leandrof/linux
1
0
Fork 0
forked from Minki/linux
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Merge ext4 changes in ext4_file_write() into for-next

Browse Source 
From ext4.git#dev, needed for switch of ext4 to ->write_iter() ;-/
This commit is contained in:
Al Viro 2014-05-06 17:38:41 -04:00
commit a832475488
9 changed files with 246 additions and 252 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

24
fs/ext4/ext4.h
View File

@ -158,7 +158,6 @@ struct ext4_allocation_request {
#define EXT4_MAP_MAPPED (1 << BH_Mapped)
#define EXT4_MAP_UNWRITTEN (1 << BH_Unwritten)
#define EXT4_MAP_BOUNDARY (1 << BH_Boundary)
#define EXT4_MAP_UNINIT (1 << BH_Uninit)
/* Sometimes (in the bigalloc case, from ext4_da_get_block_prep) the caller of
* ext4_map_blocks wants to know whether or not the underlying cluster has
* already been accounted for. EXT4_MAP_FROM_CLUSTER conveys to the caller that
@ -169,7 +168,7 @@ struct ext4_allocation_request {
#define EXT4_MAP_FROM_CLUSTER (1 << BH_AllocFromCluster)
#define EXT4_MAP_FLAGS (EXT4_MAP_NEW | EXT4_MAP_MAPPED |\
EXT4_MAP_UNWRITTEN | EXT4_MAP_BOUNDARY |\
EXT4_MAP_UNINIT | EXT4_MAP_FROM_CLUSTER)
EXT4_MAP_FROM_CLUSTER)
struct ext4_map_blocks {
ext4_fsblk_t m_pblk;
@ -184,7 +183,7 @@ struct ext4_map_blocks {
#define EXT4_IO_END_UNWRITTEN 0x0001
/*
* For converting uninitialized extents on a work queue. 'handle' is used for
* For converting unwritten extents on a work queue. 'handle' is used for
* buffered writeback.
*/
typedef struct ext4_io_end {
@ -537,26 +536,26 @@ enum {
/*
* Flags used by ext4_map_blocks()
*/
/* Allocate any needed blocks and/or convert an unitialized
/* Allocate any needed blocks and/or convert an unwritten
extent to be an initialized ext4 */
#define EXT4_GET_BLOCKS_CREATE 0x0001
/* Request the creation of an unitialized extent */
#define EXT4_GET_BLOCKS_UNINIT_EXT 0x0002
#define EXT4_GET_BLOCKS_CREATE_UNINIT_EXT (EXT4_GET_BLOCKS_UNINIT_EXT|\
/* Request the creation of an unwritten extent */
#define EXT4_GET_BLOCKS_UNWRIT_EXT 0x0002
#define EXT4_GET_BLOCKS_CREATE_UNWRIT_EXT (EXT4_GET_BLOCKS_UNWRIT_EXT|\
EXT4_GET_BLOCKS_CREATE)
/* Caller is from the delayed allocation writeout path
* finally doing the actual allocation of delayed blocks */
#define EXT4_GET_BLOCKS_DELALLOC_RESERVE 0x0004
/* caller is from the direct IO path, request to creation of an
unitialized extents if not allocated, split the uninitialized
unwritten extents if not allocated, split the unwritten
extent if blocks has been preallocated already*/
#define EXT4_GET_BLOCKS_PRE_IO 0x0008
#define EXT4_GET_BLOCKS_CONVERT 0x0010
#define EXT4_GET_BLOCKS_IO_CREATE_EXT (EXT4_GET_BLOCKS_PRE_IO|\
EXT4_GET_BLOCKS_CREATE_UNINIT_EXT)
EXT4_GET_BLOCKS_CREATE_UNWRIT_EXT)
/* Convert extent to initialized after IO complete */
#define EXT4_GET_BLOCKS_IO_CONVERT_EXT (EXT4_GET_BLOCKS_CONVERT|\
EXT4_GET_BLOCKS_CREATE_UNINIT_EXT)
EXT4_GET_BLOCKS_CREATE_UNWRIT_EXT)
/* Eventual metadata allocation (due to growing extent tree)
* should not fail, so try to use reserved blocks for that.*/
#define EXT4_GET_BLOCKS_METADATA_NOFAIL 0x0020
@ -2783,10 +2782,9 @@ extern int ext4_mmp_csum_verify(struct super_block *sb,
* See EXT4_MAP_... to see where this is used.
*/
enum ext4_state_bits {
BH_Uninit /* blocks are allocated but uninitialized on disk */
= BH_JBDPrivateStart,
BH_AllocFromCluster, /* allocated blocks were part of already
BH_AllocFromCluster /* allocated blocks were part of already
* allocated cluster. */
= BH_JBDPrivateStart
};
/*

22
fs/ext4/ext4_extents.h
View File

@ -137,21 +137,21 @@ struct ext4_ext_path {
* EXT_INIT_MAX_LEN is the maximum number of blocks we can have in an
* initialized extent. This is 2^15 and not (2^16 - 1), since we use the
* MSB of ee_len field in the extent datastructure to signify if this
* particular extent is an initialized extent or an uninitialized (i.e.
* particular extent is an initialized extent or an unwritten (i.e.
* preallocated).
* EXT_UNINIT_MAX_LEN is the maximum number of blocks we can have in an
* uninitialized extent.
* EXT_UNWRITTEN_MAX_LEN is the maximum number of blocks we can have in an
* unwritten extent.
* If ee_len is <= 0x8000, it is an initialized extent. Otherwise, it is an
* uninitialized one. In other words, if MSB of ee_len is set, it is an
* uninitialized extent with only one special scenario when ee_len = 0x8000.
* In this case we can not have an uninitialized extent of zero length and
* unwritten one. In other words, if MSB of ee_len is set, it is an
* unwritten extent with only one special scenario when ee_len = 0x8000.
* In this case we can not have an unwritten extent of zero length and
* thus we make it as a special case of initialized extent with 0x8000 length.
* This way we get better extent-to-group alignment for initialized extents.
* Hence, the maximum number of blocks we can have in an *initialized*
* extent is 2^15 (32768) and in an *uninitialized* extent is 2^15-1 (32767).
* extent is 2^15 (32768) and in an *unwritten* extent is 2^15-1 (32767).
*/
#define EXT_INIT_MAX_LEN (1UL << 15)
#define EXT_UNINIT_MAX_LEN (EXT_INIT_MAX_LEN - 1)
#define EXT_UNWRITTEN_MAX_LEN (EXT_INIT_MAX_LEN - 1)
#define EXT_FIRST_EXTENT(__hdr__) \
@ -187,14 +187,14 @@ static inline unsigned short ext_depth(struct inode *inode)
return le16_to_cpu(ext_inode_hdr(inode)->eh_depth);
}
static inline void ext4_ext_mark_uninitialized(struct ext4_extent *ext)
static inline void ext4_ext_mark_unwritten(struct ext4_extent *ext)
{
/* We can not have an uninitialized extent of zero length! */
/* We can not have an unwritten extent of zero length! */
BUG_ON((le16_to_cpu(ext->ee_len) & ~EXT_INIT_MAX_LEN) == 0);
ext->ee_len |= cpu_to_le16(EXT_INIT_MAX_LEN);
}
static inline int ext4_ext_is_uninitialized(struct ext4_extent *ext)
static inline int ext4_ext_is_unwritten(struct ext4_extent *ext)
{
/* Extent with ee_len of 0x8000 is treated as an initialized extent */
return (le16_to_cpu(ext->ee_len) > EXT_INIT_MAX_LEN);

