#include #include #include #include #include #include «xattr.h»
#include «acl.h»

/*
* Called when an inode is released. Note that this is different
* from ext3_file_open: open gets called at every open, but release
* gets called only when /all/ the files are closed.
*/
static int ext3_release_file (struct inode * inode, struct file * filp)
{
if (EXT3_I(inode)->i_state & EXT3_STATE_FLUSH_ON_CLOSE) {
filemap_flush(inode->i_mapping);
EXT3_I(inode)->i_state &= ~EXT3_STATE_FLUSH_ON_CLOSE;
}
/* if we are the last writer on the inode, drop the block reservation */
if ((filp->f_mode & FMODE_WRITE) &&
(atomic_read(&inode->i_writecount) == 1))
{
mutex_lock(&EXT3_I(inode)->truncate_mutex);
ext3_discard_reservation(inode);
mutex_unlock(&EXT3_I(inode)->truncate_mutex);
}
if (is_dx(inode) && filp->private_data)
ext3_htree_free_dir_info(filp->private_data);

return 0;
}

const struct file_operations ext3_file_operations = {
.llseek = generic_file_llseek,
.read = do_sync_read,
.write = do_sync_write,
.aio_read = generic_file_aio_read,
.aio_write = generic_file_aio_write,
.unlocked_ioctl = ext3_ioctl,
#ifdef CONFIG_COMPAT
.compat_ioctl = ext3_compat_ioctl,
#endif
.mmap = generic_file_mmap,
.open = generic_file_open,
.release = ext3_release_file,
.fsync = ext3_sync_file,
.splice_read = generic_file_splice_read,
.splice_write = generic_file_splice_write,
};

const struct inode_operations ext3_file_inode_operations = {
.truncate = ext3_truncate,
.setattr = ext3_setattr,
#ifdef CONFIG_EXT3_FS_XATTR
.setxattr = generic_setxattr,
.getxattr = generic_getxattr,
.listxattr = ext3_listxattr,
.removexattr = generic_removexattr,
#endif
.check_acl = ext3_check_acl,
.fiemap = ext3_fiemap,
};

#include

int __ext3_journal_get_undo_access(const char *where, handle_t *handle,
struct buffer_head *bh)
{
int err = journal_get_undo_access(handle, bh);
if (err)
ext3_journal_abort_handle(where, __func__, bh, handle,err);
return err;
}

int __ext3_journal_get_write_access(const char *where, handle_t *handle,
struct buffer_head *bh)
{
int err = journal_get_write_access(handle, bh);
if (err)
ext3_journal_abort_handle(where, __func__, bh, handle,err);
return err;
}

int __ext3_journal_forget(const char *where, handle_t *handle,
struct buffer_head *bh)
{
int err = journal_forget(handle, bh);
if (err)
ext3_journal_abort_handle(where, __func__, bh, handle,err);
return err;
}

int __ext3_journal_revoke(const char *where, handle_t *handle,
unsigned long blocknr, struct buffer_head *bh)
{
int err = journal_revoke(handle, blocknr, bh);
if (err)
ext3_journal_abort_handle(where, __func__, bh, handle,err);
return err;
}

int __ext3_journal_get_create_access(const char *where,
handle_t *handle, struct buffer_head *bh)
{
int err = journal_get_create_access(handle, bh);
if (err)
ext3_journal_abort_handle(where, __func__, bh, handle,err);
return err;
}

int __ext3_journal_dirty_metadata(const char *where,
handle_t *handle, struct buffer_head *bh)
{
int err = journal_dirty_metadata(handle, bh);
if (err)
ext3_journal_abort_handle(where, __func__, bh, handle,err);
return err;
}

#include #include #include #include #include #include

static unsigned char ext3_filetype_table[] = {
DT_UNKNOWN, DT_REG, DT_DIR, DT_CHR, DT_BLK, DT_FIFO, DT_SOCK, DT_LNK
};

static int ext3_readdir(struct file *, void *, filldir_t);
static int ext3_dx_readdir(struct file * filp,
void * dirent, filldir_t filldir);
static int ext3_release_dir (struct inode * inode,
struct file * filp);

const struct file_operations ext3_dir_operations = {
.llseek = generic_file_llseek,
.read = generic_read_dir,
.readdir = ext3_readdir, /* we take BKL. needed?*/
.unlocked_ioctl = ext3_ioctl,
#ifdef CONFIG_COMPAT
.compat_ioctl = ext3_compat_ioctl,
#endif
.fsync = ext3_sync_file, /* BKL held */
.release = ext3_release_dir,
};

static unsigned char get_dtype(struct super_block *sb, int filetype)
{
if (!EXT3_HAS_INCOMPAT_FEATURE(sb, EXT3_FEATURE_INCOMPAT_FILETYPE) ||
(filetype >= EXT3_FT_MAX))
return DT_UNKNOWN;

return (ext3_filetype_table[filetype]);
}

int ext3_check_dir_entry (const char * function, struct inode * dir,
struct ext3_dir_entry_2 * de,
struct buffer_head * bh,
unsigned long offset)
{
const char * error_msg = NULL;
const int rlen = ext3_rec_len_from_disk(de->rec_len);

if (rlen < EXT3_DIR_REC_LEN(1))
error_msg = "rec_len is smaller than minimal";
else if (rlen % 4 != 0)
error_msg = "rec_len % 4 != 0";
else if (rlen < EXT3_DIR_REC_LEN(de->name_len))
error_msg = «rec_len is too small for name_len»;
else if (((char *) de – bh->b_data) + rlen > dir->i_sb->s_blocksize)
error_msg = «directory entry across blocks»;
else if (le32_to_cpu(de->inode) >
le32_to_cpu(EXT3_SB(dir->i_sb)->s_es->s_inodes_count))
error_msg = «inode out of bounds»;

if (error_msg != NULL)
ext3_error (dir->i_sb, function,
«bad entry in directory #%lu: %s – »
«offset=%lu, inode=%lu, rec_len=%d, name_len=%d»,
dir->i_ino, error_msg, offset,
(unsigned long) le32_to_cpu(de->inode),
rlen, de->name_len);
return error_msg == NULL ? 1 : 0;
}

static int ext3_readdir(struct file * filp,
void * dirent, filldir_t filldir)
{
int error = 0;
unsigned long offset;
int i, stored;
struct ext3_dir_entry_2 *de;
struct super_block *sb;
int err;
struct inode *inode = filp->f_path.dentry->d_inode;
int ret = 0;
int dir_has_error = 0;

sb = inode->i_sb;

if (EXT3_HAS_COMPAT_FEATURE(inode->i_sb,
EXT3_FEATURE_COMPAT_DIR_INDEX) &&
((EXT3_I(inode)->i_flags & EXT3_INDEX_FL) ||
((inode->i_size >> sb->s_blocksize_bits) == 1))) {
err = ext3_dx_readdir(filp, dirent, filldir);
if (err != ERR_BAD_DX_DIR) {
ret = err;
goto out;
}
/*
* We don’t set the inode dirty flag since it’s not
* critical that it get flushed back to the disk.
*/
EXT3_I(filp->f_path.dentry->d_inode)->i_flags &= ~EXT3_INDEX_FL;
}
stored = 0;
offset = filp->f_pos & (sb->s_blocksize – 1);

while (!error && !stored && filp->f_pos < inode->i_size) {
unsigned long blk = filp->f_pos >> EXT3_BLOCK_SIZE_BITS(sb);
struct buffer_head map_bh;
struct buffer_head *bh = NULL;

map_bh.b_state = 0;
err = ext3_get_blocks_handle(NULL, inode, blk, 1, &map_bh, 0);
if (err > 0) {
pgoff_t index = map_bh.b_blocknr >>
(PAGE_CACHE_SHIFT – inode->i_blkbits);
if (!ra_has_index(&filp->f_ra, index))
page_cache_sync_readahead(
sb->s_bdev->bd_inode->i_mapping,
&filp->f_ra, filp,
index, 1);
filp->f_ra.prev_pos = (loff_t)index << PAGE_CACHE_SHIFT;
bh = ext3_bread(NULL, inode, blk, 0, &err);
}

/*
* We ignore I/O errors on directories so users have a chance
* of recovering data when there's a bad sector
*/
if (!bh) {
if (!dir_has_error) {
ext3_error(sb, __func__, "directory #%lu "
"contains a hole at offset %lld",
inode->i_ino, filp->f_pos);
dir_has_error = 1;
}
/* corrupt size? Maybe no more blocks to read */
if (filp->f_pos > inode->i_blocks << 9)
break;
filp->f_pos += sb->s_blocksize – offset;
continue;
}

revalidate:
/* If the dir block has changed since the last call to
* readdir(2), then we might be pointing to an invalid
* dirent right now. Scan from the start of the block
* to make sure. */
if (filp->f_version != inode->i_version) {
for (i = 0; i < sb->s_blocksize && i < offset; ) {
de = (struct ext3_dir_entry_2 *)
(bh->b_data + i);
/* It’s too expensive to do a full
* dirent test each time round this
* loop, but we do have to test at
* least that it is non-zero. A
* failure will be detected in the
* dirent test below. */
if (ext3_rec_len_from_disk(de->rec_len) <
EXT3_DIR_REC_LEN(1))
break;
i += ext3_rec_len_from_disk(de->rec_len);
}
offset = i;
filp->f_pos = (filp->f_pos & ~(sb->s_blocksize – 1))
| offset;
filp->f_version = inode->i_version;
}

while (!error && filp->f_pos < inode->i_size
&& offset < sb->s_blocksize) {
de = (struct ext3_dir_entry_2 *) (bh->b_data + offset);
if (!ext3_check_dir_entry (»ext3_readdir», inode, de,
bh, offset)) {
/* On error, skip the f_pos to the
next block. */
filp->f_pos = (filp->f_pos |
(sb->s_blocksize – 1)) + 1;
brelse (bh);
ret = stored;
goto out;
}
offset += ext3_rec_len_from_disk(de->rec_len);
if (le32_to_cpu(de->inode)) {
/* We might block in the next section
* if the data destination is
* currently swapped out. So, use a
* version stamp to detect whether or
* not the directory has been modified
* during the copy operation.
*/
u64 version = filp->f_version;

error = filldir(dirent, de->name,
de->name_len,
filp->f_pos,
le32_to_cpu(de->inode),
get_dtype(sb, de->file_type));
if (error)
break;
if (version != filp->f_version)
goto revalidate;
stored ++;
}
filp->f_pos += ext3_rec_len_from_disk(de->rec_len);
}
offset = 0;
brelse (bh);
}
out:
return ret;
}

/*
* These functions convert from the major/minor hash to an f_pos
* value.
*
* Currently we only use major hash numer. This is unfortunate, but
* on 32-bit machines, the same VFS interface is used for lseek and
* llseek, so if we use the 64 bit offset, then the 32-bit versions of
* lseek/telldir/seekdir will blow out spectacularly, and from within
* the ext2 low-level routine, we don’t know if we’re being called by
* a 64-bit version of the system call or the 32-bit version of the
* system call. Worse yet, NFSv2 only allows for a 32-bit readdir
* cookie. Sigh.
*/
#define hash2pos(major, minor) (major >> 1)
#define pos2maj_hash(pos) ((pos << 1) & 0xffffffff)
#define pos2min_hash(pos) (0)

/*
* This structure holds the nodes of the red-black tree used to store
* the directory entry in hash order.
*/
struct fname {
__u32 hash;
__u32 minor_hash;
struct rb_node rb_hash;
struct fname *next;
__u32 inode;
__u8 name_len;
__u8 file_type;
char name[0];
};

/*
* This functoin implements a non-recursive way of freeing all of the
* nodes in the red-black tree.
*/
static void free_rb_tree_fname(struct rb_root *root)
{
struct rb_node *n = root->rb_node;
struct rb_node *parent;
struct fname *fname;

while (n) {
/* Do the node’s children first */
if (n->rb_left) {
n = n->rb_left;
continue;
}
if (n->rb_right) {
n = n->rb_right;
continue;
}
/*
* The node has no children; free it, and then zero
* out parent’s link to it. Finally go to the
* beginning of the loop and try to free the parent
* node.
*/
parent = rb_parent(n);
fname = rb_entry(n, struct fname, rb_hash);
while (fname) {
struct fname * old = fname;
fname = fname->next;
kfree (old);
}
if (!parent)
root->rb_node = NULL;
else if (parent->rb_left == n)
parent->rb_left = NULL;
else if (parent->rb_right == n)
parent->rb_right = NULL;
n = parent;
}
}

static struct dir_private_info *ext3_htree_create_dir_info(loff_t pos)
{
struct dir_private_info *p;

p = kzalloc(sizeof(struct dir_private_info), GFP_KERNEL);
if (!p)
return NULL;
p->curr_hash = pos2maj_hash(pos);
p->curr_minor_hash = pos2min_hash(pos);
return p;
}

void ext3_htree_free_dir_info(struct dir_private_info *p)
{
free_rb_tree_fname(&p->root);
kfree(p);
}

/*
* Given a directory entry, enter it into the fname rb tree.
*/
int ext3_htree_store_dirent(struct file *dir_file, __u32 hash,
__u32 minor_hash,
struct ext3_dir_entry_2 *dirent)
{
struct rb_node **p, *parent = NULL;
struct fname * fname, *new_fn;
struct dir_private_info *info;
int len;

info = (struct dir_private_info *) dir_file->private_data;
p = &info->root.rb_node;

/* Create and allocate the fname structure */
len = sizeof(struct fname) + dirent->name_len + 1;
new_fn = kzalloc(len, GFP_KERNEL);
if (!new_fn)
return -ENOMEM;
new_fn->hash = hash;
new_fn->minor_hash = minor_hash;
new_fn->inode = le32_to_cpu(dirent->inode);
new_fn->name_len = dirent->name_len;
new_fn->file_type = dirent->file_type;
memcpy(new_fn->name, dirent->name, dirent->name_len);
new_fn->name[dirent->name_len] = 0;

while (*p) {
parent = *p;
fname = rb_entry(parent, struct fname, rb_hash);

/*
* If the hash and minor hash match up, then we put
* them on a linked list. This rarely happens…
*/
if ((new_fn->hash == fname->hash) &&
(new_fn->minor_hash == fname->minor_hash)) {
new_fn->next = fname->next;
fname->next = new_fn;
return 0;
}

if (new_fn->hash < fname->hash)
p = &(*p)->rb_left;
else if (new_fn->hash > fname->hash)
p = &(*p)->rb_right;
else if (new_fn->minor_hash < fname->minor_hash)
p = &(*p)->rb_left;
else /* if (new_fn->minor_hash > fname->minor_hash) */
p = &(*p)->rb_right;
}

rb_link_node(&new_fn->rb_hash, parent, p);
rb_insert_color(&new_fn->rb_hash, &info->root);
return 0;
}

/*
* This is a helper function for ext3_dx_readdir. It calls filldir
* for all entres on the fname linked list. (Normally there is only
* one entry on the linked list, unless there are 62 bit hash collisions.)
*/
static int call_filldir(struct file * filp, void * dirent,
filldir_t filldir, struct fname *fname)
{
struct dir_private_info *info = filp->private_data;
loff_t curr_pos;
struct inode *inode = filp->f_path.dentry->d_inode;
struct super_block * sb;
int error;

sb = inode->i_sb;

if (!fname) {
printk(»call_filldir: called with null fname?!?\n»);
return 0;
}
curr_pos = hash2pos(fname->hash, fname->minor_hash);
while (fname) {
error = filldir(dirent, fname->name,
fname->name_len, curr_pos,
fname->inode,
get_dtype(sb, fname->file_type));
if (error) {
filp->f_pos = curr_pos;
info->extra_fname = fname;
return error;
}
fname = fname->next;
}
return 0;
}

static int ext3_dx_readdir(struct file * filp,
void * dirent, filldir_t filldir)
{
struct dir_private_info *info = filp->private_data;
struct inode *inode = filp->f_path.dentry->d_inode;
struct fname *fname;
int ret;

if (!info) {
info = ext3_htree_create_dir_info(filp->f_pos);
if (!info)
return -ENOMEM;
filp->private_data = info;
}

if (filp->f_pos == EXT3_HTREE_EOF)
return 0; /* EOF */

/* Some one has messed with f_pos; reset the world */
if (info->last_pos != filp->f_pos) {
free_rb_tree_fname(&info->root);
info->curr_node = NULL;
info->extra_fname = NULL;
info->curr_hash = pos2maj_hash(filp->f_pos);
info->curr_minor_hash = pos2min_hash(filp->f_pos);
}

/*
* If there are any leftover names on the hash collision
* chain, return them first.
*/
if (info->extra_fname) {
if (call_filldir(filp, dirent, filldir, info->extra_fname))
goto finished;
info->extra_fname = NULL;
goto next_node;
} else if (!info->curr_node)
info->curr_node = rb_first(&info->root);

while (1) {
/*
* Fill the rbtree if we have no more entries,
* or the inode has changed since we last read in the
* cached entries.
*/
if ((!info->curr_node) ||
(filp->f_version != inode->i_version)) {
info->curr_node = NULL;
free_rb_tree_fname(&info->root);
filp->f_version = inode->i_version;
ret = ext3_htree_fill_tree(filp, info->curr_hash,
info->curr_minor_hash,
&info->next_hash);
if (ret < 0)
return ret;
if (ret == 0) {
filp->f_pos = EXT3_HTREE_EOF;
break;
}
info->curr_node = rb_first(&info->root);
}

fname = rb_entry(info->curr_node, struct fname, rb_hash);
info->curr_hash = fname->hash;
info->curr_minor_hash = fname->minor_hash;
if (call_filldir(filp, dirent, filldir, fname))
break;
next_node:
info->curr_node = rb_next(info->curr_node);
if (info->curr_node) {
fname = rb_entry(info->curr_node, struct fname,
rb_hash);
info->curr_hash = fname->hash;
info->curr_minor_hash = fname->minor_hash;
} else {
if (info->next_hash == ~0) {
filp->f_pos = EXT3_HTREE_EOF;
break;
}
info->curr_hash = info->next_hash;
info->curr_minor_hash = 0;
}
}
finished:
info->last_pos = filp->f_pos;
return 0;
}

static int ext3_release_dir (struct inode * inode, struct file * filp)
{
if (filp->private_data)
ext3_htree_free_dir_info(filp->private_data);

return 0;
}

#include #include #include

#ifdef EXT3FS_DEBUG

static const int nibblemap[] = {4, 3, 3, 2, 3, 2, 2, 1, 3, 2, 2, 1, 2, 1, 1, 0};

unsigned long ext3_count_free (struct buffer_head * map, unsigned int numchars)
{
unsigned int i;
unsigned long sum = 0;

if (!map)
return (0);
for (i = 0; i < numchars; i++)
sum += nibblemap[map->b_data[i] & 0xf] +
nibblemap[(map->b_data[i] >> 4) & 0xf];
return (sum);
}

#endif /* EXT3FS_DEBUG */

#include #include #include #include #include #include #include #include

/*
* balloc.c contains the blocks allocation and deallocation routines
*/

/*
* The free blocks are managed by bitmaps. A file system contains several
* blocks groups. Each group contains 1 bitmap block for blocks, 1 bitmap
* block for inodes, N blocks for the inode table and data blocks.
*
* The file system contains group descriptors which are located after the
* super block. Each descriptor contains the number of the bitmap block and
* the free blocks count in the block. The descriptors are loaded in memory
* when a file system is mounted (see ext3_fill_super).
*/

#define in_range(b, first, len) ((b) >= (first) && (b) <= (first) + (len) - 1)

/**
* ext3_get_group_desc() -- load group descriptor from disk
* @sb: super block
* @block_group: given block group
* @bh: pointer to the buffer head to store the block
* group descriptor
*/
struct ext3_group_desc * ext3_get_group_desc(struct super_block * sb,
unsigned int block_group,
struct buffer_head ** bh)
{
unsigned long group_desc;
unsigned long offset;
struct ext3_group_desc * desc;
struct ext3_sb_info *sbi = EXT3_SB(sb);

if (block_group >= sbi->s_groups_count) {
ext3_error (sb, «ext3_get_group_desc»,
«block_group >= groups_count – »
«block_group = %d, groups_count = %lu»,
block_group, sbi->s_groups_count);

return NULL;
}
smp_rmb();

group_desc = block_group >> EXT3_DESC_PER_BLOCK_BITS(sb);
offset = block_group & (EXT3_DESC_PER_BLOCK(sb) – 1);
if (!sbi->s_group_desc[group_desc]) {
ext3_error (sb, «ext3_get_group_desc»,
«Group descriptor not loaded – »
«block_group = %d, group_desc = %lu, desc = %lu»,
block_group, group_desc, offset);
return NULL;
}

desc = (struct ext3_group_desc *) sbi->s_group_desc[group_desc]->b_data;
if (bh)
*bh = sbi->s_group_desc[group_desc];
return desc + offset;
}

static int ext3_valid_block_bitmap(struct super_block *sb,
struct ext3_group_desc *desc,
unsigned int block_group,
struct buffer_head *bh)
{
ext3_grpblk_t offset;
ext3_grpblk_t next_zero_bit;
ext3_fsblk_t bitmap_blk;
ext3_fsblk_t group_first_block;

group_first_block = ext3_group_first_block_no(sb, block_group);

/* check whether block bitmap block number is set */
bitmap_blk = le32_to_cpu(desc->bg_block_bitmap);
offset = bitmap_blk – group_first_block;
if (!ext3_test_bit(offset, bh->b_data))
/* bad block bitmap */
goto err_out;

/* check whether the inode bitmap block number is set */
bitmap_blk = le32_to_cpu(desc->bg_inode_bitmap);
offset = bitmap_blk – group_first_block;
if (!ext3_test_bit(offset, bh->b_data))
/* bad block bitmap */
goto err_out;

/* check whether the inode table block number is set */
bitmap_blk = le32_to_cpu(desc->bg_inode_table);
offset = bitmap_blk – group_first_block;
next_zero_bit = ext3_find_next_zero_bit(bh->b_data,
offset + EXT3_SB(sb)->s_itb_per_group,
offset);
if (next_zero_bit >= offset + EXT3_SB(sb)->s_itb_per_group)
/* good bitmap for inode tables */
return 1;

err_out:
ext3_error(sb, __func__,
«Invalid block bitmap – »
«block_group = %d, block = %lu»,
block_group, bitmap_blk);
return 0;
}

/**
* read_block_bitmap()
* @sb: super block
* @block_group: given block group
*
* Read the bitmap for a given block_group,and validate the
* bits for block/inode/inode tables are set in the bitmaps
*
* Return buffer_head on success or NULL in case of failure.
*/
static struct buffer_head *
read_block_bitmap(struct super_block *sb, unsigned int block_group)
{
struct ext3_group_desc * desc;
struct buffer_head * bh = NULL;
ext3_fsblk_t bitmap_blk;

desc = ext3_get_group_desc(sb, block_group, NULL);
if (!desc)
return NULL;
bitmap_blk = le32_to_cpu(desc->bg_block_bitmap);
bh = sb_getblk(sb, bitmap_blk);
if (unlikely(!bh)) {
ext3_error(sb, __func__,
«Cannot read block bitmap – »
«block_group = %d, block_bitmap = %u»,
block_group, le32_to_cpu(desc->bg_block_bitmap));
return NULL;
}
if (likely(bh_uptodate_or_lock(bh)))
return bh;

if (bh_submit_read(bh) < 0) {
brelse(bh);
ext3_error(sb, __func__,
"Cannot read block bitmap - "
"block_group = %d, block_bitmap = %u",
block_group, le32_to_cpu(desc->bg_block_bitmap));
return NULL;
}
ext3_valid_block_bitmap(sb, desc, block_group, bh);
/*
* file system mounted not to panic on error, continue with corrupt
* bitmap
*/
return bh;
}
/*
* The reservation window structure operations
* ——————————————–
* Operations include:
* dump, find, add, remove, is_empty, find_next_reservable_window, etc.
*
* We use a red-black tree to represent per-filesystem reservation
* windows.
*
*/

/**
* __rsv_window_dump() — Dump the filesystem block allocation reservation map
* @rb_root: root of per-filesystem reservation rb tree
* @verbose: verbose mode
* @fn: function which wishes to dump the reservation map
*
* If verbose is turned on, it will print the whole block reservation
* windows(start, end). Otherwise, it will only print out the «bad» windows,
* those windows that overlap with their immediate neighbors.
*/
#if 1
static void __rsv_window_dump(struct rb_root *root, int verbose,
const char *fn)
{
struct rb_node *n;
struct ext3_reserve_window_node *rsv, *prev;
int bad;

restart:
n = rb_first(root);
bad = 0;
prev = NULL;

printk(»Block Allocation Reservation Windows Map (%s):\n», fn);
while (n) {
rsv = rb_entry(n, struct ext3_reserve_window_node, rsv_node);
if (verbose)
printk(»reservation window 0x%p »
«start: %lu, end: %lu\n»,
rsv, rsv->rsv_start, rsv->rsv_end);
if (rsv->rsv_start && rsv->rsv_start >= rsv->rsv_end) {
printk(»Bad reservation %p (start >= end)\n»,
rsv);
bad = 1;
}
if (prev && prev->rsv_end >= rsv->rsv_start) {
printk(»Bad reservation %p (prev->end >= start)\n»,
rsv);
bad = 1;
}
if (bad) {
if (!verbose) {
printk(»Restarting reservation walk in verbose mode\n»);
verbose = 1;
goto restart;
}
}
n = rb_next(n);
prev = rsv;
}
printk(»Window map complete.\n»);
BUG_ON(bad);
}
#define rsv_window_dump(root, verbose) \
__rsv_window_dump((root), (verbose), __func__)
#else
#define rsv_window_dump(root, verbose) do {} while (0)
#endif

/**
* goal_in_my_reservation()
* @rsv: inode’s reservation window
* @grp_goal: given goal block relative to the allocation block group
* @group: the current allocation block group
* @sb: filesystem super block
*
* Test if the given goal block (group relative) is within the file’s
* own block reservation window range.
*
* If the reservation window is outside the goal allocation group, return 0;
* grp_goal (given goal block) could be -1, which means no specific
* goal block. In this case, always return 1.
* If the goal block is within the reservation window, return 1;
* otherwise, return 0;
*/
static int
goal_in_my_reservation(struct ext3_reserve_window *rsv, ext3_grpblk_t grp_goal,
unsigned int group, struct super_block * sb)
{
ext3_fsblk_t group_first_block, group_last_block;

group_first_block = ext3_group_first_block_no(sb, group);
group_last_block = group_first_block + (EXT3_BLOCKS_PER_GROUP(sb) – 1);

if ((rsv->_rsv_start > group_last_block) ||
(rsv->_rsv_end < group_first_block))
return 0;
if ((grp_goal >= 0) && ((grp_goal + group_first_block < rsv->_rsv_start)
|| (grp_goal + group_first_block > rsv->_rsv_end)))
return 0;
return 1;
}

