block;
ex->ee_len = orig_ex.ee_len;
ext4_ext_store_pblock(ex, ext4_ext_pblock(&orig_ex));
ext4_ext_dirty(handle, inode, path + depth);
/* zero out the first half */
return allocated;
} else if (err)
goto fix_extent_len;
out: out:
ext4_ext_show_leaf(inode, path);
return err ? err : allocated; return err ? err : allocated;
fix_extent_len:
ex->ee_block = orig_ex.ee_block;
ex->ee_len = orig_ex.ee_len;
ext4_ext_store_pblock(ex, ext4_ext_pblock(&orig_ex));
ext4_ext_mark_uninitialized(ex);
ext4_ext_dirty(handle, inode, path + depth);
return err;
} }
/* /*
@ -3083,15 +2886,11 @@ static int ext4_split_unwritten_extents(handle_t *handle,
struct ext4_ext_path *path, struct ext4_ext_path *path,
int flags) int flags)
{ {
struct ext4_extent *ex, newex, orig_ex; ext4_lblk_t eof_block;
struct ext4_extent *ex1 = NULL; ext4_lblk_t ee_block;
struct ext4_extent *ex2 = NULL; struct ext4_extent *ex;
struct ext4_extent *ex3 = NULL; unsigned int ee_len;
ext4_lblk_t ee_block, eof_block; int split_flag = 0, depth;
unsigned int allocated, ee_len, depth;
ext4_fsblk_t newblock;
int err = 0;
int may_zeroout;
ext_debug("ext4_split_unwritten_extents: inode %lu, logical" ext_debug("ext4_split_unwritten_extents: inode %lu, logical"
"block %llu, max_blocks %u\n", inode->i_ino, "block %llu, max_blocks %u\n", inode->i_ino,
@ -3101,155 +2900,20 @@ static int ext4_split_unwritten_extents(handle_t *handle,
inode->i_sb->s_blocksize_bits; inode->i_sb->s_blocksize_bits;
if (eof_block < map->m_lblk + map->m_len) if (eof_block < map->m_lblk + map->m_len)
eof_block = map->m_lblk + map->m_len; eof_block = map->m_lblk + map->m_len;
depth = ext_depth(inode);
ex = path[depth].p_ext;
ee_block = le32_to_cpu(ex->ee_block);
ee_len = ext4_ext_get_actual_len(ex);
allocated = ee_len - (map->m_lblk - ee_block);
newblock = map->m_lblk - ee_block + ext4_ext_pblock(ex);
ex2 = ex;
orig_ex.ee_block = ex->ee_block;
orig_ex.ee_len = cpu_to_le16(ee_len);
ext4_ext_store_pblock(&orig_ex, ext4_ext_pblock(ex));
/* /*
* It is safe to convert extent to initialized via explicit * It is safe to convert extent to initialized via explicit
* zeroout only if extent is fully insde i_size or new_size. * zeroout only if extent is fully insde i_size or new_size.
*/ */
may_zeroout = ee_block + ee_len <= eof_block; depth = ext_depth(inode);
ex = path[depth].p_ext;
ee_block = le32_to_cpu(ex->ee_block);
ee_len = ext4_ext_get_actual_len(ex);
/* split_flag |= ee_block + ee_len <= eof_block ? EXT4_EXT_MAY_ZEROOUT : 0;
* If the uninitialized extent begins at the same logical split_flag |= EXT4_EXT_MARK_UNINIT2;
* block where the write begins, and the write completely
* covers the extent, then we don't need to split it.
*/
if ((map->m_lblk == ee_block) && (allocated <= map->m_len))
return allocated;
err = ext4_ext_get_access(handle, inode, path + depth); flags |= EXT4_GET_BLOCKS_PRE_IO;
if (err) return ext4_split_extent(handle, inode, path, map, split_flag, flags);
goto out;
/* ex1: ee_block to map->m_lblk - 1 : uninitialized */
if (map->m_lblk > ee_block) {
ex1 = ex;
ex1->ee_len = cpu_to_le16(map->m_lblk - ee_block);
ext4_ext_mark_uninitialized(ex1);
ex2 = &newex;
}
/*
* for sanity, update the length of the ex2 extent before
* we insert ex3, if ex1 is NULL. This is to avoid temporary
* overlap of blocks.
