summaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
authorBruce Ashfield <bruce.ashfield@gmail.com>2019-10-14 21:55:26 -0400
committerBruce Ashfield <bruce.ashfield@gmail.com>2019-10-14 21:55:26 -0400
commit18cac24ece4f2a6665f8396b00bd988d80c4899c (patch)
treed0c4f3cb87d71f934fe8e5d9f8821901bf4e781d
parent86ac40fcf8ca1c1ec138ee38c3b2c1e393a90bc9 (diff)
downloadyocto-kernel-cache-18cac24ece4f2a6665f8396b00bd988d80c4899c.tar.gz
yocto-kernel-cache-18cac24ece4f2a6665f8396b00bd988d80c4899c.tar.bz2
yocto-kernel-cache-18cac24ece4f2a6665f8396b00bd988d80c4899c.zip
meta: prep patches for v5.4 support
Signed-off-by: Bruce Ashfield <bruce.ashfield@gmail.com>
-rw-r--r--features/aufs/aufs-bugfix-opts-Fix-missing-break-statement.patch32
-rw-r--r--features/aufs/aufs-opts-Fix-missing-fallthrough.patch43
-rw-r--r--features/aufs/aufs.scc9
-rw-r--r--features/aufs/aufs5-base-support.patch345
-rw-r--r--features/aufs/aufs5-core-support.patch38587
-rw-r--r--features/aufs/aufs5-fix-build-on-v5.3.patch30
-rw-r--r--features/aufs/aufs5-kbuild-support.patch37
-rw-r--r--features/aufs/aufs5-mmap-support.patch422
-rw-r--r--features/aufs/aufs5-standalone-support.patch397
-rw-r--r--features/perf/perf-force-include-of-stdbool.h.patch17
-rw-r--r--kver2
-rw-r--r--patches/misc/linux-yocto-Handle-bin-awk-issues.patch22
12 files changed, 10 insertions, 39933 deletions
diff --git a/features/aufs/aufs-bugfix-opts-Fix-missing-break-statement.patch b/features/aufs/aufs-bugfix-opts-Fix-missing-break-statement.patch
deleted file mode 100644
index 7313d14d..00000000
--- a/features/aufs/aufs-bugfix-opts-Fix-missing-break-statement.patch
+++ /dev/null
@@ -1,32 +0,0 @@
-From 36d415080900e558b30c312c93c5ffcaab996682 Mon Sep 17 00:00:00 2001
-From: He Zhe <zhe.he@windriver.com>
-Date: Tue, 3 Sep 2019 15:28:03 +0800
-Subject: [PATCH 1/2] aufs: bugfix, opts: Fix missing break statement
-
-commit 4a80018d718f6be2e862d0c70bb11cd6e6d1fae5 upstream
-
-Add missing break statement for case Opt_wsum in au_opt_simple.
-
-Signed-off-by: He Zhe <zhe.he@windriver.com>
-See-also: https://www.mail-archive.com/aufs-users@lists.sourceforge.net/msg05684.html
-(cherry picked from commit 9e7d29356ab57fa5db7e92e51267176e50c1497c)
-Signed-off-by: Bruce Ashfield <bruce.ashfield@gmail.com>
----
- fs/aufs/opts.c | 1 +
- 1 file changed, 1 insertion(+)
-
-diff --git a/fs/aufs/opts.c b/fs/aufs/opts.c
-index c92ca14574ff..a825549c029a 100644
---- a/fs/aufs/opts.c
-+++ b/fs/aufs/opts.c
-@@ -1386,6 +1386,7 @@ static int au_opt_simple(struct super_block *sb, struct au_opt *opt,
- case Opt_wsum:
- au_opt_clr(sbinfo->si_mntflags, SUM);
- au_opt_set(sbinfo->si_mntflags, SUM_W);
-+ break;
- case Opt_nosum:
- au_opt_clr(sbinfo->si_mntflags, SUM);
- au_opt_clr(sbinfo->si_mntflags, SUM_W);
---
-2.19.1
-
diff --git a/features/aufs/aufs-opts-Fix-missing-fallthrough.patch b/features/aufs/aufs-opts-Fix-missing-fallthrough.patch
deleted file mode 100644
index 31ddf1f9..00000000
--- a/features/aufs/aufs-opts-Fix-missing-fallthrough.patch
+++ /dev/null
@@ -1,43 +0,0 @@
-From eb303f5dab8100336ca7619d99591b5ed98d01cb Mon Sep 17 00:00:00 2001
-From: He Zhe <zhe.he@windriver.com>
-Date: Tue, 3 Sep 2019 15:28:04 +0800
-Subject: [PATCH 2/2] aufs: opts: Fix missing fallthrough
-
-commit 8d7b6374d5af2c31ce9501d3502808e3c7a9ea68 upstream
-
-A compilation -Wimplicit-fallthrough warning was enabled by commit
-a035d552a93b ("Makefile: Globally enable fall-through warning")
-and triggers the following warning.
-
-fs/aufs/opts.h:78:11:
-warning: this statement may fall through [-Wimplicit-fallthrough=]
-
-This patch adds comments according GNU manual.
-https://gcc.gnu.org/onlinedocs/gcc/Warning-Options.html#Warning-Options
-
-Signed-off-by: He Zhe <zhe.he@windriver.com>
-See-also: https://www.mail-archive.com/aufs-users@lists.sourceforge.net/msg05685.html
-(cherry picked from commit e7619996b014c5d8fd2f6ad89542c545a207667f)
-Signed-off-by: Bruce Ashfield <bruce.ashfield@gmail.com>
----
- fs/aufs/opts.c | 2 ++
- 1 file changed, 2 insertions(+)
-
-diff --git a/fs/aufs/opts.c b/fs/aufs/opts.c
-index a825549c029a..77e17d7b3bdf 100644
---- a/fs/aufs/opts.c
-+++ b/fs/aufs/opts.c
-@@ -1512,8 +1512,10 @@ static int au_opt_br(struct super_block *sb, struct au_opt *opt,
- if (opt->add.bindex < 0)
- opt->add.bindex = 0;
- goto add;
-+ /* Always goto add, not fallthrough */
- case Opt_prepend:
- opt->add.bindex = 0;
-+ /* fallthrough */
- add: /* indented label */
- case Opt_add:
- err = au_br_add(sb, &opt->add,
---
-2.19.1
-
diff --git a/features/aufs/aufs.scc b/features/aufs/aufs.scc
index e919b07a..e084ec60 100644
--- a/features/aufs/aufs.scc
+++ b/features/aufs/aufs.scc
@@ -1,9 +1,2 @@
# SPDX-License-Identifier: MIT
-patch aufs5-kbuild-support.patch
-patch aufs5-base-support.patch
-patch aufs5-mmap-support.patch
-patch aufs5-standalone-support.patch
-patch aufs5-core-support.patch
-patch aufs5-fix-build-on-v5.3.patch
-patch aufs-bugfix-opts-Fix-missing-break-statement.patch
-patch aufs-opts-Fix-missing-fallthrough.patch
+#
diff --git a/features/aufs/aufs5-base-support.patch b/features/aufs/aufs5-base-support.patch
deleted file mode 100644
index 337222de..00000000
--- a/features/aufs/aufs5-base-support.patch
+++ /dev/null
@@ -1,345 +0,0 @@
-From c622fca67954cced819fe38247f8ff2aa75814f1 Mon Sep 17 00:00:00 2001
-From: Bruce Ashfield <bruce.ashfield@gmail.com>
-Date: Wed, 3 Jul 2019 10:54:31 -0400
-Subject: [PATCH 2/5] aufs5: base support
-
-Application of aufs5-base.patch
-
-Signed-off-by: Bruce Ashfield <bruce.ashfield@gmail.com>
----
- MAINTAINERS | 13 +++++++++++++
- drivers/block/loop.c | 18 ++++++++++++++++++
- fs/dcache.c | 2 +-
- fs/fcntl.c | 4 +++-
- fs/inode.c | 2 +-
- fs/namespace.c | 6 ++++++
- fs/read_write.c | 22 ++++++++++++++++++++++
- fs/splice.c | 10 +++++-----
- fs/sync.c | 2 +-
- include/linux/fs.h | 10 ++++++++++
- include/linux/lockdep.h | 3 +++
- include/linux/mnt_namespace.h | 3 +++
- include/linux/splice.h | 6 ++++++
- kernel/locking/lockdep.c | 3 ++-
- 14 files changed, 94 insertions(+), 10 deletions(-)
-
-diff --git a/MAINTAINERS b/MAINTAINERS
-index 01a52fc964da..abf52c12b830 100644
---- a/MAINTAINERS
-+++ b/MAINTAINERS
-@@ -2769,6 +2769,19 @@ F: include/linux/audit.h
- F: include/uapi/linux/audit.h
- F: kernel/audit*
-
-+AUFS (advanced multi layered unification filesystem) FILESYSTEM
-+M: "J. R. Okajima" <hooanon05g@gmail.com>
-+L: aufs-users@lists.sourceforge.net (members only)
-+L: linux-unionfs@vger.kernel.org
-+W: http://aufs.sourceforge.net
-+T: git://github.com/sfjro/aufs4-linux.git
-+S: Supported
-+F: Documentation/filesystems/aufs/
-+F: Documentation/ABI/testing/debugfs-aufs
-+F: Documentation/ABI/testing/sysfs-aufs
-+F: fs/aufs/
-+F: include/uapi/linux/aufs_type.h
-+
- AUXILIARY DISPLAY DRIVERS
- M: Miguel Ojeda Sandonis <miguel.ojeda.sandonis@gmail.com>
- S: Maintained
-diff --git a/drivers/block/loop.c b/drivers/block/loop.c
-index f11b7dc16e9d..1b723737592b 100644
---- a/drivers/block/loop.c
-+++ b/drivers/block/loop.c
-@@ -746,6 +746,24 @@ static int loop_change_fd(struct loop_device *lo, struct block_device *bdev,
- return error;
- }
-
-+/*
-+ * for AUFS
-+ * no get/put for file.
-+ */
-+struct file *loop_backing_file(struct super_block *sb)
-+{
-+ struct file *ret;
-+ struct loop_device *l;
-+
-+ ret = NULL;
-+ if (MAJOR(sb->s_dev) == LOOP_MAJOR) {
-+ l = sb->s_bdev->bd_disk->private_data;
-+ ret = l->lo_backing_file;
-+ }
-+ return ret;
-+}
-+EXPORT_SYMBOL_GPL(loop_backing_file);
-+
- /* loop sysfs attributes */
-
- static ssize_t loop_attr_show(struct device *dev, char *page,
-diff --git a/fs/dcache.c b/fs/dcache.c
-index c435398f2c81..a688a042d022 100644
---- a/fs/dcache.c
-+++ b/fs/dcache.c
-@@ -1247,7 +1247,7 @@ enum d_walk_ret {
- *
- * The @enter() callbacks are called with d_lock held.
- */
--static void d_walk(struct dentry *parent, void *data,
-+void d_walk(struct dentry *parent, void *data,
- enum d_walk_ret (*enter)(void *, struct dentry *))
- {
- struct dentry *this_parent;
-diff --git a/fs/fcntl.c b/fs/fcntl.c
-index 3d40771e8e7c..d62303c5472a 100644
---- a/fs/fcntl.c
-+++ b/fs/fcntl.c
-@@ -32,7 +32,7 @@
-
- #define SETFL_MASK (O_APPEND | O_NONBLOCK | O_NDELAY | O_DIRECT | O_NOATIME)
-
--static int setfl(int fd, struct file * filp, unsigned long arg)
-+int setfl(int fd, struct file * filp, unsigned long arg)
- {
- struct inode * inode = file_inode(filp);
- int error = 0;
-@@ -63,6 +63,8 @@ static int setfl(int fd, struct file * filp, unsigned long arg)
-
- if (filp->f_op->check_flags)
- error = filp->f_op->check_flags(arg);
-+ if (!error && filp->f_op->setfl)
-+ error = filp->f_op->setfl(filp, arg);
- if (error)
- return error;
-
-diff --git a/fs/inode.c b/fs/inode.c
-index 2bf21e2c90fc..9b908c37971f 100644
---- a/fs/inode.c
-+++ b/fs/inode.c
-@@ -1670,7 +1670,7 @@ EXPORT_SYMBOL(generic_update_time);
- * This does the actual work of updating an inodes time or version. Must have
- * had called mnt_want_write() before calling this.
- */
--static int update_time(struct inode *inode, struct timespec64 *time, int flags)
-+int update_time(struct inode *inode, struct timespec64 *time, int flags)
- {
- int (*update_time)(struct inode *, struct timespec64 *, int);
-
-diff --git a/fs/namespace.c b/fs/namespace.c
-index 7660c2749c96..d6e9681f044d 100644
---- a/fs/namespace.c
-+++ b/fs/namespace.c
-@@ -770,6 +770,12 @@ static inline int check_mnt(struct mount *mnt)
- return mnt->mnt_ns == current->nsproxy->mnt_ns;
- }
-
-+/* for aufs, CONFIG_AUFS_BR_FUSE */
-+int is_current_mnt_ns(struct vfsmount *mnt)
-+{
-+ return check_mnt(real_mount(mnt));
-+}
-+
- /*
- * vfsmount lock must be held for write
- */
-diff --git a/fs/read_write.c b/fs/read_write.c
-index c543d965e288..35ab54e0a994 100644
---- a/fs/read_write.c
-+++ b/fs/read_write.c
-@@ -498,6 +498,28 @@ static ssize_t __vfs_write(struct file *file, const char __user *p,
- return -EINVAL;
- }
-
-+vfs_readf_t vfs_readf(struct file *file)
-+{
-+ const struct file_operations *fop = file->f_op;
-+
-+ if (fop->read)
-+ return fop->read;
-+ if (fop->read_iter)
-+ return new_sync_read;
-+ return ERR_PTR(-ENOSYS);
-+}
-+
-+vfs_writef_t vfs_writef(struct file *file)
-+{
-+ const struct file_operations *fop = file->f_op;
-+
-+ if (fop->write)
-+ return fop->write;
-+ if (fop->write_iter)
-+ return new_sync_write;
-+ return ERR_PTR(-ENOSYS);
-+}
-+
- ssize_t __kernel_write(struct file *file, const void *buf, size_t count, loff_t *pos)
- {
- mm_segment_t old_fs;
-diff --git a/fs/splice.c b/fs/splice.c
-index 14cb602d9a2f..58d2692c5f30 100644
---- a/fs/splice.c
-+++ b/fs/splice.c
-@@ -834,8 +834,8 @@ EXPORT_SYMBOL(generic_splice_sendpage);
- /*
- * Attempt to initiate a splice from pipe to file.
- */
--static long do_splice_from(struct pipe_inode_info *pipe, struct file *out,
-- loff_t *ppos, size_t len, unsigned int flags)
-+long do_splice_from(struct pipe_inode_info *pipe, struct file *out,
-+ loff_t *ppos, size_t len, unsigned int flags)
- {
- ssize_t (*splice_write)(struct pipe_inode_info *, struct file *,
- loff_t *, size_t, unsigned int);
-@@ -851,9 +851,9 @@ static long do_splice_from(struct pipe_inode_info *pipe, struct file *out,
- /*
- * Attempt to initiate a splice from a file to a pipe.
- */
--static long do_splice_to(struct file *in, loff_t *ppos,
-- struct pipe_inode_info *pipe, size_t len,
-- unsigned int flags)
-+long do_splice_to(struct file *in, loff_t *ppos,
-+ struct pipe_inode_info *pipe, size_t len,
-+ unsigned int flags)
- {
- ssize_t (*splice_read)(struct file *, loff_t *,
- struct pipe_inode_info *, size_t, unsigned int);
-diff --git a/fs/sync.c b/fs/sync.c
-index 4d1ff010bc5a..457f4e4a5cc1 100644
---- a/fs/sync.c
-+++ b/fs/sync.c
-@@ -28,7 +28,7 @@
- * wait == 1 case since in that case write_inode() functions do
- * sync_dirty_buffer() and thus effectively write one block at a time.