222
fs/ext4/extents.c
View File

@ -50,8 +50,8 @@
*/
#define EXT4_EXT_MAY_ZEROOUT 0x1 /* safe to zeroout if split fails \
due to ENOSPC */
#define EXT4_EXT_MARK_UNINIT1 0x2 /* mark first half uninitialized */
#define EXT4_EXT_MARK_UNINIT2 0x4 /* mark second half uninitialized */
#define EXT4_EXT_MARK_UNWRIT1 0x2 /* mark first half unwritten */
#define EXT4_EXT_MARK_UNWRIT2 0x4 /* mark second half unwritten */
#define EXT4_EXT_DATA_VALID1 0x8 /* first half contains valid data */
#define EXT4_EXT_DATA_VALID2 0x10 /* second half contains valid data */
@ -524,7 +524,7 @@ __read_extent_tree_block(const char *function, unsigned int line,
lblk - prev, ~0,
EXTENT_STATUS_HOLE);
if (ext4_ext_is_uninitialized(ex))
if (ext4_ext_is_unwritten(ex))
status = EXTENT_STATUS_UNWRITTEN;
ext4_es_cache_extent(inode, lblk, len,
ext4_ext_pblock(ex), status);
@ -620,7 +620,7 @@ static void ext4_ext_show_path(struct inode *inode, struct ext4_ext_path *path)
} else if (path->p_ext) {
ext_debug(" %d:[%d]%d:%llu ",
le32_to_cpu(path->p_ext->ee_block),
ext4_ext_is_uninitialized(path->p_ext),
ext4_ext_is_unwritten(path->p_ext),
ext4_ext_get_actual_len(path->p_ext),
ext4_ext_pblock(path->p_ext));
} else
@ -646,7 +646,7 @@ static void ext4_ext_show_leaf(struct inode *inode, struct ext4_ext_path *path)
for (i = 0; i < le16_to_cpu(eh->eh_entries); i++, ex++) {
ext_debug("%d:[%d]%d:%llu ", le32_to_cpu(ex->ee_block),
ext4_ext_is_uninitialized(ex),
ext4_ext_is_unwritten(ex),
ext4_ext_get_actual_len(ex), ext4_ext_pblock(ex));
}
ext_debug("\n");
@ -677,7 +677,7 @@ static void ext4_ext_show_move(struct inode *inode, struct ext4_ext_path *path,
ext_debug("move %d:%llu:[%d]%d in new leaf %llu\n",
le32_to_cpu(ex->ee_block),
ext4_ext_pblock(ex),
ext4_ext_is_uninitialized(ex),
ext4_ext_is_unwritten(ex),
ext4_ext_get_actual_len(ex),
newblock);
ex++;
@ -802,7 +802,7 @@ ext4_ext_binsearch(struct inode *inode,
ext_debug(" -> %d:%llu:[%d]%d ",
le32_to_cpu(path->p_ext->ee_block),
ext4_ext_pblock(path->p_ext),
ext4_ext_is_uninitialized(path->p_ext),
ext4_ext_is_unwritten(path->p_ext),
ext4_ext_get_actual_len(path->p_ext));
#ifdef CHECK_BINSEARCH
@ -1686,11 +1686,11 @@ ext4_can_extents_be_merged(struct inode *inode, struct ext4_extent *ex1,
/*
* Make sure that both extents are initialized. We don't merge
* uninitialized extents so that we can be sure that end_io code has
* unwritten extents so that we can be sure that end_io code has
* the extent that was written properly split out and conversion to
* initialized is trivial.
*/
if (ext4_ext_is_uninitialized(ex1) != ext4_ext_is_uninitialized(ex2))
if (ext4_ext_is_unwritten(ex1) != ext4_ext_is_unwritten(ex2))
return 0;
ext1_ee_len = ext4_ext_get_actual_len(ex1);
@ -1707,10 +1707,10 @@ ext4_can_extents_be_merged(struct inode *inode, struct ext4_extent *ex1,
*/
if (ext1_ee_len + ext2_ee_len > EXT_INIT_MAX_LEN)
return 0;
if (ext4_ext_is_uninitialized(ex1) &&
if (ext4_ext_is_unwritten(ex1) &&
(ext4_test_inode_state(inode, EXT4_STATE_DIO_UNWRITTEN) ||
atomic_read(&EXT4_I(inode)->i_unwritten) ||
(ext1_ee_len + ext2_ee_len > EXT_UNINIT_MAX_LEN)))
(ext1_ee_len + ext2_ee_len > EXT_UNWRITTEN_MAX_LEN)))
return 0;
#ifdef AGGRESSIVE_TEST
if (ext1_ee_len >= 4)
@ -1735,7 +1735,7 @@ static int ext4_ext_try_to_merge_right(struct inode *inode,
{
struct ext4_extent_header *eh;
unsigned int depth, len;
int merge_done = 0, uninit;
int merge_done = 0, unwritten;
depth = ext_depth(inode);
BUG_ON(path[depth].p_hdr == NULL);
@ -1745,11 +1745,11 @@ static int ext4_ext_try_to_merge_right(struct inode *inode,
if (!ext4_can_extents_be_merged(inode, ex, ex + 1))
break;
/* merge with next extent! */
uninit = ext4_ext_is_uninitialized(ex);
unwritten = ext4_ext_is_unwritten(ex);
ex->ee_len = cpu_to_le16(ext4_ext_get_actual_len(ex)
+ ext4_ext_get_actual_len(ex + 1));
if (uninit)
ext4_ext_mark_uninitialized(ex);
if (unwritten)
ext4_ext_mark_unwritten(ex);
if (ex + 1 < EXT_LAST_EXTENT(eh)) {
len = (EXT_LAST_EXTENT(eh) - ex - 1)
@ -1903,7 +1903,7 @@ int ext4_ext_insert_extent(handle_t *handle, struct inode *inode,
struct ext4_ext_path *npath = NULL;
int depth, len, err;
ext4_lblk_t next;
int mb_flags = 0, uninit;
int mb_flags = 0, unwritten;
if (unlikely(ext4_ext_get_actual_len(newext) == 0)) {
EXT4_ERROR_INODE(inode, "ext4_ext_get_actual_len(newext) == 0");
@ -1943,21 +1943,21 @@ int ext4_ext_insert_extent(handle_t *handle, struct inode *inode,
if (ext4_can_extents_be_merged(inode, ex, newext)) {
ext_debug("append [%d]%d block to %u:[%d]%d"
"(from %llu)\n",
ext4_ext_is_uninitialized(newext),
ext4_ext_is_unwritten(newext),
ext4_ext_get_actual_len(newext),
le32_to_cpu(ex->ee_block),
ext4_ext_is_uninitialized(ex),
ext4_ext_is_unwritten(ex),
ext4_ext_get_actual_len(ex),
ext4_ext_pblock(ex));
err = ext4_ext_get_access(handle, inode,
path + depth);
if (err)
return err;
uninit = ext4_ext_is_uninitialized(ex);
unwritten = ext4_ext_is_unwritten(ex);
ex->ee_len = cpu_to_le16(ext4_ext_get_actual_len(ex)
+ ext4_ext_get_actual_len(newext));
if (uninit)
ext4_ext_mark_uninitialized(ex);
if (unwritten)
ext4_ext_mark_unwritten(ex);
eh = path[depth].p_hdr;
nearex = ex;
goto merge;
@ -1969,10 +1969,10 @@ prepend:
ext_debug("prepend %u[%d]%d block to %u:[%d]%d"
"(from %llu)\n",
le32_to_cpu(newext->ee_block),
ext4_ext_is_uninitialized(newext),
ext4_ext_is_unwritten(newext),
ext4_ext_get_actual_len(newext),
le32_to_cpu(ex->ee_block),
ext4_ext_is_uninitialized(ex),
ext4_ext_is_unwritten(ex),
ext4_ext_get_actual_len(ex),
ext4_ext_pblock(ex));
err = ext4_ext_get_access(handle, inode,
@ -1980,13 +1980,13 @@ prepend:
if (err)
return err;
uninit = ext4_ext_is_uninitialized(ex);
unwritten = ext4_ext_is_unwritten(ex);
ex->ee_block = newext->ee_block;
ext4_ext_store_pblock(ex, ext4_ext_pblock(newext));
ex->ee_len = cpu_to_le16(ext4_ext_get_actual_len(ex)
+ ext4_ext_get_actual_len(newext));
if (uninit)
ext4_ext_mark_uninitialized(ex);
if (unwritten)
ext4_ext_mark_unwritten(ex);
eh = path[depth].p_hdr;
nearex = ex;
goto merge;
@ -2046,7 +2046,7 @@ has_space:
ext_debug("first extent in the leaf: %u:%llu:[%d]%d\n",
le32_to_cpu(newext->ee_block),
