summaryrefslogtreecommitdiff
path: root/fs/ext4/namei.c
diff options
context:
space:
mode:
Diffstat (limited to 'fs/ext4/namei.c')
-rw-r--r--fs/ext4/namei.c986
1 files changed, 546 insertions, 440 deletions
diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c
index 52c9bd154122..c4b5e252af0e 100644
--- a/fs/ext4/namei.c
+++ b/fs/ext4/namei.c
@@ -54,6 +54,7 @@ static struct buffer_head *ext4_append(handle_t *handle,
struct inode *inode,
ext4_lblk_t *block)
{
+ struct ext4_map_blocks map;
struct buffer_head *bh;
int err;
@@ -63,21 +64,41 @@ static struct buffer_head *ext4_append(handle_t *handle,
return ERR_PTR(-ENOSPC);
*block = inode->i_size >> inode->i_sb->s_blocksize_bits;
+ map.m_lblk = *block;
+ map.m_len = 1;
+
+ /*
+ * We're appending new directory block. Make sure the block is not
+ * allocated yet, otherwise we will end up corrupting the
+ * directory.
+ */
+ err = ext4_map_blocks(NULL, inode, &map, 0);
+ if (err < 0)
+ return ERR_PTR(err);
+ if (err) {
+ EXT4_ERROR_INODE(inode, "Logical block already allocated");
+ return ERR_PTR(-EFSCORRUPTED);
+ }
bh = ext4_bread(handle, inode, *block, EXT4_GET_BLOCKS_CREATE);
if (IS_ERR(bh))
return bh;
inode->i_size += inode->i_sb->s_blocksize;
EXT4_I(inode)->i_disksize = inode->i_size;
+ err = ext4_mark_inode_dirty(handle, inode);
+ if (err)
+ goto out;
BUFFER_TRACE(bh, "get_write_access");
err = ext4_journal_get_write_access(handle, inode->i_sb, bh,
EXT4_JTR_NONE);
- if (err) {
- brelse(bh);
- ext4_std_error(inode->i_sb, err);
- return ERR_PTR(err);
- }
+ if (err)
+ goto out;
return bh;
+
+out:
+ brelse(bh);
+ ext4_std_error(inode->i_sb, err);
+ return ERR_PTR(err);
}
static int ext4_dx_csum_verify(struct inode *inode,
@@ -110,6 +131,13 @@ static struct buffer_head *__ext4_read_dirblock(struct inode *inode,
struct ext4_dir_entry *dirent;
int is_dx_block = 0;
+ if (block >= inode->i_size >> inode->i_blkbits) {
+ ext4_error_inode(inode, func, line, block,
+ "Attempting to read directory block (%u) that is past i_size (%llu)",
+ block, inode->i_size);
+ return ERR_PTR(-EFSCORRUPTED);
+ }
+
if (ext4_simulate_fail(inode->i_sb, EXT4_SIM_DIRBLOCK_EIO))
bh = ERR_PTR(-EIO);
else
@@ -123,10 +151,11 @@ static struct buffer_head *__ext4_read_dirblock(struct inode *inode,
return bh;
}
- if (!bh && (type == INDEX || type == DIRENT_HTREE)) {
+ /* The first directory block must not be a hole. */
+ if (!bh && (type == INDEX || type == DIRENT_HTREE || block == 0)) {
ext4_error_inode(inode, func, line, block,
- "Directory hole found for htree %s block",
- (type == INDEX) ? "index" : "leaf");
+ "Directory hole found for htree %s block %u",
+ (type == INDEX) ? "index" : "leaf", block);
return ERR_PTR(-EFSCORRUPTED);
}
if (!bh)
@@ -147,7 +176,7 @@ static struct buffer_head *__ext4_read_dirblock(struct inode *inode,
brelse(bh);
return ERR_PTR(-EFSCORRUPTED);
}
- if (!ext4_has_metadata_csum(inode->i_sb) ||
+ if (!ext4_has_feature_metadata_csum(inode->i_sb) ||
buffer_verified(bh))
return bh;
@@ -262,36 +291,6 @@ struct dx_tail {
__le32 dt_checksum; /* crc32c(uuid+inum+dirblock) */
};
-static inline ext4_lblk_t dx_get_block(struct dx_entry *entry);
-static void dx_set_block(struct dx_entry *entry, ext4_lblk_t value);
-static inline unsigned dx_get_hash(struct dx_entry *entry);
-static void dx_set_hash(struct dx_entry *entry, unsigned value);
-static unsigned dx_get_count(struct dx_entry *entries);
-static unsigned dx_get_limit(struct dx_entry *entries);
-static void dx_set_count(struct dx_entry *entries, unsigned value);
-static void dx_set_limit(struct dx_entry *entries, unsigned value);
-static unsigned dx_root_limit(struct inode *dir, unsigned infosize);
-static unsigned dx_node_limit(struct inode *dir);
-static struct dx_frame *dx_probe(struct ext4_filename *fname,
- struct inode *dir,
- struct dx_hash_info *hinfo,
- struct dx_frame *frame);
-static void dx_release(struct dx_frame *frames);
-static int dx_make_map(struct inode *dir, struct ext4_dir_entry_2 *de,
- unsigned blocksize, struct dx_hash_info *hinfo,
- struct dx_map_entry map[]);
-static void dx_sort_map(struct dx_map_entry *map, unsigned count);
-static struct ext4_dir_entry_2 *dx_move_dirents(struct inode *dir, char *from,
- char *to, struct dx_map_entry *offsets,
- int count, unsigned int blocksize);
-static struct ext4_dir_entry_2 *dx_pack_dirents(struct inode *dir, char *base,
- unsigned int blocksize);
-static void dx_insert_block(struct dx_frame *frame,
- u32 hash, ext4_lblk_t block);
-static int ext4_htree_next_block(struct inode *dir, __u32 hash,
- struct dx_frame *frame,
- struct dx_frame *frames,
- __u32 *start_hash);
static struct buffer_head * ext4_dx_find_entry(struct inode *dir,
struct ext4_filename *fname,
struct ext4_dir_entry_2 **res_dir);
@@ -315,17 +314,17 @@ static struct ext4_dir_entry_tail *get_dirent_tail(struct inode *inode,
struct buffer_head *bh)
{
struct ext4_dir_entry_tail *t;
+ int blocksize = EXT4_BLOCK_SIZE(inode->i_sb);
#ifdef PARANOID
struct ext4_dir_entry *d, *top;
d = (struct ext4_dir_entry *)bh->b_data;
top = (struct ext4_dir_entry *)(bh->b_data +
- (EXT4_BLOCK_SIZE(inode->i_sb) -
- sizeof(struct ext4_dir_entry_tail)));
- while (d < top && d->rec_len)
+ (blocksize - sizeof(struct ext4_dir_entry_tail)));
+ while (d < top && ext4_rec_len_from_disk(d->rec_len, blocksize))
d = (struct ext4_dir_entry *)(((void *)d) +
- le16_to_cpu(d->rec_len));
+ ext4_rec_len_from_disk(d->rec_len, blocksize));
if (d != top)
return NULL;
@@ -336,7 +335,8 @@ static struct ext4_dir_entry_tail *get_dirent_tail(struct inode *inode,
#endif
if (t->det_reserved_zero1 ||
- le16_to_cpu(t->det_rec_len) != sizeof(struct ext4_dir_entry_tail) ||
+ (ext4_rec_len_from_disk(t->det_rec_len, blocksize) !=
+ sizeof(struct ext4_dir_entry_tail)) ||
t->det_reserved_zero2 ||
t->det_reserved_ft != EXT4_FT_DIR_CSUM)
return NULL;
@@ -346,11 +346,10 @@ static struct ext4_dir_entry_tail *get_dirent_tail(struct inode *inode,
static __le32 ext4_dirblock_csum(struct inode *inode, void *dirent, int size)
{
- struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
struct ext4_inode_info *ei = EXT4_I(inode);
__u32 csum;
- csum = ext4_chksum(sbi, ei->i_csum_seed, (__u8 *)dirent, size);
+ csum = ext4_chksum(ei->i_csum_seed, (__u8 *)dirent, size);
return cpu_to_le32(csum);
}
@@ -368,7 +367,7 @@ int ext4_dirblock_csum_verify(struct inode *inode, struct buffer_head *bh)
{
struct ext4_dir_entry_tail *t;
- if (!ext4_has_metadata_csum(inode->i_sb))
+ if (!ext4_has_feature_metadata_csum(inode->i_sb))
return 1;
t = get_dirent_tail(inode, bh);
@@ -389,7 +388,7 @@ static void ext4_dirblock_csum_set(struct inode *inode,
{
struct ext4_dir_entry_tail *t;
- if (!ext4_has_metadata_csum(inode->i_sb))
+ if (!ext4_has_feature_metadata_csum(inode->i_sb))
return;
t = get_dirent_tail(inode, bh);
@@ -417,13 +416,14 @@ static struct dx_countlimit *get_dx_countlimit(struct inode *inode,
struct ext4_dir_entry *dp;
struct dx_root_info *root;
int count_offset;
+ int blocksize = EXT4_BLOCK_SIZE(inode->i_sb);
+ unsigned int rlen = ext4_rec_len_from_disk(dirent->rec_len, blocksize);
- if (le16_to_cpu(dirent->rec_len) == EXT4_BLOCK_SIZE(inode->i_sb))
+ if (rlen == blocksize)
count_offset = 8;
- else if (le16_to_cpu(dirent->rec_len) == 12) {
+ else if (rlen == 12) {
dp = (struct ext4_dir_entry *)(((void *)dirent) + 12);
- if (le16_to_cpu(dp->rec_len) !=
- EXT4_BLOCK_SIZE(inode->i_sb) - 12)
+ if (ext4_rec_len_from_disk(dp->rec_len, blocksize) != blocksize - 12)
return NULL;
root = (struct dx_root_info *)(((void *)dp + 12));
if (root->reserved_zero ||
@@ -441,7 +441,6 @@ static struct dx_countlimit *get_dx_countlimit(struct inode *inode,
static __le32 ext4_dx_csum(struct inode *inode, struct ext4_dir_entry *dirent,
int count_offset, int count, struct dx_tail *t)
{
- struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
struct ext4_inode_info *ei = EXT4_I(inode);
__u32 csum;
int size;
@@ -449,9 +448,9 @@ static __le32 ext4_dx_csum(struct inode *inode, struct ext4_dir_entry *dirent,
int offset = offsetof(struct dx_tail, dt_checksum);
size = count_offset + (count * sizeof(struct dx_entry));
- csum = ext4_chksum(sbi, ei->i_csum_seed, (__u8 *)dirent, size);
- csum = ext4_chksum(sbi, csum, (__u8 *)t, offset);
- csum = ext4_chksum(sbi, csum, (__u8 *)&dummy_csum, sizeof(dummy_csum));
+ csum = ext4_chksum(ei->i_csum_seed, (__u8 *)dirent, size);
+ csum = ext4_chksum(csum, (__u8 *)t, offset);
+ csum = ext4_chksum(csum, (__u8 *)&dummy_csum, sizeof(dummy_csum));
return cpu_to_le32(csum);
}