- */
--static int __sync_filesystem(struct super_block *sb, int wait)
-+int __sync_filesystem(struct super_block *sb, int wait)
- {
- if (wait)
- sync_inodes_sb(sb);
-diff --git a/include/linux/fs.h b/include/linux/fs.h
-index f7fdfe93e25d..28593b894e7b 100644
---- a/include/linux/fs.h
-+++ b/include/linux/fs.h
-@@ -1333,6 +1333,7 @@ extern void fasync_free(struct fasync_struct *);
- /* can be called from interrupts */
- extern void kill_fasync(struct fasync_struct **, int, int);
-
-+extern int setfl(int fd, struct file * filp, unsigned long arg);
- extern void __f_setown(struct file *filp, struct pid *, enum pid_type, int force);
- extern int f_setown(struct file *filp, unsigned long arg, int force);
- extern void f_delown(struct file *filp);
-@@ -1812,6 +1813,7 @@ struct file_operations {
- ssize_t (*sendpage) (struct file *, struct page *, int, size_t, loff_t *, int);
- unsigned long (*get_unmapped_area)(struct file *, unsigned long, unsigned long, unsigned long, unsigned long);
- int (*check_flags)(int);
-+ int (*setfl)(struct file *, unsigned long);
- int (*flock) (struct file *, int, struct file_lock *);
- ssize_t (*splice_write)(struct pipe_inode_info *, struct file *, loff_t *, size_t, unsigned int);
- ssize_t (*splice_read)(struct file *, loff_t *, struct pipe_inode_info *, size_t, unsigned int);
-@@ -1882,6 +1884,12 @@ ssize_t rw_copy_check_uvector(int type, const struct iovec __user * uvector,
- struct iovec *fast_pointer,
- struct iovec **ret_pointer);
-
-+typedef ssize_t (*vfs_readf_t)(struct file *, char __user *, size_t, loff_t *);
-+typedef ssize_t (*vfs_writef_t)(struct file *, const char __user *, size_t,
-+ loff_t *);
-+vfs_readf_t vfs_readf(struct file *file);
-+vfs_writef_t vfs_writef(struct file *file);
-+
- extern ssize_t __vfs_read(struct file *, char __user *, size_t, loff_t *);
- extern ssize_t vfs_read(struct file *, char __user *, size_t, loff_t *);
- extern ssize_t vfs_write(struct file *, const char __user *, size_t, loff_t *);
-@@ -2315,6 +2323,7 @@ extern int current_umask(void);
- extern void ihold(struct inode * inode);
- extern void iput(struct inode *);
- extern int generic_update_time(struct inode *, struct timespec64 *, int);
-+extern int update_time(struct inode *, struct timespec64 *, int);
-
- /* /sys/fs */
- extern struct kobject *fs_kobj;
-@@ -2603,6 +2612,7 @@ static inline bool sb_is_blkdev_sb(struct super_block *sb)
- return false;
- }
- #endif
-+extern int __sync_filesystem(struct super_block *, int);
- extern int sync_filesystem(struct super_block *);
- extern const struct file_operations def_blk_fops;
- extern const struct file_operations def_chr_fops;
-diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h
-index 6e2377e6c1d6..5a945d18a72a 100644
---- a/include/linux/lockdep.h
-+++ b/include/linux/lockdep.h
-@@ -325,6 +325,8 @@ static inline int lockdep_match_key(struct lockdep_map *lock,
- return lock->key == key;
- }
-
-+struct lock_class *lockdep_hlock_class(struct held_lock *hlock);
-+
- /*
- * Acquire a lock.
- *
-@@ -463,6 +465,7 @@ struct lockdep_map { };
-
- #define lockdep_depth(tsk) (0)
-
-+#define lockdep_is_held(lock) (1)
- #define lockdep_is_held_type(l, r) (1)
-
- #define lockdep_assert_held(l) do { (void)(l); } while (0)
-diff --git a/include/linux/mnt_namespace.h b/include/linux/mnt_namespace.h
-index 35942084cd40..24f5fd1a789d 100644
---- a/include/linux/mnt_namespace.h
-+++ b/include/linux/mnt_namespace.h
-@@ -6,11 +6,14 @@
- struct mnt_namespace;
- struct fs_struct;
- struct user_namespace;
-+struct vfsmount;
-
- extern struct mnt_namespace *copy_mnt_ns(unsigned long, struct mnt_namespace *,
- struct user_namespace *, struct fs_struct *);
- extern void put_mnt_ns(struct mnt_namespace *ns);
-
-+extern int is_current_mnt_ns(struct vfsmount *mnt);
-+
- extern const struct file_operations proc_mounts_operations;
- extern const struct file_operations proc_mountinfo_operations;
- extern const struct file_operations proc_mountstats_operations;
-diff --git a/include/linux/splice.h b/include/linux/splice.h
-index 74b4911ac16d..19789fbea567 100644
---- a/include/linux/splice.h
-+++ b/include/linux/splice.h
-@@ -87,4 +87,10 @@ extern void splice_shrink_spd(struct splice_pipe_desc *);
-
- extern const struct pipe_buf_operations page_cache_pipe_buf_ops;
- extern const struct pipe_buf_operations default_pipe_buf_ops;
-+
-+extern long do_splice_from(struct pipe_inode_info *pipe, struct file *out,
-+ loff_t *ppos, size_t len, unsigned int flags);
-+extern long do_splice_to(struct file *in, loff_t *ppos,
-+ struct pipe_inode_info *pipe, size_t len,
-+ unsigned int flags);
- #endif
-diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c
-index c47788fa85f9..3c35a1059890 100644
---- a/kernel/locking/lockdep.c
-+++ b/kernel/locking/lockdep.c
-@@ -152,7 +152,7 @@ static
- #endif
- struct lock_class lock_classes[MAX_LOCKDEP_KEYS];
-
--static inline struct lock_class *hlock_class(struct held_lock *hlock)
-+inline struct lock_class *lockdep_hlock_class(struct held_lock *hlock)
- {
- if (!hlock->class_idx) {
- /*
-@@ -163,6 +163,7 @@ static inline struct lock_class *hlock_class(struct held_lock *hlock)
- }
- return lock_classes + hlock->class_idx - 1;
- }
-+#define hlock_class(hlock) lockdep_hlock_class(hlock)
-
- #ifdef CONFIG_LOCK_STAT
- static DEFINE_PER_CPU(struct lock_class_stats[MAX_LOCKDEP_KEYS], cpu_lock_stats);
---
-2.19.1
-
diff --git a/features/aufs/aufs5-core-support.patch b/features/aufs/aufs5-core-support.patch
deleted file mode 100644
index 1f772d06..00000000
--- a/features/aufs/aufs5-core-support.patch
+++ /dev/null
@@ -1,38587 +0,0 @@
-From 8880af69d321a901f1c728e0d9c8fabaf97c7fd1 Mon Sep 17 00:00:00 2001
-From: Bruce Ashfield <bruce.ashfield@gmail.com>
-Date: Wed, 3 Jul 2019 10:56:53 -0400
-Subject: [PATCH 5/5] aufs5: core support
-
-Signed-off-by: Bruce Ashfield <bruce.ashfield@gmail.com>
----
- Documentation/ABI/testing/debugfs-aufs | 55 +
- Documentation/ABI/testing/sysfs-aufs | 31 +
- Documentation/filesystems/aufs/README | 399 ++++
- .../filesystems/aufs/design/01intro.txt | 171 ++
- .../filesystems/aufs/design/02struct.txt | 258 +++
- .../filesystems/aufs/design/03atomic_open.txt | 85 +
- .../filesystems/aufs/design/03lookup.txt | 113 +
- .../filesystems/aufs/design/04branch.txt | 74 +
- .../filesystems/aufs/design/05wbr_policy.txt | 64 +
- .../filesystems/aufs/design/06dirren.dot | 31 +
- .../filesystems/aufs/design/06dirren.txt | 102 +
- .../filesystems/aufs/design/06fhsm.txt | 120 +
- .../filesystems/aufs/design/06mmap.txt | 72 +
- .../filesystems/aufs/design/06xattr.txt | 96 +
- .../filesystems/aufs/design/07export.txt | 58 +
- .../filesystems/aufs/design/08shwh.txt | 52 +
- .../filesystems/aufs/design/10dynop.txt | 47 +
- fs/aufs/Kconfig | 199 ++
- fs/aufs/Makefile | 46 +
- fs/aufs/aufs.h | 62 +
- fs/aufs/branch.c | 1423 ++++++++++++
- fs/aufs/branch.h | 366 +++
- fs/aufs/conf.mk | 40 +
- fs/aufs/cpup.c | 1458 ++++++++++++
- fs/aufs/cpup.h | 100 +
- fs/aufs/dbgaufs.c | 526 +++++
- fs/aufs/dbgaufs.h | 53 +
- fs/aufs/dcsub.c | 225 ++
- fs/aufs/dcsub.h | 137 ++
- fs/aufs/debug.c | 441 ++++
- fs/aufs/debug.h | 226 ++
- fs/aufs/dentry.c | 1154 ++++++++++
- fs/aufs/dentry.h | 268 +++
- fs/aufs/dinfo.c | 554 +++++
- fs/aufs/dir.c | 763 +++++++
- fs/aufs/dir.h | 134 ++
- fs/aufs/dirren.c | 1316 +++++++++++
- fs/aufs/dirren.h | 140 ++
- fs/aufs/dynop.c | 367 +++
- fs/aufs/dynop.h | 77 +
- fs/aufs/export.c | 838 +++++++
- fs/aufs/f_op.c | 819 +++++++
- fs/aufs/fhsm.c | 427 ++++
- fs/aufs/file.c | 863 ++++++++
- fs/aufs/file.h | 342 +++
- fs/aufs/finfo.c | 149 ++
- fs/aufs/fstype.h | 401 ++++
- fs/aufs/hbl.h | 65 +
- fs/aufs/hfsnotify.c | 288 +++
- fs/aufs/hfsplus.c | 60 +
- fs/aufs/hnotify.c | 721 ++++++
- fs/aufs/i_op.c | 1507 +++++++++++++
- fs/aufs/i_op_add.c | 936 ++++++++
- fs/aufs/i_op_del.c | 513 +++++
- fs/aufs/i_op_ren.c | 1250 +++++++++++
- fs/aufs/iinfo.c | 286 +++
- fs/aufs/inode.c | 529 +++++
- fs/aufs/inode.h | 698 ++++++
- fs/aufs/ioctl.c | 220 ++
- fs/aufs/lcnt.h | 186 ++
- fs/aufs/loop.c | 148 ++
- fs/aufs/loop.h | 55 +
- fs/aufs/magic.mk | 31 +
- fs/aufs/module.c | 273 +++
- fs/aufs/module.h | 166 ++
- fs/aufs/mvdown.c | 706 ++++++
- fs/aufs/opts.c | 1877 ++++++++++++++++
- fs/aufs/opts.h | 225 ++
- fs/aufs/plink.c | 516 +++++
- fs/aufs/poll.c | 51 +
- fs/aufs/posix_acl.c | 103 +
- fs/aufs/procfs.c | 171 ++
- fs/aufs/rdu.c | 384 ++++
- fs/aufs/rwsem.h | 73 +
- fs/aufs/sbinfo.c | 314 +++
- fs/aufs/super.c | 1047 +++++++++
- fs/aufs/super.h | 589 +++++
- fs/aufs/sysaufs.c | 93 +
- fs/aufs/sysaufs.h | 102 +
- fs/aufs/sysfs.c | 374 ++++
- fs/aufs/sysrq.c | 160 ++
- fs/aufs/vdir.c | 896 ++++++++
- fs/aufs/vfsub.c | 902 ++++++++
- fs/aufs/vfsub.h | 354 +++
- fs/aufs/wbr_policy.c | 830 +++++++
- fs/aufs/whout.c | 1062 +++++++++
- fs/aufs/whout.h | 86 +
- fs/aufs/wkq.c | 392 ++++
- fs/aufs/wkq.h | 89 +
- fs/aufs/xattr.c | 356 +++
- fs/aufs/xino.c | 1965 +++++++++++++++++
- include/uapi/linux/aufs_type.h | 448 ++++
- 92 files changed, 37839 insertions(+)
- create mode 100644 Documentation/ABI/testing/debugfs-aufs
- create mode 100644 Documentation/ABI/testing/sysfs-aufs
- create mode 100644 Documentation/filesystems/aufs/README
- create mode 100644 Documentation/filesystems/aufs/design/01intro.txt
- create mode 100644 Documentation/filesystems/aufs/design/02struct.txt
- create mode 100644 Documentation/filesystems/aufs/design/03atomic_open.txt
- create mode 100644 Documentation/filesystems/aufs/design/03lookup.txt
- create mode 100644 Documentation/filesystems/aufs/design/04branch.txt
- create mode 100644 Documentation/filesystems/aufs/design/05wbr_policy.txt
- create mode 100644 Documentation/filesystems/aufs/design/06dirren.dot
- create mode 100644 Documentation/filesystems/aufs/design/06dirren.txt
- create mode 100644 Documentation/filesystems/aufs/design/06fhsm.txt
- create mode 100644 Documentation/filesystems/aufs/design/06mmap.txt
- create mode 100644 Documentation/filesystems/aufs/design/06xattr.txt
- create mode 100644 Documentation/filesystems/aufs/design/07export.txt
- create mode 100644 Documentation/filesystems/aufs/design/08shwh.txt
- create mode 100644 Documentation/filesystems/aufs/design/10dynop.txt
- create mode 100644 fs/aufs/Kconfig
- create mode 100644 fs/aufs/Makefile
- create mode 100644 fs/aufs/aufs.h
- create mode 100644 fs/aufs/branch.c
- create mode 100644 fs/aufs/branch.h
- create mode 100644 fs/aufs/conf.mk
- create mode 100644 fs/aufs/cpup.c
- create mode 100644 fs/aufs/cpup.h
- create mode 100644 fs/aufs/dbgaufs.c
- create mode 100644 fs/aufs/dbgaufs.h
- create mode 100644 fs/aufs/dcsub.c
- create mode 100644 fs/aufs/dcsub.h
- create mode 100644 fs/aufs/debug.c
- create mode 100644 fs/aufs/debug.h
- create mode 100644 fs/aufs/dentry.c
- create mode 100644 fs/aufs/dentry.h
- create mode 100644 fs/aufs/dinfo.c
- create mode 100644 fs/aufs/dir.c
- create mode 100644 fs/aufs/dir.h
- create mode 100644 fs/aufs/dirren.c
- create mode 100644 fs/aufs/dirren.h
- create mode 100644 fs/aufs/dynop.c
- create mode 100644 fs/aufs/dynop.h
- create mode 100644 fs/aufs/export.c
- create mode 100644 fs/aufs/f_op.c
- create mode 100644 fs/aufs/fhsm.c
- create mode 100644 fs/aufs/file.c
- create mode 100644 fs/aufs/file.h
- create mode 100644 fs/aufs/finfo.c
- create mode 100644 fs/aufs/fstype.h
- create mode 100644 fs/aufs/hbl.h
- create mode 100644 fs/aufs/hfsnotify.c
- create mode 100644 fs/aufs/hfsplus.c
- create mode 100644 fs/aufs/hnotify.c
- create mode 100644 fs/aufs/i_op.c
- create mode 100644 fs/aufs/i_op_add.c
- create mode 100644 fs/aufs/i_op_del.c
- create mode 100644 fs/aufs/i_op_ren.c
- create mode 100644 fs/aufs/iinfo.c
- create mode 100644 fs/aufs/inode.c
- create mode 100644 fs/aufs/inode.h
- create mode 100644 fs/aufs/ioctl.c
- create mode 100644 fs/aufs/lcnt.h
- create mode 100644 fs/aufs/loop.c
- create mode 100644 fs/aufs/loop.h
- create mode 100644 fs/aufs/magic.mk
- create mode 100644 fs/aufs/module.c
- create mode 100644 fs/aufs/module.h
- create mode 100644 fs/aufs/mvdown.c
- create mode 100644 fs/aufs/opts.c
- create mode 100644 fs/aufs/opts.h
- create mode 100644 fs/aufs/plink.c
- create mode 100644 fs/aufs/poll.c
- create mode 100644 fs/aufs/posix_acl.c
- create mode 100644 fs/aufs/procfs.c
- create mode 100644 fs/aufs/rdu.c
- create mode 100644 fs/aufs/rwsem.h
- create mode 100644 fs/aufs/sbinfo.c
- create mode 100644 fs/aufs/super.c
- create mode 100644 fs/aufs/super.h
- create mode 100644 fs/aufs/sysaufs.c
- create mode 100644 fs/aufs/sysaufs.h
- create mode 100644 fs/aufs/sysfs.c
- create mode 100644 fs/aufs/sysrq.c
- create mode 100644 fs/aufs/vdir.c
- create mode 100644 fs/aufs/vfsub.c
- create mode 100644 fs/aufs/vfsub.h
- create mode 100644 fs/aufs/wbr_policy.c
- create mode 100644 fs/aufs/whout.c
- create mode 100644 fs/aufs/whout.h
- create mode 100644 fs/aufs/wkq.c
- create mode 100644 fs/aufs/wkq.h
- create mode 100644 fs/aufs/xattr.c
- create mode 100644 fs/aufs/xino.c
- create mode 100644 include/uapi/linux/aufs_type.h
-
-diff --git a/Documentation/ABI/testing/debugfs-aufs b/Documentation/ABI/testing/debugfs-aufs
-new file mode 100644
-index 000000000000..4a6694194ba6
---- /dev/null
-+++ b/Documentation/ABI/testing/debugfs-aufs
-@@ -0,0 +1,55 @@
-+What: /debug/aufs/si_<id>/
-+Date: March 2009
-+Contact: J. R. Okajima <hooanon05g@gmail.com>
-+Description:
-+ Under /debug/aufs, a directory named si_<id> is created
-+ per aufs mount, where <id> is a unique id generated
-+ internally.