ext4_ext_pblock(newext),
ext4_ext_is_uninitialized(newext),
ext4_ext_is_unwritten(newext),
ext4_ext_get_actual_len(newext));
nearex = EXT_FIRST_EXTENT(eh);
} else {
@ -2057,7 +2057,7 @@ has_space:
"nearest %p\n",
le32_to_cpu(newext->ee_block),
ext4_ext_pblock(newext),
ext4_ext_is_uninitialized(newext),
ext4_ext_is_unwritten(newext),
ext4_ext_get_actual_len(newext),
nearex);
nearex++;
@ -2068,7 +2068,7 @@ has_space:
"nearest %p\n",
le32_to_cpu(newext->ee_block),
ext4_ext_pblock(newext),
ext4_ext_is_uninitialized(newext),
ext4_ext_is_unwritten(newext),
ext4_ext_get_actual_len(newext),
nearex);
}
@ -2078,7 +2078,7 @@ has_space:
"move %d extents from 0x%p to 0x%p\n",
le32_to_cpu(newext->ee_block),
ext4_ext_pblock(newext),
ext4_ext_is_uninitialized(newext),
ext4_ext_is_unwritten(newext),
ext4_ext_get_actual_len(newext),
len, nearex, nearex + 1);
memmove(nearex + 1, nearex,
@ -2200,7 +2200,7 @@ static int ext4_fill_fiemap_extents(struct inode *inode,
es.es_lblk = le32_to_cpu(ex->ee_block);
es.es_len = ext4_ext_get_actual_len(ex);
es.es_pblk = ext4_ext_pblock(ex);
if (ext4_ext_is_uninitialized(ex))
if (ext4_ext_is_unwritten(ex))
flags |= FIEMAP_EXTENT_UNWRITTEN;
}
@ -2576,7 +2576,7 @@ ext4_ext_rm_leaf(handle_t *handle, struct inode *inode,
unsigned num;
ext4_lblk_t ex_ee_block;
unsigned short ex_ee_len;
unsigned uninitialized = 0;
unsigned unwritten = 0;
struct ext4_extent *ex;
ext4_fsblk_t pblk;
@ -2623,13 +2623,13 @@ ext4_ext_rm_leaf(handle_t *handle, struct inode *inode,
while (ex >= EXT_FIRST_EXTENT(eh) &&
ex_ee_block + ex_ee_len > start) {
if (ext4_ext_is_uninitialized(ex))
uninitialized = 1;
if (ext4_ext_is_unwritten(ex))
unwritten = 1;
else
uninitialized = 0;
unwritten = 0;
ext_debug("remove ext %u:[%d]%d\n", ex_ee_block,
uninitialized, ex_ee_len);
unwritten, ex_ee_len);
path[depth].p_ext = ex;
a = ex_ee_block > start ? ex_ee_block : start;
@ -2701,11 +2701,11 @@ ext4_ext_rm_leaf(handle_t *handle, struct inode *inode,
ex->ee_len = cpu_to_le16(num);
/*
* Do not mark uninitialized if all the blocks in the
* Do not mark unwritten if all the blocks in the
* extent have been removed.
*/
if (uninitialized && num)
ext4_ext_mark_uninitialized(ex);
if (unwritten && num)
ext4_ext_mark_unwritten(ex);
/*
* If the extent was completely released,
* we need to remove it from the leaf
@ -2854,9 +2854,9 @@ again:
end < ee_block + ext4_ext_get_actual_len(ex) - 1) {
int split_flag = 0;
if (ext4_ext_is_uninitialized(ex))
split_flag = EXT4_EXT_MARK_UNINIT1 |
EXT4_EXT_MARK_UNINIT2;
if (ext4_ext_is_unwritten(ex))
split_flag = EXT4_EXT_MARK_UNWRIT1 |
EXT4_EXT_MARK_UNWRIT2;
/*
* Split the extent in two so that 'end' is the last
@ -3113,7 +3113,7 @@ static int ext4_ext_zeroout(struct inode *inode, struct ext4_extent *ex)
* @path: the path to the extent
* @split: the logical block where the extent is splitted.
* @split_flags: indicates if the extent could be zeroout if split fails, and
* the states(init or uninit) of new extents.
* the states(init or unwritten) of new extents.
* @flags: flags used to insert new extent to extent tree.
*
*
@ -3155,10 +3155,10 @@ static int ext4_split_extent_at(handle_t *handle,
newblock = split - ee_block + ext4_ext_pblock(ex);
BUG_ON(split < ee_block || split >= (ee_block + ee_len));
BUG_ON(!ext4_ext_is_uninitialized(ex) &&
BUG_ON(!ext4_ext_is_unwritten(ex) &&
split_flag & (EXT4_EXT_MAY_ZEROOUT |
EXT4_EXT_MARK_UNINIT1 |
EXT4_EXT_MARK_UNINIT2));
EXT4_EXT_MARK_UNWRIT1 |
EXT4_EXT_MARK_UNWRIT2));
err = ext4_ext_get_access(handle, inode, path + depth);
if (err)
@ -3170,8 +3170,8 @@ static int ext4_split_extent_at(handle_t *handle,
* then we just change the state of the extent, and splitting
* is not needed.
*/
if (split_flag & EXT4_EXT_MARK_UNINIT2)
ext4_ext_mark_uninitialized(ex);
if (split_flag & EXT4_EXT_MARK_UNWRIT2)
ext4_ext_mark_unwritten(ex);
else
ext4_ext_mark_initialized(ex);
@ -3185,8 +3185,8 @@ static int ext4_split_extent_at(handle_t *handle,
/* case a */
memcpy(&orig_ex, ex, sizeof(orig_ex));
ex->ee_len = cpu_to_le16(split - ee_block);
if (split_flag & EXT4_EXT_MARK_UNINIT1)
ext4_ext_mark_uninitialized(ex);
if (split_flag & EXT4_EXT_MARK_UNWRIT1)
ext4_ext_mark_unwritten(ex);
/*
* path may lead to new leaf, not to original leaf any more
@ -3200,8 +3200,8 @@ static int ext4_split_extent_at(handle_t *handle,
ex2->ee_block = cpu_to_le32(split);
ex2->ee_len = cpu_to_le16(ee_len - (split - ee_block));
ext4_ext_store_pblock(ex2, newblock);
if (split_flag & EXT4_EXT_MARK_UNINIT2)
ext4_ext_mark_uninitialized(ex2);
if (split_flag & EXT4_EXT_MARK_UNWRIT2)
ext4_ext_mark_unwritten(ex2);
err = ext4_ext_insert_extent(handle, inode, path, &newex, flags);
if (err == -ENOSPC && (EXT4_EXT_MAY_ZEROOUT & split_flag)) {
@ -3278,7 +3278,7 @@ static int ext4_split_extent(handle_t *handle,
struct ext4_extent *ex;
unsigned int ee_len, depth;
int err = 0;
int uninitialized;
int unwritten;
int split_flag1, flags1;
int allocated = map->m_len;
@ -3286,14 +3286,14 @@ static int ext4_split_extent(handle_t *handle,
ex = path[depth].p_ext;
ee_block = le32_to_cpu(ex->ee_block);
ee_len = ext4_ext_get_actual_len(ex);
uninitialized = ext4_ext_is_uninitialized(ex);
unwritten = ext4_ext_is_unwritten(ex);
if (map->m_lblk + map->m_len < ee_block + ee_len) {
split_flag1 = split_flag & EXT4_EXT_MAY_ZEROOUT;
flags1 = flags | EXT4_GET_BLOCKS_PRE_IO;
if (uninitialized)
split_flag1 |= EXT4_EXT_MARK_UNINIT1 |
EXT4_EXT_MARK_UNINIT2;
if (unwritten)
split_flag1 |= EXT4_EXT_MARK_UNWRIT1 |
EXT4_EXT_MARK_UNWRIT2;
if (split_flag & EXT4_EXT_DATA_VALID2)
split_flag1 |= EXT4_EXT_DATA_VALID1;
err = ext4_split_extent_at(handle, inode, path,
@ -3318,15 +3318,15 @@ static int ext4_split_extent(handle_t *handle,
(unsigned long) map->m_lblk);
return -EIO;
}
uninitialized = ext4_ext_is_uninitialized(ex);
unwritten = ext4_ext_is_unwritten(ex);
split_flag1 = 0;
if (map->m_lblk >= ee_block) {
split_flag1 = split_flag & EXT4_EXT_DATA_VALID2;
if (uninitialized) {
split_flag1 |= EXT4_EXT_MARK_UNINIT1;
if (unwritten) {
split_flag1 |= EXT4_EXT_MARK_UNWRIT1;
split_flag1 |= split_flag & (EXT4_EXT_MAY_ZEROOUT |
EXT4_EXT_MARK_UNINIT2);