/**
* search_reserve_window()
* @rb_root: root of reservation tree
* @goal: target allocation block
*
* Find the reserved window which includes the goal, or the previous one
* if the goal is not in any window.
* Returns NULL if there are no windows or if all windows start after the goal.
*/
static struct ext3_reserve_window_node *
search_reserve_window(struct rb_root *root, ext3_fsblk_t goal)
{
struct rb_node *n = root->rb_node;
struct ext3_reserve_window_node *rsv;

if (!n)
return NULL;

do {
rsv = rb_entry(n, struct ext3_reserve_window_node, rsv_node);

if (goal < rsv->rsv_start)
n = n->rb_left;
else if (goal > rsv->rsv_end)
n = n->rb_right;
else
return rsv;
} while (n);
/*
* We’ve fallen off the end of the tree: the goal wasn’t inside
* any particular node. OK, the previous node must be to one
* side of the interval containing the goal. If it’s the RHS,
* we need to back up one.
*/
if (rsv->rsv_start > goal) {
n = rb_prev(&rsv->rsv_node);
rsv = rb_entry(n, struct ext3_reserve_window_node, rsv_node);
}
return rsv;
}

/**
* ext3_rsv_window_add() — Insert a window to the block reservation rb tree.
* @sb: super block
* @rsv: reservation window to add
*
* Must be called with rsv_lock hold.
*/
void ext3_rsv_window_add(struct super_block *sb,
struct ext3_reserve_window_node *rsv)
{
struct rb_root *root = &EXT3_SB(sb)->s_rsv_window_root;
struct rb_node *node = &rsv->rsv_node;
ext3_fsblk_t start = rsv->rsv_start;

struct rb_node ** p = &root->rb_node;
struct rb_node * parent = NULL;
struct ext3_reserve_window_node *this;

while (*p)
{
parent = *p;
this = rb_entry(parent, struct ext3_reserve_window_node, rsv_node);

if (start < this->rsv_start)
p = &(*p)->rb_left;
else if (start > this->rsv_end)
p = &(*p)->rb_right;
else {
rsv_window_dump(root, 1);
BUG();
}
}

rb_link_node(node, parent, p);
rb_insert_color(node, root);
}

/**
* ext3_rsv_window_remove() — unlink a window from the reservation rb tree
* @sb: super block
* @rsv: reservation window to remove
*
* Mark the block reservation window as not allocated, and unlink it
* from the filesystem reservation window rb tree. Must be called with
* rsv_lock hold.
*/
static void rsv_window_remove(struct super_block *sb,
struct ext3_reserve_window_node *rsv)
{
rsv->rsv_start = EXT3_RESERVE_WINDOW_NOT_ALLOCATED;
rsv->rsv_end = EXT3_RESERVE_WINDOW_NOT_ALLOCATED;
rsv->rsv_alloc_hit = 0;
rb_erase(&rsv->rsv_node, &EXT3_SB(sb)->s_rsv_window_root);
}

/*
* rsv_is_empty() — Check if the reservation window is allocated.
* @rsv: given reservation window to check
*
* returns 1 if the end block is EXT3_RESERVE_WINDOW_NOT_ALLOCATED.
*/
static inline int rsv_is_empty(struct ext3_reserve_window *rsv)
{
/* a valid reservation end block could not be 0 */
return rsv->_rsv_end == EXT3_RESERVE_WINDOW_NOT_ALLOCATED;
}

/**
* ext3_init_block_alloc_info()
* @inode: file inode structure
*
* Allocate and initialize the reservation window structure, and
* link the window to the ext3 inode structure at last
*
* The reservation window structure is only dynamically allocated
* and linked to ext3 inode the first time the open file
* needs a new block. So, before every ext3_new_block(s) call, for
* regular files, we should check whether the reservation window
* structure exists or not. In the latter case, this function is called.
* Fail to do so will result in block reservation being turned off for that
* open file.
*
* This function is called from ext3_get_blocks_handle(), also called
* when setting the reservation window size through ioctl before the file
* is open for write (needs block allocation).
*
* Needs truncate_mutex protection prior to call this function.
*/
void ext3_init_block_alloc_info(struct inode *inode)
{
struct ext3_inode_info *ei = EXT3_I(inode);
struct ext3_block_alloc_info *block_i = ei->i_block_alloc_info;
struct super_block *sb = inode->i_sb;

block_i = kmalloc(sizeof(*block_i), GFP_NOFS);
if (block_i) {
struct ext3_reserve_window_node *rsv = &block_i->rsv_window_node;

rsv->rsv_start = EXT3_RESERVE_WINDOW_NOT_ALLOCATED;
rsv->rsv_end = EXT3_RESERVE_WINDOW_NOT_ALLOCATED;

/*
* if filesystem is mounted with NORESERVATION, the goal
* reservation window size is set to zero to indicate
* block reservation is off
*/
if (!test_opt(sb, RESERVATION))
rsv->rsv_goal_size = 0;
else
rsv->rsv_goal_size = EXT3_DEFAULT_RESERVE_BLOCKS;
rsv->rsv_alloc_hit = 0;
block_i->last_alloc_logical_block = 0;
block_i->last_alloc_physical_block = 0;
}
ei->i_block_alloc_info = block_i;
}

/**
* ext3_discard_reservation()
* @inode: inode
*
* Discard(free) block reservation window on last file close, or truncate
* or at last iput().
*
* It is being called in three cases:
* ext3_release_file(): last writer close the file
* ext3_clear_inode(): last iput(), when nobody link to this file.
* ext3_truncate(): when the block indirect map is about to change.
*
*/
void ext3_discard_reservation(struct inode *inode)
{
struct ext3_inode_info *ei = EXT3_I(inode);
struct ext3_block_alloc_info *block_i = ei->i_block_alloc_info;
struct ext3_reserve_window_node *rsv;
spinlock_t *rsv_lock = &EXT3_SB(inode->i_sb)->s_rsv_window_lock;

if (!block_i)
return;

rsv = &block_i->rsv_window_node;
if (!rsv_is_empty(&rsv->rsv_window)) {
spin_lock(rsv_lock);
if (!rsv_is_empty(&rsv->rsv_window))
rsv_window_remove(inode->i_sb, rsv);
spin_unlock(rsv_lock);
}
}

/**
* ext3_free_blocks_sb() — Free given blocks and update quota
* @handle: handle to this transaction
* @sb: super block
* @block: start physcial block to free
* @count: number of blocks to free
* @pdquot_freed_blocks: pointer to quota
*/
void ext3_free_blocks_sb(handle_t *handle, struct super_block *sb,
ext3_fsblk_t block, unsigned long count,
unsigned long *pdquot_freed_blocks)
{
struct buffer_head *bitmap_bh = NULL;
struct buffer_head *gd_bh;
unsigned long block_group;
ext3_grpblk_t bit;
unsigned long i;
unsigned long overflow;
struct ext3_group_desc * desc;
struct ext3_super_block * es;
struct ext3_sb_info *sbi;
int err = 0, ret;
ext3_grpblk_t group_freed;

*pdquot_freed_blocks = 0;
sbi = EXT3_SB(sb);
es = sbi->s_es;
if (block < le32_to_cpu(es->s_first_data_block) ||
block + count < block ||
block + count > le32_to_cpu(es->s_blocks_count)) {
ext3_error (sb, «ext3_free_blocks»,
«Freeing blocks not in datazone – »
«block = «E3FSBLK», count = %lu», block, count);
goto error_return;
}

ext3_debug (»freeing block(s) %lu-%lu\n», block, block + count – 1);

do_more:
overflow = 0;
block_group = (block – le32_to_cpu(es->s_first_data_block)) /
EXT3_BLOCKS_PER_GROUP(sb);
bit = (block – le32_to_cpu(es->s_first_data_block)) %
EXT3_BLOCKS_PER_GROUP(sb);
/*
* Check to see if we are freeing blocks across a group
* boundary.
*/
if (bit + count > EXT3_BLOCKS_PER_GROUP(sb)) {
overflow = bit + count – EXT3_BLOCKS_PER_GROUP(sb);
count -= overflow;
}
brelse(bitmap_bh);
bitmap_bh = read_block_bitmap(sb, block_group);
if (!bitmap_bh)
goto error_return;
desc = ext3_get_group_desc (sb, block_group, &gd_bh);
if (!desc)
goto error_return;

if (in_range (le32_to_cpu(desc->bg_block_bitmap), block, count) ||
in_range (le32_to_cpu(desc->bg_inode_bitmap), block, count) ||
in_range (block, le32_to_cpu(desc->bg_inode_table),
sbi->s_itb_per_group) ||
in_range (block + count – 1, le32_to_cpu(desc->bg_inode_table),
sbi->s_itb_per_group)) {
ext3_error (sb, «ext3_free_blocks»,
«Freeing blocks in system zones – »
«Block = «E3FSBLK», count = %lu»,
block, count);
goto error_return;
}

/*
* We are about to start releasing blocks in the bitmap,
* so we need undo access.
*/
/* @@@ check errors */
BUFFER_TRACE(bitmap_bh, «getting undo access»);
err = ext3_journal_get_undo_access(handle, bitmap_bh);
if (err)
goto error_return;

/*
* We are about to modify some metadata. Call the journal APIs
* to unshare ->b_data if a currently-committing transaction is
* using it
*/
BUFFER_TRACE(gd_bh, «get_write_access»);
err = ext3_journal_get_write_access(handle, gd_bh);
if (err)
goto error_return;

jbd_lock_bh_state(bitmap_bh);

for (i = 0, group_freed = 0; i < count; i++) {
/*
* An HJ special. This is expensive...
*/
#ifdef CONFIG_JBD_DEBUG
jbd_unlock_bh_state(bitmap_bh);
{
struct buffer_head *debug_bh;
debug_bh = sb_find_get_block(sb, block + i);
if (debug_bh) {
BUFFER_TRACE(debug_bh, "Deleted!");
if (!bh2jh(bitmap_bh)->b_committed_data)
BUFFER_TRACE(debug_bh,
«No commited data in bitmap»);
BUFFER_TRACE2(debug_bh, bitmap_bh, «bitmap»);
__brelse(debug_bh);
}
}
jbd_lock_bh_state(bitmap_bh);
#endif
if (need_resched()) {
jbd_unlock_bh_state(bitmap_bh);
cond_resched();
jbd_lock_bh_state(bitmap_bh);
}
/* @@@ This prevents newly-allocated data from being
* freed and then reallocated within the same
* transaction.
*
* Ideally we would want to allow that to happen, but to
* do so requires making journal_forget() capable of
* revoking the queued write of a data block, which
* implies blocking on the journal lock. *forget()
* cannot block due to truncate races.
*
* Eventually we can fix this by making journal_forget()
* return a status indicating whether or not it was able
* to revoke the buffer. On successful revoke, it is
* safe not to set the allocation bit in the committed
* bitmap, because we know that there is no outstanding
* activity on the buffer any more and so it is safe to
* reallocate it.
*/
BUFFER_TRACE(bitmap_bh, «set in b_committed_data»);
J_ASSERT_BH(bitmap_bh,
bh2jh(bitmap_bh)->b_committed_data != NULL);
ext3_set_bit_atomic(sb_bgl_lock(sbi, block_group), bit + i,
bh2jh(bitmap_bh)->b_committed_data);

/*
* We clear the bit in the bitmap after setting the committed
* data bit, because this is the reverse order to that which
* the allocator uses.
*/
BUFFER_TRACE(bitmap_bh, «clear bit»);
if (!ext3_clear_bit_atomic(sb_bgl_lock(sbi, block_group),
bit + i, bitmap_bh->b_data)) {
jbd_unlock_bh_state(bitmap_bh);
ext3_error(sb, __func__,
«bit already cleared for block «E3FSBLK,
block + i);
jbd_lock_bh_state(bitmap_bh);
BUFFER_TRACE(bitmap_bh, «bit already cleared»);
} else {
group_freed++;
}
}
jbd_unlock_bh_state(bitmap_bh);

spin_lock(sb_bgl_lock(sbi, block_group));
le16_add_cpu(&desc->bg_free_blocks_count, group_freed);
spin_unlock(sb_bgl_lock(sbi, block_group));
percpu_counter_add(&sbi->s_freeblocks_counter, count);

/* We dirtied the bitmap block */
BUFFER_TRACE(bitmap_bh, «dirtied bitmap block»);
err = ext3_journal_dirty_metadata(handle, bitmap_bh);

/* And the group descriptor block */
BUFFER_TRACE(gd_bh, «dirtied group descriptor block»);
ret = ext3_journal_dirty_metadata(handle, gd_bh);
if (!err) err = ret;
*pdquot_freed_blocks += group_freed;

if (overflow && !err) {
block += count;
count = overflow;
goto do_more;
}

error_return:
brelse(bitmap_bh);
ext3_std_error(sb, err);
return;
}

/**
* ext3_free_blocks() — Free given blocks and update quota
* @handle: handle for this transaction
* @inode: inode
* @block: start physical block to free
* @count: number of blocks to count
*/
void ext3_free_blocks(handle_t *handle, struct inode *inode,
ext3_fsblk_t block, unsigned long count)
{
struct super_block * sb;
unsigned long dquot_freed_blocks;

sb = inode->i_sb;
if (!sb) {
printk (»ext3_free_blocks: nonexistent device»);
return;
}
ext3_free_blocks_sb(handle, sb, block, count, &dquot_freed_blocks);
if (dquot_freed_blocks)
vfs_dq_free_block(inode, dquot_freed_blocks);
return;
}

/**
* ext3_test_allocatable()
* @nr: given allocation block group
* @bh: bufferhead contains the bitmap of the given block group
*
* For ext3 allocations, we must not reuse any blocks which are
* allocated in the bitmap buffer’s «last committed data» copy. This
* prevents deletes from freeing up the page for reuse until we have
* committed the delete transaction.
*
* If we didn’t do this, then deleting something and reallocating it as
* data would allow the old block to be overwritten before the
* transaction committed (because we force data to disk before commit).
* This would lead to corruption if we crashed between overwriting the
* data and committing the delete.
*
* @@@ We may want to make this allocation behaviour conditional on
* data-writes at some point, and disable it for metadata allocations or
* sync-data inodes.
*/
static int ext3_test_allocatable(ext3_grpblk_t nr, struct buffer_head *bh)
{
int ret;
struct journal_head *jh = bh2jh(bh);

if (ext3_test_bit(nr, bh->b_data))
return 0;

jbd_lock_bh_state(bh);
if (!jh->b_committed_data)
ret = 1;
else
ret = !ext3_test_bit(nr, jh->b_committed_data);
jbd_unlock_bh_state(bh);
return ret;
}

/**
* bitmap_search_next_usable_block()
* @start: the starting block (group relative) of the search
* @bh: bufferhead contains the block group bitmap
* @maxblocks: the ending block (group relative) of the reservation
*
* The bitmap search — search forward alternately through the actual
* bitmap on disk and the last-committed copy in journal, until we find a
* bit free in both bitmaps.
*/
static ext3_grpblk_t
bitmap_search_next_usable_block(ext3_grpblk_t start, struct buffer_head *bh,
ext3_grpblk_t maxblocks)
{
ext3_grpblk_t next;
struct journal_head *jh = bh2jh(bh);

while (start < maxblocks) {
next = ext3_find_next_zero_bit(bh->b_data, maxblocks, start);
if (next >= maxblocks)
return -1;
if (ext3_test_allocatable(next, bh))
return next;
jbd_lock_bh_state(bh);
if (jh->b_committed_data)
start = ext3_find_next_zero_bit(jh->b_committed_data,
maxblocks, next);
jbd_unlock_bh_state(bh);
}
return -1;
}

/**
* find_next_usable_block()
* @start: the starting block (group relative) to find next
* allocatable block in bitmap.
* @bh: bufferhead contains the block group bitmap
* @maxblocks: the ending block (group relative) for the search
*
* Find an allocatable block in a bitmap. We honor both the bitmap and
* its last-committed copy (if that exists), and perform the «most
* appropriate allocation» algorithm of looking for a free block near
* the initial goal; then for a free byte somewhere in the bitmap; then
* for any free bit in the bitmap.
*/
static ext3_grpblk_t
find_next_usable_block(ext3_grpblk_t start, struct buffer_head *bh,
ext3_grpblk_t maxblocks)
{
ext3_grpblk_t here, next;
char *p, *r;

if (start > 0) {
/*
* The goal was occupied; search forward for a free
* block within the next XX blocks.
*
* end_goal is more or less random, but it has to be
* less than EXT3_BLOCKS_PER_GROUP. Aligning up to the
* next 64-bit boundary is simple..
*/
ext3_grpblk_t end_goal = (start + 63) & ~63;
if (end_goal > maxblocks)
end_goal = maxblocks;
here = ext3_find_next_zero_bit(bh->b_data, end_goal, start);
if (here < end_goal && ext3_test_allocatable(here, bh))
return here;
ext3_debug("Bit not found near goal\n");
}

here = start;
if (here < 0)
here = 0;

p = ((char *)bh->b_data) + (here >> 3);
r = memscan(p, 0, ((maxblocks + 7) >> 3) – (here >> 3));
next = (r – ((char *)bh->b_data)) << 3;

if (next < maxblocks && next >= start && ext3_test_allocatable(next, bh))
return next;

/*
* The bitmap search — search forward alternately through the actual
* bitmap and the last-committed copy until we find a bit free in
* both
*/
here = bitmap_search_next_usable_block(here, bh, maxblocks);
return here;
}

/**
* claim_block()
* @block: the free block (group relative) to allocate
* @bh: the bufferhead containts the block group bitmap
*
* We think we can allocate this block in this bitmap. Try to set the bit.
* If that succeeds then check that nobody has allocated and then freed the
* block since we saw that is was not marked in b_committed_data. If it _was_
* allocated and freed then clear the bit in the bitmap again and return
* zero (failure).
*/
static inline int
claim_block(spinlock_t *lock, ext3_grpblk_t block, struct buffer_head *bh)
{
struct journal_head *jh = bh2jh(bh);
int ret;

if (ext3_set_bit_atomic(lock, block, bh->b_data))
return 0;
jbd_lock_bh_state(bh);
if (jh->b_committed_data && ext3_test_bit(block,jh->b_committed_data)) {
ext3_clear_bit_atomic(lock, block, bh->b_data);
ret = 0;
} else {
ret = 1;
}
jbd_unlock_bh_state(bh);
return ret;
}

/**
* ext3_try_to_allocate()
* @sb: superblock
* @handle: handle to this transaction
* @group: given allocation block group
* @bitmap_bh: bufferhead holds the block bitmap
* @grp_goal: given target block within the group
* @count: target number of blocks to allocate
* @my_rsv: reservation window
*
* Attempt to allocate blocks within a give range. Set the range of allocation
* first, then find the first free bit(s) from the bitmap (within the range),
* and at last, allocate the blocks by claiming the found free bit as allocated.
*
* To set the range of this allocation:
* if there is a reservation window, only try to allocate block(s) from the
* file’s own reservation window;
* Otherwise, the allocation range starts from the give goal block, ends at
* the block group’s last block.
*
* If we failed to allocate the desired block then we may end up crossing to a
* new bitmap. In that case we must release write access to the old one via
* ext3_journal_release_buffer(), else we’ll run out of credits.
*/
static ext3_grpblk_t
ext3_try_to_allocate(struct super_block *sb, handle_t *handle, int group,
struct buffer_head *bitmap_bh, ext3_grpblk_t grp_goal,
unsigned long *count, struct ext3_reserve_window *my_rsv)
{
ext3_fsblk_t group_first_block;
ext3_grpblk_t start, end;
unsigned long num = 0;

/* we do allocation within the reservation window if we have a window */
if (my_rsv) {
group_first_block = ext3_group_first_block_no(sb, group);
if (my_rsv->_rsv_start >= group_first_block)
start = my_rsv->_rsv_start – group_first_block;
else
/* reservation window cross group boundary */
start = 0;
end = my_rsv->_rsv_end – group_first_block + 1;
if (end > EXT3_BLOCKS_PER_GROUP(sb))
/* reservation window crosses group boundary */
end = EXT3_BLOCKS_PER_GROUP(sb);
if ((start <= grp_goal) && (grp_goal < end))
start = grp_goal;
else
grp_goal = -1;
} else {
if (grp_goal > 0)
start = grp_goal;
else
start = 0;
end = EXT3_BLOCKS_PER_GROUP(sb);
}

BUG_ON(start > EXT3_BLOCKS_PER_GROUP(sb));

repeat:
if (grp_goal < 0 || !ext3_test_allocatable(grp_goal, bitmap_bh)) {
grp_goal = find_next_usable_block(start, bitmap_bh, end);
if (grp_goal < 0)
goto fail_access;
if (!my_rsv) {
int i;

for (i = 0; i < 7 && grp_goal > start &&
ext3_test_allocatable(grp_goal – 1,
bitmap_bh);
i++, grp_goal–)
;
}
}
start = grp_goal;

if (!claim_block(sb_bgl_lock(EXT3_SB(sb), group),
grp_goal, bitmap_bh)) {
/*
* The block was allocated by another thread, or it was
* allocated and then freed by another thread
*/
start++;
grp_goal++;
if (start >= end)
goto fail_access;
goto repeat;
}
num++;
grp_goal++;
while (num < *count && grp_goal < end
&& ext3_test_allocatable(grp_goal, bitmap_bh)
&& claim_block(sb_bgl_lock(EXT3_SB(sb), group),
grp_goal, bitmap_bh)) {
num++;
grp_goal++;
}
*count = num;
return grp_goal - num;
fail_access:
*count = num;
return -1;
}

/**
* find_next_reservable_window():
* find a reservable space within the given range.
* It does not allocate the reservation window for now:
* alloc_new_reservation() will do the work later.
*
* @search_head: the head of the searching list;
* This is not necessarily the list head of the whole filesystem
*
* We have both head and start_block to assist the search
* for the reservable space. The list starts from head,
* but we will shift to the place where start_block is,
* then start from there, when looking for a reservable space.
*
* @size: the target new reservation window size
*
* @group_first_block: the first block we consider to start
* the real search from
*
* @last_block:
* the maximum block number that our goal reservable space
* could start from. This is normally the last block in this
* group. The search will end when we found the start of next
* possible reservable space is out of this boundary.
* This could handle the cross boundary reservation window
* request.
*
* basically we search from the given range, rather than the whole
* reservation double linked list, (start_block, last_block)
* to find a free region that is of my size and has not
* been reserved.
*
*/
static int find_next_reservable_window(
struct ext3_reserve_window_node *search_head,
struct ext3_reserve_window_node *my_rsv,
struct super_block * sb,
ext3_fsblk_t start_block,
ext3_fsblk_t last_block)
{
struct rb_node *next;
struct ext3_reserve_window_node *rsv, *prev;
ext3_fsblk_t cur;
int size = my_rsv->rsv_goal_size;

/* TODO: make the start of the reservation window byte-aligned */
/* cur = *start_block & ~7;*/
cur = start_block;
rsv = search_head;
if (!rsv)
return -1;

while (1) {
if (cur <= rsv->rsv_end)
cur = rsv->rsv_end + 1;

/* TODO?
* in the case we could not find a reservable space
* that is what is expected, during the re-search, we could
* remember what’s the largest reservable space we could have
* and return that one.
*
* For now it will fail if we could not find the reservable
* space with expected-size (or more)…
*/
if (cur > last_block)
return -1; /* fail */

prev = rsv;
next = rb_next(&rsv->rsv_node);
rsv = rb_entry(next,struct ext3_reserve_window_node,rsv_node);

/*
* Reached the last reservation, we can just append to the
* previous one.
*/
if (!next)
break;

if (cur + size <= rsv->rsv_start) {
/*
* Found a reserveable space big enough. We could
* have a reservation across the group boundary here
*/
break;
}
}
/*
* we come here either :
* when we reach the end of the whole list,
* and there is empty reservable space after last entry in the list.
* append it to the end of the list.
*
* or we found one reservable space in the middle of the list,
* return the reservation window that we could append to.
* succeed.
*/

if ((prev != my_rsv) && (!rsv_is_empty(&my_rsv->rsv_window)))
rsv_window_remove(sb, my_rsv);

/*
* Let’s book the whole avaliable window for now. We will check the
* disk bitmap later and then, if there are free blocks then we adjust
* the window size if it’s larger than requested.
* Otherwise, we will remove this node from the tree next time
* call find_next_reservable_window.
*/
my_rsv->rsv_start = cur;
my_rsv->rsv_end = cur + size – 1;
my_rsv->rsv_alloc_hit = 0;

if (prev != my_rsv)
ext3_rsv_window_add(sb, my_rsv);

return 0;
}

/**
* alloc_new_reservation()–allocate a new reservation window
*
* To make a new reservation, we search part of the filesystem
* reservation list (the list that inside the group). We try to
* allocate a new reservation window near the allocation goal,
* or the beginning of the group, if there is no goal.
*
* We first find a reservable space after the goal, then from
* there, we check the bitmap for the first free block after
* it. If there is no free block until the end of group, then the
* whole group is full, we failed. Otherwise, check if the free
* block is inside the expected reservable space, if so, we
* succeed.
* If the first free block is outside the reservable space, then
* start from the first free block, we search for next available
* space, and go on.
*
* on succeed, a new reservation will be found and inserted into the list
* It contains at least one free block, and it does not overlap with other
* reservation windows.
*
* failed: we failed to find a reservation window in this group
*
* @rsv: the reservation
*
* @grp_goal: The goal (group-relative). It is where the search for a
* free reservable space should start from.
* if we have a grp_goal(grp_goal >0 ), then start from there,
* no grp_goal(grp_goal = -1), we start from the first block
* of the group.
*
* @sb: the super block
* @group: the group we are trying to allocate in
* @bitmap_bh: the block group block bitmap
*
*/
static int alloc_new_reservation(struct ext3_reserve_window_node *my_rsv,
ext3_grpblk_t grp_goal, struct super_block *sb,
unsigned int group, struct buffer_head *bitmap_bh)
{
struct ext3_reserve_window_node *search_head;
ext3_fsblk_t group_first_block, group_end_block, start_block;
ext3_grpblk_t first_free_block;
struct rb_root *fs_rsv_root = &EXT3_SB(sb)->s_rsv_window_root;
unsigned long size;
int ret;
spinlock_t *rsv_lock = &EXT3_SB(sb)->s_rsv_window_lock;

group_first_block = ext3_group_first_block_no(sb, group);
group_end_block = group_first_block + (EXT3_BLOCKS_PER_GROUP(sb) – 1);

if (grp_goal < 0)
start_block = group_first_block;
else
start_block = grp_goal + group_first_block;

size = my_rsv->rsv_goal_size;

if (!rsv_is_empty(&my_rsv->rsv_window)) {
/*
* if the old reservation is cross group boundary
* and if the goal is inside the old reservation window,
* we will come here when we just failed to allocate from
* the first part of the window. We still have another part
* that belongs to the next group. In this case, there is no
* point to discard our window and try to allocate a new one
* in this group(which will fail). we should
* keep the reservation window, just simply move on.
*
* Maybe we could shift the start block of the reservation
* window to the first block of next group.
*/

if ((my_rsv->rsv_start <= group_end_block) &&
(my_rsv->rsv_end > group_end_block) &&
(start_block >= my_rsv->rsv_start))
return -1;

if ((my_rsv->rsv_alloc_hit >
(my_rsv->rsv_end – my_rsv->rsv_start + 1) / 2)) {
/*
* if the previously allocation hit ratio is
* greater than 1/2, then we double the size of
* the reservation window the next time,
* otherwise we keep the same size window
*/
size = size * 2;
if (size > EXT3_MAX_RESERVE_BLOCKS)
size = EXT3_MAX_RESERVE_BLOCKS;
my_rsv->rsv_goal_size= size;
}
}

spin_lock(rsv_lock);
/*
* shift the search start to the window near the goal block
*/
search_head = search_reserve_window(fs_rsv_root, start_block);

