* - smart tree reduction
*/
-#include <linux/module.h>
#include <linux/fs.h>
#include <linux/time.h>
#include <linux/jbd2.h>
#include <asm/uaccess.h>
#include <linux/fiemap.h>
#include "ext4_jbd2.h"
+#include "ext4_extents.h"
+#include "xattr.h"
#include <trace/events/ext4.h>
+/*
+ * used by extent splitting.
+ */
+#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_DATA_VALID1 0x8 /* first half contains valid data */
+#define EXT4_EXT_DATA_VALID2 0x10 /* second half contains valid data */
+
+static __le32 ext4_extent_block_csum(struct inode *inode,
+ struct ext4_extent_header *eh)
+{
+ struct ext4_inode_info *ei = EXT4_I(inode);
+ struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
+ __u32 csum;
+
+ csum = ext4_chksum(sbi, ei->i_csum_seed, (__u8 *)eh,
+ EXT4_EXTENT_TAIL_OFFSET(eh));
+ return cpu_to_le32(csum);
+}
+
+static int ext4_extent_block_csum_verify(struct inode *inode,
+ struct ext4_extent_header *eh)
+{
+ struct ext4_extent_tail *et;
+
+ if (!EXT4_HAS_RO_COMPAT_FEATURE(inode->i_sb,
+ EXT4_FEATURE_RO_COMPAT_METADATA_CSUM))
+ return 1;
+
+ et = find_ext4_extent_tail(eh);
+ if (et->et_checksum != ext4_extent_block_csum(inode, eh))
+ return 0;
+ return 1;
+}
+
+static void ext4_extent_block_csum_set(struct inode *inode,
+ struct ext4_extent_header *eh)
+{
+ struct ext4_extent_tail *et;
+
+ if (!EXT4_HAS_RO_COMPAT_FEATURE(inode->i_sb,
+ EXT4_FEATURE_RO_COMPAT_METADATA_CSUM))
+ return;
+
+ et = find_ext4_extent_tail(eh);
+ et->et_checksum = ext4_extent_block_csum(inode, eh);
+}
+
static int ext4_split_extent(handle_t *handle,
struct inode *inode,
struct ext4_ext_path *path,
int split_flag,
int flags);
+static int ext4_split_extent_at(handle_t *handle,
+ struct inode *inode,
+ struct ext4_ext_path *path,
+ ext4_lblk_t split,
+ int split_flag,
+ int flags);
+
+static int ext4_find_delayed_extent(struct inode *inode,
+ struct extent_status *newes);
+
static int ext4_ext_truncate_extend_restart(handle_t *handle,
struct inode *inode,
int needed)
* - 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) {
+ ext4_extent_block_csum_set(inode, ext_block_hdr(path->p_bh));
/* path points to block */
err = __ext4_handle_dirty_metadata(where, line, handle,
inode, path->p_bh);
{
ext4_fsblk_t block = ext4_ext_pblock(ext);
int len = ext4_ext_get_actual_len(ext);
+ ext4_lblk_t lblock = le32_to_cpu(ext->ee_block);
+ ext4_lblk_t last = lblock + len - 1;
+ if (lblock > last)
+ return 0;
return ext4_data_block_valid(EXT4_SB(inode->i_sb), block, len);
}
if (depth == 0) {
/* leaf entries */
struct ext4_extent *ext = EXT_FIRST_EXTENT(eh);
+ struct ext4_super_block *es = EXT4_SB(inode->i_sb)->s_es;
+ ext4_fsblk_t pblock = 0;
+ ext4_lblk_t lblock = 0;
+ ext4_lblk_t prev = 0;
+ int len = 0;
while (entries) {
if (!ext4_valid_extent(inode, ext))
return 0;
+
+ /* Check for overlapping extents */
+ lblock = le32_to_cpu(ext->ee_block);
+ len = ext4_ext_get_actual_len(ext);
+ if ((lblock <= prev) && prev) {
+ pblock = ext4_ext_pblock(ext);
+ es->s_last_error_block = cpu_to_le64(pblock);
+ return 0;
+ }
ext++;
entries--;
+ prev = lblock + len - 1;
}
} else {
struct ext4_extent_idx *ext_idx = EXT_FIRST_INDEX(eh);
error_msg = "invalid extent entries";
goto corrupted;
}
+ /* Verify checksum on non-root extent tree nodes */
+ if (ext_depth(inode) != depth &&
+ !ext4_extent_block_csum_verify(inode, eh)) {
+ error_msg = "extent tree corrupted";
+ goto corrupted;
+ }
return 0;
corrupted:
return ext4_ext_check(inode, ext_inode_hdr(inode), ext_depth(inode));
}
+static int __ext4_ext_check_block(const char *function, unsigned int line,
+ struct inode *inode,
+ struct ext4_extent_header *eh,
+ int depth,
+ struct buffer_head *bh)
+{
+ int ret;
+
+ if (buffer_verified(bh))
+ return 0;
+ ret = ext4_ext_check(inode, eh, depth);
+ if (ret)
+ return ret;
+ set_buffer_verified(bh);
+ return ret;
+}
+
+#define ext4_ext_check_block(inode, eh, depth, bh) \
+ __ext4_ext_check_block(__func__, __LINE__, inode, eh, depth, bh)
+
#ifdef EXT_DEBUG
static void ext4_ext_show_path(struct inode *inode, struct ext4_ext_path *path)
{
}
path->p_idx = l - 1;
- ext_debug(" -> %d->%lld ", le32_to_cpu(path->p_idx->ei_block),
+ ext_debug(" -> %u->%lld ", le32_to_cpu(path->p_idx->ei_block),
ext4_idx_pblock(path->p_idx));
#ifdef CHECK_BINSEARCH
eh->eh_magic = EXT4_EXT_MAGIC;
eh->eh_max = cpu_to_le16(ext4_ext_space_root(inode, 0));
ext4_mark_inode_dirty(handle, inode);
- ext4_ext_invalidate_cache(inode);
return 0;
}
struct ext4_extent_header *eh;
struct buffer_head *bh;
short int depth, i, ppos = 0, alloc = 0;
+ int ret;
eh = ext_inode_hdr(inode);
depth = ext_depth(inode);
i = depth;
/* walk through the tree */
while (i) {
- int need_to_validate = 0;
-
ext_debug("depth %d: num %d, max %d\n",
ppos, le16_to_cpu(eh->eh_entries), le16_to_cpu(eh->eh_max));
path[ppos].p_ext = NULL;
bh = sb_getblk(inode->i_sb, path[ppos].p_block);
- if (unlikely(!bh))
+ if (unlikely(!bh)) {
+ ret = -ENOMEM;
goto err;
+ }
if (!bh_uptodate_or_lock(bh)) {
trace_ext4_ext_load_extent(inode, block,
path[ppos].p_block);
- if (bh_submit_read(bh) < 0) {
+ ret = bh_submit_read(bh);
+ if (ret < 0) {
put_bh(bh);
goto err;
}
- /* validate the extent entries */
- need_to_validate = 1;
}
eh = ext_block_hdr(bh);
ppos++;
put_bh(bh);
EXT4_ERROR_INODE(inode,
"ppos %d > depth %d", ppos, depth);
+ ret = -EIO;
goto err;
}
path[ppos].p_bh = bh;
path[ppos].p_hdr = eh;
i--;
- if (need_to_validate && ext4_ext_check(inode, eh, i))
+ ret = ext4_ext_check_block(inode, eh, i, bh);
+ if (ret < 0)
goto err;
}
ext4_ext_drop_refs(path);
if (alloc)
kfree(path);
- return ERR_PTR(-EIO);
+ return ERR_PTR(ret);
}
/*
goto cleanup;
}
bh = sb_getblk(inode->i_sb, newblock);
- if (!bh) {
- err = -EIO;
+ if (unlikely(!bh)) {
+ err = -ENOMEM;
goto cleanup;
}
lock_buffer(bh);
le16_add_cpu(&neh->eh_entries, m);
}
+ ext4_extent_block_csum_set(inode, neh);
set_buffer_uptodate(bh);
unlock_buffer(bh);
oldblock = newblock;
newblock = ablocks[--a];
bh = sb_getblk(inode->i_sb, newblock);
- if (!bh) {
- err = -EIO;
+ if (unlikely(!bh)) {
+ err = -ENOMEM;
goto cleanup;
}
lock_buffer(bh);
sizeof(struct ext4_extent_idx) * m);
le16_add_cpu(&neh->eh_entries, m);
}
+ ext4_extent_block_csum_set(inode, neh);
set_buffer_uptodate(bh);
unlock_buffer(bh);
return err;
bh = sb_getblk(inode->i_sb, newblock);
- if (!bh) {
- err = -EIO;
- ext4_std_error(inode->i_sb, err);
- return err;
- }
+ if (unlikely(!bh))
+ return -ENOMEM;
lock_buffer(bh);
err = ext4_journal_get_create_access(handle, bh);
else
neh->eh_max = cpu_to_le16(ext4_ext_space_block(inode, 0));
neh->eh_magic = EXT4_EXT_MAGIC;
+ ext4_extent_block_csum_set(inode, neh);
set_buffer_uptodate(bh);
unlock_buffer(bh);
le32_to_cpu(EXT_FIRST_INDEX(neh)->ei_block),
ext4_idx_pblock(EXT_FIRST_INDEX(neh)));
- neh->eh_depth = cpu_to_le16(le16_to_cpu(neh->eh_depth) + 1);
+ le16_add_cpu(&neh->eh_depth, 1);
ext4_mark_inode_dirty(handle, inode);
out:
brelse(bh);
return -EIO;
eh = ext_block_hdr(bh);
/* subtract from p_depth to get proper eh_depth */
- if (ext4_ext_check(inode, eh, path->p_depth - depth)) {
+ if (ext4_ext_check_block(inode, eh,
+ path->p_depth - depth, bh)) {
put_bh(bh);
return -EIO;
}
if (bh == NULL)
return -EIO;
eh = ext_block_hdr(bh);
- if (ext4_ext_check(inode, eh, path->p_depth - depth)) {
+ if (ext4_ext_check_block(inode, eh, path->p_depth - depth, bh)) {
put_bh(bh);
return -EIO;
}
unsigned short ext1_ee_len, ext2_ee_len, max_len;
/*
- * Make sure that either both extents are uninitialized, or
- * both are _not_.