*/
if (!ex1 && allocated > map->m_len)
ex2->ee_len = cpu_to_le16(map->m_len);
/* ex3: to ee_block + ee_len : uninitialised */
if (allocated > map->m_len) {
unsigned int newdepth;
ex3 = &newex;
ex3->ee_block = cpu_to_le32(map->m_lblk + map->m_len);
ext4_ext_store_pblock(ex3, newblock + map->m_len);
ex3->ee_len = cpu_to_le16(allocated - map->m_len);
ext4_ext_mark_uninitialized(ex3);
err = ext4_ext_insert_extent(handle, inode, path, ex3, flags);
if (err == -ENOSPC && may_zeroout) {
err = ext4_ext_zeroout(inode, &orig_ex);
if (err)
goto fix_extent_len;
/* update the extent length and mark as initialized */
ex->ee_block = orig_ex.ee_block;
ex->ee_len = orig_ex.ee_len;
ext4_ext_store_pblock(ex, ext4_ext_pblock(&orig_ex));
ext4_ext_dirty(handle, inode, path + depth);
/* zeroed the full extent */
/* blocks available from map->m_lblk */
return allocated;
} else if (err)
goto fix_extent_len;
/*
* The depth, and hence eh & ex might change
* as part of the insert above.
*/
newdepth = ext_depth(inode);
/*
* update the extent length after successful insert of the
* split extent
*/
ee_len -= ext4_ext_get_actual_len(ex3);
orig_ex.ee_len = cpu_to_le16(ee_len);
may_zeroout = ee_block + ee_len <= eof_block;
depth = newdepth;
ext4_ext_drop_refs(path);
path = ext4_ext_find_extent(inode, map->m_lblk, path);
if (IS_ERR(path)) {
err = PTR_ERR(path);
goto out;
}
ex = path[depth].p_ext;
if (ex2 != &newex)
ex2 = ex;
err = ext4_ext_get_access(handle, inode, path + depth);
if (err)
goto out;
allocated = map->m_len;
}
/*
* If there was a change of depth as part of the
* insertion of ex3 above, we need to update the length
* of the ex1 extent again here
*/
if (ex1 && ex1 != ex) {
ex1 = ex;
ex1->ee_len = cpu_to_le16(map->m_lblk - ee_block);
ext4_ext_mark_uninitialized(ex1);
ex2 = &newex;
}
/*
* ex2: map->m_lblk to map->m_lblk + map->m_len-1 : to be written
* using direct I/O, uninitialised still.
*/
ex2->ee_block = cpu_to_le32(map->m_lblk);
ext4_ext_store_pblock(ex2, newblock);
ex2->ee_len = cpu_to_le16(allocated);
ext4_ext_mark_uninitialized(ex2);
if (ex2 != ex)
goto insert;
/* Mark modified extent as dirty */
err = ext4_ext_dirty(handle, inode, path + depth);
ext_debug("out here\n");
goto out;
insert:
err = ext4_ext_insert_extent(handle, inode, path, &newex, flags);
if (err == -ENOSPC && may_zeroout) {
err = ext4_ext_zeroout(inode, &orig_ex);
if (err)
goto fix_extent_len;
/* update the extent length and mark as initialized */
ex->ee_block = orig_ex.ee_block;
ex->ee_len = orig_ex.ee_len;
ext4_ext_store_pblock(ex, ext4_ext_pblock(&orig_ex));
ext4_ext_dirty(handle, inode, path + depth);
/* zero out the first half */
return allocated;
} else if (err)
goto fix_extent_len;
out:
ext4_ext_show_leaf(inode, path);
return err ? err : allocated;
fix_extent_len:
ex->ee_block = orig_ex.ee_block;
ex->ee_len = orig_ex.ee_len;
ext4_ext_store_pblock(ex, ext4_ext_pblock(&orig_ex));
ext4_ext_mark_uninitialized(ex);
ext4_ext_dirty(handle, inode, path + depth);
return err;
} }
static int ext4_convert_unwritten_extents_endio(handle_t *handle, static int ext4_convert_unwritten_extents_endio(handle_t *handle,