summaryrefslogtreecommitdiff
path: root/fs/ocfs2/dir.c
diff options
context:
space:
mode:
Diffstat (limited to 'fs/ocfs2/dir.c')
-rw-r--r--fs/ocfs2/dir.c229
1 files changed, 127 insertions, 102 deletions
diff --git a/fs/ocfs2/dir.c b/fs/ocfs2/dir.c
index c121abbdfc7d..2785ff245e79 100644
--- a/fs/ocfs2/dir.c
+++ b/fs/ocfs2/dir.c
@@ -1,6 +1,5 @@
-/* -*- mode: c; c-basic-offset: 8; -*-
- * vim: noexpandtab sw=8 ts=8 sts=0:
- *
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
* dir.c
*
* Creates, reads, walks and deletes directory-nodes
@@ -19,21 +18,6 @@
* linux/fs/minix/dir.c
*
* Copyright (C) 1991, 1992 Linus Torvalds
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public
- * License as published by the Free Software Foundation; either
- * version 2 of the License, or (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- * General Public License for more details.
- *
- * You should have received a copy of the GNU General Public
- * License along with this program; if not, write to the
- * Free Software Foundation, Inc., 59 Temple Place - Suite 330,
- * Boston, MA 021110-1307, USA.
*/
#include <linux/fs.h>
@@ -69,10 +53,6 @@
#define NAMEI_RA_BLOCKS 4
#define NAMEI_RA_SIZE (NAMEI_RA_CHUNKS * NAMEI_RA_BLOCKS)
-static unsigned char ocfs2_filetype_table[] = {
- DT_UNKNOWN, DT_REG, DT_DIR, DT_CHR, DT_BLK, DT_FIFO, DT_SOCK, DT_LNK
-};
-
static int ocfs2_do_extend_dir(struct super_block *sb,
handle_t *handle,
struct inode *dir,
@@ -314,13 +294,29 @@ out:
* bh passed here can be an inode block or a dir data block, depending
* on the inode inline data flag.
*/
-static int ocfs2_check_dir_entry(struct inode * dir,
- struct ocfs2_dir_entry * de,
- struct buffer_head * bh,
+static int ocfs2_check_dir_entry(struct inode *dir,
+ struct ocfs2_dir_entry *de,
+ struct buffer_head *bh,
+ char *buf,
+ unsigned int size,
unsigned long offset)
{
const char *error_msg = NULL;
- const int rlen = le16_to_cpu(de->rec_len);
+ unsigned long next_offset;
+ int rlen;
+
+ if (offset > size - OCFS2_DIR_REC_LEN(1)) {
+ /* Dirent is (maybe partially) beyond the buffer
+ * boundaries so touching 'de' members is unsafe.
+ */
+ mlog(ML_ERROR, "directory entry (#%llu: offset=%lu) "
+ "too close to end or out-of-bounds",
+ (unsigned long long)OCFS2_I(dir)->ip_blkno, offset);
+ return 0;
+ }
+
+ rlen = le16_to_cpu(de->rec_len);
+ next_offset = ((char *) de - buf) + rlen;
if (unlikely(rlen < OCFS2_DIR_REC_LEN(1)))
error_msg = "rec_len is smaller than minimal";
@@ -328,9 +324,11 @@ static int ocfs2_check_dir_entry(struct inode * dir,
error_msg = "rec_len % 4 != 0";
else if (unlikely(rlen < OCFS2_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(next_offset > size))
+ error_msg = "directory entry overrun";
+ else if (unlikely(next_offset > size - OCFS2_DIR_REC_LEN(1)) &&
+ next_offset != size)
+ error_msg = "directory entry too close to end";
if (unlikely(error_msg != NULL))
mlog(ML_ERROR, "bad entry in directory #%llu: %s - "
