UbiquitousOS
/
OpenCloudOS-Kernel
mirror of https://gitee.com/OpenCloudOS/OpenCloudOS-Kernel.git
11
0
Fork 0
Code Issues Projects Releases Wiki Activity
OpenCloudOS-Kernel/fs/ext4/extents.c

5793 lines
157 KiB
C
Raw Blame History

// SPDX-License-Identifier: GPL-2.0
/*
* Copyright (c) 2003-2006, Cluster File Systems, Inc, info@clusterfs.com
* Written by Alex Tomas <alex@clusterfs.com>
*
* Architecture independence:
* Copyright (c) 2005, Bull S.A.
* Written by Pierre Peiffer <pierre.peiffer@bull.net>
*/
/*
* Extents support for EXT4
*
* TODO:
* - ext4*_error() should be used in some situations
* - analyze all BUG()/BUG_ON(), use -EIO where appropriate
* - smart tree reduction
*/
#include <linux/fs.h>
#include <linux/time.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/uaccess.h>
#include <linux/fiemap.h>
#include <linux/backing-dev.h>
#include <linux/iomap.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_UNWRIT1 0x2 /* mark first half unwritten */
#define EXT4_EXT_MARK_UNWRIT2 0x4 /* mark second half unwritten */
#define EXT4_EXT_DATA_VALID1 0x8 /* first half contains valid data */
#define EXT4_EXT_DATA_VALID2 0x10 /* second half contains valid data */
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_metadata_csum(inode->i_sb))
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_metadata_csum(inode->i_sb))
return;
et = find_ext4_extent_tail(eh);
et->et_checksum = ext4_extent_block_csum(inode, eh);
}
static int ext4_split_extent_at(handle_t *handle,
struct inode *inode,
struct ext4_ext_path **ppath,
ext4_lblk_t split,
int split_flag,
int flags);
static int ext4_ext_trunc_restart_fn(struct inode *inode, int *dropped)
{
/*
* Drop i_data_sem to avoid deadlock with ext4_map_blocks. At this
* moment, get_block can be called only for blocks inside i_size since
* page cache has been already dropped and writes are blocked by
* i_mutex. So we can safely drop the i_data_sem here.
*/
BUG_ON(EXT4_JOURNAL(inode) == NULL);
ext4_discard_preallocations(inode);
up_write(&EXT4_I(inode)->i_data_sem);
*dropped = 1;
return 0;
}
/*
* Make sure 'handle' has at least 'check_cred' credits. If not, restart
* transaction with 'restart_cred' credits. The function drops i_data_sem
* when restarting transaction and gets it after transaction is restarted.
*
* The function returns 0 on success, 1 if transaction had to be restarted,
* and < 0 in case of fatal error.
*/
int ext4_datasem_ensure_credits(handle_t *handle, struct inode *inode,
int check_cred, int restart_cred,
int revoke_cred)
{
int ret;
int dropped = 0;
ret = ext4_journal_ensure_credits_fn(handle, check_cred, restart_cred,
revoke_cred, ext4_ext_trunc_restart_fn(inode, &dropped));
if (dropped)
down_write(&EXT4_I(inode)->i_data_sem);
return ret;
}
/*
* could return:
* - EROFS
* - ENOMEM
*/
static int ext4_ext_get_access(handle_t *handle, struct inode *inode,
struct ext4_ext_path *path)
{
if (path->p_bh) {
/* path points to block */
BUFFER_TRACE(path->p_bh, "get_write_access");
return ext4_journal_get_write_access(handle, path->p_bh);
}
/* path points to leaf/index in inode body */
/* we use in-core data, no need to protect them */
return 0;
}
/*
* could return:
* - EROFS
* - ENOMEM
* - EIO
*/
static int __ext4_ext_dirty(const char *where, unsigned int line,
handle_t *handle, struct inode *inode,
struct ext4_ext_path *path)
{
int err;
WARN_ON(!rwsem_is_locked(&EXT4_I(inode)->i_data_sem));
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);
} else {
/* path points to leaf/index in inode body */
err = ext4_mark_inode_dirty(handle, inode);
}
return err;
}
#define ext4_ext_dirty(handle, inode, path) \
__ext4_ext_dirty(__func__, __LINE__, (handle), (inode), (path))
static ext4_fsblk_t ext4_ext_find_goal(struct inode *inode,
struct ext4_ext_path *path,
ext4_lblk_t block)
{
if (path) {
int depth = path->p_depth;
struct ext4_extent *ex;
/*
* Try to predict block placement assuming that we are
* filling in a file which will eventually be
* non-sparse --- i.e., in the case of libbfd writing
* an ELF object sections out-of-order but in a way
* the eventually results in a contiguous object or
* executable file, or some database extending a table
* space file. However, this is actually somewhat
* non-ideal if we are writing a sparse file such as
* qemu or KVM writing a raw image file that is going
* to stay fairly sparse, since it will end up
* fragmenting the file system's free space. Maybe we
* should have some hueristics or some way to allow
* userspace to pass a hint to file system,
* especially if the latter case turns out to be
* common.
*/
ex = path[depth].p_ext;
if (ex) {
ext4_fsblk_t ext_pblk = ext4_ext_pblock(ex);
ext4_lblk_t ext_block = le32_to_cpu(ex->ee_block);
if (block > ext_block)
return ext_pblk + (block - ext_block);
else
return ext_pblk - (ext_block - block);
}
/* it looks like index is empty;
* try to find starting block from index itself */
if (path[depth].p_bh)
return path[depth].p_bh->b_blocknr;
}
/* OK. use inode's group */
return ext4_inode_to_goal_block(inode);
}
/*
* Allocation for a meta data block
*/
static ext4_fsblk_t
ext4_ext_new_meta_block(handle_t *handle, struct inode *inode,
struct ext4_ext_path *path,
struct ext4_extent *ex, int *err, unsigned int flags)
{
ext4_fsblk_t goal, newblock;
goal = ext4_ext_find_goal(inode, path, le32_to_cpu(ex->ee_block));
newblock = ext4_new_meta_blocks(handle, inode, goal, flags,
NULL, err);
return newblock;
}
static inline int ext4_ext_space_block(struct inode *inode, int check)
{
int size;
size = (inode->i_sb->s_blocksize - sizeof(struct ext4_extent_header))
/ sizeof(struct ext4_extent);
#ifdef AGGRESSIVE_TEST
if (!check && size > 6)
size = 6;
#endif
return size;
}
static inline int ext4_ext_space_block_idx(struct inode *inode, int check)
{
int size;
size = (inode->i_sb->s_blocksize - sizeof(struct ext4_extent_header))
/ sizeof(struct ext4_extent_idx);
#ifdef AGGRESSIVE_TEST
if (!check && size > 5)
size = 5;
#endif
return size;
}
static inline int ext4_ext_space_root(struct inode *inode, int check)
{
int size;
size = sizeof(EXT4_I(inode)->i_data);
size -= sizeof(struct ext4_extent_header);
size /= sizeof(struct ext4_extent);
#ifdef AGGRESSIVE_TEST
if (!check && size > 3)
size = 3;
#endif
return size;
}
static inline int ext4_ext_space_root_idx(struct inode *inode, int check)
{
int size;
size = sizeof(EXT4_I(inode)->i_data);
size -= sizeof(struct ext4_extent_header);
size /= sizeof(struct ext4_extent_idx);
#ifdef AGGRESSIVE_TEST
if (!check && size > 4)
size = 4;
#endif
return size;
}
static inline int
ext4_force_split_extent_at(handle_t *handle, struct inode *inode,
struct ext4_ext_path **ppath, ext4_lblk_t lblk,
int nofail)
{
struct ext4_ext_path *path = *ppath;
int unwritten = ext4_ext_is_unwritten(path[path->p_depth].p_ext);
int flags = EXT4_EX_NOCACHE | EXT4_GET_BLOCKS_PRE_IO;
if (nofail)
flags |= EXT4_GET_BLOCKS_METADATA_NOFAIL | EXT4_EX_NOFAIL;
return ext4_split_extent_at(handle, inode, ppath, lblk, unwritten ?
EXT4_EXT_MARK_UNWRIT1|EXT4_EXT_MARK_UNWRIT2 : 0,
flags);
}
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, 1);
else
max = ext4_ext_space_root_idx(inode, 1);
} else {
if (depth == 0)
max = ext4_ext_space_block(inode, 1);
else
max = ext4_ext_space_block_idx(inode, 1);
}
return max;
}
static int ext4_valid_extent(struct inode *inode, struct ext4_extent *ext)
{
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);
/*
* We allow neither:
* - zero length
* - overflow/wrap-around
*/
if (lblock + len <= lblock)
return 0;
return ext4_data_block_valid(EXT4_SB(inode->i_sb), block, len);
}
static int ext4_valid_extent_idx(struct inode *inode,
struct ext4_extent_idx *ext_idx)
{
ext4_fsblk_t block = ext4_idx_pblock(ext_idx);
return ext4_data_block_valid(EXT4_SB(inode->i_sb), block, 1);
}
static int ext4_valid_extent_entries(struct inode *inode,
struct ext4_extent_header *eh,
ext4_fsblk_t *pblk, int depth)
{
unsigned short entries;
if (eh->eh_entries == 0)
return 1;
entries = le16_to_cpu(eh->eh_entries);
if (depth == 0) {
/* leaf entries */
struct ext4_extent *ext = EXT_FIRST_EXTENT(eh);
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) {
*pblk = ext4_ext_pblock(ext);
return 0;
}
ext++;
entries--;
prev = lblock + len - 1;
}
} else {
struct ext4_extent_idx *ext_idx = EXT_FIRST_INDEX(eh);
while (entries) {
if (!ext4_valid_extent_idx(inode, ext_idx))
return 0;
ext_idx++;
entries--;
}
}
return 1;
}
static int __ext4_ext_check(const char *function, unsigned int line,
struct inode *inode, struct ext4_extent_header *eh,
int depth, ext4_fsblk_t pblk)
{
const char *error_msg;
int max = 0, err = -EFSCORRUPTED;
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;
}
if (!ext4_valid_extent_entries(inode, eh, &pblk, depth)) {
error_msg = "invalid extent entries";
goto corrupted;
}
if (unlikely(depth > 32)) {
error_msg = "too large eh_depth";
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";
err = -EFSBADCRC;
goto corrupted;
}
return 0;
corrupted:
ext4_error_inode_err(inode, function, line, 0, -err,
"pblk %llu bad header/extent: %s - magic %x, "
"entries %u, max %u(%u), depth %u(%u)",
(unsigned long long) pblk, 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 err;
}
#define ext4_ext_check(inode, eh, depth, pblk) \
__ext4_ext_check(__func__, __LINE__, (inode), (eh), (depth), (pblk))
int ext4_ext_check_inode(struct inode *inode)
{
return ext4_ext_check(inode, ext_inode_hdr(inode), ext_depth(inode), 0);
}
static void ext4_cache_extents(struct inode *inode,
struct ext4_extent_header *eh)
{
struct ext4_extent *ex = EXT_FIRST_EXTENT(eh);
ext4_lblk_t prev = 0;
int i;
for (i = le16_to_cpu(eh->eh_entries); i > 0; i--, ex++) {
unsigned int status = EXTENT_STATUS_WRITTEN;
ext4_lblk_t lblk = le32_to_cpu(ex->ee_block);
int len = ext4_ext_get_actual_len(ex);
if (prev && (prev != lblk))
ext4_es_cache_extent(inode, prev, lblk - prev, ~0,
EXTENT_STATUS_HOLE);
if (ext4_ext_is_unwritten(ex))
status = EXTENT_STATUS_UNWRITTEN;
ext4_es_cache_extent(inode, lblk, len,
ext4_ext_pblock(ex), status);
prev = lblk + len;
}
}
static struct buffer_head *
__read_extent_tree_block(const char *function, unsigned int line,
struct inode *inode, ext4_fsblk_t pblk, int depth,
int flags)
{
struct buffer_head *bh;
int err;
gfp_t gfp_flags = __GFP_MOVABLE | GFP_NOFS;
if (flags & EXT4_EX_NOFAIL)
gfp_flags |= __GFP_NOFAIL;
bh = sb_getblk_gfp(inode->i_sb, pblk, gfp_flags);
if (unlikely(!bh))
return ERR_PTR(-ENOMEM);
if (!bh_uptodate_or_lock(bh)) {
trace_ext4_ext_load_extent(inode, pblk, _RET_IP_);
err = bh_submit_read(bh);
if (err < 0)
goto errout;
}
if (buffer_verified(bh) && !(flags & EXT4_EX_FORCE_CACHE))
return bh;
if (!ext4_has_feature_journal(inode->i_sb) ||
(inode->i_ino !=
le32_to_cpu(EXT4_SB(inode->i_sb)->s_es->s_journal_inum))) {
err = __ext4_ext_check(function, line, inode,
ext_block_hdr(bh), depth, pblk);
if (err)
goto errout;
}
set_buffer_verified(bh);
/*
* If this is a leaf block, cache all of its entries
*/
if (!(flags & EXT4_EX_NOCACHE) && depth == 0) {
struct ext4_extent_header *eh = ext_block_hdr(bh);
ext4_cache_extents(inode, eh);
}
return bh;
errout:
put_bh(bh);
return ERR_PTR(err);
}
#define read_extent_tree_block(inode, pblk, depth, flags) \
__read_extent_tree_block(__func__, __LINE__, (inode), (pblk), \
(depth), (flags))
/*
* This function is called to cache a file's extent information in the
* extent status tree
*/
int ext4_ext_precache(struct inode *inode)
{
struct ext4_inode_info *ei = EXT4_I(inode);
struct ext4_ext_path *path = NULL;
struct buffer_head *bh;
int i = 0, depth, ret = 0;
if (!ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))
return 0; /* not an extent-mapped inode */
down_read(&ei->i_data_sem);
depth = ext_depth(inode);
/* Don't cache anything if there are no external extent blocks */
if (!depth) {
up_read(&ei->i_data_sem);
return ret;
}
path = kcalloc(depth + 1, sizeof(struct ext4_ext_path),
GFP_NOFS);
if (path == NULL) {
up_read(&ei->i_data_sem);
return -ENOMEM;
}
path[0].p_hdr = ext_inode_hdr(inode);
ret = ext4_ext_check(inode, path[0].p_hdr, depth, 0);
if (ret)
goto out;
path[0].p_idx = EXT_FIRST_INDEX(path[0].p_hdr);
while (i >= 0) {
/*
* If this is a leaf block or we've reached the end of
* the index block, go up
*/
if ((i == depth) ||
path[i].p_idx > EXT_LAST_INDEX(path[i].p_hdr)) {
brelse(path[i].p_bh);
path[i].p_bh = NULL;
i--;
continue;
}
bh = read_extent_tree_block(inode,
ext4_idx_pblock(path[i].p_idx++),
depth - i - 1,
EXT4_EX_FORCE_CACHE);
if (IS_ERR(bh)) {
ret = PTR_ERR(bh);
break;
}
i++;
path[i].p_bh = bh;
path[i].p_hdr = ext_block_hdr(bh);
path[i].p_idx = EXT_FIRST_INDEX(path[i].p_hdr);
}
ext4_set_inode_state(inode, EXT4_STATE_EXT_PRECACHED);
out:
up_read(&ei->i_data_sem);
ext4_ext_drop_refs(path);
kfree(path);
return ret;
}
#ifdef EXT_DEBUG
static void ext4_ext_show_path(struct inode *inode, struct ext4_ext_path *path)
{
int k, l = path->p_depth;
ext_debug(inode, "path:");
for (k = 0; k <= l; k++, path++) {
if (path->p_idx) {
ext_debug(inode, " %d->%llu",
le32_to_cpu(path->p_idx->ei_block),
ext4_idx_pblock(path->p_idx));
} else if (path->p_ext) {
ext_debug(inode, " %d:[%d]%d:%llu ",
le32_to_cpu(path->p_ext->ee_block),
ext4_ext_is_unwritten(path->p_ext),
ext4_ext_get_actual_len(path->p_ext),
ext4_ext_pblock(path->p_ext));
} else
ext_debug(inode, " []");
}
ext_debug(inode, "\n");
}
static void ext4_ext_show_leaf(struct inode *inode, struct ext4_ext_path *path)
{
int depth = ext_depth(inode);
struct ext4_extent_header *eh;
struct ext4_extent *ex;
int i;
if (!path)
return;
eh = path[depth].p_hdr;
ex = EXT_FIRST_EXTENT(eh);
ext_debug(inode, "Displaying leaf extents\n");
for (i = 0; i < le16_to_cpu(eh->eh_entries); i++, ex++) {
ext_debug(inode, "%d:[%d]%d:%llu ", le32_to_cpu(ex->ee_block),
ext4_ext_is_unwritten(ex),
ext4_ext_get_actual_len(ex), ext4_ext_pblock(ex));
}
ext_debug(inode, "\n");
}
static void ext4_ext_show_move(struct inode *inode, struct ext4_ext_path *path,
ext4_fsblk_t newblock, int level)
{
int depth = ext_depth(inode);
struct ext4_extent *ex;
if (depth != level) {
struct ext4_extent_idx *idx;
idx = path[level].p_idx;
while (idx <= EXT_MAX_INDEX(path[level].p_hdr)) {
ext_debug(inode, "%d: move %d:%llu in new index %llu\n",
level, le32_to_cpu(idx->ei_block),
ext4_idx_pblock(idx), newblock);
idx++;
}
return;
}
ex = path[depth].p_ext;
while (ex <= EXT_MAX_EXTENT(path[depth].p_hdr)) {
ext_debug(inode, "move %d:%llu:[%d]%d in new leaf %llu\n",
le32_to_cpu(ex->ee_block),
ext4_ext_pblock(ex),
ext4_ext_is_unwritten(ex),
ext4_ext_get_actual_len(ex),
newblock);
ex++;
}
}
#else
#define ext4_ext_show_path(inode, path)
#define ext4_ext_show_leaf(inode, path)
#define ext4_ext_show_move(inode, path, newblock, level)
#endif
void ext4_ext_drop_refs(struct ext4_ext_path *path)
{
int depth, i;
if (!path)
return;
depth = path->p_depth;
for (i = 0; i <= depth; i++, path++) {
if (path->p_bh) {
brelse(path->p_bh);
path->p_bh = NULL;
}
}
}
/*
* 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, ext4_lblk_t block)