-+
-+What: /debug/aufs/si_<id>/plink
-+Date: Apr 2013
-+Contact: J. R. Okajima <hooanon05g@gmail.com>
-+Description:
-+ It has three lines and shows the information about the
-+ pseudo-link. The first line is a single number
-+ representing a number of buckets. The second line is a
-+ number of pseudo-links per buckets (separated by a
-+ blank). The last line is a single number representing a
-+ total number of psedo-links.
-+ When the aufs mount option 'noplink' is specified, it
-+ will show "1\n0\n0\n".
-+
-+What: /debug/aufs/si_<id>/xib
-+Date: March 2009
-+Contact: J. R. Okajima <hooanon05g@gmail.com>
-+Description:
-+ It shows the consumed blocks by xib (External Inode Number
-+ Bitmap), its block size and file size.
-+ When the aufs mount option 'noxino' is specified, it
-+ will be empty. About XINO files, see the aufs manual.
-+
-+What: /debug/aufs/si_<id>/xi0, xi1 ... xiN and xiN-N
-+Date: March 2009
-+Contact: J. R. Okajima <hooanon05g@gmail.com>
-+Description:
-+ It shows the consumed blocks by xino (External Inode Number
-+ Translation Table), its link count, block size and file
-+ size.
-+ Due to the file size limit, there may exist multiple
-+ xino files per branch. In this case, "-N" is added to
-+ the filename and it corresponds to the index of the
-+ internal xino array. "-0" is omitted.
-+ When the aufs mount option 'noxino' is specified, Those
-+ entries won't exist. About XINO files, see the aufs
-+ manual.
-+
-+What: /debug/aufs/si_<id>/xigen
-+Date: March 2009
-+Contact: J. R. Okajima <hooanon05g@gmail.com>
-+Description:
-+ It shows the consumed blocks by xigen (External Inode
-+ Generation Table), its block size and file size.
-+ If CONFIG_AUFS_EXPORT is disabled, this entry will not
-+ be created.
-+ When the aufs mount option 'noxino' is specified, it
-+ will be empty. About XINO files, see the aufs manual.
-diff --git a/Documentation/ABI/testing/sysfs-aufs b/Documentation/ABI/testing/sysfs-aufs
-new file mode 100644
-index 000000000000..82f9518495ea
---- /dev/null
-+++ b/Documentation/ABI/testing/sysfs-aufs
-@@ -0,0 +1,31 @@
-+What: /sys/fs/aufs/si_<id>/
-+Date: March 2009
-+Contact: J. R. Okajima <hooanon05g@gmail.com>
-+Description:
-+ Under /sys/fs/aufs, a directory named si_<id> is created
-+ per aufs mount, where <id> is a unique id generated
-+ internally.
-+
-+What: /sys/fs/aufs/si_<id>/br0, br1 ... brN
-+Date: March 2009
-+Contact: J. R. Okajima <hooanon05g@gmail.com>
-+Description:
-+ It shows the abolute path of a member directory (which
-+ is called branch) in aufs, and its permission.
-+
-+What: /sys/fs/aufs/si_<id>/brid0, brid1 ... bridN
-+Date: July 2013
-+Contact: J. R. Okajima <hooanon05g@gmail.com>
-+Description:
-+ It shows the id of a member directory (which is called
-+ branch) in aufs.
-+
-+What: /sys/fs/aufs/si_<id>/xi_path
-+Date: March 2009
-+Contact: J. R. Okajima <hooanon05g@gmail.com>
-+Description:
-+ It shows the abolute path of XINO (External Inode Number
-+ Bitmap, Translation Table and Generation Table) file
-+ even if it is the default path.
-+ When the aufs mount option 'noxino' is specified, it
-+ will be empty. About XINO files, see the aufs manual.
-diff --git a/Documentation/filesystems/aufs/README b/Documentation/filesystems/aufs/README
-new file mode 100644
-index 000000000000..6e6774fbf602
---- /dev/null
-+++ b/Documentation/filesystems/aufs/README
-@@ -0,0 +1,399 @@
-+
-+Aufs5 -- advanced multi layered unification filesystem version 5.x
-+http://aufs.sf.net
-+Junjiro R. Okajima
-+
-+
-+0. Introduction
-+----------------------------------------
-+In the early days, aufs was entirely re-designed and re-implemented
-+Unionfs Version 1.x series. Adding many original ideas, approaches,
-+improvements and implementations, it became totally different from
-+Unionfs while keeping the basic features.
-+Later, Unionfs Version 2.x series began taking some of the same
-+approaches to aufs1's.
-+Unionfs was being developed by Professor Erez Zadok at Stony Brook
-+University and his team.
-+
-+Aufs5 supports linux-v5.0 and later, If you want older kernel version
-+support,
-+- for linux-v4.x series, try aufs4-linux.git or aufs4-standalone.git
-+- for linux-v3.x series, try aufs3-linux.git or aufs3-standalone.git
-+- for linux-v2.6.16 and later, try aufs2-2.6.git, aufs2-standalone.git
-+ or aufs1 from CVS on SourceForge.
-+
-+Note: it becomes clear that "Aufs was rejected. Let's give it up."
-+ According to Christoph Hellwig, linux rejects all union-type
-+ filesystems but UnionMount.
-+<http://marc.info/?l=linux-kernel&m=123938533724484&w=2>
-+
-+PS. Al Viro seems have a plan to merge aufs as well as overlayfs and
-+ UnionMount, and he pointed out an issue around a directory mutex
-+ lock and aufs addressed it. But it is still unsure whether aufs will
-+ be merged (or any other union solution).
-+<http://marc.info/?l=linux-kernel&m=136312705029295&w=1>
-+
-+
-+1. Features
-+----------------------------------------
-+- unite several directories into a single virtual filesystem. The member
-+ directory is called as a branch.
-+- you can specify the permission flags to the branch, which are 'readonly',
-+ 'readwrite' and 'whiteout-able.'
-+- by upper writable branch, internal copyup and whiteout, files/dirs on
-+ readonly branch are modifiable logically.
-+- dynamic branch manipulation, add, del.
-+- etc...
-+
-+Also there are many enhancements in aufs, such as:
-+- test only the highest one for the directory permission (dirperm1)
-+- copyup on open (coo=)
-+- 'move' policy for copy-up between two writable branches, after
-+ checking free space.
-+- xattr, acl
-+- readdir(3) in userspace.
-+- keep inode number by external inode number table
-+- keep the timestamps of file/dir in internal copyup operation
-+- seekable directory, supporting NFS readdir.
-+- whiteout is hardlinked in order to reduce the consumption of inodes
-+ on branch
-+- do not copyup, nor create a whiteout when it is unnecessary
-+- revert a single systemcall when an error occurs in aufs
-+- remount interface instead of ioctl
-+- maintain /etc/mtab by an external command, /sbin/mount.aufs.
-+- loopback mounted filesystem as a branch
-+- kernel thread for removing the dir who has a plenty of whiteouts
-+- support copyup sparse file (a file which has a 'hole' in it)
-+- default permission flags for branches
-+- selectable permission flags for ro branch, whether whiteout can
-+ exist or not
-+- export via NFS.
-+- support <sysfs>/fs/aufs and <debugfs>/aufs.
-+- support multiple writable branches, some policies to select one
-+ among multiple writable branches.
-+- a new semantics for link(2) and rename(2) to support multiple
-+ writable branches.
-+- no glibc changes are required.
-+- pseudo hardlink (hardlink over branches)
-+- allow a direct access manually to a file on branch, e.g. bypassing aufs.
-+ including NFS or remote filesystem branch.
-+- userspace wrapper for pathconf(3)/fpathconf(3) with _PC_LINK_MAX.
-+- and more...
-+
-+Currently these features are dropped temporary from aufs5.
-+See design/08plan.txt in detail.
-+- nested mount, i.e. aufs as readonly no-whiteout branch of another aufs
-+ (robr)
-+- statistics of aufs thread (/sys/fs/aufs/stat)
-+
-+Features or just an idea in the future (see also design/*.txt),
-+- reorder the branch index without del/re-add.
-+- permanent xino files for NFSD
-+- an option for refreshing the opened files after add/del branches
-+- light version, without branch manipulation. (unnecessary?)
-+- copyup in userspace
-+- inotify in userspace
-+- readv/writev
-+
-+
-+2. Download
-+----------------------------------------
-+There are three GIT trees for aufs5, aufs5-linux.git,
-+aufs5-standalone.git, and aufs-util.git. Note that there is no "5" in
-+"aufs-util.git."
-+While the aufs-util is always necessary, you need either of aufs5-linux
-+or aufs5-standalone.
-+
-+The aufs5-linux tree includes the whole linux mainline GIT tree,
-+git://git.kernel.org/.../torvalds/linux.git.
-+And you cannot select CONFIG_AUFS_FS=m for this version, eg. you cannot
-+build aufs5 as an external kernel module.
-+Several extra patches are not included in this tree. Only
-+aufs5-standalone tree contains them. They are described in the later
-+section "Configuration and Compilation."
-+
-+On the other hand, the aufs5-standalone tree has only aufs source files
-+and necessary patches, and you can select CONFIG_AUFS_FS=m.
-+But you need to apply all aufs patches manually.
-+
-+You will find GIT branches whose name is in form of "aufs5.x" where "x"
-+represents the linux kernel version, "linux-5.x". For instance,
-+"aufs5.0" is for linux-5.0. For latest "linux-5.x-rcN", use
-+"aufs5.x-rcN" branch.
-+
-+o aufs5-linux tree
-+$ git clone --reference /your/linux/git/tree \
-+ git://github.com/sfjro/aufs5-linux.git aufs5-linux.git
-+- if you don't have linux GIT tree, then remove "--reference ..."
-+$ cd aufs5-linux.git
-+$ git checkout origin/aufs5.0
-+
-+Or You may want to directly git-pull aufs into your linux GIT tree, and
-+leave the patch-work to GIT.
-+$ cd /your/linux/git/tree
-+$ git remote add aufs5 git://github.com/sfjro/aufs5-linux.git
-+$ git fetch aufs5
-+$ git checkout -b my5.0 v5.0
-+$ (add your local change...)
-+$ git pull aufs5 aufs5.0
-+- now you have v5.0 + your_changes + aufs5.0 in you my5.0 branch.
-+- you may need to solve some conflicts between your_changes and
-+ aufs5.0. in this case, git-rerere is recommended so that you can
-+ solve the similar conflicts automatically when you upgrade to 5.1 or
-+ later in the future.
-+
-+o aufs5-standalone tree
-+$ git clone git://github.com/sfjro/aufs5-standalone.git aufs5-standalone.git
-+$ cd aufs5-standalone.git
-+$ git checkout origin/aufs5.0
-+
-+o aufs-util tree
-+$ git clone git://git.code.sf.net/p/aufs/aufs-util aufs-util.git
-+- note that the public aufs-util.git is on SourceForge instead of
-+ GitHUB.
-+$ cd aufs-util.git
-+$ git checkout origin/aufs5.0
-+
-+Note: The 5.x-rcN branch is to be used with `rc' kernel versions ONLY.
-+The minor version number, 'x' in '5.x', of aufs may not always
-+follow the minor version number of the kernel.
-+Because changes in the kernel that cause the use of a new
-+minor version number do not always require changes to aufs-util.
-+
-+Since aufs-util has its own minor version number, you may not be
-+able to find a GIT branch in aufs-util for your kernel's
-+exact minor version number.
-+In this case, you should git-checkout the branch for the
-+nearest lower number.
-+
-+For (an unreleased) example:
-+If you are using "linux-5.10" and the "aufs5.10" branch
-+does not exist in aufs-util repository, then "aufs5.9", "aufs5.8"
-+or something numerically smaller is the branch for your kernel.
-+
-+Also you can view all branches by
-+ $ git branch -a
-+
-+
-+3. Configuration and Compilation
-+----------------------------------------
-+Make sure you have git-checkout'ed the correct branch.
-+
-+For aufs5-linux tree,
-+- enable CONFIG_AUFS_FS.
-+- set other aufs configurations if necessary.
-+
-+For aufs5-standalone tree,
-+There are several ways to build.
-+
-+1.
-+- apply ./aufs5-kbuild.patch to your kernel source files.
-+- apply ./aufs5-base.patch too.
-+- apply ./aufs5-mmap.patch too.
-+- apply ./aufs5-standalone.patch too, if you have a plan to set
-+ CONFIG_AUFS_FS=m. otherwise you don't need ./aufs5-standalone.patch.
-+- copy ./{Documentation,fs,include/uapi/linux/aufs_type.h} files to your
-+ kernel source tree. Never copy $PWD/include/uapi/linux/Kbuild.
-+- enable CONFIG_AUFS_FS, you can select either
-+ =m or =y.
-+- and build your kernel as usual.
-+- install the built kernel.
-+- install the header files too by "make headers_install" to the
-+ directory where you specify. By default, it is $PWD/usr.
-+ "make help" shows a brief note for headers_install.
-+- and reboot your system.
-+
-+2.
-+- module only (CONFIG_AUFS_FS=m).
-+- apply ./aufs5-base.patch to your kernel source files.
-+- apply ./aufs5-mmap.patch too.
-+- apply ./aufs5-standalone.patch too.
-+- build your kernel, don't forget "make headers_install", and reboot.
-+- edit ./config.mk and set other aufs configurations if necessary.
-+ Note: You should read $PWD/fs/aufs/Kconfig carefully which describes
-+ every aufs configurations.
-+- build the module by simple "make".
-+- you can specify ${KDIR} make variable which points to your kernel
-+ source tree.
-+- install the files
-+ + run "make install" to install the aufs module, or copy the built
-+ $PWD/aufs.ko to /lib/modules/... and run depmod -a (or reboot simply).
-+ + run "make install_headers" (instead of headers_install) to install
-+ the modified aufs header file (you can specify DESTDIR which is
-+ available in aufs standalone version's Makefile only), or copy
-+ $PWD/usr/include/linux/aufs_type.h to /usr/include/linux or wherever
-+ you like manually. By default, the target directory is $PWD/usr.
-+- no need to apply aufs5-kbuild.patch, nor copying source files to your
-+ kernel source tree.
-+
-+Note: The header file aufs_type.h is necessary to build aufs-util
-+ as well as "make headers_install" in the kernel source tree.
