* - ENOMEM
* - EIO
*/
-#define ext4_ext_dirty(handle, inode, path) \
- __ext4_ext_dirty(__func__, __LINE__, (handle), (inode), (path))
-static int __ext4_ext_dirty(const char *where, unsigned int line,
- handle_t *handle, struct inode *inode,
- struct ext4_ext_path *path)
+int __ext4_ext_dirty(const char *where, unsigned int line, handle_t *handle,
+ struct inode *inode, struct ext4_ext_path *path)
{
int err;
if (path->p_bh) {
}
depth = ext_depth(inode);
ex = path[depth].p_ext;
+ eh = path[depth].p_hdr;
if (unlikely(path[depth].p_hdr == NULL)) {
EXT4_ERROR_INODE(inode, "path[%d].p_hdr == NULL", depth);
return -EIO;
}
/* try to insert block into found extent and return */
- if (ex && !(flag & EXT4_GET_BLOCKS_PRE_IO)
- && 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_get_actual_len(newext),
- le32_to_cpu(ex->ee_block),
- ext4_ext_is_uninitialized(ex),
- ext4_ext_get_actual_len(ex),
- ext4_ext_pblock(ex));
- err = ext4_ext_get_access(handle, inode, path + depth);
- if (err)
- return err;
+ if (ex && !(flag & EXT4_GET_BLOCKS_PRE_IO)) {
/*
- * ext4_can_extents_be_merged should have checked that either
- * both extents are uninitialized, or both aren't. Thus we
- * need to check only one of them here.
+ * 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
+ * left, or on the right from the searched position. This
+ * will make merging more effective.
*/
- if (ext4_ext_is_uninitialized(ex))
- uninitialized = 1;
- ex->ee_len = cpu_to_le16(ext4_ext_get_actual_len(ex)
+ if (ex < EXT_LAST_EXTENT(eh) &&
+ (le32_to_cpu(ex->ee_block) +
+ ext4_ext_get_actual_len(ex) <
+ le32_to_cpu(newext->ee_block))) {
+ ex += 1;
+ goto prepend;
+ } else if ((ex > EXT_FIRST_EXTENT(eh)) &&
+ (le32_to_cpu(newext->ee_block) +
+ ext4_ext_get_actual_len(newext) <
+ le32_to_cpu(ex->ee_block)))
+ ex -= 1;
+
+ /* Try to append newex to the ex */
+ 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_get_actual_len(newext),
+ le32_to_cpu(ex->ee_block),
+ ext4_ext_is_uninitialized(ex),
+ ext4_ext_get_actual_len(ex),
+ ext4_ext_pblock(ex));
+ err = ext4_ext_get_access(handle, inode,
+ path + depth);
+ if (err)
+ return err;
+
+ /*
+ * ext4_can_extents_be_merged should have checked
+ * that either both extents are uninitialized, or
+ * both aren't. Thus we need to check only one of
+ * them here.
+ */
+ if (ext4_ext_is_uninitialized(ex))
+ uninitialized = 1;
+ ex->ee_len = cpu_to_le16(ext4_ext_get_actual_len(ex)
+ ext4_ext_get_actual_len(newext));
- if (uninitialized)
- ext4_ext_mark_uninitialized(ex);
- eh = path[depth].p_hdr;
- nearex = ex;
- goto merge;
+ if (uninitialized)
+ ext4_ext_mark_uninitialized(ex);
+ eh = path[depth].p_hdr;
+ nearex = ex;
+ goto merge;
+ }
+
+prepend:
+ /* Try to prepend newex to the ex */
+ if (ext4_can_extents_be_merged(inode, newext, ex)) {
+ 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_get_actual_len(newext),
+ le32_to_cpu(ex->ee_block),
+ ext4_ext_is_uninitialized(ex),
+ ext4_ext_get_actual_len(ex),
+ ext4_ext_pblock(ex));
+ err = ext4_ext_get_access(handle, inode,
+ path + depth);
+ if (err)
+ return err;
+
+ /*
+ * ext4_can_extents_be_merged should have checked
+ * that either both extents are uninitialized, or
+ * both aren't. Thus we need to check only one of
+ * them here.
+ */
+ if (ext4_ext_is_uninitialized(ex))
+ uninitialized = 1;
+ 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 (uninitialized)
+ ext4_ext_mark_uninitialized(ex);
+ eh = path[depth].p_hdr;
+ nearex = ex;
+ goto merge;
+ }
}
depth = ext_depth(inode);
* There is no free space in the found leaf.