/*
* find_next_reservable_window() simply finds a reservable window
* inside the given range(start_block, group_end_block).
*
* To make sure the reservation window has a free bit inside it, we
* need to check the bitmap after we found a reservable window.
*/
retry:
ret = find_next_reservable_window(search_head, my_rsv, sb,
start_block, group_end_block);

if (ret == -1) {
if (!rsv_is_empty(&my_rsv->rsv_window))
rsv_window_remove(sb, my_rsv);
spin_unlock(rsv_lock);
return -1;
}

/*
* On success, find_next_reservable_window() returns the
* reservation window where there is a reservable space after it.
* Before we reserve this reservable space, we need
* to make sure there is at least a free block inside this region.
*
* searching the first free bit on the block bitmap and copy of
* last committed bitmap alternatively, until we found a allocatable
* block. Search start from the start block of the reservable space
* we just found.
*/
spin_unlock(rsv_lock);
first_free_block = bitmap_search_next_usable_block(
my_rsv->rsv_start – group_first_block,
bitmap_bh, group_end_block – group_first_block + 1);

if (first_free_block < 0) {
/*
* no free block left on the bitmap, no point
* to reserve the space. return failed.
*/
spin_lock(rsv_lock);
if (!rsv_is_empty(&my_rsv->rsv_window))
rsv_window_remove(sb, my_rsv);
spin_unlock(rsv_lock);
return -1; /* failed */
}

start_block = first_free_block + group_first_block;
/*
* check if the first free block is within the
* free space we just reserved
*/
if (start_block >= my_rsv->rsv_start && start_block <= my_rsv->rsv_end)
return 0; /* success */
/*
* if the first free bit we found is out of the reservable space
* continue search for next reservable space,
* start from where the free block is,
* we also shift the list head to where we stopped last time
*/
search_head = my_rsv;
spin_lock(rsv_lock);
goto retry;
}

/**
* try_to_extend_reservation()
* @my_rsv: given reservation window
* @sb: super block
* @size: the delta to extend
*
* Attempt to expand the reservation window large enough to have
* required number of free blocks
*
* Since ext3_try_to_allocate() will always allocate blocks within
* the reservation window range, if the window size is too small,
* multiple blocks allocation has to stop at the end of the reservation
* window. To make this more efficient, given the total number of
* blocks needed and the current size of the window, we try to
* expand the reservation window size if necessary on a best-effort
* basis before ext3_new_blocks() tries to allocate blocks,
*/
static void try_to_extend_reservation(struct ext3_reserve_window_node *my_rsv,
struct super_block *sb, int size)
{
struct ext3_reserve_window_node *next_rsv;
struct rb_node *next;
spinlock_t *rsv_lock = &EXT3_SB(sb)->s_rsv_window_lock;

if (!spin_trylock(rsv_lock))
return;

next = rb_next(&my_rsv->rsv_node);

if (!next)
my_rsv->rsv_end += size;
else {
next_rsv = rb_entry(next, struct ext3_reserve_window_node, rsv_node);

if ((next_rsv->rsv_start – my_rsv->rsv_end – 1) >= size)
my_rsv->rsv_end += size;
else
my_rsv->rsv_end = next_rsv->rsv_start – 1;
}
spin_unlock(rsv_lock);
}

/**
* ext3_try_to_allocate_with_rsv()
* @sb: superblock
* @handle: handle to this transaction
* @group: given allocation block group
* @bitmap_bh: bufferhead holds the block bitmap
* @grp_goal: given target block within the group
* @count: target number of blocks to allocate
* @my_rsv: reservation window
* @errp: pointer to store the error code
*
* This is the main function used to allocate a new block and its reservation
* window.
*
* Each time when a new block allocation is need, first try to allocate from
* its own reservation. If it does not have a reservation window, instead of
* looking for a free bit on bitmap first, then look up the reservation list to
* see if it is inside somebody else’s reservation window, we try to allocate a
* reservation window for it starting from the goal first. Then do the block
* allocation within the reservation window.
*
* This will avoid keeping on searching the reservation list again and
* again when somebody is looking for a free block (without
* reservation), and there are lots of free blocks, but they are all
* being reserved.
*
* We use a red-black tree for the per-filesystem reservation list.
*
*/
static ext3_grpblk_t
ext3_try_to_allocate_with_rsv(struct super_block *sb, handle_t *handle,
unsigned int group, struct buffer_head *bitmap_bh,
ext3_grpblk_t grp_goal,
struct ext3_reserve_window_node * my_rsv,
unsigned long *count, int *errp)
{
ext3_fsblk_t group_first_block, group_last_block;
ext3_grpblk_t ret = 0;
int fatal;
unsigned long num = *count;

*errp = 0;

/*
* Make sure we use undo access for the bitmap, because it is critical
* that we do the frozen_data COW on bitmap buffers in all cases even
* if the buffer is in BJ_Forget state in the committing transaction.
*/
BUFFER_TRACE(bitmap_bh, «get undo access for new block»);
fatal = ext3_journal_get_undo_access(handle, bitmap_bh);
if (fatal) {
*errp = fatal;
return -1;
}

/*
* we don’t deal with reservation when
* filesystem is mounted without reservation
* or the file is not a regular file
* or last attempt to allocate a block with reservation turned on failed
*/
if (my_rsv == NULL ) {
ret = ext3_try_to_allocate(sb, handle, group, bitmap_bh,
grp_goal, count, NULL);
goto out;
}
/*
* grp_goal is a group relative block number (if there is a goal)
* 0 <= grp_goal < EXT3_BLOCKS_PER_GROUP(sb)
* first block is a filesystem wide block number
* first block is the block number of the first block in this group
*/
group_first_block = ext3_group_first_block_no(sb, group);
group_last_block = group_first_block + (EXT3_BLOCKS_PER_GROUP(sb) - 1);

/*
* Basically we will allocate a new block from inode's reservation
* window.
*
* We need to allocate a new reservation window, if:
* a) inode does not have a reservation window; or
* b) last attempt to allocate a block from existing reservation
* failed; or
* c) we come here with a goal and with a reservation window
*
* We do not need to allocate a new reservation window if we come here
* at the beginning with a goal and the goal is inside the window, or
* we don't have a goal but already have a reservation window.
* then we could go to allocate from the reservation window directly.
*/
while (1) {
if (rsv_is_empty(&my_rsv->rsv_window) || (ret < 0) ||
!goal_in_my_reservation(&my_rsv->rsv_window,
grp_goal, group, sb)) {
if (my_rsv->rsv_goal_size < *count)
my_rsv->rsv_goal_size = *count;
ret = alloc_new_reservation(my_rsv, grp_goal, sb,
group, bitmap_bh);
if (ret < 0)
break; /* failed */

if (!goal_in_my_reservation(&my_rsv->rsv_window,
grp_goal, group, sb))
grp_goal = -1;
} else if (grp_goal >= 0) {
int curr = my_rsv->rsv_end -
(grp_goal + group_first_block) + 1;

if (curr < *count)
try_to_extend_reservation(my_rsv, sb,
*count - curr);
}

if ((my_rsv->rsv_start > group_last_block) ||
(my_rsv->rsv_end < group_first_block)) {
rsv_window_dump(&EXT3_SB(sb)->s_rsv_window_root, 1);
BUG();
}
ret = ext3_try_to_allocate(sb, handle, group, bitmap_bh,
grp_goal, &num, &my_rsv->rsv_window);
if (ret >= 0) {
my_rsv->rsv_alloc_hit += num;
*count = num;
break; /* succeed */
}
num = *count;
}
out:
if (ret >= 0) {
BUFFER_TRACE(bitmap_bh, «journal_dirty_metadata for »
«bitmap block»);
fatal = ext3_journal_dirty_metadata(handle, bitmap_bh);
if (fatal) {
*errp = fatal;
return -1;
}
return ret;
}

BUFFER_TRACE(bitmap_bh, «journal_release_buffer»);
ext3_journal_release_buffer(handle, bitmap_bh);
return ret;
}

/**
* ext3_has_free_blocks()
* @sbi: in-core super block structure.
*
* Check if filesystem has at least 1 free block available for allocation.
*/
static int ext3_has_free_blocks(struct ext3_sb_info *sbi)
{
ext3_fsblk_t free_blocks, root_blocks;

free_blocks = percpu_counter_read_positive(&sbi->s_freeblocks_counter);
root_blocks = le32_to_cpu(sbi->s_es->s_r_blocks_count);
if (free_blocks < root_blocks + 1 && !capable(CAP_SYS_RESOURCE) &&
sbi->s_resuid != current_fsuid() &&
(sbi->s_resgid == 0 || !in_group_p (sbi->s_resgid))) {
return 0;
}
return 1;
}

/**
* ext3_should_retry_alloc()
* @sb: super block
* @retries number of attemps has been made
*
* ext3_should_retry_alloc() is called when ENOSPC is returned, and if
* it is profitable to retry the operation, this function will wait
* for the current or commiting transaction to complete, and then
* return TRUE.
*
* if the total number of retries exceed three times, return FALSE.
*/
int ext3_should_retry_alloc(struct super_block *sb, int *retries)
{
if (!ext3_has_free_blocks(EXT3_SB(sb)) || (*retries)++ > 3)
return 0;

jbd_debug(1, «%s: retrying operation after ENOSPC\n», sb->s_id);

return journal_force_commit_nested(EXT3_SB(sb)->s_journal);
}

/**
* ext3_new_blocks() — core block(s) allocation function
* @handle: handle to this transaction
* @inode: file inode
* @goal: given target block(filesystem wide)
* @count: target number of blocks to allocate
* @errp: error code
*
* ext3_new_blocks uses a goal block to assist allocation. It tries to
* allocate block(s) from the block group contains the goal block first. If that
* fails, it will try to allocate block(s) from other block groups without
* any specific goal block.
*
*/
ext3_fsblk_t ext3_new_blocks(handle_t *handle, struct inode *inode,
ext3_fsblk_t goal, unsigned long *count, int *errp)
{
struct buffer_head *bitmap_bh = NULL;
struct buffer_head *gdp_bh;
int group_no;
int goal_group;
ext3_grpblk_t grp_target_blk; /* blockgroup relative goal block */
ext3_grpblk_t grp_alloc_blk; /* blockgroup-relative allocated block*/
ext3_fsblk_t ret_block; /* filesyetem-wide allocated block */
int bgi; /* blockgroup iteration index */
int fatal = 0, err;
int performed_allocation = 0;
ext3_grpblk_t free_blocks; /* number of free blocks in a group */
struct super_block *sb;
struct ext3_group_desc *gdp;
struct ext3_super_block *es;
struct ext3_sb_info *sbi;
struct ext3_reserve_window_node *my_rsv = NULL;
struct ext3_block_alloc_info *block_i;
unsigned short windowsz = 0;
#ifdef EXT3FS_DEBUG
static int goal_hits, goal_attempts;
#endif
unsigned long ngroups;
unsigned long num = *count;

*errp = -ENOSPC;
sb = inode->i_sb;
if (!sb) {
printk(»ext3_new_block: nonexistent device»);
return 0;
}

/*
* Check quota for allocation of this block.
*/
if (vfs_dq_alloc_block(inode, num)) {
*errp = -EDQUOT;
return 0;
}

sbi = EXT3_SB(sb);
es = EXT3_SB(sb)->s_es;
ext3_debug(»goal=%lu.\n», goal);
/*
* Allocate a block from reservation only when
* filesystem is mounted with reservation(default,-o reservation), and
* it’s a regular file, and
* the desired window size is greater than 0 (One could use ioctl
* command EXT3_IOC_SETRSVSZ to set the window size to 0 to turn off
* reservation on that particular file)
*/
block_i = EXT3_I(inode)->i_block_alloc_info;
if (block_i && ((windowsz = block_i->rsv_window_node.rsv_goal_size) > 0))
my_rsv = &block_i->rsv_window_node;

if (!ext3_has_free_blocks(sbi)) {
*errp = -ENOSPC;
goto out;
}

/*
* First, test whether the goal block is free.
*/
if (goal < le32_to_cpu(es->s_first_data_block) ||
goal >= le32_to_cpu(es->s_blocks_count))
goal = le32_to_cpu(es->s_first_data_block);
group_no = (goal – le32_to_cpu(es->s_first_data_block)) /
EXT3_BLOCKS_PER_GROUP(sb);
goal_group = group_no;
retry_alloc:
gdp = ext3_get_group_desc(sb, group_no, &gdp_bh);
if (!gdp)
goto io_error;

free_blocks = le16_to_cpu(gdp->bg_free_blocks_count);
/*
* if there is not enough free blocks to make a new resevation
* turn off reservation for this allocation
*/
if (my_rsv && (free_blocks < windowsz)
&& (free_blocks > 0)
&& (rsv_is_empty(&my_rsv->rsv_window)))
my_rsv = NULL;

if (free_blocks > 0) {
grp_target_blk = ((goal – le32_to_cpu(es->s_first_data_block)) %
EXT3_BLOCKS_PER_GROUP(sb));
bitmap_bh = read_block_bitmap(sb, group_no);
if (!bitmap_bh)
goto io_error;
grp_alloc_blk = ext3_try_to_allocate_with_rsv(sb, handle,
group_no, bitmap_bh, grp_target_blk,
my_rsv, &num, &fatal);
if (fatal)
goto out;
if (grp_alloc_blk >= 0)
goto allocated;
}

ngroups = EXT3_SB(sb)->s_groups_count;
smp_rmb();

/*
* Now search the rest of the groups. We assume that
* group_no and gdp correctly point to the last group visited.
*/
for (bgi = 0; bgi < ngroups; bgi++) {
group_no++;
if (group_no >= ngroups)
group_no = 0;
gdp = ext3_get_group_desc(sb, group_no, &gdp_bh);
if (!gdp)
goto io_error;
free_blocks = le16_to_cpu(gdp->bg_free_blocks_count);
/*
* skip this group if the number of
* free blocks is less than half of the reservation
* window size.
*/
if (my_rsv && (free_blocks <= (windowsz/2)))
continue;

brelse(bitmap_bh);
bitmap_bh = read_block_bitmap(sb, group_no);
if (!bitmap_bh)
goto io_error;
/*
* try to allocate block(s) from this group, without a goal(-1).
*/
grp_alloc_blk = ext3_try_to_allocate_with_rsv(sb, handle,
group_no, bitmap_bh, -1, my_rsv,
&num, &fatal);
if (fatal)
goto out;
if (grp_alloc_blk >= 0)
goto allocated;
}
/*
* We may end up a bogus ealier ENOSPC error due to
* filesystem is «full» of reservations, but
* there maybe indeed free blocks avaliable on disk
* In this case, we just forget about the reservations
* just do block allocation as without reservations.
*/
if (my_rsv) {
my_rsv = NULL;
windowsz = 0;
group_no = goal_group;
goto retry_alloc;
}
/* No space left on the device */
*errp = -ENOSPC;
goto out;

allocated:

ext3_debug(»using block group %d(%d)\n»,
group_no, gdp->bg_free_blocks_count);

BUFFER_TRACE(gdp_bh, «get_write_access»);
fatal = ext3_journal_get_write_access(handle, gdp_bh);
if (fatal)
goto out;

ret_block = grp_alloc_blk + ext3_group_first_block_no(sb, group_no);

if (in_range(le32_to_cpu(gdp->bg_block_bitmap), ret_block, num) ||
in_range(le32_to_cpu(gdp->bg_inode_bitmap), ret_block, num) ||
in_range(ret_block, le32_to_cpu(gdp->bg_inode_table),
EXT3_SB(sb)->s_itb_per_group) ||
in_range(ret_block + num – 1, le32_to_cpu(gdp->bg_inode_table),
EXT3_SB(sb)->s_itb_per_group)) {
ext3_error(sb, «ext3_new_block»,
«Allocating block in system zone – »
«blocks from «E3FSBLK», length %lu»,
ret_block, num);
/*
* claim_block() marked the blocks we allocated as in use. So we
* may want to selectively mark some of the blocks as free.
*/
goto retry_alloc;
}

performed_allocation = 1;

#ifdef CONFIG_JBD_DEBUG
{
struct buffer_head *debug_bh;

/* Record bitmap buffer state in the newly allocated block */
debug_bh = sb_find_get_block(sb, ret_block);
if (debug_bh) {
BUFFER_TRACE(debug_bh, «state when allocated»);
BUFFER_TRACE2(debug_bh, bitmap_bh, «bitmap state»);
brelse(debug_bh);
}
}
jbd_lock_bh_state(bitmap_bh);
spin_lock(sb_bgl_lock(sbi, group_no));
if (buffer_jbd(bitmap_bh) && bh2jh(bitmap_bh)->b_committed_data) {
int i;

for (i = 0; i < num; i++) {
if (ext3_test_bit(grp_alloc_blk+i,
bh2jh(bitmap_bh)->b_committed_data)) {
printk(»%s: block was unexpectedly set in »
«b_committed_data\n», __func__);
}
}
}
ext3_debug(»found bit %d\n», grp_alloc_blk);
spin_unlock(sb_bgl_lock(sbi, group_no));
jbd_unlock_bh_state(bitmap_bh);
#endif

if (ret_block + num – 1 >= le32_to_cpu(es->s_blocks_count)) {
ext3_error(sb, «ext3_new_block»,
«block(»E3FSBLK») >= blocks count(%d) – »
«block_group = %d, es == %p «, ret_block,
le32_to_cpu(es->s_blocks_count), group_no, es);
goto out;
}

/*
* It is up to the caller to add the new buffer to a journal
* list of some description. We don’t know in advance whether
* the caller wants to use it as metadata or data.
*/
ext3_debug(»allocating block %lu. Goal hits %d of %d.\n»,
ret_block, goal_hits, goal_attempts);

spin_lock(sb_bgl_lock(sbi, group_no));
le16_add_cpu(&gdp->bg_free_blocks_count, -num);
spin_unlock(sb_bgl_lock(sbi, group_no));
percpu_counter_sub(&sbi->s_freeblocks_counter, num);

BUFFER_TRACE(gdp_bh, «journal_dirty_metadata for group descriptor»);
err = ext3_journal_dirty_metadata(handle, gdp_bh);
if (!fatal)
fatal = err;

if (fatal)
goto out;

*errp = 0;
brelse(bitmap_bh);
vfs_dq_free_block(inode, *count-num);
*count = num;
return ret_block;

io_error:
*errp = -EIO;
out:
if (fatal) {
*errp = fatal;
ext3_std_error(sb, fatal);
}
/*
* Undo the block allocation
*/
if (!performed_allocation)
vfs_dq_free_block(inode, *count);
brelse(bitmap_bh);
return 0;
}

ext3_fsblk_t ext3_new_block(handle_t *handle, struct inode *inode,
ext3_fsblk_t goal, int *errp)
{
unsigned long count = 1;

return ext3_new_blocks(handle, inode, goal, &count, errp);
}

/**
* ext3_count_free_blocks() — count filesystem free blocks
* @sb: superblock
*
* Adds up the number of free blocks from each block group.
*/
ext3_fsblk_t ext3_count_free_blocks(struct super_block *sb)
{
ext3_fsblk_t desc_count;
struct ext3_group_desc *gdp;
int i;
unsigned long ngroups = EXT3_SB(sb)->s_groups_count;
#ifdef EXT3FS_DEBUG
struct ext3_super_block *es;
ext3_fsblk_t bitmap_count;
unsigned long x;
struct buffer_head *bitmap_bh = NULL;

es = EXT3_SB(sb)->s_es;
desc_count = 0;
bitmap_count = 0;
gdp = NULL;

smp_rmb();
for (i = 0; i < ngroups; i++) {
gdp = ext3_get_group_desc(sb, i, NULL);
if (!gdp)
continue;
desc_count += le16_to_cpu(gdp->bg_free_blocks_count);
brelse(bitmap_bh);
bitmap_bh = read_block_bitmap(sb, i);
if (bitmap_bh == NULL)
continue;

x = ext3_count_free(bitmap_bh, sb->s_blocksize);
printk(»group %d: stored = %d, counted = %lu\n»,
i, le16_to_cpu(gdp->bg_free_blocks_count), x);
bitmap_count += x;
}
brelse(bitmap_bh);
printk(»ext3_count_free_blocks: stored = «E3FSBLK
«, computed = «E3FSBLK», «E3FSBLK»\n»,
le32_to_cpu(es->s_free_blocks_count),
desc_count, bitmap_count);
return bitmap_count;
#else
desc_count = 0;
smp_rmb();
for (i = 0; i < ngroups; i++) {
gdp = ext3_get_group_desc(sb, i, NULL);
if (!gdp)
continue;
desc_count += le16_to_cpu(gdp->bg_free_blocks_count);
}

return desc_count;
#endif
}

static inline int test_root(int a, int b)
{
int num = b;

while (a > num)
num *= b;
return num == a;
}

static int ext3_group_sparse(int group)
{
if (group <= 1)
return 1;
if (!(group & 1))
return 0;
return (test_root(group, 7) || test_root(group, 5) ||
test_root(group, 3));
}

/**
* ext3_bg_has_super - number of blocks used by the superblock in group
* @sb: superblock for filesystem
* @group: group number to check
*
* Return the number of blocks used by the superblock (primary or backup)
* in this group. Currently this will be only 0 or 1.
*/
int ext3_bg_has_super(struct super_block *sb, int group)
{
if (EXT3_HAS_RO_COMPAT_FEATURE(sb,
EXT3_FEATURE_RO_COMPAT_SPARSE_SUPER) &&
!ext3_group_sparse(group))
return 0;
return 1;
}

static unsigned long ext3_bg_num_gdb_meta(struct super_block *sb, int group)
{
unsigned long metagroup = group / EXT3_DESC_PER_BLOCK(sb);
unsigned long first = metagroup * EXT3_DESC_PER_BLOCK(sb);
unsigned long last = first + EXT3_DESC_PER_BLOCK(sb) - 1;

if (group == first || group == first + 1 || group == last)
return 1;
return 0;
}

static unsigned long ext3_bg_num_gdb_nometa(struct super_block *sb, int group)
{
return ext3_bg_has_super(sb, group) ? EXT3_SB(sb)->s_gdb_count : 0;
}

/**
* ext3_bg_num_gdb – number of blocks used by the group table in group
* @sb: superblock for filesystem
* @group: group number to check
*
* Return the number of blocks used by the group descriptor table
* (primary or backup) in this group. In the future there may be a
* different number of descriptor blocks in each group.
*/
unsigned long ext3_bg_num_gdb(struct super_block *sb, int group)
{
unsigned long first_meta_bg =
le32_to_cpu(EXT3_SB(sb)->s_es->s_first_meta_bg);
unsigned long metagroup = group / EXT3_DESC_PER_BLOCK(sb);

if (!EXT3_HAS_INCOMPAT_FEATURE(sb,EXT3_FEATURE_INCOMPAT_META_BG) ||
metagroup < first_meta_bg)
return ext3_bg_num_gdb_nometa(sb,group);

return ext3_bg_num_gdb_meta(sb,group);

}

(C) 2001 Andreas Gruenbacher,
*/

#include

#define EXT3_ACL_VERSION 0×0001

typedef struct {
__le16 e_tag;
__le16 e_perm;
__le32 e_id;
} ext3_acl_entry;

typedef struct {
__le16 e_tag;
__le16 e_perm;
} ext3_acl_entry_short;

typedef struct {
__le32 a_version;
} ext3_acl_header;

static inline size_t ext3_acl_size(int count)
{
if (count <= 4) {
return sizeof(ext3_acl_header) +
count * sizeof(ext3_acl_entry_short);
} else {
return sizeof(ext3_acl_header) +
4 * sizeof(ext3_acl_entry_short) +
(count - 4) * sizeof(ext3_acl_entry);
}
}

static inline int ext3_acl_count(size_t size)
{
ssize_t s;
size -= sizeof(ext3_acl_header);
s = size - 4 * sizeof(ext3_acl_entry_short);
if (s < 0) {
if (size % sizeof(ext3_acl_entry_short))
return -1;
return size / sizeof(ext3_acl_entry_short);
} else {
if (s % sizeof(ext3_acl_entry))
return -1;
return s / sizeof(ext3_acl_entry) + 4;
}
}

#ifdef CONFIG_EXT3_FS_POSIX_ACL

/* acl.c */
extern int ext3_check_acl (struct inode *, int);
extern int ext3_acl_chmod (struct inode *);
extern int ext3_init_acl (handle_t *, struct inode *, struct inode *);

#else /* CONFIG_EXT3_FS_POSIX_ACL */
#include #define ext3_check_acl NULL

static inline int
ext3_acl_chmod(struct inode *inode)
{
return 0;
}

static inline int
ext3_init_acl(handle_t *handle, struct inode *inode, struct inode *dir)
{
return 0;
}
#endif /* CONFIG_EXT3_FS_POSIX_ACL */

#ifdef CONFIG_EXT2_FS_XIP
extern void ext2_xip_verify_sb (struct super_block *);
extern int ext2_clear_xip_target (struct inode *, sector_t);

static inline int ext2_use_xip (struct super_block *sb)
{
struct ext2_sb_info *sbi = EXT2_SB(sb);
return (sbi->s_mount_opt & EXT2_MOUNT_XIP);
}
int ext2_get_xip_mem(struct address_space *, pgoff_t, int,
void **, unsigned long *);
#define mapping_is_xip(map) unlikely(map->a_ops->get_xip_mem)
#else
#define mapping_is_xip(map) 0
#define ext2_xip_verify_sb(sb) do { } while (0)
#define ext2_use_xip(sb) 0
#define ext2_clear_xip_target(inode, chain) 0
#define ext2_get_xip_mem NULL
#endif

