summaryrefslogtreecommitdiff
path: root/fs
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2022-03-31 16:09:41 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2022-03-31 16:09:41 -0700
commita87a08e3bf2decaed29c4dfde3916676f9b966a8 (patch)
tree7ecb4d9e18b48971217435615a05be0b73b3507c /fs
parent3d198e42ce25cb1d58ff7052c036407271ebfb51 (diff)
parent705757274599e2e064dd3054aabc74e8af31a095 (diff)
downloadlwn-a87a08e3bf2decaed29c4dfde3916676f9b966a8.tar.gz
lwn-a87a08e3bf2decaed29c4dfde3916676f9b966a8.zip
Merge tag 'for-linus-5.18-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/rw/ubifs
Pull JFFS2, UBI and UBIFS updates from Richard Weinberger: "JFFS2: - Fixes for various memory issues UBI: - Fix for a race condition in cdev ioctl handler UBIFS: - Fixes for O_TMPFILE and whiteout handling - Fixes for various memory issues" * tag 'for-linus-5.18-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/rw/ubifs: ubifs: rename_whiteout: correct old_dir size computing jffs2: fix memory leak in jffs2_scan_medium jffs2: fix memory leak in jffs2_do_mount_fs jffs2: fix use-after-free in jffs2_clear_xattr_subsystem fs/jffs2: fix comments mentioning i_mutex ubi: fastmap: Return error code if memory allocation fails in add_aeb() ubifs: Fix to add refcount once page is set private ubifs: Fix read out-of-bounds in ubifs_wbuf_write_nolock() ubifs: setflags: Make dirtied_ino_d 8 bytes aligned ubifs: Rectify space amount budget for mkdir/tmpfile operations ubifs: Fix 'ui->dirty' race between do_tmpfile() and writeback work ubifs: Rename whiteout atomically ubifs: Add missing iput if do_tmpfile() failed in rename whiteout ubifs: Fix wrong number of inodes locked by ui_mutex in ubifs_inode comment ubifs: Fix deadlock in concurrent rename whiteout and inode writeback ubifs: rename_whiteout: Fix double free for whiteout_ui->data ubi: Fix race condition between ctrl_cdev_ioctl and ubi_cdev_ioctl
Diffstat (limited to 'fs')
-rw-r--r--fs/jffs2/build.c4
-rw-r--r--fs/jffs2/fs.c2
-rw-r--r--fs/jffs2/jffs2_fs_i.h4
-rw-r--r--fs/jffs2/scan.c6
-rw-r--r--fs/ubifs/dir.c238
-rw-r--r--fs/ubifs/file.c14
-rw-r--r--fs/ubifs/io.c34
-rw-r--r--fs/ubifs/ioctl.c2
-rw-r--r--fs/ubifs/journal.c52
-rw-r--r--fs/ubifs/ubifs.h2
10 files changed, 238 insertions, 120 deletions
diff --git a/fs/jffs2/build.c b/fs/jffs2/build.c
index b288c8ae1236..837cd55fd4c5 100644
--- a/fs/jffs2/build.c
+++ b/fs/jffs2/build.c
@@ -415,13 +415,15 @@ int jffs2_do_mount_fs(struct jffs2_sb_info *c)
jffs2_free_ino_caches(c);
jffs2_free_raw_node_refs(c);
ret = -EIO;
- goto out_free;
+ goto out_sum_exit;
}
jffs2_calc_trigger_levels(c);
return 0;
+ out_sum_exit:
+ jffs2_sum_exit(c);
out_free:
kvfree(c->blocks);
diff --git a/fs/jffs2/fs.c b/fs/jffs2/fs.c
index 2ac410477c4f..71f03a5d36ed 100644
--- a/fs/jffs2/fs.c
+++ b/fs/jffs2/fs.c
@@ -603,8 +603,8 @@ out_root:
jffs2_free_ino_caches(c);
jffs2_free_raw_node_refs(c);
kvfree(c->blocks);
- out_inohash:
jffs2_clear_xattr_subsystem(c);
+ out_inohash:
kfree(c->inocache_list);
out_wbuf:
jffs2_flash_cleanup(c);
diff --git a/fs/jffs2/jffs2_fs_i.h b/fs/jffs2/jffs2_fs_i.h
index 2e4a86763c07..93a2951538ce 100644
--- a/fs/jffs2/jffs2_fs_i.h
+++ b/fs/jffs2/jffs2_fs_i.h
@@ -18,11 +18,11 @@
#include <linux/mutex.h>
struct jffs2_inode_info {
- /* We need an internal mutex similar to inode->i_mutex.