{
struct ext4_extent_header *eh = path->p_hdr;
struct ext4_extent_idx *r, *l, *m;
ext_debug(inode, "binsearch for %u(idx): ", block);
l = EXT_FIRST_INDEX(eh) + 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(inode, "%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(inode, " -> %u->%lld ", le32_to_cpu(path->p_idx->ei_block),
ext4_idx_pblock(path->p_idx));
#ifdef CHECK_BINSEARCH
{
struct ext4_extent_idx *chix, *ix;
int k;
chix = ix = EXT_FIRST_INDEX(eh);
for (k = 0; k < le16_to_cpu(eh->eh_entries); k++, ix++) {
if (k != 0 && le32_to_cpu(ix->ei_block) <=
le32_to_cpu(ix[-1].ei_block)) {
printk(KERN_DEBUG "k=%d, ix=0x%p, "
"first=0x%p\n", k,
ix, EXT_FIRST_INDEX(eh));
printk(KERN_DEBUG "%u <= %u\n",
le32_to_cpu(ix->ei_block),
le32_to_cpu(ix[-1].ei_block));
}
BUG_ON(k && le32_to_cpu(ix->ei_block)
<= le32_to_cpu(ix[-1].ei_block));
if (block < le32_to_cpu(ix->ei_block))
break;
chix = ix;
}
BUG_ON(chix != path->p_idx);
}
#endif
}
/*
* 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, ext4_lblk_t block)
{
struct ext4_extent_header *eh = path->p_hdr;
struct ext4_extent *r, *l, *m;
if (eh->eh_entries == 0) {
/*
* this leaf is empty:
* we get such a leaf in split/add case
*/
return;
}
ext_debug(inode, "binsearch for %u: ", block);
l = EXT_FIRST_EXTENT(eh) + 1;
r = EXT_LAST_EXTENT(eh);
while (l <= r) {
m = l + (r - l) / 2;
if (block < le32_to_cpu(m->ee_block))
r = m - 1;
else
l = m + 1;
ext_debug(inode, "%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(inode, " -> %d:%llu:[%d]%d ",
le32_to_cpu(path->p_ext->ee_block),
ext4_ext_pblock(path->p_ext),
ext4_ext_is_unwritten(path->p_ext),
ext4_ext_get_actual_len(path->p_ext));
#ifdef CHECK_BINSEARCH
{
struct ext4_extent *chex, *ex;
int k;
chex = ex = EXT_FIRST_EXTENT(eh);
for (k = 0; k < le16_to_cpu(eh->eh_entries); k++, ex++) {
BUG_ON(k && le32_to_cpu(ex->ee_block)
<= le32_to_cpu(ex[-1].ee_block));
if (block < le32_to_cpu(ex->ee_block))
break;
chex = ex;
}
BUG_ON(chex != path->p_ext);
}
#endif
}
void ext4_ext_tree_init(handle_t *handle, struct inode *inode)
{
struct ext4_extent_header *eh;
eh = ext_inode_hdr(inode);
eh->eh_depth = 0;
eh->eh_entries = 0;
eh->eh_magic = EXT4_EXT_MAGIC;
eh->eh_max = cpu_to_le16(ext4_ext_space_root(inode, 0));
ext4_mark_inode_dirty(handle, inode);
}
struct ext4_ext_path *
ext4_find_extent(struct inode *inode, ext4_lblk_t block,
struct ext4_ext_path **orig_path, int flags)
{
struct ext4_extent_header *eh;
struct buffer_head *bh;
struct ext4_ext_path *path = orig_path ? *orig_path : NULL;
short int depth, i, ppos = 0;
int ret;
gfp_t gfp_flags = GFP_NOFS;
if (flags & EXT4_EX_NOFAIL)
gfp_flags |= __GFP_NOFAIL;
eh = ext_inode_hdr(inode);
depth = ext_depth(inode);
if (depth < 0 || depth > EXT4_MAX_EXTENT_DEPTH) {
EXT4_ERROR_INODE(inode, "inode has invalid extent depth: %d",
depth);
ret = -EFSCORRUPTED;
goto err;
}
if (path) {
ext4_ext_drop_refs(path);
if (depth > path[0].p_maxdepth) {
kfree(path);
*orig_path = path = NULL;
}
}
if (!path) {
/* account possible depth increase */
path = kcalloc(depth + 2, sizeof(struct ext4_ext_path),
gfp_flags);
if (unlikely(!path))
return ERR_PTR(-ENOMEM);
path[0].p_maxdepth = depth + 1;
}
path[0].p_hdr = eh;
path[0].p_bh = NULL;
i = depth;
if (!(flags & EXT4_EX_NOCACHE) && depth == 0)
ext4_cache_extents(inode, eh);
/* walk through the tree */
while (i) {
ext_debug(inode, "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 = ext4_idx_pblock(path[ppos].p_idx);
path[ppos].p_depth = i;
path[ppos].p_ext = NULL;
bh = read_extent_tree_block(inode, path[ppos].p_block, --i,
flags);
if (IS_ERR(bh)) {
ret = PTR_ERR(bh);
goto err;
}
eh = ext_block_hdr(bh);
ppos++;
path[ppos].p_bh = bh;
path[ppos].p_hdr = eh;
}
path[ppos].p_depth = i;
path[ppos].p_ext = NULL;
path[ppos].p_idx = NULL;
/* find extent */
ext4_ext_binsearch(inode, path + ppos, block);
/* if not an empty leaf */
if (path[ppos].p_ext)
path[ppos].p_block = ext4_ext_pblock(path[ppos].p_ext);
ext4_ext_show_path(inode, path);
return path;
err:
ext4_ext_drop_refs(path);
kfree(path);
if (orig_path)
*orig_path = NULL;
return ERR_PTR(ret);
}
/*
* ext4_ext_insert_index:
* insert new index [@logical;@ptr] into the block at @curp;
* check where to insert: before @curp or after @curp
*/
static int ext4_ext_insert_index(handle_t *handle, struct inode *inode,
struct ext4_ext_path *curp,
int logical, ext4_fsblk_t ptr)
{
struct ext4_extent_idx *ix;
int len, err;
err = ext4_ext_get_access(handle, inode, curp);
if (err)
return err;
if (unlikely(logical == le32_to_cpu(curp->p_idx->ei_block))) {
EXT4_ERROR_INODE(inode,
"logical %d == ei_block %d!",
logical, le32_to_cpu(curp->p_idx->ei_block));
return -EFSCORRUPTED;
}
if (unlikely(le16_to_cpu(curp->p_hdr->eh_entries)
>= le16_to_cpu(curp->p_hdr->eh_max))) {
EXT4_ERROR_INODE(inode,
"eh_entries %d >= eh_max %d!",
le16_to_cpu(curp->p_hdr->eh_entries),
le16_to_cpu(curp->p_hdr->eh_max));
return -EFSCORRUPTED;
}
if (logical > le32_to_cpu(curp->p_idx->ei_block)) {
/* insert after */
ext_debug(inode, "insert new index %d after: %llu\n",
logical, ptr);
ix = curp->p_idx + 1;
} else {
/* insert before */
ext_debug(inode, "insert new index %d before: %llu\n",
logical, ptr);
ix = curp->p_idx;
}
len = EXT_LAST_INDEX(curp->p_hdr) - ix + 1;
BUG_ON(len < 0);
if (len > 0) {
ext_debug(inode, "insert new index %d: "
"move %d indices from 0x%p to 0x%p\n",
logical, len, ix, ix + 1);
memmove(ix + 1, ix, len * sizeof(struct ext4_extent_idx));
}
if (unlikely(ix > EXT_MAX_INDEX(curp->p_hdr))) {
EXT4_ERROR_INODE(inode, "ix > EXT_MAX_INDEX!");
return -EFSCORRUPTED;
}
ix->ei_block = cpu_to_le32(logical);
ext4_idx_store_pblock(ix, ptr);
le16_add_cpu(&curp->p_hdr->eh_entries, 1);
if (unlikely(ix > EXT_LAST_INDEX(curp->p_hdr))) {
EXT4_ERROR_INODE(inode, "ix > EXT_LAST_INDEX!");
return -EFSCORRUPTED;
}
err = ext4_ext_dirty(handle, inode, curp);
ext4_std_error(inode->i_sb, err);
return err;
}
/*
* ext4_ext_split:
* inserts new subtree into the path, using free index entry
* at depth @at:
* - allocates all needed blocks (new leaf and all intermediate index blocks)
* - makes decision where to split
* - moves remaining extents and index entries (right to the split point)
* into the newly allocated blocks
* - initializes subtree
*/
static int ext4_ext_split(handle_t *handle, struct inode *inode,
unsigned int flags,
struct ext4_ext_path *path,
struct ext4_extent *newext, int at)
{
struct buffer_head *bh = NULL;
int depth = ext_depth(inode);
struct ext4_extent_header *neh;
struct ext4_extent_idx *fidx;
int i = at, k, m, a;
ext4_fsblk_t newblock, oldblock;
__le32 border;
ext4_fsblk_t *ablocks = NULL; /* array of allocated blocks */
gfp_t gfp_flags = GFP_NOFS;
int err = 0;
size_t ext_size = 0;
if (flags & EXT4_EX_NOFAIL)
gfp_flags |= __GFP_NOFAIL;
/* make decision: where to split? */
/* FIXME: now decision is simplest: at current extent */
/* if current leaf will be split, then we should use
* border from split point */
if (unlikely(path[depth].p_ext > EXT_MAX_EXTENT(path[depth].p_hdr))) {
EXT4_ERROR_INODE(inode, "p_ext > EXT_MAX_EXTENT!");
return -EFSCORRUPTED;
}
if (path[depth].p_ext != EXT_MAX_EXTENT(path[depth].p_hdr)) {
border = path[depth].p_ext[1].ee_block;
ext_debug(inode, "leaf will be split."
" next leaf starts at %d\n",
le32_to_cpu(border));
} else {
border = newext->ee_block;
ext_debug(inode, "leaf will be added."
" next leaf starts at %d\n",
le32_to_cpu(border));
}
/*
* If error occurs, then we break processing
* and mark filesystem read-only. index won't
* be inserted and tree will be in consistent
* state. Next mount will repair buffers too.
*/
/*
* Get array to track all allocated blocks.
* We need this to handle errors and free blocks
* upon them.
*/
ablocks = kcalloc(depth, sizeof(ext4_fsblk_t), gfp_flags);
if (!ablocks)
return -ENOMEM;
/* allocate all needed blocks */
ext_debug(inode, "allocate %d blocks for indexes/leaf\n", depth - at);
for (a = 0; a < depth - at; a++) {
newblock = ext4_ext_new_meta_block(handle, inode, path,
newext, &err, flags);
if (newblock == 0)
goto cleanup;
ablocks[a] = newblock;
}
/* initialize new leaf */
newblock = ablocks[--a];
if (unlikely(newblock == 0)) {
EXT4_ERROR_INODE(inode, "newblock == 0!");
err = -EFSCORRUPTED;
goto cleanup;
}
bh = sb_getblk_gfp(inode->i_sb, newblock, __GFP_MOVABLE | GFP_NOFS);
if (unlikely(!bh)) {
err = -ENOMEM;
goto cleanup;
}
lock_buffer(bh);
err = ext4_journal_get_create_access(handle, bh);
if (err)
goto cleanup;
neh = ext_block_hdr(bh);
neh->eh_entries = 0;
neh->eh_max = cpu_to_le16(ext4_ext_space_block(inode, 0));
neh->eh_magic = EXT4_EXT_MAGIC;
neh->eh_depth = 0;
/* move remainder of path[depth] to the new leaf */
if (unlikely(path[depth].p_hdr->eh_entries !=
path[depth].p_hdr->eh_max)) {
EXT4_ERROR_INODE(inode, "eh_entries %d != eh_max %d!",
path[depth].p_hdr->eh_entries,
path[depth].p_hdr->eh_max);
err = -EFSCORRUPTED;
goto cleanup;
}
/* start copy from next extent */
m = EXT_MAX_EXTENT(path[depth].p_hdr) - path[depth].p_ext++;
ext4_ext_show_move(inode, path, newblock, depth);
if (m) {
struct ext4_extent *ex;
ex = EXT_FIRST_EXTENT(neh);
memmove(ex, path[depth].p_ext, sizeof(struct ext4_extent) * m);
le16_add_cpu(&neh->eh_entries, m);
}
/* zero out unused area in the extent block */
ext_size = sizeof(struct ext4_extent_header) +
sizeof(struct ext4_extent) * le16_to_cpu(neh->eh_entries);
memset(bh->b_data + ext_size, 0, inode->i_sb->s_blocksize - ext_size);
ext4_extent_block_csum_set(inode, neh);
set_buffer_uptodate(bh);
unlock_buffer(bh);
err = ext4_handle_dirty_metadata(handle, inode, bh);
if (err)
goto cleanup;
brelse(bh);
bh = NULL;
/* correct old leaf */
if (m) {
err = ext4_ext_get_access(handle, inode, path + depth);
if (err)
goto cleanup;
le16_add_cpu(&path[depth].p_hdr->eh_entries, -m);
err = ext4_ext_dirty(handle, inode, path + depth);
if (err)
goto cleanup;
}
/* create intermediate indexes */
k = depth - at - 1;
if (unlikely(k < 0)) {
EXT4_ERROR_INODE(inode, "k %d < 0!", k);
err = -EFSCORRUPTED;
goto cleanup;
}
if (k)
ext_debug(inode, "create %d intermediate indices\n", k);
/* insert new index into current index block */
/* current depth stored in i var */
i = depth - 1;
while (k--) {
oldblock = newblock;
newblock = ablocks[--a];
bh = sb_getblk(inode->i_sb, newblock);
if (unlikely(!bh)) {
err = -ENOMEM;
goto cleanup;
}
lock_buffer(bh);
err = ext4_journal_get_create_access(handle, bh);
if (err)
goto cleanup;
neh = ext_block_hdr(bh);
neh->eh_entries = cpu_to_le16(1);
neh->eh_magic = EXT4_EXT_MAGIC;
neh->eh_max = cpu_to_le16(ext4_ext_space_block_idx(inode, 0));
neh->eh_depth = cpu_to_le16(depth - i);
fidx = EXT_FIRST_INDEX(neh);
fidx->ei_block = border;
ext4_idx_store_pblock(fidx, oldblock);
ext_debug(inode, "int.index at %d (block %llu): %u -> %llu\n",
i, newblock, le32_to_cpu(border), oldblock);
/* move remainder of path[i] to the new index block */
if (unlikely(EXT_MAX_INDEX(path[i].p_hdr) !=
EXT_LAST_INDEX(path[i].p_hdr))) {
EXT4_ERROR_INODE(inode,
"EXT_MAX_INDEX != EXT_LAST_INDEX ee_block %d!",
le32_to_cpu(path[i].p_ext->ee_block));
err = -EFSCORRUPTED;
goto cleanup;
}
/* start copy indexes */
m = EXT_MAX_INDEX(path[i].p_hdr) - path[i].p_idx++;
ext_debug(inode, "cur 0x%p, last 0x%p\n", path[i].p_idx,
EXT_MAX_INDEX(path[i].p_hdr));
ext4_ext_show_move(inode, path, newblock, i);
if (m) {
memmove(++fidx, path[i].p_idx,
sizeof(struct ext4_extent_idx) * m);
le16_add_cpu(&neh->eh_entries, m);
}
/* zero out unused area in the extent block */
ext_size = sizeof(struct ext4_extent_header) +
(sizeof(struct ext4_extent) * le16_to_cpu(neh->eh_entries));
memset(bh->b_data + ext_size, 0,
inode->i_sb->s_blocksize - ext_size);
ext4_extent_block_csum_set(inode, neh);
set_buffer_uptodate(bh);
unlock_buffer(bh);
err = ext4_handle_dirty_metadata(handle, inode, bh);
if (err)
goto cleanup;
brelse(bh);
bh = NULL;
/* correct old index */
if (m) {
err = ext4_ext_get_access(handle, inode, path + i);
if (err)
goto cleanup;
le16_add_cpu(&path[i].p_hdr->eh_entries, -m);
err = ext4_ext_dirty(handle, inode, path + i);
if (err)
goto cleanup;
}
i--;
}
/* insert new index */
err = ext4_ext_insert_index(handle, inode, path + at,
le32_to_cpu(border), newblock);
cleanup:
if (bh) {
if (buffer_locked(bh))
unlock_buffer(bh);
brelse(bh);
}
if (err) {
/* free all allocated blocks in error case */
for (i = 0; i < depth; i++) {
if (!ablocks[i])
continue;
ext4_free_blocks(handle, inode, NULL, ablocks[i], 1,
EXT4_FREE_BLOCKS_METADATA);
}
}
kfree(ablocks);
return err;
}
/*
* ext4_ext_grow_indepth:
* implements tree growing procedure:
* - allocates new block
* - moves top-level data (index block or leaf) into the new block
* - initializes new top-level, creating index that points to the
* just created block
*/
static int ext4_ext_grow_indepth(handle_t *handle, struct inode *inode,
unsigned int flags)
{
struct ext4_extent_header *neh;
struct buffer_head *bh;
ext4_fsblk_t newblock, goal = 0;
struct ext4_super_block *es = EXT4_SB(inode->i_sb)->s_es;
int err = 0;
size_t ext_size = 0;
/* Try to prepend new index to old one */
if (ext_depth(inode))
goal = ext4_idx_pblock(EXT_FIRST_INDEX(ext_inode_hdr(inode)));
if (goal > le32_to_cpu(es->s_first_data_block)) {
flags |= EXT4_MB_HINT_TRY_GOAL;
goal--;
} else
goal = ext4_inode_to_goal_block(inode);
newblock = ext4_new_meta_blocks(handle, inode, goal, flags,
NULL, &err);
if (newblock == 0)
return err;
bh = sb_getblk_gfp(inode->i_sb, newblock, __GFP_MOVABLE | GFP_NOFS);
if (unlikely(!bh))
return -ENOMEM;
lock_buffer(bh);
err = ext4_journal_get_create_access(handle, bh);
if (err) {
unlock_buffer(bh);
goto out;
}
ext_size = sizeof(EXT4_I(inode)->i_data);
/* move top-level index/leaf into new block */
memmove(bh->b_data, EXT4_I(inode)->i_data, ext_size);
/* zero out unused area in the extent block */
memset(bh->b_data + ext_size, 0, inode->i_sb->s_blocksize - ext_size);
/* set size of new block */
neh = ext_block_hdr(bh);
/* old root could have indexes or leaves
* so calculate e_max right way */
if (ext_depth(inode))
neh->eh_max = cpu_to_le16(ext4_ext_space_block_idx(inode, 0));
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);
err = ext4_handle_dirty_metadata(handle, inode, bh);
if (err)
goto out;
/* Update top-level index: num,max,pointer */
neh = ext_inode_hdr(inode);
neh->eh_entries = cpu_to_le16(1);
ext4_idx_store_pblock(EXT_FIRST_INDEX(neh), newblock);
if (neh->eh_depth == 0) {
/* Root extent block becomes index block */
neh->eh_max = cpu_to_le16(ext4_ext_space_root_idx(inode, 0));
EXT_FIRST_INDEX(neh)->ei_block =
EXT_FIRST_EXTENT(neh)->ee_block;
}
ext_debug(inode, "new root: num %d(%d), lblock %d, ptr %llu\n",
le16_to_cpu(neh->eh_entries), le16_to_cpu(neh->eh_max),
le32_to_cpu(EXT_FIRST_INDEX(neh)->ei_block),
ext4_idx_pblock(EXT_FIRST_INDEX(neh)));
le16_add_cpu(&neh->eh_depth, 1);
err = ext4_mark_inode_dirty(handle, inode);
out:
brelse(bh);
return err;
}
/*
* ext4_ext_create_new_leaf:
* finds empty index and adds new leaf.
* if no free index is found, then it requests in-depth growing.