EXT4_EXT_MARK_UNWRIT2);
}
err = ext4_split_extent_at(handle, inode, path,
map->m_lblk, split_flag1, flags);
@ -3341,16 +3341,16 @@ out:
/*
* This function is called by ext4_ext_map_blocks() if someone tries to write
* to an uninitialized extent. It may result in splitting the uninitialized
* to an unwritten extent. It may result in splitting the unwritten
* extent into multiple extents (up to three - one initialized and two
* uninitialized).
* unwritten).
* There are three possibilities:
* a> There is no split required: Entire extent should be initialized
* 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
*
* Pre-conditions:
* - The extent pointed to by 'path' is uninitialized.
* - The extent pointed to by 'path' is unwritten.
* - The extent pointed to by 'path' contains a superset
* of the logical span [map->m_lblk, map->m_lblk + map->m_len).
*
@ -3396,12 +3396,12 @@ static int ext4_ext_convert_to_initialized(handle_t *handle,
trace_ext4_ext_convert_to_initialized_enter(inode, map, ex);
/* Pre-conditions */
BUG_ON(!ext4_ext_is_uninitialized(ex));
BUG_ON(!ext4_ext_is_unwritten(ex));
BUG_ON(!in_range(map->m_lblk, ee_block, ee_len));
/*
* Attempt to transfer newly initialized blocks from the currently
* uninitialized extent to its neighbor. This is much cheaper
* unwritten extent to its neighbor. This is much cheaper
* than an insertion followed by a merge as those involve costly
* memmove() calls. Transferring to the left is the common case in
* steady state for workloads doing fallocate(FALLOC_FL_KEEP_SIZE)
@ -3437,7 +3437,7 @@ static int ext4_ext_convert_to_initialized(handle_t *handle,
* - C4: abut_ex can receive the additional blocks without
* overflowing the (initialized) length limit.
*/
if ((!ext4_ext_is_uninitialized(abut_ex)) && /*C1*/
if ((!ext4_ext_is_unwritten(abut_ex)) && /*C1*/
((prev_lblk + prev_len) == ee_block) && /*C2*/
((prev_pblk + prev_len) == ee_pblk) && /*C3*/
(prev_len < (EXT_INIT_MAX_LEN - map_len))) { /*C4*/
@ -3452,7 +3452,7 @@ static int ext4_ext_convert_to_initialized(handle_t *handle,
ex->ee_block = cpu_to_le32(ee_block + map_len);
ext4_ext_store_pblock(ex, ee_pblk + map_len);
ex->ee_len = cpu_to_le16(ee_len - map_len);
ext4_ext_mark_uninitialized(ex); /* Restore the flag */
ext4_ext_mark_unwritten(ex); /* Restore the flag */
/* Extend abut_ex by 'map_len' blocks */
abut_ex->ee_len = cpu_to_le16(prev_len + map_len);
@ -3483,7 +3483,7 @@ static int ext4_ext_convert_to_initialized(handle_t *handle,
* - C4: abut_ex can receive the additional blocks without
* overflowing the (initialized) length limit.
*/
if ((!ext4_ext_is_uninitialized(abut_ex)) && /*C1*/
if ((!ext4_ext_is_unwritten(abut_ex)) && /*C1*/
((map->m_lblk + map_len) == next_lblk) && /*C2*/
((ee_pblk + ee_len) == next_pblk) && /*C3*/
(next_len < (EXT_INIT_MAX_LEN - map_len))) { /*C4*/
@ -3498,7 +3498,7 @@ static int ext4_ext_convert_to_initialized(handle_t *handle,
abut_ex->ee_block = cpu_to_le32(next_lblk - map_len);
ext4_ext_store_pblock(abut_ex, next_pblk - map_len);
ex->ee_len = cpu_to_le16(ee_len - map_len);
ext4_ext_mark_uninitialized(ex); /* Restore the flag */
ext4_ext_mark_unwritten(ex); /* Restore the flag */
/* Extend abut_ex by 'map_len' blocks */
abut_ex->ee_len = cpu_to_le16(next_len + map_len);
@ -3603,26 +3603,26 @@ out:
/*
* This function is called by ext4_ext_map_blocks() from
* ext4_get_blocks_dio_write() when DIO to write
* to an uninitialized extent.
* to an unwritten extent.
*
* Writing to an uninitialized extent may result in splitting the uninitialized
* extent into multiple initialized/uninitialized extents (up to three)
* Writing to an unwritten extent may result in splitting the unwritten
* extent into multiple initialized/unwritten extents (up to three)
* There are three possibilities:
* a> There is no split required: Entire extent should be uninitialized
* a> There is no split required: Entire extent should be unwritten
* 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
*
* This works the same way in the case of initialized -> unwritten conversion.
*
* One of more index blocks maybe needed if the extent tree grow after
* the uninitialized extent split. To prevent ENOSPC occur at the IO
* complete, we need to split the uninitialized extent before DIO submit
* the IO. The uninitialized extent called at this time will be split
* into three uninitialized extent(at most). After IO complete, the part
* the unwritten extent split. To prevent ENOSPC occur at the IO
* complete, we need to split the unwritten extent before DIO submit
* the IO. The unwritten extent called at this time will be split
* into three unwritten extent(at most). After IO complete, the part
* being filled will be convert to initialized by the end_io callback function
* via ext4_convert_unwritten_extents().
*
* Returns the size of uninitialized extent to be written on success.
* Returns the size of unwritten extent to be written on success.
*/
static int ext4_split_convert_extents(handle_t *handle,
struct inode *inode,
@ -3660,7 +3660,7 @@ static int ext4_split_convert_extents(handle_t *handle,
} else if (flags & EXT4_GET_BLOCKS_CONVERT) {
split_flag |= ee_block + ee_len <= eof_block ?
EXT4_EXT_MAY_ZEROOUT : 0;
split_flag |= (EXT4_EXT_MARK_UNINIT2 | EXT4_EXT_DATA_VALID2);
split_flag |= (EXT4_EXT_MARK_UNWRIT2 | EXT4_EXT_DATA_VALID2);
}
flags |= EXT4_GET_BLOCKS_PRE_IO;
return ext4_split_extent(handle, inode, path, map, split_flag, flags);
@ -3710,8 +3710,8 @@ static int ext4_convert_initialized_extents(handle_t *handle,
err = ext4_ext_get_access(handle, inode, path + depth);
if (err)
goto out;
/* first mark the extent as uninitialized */
ext4_ext_mark_uninitialized(ex);
/* first mark the extent as unwritten */
ext4_ext_mark_unwritten(ex);
/* note: ext4_ext_correct_indexes() isn't needed here because
* borders are not changed
@ -3971,10 +3971,10 @@ ext4_ext_convert_initialized_extent(handle_t *handle, struct inode *inode,
/*
* Make sure that the extent is no bigger than we support with
* uninitialized extent
* unwritten extent
*/
if (map->m_len > EXT_UNINIT_MAX_LEN)
map->m_len = EXT_UNINIT_MAX_LEN / 2;
