mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git
synced 2024-09-12 05:48:40 +00:00
![Linus Torvalds](/assets/img/avatar_default.png)
Pull nfsd changes from Bruce Fields: Highlights: - Benny Halevy and Tigran Mkrtchyan implemented some more 4.1 features, moving us closer to a complete 4.1 implementation. - Bernd Schubert fixed a long-standing problem with readdir cookies on ext2/3/4. - Jeff Layton performed a long-overdue overhaul of the server reboot recovery code which will allow us to deprecate the current code (a rather unusual user of the vfs), and give us some needed flexibility for further improvements. - Like the client, we now support numeric uid's and gid's in the auth_sys case, allowing easier upgrades from NFSv2/v3 to v4.x. Plus miscellaneous bugfixes and cleanup. Thanks to everyone! There are also some delegation fixes waiting on vfs review that I suppose will have to wait for 3.5. With that done I think we'll finally turn off the "EXPERIMENTAL" dependency for v4 (though that's mostly symbolic as it's been on by default in distro's for a while). And the list of 4.1 todo's should be achievable for 3.5 as well: http://wiki.linux-nfs.org/wiki/index.php/Server_4.0_and_4.1_issues though we may still want a bit more experience with it before turning it on by default. * 'for-3.4' of git://linux-nfs.org/~bfields/linux: (55 commits) nfsd: only register cld pipe notifier when CONFIG_NFSD_V4 is enabled nfsd4: use auth_unix unconditionally on backchannel nfsd: fix NULL pointer dereference in cld_pipe_downcall nfsd4: memory corruption in numeric_name_to_id() sunrpc: skip portmap calls on sessions backchannel nfsd4: allow numeric idmapping nfsd: don't allow legacy client tracker init for anything but init_net nfsd: add notifier to handle mount/unmount of rpc_pipefs sb nfsd: add the infrastructure to handle the cld upcall nfsd: add a header describing upcall to nfsdcld nfsd: add a per-net-namespace struct for nfsd sunrpc: create nfsd dir in rpc_pipefs nfsd: add nfsd4_client_tracking_ops struct and a way to set it nfsd: convert nfs4_client->cl_cb_flags to a generic flags field NFSD: Fix nfs4_verifier memory alignment NFSD: Fix warnings when NFSD_DEBUG is not defined nfsd: vfs_llseek() with 32 or 64 bit offsets (hashes) nfsd: rename 'int access' to 'int may_flags' in nfsd_open() ext4: return 32/64-bit dir name hash according to usage type fs: add new FMODE flags: FMODE_32bithash and FMODE_64bithash ...
667 lines
17 KiB
C
667 lines
17 KiB
C
/*
|
|
* linux/fs/ext4/dir.c
|
|
*
|
|
* Copyright (C) 1992, 1993, 1994, 1995
|
|
* Remy Card (card@masi.ibp.fr)
|
|
* Laboratoire MASI - Institut Blaise Pascal
|
|
* Universite Pierre et Marie Curie (Paris VI)
|
|
*
|
|
* from
|
|
*
|
|
* linux/fs/minix/dir.c
|
|
*
|
|
* Copyright (C) 1991, 1992 Linus Torvalds
|
|
*
|
|
* ext4 directory handling functions
|
|
*
|
|
* Big-endian to little-endian byte-swapping/bitmaps by
|
|
* David S. Miller (davem@caip.rutgers.edu), 1995
|
|
*
|
|
* Hash Tree Directory indexing (c) 2001 Daniel Phillips
|
|
*
|
|
*/
|
|
|
|
#include <linux/fs.h>
|
|
#include <linux/jbd2.h>
|
|
#include <linux/buffer_head.h>
|
|
#include <linux/slab.h>
|
|
#include <linux/rbtree.h>
|
|
#include "ext4.h"
|
|
|
|
static unsigned char ext4_filetype_table[] = {
|
|
DT_UNKNOWN, DT_REG, DT_DIR, DT_CHR, DT_BLK, DT_FIFO, DT_SOCK, DT_LNK
|
|
};
|
|
|
|
static int ext4_dx_readdir(struct file *filp,
|
|
void *dirent, filldir_t filldir);
|
|
|
|
static unsigned char get_dtype(struct super_block *sb, int filetype)
|
|
{
|
|
if (!EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_FILETYPE) ||
|
|
(filetype >= EXT4_FT_MAX))
|
|
return DT_UNKNOWN;
|
|
|
|
return (ext4_filetype_table[filetype]);
|
|
}
|
|
|
|
/**
|
|
* Check if the given dir-inode refers to an htree-indexed directory
|
|
* (or a directory which chould potentially get coverted to use htree
|
|
* indexing).
