#include <linux/quotaops.h>
#include <linux/buffer_head.h>
#include <linux/bio.h>
-#include <linux/smp_lock.h>
#include "namei.h"
#include "xattr.h"
struct dx_map_entry
{
u32 hash;
- u32 offs;
+ u16 offs;
+ u16 size;
};
-#ifdef CONFIG_EXT3_INDEX
static inline unsigned dx_get_block (struct dx_entry *entry);
static void dx_set_block (struct dx_entry *entry, unsigned value);
static inline unsigned dx_get_hash (struct dx_entry *entry);
entries = (struct dx_entry *) (((char *)&root->info) +
root->info.info_length);
- assert(dx_get_limit(entries) == dx_root_limit(dir,
- root->info.info_length));
+
+ if (dx_get_limit(entries) != dx_root_limit(dir,
+ root->info.info_length)) {
+ ext3_warning(dir->i_sb, __FUNCTION__,
+ "dx entry: limit != root limit");
+ brelse(bh);
+ *err = ERR_BAD_DX_DIR;
+ goto fail;
+ }
+
dxtrace (printk("Look up %x", hash));
while (1)
{
count = dx_get_count(entries);
- assert (count && count <= dx_get_limit(entries));
+ if (!count || count > dx_get_limit(entries)) {
+ ext3_warning(dir->i_sb, __FUNCTION__,
+ "dx entry: no count or count > limit");
+ brelse(bh);
+ *err = ERR_BAD_DX_DIR;
+ goto fail2;
+ }
+
p = entries + 1;
q = entries + count - 1;
while (p <= q)
if (!(bh = ext3_bread (NULL,dir, dx_get_block(at), 0, err)))
goto fail2;
at = entries = ((struct dx_node *) bh->b_data)->entries;
- assert (dx_get_limit(entries) == dx_node_limit (dir));
+ if (dx_get_limit(entries) != dx_node_limit (dir)) {
+ ext3_warning(dir->i_sb, __FUNCTION__,
+ "dx entry: limit != node limit");
+ brelse(bh);
+ *err = ERR_BAD_DX_DIR;
+ goto fail2;
+ }
frame++;
+ frame->bh = NULL;
}
fail2:
while (frame >= frame_in) {
frame--;
}
fail:
+ if (*err == ERR_BAD_DX_DIR)
+ ext3_warning(dir->i_sb, __FUNCTION__,
+ "Corrupt dir inode %ld, running e2fsck is "
+ "recommended.", dir->i_ino);
return NULL;
}
* Directory block splitting, compacting
*/
+/*
+ * Create map of hash values, offsets, and sizes, stored at end of block.
+ * Returns number of entries mapped.
+ */
static int dx_make_map (struct ext3_dir_entry_2 *de, int size,
struct dx_hash_info *hinfo, struct dx_map_entry *map_tail)
{
ext3fs_dirhash(de->name, de->name_len, &h);
map_tail--;
map_tail->hash = h.hash;
- map_tail->offs = (u32) ((char *) de - base);
+ map_tail->offs = (u16) ((char *) de - base);
+ map_tail->size = le16_to_cpu(de->rec_len);
count++;
cond_resched();
}
return count;
}
+/* Sort map by hash value */
static void dx_sort_map (struct dx_map_entry *map, unsigned count)
{
struct dx_map_entry *p, *q, *top = map + count - 1;
dx_set_block(new, block);
dx_set_count(entries, count + 1);
}
-#endif
-
static void ext3_update_dx_flag(struct inode *inode)
{
name = dentry->d_name.name;
if (namelen > EXT3_NAME_LEN)
return NULL;
-#ifdef CONFIG_EXT3_INDEX
if (is_dx(dir)) {
bh = ext3_dx_find_entry(dentry, res_dir, &err);
/*
return bh;
dxtrace(printk("ext3_find_entry: dx failed, falling back\n"));
}
-#endif
nblocks = dir->i_size >> EXT3_BLOCK_SIZE_BITS(sb);
start = EXT3_I(dir)->i_dir_start_lookup;
if (start >= nblocks)
return ret;
}
-#ifdef CONFIG_EXT3_INDEX
static struct buffer_head * ext3_dx_find_entry(struct dentry *dentry,
struct ext3_dir_entry_2 **res_dir, int *err)
{
(block<<EXT3_BLOCK_SIZE_BITS(sb))
+((char *)de - bh->b_data))) {
brelse (bh);
+ *err = ERR_BAD_DX_DIR;
goto errout;
}
*res_dir = de;
dx_release (frames);
return NULL;
}
-#endif
static struct dentry *ext3_lookup(struct inode * dir, struct dentry *dentry, struct nameidata *nd)
{
if (!inode)
return ERR_PTR(-EACCES);
+
+ if (is_bad_inode(inode)) {
+ iput(inode);
+ return ERR_PTR(-ENOENT);
+ }
}
return d_splice_alias(inode, dentry);
}
if (!inode)
return ERR_PTR(-EACCES);
+ if (is_bad_inode(inode)) {
+ iput(inode);
+ return ERR_PTR(-ENOENT);
+ }
+
parent = d_alloc_anon(inode);
if (!parent) {
iput(inode);
de->file_type = ext3_type_by_mode[(mode & S_IFMT)>>S_SHIFT];
}
-#ifdef CONFIG_EXT3_INDEX
+/*
+ * Move count entries from end of map between two memory locations.
