linux/fs/ext3/dir.c

593 lines
15 KiB
C
Raw Normal View History

/*
* linux/fs/ext3/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
*
* ext3 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/compat.h>
#include "ext3.h"
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_dx_readdir(struct file * filp,
void * dirent, filldir_t filldir);
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]);
}
/**
* 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 (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)))
return 1;
return 0;
}
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 (unlikely(rlen < EXT3_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 < EXT3_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(EXT3_SB(dir->i_sb)->s_es->s_inodes_count)))
error_msg = "inode out of bounds";
if (unlikely(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;
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 = 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);
[PATCH] ext3_get_blocks: Mapping multiple blocks at a once Currently ext3_get_block() only maps or allocates one block at a time. This is quite inefficient for sequential IO workload. I have posted a early implements a simply multiple block map and allocation with current ext3. The basic idea is allocating the 1st block in the existing way, and attempting to allocate the next adjacent blocks on a best effort basis. More description about the implementation could be found here: http://marc.theaimsgroup.com/?l=ext2-devel&m=112162230003522&w=2 The following the latest version of the patch: break the original patch into 5 patches, re-worked some logicals, and fixed some bugs. The break ups are: [patch 1] Adding map multiple blocks at a time in ext3_get_blocks() [patch 2] Extend ext3_get_blocks() to support multiple block allocation [patch 3] Implement multiple block allocation in ext3-try-to-allocate (called via ext3_new_block()). [patch 4] Proper accounting updates in ext3_new_blocks() [patch 5] Adjust reservation window size properly (by the given number of blocks to allocate) before block allocation to increase the possibility of allocating multiple blocks in a single call. Tests done so far includes fsx,tiobench and dbench. The following numbers collected from Direct IO tests (1G file creation/read) shows the system time have been greatly reduced (more than 50% on my 8 cpu system) with the patches. 1G file DIO write: 2.6.15 2.6.15+patches real 0m31.275s 0m31.161s user 0m0.000s 0m0.000s sys 0m3.384s 0m0.564s 1G file DIO read: 2.6.15 2.6.15+patches real 0m30.733s 0m30.624s user 0m0.000s 0m0.004s sys 0m0.748s 0m0.380s Some previous test we did on buffered IO with using multiple blocks allocation and delayed allocation shows noticeable improvement on throughput and system time. This patch: Add support of mapping multiple blocks in one call. This is useful for DIO reads and re-writes (where blocks are already allocated), also is in line with Christoph's proposal of using getblocks() in mpage_readpage() or mpage_readpages(). Signed-off-by: Mingming Cao <cmm@us.ibm.com> Cc: Badari Pulavarty <pbadari@us.ibm.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-03-26 09:37:55 +00:00
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;
}
[PATCH] handle ext3 directory corruption better I've been using Steve Grubb's purely evil "fsfuzzer" tool, at http://people.redhat.com/sgrubb/files/fsfuzzer-0.4.tar.gz Basically it makes a filesystem, splats some random bits over it, then tries to mount it and do some simple filesystem actions. At best, the filesystem catches the corruption gracefully. At worst, things spin out of control. As you might guess, we found a couple places in ext3 where things spin out of control :) First, we had a corrupted directory that was never checked for consistency... it was corrupt, and pointed to another bad "entry" of length 0. The for() loop looped forever, since the length of ext3_next_entry(de) was 0, and we kept looking at the same pointer over and over and over and over... I modeled this check and subsequent action on what is done for other directory types in ext3_readdir... (adding this check adds some computational expense; I am testing a followup patch to reduce the number of times we check and re-check these directory entries, in all cases. Thanks for the idea, Andreas). Next we had a root directory inode which had a corrupted size, claimed to be > 200M on a 4M filesystem. There was only really 1 block in the directory, but because the size was so large, readdir kept coming back for more, spewing thousands of printk's along the way. Per Andreas' suggestion, if we're in this read error condition and we're trying to read an offset which is greater than i_blocks worth of bytes, stop trying, and break out of the loop. With these two changes fsfuzz test survives quite well on ext3. Signed-off-by: Eric Sandeen <sandeen@redhat.com> Cc: <linux-ext4@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-12-07 04:36:26 +00:00
/* 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;
}
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 ext3 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 ext3_get_htree_eof(struct file *filp)
{
if ((filp->f_mode & FMODE_32BITHASH) ||
(!(filp->f_mode & FMODE_64BITHASH) && is_32bit_api()))
return EXT3_HTREE_EOF_32BIT;
else
return EXT3_HTREE_EOF_64BIT;
}
/*
* ext3_dir_llseek() calls generic_file_llseek[_size]() to handle both
* non-htree and htree directories, where the "offset" is in terms
* of the filename hash value instead of the byte offset.
*
* Because we may return a 64-bit hash that is well beyond s_maxbytes,
* we need to pass the max hash as the maximum allowable offset in
* the htree directory case.
*
* NOTE: offsets obtained *before* ext3_set_inode_flag(dir, EXT3_INODE_INDEX)
* will be invalid once the directory was converted into a dx directory
*/
loff_t ext3_dir_llseek(struct file *file, loff_t offset, int origin)
{
struct inode *inode = file->f_mapping->host;
int dx_dir = is_dx_dir(inode);
loff_t htree_max = ext3_get_htree_eof(file);
if (likely(dx_dir))
return generic_file_llseek_size(file, offset, origin,
htree_max, htree_max);
else
return generic_file_llseek(file, offset, origin);
}
/*
* 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 *ext3_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 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(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 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, filp->f_pos);
if (!info)
return -ENOMEM;
filp->private_data = info;
}
if (filp->f_pos == ext3_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 = 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_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 = ext3_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 ext3_release_dir (struct inode * inode, struct file * filp)
{
if (filp->private_data)
ext3_htree_free_dir_info(filp->private_data);
return 0;
}
const struct file_operations ext3_dir_operations = {
.llseek = ext3_dir_llseek,
.read = generic_read_dir,
.readdir = ext3_readdir,
.unlocked_ioctl = ext3_ioctl,
#ifdef CONFIG_COMPAT
.compat_ioctl = ext3_compat_ioctl,
#endif
.fsync = ext3_sync_file,
.release = ext3_release_dir,
};