summaryrefslogtreecommitdiffstats
path: root/fs/ext4/extents.c
diff options
context:
space:
mode:
Diffstat (limited to 'fs/ext4/extents.c')
-rw-r--r--fs/ext4/extents.c841
1 files changed, 518 insertions, 323 deletions
diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index 74292a71b38..bed43081720 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -73,8 +73,7 @@ static int ext4_extent_block_csum_verify(struct inode *inode,
{
struct ext4_extent_tail *et;
- if (!EXT4_HAS_RO_COMPAT_FEATURE(inode->i_sb,
- EXT4_FEATURE_RO_COMPAT_METADATA_CSUM))
+ if (!ext4_has_metadata_csum(inode->i_sb))
return 1;
et = find_ext4_extent_tail(eh);
@@ -88,8 +87,7 @@ static void ext4_extent_block_csum_set(struct inode *inode,
{
struct ext4_extent_tail *et;
- if (!EXT4_HAS_RO_COMPAT_FEATURE(inode->i_sb,
- EXT4_FEATURE_RO_COMPAT_METADATA_CSUM))
+ if (!ext4_has_metadata_csum(inode->i_sb))
return;
et = find_ext4_extent_tail(eh);
@@ -98,14 +96,14 @@ static void ext4_extent_block_csum_set(struct inode *inode,
static int ext4_split_extent(handle_t *handle,
struct inode *inode,
- struct ext4_ext_path *path,
+ struct ext4_ext_path **ppath,
struct ext4_map_blocks *map,
int split_flag,
int flags);
static int ext4_split_extent_at(handle_t *handle,
struct inode *inode,
- struct ext4_ext_path *path,
+ struct ext4_ext_path **ppath,
ext4_lblk_t split,
int split_flag,
int flags);
@@ -291,6 +289,20 @@ static inline int ext4_ext_space_root_idx(struct inode *inode, int check)
return size;
}
+static inline int
+ext4_force_split_extent_at(handle_t *handle, struct inode *inode,
+ struct ext4_ext_path **ppath, ext4_lblk_t lblk,
+ int nofail)
+{
+ struct ext4_ext_path *path = *ppath;
+ int unwritten = ext4_ext_is_unwritten(path[path->p_depth].p_ext);
+
+ return ext4_split_extent_at(handle, inode, ppath, lblk, unwritten ?
+ EXT4_EXT_MARK_UNWRIT1|EXT4_EXT_MARK_UNWRIT2 : 0,
+ EXT4_EX_NOCACHE | EXT4_GET_BLOCKS_PRE_IO |
+ (nofail ? EXT4_GET_BLOCKS_METADATA_NOFAIL:0));
+}
+
/*
* Calculate the number of metadata blocks needed
* to allocate @blocks
@@ -695,9 +707,11 @@ static void ext4_ext_show_move(struct inode *inode, struct ext4_ext_path *path,
void ext4_ext_drop_refs(struct ext4_ext_path *path)
{
- int depth = path->p_depth;
- int i;
+ int depth, i;
+ if (!path)
+ return;
+ depth = path->p_depth;
for (i = 0; i <= depth; i++, path++)
if (path->p_bh) {
brelse(path->p_bh);
@@ -841,24 +855,32 @@ int ext4_ext_tree_init(handle_t *handle, struct inode *inode)
}
struct ext4_ext_path *
-ext4_ext_find_extent(struct inode *inode, ext4_lblk_t block,
- struct ext4_ext_path *path, int flags)
+ext4_find_extent(struct inode *inode, ext4_lblk_t block,
+ struct ext4_ext_path **orig_path, int flags)
{
struct ext4_extent_header *eh;
struct buffer_head *bh;
- short int depth, i, ppos = 0, alloc = 0;
+ struct ext4_ext_path *path = orig_path ? *orig_path : NULL;
+ short int depth, i, ppos = 0;
int ret;
eh = ext_inode_hdr(inode);
depth = ext_depth(inode);
- /* account possible depth increase */
+ if (path) {
+ ext4_ext_drop_refs(path);
+ if (depth > path[0].p_maxdepth) {
+ kfree(path);
+ *orig_path = path = NULL;
+ }
+ }
if (!path) {
+ /* account possible depth increase */
path = kzalloc(sizeof(struct ext4_ext_path) * (depth + 2),
GFP_NOFS);
- if (!path)
+ if (unlikely(!path))
return ERR_PTR(-ENOMEM);
- alloc = 1;
+ path[0].p_maxdepth = depth + 1;
}
path[0].p_hdr = eh;
path[0].p_bh = NULL;
@@ -876,7 +898,7 @@ ext4_ext_find_extent(struct inode *inode, ext4_lblk_t block,
bh = read_extent_tree_block(inode, path[ppos].p_block, --i,
flags);
- if (IS_ERR(bh)) {
+ if (unlikely(IS_ERR(bh))) {
ret = PTR_ERR(bh);
goto err;
}
@@ -910,8 +932,9 @@ ext4_ext_find_extent(struct inode *inode, ext4_lblk_t block,
err:
ext4_ext_drop_refs(path);
- if (alloc)
- kfree(path);
+ kfree(path);
+ if (orig_path)
+ *orig_path = NULL;
return ERR_PTR(ret);
}
@@ -1238,16 +1261,24 @@ cleanup:
* just created block
*/
static int ext4_ext_grow_indepth(handle_t *handle, struct inode *inode,
- unsigned int flags,
- struct ext4_extent *newext)
+ unsigned int flags)
{
struct ext4_extent_header *neh;
struct buffer_head *bh;
- ext4_fsblk_t newblock;
+ ext4_fsblk_t newblock, goal = 0;
+ struct ext4_super_block *es = EXT4_SB(inode->i_sb)->s_es;
int err = 0;
- newblock = ext4_ext_new_meta_block(handle, inode, NULL,
- newext, &err, flags);
+ /* Try to prepend new index to old one */
+ if (ext_depth(inode))
+ goal = ext4_idx_pblock(EXT_FIRST_INDEX(ext_inode_hdr(inode)));
+ if (goal > le32_to_cpu(es->s_first_data_block)) {
+ flags |= EXT4_MB_HINT_TRY_GOAL;
+ goal--;
+ } else
+ goal = ext4_inode_to_goal_block(inode);
+ newblock = ext4_new_meta_blocks(handle, inode, goal, flags,
+ NULL, &err);
if (newblock == 0)
return err;
@@ -1314,9 +1345,10 @@ out:
static int ext4_ext_create_new_leaf(handle_t *handle, struct inode *inode,
unsigned int mb_flags,
unsigned int gb_flags,
- struct ext4_ext_path *path,
+ struct ext4_ext_path **ppath,
struct ext4_extent *newext)
{
+ struct ext4_ext_path *path = *ppath;
struct ext4_ext_path *curp;
int depth, i, err = 0;
@@ -1340,23 +1372,21 @@ repeat:
goto out;
/* refill path */
- ext4_ext_drop_refs(path);
- path = ext4_ext_find_extent(inode,
+ path = ext4_find_extent(inode,
(ext4_lblk_t)le32_to_cpu(newext->ee_block),
- path, gb_flags);
+ ppath, gb_flags);
if (IS_ERR(path))
err = PTR_ERR(path);
} else {
/* tree is full, time to grow in depth */
- err = ext4_ext_grow_indepth(handle, inode, mb_flags, newext);
+ err = ext4_ext_grow_indepth(handle, inode, mb_flags);
if (err)
goto out;
/* refill path */
- ext4_ext_drop_refs(path);
- path = ext4_ext_find_extent(inode,
+ path = ext4_find_extent(inode,
(ext4_lblk_t)le32_to_cpu(newext->ee_block),
- path, gb_flags);
+ ppath, gb_flags);
if (IS_ERR(path)) {
err = PTR_ERR(path);
goto out;
@@ -1559,7 +1589,7 @@ found_extent:
* allocated block. Thus, index entries have to be consistent
* with leaves.