@@ -463,7 +462,7 @@ static int ext4_dx_csum_verify(struct inode *inode,
struct dx_tail *t;
int count_offset, limit, count;
- if (!ext4_has_metadata_csum(inode->i_sb))
+ if (!ext4_has_feature_metadata_csum(inode->i_sb))
return 1;
c = get_dx_countlimit(inode, dirent, &count_offset);
@@ -492,7 +491,7 @@ static void ext4_dx_csum_set(struct inode *inode, struct ext4_dir_entry *dirent)
struct dx_tail *t;
int count_offset, limit, count;
- if (!ext4_has_metadata_csum(inode->i_sb))
+ if (!ext4_has_feature_metadata_csum(inode->i_sb))
return;
c = get_dx_countlimit(inode, dirent, &count_offset);
@@ -581,7 +580,7 @@ static inline unsigned dx_root_limit(struct inode *dir, unsigned infosize)
ext4_dir_rec_len(1, NULL) -
ext4_dir_rec_len(2, NULL) - infosize;
- if (ext4_has_metadata_csum(dir->i_sb))
+ if (ext4_has_feature_metadata_csum(dir->i_sb))
entry_space -= sizeof(struct dx_tail);
return entry_space / sizeof(struct dx_entry);
}
@@ -591,7 +590,7 @@ static inline unsigned dx_node_limit(struct inode *dir)
unsigned int entry_space = dir->i_sb->s_blocksize -
ext4_dir_rec_len(0, dir);
- if (ext4_has_metadata_csum(dir->i_sb))
+ if (ext4_has_feature_metadata_csum(dir->i_sb))
entry_space -= sizeof(struct dx_tail);
return entry_space / sizeof(struct dx_entry);
}
@@ -646,7 +645,7 @@ static struct stats dx_show_leaf(struct inode *dir,
len = de->name_len;
if (!IS_ENCRYPTED(dir)) {
/* Directory is not encrypted */
- ext4fs_dirhash(dir, de->name,
+ (void) ext4fs_dirhash(dir, de->name,
de->name_len, &h);
printk("%*.s:(U)%x.%u ", len,
name, h.hash,
@@ -681,8 +680,9 @@ static struct stats dx_show_leaf(struct inode *dir,
if (IS_CASEFOLDED(dir))
h.hash = EXT4_DIRENT_HASH(de);
else
- ext4fs_dirhash(dir, de->name,
- de->name_len, &h);
+ (void) ext4fs_dirhash(dir,
+ de->name,
+ de->name_len, &h);
printk("%*.s:(E)%x.%u ", len, name,
h.hash, (unsigned) ((char *) de
- base));
@@ -692,7 +692,8 @@ static struct stats dx_show_leaf(struct inode *dir,
#else
int len = de->name_len;
char *name = de->name;
- ext4fs_dirhash(dir, de->name, de->name_len, &h);
+ (void) ext4fs_dirhash(dir, de->name,
+ de->name_len, &h);
printk("%*.s:%x.%u ", len, name, h.hash,
(unsigned) ((char *) de - base));
#endif
@@ -777,12 +778,14 @@ static struct dx_frame *
dx_probe(struct ext4_filename *fname, struct inode *dir,
struct dx_hash_info *hinfo, struct dx_frame *frame_in)
{
- unsigned count, indirect;
+ unsigned count, indirect, level, i;
struct dx_entry *at, *entries, *p, *q, *m;
struct dx_root *root;
struct dx_frame *frame = frame_in;
struct dx_frame *ret_err = ERR_PTR(ERR_BAD_DX_DIR);
u32 hash;
+ ext4_lblk_t block;
+ ext4_lblk_t blocks[EXT4_HTREE_LEVEL];
memset(frame_in, 0, EXT4_HTREE_LEVEL * sizeof(frame_in[0]));
frame->bh = ext4_read_dirblock(dir, 0, INDEX);
@@ -819,8 +822,14 @@ dx_probe(struct ext4_filename *fname, struct inode *dir,
hinfo->seed = EXT4_SB(dir->i_sb)->s_hash_seed;
/* hash is already computed for encrypted casefolded directory */
if (fname && fname_name(fname) &&
- !(IS_ENCRYPTED(dir) && IS_CASEFOLDED(dir)))
- ext4fs_dirhash(dir, fname_name(fname), fname_len(fname), hinfo);
+ !(IS_ENCRYPTED(dir) && IS_CASEFOLDED(dir))) {
+ int ret = ext4fs_dirhash(dir, fname_name(fname),
+ fname_len(fname), hinfo);
+ if (ret < 0) {
+ ret_err = ERR_PTR(ret);
+ goto fail;
+ }
+ }
hash = hinfo->hash;
if (root->info.unused_flags & 1) {
@@ -854,6 +863,8 @@ dx_probe(struct ext4_filename *fname, struct inode *dir,
}
dxtrace(printk("Look up %x", hash));
+ level = 0;
+ blocks[0] = 0;
while (1) {
count = dx_get_count(entries);
if (!count || count > dx_get_limit(entries)) {
@@ -882,15 +893,27 @@ dx_probe(struct ext4_filename *fname, struct inode *dir,
dx_get_block(at)));
frame->entries = entries;
frame->at = at;
- if (!indirect--)
+
+ block = dx_get_block(at);
+ for (i = 0; i <= level; i++) {
+ if (blocks[i] == block) {
+ ext4_warning_inode(dir,
+ "dx entry: tree cycle block %u points back to block %u",
+ blocks[level], block);
+ goto fail;
+ }
+ }
+ if (++level > indirect)
return frame;
+ blocks[level] = block;
frame++;
- frame->bh = ext4_read_dirblock(dir, dx_get_block(at), INDEX);
+ frame->bh = ext4_read_dirblock(dir, block, INDEX);
if (IS_ERR(frame->bh)) {
ret_err = (struct dx_frame *) frame->bh;
frame->bh = NULL;
goto fail;
}
+
entries = ((struct dx_node *) frame->bh->b_data)->entries;
if (dx_get_limit(entries) != dx_node_limit(dir)) {
@@ -1021,7 +1044,7 @@ static int htree_dirblock_to_tree(struct file *dir_file,
struct ext4_dir_entry_2 *de, *top;
int err = 0, count = 0;
struct fscrypt_str fname_crypto_str = FSTR_INIT(NULL, 0), tmp_str;
- int csum = ext4_has_metadata_csum(dir->i_sb);
+ int csum = ext4_has_feature_metadata_csum(dir->i_sb);
dxtrace(printk(KERN_INFO "In htree dirblock_to_tree: block %lu\n",
(unsigned long)block));
@@ -1053,7 +1076,7 @@ static int htree_dirblock_to_tree(struct file *dir_file,
for (; de < top; de = ext4_next_entry(de, dir->i_sb->s_blocksize)) {
if (ext4_check_dir_entry(dir, NULL, de, bh,
bh->b_data, bh->b_size,
- (block<<EXT4_BLOCK_SIZE_BITS(dir->i_sb))
+ EXT4_LBLK_TO_B(dir, block)
+ ((char *)de - bh->b_data))) {
/* silently ignore the rest of the block */
break;
@@ -1067,7 +1090,12 @@ static int htree_dirblock_to_tree(struct file *dir_file,
hinfo->minor_hash = 0;
}
} else {
- ext4fs_dirhash(dir, de->name, de->name_len, hinfo);
+ err = ext4fs_dirhash(dir, de->name,
+ de->name_len, hinfo);
+ if (err < 0) {
+ count = err;
+ goto errout;
+ }
}
if ((hinfo->hash < start_hash) ||
((hinfo->hash == start_hash) &&
@@ -1249,28 +1277,41 @@ static inline int search_dirblock(struct buffer_head *bh,
* Create map of hash values, offsets, and sizes, stored at end of block.
* Returns number of entries mapped.
*/
-static int dx_make_map(struct inode *dir, struct ext4_dir_entry_2 *de,
- unsigned blocksize, struct dx_hash_info *hinfo,
+static int dx_make_map(struct inode *dir, struct buffer_head *bh,
+ struct dx_hash_info *hinfo,
struct dx_map_entry *map_tail)
{
int count = 0;
- char *base = (char *) de;
+ struct ext4_dir_entry_2 *de = (struct ext4_dir_entry_2 *)bh->b_data;
+ unsigned int buflen = bh->b_size;
+ char *base = bh->b_data;
struct dx_hash_info h = *hinfo;
+ int blocksize = EXT4_BLOCK_SIZE(dir->i_sb);
+
+ if (ext4_has_feature_metadata_csum(dir->i_sb))
+ buflen -= sizeof(struct ext4_dir_entry_tail);
- while ((char *) de < base + blocksize) {
+ while ((char *) de < base + buflen) {
+ if (ext4_check_dir_entry(dir, NULL, de, bh, base, buflen,
+ ((char *)de) - base))
+ return -EFSCORRUPTED;
if (de->name_len && de->inode) {
if (ext4_hash_in_dirent(dir))
h.hash = EXT4_DIRENT_HASH(de);
- else
- ext4fs_dirhash(dir, de->name, de->name_len, &h);
+ else {
+ int err = ext4fs_dirhash(dir, de->name,
+ de->name_len, &h);
+ if (err < 0)
+ return err;
+ }
map_tail--;
map_tail->hash = h.hash;
map_tail->offs = ((char *) de - base)>>2;
- map_tail->size = le16_to_cpu(de->rec_len);
+ map_tail->size = ext4_rec_len_from_disk(de->rec_len,
+ blocksize);
count++;
cond_resched();
}
- /* XXX: do we need to check rec_len == 0 case? -Chris */
de = ext4_next_entry(de, blocksize);
}
return count;
@@ -1317,94 +1358,42 @@ static void dx_insert_block(struct dx_frame *frame, u32 hash, ext4_lblk_t block)
dx_set_count(entries, count + 1);
}
-#ifdef CONFIG_UNICODE
-/*
- * Test whether a case-insensitive directory entry matches the filename
- * being searched for. If quick is set, assume the name being looked up
- * is already in the casefolded form.
- *
- * Returns: 0 if the directory entry matches, more than 0 if it
- * doesn't match or less than zero on error.
- */
-static int ext4_ci_compare(const struct inode *parent, const struct qstr *name,
- u8 *de_name, size_t de_name_len, bool quick)
-{
- const struct super_block *sb = parent->i_sb;
- const struct unicode_map *um = sb->s_encoding;
- struct fscrypt_str decrypted_name = FSTR_INIT(NULL, de_name_len);
- struct qstr entry = QSTR_INIT(de_name, de_name_len);
- int ret;
-
- if (IS_ENCRYPTED(parent)) {
- const struct fscrypt_str encrypted_name =
- FSTR_INIT(de_name, de_name_len);
-
- decrypted_name.name = kmalloc(de_name_len, GFP_KERNEL);
- if (!decrypted_name.name)
- return -ENOMEM;
- ret = fscrypt_fname_disk_to_usr(parent, 0, 0, &encrypted_name,
- &decrypted_name);
- if (ret < 0)
- goto out;
- entry.name = decrypted_name.name;
- entry.len = decrypted_name.len;
- }
-
- if (quick)
- ret = utf8_strncasecmp_folded(um, name, &entry);
- else
- ret = utf8_strncasecmp(um, name, &entry);
- if (ret < 0) {
- /* Handle invalid character sequence as either an error
- * or as an opaque byte sequence.