+ * Make sure that both extents are initialized. We don't merge
+ * uninitialized 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_uninitialized(ex1) || ext4_ext_is_uninitialized(ex2))
return 0;
if (ext4_ext_is_uninitialized(ex1))
return merge_done;
}
+/*
+ * This function does a very simple check to see if we can collapse
+ * an extent tree with a single extent tree leaf block into the inode.
+ */
+static void ext4_ext_try_to_merge_up(handle_t *handle,
+ struct inode *inode,
+ struct ext4_ext_path *path)
+{
+ size_t s;
+ unsigned max_root = ext4_ext_space_root(inode, 0);
+ ext4_fsblk_t blk;
+
+ if ((path[0].p_depth != 1) ||
+ (le16_to_cpu(path[0].p_hdr->eh_entries) != 1) ||
+ (le16_to_cpu(path[1].p_hdr->eh_entries) > max_root))
+ return;
+
+ /*
+ * We need to modify the block allocation bitmap and the block
+ * group descriptor to release the extent tree block. If we
+ * can't get the journal credits, give up.
+ */
+ if (ext4_journal_extend(handle, 2))
+ return;
+
+ /*
+ * Copy the extent data up to the inode
+ */
+ blk = ext4_idx_pblock(path[0].p_idx);
+ s = le16_to_cpu(path[1].p_hdr->eh_entries) *
+ sizeof(struct ext4_extent_idx);
+ s += sizeof(struct ext4_extent_header);
+
+ 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) +
+ (path[1].p_ext - EXT_FIRST_EXTENT(path[1].p_hdr));
+ path[0].p_hdr->eh_max = cpu_to_le16(max_root);
+
+ brelse(path[1].p_bh);
+ ext4_free_blocks(handle, inode, NULL, blk, 1,
+ EXT4_FREE_BLOCKS_METADATA | EXT4_FREE_BLOCKS_FORGET |
+ EXT4_FREE_BLOCKS_RESERVE);
+}
+
/*
* This function tries to merge the @ex extent to neighbours in the tree.
* return 1 if merge left else 0.
*/
-static int ext4_ext_try_to_merge(struct inode *inode,
+static void ext4_ext_try_to_merge(handle_t *handle,
+ struct inode *inode,
struct ext4_ext_path *path,
struct ext4_extent *ex) {
struct ext4_extent_header *eh;
unsigned int depth;
int merge_done = 0;
- int ret = 0;
depth = ext_depth(inode);
BUG_ON(path[depth].p_hdr == NULL);
merge_done = ext4_ext_try_to_merge_right(inode, path, ex - 1);
if (!merge_done)
- ret = ext4_ext_try_to_merge_right(inode, path, ex);
+ (void) ext4_ext_try_to_merge_right(inode, path, ex);
- return ret;
+ ext4_ext_try_to_merge_up(handle, inode, path);
}
/*
depth = ext_depth(inode);
if (!path[depth].p_ext)
goto out;
- b2 = le32_to_cpu(path[depth].p_ext->ee_block);
- b2 &= ~(sbi->s_cluster_ratio - 1);
+ b2 = EXT4_LBLK_CMASK(sbi, le32_to_cpu(path[depth].p_ext->ee_block));
/*
* get the next allocated block if the extent in the path
b2 = ext4_ext_next_allocated_block(path);
if (b2 == EXT_MAX_BLOCKS)
goto out;
- b2 &= ~(sbi->s_cluster_ratio - 1);
+ b2 = EXT4_LBLK_CMASK(sbi, b2);
}
/* check for wrap through zero on extent logical start block*/
}
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;
nearex->ee_len = newext->ee_len;
merge:
- /* try to merge extents to the right */
+ /* try to merge extents */
if (!(flag & EXT4_GET_BLOCKS_PRE_IO))
- ext4_ext_try_to_merge(inode, path, nearex);
+ ext4_ext_try_to_merge(handle, inode, path, nearex);
- /* try to merge extents to the left */
/* time to correct all indexes above */
err = ext4_ext_correct_indexes(handle, inode, path);
if (err)
goto cleanup;
- err = ext4_ext_dirty(handle, inode, path + depth);
+ err = ext4_ext_dirty(handle, inode, path + path->p_depth);
cleanup:
if (npath) {
ext4_ext_drop_refs(npath);
kfree(npath);
}
- ext4_ext_invalidate_cache(inode);
return err;
}
-static int ext4_ext_walk_space(struct inode *inode, ext4_lblk_t block,
- ext4_lblk_t num, ext_prepare_callback func,
- void *cbdata)
+static int ext4_fill_fiemap_extents(struct inode *inode,
+ ext4_lblk_t block, ext4_lblk_t num,
+ struct fiemap_extent_info *fieinfo)
{
struct ext4_ext_path *path = NULL;
- struct ext4_ext_cache cbex;
struct ext4_extent *ex;
- ext4_lblk_t next, start = 0, end = 0;
+ struct extent_status es;
+ ext4_lblk_t next, next_del, start = 0, end = 0;
ext4_lblk_t last = block + num;
- int depth, exists, err = 0;
-
- BUG_ON(func == NULL);
- BUG_ON(inode == NULL);
+ int exists, depth = 0, err = 0;
+ unsigned int flags = 0;
+ unsigned char blksize_bits = inode->i_sb->s_blocksize_bits;
while (block < last && block != EXT_MAX_BLOCKS) {
num = last - block;
/* 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);
- up_read(&EXT4_I(inode)->i_data_sem);
if (IS_ERR(path)) {
+ up_read(&EXT4_I(inode)->i_data_sem);
err = PTR_ERR(path);
path = NULL;
break;
depth = ext_depth(inode);
if (unlikely(path[depth].p_hdr == NULL)) {
+ up_read(&EXT4_I(inode)->i_data_sem);
EXT4_ERROR_INODE(inode, "path[%d].p_hdr == NULL", depth);
err = -EIO;
break;
}
ex = path[depth].p_ext;
next = ext4_ext_next_allocated_block(path);
+ ext4_ext_drop_refs(path);
+ flags = 0;
exists = 0;
if (!ex) {
/* there is no extent yet, so try to allocate
BUG_ON(end <= start);
if (!exists) {
- cbex.ec_block = start;
- cbex.ec_len = end - start;
- cbex.ec_start = 0;
+ es.es_lblk = start;
+ es.es_len = end - start;
+ es.es_pblk = 0;
} else {
- cbex.ec_block = le32_to_cpu(ex->ee_block);
- cbex.ec_len = ext4_ext_get_actual_len(ex);
- cbex.ec_start = ext4_ext_pblock(ex);
+ 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))
+ flags |= FIEMAP_EXTENT_UNWRITTEN;
}
- if (unlikely(cbex.ec_len == 0)) {
- EXT4_ERROR_INODE(inode, "cbex.ec_len == 0");
- err = -EIO;
- break;
+ /*
+ * Find delayed extent and update es accordingly. We call
+ * it even in !exists case to find out whether es is the
+ * last existing extent or not.
+ */
+ next_del = ext4_find_delayed_extent(inode, &es);
+ if (!exists && next_del) {
+ exists = 1;
+ flags |= FIEMAP_EXTENT_DELALLOC;
}
- err = func(inode, next, &cbex, ex, cbdata);
- ext4_ext_drop_refs(path);
+ up_read(&EXT4_I(inode)->i_data_sem);
- if (err < 0)
+ if (unlikely(es.es_len == 0)) {
+ EXT4_ERROR_INODE(inode, "es.es_len == 0");
+ err = -EIO;
break;
+ }
- if (err == EXT_REPEAT)
- continue;
- else if (err == EXT_BREAK) {
- err = 0;
- break;
+ /*
+ * This is possible iff next == next_del == EXT_MAX_BLOCKS.
+ * we need to check next == EXT_MAX_BLOCKS because it is
+ * possible that an extent is with unwritten and delayed
+ * status due to when an extent is delayed allocated and
+ * is allocated by fallocate status tree will track both of
+ * them in a extent.
+ *
+ * So we could return a unwritten and delayed extent, and
+ * its block is equal to 'next'.
+ */
+ if (next == next_del && next == EXT_MAX_BLOCKS) {
+ flags |= FIEMAP_EXTENT_LAST;
+ if (unlikely(next_del != EXT_MAX_BLOCKS ||
+ next != EXT_MAX_BLOCKS)) {
+ EXT4_ERROR_INODE(inode,
+ "next extent == %u, next "
+ "delalloc extent = %u",
+ next, next_del);
+ err = -EIO;
+ break;
+ }
}
- if (ext_depth(inode) != depth) {
- /* depth was changed. we have to realloc path */
- kfree(path);
- path = NULL;
+ if (exists) {
+ err = fiemap_fill_next_extent(fieinfo,
+ (__u64)es.es_lblk << blksize_bits,
+ (__u64)es.es_pblk << blksize_bits,
+ (__u64)es.es_len << blksize_bits,
+ flags);
+ if (err < 0)
+ break;
+ if (err == 1) {
+ err = 0;
+ break;
+ }
}
- block = cbex.ec_block + cbex.ec_len;
+ block = es.es_lblk + es.es_len;
}
if (path) {
return err;
}
-static void
-ext4_ext_put_in_cache(struct inode *inode, ext4_lblk_t block,
- __u32 len, ext4_fsblk_t start)
-{
- struct ext4_ext_cache *cex;
- BUG_ON(len == 0);
- spin_lock(&EXT4_I(inode)->i_block_reservation_lock);
- trace_ext4_ext_put_in_cache(inode, block, len, start);
- cex = &EXT4_I(inode)->i_cached_extent;
- cex->ec_block = block;
- cex->ec_len = len;
- cex->ec_start = start;
- spin_unlock(&EXT4_I(inode)->i_block_reservation_lock);
-}
-
/*
* ext4_ext_put_gap_in_cache:
* calculate boundaries of the gap that the requested block fits into
ext4_lblk_t block)
{
int depth = ext_depth(inode);
- unsigned long len;
- ext4_lblk_t lblock;
+ unsigned long len = 0;
+ ext4_lblk_t lblock = 0;
struct ext4_extent *ex;
ex = path[depth].p_ext;
if (ex == NULL) {
- /* there is no extent yet, so gap is [0;-] */
- lblock = 0;
- len = EXT_MAX_BLOCKS;
+ /*
+ * there is no extent yet, so gap is [0;-] and we
+ * don't cache it
+ */
ext_debug("cache gap(whole file):");
} else if (block < le32_to_cpu(ex->ee_block)) {
lblock = block;
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;
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 {
- lblock = len = 0;
BUG();
}
ext_debug(" -> %u:%lu\n", lblock, len);
- ext4_ext_put_in_cache(inode, lblock, len, 0);
-}
-
-/*
- * ext4_ext_check_cache()
- * Checks to see if the given block is in the cache.