*/
-static ext4_lblk_t
+ext4_lblk_t
ext4_ext_next_allocated_block(struct ext4_ext_path *path)
{
int depth;
@@ -1802,6 +1832,7 @@ static void ext4_ext_try_to_merge_up(handle_t *handle,
sizeof(struct ext4_extent_idx);
s += sizeof(struct ext4_extent_header);
+ path[1].p_maxdepth = path[0].p_maxdepth;
memcpy(path[0].p_hdr, path[1].p_hdr, s);
path[0].p_depth = 0;
path[0].p_ext = EXT_FIRST_EXTENT(path[0].p_hdr) +
@@ -1896,9 +1927,10 @@ out:
* creating new leaf in the no-space case.
*/
int ext4_ext_insert_extent(handle_t *handle, struct inode *inode,
- struct ext4_ext_path *path,
+ struct ext4_ext_path **ppath,
struct ext4_extent *newext, int gb_flags)
{
+ struct ext4_ext_path *path = *ppath;
struct ext4_extent_header *eh;
struct ext4_extent *ex, *fex;
struct ext4_extent *nearex; /* nearest extent */
@@ -1907,6 +1939,8 @@ int ext4_ext_insert_extent(handle_t *handle, struct inode *inode,
ext4_lblk_t next;
int mb_flags = 0, unwritten;
+ if (gb_flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE)
+ mb_flags |= EXT4_MB_DELALLOC_RESERVED;
if (unlikely(ext4_ext_get_actual_len(newext) == 0)) {
EXT4_ERROR_INODE(inode, "ext4_ext_get_actual_len(newext) == 0");
return -EIO;
@@ -1925,7 +1959,7 @@ int ext4_ext_insert_extent(handle_t *handle, struct inode *inode,
/*
* Try to see whether we should rather test the extent on
* right from ex, or from the left of ex. This is because
- * ext4_ext_find_extent() can return either extent on the
+ * ext4_find_extent() can return either extent on the
* left, or on the right from the searched position. This
* will make merging more effective.
*/
@@ -2008,7 +2042,7 @@ prepend:
if (next != EXT_MAX_BLOCKS) {
ext_debug("next leaf block - %u\n", next);
BUG_ON(npath != NULL);
- npath = ext4_ext_find_extent(inode, next, NULL, 0);
+ npath = ext4_find_extent(inode, next, NULL, 0);
if (IS_ERR(npath))
return PTR_ERR(npath);
BUG_ON(npath->p_depth != path->p_depth);
@@ -2028,9 +2062,9 @@ prepend:
* We're gonna add a new leaf in the tree.
*/
if (gb_flags & EXT4_GET_BLOCKS_METADATA_NOFAIL)
- mb_flags = EXT4_MB_USE_RESERVED;
+ mb_flags |= EXT4_MB_USE_RESERVED;
err = ext4_ext_create_new_leaf(handle, inode, mb_flags, gb_flags,
- path, newext);
+ ppath, newext);
if (err)
goto cleanup;
depth = ext_depth(inode);
@@ -2108,10 +2142,8 @@ merge:
err = ext4_ext_dirty(handle, inode, path + path->p_depth);
cleanup:
- if (npath) {
- ext4_ext_drop_refs(npath);
- kfree(npath);
- }
+ ext4_ext_drop_refs(npath);
+ kfree(npath);
return err;
}
@@ -2133,13 +2165,7 @@ static int ext4_fill_fiemap_extents(struct inode *inode,
/* find extent for this block */
down_read(&EXT4_I(inode)->i_data_sem);
- if (path && ext_depth(inode) != depth) {
- /* depth was changed. we have to realloc path */
- kfree(path);
- path = NULL;
- }
-
- path = ext4_ext_find_extent(inode, block, path, 0);
+ path = ext4_find_extent(inode, block, &path, 0);
if (IS_ERR(path)) {
up_read(&EXT4_I(inode)->i_data_sem);
err = PTR_ERR(path);
@@ -2156,7 +2182,6 @@ static int ext4_fill_fiemap_extents(struct inode *inode,
}
ex = path[depth].p_ext;
next = ext4_ext_next_allocated_block(path);
- ext4_ext_drop_refs(path);
flags = 0;
exists = 0;
@@ -2266,11 +2291,8 @@ static int ext4_fill_fiemap_extents(struct inode *inode,
block = es.es_lblk + es.es_len;
}
- if (path) {
- ext4_ext_drop_refs(path);
- kfree(path);
- }
-
+ ext4_ext_drop_refs(path);
+ kfree(path);
return err;
}
@@ -2284,16 +2306,16 @@ ext4_ext_put_gap_in_cache(struct inode *inode, struct ext4_ext_path *path,
ext4_lblk_t block)
{
int depth = ext_depth(inode);
- unsigned long len = 0;
- ext4_lblk_t lblock = 0;
+ ext4_lblk_t len;
+ ext4_lblk_t lblock;
struct ext4_extent *ex;
+ struct extent_status es;
ex = path[depth].p_ext;
if (ex == NULL) {
- /*
- * there is no extent yet, so gap is [0;-] and we
- * don't cache it
- */
+ /* there is no extent yet, so gap is [0;-] */
+ lblock = 0;
+ len = EXT_MAX_BLOCKS;
ext_debug("cache gap(whole file):");
} else if (block < le32_to_cpu(ex->ee_block)) {
lblock = block;
@@ -2302,9 +2324,6 @@ ext4_ext_put_gap_in_cache(struct inode *inode, struct ext4_ext_path *path,
block,
le32_to_cpu(ex->ee_block),
ext4_ext_get_actual_len(ex));
- if (!ext4_find_delalloc_range(inode, lblock, lblock + len - 1))
- ext4_es_insert_extent(inode, lblock, len, ~0,
- EXTENT_STATUS_HOLE);
} else if (block >= le32_to_cpu(ex->ee_block)
+ ext4_ext_get_actual_len(ex)) {
ext4_lblk_t next;
@@ -2318,14 +2337,19 @@ ext4_ext_put_gap_in_cache(struct inode *inode, struct ext4_ext_path *path,
block);
BUG_ON(next == lblock);
len = next - lblock;
- if (!ext4_find_delalloc_range(inode, lblock, lblock + len - 1))
- ext4_es_insert_extent(inode, lblock, len, ~0,
- EXTENT_STATUS_HOLE);
} else {
BUG();
}
- ext_debug(" -> %u:%lu\n", lblock, len);
+ ext4_es_find_delayed_extent_range(inode, lblock, lblock + len - 1, &es);
+ if (es.es_len) {
+ /* There's delayed extent containing lblock? */
+ if (es.es_lblk <= lblock)
+ return;
+ len = min(es.es_lblk - lblock, len);
+ }
+ ext_debug(" -> %u:%u\n", lblock, len);
+ ext4_es_insert_extent(inode, lblock, len, ~0, EXTENT_STATUS_HOLE);
}
/*
@@ -2459,7 +2483,7 @@ static int ext4_remove_blocks(handle_t *handle, struct inode *inode,
ext4_lblk_t from, ext4_lblk_t to)
{
struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
- unsigned short ee_len = ext4_ext_get_actual_len(ex);
+ unsigned short ee_len = ext4_ext_get_actual_len(ex);
ext4_fsblk_t pblk;
int flags = get_default_free_blocks_flags(inode);
@@ -2468,7 +2492,7 @@ static int ext4_remove_blocks(handle_t *handle, struct inode *inode,
* at the beginning of the extent. Instead, we make a note
* that we tried freeing the cluster, and check to see if we
* need to free it on a subsequent call to ext4_remove_blocks,
- * or at the end of the ext4_truncate() operation.