if (map->m_len > EXT_UNWRITTEN_MAX_LEN)
map->m_len = EXT_UNWRITTEN_MAX_LEN / 2;
ret = ext4_convert_initialized_extents(handle, inode, map,
path);
@ -3993,7 +3993,7 @@ ext4_ext_convert_initialized_extent(handle_t *handle, struct inode *inode,
}
static int
ext4_ext_handle_uninitialized_extents(handle_t *handle, struct inode *inode,
ext4_ext_handle_unwritten_extents(handle_t *handle, struct inode *inode,
struct ext4_map_blocks *map,
struct ext4_ext_path *path, int flags,
unsigned int allocated, ext4_fsblk_t newblock)
@ -4002,19 +4002,19 @@ ext4_ext_handle_uninitialized_extents(handle_t *handle, struct inode *inode,
int err = 0;
ext4_io_end_t *io = ext4_inode_aio(inode);
ext_debug("ext4_ext_handle_uninitialized_extents: inode %lu, logical "
ext_debug("ext4_ext_handle_unwritten_extents: inode %lu, logical "
"block %llu, max_blocks %u, flags %x, allocated %u\n",
inode->i_ino, (unsigned long long)map->m_lblk, map->m_len,
flags, allocated);
ext4_ext_show_leaf(inode, path);
/*
* When writing into uninitialized space, we should not fail to
* When writing into unwritten space, we should not fail to
* allocate metadata blocks for the new extent block if needed.
*/
flags |= EXT4_GET_BLOCKS_METADATA_NOFAIL;
trace_ext4_ext_handle_uninitialized_extents(inode, map, flags,
trace_ext4_ext_handle_unwritten_extents(inode, map, flags,
allocated, newblock);
/* get_block() before submit the IO, split the extent */
@ -4033,8 +4033,6 @@ ext4_ext_handle_uninitialized_extents(handle_t *handle, struct inode *inode,
else
ext4_set_inode_state(inode, EXT4_STATE_DIO_UNWRITTEN);
map->m_flags |= EXT4_MAP_UNWRITTEN;
if (ext4_should_dioread_nolock(inode))
map->m_flags |= EXT4_MAP_UNINIT;
goto out;
}
/* IO end_io complete, convert the filled extent to written */
@ -4059,7 +4057,7 @@ ext4_ext_handle_uninitialized_extents(handle_t *handle, struct inode *inode,
* repeat fallocate creation request
* we already have an unwritten extent
*/
if (flags & EXT4_GET_BLOCKS_UNINIT_EXT) {
if (flags & EXT4_GET_BLOCKS_UNWRIT_EXT) {
map->m_flags |= EXT4_MAP_UNWRITTEN;
goto map_out;
}
@ -4310,7 +4308,7 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode,
/*
* Uninitialized extents are treated as holes, except that
* unwritten extents are treated as holes, except that
* we split out initialized portions during a write.
*/
ee_len = ext4_ext_get_actual_len(ex);
@ -4329,16 +4327,16 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode,
* If the extent is initialized check whether the
* caller wants to convert it to unwritten.
*/
if ((!ext4_ext_is_uninitialized(ex)) &&
if ((!ext4_ext_is_unwritten(ex)) &&
(flags & EXT4_GET_BLOCKS_CONVERT_UNWRITTEN)) {
allocated = ext4_ext_convert_initialized_extent(
handle, inode, map, path, flags,
allocated, newblock);
goto out2;
} else if (!ext4_ext_is_uninitialized(ex))
} else if (!ext4_ext_is_unwritten(ex))
goto out;
ret = ext4_ext_handle_uninitialized_extents(
ret = ext4_ext_handle_unwritten_extents(
handle, inode, map, path, flags,
allocated, newblock);
if (ret < 0)
@ -4410,15 +4408,15 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode,
/*
* See if request is beyond maximum number of blocks we can have in
* a single extent. For an initialized extent this limit is
* EXT_INIT_MAX_LEN and for an uninitialized extent this limit is
* EXT_UNINIT_MAX_LEN.
* EXT_INIT_MAX_LEN and for an unwritten extent this limit is
* EXT_UNWRITTEN_MAX_LEN.
*/
if (map->m_len > EXT_INIT_MAX_LEN &&
!(flags & EXT4_GET_BLOCKS_UNINIT_EXT))
!(flags & EXT4_GET_BLOCKS_UNWRIT_EXT))
map->m_len = EXT_INIT_MAX_LEN;
else if (map->m_len > EXT_UNINIT_MAX_LEN &&
(flags & EXT4_GET_BLOCKS_UNINIT_EXT))
map->m_len = EXT_UNINIT_MAX_LEN;
else if (map->m_len > EXT_UNWRITTEN_MAX_LEN &&
(flags & EXT4_GET_BLOCKS_UNWRIT_EXT))
map->m_len = EXT_UNWRITTEN_MAX_LEN;
/* Check if we can really insert (m_lblk)::(m_lblk + m_len) extent */
newex.ee_len = cpu_to_le16(map->m_len);
@ -4466,21 +4464,19 @@ got_allocated_blocks:
/* try to insert new extent into found leaf and return */
ext4_ext_store_pblock(&newex, newblock + offset);
newex.ee_len = cpu_to_le16(ar.len);
/* Mark uninitialized */
if (flags & EXT4_GET_BLOCKS_UNINIT_EXT){
ext4_ext_mark_uninitialized(&newex);
/* Mark unwritten */
if (flags & EXT4_GET_BLOCKS_UNWRIT_EXT){
ext4_ext_mark_unwritten(&newex);
map->m_flags |= EXT4_MAP_UNWRITTEN;
/*
* io_end structure was created for every IO write to an
* uninitialized extent. To avoid unnecessary conversion,
* unwritten extent. To avoid unnecessary conversion,
* here we flag the IO that really needs the conversion.
* For non asycn direct IO case, flag the inode state
* that we need to perform conversion when IO is done.
*/
if ((flags & EXT4_GET_BLOCKS_PRE_IO))
set_unwritten = 1;
if (ext4_should_dioread_nolock(inode))
map->m_flags |= EXT4_MAP_UNINIT;
}
err = 0;
@ -4607,9 +4603,9 @@ got_allocated_blocks:
/*
* Cache the extent and update transaction to commit on fdatasync only
* when it is _not_ an uninitialized extent.
* when it is _not_ an unwritten extent.
*/
if ((flags & EXT4_GET_BLOCKS_UNINIT_EXT) == 0)
if ((flags & EXT4_GET_BLOCKS_UNWRIT_EXT) == 0)
ext4_update_inode_fsync_trans(handle, inode, 1);
else
ext4_update_inode_fsync_trans(handle, inode, 0);
@ -4683,7 +4679,7 @@ static int ext4_alloc_file_blocks(struct file *file, ext4_lblk_t offset,
* that it doesn't get unnecessarily split into multiple
* extents.
*/
if (len <= EXT_UNINIT_MAX_LEN)
if (len <= EXT_UNWRITTEN_MAX_LEN)
flags |= EXT4_GET_BLOCKS_NO_NORMALIZE;
/*
@ -4775,7 +4771,7 @@ static long ext4_zero_range(struct file *file, loff_t offset,
else
max_blocks -= lblk;
flags = EXT4_GET_BLOCKS_CREATE_UNINIT_EXT |
flags = EXT4_GET_BLOCKS_CREATE_UNWRIT_EXT |
EXT4_GET_BLOCKS_CONVERT_UNWRITTEN;
if (mode & FALLOC_FL_KEEP_SIZE)
flags |= EXT4_GET_BLOCKS_KEEP_SIZE;
@ -4918,7 +4914,7 @@ long ext4_fallocate(struct file *file, int mode, loff_t offset, loff_t len)
max_blocks = (EXT4_BLOCK_ALIGN(len + offset, blkbits) >> blkbits)
- lblk;
flags = EXT4_GET_BLOCKS_CREATE_UNINIT_EXT;
flags = EXT4_GET_BLOCKS_CREATE_UNWRIT_EXT;
if (mode & FALLOC_FL_KEEP_SIZE)
flags |= EXT4_GET_BLOCKS_KEEP_SIZE;