- * If it is, the cached extent is stored in the given
- * cache extent pointer. If the cached extent is a hole,
- * this routine should be used instead of
- * ext4_ext_in_cache if the calling function needs to
- * know the size of the hole.
- *
- * @inode: The files inode
- * @block: The block to look for in the cache
- * @ex: Pointer where the cached extent will be stored
- * if it contains block
- *
- * Return 0 if cache is invalid; 1 if the cache is valid
- */
-static int ext4_ext_check_cache(struct inode *inode, ext4_lblk_t block,
- struct ext4_ext_cache *ex){
- struct ext4_ext_cache *cex;
- struct ext4_sb_info *sbi;
- int ret = 0;
-
- /*
- * We borrow i_block_reservation_lock to protect i_cached_extent
- */
- spin_lock(&EXT4_I(inode)->i_block_reservation_lock);
- cex = &EXT4_I(inode)->i_cached_extent;
- sbi = EXT4_SB(inode->i_sb);
-
- /* has cache valid data? */
- if (cex->ec_len == 0)
- goto errout;
-
- if (in_range(block, cex->ec_block, cex->ec_len)) {
- memcpy(ex, cex, sizeof(struct ext4_ext_cache));
- ext_debug("%u cached by %u:%u:%llu\n",
- block,
- cex->ec_block, cex->ec_len, cex->ec_start);
- ret = 1;
- }
-errout:
- if (!ret)
- sbi->extent_cache_misses++;
- else
- sbi->extent_cache_hits++;
- trace_ext4_ext_in_cache(inode, block, ret);
- spin_unlock(&EXT4_I(inode)->i_block_reservation_lock);
- return ret;
-}
-
-/*
- * ext4_ext_in_cache()
- * Checks to see if the given block is in the cache.
- * If it is, the cached extent is stored in the given
- * extent pointer.
- *
- * @inode: The files inode
- * @block: The block to look for in the cache
- * @ex: Pointer where the cached extent will be stored
- * if it contains block
- *
- * Return 0 if cache is invalid; 1 if the cache is valid
- */
-static int
-ext4_ext_in_cache(struct inode *inode, ext4_lblk_t block,
- struct ext4_extent *ex)
-{
- struct ext4_ext_cache cex;
- int ret = 0;
-
- if (ext4_ext_check_cache(inode, block, &cex)) {
- ex->ee_block = cpu_to_le32(cex.ec_block);
- ext4_ext_store_pblock(ex, cex.ec_start);
- ex->ee_len = cpu_to_le16(cex.ec_len);
- ret = 1;
- }
-
- return ret;
}
-
/*
* ext4_ext_rm_idx:
* removes index from the index block.
*/
static int ext4_ext_rm_idx(handle_t *handle, struct inode *inode,
- struct ext4_ext_path *path)
+ struct ext4_ext_path *path, int depth)
{
int err;
ext4_fsblk_t leaf;
/* free index block */
- path--;
+ depth--;
+ path = path + depth;
leaf = ext4_idx_pblock(path->p_idx);
if (unlikely(path->p_hdr->eh_entries == 0)) {
EXT4_ERROR_INODE(inode, "path->p_hdr->eh_entries == 0");
ext4_free_blocks(handle, inode, NULL, leaf, 1,
EXT4_FREE_BLOCKS_METADATA | EXT4_FREE_BLOCKS_FORGET);
+
+ while (--depth >= 0) {
+ if (path->p_idx != EXT_FIRST_INDEX(path->p_hdr))
+ break;
+ path--;
+ err = ext4_ext_get_access(handle, inode, path);
+ if (err)
+ break;
+ path->p_idx->ei_block = (path+1)->p_idx->ei_block;
+ err = ext4_ext_dirty(handle, inode, path);
+ if (err)
+ break;
+ }
return err;
}
int ext4_ext_index_trans_blocks(struct inode *inode, int nrblocks, int chunk)
{
int index;
- int depth = ext_depth(inode);
+ int depth;
+
+ /* If we are converting the inline data, only one is needed here. */
+ if (ext4_has_inline_data(inode))
+ return 1;
+
+ depth = ext_depth(inode);
if (chunk)
index = depth * 2;
struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
unsigned short ee_len = ext4_ext_get_actual_len(ex);
ext4_fsblk_t pblk;
- int flags = EXT4_FREE_BLOCKS_FORGET;
+ int flags = 0;
if (S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode))
- flags |= EXT4_FREE_BLOCKS_METADATA;
+ flags |= EXT4_FREE_BLOCKS_METADATA | EXT4_FREE_BLOCKS_FORGET;
+ else if (ext4_should_journal_data(inode))
+ flags |= EXT4_FREE_BLOCKS_FORGET;
+
/*
* For bigalloc file systems, we never free a partial cluster
* at the beginning of the extent. Instead, we make a note
* truncate operation has removed all of the blocks in
* the cluster.
*/
- if (pblk & (sbi->s_cluster_ratio - 1) &&
+ if (EXT4_PBLK_COFF(sbi, pblk) &&
(ee_len == num))
*partial_cluster = EXT4_B2C(sbi, pblk);
else
struct ext4_extent *ex;
/* the header must be checked already in ext4_ext_remove_space() */
- ext_debug("truncate since %u in leaf\n", start);
+ ext_debug("truncate since %u in leaf to %u\n", start, end);
if (!path[depth].p_hdr)
path[depth].p_hdr = ext_block_hdr(path[depth].p_bh);
eh = path[depth].p_hdr;
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) &&
ext_debug(" border %u:%u\n", a, b);
/* If this extent is beyond the end of the hole, skip it */
- if (end <= ex_ee_block) {
+ if (end < ex_ee_block) {
ex--;
ex_ee_block = le32_to_cpu(ex->ee_block);
ex_ee_len = ext4_ext_get_actual_len(ex);
continue;
} else if (b != ex_ee_block + ex_ee_len - 1) {
- EXT4_ERROR_INODE(inode," bad truncate %u:%u\n",
- start, end);
+ EXT4_ERROR_INODE(inode,
+ "can not handle truncate %u:%u "
+ "on extent %u:%u",
+ start, end, ex_ee_block,
+ ex_ee_block + ex_ee_len - 1);
err = -EIO;
goto out;
} else if (a != ex_ee_block) {
/* if this leaf is free, then we should
* remove it from index block above */
if (err == 0 && eh->eh_entries == 0 && path[depth].p_bh != NULL)
- err = ext4_ext_rm_idx(handle, inode, path + depth);
+ err = ext4_ext_rm_idx(handle, inode, path, depth);
out:
return err;
return 1;
}
-static int ext4_ext_remove_space(struct inode *inode, ext4_lblk_t start)
+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;
+ struct ext4_ext_path *path = NULL;
ext4_fsblk_t partial_cluster = 0;
handle_t *handle;
- int i, err;
+ int i = 0, err = 0;
- ext_debug("truncate since %u\n", start);
+ ext_debug("truncate since %u to %u\n", start, end);
/* probably first extent we're gonna free will be last in block */
- handle = ext4_journal_start(inode, depth + 1);
+ handle = ext4_journal_start(inode, EXT4_HT_TRUNCATE, depth + 1);
if (IS_ERR(handle))
return PTR_ERR(handle);
again:
- ext4_ext_invalidate_cache(inode);
-
trace_ext4_ext_remove_space(inode, start, depth);
+ /*
+ * Check if we are removing extents inside the extent tree. If that
+ * is the case, we are going to punch a hole inside the extent tree
+ * so we have to check whether we need to split the extent covering
+ * the last block to remove so we can easily remove the part of it
+ * in ext4_ext_rm_leaf().
+ */
+ if (end < EXT_MAX_BLOCKS - 1) {
+ struct ext4_extent *ex;
+ ext4_lblk_t ee_block;
+
+ /* find extent for this block */
+ path = ext4_ext_find_extent(inode, end, NULL);
+ if (IS_ERR(path)) {
+ ext4_journal_stop(handle);
+ return PTR_ERR(path);
+ }
+ depth = ext_depth(inode);
+ /* Leaf not may not exist only if inode has no blocks at all */
+ ex = path[depth].p_ext;
+ if (!ex) {
+ if (depth) {
+ EXT4_ERROR_INODE(inode,
+ "path[%d].p_hdr == NULL",
+ depth);
+ err = -EIO;
+ }
+ goto out;
+ }
+
+ ee_block = le32_to_cpu(ex->ee_block);
+
+ /*
+ * See if the last block is inside the extent, if so split
+ * the extent at 'end' block so we can easily remove the
+ * 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 (ext4_ext_is_uninitialized(ex))
+ split_flag = EXT4_EXT_MARK_UNINIT1 |
+ EXT4_EXT_MARK_UNINIT2;
+
+ /*
+ * Split the extent in two so that 'end' is the last
+ * 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_METADATA_NOFAIL);
+
+ if (err < 0)
+ goto out;
+ }
+ }
/*
* We start scanning from right side, freeing all the blocks
* after i_size and walking into the tree depth-wise.
