#include <linux/module.h>
#include <linux/fs.h>
#include <linux/time.h>
-#include <linux/ext4_jbd2.h>
-#include <linux/jbd.h>
+#include <linux/jbd2.h>
#include <linux/highuid.h>
#include <linux/pagemap.h>
#include <linux/quotaops.h>
#include <linux/string.h>
#include <linux/slab.h>
-#include <linux/ext4_fs_extents.h>
+#include <linux/falloc.h>
#include <asm/uaccess.h>
+#include "ext4_jbd2.h"
+#include "ext4_extents.h"
/*
{
ext4_fsblk_t block;
- block = le32_to_cpu(ex->ee_start);
+ block = le32_to_cpu(ex->ee_start_lo);
block |= ((ext4_fsblk_t) le16_to_cpu(ex->ee_start_hi) << 31) << 1;
return block;
}
* idx_pblock:
* combine low and high parts of a leaf physical block number into ext4_fsblk_t
*/
-static ext4_fsblk_t idx_pblock(struct ext4_extent_idx *ix)
+ext4_fsblk_t idx_pblock(struct ext4_extent_idx *ix)
{
ext4_fsblk_t block;
- block = le32_to_cpu(ix->ei_leaf);
+ block = le32_to_cpu(ix->ei_leaf_lo);
block |= ((ext4_fsblk_t) le16_to_cpu(ix->ei_leaf_hi) << 31) << 1;
return block;
}
* stores a large physical block number into an extent struct,
* breaking it into parts
*/
-static void ext4_ext_store_pblock(struct ext4_extent *ex, ext4_fsblk_t pb)
+void ext4_ext_store_pblock(struct ext4_extent *ex, ext4_fsblk_t pb)
{
- ex->ee_start = cpu_to_le32((unsigned long) (pb & 0xffffffff));
+ ex->ee_start_lo = cpu_to_le32((unsigned long) (pb & 0xffffffff));
ex->ee_start_hi = cpu_to_le16((unsigned long) ((pb >> 31) >> 1) & 0xffff);
}
*/
static void ext4_idx_store_pblock(struct ext4_extent_idx *ix, ext4_fsblk_t pb)
{
- ix->ei_leaf = cpu_to_le32((unsigned long) (pb & 0xffffffff));
+ ix->ei_leaf_lo = cpu_to_le32((unsigned long) (pb & 0xffffffff));
ix->ei_leaf_hi = cpu_to_le16((unsigned long) ((pb >> 31) >> 1) & 0xffff);
}
-static int ext4_ext_check_header(const char *function, struct inode *inode,
- struct ext4_extent_header *eh)
-{
- const char *error_msg = NULL;
-
- if (unlikely(eh->eh_magic != EXT4_EXT_MAGIC)) {
- error_msg = "invalid magic";
- goto corrupted;
- }
- if (unlikely(eh->eh_max == 0)) {
- error_msg = "invalid eh_max";
- goto corrupted;
- }
- if (unlikely(le16_to_cpu(eh->eh_entries) > le16_to_cpu(eh->eh_max))) {
- error_msg = "invalid eh_entries";
- goto corrupted;
- }
- return 0;
-
-corrupted:
- ext4_error(inode->i_sb, function,
- "bad header in inode #%lu: %s - magic %x, "
- "entries %u, max %u, depth %u",
- inode->i_ino, error_msg, le16_to_cpu(eh->eh_magic),
- le16_to_cpu(eh->eh_entries), le16_to_cpu(eh->eh_max),
- le16_to_cpu(eh->eh_depth));
-
- return -EIO;
-}
-
static handle_t *ext4_ext_journal_restart(handle_t *handle, int needed)
{
int err;
static ext4_fsblk_t ext4_ext_find_goal(struct inode *inode,
struct ext4_ext_path *path,
- ext4_fsblk_t block)
+ ext4_lblk_t block)
{
struct ext4_inode_info *ei = EXT4_I(inode);
ext4_fsblk_t bg_start;
+ ext4_fsblk_t last_block;
ext4_grpblk_t colour;
int depth;
/* OK. use inode's group */
bg_start = (ei->i_block_group * EXT4_BLOCKS_PER_GROUP(inode->i_sb)) +
le32_to_cpu(EXT4_SB(inode->i_sb)->s_es->s_first_data_block);
- colour = (current->pid % 16) *
+ last_block = ext4_blocks_count(EXT4_SB(inode->i_sb)->s_es) - 1;
+
+ if (bg_start + EXT4_BLOCKS_PER_GROUP(inode->i_sb) <= last_block)
+ colour = (current->pid % 16) *
(EXT4_BLOCKS_PER_GROUP(inode->i_sb) / 16);
+ else
+ colour = (current->pid % 16) * ((last_block - bg_start) / 16);
return bg_start + colour + block;
}
return size;
}
+static int
+ext4_ext_max_entries(struct inode *inode, int depth)
+{
+ int max;
+
+ if (depth == ext_depth(inode)) {
+ if (depth == 0)
+ max = ext4_ext_space_root(inode);
+ else
+ max = ext4_ext_space_root_idx(inode);
+ } else {
+ if (depth == 0)
+ max = ext4_ext_space_block(inode);
+ else
+ max = ext4_ext_space_block_idx(inode);
+ }
+
+ return max;
+}
+
+static int __ext4_ext_check_header(const char *function, struct inode *inode,
+ struct ext4_extent_header *eh,
+ int depth)
+{
+ const char *error_msg;
+ int max = 0;
+
+ if (unlikely(eh->eh_magic != EXT4_EXT_MAGIC)) {
+ error_msg = "invalid magic";
+ goto corrupted;
+ }
+ if (unlikely(le16_to_cpu(eh->eh_depth) != depth)) {
+ error_msg = "unexpected eh_depth";
+ goto corrupted;
+ }
+ if (unlikely(eh->eh_max == 0)) {
+ error_msg = "invalid eh_max";
+ goto corrupted;
+ }
+ max = ext4_ext_max_entries(inode, depth);
+ if (unlikely(le16_to_cpu(eh->eh_max) > max)) {
+ error_msg = "too large eh_max";
+ goto corrupted;
+ }
+ if (unlikely(le16_to_cpu(eh->eh_entries) > le16_to_cpu(eh->eh_max))) {
+ error_msg = "invalid eh_entries";
+ goto corrupted;
+ }
+ return 0;
+
+corrupted:
+ ext4_error(inode->i_sb, function,
+ "bad header in inode #%lu: %s - magic %x, "
+ "entries %u, max %u(%u), depth %u(%u)",
+ inode->i_ino, error_msg, le16_to_cpu(eh->eh_magic),
+ le16_to_cpu(eh->eh_entries), le16_to_cpu(eh->eh_max),
+ max, le16_to_cpu(eh->eh_depth), depth);
+
+ return -EIO;
+}
+
+#define ext4_ext_check_header(inode, eh, depth) \
+ __ext4_ext_check_header(__func__, inode, eh, depth)
+
#ifdef EXT_DEBUG
static void ext4_ext_show_path(struct inode *inode, struct ext4_ext_path *path)
{
} else if (path->p_ext) {
ext_debug(" %d:%d:%llu ",
le32_to_cpu(path->p_ext->ee_block),
- le16_to_cpu(path->p_ext->ee_len),
+ ext4_ext_get_actual_len(path->p_ext),
ext_pblock(path->p_ext));
} else
ext_debug(" []");
for (i = 0; i < le16_to_cpu(eh->eh_entries); i++, ex++) {
ext_debug("%d:%d:%llu ", le32_to_cpu(ex->ee_block),
- le16_to_cpu(ex->ee_len), ext_pblock(ex));
+ ext4_ext_get_actual_len(ex), ext_pblock(ex));
}
ext_debug("\n");
}
#define ext4_ext_show_leaf(inode,path)
#endif
-static void ext4_ext_drop_refs(struct ext4_ext_path *path)
+void ext4_ext_drop_refs(struct ext4_ext_path *path)
{
int depth = path->p_depth;
int i;
/*
* ext4_ext_binsearch_idx:
* binary search for the closest index of the given block
+ * the header must be checked before calling this
*/
static void
-ext4_ext_binsearch_idx(struct inode *inode, struct ext4_ext_path *path, int block)
+ext4_ext_binsearch_idx(struct inode *inode,
+ struct ext4_ext_path *path, ext4_lblk_t block)
{
struct ext4_extent_header *eh = path->p_hdr;
struct ext4_extent_idx *r, *l, *m;
- BUG_ON(eh->eh_magic != EXT4_EXT_MAGIC);
- BUG_ON(le16_to_cpu(eh->eh_entries) > le16_to_cpu(eh->eh_max));
- BUG_ON(le16_to_cpu(eh->eh_entries) <= 0);
- ext_debug("binsearch for %d(idx): ", block);
+ ext_debug("binsearch for %u(idx): ", block);
l = EXT_FIRST_INDEX(eh) + 1;
- r = EXT_FIRST_INDEX(eh) + le16_to_cpu(eh->eh_entries) - 1;
+ r = EXT_LAST_INDEX(eh);
while (l <= r) {
m = l + (r - l) / 2;
if (block < le32_to_cpu(m->ei_block))
r = m - 1;
else
l = m + 1;
- ext_debug("%p(%u):%p(%u):%p(%u) ", l, l->ei_block,