*/
static int ext4_ext_create_new_leaf(handle_t *handle, struct inode *inode,
unsigned int mb_flags,
unsigned int gb_flags,
struct ext4_ext_path **ppath,
struct ext4_extent *newext)
{
struct ext4_ext_path *path = *ppath;
struct ext4_ext_path *curp;
int depth, i, err = 0;
repeat:
i = depth = ext_depth(inode);
/* walk up to the tree and look for free index entry */
curp = path + depth;
while (i > 0 && !EXT_HAS_FREE_INDEX(curp)) {
i--;
curp--;
}
/* we use already allocated block for index block,
* so subsequent data blocks should be contiguous */
if (EXT_HAS_FREE_INDEX(curp)) {
/* if we found index with free entry, then use that
* entry: create all needed subtree and add new leaf */
err = ext4_ext_split(handle, inode, mb_flags, path, newext, i);
if (err)
goto out;
/* refill path */
path = ext4_find_extent(inode,
(ext4_lblk_t)le32_to_cpu(newext->ee_block),
ppath, gb_flags);
if (IS_ERR(path))
err = PTR_ERR(path);
} else {
/* tree is full, time to grow in depth */
err = ext4_ext_grow_indepth(handle, inode, mb_flags);
if (err)
goto out;
/* refill path */
path = ext4_find_extent(inode,
(ext4_lblk_t)le32_to_cpu(newext->ee_block),
ppath, gb_flags);
if (IS_ERR(path)) {
err = PTR_ERR(path);
goto out;
}
/*
* only first (depth 0 -> 1) produces free space;
* in all other cases we have to split the grown tree
*/
depth = ext_depth(inode);
if (path[depth].p_hdr->eh_entries == path[depth].p_hdr->eh_max) {
/* now we need to split */
goto repeat;
}
}
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
*/
static 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;
if (unlikely(path == NULL)) {
EXT4_ERROR_INODE(inode, "path == NULL *logical %d!", *logical);
return -EFSCORRUPTED;
}
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)) {
if (unlikely(EXT_FIRST_EXTENT(path[depth].p_hdr) != ex)) {
EXT4_ERROR_INODE(inode,
"EXT_FIRST_EXTENT != ex *logical %d ee_block %d!",
*logical, le32_to_cpu(ex->ee_block));
return -EFSCORRUPTED;
}
while (--depth >= 0) {
ix = path[depth].p_idx;
if (unlikely(ix != EXT_FIRST_INDEX(path[depth].p_hdr))) {
EXT4_ERROR_INODE(inode,
"ix (%d) != EXT_FIRST_INDEX (%d) (depth %d)!",
ix != NULL ? le32_to_cpu(ix->ei_block) : 0,
EXT_FIRST_INDEX(path[depth].p_hdr) != NULL ?
le32_to_cpu(EXT_FIRST_INDEX(path[depth].p_hdr)->ei_block) : 0,
depth);
return -EFSCORRUPTED;
}
}
return 0;
}
if (unlikely(*logical < (le32_to_cpu(ex->ee_block) + ee_len))) {
EXT4_ERROR_INODE(inode,
"logical %d < ee_block %d + ee_len %d!",
*logical, le32_to_cpu(ex->ee_block), ee_len);
return -EFSCORRUPTED;
}
*logical = le32_to_cpu(ex->ee_block) + ee_len - 1;
*phys = ext4_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 largest allocated block, the function
* returns 0 at @phys
* return value contains 0 (success) or error code
*/
static int ext4_ext_search_right(struct inode *inode,
struct ext4_ext_path *path,
ext4_lblk_t *logical, ext4_fsblk_t *phys,
struct ext4_extent **ret_ex)
{
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; /* Note, NOT eh_depth; depth from top of tree */
int ee_len;
if (unlikely(path == NULL)) {
EXT4_ERROR_INODE(inode, "path == NULL *logical %d!", *logical);
return -EFSCORRUPTED;
}
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)) {
if (unlikely(EXT_FIRST_EXTENT(path[depth].p_hdr) != ex)) {
EXT4_ERROR_INODE(inode,
"first_extent(path[%d].p_hdr) != ex",
depth);
return -EFSCORRUPTED;
}
while (--depth >= 0) {
ix = path[depth].p_idx;
if (unlikely(ix != EXT_FIRST_INDEX(path[depth].p_hdr))) {
EXT4_ERROR_INODE(inode,
"ix != EXT_FIRST_INDEX *logical %d!",
*logical);
return -EFSCORRUPTED;
}
}
goto found_extent;
}
if (unlikely(*logical < (le32_to_cpu(ex->ee_block) + ee_len))) {
EXT4_ERROR_INODE(inode,
"logical %d < ee_block %d + ee_len %d!",
*logical, le32_to_cpu(ex->ee_block), ee_len);
return -EFSCORRUPTED;
}
if (ex != EXT_LAST_EXTENT(path[depth].p_hdr)) {
/* next allocated block in this leaf */
ex++;
goto found_extent;
}
/* 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))
goto got_index;
}
/* we've gone up to the root and found no index to the right */
return 0;
got_index:
/* we've found index to the right, let's
* follow it and find the closest allocated
* block to the right */
ix++;
block = ext4_idx_pblock(ix);
while (++depth < path->p_depth) {
/* subtract from p_depth to get proper eh_depth */
bh = read_extent_tree_block(inode, block,
path->p_depth - depth, 0);
if (IS_ERR(bh))
return PTR_ERR(bh);
eh = ext_block_hdr(bh);
ix = EXT_FIRST_INDEX(eh);
block = ext4_idx_pblock(ix);
put_bh(bh);
}
bh = read_extent_tree_block(inode, block, path->p_depth - depth, 0);
if (IS_ERR(bh))
return PTR_ERR(bh);
eh = ext_block_hdr(bh);
ex = EXT_FIRST_EXTENT(eh);
found_extent:
*logical = le32_to_cpu(ex->ee_block);
*phys = ext4_ext_pblock(ex);
*ret_ex = ex;
if (bh)
put_bh(bh);
return 0;
}
/*
* ext4_ext_next_allocated_block:
* returns allocated block in subsequent extent or EXT_MAX_BLOCKS.
* NOTE: it considers block number from index entry as
* allocated block. Thus, index entries have to be consistent
* with leaves.
*/
ext4_lblk_t
ext4_ext_next_allocated_block(struct ext4_ext_path *path)
{
int depth;
BUG_ON(path == NULL);
depth = path->p_depth;
if (depth == 0 && path->p_ext == NULL)
return EXT_MAX_BLOCKS;
while (depth >= 0) {
struct ext4_ext_path *p = &path[depth];
if (depth == path->p_depth) {
/* leaf */
if (p->p_ext && p->p_ext != EXT_LAST_EXTENT(p->p_hdr))
return le32_to_cpu(p->p_ext[1].ee_block);
} else {
/* index */
if (p->p_idx != EXT_LAST_INDEX(p->p_hdr))
return le32_to_cpu(p->p_idx[1].ei_block);
}
depth--;
}
return EXT_MAX_BLOCKS;
}
/*
* ext4_ext_next_leaf_block:
* returns first allocated block from next leaf or EXT_MAX_BLOCKS
*/
static ext4_lblk_t ext4_ext_next_leaf_block(struct ext4_ext_path *path)
{
int depth;
BUG_ON(path == NULL);
depth = path->p_depth;
/* zero-tree has no leaf blocks at all */
if (depth == 0)
return EXT_MAX_BLOCKS;
/* go to index block */
depth--;
while (depth >= 0) {
if (path[depth].p_idx !=
EXT_LAST_INDEX(path[depth].p_hdr))
return (ext4_lblk_t)
le32_to_cpu(path[depth].p_idx[1].ei_block);
depth--;
}
return EXT_MAX_BLOCKS;
}
/*
* ext4_ext_correct_indexes:
* if leaf gets modified and modified extent is first in the leaf,
* then we have to correct all indexes above.
* TODO: do we need to correct tree in all cases?
*/
static int ext4_ext_correct_indexes(handle_t *handle, struct inode *inode,
struct ext4_ext_path *path)
{
struct ext4_extent_header *eh;
int depth = ext_depth(inode);
struct ext4_extent *ex;
__le32 border;
int k, err = 0;
eh = path[depth].p_hdr;
ex = path[depth].p_ext;
if (unlikely(ex == NULL || eh == NULL)) {
EXT4_ERROR_INODE(inode,
"ex %p == NULL or eh %p == NULL", ex, eh);
return -EFSCORRUPTED;
}
if (depth == 0) {
/* there is no tree at all */
return 0;
}
if (ex != EXT_FIRST_EXTENT(eh)) {
/* we correct tree if first leaf got modified only */
return 0;
}
/*
* TODO: we need correction if border is smaller than current one
*/
k = depth - 1;
border = path[depth].p_ext->ee_block;
err = ext4_ext_get_access(handle, inode, path + k);
if (err)
return err;
path[k].p_idx->ei_block = border;
err = ext4_ext_dirty(handle, inode, path + k);
if (err)
return err;
while (k--) {
/* change all left-side indexes */
if (path[k+1].p_idx != EXT_FIRST_INDEX(path[k+1].p_hdr))
break;
err = ext4_ext_get_access(handle, inode, path + k);
if (err)
break;
path[k].p_idx->ei_block = border;
err = ext4_ext_dirty(handle, inode, path + k);
if (err)
break;
}
return err;
}
static int ext4_can_extents_be_merged(struct inode *inode,
struct ext4_extent *ex1,
struct ext4_extent *ex2)
{
unsigned short ext1_ee_len, ext2_ee_len;
if (ext4_ext_is_unwritten(ex1) != ext4_ext_is_unwritten(ex2))
return 0;
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;
if (ext1_ee_len + ext2_ee_len > EXT_INIT_MAX_LEN)
return 0;
if (ext4_ext_is_unwritten(ex1) &&
ext1_ee_len + ext2_ee_len > EXT_UNWRITTEN_MAX_LEN)
return 0;
#ifdef AGGRESSIVE_TEST
if (ext1_ee_len >= 4)
return 0;
#endif
if (ext4_ext_pblock(ex1) + ext1_ee_len == ext4_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.
*/
static int ext4_ext_try_to_merge_right(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, unwritten;
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! */
unwritten = ext4_ext_is_unwritten(ex);
ex->ee_len = cpu_to_le16(ext4_ext_get_actual_len(ex)
+ ext4_ext_get_actual_len(ex + 1));
if (unwritten)
ext4_ext_mark_unwritten(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(inode, "eh->eh_entries = 0!");
}
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,
ext4_free_metadata_revoke_credits(inode->i_sb, 1)))
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);
path[1].p_maxdepth = path[0].p_maxdepth;
memcpy(path[0].p_hdr, path[1].p_hdr, s);
path[0].p_depth = 0;
path[0].p_ext = EXT_FIRST_EXTENT(path[0].p_hdr) +
(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);
}
/*
* This function tries to merge the @ex extent to neighbours in the tree, then
* tries to collapse the extent tree into the 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;
depth = ext_depth(inode);
BUG_ON(path[depth].p_hdr == NULL);
eh = path[depth].p_hdr;
if (ex > EXT_FIRST_EXTENT(eh))
merge_done = ext4_ext_try_to_merge_right(inode, path, ex - 1);
if (!merge_done)
(void) ext4_ext_try_to_merge_right(inode, path, ex);
ext4_ext_try_to_merge_up(handle, inode, path);
}
/*
* check if a portion of the "newext" extent overlaps with an
* existing extent.
*
* If there is an overlap discovered, it updates the length of the newext
* such that there will be no overlap, and then returns 1.
* If there is no overlap found, it returns 0.
*/
static unsigned int ext4_ext_check_overlap(struct ext4_sb_info *sbi,
struct inode *inode,
struct ext4_extent *newext,
struct ext4_ext_path *path)
{
ext4_lblk_t b1, b2;
unsigned int depth, len1;
unsigned int ret = 0;
b1 = le32_to_cpu(newext->ee_block);
len1 = ext4_ext_get_actual_len(newext);
depth = ext_depth(inode);
if (!path[depth].p_ext)
goto out;
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
* is before the requested block(s)
*/
if (b2 < b1) {
b2 = ext4_ext_next_allocated_block(path);
if (b2 == EXT_MAX_BLOCKS)
goto out;
b2 = EXT4_LBLK_CMASK(sbi, b2);
}
/* check for wrap through zero on extent logical start block*/
if (b1 + len1 < b1) {
len1 = EXT_MAX_BLOCKS - b1;
newext->ee_len = cpu_to_le16(len1);
ret = 1;
}
/* check for overlap */
if (b1 + len1 > b2) {
newext->ee_len = cpu_to_le16(b2 - b1);
ret = 1;
}
out:
return ret;
}
/*
* ext4_ext_insert_extent:
* tries to merge requsted extent into the existing extent or
* inserts requested extent as new one into the tree,
* creating new leaf in the no-space case.
*/
int ext4_ext_insert_extent(handle_t *handle, struct inode *inode,
struct ext4_ext_path **ppath,
struct ext4_extent *newext, int gb_flags)
{
struct ext4_ext_path *path = *ppath;
struct ext4_extent_header *eh;
struct ext4_extent *ex, *fex;
struct ext4_extent *nearex; /* nearest extent */
struct ext4_ext_path *npath = NULL;
int depth, len, err;
ext4_lblk_t next;
int mb_flags = 0, unwritten;
if (gb_flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE)
mb_flags |= EXT4_MB_DELALLOC_RESERVED;
if (unlikely(ext4_ext_get_actual_len(newext) == 0)) {
EXT4_ERROR_INODE(inode, "ext4_ext_get_actual_len(newext) == 0");
return -EFSCORRUPTED;
}
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 -EFSCORRUPTED;
}
/* try to insert block into found extent and return */
if (ex && !(gb_flags & EXT4_GET_BLOCKS_PRE_IO)) {
/*
* Try to see whether we should rather test the extent on
* right from ex, or from the left of ex. This is because
* ext4_find_extent() can return either extent on the
* left, or on the right from the searched position. This
* will make merging more effective.
*/
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(inode, "append [%d]%d block to %u:[%d]%d"
"(from %llu)\n",
ext4_ext_is_unwritten(newext),
ext4_ext_get_actual_len(newext),
le32_to_cpu(ex->ee_block),
ext4_ext_is_unwritten(ex),
ext4_ext_get_actual_len(ex),
ext4_ext_pblock(ex));
err = ext4_ext_get_access(handle, inode,
path + depth);
if (err)
return err;
unwritten = ext4_ext_is_unwritten(ex);
ex->ee_len = cpu_to_le16(ext4_ext_get_actual_len(ex)
+ ext4_ext_get_actual_len(newext));
if (unwritten)
ext4_ext_mark_unwritten(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(inode, "prepend %u[%d]%d block to %u:[%d]%d"
"(from %llu)\n",
le32_to_cpu(newext->ee_block),
ext4_ext_is_unwritten(newext),
ext4_ext_get_actual_len(newext),
le32_to_cpu(ex->ee_block),
ext4_ext_is_unwritten(ex),
ext4_ext_get_actual_len(ex),
ext4_ext_pblock(ex));
err = ext4_ext_get_access(handle, inode,
path + depth);
if (err)
return err;
unwritten = ext4_ext_is_unwritten(ex);
ex->ee_block = newext->ee_block;
ext4_ext_store_pblock(ex, ext4_ext_pblock(newext));
ex->ee_len = cpu_to_le16(ext4_ext_get_actual_len(ex)
+ ext4_ext_get_actual_len(newext));
if (unwritten)
ext4_ext_mark_unwritten(ex);
eh = path[depth].p_hdr;
nearex = ex;
goto merge;
}
}
depth = ext_depth(inode);
eh = path[depth].p_hdr;
if (le16_to_cpu(eh->eh_entries) < le16_to_cpu(eh->eh_max))
goto has_space;
/* probably next leaf has space for us? */
fex = EXT_LAST_EXTENT(eh);
next = EXT_MAX_BLOCKS;
if (le32_to_cpu(newext->ee_block) > le32_to_cpu(fex->ee_block))
next = ext4_ext_next_leaf_block(path);
if (next != EXT_MAX_BLOCKS) {
ext_debug(inode, "next leaf block - %u\n", next);
BUG_ON(npath != NULL);
npath = ext4_find_extent(inode, next, NULL, gb_flags);
if (IS_ERR(npath))
return PTR_ERR(npath);
BUG_ON(npath->p_depth != path->p_depth);
eh = npath[depth].p_hdr;
if (le16_to_cpu(eh->eh_entries) < le16_to_cpu(eh->eh_max)) {
ext_debug(inode, "next leaf isn't full(%d)\n",
le16_to_cpu(eh->eh_entries));
path = npath;
goto has_space;
}
ext_debug(inode, "next leaf has no free space(%d,%d)\n",
le16_to_cpu(eh->eh_entries), le16_to_cpu(eh->eh_max));
}
/*
* There is no free space in the found leaf.
* We're gonna add a new leaf in the tree.
*/
if (gb_flags & EXT4_GET_BLOCKS_METADATA_NOFAIL)
mb_flags |= EXT4_MB_USE_RESERVED;
err = ext4_ext_create_new_leaf(handle, inode, mb_flags, gb_flags,
ppath, newext);
if (err)
goto cleanup;
depth = ext_depth(inode);
eh = path[depth].p_hdr;
has_space:
nearex = path[depth].p_ext;
err = ext4_ext_get_access(handle, inode, path + depth);
if (err)
goto cleanup;
if (!nearex) {
/* there is no extent in this leaf, create first one */
ext_debug(inode, "first extent in the leaf: %u:%llu:[%d]%d\n",
le32_to_cpu(newext->ee_block),
ext4_ext_pblock(newext),
ext4_ext_is_unwritten(newext),
ext4_ext_get_actual_len(newext));
nearex = EXT_FIRST_EXTENT(eh);
} else {
if (le32_to_cpu(newext->ee_block)
> le32_to_cpu(nearex->ee_block)) {
/* Insert after */
ext_debug(inode, "insert %u:%llu:[%d]%d before: "
"nearest %p\n",
le32_to_cpu(newext->ee_block),
ext4_ext_pblock(newext),
ext4_ext_is_unwritten(newext),
ext4_ext_get_actual_len(newext),
nearex);
nearex++;
} else {
/* Insert before */
BUG_ON(newext->ee_block == nearex->ee_block);
ext_debug(inode, "insert %u:%llu:[%d]%d after: "
"nearest %p\n",
le32_to_cpu(newext->ee_block),
ext4_ext_pblock(newext),
ext4_ext_is_unwritten(newext),
ext4_ext_get_actual_len(newext),
nearex);
}
len = EXT_LAST_EXTENT(eh) - nearex + 1;
if (len > 0) {
ext_debug(inode, "insert %u:%llu:[%d]%d: "
"move %d extents from 0x%p to 0x%p\n",
le32_to_cpu(newext->ee_block),
ext4_ext_pblock(newext),
ext4_ext_is_unwritten(newext),
ext4_ext_get_actual_len(newext),
len, nearex, nearex + 1);
memmove(nearex + 1, nearex,
len * sizeof(struct ext4_extent));
}
}
le16_add_cpu(&eh->eh_entries, 1);
path[depth].p_ext = nearex;
nearex->ee_block = newext->ee_block;
ext4_ext_store_pblock(nearex, ext4_ext_pblock(newext));
nearex->ee_len = newext->ee_len;
merge:
/* try to merge extents */
if (!(gb_flags & EXT4_GET_BLOCKS_PRE_IO))
ext4_ext_try_to_merge(handle, inode, path, nearex);
/* 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 + path->p_depth);
cleanup:
ext4_ext_drop_refs(npath);
kfree(npath);
return err;
}
static int ext4_fill_es_cache_info(struct inode *inode,
ext4_lblk_t block, ext4_lblk_t num,
struct fiemap_extent_info *fieinfo)
{
ext4_lblk_t next, end = block + num - 1;
struct extent_status es;
unsigned char blksize_bits = inode->i_sb->s_blocksize_bits;
unsigned int flags;
int err;
while (block <= end) {
next = 0;
flags = 0;
if (!ext4_es_lookup_extent(inode, block, &next, &es))
break;
if (ext4_es_is_unwritten(&es))
flags |= FIEMAP_EXTENT_UNWRITTEN;
if (ext4_es_is_delayed(&es))
flags |= (FIEMAP_EXTENT_DELALLOC |
FIEMAP_EXTENT_UNKNOWN);
if (ext4_es_is_hole(&es))
flags |= EXT4_FIEMAP_EXTENT_HOLE;
if (next == 0)
flags |= FIEMAP_EXTENT_LAST;
if (flags & (FIEMAP_EXTENT_DELALLOC|
EXT4_FIEMAP_EXTENT_HOLE))
es.es_pblk = 0;
else
es.es_pblk = ext4_es_pblock(&es);
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 (next == 0)
break;
block = next;
if (err < 0)
return err;
if (err == 1)
return 0;
}
return 0;
}
/*
* ext4_ext_determine_hole - determine hole around given block
* @inode: inode we lookup in
* @path: path in extent tree to @lblk
* @lblk: pointer to logical block around which we want to determine hole
*
* Determine hole length (and start if easily possible) around given logical
* block. We don't try too hard to find the beginning of the hole but @path
* actually points to extent before @lblk, we provide it.
*
* The function returns the length of a hole starting at @lblk. We update @lblk
* to the beginning of the hole if we managed to find it.
*/
static ext4_lblk_t ext4_ext_determine_hole(struct inode *inode,
struct ext4_ext_path *path,
ext4_lblk_t *lblk)
{
int depth = ext_depth(inode);
struct ext4_extent *ex;
ext4_lblk_t len;
ex = path[depth].p_ext;
if (ex == NULL) {
/* there is no extent yet, so gap is [0;-] */
*lblk = 0;
len = EXT_MAX_BLOCKS;
} else if (*lblk < le32_to_cpu(ex->ee_block)) {
len = le32_to_cpu(ex->ee_block) - *lblk;
} else if (*lblk >= le32_to_cpu(ex->ee_block)
+ ext4_ext_get_actual_len(ex)) {
ext4_lblk_t next;
*lblk = le32_to_cpu(ex->ee_block) + ext4_ext_get_actual_len(ex);
next = ext4_ext_next_allocated_block(path);
BUG_ON(next == *lblk);
len = next - *lblk;
} else {
BUG();
}
return len;
}
/*
* ext4_ext_put_gap_in_cache:
* calculate boundaries of the gap that the requested block fits into
* and cache this gap
*/
static void
ext4_ext_put_gap_in_cache(struct inode *inode, ext4_lblk_t hole_start,
ext4_lblk_t hole_len)
{
struct extent_status es;
ext4_es_find_extent_range(inode, &ext4_es_is_delayed, hole_start,
hole_start + hole_len - 1, &es);
if (es.es_len) {
/* There's delayed extent containing lblock? */
if (es.es_lblk <= hole_start)
return;
hole_len = min(es.es_lblk - hole_start, hole_len);
}
ext_debug(inode, " -> %u:%u\n", hole_start, hole_len);
ext4_es_insert_extent(inode, hole_start, hole_len, ~0,
EXTENT_STATUS_HOLE);
}
/*
* 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, int depth)
{
int err;
ext4_fsblk_t leaf;
/* free index block */
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");
return -EFSCORRUPTED;
}
err = ext4_ext_get_access(handle, inode, path);
if (err)
return err;
if (path->p_idx != EXT_LAST_INDEX(path->p_hdr)) {
int len = EXT_LAST_INDEX(path->p_hdr) - path->p_idx;
len *= sizeof(struct ext4_extent_idx);
memmove(path->p_idx, path->p_idx + 1, len);
}
le16_add_cpu(&path->p_hdr->eh_entries, -1);
err = ext4_ext_dirty(handle, inode, path);
if (err)
return err;
ext_debug(inode, "index is empty, remove it, free block %llu\n", leaf);
trace_ext4_ext_rm_idx(inode, leaf);
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;
}
/*
* ext4_ext_calc_credits_for_single_extent:
* This routine returns max. credits that needed to insert an extent
* to the extent tree.