*/
depth = ext_depth(inode);
- path = kzalloc(sizeof(struct ext4_ext_path) * (depth + 1), GFP_NOFS);
- if (path == NULL) {
- ext4_journal_stop(handle);
- return -ENOMEM;
- }
- path[0].p_depth = depth;
- path[0].p_hdr = ext_inode_hdr(inode);
- if (ext4_ext_check(inode, path[0].p_hdr, depth)) {
- err = -EIO;
- goto out;
+ if (path) {
+ int k = i = depth;
+ while (--k > 0)
+ path[k].p_block =
+ le16_to_cpu(path[k].p_hdr->eh_entries)+1;
+ } else {
+ path = kzalloc(sizeof(struct ext4_ext_path) * (depth + 1),
+ GFP_NOFS);
+ if (path == NULL) {
+ ext4_journal_stop(handle);
+ return -ENOMEM;
+ }
+ path[0].p_depth = depth;
+ path[0].p_hdr = ext_inode_hdr(inode);
+ i = 0;
+
+ if (ext4_ext_check(inode, path[0].p_hdr, depth)) {
+ err = -EIO;
+ goto out;
+ }
}
- i = err = 0;
+ err = 0;
while (i >= 0 && err == 0) {
if (i == depth) {
/* this is leaf block */
err = ext4_ext_rm_leaf(handle, inode, path,
&partial_cluster, start,
- EXT_MAX_BLOCKS - 1);
+ end);
/* root level has p_bh == NULL, brelse() eats this */
brelse(path[i].p_bh);
path[i].p_bh = NULL;
err = -EIO;
break;
}
- if (ext4_ext_check(inode, ext_block_hdr(bh),
- depth - i - 1)) {
+ if (ext4_ext_check_block(inode, ext_block_hdr(bh),
+ depth - i - 1, bh)) {
err = -EIO;
break;
}
/* index is empty, remove it;
* handle must be already prepared by the
* truncatei_leaf() */
- err = ext4_ext_rm_idx(handle, inode, path + i);
+ err = ext4_ext_rm_idx(handle, inode, path, i);
}
/* root level has p_bh == NULL, brelse() eats this */
brelse(path[i].p_bh);
out:
ext4_ext_drop_refs(path);
kfree(path);
- if (err == -EAGAIN)
+ if (err == -EAGAIN) {
+ path = NULL;
goto again;
+ }
ext4_journal_stop(handle);
return err;
if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_EXTENTS)) {
#if defined(AGGRESSIVE_TEST) || defined(CHECK_BINSEARCH) || defined(EXTENTS_STATS)
- printk(KERN_INFO "EXT4-fs: file extents enabled");
+ printk(KERN_INFO "EXT4-fs: file extents enabled"
#ifdef AGGRESSIVE_TEST
- printk(", aggressive tests");
+ ", aggressive tests"
#endif
#ifdef CHECK_BINSEARCH
- printk(", check binsearch");
+ ", check binsearch"
#endif
#ifdef EXTENTS_STATS
- printk(", stats");
+ ", stats"
#endif
- printk("\n");
+ "\n");
#endif
#ifdef EXTENTS_STATS
spin_lock_init(&EXT4_SB(sb)->s_ext_stats_lock);
return ret;
}
-/*
- * used by extent splitting.
- */
-#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 */
-
/*
* ext4_split_extent_at() splits an extent at given block.
*
{
ext4_fsblk_t newblock;
ext4_lblk_t ee_block;
- struct ext4_extent *ex, newex, orig_ex;
+ struct ext4_extent *ex, newex, orig_ex, zero_ex;
struct ext4_extent *ex2 = NULL;
unsigned int ee_len, depth;
int err = 0;
+ BUG_ON((split_flag & (EXT4_EXT_DATA_VALID1 | EXT4_EXT_DATA_VALID2)) ==
+ (EXT4_EXT_DATA_VALID1 | EXT4_EXT_DATA_VALID2));
+
ext_debug("ext4_split_extents_at: inode %lu, logical"
"block %llu\n", inode->i_ino, (unsigned long long)split);
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) &&
+ split_flag & (EXT4_EXT_MAY_ZEROOUT |
+ EXT4_EXT_MARK_UNINIT1 |
+ EXT4_EXT_MARK_UNINIT2));
err = ext4_ext_get_access(handle, inode, path + depth);
if (err)
ext4_ext_mark_initialized(ex);
if (!(flags & EXT4_GET_BLOCKS_PRE_IO))
- ext4_ext_try_to_merge(inode, path, ex);
+ ext4_ext_try_to_merge(handle, inode, path, ex);
- err = ext4_ext_dirty(handle, inode, path + depth);
+ err = ext4_ext_dirty(handle, inode, path + path->p_depth);
goto out;
}
err = ext4_ext_insert_extent(handle, inode, path, &newex, flags);
if (err == -ENOSPC && (EXT4_EXT_MAY_ZEROOUT & split_flag)) {
- err = ext4_ext_zeroout(inode, &orig_ex);
- if (err)
- goto fix_extent_len;
- /* update the extent length and mark as initialized */
- ex->ee_len = cpu_to_le32(ee_len);
- ext4_ext_try_to_merge(inode, path, ex);
- err = ext4_ext_dirty(handle, inode, path + depth);
+ if (split_flag & (EXT4_EXT_DATA_VALID1|EXT4_EXT_DATA_VALID2)) {
+ if (split_flag & EXT4_EXT_DATA_VALID1) {
+ err = ext4_ext_zeroout(inode, ex2);
+ zero_ex.ee_block = ex2->ee_block;
+ zero_ex.ee_len = cpu_to_le16(
+ ext4_ext_get_actual_len(ex2));
+ ext4_ext_store_pblock(&zero_ex,
+ ext4_ext_pblock(ex2));
+ } else {
+ err = ext4_ext_zeroout(inode, ex);
+ zero_ex.ee_block = ex->ee_block;
+ zero_ex.ee_len = cpu_to_le16(
+ ext4_ext_get_actual_len(ex));
+ ext4_ext_store_pblock(&zero_ex,
+ ext4_ext_pblock(ex));
+ }
+ } else {
+ err = ext4_ext_zeroout(inode, &orig_ex);
+ zero_ex.ee_block = orig_ex.ee_block;
+ zero_ex.ee_len = cpu_to_le16(
+ ext4_ext_get_actual_len(&orig_ex));
+ ext4_ext_store_pblock(&zero_ex,
+ ext4_ext_pblock(&orig_ex));
+ }
+
+ if (err)
+ goto fix_extent_len;
+ /* update the extent length and mark as initialized */
+ ex->ee_len = cpu_to_le16(ee_len);
+ ext4_ext_try_to_merge(handle, inode, path, ex);
+ err = ext4_ext_dirty(handle, inode, path + path->p_depth);
+ if (err)
+ goto fix_extent_len;
+
+ /* update extent status tree */
+ err = ext4_es_zeroout(inode, &zero_ex);
+
goto out;
} else if (err)
goto fix_extent_len;
int err = 0;
int uninitialized;
int split_flag1, flags1;
+ int allocated = map->m_len;
depth = ext_depth(inode);
ex = path[depth].p_ext;
uninitialized = ext4_ext_is_uninitialized(ex);
if (map->m_lblk + map->m_len < ee_block + ee_len) {
- split_flag1 = split_flag & EXT4_EXT_MAY_ZEROOUT ?
- EXT4_EXT_MAY_ZEROOUT : 0;
+ 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 (split_flag & EXT4_EXT_DATA_VALID2)
+ split_flag1 |= EXT4_EXT_DATA_VALID1;
err = ext4_split_extent_at(handle, inode, path,
map->m_lblk + map->m_len, split_flag1, flags1);
if (err)
goto out;
+ } else {
+ allocated = ee_len - (map->m_lblk - ee_block);
}
-
+ /*
+ * 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);
if (IS_ERR(path))
return PTR_ERR(path);
+ depth = ext_depth(inode);
+ ex = path[depth].p_ext;
+ uninitialized = ext4_ext_is_uninitialized(ex);
+ split_flag1 = 0;
if (map->m_lblk >= ee_block) {
- split_flag1 = split_flag & EXT4_EXT_MAY_ZEROOUT ?
- EXT4_EXT_MAY_ZEROOUT : 0;
- if (uninitialized)
+ split_flag1 = split_flag & EXT4_EXT_DATA_VALID2;
+ if (uninitialized) {
split_flag1 |= EXT4_EXT_MARK_UNINIT1;
- if (split_flag & EXT4_EXT_MARK_UNINIT2)
- split_flag1 |= EXT4_EXT_MARK_UNINIT2;
+ split_flag1 |= split_flag & (EXT4_EXT_MAY_ZEROOUT |
+ EXT4_EXT_MARK_UNINIT2);
+ }
err = ext4_split_extent_at(handle, inode, path,
map->m_lblk, split_flag1, flags);
if (err)
ext4_ext_show_leaf(inode, path);
out:
- return err ? err : map->m_len;
+ return err ? err : allocated;
}
-#define EXT4_EXT_ZERO_LEN 7
/*
* 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
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;
+ 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);
/*
*/
split_flag |= ee_block + ee_len <= eof_block ? EXT4_EXT_MAY_ZEROOUT : 0;
- /* If extent has less than 2*EXT4_EXT_ZERO_LEN zerout directly */
- if (ee_len <= 2*EXT4_EXT_ZERO_LEN &&
- (EXT4_EXT_MAY_ZEROOUT & split_flag)) {
+ if (EXT4_EXT_MAY_ZEROOUT & split_flag)
+ max_zeroout = sbi->s_extent_max_zeroout_kb >>
+ (inode->i_sb->s_blocksize_bits - 10);
+
+ /* If extent is less than s_max_zeroout_kb, zeroout directly */
+ if (max_zeroout && (ee_len <= max_zeroout)) {
err = ext4_ext_zeroout(inode, ex);
if (err)
goto out;
+ zero_ex.ee_block = ex->ee_block;
+ zero_ex.ee_len = cpu_to_le16(ext4_ext_get_actual_len(ex));
+ ext4_ext_store_pblock(&zero_ex, ext4_ext_pblock(ex));
err = ext4_ext_get_access(handle, inode, path + depth);
if (err)
goto out;
ext4_ext_mark_initialized(ex);
- ext4_ext_try_to_merge(inode, path, ex);
- err = ext4_ext_dirty(handle, inode, path + depth);
+ ext4_ext_try_to_merge(handle, inode, path, ex);
+ err = ext4_ext_dirty(handle, inode, path + path->p_depth);
goto out;
}
split_map.m_lblk = map->m_lblk;
split_map.m_len = map->m_len;
- if (allocated > map->m_len) {
- if (allocated <= EXT4_EXT_ZERO_LEN &&
- (EXT4_EXT_MAY_ZEROOUT & split_flag)) {
+ if (max_zeroout && (allocated > map->m_len)) {
+ if (allocated <= max_zeroout) {
/* case 3 */
zero_ex.ee_block =
cpu_to_le32(map->m_lblk);
goto out;
split_map.m_lblk = map->m_lblk;
split_map.m_len = allocated;
- } else if ((map->m_lblk - ee_block + map->m_len <
- EXT4_EXT_ZERO_LEN) &&
- (EXT4_EXT_MAY_ZEROOUT & split_flag)) {
+ } else if (map->m_lblk - ee_block + map->m_len < max_zeroout) {
/* case 2 */
if (map->m_lblk != ee_block) {
zero_ex.ee_block = ex->ee_block;
}
allocated = ext4_split_extent(handle, inode, path,
- &split_map, split_flag, 0);
+ &split_map, split_flag, flags);
if (allocated < 0)
err = allocated;
out:
+ /* If we have gotten a failure, don't zero out status tree */
+ if (!err)
+ err = ext4_es_zeroout(inode, &zero_ex);
return err ? err : allocated;
}
* to an uninitialized extent.