+ /* We need an internal mutex similar to inode->i_rwsem.
Unfortunately, we can't used the existing one, because
either the GC would deadlock, or we'd have to release it
before letting GC proceed. Or we'd have to put ugliness
- into the GC code so it didn't attempt to obtain the i_mutex
+ into the GC code so it didn't attempt to obtain the i_rwsem
for the inode(s) which are already locked */
struct mutex sem;
diff --git a/fs/jffs2/scan.c b/fs/jffs2/scan.c
index b676056826be..29671e33a171 100644
--- a/fs/jffs2/scan.c
+++ b/fs/jffs2/scan.c
@@ -136,7 +136,7 @@ int jffs2_scan_medium(struct jffs2_sb_info *c)
if (!s) {
JFFS2_WARNING("Can't allocate memory for summary\n");
ret = -ENOMEM;
- goto out;
+ goto out_buf;
}
}
@@ -275,13 +275,15 @@ int jffs2_scan_medium(struct jffs2_sb_info *c)
}
ret = 0;
out:
+ jffs2_sum_reset_collected(s);
+ kfree(s);
+ out_buf:
if (buf_size)
kfree(flashbuf);
#ifndef __ECOS
else
mtd_unpoint(c->mtd, 0, c->mtd->size);
#endif
- kfree(s);
return ret;
}
diff --git a/fs/ubifs/dir.c b/fs/ubifs/dir.c
index dbe72f664abf..86151889548e 100644
--- a/fs/ubifs/dir.c
+++ b/fs/ubifs/dir.c
@@ -349,20 +349,97 @@ out_budg:
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);
+}
+
+/**
+ * lock_2_inodes - a wrapper for locking two UBIFS inodes.
+ * @inode1: first inode
+ * @inode2: second inode
+ *
+ * We do not implement any tricks to guarantee strict lock ordering, because
+ * VFS has already done it for us on the @i_mutex. So this is just a simple
+ * wrapper function.
+ */
+static void lock_2_inodes(struct inode *inode1, struct inode *inode2)
+{
+ mutex_lock_nested(&ubifs_inode(inode1)->ui_mutex, WB_MUTEX_1);
+ mutex_lock_nested(&ubifs_inode(inode2)->ui_mutex, WB_MUTEX_2);
+}
+
+/**
+ * unlock_2_inodes - a wrapper for unlocking two UBIFS inodes.
+ * @inode1: first inode
+ * @inode2: second inode
+ */
+static void unlock_2_inodes(struct inode *inode1, struct inode *inode2)
+{
+ mutex_unlock(&ubifs_inode(inode2)->ui_mutex);
+ mutex_unlock(&ubifs_inode(inode1)->ui_mutex);
+}
+
+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;
- struct ubifs_budget_req req = { .new_ino = 1, .new_dent = 1};
+ struct ubifs_budget_req req = { .new_ino = 1, .new_dent = 1,
+ .dirtied_ino = 1};
struct ubifs_budget_req ino_req = { .dirtied_ino = 1 };
- struct ubifs_inode *ui, *dir_ui = ubifs_inode(dir);
+ struct ubifs_inode *ui;
int err, instantiated = 0;
struct fscrypt_name nm;
/*
- * Budget request settings: new dirty inode, new direntry,
- * budget for dirtied inode will be released via writeback.
+ * Budget request settings: new inode, new direntry, changing the
+ * parent directory inode.
+ * Allocate budget separately for new dirtied inode, the budget will
+ * be released via writeback.
*/
dbg_gen("dent '%pd', mode %#hx in dir ino %lu",
@@ -392,42 +469,30 @@ 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;
mutex_unlock(&ui->ui_mutex);
- mutex_lock(&dir_ui->ui_mutex);
+ lock_2_inodes(dir, inode);
err = ubifs_jnl_update(c, dir, &nm, inode, 1, 0);
if (err)
goto out_cancel;
- mutex_unlock(&dir_ui->ui_mutex);
+ unlock_2_inodes(dir, inode);
ubifs_release_budget(c, &req);
return 0;
out_cancel:
- mutex_unlock(&dir_ui->ui_mutex);
+ unlock_2_inodes(dir, inode);
out_inode:
make_bad_inode(inode);
if (!instantiated)
@@ -441,12 +506,6 @@ out_budg:
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
@@ -660,32 +719,6 @@ static int ubifs_dir_release(struct inode *dir, struct file *file)
return 0;
}
-/**
- * lock_2_inodes - a wrapper for locking two UBIFS inodes.