+ * or at the end of ext4_ext_rm_leaf or ext4_ext_remove_space.
*/
flags |= EXT4_FREE_BLOCKS_NOFREE_FIRST_CLUSTER;
@@ -2479,8 +2503,8 @@ static int ext4_remove_blocks(handle_t *handle, struct inode *inode,
* partial cluster here.
*/
pblk = ext4_ext_pblock(ex) + ee_len - 1;
- if ((*partial_cluster > 0) &&
- (EXT4_B2C(sbi, pblk) != *partial_cluster)) {
+ if (*partial_cluster > 0 &&
+ *partial_cluster != (long long) EXT4_B2C(sbi, pblk)) {
ext4_free_blocks(handle, inode, NULL,
EXT4_C2B(sbi, *partial_cluster),
sbi->s_cluster_ratio, flags);
@@ -2506,7 +2530,7 @@ static int ext4_remove_blocks(handle_t *handle, struct inode *inode,
&& to == le32_to_cpu(ex->ee_block) + ee_len - 1) {
/* tail removal */
ext4_lblk_t num;
- unsigned int unaligned;
+ long long first_cluster;
num = le32_to_cpu(ex->ee_block) + ee_len - from;
pblk = ext4_ext_pblock(ex) + ee_len - num;
@@ -2516,7 +2540,7 @@ static int ext4_remove_blocks(handle_t *handle, struct inode *inode,
* used by any other extent (partial_cluster is negative).
*/
if (*partial_cluster < 0 &&
- -(*partial_cluster) == EXT4_B2C(sbi, pblk + num - 1))
+ *partial_cluster == -(long long) EXT4_B2C(sbi, pblk+num-1))
flags |= EXT4_FREE_BLOCKS_NOFREE_LAST_CLUSTER;
ext_debug("free last %u blocks starting %llu partial %lld\n",
@@ -2527,21 +2551,24 @@ static int ext4_remove_blocks(handle_t *handle, struct inode *inode,
* beginning of a cluster, and we removed the entire
* extent and the cluster is not used by any other extent,
* save the partial cluster here, since we might need to
- * delete if we determine that the truncate operation has
- * removed all of the blocks in the cluster.
+ * delete if we determine that the truncate or punch hole
+ * operation has removed all of the blocks in the cluster.
+ * If that cluster is used by another extent, preserve its
+ * negative value so it isn't freed later on.
*
- * On the other hand, if we did not manage to free the whole
- * extent, we have to mark the cluster as used (store negative
- * cluster number in partial_cluster).
+ * If the whole extent wasn't freed, we've reached the
+ * start of the truncated/punched region and have finished
+ * removing blocks. If there's a partial cluster here it's
+ * shared with the remainder of the extent and is no longer
+ * a candidate for removal.
*/
- unaligned = EXT4_PBLK_COFF(sbi, pblk);
- if (unaligned && (ee_len == num) &&
- (*partial_cluster != -((long long)EXT4_B2C(sbi, pblk))))
- *partial_cluster = EXT4_B2C(sbi, pblk);
- else if (unaligned)
- *partial_cluster = -((long long)EXT4_B2C(sbi, pblk));
- else if (*partial_cluster > 0)
+ if (EXT4_PBLK_COFF(sbi, pblk) && ee_len == num) {
+ first_cluster = (long long) EXT4_B2C(sbi, pblk);
+ if (first_cluster != -*partial_cluster)
+ *partial_cluster = first_cluster;
+ } else {
*partial_cluster = 0;
+ }
} else
ext4_error(sbi->s_sb, "strange request: removal(2) "
"%u-%u from %u:%u\n",
@@ -2552,15 +2579,16 @@ static int ext4_remove_blocks(handle_t *handle, struct inode *inode,
/*
* ext4_ext_rm_leaf() Removes the extents associated with the
- * blocks appearing between "start" and "end", and splits the extents
- * if "start" and "end" appear in the same extent
+ * blocks appearing between "start" and "end". Both "start"
+ * and "end" must appear in the same extent or EIO is returned.
*
* @handle: The journal handle
* @inode: The files inode
* @path: The path to the leaf
* @partial_cluster: The cluster which we'll have to free if all extents
- * has been released from it. It gets negative in case
- * that the cluster is still used.
+ * has been released from it. However, if this value is
+ * negative, it's a cluster just to the right of the
+ * punched region and it must not be freed.
* @start: The first block to remove
* @end: The last block to remove
*/
@@ -2599,27 +2627,6 @@ ext4_ext_rm_leaf(handle_t *handle, struct inode *inode,
ex_ee_block = le32_to_cpu(ex->ee_block);
ex_ee_len = ext4_ext_get_actual_len(ex);
- /*
- * If we're starting with an extent other than the last one in the
- * node, we need to see if it shares a cluster with the extent to
- * the right (towards the end of the file). If its leftmost cluster
- * is this extent's rightmost cluster and it is not cluster aligned,
- * we'll mark it as a partial that is not to be deallocated.
- */
-
- if (ex != EXT_LAST_EXTENT(eh)) {
- ext4_fsblk_t current_pblk, right_pblk;
- long long current_cluster, right_cluster;
-
- current_pblk = ext4_ext_pblock(ex) + ex_ee_len - 1;
- current_cluster = (long long)EXT4_B2C(sbi, current_pblk);
- right_pblk = ext4_ext_pblock(ex + 1);
- right_cluster = (long long)EXT4_B2C(sbi, right_pblk);
- if (current_cluster == right_cluster &&
- EXT4_PBLK_COFF(sbi, right_pblk))
- *partial_cluster = -right_cluster;
- }
-
trace_ext4_ext_rm_leaf(inode, start, ex, *partial_cluster);
while (ex >= EXT_FIRST_EXTENT(eh) &&
@@ -2644,14 +2651,16 @@ ext4_ext_rm_leaf(handle_t *handle, struct inode *inode,
if (end < ex_ee_block) {
/*
* We're going to skip this extent and move to another,
- * so if this extent is not cluster aligned we have
- * to mark the current cluster as used to avoid
- * accidentally freeing it later on
+ * so note that its first cluster is in use to avoid
+ * freeing it when removing blocks. Eventually, the
+ * right edge of the truncated/punched region will
+ * be just to the left.
*/
- pblk = ext4_ext_pblock(ex);
- if (EXT4_PBLK_COFF(sbi, pblk))
+ if (sbi->s_cluster_ratio > 1) {
+ pblk = ext4_ext_pblock(ex);
*partial_cluster =
- -((long long)EXT4_B2C(sbi, pblk));
+ -(long long) EXT4_B2C(sbi, pblk);
+ }
ex--;
ex_ee_block = le32_to_cpu(ex->ee_block);
ex_ee_len = ext4_ext_get_actual_len(ex);
@@ -2727,8 +2736,7 @@ ext4_ext_rm_leaf(handle_t *handle, struct inode *inode,
sizeof(struct ext4_extent));
}
le16_add_cpu(&eh->eh_entries, -1);
- } else if (*partial_cluster > 0)
- *partial_cluster = 0;
+ }
err = ext4_ext_dirty(handle, inode, path + depth);
if (err)
@@ -2747,20 +2755,18 @@ ext4_ext_rm_leaf(handle_t *handle, struct inode *inode,
/*
* If there's a partial cluster and at least one extent remains in
* the leaf, free the partial cluster if it isn't shared with the
- * current extent. If there's a partial cluster and no extents
- * remain in the leaf, it can't be freed here. It can only be
- * freed when it's possible to determine if it's not shared with
- * any other extent - when the next leaf is processed or when space
- * removal is complete.