*
* Writing to an uninitialized extent may result in splitting the uninitialized
- * extent into multiple /initialized uninitialized extents (up to three)
+ * extent into multiple initialized/uninitialized extents (up to three)
* There are three possibilities:
* a> There is no split required: Entire extent should be uninitialized
* b> Splits in two extents: Write is happening at either end of the extent
split_flag |= ee_block + ee_len <= eof_block ? EXT4_EXT_MAY_ZEROOUT : 0;
split_flag |= EXT4_EXT_MARK_UNINIT2;
-
+ if (flags & EXT4_GET_BLOCKS_CONVERT)
+ split_flag |= 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_unwritten_extents_endio(handle_t *handle,
- struct inode *inode,
- struct ext4_ext_path *path)
+ 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("ext4_convert_unwritten_extents_endio: inode %lu, logical"
"block %llu, max_blocks %u\n", inode->i_ino,
- (unsigned long long)le32_to_cpu(ex->ee_block),
- ext4_ext_get_actual_len(ex));
+ (unsigned long long)ee_block, ee_len);
+
+ /* If extent is larger than requested it is a clear sign that we still
+ * have some extent state machine issues left. So extent_split is still
+ * required.
+ * TODO: Once all related issues will be fixed this situation should be
+ * illegal.
+ */
+ if (ee_block != map->m_lblk || ee_len > map->m_len) {
+#ifdef EXT4_DEBUG
+ ext4_warning("Inode (%ld) finished: extent logical block %llu,"
+ " len %u; IO logical block %llu, len %u\n",
+ inode->i_ino, (unsigned long long)ee_block, ee_len,
+ (unsigned long long)map->m_lblk, map->m_len);
+#endif
+ err = ext4_split_unwritten_extents(handle, inode, map, path,
+ EXT4_GET_BLOCKS_CONVERT);
+ if (err < 0)
+ goto out;
+ ext4_ext_drop_refs(path);
+ path = ext4_ext_find_extent(inode, map->m_lblk, path);
+ if (IS_ERR(path)) {
+ err = PTR_ERR(path);
+ goto out;
+ }
+ depth = ext_depth(inode);
+ ex = path[depth].p_ext;
+ }
err = ext4_ext_get_access(handle, inode, path + depth);
if (err)
/* note: ext4_ext_correct_indexes() isn't needed here because
* borders are not changed
*/
- ext4_ext_try_to_merge(inode, path, ex);
+ ext4_ext_try_to_merge(handle, inode, path, ex);
/* Mark modified extent as dirty */
- err = ext4_ext_dirty(handle, inode, path + depth);
+ err = ext4_ext_dirty(handle, inode, path + path->p_depth);
out:
ext4_ext_show_leaf(inode, path);
return err;
depth = ext_depth(inode);
eh = path[depth].p_hdr;
- if (unlikely(!eh->eh_entries)) {
- EXT4_ERROR_INODE(inode, "eh->eh_entries == 0 and "
- "EOFBLOCKS_FL set");
- return -EIO;
- }
+ /*
+ * We're going to remove EOFBLOCKS_FL entirely in future so we
+ * do not care for this case anymore. Simply remove the flag
+ * if there are no extents.
+ */
+ if (unlikely(!eh->eh_entries))
+ goto out;
last_ex = EXT_LAST_EXTENT(eh);
/*
* We should clear the EOFBLOCKS_FL flag if we are writing the
for (i = depth-1; i >= 0; i--)
if (path[i].p_idx != EXT_LAST_INDEX(path[i].p_hdr))
return 0;
+out:
ext4_clear_inode_flag(inode, EXT4_INODE_EOFBLOCKS);
return ext4_mark_inode_dirty(handle, inode);
}
/**
* ext4_find_delalloc_range: find delayed allocated block in the given range.
*
- * Goes through the buffer heads in the range [lblk_start, lblk_end] and returns
- * whether there are any buffers marked for delayed allocation. It returns '1'
- * on the first delalloc'ed buffer head found. If no buffer head in the given
- * range is marked for delalloc, it returns 0.
- * lblk_start should always be <= lblk_end.
- * search_hint_reverse is to indicate that searching in reverse from lblk_end to
- * lblk_start might be more efficient (i.e., we will likely hit the delalloc'ed
- * block sooner). This is useful when blocks are truncated sequentially from
- * lblk_start towards lblk_end.
+ * Return 1 if there is a delalloc block in the range, otherwise 0.
*/
-static int ext4_find_delalloc_range(struct inode *inode,
- ext4_lblk_t lblk_start,
- ext4_lblk_t lblk_end,
- int search_hint_reverse)
+int ext4_find_delalloc_range(struct inode *inode,
+ ext4_lblk_t lblk_start,
+ ext4_lblk_t lblk_end)
{
- struct address_space *mapping = inode->i_mapping;
- struct buffer_head *head, *bh = NULL;
- struct page *page;
- ext4_lblk_t i, pg_lblk;
- pgoff_t index;
-
- /* reverse search wont work if fs block size is less than page size */
- if (inode->i_blkbits < PAGE_CACHE_SHIFT)
- search_hint_reverse = 0;
-
- if (search_hint_reverse)
- i = lblk_end;
- else
- i = lblk_start;
-
- index = i >> (PAGE_CACHE_SHIFT - inode->i_blkbits);
-
- while ((i >= lblk_start) && (i <= lblk_end)) {
- page = find_get_page(mapping, index);
- if (!page)
- goto nextpage;
-
- if (!page_has_buffers(page))
- goto nextpage;
-
- head = page_buffers(page);
- if (!head)
- goto nextpage;
-
- bh = head;
- pg_lblk = index << (PAGE_CACHE_SHIFT -
- inode->i_blkbits);
- do {
- if (unlikely(pg_lblk < lblk_start)) {
- /*
- * This is possible when fs block size is less
- * than page size and our cluster starts/ends in
- * middle of the page. So we need to skip the
- * initial few blocks till we reach the 'lblk'
- */
- pg_lblk++;
- continue;
- }
-
- /* Check if the buffer is delayed allocated and that it
- * is not yet mapped. (when da-buffers are mapped during
- * their writeout, their da_mapped bit is set.)
- */
- if (buffer_delay(bh) && !buffer_da_mapped(bh)) {
- page_cache_release(page);
- trace_ext4_find_delalloc_range(inode,
- lblk_start, lblk_end,
- search_hint_reverse,
- 1, i);
- return 1;
- }
- if (search_hint_reverse)
- i--;
- else
- i++;
- } while ((i >= lblk_start) && (i <= lblk_end) &&
- ((bh = bh->b_this_page) != head));
-nextpage:
- if (page)
- page_cache_release(page);
- /*
- * Move to next page. 'i' will be the first lblk in the next
- * page.