@@ -372,16 +370,17 @@ static inline int ocfs2_search_dirblock(struct buffer_head *bh,
de_buf = first_de;
dlimit = de_buf + bytes;
- while (de_buf < dlimit) {
+ while (de_buf < dlimit - OCFS2_DIR_MEMBER_LEN) {
/* this code is executed quadratically often */
/* do minimal checking `by hand' */
de = (struct ocfs2_dir_entry *) de_buf;
- if (de_buf + namelen <= dlimit &&
+ if (de->name + namelen <= dlimit &&
ocfs2_match(namelen, name, de)) {
/* found a match - just to be sure, do a full check */
- if (!ocfs2_check_dir_entry(dir, de, bh, offset)) {
+ if (!ocfs2_check_dir_entry(dir, de, bh, first_de,
+ bytes, offset)) {
ret = -1;
goto bail;
}
@@ -694,7 +693,7 @@ static struct buffer_head *ocfs2_find_entry_el(const char *name, int namelen,
int ra_ptr = 0; /* Current index into readahead
buffer */
int num = 0;
- int nblocks, i, err;
+ int nblocks, i;
sb = dir->i_sb;
@@ -726,7 +725,7 @@ restart:
num++;
bh = NULL;
- err = ocfs2_read_dir_block(dir, b++, &bh,
+ ocfs2_read_dir_block(dir, b++, &bh,
OCFS2_BH_READAHEAD);
bh_use[ra_max] = bh;
}
@@ -792,6 +791,14 @@ static int ocfs2_dx_dir_lookup_rec(struct inode *inode,
struct ocfs2_extent_block *eb;
struct ocfs2_extent_rec *rec = NULL;
+ if (le16_to_cpu(el->l_count) !=
+ ocfs2_extent_recs_per_dx_root(inode->i_sb)) {
+ ret = ocfs2_error(inode->i_sb,
+ "Inode %lu has invalid extent list length %u\n",
+ inode->i_ino, le16_to_cpu(el->l_count));
+ goto out;
+ }
+
if (el->l_tree_depth) {
ret = ocfs2_find_leaf(INODE_CACHE(inode), el, major_hash,
&eb_bh);
@@ -812,6 +819,14 @@ static int ocfs2_dx_dir_lookup_rec(struct inode *inode,
}
}
+ if (le16_to_cpu(el->l_next_free_rec) == 0) {
+ ret = ocfs2_error(inode->i_sb,
+ "Inode %lu has empty extent list at depth %u\n",
+ inode->i_ino,
+ le16_to_cpu(el->l_tree_depth));
+ goto out;
+ }
+
found = 0;
for (i = le16_to_cpu(el->l_next_free_rec) - 1; i >= 0; i--) {
rec = &el->l_recs[i];
@@ -866,9 +881,9 @@ static int ocfs2_dx_dir_lookup(struct inode *inode,
u64 *ret_phys_blkno)
{
int ret = 0;
- unsigned int cend, uninitialized_var(clen);
- u32 uninitialized_var(cpos);
- u64 uninitialized_var(blkno);
+ unsigned int cend, clen;
+ u32 cpos;
+ u64 blkno;
u32 name_hash = hinfo->major_hash;
ret = ocfs2_dx_dir_lookup_rec(inode, el, name_hash, &cpos, &blkno,
@@ -912,7 +927,7 @@ static int ocfs2_dx_dir_search(const char *name, int namelen,
struct ocfs2_dir_lookup_result *res)
{
int ret, i, found;
- u64 uninitialized_var(phys);
+ u64 phys;
struct buffer_head *dx_leaf_bh = NULL;
struct ocfs2_dx_leaf *dx_leaf;
struct ocfs2_dx_entry *dx_entry = NULL;
@@ -1079,26 +1094,39 @@ int ocfs2_find_entry(const char *name, int namelen,
{
struct buffer_head *bh;
struct ocfs2_dir_entry *res_dir = NULL;
+ int ret = 0;
if (ocfs2_dir_indexed(dir))
return ocfs2_find_entry_dx(name, namelen, dir, lookup);
+ if (unlikely(i_size_read(dir) <= 0)) {
+ ret = -EFSCORRUPTED;
+ mlog_errno(ret);
+ goto out;
+ }
/*
* The unindexed dir code only uses part of the lookup
* structure, so there's no reason to push it down further
* than this.
