diff --git a/fs/ubifs/dir.c b/fs/ubifs/dir.c
index 745e6e3f246e921f4c5217022979f2835700d0fd..f2a6b45bfdaec9b31709b5d6bb6988bac3077595 100644
--- a/fs/ubifs/dir.c
+++ b/fs/ubifs/dir.c
@@ -349,8 +349,56 @@ static int ubifs_create(struct user_namespace *mnt_userns, struct inode *dir,
return err;
}
-static int do_tmpfile(struct inode *dir, struct dentry *dentry,
- umode_t mode, struct inode **whiteout)
+static struct inode *create_whiteout(struct inode *dir, struct dentry *dentry)
+{
+ int err;
+ umode_t mode = S_IFCHR | WHITEOUT_MODE;
+ struct inode *inode;
+ struct ubifs_info *c = dir->i_sb->s_fs_info;
+ struct fscrypt_name nm;
+
+ /*
+ * Create an inode('nlink = 1') for whiteout without updating journal,
+ * let ubifs_jnl_rename() store it on flash to complete rename whiteout
+ * atomically.
+ */
+
+ dbg_gen("dent '%pd', mode %#hx in dir ino %lu",
+ dentry, mode, dir->i_ino);
+
+ err = fscrypt_setup_filename(dir, &dentry->d_name, 0, &nm);
+ if (err)
+ return ERR_PTR(err);
+
+ inode = ubifs_new_inode(c, dir, mode);
+ if (IS_ERR(inode)) {
+ err = PTR_ERR(inode);
+ goto out_free;
+ }
+
+ init_special_inode(inode, inode->i_mode, WHITEOUT_DEV);
+ ubifs_assert(c, inode->i_op == &ubifs_file_inode_operations);
+
+ err = ubifs_init_security(dir, inode, &dentry->d_name);
+ if (err)
+ goto out_inode;
+
+ /* The dir size is updated by do_rename. */
+ insert_inode_hash(inode);
+
+ return inode;
+
+out_inode:
+ make_bad_inode(inode);
+ iput(inode);
+out_free:
+ fscrypt_free_filename(&nm);
+ ubifs_err(c, "cannot create whiteout file, error %d", err);
+ return ERR_PTR(err);
+}
+
+static int ubifs_tmpfile(struct user_namespace *mnt_userns, struct inode *dir,
+ struct dentry *dentry, umode_t mode)
{
struct inode *inode;
struct ubifs_info *c = dir->i_sb->s_fs_info;
@@ -392,25 +440,13 @@ static int do_tmpfile(struct inode *dir, struct dentry *dentry,
}
ui = ubifs_inode(inode);
- if (whiteout) {
- init_special_inode(inode, inode->i_mode, WHITEOUT_DEV);
- ubifs_assert(c, inode->i_op == &ubifs_file_inode_operations);
- }
-
err = ubifs_init_security(dir, inode, &dentry->d_name);
if (err)
goto out_inode;
mutex_lock(&ui->ui_mutex);
insert_inode_hash(inode);
-
- if (whiteout) {
- mark_inode_dirty(inode);
- drop_nlink(inode);
- *whiteout = inode;
- } else {
- d_tmpfile(dentry, inode);
- }
+ d_tmpfile(dentry, inode);
ubifs_assert(c, ui->dirty);
instantiated = 1;
@@ -432,8 +468,6 @@ static int do_tmpfile(struct inode *dir, struct dentry *dentry,
make_bad_inode(inode);
if (!instantiated)
iput(inode);
- else if (whiteout)
- iput(*whiteout);
out_budg:
ubifs_release_budget(c, &req);
if (!instantiated)
@@ -443,12 +477,6 @@ static int do_tmpfile(struct inode *dir, struct dentry *dentry,
return err;
}
-static int ubifs_tmpfile(struct user_namespace *mnt_userns, struct inode *dir,
- struct dentry *dentry, umode_t mode)
-{
- return do_tmpfile(dir, dentry, mode, NULL);
-}
-
/**
* vfs_dent_type - get VFS directory entry type.