-+ headers_install is subject to be forgotten, but it is essentially
-+ necessary, not only for building aufs-util.
-+ You may not meet problems without headers_install in some older
-+ version though.
-+
-+And then,
-+- read README in aufs-util, build and install it
-+- note that your distribution may contain an obsoleted version of
-+ aufs_type.h in /usr/include/linux or something. When you build aufs
-+ utilities, make sure that your compiler refers the correct aufs header
-+ file which is built by "make headers_install."
-+- if you want to use readdir(3) in userspace or pathconf(3) wrapper,
-+ then run "make install_ulib" too. And refer to the aufs manual in
-+ detail.
-+
-+There several other patches in aufs5-standalone.git. They are all
-+optional. When you meet some problems, they will help you.
-+- aufs5-loopback.patch
-+ Supports a nested loopback mount in a branch-fs. This patch is
-+ unnecessary until aufs produces a message like "you may want to try
-+ another patch for loopback file".
-+- proc_mounts.patch
-+ When there are many mountpoints and many mount(2)/umount(2) are
-+ running, then /proc/mounts may not show the all mountpoints. This
-+ patch makes /proc/mounts always show the full mountpoints list.
-+ If you don't want to apply this patch and meet such problem, then you
-+ need to increase the value of 'ProcMounts_Times' make-variable in
-+ aufs-util.git as a second best solution.
-+- vfs-ino.patch
-+ Modifies a system global kernel internal function get_next_ino() in
-+ order to stop assigning 0 for an inode-number. Not directly related to
-+ aufs, but recommended generally.
-+- tmpfs-idr.patch
-+ Keeps the tmpfs inode number as the lowest value. Effective to reduce
-+ the size of aufs XINO files for tmpfs branch. Also it prevents the
-+ duplication of inode number, which is important for backup tools and
-+ other utilities. When you find aufs XINO files for tmpfs branch
-+ growing too much, try this patch.
-+- lockdep-debug.patch
-+ Because aufs is not only an ordinary filesystem (callee of VFS), but
-+ also a caller of VFS functions for branch filesystems, subclassing of
-+ the internal locks for LOCKDEP is necessary. LOCKDEP is a debugging
-+ feature of linux kernel. If you enable CONFIG_LOCKDEP, then you will
-+ need to apply this debug patch to expand several constant values.
-+ If don't know what LOCKDEP is, then you don't have apply this patch.
-+
-+
-+4. Usage
-+----------------------------------------
-+At first, make sure aufs-util are installed, and please read the aufs
-+manual, aufs.5 in aufs-util.git tree.
-+$ man -l aufs.5
-+
-+And then,
-+$ mkdir /tmp/rw /tmp/aufs
-+# mount -t aufs -o br=/tmp/rw:${HOME} none /tmp/aufs
-+
-+Here is another example. The result is equivalent.
-+# mount -t aufs -o br=/tmp/rw=rw:${HOME}=ro none /tmp/aufs
-+ Or
-+# mount -t aufs -o br:/tmp/rw none /tmp/aufs
-+# mount -o remount,append:${HOME} /tmp/aufs
-+
-+Then, you can see whole tree of your home dir through /tmp/aufs. If
-+you modify a file under /tmp/aufs, the one on your home directory is
-+not affected, instead the same named file will be newly created under
-+/tmp/rw. And all of your modification to a file will be applied to
-+the one under /tmp/rw. This is called the file based Copy on Write
-+(COW) method.
-+Aufs mount options are described in aufs.5.
-+If you run chroot or something and make your aufs as a root directory,
-+then you need to customize the shutdown script. See the aufs manual in
-+detail.
-+
-+Additionally, there are some sample usages of aufs which are a
-+diskless system with network booting, and LiveCD over NFS.
-+See sample dir in CVS tree on SourceForge.
-+
-+
-+5. Contact
-+----------------------------------------
-+When you have any problems or strange behaviour in aufs, please let me
-+know with:
-+- /proc/mounts (instead of the output of mount(8))
-+- /sys/module/aufs/*
-+- /sys/fs/aufs/* (if you have them)
-+- /debug/aufs/* (if you have them)
-+- linux kernel version
-+ if your kernel is not plain, for example modified by distributor,
-+ the url where i can download its source is necessary too.
-+- aufs version which was printed at loading the module or booting the
-+ system, instead of the date you downloaded.
-+- configuration (define/undefine CONFIG_AUFS_xxx)
-+- kernel configuration or /proc/config.gz (if you have it)
-+- behaviour which you think to be incorrect
-+- actual operation, reproducible one is better
-+- mailto: aufs-users at lists.sourceforge.net
-+
-+Usually, I don't watch the Public Areas(Bugs, Support Requests, Patches,
-+and Feature Requests) on SourceForge. Please join and write to
-+aufs-users ML.
-+
-+
-+6. Acknowledgements
-+----------------------------------------
-+Thanks to everyone who have tried and are using aufs, whoever
-+have reported a bug or any feedback.
-+
-+Especially donators:
-+Tomas Matejicek(slax.org) made a donation (much more than once).
-+ Since Apr 2010, Tomas M (the author of Slax and Linux Live
-+ scripts) is making "doubling" donations.
-+ Unfortunately I cannot list all of the donators, but I really
-+ appreciate.
-+ It ends Aug 2010, but the ordinary donation URL is still available.
-+ <http://sourceforge.net/donate/index.php?group_id=167503>
-+Dai Itasaka made a donation (2007/8).
-+Chuck Smith made a donation (2008/4, 10 and 12).
-+Henk Schoneveld made a donation (2008/9).
-+Chih-Wei Huang, ASUS, CTC donated Eee PC 4G (2008/10).
-+Francois Dupoux made a donation (2008/11).
-+Bruno Cesar Ribas and Luis Carlos Erpen de Bona, C3SL serves public
-+ aufs2 GIT tree (2009/2).
-+William Grant made a donation (2009/3).
-+Patrick Lane made a donation (2009/4).
-+The Mail Archive (mail-archive.com) made donations (2009/5).
-+Nippy Networks (Ed Wildgoose) made a donation (2009/7).
-+New Dream Network, LLC (www.dreamhost.com) made a donation (2009/11).
-+Pavel Pronskiy made a donation (2011/2).
-+Iridium and Inmarsat satellite phone retailer (www.mailasail.com), Nippy
-+ Networks (Ed Wildgoose) made a donation for hardware (2011/3).
-+Max Lekomcev (DOM-TV project) made a donation (2011/7, 12, 2012/3, 6 and
-+11).
-+Sam Liddicott made a donation (2011/9).
-+Era Scarecrow made a donation (2013/4).
-+Bor Ratajc made a donation (2013/4).
-+Alessandro Gorreta made a donation (2013/4).
-+POIRETTE Marc made a donation (2013/4).
-+Alessandro Gorreta made a donation (2013/4).
-+lauri kasvandik made a donation (2013/5).
-+"pemasu from Finland" made a donation (2013/7).
-+The Parted Magic Project made a donation (2013/9 and 11).
-+Pavel Barta made a donation (2013/10).
-+Nikolay Pertsev made a donation (2014/5).
-+James B made a donation (2014/7 and 2015/7).
-+Stefano Di Biase made a donation (2014/8).
-+Daniel Epellei made a donation (2015/1).
-+OmegaPhil made a donation (2016/1, 2018/4).
-+Tomasz Szewczyk made a donation (2016/4).
-+James Burry made a donation (2016/12).
-+Carsten Rose made a donation (2018/9).
-+Porteus Kiosk made a donation (2018/10).
-+
-+Thank you very much.
-+Donations are always, including future donations, very important and
-+helpful for me to keep on developing aufs.
-+
-+
-+7.
-+----------------------------------------
-+If you are an experienced user, no explanation is needed. Aufs is
-+just a linux filesystem.
-+
-+
-+Enjoy!
-+
-+# Local variables: ;
-+# mode: text;
-+# End: ;
-diff --git a/Documentation/filesystems/aufs/design/01intro.txt b/Documentation/filesystems/aufs/design/01intro.txt
-new file mode 100644
-index 000000000000..609bf0e9b93a
---- /dev/null
-+++ b/Documentation/filesystems/aufs/design/01intro.txt
-@@ -0,0 +1,171 @@
-+
-+# Copyright (C) 2005-2019 Junjiro R. Okajima
-+#
-+# This program is free software; you can redistribute it and/or modify
-+# it under the terms of the GNU General Public License as published by
-+# the Free Software Foundation; either version 2 of the License, or
-+# (at your option) any later version.
-+#
-+# This program is distributed in the hope that it will be useful,
-+# but WITHOUT ANY WARRANTY; without even the implied warranty of
-+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
-+# GNU General Public License for more details.
-+#
-+# You should have received a copy of the GNU General Public License
-+# along with this program. If not, see <http://www.gnu.org/licenses/>.
-+
-+Introduction
-+----------------------------------------
-+
-+aufs [ei ju: ef es] | /ey-yoo-ef-es/ | [a u f s]
-+1. abbrev. for "advanced multi-layered unification filesystem".
-+2. abbrev. for "another unionfs".
-+3. abbrev. for "auf das" in German which means "on the" in English.
-+ Ex. "Butter aufs Brot"(G) means "butter onto bread"(E).
-+ But "Filesystem aufs Filesystem" is hard to understand.
-+4. abbrev. for "African Urban Fashion Show".
-+
-+AUFS is a filesystem with features:
-+- multi layered stackable unification filesystem, the member directory
-+ is called as a branch.
-+- branch permission and attribute, 'readonly', 'real-readonly',
-+ 'readwrite', 'whiteout-able', 'link-able whiteout', etc. and their
-+ combination.
-+- internal "file copy-on-write".
-+- logical deletion, whiteout.
-+- dynamic branch manipulation, adding, deleting and changing permission.
-+- allow bypassing aufs, user's direct branch access.
-+- external inode number translation table and bitmap which maintains the
-+ persistent aufs inode number.
-+- seekable directory, including NFS readdir.
-+- file mapping, mmap and sharing pages.
-+- pseudo-link, hardlink over branches.
-+- loopback mounted filesystem as a branch.
-+- several policies to select one among multiple writable branches.
-+- revert a single systemcall when an error occurs in aufs.
-+- and more...
-+
-+
-+Multi Layered Stackable Unification Filesystem
-+----------------------------------------------------------------------
-+Most people already knows what it is.
-+It is a filesystem which unifies several directories and provides a
-+merged single directory. When users access a file, the access will be
-+passed/re-directed/converted (sorry, I am not sure which English word is
-+correct) to the real file on the member filesystem. The member
-+filesystem is called 'lower filesystem' or 'branch' and has a mode
-+'readonly' and 'readwrite.' And the deletion for a file on the lower
-+readonly branch is handled by creating 'whiteout' on the upper writable
-+branch.
-+
-+On LKML, there have been discussions about UnionMount (Jan Blunck,
-+Bharata B Rao and Valerie Aurora) and Unionfs (Erez Zadok). They took
-+different approaches to implement the merged-view.
-+The former tries putting it into VFS, and the latter implements as a
-+separate filesystem.
-+(If I misunderstand about these implementations, please let me know and
-+I shall correct it. Because it is a long time ago when I read their
-+source files last time).
-+
-+UnionMount's approach will be able to small, but may be hard to share
-+branches between several UnionMount since the whiteout in it is
-+implemented in the inode on branch filesystem and always
-+shared. According to Bharata's post, readdir does not seems to be
-+finished yet.
-+There are several missing features known in this implementations such as
-+- for users, the inode number may change silently. eg. copy-up.
-+- link(2) may break by copy-up.
-+- read(2) may get an obsoleted filedata (fstat(2) too).
-+- fcntl(F_SETLK) may be broken by copy-up.
-+- unnecessary copy-up may happen, for example mmap(MAP_PRIVATE) after
-+ open(O_RDWR).
-+
-+In linux-3.18, "overlay" filesystem (formerly known as "overlayfs") was
-+merged into mainline. This is another implementation of UnionMount as a
-+separated filesystem. All the limitations and known problems which
-+UnionMount are equally inherited to "overlay" filesystem.
-+
-+Unionfs has a longer history. When I started implementing a stackable
-+filesystem (Aug 2005), it already existed. It has virtual super_block,
-+inode, dentry and file objects and they have an array pointing lower
-+same kind objects. After contributing many patches for Unionfs, I
-+re-started my project AUFS (Jun 2006).
-+
-+In AUFS, the structure of filesystem resembles to Unionfs, but I
-+implemented my own ideas, approaches and enhancements and it became
-+totally different one.
-+
-+Comparing DM snapshot and fs based implementation
-+- the number of bytes to be copied between devices is much smaller.
-+- the type of filesystem must be one and only.
-+- the fs must be writable, no readonly fs, even for the lower original
-+ device. so the compression fs will not be usable. but if we use
-+ loopback mount, we may address this issue.
-+ for instance,
-+ mount /cdrom/squashfs.img /sq
-+ losetup /sq/ext2.img
-+ losetup /somewhere/cow
-+ dmsetup "snapshot /dev/loop0 /dev/loop1 ..."
-+- it will be difficult (or needs more operations) to extract the
-+ difference between the original device and COW.
-+- DM snapshot-merge may help a lot when users try merging. in the
-+ fs-layer union, users will use rsync(1).
-+
-+You may want to read my old paper "Filesystems in LiveCD"
-+(http://aufs.sourceforge.net/aufs2/report/sq/sq.pdf).
-+
-+
-+Several characters/aspects/persona of aufs
-+----------------------------------------------------------------------
-+
-+Aufs has several characters, aspects or persona.
-+1. a filesystem, callee of VFS helper
-+2. sub-VFS, caller of VFS helper for branches
-+3. a virtual filesystem which maintains persistent inode number
-+4. reader/writer of files on branches such like an application
-+
-+1. Callee of VFS Helper
-+As an ordinary linux filesystem, aufs is a callee of VFS. For instance,
-+unlink(2) from an application reaches sys_unlink() kernel function and
-+then vfs_unlink() is called. vfs_unlink() is one of VFS helper and it
-+calls filesystem specific unlink operation. Actually aufs implements the
-+unlink operation but it behaves like a redirector.
-+
-+2. Caller of VFS Helper for Branches
-+aufs_unlink() passes the unlink request to the branch filesystem as if
-+it were called from VFS. So the called unlink operation of the branch
-+filesystem acts as usual. As a caller of VFS helper, aufs should handle
-+every necessary pre/post operation for the branch filesystem.
-+- acquire the lock for the parent dir on a branch
-+- lookup in a branch
-+- revalidate dentry on a branch
-+- mnt_want_write() for a branch
-+- vfs_unlink() for a branch
-+- mnt_drop_write() for a branch
-+- release the lock on a branch
-+
-+3. Persistent Inode Number
-+One of the most important issue for a filesystem is to maintain inode
-+numbers. This is particularly important to support exporting a
-+filesystem via NFS. Aufs is a virtual filesystem which doesn't have a
-+backend block device for its own. But some storage is necessary to
-+keep and maintain the inode numbers. It may be a large space and may not
-+suit to keep in memory. Aufs rents some space from its first writable
-+branch filesystem (by default) and creates file(s) on it. These files
-+are created by aufs internally and removed soon (currently) keeping
-+opened.
-+Note: Because these files are removed, they are totally gone after
-+ unmounting aufs. It means the inode numbers are not persistent
-+ across unmount or reboot. I have a plan to make them really
-+ persistent which will be important for aufs on NFS server.
-+
-+4. Read/Write Files Internally (copy-on-write)
-+Because a branch can be readonly, when you write a file on it, aufs will
-+"copy-up" it to the upper writable branch internally. And then write the
-+originally requested thing to the file. Generally kernel doesn't
-+open/read/write file actively. In aufs, even a single write may cause a
-+internal "file copy". This behaviour is very similar to cp(1) command.
-+
-+Some people may think it is better to pass such work to user space
-+helper, instead of doing in kernel space. Actually I am still thinking
-+about it. But currently I have implemented it in kernel space.