*/
- if (OCFS2_I(dir)->ip_dyn_features & OCFS2_INLINE_DATA_FL)
+ if (OCFS2_I(dir)->ip_dyn_features & OCFS2_INLINE_DATA_FL) {
+ if (unlikely(i_size_read(dir) > dir->i_sb->s_blocksize)) {
+ ret = -EFSCORRUPTED;
+ mlog_errno(ret);
+ goto out;
+ }
bh = ocfs2_find_entry_id(name, namelen, dir, &res_dir);
- else
+ } else {
bh = ocfs2_find_entry_el(name, namelen, dir, &res_dir);
+ }
if (bh == NULL)
return -ENOENT;
lookup->dl_leaf_bh = bh;
lookup->dl_entry = res_dir;
- return 0;
+out:
+ return ret;
}
/*
@@ -1158,7 +1186,7 @@ static int __ocfs2_delete_entry(handle_t *handle, struct inode *dir,
pde = NULL;
de = (struct ocfs2_dir_entry *) first_de;
while (i < bytes) {
- if (!ocfs2_check_dir_entry(dir, de, bh, i)) {
+ if (!ocfs2_check_dir_entry(dir, de, bh, first_de, bytes, i)) {
status = -EIO;
mlog_errno(status);
goto bail;
@@ -1613,9 +1641,6 @@ int __ocfs2_add_entry(handle_t *handle,
struct buffer_head *insert_bh = lookup->dl_leaf_bh;
char *data_start = insert_bh->b_data;
- if (!namelen)
- return -EINVAL;
-
if (ocfs2_dir_indexed(dir)) {
struct buffer_head *bh;
@@ -1658,7 +1683,8 @@ int __ocfs2_add_entry(handle_t *handle,
/* These checks should've already been passed by the
* prepare function, but I guess we can leave them
* here anyway. */
- if (!ocfs2_check_dir_entry(dir, de, insert_bh, offset)) {
+ if (!ocfs2_check_dir_entry(dir, de, insert_bh, data_start,
+ size, offset)) {
retval = -ENOENT;
goto bail;
}
@@ -1678,7 +1704,8 @@ int __ocfs2_add_entry(handle_t *handle,
offset, ocfs2_dir_trailer_blk_off(dir->i_sb));
if (ocfs2_dirent_would_fit(de, rec_len)) {
- dir->i_mtime = dir->i_ctime = current_time(dir);
+ inode_set_mtime_to_ts(dir,
+ inode_set_ctime_current(dir));
retval = ocfs2_mark_inode_dirty(handle, dir, parent_fe_bh);
if (retval < 0) {
mlog_errno(retval);
@@ -1718,7 +1745,7 @@ int __ocfs2_add_entry(handle_t *handle,
de->rec_len = cpu_to_le16(OCFS2_DIR_REC_LEN(de->name_len));
de = de1;
}
- de->file_type = OCFS2_FT_UNKNOWN;
+ de->file_type = FT_UNKNOWN;
if (blkno) {
de->inode = cpu_to_le64(blkno);
ocfs2_set_de_type(de, inode->i_mode);
@@ -1796,20 +1823,17 @@ static int ocfs2_dir_foreach_blk_id(struct inode *inode,
}
de = (struct ocfs2_dir_entry *) (data->id_data + ctx->pos);
- if (!ocfs2_check_dir_entry(inode, de, di_bh, ctx->pos)) {
+ if (!ocfs2_check_dir_entry(inode, de, di_bh, (char *)data->id_data,
+ i_size_read(inode), ctx->pos)) {
/* On error, skip the f_pos to the end. */
ctx->pos = i_size_read(inode);
break;
}
offset += le16_to_cpu(de->rec_len);
if (le64_to_cpu(de->inode)) {
- unsigned char d_type = DT_UNKNOWN;
-
- if (de->file_type < OCFS2_FT_MAX)
- d_type = ocfs2_filetype_table[de->file_type];
-
if (!dir_emit(ctx, de->name, de->name_len,
- le64_to_cpu(de->inode), d_type))
+ le64_to_cpu(de->inode),
+ fs_ftype_to_dtype(de->file_type)))
goto out;
}
ctx->pos += le16_to_cpu(de->rec_len);