+ * current extent. If it is shared with the current extent
+ * we zero partial_cluster because we've reached the start of the
+ * truncated/punched region and we're done removing blocks.
*/
- if (*partial_cluster > 0 && eh->eh_entries &&
- (EXT4_B2C(sbi, ext4_ext_pblock(ex) + ex_ee_len - 1) !=
- *partial_cluster)) {
- int flags = get_default_free_blocks_flags(inode);
-
- ext4_free_blocks(handle, inode, NULL,
- EXT4_C2B(sbi, *partial_cluster),
- sbi->s_cluster_ratio, flags);
+ if (*partial_cluster > 0 && ex >= EXT_FIRST_EXTENT(eh)) {
+ pblk = ext4_ext_pblock(ex) + ex_ee_len - 1;
+ if (*partial_cluster != (long long) EXT4_B2C(sbi, pblk)) {
+ ext4_free_blocks(handle, inode, NULL,
+ EXT4_C2B(sbi, *partial_cluster),
+ sbi->s_cluster_ratio,
+ get_default_free_blocks_flags(inode));
+ }
*partial_cluster = 0;
}
@@ -2797,7 +2803,7 @@ ext4_ext_more_to_rm(struct ext4_ext_path *path)
int ext4_ext_remove_space(struct inode *inode, ext4_lblk_t start,
ext4_lblk_t end)
{
- struct super_block *sb = inode->i_sb;
+ struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
int depth = ext_depth(inode);
struct ext4_ext_path *path = NULL;
long long partial_cluster = 0;
@@ -2823,10 +2829,11 @@ again:
*/
if (end < EXT_MAX_BLOCKS - 1) {
struct ext4_extent *ex;
- ext4_lblk_t ee_block;
+ ext4_lblk_t ee_block, ex_end, lblk;
+ ext4_fsblk_t pblk;
- /* find extent for this block */
- path = ext4_ext_find_extent(inode, end, NULL, EXT4_EX_NOCACHE);
+ /* find extent for or closest extent to this block */
+ path = ext4_find_extent(inode, end, NULL, EXT4_EX_NOCACHE);
if (IS_ERR(path)) {
ext4_journal_stop(handle);
return PTR_ERR(path);
@@ -2845,6 +2852,7 @@ again:
}
ee_block = le32_to_cpu(ex->ee_block);
+ ex_end = ee_block + ext4_ext_get_actual_len(ex) - 1;
/*
* See if the last block is inside the extent, if so split
@@ -2852,13 +2860,18 @@ again:
* tail of the first part of the split extent in
* ext4_ext_rm_leaf().
*/
- if (end >= ee_block &&
- end < ee_block + ext4_ext_get_actual_len(ex) - 1) {
- int split_flag = 0;
+ if (end >= ee_block && end < ex_end) {
- if (ext4_ext_is_unwritten(ex))
- split_flag = EXT4_EXT_MARK_UNWRIT1 |
- EXT4_EXT_MARK_UNWRIT2;
+ /*
+ * If we're going to split the extent, note that
+ * the cluster containing the block after 'end' is
+ * in use to avoid freeing it when removing blocks.
+ */
+ if (sbi->s_cluster_ratio > 1) {
+ pblk = ext4_ext_pblock(ex) + end - ee_block + 2;
+ partial_cluster =
+ -(long long) EXT4_B2C(sbi, pblk);
+ }
/*
* Split the extent in two so that 'end' is the last
@@ -2866,14 +2879,28 @@ again:
* fail removing space due to ENOSPC so try to use
* reserved block if that happens.
*/
- err = ext4_split_extent_at(handle, inode, path,
- end + 1, split_flag,
- EXT4_EX_NOCACHE |
- EXT4_GET_BLOCKS_PRE_IO |
- EXT4_GET_BLOCKS_METADATA_NOFAIL);
-
+ err = ext4_force_split_extent_at(handle, inode, &path,
+ end + 1, 1);
if (err < 0)
goto out;
+
+ } else if (sbi->s_cluster_ratio > 1 && end >= ex_end) {
+ /*
+ * If there's an extent to the right its first cluster
+ * contains the immediate right boundary of the
+ * truncated/punched region. Set partial_cluster to
+ * its negative value so it won't be freed if shared
+ * with the current extent. The end < ee_block case
+ * is handled in ext4_ext_rm_leaf().
+ */
+ lblk = ex_end + 1;
+ err = ext4_ext_search_right(inode, path, &lblk, &pblk,
+ &ex);
+ if (err)
+ goto out;
+ if (pblk)
+ partial_cluster =
+ -(long long) EXT4_B2C(sbi, pblk);
}
}
/*
@@ -2893,7 +2920,7 @@ again:
ext4_journal_stop(handle);
return -ENOMEM;
}
- path[0].p_depth = depth;
+ path[0].p_maxdepth = path[0].p_depth = depth;
path[0].p_hdr = ext_inode_hdr(inode);
i = 0;
@@ -2984,16 +3011,18 @@ again:
trace_ext4_ext_remove_space_done(inode, start, end, depth,
partial_cluster, path->p_hdr->eh_entries);
- /* If we still have something in the partial cluster and we have removed
+ /*
+ * If we still have something in the partial cluster and we have removed
* even the first extent, then we should free the blocks in the partial
- * cluster as well. */
- if (partial_cluster > 0 && path->p_hdr->eh_entries == 0) {
- int flags = get_default_free_blocks_flags(inode);
-
+ * cluster as well. (This code will only run when there are no leaves
+ * to the immediate left of the truncated/punched region.)
+ */
+ if (partial_cluster > 0 && err == 0) {
+ /* don't zero partial_cluster since it's not used afterwards */
ext4_free_blocks(handle, inode, NULL,
- EXT4_C2B(EXT4_SB(sb), partial_cluster),
- EXT4_SB(sb)->s_cluster_ratio, flags);
- partial_cluster = 0;
+ EXT4_C2B(sbi, partial_cluster),
+ sbi->s_cluster_ratio,
+ get_default_free_blocks_flags(inode));
}
/* TODO: flexible tree reduction should be here */
@@ -3013,10 +3042,9 @@ again:
out:
ext4_ext_drop_refs(path);
kfree(path);
- if (err == -EAGAIN) {
- path = NULL;
+ path = NULL;
+ if (err == -EAGAIN)
goto again;
- }
ext4_journal_stop(handle);
return err;
@@ -3130,11 +3158,12 @@ static int ext4_ext_zeroout(struct inode *inode, struct ext4_extent *ex)
*/
static int ext4_split_extent_at(handle_t *handle,
struct inode *inode,
- struct ext4_ext_path *path,
+ struct ext4_ext_path **ppath,
ext4_lblk_t split,
int split_flag,
int flags)
{
+ struct ext4_ext_path *path = *ppath;
ext4_fsblk_t newblock;
ext4_lblk_t ee_block;
struct ext4_extent *ex, newex, orig_ex, zero_ex;
@@ -3205,7 +3234,7 @@ static int ext4_split_extent_at(handle_t *handle,
if (split_flag & EXT4_EXT_MARK_UNWRIT2)
ext4_ext_mark_unwritten(ex2);
- err = ext4_ext_insert_extent(handle, inode, path, &newex, flags);
+ err = ext4_ext_insert_extent(handle, inode, ppath, &newex, flags);
if (err == -ENOSPC && (EXT4_EXT_MAY_ZEROOUT & split_flag)) {
if (split_flag & (EXT4_EXT_DATA_VALID1|EXT4_EXT_DATA_VALID2)) {
if (split_flag & EXT4_EXT_DATA_VALID1) {
@@ -3271,11 +3300,12 @@ fix_extent_len:
*/
static int ext4_split_extent(handle_t *handle,
struct inode *inode,
- struct ext4_ext_path *path,
+ struct ext4_ext_path **ppath,
struct ext4_map_blocks *map,
int split_flag,
int flags)
{
+ struct ext4_ext_path *path = *ppath;
ext4_lblk_t ee_block;
struct ext4_extent *ex;
unsigned int ee_len, depth;
@@ -3298,7 +3328,7 @@ static int ext4_split_extent(handle_t *handle,
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,
+ err = ext4_split_extent_at(handle, inode, ppath,
map->m_lblk + map->m_len, split_flag1, flags1);
if (err)
goto out;
@@ -3309,8 +3339,7 @@ static int ext4_split_extent(handle_t *handle,
* Update path is required because previous ext4_split_extent_at() may
* result in split of original leaf or extent zeroout.