* When pass the actual path, the caller should calculate credits
* under i_data_sem.
*/
int ext4_ext_calc_credits_for_single_extent(struct inode *inode, int nrblocks,
struct ext4_ext_path *path)
{
if (path) {
int depth = ext_depth(inode);
int ret = 0;
/* probably there is space in leaf? */
if (le16_to_cpu(path[depth].p_hdr->eh_entries)
< le16_to_cpu(path[depth].p_hdr->eh_max)) {
/*
* There are some space in the leaf tree, no
* need to account for leaf block credit
*
* bitmaps and block group descriptor blocks
* and other metadata blocks still need to be
* accounted.
*/
/* 1 bitmap, 1 block group descriptor */
ret = 2 + EXT4_META_TRANS_BLOCKS(inode->i_sb);
return ret;
}
}
return ext4_chunk_trans_blocks(inode, nrblocks);
}
/*
* How many index/leaf blocks need to change/allocate to add @extents extents?
*
* If we add a single extent, then in the worse case, each tree level
* index/leaf need to be changed in case of the tree split.
*
* If more extents are inserted, they could cause the whole tree split more
* than once, but this is really rare.
*/
int ext4_ext_index_trans_blocks(struct inode *inode, int extents)
{
int index;
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 (extents <= 1)
index = depth * 2;
else
index = depth * 3;
return index;
}
static inline int get_default_free_blocks_flags(struct inode *inode)
{
if (S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode) ||
ext4_test_inode_flag(inode, EXT4_INODE_EA_INODE))
return EXT4_FREE_BLOCKS_METADATA | EXT4_FREE_BLOCKS_FORGET;
else if (ext4_should_journal_data(inode))
return EXT4_FREE_BLOCKS_FORGET;
return 0;
}
/*
* ext4_rereserve_cluster - increment the reserved cluster count when
* freeing a cluster with a pending reservation
*
* @inode - file containing the cluster
* @lblk - logical block in cluster to be reserved
*
* Increments the reserved cluster count and adjusts quota in a bigalloc
* file system when freeing a partial cluster containing at least one
* delayed and unwritten block. A partial cluster meeting that
* requirement will have a pending reservation. If so, the
* RERESERVE_CLUSTER flag is used when calling ext4_free_blocks() to
* defer reserved and allocated space accounting to a subsequent call
* to this function.
*/
static void ext4_rereserve_cluster(struct inode *inode, ext4_lblk_t lblk)
{
struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
struct ext4_inode_info *ei = EXT4_I(inode);
dquot_reclaim_block(inode, EXT4_C2B(sbi, 1));
spin_lock(&ei->i_block_reservation_lock);
ei->i_reserved_data_blocks++;
percpu_counter_add(&sbi->s_dirtyclusters_counter, 1);
spin_unlock(&ei->i_block_reservation_lock);
percpu_counter_add(&sbi->s_freeclusters_counter, 1);
ext4_remove_pending(inode, lblk);
}
static int ext4_remove_blocks(handle_t *handle, struct inode *inode,
struct ext4_extent *ex,
struct partial_cluster *partial,
ext4_lblk_t from, ext4_lblk_t to)
{
struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
unsigned short ee_len = ext4_ext_get_actual_len(ex);
ext4_fsblk_t last_pblk, pblk;
ext4_lblk_t num;
int flags;
/* only extent tail removal is allowed */
if (from < le32_to_cpu(ex->ee_block) ||
to != le32_to_cpu(ex->ee_block) + ee_len - 1) {
ext4_error(sbi->s_sb,
"strange request: removal(2) %u-%u from %u:%u",
from, to, le32_to_cpu(ex->ee_block), ee_len);
return 0;
}
#ifdef EXTENTS_STATS
spin_lock(&sbi->s_ext_stats_lock);
sbi->s_ext_blocks += ee_len;
sbi->s_ext_extents++;
if (ee_len < sbi->s_ext_min)
sbi->s_ext_min = ee_len;
if (ee_len > sbi->s_ext_max)
sbi->s_ext_max = ee_len;
if (ext_depth(inode) > sbi->s_depth_max)
sbi->s_depth_max = ext_depth(inode);
spin_unlock(&sbi->s_ext_stats_lock);
#endif
trace_ext4_remove_blocks(inode, ex, from, to, partial);
/*
* if we have a partial cluster, and it's different from the
* cluster of the last block in the extent, we free it
*/
last_pblk = ext4_ext_pblock(ex) + ee_len - 1;
if (partial->state != initial &&
partial->pclu != EXT4_B2C(sbi, last_pblk)) {
if (partial->state == tofree) {
flags = get_default_free_blocks_flags(inode);
if (ext4_is_pending(inode, partial->lblk))
flags |= EXT4_FREE_BLOCKS_RERESERVE_CLUSTER;
ext4_free_blocks(handle, inode, NULL,
EXT4_C2B(sbi, partial->pclu),
sbi->s_cluster_ratio, flags);
if (flags & EXT4_FREE_BLOCKS_RERESERVE_CLUSTER)
ext4_rereserve_cluster(inode, partial->lblk);
}
partial->state = initial;
}
num = le32_to_cpu(ex->ee_block) + ee_len - from;
pblk = ext4_ext_pblock(ex) + ee_len - num;
/*
* We free the partial cluster at the end of the extent (if any),
* unless the cluster is used by another extent (partial_cluster
* state is nofree). If a partial cluster exists here, it must be
* shared with the last block in the extent.
*/
flags = get_default_free_blocks_flags(inode);
/* partial, left end cluster aligned, right end unaligned */
if ((EXT4_LBLK_COFF(sbi, to) != sbi->s_cluster_ratio - 1) &&
(EXT4_LBLK_CMASK(sbi, to) >= from) &&
(partial->state != nofree)) {
if (ext4_is_pending(inode, to))
flags |= EXT4_FREE_BLOCKS_RERESERVE_CLUSTER;
ext4_free_blocks(handle, inode, NULL,
EXT4_PBLK_CMASK(sbi, last_pblk),
sbi->s_cluster_ratio, flags);
if (flags & EXT4_FREE_BLOCKS_RERESERVE_CLUSTER)
ext4_rereserve_cluster(inode, to);
partial->state = initial;
flags = get_default_free_blocks_flags(inode);
}
flags |= EXT4_FREE_BLOCKS_NOFREE_LAST_CLUSTER;
/*
* For bigalloc file systems, we never free a partial cluster
* at the beginning of the extent. Instead, we check to see if we
* need to free it on a subsequent call to ext4_remove_blocks,
* or at the end of ext4_ext_rm_leaf or ext4_ext_remove_space.
*/
flags |= EXT4_FREE_BLOCKS_NOFREE_FIRST_CLUSTER;
ext4_free_blocks(handle, inode, NULL, pblk, num, flags);
/* reset the partial cluster if we've freed past it */
if (partial->state != initial && partial->pclu != EXT4_B2C(sbi, pblk))
partial->state = initial;
/*
* If we've freed the entire extent but the beginning is not left
* cluster aligned and is not marked as ineligible for freeing we
* record the partial cluster at the beginning of the extent. It
* wasn't freed by the preceding ext4_free_blocks() call, and we
* need to look farther to the left to determine if it's to be freed
* (not shared with another extent). Else, reset the partial
* cluster - we're either done freeing or the beginning of the
* extent is left cluster aligned.
*/
if (EXT4_LBLK_COFF(sbi, from) && num == ee_len) {
if (partial->state == initial) {
partial->pclu = EXT4_B2C(sbi, pblk);
partial->lblk = from;
partial->state = tofree;
}
} else {
partial->state = initial;
}
return 0;
}
/*
* ext4_ext_rm_leaf() Removes the extents associated with the
* blocks appearing between "start" and "end". Both "start"
* and "end" must appear in the same extent or EIO is returned.
*
* @handle: The journal handle
* @inode: The files inode
* @path: The path to the leaf
* @partial_cluster: The cluster which we'll have to free if all extents
* has been released from it. However, if this value is
* negative, it's a cluster just to the right of the
* punched region and it must not be freed.
* @start: The first block to remove
* @end: The last block to remove
*/
static int
ext4_ext_rm_leaf(handle_t *handle, struct inode *inode,
struct ext4_ext_path *path,
struct partial_cluster *partial,
ext4_lblk_t start, ext4_lblk_t end)
{
struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
int err = 0, correct_index = 0;
int depth = ext_depth(inode), credits, revoke_credits;
struct ext4_extent_header *eh;
ext4_lblk_t a, b;
unsigned num;
ext4_lblk_t ex_ee_block;
unsigned short ex_ee_len;
unsigned unwritten = 0;
struct ext4_extent *ex;
ext4_fsblk_t pblk;
/* the header must be checked already in ext4_ext_remove_space() */
ext_debug(inode, "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;
if (unlikely(path[depth].p_hdr == NULL)) {
EXT4_ERROR_INODE(inode, "path[%d].p_hdr == NULL", depth);
return -EFSCORRUPTED;
}
/* find where to start removing */
ex = path[depth].p_ext;
if (!ex)
ex = EXT_LAST_EXTENT(eh);
ex_ee_block = le32_to_cpu(ex->ee_block);
ex_ee_len = ext4_ext_get_actual_len(ex);
trace_ext4_ext_rm_leaf(inode, start, ex, partial);
while (ex >= EXT_FIRST_EXTENT(eh) &&
ex_ee_block + ex_ee_len > start) {
if (ext4_ext_is_unwritten(ex))
unwritten = 1;
else
unwritten = 0;
ext_debug(inode, "remove ext %u:[%d]%d\n", ex_ee_block,
unwritten, ex_ee_len);
path[depth].p_ext = ex;
a = ex_ee_block > start ? ex_ee_block : start;
b = ex_ee_block+ex_ee_len - 1 < end ?
ex_ee_block+ex_ee_len - 1 : end;
ext_debug(inode, " border %u:%u\n", a, b);
/* If this extent is beyond the end of the hole, skip it */
if (end < ex_ee_block) {
/*
* We're going to skip this extent and move to another,
* so note that its first cluster is in use to avoid
* freeing it when removing blocks. Eventually, the
* right edge of the truncated/punched region will
* be just to the left.
*/
if (sbi->s_cluster_ratio > 1) {
pblk = ext4_ext_pblock(ex);
partial->pclu = EXT4_B2C(sbi, pblk);
partial->state = nofree;
}
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,
"can not handle truncate %u:%u "
"on extent %u:%u",
start, end, ex_ee_block,
ex_ee_block + ex_ee_len - 1);
err = -EFSCORRUPTED;
goto out;
} else if (a != ex_ee_block) {
/* remove tail of the extent */
num = a - ex_ee_block;
} else {
/* remove whole extent: excellent! */
num = 0;
}
/*
* 3 for leaf, sb, and inode plus 2 (bmap and group
* descriptor) for each block group; assume two block
* groups plus ex_ee_len/blocks_per_block_group for
* the worst case
*/
credits = 7 + 2*(ex_ee_len/EXT4_BLOCKS_PER_GROUP(inode->i_sb));
if (ex == EXT_FIRST_EXTENT(eh)) {
correct_index = 1;
credits += (ext_depth(inode)) + 1;
}
credits += EXT4_MAXQUOTAS_TRANS_BLOCKS(inode->i_sb);
/*
* We may end up freeing some index blocks and data from the
* punched range. Note that partial clusters are accounted for
* by ext4_free_data_revoke_credits().
*/
revoke_credits =
ext4_free_metadata_revoke_credits(inode->i_sb,
ext_depth(inode)) +
ext4_free_data_revoke_credits(inode, b - a + 1);
err = ext4_datasem_ensure_credits(handle, inode, credits,
credits, revoke_credits);
if (err) {
if (err > 0)
err = -EAGAIN;
goto out;
}
err = ext4_ext_get_access(handle, inode, path + depth);
if (err)
goto out;
err = ext4_remove_blocks(handle, inode, ex, partial, a, b);
if (err)
goto out;
if (num == 0)
/* this extent is removed; mark slot entirely unused */
ext4_ext_store_pblock(ex, 0);
ex->ee_len = cpu_to_le16(num);
/*
* Do not mark unwritten if all the blocks in the
* extent have been removed.
*/
if (unwritten && num)
ext4_ext_mark_unwritten(ex);
/*
* If the extent was completely released,
* we need to remove it from the leaf
*/
if (num == 0) {
if (end != EXT_MAX_BLOCKS - 1) {
/*
* For hole punching, we need to scoot all the
* extents up when an extent is removed so that
* we dont have blank extents in the middle
*/
memmove(ex, ex+1, (EXT_LAST_EXTENT(eh) - ex) *
sizeof(struct ext4_extent));
/* Now get rid of the one at the end */
memset(EXT_LAST_EXTENT(eh), 0,
sizeof(struct ext4_extent));
}
le16_add_cpu(&eh->eh_entries, -1);
}
err = ext4_ext_dirty(handle, inode, path + depth);
if (err)
goto out;
ext_debug(inode, "new extent: %u:%u:%llu\n", ex_ee_block, num,
ext4_ext_pblock(ex));
ex--;
ex_ee_block = le32_to_cpu(ex->ee_block);
ex_ee_len = ext4_ext_get_actual_len(ex);
}
if (correct_index && eh->eh_entries)
err = ext4_ext_correct_indexes(handle, inode, path);
/*
* If there's a partial cluster and at least one extent remains in
* the leaf, free the partial cluster if it isn't shared with the
* current extent. If it is shared with the current extent
* we reset the partial cluster because we've reached the start of the
* truncated/punched region and we're done removing blocks.
*/
if (partial->state == tofree && ex >= EXT_FIRST_EXTENT(eh)) {
pblk = ext4_ext_pblock(ex) + ex_ee_len - 1;
if (partial->pclu != EXT4_B2C(sbi, pblk)) {
int flags = get_default_free_blocks_flags(inode);
if (ext4_is_pending(inode, partial->lblk))
flags |= EXT4_FREE_BLOCKS_RERESERVE_CLUSTER;
ext4_free_blocks(handle, inode, NULL,
EXT4_C2B(sbi, partial->pclu),
sbi->s_cluster_ratio, flags);
if (flags & EXT4_FREE_BLOCKS_RERESERVE_CLUSTER)
ext4_rereserve_cluster(inode, partial->lblk);
}
partial->state = initial;
}
/* 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);
out:
return err;
}
/*
* ext4_ext_more_to_rm:
* returns 1 if current index has to be freed (even partial)
*/
static int
ext4_ext_more_to_rm(struct ext4_ext_path *path)
{
BUG_ON(path->p_idx == NULL);
if (path->p_idx < EXT_FIRST_INDEX(path->p_hdr))
return 0;
/*
* if truncate on deeper level happened, it wasn't partial,
* so we have to consider current index for truncation
*/
if (le16_to_cpu(path->p_hdr->eh_entries) == path->p_block)
return 0;
return 1;
}
int ext4_ext_remove_space(struct inode *inode, ext4_lblk_t start,
ext4_lblk_t end)
{
struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
int depth = ext_depth(inode);
struct ext4_ext_path *path = NULL;
struct partial_cluster partial;
handle_t *handle;
int i = 0, err = 0;
partial.pclu = 0;
partial.lblk = 0;
partial.state = initial;
ext_debug(inode, "truncate since %u to %u\n", start, end);
/* probably first extent we're gonna free will be last in block */
handle = ext4_journal_start_with_revoke(inode, EXT4_HT_TRUNCATE,
depth + 1,
ext4_free_metadata_revoke_credits(inode->i_sb, depth));
if (IS_ERR(handle))
return PTR_ERR(handle);
again:
trace_ext4_ext_remove_space(inode, start, end, 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, ex_end, lblk;
ext4_fsblk_t pblk;
/* find extent for or closest extent to this block */
path = ext4_find_extent(inode, end, NULL,
EXT4_EX_NOCACHE | EXT4_EX_NOFAIL);
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 = -EFSCORRUPTED;
}
goto out;
}
ee_block = le32_to_cpu(ex->ee_block);
ex_end = ee_block + ext4_ext_get_actual_len(ex) - 1;
/*
* See if the last block is inside the extent, if so split
* 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 < ex_end) {
/*
* If we're going to split the extent, note that
* the cluster containing the block after 'end' is
* in use to avoid freeing it when removing blocks.
*/
if (sbi->s_cluster_ratio > 1) {
pblk = ext4_ext_pblock(ex) + end - ee_block + 1;
partial.pclu = EXT4_B2C(sbi, pblk);
partial.state = nofree;
}
/*
* 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_force_split_extent_at(handle, inode, &path,
end + 1, 1);
if (err < 0)
goto out;
} else if (sbi->s_cluster_ratio > 1 && end >= ex_end &&
partial.state == initial) {
/*
* If we're punching, there's an extent to the right.
* If the partial cluster hasn't been set, set it to
* that extent's first cluster and its state to nofree
* so it won't be freed should it contain blocks to be
* removed. If it's already set (tofree/nofree), we're
* retrying and keep the original partial cluster info
* so a cluster marked tofree as a result of earlier
* extent removal is not lost.
*/
lblk = ex_end + 1;
err = ext4_ext_search_right(inode, path, &lblk, &pblk,
&ex);
if (err)
goto out;
if (pblk) {
partial.pclu = EXT4_B2C(sbi, pblk);
partial.state = nofree;
}
}
}
/*
* We start scanning from right side, freeing all the blocks
* after i_size and walking into the tree depth-wise.
*/
depth = ext_depth(inode);
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 = kcalloc(depth + 1, sizeof(struct ext4_ext_path),
GFP_NOFS | __GFP_NOFAIL);
if (path == NULL) {
ext4_journal_stop(handle);
return -ENOMEM;
}
path[0].p_maxdepth = 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, 0)) {
err = -EFSCORRUPTED;
goto out;
}
}
err = 0;
while (i >= 0 && err == 0) {
if (i == depth) {
/* this is leaf block */
err = ext4_ext_rm_leaf(handle, inode, path,
&partial, start, end);
/* root level has p_bh == NULL, brelse() eats this */
brelse(path[i].p_bh);
path[i].p_bh = NULL;
i--;
continue;
}
/* this is index block */
if (!path[i].p_hdr) {
ext_debug(inode, "initialize header\n");
path[i].p_hdr = ext_block_hdr(path[i].p_bh);
}
if (!path[i].p_idx) {
/* this level hasn't been touched yet */
path[i].p_idx = EXT_LAST_INDEX(path[i].p_hdr);
path[i].p_block = le16_to_cpu(path[i].p_hdr->eh_entries)+1;
ext_debug(inode, "init index ptr: hdr 0x%p, num %d\n",
path[i].p_hdr,
le16_to_cpu(path[i].p_hdr->eh_entries));
} else {
/* we were already here, see at next index */
path[i].p_idx--;
}
ext_debug(inode, "level %d - index, first 0x%p, cur 0x%p\n",
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(inode, "move to level %d (block %llu)\n",
i + 1, ext4_idx_pblock(path[i].p_idx));
memset(path + i + 1, 0, sizeof(*path));
bh = read_extent_tree_block(inode,
ext4_idx_pblock(path[i].p_idx), depth - i - 1,
EXT4_EX_NOCACHE);
if (IS_ERR(bh)) {
/* should we reset i_size? */
err = PTR_ERR(bh);
break;
}
/* Yield here to deal with large extent trees.