- */
- if (sb_has_strict_encoding(sb))
- ret = -EINVAL;
- else if (name->len != entry.len)
- ret = 1;
- else
- ret = !!memcmp(name->name, entry.name, entry.len);
- }
-out:
- kfree(decrypted_name.name);
- return ret;
-}
-
+#if IS_ENABLED(CONFIG_UNICODE)
int ext4_fname_setup_ci_filename(struct inode *dir, const struct qstr *iname,
struct ext4_filename *name)
{
- struct fscrypt_str *cf_name = &name->cf_name;
+ struct qstr *cf_name = &name->cf_name;
+ unsigned char *buf;
struct dx_hash_info *hinfo = &name->hinfo;
int len;
- if (!IS_CASEFOLDED(dir) || !dir->i_sb->s_encoding ||
+ if (!IS_CASEFOLDED(dir) ||
(IS_ENCRYPTED(dir) && !fscrypt_has_encryption_key(dir))) {
cf_name->name = NULL;
return 0;
}
- cf_name->name = kmalloc(EXT4_NAME_LEN, GFP_NOFS);
- if (!cf_name->name)
+ buf = kmalloc(EXT4_NAME_LEN, GFP_NOFS);
+ if (!buf)
return -ENOMEM;
- len = utf8_casefold(dir->i_sb->s_encoding,
- iname, cf_name->name,
- EXT4_NAME_LEN);
+ len = utf8_casefold(dir->i_sb->s_encoding, iname, buf, EXT4_NAME_LEN);
if (len <= 0) {
- kfree(cf_name->name);
- cf_name->name = NULL;
+ kfree(buf);
+ buf = NULL;
}
+ cf_name->name = buf;
cf_name->len = (unsigned) len;
+
if (!IS_ENCRYPTED(dir))
return 0;
hinfo->hash_version = DX_HASH_SIPHASH;
hinfo->seed = NULL;
if (cf_name->name)
- ext4fs_dirhash(dir, cf_name->name, cf_name->len, hinfo);
+ return ext4fs_dirhash(dir, cf_name->name, cf_name->len, hinfo);
else
- ext4fs_dirhash(dir, iname->name, iname->len, hinfo);
- return 0;
+ return ext4fs_dirhash(dir, iname->name, iname->len, hinfo);
}
#endif
@@ -1428,25 +1417,33 @@ static bool ext4_match(struct inode *parent,
f.crypto_buf = fname->crypto_buf;
#endif
-#ifdef CONFIG_UNICODE
- if (parent->i_sb->s_encoding && IS_CASEFOLDED(parent) &&
+#if IS_ENABLED(CONFIG_UNICODE)
+ if (IS_CASEFOLDED(parent) &&
(!IS_ENCRYPTED(parent) || fscrypt_has_encryption_key(parent))) {
- if (fname->cf_name.name) {
- struct qstr cf = {.name = fname->cf_name.name,
- .len = fname->cf_name.len};
- if (IS_ENCRYPTED(parent)) {
- if (fname->hinfo.hash != EXT4_DIRENT_HASH(de) ||
- fname->hinfo.minor_hash !=
- EXT4_DIRENT_MINOR_HASH(de)) {
-
- return false;
- }
- }
- return !ext4_ci_compare(parent, &cf, de->name,
- de->name_len, true);
- }
- return !ext4_ci_compare(parent, fname->usr_fname, de->name,
- de->name_len, false);
+ /*
+ * Just checking IS_ENCRYPTED(parent) below is not
+ * sufficient to decide whether one can use the hash for
+ * skipping the string comparison, because the key might
+ * have been added right after
+ * ext4_fname_setup_ci_filename(). In this case, a hash
+ * mismatch will be a false negative. Therefore, make
+ * sure cf_name was properly initialized before
+ * considering the calculated hash.
+ */
+ if (sb_no_casefold_compat_fallback(parent->i_sb) &&
+ IS_ENCRYPTED(parent) && fname->cf_name.name &&
+ (fname->hinfo.hash != EXT4_DIRENT_HASH(de) ||
+ fname->hinfo.minor_hash != EXT4_DIRENT_MINOR_HASH(de)))
+ return false;
+ /*
+ * Treat comparison errors as not a match. The
+ * only case where it happens is on a disk
+ * corruption or ENOMEM.
+ */
+
+ return generic_ci_match(parent, fname->usr_fname,
+ &fname->cf_name, de->name,
+ de->name_len) > 0;
}
#endif
@@ -1454,7 +1451,7 @@ static bool ext4_match(struct inode *parent,
}
/*
- * Returns 0 if not found, -1 on failure, and 1 on success
+ * Returns 0 if not found, -EFSCORRUPTED on failure, and 1 on success
*/
int ext4_search_dir(struct buffer_head *bh, char *search_buf, int buf_size,
struct inode *dir, struct ext4_filename *fname,
@@ -1466,16 +1463,16 @@ int ext4_search_dir(struct buffer_head *bh, char *search_buf, int buf_size,
de = (struct ext4_dir_entry_2 *)search_buf;
dlimit = search_buf + buf_size;
- while ((char *) de < dlimit) {
+ while ((char *) de < dlimit - EXT4_BASE_DIR_LEN) {
/* this code is executed quadratically often */
/* do minimal checking `by hand' */
- if ((char *) de + de->name_len <= dlimit &&
+ if (de->name + de->name_len <= dlimit &&
ext4_match(dir, fname, de)) {
/* found a match - just to be sure, do
* a full check */
if (ext4_check_dir_entry(dir, NULL, de, bh, search_buf,
buf_size, offset))
- return -1;
+ return -EFSCORRUPTED;
*res_dir = de;
return 1;
}
@@ -1483,7 +1480,7 @@ int ext4_search_dir(struct buffer_head *bh, char *search_buf, int buf_size,
de_len = ext4_rec_len_from_disk(de->rec_len,
dir->i_sb->s_blocksize);
if (de_len <= 0)
- return -1;
+ return -EFSCORRUPTED;
offset += de_len;
de = (struct ext4_dir_entry_2 *) ((char *) de + de_len);
}
@@ -1544,11 +1541,10 @@ static struct buffer_head *__ext4_find_entry(struct inode *dir,
int has_inline_data = 1;
ret = ext4_find_inline_entry(dir, fname, res_dir,
&has_inline_data);
- if (has_inline_data) {
- if (inlined)
- *inlined = 1;
+ if (inlined)
+ *inlined = has_inline_data;
+ if (has_inline_data || IS_ERR(ret))
goto cleanup_and_exit;
- }
}
if ((namelen <= 2) && (name[0] == '.') &&
@@ -1568,10 +1564,15 @@ static struct buffer_head *__ext4_find_entry(struct inode *dir,
* return. Otherwise, fall back to doing a search the
* old fashioned way.
*/
- if (!IS_ERR(ret) || PTR_ERR(ret) != ERR_BAD_DX_DIR)
+ if (IS_ERR(ret) && PTR_ERR(ret) == ERR_BAD_DX_DIR)
+ dxtrace(printk(KERN_DEBUG "ext4_find_entry: dx failed, "
+ "falling back\n"));
+ else if (!sb_no_casefold_compat_fallback(dir->i_sb) &&
+ *res_dir == NULL && IS_CASEFOLDED(dir))
+ dxtrace(printk(KERN_DEBUG "ext4_find_entry: casefold "
+ "failed, falling back\n"));
+ else
goto cleanup_and_exit;
- dxtrace(printk(KERN_DEBUG "ext4_find_entry: dx failed, "
- "falling back\n"));
ret = NULL;
}
nblocks = dir->i_size >> EXT4_BLOCK_SIZE_BITS(sb);
@@ -1629,15 +1630,17 @@ restart:
}
set_buffer_verified(bh);
i = search_dirblock(bh, dir, fname,
- block << EXT4_BLOCK_SIZE_BITS(sb), res_dir);
+ EXT4_LBLK_TO_B(dir, block), res_dir);
if (i == 1) {
EXT4_I(dir)->i_dir_start_lookup = block;
ret = bh;
goto cleanup_and_exit;
} else {
brelse(bh);
- if (i < 0)
+ if (i < 0) {
+ ret = ERR_PTR(i);
goto cleanup_and_exit;
+ }
}
next:
if (++block >= nblocks)
@@ -1692,7 +1695,6 @@ static struct buffer_head *ext4_lookup_entry(struct inode *dir,
struct buffer_head *bh;
err = ext4_fname_prepare_lookup(dir, dentry, &fname);
- generic_set_encrypted_ci_d_ops(dentry);
if (err == -ENOENT)
return NULL;
if (err)
@@ -1708,7 +1710,6 @@ static struct buffer_head * ext4_dx_find_entry(struct inode *dir,
struct ext4_filename *fname,
struct ext4_dir_entry_2 **res_dir)
{
- struct super_block * sb = dir->i_sb;
struct dx_frame frames[EXT4_HTREE_LEVEL], *frame;
struct buffer_head *bh;
ext4_lblk_t block;
@@ -1719,7 +1720,7 @@ static struct buffer_head * ext4_dx_find_entry(struct inode *dir,
#endif
frame = dx_probe(fname, dir, NULL, frames);
if (IS_ERR(frame))
- return (struct buffer_head *) frame;
+ return ERR_CAST(frame);
do {
block = dx_get_block(frame->at);
bh = ext4_read_dirblock(dir, block, DIRENT_HTREE);
@@ -1727,12 +1728,11 @@ static struct buffer_head * ext4_dx_find_entry(struct inode *dir,
goto errout;
retval = search_dirblock(bh, dir, fname,
- block << EXT4_BLOCK_SIZE_BITS(sb),
- res_dir);
+ EXT4_LBLK_TO_B(dir, block), res_dir);
if (retval == 1)
goto success;
brelse(bh);
- if (retval == -1) {
+ if (retval < 0) {
bh = ERR_PTR(ERR_BAD_DX_DIR);
goto errout;
}
@@ -1760,7 +1760,7 @@ success:
static struct dentry *ext4_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags)
{
struct inode *inode;
- struct ext4_dir_entry_2 *de;
+ struct ext4_dir_entry_2 *de = NULL;
struct buffer_head *bh;
if (dentry->d_name.len > EXT4_NAME_LEN)
@@ -1800,8 +1800,7 @@ static struct dentry *ext4_lookup(struct inode *dir, struct dentry *dentry, unsi
}
}
-#ifdef CONFIG_UNICODE
- if (!inode && IS_CASEFOLDED(dir)) {
+ if (IS_ENABLED(CONFIG_UNICODE) && !inode && IS_CASEFOLDED(dir)) {
/* Eventually we want to call d_add_ci(dentry, NULL)
* for negative dentries in the encoding case as
* well. For now, prevent the negative dentry
@@ -1809,7 +1808,7 @@ static struct dentry *ext4_lookup(struct inode *dir, struct dentry *dentry, unsi
*/
return NULL;
}
-#endif
+
return d_splice_alias(inode, dentry);
}
@@ -1817,7 +1816,7 @@ static struct dentry *ext4_lookup(struct inode *dir, struct dentry *dentry, unsi
struct dentry *ext4_get_parent(struct dentry *child)
{
__u32 ino;
- struct ext4_dir_entry_2 * de;
+ struct ext4_dir_entry_2 * de = NULL;
struct buffer_head *bh;
bh = ext4_find_entry(d_inode(child), &dotdot_name, &de, NULL);
@@ -1906,7 +1905,8 @@ static struct ext4_dir_entry_2 *do_split(handle_t *handle, struct inode *dir,
struct dx_hash_info *hinfo)
{
unsigned blocksize = dir->i_sb->s_blocksize;
- unsigned count, continued;
+ unsigned continued;
+ int count;
struct buffer_head *bh2;
ext4_lblk_t newblock;
u32 hash2;
@@ -1917,14 +1917,14 @@ static struct ext4_dir_entry_2 *do_split(handle_t *handle, struct inode *dir,
int csum_size = 0;
int err = 0, i;
- if (ext4_has_metadata_csum(dir->i_sb))
+ if (ext4_has_feature_metadata_csum(dir->i_sb))
csum_size = sizeof(struct ext4_dir_entry_tail);
bh2 = ext4_append(handle, dir, &newblock);
if (IS_ERR(bh2)) {
brelse(*bh);
*bh = NULL;
- return (struct ext4_dir_entry_2 *) bh2;
+ return ERR_CAST(bh2);
}
BUFFER_TRACE(*bh, "get_write_access");
@@ -1943,8 +1943,11 @@ static struct ext4_dir_entry_2 *do_split(handle_t *handle, struct inode *dir,
/* create map in the end of data2 block */
map = (struct dx_map_entry *) (data2 + blocksize);
- count = dx_make_map(dir, (struct ext4_dir_entry_2 *) data1,
- blocksize, hinfo, map);
+ count = dx_make_map(dir, *bh, hinfo, map);
+ if (count < 0) {
+ err = count;
+ goto journal_error;
+ }
map -= count;
dx_sort_map(map, count);
/* Ensure that neither split block is over half full */
@@ -1964,11 +1967,20 @@ static struct ext4_dir_entry_2 *do_split(handle_t *handle, struct inode *dir,
* split it in half by count; each resulting block will have at least
* half the space free.