2
fs/ext4/extents_status.c
View File

@ -433,7 +433,7 @@ static void ext4_es_insert_extent_ext_check(struct inode *inode,
ee_start = ext4_ext_pblock(ex);
ee_len = ext4_ext_get_actual_len(ex);
ee_status = ext4_ext_is_uninitialized(ex) ? 1 : 0;
ee_status = ext4_ext_is_unwritten(ex) ? 1 : 0;
es_status = ext4_es_is_unwritten(es) ? 1 : 0;
/*

154
fs/ext4/file.c
View File

@ -92,58 +92,91 @@ ext4_unaligned_aio(struct inode *inode, const struct iovec *iov,
}
static ssize_t
ext4_file_dio_write(struct kiocb *iocb, const struct iovec *iov,
unsigned long nr_segs, loff_t pos)
ext4_file_write(struct kiocb *iocb, const struct iovec *iov,
unsigned long nr_segs, loff_t pos)
{
struct file *file = iocb->ki_filp;
struct inode *inode = file->f_mapping->host;
struct inode *inode = file_inode(iocb->ki_filp);
struct mutex *aio_mutex = NULL;
struct blk_plug plug;
int unaligned_aio = 0;
ssize_t ret;
int o_direct = file->f_flags & O_DIRECT;
int overwrite = 0;
size_t length = iov_length(iov, nr_segs);
if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS) &&
!is_sync_kiocb(iocb))
unaligned_aio = ext4_unaligned_aio(inode, iov, nr_segs, pos);
/* Unaligned direct AIO must be serialized; see comment above */
if (unaligned_aio) {
mutex_lock(ext4_aio_mutex(inode));
ext4_unwritten_wait(inode);
}
ssize_t ret;
BUG_ON(iocb->ki_pos != pos);
/*
* Unaligned direct AIO must be serialized; see comment above
* In the case of O_APPEND, assume that we must always serialize
*/
if (o_direct &&
ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS) &&
!is_sync_kiocb(iocb) &&
(file->f_flags & O_APPEND ||
ext4_unaligned_aio(inode, iov, nr_segs, pos))) {
aio_mutex = ext4_aio_mutex(inode);
mutex_lock(aio_mutex);
ext4_unwritten_wait(inode);
}
mutex_lock(&inode->i_mutex);
blk_start_plug(&plug);
if (file->f_flags & O_APPEND)
iocb->ki_pos = pos = i_size_read(inode);
iocb->private = &overwrite;
/*
* If we have encountered a bitmap-format file, the size limit
* is smaller than s_maxbytes, which is for extent-mapped files.
*/
if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))) {
struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
/* check whether we do a DIO overwrite or not */
if (ext4_should_dioread_nolock(inode) && !unaligned_aio &&
!file->f_mapping->nrpages && pos + length <= i_size_read(inode)) {
struct ext4_map_blocks map;
unsigned int blkbits = inode->i_blkbits;
int err, len;
if ((pos > sbi->s_bitmap_maxbytes) ||
(pos == sbi->s_bitmap_maxbytes && length > 0)) {
mutex_unlock(&inode->i_mutex);
ret = -EFBIG;
goto errout;
}
map.m_lblk = pos >> blkbits;
map.m_len = (EXT4_BLOCK_ALIGN(pos + length, blkbits) >> blkbits)
- map.m_lblk;
len = map.m_len;
if (pos + length > sbi->s_bitmap_maxbytes) {
nr_segs = iov_shorten((struct iovec *)iov, nr_segs,
sbi->s_bitmap_maxbytes - pos);
}
}
err = ext4_map_blocks(NULL, inode, &map, 0);
/*
* 'err==len' means that all of blocks has been preallocated no
* matter they are initialized or not. For excluding
* uninitialized extents, we need to check m_flags. There are
* two conditions that indicate for initialized extents.
* 1) If we hit extent cache, EXT4_MAP_MAPPED flag is returned;
* 2) If we do a real lookup, non-flags are returned.
* So we should check these two conditions.
*/
if (err == len && (map.m_flags & EXT4_MAP_MAPPED))
overwrite = 1;
if (o_direct) {
blk_start_plug(&plug);
iocb->private = &overwrite;
/* check whether we do a DIO overwrite or not */
if (ext4_should_dioread_nolock(inode) && !aio_mutex &&
!file->f_mapping->nrpages && pos + length <= i_size_read(inode)) {
struct ext4_map_blocks map;
unsigned int blkbits = inode->i_blkbits;
int err, len;
map.m_lblk = pos >> blkbits;
map.m_len = (EXT4_BLOCK_ALIGN(pos + length, blkbits) >> blkbits)
- map.m_lblk;
len = map.m_len;
err = ext4_map_blocks(NULL, inode, &map, 0);
/*
* 'err==len' means that all of blocks has
* been preallocated no matter they are
* initialized or not. For excluding
* unwritten extents, we need to check
* m_flags. There are two conditions that
* indicate for initialized extents. 1) If we
* hit extent cache, EXT4_MAP_MAPPED flag is
* returned; 2) If we do a real lookup,
* non-flags are returned. So we should check
* these two conditions.
*/
if (err == len && (map.m_flags & EXT4_MAP_MAPPED))
overwrite = 1;
}
}
ret = __generic_file_aio_write(iocb, iov, nr_segs);
@ -156,45 +189,12 @@ ext4_file_dio_write(struct kiocb *iocb, const struct iovec *iov,
if (err < 0)
ret = err;
}
blk_finish_plug(&plug);
if (unaligned_aio)
mutex_unlock(ext4_aio_mutex(inode));
return ret;
}
static ssize_t
ext4_file_write(struct kiocb *iocb, const struct iovec *iov,
unsigned long nr_segs, loff_t pos)
{
struct inode *inode = file_inode(iocb->ki_filp);
ssize_t ret;
/*
* If we have encountered a bitmap-format file, the size limit
* is smaller than s_maxbytes, which is for extent-mapped files.
*/
if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))) {
struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
size_t length = iov_length(iov, nr_segs);
if ((pos > sbi->s_bitmap_maxbytes ||
(pos == sbi->s_bitmap_maxbytes && length > 0)))
return -EFBIG;
if (pos + length > sbi->s_bitmap_maxbytes) {
nr_segs = iov_shorten((struct iovec *)iov, nr_segs,
sbi->s_bitmap_maxbytes - pos);
}
}
if (unlikely(iocb->ki_filp->f_flags & O_DIRECT))
ret = ext4_file_dio_write(iocb, iov, nr_segs, pos);
else
ret = generic_file_aio_write(iocb, iov, nr_segs, pos);
if (o_direct)
blk_finish_plug(&plug);
errout:
if (aio_mutex)
mutex_unlock(aio_mutex);
return ret;
}