+ * Returns pointer to last entry moved.
+ */
static struct ext3_dir_entry_2 *
dx_move_dirents(char *from, char *to, struct dx_map_entry *map, int count)
{
return (struct ext3_dir_entry_2 *) (to - rec_len);
}
+/*
+ * Compact each dir entry in the range to the minimal rec_len.
+ * Returns pointer to last entry in range.
+ */
static struct ext3_dir_entry_2* dx_pack_dirents(char *base, int size)
{
struct ext3_dir_entry_2 *next, *to, *prev, *de = (struct ext3_dir_entry_2 *) base;
return prev;
}
+/*
+ * Split a full leaf block to make room for a new dir entry.
+ * Allocate a new block, and move entries so that they are approx. equally full.
+ * Returns pointer to de in block into which the new entry will be inserted.
+ */
static struct ext3_dir_entry_2 *do_split(handle_t *handle, struct inode *dir,
struct buffer_head **bh,struct dx_frame *frame,
struct dx_hash_info *hinfo, int *error)
u32 hash2;
struct dx_map_entry *map;
char *data1 = (*bh)->b_data, *data2;
- unsigned split;
+ unsigned split, move, size, i;
struct ext3_dir_entry_2 *de = NULL, *de2;
- int err;
+ int err = 0;
- bh2 = ext3_append (handle, dir, &newblock, error);
+ bh2 = ext3_append (handle, dir, &newblock, &err);
if (!(bh2)) {
brelse(*bh);
*bh = NULL;
BUFFER_TRACE(*bh, "get_write_access");
err = ext3_journal_get_write_access(handle, *bh);
- if (err) {
- journal_error:
- brelse(*bh);
- brelse(bh2);
- *bh = NULL;
- ext3_std_error(dir->i_sb, err);
- goto errout;
- }
+ if (err)
+ goto journal_error;
+
BUFFER_TRACE(frame->bh, "get_write_access");
err = ext3_journal_get_write_access(handle, frame->bh);
if (err)
count = dx_make_map ((struct ext3_dir_entry_2 *) data1,
blocksize, hinfo, map);
map -= count;
- split = count/2; // need to adjust to actual middle
dx_sort_map (map, count);
+ /* Split the existing block in the middle, size-wise */
+ size = 0;
+ move = 0;
+ for (i = count-1; i >= 0; i--) {
+ /* is more than half of this entry in 2nd half of the block? */
+ if (size + map[i].size/2 > blocksize/2)
+ break;
+ size += map[i].size;
+ move++;
+ }
+ /* map index at which we will split */
+ split = count - move;
hash2 = map[split].hash;
continued = hash2 == map[split - 1].hash;
dxtrace(printk("Split block %i at %x, %i/%i\n",
goto journal_error;
brelse (bh2);
dxtrace(dx_show_index ("frame", frame->entries));
-errout:
return de;
+
+journal_error:
+ brelse(*bh);
+ brelse(bh2);
+ *bh = NULL;
+ ext3_std_error(dir->i_sb, err);
+errout:
+ *error = err;
+ return NULL;
}
-#endif
/*
return 0;
}
-#ifdef CONFIG_EXT3_INDEX
/*
* This converts a one block unindexed directory to a 3 block indexed
* directory, and adds the dentry to the indexed directory.