-diff --git a/Documentation/filesystems/aufs/design/02struct.txt b/Documentation/filesystems/aufs/design/02struct.txt
-new file mode 100644
-index 000000000000..2467788c7f10
---- /dev/null
-+++ b/Documentation/filesystems/aufs/design/02struct.txt
-@@ -0,0 +1,258 @@
-+
-+# Copyright (C) 2005-2019 Junjiro R. Okajima
-+#
-+# This program is free software; you can redistribute it and/or modify
-+# it under the terms of the GNU General Public License as published by
-+# the Free Software Foundation; either version 2 of the License, or
-+# (at your option) any later version.
-+#
-+# This program is distributed in the hope that it will be useful,
-+# but WITHOUT ANY WARRANTY; without even the implied warranty of
-+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
-+# GNU General Public License for more details.
-+#
-+# You should have received a copy of the GNU General Public License
-+# along with this program. If not, see <http://www.gnu.org/licenses/>.
-+
-+Basic Aufs Internal Structure
-+
-+Superblock/Inode/Dentry/File Objects
-+----------------------------------------------------------------------
-+As like an ordinary filesystem, aufs has its own
-+superblock/inode/dentry/file objects. All these objects have a
-+dynamically allocated array and store the same kind of pointers to the
-+lower filesystem, branch.
-+For example, when you build a union with one readwrite branch and one
-+readonly, mounted /au, /rw and /ro respectively.
-+- /au = /rw + /ro
-+- /ro/fileA exists but /rw/fileA
-+
-+Aufs lookup operation finds /ro/fileA and gets dentry for that. These
-+pointers are stored in a aufs dentry. The array in aufs dentry will be,
-+- [0] = NULL (because /rw/fileA doesn't exist)
-+- [1] = /ro/fileA
-+
-+This style of an array is essentially same to the aufs
-+superblock/inode/dentry/file objects.
-+
-+Because aufs supports manipulating branches, ie. add/delete/change
-+branches dynamically, these objects has its own generation. When
-+branches are changed, the generation in aufs superblock is
-+incremented. And a generation in other object are compared when it is
-+accessed. When a generation in other objects are obsoleted, aufs
-+refreshes the internal array.
-+
-+
-+Superblock
-+----------------------------------------------------------------------
-+Additionally aufs superblock has some data for policies to select one
-+among multiple writable branches, XIB files, pseudo-links and kobject.
-+See below in detail.
-+About the policies which supports copy-down a directory, see
-+wbr_policy.txt too.
-+
-+
-+Branch and XINO(External Inode Number Translation Table)
-+----------------------------------------------------------------------
-+Every branch has its own xino (external inode number translation table)
-+file. The xino file is created and unlinked by aufs internally. When two
-+members of a union exist on the same filesystem, they share the single
-+xino file.
-+The struct of a xino file is simple, just a sequence of aufs inode
-+numbers which is indexed by the lower inode number.
-+In the above sample, assume the inode number of /ro/fileA is i111 and
-+aufs assigns the inode number i999 for fileA. Then aufs writes 999 as
-+4(8) bytes at 111 * 4(8) bytes offset in the xino file.
-+
-+When the inode numbers are not contiguous, the xino file will be sparse
-+which has a hole in it and doesn't consume as much disk space as it
-+might appear. If your branch filesystem consumes disk space for such
-+holes, then you should specify 'xino=' option at mounting aufs.
-+
-+Aufs has a mount option to free the disk blocks for such holes in XINO
-+files on tmpfs or ramdisk. But it is not so effective actually. If you
-+meet a problem of disk shortage due to XINO files, then you should try
-+"tmpfs-ino.patch" (and "vfs-ino.patch" too) in aufs4-standalone.git.
-+The patch localizes the assignment inumbers per tmpfs-mount and avoid
-+the holes in XINO files.
-+
-+Also a writable branch has three kinds of "whiteout bases". All these
-+are existed when the branch is joined to aufs, and their names are
-+whiteout-ed doubly, so that users will never see their names in aufs
-+hierarchy.
-+1. a regular file which will be hardlinked to all whiteouts.
-+2. a directory to store a pseudo-link.
-+3. a directory to store an "orphan"-ed file temporary.
-+
-+1. Whiteout Base
-+ When you remove a file on a readonly branch, aufs handles it as a
-+ logical deletion and creates a whiteout on the upper writable branch
-+ as a hardlink of this file in order not to consume inode on the
-+ writable branch.
-+2. Pseudo-link Dir
-+ See below, Pseudo-link.
-+3. Step-Parent Dir
-+ When "fileC" exists on the lower readonly branch only and it is
-+ opened and removed with its parent dir, and then user writes
-+ something into it, then aufs copies-up fileC to this
-+ directory. Because there is no other dir to store fileC. After
-+ creating a file under this dir, the file is unlinked.
-+
-+Because aufs supports manipulating branches, ie. add/delete/change
-+dynamically, a branch has its own id. When the branch order changes,
-+aufs finds the new index by searching the branch id.
-+
-+
-+Pseudo-link
-+----------------------------------------------------------------------
-+Assume "fileA" exists on the lower readonly branch only and it is
-+hardlinked to "fileB" on the branch. When you write something to fileA,
-+aufs copies-up it to the upper writable branch. Additionally aufs
-+creates a hardlink under the Pseudo-link Directory of the writable
-+branch. The inode of a pseudo-link is kept in aufs super_block as a
-+simple list. If fileB is read after unlinking fileA, aufs returns
-+filedata from the pseudo-link instead of the lower readonly
-+branch. Because the pseudo-link is based upon the inode, to keep the
-+inode number by xino (see above) is essentially necessary.
-+
-+All the hardlinks under the Pseudo-link Directory of the writable branch
-+should be restored in a proper location later. Aufs provides a utility
-+to do this. The userspace helpers executed at remounting and unmounting
-+aufs by default.
-+During this utility is running, it puts aufs into the pseudo-link
-+maintenance mode. In this mode, only the process which began the
-+maintenance mode (and its child processes) is allowed to operate in
-+aufs. Some other processes which are not related to the pseudo-link will
-+be allowed to run too, but the rest have to return an error or wait
-+until the maintenance mode ends. If a process already acquires an inode
-+mutex (in VFS), it has to return an error.
-+
-+
-+XIB(external inode number bitmap)
-+----------------------------------------------------------------------
-+Addition to the xino file per a branch, aufs has an external inode number
-+bitmap in a superblock object. It is also an internal file such like a
-+xino file.
-+It is a simple bitmap to mark whether the aufs inode number is in-use or
-+not.
-+To reduce the file I/O, aufs prepares a single memory page to cache xib.
-+
-+As well as XINO files, aufs has a feature to truncate/refresh XIB to
-+reduce the number of consumed disk blocks for these files.
-+
-+
-+Virtual or Vertical Dir, and Readdir in Userspace
-+----------------------------------------------------------------------
-+In order to support multiple layers (branches), aufs readdir operation
-+constructs a virtual dir block on memory. For readdir, aufs calls
-+vfs_readdir() internally for each dir on branches, merges their entries
-+with eliminating the whiteout-ed ones, and sets it to file (dir)
-+object. So the file object has its entry list until it is closed. The
-+entry list will be updated when the file position is zero and becomes
-+obsoleted. This decision is made in aufs automatically.
-+
-+The dynamically allocated memory block for the name of entries has a
-+unit of 512 bytes (by default) and stores the names contiguously (no
-+padding). Another block for each entry is handled by kmem_cache too.
-+During building dir blocks, aufs creates hash list and judging whether
-+the entry is whiteouted by its upper branch or already listed.
-+The merged result is cached in the corresponding inode object and
-+maintained by a customizable life-time option.
-+
-+Some people may call it can be a security hole or invite DoS attack
-+since the opened and once readdir-ed dir (file object) holds its entry
-+list and becomes a pressure for system memory. But I'd say it is similar
-+to files under /proc or /sys. The virtual files in them also holds a
-+memory page (generally) while they are opened. When an idea to reduce
-+memory for them is introduced, it will be applied to aufs too.
-+For those who really hate this situation, I've developed readdir(3)
-+library which operates this merging in userspace. You just need to set
-+LD_PRELOAD environment variable, and aufs will not consume no memory in
-+kernel space for readdir(3).
-+
-+
-+Workqueue
-+----------------------------------------------------------------------
-+Aufs sometimes requires privilege access to a branch. For instance,
-+in copy-up/down operation. When a user process is going to make changes
-+to a file which exists in the lower readonly branch only, and the mode
-+of one of ancestor directories may not be writable by a user
-+process. Here aufs copy-up the file with its ancestors and they may
-+require privilege to set its owner/group/mode/etc.
-+This is a typical case of a application character of aufs (see
-+Introduction).
-+
-+Aufs uses workqueue synchronously for this case. It creates its own
-+workqueue. The workqueue is a kernel thread and has privilege. Aufs
-+passes the request to call mkdir or write (for example), and wait for
-+its completion. This approach solves a problem of a signal handler
-+simply.
-+If aufs didn't adopt the workqueue and changed the privilege of the
-+process, then the process may receive the unexpected SIGXFSZ or other
-+signals.
-+
-+Also aufs uses the system global workqueue ("events" kernel thread) too
-+for asynchronous tasks, such like handling inotify/fsnotify, re-creating a
-+whiteout base and etc. This is unrelated to a privilege.
-+Most of aufs operation tries acquiring a rw_semaphore for aufs
-+superblock at the beginning, at the same time waits for the completion
-+of all queued asynchronous tasks.
-+
-+
-+Whiteout
-+----------------------------------------------------------------------
-+The whiteout in aufs is very similar to Unionfs's. That is represented
-+by its filename. UnionMount takes an approach of a file mode, but I am
-+afraid several utilities (find(1) or something) will have to support it.
-+
-+Basically the whiteout represents "logical deletion" which stops aufs to
-+lookup further, but also it represents "dir is opaque" which also stop
-+further lookup.
-+
-+In aufs, rmdir(2) and rename(2) for dir uses whiteout alternatively.
-+In order to make several functions in a single systemcall to be
-+revertible, aufs adopts an approach to rename a directory to a temporary
-+unique whiteouted name.
-+For example, in rename(2) dir where the target dir already existed, aufs
-+renames the target dir to a temporary unique whiteouted name before the
-+actual rename on a branch, and then handles other actions (make it opaque,
-+update the attributes, etc). If an error happens in these actions, aufs
-+simply renames the whiteouted name back and returns an error. If all are
-+succeeded, aufs registers a function to remove the whiteouted unique
-+temporary name completely and asynchronously to the system global
-+workqueue.
-+
-+
-+Copy-up
-+----------------------------------------------------------------------
-+It is a well-known feature or concept.
-+When user modifies a file on a readonly branch, aufs operate "copy-up"
-+internally and makes change to the new file on the upper writable branch.
-+When the trigger systemcall does not update the timestamps of the parent
-+dir, aufs reverts it after copy-up.
-+
-+
-+Move-down (aufs3.9 and later)
-+----------------------------------------------------------------------
-+"Copy-up" is one of the essential feature in aufs. It copies a file from
-+the lower readonly branch to the upper writable branch when a user
-+changes something about the file.
-+"Move-down" is an opposite action of copy-up. Basically this action is
-+ran manually instead of automatically and internally.
-+For desgin and implementation, aufs has to consider these issues.
-+- whiteout for the file may exist on the lower branch.
-+- ancestor directories may not exist on the lower branch.
-+- diropq for the ancestor directories may exist on the upper branch.
-+- free space on the lower branch will reduce.
-+- another access to the file may happen during moving-down, including
-+ UDBA (see "Revalidate Dentry and UDBA").
-+- the file should not be hard-linked nor pseudo-linked. they should be
-+ handled by auplink utility later.
-+
-+Sometimes users want to move-down a file from the upper writable branch
-+to the lower readonly or writable branch. For instance,
-+- the free space of the upper writable branch is going to run out.
-+- create a new intermediate branch between the upper and lower branch.
-+- etc.
-+
-+For this purpose, use "aumvdown" command in aufs-util.git.
-diff --git a/Documentation/filesystems/aufs/design/03atomic_open.txt b/Documentation/filesystems/aufs/design/03atomic_open.txt
-new file mode 100644
-index 000000000000..9f16ac1e0173
---- /dev/null
-+++ b/Documentation/filesystems/aufs/design/03atomic_open.txt
-@@ -0,0 +1,85 @@
-+
-+# Copyright (C) 2015-2019 Junjiro R. Okajima
-+#
-+# This program is free software; you can redistribute it and/or modify
-+# it under the terms of the GNU General Public License as published by
-+# the Free Software Foundation; either version 2 of the License, or
-+# (at your option) any later version.
-+#
-+# This program is distributed in the hope that it will be useful,
-+# but WITHOUT ANY WARRANTY; without even the implied warranty of
-+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
-+# GNU General Public License for more details.
-+#
-+# You should have received a copy of the GNU General Public License
-+# along with this program. If not, see <http://www.gnu.org/licenses/>.
-+
-+Support for a branch who has its ->atomic_open()
-+----------------------------------------------------------------------
-+The filesystems who implement its ->atomic_open() are not majority. For
-+example NFSv4 does, and aufs should call NFSv4 ->atomic_open,
-+particularly for open(O_CREAT|O_EXCL, 0400) case. Other than
-+->atomic_open(), NFSv4 returns an error for this open(2). While I am not
-+sure whether all filesystems who have ->atomic_open() behave like this,
-+but NFSv4 surely returns the error.
-+
-+In order to support ->atomic_open() for aufs, there are a few
-+approaches.
-+
-+A. Introduce aufs_atomic_open()
-+ - calls one of VFS:do_last(), lookup_open() or atomic_open() for
-+ branch fs.
-+B. Introduce aufs_atomic_open() calling create, open and chmod. this is
-+ an aufs user Pip Cet's approach
-+ - calls aufs_create(), VFS finish_open() and notify_change().
-+ - pass fake-mode to finish_open(), and then correct the mode by
-+ notify_change().
-+C. Extend aufs_open() to call branch fs's ->atomic_open()
-+ - no aufs_atomic_open().
-+ - aufs_lookup() registers the TID to an aufs internal object.
-+ - aufs_create() does nothing when the matching TID is registered, but
-+ registers the mode.
-+ - aufs_open() calls branch fs's ->atomic_open() when the matching
-+ TID is registered.
-+D. Extend aufs_open() to re-try branch fs's ->open() with superuser's
-+ credential
-+ - no aufs_atomic_open().
-+ - aufs_create() registers the TID to an internal object. this info
-+ represents "this process created this file just now."
-+ - when aufs gets EACCES from branch fs's ->open(), then confirm the
-+ registered TID and re-try open() with superuser's credential.
-+
-+Pros and cons for each approach.
-+
-+A.
-+ - straightforward but highly depends upon VFS internal.
-+ - the atomic behavaiour is kept.
-+ - some of parameters such as nameidata are hard to reproduce for
-+ branch fs.
-+ - large overhead.
-+B.
-+ - easy to implement.
-+ - the atomic behavaiour is lost.
-+C.
-+ - the atomic behavaiour is kept.
-+ - dirty and tricky.
-+ - VFS checks whether the file is created correctly after calling
-+ ->create(), which means this approach doesn't work.
-+D.
-+ - easy to implement.
-+ - the atomic behavaiour is lost.
-+ - to open a file with superuser's credential and give it to a user
-+ process is a bad idea, since the file object keeps the credential
-+ in it. It may affect LSM or something. This approach doesn't work
-+ either.
-+
-+The approach A is ideal, but it hard to implement. So here is a
-+variation of A, which is to be implemented.
-+
-+A-1. Introduce aufs_atomic_open()
-+ - calls branch fs ->atomic_open() if exists. otherwise calls
-+ vfs_create() and finish_open().
-+ - the demerit is that the several checks after branch fs
-+ ->atomic_open() are lost. in the ordinary case, the checks are
-+ done by VFS:do_last(), lookup_open() and atomic_open(). some can
-+ be implemented in aufs, but not all I am afraid.