*/
- ext4_ext_drop_refs(path);
- path = ext4_ext_find_extent(inode, map->m_lblk, path, 0);
+ path = ext4_find_extent(inode, map->m_lblk, ppath, 0);
if (IS_ERR(path))
return PTR_ERR(path);
depth = ext_depth(inode);
@@ -3330,7 +3359,7 @@ static int ext4_split_extent(handle_t *handle,
split_flag1 |= split_flag & (EXT4_EXT_MAY_ZEROOUT |
EXT4_EXT_MARK_UNWRIT2);
}
- err = ext4_split_extent_at(handle, inode, path,
+ err = ext4_split_extent_at(handle, inode, ppath,
map->m_lblk, split_flag1, flags);
if (err)
goto out;
@@ -3364,9 +3393,10 @@ out:
static int ext4_ext_convert_to_initialized(handle_t *handle,
struct inode *inode,
struct ext4_map_blocks *map,
- struct ext4_ext_path *path,
+ struct ext4_ext_path **ppath,
int flags)
{
+ struct ext4_ext_path *path = *ppath;
struct ext4_sb_info *sbi;
struct ext4_extent_header *eh;
struct ext4_map_blocks split_map;
@@ -3590,11 +3620,10 @@ static int ext4_ext_convert_to_initialized(handle_t *handle,
}
}
- allocated = ext4_split_extent(handle, inode, path,
- &split_map, split_flag, flags);
- if (allocated < 0)
- err = allocated;
-
+ err = ext4_split_extent(handle, inode, ppath, &split_map, split_flag,
+ flags);
+ if (err > 0)
+ err = 0;
out:
/* If we have gotten a failure, don't zero out status tree */
if (!err)
@@ -3629,9 +3658,10 @@ out:
static int ext4_split_convert_extents(handle_t *handle,
struct inode *inode,
struct ext4_map_blocks *map,
- struct ext4_ext_path *path,
+ struct ext4_ext_path **ppath,
int flags)
{
+ struct ext4_ext_path *path = *ppath;
ext4_lblk_t eof_block;
ext4_lblk_t ee_block;
struct ext4_extent *ex;
@@ -3665,74 +3695,15 @@ static int ext4_split_convert_extents(handle_t *handle,
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);
-}
-
-static int ext4_convert_initialized_extents(handle_t *handle,
- struct inode *inode,
- struct ext4_map_blocks *map,
- struct ext4_ext_path *path)
-{
- struct ext4_extent *ex;
- ext4_lblk_t ee_block;
- unsigned int ee_len;
- int depth;
- int err = 0;
-
- 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);
-
- ext_debug("%s: inode %lu, logical"
- "block %llu, max_blocks %u\n", __func__, inode->i_ino,
- (unsigned long long)ee_block, ee_len);
-
- if (ee_block != map->m_lblk || ee_len > map->m_len) {
- err = ext4_split_convert_extents(handle, inode, map, path,
- EXT4_GET_BLOCKS_CONVERT_UNWRITTEN);
- if (err < 0)
- goto out;
- ext4_ext_drop_refs(path);
- path = ext4_ext_find_extent(inode, map->m_lblk, path, 0);
- if (IS_ERR(path)) {
- err = PTR_ERR(path);
- goto out;
- }
- depth = ext_depth(inode);
- ex = path[depth].p_ext;
- if (!ex) {
- EXT4_ERROR_INODE(inode, "unexpected hole at %lu",
- (unsigned long) map->m_lblk);
- err = -EIO;
- goto out;
- }
- }
-
- err = ext4_ext_get_access(handle, inode, path + depth);
- if (err)
- goto out;
- /* 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
- */
- ext4_ext_try_to_merge(handle, inode, path, ex);
-
- /* Mark modified extent as dirty */
- err = ext4_ext_dirty(handle, inode, path + path->p_depth);
-out:
- ext4_ext_show_leaf(inode, path);
- return err;
+ return ext4_split_extent(handle, inode, ppath, map, split_flag, flags);
}
-
static int ext4_convert_unwritten_extents_endio(handle_t *handle,
struct inode *inode,
struct ext4_map_blocks *map,
- struct ext4_ext_path *path)
+ struct ext4_ext_path **ppath)
{
+ struct ext4_ext_path *path = *ppath;
struct ext4_extent *ex;
ext4_lblk_t ee_block;
unsigned int ee_len;
@@ -3761,16 +3732,13 @@ static int ext4_convert_unwritten_extents_endio(handle_t *handle,
inode->i_ino, (unsigned long long)ee_block, ee_len,
(unsigned long long)map->m_lblk, map->m_len);
#endif
- err = ext4_split_convert_extents(handle, inode, map, path,
+ err = ext4_split_convert_extents(handle, inode, map, ppath,
EXT4_GET_BLOCKS_CONVERT);
if (err < 0)
- goto out;
- ext4_ext_drop_refs(path);
- path = ext4_ext_find_extent(inode, map->m_lblk, path, 0);
- if (IS_ERR(path)) {
- err = PTR_ERR(path);
- goto out;
- }
+ return err;
+ path = ext4_find_extent(inode, map->m_lblk, ppath, 0);
+ if (IS_ERR(path))
+ return PTR_ERR(path);
depth = ext_depth(inode);
ex = path[depth].p_ext;
}
@@ -3963,12 +3931,16 @@ get_reserved_cluster_alloc(struct inode *inode, ext4_lblk_t lblk_start,
}
static int
-ext4_ext_convert_initialized_extent(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)
+convert_initialized_extent(handle_t *handle, struct inode *inode,
+ struct ext4_map_blocks *map,
+ struct ext4_ext_path **ppath, int flags,
+ unsigned int allocated, ext4_fsblk_t newblock)
{
- int ret = 0;
+ struct ext4_ext_path *path = *ppath;
+ struct ext4_extent *ex;
+ ext4_lblk_t ee_block;
+ unsigned int ee_len;
+ int depth;
int err = 0;
/*
@@ -3978,28 +3950,67 @@ ext4_ext_convert_initialized_extent(handle_t *handle, struct inode *inode,
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);
- if (ret >= 0) {
- ext4_update_inode_fsync_trans(handle, inode, 1);
- err = check_eofblocks_fl(handle, inode, map->m_lblk,
- path, map->m_len);
- } else
- err = ret;
+ 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);
+
+ ext_debug("%s: inode %lu, logical"
+ "block %llu, max_blocks %u\n", __func__, inode->i_ino,