* We're gonna add a new leaf in the tree.
*/
- if (flag & EXT4_GET_BLOCKS_PUNCH_OUT_EXT)
- flags = EXT4_MB_USE_ROOT_BLOCKS;
+ if (flag & EXT4_GET_BLOCKS_METADATA_NOFAIL)
+ flags = EXT4_MB_USE_RESERVED;
err = ext4_ext_create_new_leaf(handle, inode, flags, path, newext);
if (err)
goto cleanup;
static int ext4_remove_blocks(handle_t *handle, struct inode *inode,
struct ext4_extent *ex,
- ext4_fsblk_t *partial_cluster,
+ long long *partial_cluster,
ext4_lblk_t from, ext4_lblk_t to)
{
struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
* partial cluster here.
*/
pblk = ext4_ext_pblock(ex) + ee_len - 1;
- if (*partial_cluster && (EXT4_B2C(sbi, pblk) != *partial_cluster)) {
+ if ((*partial_cluster > 0) &&
+ (EXT4_B2C(sbi, pblk) != *partial_cluster)) {
ext4_free_blocks(handle, inode, NULL,
EXT4_C2B(sbi, *partial_cluster),
sbi->s_cluster_ratio, flags);
&& to == le32_to_cpu(ex->ee_block) + ee_len - 1) {
/* tail removal */
ext4_lblk_t num;
+ unsigned int unaligned;
num = le32_to_cpu(ex->ee_block) + ee_len - from;
pblk = ext4_ext_pblock(ex) + ee_len - num;
- ext_debug("free last %u blocks starting %llu\n", num, pblk);
+ /*
+ * Usually we want to free partial cluster at the end of the
+ * extent, except for the situation when the cluster is still
+ * used by any other extent (partial_cluster is negative).
+ */
+ if (*partial_cluster < 0 &&
+ -(*partial_cluster) == EXT4_B2C(sbi, pblk + num - 1))
+ flags |= EXT4_FREE_BLOCKS_NOFREE_LAST_CLUSTER;
+
+ ext_debug("free last %u blocks starting %llu partial %lld\n",
+ num, pblk, *partial_cluster);
ext4_free_blocks(handle, inode, NULL, pblk, num, flags);
/*
* If the block range to be freed didn't start at the
* beginning of a cluster, and we removed the entire
- * 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.
+ * 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.
+ *
+ * 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 (pblk & (sbi->s_cluster_ratio - 1) &&
- (ee_len == num))
+ unaligned = pblk & (sbi->s_cluster_ratio - 1);
+ if (unaligned && (ee_len == num) &&
+ (*partial_cluster != -((long long)EXT4_B2C(sbi, pblk))))
*partial_cluster = EXT4_B2C(sbi, pblk);
- else
+ else if (unaligned)
+ *partial_cluster = -((long long)EXT4_B2C(sbi, pblk));
+ else if (*partial_cluster > 0)
*partial_cluster = 0;
- } else if (from == le32_to_cpu(ex->ee_block)
- && to <= le32_to_cpu(ex->ee_block) + ee_len - 1) {
- /* head removal */
- ext4_lblk_t num;
- ext4_fsblk_t start;
-
- num = to - from;
- start = ext4_ext_pblock(ex);
-
- ext_debug("free first %u blocks starting %llu\n", num, start);
- ext4_free_blocks(handle, inode, NULL, start, num, flags);
-
- } else {
- printk(KERN_INFO "strange request: removal(2) "
- "%u-%u from %u:%u\n",
- from, to, le32_to_cpu(ex->ee_block), ee_len);
- }
+ } else
+ ext4_error(sbi->s_sb, "strange request: removal(2) "
+ "%u-%u from %u:%u\n",
+ from, to, le32_to_cpu(ex->ee_block), ee_len);
return 0;
}
* @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.