- * @inode1: first inode
- * @inode2: second inode
- *
- * We do not implement any tricks to guarantee strict lock ordering, because
- * VFS has already done it for us on the @i_mutex. So this is just a simple
- * wrapper function.
- */
-static void lock_2_inodes(struct inode *inode1, struct inode *inode2)
-{
- mutex_lock_nested(&ubifs_inode(inode1)->ui_mutex, WB_MUTEX_1);
- mutex_lock_nested(&ubifs_inode(inode2)->ui_mutex, WB_MUTEX_2);
-}
-
-/**
- * unlock_2_inodes - a wrapper for unlocking two UBIFS inodes.
- * @inode1: first inode
- * @inode2: second inode
- */
-static void unlock_2_inodes(struct inode *inode1, struct inode *inode2)
-{
- mutex_unlock(&ubifs_inode(inode2)->ui_mutex);
- mutex_unlock(&ubifs_inode(inode1)->ui_mutex);
-}
-
static int ubifs_link(struct dentry *old_dentry, struct inode *dir,
struct dentry *dentry)
{
@@ -949,7 +982,8 @@ static int ubifs_mkdir(struct user_namespace *mnt_userns, struct inode *dir,
struct ubifs_inode *dir_ui = ubifs_inode(dir);
struct ubifs_info *c = dir->i_sb->s_fs_info;
int err, sz_change;
- struct ubifs_budget_req req = { .new_ino = 1, .new_dent = 1 };
+ struct ubifs_budget_req req = { .new_ino = 1, .new_dent = 1,
+ .dirtied_ino = 1};
struct fscrypt_name nm;
/*
@@ -1264,17 +1298,19 @@ 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.
+ *
+ * wht_req: new whiteout inode for RENAME_WHITEOUT.
*
- * However, this operation also marks the target inode as dirty and
- * does not write it, so we allocate budget for the target inode
- * separately.
+ * 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",
@@ -1331,20 +1367,44 @@ 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.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
+ * budget before ubifs inodes locked.
+ */
+ 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;
+ }
+
+ /* Add the old_dentry size to the old_dir size. */
+ old_sz -= CALC_DENT_SIZE(fname_len(&old_nm));
}
lock_4_inodes(old_dir, new_dir, new_inode, whiteout);
@@ -1416,29 +1476,11 @@ 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) {
- struct ubifs_budget_req wht_req = { .dirtied_ino = 1,
- .dirtied_ino_d = \
- ALIGN(ubifs_inode(whiteout)->data_len, 8) };
-
- err = ubifs_budget_space(c, &wht_req);
- if (err) {
- kfree(whiteout_ui->data);
- whiteout_ui->data_len = 0;
- iput(whiteout);
- goto out_release;
- }
-
- 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,
@@ -1449,6 +1491,11 @@ 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);
@@ -1457,11 +1504,16 @@ 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) {
@@ -1482,11 +1534,11 @@ out_cancel:
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/file.c b/fs/ubifs/file.c
index 8a9ffc2d4167..0383fbdc95ff 100644
--- a/fs/ubifs/file.c
+++ b/fs/ubifs/file.c
@@ -570,7 +570,7 @@ static int ubifs_write_end(struct file *file, struct address_space *mapping,
}
if (!PagePrivate(page)) {
- SetPagePrivate(page);
+ attach_page_private(page, (void *)1);
atomic_long_inc(&c->dirty_pg_cnt);
__set_page_dirty_nobuffers(page);
}
@@ -947,7 +947,7 @@ static int do_writepage(struct page *page, int len)
release_existing_page_budget(c);
atomic_long_dec(&c->dirty_pg_cnt);
- ClearPagePrivate(page);
+ detach_page_private(page);
ClearPageChecked(page);
kunmap(page);
@@ -1304,7 +1304,7 @@ static void ubifs_invalidate_folio(struct folio *folio, size_t offset,
release_existing_page_budget(c);
atomic_long_dec(&c->dirty_pg_cnt);
- folio_clear_private(folio);
+ folio_detach_private(folio);