- m, m->ei_block, r, r->ei_block);
+ ext_debug("%p(%u):%p(%u):%p(%u) ", l, le32_to_cpu(l->ei_block),
+ m, le32_to_cpu(m->ei_block),
+ r, le32_to_cpu(r->ei_block));
}
path->p_idx = l - 1;
ext_debug(" -> %d->%lld ", le32_to_cpu(path->p_idx->ei_block),
- idx_block(path->p_idx));
+ idx_pblock(path->p_idx));
#ifdef CHECK_BINSEARCH
{
/*
* ext4_ext_binsearch:
* binary search for closest extent of the given block
+ * the header must be checked before calling this
*/
static void
-ext4_ext_binsearch(struct inode *inode, struct ext4_ext_path *path, int block)
+ext4_ext_binsearch(struct inode *inode,
+ struct ext4_ext_path *path, ext4_lblk_t block)
{
struct ext4_extent_header *eh = path->p_hdr;
struct ext4_extent *r, *l, *m;
- BUG_ON(eh->eh_magic != EXT4_EXT_MAGIC);
- BUG_ON(le16_to_cpu(eh->eh_entries) > le16_to_cpu(eh->eh_max));
-
if (eh->eh_entries == 0) {
/*
* this leaf is empty:
return;
}
- ext_debug("binsearch for %d: ", block);
+ ext_debug("binsearch for %u: ", block);
l = EXT_FIRST_EXTENT(eh) + 1;
- r = EXT_FIRST_EXTENT(eh) + le16_to_cpu(eh->eh_entries) - 1;
+ r = EXT_LAST_EXTENT(eh);
while (l <= r) {
m = l + (r - l) / 2;
r = m - 1;
else
l = m + 1;
- ext_debug("%p(%u):%p(%u):%p(%u) ", l, l->ee_block,
- m, m->ee_block, r, r->ee_block);
+ ext_debug("%p(%u):%p(%u):%p(%u) ", l, le32_to_cpu(l->ee_block),
+ m, le32_to_cpu(m->ee_block),
+ r, le32_to_cpu(r->ee_block));
}
path->p_ext = l - 1;
ext_debug(" -> %d:%llu:%d ",
le32_to_cpu(path->p_ext->ee_block),
ext_pblock(path->p_ext),
- le16_to_cpu(path->p_ext->ee_len));
+ ext4_ext_get_actual_len(path->p_ext));
#ifdef CHECK_BINSEARCH
{
}
struct ext4_ext_path *
-ext4_ext_find_extent(struct inode *inode, int block, struct ext4_ext_path *path)
+ext4_ext_find_extent(struct inode *inode, ext4_lblk_t block,
+ struct ext4_ext_path *path)
{
struct ext4_extent_header *eh;
struct buffer_head *bh;
short int depth, i, ppos = 0, alloc = 0;
eh = ext_inode_hdr(inode);
- BUG_ON(eh == NULL);
- if (ext4_ext_check_header(__FUNCTION__, inode, eh))
+ depth = ext_depth(inode);
+ if (ext4_ext_check_header(inode, eh, depth))
return ERR_PTR(-EIO);
- i = depth = ext_depth(inode);
/* account possible depth increase */
if (!path) {
}
path[0].p_hdr = eh;
+ i = depth;
/* walk through the tree */
while (i) {
ext_debug("depth %d: num %d, max %d\n",
ppos, le16_to_cpu(eh->eh_entries), le16_to_cpu(eh->eh_max));
+
ext4_ext_binsearch_idx(inode, path + ppos, block);
path[ppos].p_block = idx_pblock(path[ppos].p_idx);
path[ppos].p_depth = i;
path[ppos].p_hdr = eh;
i--;
- if (ext4_ext_check_header(__FUNCTION__, inode, eh))
+ if (ext4_ext_check_header(inode, eh, i))
goto err;
}
path[ppos].p_ext = NULL;
path[ppos].p_idx = NULL;
- if (ext4_ext_check_header(__FUNCTION__, inode, eh))
- goto err;
-
/* find extent */
ext4_ext_binsearch(inode, path + ppos, block);
if (curp->p_idx != EXT_LAST_INDEX(curp->p_hdr)) {
len = (len - 1) * sizeof(struct ext4_extent_idx);
len = len < 0 ? 0 : len;
- ext_debug("insert new index %d after: %d. "
+ ext_debug("insert new index %d after: %llu. "
"move %d from 0x%p to 0x%p\n",
logical, ptr, len,
(curp->p_idx + 1), (curp->p_idx + 2));
/* insert before */
len = len * sizeof(struct ext4_extent_idx);
len = len < 0 ? 0 : len;
- ext_debug("insert new index %d before: %d. "
+ ext_debug("insert new index %d before: %llu. "
"move %d from 0x%p to 0x%p\n",
logical, ptr, len,
curp->p_idx, (curp->p_idx + 1));
ix->ei_block = cpu_to_le32(logical);
ext4_idx_store_pblock(ix, ptr);
- curp->p_hdr->eh_entries = cpu_to_le16(le16_to_cpu(curp->p_hdr->eh_entries)+1);
+ le16_add_cpu(&curp->p_hdr->eh_entries, 1);
BUG_ON(le16_to_cpu(curp->p_hdr->eh_entries)
> le16_to_cpu(curp->p_hdr->eh_max));
ext_debug("move %d:%llu:%d in new leaf %llu\n",
le32_to_cpu(path[depth].p_ext->ee_block),
ext_pblock(path[depth].p_ext),
- le16_to_cpu(path[depth].p_ext->ee_len),
+ ext4_ext_get_actual_len(path[depth].p_ext),
newblock);
/*memmove(ex++, path[depth].p_ext++,
sizeof(struct ext4_extent));
}
if (m) {
memmove(ex, path[depth].p_ext-m, sizeof(struct ext4_extent)*m);
- neh->eh_entries = cpu_to_le16(le16_to_cpu(neh->eh_entries)+m);
+ le16_add_cpu(&neh->eh_entries, m);
}
set_buffer_uptodate(bh);
err = ext4_ext_get_access(handle, inode, path + depth);
if (err)
goto cleanup;
- path[depth].p_hdr->eh_entries =
- cpu_to_le16(le16_to_cpu(path[depth].p_hdr->eh_entries)-m);
+ le16_add_cpu(&path[depth].p_hdr->eh_entries, -m);
err = ext4_ext_dirty(handle, inode, path + depth);
if (err)
goto cleanup;
while (k--) {
oldblock = newblock;
newblock = ablocks[--a];
- bh = sb_getblk(inode->i_sb, (ext4_fsblk_t)newblock);
+ bh = sb_getblk(inode->i_sb, newblock);
if (!bh) {
err = -EIO;
goto cleanup;
fidx->ei_block = border;
ext4_idx_store_pblock(fidx, oldblock);
- ext_debug("int.index at %d (block %llu): %lu -> %llu\n", i,
- newblock, (unsigned long) le32_to_cpu(border),
- oldblock);
+ ext_debug("int.index at %d (block %llu): %u -> %llu\n",
+ i, newblock, le32_to_cpu(border), oldblock);
/* copy indexes */
m = 0;
path[i].p_idx++;
BUG_ON(EXT_MAX_INDEX(path[i].p_hdr) !=
EXT_LAST_INDEX(path[i].p_hdr));
while (path[i].p_idx <= EXT_MAX_INDEX(path[i].p_hdr)) {
- ext_debug("%d: move %d:%d in new index %llu\n", i,
+ ext_debug("%d: move %d:%llu in new index %llu\n", i,
le32_to_cpu(path[i].p_idx->ei_block),
idx_pblock(path[i].p_idx),
newblock);
if (m) {
memmove(++fidx, path[i].p_idx - m,
sizeof(struct ext4_extent_idx) * m);
- neh->eh_entries =
- cpu_to_le16(le16_to_cpu(neh->eh_entries) + m);
+ le16_add_cpu(&neh->eh_entries, m);
}
set_buffer_uptodate(bh);
unlock_buffer(bh);
err = ext4_ext_get_access(handle, inode, path + i);
if (err)
goto cleanup;
- path[i].p_hdr->eh_entries = cpu_to_le16(le16_to_cpu(path[i].p_hdr->eh_entries)-m);
+ le16_add_cpu(&path[i].p_hdr->eh_entries, -m);
err = ext4_ext_dirty(handle, inode, path + i);
if (err)
goto cleanup;
for (i = 0; i < depth; i++) {
if (!ablocks[i])
continue;
- ext4_free_blocks(handle, inode, ablocks[i], 1);
+ ext4_free_blocks(handle, inode, ablocks[i], 1, 1);
}
}
kfree(ablocks);
curp->p_hdr->eh_max = cpu_to_le16(ext4_ext_space_root_idx(inode));
curp->p_hdr->eh_entries = cpu_to_le16(1);
curp->p_idx = EXT_FIRST_INDEX(curp->p_hdr);
- /* FIXME: it works, but actually path[0] can be index */
- curp->p_idx->ei_block = EXT_FIRST_EXTENT(path[0].p_hdr)->ee_block;
+
+ if (path[0].p_hdr->eh_depth)
+ curp->p_idx->ei_block =
+ EXT_FIRST_INDEX(path[0].p_hdr)->ei_block;
+ else
+ curp->p_idx->ei_block =
+ EXT_FIRST_EXTENT(path[0].p_hdr)->ee_block;
ext4_idx_store_pblock(curp->p_idx, newblock);
neh = ext_inode_hdr(inode);
/* refill path */
ext4_ext_drop_refs(path);
path = ext4_ext_find_extent(inode,