* @start: The first block to remove
* @end: The last block to remove
*/
static int
ext4_ext_rm_leaf(handle_t *handle, struct inode *inode,
- struct ext4_ext_path *path, ext4_fsblk_t *partial_cluster,
+ struct ext4_ext_path *path,
+ long long *partial_cluster,
ext4_lblk_t start, ext4_lblk_t end)
{
struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
unsigned short ex_ee_len;
unsigned uninitialized = 0;
struct ext4_extent *ex;
+ ext4_fsblk_t pblk;
/* the header must be checked already in ext4_ext_remove_space() */
ext_debug("truncate since %u in leaf to %u\n", start, end);
/* If this extent is beyond the end of the hole, skip it */
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
+ */
+ pblk = ext4_ext_pblock(ex);
+ if (pblk & (sbi->s_cluster_ratio - 1))
+ *partial_cluster =
+ -((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);
sizeof(struct ext4_extent));
}
le16_add_cpu(&eh->eh_entries, -1);
- } else
+ } else if (*partial_cluster > 0)
*partial_cluster = 0;
err = ext4_ext_dirty(handle, inode, path + depth);
err = ext4_ext_correct_indexes(handle, inode, path);
/*
- * If there is still a entry in the leaf node, check to see if
- * it references the partial cluster. This is the only place
- * where it could; if it doesn't, we can free the cluster.
+ * Free the partial cluster only if the current extent does not
+ * reference it. Otherwise we might free used cluster.
*/
- if (*partial_cluster && ex >= EXT_FIRST_EXTENT(eh) &&
+ if (*partial_cluster > 0 &&
(EXT4_B2C(sbi, ext4_ext_pblock(ex) + ex_ee_len - 1) !=
*partial_cluster)) {
int flags = EXT4_FREE_BLOCKS_FORGET;
return 1;
}
-static int ext4_ext_remove_space(struct inode *inode, ext4_lblk_t start,
- ext4_lblk_t end)
+int ext4_ext_remove_space(struct inode *inode, ext4_lblk_t start,
+ ext4_lblk_t end)
{
struct super_block *sb = inode->i_sb;
int depth = ext_depth(inode);
struct ext4_ext_path *path = NULL;
- ext4_fsblk_t partial_cluster = 0;
+ long long partial_cluster = 0;
handle_t *handle;
int i = 0, err = 0;
return PTR_ERR(handle);
again:
- trace_ext4_ext_remove_space(inode, start, depth);
+ trace_ext4_ext_remove_space(inode, start, end, depth);
/*
* Check if we are removing extents inside the extent tree. If that
/*
* Split the extent in two so that 'end' is the last
- * block in the first new extent
+ * block in the first new extent. Also we should not
+ * 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_GET_BLOCKS_PRE_IO |
- EXT4_GET_BLOCKS_PUNCH_OUT_EXT);
+ end + 1, split_flag,
+ EXT4_GET_BLOCKS_PRE_IO |
+ EXT4_GET_BLOCKS_METADATA_NOFAIL);
if (err < 0)
goto out;
}
}
- trace_ext4_ext_remove_space_done(inode, start, depth, partial_cluster,
- path->p_hdr->eh_entries);
+ 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
* even the first extent, then we should free the blocks in the partial
* cluster as well. */
- if (partial_cluster && path->p_hdr->eh_entries == 0) {
+ if (partial_cluster > 0 && path->p_hdr->eh_entries == 0) {
int flags = EXT4_FREE_BLOCKS_FORGET;
if (S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode))
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 *path,
+ int flags)
{
struct ext4_sb_info *sbi;
struct ext4_extent_header *eh;
struct ext4_map_blocks split_map;
struct ext4_extent zero_ex;
- struct ext4_extent *ex;
+ struct ext4_extent *ex, *abut_ex;
ext4_lblk_t ee_block, eof_block;
- unsigned int ee_len, depth;
- int allocated, max_zeroout = 0;
+ unsigned int ee_len, depth, map_len = map->m_len;
+ int allocated = 0, max_zeroout = 0;
int err = 0;
int split_flag = 0;
ext_debug("ext4_ext_convert_to_initialized: inode %lu, logical"
"block %llu, max_blocks %u\n", inode->i_ino,
- (unsigned long long)map->m_lblk, map->m_len);
+ (unsigned long long)map->m_lblk, map_len);
sbi = EXT4_SB(inode->i_sb);
eof_block = (inode->i_size + inode->i_sb->s_blocksize - 1) >>
inode->i_sb->s_blocksize_bits;
- if (eof_block < map->m_lblk + map->m_len)
- eof_block = map->m_lblk + map->m_len;
+ if (eof_block < map->m_lblk + map_len)
+ eof_block = map->m_lblk + map_len;
depth = ext_depth(inode);
eh = path[depth].p_hdr;
ex = path[depth].p_ext;
ee_block = le32_to_cpu(ex->ee_block);
ee_len = ext4_ext_get_actual_len(ex);
- allocated = ee_len - (map->m_lblk - ee_block);
zero_ex.ee_len = 0;
trace_ext4_ext_convert_to_initialized_enter(inode, map, ex);
/*
* Attempt to transfer newly initialized blocks from the currently
- * uninitialized extent to its left neighbor. This is much cheaper
+ * uninitialized extent to its neighbor. This is much cheaper
* than an insertion followed by a merge as those involve costly
- * memmove() calls. This is the common case in steady state for
- * workloads doing fallocate(FALLOC_FL_KEEP_SIZE) followed by append
- * writes.