* Should be a no-op if we did IO above. */
cond_resched();
if (WARN_ON(i + 1 > depth)) {
err = -EFSCORRUPTED;
break;
}
path[i + 1].p_bh = bh;
/* save actual number of indexes since this
* number is changed at the next iteration */
path[i].p_block = le16_to_cpu(path[i].p_hdr->eh_entries);
i++;
} else {
/* we finished processing this index, go up */
if (path[i].p_hdr->eh_entries == 0 && i > 0) {
/* index is empty, remove it;
* handle must be already prepared by the
* truncatei_leaf() */
err = ext4_ext_rm_idx(handle, inode, path, i);
}
/* root level has p_bh == NULL, brelse() eats this */
brelse(path[i].p_bh);
path[i].p_bh = NULL;
i--;
ext_debug(inode, "return to level %d\n", i);
}
}
trace_ext4_ext_remove_space_done(inode, start, end, depth, &partial,
path->p_hdr->eh_entries);
/*
* if there's a partial cluster and we have removed the first extent
* in the file, then we also free the partial cluster, if any
*/
if (partial.state == tofree && err == 0) {
int flags = get_default_free_blocks_flags(inode);
if (ext4_is_pending(inode, partial.lblk))
flags |= EXT4_FREE_BLOCKS_RERESERVE_CLUSTER;
ext4_free_blocks(handle, inode, NULL,
EXT4_C2B(sbi, partial.pclu),
sbi->s_cluster_ratio, flags);
if (flags & EXT4_FREE_BLOCKS_RERESERVE_CLUSTER)
ext4_rereserve_cluster(inode, partial.lblk);
partial.state = initial;
}
/* TODO: flexible tree reduction should be here */
if (path->p_hdr->eh_entries == 0) {
/*
* truncate to zero freed all the 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);
}
}
out:
ext4_ext_drop_refs(path);
kfree(path);
path = NULL;
if (err == -EAGAIN)
goto again;
ext4_journal_stop(handle);
return err;
}
/*
* called at mount time
*/
void ext4_ext_init(struct super_block *sb)
{
/*
* possible initialization would be here
*/
if (ext4_has_feature_extents(sb)) {
#if defined(AGGRESSIVE_TEST) || defined(CHECK_BINSEARCH) || defined(EXTENTS_STATS)
printk(KERN_INFO "EXT4-fs: file extents enabled"
#ifdef AGGRESSIVE_TEST
", aggressive tests"
#endif
#ifdef CHECK_BINSEARCH
", check binsearch"
#endif
#ifdef EXTENTS_STATS
", stats"
#endif
"\n");
#endif
#ifdef EXTENTS_STATS
spin_lock_init(&EXT4_SB(sb)->s_ext_stats_lock);
EXT4_SB(sb)->s_ext_min = 1 << 30;
EXT4_SB(sb)->s_ext_max = 0;
#endif
}
}
/*
* called at umount time
*/
void ext4_ext_release(struct super_block *sb)
{
if (!ext4_has_feature_extents(sb))
return;
#ifdef EXTENTS_STATS
if (EXT4_SB(sb)->s_ext_blocks && EXT4_SB(sb)->s_ext_extents) {
struct ext4_sb_info *sbi = EXT4_SB(sb);
printk(KERN_ERR "EXT4-fs: %lu blocks in %lu extents (%lu ave)\n",
sbi->s_ext_blocks, sbi->s_ext_extents,
sbi->s_ext_blocks / sbi->s_ext_extents);
printk(KERN_ERR "EXT4-fs: extents: %lu min, %lu max, max depth %lu\n",
sbi->s_ext_min, sbi->s_ext_max, sbi->s_depth_max);
}
#endif
}
static int ext4_zeroout_es(struct inode *inode, struct ext4_extent *ex)
{
ext4_lblk_t ee_block;
ext4_fsblk_t ee_pblock;
unsigned int ee_len;
ee_block = le32_to_cpu(ex->ee_block);
ee_len = ext4_ext_get_actual_len(ex);
ee_pblock = ext4_ext_pblock(ex);
if (ee_len == 0)
return 0;
return ext4_es_insert_extent(inode, ee_block, ee_len, ee_pblock,
EXTENT_STATUS_WRITTEN);
}
/* 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)
{
ext4_fsblk_t ee_pblock;
unsigned int ee_len;
ee_len = ext4_ext_get_actual_len(ex);
ee_pblock = ext4_ext_pblock(ex);
return ext4_issue_zeroout(inode, le32_to_cpu(ex->ee_block), ee_pblock,
ee_len);
}
/*
* ext4_split_extent_at() splits an extent at given block.
*
* @handle: the journal handle
* @inode: the file inode
* @path: the path to the extent
* @split: the logical block where the extent is splitted.
* @split_flags: indicates if the extent could be zeroout if split fails, and
* the states(init or unwritten) of new extents.
* @flags: flags used to insert new extent to extent tree.
*
*
* Splits extent [a, b] into two extents [a, @split) and [@split, b], states
* of which are deterimined by split_flag.
*
* There are two cases:
* a> the extent are splitted into two extent.
* b> split is not needed, and just mark the extent.
*
* return 0 on success.
*/
static int ext4_split_extent_at(handle_t *handle,
struct inode *inode,
struct ext4_ext_path **ppath,
ext4_lblk_t split,
int split_flag,
int flags)
{
struct ext4_ext_path *path = *ppath;
ext4_fsblk_t newblock;
ext4_lblk_t ee_block;
struct ext4_extent *ex, newex, orig_ex, zero_ex;
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(inode, "logical block %llu\n", (unsigned long long)split);
ext4_ext_show_leaf(inode, path);
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);
newblock = split - ee_block + ext4_ext_pblock(ex);
BUG_ON(split < ee_block || split >= (ee_block + ee_len));
BUG_ON(!ext4_ext_is_unwritten(ex) &&
split_flag & (EXT4_EXT_MAY_ZEROOUT |
EXT4_EXT_MARK_UNWRIT1 |
EXT4_EXT_MARK_UNWRIT2));
err = ext4_ext_get_access(handle, inode, path + depth);
if (err)
goto out;
if (split == ee_block) {
/*
* case b: block @split is the block that the extent begins with
* then we just change the state of the extent, and splitting
* is not needed.
*/
if (split_flag & EXT4_EXT_MARK_UNWRIT2)
ext4_ext_mark_unwritten(ex);
else
ext4_ext_mark_initialized(ex);
if (!(flags & EXT4_GET_BLOCKS_PRE_IO))
ext4_ext_try_to_merge(handle, inode, path, ex);
err = ext4_ext_dirty(handle, inode, path + path->p_depth);
goto out;
}
/* case a */
memcpy(&orig_ex, ex, sizeof(orig_ex));
ex->ee_len = cpu_to_le16(split - ee_block);
if (split_flag & EXT4_EXT_MARK_UNWRIT1)
ext4_ext_mark_unwritten(ex);
/*
* path may lead to new leaf, not to original leaf any more
* after ext4_ext_insert_extent() returns,
*/
err = ext4_ext_dirty(handle, inode, path + depth);
if (err)
goto fix_extent_len;
ex2 = &newex;
ex2->ee_block = cpu_to_le32(split);
ex2->ee_len = cpu_to_le16(ee_len - (split - ee_block));
ext4_ext_store_pblock(ex2, newblock);
if (split_flag & EXT4_EXT_MARK_UNWRIT2)
ext4_ext_mark_unwritten(ex2);
err = ext4_ext_insert_extent(handle, inode, ppath, &newex, flags);
if (err == -ENOSPC && (EXT4_EXT_MAY_ZEROOUT & split_flag)) {
if (split_flag & (EXT4_EXT_DATA_VALID1|EXT4_EXT_DATA_VALID2)) {
if (split_flag & EXT4_EXT_DATA_VALID1) {
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_zeroout_es(inode, &zero_ex);
goto out;
} else if (err)
goto fix_extent_len;
out:
ext4_ext_show_leaf(inode, path);
return err;
fix_extent_len:
ex->ee_len = orig_ex.ee_len;
/*
* Ignore ext4_ext_dirty return value since we are already in error path
* and err is a non-zero error code.
*/
ext4_ext_dirty(handle, inode, path + path->p_depth);
return err;
}
/*
* ext4_split_extents() splits an extent and mark extent which is covered
* by @map as split_flags indicates
*
* It may result in splitting the extent into multiple extents (up to three)
* There are three possibilities:
* a> There is no split required
* b> Splits in two extents: Split is happening at either end of the extent
* c> Splits in three extents: Somone is splitting in middle of the extent
*
*/
static int ext4_split_extent(handle_t *handle,
struct inode *inode,
struct ext4_ext_path **ppath,
struct ext4_map_blocks *map,
int split_flag,
int flags)
{
struct ext4_ext_path *path = *ppath;
ext4_lblk_t ee_block;
struct ext4_extent *ex;
unsigned int ee_len, depth;
int err = 0;
int unwritten;
int split_flag1, flags1;
int allocated = map->m_len;
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);
unwritten = ext4_ext_is_unwritten(ex);
if (map->m_lblk + map->m_len < ee_block + ee_len) {
split_flag1 = split_flag & EXT4_EXT_MAY_ZEROOUT;
flags1 = flags | EXT4_GET_BLOCKS_PRE_IO;
if (unwritten)
split_flag1 |= EXT4_EXT_MARK_UNWRIT1 |
EXT4_EXT_MARK_UNWRIT2;
if (split_flag & EXT4_EXT_DATA_VALID2)
split_flag1 |= EXT4_EXT_DATA_VALID1;
err = ext4_split_extent_at(handle, inode, ppath,
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.
*/
path = ext4_find_extent(inode, map->m_lblk, ppath, flags);
if (IS_ERR(path))
return PTR_ERR(path);
depth = ext_depth(inode);
ex = path[depth].p_ext;
if (!ex) {
EXT4_ERROR_INODE(inode, "unexpected hole at %lu",
(unsigned long) map->m_lblk);
return -EFSCORRUPTED;
}
unwritten = ext4_ext_is_unwritten(ex);
split_flag1 = 0;
if (map->m_lblk >= ee_block) {
split_flag1 = split_flag & EXT4_EXT_DATA_VALID2;
if (unwritten) {
split_flag1 |= EXT4_EXT_MARK_UNWRIT1;
split_flag1 |= split_flag & (EXT4_EXT_MAY_ZEROOUT |
EXT4_EXT_MARK_UNWRIT2);
}
err = ext4_split_extent_at(handle, inode, ppath,
map->m_lblk, split_flag1, flags);
if (err)
goto out;
}
ext4_ext_show_leaf(inode, path);
out:
return err ? err : allocated;
}
/*
* This function is called by ext4_ext_map_blocks() if someone tries to write
* to an unwritten extent. It may result in splitting the unwritten
* extent into multiple extents (up to three - one initialized and two
* unwritten).
* There are three possibilities:
* a> There is no split required: Entire extent should be initialized
* b> Splits in two extents: Write is happening at either end of the extent
* c> Splits in three extents: Somone is writing in middle of the extent
*
* Pre-conditions:
* - The extent pointed to by 'path' is unwritten.
* - The extent pointed to by 'path' contains a superset
* of the logical span [map->m_lblk, map->m_lblk + map->m_len).
*
* Post-conditions on success:
* - the returned value is the number of blocks beyond map->l_lblk
* that are allocated and initialized.
* It is guaranteed to be >= map->m_len.
*/
static int ext4_ext_convert_to_initialized(handle_t *handle,
struct inode *inode,
struct ext4_map_blocks *map,
struct ext4_ext_path **ppath,
int flags)
{
struct ext4_ext_path *path = *ppath;
struct ext4_sb_info *sbi;
struct ext4_extent_header *eh;
struct ext4_map_blocks split_map;
struct ext4_extent zero_ex1, zero_ex2;
struct ext4_extent *ex, *abut_ex;
ext4_lblk_t ee_block, eof_block;
unsigned int ee_len, depth, map_len = map->m_len;
int allocated = 0, max_zeroout = 0;
int err = 0;
int split_flag = EXT4_EXT_DATA_VALID2;
ext_debug(inode, "logical block %llu, max_blocks %u\n",
(unsigned long long)map->m_lblk, map_len);
sbi = EXT4_SB(inode->i_sb);
eof_block = (EXT4_I(inode)->i_disksize + inode->i_sb->s_blocksize - 1)
>> inode->i_sb->s_blocksize_bits;
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);
zero_ex1.ee_len = 0;
zero_ex2.ee_len = 0;
trace_ext4_ext_convert_to_initialized_enter(inode, map, ex);
/* Pre-conditions */
BUG_ON(!ext4_ext_is_unwritten(ex));
BUG_ON(!in_range(map->m_lblk, ee_block, ee_len));
/*
* Attempt to transfer newly initialized blocks from the currently
* unwritten extent to its neighbor. This is much cheaper
* than an insertion followed by a merge as those involve costly
* memmove() calls. Transferring to the left is the common case in
* steady state for workloads doing fallocate(FALLOC_FL_KEEP_SIZE)
* followed by append writes.
*
* Limitations of the current logic:
* - L1: we do not deal with writes covering the whole extent.
* This would require removing the extent if the transfer
* is possible.
* - L2: we only attempt to merge with an extent stored in the
* same extent tree node.
*/
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;
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);
/*
* 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_unwritten(abut_ex)) && /*C1*/
((prev_lblk + prev_len) == ee_block) && /*C2*/
((prev_pblk + prev_len) == ee_pblk) && /*C3*/
(prev_len < (EXT_INIT_MAX_LEN - map_len))) { /*C4*/
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);
/* 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_unwritten(ex); /* Restore the flag */
/* 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_unwritten(abut_ex)) && /*C1*/
((map->m_lblk + map_len) == next_lblk) && /*C2*/
((ee_pblk + ee_len) == next_pblk) && /*C3*/
(next_len < (EXT_INIT_MAX_LEN - map_len))) { /*C4*/
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);
/* 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_unwritten(ex); /* Restore the flag */
/* 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 = map_len;
}
}
if (allocated) {
/* Mark the block containing both extents as dirty */
err = 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);
/*
* It is safe to convert extent to initialized via explicit
* zeroout only if extent is fully inside i_size or new_size.
*/
split_flag |= ee_block + ee_len <= eof_block ? EXT4_EXT_MAY_ZEROOUT : 0;
if (EXT4_EXT_MAY_ZEROOUT & split_flag)
max_zeroout = sbi->s_extent_max_zeroout_kb >>
(inode->i_sb->s_blocksize_bits - 10);
/*
* five cases:
* 1. split the extent into three extents.
* 2. split the extent into two extents, zeroout the head of the first
* extent.
* 3. split the extent into two extents, zeroout the tail of the second
* extent.
* 4. split the extent into two extents with out zeroout.
* 5. no splitting needed, just possibly zeroout the head and / or the
* tail of the extent.
*/
split_map.m_lblk = map->m_lblk;
split_map.m_len = map->m_len;
if (max_zeroout && (allocated > split_map.m_len)) {
if (allocated <= max_zeroout) {
/* case 3 or 5 */
zero_ex1.ee_block =
cpu_to_le32(split_map.m_lblk +
split_map.m_len);
zero_ex1.ee_len =
cpu_to_le16(allocated - split_map.m_len);
ext4_ext_store_pblock(&zero_ex1,
ext4_ext_pblock(ex) + split_map.m_lblk +
split_map.m_len - ee_block);
err = ext4_ext_zeroout(inode, &zero_ex1);
if (err)
goto out;
split_map.m_len = allocated;
}
if (split_map.m_lblk - ee_block + split_map.m_len <
max_zeroout) {
/* case 2 or 5 */
if (split_map.m_lblk != ee_block) {
zero_ex2.ee_block = ex->ee_block;
zero_ex2.ee_len = cpu_to_le16(split_map.m_lblk -
ee_block);
ext4_ext_store_pblock(&zero_ex2,
ext4_ext_pblock(ex));
err = ext4_ext_zeroout(inode, &zero_ex2);
if (err)
goto out;
}
split_map.m_len += split_map.m_lblk - ee_block;
split_map.m_lblk = ee_block;
allocated = map->m_len;
}
}
err = ext4_split_extent(handle, inode, ppath, &split_map, split_flag,
flags);
if (err > 0)
err = 0;
out:
/* If we have gotten a failure, don't zero out status tree */
if (!err) {
err = ext4_zeroout_es(inode, &zero_ex1);
if (!err)
err = ext4_zeroout_es(inode, &zero_ex2);
}
return err ? err : allocated;
}
/*
* This function is called by ext4_ext_map_blocks() from
* ext4_get_blocks_dio_write() when DIO to write
* to an unwritten extent.
*
* Writing to an unwritten extent may result in splitting the unwritten
* extent into multiple initialized/unwritten extents (up to three)
* There are three possibilities:
* a> There is no split required: Entire extent should be unwritten
* b> Splits in two extents: Write is happening at either end of the extent
* c> Splits in three extents: Somone is writing in middle of the extent
*
* This works the same way in the case of initialized -> unwritten conversion.
*
* One of more index blocks maybe needed if the extent tree grow after
* the unwritten extent split. To prevent ENOSPC occur at the IO
* complete, we need to split the unwritten extent before DIO submit
* the IO. The unwritten extent called at this time will be split
* into three unwritten extent(at most). After IO complete, the part
* being filled will be convert to initialized by the end_io callback function
* via ext4_convert_unwritten_extents().
*
* Returns the size of unwritten extent to be written on success.
*/
static int ext4_split_convert_extents(handle_t *handle,
struct inode *inode,
struct ext4_map_blocks *map,
struct ext4_ext_path **ppath,
int flags)
{
struct ext4_ext_path *path = *ppath;
ext4_lblk_t eof_block;
ext4_lblk_t ee_block;
struct ext4_extent *ex;
unsigned int ee_len;
int split_flag = 0, depth;
ext_debug(inode, "logical block %llu, max_blocks %u\n",
(unsigned long long)map->m_lblk, map->m_len);
eof_block = (EXT4_I(inode)->i_disksize + 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;
/*
* It is safe to convert extent to initialized via explicit
* zeroout only if extent is fully insde i_size or new_size.
*/
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);
/* Convert to unwritten */
if (flags & EXT4_GET_BLOCKS_CONVERT_UNWRITTEN) {
split_flag |= EXT4_EXT_DATA_VALID1;
/* Convert to initialized */
} else if (flags & EXT4_GET_BLOCKS_CONVERT) {
split_flag |= ee_block + ee_len <= eof_block ?