#include #include #include #include #include #include #include #include «ext2.h»
#include «xip.h»

static inline int
__inode_direct_access(struct inode *inode, sector_t block,
void **kaddr, unsigned long *pfn)
{
struct block_device *bdev = inode->i_sb->s_bdev;
const struct block_device_operations *ops = bdev->bd_disk->fops;
sector_t sector;

sector = block * (PAGE_SIZE / 512); /* ext2 block to bdev sector */

BUG_ON(!ops->direct_access);
return ops->direct_access(bdev, sector, kaddr, pfn);
}

static inline int
__ext2_get_block(struct inode *inode, pgoff_t pgoff, int create,
sector_t *result)
{
struct buffer_head tmp;
int rc;

memset(&tmp, 0, sizeof(struct buffer_head));
rc = ext2_get_block(inode, pgoff, &tmp, create);
*result = tmp.b_blocknr;

/* did we get a sparse block (hole in the file)? */
if (!tmp.b_blocknr && !rc) {
BUG_ON(create);
rc = -ENODATA;
}

return rc;
}

int
ext2_clear_xip_target(struct inode *inode, sector_t block)
{
void *kaddr;
unsigned long pfn;
int rc;

rc = __inode_direct_access(inode, block, &kaddr, &pfn);
if (!rc)
clear_page(kaddr);
return rc;
}

void ext2_xip_verify_sb(struct super_block *sb)
{
struct ext2_sb_info *sbi = EXT2_SB(sb);

if ((sbi->s_mount_opt & EXT2_MOUNT_XIP) &&
!sb->s_bdev->bd_disk->fops->direct_access) {
sbi->s_mount_opt &= (~EXT2_MOUNT_XIP);
ext2_warning(sb, __func__,
«ignoring xip option – not supported by bdev»);
}
}

int ext2_get_xip_mem(struct address_space *mapping, pgoff_t pgoff, int create,
void **kmem, unsigned long *pfn)
{
int rc;
sector_t block;

/* first, retrieve the sector number */
rc = __ext2_get_block(mapping->host, pgoff, create, &block);
if (rc)
return rc;

/* retrieve address of the target data */
rc = __inode_direct_access(mapping->host, block, kmem, pfn);
return rc;
}

#include #include #include #include #include #include «xattr.h»

static size_t
ext2_xattr_security_list(struct inode *inode, char *list, size_t list_size,
const char *name, size_t name_len)
{
const int prefix_len = XATTR_SECURITY_PREFIX_LEN;
const size_t total_len = prefix_len + name_len + 1;

if (list && total_len <= list_size) {
memcpy(list, XATTR_SECURITY_PREFIX, prefix_len);
memcpy(list+prefix_len, name, name_len);
list[prefix_len + name_len] = ‘\0′;
}
return total_len;
}

static int
ext2_xattr_security_get(struct inode *inode, const char *name,
void *buffer, size_t size)
{
if (strcmp(name, «») == 0)
return -EINVAL;
return ext2_xattr_get(inode, EXT2_XATTR_INDEX_SECURITY, name,
buffer, size);
}

static int
ext2_xattr_security_set(struct inode *inode, const char *name,
const void *value, size_t size, int flags)
{
if (strcmp(name, «») == 0)
return -EINVAL;
return ext2_xattr_set(inode, EXT2_XATTR_INDEX_SECURITY, name,
value, size, flags);
}

int
ext2_init_security(struct inode *inode, struct inode *dir)
{
int err;
size_t len;
void *value;
char *name;

err = security_inode_init_security(inode, dir, &name, &value, &len);
if (err) {
if (err == -EOPNOTSUPP)
return 0;
return err;
}
err = ext2_xattr_set(inode, EXT2_XATTR_INDEX_SECURITY,
name, value, len, 0);
kfree(name);
kfree(value);
return err;
}

struct xattr_handler ext2_xattr_security_handler = {
.prefix = XATTR_SECURITY_PREFIX,
.list = ext2_xattr_security_list,
.get = ext2_xattr_security_get,
.set = ext2_xattr_security_set,
};

On-disk format of extended attributes for the ext2 filesystem.

(C) 2001 Andreas Gruenbacher,
*/

#include #include

/* Magic value in attribute blocks */
#define EXT2_XATTR_MAGIC 0xEA020000

/* Maximum number of references to one attribute block */
#define EXT2_XATTR_REFCOUNT_MAX 1024

/* Name indexes */
#define EXT2_XATTR_INDEX_USER 1
#define EXT2_XATTR_INDEX_POSIX_ACL_ACCESS 2
#define EXT2_XATTR_INDEX_POSIX_ACL_DEFAULT 3
#define EXT2_XATTR_INDEX_TRUSTED 4
#define EXT2_XATTR_INDEX_LUSTRE 5
#define EXT2_XATTR_INDEX_SECURITY 6

struct ext2_xattr_header {
__le32 h_magic; /* magic number for identification */
__le32 h_refcount; /* reference count */
__le32 h_blocks; /* number of disk blocks used */
__le32 h_hash; /* hash value of all attributes */
__u32 h_reserved[4]; /* zero right now */
};

struct ext2_xattr_entry {
__u8 e_name_len; /* length of name */
__u8 e_name_index; /* attribute name index */
__le16 e_value_offs; /* offset in disk block of value */
__le32 e_value_block; /* disk block attribute is stored on (n/i) */
__le32 e_value_size; /* size of attribute value */
__le32 e_hash; /* hash value of name and value */
char e_name[0]; /* attribute name */
};

#define EXT2_XATTR_PAD_BITS 2
#define EXT2_XATTR_PAD (1< #define EXT2_XATTR_ROUND (EXT2_XATTR_PAD-1)
#define EXT2_XATTR_LEN(name_len) \
(((name_len) + EXT2_XATTR_ROUND + \
sizeof(struct ext2_xattr_entry)) & ~EXT2_XATTR_ROUND)
#define EXT2_XATTR_NEXT(entry) \
( (struct ext2_xattr_entry *)( \
(char *)(entry) + EXT2_XATTR_LEN((entry)->e_name_len)) )
#define EXT2_XATTR_SIZE(size) \
(((size) + EXT2_XATTR_ROUND) & ~EXT2_XATTR_ROUND)

# ifdef CONFIG_EXT2_FS_XATTR

extern struct xattr_handler ext2_xattr_user_handler;
extern struct xattr_handler ext2_xattr_trusted_handler;
extern struct xattr_handler ext2_xattr_acl_access_handler;
extern struct xattr_handler ext2_xattr_acl_default_handler;
extern struct xattr_handler ext2_xattr_security_handler;

extern ssize_t ext2_listxattr(struct dentry *, char *, size_t);

extern int ext2_xattr_get(struct inode *, int, const char *, void *, size_t);
extern int ext2_xattr_set(struct inode *, int, const char *, const void *, size_t, int);

extern void ext2_xattr_delete_inode(struct inode *);
extern void ext2_xattr_put_super(struct super_block *);

extern int init_ext2_xattr(void);
extern void exit_ext2_xattr(void);

extern struct xattr_handler *ext2_xattr_handlers[];

# else /* CONFIG_EXT2_FS_XATTR */

static inline int
ext2_xattr_get(struct inode *inode, int name_index,
const char *name, void *buffer, size_t size)
{
return -EOPNOTSUPP;
}

static inline int
ext2_xattr_set(struct inode *inode, int name_index, const char *name,
const void *value, size_t size, int flags)
{
return -EOPNOTSUPP;
}

static inline void
ext2_xattr_delete_inode(struct inode *inode)
{
}

static inline void
ext2_xattr_put_super(struct super_block *sb)
{
}

static inline int
init_ext2_xattr(void)
{
return 0;
}

static inline void
exit_ext2_xattr(void)
{
}

#define ext2_xattr_handlers NULL

# endif /* CONFIG_EXT2_FS_XATTR */

#ifdef CONFIG_EXT2_FS_SECURITY
extern int ext2_init_security(struct inode *inode, struct inode *dir);
#else
static inline int ext2_init_security(struct inode *inode, struct inode *dir)
{
return 0;
}
#endif

#include «ext2.h»
#include «xattr.h»
#include

static void *ext2_follow_link(struct dentry *dentry, struct nameidata *nd)
{
struct ext2_inode_info *ei = EXT2_I(dentry->d_inode);
nd_set_link(nd, (char *)ei->i_data);
return NULL;
}

const struct inode_operations ext2_symlink_inode_operations = {
.readlink = generic_readlink,
.follow_link = page_follow_link_light,
.put_link = page_put_link,
#ifdef CONFIG_EXT2_FS_XATTR
.setxattr = generic_setxattr,
.getxattr = generic_getxattr,
.listxattr = ext2_listxattr,
.removexattr = generic_removexattr,
#endif
};

const struct inode_operations ext2_fast_symlink_inode_operations = {
.readlink = generic_readlink,
.follow_link = ext2_follow_link,
#ifdef CONFIG_EXT2_FS_XATTR
.setxattr = generic_setxattr,
.getxattr = generic_getxattr,
.listxattr = ext2_listxattr,
.removexattr = generic_removexattr,
#endif
};

#include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include
#include «ext2.h»
#include «xattr.h»
#include «acl.h»
#include «xip.h»

static void ext2_sync_super(struct super_block *sb,
struct ext2_super_block *es);
static int ext2_remount (struct super_block * sb, int * flags, char * data);
static int ext2_statfs (struct dentry * dentry, struct kstatfs * buf);
static int ext2_sync_fs(struct super_block *sb, int wait);

void ext2_error (struct super_block * sb, const char * function,
const char * fmt, …)
{
va_list args;
struct ext2_sb_info *sbi = EXT2_SB(sb);
struct ext2_super_block *es = sbi->s_es;

if (!(sb->s_flags & MS_RDONLY)) {
sbi->s_mount_state |= EXT2_ERROR_FS;
es->s_state |= cpu_to_le16(EXT2_ERROR_FS);
ext2_sync_super(sb, es);
}

va_start(args, fmt);
printk(KERN_CRIT «EXT2-fs error (device %s): %s: «,sb->s_id, function);
vprintk(fmt, args);
printk(»\n»);
va_end(args);

if (test_opt(sb, ERRORS_PANIC))
panic(»EXT2-fs panic from previous error\n»);
if (test_opt(sb, ERRORS_RO)) {
printk(»Remounting filesystem read-only\n»);
sb->s_flags |= MS_RDONLY;
}
}

void ext2_warning (struct super_block * sb, const char * function,
const char * fmt, …)
{
va_list args;

va_start(args, fmt);
printk(KERN_WARNING «EXT2-fs warning (device %s): %s: «,
sb->s_id, function);
vprintk(fmt, args);
printk(»\n»);
va_end(args);
}

void ext2_update_dynamic_rev(struct super_block *sb)
{
struct ext2_super_block *es = EXT2_SB(sb)->s_es;

if (le32_to_cpu(es->s_rev_level) > EXT2_GOOD_OLD_REV)
return;

ext2_warning(sb, __func__,
«updating to rev %d because of new feature flag, »
«running e2fsck is recommended»,
EXT2_DYNAMIC_REV);

es->s_first_ino = cpu_to_le32(EXT2_GOOD_OLD_FIRST_INO);
es->s_inode_size = cpu_to_le16(EXT2_GOOD_OLD_INODE_SIZE);
es->s_rev_level = cpu_to_le32(EXT2_DYNAMIC_REV);
/* leave es->s_feature_*compat flags alone */
/* es->s_uuid will be set by e2fsck if empty */

/*
* The rest of the superblock fields should be zero, and if not it
* means they are likely already in use, so leave them alone. We
* can leave it up to e2fsck to clean up any inconsistencies there.
*/
}

static void ext2_put_super (struct super_block * sb)
{
int db_count;
int i;
struct ext2_sb_info *sbi = EXT2_SB(sb);

lock_kernel();

if (sb->s_dirt)
ext2_write_super(sb);

ext2_xattr_put_super(sb);
if (!(sb->s_flags & MS_RDONLY)) {
struct ext2_super_block *es = sbi->s_es;

es->s_state = cpu_to_le16(sbi->s_mount_state);
ext2_sync_super(sb, es);
}
db_count = sbi->s_gdb_count;
for (i = 0; i < db_count; i++)
if (sbi->s_group_desc[i])
brelse (sbi->s_group_desc[i]);
kfree(sbi->s_group_desc);
kfree(sbi->s_debts);
percpu_counter_destroy(&sbi->s_freeblocks_counter);
percpu_counter_destroy(&sbi->s_freeinodes_counter);
percpu_counter_destroy(&sbi->s_dirs_counter);
brelse (sbi->s_sbh);
sb->s_fs_info = NULL;
kfree(sbi->s_blockgroup_lock);
kfree(sbi);

unlock_kernel();
}

static struct kmem_cache * ext2_inode_cachep;

static struct inode *ext2_alloc_inode(struct super_block *sb)
{
struct ext2_inode_info *ei;
ei = (struct ext2_inode_info *)kmem_cache_alloc(ext2_inode_cachep, GFP_KERNEL);
if (!ei)
return NULL;
ei->i_block_alloc_info = NULL;
ei->vfs_inode.i_version = 1;
return &ei->vfs_inode;
}

static void ext2_destroy_inode(struct inode *inode)
{
kmem_cache_free(ext2_inode_cachep, EXT2_I(inode));
}

static void init_once(void *foo)
{
struct ext2_inode_info *ei = (struct ext2_inode_info *) foo;

rwlock_init(&ei->i_meta_lock);
#ifdef CONFIG_EXT2_FS_XATTR
init_rwsem(&ei->xattr_sem);
#endif
mutex_init(&ei->truncate_mutex);
inode_init_once(&ei->vfs_inode);
}

static int init_inodecache(void)
{
ext2_inode_cachep = kmem_cache_create(»ext2_inode_cache»,
sizeof(struct ext2_inode_info),
0, (SLAB_RECLAIM_ACCOUNT|
SLAB_MEM_SPREAD),
init_once);
if (ext2_inode_cachep == NULL)
return -ENOMEM;
return 0;
}

static void destroy_inodecache(void)
{
kmem_cache_destroy(ext2_inode_cachep);
}

static void ext2_clear_inode(struct inode *inode)
{
struct ext2_block_alloc_info *rsv = EXT2_I(inode)->i_block_alloc_info;
ext2_discard_reservation(inode);
EXT2_I(inode)->i_block_alloc_info = NULL;
if (unlikely(rsv))
kfree(rsv);
}

static int ext2_show_options(struct seq_file *seq, struct vfsmount *vfs)
{
struct super_block *sb = vfs->mnt_sb;
struct ext2_sb_info *sbi = EXT2_SB(sb);
struct ext2_super_block *es = sbi->s_es;
unsigned long def_mount_opts;

def_mount_opts = le32_to_cpu(es->s_default_mount_opts);

if (sbi->s_sb_block != 1)
seq_printf(seq, «,sb=%lu», sbi->s_sb_block);
if (test_opt(sb, MINIX_DF))
seq_puts(seq, «,minixdf»);
if (test_opt(sb, GRPID))
seq_puts(seq, «,grpid»);
if (!test_opt(sb, GRPID) && (def_mount_opts & EXT2_DEFM_BSDGROUPS))
seq_puts(seq, «,nogrpid»);
if (sbi->s_resuid != EXT2_DEF_RESUID ||
le16_to_cpu(es->s_def_resuid) != EXT2_DEF_RESUID) {
seq_printf(seq, «,resuid=%u», sbi->s_resuid);
}
if (sbi->s_resgid != EXT2_DEF_RESGID ||
le16_to_cpu(es->s_def_resgid) != EXT2_DEF_RESGID) {
seq_printf(seq, «,resgid=%u», sbi->s_resgid);
}
if (test_opt(sb, ERRORS_RO)) {
int def_errors = le16_to_cpu(es->s_errors);

if (def_errors == EXT2_ERRORS_PANIC ||
def_errors == EXT2_ERRORS_CONTINUE) {
seq_puts(seq, «,errors=remount-ro»);
}
}
if (test_opt(sb, ERRORS_CONT))
seq_puts(seq, «,errors=continue»);
if (test_opt(sb, ERRORS_PANIC))
seq_puts(seq, «,errors=panic»);
if (test_opt(sb, NO_UID32))
seq_puts(seq, «,nouid32″);
if (test_opt(sb, DEBUG))
seq_puts(seq, «,debug»);
if (test_opt(sb, OLDALLOC))
seq_puts(seq, «,oldalloc»);

#ifdef CONFIG_EXT2_FS_XATTR
if (test_opt(sb, XATTR_USER))
seq_puts(seq, «,user_xattr»);
if (!test_opt(sb, XATTR_USER) &&
(def_mount_opts & EXT2_DEFM_XATTR_USER)) {
seq_puts(seq, «,nouser_xattr»);
}
#endif

#ifdef CONFIG_EXT2_FS_POSIX_ACL
if (test_opt(sb, POSIX_ACL))
seq_puts(seq, «,acl»);
if (!test_opt(sb, POSIX_ACL) && (def_mount_opts & EXT2_DEFM_ACL))
seq_puts(seq, «,noacl»);
#endif

if (test_opt(sb, NOBH))
seq_puts(seq, «,nobh»);

#if defined(CONFIG_QUOTA)
if (sbi->s_mount_opt & EXT2_MOUNT_USRQUOTA)
seq_puts(seq, «,usrquota»);

if (sbi->s_mount_opt & EXT2_MOUNT_GRPQUOTA)
seq_puts(seq, «,grpquota»);
#endif

#if defined(CONFIG_EXT2_FS_XIP)
if (sbi->s_mount_opt & EXT2_MOUNT_XIP)
seq_puts(seq, «,xip»);
#endif

if (!test_opt(sb, RESERVATION))
seq_puts(seq, «,noreservation»);

return 0;
}

#ifdef CONFIG_QUOTA
static ssize_t ext2_quota_read(struct super_block *sb, int type, char *data, size_t len, loff_t off);
static ssize_t ext2_quota_write(struct super_block *sb, int type, const char *data, size_t len, loff_t off);
#endif

static const struct super_operations ext2_sops = {
.alloc_inode = ext2_alloc_inode,
.destroy_inode = ext2_destroy_inode,
.write_inode = ext2_write_inode,
.delete_inode = ext2_delete_inode,
.put_super = ext2_put_super,
.write_super = ext2_write_super,
.sync_fs = ext2_sync_fs,
.statfs = ext2_statfs,
.remount_fs = ext2_remount,
.clear_inode = ext2_clear_inode,
.show_options = ext2_show_options,
#ifdef CONFIG_QUOTA
.quota_read = ext2_quota_read,
.quota_write = ext2_quota_write,
#endif
};

static struct inode *ext2_nfs_get_inode(struct super_block *sb,
u64 ino, u32 generation)
{
struct inode *inode;

if (ino < EXT2_FIRST_INO(sb) && ino != EXT2_ROOT_INO)
return ERR_PTR(-ESTALE);
if (ino > le32_to_cpu(EXT2_SB(sb)->s_es->s_inodes_count))
return ERR_PTR(-ESTALE);

/* iget isn’t really right if the inode is currently unallocated!!
* ext2_read_inode currently does appropriate checks, but
* it might be «neater» to call ext2_get_inode first and check
* if the inode is valid…..
*/
inode = ext2_iget(sb, ino);
if (IS_ERR(inode))
return ERR_CAST(inode);
if (generation && inode->i_generation != generation) {
/* we didn’t find the right inode.. */
iput(inode);
return ERR_PTR(-ESTALE);
}
return inode;
}

static struct dentry *ext2_fh_to_dentry(struct super_block *sb, struct fid *fid,
int fh_len, int fh_type)
{
return generic_fh_to_dentry(sb, fid, fh_len, fh_type,
ext2_nfs_get_inode);
}

static struct dentry *ext2_fh_to_parent(struct super_block *sb, struct fid *fid,
int fh_len, int fh_type)
{
return generic_fh_to_parent(sb, fid, fh_len, fh_type,
ext2_nfs_get_inode);
}

/* Yes, most of these are left as NULL!!
* A NULL value implies the default, which works with ext2-like file
* systems, but can be improved upon.
* Currently only get_parent is required.
*/
static const struct export_operations ext2_export_ops = {
.fh_to_dentry = ext2_fh_to_dentry,
.fh_to_parent = ext2_fh_to_parent,
.get_parent = ext2_get_parent,
};

static unsigned long get_sb_block(void **data)
{
unsigned long sb_block;
char *options = (char *) *data;

if (!options || strncmp(options, «sb=», 3) != 0)
return 1; /* Default location */
options += 3;
sb_block = simple_strtoul(options, &options, 0);
if (*options && *options != ‘,’) {
printk(»EXT2-fs: Invalid sb specification: %s\n»,
(char *) *data);
return 1;
}
if (*options == ‘,’)
options++;
*data = (void *) options;
return sb_block;
}

enum {
Opt_bsd_df, Opt_minix_df, Opt_grpid, Opt_nogrpid,
Opt_resgid, Opt_resuid, Opt_sb, Opt_err_cont, Opt_err_panic,
Opt_err_ro, Opt_nouid32, Opt_nocheck, Opt_debug,
Opt_oldalloc, Opt_orlov, Opt_nobh, Opt_user_xattr, Opt_nouser_xattr,
Opt_acl, Opt_noacl, Opt_xip, Opt_ignore, Opt_err, Opt_quota,
Opt_usrquota, Opt_grpquota, Opt_reservation, Opt_noreservation
};

static const match_table_t tokens = {
{Opt_bsd_df, «bsddf»},
{Opt_minix_df, «minixdf»},
{Opt_grpid, «grpid»},
{Opt_grpid, «bsdgroups»},
{Opt_nogrpid, «nogrpid»},
{Opt_nogrpid, «sysvgroups»},
{Opt_resgid, «resgid=%u»},
{Opt_resuid, «resuid=%u»},
{Opt_sb, «sb=%u»},
{Opt_err_cont, «errors=continue»},
{Opt_err_panic, «errors=panic»},
{Opt_err_ro, «errors=remount-ro»},
{Opt_nouid32, «nouid32″},
{Opt_nocheck, «check=none»},
{Opt_nocheck, «nocheck»},
{Opt_debug, «debug»},
{Opt_oldalloc, «oldalloc»},
{Opt_orlov, «orlov»},
{Opt_nobh, «nobh»},
{Opt_user_xattr, «user_xattr»},
{Opt_nouser_xattr, «nouser_xattr»},
{Opt_acl, «acl»},
{Opt_noacl, «noacl»},
{Opt_xip, «xip»},
{Opt_grpquota, «grpquota»},
{Opt_ignore, «noquota»},
{Opt_quota, «quota»},
{Opt_usrquota, «usrquota»},
{Opt_reservation, «reservation»},
{Opt_noreservation, «noreservation»},
{Opt_err, NULL}
};

static int parse_options (char * options,
struct ext2_sb_info *sbi)
{
char * p;
substring_t args[MAX_OPT_ARGS];
int option;

if (!options)
return 1;

while ((p = strsep (&options, «,»)) != NULL) {
int token;
if (!*p)
continue;

token = match_token(p, tokens, args);
switch (token) {
case Opt_bsd_df:
clear_opt (sbi->s_mount_opt, MINIX_DF);
break;
case Opt_minix_df:
set_opt (sbi->s_mount_opt, MINIX_DF);
break;
case Opt_grpid:
set_opt (sbi->s_mount_opt, GRPID);
break;
case Opt_nogrpid:
clear_opt (sbi->s_mount_opt, GRPID);
break;
case Opt_resuid:
if (match_int(&args[0], &option))
return 0;
sbi->s_resuid = option;
break;
case Opt_resgid:
if (match_int(&args[0], &option))
return 0;
sbi->s_resgid = option;
break;
case Opt_sb:
/* handled by get_sb_block() instead of here */
/* *sb_block = match_int(&args[0]); */
break;
case Opt_err_panic:
clear_opt (sbi->s_mount_opt, ERRORS_CONT);
clear_opt (sbi->s_mount_opt, ERRORS_RO);
set_opt (sbi->s_mount_opt, ERRORS_PANIC);
break;
case Opt_err_ro:
clear_opt (sbi->s_mount_opt, ERRORS_CONT);
clear_opt (sbi->s_mount_opt, ERRORS_PANIC);
set_opt (sbi->s_mount_opt, ERRORS_RO);
break;
case Opt_err_cont:
clear_opt (sbi->s_mount_opt, ERRORS_RO);
clear_opt (sbi->s_mount_opt, ERRORS_PANIC);
set_opt (sbi->s_mount_opt, ERRORS_CONT);
break;
case Opt_nouid32:
set_opt (sbi->s_mount_opt, NO_UID32);
break;
case Opt_nocheck:
clear_opt (sbi->s_mount_opt, CHECK);
break;
case Opt_debug:
set_opt (sbi->s_mount_opt, DEBUG);
break;
case Opt_oldalloc:
set_opt (sbi->s_mount_opt, OLDALLOC);
break;
case Opt_orlov:
clear_opt (sbi->s_mount_opt, OLDALLOC);
break;
case Opt_nobh:
set_opt (sbi->s_mount_opt, NOBH);
break;
#ifdef CONFIG_EXT2_FS_XATTR
case Opt_user_xattr:
set_opt (sbi->s_mount_opt, XATTR_USER);
break;
case Opt_nouser_xattr:
clear_opt (sbi->s_mount_opt, XATTR_USER);
break;
#else
case Opt_user_xattr:
case Opt_nouser_xattr:
printk(»EXT2 (no)user_xattr options not supported\n»);
break;
#endif
#ifdef CONFIG_EXT2_FS_POSIX_ACL
case Opt_acl:
set_opt(sbi->s_mount_opt, POSIX_ACL);
break;
case Opt_noacl:
clear_opt(sbi->s_mount_opt, POSIX_ACL);
break;
#else
case Opt_acl:
case Opt_noacl:
printk(»EXT2 (no)acl options not supported\n»);
break;
#endif
case Opt_xip:
#ifdef CONFIG_EXT2_FS_XIP
set_opt (sbi->s_mount_opt, XIP);
#else
printk(»EXT2 xip option not supported\n»);
#endif
break;