* @type: UBIFS directory entry type
@@ -1266,17 +1294,19 @@ static int do_rename(struct inode *old_dir, struct dentry *old_dentry,
.dirtied_ino = 3 };
struct ubifs_budget_req ino_req = { .dirtied_ino = 1,
.dirtied_ino_d = ALIGN(old_inode_ui->data_len, 8) };
+ struct ubifs_budget_req wht_req;
struct timespec64 time;
unsigned int saved_nlink;
struct fscrypt_name old_nm, new_nm;
/*
- * Budget request settings: deletion direntry, new direntry, removing
- * the old inode, and changing old and new parent directory inodes.
+ * Budget request settings:
+ * req: deletion direntry, new direntry, removing the old inode,
+ * and changing old and new parent directory inodes.
*
- * However, this operation also marks the target inode as dirty and
- * does not write it, so we allocate budget for the target inode
- * separately.
+ * wht_req: new whiteout inode for RENAME_WHITEOUT.
+ *
+ * ino_req: marks the target inode as dirty and does not write it.
*/
dbg_gen("dent '%pd' ino %lu in dir ino %lu to dent '%pd' in dir ino %lu flags 0x%x",
@@ -1326,7 +1356,6 @@ static int do_rename(struct inode *old_dir, struct dentry *old_dentry,
if (flags & RENAME_WHITEOUT) {
union ubifs_dev_desc *dev = NULL;
- struct ubifs_budget_req wht_req;
dev = kmalloc(sizeof(union ubifs_dev_desc), GFP_NOFS);
if (!dev) {
@@ -1334,24 +1363,26 @@ static int do_rename(struct inode *old_dir, struct dentry *old_dentry,
goto out_release;
}
- err = do_tmpfile(old_dir, old_dentry, S_IFCHR | WHITEOUT_MODE, &whiteout);
- if (err) {
+ /*
+ * The whiteout inode without dentry is pinned in memory,
+ * umount won't happen during rename process because we
+ * got parent dentry.
+ */
+ whiteout = create_whiteout(old_dir, old_dentry);
+ if (IS_ERR(whiteout)) {
+ err = PTR_ERR(whiteout);
kfree(dev);
goto out_release;
}
- spin_lock(&whiteout->i_lock);
- whiteout->i_state |= I_LINKABLE;
- spin_unlock(&whiteout->i_lock);
-
whiteout_ui = ubifs_inode(whiteout);
whiteout_ui->data = dev;
whiteout_ui->data_len = ubifs_encode_dev(dev, MKDEV(0, 0));
ubifs_assert(c, !whiteout_ui->dirty);
memset(&wht_req, 0, sizeof(struct ubifs_budget_req));
- wht_req.dirtied_ino = 1;
- wht_req.dirtied_ino_d = ALIGN(whiteout_ui->data_len, 8);
+ wht_req.new_ino = 1;
+ wht_req.new_ino_d = ALIGN(whiteout_ui->data_len, 8);
/*
* To avoid deadlock between space budget (holds ui_mutex and
* waits wb work) and writeback work(waits ui_mutex), do space
@@ -1359,6 +1390,11 @@ static int do_rename(struct inode *old_dir, struct dentry *old_dentry,
*/
err = ubifs_budget_space(c, &wht_req);
if (err) {
+ /*
+ * Whiteout inode can not be written on flash by
+ * ubifs_jnl_write_inode(), because it's neither
+ * dirty nor zero-nlink.
+ */
iput(whiteout);
goto out_release;
}
@@ -1433,17 +1469,11 @@ static int do_rename(struct inode *old_dir, struct dentry *old_dentry,
sync = IS_DIRSYNC(old_dir) || IS_DIRSYNC(new_dir);
if (unlink && IS_SYNC(new_inode))
sync = 1;
- }
-
- if (whiteout) {
- inc_nlink(whiteout);
- mark_inode_dirty(whiteout);
-
- spin_lock(&whiteout->i_lock);
- whiteout->i_state &= ~I_LINKABLE;
- spin_unlock(&whiteout->i_lock);
-
- iput(whiteout);
+ /*
+ * S_SYNC flag of whiteout inherits from the old_dir, and we
+ * have already checked the old dir inode. So there is no need
+ * to check whiteout.