- le32_to_cpu(newext->ee_block),
- path);
+ (ext4_lblk_t)le32_to_cpu(newext->ee_block),
+ path);
if (IS_ERR(path))
err = PTR_ERR(path);
} else {
/* refill path */
ext4_ext_drop_refs(path);
path = ext4_ext_find_extent(inode,
- le32_to_cpu(newext->ee_block),
- path);
+ (ext4_lblk_t)le32_to_cpu(newext->ee_block),
+ path);
if (IS_ERR(path)) {
err = PTR_ERR(path);
goto out;
return err;
}
+/*
+ * search the closest allocated block to the left for *logical
+ * and returns it at @logical + it's physical address at @phys
+ * if *logical is the smallest allocated block, the function
+ * returns 0 at @phys
+ * return value contains 0 (success) or error code
+ */
+int
+ext4_ext_search_left(struct inode *inode, struct ext4_ext_path *path,
+ ext4_lblk_t *logical, ext4_fsblk_t *phys)
+{
+ struct ext4_extent_idx *ix;
+ struct ext4_extent *ex;
+ int depth, ee_len;
+
+ BUG_ON(path == NULL);
+ depth = path->p_depth;
+ *phys = 0;
+
+ if (depth == 0 && path->p_ext == NULL)
+ return 0;
+
+ /* usually extent in the path covers blocks smaller
+ * then *logical, but it can be that extent is the
+ * first one in the file */
+
+ ex = path[depth].p_ext;
+ ee_len = ext4_ext_get_actual_len(ex);
+ if (*logical < le32_to_cpu(ex->ee_block)) {
+ BUG_ON(EXT_FIRST_EXTENT(path[depth].p_hdr) != ex);
+ while (--depth >= 0) {
+ ix = path[depth].p_idx;
+ BUG_ON(ix != EXT_FIRST_INDEX(path[depth].p_hdr));
+ }
+ return 0;
+ }
+
+ BUG_ON(*logical < (le32_to_cpu(ex->ee_block) + ee_len));
+
+ *logical = le32_to_cpu(ex->ee_block) + ee_len - 1;
+ *phys = ext_pblock(ex) + ee_len - 1;
+ return 0;
+}
+
+/*
+ * search the closest allocated block to the right for *logical
+ * and returns it at @logical + it's physical address at @phys
+ * if *logical is the smallest allocated block, the function
+ * returns 0 at @phys
+ * return value contains 0 (success) or error code
+ */
+int
+ext4_ext_search_right(struct inode *inode, struct ext4_ext_path *path,
+ ext4_lblk_t *logical, ext4_fsblk_t *phys)
+{
+ struct buffer_head *bh = NULL;
+ struct ext4_extent_header *eh;
+ struct ext4_extent_idx *ix;
+ struct ext4_extent *ex;
+ ext4_fsblk_t block;
+ int depth, ee_len;
+
+ BUG_ON(path == NULL);
+ depth = path->p_depth;
+ *phys = 0;
+
+ if (depth == 0 && path->p_ext == NULL)
+ return 0;
+
+ /* usually extent in the path covers blocks smaller
+ * then *logical, but it can be that extent is the
+ * first one in the file */
+
+ ex = path[depth].p_ext;
+ ee_len = ext4_ext_get_actual_len(ex);
+ if (*logical < le32_to_cpu(ex->ee_block)) {
+ BUG_ON(EXT_FIRST_EXTENT(path[depth].p_hdr) != ex);
+ while (--depth >= 0) {
+ ix = path[depth].p_idx;
+ BUG_ON(ix != EXT_FIRST_INDEX(path[depth].p_hdr));
+ }
+ *logical = le32_to_cpu(ex->ee_block);
+ *phys = ext_pblock(ex);
+ return 0;
+ }
+
+ BUG_ON(*logical < (le32_to_cpu(ex->ee_block) + ee_len));
+
+ if (ex != EXT_LAST_EXTENT(path[depth].p_hdr)) {
+ /* next allocated block in this leaf */
+ ex++;
+ *logical = le32_to_cpu(ex->ee_block);
+ *phys = ext_pblock(ex);
+ return 0;
+ }
+
+ /* go up and search for index to the right */
+ while (--depth >= 0) {
+ ix = path[depth].p_idx;
+ if (ix != EXT_LAST_INDEX(path[depth].p_hdr))
+ break;
+ }
+
+ if (depth < 0) {
+ /* we've gone up to the root and
+ * found no index to the right */
+ return 0;
+ }
+
+ /* we've found index to the right, let's
+ * follow it and find the closest allocated
+ * block to the right */
+ ix++;
+ block = idx_pblock(ix);
+ while (++depth < path->p_depth) {
+ bh = sb_bread(inode->i_sb, block);
+ if (bh == NULL)
+ return -EIO;
+ eh = ext_block_hdr(bh);
+ if (ext4_ext_check_header(inode, eh, depth)) {
+ put_bh(bh);
+ return -EIO;
+ }
+ ix = EXT_FIRST_INDEX(eh);
+ block = idx_pblock(ix);
+ put_bh(bh);
+ }
+
+ bh = sb_bread(inode->i_sb, block);
+ if (bh == NULL)
+ return -EIO;
+ eh = ext_block_hdr(bh);
+ if (ext4_ext_check_header(inode, eh, path->p_depth - depth)) {
+ put_bh(bh);
+ return -EIO;
+ }
+ ex = EXT_FIRST_EXTENT(eh);
+ *logical = le32_to_cpu(ex->ee_block);
+ *phys = ext_pblock(ex);
+ put_bh(bh);
+ return 0;
+
+}
+
/*
* ext4_ext_next_allocated_block:
* returns allocated block in subsequent extent or EXT_MAX_BLOCK.
* allocated block. Thus, index entries have to be consistent
* with leaves.
*/
-static unsigned long
+static ext4_lblk_t
ext4_ext_next_allocated_block(struct ext4_ext_path *path)
{
int depth;
* ext4_ext_next_leaf_block:
* returns first allocated block from next leaf or EXT_MAX_BLOCK
*/
-static unsigned ext4_ext_next_leaf_block(struct inode *inode,
+static ext4_lblk_t ext4_ext_next_leaf_block(struct inode *inode,
struct ext4_ext_path *path)
{
int depth;
while (depth >= 0) {
if (path[depth].p_idx !=
EXT_LAST_INDEX(path[depth].p_hdr))
- return le32_to_cpu(path[depth].p_idx[1].ei_block);
+ return (ext4_lblk_t)
+ le32_to_cpu(path[depth].p_idx[1].ei_block);
depth--;
}
* then we have to correct all indexes above.
* TODO: do we need to correct tree in all cases?
*/
-int ext4_ext_correct_indexes(handle_t *handle, struct inode *inode,
+static int ext4_ext_correct_indexes(handle_t *handle, struct inode *inode,
struct ext4_ext_path *path)
{
struct ext4_extent_header *eh;
ext4_can_extents_be_merged(struct inode *inode, struct ext4_extent *ex1,
struct ext4_extent *ex2)
{
- if (le32_to_cpu(ex1->ee_block) + le16_to_cpu(ex1->ee_len) !=
+ unsigned short ext1_ee_len, ext2_ee_len, max_len;
+
+ /*
+ * Make sure that either both extents are uninitialized, or
+ * both are _not_.
+ */
+ if (ext4_ext_is_uninitialized(ex1) ^ ext4_ext_is_uninitialized(ex2))
+ return 0;
+
+ if (ext4_ext_is_uninitialized(ex1))
+ max_len = EXT_UNINIT_MAX_LEN;
+ else
+ max_len = EXT_INIT_MAX_LEN;
+
+ ext1_ee_len = ext4_ext_get_actual_len(ex1);
+ ext2_ee_len = ext4_ext_get_actual_len(ex2);
+
+ if (le32_to_cpu(ex1->ee_block) + ext1_ee_len !=
le32_to_cpu(ex2->ee_block))
return 0;
* as an RO_COMPAT feature, refuse to merge to extents if
* this can result in the top bit of ee_len being set.
*/
- if (le16_to_cpu(ex1->ee_len) + le16_to_cpu(ex2->ee_len) > EXT_MAX_LEN)
+ if (ext1_ee_len + ext2_ee_len > max_len)
return 0;
#ifdef AGGRESSIVE_TEST
- if (le16_to_cpu(ex1->ee_len) >= 4)
+ if (ext1_ee_len >= 4)
return 0;
#endif
- if (ext_pblock(ex1) + le16_to_cpu(ex1->ee_len) == ext_pblock(ex2))
+ if (ext_pblock(ex1) + ext1_ee_len == ext_pblock(ex2))
return 1;
return 0;
}
+/*
+ * This function tries to merge the "ex" extent to the next extent in the tree.
+ * It always tries to merge towards right. If you want to merge towards
+ * left, pass "ex - 1" as argument instead of "ex".
+ * Returns 0 if the extents (ex and ex+1) were _not_ merged and returns
+ * 1 if they got merged.