|
|
*
|
|
* Return 1 if it is a dx dir, 0 if not
|
|
*/
|
|
static int is_dx_dir(struct inode *inode)
|
|
{
|
|
struct super_block *sb = inode->i_sb;
|
|
|
|
if (EXT4_HAS_COMPAT_FEATURE(inode->i_sb,
|
|
EXT4_FEATURE_COMPAT_DIR_INDEX) &&
|
|
((ext4_test_inode_flag(inode, EXT4_INODE_INDEX)) ||
|
|
((inode->i_size >> sb->s_blocksize_bits) == 1)))
|
|
return 1;
|
|
|
|
return 0;
|
|
}
|
|
|
|
/*
|
|
* Return 0 if the directory entry is OK, and 1 if there is a problem
|
|
*
|
|
* Note: this is the opposite of what ext2 and ext3 historically returned...
|
|
*/
|
|
int __ext4_check_dir_entry(const char *function, unsigned int line,
|
|
struct inode *dir, struct file *filp,
|
|
struct ext4_dir_entry_2 *de,
|
|
struct buffer_head *bh,
|
|
unsigned int offset)
|
|
{
|
|
const char *error_msg = NULL;
|
|
const int rlen = ext4_rec_len_from_disk(de->rec_len,
|
|
dir->i_sb->s_blocksize);
|
|
|
|
if (unlikely(rlen < EXT4_DIR_REC_LEN(1)))
|
|
error_msg = "rec_len is smaller than minimal";
|
|
else if (unlikely(rlen % 4 != 0))
|
|
error_msg = "rec_len % 4 != 0";
|
|
else if (unlikely(rlen < EXT4_DIR_REC_LEN(de->name_len)))
|
|
error_msg = "rec_len is too small for name_len";
|
|
else if (unlikely(((char *) de - bh->b_data) + rlen >
|
|
dir->i_sb->s_blocksize))
|
|
error_msg = "directory entry across blocks";
|
|
else if (unlikely(le32_to_cpu(de->inode) >
|
|
le32_to_cpu(EXT4_SB(dir->i_sb)->s_es->s_inodes_count)))
|
|
error_msg = "inode out of bounds";
|
|
else
|
|
return 0;
|
|
|
|
if (filp)
|
|
ext4_error_file(filp, function, line, bh->b_blocknr,
|
|
"bad entry in directory: %s - offset=%u(%u), "
|
|
"inode=%u, rec_len=%d, name_len=%d",
|
|
error_msg, (unsigned) (offset % bh->b_size),
|
|
offset, le32_to_cpu(de->inode),
|
|
rlen, de->name_len);
|
|
else
|
|
ext4_error_inode(dir, function, line, bh->b_blocknr,
|
|
"bad entry in directory: %s - offset=%u(%u), "
|
|
"inode=%u, rec_len=%d, name_len=%d",
|
|
error_msg, (unsigned) (offset % bh->b_size),
|
|
offset, le32_to_cpu(de->inode),
|
|
rlen, de->name_len);
|
|
|
|
return 1;
|
|
}
|
|
|
|
static int ext4_readdir(struct file *filp,
|
|
void *dirent, filldir_t filldir)
|
|
{
|
|
int error = 0;
|
|
unsigned int offset;
|
|
int i, stored;
|
|
struct ext4_dir_entry_2 *de;
|
|
int err;
|
|
struct inode *inode = filp->f_path.dentry->d_inode;
|
|
struct super_block *sb = inode->i_sb;
|
|
int ret = 0;
|
|
int dir_has_error = 0;
|
|
|
|
if (is_dx_dir(inode)) {
|
|
err = ext4_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.