EXT4_EXT_MAY_ZEROOUT : 0;
split_flag |= (EXT4_EXT_MARK_UNWRIT2 | EXT4_EXT_DATA_VALID2);
}
flags |= EXT4_GET_BLOCKS_PRE_IO;
return ext4_split_extent(handle, inode, ppath, map, split_flag, flags);
}
static int ext4_convert_unwritten_extents_endio(handle_t *handle,
struct inode *inode,
struct ext4_map_blocks *map,
struct ext4_ext_path **ppath)
{
struct ext4_ext_path *path = *ppath;
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(inode, "logical block %llu, max_blocks %u\n",
(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 CONFIG_EXT4_DEBUG
ext4_warning(inode->i_sb, "Inode (%ld) finished: extent logical block %llu,"
" len %u; IO logical block %llu, len %u",
inode->i_ino, (unsigned long long)ee_block, ee_len,
(unsigned long long)map->m_lblk, map->m_len);
#endif
err = ext4_split_convert_extents(handle, inode, map, ppath,
EXT4_GET_BLOCKS_CONVERT);
if (err < 0)
return err;
path = ext4_find_extent(inode, map->m_lblk, ppath, 0);
if (IS_ERR(path))
return PTR_ERR(path);
depth = ext_depth(inode);
ex = path[depth].p_ext;
}
err = ext4_ext_get_access(handle, inode, path + depth);
if (err)
goto out;
/* first mark the extent as initialized */
ext4_ext_mark_initialized(ex);
/* note: ext4_ext_correct_indexes() isn't needed here because
* borders are not changed
*/
ext4_ext_try_to_merge(handle, inode, path, ex);
/* Mark modified extent as dirty */
err = ext4_ext_dirty(handle, inode, path + path->p_depth);
out:
ext4_ext_show_leaf(inode, path);
return err;
}
static int
convert_initialized_extent(handle_t *handle, struct inode *inode,
struct ext4_map_blocks *map,
struct ext4_ext_path **ppath,
unsigned int *allocated)
{
struct ext4_ext_path *path = *ppath;
struct ext4_extent *ex;
ext4_lblk_t ee_block;
unsigned int ee_len;
int depth;
int err = 0;
/*
* Make sure that the extent is no bigger than we support with
* unwritten extent
*/
if (map->m_len > EXT_UNWRITTEN_MAX_LEN)
map->m_len = EXT_UNWRITTEN_MAX_LEN / 2;
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(inode, "logical block %llu, max_blocks %u\n",
(unsigned long long)ee_block, ee_len);
if (ee_block != map->m_lblk || ee_len > map->m_len) {
err = ext4_split_convert_extents(handle, inode, map, ppath,
EXT4_GET_BLOCKS_CONVERT_UNWRITTEN);
if (err < 0)
return err;
path = ext4_find_extent(inode, map->m_lblk, ppath, 0);
if (IS_ERR(path))
return PTR_ERR(path);
depth = ext_depth(inode);
ex = path[depth].p_ext;
if (!ex) {
EXT4_ERROR_INODE(inode, "unexpected hole at %lu",
(unsigned long) map->m_lblk);
return -EFSCORRUPTED;
}
}
err = ext4_ext_get_access(handle, inode, path + depth);
if (err)
return err;
/* first mark the extent as unwritten */
ext4_ext_mark_unwritten(ex);
/* note: ext4_ext_correct_indexes() isn't needed here because
* borders are not changed
*/
ext4_ext_try_to_merge(handle, inode, path, ex);
/* Mark modified extent as dirty */
err = ext4_ext_dirty(handle, inode, path + path->p_depth);
if (err)
return err;
ext4_ext_show_leaf(inode, path);
ext4_update_inode_fsync_trans(handle, inode, 1);
map->m_flags |= EXT4_MAP_UNWRITTEN;
if (*allocated > map->m_len)
*allocated = map->m_len;
map->m_len = *allocated;
return 0;
}
static int
ext4_ext_handle_unwritten_extents(handle_t *handle, struct inode *inode,
struct ext4_map_blocks *map,
struct ext4_ext_path **ppath, int flags,
unsigned int allocated, ext4_fsblk_t newblock)
{
struct ext4_ext_path __maybe_unused *path = *ppath;
int ret = 0;
int err = 0;
ext_debug(inode, "logical block %llu, max_blocks %u, flags 0x%x, allocated %u\n",
(unsigned long long)map->m_lblk, map->m_len, flags,
allocated);
ext4_ext_show_leaf(inode, path);
/*
* When writing into unwritten space, we should not fail to
* allocate metadata blocks for the new extent block if needed.
*/
flags |= EXT4_GET_BLOCKS_METADATA_NOFAIL;
trace_ext4_ext_handle_unwritten_extents(inode, map, flags,
allocated, newblock);
/* get_block() before submitting IO, split the extent */
if (flags & EXT4_GET_BLOCKS_PRE_IO) {
ret = ext4_split_convert_extents(handle, inode, map, ppath,
flags | EXT4_GET_BLOCKS_CONVERT);
if (ret < 0) {
err = ret;
goto out2;
}
/*
* shouldn't get a 0 return when splitting an extent unless
* m_len is 0 (bug) or extent has been corrupted
*/
if (unlikely(ret == 0)) {
EXT4_ERROR_INODE(inode,
"unexpected ret == 0, m_len = %u",
map->m_len);
err = -EFSCORRUPTED;
goto out2;
}
map->m_flags |= EXT4_MAP_UNWRITTEN;
goto out;
}
/* IO end_io complete, convert the filled extent to written */
if (flags & EXT4_GET_BLOCKS_CONVERT) {
err = ext4_convert_unwritten_extents_endio(handle, inode, map,
ppath);
if (err < 0)
goto out2;
ext4_update_inode_fsync_trans(handle, inode, 1);
goto map_out;
}
/* buffered IO cases */
/*
* repeat fallocate creation request
* we already have an unwritten extent
*/
if (flags & EXT4_GET_BLOCKS_UNWRIT_EXT) {
map->m_flags |= EXT4_MAP_UNWRITTEN;
goto map_out;
}
/* buffered READ or buffered write_begin() lookup */
if ((flags & EXT4_GET_BLOCKS_CREATE) == 0) {
/*
* 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.
*/
map->m_flags |= EXT4_MAP_UNWRITTEN;
goto out1;
}
/*
* Default case when (flags & EXT4_GET_BLOCKS_CREATE) == 1.
* For buffered writes, at writepage time, etc. Convert a
* discovered unwritten extent to written.
*/
ret = ext4_ext_convert_to_initialized(handle, inode, map, ppath, flags);
if (ret < 0) {
err = ret;
goto out2;
}
ext4_update_inode_fsync_trans(handle, inode, 1);
/*
* shouldn't get a 0 return when converting an unwritten extent
* unless m_len is 0 (bug) or extent has been corrupted
*/
if (unlikely(ret == 0)) {
EXT4_ERROR_INODE(inode, "unexpected ret == 0, m_len = %u",
map->m_len);
err = -EFSCORRUPTED;
goto out2;
}
out:
allocated = ret;
map->m_flags |= EXT4_MAP_NEW;
map_out:
map->m_flags |= EXT4_MAP_MAPPED;
out1:
map->m_pblk = newblock;
if (allocated > map->m_len)
allocated = map->m_len;
map->m_len = allocated;
ext4_ext_show_leaf(inode, path);
out2:
return err ? err : allocated;
}
/*
* get_implied_cluster_alloc - check to see if the requested
* allocation (in the map structure) overlaps with a cluster already
* allocated in an extent.
* @sb The filesystem superblock structure
* @map The requested lblk->pblk mapping
* @ex The extent structure which might contain an implied
* cluster allocation
*
* This function is called by ext4_ext_map_blocks() after we failed to
* find blocks that were already in the inode's extent tree. Hence,
* we know that the beginning of the requested region cannot overlap
* the extent from the inode's extent tree. There are three cases we
* want to catch. The first is this case:
*
* |--- cluster # N--|
* |--- extent ---| |---- requested region ---|
* |==========|
*
* The second case that we need to test for is this one:
*
* |--------- cluster # N ----------------|
* |--- requested region --| |------- extent ----|
* |=======================|
*
* The third case is when the requested region lies between two extents
* within the same cluster:
* |------------- cluster # N-------------|
* |----- ex -----| |---- ex_right ----|
* |------ requested region ------|
* |================|
*
* In each of the above cases, we need to set the map->m_pblk and
* map->m_len so it corresponds to the return the extent labelled as
* "|====|" from cluster #N, since it is already in use for data in
* cluster EXT4_B2C(sbi, map->m_lblk). We will then return 1 to
* signal to ext4_ext_map_blocks() that map->m_pblk should be treated
* as a new "allocated" block region. Otherwise, we will return 0 and
* ext4_ext_map_blocks() will then allocate one or more new clusters
* by calling ext4_mb_new_blocks().
*/
static int get_implied_cluster_alloc(struct super_block *sb,
struct ext4_map_blocks *map,
struct ext4_extent *ex,
struct ext4_ext_path *path)
{
struct ext4_sb_info *sbi = EXT4_SB(sb);
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;
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 extent passed in that we are trying to match */
ex_cluster_start = EXT4_B2C(sbi, ee_block);
ex_cluster_end = EXT4_B2C(sbi, ee_block + ee_len - 1);
/* The requested region passed into ext4_map_blocks() */
rr_cluster_start = EXT4_B2C(sbi, map->m_lblk);
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 = EXT4_PBLK_CMASK(sbi, ee_start) + c_offset;
map->m_len = min(map->m_len,
(unsigned) sbi->s_cluster_ratio - c_offset);
/*
* Check for and handle this case:
*
* |--------- cluster # N-------------|
* |------- extent ----|
* |--- requested region ---|
* |===========|
*/
if (map->m_lblk < ee_block)
map->m_len = min(map->m_len, ee_block - map->m_lblk);
/*
* Check for the case where there is already another allocated
* block to the right of 'ex' but before the end of the cluster.
*
* |------------- cluster # N-------------|
* |----- ex -----| |---- ex_right ----|
* |------ requested region ------|
* |================|
*/
if (map->m_lblk > ee_block) {
ext4_lblk_t next = ext4_ext_next_allocated_block(path);
map->m_len = min(map->m_len, next - map->m_lblk);
}
trace_ext4_get_implied_cluster_alloc_exit(sb, map, 1);
return 1;
}
trace_ext4_get_implied_cluster_alloc_exit(sb, map, 0);
return 0;
}
/*
* 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_map_blocks(handle_t *handle, struct inode *inode,
struct ext4_map_blocks *map, int flags)
{
struct ext4_ext_path *path = NULL;
struct ext4_extent newex, *ex, *ex2;
struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
ext4_fsblk_t newblock = 0, pblk;
int err = 0, depth, ret;
unsigned int allocated = 0, offset = 0;
unsigned int allocated_clusters = 0;
struct ext4_allocation_request ar;
ext4_lblk_t cluster_offset;
ext_debug(inode, "blocks %u/%u requested\n", map->m_lblk, map->m_len);
trace_ext4_ext_map_blocks_enter(inode, map->m_lblk, map->m_len, flags);
/* find extent for this block */
path = ext4_find_extent(inode, map->m_lblk, NULL, 0);
if (IS_ERR(path)) {
err = PTR_ERR(path);
path = NULL;
goto out;
}
depth = ext_depth(inode);
/*
* consistent leaf must not be empty;
* this situation is possible, though, _during_ tree modification;
* this is why assert can't be put in ext4_find_extent()
*/
if (unlikely(path[depth].p_ext == NULL && depth != 0)) {
EXT4_ERROR_INODE(inode, "bad extent address "
"lblock: %lu, depth: %d pblock %lld",
(unsigned long) map->m_lblk, depth,
path[depth].p_block);
err = -EFSCORRUPTED;
goto out;
}
ex = path[depth].p_ext;
if (ex) {
ext4_lblk_t ee_block = le32_to_cpu(ex->ee_block);
ext4_fsblk_t ee_start = ext4_ext_pblock(ex);
unsigned short ee_len;
/*
* unwritten extents are treated as holes, except that
* we split out initialized portions during a write.
*/
ee_len = ext4_ext_get_actual_len(ex);
trace_ext4_ext_show_extent(inode, ee_block, ee_start, ee_len);
/* if found extent covers block, simply return it */
if (in_range(map->m_lblk, ee_block, ee_len)) {
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(inode, "%u fit into %u:%d -> %llu\n",
map->m_lblk, ee_block, ee_len, newblock);
/*
* If the extent is initialized check whether the
* caller wants to convert it to unwritten.
*/
if ((!ext4_ext_is_unwritten(ex)) &&
(flags & EXT4_GET_BLOCKS_CONVERT_UNWRITTEN)) {
err = convert_initialized_extent(handle,
inode, map, &path, &allocated);
goto out;
} else if (!ext4_ext_is_unwritten(ex)) {
map->m_flags |= EXT4_MAP_MAPPED;
map->m_pblk = newblock;
if (allocated > map->m_len)
allocated = map->m_len;
map->m_len = allocated;
ext4_ext_show_leaf(inode, path);
goto out;
}
ret = ext4_ext_handle_unwritten_extents(
handle, inode, map, &path, flags,
allocated, newblock);
if (ret < 0)
err = ret;
else
allocated = ret;
goto out;
}
}
/*
* requested block isn't allocated yet;
* we couldn't try to create block if create flag is zero
*/
if ((flags & EXT4_GET_BLOCKS_CREATE) == 0) {
ext4_lblk_t hole_start, hole_len;
hole_start = map->m_lblk;
hole_len = ext4_ext_determine_hole(inode, path, &hole_start);
/*
* put just found gap into cache to speed up
* subsequent requests
*/
ext4_ext_put_gap_in_cache(inode, hole_start, hole_len);
/* Update hole_len to reflect hole size after map->m_lblk */
if (hole_start != map->m_lblk)
hole_len -= map->m_lblk - hole_start;
map->m_pblk = 0;
map->m_len = min_t(unsigned int, map->m_len, hole_len);
goto out;
}
/*
* Okay, we need to do block allocation.
*/
newex.ee_block = cpu_to_le32(map->m_lblk);
cluster_offset = EXT4_LBLK_COFF(sbi, map->m_lblk);
/*
* If we are doing bigalloc, check to see if the extent returned
* by ext4_find_extent() implies a cluster we can use.
*/
if (cluster_offset && ex &&
get_implied_cluster_alloc(inode->i_sb, map, ex, path)) {
ar.len = allocated = map->m_len;
newblock = map->m_pblk;
goto got_allocated_blocks;
}
/* find neighbour allocated blocks */
ar.lleft = map->m_lblk;
err = ext4_ext_search_left(inode, path, &ar.lleft, &ar.pleft);
if (err)
goto out;
ar.lright = map->m_lblk;
ex2 = NULL;
err = ext4_ext_search_right(inode, path, &ar.lright, &ar.pright, &ex2);
if (err)
goto out;
/* Check if the extent after searching to the right implies a
* cluster we can use. */
if ((sbi->s_cluster_ratio > 1) && ex2 &&
get_implied_cluster_alloc(inode->i_sb, map, ex2, path)) {
ar.len = allocated = map->m_len;
newblock = map->m_pblk;
goto got_allocated_blocks;
}
/*
* 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 unwritten extent this limit is
* EXT_UNWRITTEN_MAX_LEN.
*/
if (map->m_len > EXT_INIT_MAX_LEN &&
!(flags & EXT4_GET_BLOCKS_UNWRIT_EXT))
map->m_len = EXT_INIT_MAX_LEN;
else if (map->m_len > EXT_UNWRITTEN_MAX_LEN &&
(flags & EXT4_GET_BLOCKS_UNWRIT_EXT))
map->m_len = EXT_UNWRITTEN_MAX_LEN;
/* Check if we can really insert (m_lblk)::(m_lblk + m_len) extent */
newex.ee_len = cpu_to_le16(map->m_len);
err = ext4_ext_check_overlap(sbi, inode, &newex, path);
if (err)
allocated = ext4_ext_get_actual_len(&newex);
else
allocated = map->m_len;
/* allocate new block */
ar.inode = inode;
ar.goal = ext4_ext_find_goal(inode, path, map->m_lblk);
ar.logical = map->m_lblk;
/*
* We calculate the offset from the beginning of the cluster
* for the logical block number, since when we allocate a
* physical cluster, the physical block should start at the
* same offset from the beginning of the cluster. This is
* needed so that future calls to get_implied_cluster_alloc()
* work correctly.
*/
offset = EXT4_LBLK_COFF(sbi, map->m_lblk);
ar.len = EXT4_NUM_B2C(sbi, offset+allocated);
ar.goal -= offset;
ar.logical -= offset;
if (S_ISREG(inode->i_mode))
ar.flags = EXT4_MB_HINT_DATA;
else
/* disable in-core preallocation for non-regular files */
ar.flags = 0;
if (flags & EXT4_GET_BLOCKS_NO_NORMALIZE)
ar.flags |= EXT4_MB_HINT_NOPREALLOC;
if (flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE)
ar.flags |= EXT4_MB_DELALLOC_RESERVED;
if (flags & EXT4_GET_BLOCKS_METADATA_NOFAIL)
ar.flags |= EXT4_MB_USE_RESERVED;
newblock = ext4_mb_new_blocks(handle, &ar, &err);
if (!newblock)
goto out;
allocated_clusters = ar.len;
ar.len = EXT4_C2B(sbi, ar.len) - offset;
ext_debug(inode, "allocate new block: goal %llu, found %llu/%u, requested %u\n",
ar.goal, newblock, ar.len, allocated);
if (ar.len > allocated)
ar.len = allocated;
got_allocated_blocks:
/* try to insert new extent into found leaf and return */
pblk = newblock + offset;
ext4_ext_store_pblock(&newex, pblk);
newex.ee_len = cpu_to_le16(ar.len);
/* Mark unwritten */
if (flags & EXT4_GET_BLOCKS_UNWRIT_EXT) {
ext4_ext_mark_unwritten(&newex);
map->m_flags |= EXT4_MAP_UNWRITTEN;
}
err = ext4_ext_insert_extent(handle, inode, &path, &newex, flags);
if (err) {
if (allocated_clusters) {
int fb_flags = 0;
/*
* 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_discard_preallocations(inode);
if (flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE)
fb_flags = EXT4_FREE_BLOCKS_NO_QUOT_UPDATE;
ext4_free_blocks(handle, inode, NULL, newblock,
EXT4_C2B(sbi, allocated_clusters),
fb_flags);
}
goto out;
}
/*
* Reduce the reserved cluster count to reflect successful deferred
* allocation of delayed allocated clusters or direct allocation of
* clusters discovered to be delayed allocated. Once allocated, a
* cluster is not included in the reserved count.
*/
if (test_opt(inode->i_sb, DELALLOC) && allocated_clusters) {
if (flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE) {
/*
* When allocating delayed allocated clusters, simply
* reduce the reserved cluster count and claim quota
*/
ext4_da_update_reserve_space(inode, allocated_clusters,
1);
} else {
ext4_lblk_t lblk, len;
unsigned int n;
/*
* When allocating non-delayed allocated clusters
* (from fallocate, filemap, DIO, or clusters
* allocated when delalloc has been disabled by
* ext4_nonda_switch), reduce the reserved cluster
* count by the number of allocated clusters that
* have previously been delayed allocated. Quota
* has been claimed by ext4_mb_new_blocks() above,
* so release the quota reservations made for any
* previously delayed allocated clusters.
*/
lblk = EXT4_LBLK_CMASK(sbi, map->m_lblk);
len = allocated_clusters << sbi->s_cluster_bits;
n = ext4_es_delayed_clu(inode, lblk, len);
if (n > 0)
ext4_da_update_reserve_space(inode, (int) n, 0);
}
}
/*
* Cache the extent and update transaction to commit on fdatasync only
* when it is _not_ an unwritten extent.
*/
if ((flags & EXT4_GET_BLOCKS_UNWRIT_EXT) == 0)
ext4_update_inode_fsync_trans(handle, inode, 1);
else
ext4_update_inode_fsync_trans(handle, inode, 0);
map->m_flags |= (EXT4_MAP_NEW | EXT4_MAP_MAPPED);
map->m_pblk = pblk;
map->m_len = ar.len;
allocated = map->m_len;
ext4_ext_show_leaf(inode, path);
out:
ext4_ext_drop_refs(path);
kfree(path);
trace_ext4_ext_map_blocks_exit(inode, flags, map,
err ? err : allocated);
return err ? err : allocated;
}
int ext4_ext_truncate(handle_t *handle, struct inode *inode)
{
struct super_block *sb = inode->i_sb;
ext4_lblk_t last_block;
int err = 0;
/*
* TODO: optimization is possible here.
* Probably we need not scan at all,
* because page truncation is enough.
*/
/* we have to know where to truncate from in crash case */
EXT4_I(inode)->i_disksize = inode->i_size;
err = ext4_mark_inode_dirty(handle, inode);
if (err)
return err;
last_block = (inode->i_size + sb->s_blocksize - 1)
>> EXT4_BLOCK_SIZE_BITS(sb);
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)
return err;
retry_remove_space:
err = ext4_ext_remove_space(inode, last_block, EXT_MAX_BLOCKS - 1);
if (err == -ENOMEM) {
cond_resched();
congestion_wait(BLK_RW_ASYNC, HZ/50);
goto retry_remove_space;
}
return err;
}
static int ext4_alloc_file_blocks(struct file *file, ext4_lblk_t offset,
ext4_lblk_t len, loff_t new_size,
int flags)
{
struct inode *inode = file_inode(file);
handle_t *handle;
int ret = 0;
int ret2 = 0, ret3 = 0;
int retries = 0;
int depth = 0;
struct ext4_map_blocks map;
unsigned int credits;
loff_t epos;
BUG_ON(!ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS));
map.m_lblk = offset;
map.m_len = len;
/*
* Don't normalize the request if it can fit in one extent so
* that it doesn't get unnecessarily split into multiple
* extents.
*/
if (len <= EXT_UNWRITTEN_MAX_LEN)
flags |= EXT4_GET_BLOCKS_NO_NORMALIZE;
/*
* credits to insert 1 extent into extent tree
*/
credits = ext4_chunk_trans_blocks(inode, len);
depth = ext_depth(inode);
retry:
while (ret >= 0 && len) {
/*
* Recalculate credits when extent tree depth changes.