+ */
+int ext4_ext_try_to_merge(struct inode *inode,
+ struct ext4_ext_path *path,
+ struct ext4_extent *ex)
+{
+ struct ext4_extent_header *eh;
+ unsigned int depth, len;
+ int merge_done = 0;
+ int uninitialized = 0;
+
+ depth = ext_depth(inode);
+ BUG_ON(path[depth].p_hdr == NULL);
+ eh = path[depth].p_hdr;
+
+ while (ex < EXT_LAST_EXTENT(eh)) {
+ if (!ext4_can_extents_be_merged(inode, ex, ex + 1))
+ break;
+ /* merge with next extent! */
+ 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(ex + 1));
+ if (uninitialized)
+ ext4_ext_mark_uninitialized(ex);
+
+ if (ex + 1 < EXT_LAST_EXTENT(eh)) {
+ len = (EXT_LAST_EXTENT(eh) - ex - 1)
+ * sizeof(struct ext4_extent);
+ memmove(ex + 1, ex + 2, len);
+ }
+ le16_add_cpu(&eh->eh_entries, -1);
+ merge_done = 1;
+ WARN_ON(eh->eh_entries == 0);
+ if (!eh->eh_entries)
+ ext4_error(inode->i_sb, "ext4_ext_try_to_merge",
+ "inode#%lu, eh->eh_entries = 0!", inode->i_ino);
+ }
+
+ return merge_done;
+}
+
/*
* check if a portion of the "newext" extent overlaps with an
* existing extent.
struct ext4_extent *newext,
struct ext4_ext_path *path)
{
- unsigned long b1, b2;
+ ext4_lblk_t b1, b2;
unsigned int depth, len1;
unsigned int ret = 0;
b1 = le32_to_cpu(newext->ee_block);
- len1 = le16_to_cpu(newext->ee_len);
+ len1 = ext4_ext_get_actual_len(newext);
depth = ext_depth(inode);
if (!path[depth].p_ext)
goto out;
goto out;
}
- /* check for wrap through zero */
+ /* check for wrap through zero on extent logical start block*/
if (b1 + len1 < b1) {
len1 = EXT_MAX_BLOCK - b1;
newext->ee_len = cpu_to_le16(len1);
struct ext4_extent *ex, *fex;
struct ext4_extent *nearex; /* nearest extent */
struct ext4_ext_path *npath = NULL;
- int depth, len, err, next;
+ int depth, len, err;
+ ext4_lblk_t next;
+ unsigned uninitialized = 0;
- BUG_ON(newext->ee_len == 0);
+ BUG_ON(ext4_ext_get_actual_len(newext) == 0);
depth = ext_depth(inode);
ex = path[depth].p_ext;
BUG_ON(path[depth].p_hdr == NULL);
/* try to insert block into found extent and return */
if (ex && ext4_can_extents_be_merged(inode, ex, newext)) {
ext_debug("append %d block to %d:%d (from %llu)\n",
- le16_to_cpu(newext->ee_len),
+ ext4_ext_get_actual_len(newext),
le32_to_cpu(ex->ee_block),
- le16_to_cpu(ex->ee_len), ext_pblock(ex));
+ ext4_ext_get_actual_len(ex), ext_pblock(ex));
err = ext4_ext_get_access(handle, inode, path + depth);
if (err)
return err;
- ex->ee_len = cpu_to_le16(le16_to_cpu(ex->ee_len)
- + le16_to_cpu(newext->ee_len));
+
+ /*
+ * 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;
ext_debug("first extent in the leaf: %d:%llu:%d\n",
le32_to_cpu(newext->ee_block),
ext_pblock(newext),
- le16_to_cpu(newext->ee_len));
+ ext4_ext_get_actual_len(newext));
path[depth].p_ext = EXT_FIRST_EXTENT(eh);
} else if (le32_to_cpu(newext->ee_block)
> le32_to_cpu(nearex->ee_block)) {
"move %d from 0x%p to 0x%p\n",
le32_to_cpu(newext->ee_block),
ext_pblock(newext),
- le16_to_cpu(newext->ee_len),
+ ext4_ext_get_actual_len(newext),
nearex, len, nearex + 1, nearex + 2);
memmove(nearex + 2, nearex + 1, len);
}
"move %d from 0x%p to 0x%p\n",
le32_to_cpu(newext->ee_block),
ext_pblock(newext),
- le16_to_cpu(newext->ee_len),
+ ext4_ext_get_actual_len(newext),
nearex, len, nearex + 1, nearex + 2);
memmove(nearex + 1, nearex, len);
path[depth].p_ext = nearex;
}
- eh->eh_entries = cpu_to_le16(le16_to_cpu(eh->eh_entries)+1);
+ le16_add_cpu(&eh->eh_entries, 1);
nearex = path[depth].p_ext;
nearex->ee_block = newext->ee_block;
- nearex->ee_start = newext->ee_start;
- nearex->ee_start_hi = newext->ee_start_hi;
+ ext4_ext_store_pblock(nearex, ext_pblock(newext));
nearex->ee_len = newext->ee_len;
merge:
/* try to merge extents to the right */
- while (nearex < EXT_LAST_EXTENT(eh)) {
- if (!ext4_can_extents_be_merged(inode, nearex, nearex + 1))
- break;
- /* merge with next extent! */
- nearex->ee_len = cpu_to_le16(le16_to_cpu(nearex->ee_len)
- + le16_to_cpu(nearex[1].ee_len));
- if (nearex + 1 < EXT_LAST_EXTENT(eh)) {
- len = (EXT_LAST_EXTENT(eh) - nearex - 1)
- * sizeof(struct ext4_extent);
- memmove(nearex + 1, nearex + 2, len);
- }
- eh->eh_entries = cpu_to_le16(le16_to_cpu(eh->eh_entries)-1);
- BUG_ON(eh->eh_entries == 0);
- }
+ ext4_ext_try_to_merge(inode, path, nearex);
/* try to merge extents to the left */
return err;
}
-int ext4_ext_walk_space(struct inode *inode, unsigned long block,
- unsigned long num, ext_prepare_callback func,
- void *cbdata)
-{
- struct ext4_ext_path *path = NULL;
- struct ext4_ext_cache cbex;
- struct ext4_extent *ex;
- unsigned long next, start = 0, end = 0;
- unsigned long last = block + num;
- int depth, exists, err = 0;
-
- BUG_ON(func == NULL);
- BUG_ON(inode == NULL);
-
- while (block < last && block != EXT_MAX_BLOCK) {
- num = last - block;
- /* find extent for this block */
- path = ext4_ext_find_extent(inode, block, path);
- if (IS_ERR(path)) {
- err = PTR_ERR(path);
- path = NULL;
- break;
- }
-
- depth = ext_depth(inode);
- BUG_ON(path[depth].p_hdr == NULL);
- ex = path[depth].p_ext;
- next = ext4_ext_next_allocated_block(path);
-
- exists = 0;
- if (!ex) {
- /* there is no extent yet, so try to allocate
- * all requested space */
- start = block;
- end = block + num;
- } else if (le32_to_cpu(ex->ee_block) > block) {
- /* need to allocate space before found extent */
- start = block;
- end = le32_to_cpu(ex->ee_block);
- if (block + num < end)
- end = block + num;
- } else if (block >=
- le32_to_cpu(ex->ee_block) + le16_to_cpu(ex->ee_len)) {
- /* need to allocate space after found extent */
- start = block;
- end = block + num;
- if (end >= next)
- end = next;
- } else if (block >= le32_to_cpu(ex->ee_block)) {
- /*
- * some part of requested space is covered
- * by found extent
- */
- start = block;
- end = le32_to_cpu(ex->ee_block) + le16_to_cpu(ex->ee_len);
- if (block + num < end)
- end = block + num;
- exists = 1;
- } else {
- BUG();
- }
- BUG_ON(end <= start);
-
- if (!exists) {
- cbex.ec_block = start;
- cbex.ec_len = end - start;
- cbex.ec_start = 0;
- cbex.ec_type = EXT4_EXT_CACHE_GAP;
- } else {
- cbex.ec_block = le32_to_cpu(ex->ee_block);
- cbex.ec_len = le16_to_cpu(ex->ee_len);
- cbex.ec_start = ext_pblock(ex);
- cbex.ec_type = EXT4_EXT_CACHE_EXTENT;
- }
-
- BUG_ON(cbex.ec_len == 0);
- err = func(inode, path, &cbex, cbdata);
- ext4_ext_drop_refs(path);
-
- if (err < 0)
- break;
- if (err == EXT_REPEAT)
- continue;
- else if (err == EXT_BREAK) {
- err = 0;
- break;
- }
-
- if (ext_depth(inode) != depth) {
- /* depth was changed. we have to realloc path */
- kfree(path);
- path = NULL;
- }
-
- block = cbex.ec_block + cbex.ec_len;
- }
-
- if (path) {
- ext4_ext_drop_refs(path);
- kfree(path);
- }
-
- return err;
-}
-
static void
-ext4_ext_put_in_cache(struct inode *inode, __u32 block,
- __u32 len, __u32 start, int type)
+ext4_ext_put_in_cache(struct inode *inode, ext4_lblk_t block,
+ __u32 len, ext4_fsblk_t start, int type)
{
struct ext4_ext_cache *cex;
BUG_ON(len == 0);
*/
static void
ext4_ext_put_gap_in_cache(struct inode *inode, struct ext4_ext_path *path,
- unsigned long block)
+ ext4_lblk_t block)
{
int depth = ext_depth(inode);
- unsigned long lblock, len;
+ unsigned long len;
+ ext4_lblk_t lblock;
struct ext4_extent *ex;
ex = path[depth].p_ext;
} else if (block < le32_to_cpu(ex->ee_block)) {
lblock = block;
len = le32_to_cpu(ex->ee_block) - block;
- ext_debug("cache gap(before): %lu [%lu:%lu]",
- (unsigned long) block,
- (unsigned long) le32_to_cpu(ex->ee_block),
- (unsigned long) le16_to_cpu(ex->ee_len));
+ ext_debug("cache gap(before): %u [%u:%u]",
+ block,
+ le32_to_cpu(ex->ee_block),
+ ext4_ext_get_actual_len(ex));
} else if (block >= le32_to_cpu(ex->ee_block)
- + le16_to_cpu(ex->ee_len)) {
+ + ext4_ext_get_actual_len(ex)) {
+ ext4_lblk_t next;
lblock = le32_to_cpu(ex->ee_block)
- + le16_to_cpu(ex->ee_len);
- len = ext4_ext_next_allocated_block(path);
- ext_debug("cache gap(after): [%lu:%lu] %lu",
- (unsigned long) le32_to_cpu(ex->ee_block),
- (unsigned long) le16_to_cpu(ex->ee_len),
- (unsigned long) block);
- BUG_ON(len == lblock);
- len = len - lblock;
+ + ext4_ext_get_actual_len(ex);
+
+ next = ext4_ext_next_allocated_block(path);
+ ext_debug("cache gap(after): [%u:%u] %u",
+ le32_to_cpu(ex->ee_block),
+ ext4_ext_get_actual_len(ex),
+ block);
+ BUG_ON(next == lblock);
+ len = next - lblock;
} else {
lblock = len = 0;
BUG();
}
- ext_debug(" -> %lu:%lu\n", (unsigned long) lblock, len);
+ ext_debug(" -> %u:%lu\n", lblock, len);
ext4_ext_put_in_cache(inode, lblock, len, 0, EXT4_EXT_CACHE_GAP);
}
static int
-ext4_ext_in_cache(struct inode *inode, unsigned long block,
+ext4_ext_in_cache(struct inode *inode, ext4_lblk_t block,
struct ext4_extent *ex)
{
struct ext4_ext_cache *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);
- ext_debug("%lu cached by %lu:%lu:%llu\n",
- (unsigned long) block,
- (unsigned long) cex->ec_block,
- (unsigned long) cex->ec_len,
- cex->ec_start);
+ ext_debug("%u cached by %u:%u:%llu\n",
+ block,
+ cex->ec_block, cex->ec_len, cex->ec_start);
return cex->ec_type;
}
* It's used in truncate case only, thus all requests are for
* last index in the block only.