|
|
*/
|
|
ext4_clear_inode_flag(filp->f_path.dentry->d_inode,
|
|
EXT4_INODE_INDEX);
|
|
}
|
|
stored = 0;
|
|
offset = filp->f_pos & (sb->s_blocksize - 1);
|
|
|
|
while (!error && !stored && filp->f_pos < inode->i_size) {
|
|
struct ext4_map_blocks map;
|
|
struct buffer_head *bh = NULL;
|
|
|
|
map.m_lblk = filp->f_pos >> EXT4_BLOCK_SIZE_BITS(sb);
|
|
map.m_len = 1;
|
|
err = ext4_map_blocks(NULL, inode, &map, 0);
|
|
if (err > 0) {
|
|
pgoff_t index = map.m_pblk >>
|
|
(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 = ext4_bread(NULL, inode, map.m_lblk, 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) {
|
|
EXT4_ERROR_FILE(filp, 0,
|
|
"directory contains a "
|
|
"hole at offset %llu",
|
|
(unsigned long long) 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 ext4_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 (ext4_rec_len_from_disk(de->rec_len,
|
|
sb->s_blocksize) < EXT4_DIR_REC_LEN(1))
|
|
break;
|
|
i += ext4_rec_len_from_disk(de->rec_len,
|
|
sb->s_blocksize);
|
|
}
|
|
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 ext4_dir_entry_2 *) (bh->b_data + offset);
|
|
if (ext4_check_dir_entry(inode, filp, 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 += ext4_rec_len_from_disk(de->rec_len,
|
|
sb->s_blocksize);
|
|
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 += ext4_rec_len_from_disk(de->rec_len,
|
|
sb->s_blocksize);
|
|
}
|
|
offset = 0;
|
|
brelse(bh);
|
|
}
|
|
out:
|
|
return ret;
|
|
}
|
|
|
|
static inline int is_32bit_api(void)
|
|
{
|
|
#ifdef CONFIG_COMPAT
|
|
return is_compat_task();
|
|
#else
|
|
return (BITS_PER_LONG == 32);
|
|
#endif
|
|
}
|
|
|
|
/*
|
|
* These functions convert from the major/minor hash to an f_pos
|
|
* value for dx directories
|
|
*
|
|
* Upper layer (for example NFS) should specify FMODE_32BITHASH or
|
|
* FMODE_64BITHASH explicitly. On the other hand, we allow ext4 to be mounted
|
|
* directly on both 32-bit and 64-bit nodes, under such case, neither
|
|
* FMODE_32BITHASH nor FMODE_64BITHASH is specified.
|
|
*/
|
|
static inline loff_t hash2pos(struct file *filp, __u32 major, __u32 minor)
|
|
{
|
|
if ((filp->f_mode & FMODE_32BITHASH) ||
|
|
(!(filp->f_mode & FMODE_64BITHASH) && is_32bit_api()))
|
|
return major >> 1;
|
|
else
|
|
return ((__u64)(major >> 1) << 32) | (__u64)minor;
|
|
}
|
|
|
|
static inline __u32 pos2maj_hash(struct file *filp, loff_t pos)
|
|
{
|
|
if ((filp->f_mode & FMODE_32BITHASH) ||
|
|
(!(filp->f_mode & FMODE_64BITHASH) && is_32bit_api()))
|
|
return (pos << 1) & 0xffffffff;
|
|
else
|
|
return ((pos >> 32) << 1) & 0xffffffff;
|
|
}
|
|
|
|
static inline __u32 pos2min_hash(struct file *filp, loff_t pos)
|
|
{
|
|
if ((filp->f_mode & FMODE_32BITHASH) ||
|
|
(!(filp->f_mode & FMODE_64BITHASH) && is_32bit_api()))
|
|
return 0;
|
|
else
|
|
return pos & 0xffffffff;
|
|
}
|
|
|
|
/*
|
|
* Return 32- or 64-bit end-of-file for dx directories
|
|
*/
|
|
static inline loff_t ext4_get_htree_eof(struct file *filp)
|
|
{
|
|
if ((filp->f_mode & FMODE_32BITHASH) ||
|
|
(!(filp->f_mode & FMODE_64BITHASH) && is_32bit_api()))
|
|
return EXT4_HTREE_EOF_32BIT;
|
|
else
|
|
return EXT4_HTREE_EOF_64BIT;
|
|
}
|
|
|
|
|
|
/*
|
|
* ext4_dir_llseek() based on generic_file_llseek() to handle both
|
|
* non-htree and htree directories, where the "offset" is in terms
|
|
* of the filename hash value instead of the byte offset.