folio_clear_checked(folio);
}
@@ -1471,8 +1471,8 @@ static int ubifs_migrate_page(struct address_space *mapping,
return rc;
if (PagePrivate(page)) {
- ClearPagePrivate(page);
- SetPagePrivate(newpage);
+ detach_page_private(page);
+ attach_page_private(newpage, (void *)1);
}
if (mode != MIGRATE_SYNC_NO_COPY)
@@ -1496,7 +1496,7 @@ static int ubifs_releasepage(struct page *page, gfp_t unused_gfp_flags)
return 0;
ubifs_assert(c, PagePrivate(page));
ubifs_assert(c, 0);
- ClearPagePrivate(page);
+ detach_page_private(page);
ClearPageChecked(page);
return 1;
}
@@ -1567,7 +1567,7 @@ static vm_fault_t ubifs_vm_page_mkwrite(struct vm_fault *vmf)
else {
if (!PageChecked(page))
ubifs_convert_page_budget(c);
- SetPagePrivate(page);
+ attach_page_private(page, (void *)1);
atomic_long_inc(&c->dirty_pg_cnt);
__set_page_dirty_nobuffers(page);
}
diff --git a/fs/ubifs/io.c b/fs/ubifs/io.c
index 789a7813f3fa..1607a3c76681 100644
--- a/fs/ubifs/io.c
+++ b/fs/ubifs/io.c
@@ -854,16 +854,42 @@ int ubifs_wbuf_write_nolock(struct ubifs_wbuf *wbuf, void *buf, int len)
*/
n = aligned_len >> c->max_write_shift;
if (n) {
- n <<= c->max_write_shift;
+ int m = n - 1;
+
dbg_io("write %d bytes to LEB %d:%d", n, wbuf->lnum,
wbuf->offs);
- err = ubifs_leb_write(c, wbuf->lnum, buf + written,
- wbuf->offs, n);
+
+ if (m) {
+ /* '(n-1)<<c->max_write_shift < len' is always true. */
+ m <<= c->max_write_shift;
+ err = ubifs_leb_write(c, wbuf->lnum, buf + written,
+ wbuf->offs, m);
+ if (err)
+ goto out;
+ wbuf->offs += m;
+ aligned_len -= m;
+ len -= m;
+ written += m;
+ }
+
+ /*
+ * The non-written len of buf may be less than 'n' because
+ * parameter 'len' is not 8 bytes aligned, so here we read
+ * min(len, n) bytes from buf.
+ */
+ n = 1 << c->max_write_shift;
+ memcpy(wbuf->buf, buf + written, min(len, n));
+ if (n > len) {
+ ubifs_assert(c, n - len < 8);
+ ubifs_pad(c, wbuf->buf + len, n - len);
+ }
+
+ err = ubifs_leb_write(c, wbuf->lnum, wbuf->buf, wbuf->offs, n);
if (err)
goto out;
wbuf->offs += n;
aligned_len -= n;
- len -= n;
+ len -= min(len, n);
written += n;
}
diff --git a/fs/ubifs/ioctl.c b/fs/ubifs/ioctl.c
index c6a863487780..71bcebe45f9c 100644
--- a/fs/ubifs/ioctl.c
+++ b/fs/ubifs/ioctl.c
@@ -108,7 +108,7 @@ static int setflags(struct inode *inode, int flags)
struct ubifs_inode *ui = ubifs_inode(inode);
struct ubifs_info *c = inode->i_sb->s_fs_info;
struct ubifs_budget_req req = { .dirtied_ino = 1,
- .dirtied_ino_d = ui->data_len };
+ .dirtied_ino_d = ALIGN(ui->data_len, 8) };
err = ubifs_budget_space(c, &req);
if (err)
diff --git a/fs/ubifs/journal.c b/fs/ubifs/journal.c
index 8ea680dba61e..75dab0ae3939 100644
--- a/fs/ubifs/journal.c
+++ b/fs/ubifs/journal.c
@@ -1207,9 +1207,9 @@ out_free:
* @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));
diff --git a/fs/ubifs/ubifs.h b/fs/ubifs/ubifs.h
index f55828c0a300..008fa46ef61e 100644
--- a/fs/ubifs/ubifs.h
+++ b/fs/ubifs/ubifs.h
@@ -381,7 +381,7 @@ struct ubifs_gced_idx_leb {
* @ui_mutex exists for two main reasons. At first it prevents inodes from
* being written back while UBIFS changing them, being in the middle of an VFS
* operation. This way UBIFS makes sure the inode fields are consistent. For
- * example, in 'ubifs_rename()' we change 3 inodes simultaneously, and
+ * example, in 'ubifs_rename()' we change 4 inodes simultaneously, and
* write-back must not write any of them before we have finished.
*
* The second reason is budgeting - UBIFS has to budget all operations. If an