*/
- if (i > 0)
+ if (i >= 0)
split = count - move;
else
split = count/2;
+ if (WARN_ON_ONCE(split == 0)) {
+ /* Should never happen, but avoid out-of-bounds access below */
+ ext4_error_inode_block(dir, (*bh)->b_blocknr, 0,
+ "bad indexed directory? hash=%08x:%08x count=%d move=%u",
+ hinfo->hash, hinfo->minor_hash, count, move);
+ err = -EFSCORRUPTED;
+ goto out;
+ }
+
hash2 = map[split].hash;
continued = hash2 == map[split - 1].hash;
dxtrace(printk(KERN_INFO "Split block %lu at %x, %i/%i\n",
@@ -2012,15 +2024,15 @@ static struct ext4_dir_entry_2 *do_split(handle_t *handle, struct inode *dir,
return de;
journal_error:
+ ext4_std_error(dir->i_sb, err);
+out:
brelse(*bh);
brelse(bh2);
*bh = NULL;
- ext4_std_error(dir->i_sb, err);
return ERR_PTR(err);
}
-int ext4_find_dest_de(struct inode *dir, struct inode *inode,
- struct buffer_head *bh,
+int ext4_find_dest_de(struct inode *dir, struct buffer_head *bh,
void *buf, int buf_size,
struct ext4_filename *fname,
struct ext4_dir_entry_2 **dest_de)
@@ -2031,7 +2043,7 @@ int ext4_find_dest_de(struct inode *dir, struct inode *inode,
unsigned int offset = 0;
char *top;
- de = (struct ext4_dir_entry_2 *)buf;
+ de = buf;
top = buf + buf_size - reclen;
while ((char *) de <= top) {
if (ext4_check_dir_entry(dir, NULL, de, bh,
@@ -2102,11 +2114,11 @@ static int add_dirent_to_buf(handle_t *handle, struct ext4_filename *fname,
int csum_size = 0;
int err, err2;
- if (ext4_has_metadata_csum(inode->i_sb))
+ if (ext4_has_feature_metadata_csum(inode->i_sb))
csum_size = sizeof(struct ext4_dir_entry_tail);
if (!de) {
- err = ext4_find_dest_de(dir, inode, bh, bh->b_data,
+ err = ext4_find_dest_de(dir, bh, bh->b_data,
blocksize - csum_size, fname, &de);
if (err)
return err;
@@ -2133,7 +2145,7 @@ static int add_dirent_to_buf(handle_t *handle, struct ext4_filename *fname,
* happen is that the times are slightly out of date
* and/or different from the directory change time.
*/
- dir->i_mtime = dir->i_ctime = current_time(dir);
+ inode_set_mtime_to_ts(dir, inode_set_ctime_current(dir));
ext4_update_dx_flag(dir);
inode_inc_iversion(dir);
err2 = ext4_mark_inode_dirty(handle, dir);
@@ -2144,6 +2156,52 @@ static int add_dirent_to_buf(handle_t *handle, struct ext4_filename *fname,
return err ? err : err2;
}
+static bool ext4_check_dx_root(struct inode *dir, struct dx_root *root)
+{
+ struct fake_dirent *fde;
+ const char *error_msg;
+ unsigned int rlen;
+ unsigned int blocksize = dir->i_sb->s_blocksize;
+ char *blockend = (char *)root + dir->i_sb->s_blocksize;
+
+ fde = &root->dot;
+ if (unlikely(fde->name_len != 1)) {
+ error_msg = "invalid name_len for '.'";
+ goto corrupted;
+ }
+ if (unlikely(strncmp(root->dot_name, ".", fde->name_len))) {
+ error_msg = "invalid name for '.'";
+ goto corrupted;
+ }
+ rlen = ext4_rec_len_from_disk(fde->rec_len, blocksize);
+ if (unlikely((char *)fde + rlen >= blockend)) {
+ error_msg = "invalid rec_len for '.'";
+ goto corrupted;
+ }
+
+ fde = &root->dotdot;
+ if (unlikely(fde->name_len != 2)) {
+ error_msg = "invalid name_len for '..'";
+ goto corrupted;
+ }
+ if (unlikely(strncmp(root->dotdot_name, "..", fde->name_len))) {
+ error_msg = "invalid name for '..'";
+ goto corrupted;
+ }
+ rlen = ext4_rec_len_from_disk(fde->rec_len, blocksize);
+ if (unlikely((char *)fde + rlen >= blockend)) {
+ error_msg = "invalid rec_len for '..'";
+ goto corrupted;
+ }
+
+ return true;
+
+corrupted:
+ EXT4_ERROR_INODE(dir, "Corrupt dir, %s, running e2fsck is recommended",
+ error_msg);
+ return false;
+}
+
/*
* This converts a one block unindexed directory to a 3 block indexed
* directory, and adds the dentry to the indexed directory.
@@ -2165,7 +2223,7 @@ static int make_indexed_dir(handle_t *handle, struct ext4_filename *fname,
struct fake_dirent *fde;
int csum_size = 0;
- if (ext4_has_metadata_csum(inode->i_sb))
+ if (ext4_has_feature_metadata_csum(inode->i_sb))
csum_size = sizeof(struct ext4_dir_entry_tail);
blocksize = dir->i_sb->s_blocksize;
@@ -2178,17 +2236,17 @@ static int make_indexed_dir(handle_t *handle, struct ext4_filename *fname,
brelse(bh);
return retval;
}
+
root = (struct dx_root *) bh->b_data;
+ if (!ext4_check_dx_root(dir, root)) {
+ brelse(bh);
+ return -EFSCORRUPTED;
+ }
/* The 0th block becomes the root, move the dirents out */
fde = &root->dotdot;
de = (struct ext4_dir_entry_2 *)((char *)fde +
ext4_rec_len_from_disk(fde->rec_len, blocksize));
- if ((char *) de >= (((char *) root) + blocksize)) {
- EXT4_ERROR_INODE(dir, "invalid rec_len for '..'");
- brelse(bh);
- return -EFSCORRUPTED;
- }
len = ((char *) root) + (blocksize - csum_size) - (char *) de;
/* Allocate new block for the 0th block's dirents */
@@ -2204,8 +2262,15 @@ static int make_indexed_dir(handle_t *handle, struct ext4_filename *fname,
memset(de, 0, len); /* wipe old data */
de = (struct ext4_dir_entry_2 *) data2;
top = data2 + len;
- while ((char *)(de2 = ext4_next_entry(de, blocksize)) < top)
+ while ((char *)(de2 = ext4_next_entry(de, blocksize)) < top) {
+ if (ext4_check_dir_entry(dir, NULL, de, bh2, data2, len,
+ (char *)de - data2)) {
+ brelse(bh2);
+ brelse(bh);
+ return -EFSCORRUPTED;
+ }
de = de2;
+ }
de->rec_len = ext4_rec_len_to_disk(data2 + (blocksize - csum_size) -
(char *) de, blocksize);
@@ -2236,10 +2301,15 @@ static int make_indexed_dir(handle_t *handle, struct ext4_filename *fname,
fname->hinfo.seed = EXT4_SB(dir->i_sb)->s_hash_seed;
/* casefolded encrypted hashes are computed on fname setup */
- if (!ext4_hash_in_dirent(dir))
- ext4fs_dirhash(dir, fname_name(fname),
- fname_len(fname), &fname->hinfo);
-
+ if (!ext4_hash_in_dirent(dir)) {
+ int err = ext4fs_dirhash(dir, fname_name(fname),
+ fname_len(fname), &fname->hinfo);
+ if (err < 0) {
+ brelse(bh2);
+ brelse(bh);
+ return err;
+ }
+ }
memset(frames, 0, sizeof(frames));
frame = frames;
frame->entries = entries;
@@ -2297,22 +2367,17 @@ static int ext4_add_entry(handle_t *handle, struct dentry *dentry,
ext4_lblk_t block, blocks;
int csum_size = 0;
- if (ext4_has_metadata_csum(inode->i_sb))
+ if (ext4_has_feature_metadata_csum(inode->i_sb))
csum_size = sizeof(struct ext4_dir_entry_tail);
sb = dir->i_sb;
blocksize = sb->s_blocksize;
- if (!dentry->d_name.len)
- return -EINVAL;
if (fscrypt_is_nokey_name(dentry))
return -ENOKEY;
-#ifdef CONFIG_UNICODE
- if (sb_has_strict_encoding(sb) && IS_CASEFOLDED(dir) &&
- sb->s_encoding && utf8_validate(sb->s_encoding, &dentry->d_name))
+ if (!generic_ci_validate_strict_name(dir, &dentry->d_name))
return -EINVAL;
-#endif
retval = ext4_fname_setup_filename(dir, &dentry->d_name, 0, &fname);
if (retval)
@@ -2333,7 +2398,7 @@ static int ext4_add_entry(handle_t *handle, struct dentry *dentry,
if (!retval || (retval != ERR_BAD_DX_DIR))
goto out;
/* Can we just ignore htree data? */
- if (ext4_has_metadata_csum(sb)) {
+ if (ext4_has_feature_metadata_csum(sb)) {
EXT4_ERROR_INODE(dir,
"Directory has corrupted htree index.");
retval = -EFSCORRUPTED;
@@ -2483,8 +2548,10 @@ again:
BUFFER_TRACE(frame->bh, "get_write_access");
err = ext4_journal_get_write_access(handle, sb, frame->bh,
EXT4_JTR_NONE);
- if (err)
+ if (err) {
+ brelse(bh2);
goto journal_error;
+ }
if (!add_level) {
unsigned icount1 = icount/2, icount2 = icount - icount1;
unsigned hash2 = dx_get_hash(entries + icount1);
@@ -2495,8 +2562,10 @@ again:
err = ext4_journal_get_write_access(handle, sb,
(frame - 1)->bh,
EXT4_JTR_NONE);
- if (err)
+ if (err) {