+ (unsigned long long)ee_block, ee_len);
+
+ if (ee_block != map->m_lblk || ee_len > map->m_len) {
+ err = ext4_split_convert_extents(handle, inode, map, ppath,
+ EXT4_GET_BLOCKS_CONVERT_UNWRITTEN);
+ if (err < 0)
+ return err;
+ path = ext4_find_extent(inode, map->m_lblk, ppath, 0);
+ if (IS_ERR(path))
+ return PTR_ERR(path);
+ depth = ext_depth(inode);
+ ex = path[depth].p_ext;
+ if (!ex) {
+ EXT4_ERROR_INODE(inode, "unexpected hole at %lu",
+ (unsigned long) map->m_lblk);
+ return -EIO;
+ }
+ }
+
+ err = ext4_ext_get_access(handle, inode, path + depth);
+ if (err)
+ return err;
+ /* 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
+ */
+ ext4_ext_try_to_merge(handle, inode, path, ex);
+
+ /* Mark modified extent as dirty */
+ err = ext4_ext_dirty(handle, inode, path + path->p_depth);
+ if (err)
+ return err;
+ ext4_ext_show_leaf(inode, path);
+
+ ext4_update_inode_fsync_trans(handle, inode, 1);
+ err = check_eofblocks_fl(handle, inode, map->m_lblk, path, map->m_len);
+ if (err)
+ return err;
map->m_flags |= EXT4_MAP_UNWRITTEN;
if (allocated > map->m_len)
allocated = map->m_len;
map->m_len = allocated;
-
- return err ? err : allocated;
+ return allocated;
}
static int
ext4_ext_handle_unwritten_extents(handle_t *handle, struct inode *inode,
struct ext4_map_blocks *map,
- struct ext4_ext_path *path, int flags,
+ struct ext4_ext_path **ppath, int flags,
unsigned int allocated, ext4_fsblk_t newblock)
{
+ struct ext4_ext_path *path = *ppath;
int ret = 0;
int err = 0;
ext4_io_end_t *io = ext4_inode_aio(inode);
@@ -4021,8 +4032,8 @@ ext4_ext_handle_unwritten_extents(handle_t *handle, struct inode *inode,
/* get_block() before submit the IO, split the extent */
if (flags & EXT4_GET_BLOCKS_PRE_IO) {
- ret = ext4_split_convert_extents(handle, inode, map,
- path, flags | EXT4_GET_BLOCKS_CONVERT);
+ ret = ext4_split_convert_extents(handle, inode, map, ppath,
+ flags | EXT4_GET_BLOCKS_CONVERT);
if (ret <= 0)
goto out;
/*
@@ -4040,7 +4051,7 @@ ext4_ext_handle_unwritten_extents(handle_t *handle, struct inode *inode,
/* IO end_io complete, convert the filled extent to written */
if (flags & EXT4_GET_BLOCKS_CONVERT) {
ret = ext4_convert_unwritten_extents_endio(handle, inode, map,
- path);
+ ppath);
if (ret >= 0) {
ext4_update_inode_fsync_trans(handle, inode, 1);
err = check_eofblocks_fl(handle, inode, map->m_lblk,
@@ -4078,7 +4089,7 @@ ext4_ext_handle_unwritten_extents(handle_t *handle, struct inode *inode,
}
/* buffered write, writepage time, convert*/
- ret = ext4_ext_convert_to_initialized(handle, inode, map, path, flags);
+ ret = ext4_ext_convert_to_initialized(handle, inode, map, ppath, flags);
if (ret >= 0)
ext4_update_inode_fsync_trans(handle, inode, 1);
out:
@@ -4273,13 +4284,14 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode,
ext4_io_end_t *io = ext4_inode_aio(inode);
ext4_lblk_t cluster_offset;
int set_unwritten = 0;
+ bool map_from_cluster = false;
ext_debug("blocks %u/%u requested for inode %lu\n",
map->m_lblk, map->m_len, inode->i_ino);
trace_ext4_ext_map_blocks_enter(inode, map->m_lblk, map->m_len, flags);
/* find extent for this block */
- path = ext4_ext_find_extent(inode, map->m_lblk, NULL, 0);
+ path = ext4_find_extent(inode, map->m_lblk, NULL, 0);
if (IS_ERR(path)) {
err = PTR_ERR(path);
path = NULL;
@@ -4291,7 +4303,7 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode,
/*
* consistent leaf must not be empty;
* this situation is possible, though, _during_ tree modification;
- * this is why assert can't be put in ext4_ext_find_extent()
+ * this is why assert can't be put in ext4_find_extent()
*/
if (unlikely(path[depth].p_ext == NULL && depth != 0)) {
EXT4_ERROR_INODE(inode, "bad extent address "
@@ -4331,15 +4343,15 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode,
*/
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);
+ allocated = convert_initialized_extent(
+ handle, inode, map, &path,
+ flags, allocated, newblock);
goto out2;
} else if (!ext4_ext_is_unwritten(ex))
goto out;
ret = ext4_ext_handle_unwritten_extents(
- handle, inode, map, path, flags,
+ handle, inode, map, &path, flags,
allocated, newblock);
if (ret < 0)
err = ret;
@@ -4349,10 +4361,6 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode,
}
}
- if ((sbi->s_cluster_ratio > 1) &&
- ext4_find_delalloc_cluster(inode, map->m_lblk))
- map->m_flags |= EXT4_MAP_FROM_CLUSTER;
-
/*
* requested block isn't allocated yet;
* we couldn't try to create block if create flag is zero
@@ -4362,27 +4370,25 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode,
* put just found gap into cache to speed up
* subsequent requests
*/
- if ((flags & EXT4_GET_BLOCKS_NO_PUT_HOLE) == 0)
- ext4_ext_put_gap_in_cache(inode, path, map->m_lblk);
+ ext4_ext_put_gap_in_cache(inode, path, map->m_lblk);
goto out2;
}
/*
* Okay, we need to do block allocation.
*/
- map->m_flags &= ~EXT4_MAP_FROM_CLUSTER;
newex.ee_block = cpu_to_le32(map->m_lblk);
cluster_offset = EXT4_LBLK_COFF(sbi, map->m_lblk);
/*
* If we are doing bigalloc, check to see if the extent returned
- * by ext4_ext_find_extent() implies a cluster we can use.
+ * by ext4_find_extent() implies a cluster we can use.