return add_dirent_to_buf(handle, dentry, inode, de, bh);
}
-#endif
/*
* ext3_add_entry()
struct ext3_dir_entry_2 *de;
struct super_block * sb;
int retval;
-#ifdef CONFIG_EXT3_INDEX
int dx_fallback=0;
-#endif
unsigned blocksize;
u32 block, blocks;
blocksize = sb->s_blocksize;
if (!dentry->d_name.len)
return -EINVAL;
-#ifdef CONFIG_EXT3_INDEX
if (is_dx(dir)) {
retval = ext3_dx_add_entry(handle, dentry, inode);
if (!retval || (retval != ERR_BAD_DX_DIR))
dx_fallback++;
ext3_mark_inode_dirty(handle, dir);
}
-#endif
blocks = dir->i_size >> sb->s_blocksize_bits;
for (block = 0, offset = 0; block < blocks; block++) {
bh = ext3_bread(handle, dir, block, 0, &retval);
if (retval != -ENOSPC)
return retval;
-#ifdef CONFIG_EXT3_INDEX
if (blocks == 1 && !dx_fallback &&
EXT3_HAS_COMPAT_FEATURE(sb, EXT3_FEATURE_COMPAT_DIR_INDEX))
return make_indexed_dir(handle, dentry, inode, bh);
-#endif
brelse(bh);
}
bh = ext3_append(handle, dir, &block, &retval);
return add_dirent_to_buf(handle, dentry, inode, de, bh);
}
-#ifdef CONFIG_EXT3_INDEX
/*
* Returns 0 for success, or a negative error value
*/
dx_release(frames);
return err;
}
-#endif
/*
* ext3_delete_entry deletes a directory entry by merging it with the
return -ENOENT;
}
-/*
- * ext3_mark_inode_dirty is somewhat expensive, so unlike ext2 we
- * do not perform it in these functions. We perform it at the call site,
- * if it is needed.
- */
-static inline void ext3_inc_count(handle_t *handle, struct inode *inode)
-{
- inc_nlink(inode);
-}
-
-static inline void ext3_dec_count(handle_t *handle, struct inode *inode)
-{
- drop_nlink(inode);
-}
-
static int ext3_add_nondir(handle_t *handle,
struct dentry *dentry, struct inode *inode)
{
d_instantiate(dentry, inode);
return 0;
}
- ext3_dec_count(handle, inode);
+ drop_nlink(inode);
iput(inode);
return err;
}
err = __page_symlink(inode, symname, l,
mapping_gfp_mask(inode->i_mapping) & ~__GFP_FS);
if (err) {
- ext3_dec_count(handle, inode);
+ drop_nlink(inode);
ext3_mark_inode_dirty(handle, inode);
iput (inode);
goto out_stop;
if (inode->i_nlink >= EXT3_LINK_MAX)
return -EMLINK;
+ /*
+ * Return -ENOENT if we've raced with unlink and i_nlink is 0. Doing
+ * otherwise has the potential to corrupt the orphan inode list.
+ */
+ if (inode->i_nlink == 0)
+ return -ENOENT;
retry:
handle = ext3_journal_start(dir, EXT3_DATA_TRANS_BLOCKS(dir->i_sb) +
handle->h_sync = 1;
inode->i_ctime = CURRENT_TIME_SEC;
- ext3_inc_count(handle, inode);
+ inc_nlink(inode);
atomic_inc(&inode->i_count);
err = ext3_add_nondir(handle, dentry, inode);
/*
* directories can handle most operations...
*/
-struct inode_operations ext3_dir_inode_operations = {
+const struct inode_operations ext3_dir_inode_operations = {
.create = ext3_create,
.lookup = ext3_lookup,
.link = ext3_link,
.permission = ext3_permission,
};
-struct inode_operations ext3_special_inode_operations = {
+const struct inode_operations ext3_special_inode_operations = {
.setattr = ext3_setattr,
#ifdef CONFIG_EXT3_FS_XATTR
.setxattr = generic_setxattr,