+ brelse(bh2);
goto journal_error;
+ }
memcpy((char *) entries2, (char *) (entries + icount1),
icount2 * sizeof(struct dx_entry));
@@ -2515,8 +2584,10 @@ again:
dxtrace(dx_show_index("node",
((struct dx_node *) bh2->b_data)->entries));
err = ext4_handle_dirty_dx_node(handle, dir, bh2);
- if (err)
+ if (err) {
+ brelse(bh2);
goto journal_error;
+ }
brelse (bh2);
err = ext4_handle_dirty_dx_node(handle, dir,
(frame - 1)->bh);
@@ -2541,8 +2612,10 @@ again:
"Creating %d level index...\n",
dxroot->info.indirect_levels));
err = ext4_handle_dirty_dx_node(handle, dir, frame->bh);
- if (err)
+ if (err) {
+ brelse(bh2);
goto journal_error;
+ }
err = ext4_handle_dirty_dx_node(handle, dir, bh2);
brelse(bh2);
restart = 1;
@@ -2587,7 +2660,7 @@ int ext4_generic_delete_entry(struct inode *dir,
i = 0;
pde = NULL;
- de = (struct ext4_dir_entry_2 *)entry_buf;
+ de = entry_buf;
while (i < buf_size - csum_size) {
if (ext4_check_dir_entry(dir, NULL, de, bh,
entry_buf, buf_size, i))
@@ -2639,7 +2712,7 @@ static int ext4_delete_entry(handle_t *handle,
return err;
}
- if (ext4_has_metadata_csum(dir->i_sb))
+ if (ext4_has_feature_metadata_csum(dir->i_sb))
csum_size = sizeof(struct ext4_dir_entry_tail);
BUFFER_TRACE(bh, "get_write_access");
@@ -2716,6 +2789,7 @@ static int ext4_add_nondir(handle_t *handle,
return err;
}
drop_nlink(inode);
+ ext4_mark_inode_dirty(handle, inode);
ext4_orphan_add(handle, inode);
unlock_new_inode(inode);
return err;
@@ -2729,7 +2803,7 @@ static int ext4_add_nondir(handle_t *handle,
* If the create succeeds, we fill in the inode information
* with d_instantiate().
*/
-static int ext4_create(struct user_namespace *mnt_userns, struct inode *dir,
+static int ext4_create(struct mnt_idmap *idmap, struct inode *dir,
struct dentry *dentry, umode_t mode, bool excl)
{
handle_t *handle;
@@ -2743,7 +2817,7 @@ static int ext4_create(struct user_namespace *mnt_userns, struct inode *dir,
credits = (EXT4_DATA_TRANS_BLOCKS(dir->i_sb) +
EXT4_INDEX_EXTRA_TRANS_BLOCKS + 3);
retry:
- inode = ext4_new_inode_start_handle(mnt_userns, dir, mode, &dentry->d_name,
+ inode = ext4_new_inode_start_handle(idmap, dir, mode, &dentry->d_name,
0, NULL, EXT4_HT_DIR, credits);
handle = ext4_journal_current_handle();
err = PTR_ERR(inode);
@@ -2764,7 +2838,7 @@ retry:
return err;
}
-static int ext4_mknod(struct user_namespace *mnt_userns, struct inode *dir,
+static int ext4_mknod(struct mnt_idmap *idmap, struct inode *dir,
struct dentry *dentry, umode_t mode, dev_t rdev)
{
handle_t *handle;
@@ -2778,7 +2852,7 @@ static int ext4_mknod(struct user_namespace *mnt_userns, struct inode *dir,
credits = (EXT4_DATA_TRANS_BLOCKS(dir->i_sb) +
EXT4_INDEX_EXTRA_TRANS_BLOCKS + 3);
retry:
- inode = ext4_new_inode_start_handle(mnt_userns, dir, mode, &dentry->d_name,
+ inode = ext4_new_inode_start_handle(idmap, dir, mode, &dentry->d_name,
0, NULL, EXT4_HT_DIR, credits);
handle = ext4_journal_current_handle();
err = PTR_ERR(inode);
@@ -2798,8 +2872,8 @@ retry:
return err;
}
-static int ext4_tmpfile(struct user_namespace *mnt_userns, struct inode *dir,
- struct dentry *dentry, umode_t mode)
+static int ext4_tmpfile(struct mnt_idmap *idmap, struct inode *dir,
+ struct file *file, umode_t mode)
{
handle_t *handle;
struct inode *inode;
@@ -2810,10 +2884,10 @@ static int ext4_tmpfile(struct user_namespace *mnt_userns, struct inode *dir,
return err;
retry:
- inode = ext4_new_inode_start_handle(mnt_userns, dir, mode,
+ inode = ext4_new_inode_start_handle(idmap, dir, mode,
NULL, 0, NULL,
EXT4_HT_DIR,
- EXT4_MAXQUOTAS_INIT_BLOCKS(dir->i_sb) +
+ EXT4_MAXQUOTAS_TRANS_BLOCKS(dir->i_sb) +
4 + EXT4_XATTR_TRANS_BLOCKS);
handle = ext4_journal_current_handle();
err = PTR_ERR(inode);
@@ -2821,7 +2895,7 @@ retry:
inode->i_op = &ext4_file_inode_operations;
inode->i_fop = &ext4_file_operations;
ext4_set_aops(inode);
- d_tmpfile(dentry, inode);
+ d_tmpfile(file, inode);
err = ext4_orphan_add(handle, inode);
if (err)
goto err_unlock_inode;
@@ -2832,55 +2906,66 @@ retry:
ext4_journal_stop(handle);
if (err == -ENOSPC && ext4_should_retry_alloc(dir->i_sb, &retries))
goto retry;
- return err;
+ return finish_open_simple(file, err);
err_unlock_inode:
ext4_journal_stop(handle);
unlock_new_inode(inode);
return err;
}
-struct ext4_dir_entry_2 *ext4_init_dot_dotdot(struct inode *inode,
- struct ext4_dir_entry_2 *de,
- int blocksize, int csum_size,
- unsigned int parent_ino, int dotdot_real_len)
+int ext4_init_dirblock(handle_t *handle, struct inode *inode,
+ struct buffer_head *bh, unsigned int parent_ino,
+ void *inline_buf, int inline_size)
{
+ struct ext4_dir_entry_2 *de = (struct ext4_dir_entry_2 *) bh->b_data;
+ size_t blocksize = bh->b_size;
+ int csum_size = 0, header_size;
+
+ if (ext4_has_feature_metadata_csum(inode->i_sb))
+ csum_size = sizeof(struct ext4_dir_entry_tail);
+
de->inode = cpu_to_le32(inode->i_ino);
de->name_len = 1;
de->rec_len = ext4_rec_len_to_disk(ext4_dir_rec_len(de->name_len, NULL),
blocksize);
- strcpy(de->name, ".");
+ memcpy(de->name, ".", 2);
ext4_set_de_type(inode->i_sb, de, S_IFDIR);
de = ext4_next_entry(de, blocksize);
de->inode = cpu_to_le32(parent_ino);
de->name_len = 2;
- if (!dotdot_real_len)
- de->rec_len = ext4_rec_len_to_disk(blocksize -
- (csum_size + ext4_dir_rec_len(1, NULL)),
- blocksize);
- else
+ memcpy(de->name, "..", 3);
+ ext4_set_de_type(inode->i_sb, de, S_IFDIR);
+ if (inline_buf) {
de->rec_len = ext4_rec_len_to_disk(
ext4_dir_rec_len(de->name_len, NULL),
blocksize);
- strcpy(de->name, "..");
- ext4_set_de_type(inode->i_sb, de, S_IFDIR);
+ de = ext4_next_entry(de, blocksize);
+ header_size = (char *)de - bh->b_data;
+ memcpy((void *)de, inline_buf, inline_size);
+ ext4_update_final_de(bh->b_data, inline_size + header_size,
+ blocksize - csum_size);
+ } else {
+ de->rec_len = ext4_rec_len_to_disk(blocksize -
+ (csum_size + ext4_dir_rec_len(1, NULL)),
+ blocksize);
+ }
- return ext4_next_entry(de, blocksize);
+ if (csum_size)
+ ext4_initialize_dirent_tail(bh, blocksize);
+ BUFFER_TRACE(dir_block, "call ext4_handle_dirty_metadata");
+ set_buffer_uptodate(bh);
+ set_buffer_verified(bh);
+ return ext4_handle_dirty_dirblock(handle, inode, bh);
}
int ext4_init_new_dir(handle_t *handle, struct inode *dir,
struct inode *inode)
{
struct buffer_head *dir_block = NULL;
- struct ext4_dir_entry_2 *de;
ext4_lblk_t block = 0;
- unsigned int blocksize = dir->i_sb->s_blocksize;
- int csum_size = 0;
int err;
- if (ext4_has_metadata_csum(dir->i_sb))
- csum_size = sizeof(struct ext4_dir_entry_tail);
-
if (ext4_test_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA)) {
err = ext4_try_create_inline_dir(handle, dir, inode);
if (err < 0 && err != -ENOSPC)
@@ -2889,44 +2974,35 @@ int ext4_init_new_dir(handle_t *handle, struct inode *dir,
goto out;
}
+ set_nlink(inode, 2);
inode->i_size = 0;
dir_block = ext4_append(handle, inode, &block);
if (IS_ERR(dir_block))
return PTR_ERR(dir_block);
- de = (struct ext4_dir_entry_2 *)dir_block->b_data;
- ext4_init_dot_dotdot(inode, de, blocksize, csum_size, dir->i_ino, 0);
- set_nlink(inode, 2);
- if (csum_size)
- ext4_initialize_dirent_tail(dir_block, blocksize);
-
- BUFFER_TRACE(dir_block, "call ext4_handle_dirty_metadata");
- err = ext4_handle_dirty_dirblock(handle, inode, dir_block);
- if (err)
- goto out;
- set_buffer_verified(dir_block);
+ err = ext4_init_dirblock(handle, inode, dir_block, dir->i_ino, NULL, 0);
out:
brelse(dir_block);