@@ -1893,21 +1917,18 @@ static int ocfs2_dir_foreach_blk_el(struct inode *inode,
while (ctx->pos < i_size_read(inode)
&& offset < sb->s_blocksize) {
de = (struct ocfs2_dir_entry *) (bh->b_data + offset);
- if (!ocfs2_check_dir_entry(inode, de, bh, offset)) {
+ if (!ocfs2_check_dir_entry(inode, de, bh, bh->b_data,
+ sb->s_blocksize, offset)) {
/* On error, skip the f_pos to the
next block. */
ctx->pos = (ctx->pos | (sb->s_blocksize - 1)) + 1;
break;
}
if (le64_to_cpu(de->inode)) {
- unsigned char d_type = DT_UNKNOWN;
-
- if (de->file_type < OCFS2_FT_MAX)
- d_type = ocfs2_filetype_table[de->file_type];
if (!dir_emit(ctx, de->name,
de->name_len,
le64_to_cpu(de->inode),
- d_type)) {
+ fs_ftype_to_dtype(de->file_type))) {
brelse(bh);
return 0;
}
@@ -1953,6 +1974,7 @@ int ocfs2_readdir(struct file *file, struct dir_context *ctx)
{
int error = 0;
struct inode *inode = file_inode(file);
+ struct ocfs2_file_private *fp = file->private_data;
int lock_level = 0;
trace_ocfs2_readdir((unsigned long long)OCFS2_I(inode)->ip_blkno);
@@ -1973,7 +1995,7 @@ int ocfs2_readdir(struct file *file, struct dir_context *ctx)
goto bail_nolock;
}
- error = ocfs2_dir_foreach_blk(inode, &file->f_version, ctx, false);
+ error = ocfs2_dir_foreach_blk(inode, &fp->cookie, ctx, false);
ocfs2_inode_unlock(inode, lock_level);
if (error)
@@ -1985,7 +2007,7 @@ bail_nolock:
}
/*
- * NOTE: this should always be called with parent dir i_mutex taken.
+ * NOTE: this should always be called with parent dir i_rwsem taken.
*/
int ocfs2_find_files_on_disk(const char *name,
int namelen,
@@ -2030,8 +2052,9 @@ int ocfs2_lookup_ino_from_name(struct inode *dir, const char *name,
*
* Return 0 if the name does not exist
* Return -EEXIST if the directory contains the name
+ * Return -EFSCORRUPTED if found corruption
*
- * Callers should have i_mutex + a cluster lock on dir
+ * Callers should have i_rwsem + a cluster lock on dir
*/
int ocfs2_check_dir_for_entry(struct inode *dir,
const char *name,
@@ -2043,9 +2066,12 @@ int ocfs2_check_dir_for_entry(struct inode *dir,
trace_ocfs2_check_dir_for_entry(
(unsigned long long)OCFS2_I(dir)->ip_blkno, namelen, name);
- if (ocfs2_find_entry(name, namelen, dir, &lookup) == 0) {
+ ret = ocfs2_find_entry(name, namelen, dir, &lookup);
+ if (ret == 0) {
ret = -EEXIST;
mlog_errno(ret);
+ } else if (ret == -ENOENT) {
+ ret = 0;
}
ocfs2_free_dir_lookup_result(&lookup);
@@ -2060,7 +2086,7 @@ struct ocfs2_empty_dir_priv {
unsigned seen_other;
unsigned dx_dir;
};
-static int ocfs2_empty_dir_filldir(struct dir_context *ctx, const char *name,
+static bool ocfs2_empty_dir_filldir(struct dir_context *ctx, const char *name,
int name_len, loff_t pos, u64 ino,
unsigned type)
{
@@ -2080,7 +2106,7 @@ static int ocfs2_empty_dir_filldir(struct dir_context *ctx, const char *name,
*/
if (name_len == 1 && !strncmp(".", name, 1) && pos == 0) {
p->seen_dot = 1;
- return 0;
+ return true;