+ * memmove() calls. Transferring to the left is the common case in
+ * steady state for workloads doing fallocate(FALLOC_FL_KEEP_SIZE)
+ * followed by append writes.
*
* Limitations of the current logic:
- * - L1: we only deal with writes at the start of the extent.
- * The approach could be extended to writes at the end
- * of the extent but this scenario was deemed less common.
- * - L2: we do not deal with writes covering the whole extent.
+ * - L1: we do not deal with writes covering the whole extent.
* This would require removing the extent if the transfer
* is possible.
- * - L3: we only attempt to merge with an extent stored in the
+ * - L2: we only attempt to merge with an extent stored in the
* same extent tree node.
*/
- if ((map->m_lblk == ee_block) && /*L1*/
- (map->m_len < ee_len) && /*L2*/
- (ex > EXT_FIRST_EXTENT(eh))) { /*L3*/
- struct ext4_extent *prev_ex;
+ if ((map->m_lblk == ee_block) &&
+ /* See if we can merge left */
+ (map_len < ee_len) && /*L1*/
+ (ex > EXT_FIRST_EXTENT(eh))) { /*L2*/
ext4_lblk_t prev_lblk;
ext4_fsblk_t prev_pblk, ee_pblk;
- unsigned int prev_len, write_len;
+ unsigned int prev_len;
- prev_ex = ex - 1;
- prev_lblk = le32_to_cpu(prev_ex->ee_block);
- prev_len = ext4_ext_get_actual_len(prev_ex);
- prev_pblk = ext4_ext_pblock(prev_ex);
+ abut_ex = ex - 1;
+ prev_lblk = le32_to_cpu(abut_ex->ee_block);
+ prev_len = ext4_ext_get_actual_len(abut_ex);
+ prev_pblk = ext4_ext_pblock(abut_ex);
ee_pblk = ext4_ext_pblock(ex);
- write_len = map->m_len;
/*
- * A transfer of blocks from 'ex' to 'prev_ex' is allowed
+ * A transfer of blocks from 'ex' to 'abut_ex' is allowed
* upon those conditions:
- * - C1: prev_ex is initialized,
- * - C2: prev_ex is logically abutting ex,
- * - C3: prev_ex is physically abutting ex,
- * - C4: prev_ex can receive the additional blocks without
+ * - C1: abut_ex is initialized,
+ * - C2: abut_ex is logically abutting ex,
+ * - C3: abut_ex is physically abutting ex,
+ * - C4: abut_ex can receive the additional blocks without
* overflowing the (initialized) length limit.