*/
-int ext4_ext_rm_idx(handle_t *handle, struct inode *inode,
+static int ext4_ext_rm_idx(handle_t *handle, struct inode *inode,
struct ext4_ext_path *path)
{
struct buffer_head *bh;
err = ext4_ext_get_access(handle, inode, path);
if (err)
return err;
- path->p_hdr->eh_entries = cpu_to_le16(le16_to_cpu(path->p_hdr->eh_entries)-1);
+ le16_add_cpu(&path->p_hdr->eh_entries, -1);
err = ext4_ext_dirty(handle, inode, path);
if (err)
return err;
ext_debug("index is empty, remove it, free block %llu\n", leaf);
bh = sb_find_get_block(inode->i_sb, leaf);
ext4_forget(handle, 1, inode, bh, leaf);
- ext4_free_blocks(handle, inode, leaf, 1);
+ ext4_free_blocks(handle, inode, leaf, 1, 1);
return err;
}
* This routine returns max. credits that the extent tree can consume.
* It should be OK for low-performance paths like ->writepage()
* To allow many writing processes to fit into a single transaction,
- * the caller should calculate credits under truncate_mutex and
+ * the caller should calculate credits under i_data_sem and
* pass the actual path.
*/
int ext4_ext_calc_credits_for_insert(struct inode *inode,
static int ext4_remove_blocks(handle_t *handle, struct inode *inode,
struct ext4_extent *ex,
- unsigned long from, unsigned long to)
+ ext4_lblk_t from, ext4_lblk_t to)
{
struct buffer_head *bh;
- int i;
+ unsigned short ee_len = ext4_ext_get_actual_len(ex);
+ int i, metadata = 0;
+ if (S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode))
+ metadata = 1;
#ifdef EXTENTS_STATS
{
struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
- unsigned short ee_len = le16_to_cpu(ex->ee_len);
spin_lock(&sbi->s_ext_stats_lock);
sbi->s_ext_blocks += ee_len;
sbi->s_ext_extents++;
}
#endif
if (from >= le32_to_cpu(ex->ee_block)
- && to == le32_to_cpu(ex->ee_block) + le16_to_cpu(ex->ee_len) - 1) {
+ && to == le32_to_cpu(ex->ee_block) + ee_len - 1) {
/* tail removal */
- unsigned long num;
+ ext4_lblk_t num;
ext4_fsblk_t start;
- num = le32_to_cpu(ex->ee_block) + le16_to_cpu(ex->ee_len) - from;
- start = ext_pblock(ex) + le16_to_cpu(ex->ee_len) - num;
- ext_debug("free last %lu blocks starting %llu\n", num, start);
+
+ num = le32_to_cpu(ex->ee_block) + ee_len - from;
+ start = ext_pblock(ex) + ee_len - num;
+ ext_debug("free last %u blocks starting %llu\n", num, start);
for (i = 0; i < num; i++) {
bh = sb_find_get_block(inode->i_sb, start + i);
ext4_forget(handle, 0, inode, bh, start + i);
}
- ext4_free_blocks(handle, inode, start, num);
+ ext4_free_blocks(handle, inode, start, num, metadata);
} else if (from == le32_to_cpu(ex->ee_block)
- && to <= le32_to_cpu(ex->ee_block) + le16_to_cpu(ex->ee_len) - 1) {
- printk("strange request: removal %lu-%lu from %u:%u\n",
- from, to, le32_to_cpu(ex->ee_block), le16_to_cpu(ex->ee_len));
+ && to <= le32_to_cpu(ex->ee_block) + ee_len - 1) {
+ printk(KERN_INFO "strange request: removal %u-%u from %u:%u\n",
+ from, to, le32_to_cpu(ex->ee_block), ee_len);
} else {
- printk("strange request: removal(2) %lu-%lu from %u:%u\n",
- from, to, le32_to_cpu(ex->ee_block), le16_to_cpu(ex->ee_len));
+ printk(KERN_INFO "strange request: removal(2) "
+ "%u-%u from %u:%u\n",
+ from, to, le32_to_cpu(ex->ee_block), ee_len);
}
return 0;
}
static int
ext4_ext_rm_leaf(handle_t *handle, struct inode *inode,
- struct ext4_ext_path *path, unsigned long start)
+ struct ext4_ext_path *path, ext4_lblk_t start)
{
int err = 0, correct_index = 0;
int depth = ext_depth(inode), credits;
struct ext4_extent_header *eh;
- unsigned a, b, block, num;
- unsigned long ex_ee_block;
+ ext4_lblk_t a, b, block;
+ unsigned num;
+ ext4_lblk_t ex_ee_block;
unsigned short ex_ee_len;
+ unsigned uninitialized = 0;
struct ext4_extent *ex;
- ext_debug("truncate since %lu in leaf\n", start);
+ /* the header must be checked already in ext4_ext_remove_space() */
+ ext_debug("truncate since %u in leaf\n", start);
if (!path[depth].p_hdr)
path[depth].p_hdr = ext_block_hdr(path[depth].p_bh);
eh = path[depth].p_hdr;
BUG_ON(eh == NULL);
- BUG_ON(le16_to_cpu(eh->eh_entries) > le16_to_cpu(eh->eh_max));
- BUG_ON(eh->eh_magic != EXT4_EXT_MAGIC);
/* find where to start removing */
ex = EXT_LAST_EXTENT(eh);
ex_ee_block = le32_to_cpu(ex->ee_block);
- ex_ee_len = le16_to_cpu(ex->ee_len);
+ if (ext4_ext_is_uninitialized(ex))
+ uninitialized = 1;
+ ex_ee_len = ext4_ext_get_actual_len(ex);
while (ex >= EXT_FIRST_EXTENT(eh) &&
ex_ee_block + ex_ee_len > start) {
if (num == 0) {
/* this extent is removed; mark slot entirely unused */
ext4_ext_store_pblock(ex, 0);
- eh->eh_entries = cpu_to_le16(le16_to_cpu(eh->eh_entries)-1);
+ le16_add_cpu(&eh->eh_entries, -1);
}
ex->ee_block = cpu_to_le32(block);
ex->ee_len = cpu_to_le16(num);
+ /*
+ * Do not mark uninitialized if all the blocks in the
+ * extent have been removed.
+ */
+ if (uninitialized && num)
+ ext4_ext_mark_uninitialized(ex);
err = ext4_ext_dirty(handle, inode, path + depth);
if (err)
ext_pblock(ex));
ex--;
ex_ee_block = le32_to_cpu(ex->ee_block);
- ex_ee_len = le16_to_cpu(ex->ee_len);
+ ex_ee_len = ext4_ext_get_actual_len(ex);
}
if (correct_index && eh->eh_entries)
return 1;
}
-int ext4_ext_remove_space(struct inode *inode, unsigned long start)
+static int ext4_ext_remove_space(struct inode *inode, ext4_lblk_t start)
{
struct super_block *sb = inode->i_sb;
int depth = ext_depth(inode);
handle_t *handle;
int i = 0, err = 0;
- ext_debug("truncate since %lu\n", start);
+ ext_debug("truncate since %u\n", start);
/* probably first extent we're gonna free will be last in block */
handle = ext4_journal_start(inode, depth + 1);
* We start scanning from right side, freeing all the blocks
* after i_size and walking into the tree depth-wise.