#if defined(CONFIG_QUOTA)
case Opt_quota:
case Opt_usrquota:
set_opt(sbi->s_mount_opt, USRQUOTA);
break;

case Opt_grpquota:
set_opt(sbi->s_mount_opt, GRPQUOTA);
break;
#else
case Opt_quota:
case Opt_usrquota:
case Opt_grpquota:
printk(KERN_ERR
«EXT2-fs: quota operations not supported.\n»);

break;
#endif

case Opt_reservation:
set_opt(sbi->s_mount_opt, RESERVATION);
printk(»reservations ON\n»);
break;
case Opt_noreservation:
clear_opt(sbi->s_mount_opt, RESERVATION);
printk(»reservations OFF\n»);
break;
case Opt_ignore:
break;
default:
return 0;
}
}
return 1;
}

static int ext2_setup_super (struct super_block * sb,
struct ext2_super_block * es,
int read_only)
{
int res = 0;
struct ext2_sb_info *sbi = EXT2_SB(sb);

if (le32_to_cpu(es->s_rev_level) > EXT2_MAX_SUPP_REV) {
printk (»EXT2-fs warning: revision level too high, »
«forcing read-only mode\n»);
res = MS_RDONLY;
}
if (read_only)
return res;
if (!(sbi->s_mount_state & EXT2_VALID_FS))
printk (»EXT2-fs warning: mounting unchecked fs, »
«running e2fsck is recommended\n»);
else if ((sbi->s_mount_state & EXT2_ERROR_FS))
printk (»EXT2-fs warning: mounting fs with errors, »
«running e2fsck is recommended\n»);
else if ((__s16) le16_to_cpu(es->s_max_mnt_count) >= 0 &&
le16_to_cpu(es->s_mnt_count) >=
(unsigned short) (__s16) le16_to_cpu(es->s_max_mnt_count))
printk (»EXT2-fs warning: maximal mount count reached, »
«running e2fsck is recommended\n»);
else if (le32_to_cpu(es->s_checkinterval) &&
(le32_to_cpu(es->s_lastcheck) + le32_to_cpu(es->s_checkinterval) <= get_seconds()))
printk ("EXT2-fs warning: checktime reached, "
"running e2fsck is recommended\n");
if (!le16_to_cpu(es->s_max_mnt_count))
es->s_max_mnt_count = cpu_to_le16(EXT2_DFL_MAX_MNT_COUNT);
le16_add_cpu(&es->s_mnt_count, 1);
ext2_write_super(sb);
if (test_opt (sb, DEBUG))
printk (»[EXT II FS %s, %s, bs=%lu, fs=%lu, gc=%lu, "
"bpg=%lu, ipg=%lu, mo=%04lx]\n»,
EXT2FS_VERSION, EXT2FS_DATE, sb->s_blocksize,
sbi->s_frag_size,
sbi->s_groups_count,
EXT2_BLOCKS_PER_GROUP(sb),
EXT2_INODES_PER_GROUP(sb),
sbi->s_mount_opt);
return res;
}

static int ext2_check_descriptors(struct super_block *sb)
{
int i;
struct ext2_sb_info *sbi = EXT2_SB(sb);

ext2_debug (»Checking group descriptors»);

for (i = 0; i < sbi->s_groups_count; i++) {
struct ext2_group_desc *gdp = ext2_get_group_desc(sb, i, NULL);
ext2_fsblk_t first_block = ext2_group_first_block_no(sb, i);
ext2_fsblk_t last_block;

if (i == sbi->s_groups_count – 1)
last_block = le32_to_cpu(sbi->s_es->s_blocks_count) – 1;
else
last_block = first_block +
(EXT2_BLOCKS_PER_GROUP(sb) – 1);

if (le32_to_cpu(gdp->bg_block_bitmap) < first_block ||
le32_to_cpu(gdp->bg_block_bitmap) > last_block)
{
ext2_error (sb, «ext2_check_descriptors»,
«Block bitmap for group %d»
» not in group (block %lu)!»,
i, (unsigned long) le32_to_cpu(gdp->bg_block_bitmap));
return 0;
}
if (le32_to_cpu(gdp->bg_inode_bitmap) < first_block ||
le32_to_cpu(gdp->bg_inode_bitmap) > last_block)
{
ext2_error (sb, «ext2_check_descriptors»,
«Inode bitmap for group %d»
» not in group (block %lu)!»,
i, (unsigned long) le32_to_cpu(gdp->bg_inode_bitmap));
return 0;
}
if (le32_to_cpu(gdp->bg_inode_table) < first_block ||
le32_to_cpu(gdp->bg_inode_table) + sbi->s_itb_per_group – 1 >
last_block)
{
ext2_error (sb, «ext2_check_descriptors»,
«Inode table for group %d»
» not in group (block %lu)!»,
i, (unsigned long) le32_to_cpu(gdp->bg_inode_table));
return 0;
}
}
return 1;
}

/*
* Maximal file size. There is a direct, and {,double-,triple-}indirect
* block limit, and also a limit of (2^32 – 1) 512-byte sectors in i_blocks.
* We need to be 1 filesystem block less than the 2^32 sector limit.
*/
static loff_t ext2_max_size(int bits)
{
loff_t res = EXT2_NDIR_BLOCKS;
int meta_blocks;
loff_t upper_limit;

/* This is calculated to be the largest file size for a
* dense, file such that the total number of
* sectors in the file, including data and all indirect blocks,
* does not exceed 2^32 -1
* __u32 i_blocks representing the total number of
* 512 bytes blocks of the file
*/
upper_limit = (1LL << 32) - 1;

/* total blocks in file system block size */
upper_limit >>= (bits – 9);

/* indirect blocks */
meta_blocks = 1;
/* double indirect blocks */
meta_blocks += 1 + (1LL << (bits-2));
/* tripple indirect blocks */
meta_blocks += 1 + (1LL << (bits-2)) + (1LL << (2*(bits-2)));

upper_limit -= meta_blocks;
upper_limit <<= bits;

res += 1LL << (bits-2);
res += 1LL << (2*(bits-2));
res += 1LL << (3*(bits-2));
res <<= bits;
if (res > upper_limit)
res = upper_limit;

if (res > MAX_LFS_FILESIZE)
res = MAX_LFS_FILESIZE;

return res;
}

static unsigned long descriptor_loc(struct super_block *sb,
unsigned long logic_sb_block,
int nr)
{
struct ext2_sb_info *sbi = EXT2_SB(sb);
unsigned long bg, first_meta_bg;
int has_super = 0;

first_meta_bg = le32_to_cpu(sbi->s_es->s_first_meta_bg);

if (!EXT2_HAS_INCOMPAT_FEATURE(sb, EXT2_FEATURE_INCOMPAT_META_BG) ||
nr < first_meta_bg)
return (logic_sb_block + nr + 1);
bg = sbi->s_desc_per_block * nr;
if (ext2_bg_has_super(sb, bg))
has_super = 1;

return ext2_group_first_block_no(sb, bg) + has_super;
}

static int ext2_fill_super(struct super_block *sb, void *data, int silent)
{
struct buffer_head * bh;
struct ext2_sb_info * sbi;
struct ext2_super_block * es;
struct inode *root;
unsigned long block;
unsigned long sb_block = get_sb_block(&data);
unsigned long logic_sb_block;
unsigned long offset = 0;
unsigned long def_mount_opts;
long ret = -EINVAL;
int blocksize = BLOCK_SIZE;
int db_count;
int i, j;
__le32 features;
int err;

sbi = kzalloc(sizeof(*sbi), GFP_KERNEL);
if (!sbi)
return -ENOMEM;

sbi->s_blockgroup_lock =
kzalloc(sizeof(struct blockgroup_lock), GFP_KERNEL);
if (!sbi->s_blockgroup_lock) {
kfree(sbi);
return -ENOMEM;
}
sb->s_fs_info = sbi;
sbi->s_sb_block = sb_block;

/*
* See what the current blocksize for the device is, and
* use that as the blocksize. Otherwise (or if the blocksize
* is smaller than the default) use the default.
* This is important for devices that have a hardware
* sectorsize that is larger than the default.
*/
blocksize = sb_min_blocksize(sb, BLOCK_SIZE);
if (!blocksize) {
printk (»EXT2-fs: unable to set blocksize\n»);
goto failed_sbi;
}

/*
* If the superblock doesn’t start on a hardware sector boundary,
* calculate the offset.
*/
if (blocksize != BLOCK_SIZE) {
logic_sb_block = (sb_block*BLOCK_SIZE) / blocksize;
offset = (sb_block*BLOCK_SIZE) % blocksize;
} else {
logic_sb_block = sb_block;
}

if (!(bh = sb_bread(sb, logic_sb_block))) {
printk (»EXT2-fs: unable to read superblock\n»);
goto failed_sbi;
}
/*
* Note: s_es must be initialized as soon as possible because
* some ext2 macro-instructions depend on its value
*/
es = (struct ext2_super_block *) (((char *)bh->b_data) + offset);
sbi->s_es = es;
sb->s_magic = le16_to_cpu(es->s_magic);

if (sb->s_magic != EXT2_SUPER_MAGIC)
goto cantfind_ext2;

/* Set defaults before we parse the mount options */
def_mount_opts = le32_to_cpu(es->s_default_mount_opts);
if (def_mount_opts & EXT2_DEFM_DEBUG)
set_opt(sbi->s_mount_opt, DEBUG);
if (def_mount_opts & EXT2_DEFM_BSDGROUPS)
set_opt(sbi->s_mount_opt, GRPID);
if (def_mount_opts & EXT2_DEFM_UID16)
set_opt(sbi->s_mount_opt, NO_UID32);
#ifdef CONFIG_EXT2_FS_XATTR
if (def_mount_opts & EXT2_DEFM_XATTR_USER)
set_opt(sbi->s_mount_opt, XATTR_USER);
#endif
#ifdef CONFIG_EXT2_FS_POSIX_ACL
if (def_mount_opts & EXT2_DEFM_ACL)
set_opt(sbi->s_mount_opt, POSIX_ACL);
#endif

if (le16_to_cpu(sbi->s_es->s_errors) == EXT2_ERRORS_PANIC)
set_opt(sbi->s_mount_opt, ERRORS_PANIC);
else if (le16_to_cpu(sbi->s_es->s_errors) == EXT2_ERRORS_CONTINUE)
set_opt(sbi->s_mount_opt, ERRORS_CONT);
else
set_opt(sbi->s_mount_opt, ERRORS_RO);

sbi->s_resuid = le16_to_cpu(es->s_def_resuid);
sbi->s_resgid = le16_to_cpu(es->s_def_resgid);

set_opt(sbi->s_mount_opt, RESERVATION);

if (!parse_options ((char *) data, sbi))
goto failed_mount;

sb->s_flags = (sb->s_flags & ~MS_POSIXACL) |
((EXT2_SB(sb)->s_mount_opt & EXT2_MOUNT_POSIX_ACL) ?
MS_POSIXACL : 0);

ext2_xip_verify_sb(sb); /* see if bdev supports xip, unset
EXT2_MOUNT_XIP if not */

if (le32_to_cpu(es->s_rev_level) == EXT2_GOOD_OLD_REV &&
(EXT2_HAS_COMPAT_FEATURE(sb, ~0U) ||
EXT2_HAS_RO_COMPAT_FEATURE(sb, ~0U) ||
EXT2_HAS_INCOMPAT_FEATURE(sb, ~0U)))
printk(»EXT2-fs warning: feature flags set on rev 0 fs, »
«running e2fsck is recommended\n»);
/*
* Check feature flags regardless of the revision level, since we
* previously didn’t change the revision level when setting the flags,
* so there is a chance incompat flags are set on a rev 0 filesystem.
*/
features = EXT2_HAS_INCOMPAT_FEATURE(sb, ~EXT2_FEATURE_INCOMPAT_SUPP);
if (features) {
printk(»EXT2-fs: %s: couldn’t mount because of »
«unsupported optional features (%x).\n»,
sb->s_id, le32_to_cpu(features));
goto failed_mount;
}
if (!(sb->s_flags & MS_RDONLY) &&
(features = EXT2_HAS_RO_COMPAT_FEATURE(sb, ~EXT2_FEATURE_RO_COMPAT_SUPP))){
printk(»EXT2-fs: %s: couldn’t mount RDWR because of »
«unsupported optional features (%x).\n»,
sb->s_id, le32_to_cpu(features));
goto failed_mount;
}

blocksize = BLOCK_SIZE << le32_to_cpu(sbi->s_es->s_log_block_size);

if (ext2_use_xip(sb) && blocksize != PAGE_SIZE) {
if (!silent)
printk(»XIP: Unsupported blocksize\n»);
goto failed_mount;
}

/* If the blocksize doesn’t match, re-read the thing.. */
if (sb->s_blocksize != blocksize) {
brelse(bh);

if (!sb_set_blocksize(sb, blocksize)) {
printk(KERN_ERR «EXT2-fs: blocksize too small for device.\n»);
goto failed_sbi;
}

logic_sb_block = (sb_block*BLOCK_SIZE) / blocksize;
offset = (sb_block*BLOCK_SIZE) % blocksize;
bh = sb_bread(sb, logic_sb_block);
if(!bh) {
printk(»EXT2-fs: Couldn’t read superblock on »
«2nd try.\n»);
goto failed_sbi;
}
es = (struct ext2_super_block *) (((char *)bh->b_data) + offset);
sbi->s_es = es;
if (es->s_magic != cpu_to_le16(EXT2_SUPER_MAGIC)) {
printk (»EXT2-fs: Magic mismatch, very weird !\n»);
goto failed_mount;
}
}

sb->s_maxbytes = ext2_max_size(sb->s_blocksize_bits);

if (le32_to_cpu(es->s_rev_level) == EXT2_GOOD_OLD_REV) {
sbi->s_inode_size = EXT2_GOOD_OLD_INODE_SIZE;
sbi->s_first_ino = EXT2_GOOD_OLD_FIRST_INO;
} else {
sbi->s_inode_size = le16_to_cpu(es->s_inode_size);
sbi->s_first_ino = le32_to_cpu(es->s_first_ino);
if ((sbi->s_inode_size < EXT2_GOOD_OLD_INODE_SIZE) ||
!is_power_of_2(sbi->s_inode_size) ||
(sbi->s_inode_size > blocksize)) {
printk (»EXT2-fs: unsupported inode size: %d\n»,
sbi->s_inode_size);
goto failed_mount;
}
}

sbi->s_frag_size = EXT2_MIN_FRAG_SIZE <<
le32_to_cpu(es->s_log_frag_size);
if (sbi->s_frag_size == 0)
goto cantfind_ext2;
sbi->s_frags_per_block = sb->s_blocksize / sbi->s_frag_size;

sbi->s_blocks_per_group = le32_to_cpu(es->s_blocks_per_group);
sbi->s_frags_per_group = le32_to_cpu(es->s_frags_per_group);
sbi->s_inodes_per_group = le32_to_cpu(es->s_inodes_per_group);

if (EXT2_INODE_SIZE(sb) == 0)
goto cantfind_ext2;
sbi->s_inodes_per_block = sb->s_blocksize / EXT2_INODE_SIZE(sb);
if (sbi->s_inodes_per_block == 0 || sbi->s_inodes_per_group == 0)
goto cantfind_ext2;
sbi->s_itb_per_group = sbi->s_inodes_per_group /
sbi->s_inodes_per_block;
sbi->s_desc_per_block = sb->s_blocksize /
sizeof (struct ext2_group_desc);
sbi->s_sbh = bh;
sbi->s_mount_state = le16_to_cpu(es->s_state);
sbi->s_addr_per_block_bits =
ilog2 (EXT2_ADDR_PER_BLOCK(sb));
sbi->s_desc_per_block_bits =
ilog2 (EXT2_DESC_PER_BLOCK(sb));

if (sb->s_magic != EXT2_SUPER_MAGIC)
goto cantfind_ext2;

if (sb->s_blocksize != bh->b_size) {
if (!silent)
printk (»VFS: Unsupported blocksize on dev »
«%s.\n», sb->s_id);
goto failed_mount;
}

if (sb->s_blocksize != sbi->s_frag_size) {
printk (»EXT2-fs: fragsize %lu != blocksize %lu (not supported yet)\n»,
sbi->s_frag_size, sb->s_blocksize);
goto failed_mount;
}

if (sbi->s_blocks_per_group > sb->s_blocksize * {
printk (»EXT2-fs: #blocks per group too big: %lu\n»,
sbi->s_blocks_per_group);
goto failed_mount;
}
if (sbi->s_frags_per_group > sb->s_blocksize * {
printk (»EXT2-fs: #fragments per group too big: %lu\n»,
sbi->s_frags_per_group);
goto failed_mount;
}
if (sbi->s_inodes_per_group > sb->s_blocksize * {
printk (»EXT2-fs: #inodes per group too big: %lu\n»,
sbi->s_inodes_per_group);
goto failed_mount;
}

if (EXT2_BLOCKS_PER_GROUP(sb) == 0)
goto cantfind_ext2;
sbi->s_groups_count = ((le32_to_cpu(es->s_blocks_count) -
le32_to_cpu(es->s_first_data_block) – 1)
/ EXT2_BLOCKS_PER_GROUP(sb)) + 1;
db_count = (sbi->s_groups_count + EXT2_DESC_PER_BLOCK(sb) – 1) /
EXT2_DESC_PER_BLOCK(sb);
sbi->s_group_desc = kmalloc (db_count * sizeof (struct buffer_head *), GFP_KERNEL);
if (sbi->s_group_desc == NULL) {
printk (»EXT2-fs: not enough memory\n»);
goto failed_mount;
}
bgl_lock_init(sbi->s_blockgroup_lock);
sbi->s_debts = kcalloc(sbi->s_groups_count, sizeof(*sbi->s_debts), GFP_KERNEL);
if (!sbi->s_debts) {
printk (»EXT2-fs: not enough memory\n»);
goto failed_mount_group_desc;
}
for (i = 0; i < db_count; i++) {
block = descriptor_loc(sb, logic_sb_block, i);
sbi->s_group_desc[i] = sb_bread(sb, block);
if (!sbi->s_group_desc[i]) {
for (j = 0; j < i; j++)
brelse (sbi->s_group_desc[j]);
printk (»EXT2-fs: unable to read group descriptors\n»);
goto failed_mount_group_desc;
}
}
if (!ext2_check_descriptors (sb)) {
printk (»EXT2-fs: group descriptors corrupted!\n»);
goto failed_mount2;
}
sbi->s_gdb_count = db_count;
get_random_bytes(&sbi->s_next_generation, sizeof(u32));
spin_lock_init(&sbi->s_next_gen_lock);

/* per fileystem reservation list head & lock */
spin_lock_init(&sbi->s_rsv_window_lock);
sbi->s_rsv_window_root = RB_ROOT;
/*
* Add a single, static dummy reservation to the start of the
* reservation window list — it gives us a placeholder for
* append-at-start-of-list which makes the allocation logic
* _much_ simpler.
*/
sbi->s_rsv_window_head.rsv_start = EXT2_RESERVE_WINDOW_NOT_ALLOCATED;
sbi->s_rsv_window_head.rsv_end = EXT2_RESERVE_WINDOW_NOT_ALLOCATED;
sbi->s_rsv_window_head.rsv_alloc_hit = 0;
sbi->s_rsv_window_head.rsv_goal_size = 0;
ext2_rsv_window_add(sb, &sbi->s_rsv_window_head);

err = percpu_counter_init(&sbi->s_freeblocks_counter,
ext2_count_free_blocks(sb));
if (!err) {
err = percpu_counter_init(&sbi->s_freeinodes_counter,
ext2_count_free_inodes(sb));
}
if (!err) {
err = percpu_counter_init(&sbi->s_dirs_counter,
ext2_count_dirs(sb));
}
if (err) {
printk(KERN_ERR «EXT2-fs: insufficient memory\n»);
goto failed_mount3;
}
/*
* set up enough so that it can read an inode
*/
sb->s_op = &ext2_sops;
sb->s_export_op = &ext2_export_ops;
sb->s_xattr = ext2_xattr_handlers;
root = ext2_iget(sb, EXT2_ROOT_INO);
if (IS_ERR(root)) {
ret = PTR_ERR(root);
goto failed_mount3;
}
if (!S_ISDIR(root->i_mode) || !root->i_blocks || !root->i_size) {
iput(root);
printk(KERN_ERR «EXT2-fs: corrupt root inode, run e2fsck\n»);
goto failed_mount3;
}

sb->s_root = d_alloc_root(root);
if (!sb->s_root) {
iput(root);
printk(KERN_ERR «EXT2-fs: get root inode failed\n»);
ret = -ENOMEM;
goto failed_mount3;
}
if (EXT2_HAS_COMPAT_FEATURE(sb, EXT3_FEATURE_COMPAT_HAS_JOURNAL))
ext2_warning(sb, __func__,
«mounting ext3 filesystem as ext2″);
ext2_setup_super (sb, es, sb->s_flags & MS_RDONLY);
return 0;

cantfind_ext2:
if (!silent)
printk(»VFS: Can’t find an ext2 filesystem on dev %s.\n»,
sb->s_id);
goto failed_mount;
failed_mount3:
percpu_counter_destroy(&sbi->s_freeblocks_counter);
percpu_counter_destroy(&sbi->s_freeinodes_counter);
percpu_counter_destroy(&sbi->s_dirs_counter);
failed_mount2:
for (i = 0; i < db_count; i++)
brelse(sbi->s_group_desc[i]);
failed_mount_group_desc:
kfree(sbi->s_group_desc);
kfree(sbi->s_debts);
failed_mount:
brelse(bh);
failed_sbi:
sb->s_fs_info = NULL;
kfree(sbi->s_blockgroup_lock);
kfree(sbi);
return ret;
}

static void ext2_commit_super (struct super_block * sb,
struct ext2_super_block * es)
{
es->s_wtime = cpu_to_le32(get_seconds());
mark_buffer_dirty(EXT2_SB(sb)->s_sbh);
sb->s_dirt = 0;
}

static void ext2_sync_super(struct super_block *sb, struct ext2_super_block *es)
{
es->s_free_blocks_count = cpu_to_le32(ext2_count_free_blocks(sb));
es->s_free_inodes_count = cpu_to_le32(ext2_count_free_inodes(sb));
es->s_wtime = cpu_to_le32(get_seconds());
mark_buffer_dirty(EXT2_SB(sb)->s_sbh);
sync_dirty_buffer(EXT2_SB(sb)->s_sbh);
sb->s_dirt = 0;
}

/*
* In the second extended file system, it is not necessary to
* write the super block since we use a mapping of the
* disk super block in a buffer.
*
* However, this function is still used to set the fs valid
* flags to 0. We need to set this flag to 0 since the fs
* may have been checked while mounted and e2fsck may have
* set s_state to EXT2_VALID_FS after some corrections.
*/

static int ext2_sync_fs(struct super_block *sb, int wait)
{
struct ext2_super_block *es = EXT2_SB(sb)->s_es;

lock_kernel();
if (es->s_state & cpu_to_le16(EXT2_VALID_FS)) {
ext2_debug(»setting valid to 0\n»);
es->s_state &= cpu_to_le16(~EXT2_VALID_FS);
es->s_free_blocks_count =
cpu_to_le32(ext2_count_free_blocks(sb));
es->s_free_inodes_count =
cpu_to_le32(ext2_count_free_inodes(sb));
es->s_mtime = cpu_to_le32(get_seconds());
ext2_sync_super(sb, es);
} else {
ext2_commit_super(sb, es);
}
sb->s_dirt = 0;
unlock_kernel();

return 0;
}

void ext2_write_super(struct super_block *sb)
{
if (!(sb->s_flags & MS_RDONLY))
ext2_sync_fs(sb, 1);
else
sb->s_dirt = 0;
}

static int ext2_remount (struct super_block * sb, int * flags, char * data)
{
struct ext2_sb_info * sbi = EXT2_SB(sb);
struct ext2_super_block * es;
unsigned long old_mount_opt = sbi->s_mount_opt;
struct ext2_mount_options old_opts;
unsigned long old_sb_flags;
int err;

lock_kernel();

/* Store the old options */
old_sb_flags = sb->s_flags;
old_opts.s_mount_opt = sbi->s_mount_opt;
old_opts.s_resuid = sbi->s_resuid;
old_opts.s_resgid = sbi->s_resgid;

/*
* Allow the «check» option to be passed as a remount option.
*/
if (!parse_options (data, sbi)) {
err = -EINVAL;
goto restore_opts;
}

sb->s_flags = (sb->s_flags & ~MS_POSIXACL) |
((sbi->s_mount_opt & EXT2_MOUNT_POSIX_ACL) ? MS_POSIXACL : 0);

ext2_xip_verify_sb(sb); /* see if bdev supports xip, unset
EXT2_MOUNT_XIP if not */

if ((ext2_use_xip(sb)) && (sb->s_blocksize != PAGE_SIZE)) {
printk(»XIP: Unsupported blocksize\n»);
err = -EINVAL;
goto restore_opts;
}

es = sbi->s_es;
if (((sbi->s_mount_opt & EXT2_MOUNT_XIP) !=
(old_mount_opt & EXT2_MOUNT_XIP)) &&
invalidate_inodes(sb)) {
ext2_warning(sb, __func__, «refusing change of xip flag »
«with busy inodes while remounting»);
sbi->s_mount_opt &= ~EXT2_MOUNT_XIP;
sbi->s_mount_opt |= old_mount_opt & EXT2_MOUNT_XIP;
}
if ((*flags & MS_RDONLY) == (sb->s_flags & MS_RDONLY)) {
unlock_kernel();
return 0;
}
if (*flags & MS_RDONLY) {
if (le16_to_cpu(es->s_state) & EXT2_VALID_FS ||
!(sbi->s_mount_state & EXT2_VALID_FS)) {
unlock_kernel();
return 0;
}
/*
* OK, we are remounting a valid rw partition rdonly, so set
* the rdonly flag and then mark the partition as valid again.
*/
es->s_state = cpu_to_le16(sbi->s_mount_state);
es->s_mtime = cpu_to_le32(get_seconds());
} else {
__le32 ret = EXT2_HAS_RO_COMPAT_FEATURE(sb,
~EXT2_FEATURE_RO_COMPAT_SUPP);
if (ret) {
printk(»EXT2-fs: %s: couldn’t remount RDWR because of »
«unsupported optional features (%x).\n»,
sb->s_id, le32_to_cpu(ret));
err = -EROFS;
goto restore_opts;
}
/*
* Mounting a RDONLY partition read-write, so reread and
* store the current valid flag. (It may have been changed
* by e2fsck since we originally mounted the partition.)
*/
sbi->s_mount_state = le16_to_cpu(es->s_state);
if (!ext2_setup_super (sb, es, 0))
sb->s_flags &= ~MS_RDONLY;
}
ext2_sync_super(sb, es);
unlock_kernel();
return 0;
restore_opts:
sbi->s_mount_opt = old_opts.s_mount_opt;
sbi->s_resuid = old_opts.s_resuid;
sbi->s_resgid = old_opts.s_resgid;
sb->s_flags = old_sb_flags;
unlock_kernel();
return err;
}

static int ext2_statfs (struct dentry * dentry, struct kstatfs * buf)
{
struct super_block *sb = dentry->d_sb;
struct ext2_sb_info *sbi = EXT2_SB(sb);
struct ext2_super_block *es = sbi->s_es;
u64 fsid;

if (test_opt (sb, MINIX_DF))
sbi->s_overhead_last = 0;
else if (sbi->s_blocks_last != le32_to_cpu(es->s_blocks_count)) {
unsigned long i, overhead = 0;
smp_rmb();