25
fs/ext4/inode.c
View File

@ -489,8 +489,8 @@ static void ext4_map_blocks_es_recheck(handle_t *handle,
* Otherwise, call with ext4_ind_map_blocks() to handle indirect mapping
* based files
*
* On success, it returns the number of blocks being mapped or allocate.
* if create==0 and the blocks are pre-allocated and uninitialized block,
* On success, it returns the number of blocks being mapped or allocated.
* if create==0 and the blocks are pre-allocated and unwritten block,
* the result buffer head is unmapped. If the create ==1, it will make sure
* the buffer head is mapped.
*
@ -622,7 +622,7 @@ found:
map->m_flags &= ~EXT4_MAP_FLAGS;
/*
* New blocks allocate and/or writing to uninitialized extent
* New blocks allocate and/or writing to unwritten extent
* will possibly result in updating i_data, so we take
* the write lock of i_data_sem, and call get_blocks()
* with create == 1 flag.
@ -2032,7 +2032,7 @@ static int mpage_process_page_bufs(struct mpage_da_data *mpd,
* Scan buffers corresponding to changed extent (we expect corresponding pages
* to be already locked) and update buffer state according to new extent state.
* We map delalloc buffers to their physical location, clear unwritten bits,
* and mark buffers as uninit when we perform writes to uninitialized extents
* and mark buffers as uninit when we perform writes to unwritten extents
* and do extent conversion after IO is finished. If the last page is not fully
* mapped, we update @map to the next extent in the last page that needs
* mapping. Otherwise we submit the page for IO.
@ -2126,12 +2126,12 @@ static int mpage_map_one_extent(handle_t *handle, struct mpage_da_data *mpd)
struct inode *inode = mpd->inode;
struct ext4_map_blocks *map = &mpd->map;
int get_blocks_flags;
int err;
int err, dioread_nolock;
trace_ext4_da_write_pages_extent(inode, map);
/*
* Call ext4_map_blocks() to allocate any delayed allocation blocks, or
* to convert an uninitialized extent to be initialized (in the case
* to convert an unwritten extent to be initialized (in the case
* where we have written into one or more preallocated blocks). It is
* possible that we're going to need more metadata blocks than
* previously reserved. However we must not fail because we're in
@ -2148,7 +2148,8 @@ static int mpage_map_one_extent(handle_t *handle, struct mpage_da_data *mpd)
*/
get_blocks_flags = EXT4_GET_BLOCKS_CREATE |
EXT4_GET_BLOCKS_METADATA_NOFAIL;
if (ext4_should_dioread_nolock(inode))
dioread_nolock = ext4_should_dioread_nolock(inode);
if (dioread_nolock)
get_blocks_flags |= EXT4_GET_BLOCKS_IO_CREATE_EXT;
if (map->m_flags & (1 << BH_Delay))
get_blocks_flags |= EXT4_GET_BLOCKS_DELALLOC_RESERVE;
@ -2156,7 +2157,7 @@ static int mpage_map_one_extent(handle_t *handle, struct mpage_da_data *mpd)
err = ext4_map_blocks(handle, inode, map, get_blocks_flags);
if (err < 0)
return err;
if (map->m_flags & EXT4_MAP_UNINIT) {
if (dioread_nolock && (map->m_flags & EXT4_MAP_UNWRITTEN)) {
if (!mpd->io_submit.io_end->handle &&
ext4_handle_valid(handle)) {
mpd->io_submit.io_end->handle = handle->h_rsv_handle;
@ -3070,9 +3071,9 @@ static void ext4_end_io_dio(struct kiocb *iocb, loff_t offset,
* preallocated extents, and those write extend the file, no need to
* fall back to buffered IO.
*
* For holes, we fallocate those blocks, mark them as uninitialized
* For holes, we fallocate those blocks, mark them as unwritten
* If those blocks were preallocated, we mark sure they are split, but
* still keep the range to write as uninitialized.
* still keep the range to write as unwritten.
*
* The unwritten extents will be converted to written when DIO is completed.
* For async direct IO, since the IO may still pending when return, we
@ -3123,12 +3124,12 @@ static ssize_t ext4_ext_direct_IO(int rw, struct kiocb *iocb,
* We could direct write to holes and fallocate.
*
* Allocated blocks to fill the hole are marked as
* uninitialized to prevent parallel buffered read to expose
* unwritten to prevent parallel buffered read to expose
* the stale data before DIO complete the data IO.
*
* As to previously fallocated extents, ext4 get_block will
* just simply mark the buffer mapped but still keep the
* extents uninitialized.
* extents unwritten.
*
* For non AIO case, we will convert those unwritten extents
* to written after return back from blockdev_direct_IO.