*/
- if ((!ext4_ext_is_uninitialized(prev_ex)) && /*C1*/
+ if ((!ext4_ext_is_uninitialized(abut_ex)) && /*C1*/
((prev_lblk + prev_len) == ee_block) && /*C2*/
((prev_pblk + prev_len) == ee_pblk) && /*C3*/
- (prev_len < (EXT_INIT_MAX_LEN - write_len))) { /*C4*/
+ (prev_len < (EXT_INIT_MAX_LEN - map_len))) { /*C4*/
err = ext4_ext_get_access(handle, inode, path + depth);
if (err)
goto out;
trace_ext4_ext_convert_to_initialized_fastpath(inode,
- map, ex, prev_ex);
+ map, ex, abut_ex);
- /* Shift the start of ex by 'write_len' blocks */
- ex->ee_block = cpu_to_le32(ee_block + write_len);
- ext4_ext_store_pblock(ex, ee_pblk + write_len);
- ex->ee_len = cpu_to_le16(ee_len - write_len);
+ /* Shift the start of ex by 'map_len' blocks */
+ 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 */
- /* Extend prev_ex by 'write_len' blocks */
- prev_ex->ee_len = cpu_to_le16(prev_len + write_len);
+ /* Extend abut_ex by 'map_len' blocks */
+ abut_ex->ee_len = cpu_to_le16(prev_len + map_len);
+
+ /* Result: number of initialized blocks past m_lblk */
+ allocated = map_len;
+ }
+ } else if (((map->m_lblk + map_len) == (ee_block + ee_len)) &&
+ (map_len < ee_len) && /*L1*/
+ ex < EXT_LAST_EXTENT(eh)) { /*L2*/
+ /* See if we can merge right */
+ ext4_lblk_t next_lblk;
+ ext4_fsblk_t next_pblk, ee_pblk;
+ unsigned int next_len;
+
+ abut_ex = ex + 1;
+ next_lblk = le32_to_cpu(abut_ex->ee_block);
+ next_len = ext4_ext_get_actual_len(abut_ex);
+ next_pblk = ext4_ext_pblock(abut_ex);
+ ee_pblk = ext4_ext_pblock(ex);
+
+ /*
+ * A transfer of blocks from 'ex' to 'abut_ex' is allowed
+ * upon those conditions:
+ * - C1: abut_ex is initialized,
+ * - C2: abut_ex is logically abutting ex,
+ * - C3: abut_ex is physically abutting ex,
+ * - C4: abut_ex can receive the additional blocks without
+ * overflowing the (initialized) length limit.
+ */
+ if ((!ext4_ext_is_uninitialized(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*/
+ err = ext4_ext_get_access(handle, inode, path + depth);
+ if (err)
+ goto out;
+
+ trace_ext4_ext_convert_to_initialized_fastpath(inode,
+ map, ex, abut_ex);
- /* Mark the block containing both extents as dirty */
- ext4_ext_dirty(handle, inode, path + depth);
+ /* Shift the start of abut_ex by 'map_len' blocks */
+ 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 */
- /* Update path to point to the right extent */
- path[depth].p_ext = prev_ex;
+ /* Extend abut_ex by 'map_len' blocks */
+ abut_ex->ee_len = cpu_to_le16(next_len + map_len);
/* Result: number of initialized blocks past m_lblk */
- allocated = write_len;
- goto out;
+ allocated = map_len;
}
}
+ if (allocated) {
+ /* Mark the block containing both extents as dirty */
+ ext4_ext_dirty(handle, inode, path + depth);
+
+ /* Update path to point to the right extent */
+ path[depth].p_ext = abut_ex;
+ goto out;
+ } else
+ allocated = ee_len - (map->m_lblk - ee_block);
WARN_ON(map->m_lblk < ee_block);
/*
}
allocated = ext4_split_extent(handle, inode, path,
- &split_map, split_flag, 0);
+ &split_map, split_flag, flags);
if (allocated < 0)
err = allocated;
{
struct extent_status es;
- ext4_es_find_delayed_extent(inode, lblk_start, &es);
+ ext4_es_find_delayed_extent_range(inode, lblk_start, lblk_end, &es);
if (es.es_len == 0)
return 0; /* there is no delay extent in this tree */
else if (es.es_lblk <= lblk_start &&
flags, allocated);
ext4_ext_show_leaf(inode, path);
+ /*
+ * When writing into uninitialized 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,
allocated, newblock);
}
/* buffered write, writepage time, convert*/
- ret = ext4_ext_convert_to_initialized(handle, inode, map, path);
+ ret = ext4_ext_convert_to_initialized(handle, inode, map, path, flags);
if (ret >= 0)
ext4_update_inode_fsync_trans(handle, inode, 1);
out:
return err ? err : allocated;
}
-void ext4_ext_truncate(struct inode *inode)
+void ext4_ext_truncate(handle_t *handle, struct inode *inode)
{
- struct address_space *mapping = inode->i_mapping;
struct super_block *sb = inode->i_sb;
ext4_lblk_t last_block;
- handle_t *handle;
- loff_t page_len;
int err = 0;
- /*
- * finish any pending end_io work so we won't run the risk of
- * converting any truncated blocks to initialized later
- */
- ext4_flush_unwritten_io(inode);
-
- /*
- * probably first extent we're gonna free will be last in block
- */
- err = ext4_writepage_trans_blocks(inode);
- handle = ext4_journal_start(inode, EXT4_HT_TRUNCATE, err);
- if (IS_ERR(handle))
- return;
-
- if (inode->i_size % PAGE_CACHE_SIZE != 0) {
- page_len = PAGE_CACHE_SIZE -
- (inode->i_size & (PAGE_CACHE_SIZE - 1));
-
- err = ext4_discard_partial_page_buffers(handle,
- mapping, inode->i_size, page_len, 0);
-
- if (err)
- goto out_stop;
- }
-
- if (ext4_orphan_add(handle, inode))
- goto out_stop;
-
- down_write(&EXT4_I(inode)->i_data_sem);
-
- ext4_discard_preallocations(inode);
-
/*
* TODO: optimization is possible here.