return err;
}
-static int ext4_mkdir(struct user_namespace *mnt_userns, struct inode *dir,
- struct dentry *dentry, umode_t mode)
+static struct dentry *ext4_mkdir(struct mnt_idmap *idmap, struct inode *dir,
+ struct dentry *dentry, umode_t mode)
{
handle_t *handle;
struct inode *inode;
int err, err2 = 0, credits, retries = 0;
if (EXT4_DIR_LINK_MAX(dir))
- return -EMLINK;
+ return ERR_PTR(-EMLINK);
err = dquot_initialize(dir);
if (err)
- return err;
+ return ERR_PTR(err);
credits = (EXT4_DATA_TRANS_BLOCKS(dir->i_sb) +
EXT4_INDEX_EXTRA_TRANS_BLOCKS + 3);
retry:
- inode = ext4_new_inode_start_handle(mnt_userns, dir, S_IFDIR | mode,
+ inode = ext4_new_inode_start_handle(idmap, dir, S_IFDIR | mode,
&dentry->d_name,
0, NULL, EXT4_HT_DIR, credits);
handle = ext4_journal_current_handle();
@@ -2971,7 +3047,7 @@ out_stop:
out_retry:
if (err == -ENOSPC && ext4_should_retry_alloc(dir->i_sb, &retries))
goto retry;
- return err;
+ return ERR_PTR(err);
}
/*
@@ -2997,31 +3073,30 @@ bool ext4_empty_dir(struct inode *inode)
if (inode->i_size < ext4_dir_rec_len(1, NULL) +
ext4_dir_rec_len(2, NULL)) {
EXT4_ERROR_INODE(inode, "invalid size");
- return true;
+ return false;
}
- /* The first directory block must not be a hole,
- * so treat it as DIRENT_HTREE
- */
- bh = ext4_read_dirblock(inode, 0, DIRENT_HTREE);
+ bh = ext4_read_dirblock(inode, 0, EITHER);
if (IS_ERR(bh))
- return true;
+ return false;
de = (struct ext4_dir_entry_2 *) bh->b_data;
if (ext4_check_dir_entry(inode, NULL, de, bh, bh->b_data, bh->b_size,
0) ||
- le32_to_cpu(de->inode) != inode->i_ino || strcmp(".", de->name)) {
+ le32_to_cpu(de->inode) != inode->i_ino || de->name_len != 1 ||
+ de->name[0] != '.') {
ext4_warning_inode(inode, "directory missing '.'");
brelse(bh);
- return true;
+ return false;
}
offset = ext4_rec_len_from_disk(de->rec_len, sb->s_blocksize);
de = ext4_next_entry(de, sb->s_blocksize);
if (ext4_check_dir_entry(inode, NULL, de, bh, bh->b_data, bh->b_size,
offset) ||
- le32_to_cpu(de->inode) == 0 || strcmp("..", de->name)) {
+ le32_to_cpu(de->inode) == 0 || de->name_len != 2 ||
+ de->name[0] != '.' || de->name[1] != '.') {
ext4_warning_inode(inode, "directory missing '..'");
brelse(bh);
- return true;
+ return false;
}
offset += ext4_rec_len_from_disk(de->rec_len, sb->s_blocksize);
while (offset < inode->i_size) {
@@ -3035,16 +3110,13 @@ bool ext4_empty_dir(struct inode *inode)
continue;
}
if (IS_ERR(bh))
- return true;
+ return false;
}
de = (struct ext4_dir_entry_2 *) (bh->b_data +
(offset & (sb->s_blocksize - 1)));
if (ext4_check_dir_entry(inode, NULL, de, bh,
- bh->b_data, bh->b_size, offset)) {
- offset = (offset | (sb->s_blocksize - 1)) + 1;
- continue;
- }
- if (le32_to_cpu(de->inode)) {
+ bh->b_data, bh->b_size, offset) ||
+ le32_to_cpu(de->inode)) {
brelse(bh);
return false;
}
@@ -3059,11 +3131,12 @@ static int ext4_rmdir(struct inode *dir, struct dentry *dentry)
int retval;
struct inode *inode;
struct buffer_head *bh;
- struct ext4_dir_entry_2 *de;
+ struct ext4_dir_entry_2 *de = NULL;
handle_t *handle = NULL;
- if (unlikely(ext4_forced_shutdown(EXT4_SB(dir->i_sb))))
- return -EIO;
+ retval = ext4_emergency_state(dir->i_sb);
+ if (unlikely(retval))
+ return retval;
/* Initialize quotas before so that eventual writes go in
* separate transaction */
@@ -3117,7 +3190,8 @@ static int ext4_rmdir(struct inode *dir, struct dentry *dentry)
* recovery. */
inode->i_size = 0;
ext4_orphan_add(handle, inode);
- inode->i_ctime = dir->i_ctime = dir->i_mtime = current_time(inode);
+ inode_set_mtime_to_ts(dir, inode_set_ctime_current(dir));
+ inode_set_ctime_current(inode);
retval = ext4_mark_inode_dirty(handle, inode);
if (retval)
goto end_rmdir;
@@ -3126,16 +3200,14 @@ static int ext4_rmdir(struct inode *dir, struct dentry *dentry)
ext4_fc_track_unlink(handle, dentry);
retval = ext4_mark_inode_dirty(handle, dir);
-#ifdef CONFIG_UNICODE
/* VFS negative dentries are incompatible with Encoding and
* Case-insensitiveness. Eventually we'll want avoid
* invalidating the dentries here, alongside with returning the
* negative dentries at ext4_lookup(), when it is better
* supported by the VFS for the CI case.
*/
- if (IS_CASEFOLDED(dir))
+ if (IS_ENABLED(CONFIG_UNICODE) && IS_CASEFOLDED(dir))
d_invalidate(dentry);
-#endif
end_rmdir:
brelse(bh);
@@ -3144,14 +3216,20 @@ end_rmdir:
return retval;
}
-int __ext4_unlink(handle_t *handle, struct inode *dir, const struct qstr *d_name,
- struct inode *inode)
+int __ext4_unlink(struct inode *dir, const struct qstr *d_name,
+ struct inode *inode,
+ struct dentry *dentry /* NULL during fast_commit recovery */)
{
int retval = -ENOENT;
struct buffer_head *bh;
- struct ext4_dir_entry_2 *de;
+ struct ext4_dir_entry_2 *de = NULL;
+ handle_t *handle;
int skip_remove_dentry = 0;
+ /*
+ * Keep this outside the transaction; it may have to set up the
+ * directory's encryption key, which isn't GFP_NOFS-safe.
+ */
bh = ext4_find_entry(dir, d_name, &de, NULL);
if (IS_ERR(bh))
return PTR_ERR(bh);
@@ -3168,7 +3246,14 @@ int __ext4_unlink(handle_t *handle, struct inode *dir, const struct qstr *d_name
if (EXT4_SB(inode->i_sb)->s_mount_state & EXT4_FC_REPLAY)
skip_remove_dentry = 1;
else
- goto out;
+ goto out_bh;
+ }
+
+ handle = ext4_journal_start(dir, EXT4_HT_DIR,
+ EXT4_DATA_TRANS_BLOCKS(dir->i_sb));
+ if (IS_ERR(handle)) {
+ retval = PTR_ERR(handle);
+ goto out_bh;
}
if (IS_DIRSYNC(dir))
@@ -3177,12 +3262,12 @@ int __ext4_unlink(handle_t *handle, struct inode *dir, const struct qstr *d_name
if (!skip_remove_dentry) {
retval = ext4_delete_entry(handle, dir, de, bh);
if (retval)
- goto out;
- dir->i_ctime = dir->i_mtime = current_time(dir);
+ goto out_handle;
+ inode_set_mtime_to_ts(dir, inode_set_ctime_current(dir));
ext4_update_dx_flag(dir);
retval = ext4_mark_inode_dirty(handle, dir);
if (retval)
- goto out;
+ goto out_handle;
} else {
retval = 0;
}
@@ -3193,21 +3278,24 @@ int __ext4_unlink(handle_t *handle, struct inode *dir, const struct qstr *d_name
drop_nlink(inode);
if (!inode->i_nlink)
ext4_orphan_add(handle, inode);
- inode->i_ctime = current_time(inode);
+ inode_set_ctime_current(inode);
retval = ext4_mark_inode_dirty(handle, inode);
-
-out:
+ if (dentry && !retval)
+ ext4_fc_track_unlink(handle, dentry);
+out_handle:
+ ext4_journal_stop(handle);
+out_bh:
brelse(bh);
return retval;
}
static int ext4_unlink(struct inode *dir, struct dentry *dentry)
{
- handle_t *handle;
int retval;
- if (unlikely(ext4_forced_shutdown(EXT4_SB(dir->i_sb))))
- return -EIO;
+ retval = ext4_emergency_state(dir->i_sb);
+ if (unlikely(retval))
+ return retval;
trace_ext4_unlink_enter(dir, dentry);
/*
@@ -3221,35 +3309,49 @@ static int ext4_unlink(struct inode *dir, struct dentry *dentry)
if (retval)
goto out_trace;
- handle = ext4_journal_start(dir, EXT4_HT_DIR,
- EXT4_DATA_TRANS_BLOCKS(dir->i_sb));
- if (IS_ERR(handle)) {
- retval = PTR_ERR(handle);
- goto out_trace;
- }
+ retval = __ext4_unlink(dir, &dentry->d_name, d_inode(dentry), dentry);
- retval = __ext4_unlink(handle, dir, &dentry->d_name, d_inode(dentry));
- if (!retval)
- ext4_fc_track_unlink(handle, dentry);
-#ifdef CONFIG_UNICODE
/* VFS negative dentries are incompatible with Encoding and
* Case-insensitiveness. Eventually we'll want avoid
* invalidating the dentries here, alongside with returning the
* negative dentries at ext4_lookup(), when it is better
* supported by the VFS for the CI case.