*/
if (cluster_offset && ex &&
get_implied_cluster_alloc(inode->i_sb, map, ex, path)) {
ar.len = allocated = map->m_len;
newblock = map->m_pblk;
- map->m_flags |= EXT4_MAP_FROM_CLUSTER;
+ map_from_cluster = true;
goto got_allocated_blocks;
}
@@ -4403,7 +4409,7 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode,
get_implied_cluster_alloc(inode->i_sb, map, ex2, path)) {
ar.len = allocated = map->m_len;
newblock = map->m_pblk;
- map->m_flags |= EXT4_MAP_FROM_CLUSTER;
+ map_from_cluster = true;
goto got_allocated_blocks;
}
@@ -4451,6 +4457,8 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode,
ar.flags = 0;
if (flags & EXT4_GET_BLOCKS_NO_NORMALIZE)
ar.flags |= EXT4_MB_HINT_NOPREALLOC;
+ if (flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE)
+ ar.flags |= EXT4_MB_DELALLOC_RESERVED;
newblock = ext4_mb_new_blocks(handle, &ar, &err);
if (!newblock)
goto out2;
@@ -4486,7 +4494,7 @@ got_allocated_blocks:
err = check_eofblocks_fl(handle, inode, map->m_lblk,
path, ar.len);
if (!err)
- err = ext4_ext_insert_extent(handle, inode, path,
+ err = ext4_ext_insert_extent(handle, inode, &path,
&newex, flags);
if (!err && set_unwritten) {
@@ -4527,7 +4535,7 @@ got_allocated_blocks:
*/
reserved_clusters = get_reserved_cluster_alloc(inode,
map->m_lblk, allocated);
- if (map->m_flags & EXT4_MAP_FROM_CLUSTER) {
+ if (map_from_cluster) {
if (reserved_clusters) {
/*
* We have clusters reserved for this range.
@@ -4619,14 +4627,11 @@ out:
map->m_pblk = newblock;
map->m_len = allocated;
out2:
- if (path) {
- ext4_ext_drop_refs(path);
- kfree(path);
- }
+ ext4_ext_drop_refs(path);
+ kfree(path);
trace_ext4_ext_map_blocks_exit(inode, flags, map,
err ? err : allocated);
- ext4_es_lru_add(inode);
return err ? err : allocated;
}
@@ -4799,7 +4804,8 @@ static long ext4_zero_range(struct file *file, loff_t offset,
max_blocks -= lblk;
flags = EXT4_GET_BLOCKS_CREATE_UNWRIT_EXT |
- EXT4_GET_BLOCKS_CONVERT_UNWRITTEN;
+ EXT4_GET_BLOCKS_CONVERT_UNWRITTEN |
+ EXT4_EX_NOCACHE;
if (mode & FALLOC_FL_KEEP_SIZE)
flags |= EXT4_GET_BLOCKS_KEEP_SIZE;
@@ -4837,15 +4843,21 @@ static long ext4_zero_range(struct file *file, loff_t offset,
ext4_inode_block_unlocked_dio(inode);
inode_dio_wait(inode);
+ ret = ext4_alloc_file_blocks(file, lblk, max_blocks, new_size,
+ flags, mode);
+ if (ret)
+ goto out_dio;
/*
* Remove entire range from the extent status tree.
+ *
+ * ext4_es_remove_extent(inode, lblk, max_blocks) is
+ * NOT sufficient. I'm not sure why this is the case,
+ * but let's be conservative and remove the extent
+ * status tree for the entire inode. There should be
+ * no outstanding delalloc extents thanks to the
+ * filemap_write_and_wait_range() call above.
*/
- ret = ext4_es_remove_extent(inode, lblk, max_blocks);
- if (ret)
- goto out_dio;
-
- ret = ext4_alloc_file_blocks(file, lblk, max_blocks, new_size,
- flags, mode);
+ ret = ext4_es_remove_extent(inode, 0, EXT_MAX_BLOCKS);
if (ret)
goto out_dio;
}
@@ -5139,7 +5151,8 @@ int ext4_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
if (ext4_has_inline_data(inode)) {
int has_inline = 1;
- error = ext4_inline_data_fiemap(inode, fieinfo, &has_inline);
+ error = ext4_inline_data_fiemap(inode, fieinfo, &has_inline,
+ start, len);
if (has_inline)
return error;
@@ -5178,7 +5191,6 @@ int ext4_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
error = ext4_fill_fiemap_extents(inode, start_blk,
len_blks, fieinfo);
}
- ext4_es_lru_add(inode);
return error;
}
@@ -5238,8 +5250,6 @@ ext4_ext_shift_path_extents(struct ext4_ext_path *path, ext4_lblk_t shift,
return -EIO;
ex_last = EXT_LAST_EXTENT(path[depth].p_hdr);
- if (!ex_last)
- return -EIO;
err = ext4_access_path(handle, inode, path + depth);
if (err)
@@ -5304,36 +5314,31 @@ ext4_ext_shift_extents(struct inode *inode, handle_t *handle,
struct ext4_ext_path *path;
int ret = 0, depth;
struct ext4_extent *extent;
- ext4_lblk_t stop_block, current_block;
+ ext4_lblk_t stop_block;
ext4_lblk_t ex_start, ex_end;
/* Let path point to the last extent */
- path = ext4_ext_find_extent(inode, EXT_MAX_BLOCKS - 1, NULL, 0);
+ path = ext4_find_extent(inode, EXT_MAX_BLOCKS - 1, NULL, 0);
if (IS_ERR(path))
return PTR_ERR(path);
depth = path->p_depth;
extent = path[depth].p_ext;
- if (!extent) {
- ext4_ext_drop_refs(path);
- kfree(path);
- return ret;
- }
+ if (!extent)
+ goto out;
stop_block = le32_to_cpu(extent->ee_block) +
ext4_ext_get_actual_len(extent);
- ext4_ext_drop_refs(path);
- kfree(path);
/* Nothing to shift, if hole is at the end of file */
if (start >= stop_block)
- return ret;
+ goto out;
/*
* Don't start shifting extents until we make sure the hole is big
* enough to accomodate the shift.
*/
- path = ext4_ext_find_extent(inode, start - 1, NULL, 0);
+ path = ext4_find_extent(inode, start - 1, &path, 0);
if (IS_ERR(path))
return PTR_ERR(path);
depth = path->p_depth;
@@ -5346,8 +5351,6 @@ ext4_ext_shift_extents(struct inode *inode, handle_t *handle,
ex_start = 0;
ex_end = 0;
}
- ext4_ext_drop_refs(path);
- kfree(path);
if ((start == ex_start && shift > ex_start) ||
(shift > start - ex_end))
@@ -5355,7 +5358,7 @@ ext4_ext_shift_extents(struct inode *inode, handle_t *handle,
/* Its safe to start updating extents */
while (start < stop_block) {
- path = ext4_ext_find_extent(inode, start, NULL, 0);
+ path = ext4_find_extent(inode, start, &path, 0);
if (IS_ERR(path))
return PTR_ERR(path);
depth = path->p_depth;
@@ -5365,27 +5368,23 @@ ext4_ext_shift_extents(struct inode *inode, handle_t *handle,
(unsigned long) start);
return -EIO;
}
-
- current_block = le32_to_cpu(extent->ee_block);
- if (start > current_block) {
+ if (start > le32_to_cpu(extent->ee_block)) {
/* Hole, move to the next extent */
- ret = mext_next_extent(inode, path, &extent);
- if (ret != 0) {
- ext4_ext_drop_refs(path);
- kfree(path);
- if (ret == 1)
- ret = 0;
- break;
+ if (extent < EXT_LAST_EXTENT(path[depth].p_hdr)) {
+ path[depth].p_ext++;
+ } else {
+ start = ext4_ext_next_allocated_block(path);
+ continue;
}
}
ret = ext4_ext_shift_path_extents(path, shift, inode,
handle, &start);
- ext4_ext_drop_refs(path);
- kfree(path);
if (ret)
break;
}
-
+out:
+ ext4_ext_drop_refs(path);
+ kfree(path);
return ret;
}
@@ -5508,3 +5507,199 @@ out_mutex:
mutex_unlock(&inode->i_mutex);
return ret;
}
+
+/**
+ * ext4_swap_extents - Swap extents between two inodes
+ *
+ * @inode1: First inode
+ * @inode2: Second inode
+ * @lblk1: Start block for first inode
+ * @lblk2: Start block for second inode
+ * @count: Number of blocks to swap
+ * @mark_unwritten: Mark second inode's extents as unwritten after swap
+ * @erp: Pointer to save error value
+ *
+ * This helper routine does exactly what is promise "swap extents". All other
+ * stuff such as page-cache locking consistency, bh mapping consistency or
+ * extent's data copying must be performed by caller.