*/
if (depth != ext_depth(inode)) {
credits = ext4_chunk_trans_blocks(inode, len);
depth = ext_depth(inode);
}
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) {
ext4_debug("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);
break;
}
map.m_lblk += ret;
map.m_len = len = len - ret;
epos = (loff_t)map.m_lblk << inode->i_blkbits;
inode->i_ctime = current_time(inode);
if (new_size) {
if (epos > new_size)
epos = new_size;
if (ext4_update_inode_size(inode, epos) & 0x1)
inode->i_mtime = inode->i_ctime;
}
ret2 = ext4_mark_inode_dirty(handle, inode);
ext4_update_inode_fsync_trans(handle, inode, 1);
ret3 = ext4_journal_stop(handle);
ret2 = ret3 ? ret3 : ret2;
if (unlikely(ret2))
break;
}
if (ret == -ENOSPC &&
ext4_should_retry_alloc(inode->i_sb, &retries)) {
ret = 0;
goto retry;
}
return ret > 0 ? ret2 : ret;
}
static int ext4_collapse_range(struct inode *inode, loff_t offset, loff_t len);
static int ext4_insert_range(struct inode *inode, loff_t offset, loff_t len);
static long ext4_zero_range(struct file *file, loff_t offset,
loff_t len, int mode)
{
struct inode *inode = file_inode(file);
handle_t *handle = NULL;
unsigned int max_blocks;
loff_t new_size = 0;
int ret = 0;
int flags;
int credits;
int partial_begin, partial_end;
loff_t start, end;
ext4_lblk_t lblk;
unsigned int blkbits = inode->i_blkbits;
trace_ext4_zero_range(inode, offset, len, mode);
/* Call ext4_force_commit to flush all data in case of data=journal. */
if (ext4_should_journal_data(inode)) {
ret = ext4_force_commit(inode->i_sb);
if (ret)
return ret;
}
/*
* Round up offset. This is not fallocate, we neet to zero out
* blocks, so convert interior block aligned part of the range to
* unwritten and possibly manually zero out unaligned parts of the
* range.
*/
start = round_up(offset, 1 << blkbits);
end = round_down((offset + len), 1 << blkbits);
if (start < offset || end > offset + len)
return -EINVAL;
partial_begin = offset & ((1 << blkbits) - 1);
partial_end = (offset + len) & ((1 << blkbits) - 1);
lblk = start >> blkbits;
max_blocks = (end >> blkbits);
if (max_blocks < lblk)
max_blocks = 0;
else
max_blocks -= lblk;
inode_lock(inode);
/*
* Indirect files do not support unwritten extents
*/
if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))) {
ret = -EOPNOTSUPP;
goto out_mutex;
}
if (!(mode & FALLOC_FL_KEEP_SIZE) &&
(offset + len > inode->i_size ||
offset + len > EXT4_I(inode)->i_disksize)) {
new_size = offset + len;
ret = inode_newsize_ok(inode, new_size);
if (ret)
goto out_mutex;
}
flags = EXT4_GET_BLOCKS_CREATE_UNWRIT_EXT;
/* Wait all existing dio workers, newcomers will block on i_mutex */
inode_dio_wait(inode);
/* Preallocate the range including the unaligned edges */
if (partial_begin || partial_end) {
ret = ext4_alloc_file_blocks(file,
round_down(offset, 1 << blkbits) >> blkbits,
(round_up((offset + len), 1 << blkbits) -
round_down(offset, 1 << blkbits)) >> blkbits,
new_size, flags);
if (ret)
goto out_mutex;
}
/* Zero range excluding the unaligned edges */
if (max_blocks > 0) {
flags |= (EXT4_GET_BLOCKS_CONVERT_UNWRITTEN |
EXT4_EX_NOCACHE);
/*
* Prevent page faults from reinstantiating pages we have
* released from page cache.
*/
down_write(&EXT4_I(inode)->i_mmap_sem);
ret = ext4_break_layouts(inode);
if (ret) {
up_write(&EXT4_I(inode)->i_mmap_sem);
goto out_mutex;
}
ret = ext4_update_disksize_before_punch(inode, offset, len);
if (ret) {
up_write(&EXT4_I(inode)->i_mmap_sem);
goto out_mutex;
}
/* Now release the pages and zero block aligned part of pages */
truncate_pagecache_range(inode, start, end - 1);
inode->i_mtime = inode->i_ctime = current_time(inode);
ret = ext4_alloc_file_blocks(file, lblk, max_blocks, new_size,
flags);
up_write(&EXT4_I(inode)->i_mmap_sem);
if (ret)
goto out_mutex;
}
if (!partial_begin && !partial_end)
goto out_mutex;
/*
* In worst case we have to writeout two nonadjacent unwritten
* blocks and update the inode
*/
credits = (2 * ext4_ext_index_trans_blocks(inode, 2)) + 1;
if (ext4_should_journal_data(inode))
credits += 2;
handle = ext4_journal_start(inode, EXT4_HT_MISC, credits);
if (IS_ERR(handle)) {
ret = PTR_ERR(handle);
ext4_std_error(inode->i_sb, ret);
goto out_mutex;
}
inode->i_mtime = inode->i_ctime = current_time(inode);
if (new_size)
ext4_update_inode_size(inode, new_size);
ret = ext4_mark_inode_dirty(handle, inode);
if (unlikely(ret))
goto out_handle;
/* Zero out partial block at the edges of the range */
ret = ext4_zero_partial_blocks(handle, inode, offset, len);
if (ret >= 0)
ext4_update_inode_fsync_trans(handle, inode, 1);
if (file->f_flags & O_SYNC)
ext4_handle_sync(handle);
out_handle:
ext4_journal_stop(handle);
out_mutex:
inode_unlock(inode);
return ret;
}
/*
* preallocate space for a file. This implements ext4's fallocate file
* 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 file *file, int mode, loff_t offset, loff_t len)
{
struct inode *inode = file_inode(file);
loff_t new_size = 0;
unsigned int max_blocks;
int ret = 0;
int flags;
ext4_lblk_t lblk;
unsigned int blkbits = inode->i_blkbits;
/*
* Encrypted inodes can't handle collapse range or insert
* range since we would need to re-encrypt blocks with a
* different IV or XTS tweak (which are based on the logical
* block number).
*/
if (IS_ENCRYPTED(inode) &&
(mode & (FALLOC_FL_COLLAPSE_RANGE | FALLOC_FL_INSERT_RANGE)))
return -EOPNOTSUPP;
/* Return error if mode is not supported */
if (mode & ~(FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE |
FALLOC_FL_COLLAPSE_RANGE | FALLOC_FL_ZERO_RANGE |
FALLOC_FL_INSERT_RANGE))
return -EOPNOTSUPP;
if (mode & FALLOC_FL_PUNCH_HOLE)
return ext4_punch_hole(inode, offset, len);
ret = ext4_convert_inline_data(inode);
if (ret)
return ret;
if (mode & FALLOC_FL_COLLAPSE_RANGE)
return ext4_collapse_range(inode, offset, len);
if (mode & FALLOC_FL_INSERT_RANGE)
return ext4_insert_range(inode, offset, len);
if (mode & FALLOC_FL_ZERO_RANGE)
return ext4_zero_range(file, offset, len, mode);
trace_ext4_fallocate_enter(inode, offset, len, mode);
lblk = offset >> blkbits;
max_blocks = EXT4_MAX_BLOCKS(len, offset, blkbits);
flags = EXT4_GET_BLOCKS_CREATE_UNWRIT_EXT;
inode_lock(inode);
/*
* We only support preallocation for extent-based files only
*/
if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))) {
ret = -EOPNOTSUPP;
goto out;
}
if (!(mode & FALLOC_FL_KEEP_SIZE) &&
(offset + len > inode->i_size ||
offset + len > EXT4_I(inode)->i_disksize)) {
new_size = offset + len;
ret = inode_newsize_ok(inode, new_size);
if (ret)
goto out;
}
/* Wait all existing dio workers, newcomers will block on i_mutex */
inode_dio_wait(inode);
ret = ext4_alloc_file_blocks(file, lblk, max_blocks, new_size, flags);
if (ret)
goto out;
if (file->f_flags & O_SYNC && EXT4_SB(inode->i_sb)->s_journal) {
ret = jbd2_complete_transaction(EXT4_SB(inode->i_sb)->s_journal,
EXT4_I(inode)->i_sync_tid);
}
out:
inode_unlock(inode);
trace_ext4_fallocate_exit(inode, offset, max_blocks, ret);
return ret;
}
/*
* This function convert a range of blocks to written extents
* The caller of this function will pass the start offset and the size.
* all unwritten extents within this range will be converted to
* written extents.
*
* This function is called from the direct IO end io call back
* function, to convert the fallocated extents after IO is completed.
* Returns 0 on success.
*/
int ext4_convert_unwritten_extents(handle_t *handle, struct inode *inode,
loff_t offset, ssize_t len)
{
unsigned int max_blocks;
int ret = 0, ret2 = 0, ret3 = 0;
struct ext4_map_blocks map;
unsigned int blkbits = inode->i_blkbits;
unsigned int credits = 0;
map.m_lblk = offset >> blkbits;
max_blocks = EXT4_MAX_BLOCKS(len, offset, blkbits);
if (!handle) {
/*
* credits to insert 1 extent into extent tree
*/
credits = ext4_chunk_trans_blocks(inode, max_blocks);
}
while (ret >= 0 && ret < max_blocks) {
map.m_lblk += ret;
map.m_len = (max_blocks -= ret);
if (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)
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);
ret2 = ext4_mark_inode_dirty(handle, inode);
if (credits) {
ret3 = ext4_journal_stop(handle);
if (unlikely(ret3))
ret2 = ret3;
}
if (ret <= 0 || ret2)
break;
}
return ret > 0 ? ret2 : ret;
}
int ext4_convert_unwritten_io_end_vec(handle_t *handle, ext4_io_end_t *io_end)
{
int ret, err = 0;
struct ext4_io_end_vec *io_end_vec;
/*
* This is somewhat ugly but the idea is clear: When transaction is
* reserved, everything goes into it. Otherwise we rather start several
* smaller transactions for conversion of each extent separately.
*/
if (handle) {
handle = ext4_journal_start_reserved(handle,
EXT4_HT_EXT_CONVERT);
if (IS_ERR(handle))
return PTR_ERR(handle);
}
list_for_each_entry(io_end_vec, &io_end->list_vec, list) {
ret = ext4_convert_unwritten_extents(handle, io_end->inode,
io_end_vec->offset,
io_end_vec->size);
if (ret)
break;
}
if (handle)
err = ext4_journal_stop(handle);
return ret < 0 ? ret : err;
}
static int ext4_iomap_xattr_fiemap(struct inode *inode, struct iomap *iomap)
{
__u64 physical = 0;
__u64 length = 0;
int blockbits = inode->i_sb->s_blocksize_bits;
int error = 0;
u16 iomap_type;
/* in-inode? */
if (ext4_test_inode_state(inode, EXT4_STATE_XATTR)) {
struct ext4_iloc iloc;
int offset; /* offset of xattr in inode */
error = ext4_get_inode_loc(inode, &iloc);
if (error)
return error;
physical = (__u64)iloc.bh->b_blocknr << blockbits;
offset = EXT4_GOOD_OLD_INODE_SIZE +
EXT4_I(inode)->i_extra_isize;
physical += offset;
length = EXT4_SB(inode->i_sb)->s_inode_size - offset;
brelse(iloc.bh);
iomap_type = IOMAP_INLINE;
} else if (EXT4_I(inode)->i_file_acl) { /* external block */
physical = (__u64)EXT4_I(inode)->i_file_acl << blockbits;
length = inode->i_sb->s_blocksize;
iomap_type = IOMAP_MAPPED;
} else {
/* no in-inode or external block for xattr, so return -ENOENT */
error = -ENOENT;
goto out;
}
iomap->addr = physical;
iomap->offset = 0;
iomap->length = length;
iomap->type = iomap_type;
iomap->flags = 0;
out:
return error;
}
static int ext4_iomap_xattr_begin(struct inode *inode, loff_t offset,
loff_t length, unsigned flags,
struct iomap *iomap, struct iomap *srcmap)
{
int error;
error = ext4_iomap_xattr_fiemap(inode, iomap);
if (error == 0 && (offset >= iomap->length))
error = -ENOENT;
return error;
}
static const struct iomap_ops ext4_iomap_xattr_ops = {
.iomap_begin = ext4_iomap_xattr_begin,
};
static int ext4_fiemap_check_ranges(struct inode *inode, u64 start, u64 *len)
{
u64 maxbytes;
if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))
maxbytes = inode->i_sb->s_maxbytes;
else
maxbytes = EXT4_SB(inode->i_sb)->s_bitmap_maxbytes;
if (*len == 0)
return -EINVAL;
if (start > maxbytes)
return -EFBIG;
/*
* Shrink request scope to what the fs can actually handle.
*/
if (*len > maxbytes || (maxbytes - *len) < start)
*len = maxbytes - start;
return 0;
}
int ext4_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
u64 start, u64 len)
{
int error = 0;
if (fieinfo->fi_flags & FIEMAP_FLAG_CACHE) {
error = ext4_ext_precache(inode);
if (error)
return error;
fieinfo->fi_flags &= ~FIEMAP_FLAG_CACHE;
}
/*
* For bitmap files the maximum size limit could be smaller than
* s_maxbytes, so check len here manually instead of just relying on the
* generic check.
*/
error = ext4_fiemap_check_ranges(inode, start, &len);
if (error)
return error;
if (fieinfo->fi_flags & FIEMAP_FLAG_XATTR) {
fieinfo->fi_flags &= ~FIEMAP_FLAG_XATTR;
return iomap_fiemap(inode, fieinfo, start, len,
&ext4_iomap_xattr_ops);
}
return iomap_fiemap(inode, fieinfo, start, len, &ext4_iomap_report_ops);
}
int ext4_get_es_cache(struct inode *inode, struct fiemap_extent_info *fieinfo,
__u64 start, __u64 len)
{
ext4_lblk_t start_blk, len_blks;
__u64 last_blk;
int error = 0;
if (ext4_has_inline_data(inode)) {
int has_inline;
down_read(&EXT4_I(inode)->xattr_sem);
has_inline = ext4_has_inline_data(inode);
up_read(&EXT4_I(inode)->xattr_sem);
if (has_inline)
return 0;
}
if (fieinfo->fi_flags & FIEMAP_FLAG_CACHE) {
error = ext4_ext_precache(inode);
if (error)
return error;
fieinfo->fi_flags &= ~FIEMAP_FLAG_CACHE;
}
error = fiemap_prep(inode, fieinfo, start, &len, 0);
if (error)
return error;
error = ext4_fiemap_check_ranges(inode, start, &len);
if (error)
return error;
start_blk = start >> inode->i_sb->s_blocksize_bits;
last_blk = (start + len - 1) >> inode->i_sb->s_blocksize_bits;
if (last_blk >= EXT_MAX_BLOCKS)
last_blk = EXT_MAX_BLOCKS-1;
len_blks = ((ext4_lblk_t) last_blk) - start_blk + 1;
/*
* Walk the extent tree gathering extent information
* and pushing extents back to the user.
*/
return ext4_fill_es_cache_info(inode, start_blk, len_blks, fieinfo);
}
/*
* ext4_access_path:
* Function to access the path buffer for marking it dirty.
* It also checks if there are sufficient credits left in the journal handle
* to update path.
*/
static int
ext4_access_path(handle_t *handle, struct inode *inode,
struct ext4_ext_path *path)
{
int credits, err;
if (!ext4_handle_valid(handle))
return 0;
/*
* Check if need to extend journal credits
* 3 for leaf, sb, and inode plus 2 (bmap and group
* descriptor) for each block group; assume two block
* groups
*/
credits = ext4_writepage_trans_blocks(inode);
err = ext4_datasem_ensure_credits(handle, inode, 7, credits, 0);
if (err < 0)
return err;
err = ext4_ext_get_access(handle, inode, path);
return err;
}
/*
* ext4_ext_shift_path_extents:
* Shift the extents of a path structure lying between path[depth].p_ext
* and EXT_LAST_EXTENT(path[depth].p_hdr), by @shift blocks. @SHIFT tells
* if it is right shift or left shift operation.
*/
static int
ext4_ext_shift_path_extents(struct ext4_ext_path *path, ext4_lblk_t shift,
struct inode *inode, handle_t *handle,
enum SHIFT_DIRECTION SHIFT)
{
int depth, err = 0;
struct ext4_extent *ex_start, *ex_last;
bool update = false;
depth = path->p_depth;
while (depth >= 0) {
if (depth == path->p_depth) {
ex_start = path[depth].p_ext;
if (!ex_start)
return -EFSCORRUPTED;
ex_last = EXT_LAST_EXTENT(path[depth].p_hdr);
err = ext4_access_path(handle, inode, path + depth);
if (err)
goto out;
if (ex_start == EXT_FIRST_EXTENT(path[depth].p_hdr))
update = true;
while (ex_start <= ex_last) {
if (SHIFT == SHIFT_LEFT) {
le32_add_cpu(&ex_start->ee_block,
-shift);
/* Try to merge to the left. */
if ((ex_start >
EXT_FIRST_EXTENT(path[depth].p_hdr))
&&
ext4_ext_try_to_merge_right(inode,
path, ex_start - 1))
ex_last--;
else
ex_start++;
} else {
le32_add_cpu(&ex_last->ee_block, shift);
ext4_ext_try_to_merge_right(inode, path,
ex_last);
ex_last--;
}
}
err = ext4_ext_dirty(handle, inode, path + depth);
if (err)
goto out;
if (--depth < 0 || !update)
break;
}
/* Update index too */
err = ext4_access_path(handle, inode, path + depth);
if (err)
goto out;
if (SHIFT == SHIFT_LEFT)
le32_add_cpu(&path[depth].p_idx->ei_block, -shift);
else
le32_add_cpu(&path[depth].p_idx->ei_block, shift);
err = ext4_ext_dirty(handle, inode, path + depth);
if (err)
goto out;
/* we are done if current index is not a starting index */
if (path[depth].p_idx != EXT_FIRST_INDEX(path[depth].p_hdr))
break;
depth--;
}
out:
return err;
}
/*
* ext4_ext_shift_extents:
* All the extents which lies in the range from @start to the last allocated
* block for the @inode are shifted either towards left or right (depending
* upon @SHIFT) by @shift blocks.
* On success, 0 is returned, error otherwise.
*/
static int
ext4_ext_shift_extents(struct inode *inode, handle_t *handle,
ext4_lblk_t start, ext4_lblk_t shift,
enum SHIFT_DIRECTION SHIFT)
{
struct ext4_ext_path *path;
int ret = 0, depth;
struct ext4_extent *extent;
ext4_lblk_t stop, *iterator, ex_start, ex_end;
/* Let path point to the last extent */
path = ext4_find_extent(inode, EXT_MAX_BLOCKS - 1, NULL,
EXT4_EX_NOCACHE);
if (IS_ERR(path))
return PTR_ERR(path);
depth = path->p_depth;
extent = path[depth].p_ext;
if (!extent)
goto out;
stop = le32_to_cpu(extent->ee_block);
/*
* For left shifts, make sure the hole on the left is big enough to
* accommodate the shift. For right shifts, make sure the last extent
* won't be shifted beyond EXT_MAX_BLOCKS.
*/
if (SHIFT == SHIFT_LEFT) {
path = ext4_find_extent(inode, start - 1, &path,
EXT4_EX_NOCACHE);
if (IS_ERR(path))
return PTR_ERR(path);
depth = path->p_depth;
extent = path[depth].p_ext;
if (extent) {
ex_start = le32_to_cpu(extent->ee_block);
ex_end = le32_to_cpu(extent->ee_block) +
ext4_ext_get_actual_len(extent);
} else {
ex_start = 0;
ex_end = 0;
}
if ((start == ex_start && shift > ex_start) ||
(shift > start - ex_end)) {
ret = -EINVAL;
goto out;
}
} else {
if (shift > EXT_MAX_BLOCKS -
(stop + ext4_ext_get_actual_len(extent))) {
ret = -EINVAL;
goto out;
}
}
/*
* In case of left shift, iterator points to start and it is increased
* till we reach stop. In case of right shift, iterator points to stop
* and it is decreased till we reach start.