-diff --git a/Documentation/filesystems/aufs/design/03lookup.txt b/Documentation/filesystems/aufs/design/03lookup.txt
-new file mode 100644
-index 000000000000..08b443d94dfa
---- /dev/null
-+++ b/Documentation/filesystems/aufs/design/03lookup.txt
-@@ -0,0 +1,113 @@
-+
-+# Copyright (C) 2005-2019 Junjiro R. Okajima
-+#
-+# This program is free software; you can redistribute it and/or modify
-+# it under the terms of the GNU General Public License as published by
-+# the Free Software Foundation; either version 2 of the License, or
-+# (at your option) any later version.
-+#
-+# This program is distributed in the hope that it will be useful,
-+# but WITHOUT ANY WARRANTY; without even the implied warranty of
-+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
-+# GNU General Public License for more details.
-+#
-+# You should have received a copy of the GNU General Public License
-+# along with this program. If not, see <http://www.gnu.org/licenses/>.
-+
-+Lookup in a Branch
-+----------------------------------------------------------------------
-+Since aufs has a character of sub-VFS (see Introduction), it operates
-+lookup for branches as VFS does. It may be a heavy work. But almost all
-+lookup operation in aufs is the simplest case, ie. lookup only an entry
-+directly connected to its parent. Digging down the directory hierarchy
-+is unnecessary. VFS has a function lookup_one_len() for that use, and
-+aufs calls it.
-+
-+When a branch is a remote filesystem, aufs basically relies upon its
-+->d_revalidate(), also aufs forces the hardest revalidate tests for
-+them.
-+For d_revalidate, aufs implements three levels of revalidate tests. See
-+"Revalidate Dentry and UDBA" in detail.
-+
-+
-+Test Only the Highest One for the Directory Permission (dirperm1 option)
-+----------------------------------------------------------------------
-+Let's try case study.
-+- aufs has two branches, upper readwrite and lower readonly.
-+ /au = /rw + /ro
-+- "dirA" exists under /ro, but /rw. and its mode is 0700.
-+- user invoked "chmod a+rx /au/dirA"
-+- the internal copy-up is activated and "/rw/dirA" is created and its
-+ permission bits are set to world readable.
-+- then "/au/dirA" becomes world readable?
-+
-+In this case, /ro/dirA is still 0700 since it exists in readonly branch,
-+or it may be a natively readonly filesystem. If aufs respects the lower
-+branch, it should not respond readdir request from other users. But user
-+allowed it by chmod. Should really aufs rejects showing the entries
-+under /ro/dirA?
-+
-+To be honest, I don't have a good solution for this case. So aufs
-+implements 'dirperm1' and 'nodirperm1' mount options, and leave it to
-+users.
-+When dirperm1 is specified, aufs checks only the highest one for the
-+directory permission, and shows the entries. Otherwise, as usual, checks
-+every dir existing on all branches and rejects the request.
-+
-+As a side effect, dirperm1 option improves the performance of aufs
-+because the number of permission check is reduced when the number of
-+branch is many.
-+
-+
-+Revalidate Dentry and UDBA (User's Direct Branch Access)
-+----------------------------------------------------------------------
-+Generally VFS helpers re-validate a dentry as a part of lookup.
-+0. digging down the directory hierarchy.
-+1. lock the parent dir by its i_mutex.
-+2. lookup the final (child) entry.
-+3. revalidate it.
-+4. call the actual operation (create, unlink, etc.)
-+5. unlock the parent dir
-+
-+If the filesystem implements its ->d_revalidate() (step 3), then it is
-+called. Actually aufs implements it and checks the dentry on a branch is
-+still valid.
-+But it is not enough. Because aufs has to release the lock for the
-+parent dir on a branch at the end of ->lookup() (step 2) and
-+->d_revalidate() (step 3) while the i_mutex of the aufs dir is still
-+held by VFS.
-+If the file on a branch is changed directly, eg. bypassing aufs, after
-+aufs released the lock, then the subsequent operation may cause
-+something unpleasant result.
-+
-+This situation is a result of VFS architecture, ->lookup() and
-+->d_revalidate() is separated. But I never say it is wrong. It is a good
-+design from VFS's point of view. It is just not suitable for sub-VFS
-+character in aufs.
-+
-+Aufs supports such case by three level of revalidation which is
-+selectable by user.
-+1. Simple Revalidate
-+ Addition to the native flow in VFS's, confirm the child-parent
-+ relationship on the branch just after locking the parent dir on the
-+ branch in the "actual operation" (step 4). When this validation
-+ fails, aufs returns EBUSY. ->d_revalidate() (step 3) in aufs still
-+ checks the validation of the dentry on branches.
-+2. Monitor Changes Internally by Inotify/Fsnotify
-+ Addition to above, in the "actual operation" (step 4) aufs re-lookup
-+ the dentry on the branch, and returns EBUSY if it finds different
-+ dentry.
-+ Additionally, aufs sets the inotify/fsnotify watch for every dir on branches
-+ during it is in cache. When the event is notified, aufs registers a
-+ function to kernel 'events' thread by schedule_work(). And the
-+ function sets some special status to the cached aufs dentry and inode
-+ private data. If they are not cached, then aufs has nothing to
-+ do. When the same file is accessed through aufs (step 0-3) later,
-+ aufs will detect the status and refresh all necessary data.
-+ In this mode, aufs has to ignore the event which is fired by aufs
-+ itself.
-+3. No Extra Validation
-+ This is the simplest test and doesn't add any additional revalidation
-+ test, and skip the revalidation in step 4. It is useful and improves
-+ aufs performance when system surely hide the aufs branches from user,
-+ by over-mounting something (or another method).
-diff --git a/Documentation/filesystems/aufs/design/04branch.txt b/Documentation/filesystems/aufs/design/04branch.txt
-new file mode 100644
-index 000000000000..3ab3682a42b4
---- /dev/null
-+++ b/Documentation/filesystems/aufs/design/04branch.txt
-@@ -0,0 +1,74 @@
-+
-+# Copyright (C) 2005-2019 Junjiro R. Okajima
-+#
-+# This program is free software; you can redistribute it and/or modify
-+# it under the terms of the GNU General Public License as published by
-+# the Free Software Foundation; either version 2 of the License, or
-+# (at your option) any later version.
-+#
-+# This program is distributed in the hope that it will be useful,
-+# but WITHOUT ANY WARRANTY; without even the implied warranty of
-+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
-+# GNU General Public License for more details.
-+#
-+# You should have received a copy of the GNU General Public License
-+# along with this program. If not, see <http://www.gnu.org/licenses/>.
-+
-+Branch Manipulation
-+
-+Since aufs supports dynamic branch manipulation, ie. add/remove a branch
-+and changing its permission/attribute, there are a lot of works to do.
-+
-+
-+Add a Branch
-+----------------------------------------------------------------------
-+o Confirm the adding dir exists outside of aufs, including loopback
-+ mount, and its various attributes.
-+o Initialize the xino file and whiteout bases if necessary.
-+ See struct.txt.
-+
-+o Check the owner/group/mode of the directory
-+ When the owner/group/mode of the adding directory differs from the
-+ existing branch, aufs issues a warning because it may impose a
-+ security risk.
-+ For example, when a upper writable branch has a world writable empty
-+ top directory, a malicious user can create any files on the writable
-+ branch directly, like copy-up and modify manually. If something like
-+ /etc/{passwd,shadow} exists on the lower readonly branch but the upper
-+ writable branch, and the writable branch is world-writable, then a
-+ malicious guy may create /etc/passwd on the writable branch directly
-+ and the infected file will be valid in aufs.
-+ I am afraid it can be a security issue, but aufs can do nothing except
-+ producing a warning.
-+
-+
-+Delete a Branch
-+----------------------------------------------------------------------
-+o Confirm the deleting branch is not busy
-+ To be general, there is one merit to adopt "remount" interface to
-+ manipulate branches. It is to discard caches. At deleting a branch,
-+ aufs checks the still cached (and connected) dentries and inodes. If
-+ there are any, then they are all in-use. An inode without its
-+ corresponding dentry can be alive alone (for example, inotify/fsnotify case).
-+
-+ For the cached one, aufs checks whether the same named entry exists on
-+ other branches.
-+ If the cached one is a directory, because aufs provides a merged view
-+ to users, as long as one dir is left on any branch aufs can show the
-+ dir to users. In this case, the branch can be removed from aufs.
-+ Otherwise aufs rejects deleting the branch.
-+
-+ If any file on the deleting branch is opened by aufs, then aufs
-+ rejects deleting.
-+
-+
-+Modify the Permission of a Branch
-+----------------------------------------------------------------------
-+o Re-initialize or remove the xino file and whiteout bases if necessary.
-+ See struct.txt.
-+
-+o rw --> ro: Confirm the modifying branch is not busy
-+ Aufs rejects the request if any of these conditions are true.
-+ - a file on the branch is mmap-ed.
-+ - a regular file on the branch is opened for write and there is no
-+ same named entry on the upper branch.
-diff --git a/Documentation/filesystems/aufs/design/05wbr_policy.txt b/Documentation/filesystems/aufs/design/05wbr_policy.txt
-new file mode 100644
-index 000000000000..1f9b86bc6a3e
---- /dev/null
-+++ b/Documentation/filesystems/aufs/design/05wbr_policy.txt
-@@ -0,0 +1,64 @@
-+
-+# Copyright (C) 2005-2019 Junjiro R. Okajima
-+#
-+# This program is free software; you can redistribute it and/or modify
-+# it under the terms of the GNU General Public License as published by
-+# the Free Software Foundation; either version 2 of the License, or
-+# (at your option) any later version.
-+#
-+# This program is distributed in the hope that it will be useful,
-+# but WITHOUT ANY WARRANTY; without even the implied warranty of
-+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
-+# GNU General Public License for more details.
-+#
-+# You should have received a copy of the GNU General Public License
-+# along with this program. If not, see <http://www.gnu.org/licenses/>.
-+
-+Policies to Select One among Multiple Writable Branches
-+----------------------------------------------------------------------
-+When the number of writable branch is more than one, aufs has to decide
-+the target branch for file creation or copy-up. By default, the highest
-+writable branch which has the parent (or ancestor) dir of the target
-+file is chosen (top-down-parent policy).
-+By user's request, aufs implements some other policies to select the
-+writable branch, for file creation several policies, round-robin,
-+most-free-space, and other policies. For copy-up, top-down-parent,
-+bottom-up-parent, bottom-up and others.
-+
-+As expected, the round-robin policy selects the branch in circular. When
-+you have two writable branches and creates 10 new files, 5 files will be
-+created for each branch. mkdir(2) systemcall is an exception. When you
-+create 10 new directories, all will be created on the same branch.
-+And the most-free-space policy selects the one which has most free
-+space among the writable branches. The amount of free space will be
-+checked by aufs internally, and users can specify its time interval.
-+
-+The policies for copy-up is more simple,
-+top-down-parent is equivalent to the same named on in create policy,
-+bottom-up-parent selects the writable branch where the parent dir
-+exists and the nearest upper one from the copyup-source,
-+bottom-up selects the nearest upper writable branch from the
-+copyup-source, regardless the existence of the parent dir.
-+
-+There are some rules or exceptions to apply these policies.
-+- If there is a readonly branch above the policy-selected branch and
-+ the parent dir is marked as opaque (a variation of whiteout), or the
-+ target (creating) file is whiteout-ed on the upper readonly branch,
-+ then the result of the policy is ignored and the target file will be
-+ created on the nearest upper writable branch than the readonly branch.
-+- If there is a writable branch above the policy-selected branch and
-+ the parent dir is marked as opaque or the target file is whiteouted
-+ on the branch, then the result of the policy is ignored and the target
-+ file will be created on the highest one among the upper writable
-+ branches who has diropq or whiteout. In case of whiteout, aufs removes
-+ it as usual.
-+- link(2) and rename(2) systemcalls are exceptions in every policy.
-+ They try selecting the branch where the source exists as possible
-+ since copyup a large file will take long time. If it can't be,
-+ ie. the branch where the source exists is readonly, then they will
-+ follow the copyup policy.
-+- There is an exception for rename(2) when the target exists.
-+ If the rename target exists, aufs compares the index of the branches
-+ where the source and the target exists and selects the higher
-+ one. If the selected branch is readonly, then aufs follows the
-+ copyup policy.
-diff --git a/Documentation/filesystems/aufs/design/06dirren.dot b/Documentation/filesystems/aufs/design/06dirren.dot
-new file mode 100644
-index 000000000000..2d62bb6dd55f
---- /dev/null
-+++ b/Documentation/filesystems/aufs/design/06dirren.dot
-@@ -0,0 +1,31 @@
-+
-+// to view this graph, run dot(1) command in GRAPHVIZ.
-+
-+digraph G {
-+node [shape=box];
-+whinfo [label="detailed info file\n(lower_brid_root-hinum, h_inum, namelen, old name)"];
-+
-+node [shape=oval];
-+
-+aufs_rename -> whinfo [label="store/remove"];
-+
-+node [shape=oval];
-+inode_list [label="h_inum list in branch\ncache"];
-+
-+node [shape=box];
-+whinode [label="h_inum list file"];
-+
-+node [shape=oval];
-+brmgmt [label="br_add/del/mod/umount"];
-+
-+brmgmt -> inode_list [label="create/remove"];
-+brmgmt -> whinode [label="load/store"];
-+
-+inode_list -> whinode [style=dashed,dir=both];
-+
-+aufs_rename -> inode_list [label="add/del"];
-+
-+aufs_lookup -> inode_list [label="search"];
-+
-+aufs_lookup -> whinfo [label="load/remove"];
-+}
-diff --git a/Documentation/filesystems/aufs/design/06dirren.txt b/Documentation/filesystems/aufs/design/06dirren.txt
-new file mode 100644
-index 000000000000..3b80f8659b3e
---- /dev/null
-+++ b/Documentation/filesystems/aufs/design/06dirren.txt
-@@ -0,0 +1,102 @@
-+
-+# Copyright (C) 2017-2019 Junjiro R. Okajima
-+#
-+# This program is free software; you can redistribute it and/or modify
-+# it under the terms of the GNU General Public License as published by
-+# the Free Software Foundation; either version 2 of the License, or
-+# (at your option) any later version.
-+#
-+# This program is distributed in the hope that it will be useful,
-+# but WITHOUT ANY WARRANTY; without even the implied warranty of
-+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
-+# GNU General Public License for more details.
-+#
-+# You should have received a copy of the GNU General Public License
-+# along with this program. If not, see <http://www.gnu.org/licenses/>.
-+
-+Special handling for renaming a directory (DIRREN)
-+----------------------------------------------------------------------
-+First, let's assume we have a simple usecase.
-+
-+- /u = /rw + /ro
-+- /rw/dirA exists
-+- /ro/dirA and /ro/dirA/file exist too
-+- there is no dirB on both branches
-+- a user issues rename("dirA", "dirB")
-+
-+Now, what should aufs behave against this rename(2)?
-+There are a few possible cases.
-+
-+A. returns EROFS.
-+ since dirA exists on a readonly branch which cannot be renamed.
-+B. returns EXDEV.
-+ it is possible to copy-up dirA (only the dir itself), but the child
-+ entries ("file" in this case) should not be. it must be a bad
-+ approach to copy-up recursively.
-+C. returns a success.
-+ even the branch /ro is readonly, aufs tries renaming it. Obviously it
-+ is a violation of aufs' policy.
-+D. construct an extra information which indicates that /ro/dirA should
-+ be handled as the name of dirB.
-+ overlayfs has a similar feature called REDIRECT.
-+
-+Until now, aufs implements the case B only which returns EXDEV, and
-+expects the userspace application behaves like mv(1) which tries
-+issueing rename(2) recursively.
-+
-+A new aufs feature called DIRREN is introduced which implements the case
-+D. There are several "extra information" added.
-+
-+1. detailed info per renamed directory
-+ path: /rw/dirB/$AUFS_WH_DR_INFO_PFX.<lower branch-id>
-+2. the inode-number list of directories on a branch
-+ path: /rw/dirB/$AUFS_WH_DR_BRHINO
-+
-+The filename of "detailed info per directory" represents the lower
-+branch, and its format is
-+- a type of the branch id
-+ one of these.