/*
* Compute the overhead (FS structures). This is constant
* for a given filesystem unless the number of block groups
* changes so we cache the previous value until it does.
*/

/*
* All of the blocks before first_data_block are
* overhead
*/
overhead = le32_to_cpu(es->s_first_data_block);

/*
* Add the overhead attributed to the superblock and
* block group descriptors. If the sparse superblocks
* feature is turned on, then not all groups have this.
*/
for (i = 0; i < sbi->s_groups_count; i++)
overhead += ext2_bg_has_super(sb, i) +
ext2_bg_num_gdb(sb, i);

/*
* Every block group has an inode bitmap, a block
* bitmap, and an inode table.
*/
overhead += (sbi->s_groups_count *
(2 + sbi->s_itb_per_group));
sbi->s_overhead_last = overhead;
smp_wmb();
sbi->s_blocks_last = le32_to_cpu(es->s_blocks_count);
}

buf->f_type = EXT2_SUPER_MAGIC;
buf->f_bsize = sb->s_blocksize;
buf->f_blocks = le32_to_cpu(es->s_blocks_count) – sbi->s_overhead_last;
buf->f_bfree = ext2_count_free_blocks(sb);
es->s_free_blocks_count = cpu_to_le32(buf->f_bfree);
buf->f_bavail = buf->f_bfree – le32_to_cpu(es->s_r_blocks_count);
if (buf->f_bfree < le32_to_cpu(es->s_r_blocks_count))
buf->f_bavail = 0;
buf->f_files = le32_to_cpu(es->s_inodes_count);
buf->f_ffree = ext2_count_free_inodes(sb);
es->s_free_inodes_count = cpu_to_le32(buf->f_ffree);
buf->f_namelen = EXT2_NAME_LEN;
fsid = le64_to_cpup((void *)es->s_uuid) ^
le64_to_cpup((void *)es->s_uuid + sizeof(u64));
buf->f_fsid.val[0] = fsid & 0xFFFFFFFFUL;
buf->f_fsid.val[1] = (fsid >> 32) & 0xFFFFFFFFUL;
return 0;
}

static int ext2_get_sb(struct file_system_type *fs_type,
int flags, const char *dev_name, void *data, struct vfsmount *mnt)
{
return get_sb_bdev(fs_type, flags, dev_name, data, ext2_fill_super, mnt);
}

#ifdef CONFIG_QUOTA

/* Read data from quotafile – avoid pagecache and such because we cannot afford
* acquiring the locks… As quota files are never truncated and quota code
* itself serializes the operations (and noone else should touch the files)
* we don’t have to be afraid of races */
static ssize_t ext2_quota_read(struct super_block *sb, int type, char *data,
size_t len, loff_t off)
{
struct inode *inode = sb_dqopt(sb)->files[type];
sector_t blk = off >> EXT2_BLOCK_SIZE_BITS(sb);
int err = 0;
int offset = off & (sb->s_blocksize – 1);
int tocopy;
size_t toread;
struct buffer_head tmp_bh;
struct buffer_head *bh;
loff_t i_size = i_size_read(inode);

if (off > i_size)
return 0;
if (off+len > i_size)
len = i_size-off;
toread = len;
while (toread > 0) {
tocopy = sb->s_blocksize – offset < toread ?
sb->s_blocksize – offset : toread;

tmp_bh.b_state = 0;
tmp_bh.b_size = sb->s_blocksize;
err = ext2_get_block(inode, blk, &tmp_bh, 0);
if (err < 0)
return err;
if (!buffer_mapped(&tmp_bh)) /* A hole? */
memset(data, 0, tocopy);
else {
bh = sb_bread(sb, tmp_bh.b_blocknr);
if (!bh)
return -EIO;
memcpy(data, bh->b_data+offset, tocopy);
brelse(bh);
}
offset = 0;
toread -= tocopy;
data += tocopy;
blk++;
}
return len;
}

/* Write to quotafile */
static ssize_t ext2_quota_write(struct super_block *sb, int type,
const char *data, size_t len, loff_t off)
{
struct inode *inode = sb_dqopt(sb)->files[type];
sector_t blk = off >> EXT2_BLOCK_SIZE_BITS(sb);
int err = 0;
int offset = off & (sb->s_blocksize – 1);
int tocopy;
size_t towrite = len;
struct buffer_head tmp_bh;
struct buffer_head *bh;

mutex_lock_nested(&inode->i_mutex, I_MUTEX_QUOTA);
while (towrite > 0) {
tocopy = sb->s_blocksize – offset < towrite ?
sb->s_blocksize – offset : towrite;

tmp_bh.b_state = 0;
err = ext2_get_block(inode, blk, &tmp_bh, 1);
if (err < 0)
goto out;
if (offset || tocopy != EXT2_BLOCK_SIZE(sb))
bh = sb_bread(sb, tmp_bh.b_blocknr);
else
bh = sb_getblk(sb, tmp_bh.b_blocknr);
if (!bh) {
err = -EIO;
goto out;
}
lock_buffer(bh);
memcpy(bh->b_data+offset, data, tocopy);
flush_dcache_page(bh->b_page);
set_buffer_uptodate(bh);
mark_buffer_dirty(bh);
unlock_buffer(bh);
brelse(bh);
offset = 0;
towrite -= tocopy;
data += tocopy;
blk++;
}
out:
if (len == towrite) {
mutex_unlock(&inode->i_mutex);
return err;
}
if (inode->i_size < off+len-towrite)
i_size_write(inode, off+len-towrite);
inode->i_version++;
inode->i_mtime = inode->i_ctime = CURRENT_TIME;
mark_inode_dirty(inode);
mutex_unlock(&inode->i_mutex);
return len – towrite;
}

#endif

static struct file_system_type ext2_fs_type = {
.owner = THIS_MODULE,
.name = «ext2″,
.get_sb = ext2_get_sb,
.kill_sb = kill_block_super,
.fs_flags = FS_REQUIRES_DEV,
};

static int __init init_ext2_fs(void)
{
int err = init_ext2_xattr();
if (err)
return err;
err = init_inodecache();
if (err)
goto out1;
err = register_filesystem(&ext2_fs_type);
if (err)
goto out;
return 0;
out:
destroy_inodecache();
out1:
exit_ext2_xattr();
return err;
}

static void __exit exit_ext2_fs(void)
{
unregister_filesystem(&ext2_fs_type);
destroy_inodecache();
exit_ext2_xattr();
}

module_init(init_ext2_fs)
module_exit(exit_ext2_fs)

#include #include «ext2.h»
#include «xattr.h»
#include «acl.h»
#include «xip.h»

static inline int ext2_add_nondir(struct dentry *dentry, struct inode *inode)
{
int err = ext2_add_link(dentry, inode);
if (!err) {
d_instantiate(dentry, inode);
unlock_new_inode(inode);
return 0;
}
inode_dec_link_count(inode);
unlock_new_inode(inode);
iput(inode);
return err;
}

/*
* Methods themselves.
*/

static struct dentry *ext2_lookup(struct inode * dir, struct dentry *dentry, struct nameidata *nd)
{
struct inode * inode;
ino_t ino;

if (dentry->d_name.len > EXT2_NAME_LEN)
return ERR_PTR(-ENAMETOOLONG);

ino = ext2_inode_by_name(dir, &dentry->d_name);
inode = NULL;
if (ino) {
inode = ext2_iget(dir->i_sb, ino);
if (unlikely(IS_ERR(inode))) {
if (PTR_ERR(inode) == -ESTALE) {
ext2_error(dir->i_sb, __func__,
«deleted inode referenced: %lu»,
(unsigned long) ino);
return ERR_PTR(-EIO);
} else {
return ERR_CAST(inode);
}
}
}
return d_splice_alias(inode, dentry);
}

struct dentry *ext2_get_parent(struct dentry *child)
{
struct qstr dotdot = {.name = «..», .len = 2};
unsigned long ino = ext2_inode_by_name(child->d_inode, &dotdot);
if (!ino)
return ERR_PTR(-ENOENT);
return d_obtain_alias(ext2_iget(child->d_inode->i_sb, ino));
}

/*
* By the time this is called, we already have created
* the directory cache entry for the new file, but it
* is so far negative – it has no inode.
*
* If the create succeeds, we fill in the inode information
* with d_instantiate().
*/
static int ext2_create (struct inode * dir, struct dentry * dentry, int mode, struct nameidata *nd)
{
struct inode * inode = ext2_new_inode (dir, mode);
int err = PTR_ERR(inode);
if (!IS_ERR(inode)) {
inode->i_op = &ext2_file_inode_operations;
if (ext2_use_xip(inode->i_sb)) {
inode->i_mapping->a_ops = &ext2_aops_xip;
inode->i_fop = &ext2_xip_file_operations;
} else if (test_opt(inode->i_sb, NOBH)) {
inode->i_mapping->a_ops = &ext2_nobh_aops;
inode->i_fop = &ext2_file_operations;
} else {
inode->i_mapping->a_ops = &ext2_aops;
inode->i_fop = &ext2_file_operations;
}
mark_inode_dirty(inode);
err = ext2_add_nondir(dentry, inode);
}
return err;
}

static int ext2_mknod (struct inode * dir, struct dentry *dentry, int mode, dev_t rdev)
{
struct inode * inode;
int err;

if (!new_valid_dev(rdev))
return -EINVAL;

inode = ext2_new_inode (dir, mode);
err = PTR_ERR(inode);
if (!IS_ERR(inode)) {
init_special_inode(inode, inode->i_mode, rdev);
#ifdef CONFIG_EXT2_FS_XATTR
inode->i_op = &ext2_special_inode_operations;
#endif
mark_inode_dirty(inode);
err = ext2_add_nondir(dentry, inode);
}
return err;
}

static int ext2_symlink (struct inode * dir, struct dentry * dentry,
const char * symname)
{
struct super_block * sb = dir->i_sb;
int err = -ENAMETOOLONG;
unsigned l = strlen(symname)+1;
struct inode * inode;

if (l > sb->s_blocksize)
goto out;

inode = ext2_new_inode (dir, S_IFLNK | S_IRWXUGO);
err = PTR_ERR(inode);
if (IS_ERR(inode))
goto out;

if (l > sizeof (EXT2_I(inode)->i_data)) {
/* slow symlink */
inode->i_op = &ext2_symlink_inode_operations;
if (test_opt(inode->i_sb, NOBH))
inode->i_mapping->a_ops = &ext2_nobh_aops;
else
inode->i_mapping->a_ops = &ext2_aops;
err = page_symlink(inode, symname, l);
if (err)
goto out_fail;
} else {
/* fast symlink */
inode->i_op = &ext2_fast_symlink_inode_operations;
memcpy((char*)(EXT2_I(inode)->i_data),symname,l);
inode->i_size = l-1;
}
mark_inode_dirty(inode);

err = ext2_add_nondir(dentry, inode);
out:
return err;

out_fail:
inode_dec_link_count(inode);
unlock_new_inode(inode);
iput (inode);
goto out;
}

static int ext2_link (struct dentry * old_dentry, struct inode * dir,
struct dentry *dentry)
{
struct inode *inode = old_dentry->d_inode;
int err;

if (inode->i_nlink >= EXT2_LINK_MAX)
return -EMLINK;

inode->i_ctime = CURRENT_TIME_SEC;
inode_inc_link_count(inode);
atomic_inc(&inode->i_count);

err = ext2_add_link(dentry, inode);
if (!err) {
d_instantiate(dentry, inode);
return 0;
}
inode_dec_link_count(inode);
iput(inode);
return err;
}

static int ext2_mkdir(struct inode * dir, struct dentry * dentry, int mode)
{
struct inode * inode;
int err = -EMLINK;

if (dir->i_nlink >= EXT2_LINK_MAX)
goto out;

inode_inc_link_count(dir);

inode = ext2_new_inode (dir, S_IFDIR | mode);
err = PTR_ERR(inode);
if (IS_ERR(inode))
goto out_dir;

inode->i_op = &ext2_dir_inode_operations;
inode->i_fop = &ext2_dir_operations;
if (test_opt(inode->i_sb, NOBH))
inode->i_mapping->a_ops = &ext2_nobh_aops;
else
inode->i_mapping->a_ops = &ext2_aops;

inode_inc_link_count(inode);

err = ext2_make_empty(inode, dir);
if (err)
goto out_fail;

err = ext2_add_link(dentry, inode);
if (err)
goto out_fail;

d_instantiate(dentry, inode);
unlock_new_inode(inode);
out:
return err;

out_fail:
inode_dec_link_count(inode);
inode_dec_link_count(inode);
unlock_new_inode(inode);
iput(inode);
out_dir:
inode_dec_link_count(dir);
goto out;
}

static int ext2_unlink(struct inode * dir, struct dentry *dentry)
{
struct inode * inode = dentry->d_inode;
struct ext2_dir_entry_2 * de;
struct page * page;
int err = -ENOENT;

de = ext2_find_entry (dir, &dentry->d_name, &page);
if (!de)
goto out;

err = ext2_delete_entry (de, page);
if (err)
goto out;

inode->i_ctime = dir->i_ctime;
inode_dec_link_count(inode);
err = 0;
out:
return err;
}

static int ext2_rmdir (struct inode * dir, struct dentry *dentry)
{
struct inode * inode = dentry->d_inode;
int err = -ENOTEMPTY;

if (ext2_empty_dir(inode)) {
err = ext2_unlink(dir, dentry);
if (!err) {
inode->i_size = 0;
inode_dec_link_count(inode);
inode_dec_link_count(dir);
}
}
return err;
}

static int ext2_rename (struct inode * old_dir, struct dentry * old_dentry,
struct inode * new_dir, struct dentry * new_dentry )
{
struct inode * old_inode = old_dentry->d_inode;
struct inode * new_inode = new_dentry->d_inode;
struct page * dir_page = NULL;
struct ext2_dir_entry_2 * dir_de = NULL;
struct page * old_page;
struct ext2_dir_entry_2 * old_de;
int err = -ENOENT;

old_de = ext2_find_entry (old_dir, &old_dentry->d_name, &old_page);
if (!old_de)
goto out;

if (S_ISDIR(old_inode->i_mode)) {
err = -EIO;
dir_de = ext2_dotdot(old_inode, &dir_page);
if (!dir_de)
goto out_old;
}

if (new_inode) {
struct page *new_page;
struct ext2_dir_entry_2 *new_de;

err = -ENOTEMPTY;
if (dir_de && !ext2_empty_dir (new_inode))
goto out_dir;

err = -ENOENT;
new_de = ext2_find_entry (new_dir, &new_dentry->d_name, &new_page);
if (!new_de)
goto out_dir;
inode_inc_link_count(old_inode);
ext2_set_link(new_dir, new_de, new_page, old_inode, 1);
new_inode->i_ctime = CURRENT_TIME_SEC;
if (dir_de)
drop_nlink(new_inode);
inode_dec_link_count(new_inode);
} else {
if (dir_de) {
err = -EMLINK;
if (new_dir->i_nlink >= EXT2_LINK_MAX)
goto out_dir;
}
inode_inc_link_count(old_inode);
err = ext2_add_link(new_dentry, old_inode);
if (err) {
inode_dec_link_count(old_inode);
goto out_dir;
}
if (dir_de)
inode_inc_link_count(new_dir);
}

/*
* Like most other Unix systems, set the ctime for inodes on a
* rename.
* inode_dec_link_count() will mark the inode dirty.
*/
old_inode->i_ctime = CURRENT_TIME_SEC;

ext2_delete_entry (old_de, old_page);
inode_dec_link_count(old_inode);

if (dir_de) {
if (old_dir != new_dir)
ext2_set_link(old_inode, dir_de, dir_page, new_dir, 0);
else {
kunmap(dir_page);
page_cache_release(dir_page);
}
inode_dec_link_count(old_dir);
}
return 0;

out_dir:
if (dir_de) {
kunmap(dir_page);
page_cache_release(dir_page);
}
out_old:
kunmap(old_page);
page_cache_release(old_page);
out:
return err;
}

const struct inode_operations ext2_dir_inode_operations = {
.create = ext2_create,
.lookup = ext2_lookup,
.link = ext2_link,
.unlink = ext2_unlink,
.symlink = ext2_symlink,
.mkdir = ext2_mkdir,
.rmdir = ext2_rmdir,
.mknod = ext2_mknod,
.rename = ext2_rename,
#ifdef CONFIG_EXT2_FS_XATTR
.setxattr = generic_setxattr,
.getxattr = generic_getxattr,
.listxattr = ext2_listxattr,
.removexattr = generic_removexattr,
#endif
.setattr = ext2_setattr,
.check_acl = ext2_check_acl,
};

const struct inode_operations ext2_special_inode_operations = {
#ifdef CONFIG_EXT2_FS_XATTR
.setxattr = generic_setxattr,
.getxattr = generic_getxattr,
.listxattr = ext2_listxattr,
.removexattr = generic_removexattr,
#endif
.setattr = ext2_setattr,
.check_acl = ext2_check_acl,
};

obj-$(CONFIG_EXT2_FS) += ext2.o

ext2-y := balloc.o dir.o file.o ialloc.o inode.o \
ioctl.o namei.o super.o symlink.o

ext2-$(CONFIG_EXT2_FS_XATTR) += xattr.o xattr_user.o xattr_trusted.o
ext2-$(CONFIG_EXT2_FS_POSIX_ACL) += acl.o
ext2-$(CONFIG_EXT2_FS_SECURITY) += xattr_security.o
ext2-$(CONFIG_EXT2_FS_XIP) += xip.o

To compile this file system support as a module, choose M here: the
module will be called ext2.

If unsure, say Y.

config EXT2_FS_XATTR
bool «Ext2 extended attributes»
depends on EXT2_FS
help
Extended attributes are name:value pairs associated with inodes by
the kernel or by users (see the attr(5) manual page, or visit
for details).

If unsure, say N.

config EXT2_FS_POSIX_ACL
bool «Ext2 POSIX Access Control Lists»
depends on EXT2_FS_XATTR
select FS_POSIX_ACL
help
Posix Access Control Lists (ACLs) support permissions for users and
groups beyond the owner/group/world scheme.

To learn more about Access Control Lists, visit the Posix ACLs for
Linux website .

If you don’t know what Access Control Lists are, say N

config EXT2_FS_SECURITY
bool «Ext2 Security Labels»
depends on EXT2_FS_XATTR
help
Security labels support alternative access control models
implemented by security modules like SELinux. This option
enables an extended attribute handler for file security
labels in the ext2 filesystem.

If you are not using a security module that requires using
extended attributes for file security labels, say N.

config EXT2_FS_XIP
bool «Ext2 execute in place support»
depends on EXT2_FS && MMU
help
Execute in place can be used on memory-backed block devices. If you
enable this option, you can select to mount block devices which are
capable of this feature without using the page cache.

If you do not use a block device that is capable of using this,
or if unsure, say N.

#include «ext2.h»
#include #include #include #include #include #include
#include

long ext2_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
{
struct inode *inode = filp->f_dentry->d_inode;
struct ext2_inode_info *ei = EXT2_I(inode);
unsigned int flags;
unsigned short rsv_window_size;
int ret;

ext2_debug (»cmd = %u, arg = %lu\n», cmd, arg);

switch (cmd) {
case EXT2_IOC_GETFLAGS:
ext2_get_inode_flags(ei);
flags = ei->i_flags & EXT2_FL_USER_VISIBLE;
return put_user(flags, (int __user *) arg);
case EXT2_IOC_SETFLAGS: {
unsigned int oldflags;

ret = mnt_want_write(filp->f_path.mnt);
if (ret)
return ret;

if (!is_owner_or_cap(inode)) {
ret = -EACCES;
goto setflags_out;
}

if (get_user(flags, (int __user *) arg)) {
ret = -EFAULT;
goto setflags_out;
}

flags = ext2_mask_flags(inode->i_mode, flags);

mutex_lock(&inode->i_mutex);
/* Is it quota file? Do not allow user to mess with it */
if (IS_NOQUOTA(inode)) {
mutex_unlock(&inode->i_mutex);
ret = -EPERM;
goto setflags_out;
}
oldflags = ei->i_flags;

/*
* The IMMUTABLE and APPEND_ONLY flags can only be changed by
* the relevant capability.
*
* This test looks nicer. Thanks to Pauline Middelink
*/
if ((flags ^ oldflags) & (EXT2_APPEND_FL | EXT2_IMMUTABLE_FL)) {
if (!capable(CAP_LINUX_IMMUTABLE)) {
mutex_unlock(&inode->i_mutex);
ret = -EPERM;
goto setflags_out;
}
}

flags = flags & EXT2_FL_USER_MODIFIABLE;
flags |= oldflags & ~EXT2_FL_USER_MODIFIABLE;
ei->i_flags = flags;
mutex_unlock(&inode->i_mutex);

ext2_set_inode_flags(inode);
inode->i_ctime = CURRENT_TIME_SEC;
mark_inode_dirty(inode);
setflags_out:
mnt_drop_write(filp->f_path.mnt);
return ret;
}
case EXT2_IOC_GETVERSION:
return put_user(inode->i_generation, (int __user *) arg);
case EXT2_IOC_SETVERSION:
if (!is_owner_or_cap(inode))
return -EPERM;
ret = mnt_want_write(filp->f_path.mnt);
if (ret)
return ret;
if (get_user(inode->i_generation, (int __user *) arg)) {
ret = -EFAULT;
} else {
inode->i_ctime = CURRENT_TIME_SEC;
mark_inode_dirty(inode);
}
mnt_drop_write(filp->f_path.mnt);
return ret;
case EXT2_IOC_GETRSVSZ:
if (test_opt(inode->i_sb, RESERVATION)
&& S_ISREG(inode->i_mode)
&& ei->i_block_alloc_info) {
rsv_window_size = ei->i_block_alloc_info->rsv_window_node.rsv_goal_size;
return put_user(rsv_window_size, (int __user *)arg);
}
return -ENOTTY;
case EXT2_IOC_SETRSVSZ: {

if (!test_opt(inode->i_sb, RESERVATION) ||!S_ISREG(inode->i_mode))
return -ENOTTY;

if (!is_owner_or_cap(inode))
return -EACCES;

if (get_user(rsv_window_size, (int __user *)arg))
return -EFAULT;

ret = mnt_want_write(filp->f_path.mnt);
if (ret)
return ret;

if (rsv_window_size > EXT2_MAX_RESERVE_BLOCKS)
rsv_window_size = EXT2_MAX_RESERVE_BLOCKS;

/*
* need to allocate reservation structure for this inode
* before set the window size
*/
/*
* XXX What lock should protect the rsv_goal_size?
* Accessed in ext2_get_block only. ext3 uses i_truncate.
*/
mutex_lock(&ei->truncate_mutex);
if (!ei->i_block_alloc_info)
ext2_init_block_alloc_info(inode);

if (ei->i_block_alloc_info){
struct ext2_reserve_window_node *rsv = &ei->i_block_alloc_info->rsv_window_node;
rsv->rsv_goal_size = rsv_window_size;
}
mutex_unlock(&ei->truncate_mutex);
mnt_drop_write(filp->f_path.mnt);
return 0;
}
default:
return -ENOTTY;
}
}

#ifdef CONFIG_COMPAT
long ext2_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
{
/* These are just misnamed, they actually get/put from/to user an int */
switch (cmd) {
case EXT2_IOC32_GETFLAGS:
cmd = EXT2_IOC_GETFLAGS;
break;
case EXT2_IOC32_SETFLAGS:
cmd = EXT2_IOC_SETFLAGS;
break;
case EXT2_IOC32_GETVERSION:
cmd = EXT2_IOC_GETVERSION;
break;
case EXT2_IOC32_SETVERSION:
cmd = EXT2_IOC_SETVERSION;
break;
default:
return -ENOIOCTLCMD;
}
return ext2_ioctl(file, cmd, (unsigned long) compat_ptr(arg));
}
#endif

#include #include #include #include #include #include #include #include #include #include #include #include «ext2.h»
#include «acl.h»
#include «xip.h»

MODULE_AUTHOR(»Remy Card and others»);
MODULE_DESCRIPTION(»Second Extended Filesystem»);
MODULE_LICENSE(»GPL»);

/*
* Test whether an inode is a fast symlink.
*/
static inline int ext2_inode_is_fast_symlink(struct inode *inode)
{
int ea_blocks = EXT2_I(inode)->i_file_acl ?
(inode->i_sb->s_blocksize >> 9) : 0;

return (S_ISLNK(inode->i_mode) &&
inode->i_blocks – ea_blocks == 0);
}

/*
* Called at the last iput() if i_nlink is zero.
*/
void ext2_delete_inode (struct inode * inode)
{
truncate_inode_pages(&inode->i_data, 0);

if (is_bad_inode(inode))
goto no_delete;
EXT2_I(inode)->i_dtime = get_seconds();
mark_inode_dirty(inode);
ext2_write_inode(inode, inode_needs_sync(inode));

inode->i_size = 0;
if (inode->i_blocks)
ext2_truncate (inode);
ext2_free_inode (inode);

return;
no_delete:
clear_inode(inode); /* We must guarantee clearing of inode… */
}

typedef struct {
__le32 *p;
__le32 key;
struct buffer_head *bh;
} Indirect;

static inline void add_chain(Indirect *p, struct buffer_head *bh, __le32 *v)
{
p->key = *(p->p = v);
p->bh = bh;
}

static inline int verify_chain(Indirect *from, Indirect *to)
{
while (from <= to && from->key == *from->p)
from++;
return (from > to);
}

/**
* ext2_block_to_path – parse the block number into array of offsets
* @inode: inode in question (we are only interested in its superblock)
* @i_block: block number to be parsed
* @offsets: array to store the offsets in
* @boundary: set this non-zero if the referred-to block is likely to be
* followed (on disk) by an indirect block.
* To store the locations of file’s data ext2 uses a data structure common
* for UNIX filesystems – tree of pointers anchored in the inode, with
* data blocks at leaves and indirect blocks in intermediate nodes.
* This function translates the block number into path in that tree -
* return value is the path length and @offsets[n] is the offset of
* pointer to (n+1)th node in the nth one. If @block is out of range
* (negative or too large) warning is printed and zero returned.
*
* Note: function doesn’t find node addresses, so no IO is needed. All
* we need to know is the capacity of indirect blocks (taken from the
* inode->i_sb).
*/