*/
- if (IS_CASEFOLDED(dir))
+ if (IS_ENABLED(CONFIG_UNICODE) && IS_CASEFOLDED(dir))
d_invalidate(dentry);
-#endif
- if (handle)
- ext4_journal_stop(handle);
out_trace:
trace_ext4_unlink_exit(dentry, retval);
return retval;
}
-static int ext4_symlink(struct user_namespace *mnt_userns, struct inode *dir,
+static int ext4_init_symlink_block(handle_t *handle, struct inode *inode,
+ struct fscrypt_str *disk_link)
+{
+ struct buffer_head *bh;
+ char *kaddr;
+ int err = 0;
+
+ bh = ext4_bread(handle, inode, 0, EXT4_GET_BLOCKS_CREATE);
+ if (IS_ERR(bh))
+ return PTR_ERR(bh);
+
+ BUFFER_TRACE(bh, "get_write_access");
+ err = ext4_journal_get_write_access(handle, inode->i_sb, bh, EXT4_JTR_NONE);
+ if (err)
+ goto out;
+
+ kaddr = (char *)bh->b_data;
+ memcpy(kaddr, disk_link->name, disk_link->len);
+ inode->i_size = disk_link->len - 1;
+ EXT4_I(inode)->i_disksize = inode->i_size;
+ err = ext4_handle_dirty_metadata(handle, inode, bh);
+out:
+ brelse(bh);
+ return err;
+}
+
+static int ext4_symlink(struct mnt_idmap *idmap, struct inode *dir,
struct dentry *dentry, const char *symname)
{
handle_t *handle;
@@ -3257,9 +3359,11 @@ static int ext4_symlink(struct user_namespace *mnt_userns, struct inode *dir,
int err, len = strlen(symname);
int credits;
struct fscrypt_str disk_link;
+ int retries = 0;
- if (unlikely(ext4_forced_shutdown(EXT4_SB(dir->i_sb))))
- return -EIO;
+ err = ext4_emergency_state(dir->i_sb);
+ if (unlikely(err))
+ return err;
err = fscrypt_prepare_symlink(dir, symname, len, dir->i_sb->s_blocksize,
&disk_link);
@@ -3270,34 +3374,24 @@ static int ext4_symlink(struct user_namespace *mnt_userns, struct inode *dir,
if (err)
return err;
- if ((disk_link.len > EXT4_N_BLOCKS * 4)) {
- /*
- * For non-fast symlinks, we just allocate inode and put it on
- * orphan list in the first transaction => we need bitmap,
- * group descriptor, sb, inode block, quota blocks, and
- * possibly selinux xattr blocks.
- */
- credits = 4 + EXT4_MAXQUOTAS_INIT_BLOCKS(dir->i_sb) +
- EXT4_XATTR_TRANS_BLOCKS;
- } else {
- /*
- * Fast symlink. We have to add entry to directory
- * (EXT4_DATA_TRANS_BLOCKS + EXT4_INDEX_EXTRA_TRANS_BLOCKS),
- * allocate new inode (bitmap, group descriptor, inode block,
- * quota blocks, sb is already counted in previous macros).
- */
- credits = EXT4_DATA_TRANS_BLOCKS(dir->i_sb) +
- EXT4_INDEX_EXTRA_TRANS_BLOCKS + 3;
- }
-
- inode = ext4_new_inode_start_handle(mnt_userns, dir, S_IFLNK|S_IRWXUGO,
+ /*
+ * EXT4_INDEX_EXTRA_TRANS_BLOCKS for addition of entry into the
+ * directory. +3 for inode, inode bitmap, group descriptor allocation.
+ * EXT4_DATA_TRANS_BLOCKS for the data block allocation and
+ * modification.
+ */
+ credits = EXT4_DATA_TRANS_BLOCKS(dir->i_sb) +
+ EXT4_INDEX_EXTRA_TRANS_BLOCKS + 3;
+retry:
+ inode = ext4_new_inode_start_handle(idmap, dir, S_IFLNK|S_IRWXUGO,
&dentry->d_name, 0, NULL,
EXT4_HT_DIR, credits);
handle = ext4_journal_current_handle();
if (IS_ERR(inode)) {
if (handle)
ext4_journal_stop(handle);
- return PTR_ERR(inode);
+ err = PTR_ERR(inode);
+ goto out_retry;
}
if (IS_ENCRYPTED(inode)) {
@@ -3305,75 +3399,47 @@ static int ext4_symlink(struct user_namespace *mnt_userns, struct inode *dir,
if (err)
goto err_drop_inode;
inode->i_op = &ext4_encrypted_symlink_inode_operations;
+ } else {
+ if ((disk_link.len > EXT4_N_BLOCKS * 4)) {
+ inode->i_op = &ext4_symlink_inode_operations;
+ } else {
+ inode->i_op = &ext4_fast_symlink_inode_operations;
+ }
}
if ((disk_link.len > EXT4_N_BLOCKS * 4)) {
- if (!IS_ENCRYPTED(inode))
- inode->i_op = &ext4_symlink_inode_operations;
- inode_nohighmem(inode);
- ext4_set_aops(inode);
- /*
- * We cannot call page_symlink() with transaction started
- * because it calls into ext4_write_begin() which can wait
- * for transaction commit if we are running out of space
- * and thus we deadlock. So we have to stop transaction now
- * and restart it when symlink contents is written.
- *
- * To keep fs consistent in case of crash, we have to put inode
- * to orphan list in the mean time.
- */
- drop_nlink(inode);
- err = ext4_orphan_add(handle, inode);
- if (handle)
- ext4_journal_stop(handle);
- handle = NULL;
- if (err)
- goto err_drop_inode;
- err = __page_symlink(inode, disk_link.name, disk_link.len, 1);
- if (err)
- goto err_drop_inode;
- /*
- * Now inode is being linked into dir (EXT4_DATA_TRANS_BLOCKS
- * + EXT4_INDEX_EXTRA_TRANS_BLOCKS), inode is also modified
- */
- handle = ext4_journal_start(dir, EXT4_HT_DIR,
- EXT4_DATA_TRANS_BLOCKS(dir->i_sb) +
- EXT4_INDEX_EXTRA_TRANS_BLOCKS + 1);
- if (IS_ERR(handle)) {
- err = PTR_ERR(handle);
- handle = NULL;
- goto err_drop_inode;
- }
- set_nlink(inode, 1);
- err = ext4_orphan_del(handle, inode);
+ /* alloc symlink block and fill it */
+ err = ext4_init_symlink_block(handle, inode, &disk_link);
if (err)
goto err_drop_inode;
} else {
/* clear the extent format for fast symlink */
ext4_clear_inode_flag(inode, EXT4_INODE_EXTENTS);
- if (!IS_ENCRYPTED(inode)) {
- inode->i_op = &ext4_fast_symlink_inode_operations;
- inode->i_link = (char *)&EXT4_I(inode)->i_data;
- }
memcpy((char *)&EXT4_I(inode)->i_data, disk_link.name,
disk_link.len);
inode->i_size = disk_link.len - 1;
+ EXT4_I(inode)->i_disksize = inode->i_size;
+ if (!IS_ENCRYPTED(inode))
+ inode_set_cached_link(inode, (char *)&EXT4_I(inode)->i_data,
+ inode->i_size);
}
- EXT4_I(inode)->i_disksize = inode->i_size;
err = ext4_add_nondir(handle, dentry, &inode);
if (handle)
ext4_journal_stop(handle);
- if (inode)
- iput(inode);
- goto out_free_encrypted_link;
+ iput(inode);
+ goto out_retry;
err_drop_inode:
- if (handle)
- ext4_journal_stop(handle);
clear_nlink(inode);
+ ext4_mark_inode_dirty(handle, inode);
+ ext4_orphan_add(handle, inode);
unlock_new_inode(inode);
+ if (handle)
+ ext4_journal_stop(handle);
iput(inode);
-out_free_encrypted_link:
+out_retry:
+ if (err == -ENOSPC && ext4_should_retry_alloc(dir->i_sb, &retries))
+ goto retry;
if (disk_link.name != (unsigned char *)symname)
kfree(disk_link.name);
return err;
@@ -3393,7 +3459,7 @@ retry:
if (IS_DIRSYNC(dir))
ext4_handle_sync(handle);
- inode->i_ctime = current_time(inode);
+ inode_set_ctime_current(inode);
ext4_inc_count(inode);
ihold(inode);
@@ -3455,17 +3521,39 @@ static struct buffer_head *ext4_get_first_dir_block(handle_t *handle,
struct buffer_head *bh;
if (!ext4_has_inline_data(inode)) {
- /* The first directory block must not be a hole, so
- * treat it as DIRENT_HTREE
- */
- bh = ext4_read_dirblock(inode, 0, DIRENT_HTREE);
+ struct ext4_dir_entry_2 *de;
+ unsigned int offset;
+
+ bh = ext4_read_dirblock(inode, 0, EITHER);
if (IS_ERR(bh)) {
*retval = PTR_ERR(bh);
return NULL;
}
- *parent_de = ext4_next_entry(
- (struct ext4_dir_entry_2 *)bh->b_data,
- inode->i_sb->s_blocksize);
+
+ de = (struct ext4_dir_entry_2 *) bh->b_data;
+ if (ext4_check_dir_entry(inode, NULL, de, bh, bh->b_data,
+ bh->b_size, 0) ||
+ le32_to_cpu(de->inode) != inode->i_ino ||
+ de->name_len != 1 || de->name[0] != '.') {
+ EXT4_ERROR_INODE(inode, "directory missing '.'");
+ brelse(bh);
+ *retval = -EFSCORRUPTED;
+ return NULL;
+ }
+ offset = ext4_rec_len_from_disk(de->rec_len,
+ inode->i_sb->s_blocksize);
+ de = ext4_next_entry(de, inode->i_sb->s_blocksize);
+ if (ext4_check_dir_entry(inode, NULL, de, bh, bh->b_data,
+ bh->b_size, offset) ||
+ le32_to_cpu(de->inode) == 0 || de->name_len != 2 ||
+ de->name[0] != '.' || de->name[1] != '.') {
+ EXT4_ERROR_INODE(inode, "directory missing '..'");
+ brelse(bh);
+ *retval = -EFSCORRUPTED;
+ return NULL;
+ }
+ *parent_de = de;
+
return bh;
}
@@ -3491,10 +3579,14 @@ struct ext4_renament {
int dir_inlined;
};
-static int ext4_rename_dir_prepare(handle_t *handle, struct ext4_renament *ent)
+static int ext4_rename_dir_prepare(handle_t *handle, struct ext4_renament *ent, bool is_cross)
{
int retval;
+ ent->is_dir = true;
+ if (!is_cross)
+ return 0;
+
ent->dir_bh = ext4_get_first_dir_block(handle, ent->inode,
&retval, &ent->parent_de,
&ent->dir_inlined);
@@ -3512,6 +3604,9 @@ static int ext4_rename_dir_finish(handle_t *handle, struct ext4_renament *ent,
{
int retval;
+ if (!ent->dir_bh)
+ return 0;
+
ent->parent_de->inode = cpu_to_le32(dir_ino);
BUFFER_TRACE(ent->dir_bh, "call ext4_handle_dirty_metadata");
if (!ent->dir_inlined) {
@@ -3547,8 +3642,7 @@ static int ext4_setent(handle_t *handle, struct ext4_renament *ent,
if (ext4_has_feature_filetype(ent->dir->i_sb))
ent->de->file_type = file_type;
inode_inc_iversion(ent->dir);
- ent->dir->i_ctime = ent->dir->i_mtime =
- current_time(ent->dir);
+ inode_set_mtime_to_ts(ent->dir, inode_set_ctime_current(ent->dir));
retval = ext4_mark_inode_dirty(handle, ent->dir);
BUFFER_TRACE(ent->bh, "call ext4_handle_dirty_metadata");
if (!ent->inlined) {
@@ -3572,7 +3666,8 @@ static void ext4_resetent(handle_t *handle, struct ext4_renament *ent,
* so the old->de may no longer valid and need to find it again
* before reset old inode info.