-+ + uuid (not implemented yet)
-+ + fsid
-+ + dev
-+- the inode-number of the branch root dir
-+
-+And it contains these info in a single regular file.
-+- magic number
-+- branch's inode-number of the logically renamed dir
-+- the name of the before-renamed dir
-+
-+The "detailed info per directory" file is created in aufs rename(2), and
-+loaded in any lookup.
-+The info is considered in lookup for the matching case only. Here
-+"matching" means that the root of branch (in the info filename) is same
-+to the current looking-up branch. After looking-up the before-renamed
-+name, the inode-number is compared. And the matched dentry is used.
-+
-+The "inode-number list of directories" is a regular file which contains
-+simply the inode-numbers on the branch. The file is created or updated
-+in removing the branch, and loaded in adding the branch. Its lifetime is
-+equal to the branch.
-+The list is refered in lookup, and when the current target inode is
-+found in the list, the aufs tries loading the "detailed info per
-+directory" and get the changed and valid name of the dir.
-+
-+Theoretically these "extra informaiton" may be able to be put into XATTR
-+in the dir inode. But aufs doesn't choose this way because
-+1. XATTR may not be supported by the branch (or its configuration)
-+2. XATTR may have its size limit.
-+3. XATTR may be less easy to convert than a regular file, when the
-+ format of the info is changed in the future.
-+At the same time, I agree that the regular file approach is much slower
-+than XATTR approach. So, in the future, aufs may take the XATTR or other
-+better approach.
-+
-+This DIRREN feature is enabled by aufs configuration, and is activated
-+by a new mount option.
-+
-+For the more complicated case, there is a work with UDBA option, which
-+is to dected the direct access to the branches (by-passing aufs) and to
-+maintain the cashes in aufs. Since a single cached aufs dentry may
-+contains two names, before- and after-rename, the name comparision in
-+UDBA handler may not work correctly. In this case, the behaviour will be
-+equivalen to udba=reval case.
-diff --git a/Documentation/filesystems/aufs/design/06fhsm.txt b/Documentation/filesystems/aufs/design/06fhsm.txt
-new file mode 100644
-index 000000000000..8b498d0af812
---- /dev/null
-+++ b/Documentation/filesystems/aufs/design/06fhsm.txt
-@@ -0,0 +1,120 @@
-+
-+# Copyright (C) 2011-2019 Junjiro R. Okajima
-+#
-+# This program is free software; you can redistribute it and/or modify
-+# it under the terms of the GNU General Public License as published by
-+# the Free Software Foundation; either version 2 of the License, or
-+# (at your option) any later version.
-+#
-+# This program is distributed in the hope that it will be useful,
-+# but WITHOUT ANY WARRANTY; without even the implied warranty of
-+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
-+# GNU General Public License for more details.
-+#
-+# You should have received a copy of the GNU General Public License
-+# along with this program; if not, write to the Free Software
-+# Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
-+
-+
-+File-based Hierarchical Storage Management (FHSM)
-+----------------------------------------------------------------------
-+Hierarchical Storage Management (or HSM) is a well-known feature in the
-+storage world. Aufs provides this feature as file-based with multiple
-+writable branches, based upon the principle of "Colder, the Lower".
-+Here the word "colder" means that the less used files, and "lower" means
-+that the position in the order of the stacked branches vertically.
-+These multiple writable branches are prioritized, ie. the topmost one
-+should be the fastest drive and be used heavily.
-+
-+o Characters in aufs FHSM story
-+- aufs itself and a new branch attribute.
-+- a new ioctl interface to move-down and to establish a connection with
-+ the daemon ("move-down" is a converse of "copy-up").
-+- userspace tool and daemon.
-+
-+The userspace daemon establishes a connection with aufs and waits for
-+the notification. The notified information is very similar to struct
-+statfs containing the number of consumed blocks and inodes.
-+When the consumed blocks/inodes of a branch exceeds the user-specified
-+upper watermark, the daemon activates its move-down process until the
-+consumed blocks/inodes reaches the user-specified lower watermark.
-+
-+The actual move-down is done by aufs based upon the request from
-+user-space since we need to maintain the inode number and the internal
-+pointer arrays in aufs.
-+
-+Currently aufs FHSM handles the regular files only. Additionally they
-+must not be hard-linked nor pseudo-linked.
-+
-+
-+o Cowork of aufs and the user-space daemon
-+ During the userspace daemon established the connection, aufs sends a
-+ small notification to it whenever aufs writes something into the
-+ writable branch. But it may cost high since aufs issues statfs(2)
-+ internally. So user can specify a new option to cache the
-+ info. Actually the notification is controlled by these factors.
-+ + the specified cache time.
-+ + classified as "force" by aufs internally.
-+ Until the specified time expires, aufs doesn't send the info
-+ except the forced cases. When aufs decide forcing, the info is always
-+ notified to userspace.
-+ For example, the number of free inodes is generally large enough and
-+ the shortage of it happens rarely. So aufs doesn't force the
-+ notification when creating a new file, directory and others. This is
-+ the typical case which aufs doesn't force.
-+ When aufs writes the actual filedata and the files consumes any of new
-+ blocks, the aufs forces notifying.
-+
-+
-+o Interfaces in aufs
-+- New branch attribute.
-+ + fhsm
-+ Specifies that the branch is managed by FHSM feature. In other word,
-+ participant in the FHSM.
-+ When nofhsm is set to the branch, it will not be the source/target
-+ branch of the move-down operation. This attribute is set
-+ independently from coo and moo attributes, and if you want full
-+ FHSM, you should specify them as well.
-+- New mount option.
-+ + fhsm_sec
-+ Specifies a second to suppress many less important info to be
-+ notified.
-+- New ioctl.
-+ + AUFS_CTL_FHSM_FD
-+ create a new file descriptor which userspace can read the notification
-+ (a subset of struct statfs) from aufs.
-+- Module parameter 'brs'
-+ It has to be set to 1. Otherwise the new mount option 'fhsm' will not
-+ be set.
-+- mount helpers /sbin/mount.aufs and /sbin/umount.aufs
-+ When there are two or more branches with fhsm attributes,
-+ /sbin/mount.aufs invokes the user-space daemon and /sbin/umount.aufs
-+ terminates it. As a result of remounting and branch-manipulation, the
-+ number of branches with fhsm attribute can be one. In this case,
-+ /sbin/mount.aufs will terminate the user-space daemon.
-+
-+
-+Finally the operation is done as these steps in kernel-space.
-+- make sure that,
-+ + no one else is using the file.
-+ + the file is not hard-linked.
-+ + the file is not pseudo-linked.
-+ + the file is a regular file.
-+ + the parent dir is not opaqued.
-+- find the target writable branch.
-+- make sure the file is not whiteout-ed by the upper (than the target)
-+ branch.
-+- make the parent dir on the target branch.
-+- mutex lock the inode on the branch.
-+- unlink the whiteout on the target branch (if exists).
-+- lookup and create the whiteout-ed temporary name on the target branch.
-+- copy the file as the whiteout-ed temporary name on the target branch.
-+- rename the whiteout-ed temporary name to the original name.
-+- unlink the file on the source branch.
-+- maintain the internal pointer array and the external inode number
-+ table (XINO).
-+- maintain the timestamps and other attributes of the parent dir and the
-+ file.
-+
-+And of course, in every step, an error may happen. So the operation
-+should restore the original file state after an error happens.
-diff --git a/Documentation/filesystems/aufs/design/06mmap.txt b/Documentation/filesystems/aufs/design/06mmap.txt
-new file mode 100644
-index 000000000000..cdd84ea777fc
---- /dev/null
-+++ b/Documentation/filesystems/aufs/design/06mmap.txt
-@@ -0,0 +1,72 @@
-+
-+# Copyright (C) 2005-2019 Junjiro R. Okajima
-+#
-+# This program is free software; you can redistribute it and/or modify
-+# it under the terms of the GNU General Public License as published by
-+# the Free Software Foundation; either version 2 of the License, or
-+# (at your option) any later version.
-+#
-+# This program is distributed in the hope that it will be useful,
-+# but WITHOUT ANY WARRANTY; without even the implied warranty of
-+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
-+# GNU General Public License for more details.
-+#
-+# You should have received a copy of the GNU General Public License
-+# along with this program. If not, see <http://www.gnu.org/licenses/>.
-+
-+mmap(2) -- File Memory Mapping
-+----------------------------------------------------------------------
-+In aufs, the file-mapped pages are handled by a branch fs directly, no
-+interaction with aufs. It means aufs_mmap() calls the branch fs's
-+->mmap().
-+This approach is simple and good, but there is one problem.
-+Under /proc, several entries show the mmapped files by its path (with
-+device and inode number), and the printed path will be the path on the
-+branch fs's instead of virtual aufs's.
-+This is not a problem in most cases, but some utilities lsof(1) (and its
-+user) may expect the path on aufs.
-+
-+To address this issue, aufs adds a new member called vm_prfile in struct
-+vm_area_struct (and struct vm_region). The original vm_file points to
-+the file on the branch fs in order to handle everything correctly as
-+usual. The new vm_prfile points to a virtual file in aufs, and the
-+show-functions in procfs refers to vm_prfile if it is set.
-+Also we need to maintain several other places where touching vm_file
-+such like
-+- fork()/clone() copies vma and the reference count of vm_file is
-+ incremented.
-+- merging vma maintains the ref count too.
-+
-+This is not a good approach. It just fakes the printed path. But it
-+leaves all behaviour around f_mapping unchanged. This is surely an
-+advantage.
-+Actually aufs had adopted another complicated approach which calls
-+generic_file_mmap() and handles struct vm_operations_struct. In this
-+approach, aufs met a hard problem and I could not solve it without
-+switching the approach.
-+
-+There may be one more another approach which is
-+- bind-mount the branch-root onto the aufs-root internally
-+- grab the new vfsmount (ie. struct mount)
-+- lazy-umount the branch-root internally
-+- in open(2) the aufs-file, open the branch-file with the hidden
-+ vfsmount (instead of the original branch's vfsmount)
-+- ideally this "bind-mount and lazy-umount" should be done atomically,
-+ but it may be possible from userspace by the mount helper.
-+
-+Adding the internal hidden vfsmount and using it in opening a file, the
-+file path under /proc will be printed correctly. This approach looks
-+smarter, but is not possible I am afraid.
-+- aufs-root may be bind-mount later. when it happens, another hidden
-+ vfsmount will be required.
-+- it is hard to get the chance to bind-mount and lazy-umount
-+ + in kernel-space, FS can have vfsmount in open(2) via
-+ file->f_path, and aufs can know its vfsmount. But several locks are
-+ already acquired, and if aufs tries to bind-mount and lazy-umount
-+ here, then it may cause a deadlock.
-+ + in user-space, bind-mount doesn't invoke the mount helper.
-+- since /proc shows dev and ino, aufs has to give vma these info. it
-+ means a new member vm_prinode will be necessary. this is essentially
-+ equivalent to vm_prfile described above.
-+
-+I have to give up this "looks-smater" approach.
-diff --git a/Documentation/filesystems/aufs/design/06xattr.txt b/Documentation/filesystems/aufs/design/06xattr.txt
-new file mode 100644
-index 000000000000..edd7553f3289
---- /dev/null
-+++ b/Documentation/filesystems/aufs/design/06xattr.txt
-@@ -0,0 +1,96 @@
-+
-+# Copyright (C) 2014-2019 Junjiro R. Okajima
-+#
-+# This program is free software; you can redistribute it and/or modify
-+# it under the terms of the GNU General Public License as published by
-+# the Free Software Foundation; either version 2 of the License, or
-+# (at your option) any later version.
-+#
-+# This program is distributed in the hope that it will be useful,
-+# but WITHOUT ANY WARRANTY; without even the implied warranty of
-+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
-+# GNU General Public License for more details.
-+#
-+# You should have received a copy of the GNU General Public License
-+# along with this program; if not, write to the Free Software
-+# Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
-+
-+
-+Listing XATTR/EA and getting the value
-+----------------------------------------------------------------------
-+For the inode standard attributes (owner, group, timestamps, etc.), aufs
-+shows the values from the topmost existing file. This behaviour is good
-+for the non-dir entries since the bahaviour exactly matches the shown
-+information. But for the directories, aufs considers all the same named
-+entries on the lower branches. Which means, if one of the lower entry
-+rejects readdir call, then aufs returns an error even if the topmost
-+entry allows it. This behaviour is necessary to respect the branch fs's
-+security, but can make users confused since the user-visible standard
-+attributes don't match the behaviour.
-+To address this issue, aufs has a mount option called dirperm1 which
-+checks the permission for the topmost entry only, and ignores the lower
-+entry's permission.
-+
-+A similar issue can happen around XATTR.
-+getxattr(2) and listxattr(2) families behave as if dirperm1 option is
-+always set. Otherwise these very unpleasant situation would happen.
-+- listxattr(2) may return the duplicated entries.
-+- users may not be able to remove or reset the XATTR forever,
-+
-+
-+XATTR/EA support in the internal (copy,move)-(up,down)
-+----------------------------------------------------------------------
-+Generally the extended attributes of inode are categorized as these.
-+- "security" for LSM and capability.
-+- "system" for posix ACL, 'acl' mount option is required for the branch
-+ fs generally.
-+- "trusted" for userspace, CAP_SYS_ADMIN is required.
-+- "user" for userspace, 'user_xattr' mount option is required for the
-+ branch fs generally.
-+
-+Moreover there are some other categories. Aufs handles these rather
-+unpopular categories as the ordinary ones, ie. there is no special
-+condition nor exception.
-+
-+In copy-up, the support for XATTR on the dst branch may differ from the
-+src branch. In this case, the copy-up operation will get an error and
-+the original user operation which triggered the copy-up will fail. It
-+can happen that even all copy-up will fail.
-+When both of src and dst branches support XATTR and if an error occurs
-+during copying XATTR, then the copy-up should fail obviously. That is a
-+good reason and aufs should return an error to userspace. But when only
-+the src branch support that XATTR, aufs should not return an error.
-+For example, the src branch supports ACL but the dst branch doesn't
-+because the dst branch may natively un-support it or temporary
-+un-support it due to "noacl" mount option. Of course, the dst branch fs
-+may NOT return an error even if the XATTR is not supported. It is
-+totally up to the branch fs.
-+
-+Anyway when the aufs internal copy-up gets an error from the dst branch
-+fs, then aufs tries removing the just copied entry and returns the error
-+to the userspace. The worst case of this situation will be all copy-up
-+will fail.
-+
-+For the copy-up operation, there two basic approaches.
-+- copy the specified XATTR only (by category above), and return the
-+ error unconditionally if it happens.
-+- copy all XATTR, and ignore the error on the specified category only.
-+
-+In order to support XATTR and to implement the correct behaviour, aufs
-+chooses the latter approach and introduces some new branch attributes,
-+"icexsec", "icexsys", "icextr", "icexusr", and "icexoth".
-+They correspond to the XATTR namespaces (see above). Additionally, to be
-+convenient, "icex" is also provided which means all "icex*" attributes
-+are set (here the word "icex" stands for "ignore copy-error on XATTR").
-+
-+The meaning of these attributes is to ignore the error from setting
-+XATTR on that branch.
-+Note that aufs tries copying all XATTR unconditionally, and ignores the
-+error from the dst branch according to the specified attributes.
-+
-+Some XATTR may have its default value. The default value may come from
-+the parent dir or the environment. If the default value is set at the
-+file creating-time, it will be overwritten by copy-up.
-+Some contradiction may happen I am afraid.
-+Do we need another attribute to stop copying XATTR? I am unsure. For
-+now, aufs implements the branch attributes to ignore the error.
-diff --git a/Documentation/filesystems/aufs/design/07export.txt b/Documentation/filesystems/aufs/design/07export.txt
-new file mode 100644
-index 000000000000..9b983f3dd78a
---- /dev/null
-+++ b/Documentation/filesystems/aufs/design/07export.txt
-@@ -0,0 +1,58 @@
-+
-+# Copyright (C) 2005-2019 Junjiro R. Okajima
-+#
-+# This program is free software; you can redistribute it and/or modify
-+# it under the terms of the GNU General Public License as published by
-+# the Free Software Foundation; either version 2 of the License, or
-+# (at your option) any later version.