*/
if (SHIFT == SHIFT_LEFT)
iterator = &start;
else
iterator = &stop;
/*
* Its safe to start updating extents. Start and stop are unsigned, so
* in case of right shift if extent with 0 block is reached, iterator
* becomes NULL to indicate the end of the loop.
*/
while (iterator && start <= stop) {
path = ext4_find_extent(inode, *iterator, &path,
EXT4_EX_NOCACHE);
if (IS_ERR(path))
return PTR_ERR(path);
depth = path->p_depth;
extent = path[depth].p_ext;
if (!extent) {
EXT4_ERROR_INODE(inode, "unexpected hole at %lu",
(unsigned long) *iterator);
return -EFSCORRUPTED;
}
if (SHIFT == SHIFT_LEFT && *iterator >
le32_to_cpu(extent->ee_block)) {
/* Hole, move to the next extent */
if (extent < EXT_LAST_EXTENT(path[depth].p_hdr)) {
path[depth].p_ext++;
} else {
*iterator = ext4_ext_next_allocated_block(path);
continue;
}
}
if (SHIFT == SHIFT_LEFT) {
extent = EXT_LAST_EXTENT(path[depth].p_hdr);
*iterator = le32_to_cpu(extent->ee_block) +
ext4_ext_get_actual_len(extent);
} else {
extent = EXT_FIRST_EXTENT(path[depth].p_hdr);
if (le32_to_cpu(extent->ee_block) > 0)
*iterator = le32_to_cpu(extent->ee_block) - 1;
else
/* Beginning is reached, end of the loop */
iterator = NULL;
/* Update path extent in case we need to stop */
while (le32_to_cpu(extent->ee_block) < start)
extent++;
path[depth].p_ext = extent;
}
ret = ext4_ext_shift_path_extents(path, shift, inode,
handle, SHIFT);
if (ret)
break;
}
out:
ext4_ext_drop_refs(path);
kfree(path);
return ret;
}
/*
* ext4_collapse_range:
* This implements the fallocate's collapse range functionality for ext4
* Returns: 0 and non-zero on error.
*/
static int ext4_collapse_range(struct inode *inode, loff_t offset, loff_t len)
{
struct super_block *sb = inode->i_sb;
ext4_lblk_t punch_start, punch_stop;
handle_t *handle;
unsigned int credits;
loff_t new_size, ioffset;
int ret;
/*
* We need to test this early because xfstests assumes that a
* collapse range of (0, 1) will return EOPNOTSUPP if the file
* system does not support collapse range.
*/
if (!ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))
return -EOPNOTSUPP;
/* Collapse range works only on fs cluster size aligned regions. */
if (!IS_ALIGNED(offset | len, EXT4_CLUSTER_SIZE(sb)))
return -EINVAL;
trace_ext4_collapse_range(inode, offset, len);
punch_start = offset >> EXT4_BLOCK_SIZE_BITS(sb);
punch_stop = (offset + len) >> EXT4_BLOCK_SIZE_BITS(sb);
/* Call ext4_force_commit to flush all data in case of data=journal. */
if (ext4_should_journal_data(inode)) {
ret = ext4_force_commit(inode->i_sb);
if (ret)
return ret;
}
inode_lock(inode);
/*
* There is no need to overlap collapse range with EOF, in which case
* it is effectively a truncate operation
*/
if (offset + len >= inode->i_size) {
ret = -EINVAL;
goto out_mutex;
}
/* Currently just for extent based files */
if (!ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) {
ret = -EOPNOTSUPP;
goto out_mutex;
}
/* Wait for existing dio to complete */
inode_dio_wait(inode);
/*
* Prevent page faults from reinstantiating pages we have released from
* page cache.
*/
down_write(&EXT4_I(inode)->i_mmap_sem);
ret = ext4_break_layouts(inode);
if (ret)
goto out_mmap;
/*
* Need to round down offset to be aligned with page size boundary
* for page size > block size.
*/
ioffset = round_down(offset, PAGE_SIZE);
/*
* Write tail of the last page before removed range since it will get
* removed from the page cache below.
*/
ret = filemap_write_and_wait_range(inode->i_mapping, ioffset, offset);
if (ret)
goto out_mmap;
/*
* Write data that will be shifted to preserve them when discarding
* page cache below. We are also protected from pages becoming dirty
* by i_mmap_sem.
*/
ret = filemap_write_and_wait_range(inode->i_mapping, offset + len,
LLONG_MAX);
if (ret)
goto out_mmap;
truncate_pagecache(inode, ioffset);
credits = ext4_writepage_trans_blocks(inode);
handle = ext4_journal_start(inode, EXT4_HT_TRUNCATE, credits);
if (IS_ERR(handle)) {
ret = PTR_ERR(handle);
goto out_mmap;
}
down_write(&EXT4_I(inode)->i_data_sem);
ext4_discard_preallocations(inode);
ret = ext4_es_remove_extent(inode, punch_start,
EXT_MAX_BLOCKS - punch_start);
if (ret) {
up_write(&EXT4_I(inode)->i_data_sem);
goto out_stop;
}
ret = ext4_ext_remove_space(inode, punch_start, punch_stop - 1);
if (ret) {
up_write(&EXT4_I(inode)->i_data_sem);
goto out_stop;
}
ext4_discard_preallocations(inode);
ret = ext4_ext_shift_extents(inode, handle, punch_stop,
punch_stop - punch_start, SHIFT_LEFT);
if (ret) {
up_write(&EXT4_I(inode)->i_data_sem);
goto out_stop;
}
new_size = inode->i_size - len;
i_size_write(inode, new_size);
EXT4_I(inode)->i_disksize = new_size;
up_write(&EXT4_I(inode)->i_data_sem);
if (IS_SYNC(inode))
ext4_handle_sync(handle);
inode->i_mtime = inode->i_ctime = current_time(inode);
ret = ext4_mark_inode_dirty(handle, inode);
ext4_update_inode_fsync_trans(handle, inode, 1);
out_stop:
ext4_journal_stop(handle);
out_mmap:
up_write(&EXT4_I(inode)->i_mmap_sem);
out_mutex:
inode_unlock(inode);
return ret;
}
/*
* ext4_insert_range:
* This function implements the FALLOC_FL_INSERT_RANGE flag of fallocate.
* The data blocks starting from @offset to the EOF are shifted by @len
* towards right to create a hole in the @inode. Inode size is increased
* by len bytes.
* Returns 0 on success, error otherwise.
*/
static int ext4_insert_range(struct inode *inode, loff_t offset, loff_t len)
{
struct super_block *sb = inode->i_sb;
handle_t *handle;
struct ext4_ext_path *path;
struct ext4_extent *extent;
ext4_lblk_t offset_lblk, len_lblk, ee_start_lblk = 0;
unsigned int credits, ee_len;
int ret = 0, depth, split_flag = 0;
loff_t ioffset;
/*
* We need to test this early because xfstests assumes that an
* insert range of (0, 1) will return EOPNOTSUPP if the file
* system does not support insert range.
*/
if (!ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))
return -EOPNOTSUPP;
/* Insert range works only on fs cluster size aligned regions. */
if (!IS_ALIGNED(offset | len, EXT4_CLUSTER_SIZE(sb)))
return -EINVAL;
trace_ext4_insert_range(inode, offset, len);
offset_lblk = offset >> EXT4_BLOCK_SIZE_BITS(sb);
len_lblk = len >> EXT4_BLOCK_SIZE_BITS(sb);
/* Call ext4_force_commit to flush all data in case of data=journal */
if (ext4_should_journal_data(inode)) {
ret = ext4_force_commit(inode->i_sb);
if (ret)
return ret;
}
inode_lock(inode);
/* Currently just for extent based files */
if (!ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) {
ret = -EOPNOTSUPP;
goto out_mutex;
}
/* Check whether the maximum file size would be exceeded */
if (len > inode->i_sb->s_maxbytes - inode->i_size) {
ret = -EFBIG;
goto out_mutex;
}
/* Offset must be less than i_size */
if (offset >= inode->i_size) {
ret = -EINVAL;
goto out_mutex;
}
/* Wait for existing dio to complete */
inode_dio_wait(inode);
/*
* Prevent page faults from reinstantiating pages we have released from
* page cache.
*/
down_write(&EXT4_I(inode)->i_mmap_sem);
ret = ext4_break_layouts(inode);
if (ret)
goto out_mmap;
/*
* Need to round down to align start offset to page size boundary
* for page size > block size.
*/
ioffset = round_down(offset, PAGE_SIZE);
/* Write out all dirty pages */
ret = filemap_write_and_wait_range(inode->i_mapping, ioffset,
LLONG_MAX);
if (ret)
goto out_mmap;
truncate_pagecache(inode, ioffset);
credits = ext4_writepage_trans_blocks(inode);
handle = ext4_journal_start(inode, EXT4_HT_TRUNCATE, credits);
if (IS_ERR(handle)) {
ret = PTR_ERR(handle);
goto out_mmap;
}
/* Expand file to avoid data loss if there is error while shifting */
inode->i_size += len;
EXT4_I(inode)->i_disksize += len;
inode->i_mtime = inode->i_ctime = current_time(inode);
ret = ext4_mark_inode_dirty(handle, inode);
if (ret)
goto out_stop;
down_write(&EXT4_I(inode)->i_data_sem);
ext4_discard_preallocations(inode);
path = ext4_find_extent(inode, offset_lblk, NULL, 0);
if (IS_ERR(path)) {
up_write(&EXT4_I(inode)->i_data_sem);
goto out_stop;
}
depth = ext_depth(inode);
extent = path[depth].p_ext;
if (extent) {
ee_start_lblk = le32_to_cpu(extent->ee_block);
ee_len = ext4_ext_get_actual_len(extent);
/*
* If offset_lblk is not the starting block of extent, split
* the extent @offset_lblk
*/
if ((offset_lblk > ee_start_lblk) &&
(offset_lblk < (ee_start_lblk + ee_len))) {
if (ext4_ext_is_unwritten(extent))
split_flag = EXT4_EXT_MARK_UNWRIT1 |
EXT4_EXT_MARK_UNWRIT2;
ret = ext4_split_extent_at(handle, inode, &path,
offset_lblk, split_flag,
EXT4_EX_NOCACHE |
EXT4_GET_BLOCKS_PRE_IO |
EXT4_GET_BLOCKS_METADATA_NOFAIL);
}
ext4_ext_drop_refs(path);
kfree(path);
if (ret < 0) {
up_write(&EXT4_I(inode)->i_data_sem);
goto out_stop;
}
} else {
ext4_ext_drop_refs(path);
kfree(path);
}
ret = ext4_es_remove_extent(inode, offset_lblk,
EXT_MAX_BLOCKS - offset_lblk);
if (ret) {
up_write(&EXT4_I(inode)->i_data_sem);
goto out_stop;
}
/*
* if offset_lblk lies in a hole which is at start of file, use
* ee_start_lblk to shift extents
*/
ret = ext4_ext_shift_extents(inode, handle,
ee_start_lblk > offset_lblk ? ee_start_lblk : offset_lblk,
len_lblk, SHIFT_RIGHT);
up_write(&EXT4_I(inode)->i_data_sem);
if (IS_SYNC(inode))
ext4_handle_sync(handle);
if (ret >= 0)
ext4_update_inode_fsync_trans(handle, inode, 1);
out_stop:
ext4_journal_stop(handle);
out_mmap:
up_write(&EXT4_I(inode)->i_mmap_sem);
out_mutex:
inode_unlock(inode);
return ret;
}
/**
* ext4_swap_extents() - Swap extents between two inodes
* @handle: handle for this transaction
* @inode1: First inode
* @inode2: Second inode
* @lblk1: Start block for first inode
* @lblk2: Start block for second inode
* @count: Number of blocks to swap
* @unwritten: Mark second inode's extents as unwritten after swap
* @erp: Pointer to save error value
*
* This helper routine does exactly what is promise "swap extents". All other
* stuff such as page-cache locking consistency, bh mapping consistency or
* extent's data copying must be performed by caller.
* Locking:
* i_mutex is held for both inodes
* i_data_sem is locked for write for both inodes
* Assumptions:
* All pages from requested range are locked for both inodes
*/
int
ext4_swap_extents(handle_t *handle, struct inode *inode1,
struct inode *inode2, ext4_lblk_t lblk1, ext4_lblk_t lblk2,
ext4_lblk_t count, int unwritten, int *erp)
{
struct ext4_ext_path *path1 = NULL;
struct ext4_ext_path *path2 = NULL;
int replaced_count = 0;
BUG_ON(!rwsem_is_locked(&EXT4_I(inode1)->i_data_sem));
BUG_ON(!rwsem_is_locked(&EXT4_I(inode2)->i_data_sem));
BUG_ON(!inode_is_locked(inode1));
BUG_ON(!inode_is_locked(inode2));
*erp = ext4_es_remove_extent(inode1, lblk1, count);
if (unlikely(*erp))
return 0;
*erp = ext4_es_remove_extent(inode2, lblk2, count);
if (unlikely(*erp))
return 0;
while (count) {
struct ext4_extent *ex1, *ex2, tmp_ex;
ext4_lblk_t e1_blk, e2_blk;
int e1_len, e2_len, len;
int split = 0;
path1 = ext4_find_extent(inode1, lblk1, NULL, EXT4_EX_NOCACHE);
if (IS_ERR(path1)) {
*erp = PTR_ERR(path1);
path1 = NULL;
finish:
count = 0;
goto repeat;
}
path2 = ext4_find_extent(inode2, lblk2, NULL, EXT4_EX_NOCACHE);
if (IS_ERR(path2)) {
*erp = PTR_ERR(path2);
path2 = NULL;
goto finish;
}
ex1 = path1[path1->p_depth].p_ext;
ex2 = path2[path2->p_depth].p_ext;
/* Do we have somthing to swap ? */
if (unlikely(!ex2 || !ex1))
goto finish;
e1_blk = le32_to_cpu(ex1->ee_block);
e2_blk = le32_to_cpu(ex2->ee_block);
e1_len = ext4_ext_get_actual_len(ex1);
e2_len = ext4_ext_get_actual_len(ex2);
/* Hole handling */
if (!in_range(lblk1, e1_blk, e1_len) ||
!in_range(lblk2, e2_blk, e2_len)) {
ext4_lblk_t next1, next2;
/* if hole after extent, then go to next extent */
next1 = ext4_ext_next_allocated_block(path1);
next2 = ext4_ext_next_allocated_block(path2);
/* If hole before extent, then shift to that extent */
if (e1_blk > lblk1)
next1 = e1_blk;
if (e2_blk > lblk2)
next2 = e2_blk;
/* Do we have something to swap */
if (next1 == EXT_MAX_BLOCKS || next2 == EXT_MAX_BLOCKS)
goto finish;
/* Move to the rightest boundary */
len = next1 - lblk1;
if (len < next2 - lblk2)
len = next2 - lblk2;
if (len > count)
len = count;
lblk1 += len;
lblk2 += len;
count -= len;
goto repeat;
}
/* Prepare left boundary */
if (e1_blk < lblk1) {
split = 1;
*erp = ext4_force_split_extent_at(handle, inode1,
&path1, lblk1, 0);
if (unlikely(*erp))
goto finish;
}
if (e2_blk < lblk2) {
split = 1;
*erp = ext4_force_split_extent_at(handle, inode2,
&path2, lblk2, 0);
if (unlikely(*erp))
goto finish;
}
/* ext4_split_extent_at() may result in leaf extent split,
* path must to be revalidated. */
if (split)
goto repeat;
/* Prepare right boundary */
len = count;
if (len > e1_blk + e1_len - lblk1)
len = e1_blk + e1_len - lblk1;
if (len > e2_blk + e2_len - lblk2)
len = e2_blk + e2_len - lblk2;
if (len != e1_len) {
split = 1;
*erp = ext4_force_split_extent_at(handle, inode1,
&path1, lblk1 + len, 0);
if (unlikely(*erp))
goto finish;
}
if (len != e2_len) {
split = 1;
*erp = ext4_force_split_extent_at(handle, inode2,
&path2, lblk2 + len, 0);
if (*erp)
goto finish;
}
/* ext4_split_extent_at() may result in leaf extent split,
* path must to be revalidated. */
if (split)
goto repeat;
BUG_ON(e2_len != e1_len);
*erp = ext4_ext_get_access(handle, inode1, path1 + path1->p_depth);
if (unlikely(*erp))
goto finish;
*erp = ext4_ext_get_access(handle, inode2, path2 + path2->p_depth);
if (unlikely(*erp))
goto finish;
/* Both extents are fully inside boundaries. Swap it now */
tmp_ex = *ex1;
ext4_ext_store_pblock(ex1, ext4_ext_pblock(ex2));
ext4_ext_store_pblock(ex2, ext4_ext_pblock(&tmp_ex));
ex1->ee_len = cpu_to_le16(e2_len);
ex2->ee_len = cpu_to_le16(e1_len);
if (unwritten)
ext4_ext_mark_unwritten(ex2);
if (ext4_ext_is_unwritten(&tmp_ex))
ext4_ext_mark_unwritten(ex1);
ext4_ext_try_to_merge(handle, inode2, path2, ex2);
ext4_ext_try_to_merge(handle, inode1, path1, ex1);
*erp = ext4_ext_dirty(handle, inode2, path2 +
path2->p_depth);
if (unlikely(*erp))
goto finish;
*erp = ext4_ext_dirty(handle, inode1, path1 +
path1->p_depth);
/*
* Looks scarry ah..? second inode already points to new blocks,
* and it was successfully dirtied. But luckily error may happen
* only due to journal error, so full transaction will be
* aborted anyway.
*/
if (unlikely(*erp))
goto finish;
lblk1 += len;
lblk2 += len;
replaced_count += len;
count -= len;
repeat:
ext4_ext_drop_refs(path1);
kfree(path1);
ext4_ext_drop_refs(path2);
kfree(path2);
path1 = path2 = NULL;
}
return replaced_count;
}
/*
* ext4_clu_mapped - determine whether any block in a logical cluster has
* been mapped to a physical cluster
*
* @inode - file containing the logical cluster
* @lclu - logical cluster of interest
*
* Returns 1 if any block in the logical cluster is mapped, signifying
* that a physical cluster has been allocated for it. Otherwise,
* returns 0. Can also return negative error codes. Derived from
* ext4_ext_map_blocks().
*/
int ext4_clu_mapped(struct inode *inode, ext4_lblk_t lclu)
{
struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
struct ext4_ext_path *path;
int depth, mapped = 0, err = 0;
struct ext4_extent *extent;
ext4_lblk_t first_lblk, first_lclu, last_lclu;
/* search for the extent closest to the first block in the cluster */
path = ext4_find_extent(inode, EXT4_C2B(sbi, lclu), NULL, 0);
if (IS_ERR(path)) {
err = PTR_ERR(path);
path = NULL;
goto out;
}
depth = ext_depth(inode);
/*
* A consistent leaf must not be empty. This situation is possible,
* though, _during_ tree modification, and it's why an assert can't
* be put in ext4_find_extent().
*/
if (unlikely(path[depth].p_ext == NULL && depth != 0)) {
EXT4_ERROR_INODE(inode,
"bad extent address - lblock: %lu, depth: %d, pblock: %lld",
(unsigned long) EXT4_C2B(sbi, lclu),
depth, path[depth].p_block);
err = -EFSCORRUPTED;
goto out;
}
extent = path[depth].p_ext;
/* can't be mapped if the extent tree is empty */
if (extent == NULL)
goto out;
first_lblk = le32_to_cpu(extent->ee_block);
first_lclu = EXT4_B2C(sbi, first_lblk);
/*
* Three possible outcomes at this point - found extent spanning
* the target cluster, to the left of the target cluster, or to the
* right of the target cluster. The first two cases are handled here.
* The last case indicates the target cluster is not mapped.
*/
if (lclu >= first_lclu) {
last_lclu = EXT4_B2C(sbi, first_lblk +
ext4_ext_get_actual_len(extent) - 1);
if (lclu <= last_lclu) {
mapped = 1;
} else {
first_lblk = ext4_ext_next_allocated_block(path);
first_lclu = EXT4_B2C(sbi, first_lblk);
if (lclu == first_lclu)
mapped = 1;
}
}
out:
ext4_ext_drop_refs(path);
kfree(path);
return err ? err : mapped;
}
Reference in New Issue View Git Blame Copy Permalink