*/
- old.bh = ext4_find_entry(old.dir, &old.dentry->d_name, &old.de, NULL);
+ old.bh = ext4_find_entry(old.dir, &old.dentry->d_name, &old.de,
+ &old.inlined);
if (IS_ERR(old.bh))
retval = PTR_ERR(old.bh);
if (!old.bh)
@@ -3591,7 +3686,7 @@ static int ext4_find_delete_entry(handle_t *handle, struct inode *dir,
{
int retval = -ENOENT;
struct buffer_head *bh;
- struct ext4_dir_entry_2 *de;
+ struct ext4_dir_entry_2 *de = NULL;
bh = ext4_find_entry(dir, d_name, &de, NULL);
if (IS_ERR(bh))
@@ -3646,7 +3741,7 @@ static void ext4_update_dir_count(handle_t *handle, struct ext4_renament *ent)
}
}
-static struct inode *ext4_whiteout_for_rename(struct user_namespace *mnt_userns,
+static struct inode *ext4_whiteout_for_rename(struct mnt_idmap *idmap,
struct ext4_renament *ent,
int credits, handle_t **h)
{
@@ -3661,7 +3756,7 @@ static struct inode *ext4_whiteout_for_rename(struct user_namespace *mnt_userns,
credits += (EXT4_MAXQUOTAS_TRANS_BLOCKS(ent->dir->i_sb) +
EXT4_XATTR_TRANS_BLOCKS + 4);
retry:
- wh = ext4_new_inode_start_handle(mnt_userns, ent->dir,
+ wh = ext4_new_inode_start_handle(idmap, ent->dir,
S_IFCHR | WHITEOUT_MODE,
&ent->dentry->d_name, 0, NULL,
EXT4_HT_DIR, credits);
@@ -3689,7 +3784,7 @@ retry:
* while new_{dentry,inode) refers to the destination dentry/inode
* This comes from rename(const char *oldpath, const char *newpath)
*/
-static int ext4_rename(struct user_namespace *mnt_userns, struct inode *old_dir,
+static int ext4_rename(struct mnt_idmap *idmap, struct inode *old_dir,
struct dentry *old_dentry, struct inode *new_dir,
struct dentry *new_dentry, unsigned int flags)
{
@@ -3724,6 +3819,9 @@ static int ext4_rename(struct user_namespace *mnt_userns, struct inode *old_dir,
retval = dquot_initialize(old.dir);
if (retval)
return retval;
+ retval = dquot_initialize(old.inode);
+ if (retval)
+ return retval;
retval = dquot_initialize(new.dir);
if (retval)
return retval;
@@ -3736,9 +3834,11 @@ static int ext4_rename(struct user_namespace *mnt_userns, struct inode *old_dir,
return retval;
}
- old.bh = ext4_find_entry(old.dir, &old.dentry->d_name, &old.de, NULL);
+ old.bh = ext4_find_entry(old.dir, &old.dentry->d_name, &old.de,
+ &old.inlined);
if (IS_ERR(old.bh))
return PTR_ERR(old.bh);
+
/*
* Check for inode number is _not_ due to possible IO errors.
* We might rmdir the source, keep it as pwd of some process
@@ -3774,7 +3874,7 @@ static int ext4_rename(struct user_namespace *mnt_userns, struct inode *old_dir,
goto release_bh;
}
} else {
- whiteout = ext4_whiteout_for_rename(mnt_userns, &old, credits, &handle);
+ whiteout = ext4_whiteout_for_rename(idmap, &old, credits, &handle);
if (IS_ERR(whiteout)) {
retval = PTR_ERR(whiteout);
goto release_bh;
@@ -3795,7 +3895,7 @@ static int ext4_rename(struct user_namespace *mnt_userns, struct inode *old_dir,
if (new.dir != old.dir && EXT4_DIR_LINK_MAX(new.dir))
goto end_rename;
}
- retval = ext4_rename_dir_prepare(handle, &old);
+ retval = ext4_rename_dir_prepare(handle, &old, new.dir != old.dir);
if (retval)
goto end_rename;
}
@@ -3841,7 +3941,7 @@ static int ext4_rename(struct user_namespace *mnt_userns, struct inode *old_dir,
* Like most other Unix systems, set the ctime for inodes on a
* rename.
*/
- old.inode->i_ctime = current_time(old.inode);
+ inode_set_ctime_current(old.inode);
retval = ext4_mark_inode_dirty(handle, old.inode);
if (unlikely(retval))
goto end_rename;
@@ -3855,11 +3955,11 @@ static int ext4_rename(struct user_namespace *mnt_userns, struct inode *old_dir,
if (new.inode) {
ext4_dec_count(new.inode);
- new.inode->i_ctime = current_time(new.inode);
+ inode_set_ctime_current(new.inode);
}
- old.dir->i_ctime = old.dir->i_mtime = current_time(old.dir);
+ inode_set_mtime_to_ts(old.dir, inode_set_ctime_current(old.dir));
ext4_update_dx_flag(old.dir);
- if (old.dir_bh) {
+ if (old.is_dir) {
retval = ext4_rename_dir_finish(handle, &old, new.dir->i_ino);
if (retval)
goto end_rename;
@@ -3882,21 +3982,28 @@ static int ext4_rename(struct user_namespace *mnt_userns, struct inode *old_dir,
if (unlikely(retval))
goto end_rename;
- if (S_ISDIR(old.inode->i_mode)) {
+ if (old.is_dir) {
/*
* We disable fast commits here that's because the
* replay code is not yet capable of changing dot dot
* dirents in directories.
*/
ext4_fc_mark_ineligible(old.inode->i_sb,
- EXT4_FC_REASON_RENAME_DIR);
+ EXT4_FC_REASON_RENAME_DIR, handle);
} else {
+ struct super_block *sb = old.inode->i_sb;
+
if (new.inode)
ext4_fc_track_unlink(handle, new.dentry);
- __ext4_fc_track_link(handle, old.inode, new.dentry);
- __ext4_fc_track_unlink(handle, old.inode, old.dentry);
- if (whiteout)
- __ext4_fc_track_create(handle, whiteout, old.dentry);
+ if (test_opt2(sb, JOURNAL_FAST_COMMIT) &&
+ !(EXT4_SB(sb)->s_mount_state & EXT4_FC_REPLAY) &&
+ !(ext4_test_mount_flag(sb, EXT4_MF_FC_INELIGIBLE))) {
+ __ext4_fc_track_link(handle, old.inode, new.dentry);
+ __ext4_fc_track_unlink(handle, old.inode, old.dentry);
+ if (whiteout)
+ __ext4_fc_track_create(handle, whiteout,
+ old.dentry);
+ }
}
if (new.inode) {
@@ -3914,6 +4021,7 @@ end_rename:
ext4_resetent(handle, &old,
old.inode->i_ino, old_file_type);
drop_nlink(whiteout);
+ ext4_mark_inode_dirty(handle, whiteout);
ext4_orphan_add(handle, whiteout);
}
unlock_new_inode(whiteout);
@@ -3926,6 +4034,7 @@ release_bh:
brelse(old.dir_bh);
brelse(old.bh);
brelse(new.bh);
+
return retval;
}
@@ -3945,7 +4054,6 @@ static int ext4_cross_rename(struct inode *old_dir, struct dentry *old_dentry,
};
u8 new_file_type;
int retval;
- struct timespec64 ctime;
if ((ext4_test_inode_flag(new_dir, EXT4_INODE_PROJINHERIT) &&
!projid_eq(EXT4_I(new_dir)->i_projid,
@@ -4001,14 +4109,12 @@ static int ext4_cross_rename(struct inode *old_dir, struct dentry *old_dentry,
ext4_handle_sync(handle);
if (S_ISDIR(old.inode->i_mode)) {
- old.is_dir = true;
- retval = ext4_rename_dir_prepare(handle, &old);
+ retval = ext4_rename_dir_prepare(handle, &old, new.dir != old.dir);
if (retval)
goto end_rename;
}
if (S_ISDIR(new.inode->i_mode)) {
- new.is_dir = true;
- retval = ext4_rename_dir_prepare(handle, &new);
+ retval = ext4_rename_dir_prepare(handle, &new, new.dir != old.dir);
if (retval)
goto end_rename;
}
@@ -4039,9 +4145,8 @@ static int ext4_cross_rename(struct inode *old_dir, struct dentry *old_dentry,
* Like most other Unix systems, set the ctime for inodes on a
* rename.
*/
- ctime = current_time(old.inode);
- old.inode->i_ctime = ctime;
- new.inode->i_ctime = ctime;
+ inode_set_ctime_current(old.inode);
+ inode_set_ctime_current(new.inode);
retval = ext4_mark_inode_dirty(handle, old.inode);
if (unlikely(retval))
goto end_rename;
@@ -4049,7 +4154,7 @@ static int ext4_cross_rename(struct inode *old_dir, struct dentry *old_dentry,
if (unlikely(retval))
goto end_rename;
ext4_fc_mark_ineligible(new.inode->i_sb,
- EXT4_FC_REASON_CROSS_RENAME);
+ EXT4_FC_REASON_CROSS_RENAME, handle);
if (old.dir_bh) {
retval = ext4_rename_dir_finish(handle, &old, new.dir->i_ino);
if (retval)
@@ -4074,15 +4179,16 @@ end_rename:
return retval;
}
-static int ext4_rename2(struct user_namespace *mnt_userns,
+static int ext4_rename2(struct mnt_idmap *idmap,
struct inode *old_dir, struct dentry *old_dentry,
struct inode *new_dir, struct dentry *new_dentry,
unsigned int flags)
{
int err;
- if (unlikely(ext4_forced_shutdown(EXT4_SB(old_dir->i_sb))))
- return -EIO;
+ err = ext4_emergency_state(old_dir->i_sb);
+ if (unlikely(err))
+ return err;
if (flags & ~(RENAME_NOREPLACE | RENAME_EXCHANGE | RENAME_WHITEOUT))
return -EINVAL;
@@ -4097,7 +4203,7 @@ static int ext4_rename2(struct user_namespace *mnt_userns,
new_dir, new_dentry);
}
- return ext4_rename(mnt_userns, old_dir, old_dentry, new_dir, new_dentry, flags);
+ return ext4_rename(idmap, old_dir, old_dentry, new_dir, new_dentry, flags);
}
/*
@@ -4117,7 +4223,7 @@ const struct inode_operations ext4_dir_inode_operations = {
.setattr = ext4_setattr,
.getattr = ext4_getattr,
.listxattr = ext4_listxattr,
- .get_acl = ext4_get_acl,
+ .get_inode_acl = ext4_get_acl,
.set_acl = ext4_set_acl,
.fiemap = ext4_fiemap,
.fileattr_get = ext4_fileattr_get,
@@ -4128,6 +4234,6 @@ const struct inode_operations ext4_special_inode_operations = {
.setattr = ext4_setattr,
.getattr = ext4_getattr,
.listxattr = ext4_listxattr,
- .get_acl = ext4_get_acl,
+ .get_inode_acl = ext4_get_acl,
.set_acl = ext4_set_acl,
};