38
fs/ext4/move_extent.c
View File

@ -57,8 +57,8 @@ get_ext_path(struct inode *inode, ext4_lblk_t lblock,
static void
copy_extent_status(struct ext4_extent *src, struct ext4_extent *dest)
{
if (ext4_ext_is_uninitialized(src))
ext4_ext_mark_uninitialized(dest);
if (ext4_ext_is_unwritten(src))
ext4_ext_mark_unwritten(dest);
else
dest->ee_len = cpu_to_le16(ext4_ext_get_actual_len(dest));
}
@ -593,14 +593,14 @@ mext_calc_swap_extents(struct ext4_extent *tmp_dext,
* @inode: inode in question
* @from: block offset of inode
* @count: block count to be checked
* @uninit: extents expected to be uninitialized
* @unwritten: extents expected to be unwritten
* @err: pointer to save error value
*
* Return 1 if all extents in range has expected type, and zero otherwise.
*/
static int
mext_check_coverage(struct inode *inode, ext4_lblk_t from, ext4_lblk_t count,
int uninit, int *err)
int unwritten, int *err)
{
struct ext4_ext_path *path = NULL;
struct ext4_extent *ext;
@ -611,7 +611,7 @@ mext_check_coverage(struct inode *inode, ext4_lblk_t from, ext4_lblk_t count,
if (*err)
goto out;
ext = path[ext_depth(inode)].p_ext;
if (uninit != ext4_ext_is_uninitialized(ext))
if (unwritten != ext4_ext_is_unwritten(ext))
goto out;
from += ext4_ext_get_actual_len(ext);
ext4_ext_drop_refs(path);
@ -894,7 +894,7 @@ out:
* @orig_page_offset: page index on original file
* @data_offset_in_page: block index where data swapping starts
* @block_len_in_page: the number of blocks to be swapped
* @uninit: orig extent is uninitialized or not
* @unwritten: orig extent is unwritten or not
* @err: pointer to save return value
*
* Save the data in original inode blocks and replace original inode extents
@ -905,7 +905,7 @@ out:
static int
move_extent_per_page(struct file *o_filp, struct inode *donor_inode,
pgoff_t orig_page_offset, int data_offset_in_page,
int block_len_in_page, int uninit, int *err)
int block_len_in_page, int unwritten, int *err)
{
struct inode *orig_inode = file_inode(o_filp);
struct page *pagep[2] = {NULL, NULL};
@ -962,27 +962,27 @@ again:
if (unlikely(*err < 0))
goto stop_journal;
/*
* If orig extent was uninitialized it can become initialized
* If orig extent was unwritten it can become initialized
* at any time after i_data_sem was dropped, in order to
* serialize with delalloc we have recheck extent while we
* hold page's lock, if it is still the case data copy is not
* necessary, just swap data blocks between orig and donor.
*/
if (uninit) {
if (unwritten) {
ext4_double_down_write_data_sem(orig_inode, donor_inode);
/* If any of extents in range became initialized we have to
* fallback to data copying */
uninit = mext_check_coverage(orig_inode, orig_blk_offset,
block_len_in_page, 1, err);
unwritten = mext_check_coverage(orig_inode, orig_blk_offset,
block_len_in_page, 1, err);
if (*err)
goto drop_data_sem;
uninit &= mext_check_coverage(donor_inode, orig_blk_offset,
block_len_in_page, 1, err);
unwritten &= mext_check_coverage(donor_inode, orig_blk_offset,
block_len_in_page, 1, err);
if (*err)
goto drop_data_sem;
if (!uninit) {
if (!unwritten) {
ext4_double_up_write_data_sem(orig_inode, donor_inode);
goto data_copy;
}
@ -1259,7 +1259,7 @@ ext4_move_extents(struct file *o_filp, struct file *d_filp,
int blocks_per_page = PAGE_CACHE_SIZE >> orig_inode->i_blkbits;
int data_offset_in_page;
int block_len_in_page;
int uninit;
int unwritten;
if (orig_inode->i_sb != donor_inode->i_sb) {
ext4_debug("ext4 move extent: The argument files "
@ -1391,8 +1391,8 @@ ext4_move_extents(struct file *o_filp, struct file *d_filp,
!last_extent)
continue;
/* Is original extent is uninitialized */
uninit = ext4_ext_is_uninitialized(ext_prev);
/* Is original extent is unwritten */
unwritten = ext4_ext_is_unwritten(ext_prev);
data_offset_in_page = seq_start % blocks_per_page;
@ -1432,8 +1432,8 @@ ext4_move_extents(struct file *o_filp, struct file *d_filp,
o_filp, donor_inode,
orig_page_offset,
data_offset_in_page,
block_len_in_page, uninit,
&ret);
block_len_in_page,
unwritten, &ret);
/* Count how many blocks we have exchanged */
*moved_len += block_len_in_page;

2
fs/ext4/super.c
View File

@ -3337,7 +3337,7 @@ static ext4_fsblk_t ext4_calculate_resv_clusters(struct super_block *sb)
* By default we reserve 2% or 4096 clusters, whichever is smaller.
* This should cover the situations where we can not afford to run
* out of space like for example punch hole, or converting
* uninitialized extents in delalloc path. In most cases such
* unwritten extents in delalloc path. In most cases such
* allocation would require 1, or 2 blocks, higher numbers are
* very rare.
*/

9
include/trace/events/ext4.h
View File

@ -36,7 +36,7 @@ struct extent_status;
#define show_map_flags(flags) __print_flags(flags, "|", \
{ EXT4_GET_BLOCKS_CREATE, "CREATE" }, \
{ EXT4_GET_BLOCKS_UNINIT_EXT, "UNINIT" }, \
{ EXT4_GET_BLOCKS_UNWRIT_EXT, "UNWRIT" }, \
{ EXT4_GET_BLOCKS_DELALLOC_RESERVE, "DELALLOC" }, \
{ EXT4_GET_BLOCKS_PRE_IO, "PRE_IO" }, \
{ EXT4_GET_BLOCKS_CONVERT, "CONVERT" }, \
@ -51,7 +51,6 @@ struct extent_status;
{ EXT4_MAP_MAPPED, "M" }, \
{ EXT4_MAP_UNWRITTEN, "U" }, \
{ EXT4_MAP_BOUNDARY, "B" }, \
{ EXT4_MAP_UNINIT, "u" }, \
{ EXT4_MAP_FROM_CLUSTER, "C" })
#define show_free_flags(flags) __print_flags(flags, "|", \
@ -1497,7 +1496,7 @@ DEFINE_EVENT(ext4__truncate, ext4_truncate_exit,
TP_ARGS(inode)
);
/* 'ux' is the uninitialized extent. */
/* 'ux' is the unwritten extent. */
TRACE_EVENT(ext4_ext_convert_to_initialized_enter,
TP_PROTO(struct inode *inode, struct ext4_map_blocks *map,
struct ext4_extent *ux),
@ -1533,7 +1532,7 @@ TRACE_EVENT(ext4_ext_convert_to_initialized_enter,
);
/*
* 'ux' is the uninitialized extent.
* 'ux' is the unwritten extent.
* 'ix' is the initialized extent to which blocks are transferred.
*/
TRACE_EVENT(ext4_ext_convert_to_initialized_fastpath,
@ -1811,7 +1810,7 @@ DEFINE_EVENT(ext4__trim, ext4_trim_all_free,
TP_ARGS(sb, group, start, len)
);
TRACE_EVENT(ext4_ext_handle_uninitialized_extents,
TRACE_EVENT(ext4_ext_handle_unwritten_extents,
TP_PROTO(struct inode *inode, struct ext4_map_blocks *map, int flags,
unsigned int allocated, ext4_fsblk_t newblock),