}
if (name_len == 2 && !strncmp("..", name, 2) &&
@@ -2088,13 +2114,13 @@ static int ocfs2_empty_dir_filldir(struct dir_context *ctx, const char *name,
p->seen_dot_dot = 1;
if (p->dx_dir && p->seen_dot)
- return 1;
+ return false;
- return 0;
+ return true;
}
p->seen_other = 1;
- return 1;
+ return false;
}
static int ocfs2_empty_dir_dx(struct inode *inode,
@@ -2990,11 +3016,11 @@ static int ocfs2_expand_inline_dir(struct inode *dir, struct buffer_head *di_bh,
ocfs2_dinode_new_extent_list(dir, di);
i_size_write(dir, sb->s_blocksize);
- dir->i_mtime = dir->i_ctime = current_time(dir);
+ inode_set_mtime_to_ts(dir, inode_set_ctime_current(dir));
di->i_size = cpu_to_le64(sb->s_blocksize);
- di->i_ctime = di->i_mtime = cpu_to_le64(dir->i_ctime.tv_sec);
- di->i_ctime_nsec = di->i_mtime_nsec = cpu_to_le32(dir->i_ctime.tv_nsec);
+ di->i_ctime = di->i_mtime = cpu_to_le64(inode_get_ctime_sec(dir));
+ di->i_ctime_nsec = di->i_mtime_nsec = cpu_to_le32(inode_get_ctime_nsec(dir));
ocfs2_update_inode_fsync_trans(handle, dir, 1);
/*
@@ -3369,9 +3395,9 @@ static int ocfs2_find_dir_space_id(struct inode *dir, struct buffer_head *di_bh,
struct super_block *sb = dir->i_sb;
struct ocfs2_dinode *di = (struct ocfs2_dinode *)di_bh->b_data;
struct ocfs2_dir_entry *de, *last_de = NULL;
- char *de_buf, *limit;
+ char *first_de, *de_buf, *limit;
unsigned long offset = 0;
- unsigned int rec_len, new_rec_len, free_space = dir->i_sb->s_blocksize;
+ unsigned int rec_len, new_rec_len, free_space;
/*
* This calculates how many free bytes we'd have in block zero, should
@@ -3382,14 +3408,16 @@ static int ocfs2_find_dir_space_id(struct inode *dir, struct buffer_head *di_bh,
else
free_space = dir->i_sb->s_blocksize - i_size_read(dir);
- de_buf = di->id2.i_data.id_data;
+ first_de = di->id2.i_data.id_data;
+ de_buf = first_de;
limit = de_buf + i_size_read(dir);
rec_len = OCFS2_DIR_REC_LEN(namelen);
while (de_buf < limit) {
de = (struct ocfs2_dir_entry *)de_buf;
- if (!ocfs2_check_dir_entry(dir, de, di_bh, offset)) {
+ if (!ocfs2_check_dir_entry(dir, de, di_bh, first_de,
+ i_size_read(dir), offset)) {
ret = -ENOENT;
goto out;
}
@@ -3416,6 +3444,14 @@ static int ocfs2_find_dir_space_id(struct inode *dir, struct buffer_head *di_bh,
offset += le16_to_cpu(de->rec_len);
}
+ if (!last_de) {
+ ret = ocfs2_error(sb, "Directory entry (#%llu: size=%lld) "
+ "is unexpectedly short",
+ (unsigned long long)OCFS2_I(dir)->ip_blkno,
+ i_size_read(dir));
+ goto out;
+ }
+
/*
* We're going to require expansion of the directory - figure
* out how many blocks we'll need so that a place for the
@@ -3471,7 +3507,8 @@ static int ocfs2_find_dir_space_el(struct inode *dir, const char *name,
/* move to next block */
de = (struct ocfs2_dir_entry *) bh->b_data;
}
- if (!ocfs2_check_dir_entry(dir, de, bh, offset)) {
+ if (!ocfs2_check_dir_entry(dir, de, bh, bh->b_data, blocksize,