*/
- path = kzalloc(sizeof(struct ext4_ext_path) * (depth + 1), GFP_KERNEL);
+ path = kzalloc(sizeof(struct ext4_ext_path) * (depth + 1), GFP_NOFS);
if (path == NULL) {
ext4_journal_stop(handle);
return -ENOMEM;
}
path[0].p_hdr = ext_inode_hdr(inode);
- if (ext4_ext_check_header(__FUNCTION__, inode, path[0].p_hdr)) {
+ if (ext4_ext_check_header(inode, path[0].p_hdr, depth)) {
err = -EIO;
goto out;
}
if (!path[i].p_hdr) {
ext_debug("initialize header\n");
path[i].p_hdr = ext_block_hdr(path[i].p_bh);
- if (ext4_ext_check_header(__FUNCTION__, inode,
- path[i].p_hdr)) {
- err = -EIO;
- goto out;
- }
}
- BUG_ON(le16_to_cpu(path[i].p_hdr->eh_entries)
- > le16_to_cpu(path[i].p_hdr->eh_max));
- BUG_ON(path[i].p_hdr->eh_magic != EXT4_EXT_MAGIC);
-
if (!path[i].p_idx) {
/* this level hasn't been touched yet */
path[i].p_idx = EXT_LAST_INDEX(path[i].p_hdr);
i, EXT_FIRST_INDEX(path[i].p_hdr),
path[i].p_idx);
if (ext4_ext_more_to_rm(path + i)) {
+ struct buffer_head *bh;
/* go to the next level */
ext_debug("move to level %d (block %llu)\n",
i + 1, idx_pblock(path[i].p_idx));
memset(path + i + 1, 0, sizeof(*path));
- path[i+1].p_bh =
- sb_bread(sb, idx_pblock(path[i].p_idx));
- if (!path[i+1].p_bh) {
+ bh = sb_bread(sb, idx_pblock(path[i].p_idx));
+ if (!bh) {
/* should we reset i_size? */
err = -EIO;
break;
}
+ if (WARN_ON(i + 1 > depth)) {
+ err = -EIO;
+ break;
+ }
+ if (ext4_ext_check_header(inode, ext_block_hdr(bh),
+ depth - i - 1)) {
+ err = -EIO;
+ break;
+ }
+ path[i + 1].p_bh = bh;
/* save actual number of indexes since this
* number is changed at the next iteration */
#endif
}
+static void bi_complete(struct bio *bio, int error)
+{
+ complete((struct completion *)bio->bi_private);
+}
+
+/* FIXME!! we need to try to merge to left or right after zero-out */
+static int ext4_ext_zeroout(struct inode *inode, struct ext4_extent *ex)
+{
+ int ret = -EIO;
+ struct bio *bio;
+ int blkbits, blocksize;
+ sector_t ee_pblock;
+ struct completion event;
+ unsigned int ee_len, len, done, offset;
+
+
+ blkbits = inode->i_blkbits;
+ blocksize = inode->i_sb->s_blocksize;
+ ee_len = ext4_ext_get_actual_len(ex);
+ ee_pblock = ext_pblock(ex);
+
+ /* convert ee_pblock to 512 byte sectors */
+ ee_pblock = ee_pblock << (blkbits - 9);
+
+ while (ee_len > 0) {
+
+ if (ee_len > BIO_MAX_PAGES)
+ len = BIO_MAX_PAGES;
+ else
+ len = ee_len;
+
+ bio = bio_alloc(GFP_NOIO, len);
+ if (!bio)
+ return -ENOMEM;
+ bio->bi_sector = ee_pblock;
+ bio->bi_bdev = inode->i_sb->s_bdev;
+
+ done = 0;
+ offset = 0;
+ while (done < len) {
+ ret = bio_add_page(bio, ZERO_PAGE(0),
+ blocksize, offset);
+ if (ret != blocksize) {
+ /*
+ * We can't add any more pages because of
+ * hardware limitations. Start a new bio.
+ */
+ break;
+ }
+ done++;
+ offset += blocksize;
+ if (offset >= PAGE_CACHE_SIZE)
+ offset = 0;
+ }
+
+ init_completion(&event);
+ bio->bi_private = &event;
+ bio->bi_end_io = bi_complete;
+ submit_bio(WRITE, bio);
+ wait_for_completion(&event);
+
+ if (test_bit(BIO_UPTODATE, &bio->bi_flags))
+ ret = 0;
+ else {
+ ret = -EIO;
+ break;
+ }
+ bio_put(bio);
+ ee_len -= done;
+ ee_pblock += done << (blkbits - 9);
+ }
+ return ret;
+}
+
+#define EXT4_EXT_ZERO_LEN 7
+
+/*
+ * This function is called by ext4_ext_get_blocks() if someone tries to write
+ * to an uninitialized extent. It may result in splitting the uninitialized
+ * extent into multiple extents (upto three - one initialized and two
+ * uninitialized).
+ * There are three possibilities:
+ * a> There is no split required: Entire extent should be initialized
+ * b> Splits in two extents: Write is happening at either end of the extent
+ * c> Splits in three extents: Somone is writing in middle of the extent
+ */
+static int ext4_ext_convert_to_initialized(handle_t *handle,
+ struct inode *inode,
+ struct ext4_ext_path *path,
+ ext4_lblk_t iblock,
+ unsigned long max_blocks)
+{
+ struct ext4_extent *ex, newex, orig_ex;
+ struct ext4_extent *ex1 = NULL;
+ struct ext4_extent *ex2 = NULL;
+ struct ext4_extent *ex3 = NULL;
+ struct ext4_extent_header *eh;
+ ext4_lblk_t ee_block;
+ unsigned int allocated, ee_len, depth;
+ ext4_fsblk_t newblock;
+ int err = 0;
+ int ret = 0;
+
+ 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 - (iblock - ee_block);
+ newblock = iblock - ee_block + ext_pblock(ex);
+ ex2 = ex;
+ orig_ex.ee_block = ex->ee_block;
+ orig_ex.ee_len = cpu_to_le16(ee_len);
+ ext4_ext_store_pblock(&orig_ex, ext_pblock(ex));
+
+ err = ext4_ext_get_access(handle, inode, path + depth);
+ if (err)
+ goto out;
+ /* If extent has less than 2*EXT4_EXT_ZERO_LEN zerout directly */
+ if (ee_len <= 2*EXT4_EXT_ZERO_LEN) {
+ err = ext4_ext_zeroout(inode, &orig_ex);
+ if (err)
+ goto fix_extent_len;
+ /* update the extent length and mark as initialized */
+ ex->ee_block = orig_ex.ee_block;
+ ex->ee_len = orig_ex.ee_len;
+ ext4_ext_store_pblock(ex, ext_pblock(&orig_ex));
+ ext4_ext_dirty(handle, inode, path + depth);
+ /* zeroed the full extent */
+ return allocated;
+ }
+
+ /* ex1: ee_block to iblock - 1 : uninitialized */
+ if (iblock > ee_block) {
+ ex1 = ex;
+ ex1->ee_len = cpu_to_le16(iblock - ee_block);
+ ext4_ext_mark_uninitialized(ex1);
+ ex2 = &newex;
+ }
+ /*
+ * for sanity, update the length of the ex2 extent before
+ * we insert ex3, if ex1 is NULL. This is to avoid temporary
+ * overlap of blocks.
+ */
+ if (!ex1 && allocated > max_blocks)
+ ex2->ee_len = cpu_to_le16(max_blocks);
+ /* ex3: to ee_block + ee_len : uninitialised */
+ if (allocated > max_blocks) {
+ unsigned int newdepth;
+ /* If extent has less than EXT4_EXT_ZERO_LEN zerout directly */
+ if (allocated <= EXT4_EXT_ZERO_LEN) {
+ /* Mark first half uninitialized.
+ * Mark second half initialized and zero out the
+ * initialized extent
+ */
+ ex->ee_block = orig_ex.ee_block;
+ ex->ee_len = cpu_to_le16(ee_len - allocated);
+ ext4_ext_mark_uninitialized(ex);
+ ext4_ext_store_pblock(ex, ext_pblock(&orig_ex));
+ ext4_ext_dirty(handle, inode, path + depth);
+
+ ex3 = &newex;
+ ex3->ee_block = cpu_to_le32(iblock);
+ ext4_ext_store_pblock(ex3, newblock);
+ ex3->ee_len = cpu_to_le16(allocated);
+ err = ext4_ext_insert_extent(handle, inode, path, ex3);
+ if (err == -ENOSPC) {
+ err = ext4_ext_zeroout(inode, &orig_ex);
+ if (err)
+ goto fix_extent_len;
+ ex->ee_block = orig_ex.ee_block;
+ ex->ee_len = orig_ex.ee_len;
+ ext4_ext_store_pblock(ex, ext_pblock(&orig_ex));
+ ext4_ext_dirty(handle, inode, path + depth);
+ /* zeroed the full extent */
+ return allocated;
+
+ } else if (err)
+ goto fix_extent_len;
+
+ /*
+ * We need to zero out the second half because
+ * an fallocate request can update file size and
+ * converting the second half to initialized extent
+ * implies that we can leak some junk data to user
+ * space.
+ */
+ err = ext4_ext_zeroout(inode, ex3);
+ if (err) {
+ /*
+ * We should actually mark the
+ * second half as uninit and return error
+ * Insert would have changed the extent
+ */
+ depth = ext_depth(inode);
+ ext4_ext_drop_refs(path);
+ path = ext4_ext_find_extent(inode,
+ iblock, path);
+ if (IS_ERR(path)) {
+ err = PTR_ERR(path);
+ return err;
+ }
+ ex = path[depth].p_ext;
+ err = ext4_ext_get_access(handle, inode,
+ path + depth);
+ if (err)
+ return err;
+ ext4_ext_mark_uninitialized(ex);
+ ext4_ext_dirty(handle, inode, path + depth);
+ return err;
+ }
+
+ /* zeroed the second half */
+ return allocated;
+ }
+ ex3 = &newex;
+ ex3->ee_block = cpu_to_le32(iblock + max_blocks);
+ ext4_ext_store_pblock(ex3, newblock + max_blocks);
+ ex3->ee_len = cpu_to_le16(allocated - max_blocks);
+ ext4_ext_mark_uninitialized(ex3);
+ err = ext4_ext_insert_extent(handle, inode, path, ex3);
+ if (err == -ENOSPC) {
+ err = ext4_ext_zeroout(inode, &orig_ex);
+ if (err)
+ goto fix_extent_len;
+ /* update the extent length and mark as initialized */
+ ex->ee_block = orig_ex.ee_block;
+ ex->ee_len = orig_ex.ee_len;
+ ext4_ext_store_pblock(ex, ext_pblock(&orig_ex));
+ ext4_ext_dirty(handle, inode, path + depth);
+ /* zeroed the full extent */
+ return allocated;
+
+ } else if (err)
+ goto fix_extent_len;
+ /*
+ * The depth, and hence eh & ex might change
+ * as part of the insert above.