* Probably we need not scan at all,
err = ext4_es_remove_extent(inode, last_block,
EXT_MAX_BLOCKS - last_block);
err = ext4_ext_remove_space(inode, last_block, EXT_MAX_BLOCKS - 1);
-
- /* In a multi-transaction truncate, we only make the final
- * transaction synchronous.
- */
- if (IS_SYNC(inode))
- ext4_handle_sync(handle);
-
- up_write(&EXT4_I(inode)->i_data_sem);
-
-out_stop:
- /*
- * If this was a simple ftruncate() and the file will remain alive,
- * then we need to clear up the orphan record which we created above.
- * However, if this was a real unlink then we were called by
- * ext4_delete_inode(), and we allow that function to clean up the
- * orphan info for us.
- */
- if (inode->i_nlink)
- ext4_orphan_del(handle, inode);
-
- inode->i_mtime = inode->i_ctime = ext4_current_time(inode);
- ext4_mark_inode_dirty(handle, inode);
- ext4_journal_stop(handle);
}
static void ext4_falloc_update_inode(struct inode *inode,
struct extent_status es;
ext4_lblk_t block, next_del;
- ext4_es_find_delayed_extent(inode, newes->es_lblk, &es);
-
if (newes->es_pblk == 0) {
+ ext4_es_find_delayed_extent_range(inode, newes->es_lblk,
+ newes->es_lblk + newes->es_len - 1, &es);
+
/*
* No extent in extent-tree contains block @newes->es_pblk,
* then the block may stay in 1)a hole or 2)delayed-extent.
}
block = newes->es_lblk + newes->es_len;
- ext4_es_find_delayed_extent(inode, block, &es);
+ ext4_es_find_delayed_extent_range(inode, block, EXT_MAX_BLOCKS, &es);
if (es.es_len == 0)
next_del = EXT_MAX_BLOCKS;
else
error = ext4_get_inode_loc(inode, &iloc);
if (error)
return error;
- physical = iloc.bh->b_blocknr << blockbits;
+ physical = (__u64)iloc.bh->b_blocknr << blockbits;
offset = EXT4_GOOD_OLD_INODE_SIZE +
EXT4_I(inode)->i_extra_isize;
physical += offset;
flags |= FIEMAP_EXTENT_DATA_INLINE;
brelse(iloc.bh);
} else { /* external block */
- physical = EXT4_I(inode)->i_file_acl << blockbits;
+ physical = (__u64)EXT4_I(inode)->i_file_acl << blockbits;
length = inode->i_sb->s_blocksize;
}
return (error < 0 ? error : 0);
}
-/*
- * ext4_ext_punch_hole
- *
- * Punches a hole of "length" bytes in a file starting
- * at byte "offset"
- *
- * @inode: The inode of the file to punch a hole in
- * @offset: The starting byte offset of the hole
- * @length: The length of the hole
- *
- * Returns the number of blocks removed or negative on err
- */
-int ext4_ext_punch_hole(struct file *file, loff_t offset, loff_t length)
-{
- struct inode *inode = file_inode(file);
- struct super_block *sb = inode->i_sb;
- ext4_lblk_t first_block, stop_block;
- struct address_space *mapping = inode->i_mapping;
- handle_t *handle;
- loff_t first_page, last_page, page_len;
- loff_t first_page_offset, last_page_offset;
- int credits, err = 0;
-
- /*
- * Write out all dirty pages to avoid race conditions
- * Then release them.