+ offset)) {
status = -ENOENT;
goto bail;
}
@@ -3529,16 +3566,6 @@ static int dx_leaf_sort_cmp(const void *a, const void *b)
return 0;
}
-static void dx_leaf_sort_swap(void *a, void *b, int size)
-{
- struct ocfs2_dx_entry *entry1 = a;
- struct ocfs2_dx_entry *entry2 = b;
-
- BUG_ON(size != sizeof(*entry1));
-
- swap(*entry1, *entry2);
-}
-
static int ocfs2_dx_leaf_same_major(struct ocfs2_dx_leaf *dx_leaf)
{
struct ocfs2_dx_entry_list *dl_list = &dx_leaf->dl_list;
@@ -3662,7 +3689,7 @@ static void ocfs2_dx_dir_transfer_leaf(struct inode *dir, u32 split_hash,
int i, j, num_used;
u32 major_hash;
struct ocfs2_dx_leaf *orig_dx_leaf, *new_dx_leaf;
- struct ocfs2_dx_entry_list *orig_list, *new_list, *tmp_list;
+ struct ocfs2_dx_entry_list *orig_list, *tmp_list;
struct ocfs2_dx_entry *dx_entry;
tmp_list = &tmp_dx_leaf->dl_list;
@@ -3671,7 +3698,6 @@ static void ocfs2_dx_dir_transfer_leaf(struct inode *dir, u32 split_hash,
orig_dx_leaf = (struct ocfs2_dx_leaf *) orig_dx_leaves[i]->b_data;
orig_list = &orig_dx_leaf->dl_list;
new_dx_leaf = (struct ocfs2_dx_leaf *) new_dx_leaves[i]->b_data;
- new_list = &new_dx_leaf->dl_list;
num_used = le16_to_cpu(orig_list->de_num_used);
@@ -3800,7 +3826,7 @@ static int ocfs2_dx_dir_rebalance(struct ocfs2_super *osb, struct inode *dir,
*/
sort(dx_leaf->dl_list.de_entries, num_used,
sizeof(struct ocfs2_dx_entry), dx_leaf_sort_cmp,
- dx_leaf_sort_swap);
+ NULL);
ocfs2_journal_dirty(handle, dx_leaf_bh);
@@ -4107,10 +4133,15 @@ static int ocfs2_expand_inline_dx_root(struct inode *dir,
}
dx_root->dr_flags &= ~OCFS2_DX_FLAG_INLINE;
- memset(&dx_root->dr_list, 0, osb->sb->s_blocksize -
- offsetof(struct ocfs2_dx_root_block, dr_list));
+
+ dx_root->dr_list.l_tree_depth = 0;
dx_root->dr_list.l_count =
cpu_to_le16(ocfs2_extent_recs_per_dx_root(osb->sb));
+ dx_root->dr_list.l_next_free_rec = 0;
+ memset(&dx_root->dr_list.l_recs, 0,
+ osb->sb->s_blocksize -
+ (offsetof(struct ocfs2_dx_root_block, dr_list) +
+ offsetof(struct ocfs2_extent_list, l_recs)));
/* This should never fail considering we start with an empty
* dx_root. */
@@ -4273,12 +4304,6 @@ int ocfs2_prepare_dir_for_insert(struct ocfs2_super *osb,
trace_ocfs2_prepare_dir_for_insert(
(unsigned long long)OCFS2_I(dir)->ip_blkno, namelen);
- if (!namelen) {
- ret = -EINVAL;
- mlog_errno(ret);
- goto out;
- }
-
/*
* Do this up front to reduce confusion.
*
@@ -4420,9 +4445,9 @@ out:
int ocfs2_dx_dir_truncate(struct inode *dir, struct buffer_head *di_bh)
{
int ret;
- unsigned int uninitialized_var(clen);
- u32 major_hash = UINT_MAX, p_cpos, uninitialized_var(cpos);
- u64 uninitialized_var(blkno);
+ unsigned int clen;
+ u32 major_hash = UINT_MAX, p_cpos, cpos;
+ u64 blkno;
struct ocfs2_super *osb = OCFS2_SB(dir->i_sb);
struct buffer_head *dx_root_bh = NULL;
struct ocfs2_dx_root_block *dx_root;
generated by cgit (git 2.34.1) at 2025-12-25 07:50:24 +0000