+ */
}
err = ubifs_jnl_rename(c, old_dir, old_inode, &old_nm, new_dir,
@@ -1454,6 +1484,11 @@ static int do_rename(struct inode *old_dir, struct dentry *old_dentry,
unlock_4_inodes(old_dir, new_dir, new_inode, whiteout);
ubifs_release_budget(c, &req);
+ if (whiteout) {
+ ubifs_release_budget(c, &wht_req);
+ iput(whiteout);
+ }
+
mutex_lock(&old_inode_ui->ui_mutex);
release = old_inode_ui->dirty;
mark_inode_dirty_sync(old_inode);
@@ -1462,11 +1497,16 @@ static int do_rename(struct inode *old_dir, struct dentry *old_dentry,
if (release)
ubifs_release_budget(c, &ino_req);
if (IS_SYNC(old_inode))
- err = old_inode->i_sb->s_op->write_inode(old_inode, NULL);
+ /*
+ * Rename finished here. Although old inode cannot be updated
+ * on flash, old ctime is not a big problem, don't return err
+ * code to userspace.
+ */
+ old_inode->i_sb->s_op->write_inode(old_inode, NULL);
fscrypt_free_filename(&old_nm);
fscrypt_free_filename(&new_nm);
- return err;
+ return 0;
out_cancel:
if (unlink) {
@@ -1487,11 +1527,11 @@ static int do_rename(struct inode *old_dir, struct dentry *old_dentry,
inc_nlink(old_dir);
}
}
+ unlock_4_inodes(old_dir, new_dir, new_inode, whiteout);
if (whiteout) {
- drop_nlink(whiteout);
+ ubifs_release_budget(c, &wht_req);
iput(whiteout);
}
- unlock_4_inodes(old_dir, new_dir, new_inode, whiteout);
out_release:
ubifs_release_budget(c, &ino_req);
ubifs_release_budget(c, &req);
diff --git a/fs/ubifs/journal.c b/fs/ubifs/journal.c
index 8ea680dba61e39c4a41b821ae7b048c6a716ed98..75dab0ae3939d0a9011fad14242fe01b81380a52 100644
--- a/fs/ubifs/journal.c
+++ b/fs/ubifs/journal.c
@@ -1207,9 +1207,9 @@ int ubifs_jnl_xrename(struct ubifs_info *c, const struct inode *fst_dir,
* @sync: non-zero if the write-buffer has to be synchronized
*
* This function implements the re-name operation which may involve writing up
- * to 4 inodes and 2 directory entries. It marks the written inodes as clean
- * and returns zero on success. In case of failure, a negative error code is
- * returned.
+ * to 4 inodes(new inode, whiteout inode, old and new parent directory inodes)
+ * and 2 directory entries. It marks the written inodes as clean and returns
+ * zero on success. In case of failure, a negative error code is returned.