+ */
+ newdepth = ext_depth(inode);
+ /*
+ * update the extent length after successfull insert of the
+ * split extent
+ */
+ orig_ex.ee_len = cpu_to_le16(ee_len -
+ ext4_ext_get_actual_len(ex3));
+ if (newdepth != depth) {
+ depth = newdepth;
+ ext4_ext_drop_refs(path);
+ path = ext4_ext_find_extent(inode, iblock, path);
+ if (IS_ERR(path)) {
+ err = PTR_ERR(path);
+ goto out;
+ }
+ eh = path[depth].p_hdr;
+ ex = path[depth].p_ext;
+ if (ex2 != &newex)
+ ex2 = ex;
+
+ err = ext4_ext_get_access(handle, inode, path + depth);
+ if (err)
+ goto out;
+ }
+ allocated = max_blocks;
+
+ /* If extent has less than EXT4_EXT_ZERO_LEN and we are trying
+ * to insert a extent in the middle zerout directly
+ * otherwise give the extent a chance to merge to left
+ */
+ if (le16_to_cpu(orig_ex.ee_len) <= EXT4_EXT_ZERO_LEN &&
+ iblock != ee_block) {
+ err = ext4_ext_zeroout(inode, &orig_ex);
+ if (err)
+ goto fix_extent_len;
+ /* update the extent length and mark as initialized */
+ ex->ee_block = orig_ex.ee_block;
+ ex->ee_len = orig_ex.ee_len;
+ ext4_ext_store_pblock(ex, ext_pblock(&orig_ex));
+ ext4_ext_dirty(handle, inode, path + depth);
+ /* zero out the first half */
+ return allocated;
+ }
+ }
+ /*
+ * If there was a change of depth as part of the
+ * insertion of ex3 above, we need to update the length
+ * of the ex1 extent again here
+ */
+ if (ex1 && ex1 != ex) {
+ ex1 = ex;
+ ex1->ee_len = cpu_to_le16(iblock - ee_block);
+ ext4_ext_mark_uninitialized(ex1);
+ ex2 = &newex;
+ }
+ /* ex2: iblock to iblock + maxblocks-1 : initialised */
+ ex2->ee_block = cpu_to_le32(iblock);
+ ext4_ext_store_pblock(ex2, newblock);
+ ex2->ee_len = cpu_to_le16(allocated);
+ if (ex2 != ex)
+ goto insert;
+ /*
+ * New (initialized) extent starts from the first block
+ * in the current extent. i.e., ex2 == ex
+ * We have to see if it can be merged with the extent
+ * on the left.
+ */
+ if (ex2 > EXT_FIRST_EXTENT(eh)) {
+ /*
+ * To merge left, pass "ex2 - 1" to try_to_merge(),
+ * since it merges towards right _only_.
+ */
+ ret = ext4_ext_try_to_merge(inode, path, ex2 - 1);
+ if (ret) {
+ err = ext4_ext_correct_indexes(handle, inode, path);
+ if (err)
+ goto out;
+ depth = ext_depth(inode);
+ ex2--;
+ }
+ }
+ /*
+ * Try to Merge towards right. This might be required
+ * only when the whole extent is being written to.
+ * i.e. ex2 == ex and ex3 == NULL.
+ */
+ if (!ex3) {
+ ret = ext4_ext_try_to_merge(inode, path, ex2);
+ if (ret) {
+ err = ext4_ext_correct_indexes(handle, inode, path);
+ if (err)
+ goto out;
+ }
+ }
+ /* Mark modified extent as dirty */
+ err = ext4_ext_dirty(handle, inode, path + depth);
+ goto out;
+insert:
+ err = ext4_ext_insert_extent(handle, inode, path, &newex);
+ if (err == -ENOSPC) {
+ err = ext4_ext_zeroout(inode, &orig_ex);
+ if (err)
+ goto fix_extent_len;
+ /* update the extent length and mark as initialized */
+ ex->ee_block = orig_ex.ee_block;
+ ex->ee_len = orig_ex.ee_len;
+ ext4_ext_store_pblock(ex, ext_pblock(&orig_ex));
+ ext4_ext_dirty(handle, inode, path + depth);
+ /* zero out the first half */
+ return allocated;
+ } else if (err)
+ goto fix_extent_len;
+out:
+ return err ? err : allocated;
+
+fix_extent_len:
+ ex->ee_block = orig_ex.ee_block;
+ ex->ee_len = orig_ex.ee_len;
+ ext4_ext_store_pblock(ex, ext_pblock(&orig_ex));
+ ext4_ext_mark_uninitialized(ex);
+ ext4_ext_dirty(handle, inode, path + depth);
+ return err;
+}
+
+/*
+ * Block allocation/map/preallocation routine for extents based files
+ *
+ *
+ * Need to be called with
+ * down_read(&EXT4_I(inode)->i_data_sem) if not allocating file system block
+ * (ie, create is zero). Otherwise down_write(&EXT4_I(inode)->i_data_sem)
+ *
+ * return > 0, number of of blocks already mapped/allocated
+ * if create == 0 and these are pre-allocated blocks
+ * buffer head is unmapped
+ * otherwise blocks are mapped
+ *
+ * return = 0, if plain look up failed (blocks have not been allocated)
+ * buffer head is unmapped
+ *
+ * return < 0, error case.
+ */
int ext4_ext_get_blocks(handle_t *handle, struct inode *inode,
- ext4_fsblk_t iblock,
+ ext4_lblk_t iblock,
unsigned long max_blocks, struct buffer_head *bh_result,
int create, int extend_disksize)
{
struct ext4_ext_path *path = NULL;
+ struct ext4_extent_header *eh;
struct ext4_extent newex, *ex;
ext4_fsblk_t goal, newblock;
- int err = 0, depth;
+ int err = 0, depth, ret;
unsigned long allocated = 0;
+ struct ext4_allocation_request ar;
__clear_bit(BH_New, &bh_result->b_state);
- ext_debug("blocks %d/%lu requested for inode %u\n", (int) iblock,
- max_blocks, (unsigned) inode->i_ino);
- mutex_lock(&EXT4_I(inode)->truncate_mutex);
+ ext_debug("blocks %u/%lu requested for inode %u\n",
+ iblock, max_blocks, inode->i_ino);
/* check in cache */
goal = ext4_ext_in_cache(inode, iblock, &newex);
if (goal) {
if (goal == EXT4_EXT_CACHE_GAP) {
if (!create) {
- /* block isn't allocated yet and
- * user doesn't want to allocate it */
+ /*
+ * block isn't allocated yet and
+ * user doesn't want to allocate it
+ */
goto out2;
}
/* we should allocate requested block */
- le32_to_cpu(newex.ee_block)
+ ext_pblock(&newex);
/* number of remaining blocks in the extent */
- allocated = le16_to_cpu(newex.ee_len) -
+ allocated = ext4_ext_get_actual_len(&newex) -
(iblock - le32_to_cpu(newex.ee_block));
goto out;
} else {
* this is why assert can't be put in ext4_ext_find_extent()
*/
BUG_ON(path[depth].p_ext == NULL && depth != 0);
+ eh = path[depth].p_hdr;
ex = path[depth].p_ext;
if (ex) {
- unsigned long ee_block = le32_to_cpu(ex->ee_block);
+ ext4_lblk_t ee_block = le32_to_cpu(ex->ee_block);
ext4_fsblk_t ee_start = ext_pblock(ex);
- unsigned short ee_len = le16_to_cpu(ex->ee_len);
+ unsigned short ee_len;
/*
- * Allow future support for preallocated extents to be added
- * as an RO_COMPAT feature:
* Uninitialized extents are treated as holes, except that
- * we avoid (fail) allocating new blocks during a write.
+ * we split out initialized portions during a write.
*/
- if (ee_len > EXT_MAX_LEN)
- goto out2;
+ ee_len = ext4_ext_get_actual_len(ex);
/* if found extent covers block, simply return it */
if (iblock >= ee_block && iblock < ee_block + ee_len) {
newblock = iblock - ee_block + ee_start;
/* number of remaining blocks in the extent */
allocated = ee_len - (iblock - ee_block);
- ext_debug("%d fit into %lu:%d -> %llu\n", (int) iblock,
+ ext_debug("%u fit into %lu:%d -> %llu\n", iblock,
ee_block, ee_len, newblock);
- ext4_ext_put_in_cache(inode, ee_block, ee_len,
- ee_start, EXT4_EXT_CACHE_EXTENT);
- goto out;
+
+ /* 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,
+ EXT4_EXT_CACHE_EXTENT);
+ goto out;
+ }
+ if (create == EXT4_CREATE_UNINITIALIZED_EXT)
+ goto out;
+ if (!create) {
+ /*
+ * We have blocks reserved already. We
+ * return allocated blocks so that delalloc
+ * won't do block reservation for us. But
+ * the buffer head will be unmapped so that
+ * a read from the block returns 0s.