- */
- if (search_hint_reverse)
- index--;
- else
- index++;
- i = index << (PAGE_CACHE_SHIFT - inode->i_blkbits);
- }
+ struct extent_status es;
- trace_ext4_find_delalloc_range(inode, lblk_start, lblk_end,
- search_hint_reverse, 0, 0);
- return 0;
+ 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 &&
+ lblk_start < es.es_lblk + es.es_len)
+ return 1;
+ else if (lblk_start <= es.es_lblk && es.es_lblk <= lblk_end)
+ return 1;
+ else
+ return 0;
}
-int ext4_find_delalloc_cluster(struct inode *inode, ext4_lblk_t lblk,
- int search_hint_reverse)
+int ext4_find_delalloc_cluster(struct inode *inode, ext4_lblk_t lblk)
{
struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
ext4_lblk_t lblk_start, lblk_end;
- lblk_start = lblk & (~(sbi->s_cluster_ratio - 1));
+ lblk_start = EXT4_LBLK_CMASK(sbi, lblk);
lblk_end = lblk_start + sbi->s_cluster_ratio - 1;
- return ext4_find_delalloc_range(inode, lblk_start, lblk_end,
- search_hint_reverse);
+ return ext4_find_delalloc_range(inode, lblk_start, lblk_end);
}
/**
trace_ext4_get_reserved_cluster_alloc(inode, lblk_start, num_blks);
/* Check towards left side */
- c_offset = lblk_start & (sbi->s_cluster_ratio - 1);
+ c_offset = EXT4_LBLK_COFF(sbi, lblk_start);
if (c_offset) {
- lblk_from = lblk_start & (~(sbi->s_cluster_ratio - 1));
+ lblk_from = EXT4_LBLK_CMASK(sbi, lblk_start);
lblk_to = lblk_from + c_offset - 1;
- if (ext4_find_delalloc_range(inode, lblk_from, lblk_to, 0))
+ if (ext4_find_delalloc_range(inode, lblk_from, lblk_to))
allocated_clusters--;
}
/* Now check towards right. */
- c_offset = (lblk_start + num_blks) & (sbi->s_cluster_ratio - 1);
+ c_offset = EXT4_LBLK_COFF(sbi, lblk_start + num_blks);
if (allocated_clusters && c_offset) {
lblk_from = lblk_start + num_blks;
lblk_to = lblk_from + (sbi->s_cluster_ratio - c_offset) - 1;
- if (ext4_find_delalloc_range(inode, lblk_from, lblk_to, 0))
+ if (ext4_find_delalloc_range(inode, lblk_from, lblk_to))
allocated_clusters--;
}
{
int ret = 0;
int err = 0;
- ext4_io_end_t *io = EXT4_I(inode)->cur_aio_dio;
+ ext4_io_end_t *io = ext4_inode_aio(inode);
- ext_debug("ext4_ext_handle_uninitialized_extents: inode %lu, logical"
- "block %llu, max_blocks %u, flags %d, allocated %u",
+ ext_debug("ext4_ext_handle_uninitialized_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);
- trace_ext4_ext_handle_uninitialized_extents(inode, map, allocated,
- newblock);
+ /*
+ * 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);
/* get_block() before submit the IO, split the extent */
if ((flags & EXT4_GET_BLOCKS_PRE_IO)) {
ret = ext4_split_unwritten_extents(handle, inode, map,
path, flags);
+ if (ret <= 0)
+ goto out;
/*
* Flag the inode(non aio case) or end_io struct (aio case)
* that this IO needs to conversion to written when IO is
ext4_set_io_unwritten_flag(inode, io);
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 */
if ((flags & EXT4_GET_BLOCKS_CONVERT)) {
- ret = ext4_convert_unwritten_extents_endio(handle, inode,
+ ret = ext4_convert_unwritten_extents_endio(handle, inode, map,
path);
if (ret >= 0) {
ext4_update_inode_fsync_trans(handle, inode, 1);
path, map->m_len);
} else
err = ret;
+ map->m_flags |= EXT4_MAP_MAPPED;
+ if (allocated > map->m_len)
+ allocated = map->m_len;
+ map->m_len = allocated;
goto out2;
}
/* buffered IO case */
* repeat fallocate creation request
* we already have an unwritten extent
*/
- if (flags & EXT4_GET_BLOCKS_UNINIT_EXT)
+ if (flags & EXT4_GET_BLOCKS_UNINIT_EXT) {
+ map->m_flags |= EXT4_MAP_UNWRITTEN;
goto map_out;
+ }
/* buffered READ or buffered write_begin() lookup */
if ((flags & EXT4_GET_BLOCKS_CREATE) == 0) {
}
/* 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:
allocated - map->m_len);
allocated = map->m_len;
}
+ map->m_len = allocated;
/*
* If we have done fallocate with the offset that is already
struct ext4_ext_path *path)
{
struct ext4_sb_info *sbi = EXT4_SB(sb);
- ext4_lblk_t c_offset = map->m_lblk & (sbi->s_cluster_ratio-1);
+ ext4_lblk_t c_offset = EXT4_LBLK_COFF(sbi, map->m_lblk);
ext4_lblk_t ex_cluster_start, ex_cluster_end;
- ext4_lblk_t rr_cluster_start, rr_cluster_end;
+ ext4_lblk_t rr_cluster_start;
ext4_lblk_t ee_block = le32_to_cpu(ex->ee_block);
ext4_fsblk_t ee_start = ext4_ext_pblock(ex);
unsigned short ee_len = ext4_ext_get_actual_len(ex);
/* The requested region passed into ext4_map_blocks() */
rr_cluster_start = EXT4_B2C(sbi, map->m_lblk);
- rr_cluster_end = EXT4_B2C(sbi, map->m_lblk + map->m_len - 1);
if ((rr_cluster_start == ex_cluster_end) ||
(rr_cluster_start == ex_cluster_start)) {
if (rr_cluster_start == ex_cluster_end)
ee_start += ee_len - 1;
- map->m_pblk = (ee_start & ~(sbi->s_cluster_ratio - 1)) +
- c_offset;
+ map->m_pblk = EXT4_PBLK_CMASK(sbi, ee_start) + c_offset;
map->m_len = min(map->m_len,
(unsigned) sbi->s_cluster_ratio - c_offset);
/*
int free_on_err = 0, err = 0, depth, ret;
unsigned int allocated = 0, offset = 0;
unsigned int allocated_clusters = 0;
- unsigned int punched_out = 0;
- unsigned int result = 0;
struct ext4_allocation_request ar;
- ext4_io_end_t *io = EXT4_I(inode)->cur_aio_dio;
+ ext4_io_end_t *io = ext4_inode_aio(inode);
ext4_lblk_t cluster_offset;
+ int set_unwritten = 0;
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);
- /* check in cache */
- if (!(flags & EXT4_GET_BLOCKS_PUNCH_OUT_EXT) &&
- ext4_ext_in_cache(inode, map->m_lblk, &newex)) {
- if (!newex.ee_start_lo && !newex.ee_start_hi) {
- if ((sbi->s_cluster_ratio > 1) &&
- ext4_find_delalloc_cluster(inode, map->m_lblk, 0))
- map->m_flags |= EXT4_MAP_FROM_CLUSTER;
-
- if ((flags & EXT4_GET_BLOCKS_CREATE) == 0) {
- /*
- * block isn't allocated yet and
- * user doesn't want to allocate it
- */
- goto out2;
- }
- /* we should allocate requested block */
- } else {
- /* block is already allocated */
- if (sbi->s_cluster_ratio > 1)
- map->m_flags |= EXT4_MAP_FROM_CLUSTER;
- newblock = map->m_lblk
- - le32_to_cpu(newex.ee_block)
- + ext4_ext_pblock(&newex);
- /* number of remaining blocks in the extent */
- allocated = ext4_ext_get_actual_len(&newex) -
- (map->m_lblk - le32_to_cpu(newex.ee_block));
- goto out;
- }
- }
-
/* find extent for this block */
path = ext4_ext_find_extent(inode, map->m_lblk, NULL);
if (IS_ERR(path)) {
/* if found extent covers block, simply return it */
if (in_range(map->m_lblk, ee_block, ee_len)) {
- struct ext4_map_blocks punch_map;
- ext4_fsblk_t partial_cluster = 0;
-
newblock = map->m_lblk - ee_block + ee_start;
/* number of remaining blocks in the extent */
allocated = ee_len - (map->m_lblk - ee_block);
ext_debug("%u fit into %u:%d -> %llu\n", map->m_lblk,
ee_block, ee_len, newblock);
- if ((flags & EXT4_GET_BLOCKS_PUNCH_OUT_EXT) == 0) {
- /*
- * Do not put uninitialized extent
- * in the cache
- */
- if (!ext4_ext_is_uninitialized(ex)) {
- ext4_ext_put_in_cache(inode, ee_block,
- ee_len, ee_start);
- goto out;
- }
- ret = ext4_ext_handle_uninitialized_extents(
- handle, inode, map, path, flags,
- allocated, newblock);
- return ret;
- }
-
- /*
- * Punch out the map length, but only to the
- * end of the extent
- */
- punched_out = allocated < map->m_len ?
- allocated : map->m_len;
-
- /*
- * Sense extents need to be converted to
- * uninitialized, they must fit in an
- * uninitialized extent
- */
- if (punched_out > EXT_UNINIT_MAX_LEN)
- punched_out = EXT_UNINIT_MAX_LEN;
-
- punch_map.m_lblk = map->m_lblk;
- punch_map.m_pblk = newblock;
- punch_map.m_len = punched_out;
- punch_map.m_flags = 0;
-
- /* Check to see if the extent needs to be split */
- if (punch_map.m_len != ee_len ||
- punch_map.m_lblk != ee_block) {
-
- ret = ext4_split_extent(handle, inode,
- path, &punch_map, 0,
- EXT4_GET_BLOCKS_PUNCH_OUT_EXT |
- EXT4_GET_BLOCKS_PRE_IO);
-
- if (ret < 0) {
- err = ret;
- goto out2;
- }
- /*
- * find extent for the block at
- * the start of the hole
- */
- ext4_ext_drop_refs(path);
- kfree(path);
-
- path = ext4_ext_find_extent(inode,
- map->m_lblk, NULL);
- if (IS_ERR(path)) {
- err = PTR_ERR(path);
- path = NULL;
- goto out2;
- }
-
- depth = ext_depth(inode);
- ex = path[depth].p_ext;
- ee_len = ext4_ext_get_actual_len(ex);
- ee_block = le32_to_cpu(ex->ee_block);
- ee_start = ext4_ext_pblock(ex);
-
- }
-
- ext4_ext_mark_uninitialized(ex);
-
- ext4_ext_invalidate_cache(inode);
-
- err = ext4_ext_rm_leaf(handle, inode, path,
- &partial_cluster, map->m_lblk,
- map->m_lblk + punched_out);
-
- if (!err && path->p_hdr->eh_entries == 0) {
- /*
- * Punch hole freed all of this sub tree,
- * so we need to correct eh_depth
- */
- err = ext4_ext_get_access(handle, inode, path);
- if (err == 0) {
- ext_inode_hdr(inode)->eh_depth = 0;
- ext_inode_hdr(inode)->eh_max =
- cpu_to_le16(ext4_ext_space_root(
- inode, 0));
-
- err = ext4_ext_dirty(
- handle, inode, path);
- }
- }
+ if (!ext4_ext_is_uninitialized(ex))
+ goto out;
- goto out2;
+ ret = ext4_ext_handle_uninitialized_extents(
+ handle, inode, map, path, flags,
+ allocated, newblock);
+ if (ret < 0)
+ err = ret;
+ else
+ allocated = ret;
+ goto out3;
}
}
if ((sbi->s_cluster_ratio > 1) &&
- ext4_find_delalloc_cluster(inode, map->m_lblk, 0))
+ ext4_find_delalloc_cluster(inode, map->m_lblk))
map->m_flags |= EXT4_MAP_FROM_CLUSTER;
/*
* put just found gap into cache to speed up
* subsequent requests
*/
- ext4_ext_put_gap_in_cache(inode, path, map->m_lblk);
+ if ((flags & EXT4_GET_BLOCKS_NO_PUT_HOLE) == 0)
+ ext4_ext_put_gap_in_cache(inode, path, map->m_lblk);
goto out2;
}
*/
map->m_flags &= ~EXT4_MAP_FROM_CLUSTER;
newex.ee_block = cpu_to_le32(map->m_lblk);
- cluster_offset = map->m_lblk & (sbi->s_cluster_ratio-1);
+ cluster_offset = EXT4_LBLK_COFF(sbi, map->m_lblk);
/*
* If we are doing bigalloc, check to see if the extent returned
* needed so that future calls to get_implied_cluster_alloc()
* work correctly.