|
|
*
|
|
* NOTE: offsets obtained *before* ext4_set_inode_flag(dir, EXT4_INODE_INDEX)
|
|
* will be invalid once the directory was converted into a dx directory
|
|
*/
|
|
loff_t ext4_dir_llseek(struct file *file, loff_t offset, int origin)
|
|
{
|
|
struct inode *inode = file->f_mapping->host;
|
|
loff_t ret = -EINVAL;
|
|
int dx_dir = is_dx_dir(inode);
|
|
|
|
mutex_lock(&inode->i_mutex);
|
|
|
|
/* NOTE: relative offsets with dx directories might not work
|
|
* as expected, as it is difficult to figure out the
|
|
* correct offset between dx hashes */
|
|
|
|
switch (origin) {
|
|
case SEEK_END:
|
|
if (unlikely(offset > 0))
|
|
goto out_err; /* not supported for directories */
|
|
|
|
/* so only negative offsets are left, does that have a
|
|
* meaning for directories at all? */
|
|
if (dx_dir)
|
|
offset += ext4_get_htree_eof(file);
|
|
else
|
|
offset += inode->i_size;
|
|
break;
|
|
case SEEK_CUR:
|
|
/*
|
|
* Here we special-case the lseek(fd, 0, SEEK_CUR)
|
|
* position-querying operation. Avoid rewriting the "same"
|
|
* f_pos value back to the file because a concurrent read(),
|
|
* write() or lseek() might have altered it
|
|
*/
|
|
if (offset == 0) {
|
|
offset = file->f_pos;
|
|
goto out_ok;
|
|
}
|
|
|
|
offset += file->f_pos;
|
|
break;
|
|
}
|
|
|
|
if (unlikely(offset < 0))
|
|
goto out_err;
|
|
|
|
if (!dx_dir) {
|
|
if (offset > inode->i_sb->s_maxbytes)
|
|
goto out_err;
|
|
} else if (offset > ext4_get_htree_eof(file))
|
|
goto out_err;
|
|
|
|
/* Special lock needed here? */
|
|
if (offset != file->f_pos) {
|
|
file->f_pos = offset;
|
|
file->f_version = 0;
|
|
}
|
|
|
|
out_ok:
|
|
ret = offset;
|
|
out_err:
|
|
mutex_unlock(&inode->i_mutex);
|
|
|
|
return ret;
|
|
}
|
|
|
|
/*
|
|
* 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_ROOT;
|
|
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 *ext4_htree_create_dir_info(struct file *filp,
|
|
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(filp, pos);
|
|
p->curr_minor_hash = pos2min_hash(filp, pos);
|
|
return p;
|
|
}
|
|
|
|
void ext4_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 ext4_htree_store_dirent(struct file *dir_file, __u32 hash,
|
|
__u32 minor_hash,
|
|
struct ext4_dir_entry_2 *dirent)
|
|
{
|
|
struct rb_node **p, *parent = NULL;
|
|
struct fname *fname, *new_fn;
|
|
struct dir_private_info *info;
|
|
int len;
|
|
|
|
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 ext4_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) {
|
|
ext4_msg(sb, KERN_ERR, "%s:%d: inode #%lu: comm %s: "
|
|
"called with null fname?!?", __func__, __LINE__,
|
|
inode->i_ino, current->comm);
|
|
return 0;
|
|
}
|
|
curr_pos = hash2pos(filp, 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 ext4_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 = ext4_htree_create_dir_info(filp, filp->f_pos);
|
|
if (!info)
|
|
return -ENOMEM;
|
|
filp->private_data = info;
|
|
}
|
|
|
|
if (filp->f_pos == ext4_get_htree_eof(filp))
|
|
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, filp->f_pos);
|
|
info->curr_minor_hash = pos2min_hash(filp, 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 = ext4_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 = ext4_get_htree_eof(filp);
|
|
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 = ext4_get_htree_eof(filp);
|
|
break;
|
|
}
|
|
info->curr_hash = info->next_hash;
|
|
info->curr_minor_hash = 0;
|
|
}
|
|
}
|
|
finished:
|
|
info->last_pos = filp->f_pos;
|
|
return 0;
|
|
}
|
|
|
|
static int ext4_release_dir(struct inode *inode, struct file *filp)
|
|
{
|
|
if (filp->private_data)
|
|
ext4_htree_free_dir_info(filp->private_data);
|
|
|
|
return 0;
|
|
}
|
|
|
|
const struct file_operations ext4_dir_operations = {
|
|
.llseek = ext4_dir_llseek,
|
|
.read = generic_read_dir,
|
|
.readdir = ext4_readdir,
|
|
.unlocked_ioctl = ext4_ioctl,
|
|
#ifdef CONFIG_COMPAT
|
|
.compat_ioctl = ext4_compat_ioctl,
|
|
#endif
|
|
.fsync = ext4_sync_file,
|
|
.release = ext4_release_dir,
|
|
};
|