/*
* Portability note: the last comparison (check that we fit into triple
* indirect block) is spelled differently, because otherwise on an
* architecture with 32-bit longs and 8Kb pages we might get into trouble
* if our filesystem had 8Kb blocks. We might use long long, but that would
* kill us on x86. Oh, well, at least the sign propagation does not matter -
* i_block would have to be negative in the very beginning, so we would not
* get there at all.
*/

static int ext2_block_to_path(struct inode *inode,
long i_block, int offsets[4], int *boundary)
{
int ptrs = EXT2_ADDR_PER_BLOCK(inode->i_sb);
int ptrs_bits = EXT2_ADDR_PER_BLOCK_BITS(inode->i_sb);
const long direct_blocks = EXT2_NDIR_BLOCKS,
indirect_blocks = ptrs,
double_blocks = (1 << (ptrs_bits * 2));
int n = 0;
int final = 0;

if (i_block < 0) {
ext2_warning (inode->i_sb, «ext2_block_to_path», «block < 0");
} else if (i_block < direct_blocks) {
offsets[n++] = i_block;
final = direct_blocks;
} else if ( (i_block -= direct_blocks) < indirect_blocks) {
offsets[n++] = EXT2_IND_BLOCK;
offsets[n++] = i_block;
final = ptrs;
} else if ((i_block -= indirect_blocks) < double_blocks) {
offsets[n++] = EXT2_DIND_BLOCK;
offsets[n++] = i_block >> ptrs_bits;
offsets[n++] = i_block & (ptrs – 1);
final = ptrs;
} else if (((i_block -= double_blocks) >> (ptrs_bits * 2)) < ptrs) {
offsets[n++] = EXT2_TIND_BLOCK;
offsets[n++] = i_block >> (ptrs_bits * 2);
offsets[n++] = (i_block >> ptrs_bits) & (ptrs – 1);
offsets[n++] = i_block & (ptrs – 1);
final = ptrs;
} else {
ext2_warning (inode->i_sb, «ext2_block_to_path», «block > big»);
}
if (boundary)
*boundary = final – 1 – (i_block & (ptrs – 1));

return n;
}

/**
* ext2_get_branch – read the chain of indirect blocks leading to data
* @inode: inode in question
* @depth: depth of the chain (1 – direct pointer, etc.)
* @offsets: offsets of pointers in inode/indirect blocks
* @chain: place to store the result
* @err: here we store the error value
*
* Function fills the array of triples and returns %NULL
* if everything went OK or the pointer to the last filled triple
* (incomplete one) otherwise. Upon the return chain[i].key contains
* the number of (i+1)-th block in the chain (as it is stored in memory,
* i.e. little-endian 32-bit), chain[i].p contains the address of that
* number (it points into struct inode for i==0 and into the bh->b_data
* for i>0) and chain[i].bh points to the buffer_head of i-th indirect
* block for i>0 and NULL for i==0. In other words, it holds the block
* numbers of the chain, addresses they were taken from (and where we can
* verify that chain did not change) and buffer_heads hosting these
* numbers.
*
* Function stops when it stumbles upon zero pointer (absent block)
* (pointer to last triple returned, *@err == 0)
* or when it gets an IO error reading an indirect block
* (ditto, *@err == -EIO)
* or when it notices that chain had been changed while it was reading
* (ditto, *@err == -EAGAIN)
* or when it reads all @depth-1 indirect blocks successfully and finds
* the whole chain, all way to the data (returns %NULL, *err == 0).
*/
static Indirect *ext2_get_branch(struct inode *inode,
int depth,
int *offsets,
Indirect chain[4],
int *err)
{
struct super_block *sb = inode->i_sb;
Indirect *p = chain;
struct buffer_head *bh;

*err = 0;
/* i_data is not going away, no lock needed */
add_chain (chain, NULL, EXT2_I(inode)->i_data + *offsets);
if (!p->key)
goto no_block;
while (–depth) {
bh = sb_bread(sb, le32_to_cpu(p->key));
if (!bh)
goto failure;
read_lock(&EXT2_I(inode)->i_meta_lock);
if (!verify_chain(chain, p))
goto changed;
add_chain(++p, bh, (__le32*)bh->b_data + *++offsets);
read_unlock(&EXT2_I(inode)->i_meta_lock);
if (!p->key)
goto no_block;
}
return NULL;

changed:
read_unlock(&EXT2_I(inode)->i_meta_lock);
brelse(bh);
*err = -EAGAIN;
goto no_block;
failure:
*err = -EIO;
no_block:
return p;
}

/**
* ext2_find_near – find a place for allocation with sufficient locality
* @inode: owner
* @ind: descriptor of indirect block.
*
* This function returns the preferred place for block allocation.
* It is used when heuristic for sequential allocation fails.
* Rules are:
* + if there is a block to the left of our position – allocate near it.
* + if pointer will live in indirect block – allocate near that block.
* + if pointer will live in inode – allocate in the same cylinder group.
*
* In the latter case we colour the starting block by the callers PID to
* prevent it from clashing with concurrent allocations for a different inode
* in the same block group. The PID is used here so that functionally related
* files will be close-by on-disk.
*
* Caller must make sure that @ind is valid and will stay that way.
*/

static ext2_fsblk_t ext2_find_near(struct inode *inode, Indirect *ind)
{
struct ext2_inode_info *ei = EXT2_I(inode);
__le32 *start = ind->bh ? (__le32 *) ind->bh->b_data : ei->i_data;
__le32 *p;
ext2_fsblk_t bg_start;
ext2_fsblk_t colour;

/* Try to find previous block */
for (p = ind->p – 1; p >= start; p–)
if (*p)
return le32_to_cpu(*p);

/* No such thing, so let’s try location of indirect block */
if (ind->bh)
return ind->bh->b_blocknr;

/*
* It is going to be refered from inode itself? OK, just put it into
* the same cylinder group then.
*/
bg_start = ext2_group_first_block_no(inode->i_sb, ei->i_block_group);
colour = (current->pid % 16) *
(EXT2_BLOCKS_PER_GROUP(inode->i_sb) / 16);
return bg_start + colour;
}

/**
* ext2_find_goal – find a preferred place for allocation.
* @inode: owner
* @block: block we want
* @partial: pointer to the last triple within a chain
*
* Returns preferred place for a block (the goal).
*/

static inline ext2_fsblk_t ext2_find_goal(struct inode *inode, long block,
Indirect *partial)
{
struct ext2_block_alloc_info *block_i;

block_i = EXT2_I(inode)->i_block_alloc_info;

/*
* try the heuristic for sequential allocation,
* failing that at least try to get decent locality.
*/
if (block_i && (block == block_i->last_alloc_logical_block + 1)
&& (block_i->last_alloc_physical_block != 0)) {
return block_i->last_alloc_physical_block + 1;
}

return ext2_find_near(inode, partial);
}

/**
* ext2_blks_to_allocate: Look up the block map and count the number
* of direct blocks need to be allocated for the given branch.
*
* @branch: chain of indirect blocks
* @k: number of blocks need for indirect blocks
* @blks: number of data blocks to be mapped.
* @blocks_to_boundary: the offset in the indirect block
*
* return the total number of blocks to be allocate, including the
* direct and indirect blocks.
*/
static int
ext2_blks_to_allocate(Indirect * branch, int k, unsigned long blks,
int blocks_to_boundary)
{
unsigned long count = 0;

/*
* Simple case, [t,d]Indirect block(s) has not allocated yet
* then it’s clear blocks on that path have not allocated
*/
if (k > 0) {
/* right now don’t hanel cross boundary allocation */
if (blks < blocks_to_boundary + 1)
count += blks;
else
count += blocks_to_boundary + 1;
return count;
}

count++;
while (count < blks && count <= blocks_to_boundary
&& le32_to_cpu(*(branch[0].p + count)) == 0) {
count++;
}
return count;
}

/**
* ext2_alloc_blocks: multiple allocate blocks needed for a branch
* @indirect_blks: the number of blocks need to allocate for indirect
* blocks
*
* @new_blocks: on return it will store the new block numbers for
* the indirect blocks(if needed) and the first direct block,
* @blks: on return it will store the total number of allocated
* direct blocks
*/
static int ext2_alloc_blocks(struct inode *inode,
ext2_fsblk_t goal, int indirect_blks, int blks,
ext2_fsblk_t new_blocks[4], int *err)
{
int target, i;
unsigned long count = 0;
int index = 0;
ext2_fsblk_t current_block = 0;
int ret = 0;

/*
* Here we try to allocate the requested multiple blocks at once,
* on a best-effort basis.
* To build a branch, we should allocate blocks for
* the indirect blocks(if not allocated yet), and at least
* the first direct block of this branch. That's the
* minimum number of blocks need to allocate(required)
*/
target = blks + indirect_blks;

while (1) {
count = target;
/* allocating blocks for indirect blocks and direct blocks */
current_block = ext2_new_blocks(inode,goal,&count,err);
if (*err)
goto failed_out;

target -= count;
/* allocate blocks for indirect blocks */
while (index < indirect_blks && count) {
new_blocks[index++] = current_block++;
count--;
}

if (count > 0)
break;
}

/* save the new block number for the first direct block */
new_blocks[index] = current_block;

/* total number of blocks allocated for direct blocks */
ret = count;
*err = 0;
return ret;
failed_out:
for (i = 0; i ext2_free_blocks(inode, new_blocks[i], 1);
return ret;
}

/**
* ext2_alloc_branch - allocate and set up a chain of blocks.
* @inode: owner
* @num: depth of the chain (number of blocks to allocate)
* @offsets: offsets (in the blocks) to store the pointers to next.
* @branch: place to store the chain in.
*
* This function allocates @num blocks, zeroes out all but the last one,
* links them into chain and (if we are synchronous) writes them to disk.
* In other words, it prepares a branch that can be spliced onto the
* inode. It stores the information about that chain in the branch[], in
* the same format as ext2_get_branch() would do. We are calling it after
* we had read the existing part of chain and partial points to the last
* triple of that (one with zero ->key). Upon the exit we have the same
* picture as after the successful ext2_get_block(), excpet that in one
* place chain is disconnected – *branch->p is still zero (we did not
* set the last link), but branch->key contains the number that should
* be placed into *branch->p to fill that gap.
*
* If allocation fails we free all blocks we’ve allocated (and forget
* their buffer_heads) and return the error value the from failed
* ext2_alloc_block() (normally -ENOSPC). Otherwise we set the chain
* as described above and return 0.
*/

static int ext2_alloc_branch(struct inode *inode,
int indirect_blks, int *blks, ext2_fsblk_t goal,
int *offsets, Indirect *branch)
{
int blocksize = inode->i_sb->s_blocksize;
int i, n = 0;
int err = 0;
struct buffer_head *bh;
int num;
ext2_fsblk_t new_blocks[4];
ext2_fsblk_t current_block;

num = ext2_alloc_blocks(inode, goal, indirect_blks,
*blks, new_blocks, &err);
if (err)
return err;

branch[0].key = cpu_to_le32(new_blocks[0]);
/*
* metadata blocks and data blocks are allocated.
*/
for (n = 1; n <= indirect_blks; n++) {
/*
* Get buffer_head for parent block, zero it out
* and set the pointer to new one, then send
* parent to disk.
*/
bh = sb_getblk(inode->i_sb, new_blocks[n-1]);
branch[n].bh = bh;
lock_buffer(bh);
memset(bh->b_data, 0, blocksize);
branch[n].p = (__le32 *) bh->b_data + offsets[n];
branch[n].key = cpu_to_le32(new_blocks[n]);
*branch[n].p = branch[n].key;
if ( n == indirect_blks) {
current_block = new_blocks[n];
/*
* End of chain, update the last new metablock of
* the chain to point to the new allocated
* data blocks numbers
*/
for (i=1; i < num; i++)
*(branch[n].p + i) = cpu_to_le32(++current_block);
}
set_buffer_uptodate(bh);
unlock_buffer(bh);
mark_buffer_dirty_inode(bh, inode);
/* We used to sync bh here if IS_SYNC(inode).
* But we now rely upon generic_write_sync()
* and b_inode_buffers. But not for directories.
*/
if (S_ISDIR(inode->i_mode) && IS_DIRSYNC(inode))
sync_dirty_buffer(bh);
}
*blks = num;
return err;
}

/**
* ext2_splice_branch – splice the allocated branch onto inode.
* @inode: owner
* @block: (logical) number of block we are adding
* @where: location of missing link
* @num: number of indirect blocks we are adding
* @blks: number of direct blocks we are adding
*
* This function fills the missing link and does all housekeeping needed in
* inode (->i_blocks, etc.). In case of success we end up with the full
* chain to new block and return 0.
*/
static void ext2_splice_branch(struct inode *inode,
long block, Indirect *where, int num, int blks)
{
int i;
struct ext2_block_alloc_info *block_i;
ext2_fsblk_t current_block;

block_i = EXT2_I(inode)->i_block_alloc_info;

/* XXX LOCKING probably should have i_meta_lock ?*/
/* That’s it */

*where->p = where->key;

/*
* Update the host buffer_head or inode to point to more just allocated
* direct blocks blocks
*/
if (num == 0 && blks > 1) {
current_block = le32_to_cpu(where->key) + 1;
for (i = 1; i < blks; i++)
*(where->p + i ) = cpu_to_le32(current_block++);
}

/*
* update the most recently allocated logical & physical block
* in i_block_alloc_info, to assist find the proper goal block for next
* allocation
*/
if (block_i) {
block_i->last_alloc_logical_block = block + blks – 1;
block_i->last_alloc_physical_block =
le32_to_cpu(where[num].key) + blks – 1;
}

/* We are done with atomic stuff, now do the rest of housekeeping */

/* had we spliced it onto indirect block? */
if (where->bh)
mark_buffer_dirty_inode(where->bh, inode);

inode->i_ctime = CURRENT_TIME_SEC;
mark_inode_dirty(inode);
}

/*
* Allocation strategy is simple: if we have to allocate something, we will
* have to go the whole way to leaf. So let’s do it before attaching anything
* to tree, set linkage between the newborn blocks, write them if sync is
* required, recheck the path, free and repeat if check fails, otherwise
* set the last missing link (that will protect us from any truncate-generated
* removals – all blocks on the path are immune now) and possibly force the
* write on the parent block.
* That has a nice additional property: no special recovery from the failed
* allocations is needed – we simply release blocks and do not touch anything
* reachable from inode.
*
* `handle’ can be NULL if create == 0.
*
* return > 0, # of blocks mapped or allocated.
* return = 0, if plain lookup failed.
* return < 0, error case.
*/
static int ext2_get_blocks(struct inode *inode,
sector_t iblock, unsigned long maxblocks,
struct buffer_head *bh_result,
int create)
{
int err = -EIO;
int offsets[4];
Indirect chain[4];
Indirect *partial;
ext2_fsblk_t goal;
int indirect_blks;
int blocks_to_boundary = 0;
int depth;
struct ext2_inode_info *ei = EXT2_I(inode);
int count = 0;
ext2_fsblk_t first_block = 0;

depth = ext2_block_to_path(inode,iblock,offsets,&blocks_to_boundary);

if (depth == 0)
return (err);

partial = ext2_get_branch(inode, depth, offsets, chain, &err);
/* Simplest case - block found, no allocation needed */
if (!partial) {
first_block = le32_to_cpu(chain[depth - 1].key);
clear_buffer_new(bh_result); /* What's this do? */
count++;
/*map more blocks*/
while (count < maxblocks && count <= blocks_to_boundary) {
ext2_fsblk_t blk;

if (!verify_chain(chain, chain + depth - 1)) {
/*
* Indirect block might be removed by
* truncate while we were reading it.
* Handling of that case: forget what we've
* got now, go to reread.
*/
err = -EAGAIN;
count = 0;
break;
}
blk = le32_to_cpu(*(chain[depth-1].p + count));
if (blk == first_block + count)
count++;
else
break;
}
if (err != -EAGAIN)
goto got_it;
}

/* Next simple case - plain lookup or failed read of indirect block */
if (!create || err == -EIO)
goto cleanup;

mutex_lock(&ei->truncate_mutex);
/*
* If the indirect block is missing while we are reading
* the chain(ext3_get_branch() returns -EAGAIN err), or
* if the chain has been changed after we grab the semaphore,
* (either because another process truncated this branch, or
* another get_block allocated this branch) re-grab the chain to see if
* the request block has been allocated or not.
*
* Since we already block the truncate/other get_block
* at this point, we will have the current copy of the chain when we
* splice the branch into the tree.
*/
if (err == -EAGAIN || !verify_chain(chain, partial)) {
while (partial > chain) {
brelse(partial->bh);
partial–;
}
partial = ext2_get_branch(inode, depth, offsets, chain, &err);
if (!partial) {
count++;
mutex_unlock(&ei->truncate_mutex);
if (err)
goto cleanup;
clear_buffer_new(bh_result);
goto got_it;
}
}

/*
* Okay, we need to do block allocation. Lazily initialize the block
* allocation info here if necessary
*/
if (S_ISREG(inode->i_mode) && (!ei->i_block_alloc_info))
ext2_init_block_alloc_info(inode);

goal = ext2_find_goal(inode, iblock, partial);

/* the number of blocks need to allocate for [d,t]indirect blocks */
indirect_blks = (chain + depth) – partial – 1;
/*
* Next look up the indirect map to count the totoal number of
* direct blocks to allocate for this branch.
*/
count = ext2_blks_to_allocate(partial, indirect_blks,
maxblocks, blocks_to_boundary);
/*
* XXX ???? Block out ext2_truncate while we alter the tree
*/
err = ext2_alloc_branch(inode, indirect_blks, &count, goal,
offsets + (partial – chain), partial);

if (err) {
mutex_unlock(&ei->truncate_mutex);
goto cleanup;
}

if (ext2_use_xip(inode->i_sb)) {
/*
* we need to clear the block
*/
err = ext2_clear_xip_target (inode,
le32_to_cpu(chain[depth-1].key));
if (err) {
mutex_unlock(&ei->truncate_mutex);
goto cleanup;
}
}

ext2_splice_branch(inode, iblock, partial, indirect_blks, count);
mutex_unlock(&ei->truncate_mutex);
set_buffer_new(bh_result);
got_it:
map_bh(bh_result, inode->i_sb, le32_to_cpu(chain[depth-1].key));
if (count > blocks_to_boundary)
set_buffer_boundary(bh_result);
err = count;
/* Clean up and exit */
partial = chain + depth – 1; /* the whole chain */
cleanup:
while (partial > chain) {
brelse(partial->bh);
partial–;
}
return err;
}

int ext2_get_block(struct inode *inode, sector_t iblock, struct buffer_head *bh_result, int create)
{
unsigned max_blocks = bh_result->b_size >> inode->i_blkbits;
int ret = ext2_get_blocks(inode, iblock, max_blocks,
bh_result, create);
if (ret > 0) {
bh_result->b_size = (ret << inode->i_blkbits);
ret = 0;
}
return ret;

}

int ext2_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
u64 start, u64 len)
{
return generic_block_fiemap(inode, fieinfo, start, len,
ext2_get_block);
}

static int ext2_writepage(struct page *page, struct writeback_control *wbc)
{
return block_write_full_page(page, ext2_get_block, wbc);
}

static int ext2_readpage(struct file *file, struct page *page)
{
return mpage_readpage(page, ext2_get_block);
}

static int
ext2_readpages(struct file *file, struct address_space *mapping,
struct list_head *pages, unsigned nr_pages)
{
return mpage_readpages(mapping, pages, nr_pages, ext2_get_block);
}

int __ext2_write_begin(struct file *file, struct address_space *mapping,
loff_t pos, unsigned len, unsigned flags,
struct page **pagep, void **fsdata)
{
return block_write_begin(file, mapping, pos, len, flags, pagep, fsdata,
ext2_get_block);
}

static int
ext2_write_begin(struct file *file, struct address_space *mapping,
loff_t pos, unsigned len, unsigned flags,
struct page **pagep, void **fsdata)
{
*pagep = NULL;
return __ext2_write_begin(file, mapping, pos, len, flags, pagep,fsdata);
}

static int
ext2_nobh_write_begin(struct file *file, struct address_space *mapping,
loff_t pos, unsigned len, unsigned flags,
struct page **pagep, void **fsdata)
{
/*
* Dir-in-pagecache still uses ext2_write_begin. Would have to rework
* directory handling code to pass around offsets rather than struct
* pages in order to make this work easily.
*/
return nobh_write_begin(file, mapping, pos, len, flags, pagep, fsdata,
ext2_get_block);
}

static int ext2_nobh_writepage(struct page *page,
struct writeback_control *wbc)
{
return nobh_writepage(page, ext2_get_block, wbc);
}

static sector_t ext2_bmap(struct address_space *mapping, sector_t block)
{
return generic_block_bmap(mapping,block,ext2_get_block);
}

static ssize_t
ext2_direct_IO(int rw, struct kiocb *iocb, const struct iovec *iov,
loff_t offset, unsigned long nr_segs)
{
struct file *file = iocb->ki_filp;
struct inode *inode = file->f_mapping->host;

return blockdev_direct_IO(rw, iocb, inode, inode->i_sb->s_bdev, iov,
offset, nr_segs, ext2_get_block, NULL);
}

static int
ext2_writepages(struct address_space *mapping, struct writeback_control *wbc)
{
return mpage_writepages(mapping, wbc, ext2_get_block);
}

const struct address_space_operations ext2_aops = {
.readpage = ext2_readpage,
.readpages = ext2_readpages,
.writepage = ext2_writepage,
.sync_page = block_sync_page,
.write_begin = ext2_write_begin,
.write_end = generic_write_end,
.bmap = ext2_bmap,
.direct_IO = ext2_direct_IO,
.writepages = ext2_writepages,
.migratepage = buffer_migrate_page,
.is_partially_uptodate = block_is_partially_uptodate,
.error_remove_page = generic_error_remove_page,
};

const struct address_space_operations ext2_aops_xip = {
.bmap = ext2_bmap,
.get_xip_mem = ext2_get_xip_mem,
};

const struct address_space_operations ext2_nobh_aops = {
.readpage = ext2_readpage,
.readpages = ext2_readpages,
.writepage = ext2_nobh_writepage,
.sync_page = block_sync_page,
.write_begin = ext2_nobh_write_begin,
.write_end = nobh_write_end,
.bmap = ext2_bmap,
.direct_IO = ext2_direct_IO,
.writepages = ext2_writepages,
.migratepage = buffer_migrate_page,
.error_remove_page = generic_error_remove_page,
};

/*
* Probably it should be a library function… search for first non-zero word
* or memcmp with zero_page, whatever is better for particular architecture.
* Linus?
*/
static inline int all_zeroes(__le32 *p, __le32 *q)
{
while (p < q)
if (*p++)
return 0;
return 1;
}

/**
* ext2_find_shared - find the indirect blocks for partial truncation.
* @inode: inode in question
* @depth: depth of the affected branch
* @offsets: offsets of pointers in that branch (see ext2_block_to_path)
* @chain: place to store the pointers to partial indirect blocks
* @top: place to the (detached) top of branch
*
* This is a helper function used by ext2_truncate().
*
* When we do truncate() we may have to clean the ends of several indirect
* blocks but leave the blocks themselves alive. Block is partially
* truncated if some data below the new i_size is refered from it (and
* it is on the path to the first completely truncated data block, indeed).
* We have to free the top of that path along with everything to the right
* of the path. Since no allocation past the truncation point is possible
* until ext2_truncate() finishes, we may safely do the latter, but top
* of branch may require special attention - pageout below the truncation
* point might try to populate it.
*
* We atomically detach the top of branch from the tree, store the block
* number of its root in *@top, pointers to buffer_heads of partially
* truncated blocks - in @chain[].bh and pointers to their last elements
* that should not be removed - in @chain[].p. Return value is the pointer
* to last filled element of @chain.
*
* The work left to caller to do the actual freeing of subtrees:
* a) free the subtree starting from *@top
* b) free the subtrees whose roots are stored in
* (@chain[i].p+1 .. end of @chain[i].bh->b_data)
* c) free the subtrees growing from the inode past the @chain[0].p
* (no partially truncated stuff there).
*/

static Indirect *ext2_find_shared(struct inode *inode,
int depth,
int offsets[4],
Indirect chain[4],
__le32 *top)
{
Indirect *partial, *p;
int k, err;

*top = 0;
for (k = depth; k > 1 && !offsets[k-1]; k–)
;
partial = ext2_get_branch(inode, k, offsets, chain, &err);
if (!partial)
partial = chain + k-1;
/*
* If the branch acquired continuation since we’ve looked at it -
* fine, it should all survive and (new) top doesn’t belong to us.
*/
write_lock(&EXT2_I(inode)->i_meta_lock);
if (!partial->key && *partial->p) {
write_unlock(&EXT2_I(inode)->i_meta_lock);
goto no_top;
}
for (p=partial; p>chain && all_zeroes((__le32*)p->bh->b_data,p->p); p–)
;
/*
* OK, we’ve found the last block that must survive. The rest of our
* branch should be detached before unlocking. However, if that rest
* of branch is all ours and does not grow immediately from the inode
* it’s easier to cheat and just decrement partial->p.
*/
if (p == chain + k – 1 && p > chain) {
p->p–;
} else {
*top = *p->p;
*p->p = 0;
}
write_unlock(&EXT2_I(inode)->i_meta_lock);

while(partial > p)
{
brelse(partial->bh);
partial–;
}
no_top:
return partial;
}

/**
* ext2_free_data – free a list of data blocks
* @inode: inode we are dealing with
* @p: array of block numbers
* @q: points immediately past the end of array
*
* We are freeing all blocks refered from that array (numbers are
* stored as little-endian 32-bit) and updating @inode->i_blocks
* appropriately.
*/
static inline void ext2_free_data(struct inode *inode, __le32 *p, __le32 *q)
{
unsigned long block_to_free = 0, count = 0;
unsigned long nr;

for ( ; p < q ; p++) {
nr = le32_to_cpu(*p);
if (nr) {
*p = 0;
/* accumulate blocks to free if they're contiguous */
if (count == 0)
goto free_this;
else if (block_to_free == nr - count)
count++;
else {
mark_inode_dirty(inode);
ext2_free_blocks (inode, block_to_free, count);
free_this:
block_to_free = nr;
count = 1;
}
}
}
if (count > 0) {
mark_inode_dirty(inode);
ext2_free_blocks (inode, block_to_free, count);
}
}