*/
- offset = map->m_lblk & (sbi->s_cluster_ratio - 1);
+ offset = EXT4_LBLK_COFF(sbi, map->m_lblk);
ar.len = EXT4_NUM_B2C(sbi, offset+allocated);
ar.goal -= offset;
ar.logical -= offset;
/* Mark uninitialized */
if (flags & EXT4_GET_BLOCKS_UNINIT_EXT){
ext4_ext_mark_uninitialized(&newex);
+ map->m_flags |= EXT4_MAP_UNWRITTEN;
/*
* io_end structure was created for every IO write to an
* uninitialized extent. To avoid unnecessary 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)) {
- if (io)
- ext4_set_io_unwritten_flag(inode, io);
- else
- ext4_set_inode_state(inode,
- EXT4_STATE_DIO_UNWRITTEN);
- }
+ if ((flags & EXT4_GET_BLOCKS_PRE_IO))
+ set_unwritten = 1;
if (ext4_should_dioread_nolock(inode))
map->m_flags |= EXT4_MAP_UNINIT;
}
if (!err)
err = ext4_ext_insert_extent(handle, inode, path,
&newex, flags);
+
+ if (!err && set_unwritten) {
+ if (io)
+ ext4_set_io_unwritten_flag(inode, io);
+ else
+ ext4_set_inode_state(inode,
+ EXT4_STATE_DIO_UNWRITTEN);
+ }
+
if (err && free_on_err) {
int fb_flags = flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE ?
EXT4_FREE_BLOCKS_NO_QUOT_UPDATE : 0;
}
} else {
BUG_ON(allocated_clusters < reserved_clusters);
- /* We will claim quota for all newly allocated blocks.*/
- ext4_da_update_reserve_space(inode, allocated_clusters,
- 1);
if (reserved_clusters < allocated_clusters) {
struct ext4_inode_info *ei = EXT4_I(inode);
int reservation = allocated_clusters -
ei->i_reserved_data_blocks += reservation;
spin_unlock(&ei->i_block_reservation_lock);
}
+ /*
+ * We will claim quota for all newly allocated blocks.
+ * We're updating the reserved space *after* the
+ * correction above so we do not accidentally free
+ * all the metadata reservation because we might
+ * actually need it later on.
+ */
+ ext4_da_update_reserve_space(inode, allocated_clusters,
+ 1);
}
}
* Cache the extent and update transaction to commit on fdatasync only
* when it is _not_ an uninitialized extent.
*/
- if ((flags & EXT4_GET_BLOCKS_UNINIT_EXT) == 0) {
- ext4_ext_put_in_cache(inode, map->m_lblk, allocated, newblock);
+ if ((flags & EXT4_GET_BLOCKS_UNINIT_EXT) == 0)
ext4_update_inode_fsync_trans(handle, inode, 1);
- } else
+ else
ext4_update_inode_fsync_trans(handle, inode, 0);
out:
if (allocated > map->m_len)
ext4_ext_drop_refs(path);
kfree(path);
}
- result = (flags & EXT4_GET_BLOCKS_PUNCH_OUT_EXT) ?
- punched_out : allocated;
- trace_ext4_ext_map_blocks_exit(inode, map->m_lblk,
- newblock, map->m_len, err ? err : result);
+out3:
+ trace_ext4_ext_map_blocks_exit(inode, map, err ? err : allocated);
- return err ? err : result;
+ 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_completed_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, 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_ext_invalidate_cache(inode);
-
- ext4_discard_preallocations(inode);
-
/*
* TODO: optimization is possible here.
* Probably we need not scan at all,
last_block = (inode->i_size + sb->s_blocksize - 1)
>> EXT4_BLOCK_SIZE_BITS(sb);
- err = ext4_ext_remove_space(inode, last_block);
-
- /* 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);
+retry:
+ err = ext4_es_remove_extent(inode, last_block,
+ EXT_MAX_BLOCKS - last_block);
+ if (err == -ENOMEM) {
+ cond_resched();
+ congestion_wait(BLK_RW_ASYNC, HZ/50);
+ goto retry;
+ }
+ if (err) {
+ ext4_std_error(inode->i_sb, err);
+ return;
+ }
+ err = ext4_ext_remove_space(inode, last_block, EXT_MAX_BLOCKS - 1);
+ ext4_std_error(inode->i_sb, err);
}
static void ext4_falloc_update_inode(struct inode *inode,
*/
long ext4_fallocate(struct file *file, int mode, loff_t offset, loff_t len)
{
- struct inode *inode = file->f_path.dentry->d_inode;
+ struct inode *inode = file_inode(file);
handle_t *handle;
loff_t new_size;
unsigned int max_blocks;
struct ext4_map_blocks map;
unsigned int credits, blkbits = inode->i_blkbits;
- /*
- * currently supporting (pre)allocate mode for extent-based
- * files _only_
- */
- if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)))
- return -EOPNOTSUPP;
-
/* Return error if mode is not supported */
if (mode & ~(FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE))
return -EOPNOTSUPP;
if (mode & FALLOC_FL_PUNCH_HOLE)
return ext4_punch_hole(file, offset, len);
+ ret = ext4_convert_inline_data(inode);
+ if (ret)
+ return ret;
+
+ /*
+ * currently supporting (pre)allocate mode for extent-based
+ * files _only_
+ */
+ if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)))
+ return -EOPNOTSUPP;
+
trace_ext4_fallocate_enter(inode, offset, len, mode);
map.m_lblk = offset >> blkbits;
/*
*/
if (len <= EXT_UNINIT_MAX_LEN << blkbits)
flags |= EXT4_GET_BLOCKS_NO_NORMALIZE;
+
retry:
while (ret >= 0 && ret < max_blocks) {
map.m_lblk = map.m_lblk + ret;
map.m_len = max_blocks = max_blocks - ret;
- handle = ext4_journal_start(inode, credits);
+ handle = ext4_journal_start(inode, EXT4_HT_MAP_BLOCKS,
+ credits);
if (IS_ERR(handle)) {
ret = PTR_ERR(handle);
break;
ret = ext4_map_blocks(handle, inode, &map, flags);
if (ret <= 0) {
#ifdef EXT4FS_DEBUG
- WARN_ON(ret <= 0);
- printk(KERN_ERR "%s: ext4_ext_map_blocks "
- "returned error inode#%lu, block=%u, "
- "max_blocks=%u", __func__,
- inode->i_ino, map.m_lblk, max_blocks);
+ ext4_warning(inode->i_sb,
+ "inode #%lu: block %u: len %u: "
+ "ext4_ext_map_blocks returned %d",
+ inode->i_ino, map.m_lblk,
+ map.m_len, ret);
#endif
ext4_mark_inode_dirty(handle, inode);
ret2 = ext4_journal_stop(handle);
ext4_falloc_update_inode(inode, mode, new_size,
(map.m_flags & EXT4_MAP_NEW));
ext4_mark_inode_dirty(handle, inode);
+ if ((file->f_flags & O_SYNC) && ret >= max_blocks)
+ ext4_handle_sync(handle);
ret2 = ext4_journal_stop(handle);
if (ret2)
break;
while (ret >= 0 && ret < max_blocks) {
map.m_lblk += ret;
map.m_len = (max_blocks -= ret);
- handle = ext4_journal_start(inode, credits);
+ handle = ext4_journal_start(inode, EXT4_HT_MAP_BLOCKS, credits);
if (IS_ERR(handle)) {
ret = PTR_ERR(handle);
break;
}
ret = ext4_map_blocks(handle, inode, &map,
EXT4_GET_BLOCKS_IO_CONVERT_EXT);
- if (ret <= 0) {
- WARN_ON(ret <= 0);
- printk(KERN_ERR "%s: ext4_ext_map_blocks "
- "returned error inode#%lu, block=%u, "
- "max_blocks=%u", __func__,
- inode->i_ino, map.m_lblk, map.m_len);
- }
+ if (ret <= 0)
+ ext4_warning(inode->i_sb,
+ "inode #%lu: block %u: len %u: "
+ "ext4_ext_map_blocks returned %d",
+ inode->i_ino, map.m_lblk,
+ map.m_len, ret);
ext4_mark_inode_dirty(handle, inode);
ret2 = ext4_journal_stop(handle);
if (ret <= 0 || ret2 )
}
/*
- * Callback function called for each extent to gather FIEMAP information.
+ * If newes is not existing extent (newes->ec_pblk equals zero) find
+ * delayed extent at start of newes and update newes accordingly and
+ * return start of the next delayed extent.
+ *
+ * If newes is existing extent (newes->ec_pblk is not equal zero)
+ * return start of next delayed extent or EXT_MAX_BLOCKS if no delayed
+ * extent found. Leave newes unmodified.
*/
-static int ext4_ext_fiemap_cb(struct inode *inode, ext4_lblk_t next,
- struct ext4_ext_cache *newex, struct ext4_extent *ex,
- void *data)
+static int ext4_find_delayed_extent(struct inode *inode,
+ struct extent_status *newes)
{
- __u64 logical;
- __u64 physical;
- __u64 length;
- __u32 flags = 0;
- int ret = 0;
- struct fiemap_extent_info *fieinfo = data;
- unsigned char blksize_bits;
-
- blksize_bits = inode->i_sb->s_blocksize_bits;
- logical = (__u64)newex->ec_block << blksize_bits;
-
- if (newex->ec_start == 0) {
+ struct extent_status es;
+ ext4_lblk_t block, next_del;
+
+ 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 @newex->ec_start,
+ * No extent in extent-tree contains block @newes->es_pblk,
* then the block may stay in 1)a hole or 2)delayed-extent.
- *
- * Holes or delayed-extents are processed as follows.
- * 1. lookup dirty pages with specified range in pagecache.
- * If no page is got, then there is no delayed-extent and
- * return with EXT_CONTINUE.
- * 2. find the 1st mapped buffer,
- * 3. check if the mapped buffer is both in the request range
- * and a delayed buffer. If not, there is no delayed-extent,
- * then return.