- */
- if (mapping->nrpages && mapping_tagged(mapping, PAGECACHE_TAG_DIRTY)) {
- err = filemap_write_and_wait_range(mapping,
- offset, offset + length - 1);
-
- if (err)
- return err;
- }
-
- mutex_lock(&inode->i_mutex);
- /* It's not possible punch hole on append only file */
- if (IS_APPEND(inode) || IS_IMMUTABLE(inode)) {
- err = -EPERM;
- goto out_mutex;
- }
- if (IS_SWAPFILE(inode)) {
- err = -ETXTBSY;
- goto out_mutex;
- }
-
- /* No need to punch hole beyond i_size */
- if (offset >= inode->i_size)
- goto out_mutex;
-
- /*
- * If the hole extends beyond i_size, set the hole
- * to end after the page that contains i_size
- */
- if (offset + length > inode->i_size) {
- length = inode->i_size +
- PAGE_CACHE_SIZE - (inode->i_size & (PAGE_CACHE_SIZE - 1)) -
- offset;
- }
-
- first_page = (offset + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
- last_page = (offset + length) >> PAGE_CACHE_SHIFT;
-
- first_page_offset = first_page << PAGE_CACHE_SHIFT;
- last_page_offset = last_page << PAGE_CACHE_SHIFT;
-
- /* Now release the pages */
- if (last_page_offset > first_page_offset) {
- truncate_pagecache_range(inode, first_page_offset,
- last_page_offset - 1);
- }
-
- /* Wait all existing dio workers, newcomers will block on i_mutex */
- ext4_inode_block_unlocked_dio(inode);
- err = ext4_flush_unwritten_io(inode);
- if (err)
- goto out_dio;
- inode_dio_wait(inode);
-
- credits = ext4_writepage_trans_blocks(inode);
- handle = ext4_journal_start(inode, EXT4_HT_TRUNCATE, credits);
- if (IS_ERR(handle)) {
- err = PTR_ERR(handle);
- goto out_dio;
- }
-
-
- /*
- * Now we need to zero out the non-page-aligned data in the
- * pages at the start and tail of the hole, and unmap the buffer
- * heads for the block aligned regions of the page that were
- * completely zeroed.
- */
- if (first_page > last_page) {
- /*
- * If the file space being truncated is contained within a page
- * just zero out and unmap the middle of that page
- */
- err = ext4_discard_partial_page_buffers(handle,
- mapping, offset, length, 0);
-
- if (err)
- goto out;
- } else {
- /*
- * zero out and unmap the partial page that contains
- * the start of the hole
- */
- page_len = first_page_offset - offset;
- if (page_len > 0) {
- err = ext4_discard_partial_page_buffers(handle, mapping,
- offset, page_len, 0);
- if (err)
- goto out;
- }
-
- /*
- * zero out and unmap the partial page that contains
- * the end of the hole
- */
- page_len = offset + length - last_page_offset;
- if (page_len > 0) {
- err = ext4_discard_partial_page_buffers(handle, mapping,
- last_page_offset, page_len, 0);
- if (err)
- goto out;
- }
- }
-
- /*
- * If i_size is contained in the last page, we need to
- * unmap and zero the partial page after i_size
- */
- if (inode->i_size >> PAGE_CACHE_SHIFT == last_page &&
- inode->i_size % PAGE_CACHE_SIZE != 0) {
-
- page_len = PAGE_CACHE_SIZE -
- (inode->i_size & (PAGE_CACHE_SIZE - 1));
-
- if (page_len > 0) {
- err = ext4_discard_partial_page_buffers(handle,
- mapping, inode->i_size, page_len, 0);
-
- if (err)
- goto out;
- }
- }
-
- first_block = (offset + sb->s_blocksize - 1) >>
- EXT4_BLOCK_SIZE_BITS(sb);
- stop_block = (offset + length) >> EXT4_BLOCK_SIZE_BITS(sb);
-
- /* If there are no blocks to remove, return now */
- if (first_block >= stop_block)
- goto out;
-
- down_write(&EXT4_I(inode)->i_data_sem);
- ext4_discard_preallocations(inode);
-
- err = ext4_es_remove_extent(inode, first_block,
- stop_block - first_block);
- err = ext4_ext_remove_space(inode, first_block, stop_block - 1);
-
- ext4_discard_preallocations(inode);
-
- if (IS_SYNC(inode))
- ext4_handle_sync(handle);
-
- up_write(&EXT4_I(inode)->i_data_sem);
-
-out:
- inode->i_mtime = inode->i_ctime = ext4_current_time(inode);
- ext4_mark_inode_dirty(handle, inode);
- ext4_journal_stop(handle);
-out_dio:
- ext4_inode_resume_unlocked_dio(inode);
-out_mutex:
- mutex_unlock(&inode->i_mutex);
- return err;
-}
-
int ext4_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
__u64 start, __u64 len)
{
projects / linux-2.6-microblaze.git / blobdiff