*/
int ubifs_jnl_rename(struct ubifs_info *c, const struct inode *old_dir,
const struct inode *old_inode,
@@ -1222,14 +1222,15 @@ int ubifs_jnl_rename(struct ubifs_info *c, const struct inode *old_dir,
void *p;
union ubifs_key key;
struct ubifs_dent_node *dent, *dent2;
- int err, dlen1, dlen2, ilen, lnum, offs, len, orphan_added = 0;
+ int err, dlen1, dlen2, ilen, wlen, lnum, offs, len, orphan_added = 0;
int aligned_dlen1, aligned_dlen2, plen = UBIFS_INO_NODE_SZ;
int last_reference = !!(new_inode && new_inode->i_nlink == 0);
int move = (old_dir != new_dir);
- struct ubifs_inode *new_ui;
+ struct ubifs_inode *new_ui, *whiteout_ui;
u8 hash_old_dir[UBIFS_HASH_ARR_SZ];
u8 hash_new_dir[UBIFS_HASH_ARR_SZ];
u8 hash_new_inode[UBIFS_HASH_ARR_SZ];
+ u8 hash_whiteout_inode[UBIFS_HASH_ARR_SZ];
u8 hash_dent1[UBIFS_HASH_ARR_SZ];
u8 hash_dent2[UBIFS_HASH_ARR_SZ];
@@ -1249,9 +1250,20 @@ int ubifs_jnl_rename(struct ubifs_info *c, const struct inode *old_dir,
} else
ilen = 0;
+ if (whiteout) {
+ whiteout_ui = ubifs_inode(whiteout);
+ ubifs_assert(c, mutex_is_locked(&whiteout_ui->ui_mutex));
+ ubifs_assert(c, whiteout->i_nlink == 1);
+ ubifs_assert(c, !whiteout_ui->dirty);
+ wlen = UBIFS_INO_NODE_SZ;
+ wlen += whiteout_ui->data_len;
+ } else
+ wlen = 0;
+
aligned_dlen1 = ALIGN(dlen1, 8);
aligned_dlen2 = ALIGN(dlen2, 8);
- len = aligned_dlen1 + aligned_dlen2 + ALIGN(ilen, 8) + ALIGN(plen, 8);
+ len = aligned_dlen1 + aligned_dlen2 + ALIGN(ilen, 8) +
+ ALIGN(wlen, 8) + ALIGN(plen, 8);
if (move)
len += plen;
@@ -1313,6 +1325,15 @@ int ubifs_jnl_rename(struct ubifs_info *c, const struct inode *old_dir,
p += ALIGN(ilen, 8);
}
+ if (whiteout) {
+ pack_inode(c, p, whiteout, 0);
+ err = ubifs_node_calc_hash(c, p, hash_whiteout_inode);
+ if (err)
+ goto out_release;
+
+ p += ALIGN(wlen, 8);
+ }
+
if (!move) {
pack_inode(c, p, old_dir, 1);
err = ubifs_node_calc_hash(c, p, hash_old_dir);
@@ -1352,6 +1373,9 @@ int ubifs_jnl_rename(struct ubifs_info *c, const struct inode *old_dir,
if (new_inode)
ubifs_wbuf_add_ino_nolock(&c->jheads[BASEHD].wbuf,
new_inode->i_ino);
+ if (whiteout)
+ ubifs_wbuf_add_ino_nolock(&c->jheads[BASEHD].wbuf,
+ whiteout->i_ino);
}
release_head(c, BASEHD);
@@ -1368,8 +1392,6 @@ int ubifs_jnl_rename(struct ubifs_info *c, const struct inode *old_dir,
err = ubifs_tnc_add_nm(c, &key, lnum, offs, dlen2, hash_dent2, old_nm);
if (err)
goto out_ro;
-
- ubifs_delete_orphan(c, whiteout->i_ino);
} else {
err = ubifs_add_dirt(c, lnum, dlen2);
if (err)
@@ -1390,6 +1412,15 @@ int ubifs_jnl_rename(struct ubifs_info *c, const struct inode *old_dir,
offs += ALIGN(ilen, 8);
}
+ if (whiteout) {
+ ino_key_init(c, &key, whiteout->i_ino);
+ err = ubifs_tnc_add(c, &key, lnum, offs, wlen,
+ hash_whiteout_inode);
+ if (err)
+ goto out_ro;
+ offs += ALIGN(wlen, 8);
+ }
+
ino_key_init(c, &key, old_dir->i_ino);
err = ubifs_tnc_add(c, &key, lnum, offs, plen, hash_old_dir);
if (err)
@@ -1410,6 +1441,11 @@ int ubifs_jnl_rename(struct ubifs_info *c, const struct inode *old_dir,
new_ui->synced_i_size = new_ui->ui_size;
spin_unlock(&new_ui->ui_lock);
}
+ /*
+ * No need to mark whiteout inode clean.
+ * Whiteout doesn't have non-zero size, no need to update
+ * synced_i_size for whiteout_ui.
+ */
mark_inode_clean(c, ubifs_inode(old_dir));
if (move)
mark_inode_clean(c, ubifs_inode(new_dir));