- * 4. a delayed-extent is found, the extent will be collected.
*/
- ext4_lblk_t end = 0;
- pgoff_t last_offset;
- pgoff_t offset;
- pgoff_t index;
- pgoff_t start_index = 0;
- struct page **pages = NULL;
- struct buffer_head *bh = NULL;
- struct buffer_head *head = NULL;
- unsigned int nr_pages = PAGE_SIZE / sizeof(struct page *);
-
- pages = kmalloc(PAGE_SIZE, GFP_KERNEL);
- if (pages == NULL)
- return -ENOMEM;
-
- offset = logical >> PAGE_SHIFT;
-repeat:
- last_offset = offset;
- head = NULL;
- ret = find_get_pages_tag(inode->i_mapping, &offset,
- PAGECACHE_TAG_DIRTY, nr_pages, pages);
-
- if (!(flags & FIEMAP_EXTENT_DELALLOC)) {
- /* First time, try to find a mapped buffer. */
- if (ret == 0) {
-out:
- for (index = 0; index < ret; index++)
- page_cache_release(pages[index]);
- /* just a hole. */
- kfree(pages);
- return EXT_CONTINUE;
- }
- index = 0;
-
-next_page:
- /* Try to find the 1st mapped buffer. */
- end = ((__u64)pages[index]->index << PAGE_SHIFT) >>
- blksize_bits;
- if (!page_has_buffers(pages[index]))
- goto out;
- head = page_buffers(pages[index]);
- if (!head)
- goto out;
-
- index++;
- bh = head;
- do {
- if (end >= newex->ec_block +
- newex->ec_len)
- /* The buffer is out of
- * the request range.
- */
- goto out;
-
- if (buffer_mapped(bh) &&
- end >= newex->ec_block) {
- start_index = index - 1;
- /* get the 1st mapped buffer. */
- goto found_mapped_buffer;
- }
-
- bh = bh->b_this_page;
- end++;
- } while (bh != head);
-
- /* No mapped buffer in the range found in this page,
- * We need to look up next page.
- */
- if (index >= ret) {
- /* There is no page left, but we need to limit
- * newex->ec_len.
- */
- newex->ec_len = end - newex->ec_block;
- goto out;
- }
- goto next_page;
- } else {
- /*Find contiguous delayed buffers. */
- if (ret > 0 && pages[0]->index == last_offset)
- head = page_buffers(pages[0]);
- bh = head;
- index = 1;
- start_index = 0;
- }
-
-found_mapped_buffer:
- if (bh != NULL && buffer_delay(bh)) {
- /* 1st or contiguous delayed buffer found. */
- if (!(flags & FIEMAP_EXTENT_DELALLOC)) {
- /*
- * 1st delayed buffer found, record
- * the start of extent.
- */
- flags |= FIEMAP_EXTENT_DELALLOC;
- newex->ec_block = end;
- logical = (__u64)end << blksize_bits;
- }
- /* Find contiguous delayed buffers. */
- do {
- if (!buffer_delay(bh))
- goto found_delayed_extent;
- bh = bh->b_this_page;
- end++;
- } while (bh != head);
-
- for (; index < ret; index++) {
- if (!page_has_buffers(pages[index])) {
- bh = NULL;
- break;
- }
- head = page_buffers(pages[index]);
- if (!head) {
- bh = NULL;
- break;
- }
-
- if (pages[index]->index !=
- pages[start_index]->index + index
- - start_index) {
- /* Blocks are not contiguous. */
- bh = NULL;
- break;
- }
- bh = head;
- do {
- if (!buffer_delay(bh))
- /* Delayed-extent ends. */
- goto found_delayed_extent;
- bh = bh->b_this_page;
- end++;
- } while (bh != head);
- }
- } else if (!(flags & FIEMAP_EXTENT_DELALLOC))
- /* a hole found. */
- goto out;
+ if (es.es_len == 0)
+ /* A hole found. */
+ return 0;
-found_delayed_extent:
- newex->ec_len = min(end - newex->ec_block,
- (ext4_lblk_t)EXT_INIT_MAX_LEN);
- if (ret == nr_pages && bh != NULL &&
- newex->ec_len < EXT_INIT_MAX_LEN &&
- buffer_delay(bh)) {
- /* Have not collected an extent and continue. */
- for (index = 0; index < ret; index++)
- page_cache_release(pages[index]);
- goto repeat;
+ if (es.es_lblk > newes->es_lblk) {
+ /* A hole found. */
+ newes->es_len = min(es.es_lblk - newes->es_lblk,
+ newes->es_len);
+ return 0;
}
- for (index = 0; index < ret; index++)
- page_cache_release(pages[index]);
- kfree(pages);
+ newes->es_len = es.es_lblk + es.es_len - newes->es_lblk;
}
- physical = (__u64)newex->ec_start << blksize_bits;
- length = (__u64)newex->ec_len << blksize_bits;
-
- if (ex && ext4_ext_is_uninitialized(ex))
- flags |= FIEMAP_EXTENT_UNWRITTEN;
-
- if (next == EXT_MAX_BLOCKS)
- flags |= FIEMAP_EXTENT_LAST;
+ block = newes->es_lblk + newes->es_len;
+ ext4_es_find_delayed_extent_range(inode, block, EXT_MAX_BLOCKS, &es);
+ if (es.es_len == 0)
+ next_del = EXT_MAX_BLOCKS;
+ else
+ next_del = es.es_lblk;
- ret = fiemap_fill_next_extent(fieinfo, logical, physical,
- length, flags);
- if (ret < 0)
- return ret;
- if (ret == 1)
- return EXT_BREAK;
- return EXT_CONTINUE;
+ return next_del;
}
/* fiemap flags we can handle specified here */
#define EXT4_FIEMAP_FLAGS (FIEMAP_FLAG_SYNC|FIEMAP_FLAG_XATTR)
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->f_path.dentry->d_inode;
- struct super_block *sb = inode->i_sb;
- struct ext4_ext_cache cache_ex;
- ext4_lblk_t first_block, last_block, num_blocks, iblock, max_blocks;
- struct address_space *mapping = inode->i_mapping;
- struct ext4_map_blocks map;
- handle_t *handle;
- loff_t first_page, last_page, page_len;
- loff_t first_page_offset, last_page_offset;
- int ret, credits, blocks_released, err = 0;
-
- /* No need to punch hole beyond i_size */
- if (offset >= inode->i_size)
- return 0;
-
- /*
- * 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_block = (offset + sb->s_blocksize - 1) >>
- EXT4_BLOCK_SIZE_BITS(sb);
- last_block = (offset + length) >> EXT4_BLOCK_SIZE_BITS(sb);
-
- 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;
-
- /*
- * 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;
- }
-
- /* Now release the pages */
- if (last_page_offset > first_page_offset) {
- truncate_inode_pages_range(mapping, first_page_offset,
- last_page_offset-1);
- }
-
- /* finish any pending end_io work */
- ext4_flush_completed_IO(inode);
-
- credits = ext4_writepage_trans_blocks(inode);
- handle = ext4_journal_start(inode, credits);
- if (IS_ERR(handle))
- return PTR_ERR(handle);
-
- err = ext4_orphan_add(handle, inode);
- if (err)
- goto out;
-
- /*
- * 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;
- }
- }
-
- /* If there are no blocks to remove, return now */
- if (first_block >= last_block)
- goto out;
-
- down_write(&EXT4_I(inode)->i_data_sem);
- ext4_ext_invalidate_cache(inode);
- ext4_discard_preallocations(inode);
-
- /*
- * Loop over all the blocks and identify blocks
- * that need to be punched out
- */
- iblock = first_block;
- blocks_released = 0;
- while (iblock < last_block) {
- max_blocks = last_block - iblock;
- num_blocks = 1;
- memset(&map, 0, sizeof(map));
- map.m_lblk = iblock;
- map.m_len = max_blocks;
- ret = ext4_ext_map_blocks(handle, inode, &map,
- EXT4_GET_BLOCKS_PUNCH_OUT_EXT);
-
- if (ret > 0) {
- blocks_released += ret;
- num_blocks = ret;
- } else if (ret == 0) {
- /*
- * If map blocks could not find the block,
- * then it is in a hole. If the hole was
- * not already cached, then map blocks should
- * put it in the cache. So we can get the hole
- * out of the cache
- */
- memset(&cache_ex, 0, sizeof(cache_ex));
- if ((ext4_ext_check_cache(inode, iblock, &cache_ex)) &&
- !cache_ex.ec_start) {
-
- /* The hole is cached */
- num_blocks = cache_ex.ec_block +
- cache_ex.ec_len - iblock;
-
- } else {
- /* The block could not be identified */
- err = -EIO;
- break;
- }
- } else {
- /* Map blocks error */
- err = ret;
- break;
- }
-
- if (num_blocks == 0) {
- /* This condition should never happen */
- ext_debug("Block lookup failed");
- err = -EIO;
- break;
- }
-
- iblock += num_blocks;
- }
-
- if (blocks_released > 0) {
- ext4_ext_invalidate_cache(inode);
- ext4_discard_preallocations(inode);
- }
-
- if (IS_SYNC(inode))
- ext4_handle_sync(handle);
-
- up_write(&EXT4_I(inode)->i_data_sem);
-
-out:
- 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);
- return err;
-}
int ext4_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
__u64 start, __u64 len)
{
ext4_lblk_t start_blk;
int error = 0;
+ if (ext4_has_inline_data(inode)) {
+ int has_inline = 1;
+
+ error = ext4_inline_data_fiemap(inode, fieinfo, &has_inline);
+
+ if (has_inline)
+ return error;
+ }
+
/* fallback to generic here if not in extents fmt */
if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)))
return generic_block_fiemap(inode, fieinfo, start, len,
len_blks = ((ext4_lblk_t) last_blk) - start_blk + 1;
/*
- * Walk the extent tree gathering extent information.
- * ext4_ext_fiemap_cb will push extents back to user.
+ * Walk the extent tree gathering extent information
+ * and pushing extents back to the user.
*/
- error = ext4_ext_walk_space(inode, start_blk, len_blks,
- ext4_ext_fiemap_cb, fieinfo);
+ error = ext4_fill_fiemap_extents(inode, start_blk,
+ len_blks, fieinfo);
}
return error;