/**
* ext2_free_branches – free an array of branches
* @inode: inode we are dealing with
* @p: array of block numbers
* @q: pointer immediately past the end of array
* @depth: depth of the branches to free
*
* We are freeing all blocks refered from these branches (numbers are
* stored as little-endian 32-bit) and updating @inode->i_blocks
* appropriately.
*/
static void ext2_free_branches(struct inode *inode, __le32 *p, __le32 *q, int depth)
{
struct buffer_head * bh;
unsigned long nr;

if (depth–) {
int addr_per_block = EXT2_ADDR_PER_BLOCK(inode->i_sb);
for ( ; p < q ; p++) {
nr = le32_to_cpu(*p);
if (!nr)
continue;
*p = 0;
bh = sb_bread(inode->i_sb, nr);
/*
* A read failure? Report error and clear slot
* (should be rare).
*/
if (!bh) {
ext2_error(inode->i_sb, «ext2_free_branches»,
«Read failure, inode=%ld, block=%ld»,
inode->i_ino, nr);
continue;
}
ext2_free_branches(inode,
(__le32*)bh->b_data,
(__le32*)bh->b_data + addr_per_block,
depth);
bforget(bh);
ext2_free_blocks(inode, nr, 1);
mark_inode_dirty(inode);
}
} else
ext2_free_data(inode, p, q);
}

void ext2_truncate(struct inode *inode)
{
__le32 *i_data = EXT2_I(inode)->i_data;
struct ext2_inode_info *ei = EXT2_I(inode);
int addr_per_block = EXT2_ADDR_PER_BLOCK(inode->i_sb);
int offsets[4];
Indirect chain[4];
Indirect *partial;
__le32 nr = 0;
int n;
long iblock;
unsigned blocksize;

if (!(S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) ||
S_ISLNK(inode->i_mode)))
return;
if (ext2_inode_is_fast_symlink(inode))
return;
if (IS_APPEND(inode) || IS_IMMUTABLE(inode))
return;

blocksize = inode->i_sb->s_blocksize;
iblock = (inode->i_size + blocksize-1)
>> EXT2_BLOCK_SIZE_BITS(inode->i_sb);

if (mapping_is_xip(inode->i_mapping))
xip_truncate_page(inode->i_mapping, inode->i_size);
else if (test_opt(inode->i_sb, NOBH))
nobh_truncate_page(inode->i_mapping,
inode->i_size, ext2_get_block);
else
block_truncate_page(inode->i_mapping,
inode->i_size, ext2_get_block);

n = ext2_block_to_path(inode, iblock, offsets, NULL);
if (n == 0)
return;

/*
* From here we block out all ext2_get_block() callers who want to
* modify the block allocation tree.
*/
mutex_lock(&ei->truncate_mutex);

if (n == 1) {
ext2_free_data(inode, i_data+offsets[0],
i_data + EXT2_NDIR_BLOCKS);
goto do_indirects;
}

partial = ext2_find_shared(inode, n, offsets, chain, &nr);
/* Kill the top of shared branch (already detached) */
if (nr) {
if (partial == chain)
mark_inode_dirty(inode);
else
mark_buffer_dirty_inode(partial->bh, inode);
ext2_free_branches(inode, &nr, &nr+1, (chain+n-1) – partial);
}
/* Clear the ends of indirect blocks on the shared branch */
while (partial > chain) {
ext2_free_branches(inode,
partial->p + 1,
(__le32*)partial->bh->b_data+addr_per_block,
(chain+n-1) – partial);
mark_buffer_dirty_inode(partial->bh, inode);
brelse (partial->bh);
partial–;
}
do_indirects:
/* Kill the remaining (whole) subtrees */
switch (offsets[0]) {
default:
nr = i_data[EXT2_IND_BLOCK];
if (nr) {
i_data[EXT2_IND_BLOCK] = 0;
mark_inode_dirty(inode);
ext2_free_branches(inode, &nr, &nr+1, 1);
}
case EXT2_IND_BLOCK:
nr = i_data[EXT2_DIND_BLOCK];
if (nr) {
i_data[EXT2_DIND_BLOCK] = 0;
mark_inode_dirty(inode);
ext2_free_branches(inode, &nr, &nr+1, 2);
}
case EXT2_DIND_BLOCK:
nr = i_data[EXT2_TIND_BLOCK];
if (nr) {
i_data[EXT2_TIND_BLOCK] = 0;
mark_inode_dirty(inode);
ext2_free_branches(inode, &nr, &nr+1, 3);
}
case EXT2_TIND_BLOCK:
;
}

ext2_discard_reservation(inode);

mutex_unlock(&ei->truncate_mutex);
inode->i_mtime = inode->i_ctime = CURRENT_TIME_SEC;
if (inode_needs_sync(inode)) {
sync_mapping_buffers(inode->i_mapping);
ext2_sync_inode (inode);
} else {
mark_inode_dirty(inode);
}
}

static struct ext2_inode *ext2_get_inode(struct super_block *sb, ino_t ino,
struct buffer_head **p)
{
struct buffer_head * bh;
unsigned long block_group;
unsigned long block;
unsigned long offset;
struct ext2_group_desc * gdp;

*p = NULL;
if ((ino != EXT2_ROOT_INO && ino < EXT2_FIRST_INO(sb)) ||
ino > le32_to_cpu(EXT2_SB(sb)->s_es->s_inodes_count))
goto Einval;

block_group = (ino – 1) / EXT2_INODES_PER_GROUP(sb);
gdp = ext2_get_group_desc(sb, block_group, NULL);
if (!gdp)
goto Egdp;
/*
* Figure out the offset within the block group inode table
*/
offset = ((ino – 1) % EXT2_INODES_PER_GROUP(sb)) * EXT2_INODE_SIZE(sb);
block = le32_to_cpu(gdp->bg_inode_table) +
(offset >> EXT2_BLOCK_SIZE_BITS(sb));
if (!(bh = sb_bread(sb, block)))
goto Eio;

*p = bh;
offset &= (EXT2_BLOCK_SIZE(sb) – 1);
return (struct ext2_inode *) (bh->b_data + offset);

Einval:
ext2_error(sb, «ext2_get_inode», «bad inode number: %lu»,
(unsigned long) ino);
return ERR_PTR(-EINVAL);
Eio:
ext2_error(sb, «ext2_get_inode»,
«unable to read inode block – inode=%lu, block=%lu»,
(unsigned long) ino, block);
Egdp:
return ERR_PTR(-EIO);
}

void ext2_set_inode_flags(struct inode *inode)
{
unsigned int flags = EXT2_I(inode)->i_flags;

inode->i_flags &= ~(S_SYNC|S_APPEND|S_IMMUTABLE|S_NOATIME|S_DIRSYNC);
if (flags & EXT2_SYNC_FL)
inode->i_flags |= S_SYNC;
if (flags & EXT2_APPEND_FL)
inode->i_flags |= S_APPEND;
if (flags & EXT2_IMMUTABLE_FL)
inode->i_flags |= S_IMMUTABLE;
if (flags & EXT2_NOATIME_FL)
inode->i_flags |= S_NOATIME;
if (flags & EXT2_DIRSYNC_FL)
inode->i_flags |= S_DIRSYNC;
}

/* Propagate flags from i_flags to EXT2_I(inode)->i_flags */
void ext2_get_inode_flags(struct ext2_inode_info *ei)
{
unsigned int flags = ei->vfs_inode.i_flags;

ei->i_flags &= ~(EXT2_SYNC_FL|EXT2_APPEND_FL|
EXT2_IMMUTABLE_FL|EXT2_NOATIME_FL|EXT2_DIRSYNC_FL);
if (flags & S_SYNC)
ei->i_flags |= EXT2_SYNC_FL;
if (flags & S_APPEND)
ei->i_flags |= EXT2_APPEND_FL;
if (flags & S_IMMUTABLE)
ei->i_flags |= EXT2_IMMUTABLE_FL;
if (flags & S_NOATIME)
ei->i_flags |= EXT2_NOATIME_FL;
if (flags & S_DIRSYNC)
ei->i_flags |= EXT2_DIRSYNC_FL;
}

struct inode *ext2_iget (struct super_block *sb, unsigned long ino)
{
struct ext2_inode_info *ei;
struct buffer_head * bh;
struct ext2_inode *raw_inode;
struct inode *inode;
long ret = -EIO;
int n;

inode = iget_locked(sb, ino);
if (!inode)
return ERR_PTR(-ENOMEM);
if (!(inode->i_state & I_NEW))
return inode;

ei = EXT2_I(inode);
ei->i_block_alloc_info = NULL;

raw_inode = ext2_get_inode(inode->i_sb, ino, &bh);
if (IS_ERR(raw_inode)) {
ret = PTR_ERR(raw_inode);
goto bad_inode;
}

inode->i_mode = le16_to_cpu(raw_inode->i_mode);
inode->i_uid = (uid_t)le16_to_cpu(raw_inode->i_uid_low);
inode->i_gid = (gid_t)le16_to_cpu(raw_inode->i_gid_low);
if (!(test_opt (inode->i_sb, NO_UID32))) {
inode->i_uid |= le16_to_cpu(raw_inode->i_uid_high) << 16;
inode->i_gid |= le16_to_cpu(raw_inode->i_gid_high) << 16;
}
inode->i_nlink = le16_to_cpu(raw_inode->i_links_count);
inode->i_size = le32_to_cpu(raw_inode->i_size);
inode->i_atime.tv_sec = (signed)le32_to_cpu(raw_inode->i_atime);
inode->i_ctime.tv_sec = (signed)le32_to_cpu(raw_inode->i_ctime);
inode->i_mtime.tv_sec = (signed)le32_to_cpu(raw_inode->i_mtime);
inode->i_atime.tv_nsec = inode->i_mtime.tv_nsec = inode->i_ctime.tv_nsec = 0;
ei->i_dtime = le32_to_cpu(raw_inode->i_dtime);
/* We now have enough fields to check if the inode was active or not.
* This is needed because nfsd might try to access dead inodes
* the test is that same one that e2fsck uses
* NeilBrown 1999oct15
*/
if (inode->i_nlink == 0 && (inode->i_mode == 0 || ei->i_dtime)) {
/* this inode is deleted */
brelse (bh);
ret = -ESTALE;
goto bad_inode;
}
inode->i_blocks = le32_to_cpu(raw_inode->i_blocks);
ei->i_flags = le32_to_cpu(raw_inode->i_flags);
ei->i_faddr = le32_to_cpu(raw_inode->i_faddr);
ei->i_frag_no = raw_inode->i_frag;
ei->i_frag_size = raw_inode->i_fsize;
ei->i_file_acl = le32_to_cpu(raw_inode->i_file_acl);
ei->i_dir_acl = 0;
if (S_ISREG(inode->i_mode))
inode->i_size |= ((__u64)le32_to_cpu(raw_inode->i_size_high)) << 32;
else
ei->i_dir_acl = le32_to_cpu(raw_inode->i_dir_acl);
ei->i_dtime = 0;
inode->i_generation = le32_to_cpu(raw_inode->i_generation);
ei->i_state = 0;
ei->i_block_group = (ino – 1) / EXT2_INODES_PER_GROUP(inode->i_sb);
ei->i_dir_start_lookup = 0;

/*
* NOTE! The in-memory inode i_data array is in little-endian order
* even on big-endian machines: we do NOT byteswap the block numbers!
*/
for (n = 0; n < EXT2_N_BLOCKS; n++)
ei->i_data[n] = raw_inode->i_block[n];

if (S_ISREG(inode->i_mode)) {
inode->i_op = &ext2_file_inode_operations;
if (ext2_use_xip(inode->i_sb)) {
inode->i_mapping->a_ops = &ext2_aops_xip;
inode->i_fop = &ext2_xip_file_operations;
} else if (test_opt(inode->i_sb, NOBH)) {
inode->i_mapping->a_ops = &ext2_nobh_aops;
inode->i_fop = &ext2_file_operations;
} else {
inode->i_mapping->a_ops = &ext2_aops;
inode->i_fop = &ext2_file_operations;
}
} else if (S_ISDIR(inode->i_mode)) {
inode->i_op = &ext2_dir_inode_operations;
inode->i_fop = &ext2_dir_operations;
if (test_opt(inode->i_sb, NOBH))
inode->i_mapping->a_ops = &ext2_nobh_aops;
else
inode->i_mapping->a_ops = &ext2_aops;
} else if (S_ISLNK(inode->i_mode)) {
if (ext2_inode_is_fast_symlink(inode)) {
inode->i_op = &ext2_fast_symlink_inode_operations;
nd_terminate_link(ei->i_data, inode->i_size,
sizeof(ei->i_data) – 1);
} else {
inode->i_op = &ext2_symlink_inode_operations;
if (test_opt(inode->i_sb, NOBH))
inode->i_mapping->a_ops = &ext2_nobh_aops;
else
inode->i_mapping->a_ops = &ext2_aops;
}
} else {
inode->i_op = &ext2_special_inode_operations;
if (raw_inode->i_block[0])
init_special_inode(inode, inode->i_mode,
old_decode_dev(le32_to_cpu(raw_inode->i_block[0])));
else
init_special_inode(inode, inode->i_mode,
new_decode_dev(le32_to_cpu(raw_inode->i_block[1])));
}
brelse (bh);
ext2_set_inode_flags(inode);
unlock_new_inode(inode);
return inode;

bad_inode:
iget_failed(inode);
return ERR_PTR(ret);
}

int ext2_write_inode(struct inode *inode, int do_sync)
{
struct ext2_inode_info *ei = EXT2_I(inode);
struct super_block *sb = inode->i_sb;
ino_t ino = inode->i_ino;
uid_t uid = inode->i_uid;
gid_t gid = inode->i_gid;
struct buffer_head * bh;
struct ext2_inode * raw_inode = ext2_get_inode(sb, ino, &bh);
int n;
int err = 0;

if (IS_ERR(raw_inode))
return -EIO;

/* For fields not not tracking in the in-memory inode,
* initialise them to zero for new inodes. */
if (ei->i_state & EXT2_STATE_NEW)
memset(raw_inode, 0, EXT2_SB(sb)->s_inode_size);

ext2_get_inode_flags(ei);
raw_inode->i_mode = cpu_to_le16(inode->i_mode);
if (!(test_opt(sb, NO_UID32))) {
raw_inode->i_uid_low = cpu_to_le16(low_16_bits(uid));
raw_inode->i_gid_low = cpu_to_le16(low_16_bits(gid));
/*
* Fix up interoperability with old kernels. Otherwise, old inodes get
* re-used with the upper 16 bits of the uid/gid intact
*/
if (!ei->i_dtime) {
raw_inode->i_uid_high = cpu_to_le16(high_16_bits(uid));
raw_inode->i_gid_high = cpu_to_le16(high_16_bits(gid));
} else {
raw_inode->i_uid_high = 0;
raw_inode->i_gid_high = 0;
}
} else {
raw_inode->i_uid_low = cpu_to_le16(fs_high2lowuid(uid));
raw_inode->i_gid_low = cpu_to_le16(fs_high2lowgid(gid));
raw_inode->i_uid_high = 0;
raw_inode->i_gid_high = 0;
}
raw_inode->i_links_count = cpu_to_le16(inode->i_nlink);
raw_inode->i_size = cpu_to_le32(inode->i_size);
raw_inode->i_atime = cpu_to_le32(inode->i_atime.tv_sec);
raw_inode->i_ctime = cpu_to_le32(inode->i_ctime.tv_sec);
raw_inode->i_mtime = cpu_to_le32(inode->i_mtime.tv_sec);

raw_inode->i_blocks = cpu_to_le32(inode->i_blocks);
raw_inode->i_dtime = cpu_to_le32(ei->i_dtime);
raw_inode->i_flags = cpu_to_le32(ei->i_flags);
raw_inode->i_faddr = cpu_to_le32(ei->i_faddr);
raw_inode->i_frag = ei->i_frag_no;
raw_inode->i_fsize = ei->i_frag_size;
raw_inode->i_file_acl = cpu_to_le32(ei->i_file_acl);
if (!S_ISREG(inode->i_mode))
raw_inode->i_dir_acl = cpu_to_le32(ei->i_dir_acl);
else {
raw_inode->i_size_high = cpu_to_le32(inode->i_size >> 32);
if (inode->i_size > 0×7fffffffULL) {
if (!EXT2_HAS_RO_COMPAT_FEATURE(sb,
EXT2_FEATURE_RO_COMPAT_LARGE_FILE) ||
EXT2_SB(sb)->s_es->s_rev_level ==
cpu_to_le32(EXT2_GOOD_OLD_REV)) {
/* If this is the first large file
* created, add a flag to the superblock.
*/
lock_kernel();
ext2_update_dynamic_rev(sb);
EXT2_SET_RO_COMPAT_FEATURE(sb,
EXT2_FEATURE_RO_COMPAT_LARGE_FILE);
unlock_kernel();
ext2_write_super(sb);
}
}
}

raw_inode->i_generation = cpu_to_le32(inode->i_generation);
if (S_ISCHR(inode->i_mode) || S_ISBLK(inode->i_mode)) {
if (old_valid_dev(inode->i_rdev)) {
raw_inode->i_block[0] =
cpu_to_le32(old_encode_dev(inode->i_rdev));
raw_inode->i_block[1] = 0;
} else {
raw_inode->i_block[0] = 0;
raw_inode->i_block[1] =
cpu_to_le32(new_encode_dev(inode->i_rdev));
raw_inode->i_block[2] = 0;
}
} else for (n = 0; n < EXT2_N_BLOCKS; n++)
raw_inode->i_block[n] = ei->i_data[n];
mark_buffer_dirty(bh);
if (do_sync) {
sync_dirty_buffer(bh);
if (buffer_req(bh) && !buffer_uptodate(bh)) {
printk (»IO error syncing ext2 inode [%s:%08lx]\n»,
sb->s_id, (unsigned long) ino);
err = -EIO;
}
}
ei->i_state &= ~EXT2_STATE_NEW;
brelse (bh);
return err;
}

int ext2_sync_inode(struct inode *inode)
{
struct writeback_control wbc = {
.sync_mode = WB_SYNC_ALL,
.nr_to_write = 0, /* sys_fsync did this */
};
return sync_inode(inode, &wbc);
}

int ext2_setattr(struct dentry *dentry, struct iattr *iattr)
{
struct inode *inode = dentry->d_inode;
int error;

error = inode_change_ok(inode, iattr);
if (error)
return error;
if ((iattr->ia_valid & ATTR_UID && iattr->ia_uid != inode->i_uid) ||
(iattr->ia_valid & ATTR_GID && iattr->ia_gid != inode->i_gid)) {
error = vfs_dq_transfer(inode, iattr) ? -EDQUOT : 0;
if (error)
return error;
}
error = inode_setattr(inode, iattr);
if (!error && (iattr->ia_valid & ATTR_MODE))
error = ext2_acl_chmod(inode);
return error;
}

#include #include #include #include #include #include «ext2.h»
#include «xattr.h»
#include «acl.h»

/*
* ialloc.c contains the inodes allocation and deallocation routines
*/

/*
* The free inodes are managed by bitmaps. A file system contains several
* blocks groups. Each group contains 1 bitmap block for blocks, 1 bitmap
* block for inodes, N blocks for the inode table and data blocks.
*
* The file system contains group descriptors which are located after the
* super block. Each descriptor contains the number of the bitmap block and
* the free blocks count in the block.
*/

/*
* Read the inode allocation bitmap for a given block_group, reading
* into the specified slot in the superblock’s bitmap cache.
*
* Return buffer_head of bitmap on success or NULL.
*/
static struct buffer_head *
read_inode_bitmap(struct super_block * sb, unsigned long block_group)
{
struct ext2_group_desc *desc;
struct buffer_head *bh = NULL;

desc = ext2_get_group_desc(sb, block_group, NULL);
if (!desc)
goto error_out;

bh = sb_bread(sb, le32_to_cpu(desc->bg_inode_bitmap));
if (!bh)
ext2_error(sb, «read_inode_bitmap»,
«Cannot read inode bitmap – »
«block_group = %lu, inode_bitmap = %u»,
block_group, le32_to_cpu(desc->bg_inode_bitmap));
error_out:
return bh;
}

static void ext2_release_inode(struct super_block *sb, int group, int dir)
{
struct ext2_group_desc * desc;
struct buffer_head *bh;

desc = ext2_get_group_desc(sb, group, &bh);
if (!desc) {
ext2_error(sb, «ext2_release_inode»,
«can’t get descriptor for group %d», group);
return;
}

spin_lock(sb_bgl_lock(EXT2_SB(sb), group));
le16_add_cpu(&desc->bg_free_inodes_count, 1);
if (dir)
le16_add_cpu(&desc->bg_used_dirs_count, -1);
spin_unlock(sb_bgl_lock(EXT2_SB(sb), group));
if (dir)
percpu_counter_dec(&EXT2_SB(sb)->s_dirs_counter);
sb->s_dirt = 1;
mark_buffer_dirty(bh);
}

/*
* NOTE! When we get the inode, we’re the only people
* that have access to it, and as such there are no
* race conditions we have to worry about. The inode
* is not on the hash-lists, and it cannot be reached
* through the filesystem because the directory entry
* has been deleted earlier.
*
* HOWEVER: we must make sure that we get no aliases,
* which means that we have to call «clear_inode()»
* _before_ we mark the inode not in use in the inode
* bitmaps. Otherwise a newly created file might use
* the same inode number (not actually the same pointer
* though), and then we’d have two inodes sharing the
* same inode number and space on the harddisk.
*/
void ext2_free_inode (struct inode * inode)
{
struct super_block * sb = inode->i_sb;
int is_directory;
unsigned long ino;
struct buffer_head *bitmap_bh = NULL;
unsigned long block_group;
unsigned long bit;
struct ext2_super_block * es;

ino = inode->i_ino;
ext2_debug (»freeing inode %lu\n», ino);

/*
* Note: we must free any quota before locking the superblock,
* as writing the quota to disk may need the lock as well.
*/
if (!is_bad_inode(inode)) {
/* Quota is already initialized in iput() */
ext2_xattr_delete_inode(inode);
vfs_dq_free_inode(inode);
vfs_dq_drop(inode);
}

es = EXT2_SB(sb)->s_es;
is_directory = S_ISDIR(inode->i_mode);

/* Do this BEFORE marking the inode not in use or returning an error */
clear_inode (inode);

if (ino < EXT2_FIRST_INO(sb) ||
ino > le32_to_cpu(es->s_inodes_count)) {
ext2_error (sb, «ext2_free_inode»,
«reserved or nonexistent inode %lu», ino);
goto error_return;
}
block_group = (ino – 1) / EXT2_INODES_PER_GROUP(sb);
bit = (ino – 1) % EXT2_INODES_PER_GROUP(sb);
brelse(bitmap_bh);
bitmap_bh = read_inode_bitmap(sb, block_group);
if (!bitmap_bh)
goto error_return;

/* Ok, now we can actually update the inode bitmaps.. */
if (!ext2_clear_bit_atomic(sb_bgl_lock(EXT2_SB(sb), block_group),
bit, (void *) bitmap_bh->b_data))
ext2_error (sb, «ext2_free_inode»,
«bit already cleared for inode %lu», ino);
else
ext2_release_inode(sb, block_group, is_directory);
mark_buffer_dirty(bitmap_bh);
if (sb->s_flags & MS_SYNCHRONOUS)
sync_dirty_buffer(bitmap_bh);
error_return:
brelse(bitmap_bh);
}

/*
* We perform asynchronous prereading of the new inode’s inode block when
* we create the inode, in the expectation that the inode will be written
* back soon. There are two reasons:
*
* – When creating a large number of files, the async prereads will be
* nicely merged into large reads
* – When writing out a large number of inodes, we don’t need to keep on
* stalling the writes while we read the inode block.
*
* FIXME: ext2_get_group_desc() needs to be simplified.
*/
static void ext2_preread_inode(struct inode *inode)
{
unsigned long block_group;
unsigned long offset;
unsigned long block;
struct ext2_group_desc * gdp;
struct backing_dev_info *bdi;

bdi = inode->i_mapping->backing_dev_info;
if (bdi_read_congested(bdi))
return;
if (bdi_write_congested(bdi))
return;

block_group = (inode->i_ino – 1) / EXT2_INODES_PER_GROUP(inode->i_sb);
gdp = ext2_get_group_desc(inode->i_sb, block_group, NULL);
if (gdp == NULL)
return;

/*
* Figure out the offset within the block group inode table
*/
offset = ((inode->i_ino – 1) % EXT2_INODES_PER_GROUP(inode->i_sb)) *
EXT2_INODE_SIZE(inode->i_sb);
block = le32_to_cpu(gdp->bg_inode_table) +
(offset >> EXT2_BLOCK_SIZE_BITS(inode->i_sb));
sb_breadahead(inode->i_sb, block);
}

/*
* There are two policies for allocating an inode. If the new inode is
* a directory, then a forward search is made for a block group with both
* free space and a low directory-to-inode ratio; if that fails, then of
* the groups with above-average free space, that group with the fewest
* directories already is chosen.
*
* For other inodes, search forward from the parent directory\’s block
* group to find a free inode.
*/
static int find_group_dir(struct super_block *sb, struct inode *parent)
{
int ngroups = EXT2_SB(sb)->s_groups_count;
int avefreei = ext2_count_free_inodes(sb) / ngroups;
struct ext2_group_desc *desc, *best_desc = NULL;
int group, best_group = -1;

for (group = 0; group < ngroups; group++) {
desc = ext2_get_group_desc (sb, group, NULL);
if (!desc || !desc->bg_free_inodes_count)
continue;
if (le16_to_cpu(desc->bg_free_inodes_count) < avefreei)
continue;
if (!best_desc ||
(le16_to_cpu(desc->bg_free_blocks_count) >
le16_to_cpu(best_desc->bg_free_blocks_count))) {
best_group = group;
best_desc = desc;
}
}
if (!best_desc)
return -1;

return best_group;
}

/*
* Orlov’s allocator for directories.
*
* We always try to spread first-level directories.
*
* If there are blockgroups with both free inodes and free blocks counts
* not worse than average we return one with smallest directory count.
* Otherwise we simply return a random group.
*
* For the rest rules look so:
*
* It’s OK to put directory into a group unless
* it has too many directories already (max_dirs) or
* it has too few free inodes left (min_inodes) or
* it has too few free blocks left (min_blocks) or
* it’s already running too large debt (max_debt).
* Parent’s group is preferred, if it doesn’t satisfy these
* conditions we search cyclically through the rest. If none
* of the groups look good we just look for a group with more
* free inodes than average (starting at parent’s group).
*
* Debt is incremented each time we allocate a directory and decremented
* when we allocate an inode, within 0–255.
*/

#define INODE_COST 64
#define BLOCK_COST 256

static int find_group_orlov(struct super_block *sb, struct inode *parent)
{
int parent_group = EXT2_I(parent)->i_block_group;
struct ext2_sb_info *sbi = EXT2_SB(sb);
struct ext2_super_block *es = sbi->s_es;
int ngroups = sbi->s_groups_count;
int inodes_per_group = EXT2_INODES_PER_GROUP(sb);
int freei;
int avefreei;
int free_blocks;
int avefreeb;
int blocks_per_dir;
int ndirs;
int max_debt, max_dirs, min_blocks, min_inodes;
int group = -1, i;
struct ext2_group_desc *desc;