+ * Locking:
+ * i_mutex is held for both inodes
+ * i_data_sem is locked for write for both inodes
+ * Assumptions:
+ * All pages from requested range are locked for both inodes
+ */
+int
+ext4_swap_extents(handle_t *handle, struct inode *inode1,
+ struct inode *inode2, ext4_lblk_t lblk1, ext4_lblk_t lblk2,
+ ext4_lblk_t count, int unwritten, int *erp)
+{
+ struct ext4_ext_path *path1 = NULL;
+ struct ext4_ext_path *path2 = NULL;
+ int replaced_count = 0;
+
+ BUG_ON(!rwsem_is_locked(&EXT4_I(inode1)->i_data_sem));
+ BUG_ON(!rwsem_is_locked(&EXT4_I(inode2)->i_data_sem));
+ BUG_ON(!mutex_is_locked(&inode1->i_mutex));
+ BUG_ON(!mutex_is_locked(&inode1->i_mutex));
+
+ *erp = ext4_es_remove_extent(inode1, lblk1, count);
+ if (unlikely(*erp))
+ return 0;
+ *erp = ext4_es_remove_extent(inode2, lblk2, count);
+ if (unlikely(*erp))
+ return 0;
+
+ while (count) {
+ struct ext4_extent *ex1, *ex2, tmp_ex;
+ ext4_lblk_t e1_blk, e2_blk;
+ int e1_len, e2_len, len;
+ int split = 0;
+
+ path1 = ext4_find_extent(inode1, lblk1, NULL, EXT4_EX_NOCACHE);
+ if (unlikely(IS_ERR(path1))) {
+ *erp = PTR_ERR(path1);
+ path1 = NULL;
+ finish:
+ count = 0;
+ goto repeat;
+ }
+ path2 = ext4_find_extent(inode2, lblk2, NULL, EXT4_EX_NOCACHE);
+ if (unlikely(IS_ERR(path2))) {
+ *erp = PTR_ERR(path2);
+ path2 = NULL;
+ goto finish;
+ }
+ ex1 = path1[path1->p_depth].p_ext;
+ ex2 = path2[path2->p_depth].p_ext;
+ /* Do we have somthing to swap ? */
+ if (unlikely(!ex2 || !ex1))
+ goto finish;
+
+ e1_blk = le32_to_cpu(ex1->ee_block);
+ e2_blk = le32_to_cpu(ex2->ee_block);
+ e1_len = ext4_ext_get_actual_len(ex1);
+ e2_len = ext4_ext_get_actual_len(ex2);
+
+ /* Hole handling */
+ if (!in_range(lblk1, e1_blk, e1_len) ||
+ !in_range(lblk2, e2_blk, e2_len)) {
+ ext4_lblk_t next1, next2;
+
+ /* if hole after extent, then go to next extent */
+ next1 = ext4_ext_next_allocated_block(path1);
+ next2 = ext4_ext_next_allocated_block(path2);
+ /* If hole before extent, then shift to that extent */
+ if (e1_blk > lblk1)
+ next1 = e1_blk;
+ if (e2_blk > lblk2)
+ next2 = e1_blk;
+ /* Do we have something to swap */
+ if (next1 == EXT_MAX_BLOCKS || next2 == EXT_MAX_BLOCKS)
+ goto finish;
+ /* Move to the rightest boundary */
+ len = next1 - lblk1;
+ if (len < next2 - lblk2)
+ len = next2 - lblk2;
+ if (len > count)
+ len = count;
+ lblk1 += len;
+ lblk2 += len;
+ count -= len;
+ goto repeat;
+ }
+
+ /* Prepare left boundary */
+ if (e1_blk < lblk1) {
+ split = 1;
+ *erp = ext4_force_split_extent_at(handle, inode1,
+ &path1, lblk1, 0);
+ if (unlikely(*erp))
+ goto finish;
+ }
+ if (e2_blk < lblk2) {
+ split = 1;
+ *erp = ext4_force_split_extent_at(handle, inode2,
+ &path2, lblk2, 0);
+ if (unlikely(*erp))
+ goto finish;
+ }
+ /* ext4_split_extent_at() may result in leaf extent split,
+ * path must to be revalidated. */
+ if (split)
+ goto repeat;
+
+ /* Prepare right boundary */
+ len = count;
+ if (len > e1_blk + e1_len - lblk1)
+ len = e1_blk + e1_len - lblk1;
+ if (len > e2_blk + e2_len - lblk2)
+ len = e2_blk + e2_len - lblk2;
+
+ if (len != e1_len) {
+ split = 1;
+ *erp = ext4_force_split_extent_at(handle, inode1,
+ &path1, lblk1 + len, 0);
+ if (unlikely(*erp))
+ goto finish;
+ }
+ if (len != e2_len) {
+ split = 1;
+ *erp = ext4_force_split_extent_at(handle, inode2,
+ &path2, lblk2 + len, 0);
+ if (*erp)
+ goto finish;
+ }
+ /* ext4_split_extent_at() may result in leaf extent split,
+ * path must to be revalidated. */
+ if (split)
+ goto repeat;
+
+ BUG_ON(e2_len != e1_len);
+ *erp = ext4_ext_get_access(handle, inode1, path1 + path1->p_depth);
+ if (unlikely(*erp))
+ goto finish;
+ *erp = ext4_ext_get_access(handle, inode2, path2 + path2->p_depth);
+ if (unlikely(*erp))
+ goto finish;
+
+ /* Both extents are fully inside boundaries. Swap it now */
+ tmp_ex = *ex1;
+ ext4_ext_store_pblock(ex1, ext4_ext_pblock(ex2));
+ ext4_ext_store_pblock(ex2, ext4_ext_pblock(&tmp_ex));
+ ex1->ee_len = cpu_to_le16(e2_len);
+ ex2->ee_len = cpu_to_le16(e1_len);
+ if (unwritten)
+ ext4_ext_mark_unwritten(ex2);
+ if (ext4_ext_is_unwritten(&tmp_ex))
+ ext4_ext_mark_unwritten(ex1);
+
+ ext4_ext_try_to_merge(handle, inode2, path2, ex2);
+ ext4_ext_try_to_merge(handle, inode1, path1, ex1);
+ *erp = ext4_ext_dirty(handle, inode2, path2 +
+ path2->p_depth);
+ if (unlikely(*erp))
+ goto finish;
+ *erp = ext4_ext_dirty(handle, inode1, path1 +
+ path1->p_depth);
+ /*
+ * Looks scarry ah..? second inode already points to new blocks,
+ * and it was successfully dirtied. But luckily error may happen
+ * only due to journal error, so full transaction will be
+ * aborted anyway.
+ */
+ if (unlikely(*erp))
+ goto finish;
+ lblk1 += len;
+ lblk2 += len;
+ replaced_count += len;
+ count -= len;
+
+ repeat:
+ ext4_ext_drop_refs(path1);
+ kfree(path1);
+ ext4_ext_drop_refs(path2);
+ kfree(path2);
+ path1 = path2 = NULL;
+ }
+ return replaced_count;
+}
generated by cgit v1.2.3-70-g09d2 (git 2.46.0) at 2025-04-12 20:21:25 +0000