+ */
+ if (allocated > max_blocks)
+ allocated = max_blocks;
+ /* mark the buffer unwritten */
+ __set_bit(BH_Unwritten, &bh_result->b_state);
+ goto out2;
+ }
+
+ ret = ext4_ext_convert_to_initialized(handle, inode,
+ path, iblock,
+ max_blocks);
+ if (ret <= 0) {
+ err = ret;
+ goto out2;
+ } else
+ allocated = ret;
+ goto outnew;
}
}
* we couldn't try to create block if create flag is zero
*/
if (!create) {
- /* put just found gap into cache to speed up
- * subsequent requests */
+ /*
+ * put just found gap into cache to speed up
+ * subsequent requests
+ */
ext4_ext_put_gap_in_cache(inode, path, iblock);
goto out2;
}
if (S_ISREG(inode->i_mode) && (!EXT4_I(inode)->i_block_alloc_info))
ext4_init_block_alloc_info(inode);
- /* allocate new block */
- goal = ext4_ext_find_goal(inode, path, iblock);
+ /* find neighbour allocated blocks */
+ ar.lleft = iblock;
+ err = ext4_ext_search_left(inode, path, &ar.lleft, &ar.pleft);
+ if (err)
+ goto out2;
+ ar.lright = iblock;
+ err = ext4_ext_search_right(inode, path, &ar.lright, &ar.pright);
+ if (err)
+ goto out2;
+
+ /*
+ * See if request is beyond maximum number of blocks we can have in
+ * a single extent. For an initialized extent this limit is
+ * EXT_INIT_MAX_LEN and for an uninitialized extent this limit is
+ * EXT_UNINIT_MAX_LEN.
+ */
+ if (max_blocks > EXT_INIT_MAX_LEN &&
+ create != EXT4_CREATE_UNINITIALIZED_EXT)
+ max_blocks = EXT_INIT_MAX_LEN;
+ else if (max_blocks > EXT_UNINIT_MAX_LEN &&
+ create == EXT4_CREATE_UNINITIALIZED_EXT)
+ max_blocks = EXT_UNINIT_MAX_LEN;
/* Check if we can really insert (iblock)::(iblock+max_blocks) extent */
newex.ee_block = cpu_to_le32(iblock);
newex.ee_len = cpu_to_le16(max_blocks);
err = ext4_ext_check_overlap(inode, &newex, path);
if (err)
- allocated = le16_to_cpu(newex.ee_len);
+ allocated = ext4_ext_get_actual_len(&newex);
else
allocated = max_blocks;
- newblock = ext4_new_blocks(handle, inode, goal, &allocated, &err);
+
+ /* allocate new block */
+ ar.inode = inode;
+ ar.goal = ext4_ext_find_goal(inode, path, iblock);
+ ar.logical = iblock;
+ ar.len = allocated;
+ if (S_ISREG(inode->i_mode))
+ ar.flags = EXT4_MB_HINT_DATA;
+ else
+ /* disable in-core preallocation for non-regular files */
+ ar.flags = 0;
+ newblock = ext4_mb_new_blocks(handle, &ar, &err);
if (!newblock)
goto out2;
ext_debug("allocate new block: goal %llu, found %llu/%lu\n",
/* try to insert new extent into found leaf and return */
ext4_ext_store_pblock(&newex, newblock);
- newex.ee_len = cpu_to_le16(allocated);
+ newex.ee_len = cpu_to_le16(ar.len);
+ if (create == EXT4_CREATE_UNINITIALIZED_EXT) /* Mark uninitialized */
+ ext4_ext_mark_uninitialized(&newex);
err = ext4_ext_insert_extent(handle, inode, path, &newex);
if (err) {
/* free data blocks we just allocated */
+ /* not a good idea to call discard here directly,
+ * but otherwise we'd need to call it every free() */
+ ext4_mb_discard_inode_preallocations(inode);
ext4_free_blocks(handle, inode, ext_pblock(&newex),
- le16_to_cpu(newex.ee_len));
+ ext4_ext_get_actual_len(&newex), 0);
goto out2;
}
/* previous routine could use block we allocated */
newblock = ext_pblock(&newex);
+ allocated = ext4_ext_get_actual_len(&newex);
+outnew:
__set_bit(BH_New, &bh_result->b_state);
- ext4_ext_put_in_cache(inode, iblock, allocated, newblock,
- EXT4_EXT_CACHE_EXTENT);
+ /* Cache only when it is _not_ an uninitialized extent */
+ if (create != EXT4_CREATE_UNINITIALIZED_EXT)
+ ext4_ext_put_in_cache(inode, iblock, allocated, newblock,
+ EXT4_EXT_CACHE_EXTENT);
out:
if (allocated > max_blocks)
allocated = max_blocks;
ext4_ext_drop_refs(path);
kfree(path);
}
- mutex_unlock(&EXT4_I(inode)->truncate_mutex);
-
return err ? err : allocated;
}
{
struct address_space *mapping = inode->i_mapping;
struct super_block *sb = inode->i_sb;
- unsigned long last_block;
+ ext4_lblk_t last_block;
handle_t *handle;
int err = 0;
if (page)
ext4_block_truncate_page(handle, page, mapping, inode->i_size);
- mutex_lock(&EXT4_I(inode)->truncate_mutex);
+ down_write(&EXT4_I(inode)->i_data_sem);
ext4_ext_invalidate_cache(inode);
+ ext4_mb_discard_inode_preallocations(inode);
+
/*
* TODO: optimization is possible here.
* Probably we need not scan at all,
err = ext4_ext_remove_space(inode, last_block);
/* In a multi-transaction truncate, we only make the final
- * transaction synchronous. */
+ * transaction synchronous.
+ */
if (IS_SYNC(inode))
handle->h_sync = 1;
if (inode->i_nlink)
ext4_orphan_del(handle, inode);
- mutex_unlock(&EXT4_I(inode)->truncate_mutex);
+ up_write(&EXT4_I(inode)->i_data_sem);
+ inode->i_mtime = inode->i_ctime = ext4_current_time(inode);
+ ext4_mark_inode_dirty(handle, inode);
ext4_journal_stop(handle);
}
return needed;
}
+
+static void ext4_falloc_update_inode(struct inode *inode,
+ int mode, loff_t new_size, int update_ctime)
+{
+ struct timespec now;
+
+ if (update_ctime) {
+ now = current_fs_time(inode->i_sb);
+ if (!timespec_equal(&inode->i_ctime, &now))
+ inode->i_ctime = now;
+ }
+ /*
+ * Update only when preallocation was requested beyond
+ * the file size.
+ */
+ if (!(mode & FALLOC_FL_KEEP_SIZE) &&
+ new_size > i_size_read(inode)) {
+ i_size_write(inode, new_size);
+ EXT4_I(inode)->i_disksize = new_size;
+ }
+
+}
+
+/*
+ * preallocate space for a file. This implements ext4's fallocate inode
+ * operation, which gets called from sys_fallocate system call.
+ * For block-mapped files, posix_fallocate should fall back to the method
+ * of writing zeroes to the required new blocks (the same behavior which is
+ * expected for file systems which do not support fallocate() system call).
+ */
+long ext4_fallocate(struct inode *inode, int mode, loff_t offset, loff_t len)
+{
+ handle_t *handle;
+ ext4_lblk_t block;
+ loff_t new_size;
+ unsigned long max_blocks;
+ int ret = 0;
+ int ret2 = 0;
+ int retries = 0;
+ struct buffer_head map_bh;
+ unsigned int credits, blkbits = inode->i_blkbits;
+
+ /*
+ * currently supporting (pre)allocate mode for extent-based
+ * files _only_
+ */
+ if (!(EXT4_I(inode)->i_flags & EXT4_EXTENTS_FL))
+ return -EOPNOTSUPP;
+
+ /* preallocation to directories is currently not supported */
+ if (S_ISDIR(inode->i_mode))
+ return -ENODEV;
+
+ block = offset >> blkbits;
+ /*
+ * We can't just convert len to max_blocks because
+ * If blocksize = 4096 offset = 3072 and len = 2048
+ */
+ max_blocks = (EXT4_BLOCK_ALIGN(len + offset, blkbits) >> blkbits)
+ - block;
+ /*
+ * credits to insert 1 extent into extent tree + buffers to be able to
+ * modify 1 super block, 1 block bitmap and 1 group descriptor.
+ */
+ credits = EXT4_DATA_TRANS_BLOCKS(inode->i_sb) + 3;
+ mutex_lock(&inode->i_mutex);
+retry:
+ while (ret >= 0 && ret < max_blocks) {
+ block = block + ret;
+ max_blocks = max_blocks - ret;
+ handle = ext4_journal_start(inode, credits);
+ if (IS_ERR(handle)) {
+ ret = PTR_ERR(handle);
+ break;
+ }
+ ret = ext4_get_blocks_wrap(handle, inode, block,
+ max_blocks, &map_bh,
+ EXT4_CREATE_UNINITIALIZED_EXT, 0);
+ if (ret <= 0) {
+#ifdef EXT4FS_DEBUG
+ WARN_ON(ret <= 0);
+ printk(KERN_ERR "%s: ext4_ext_get_blocks "
+ "returned error inode#%lu, block=%u, "
+ "max_blocks=%lu", __func__,
+ inode->i_ino, block, max_blocks);
+#endif
+ ext4_mark_inode_dirty(handle, inode);
+ ret2 = ext4_journal_stop(handle);
+ break;
+ }
+ if ((block + ret) >= (EXT4_BLOCK_ALIGN(offset + len,
+ blkbits) >> blkbits))
+ new_size = offset + len;
+ else
+ new_size = (block + ret) << blkbits;
+
+ ext4_falloc_update_inode(inode, mode, new_size,
+ buffer_new(&map_bh));
+ ext4_mark_inode_dirty(handle, inode);
+ ret2 = ext4_journal_stop(handle);
+ if (ret2)
+ break;
+ }
+ if (ret == -ENOSPC &&
+ ext4_should_retry_alloc(inode->i_sb, &retries)) {
+ ret = 0;
+ goto retry;
+ }
+ mutex_unlock(&inode->i_mutex);
+ return ret > 0 ? ret2 : ret;
+}