-+#
-+# This program is distributed in the hope that it will be useful,
-+# but WITHOUT ANY WARRANTY; without even the implied warranty of
-+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
-+# GNU General Public License for more details.
-+#
-+# You should have received a copy of the GNU General Public License
-+# along with this program. If not, see <http://www.gnu.org/licenses/>.
-+
-+Export Aufs via NFS
-+----------------------------------------------------------------------
-+Here is an approach.
-+- like xino/xib, add a new file 'xigen' which stores aufs inode
-+ generation.
-+- iget_locked(): initialize aufs inode generation for a new inode, and
-+ store it in xigen file.
-+- destroy_inode(): increment aufs inode generation and store it in xigen
-+ file. it is necessary even if it is not unlinked, because any data of
-+ inode may be changed by UDBA.
-+- encode_fh(): for a root dir, simply return FILEID_ROOT. otherwise
-+ build file handle by
-+ + branch id (4 bytes)
-+ + superblock generation (4 bytes)
-+ + inode number (4 or 8 bytes)
-+ + parent dir inode number (4 or 8 bytes)
-+ + inode generation (4 bytes))
-+ + return value of exportfs_encode_fh() for the parent on a branch (4
-+ bytes)
-+ + file handle for a branch (by exportfs_encode_fh())
-+- fh_to_dentry():
-+ + find the index of a branch from its id in handle, and check it is
-+ still exist in aufs.
-+ + 1st level: get the inode number from handle and search it in cache.
-+ + 2nd level: if not found in cache, get the parent inode number from
-+ the handle and search it in cache. and then open the found parent
-+ dir, find the matching inode number by vfs_readdir() and get its
-+ name, and call lookup_one_len() for the target dentry.
-+ + 3rd level: if the parent dir is not cached, call
-+ exportfs_decode_fh() for a branch and get the parent on a branch,
-+ build a pathname of it, convert it a pathname in aufs, call
-+ path_lookup(). now aufs gets a parent dir dentry, then handle it as
-+ the 2nd level.
-+ + to open the dir, aufs needs struct vfsmount. aufs keeps vfsmount
-+ for every branch, but not itself. to get this, (currently) aufs
-+ searches in current->nsproxy->mnt_ns list. it may not be a good
-+ idea, but I didn't get other approach.
-+ + test the generation of the gotten inode.
-+- every inode operation: they may get EBUSY due to UDBA. in this case,
-+ convert it into ESTALE for NFSD.
-+- readdir(): call lockdep_on/off() because filldir in NFSD calls
-+ lookup_one_len(), vfs_getattr(), encode_fh() and others.
-diff --git a/Documentation/filesystems/aufs/design/08shwh.txt b/Documentation/filesystems/aufs/design/08shwh.txt
-new file mode 100644
-index 000000000000..647a86a65db7
---- /dev/null
-+++ b/Documentation/filesystems/aufs/design/08shwh.txt
-@@ -0,0 +1,52 @@
-+
-+# Copyright (C) 2005-2019 Junjiro R. Okajima
-+#
-+# This program is free software; you can redistribute it and/or modify
-+# it under the terms of the GNU General Public License as published by
-+# the Free Software Foundation; either version 2 of the License, or
-+# (at your option) any later version.
-+#
-+# This program is distributed in the hope that it will be useful,
-+# but WITHOUT ANY WARRANTY; without even the implied warranty of
-+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
-+# GNU General Public License for more details.
-+#
-+# You should have received a copy of the GNU General Public License
-+# along with this program. If not, see <http://www.gnu.org/licenses/>.
-+
-+Show Whiteout Mode (shwh)
-+----------------------------------------------------------------------
-+Generally aufs hides the name of whiteouts. But in some cases, to show
-+them is very useful for users. For instance, creating a new middle layer
-+(branch) by merging existing layers.
-+
-+(borrowing aufs1 HOW-TO from a user, Michael Towers)
-+When you have three branches,
-+- Bottom: 'system', squashfs (underlying base system), read-only
-+- Middle: 'mods', squashfs, read-only
-+- Top: 'overlay', ram (tmpfs), read-write
-+
-+The top layer is loaded at boot time and saved at shutdown, to preserve
-+the changes made to the system during the session.
-+When larger changes have been made, or smaller changes have accumulated,
-+the size of the saved top layer data grows. At this point, it would be
-+nice to be able to merge the two overlay branches ('mods' and 'overlay')
-+and rewrite the 'mods' squashfs, clearing the top layer and thus
-+restoring save and load speed.
-+
-+This merging is simplified by the use of another aufs mount, of just the
-+two overlay branches using the 'shwh' option.
-+# mount -t aufs -o ro,shwh,br:/livesys/overlay=ro+wh:/livesys/mods=rr+wh \
-+ aufs /livesys/merge_union
-+
-+A merged view of these two branches is then available at
-+/livesys/merge_union, and the new feature is that the whiteouts are
-+visible!
-+Note that in 'shwh' mode the aufs mount must be 'ro', which will disable
-+writing to all branches. Also the default mode for all branches is 'ro'.
-+It is now possible to save the combined contents of the two overlay
-+branches to a new squashfs, e.g.:
-+# mksquashfs /livesys/merge_union /path/to/newmods.squash
-+
-+This new squashfs archive can be stored on the boot device and the
-+initramfs will use it to replace the old one at the next boot.
-diff --git a/Documentation/filesystems/aufs/design/10dynop.txt b/Documentation/filesystems/aufs/design/10dynop.txt
-new file mode 100644
-index 000000000000..13e8583f2b91
---- /dev/null
-+++ b/Documentation/filesystems/aufs/design/10dynop.txt
-@@ -0,0 +1,47 @@
-+
-+# Copyright (C) 2010-2019 Junjiro R. Okajima
-+#
-+# This program is free software; you can redistribute it and/or modify
-+# it under the terms of the GNU General Public License as published by
-+# the Free Software Foundation; either version 2 of the License, or
-+# (at your option) any later version.
-+#
-+# This program is distributed in the hope that it will be useful,
-+# but WITHOUT ANY WARRANTY; without even the implied warranty of
-+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
-+# GNU General Public License for more details.
-+#
-+# You should have received a copy of the GNU General Public License
-+# along with this program. If not, see <http://www.gnu.org/licenses/>.
-+
-+Dynamically customizable FS operations
-+----------------------------------------------------------------------
-+Generally FS operations (struct inode_operations, struct
-+address_space_operations, struct file_operations, etc.) are defined as
-+"static const", but it never means that FS have only one set of
-+operation. Some FS have multiple sets of them. For instance, ext2 has
-+three sets, one for XIP, for NOBH, and for normal.
-+Since aufs overrides and redirects these operations, sometimes aufs has
-+to change its behaviour according to the branch FS type. More importantly
-+VFS acts differently if a function (member in the struct) is set or
-+not. It means aufs should have several sets of operations and select one
-+among them according to the branch FS definition.
-+
-+In order to solve this problem and not to affect the behaviour of VFS,
-+aufs defines these operations dynamically. For instance, aufs defines
-+dummy direct_IO function for struct address_space_operations, but it may
-+not be set to the address_space_operations actually. When the branch FS
-+doesn't have it, aufs doesn't set it to its address_space_operations
-+while the function definition itself is still alive. So the behaviour
-+itself will not change, and it will return an error when direct_IO is
-+not set.
-+
-+The lifetime of these dynamically generated operation object is
-+maintained by aufs branch object. When the branch is removed from aufs,
-+the reference counter of the object is decremented. When it reaches
-+zero, the dynamically generated operation object will be freed.
-+
-+This approach is designed to support AIO (io_submit), Direct I/O and
-+XIP (DAX) mainly.
-+Currently this approach is applied to address_space_operations for
-+regular files only.
-diff --git a/fs/aufs/Kconfig b/fs/aufs/Kconfig
-new file mode 100644
-index 000000000000..9f436425716a
---- /dev/null
-+++ b/fs/aufs/Kconfig
-@@ -0,0 +1,199 @@
-+# SPDX-License-Identifier: GPL-2.0
-+config AUFS_FS
-+ tristate "Aufs (Advanced multi layered unification filesystem) support"
-+ help
-+ Aufs is a stackable unification filesystem such as Unionfs,
-+ which unifies several directories and provides a merged single
-+ directory.
-+ In the early days, aufs was entirely re-designed and
-+ re-implemented Unionfs Version 1.x series. Introducing many
-+ original ideas, approaches and improvements, it becomes totally
-+ different from Unionfs while keeping the basic features.
-+
-+if AUFS_FS
-+choice
-+ prompt "Maximum number of branches"
-+ default AUFS_BRANCH_MAX_127
-+ help
-+ Specifies the maximum number of branches (or member directories)
-+ in a single aufs. The larger value consumes more system
-+ resources and has a minor impact to performance.
-+config AUFS_BRANCH_MAX_127
-+ bool "127"
-+ help
-+ Specifies the maximum number of branches (or member directories)
-+ in a single aufs. The larger value consumes more system
-+ resources and has a minor impact to performance.
-+config AUFS_BRANCH_MAX_511
-+ bool "511"
-+ help
-+ Specifies the maximum number of branches (or member directories)
-+ in a single aufs. The larger value consumes more system
-+ resources and has a minor impact to performance.
-+config AUFS_BRANCH_MAX_1023
-+ bool "1023"
-+ help
-+ Specifies the maximum number of branches (or member directories)
-+ in a single aufs. The larger value consumes more system
-+ resources and has a minor impact to performance.
-+config AUFS_BRANCH_MAX_32767
-+ bool "32767"
-+ help
-+ Specifies the maximum number of branches (or member directories)
-+ in a single aufs. The larger value consumes more system
-+ resources and has a minor impact to performance.
-+endchoice
-+
-+config AUFS_SBILIST
-+ bool
-+ depends on AUFS_MAGIC_SYSRQ || PROC_FS
-+ default y
-+ help
-+ Automatic configuration for internal use.
-+ When aufs supports Magic SysRq or /proc, enabled automatically.
-+
-+config AUFS_HNOTIFY
-+ bool "Detect direct branch access (bypassing aufs)"
-+ help
-+ If you want to modify files on branches directly, eg. bypassing aufs,
-+ and want aufs to detect the changes of them fully, then enable this
-+ option and use 'udba=notify' mount option.
-+ Currently there is only one available configuration, "fsnotify".
-+ It will have a negative impact to the performance.
-+ See detail in aufs.5.
-+
-+choice
-+ prompt "method" if AUFS_HNOTIFY
-+ default AUFS_HFSNOTIFY
-+config AUFS_HFSNOTIFY
-+ bool "fsnotify"
-+ select FSNOTIFY
-+endchoice
-+
-+config AUFS_EXPORT
-+ bool "NFS-exportable aufs"
-+ depends on EXPORTFS
-+ help
-+ If you want to export your mounted aufs via NFS, then enable this
-+ option. There are several requirements for this configuration.
-+ See detail in aufs.5.
-+
-+config AUFS_INO_T_64
-+ bool
-+ depends on AUFS_EXPORT
-+ depends on 64BIT && !(ALPHA || S390)
-+ default y
-+ help
-+ Automatic configuration for internal use.
-+ /* typedef unsigned long/int __kernel_ino_t */
-+ /* alpha and s390x are int */
-+
-+config AUFS_XATTR
-+ bool "support for XATTR/EA (including Security Labels)"
-+ help
-+ If your branch fs supports XATTR/EA and you want to make them
-+ available in aufs too, then enable this opsion and specify the
-+ branch attributes for EA.
-+ See detail in aufs.5.
-+
-+config AUFS_FHSM
-+ bool "File-based Hierarchical Storage Management"
-+ help
-+ Hierarchical Storage Management (or HSM) is a well-known feature
-+ in the storage world. Aufs provides this feature as file-based.
-+ with multiple branches.
-+ These multiple branches are prioritized, ie. the topmost one
-+ should be the fastest drive and be used heavily.
-+
-+config AUFS_RDU
-+ bool "Readdir in userspace"
-+ help
-+ Aufs has two methods to provide a merged view for a directory,
-+ by a user-space library and by kernel-space natively. The latter
-+ is always enabled but sometimes large and slow.
-+ If you enable this option, install the library in aufs2-util
-+ package, and set some environment variables for your readdir(3),
-+ then the work will be handled in user-space which generally
-+ shows better performance in most cases.
-+ See detail in aufs.5.
-+
-+config AUFS_DIRREN
-+ bool "Workaround for rename(2)-ing a directory"
-+ help
-+ By default, aufs returns EXDEV error in renameing a dir who has
-+ his child on the lower branch, since it is a bad idea to issue
-+ rename(2) internally for every lower branch. But user may not
-+ accept this behaviour. So here is a workaround to allow such
-+ rename(2) and store some extra infromation on the writable
-+ branch. Obviously this costs high (and I don't like it).
-+ To use this feature, you need to enable this configuration AND
-+ to specify the mount option `dirren.'
-+ See details in aufs.5 and the design documents.
-+
-+config AUFS_SHWH
-+ bool "Show whiteouts"
-+ help
-+ If you want to make the whiteouts in aufs visible, then enable
-+ this option and specify 'shwh' mount option. Although it may
-+ sounds like philosophy or something, but in technically it
-+ simply shows the name of whiteout with keeping its behaviour.
-+
-+config AUFS_BR_RAMFS
-+ bool "Ramfs (initramfs/rootfs) as an aufs branch"
-+ help
-+ If you want to use ramfs as an aufs branch fs, then enable this
-+ option. Generally tmpfs is recommended.
-+ Aufs prohibited them to be a branch fs by default, because
-+ initramfs becomes unusable after switch_root or something
-+ generally. If you sets initramfs as an aufs branch and boot your
-+ system by switch_root, you will meet a problem easily since the
-+ files in initramfs may be inaccessible.
-+ Unless you are going to use ramfs as an aufs branch fs without
-+ switch_root or something, leave it N.
-+
-+config AUFS_BR_FUSE
-+ bool "Fuse fs as an aufs branch"
-+ depends on FUSE_FS
-+ select AUFS_POLL
-+ help
-+ If you want to use fuse-based userspace filesystem as an aufs
-+ branch fs, then enable this option.
-+ It implements the internal poll(2) operation which is
-+ implemented by fuse only (curretnly).
-+
-+config AUFS_POLL
-+ bool
-+ help
-+ Automatic configuration for internal use.
-+
-+config AUFS_BR_HFSPLUS
-+ bool "Hfsplus as an aufs branch"
-+ depends on HFSPLUS_FS
-+ default y
-+ help
-+ If you want to use hfsplus fs as an aufs branch fs, then enable
-+ this option. This option introduces a small overhead at
-+ copying-up a file on hfsplus.
-+
-+config AUFS_BDEV_LOOP
-+ bool
-+ depends on BLK_DEV_LOOP
-+ default y
-+ help
-+ Automatic configuration for internal use.
-+ Convert =[ym] into =y.
-+
-+config AUFS_DEBUG
-+ bool "Debug aufs"
-+ help
-+ Enable this to compile aufs internal debug code.
-+ It will have a negative impact to the performance.
-+
-+config AUFS_MAGIC_SYSRQ
-+ bool
-+ depends on AUFS_DEBUG && MAGIC_SYSRQ
-+ default y
-+ help
-+ Automatic configuration for internal use.
-+ When aufs supports Magic SysRq, enabled automatically.
-+endif
-diff --git a/fs/aufs/Makefile b/fs/aufs/Makefile
-new file mode 100644
-index 000000000000..2c819a64935e
---- /dev/null
-+++ b/fs/aufs/Makefile
-@@ -0,0 +1,46 @@
-+# SPDX-License-Identifier: GPL-2.0
-+
-+include ${src}/magic.mk
-+ifeq (${CONFIG_AUFS_FS},m)
-+include ${src}/conf.mk
-+endif
-+-include ${src}/priv_def.mk
-+
-+# cf. include/linux/kernel.h
-+# enable pr_debug
-+ccflags-y += -DDEBUG
-+# sparse requires the full pathname
-+ifdef M
-+ccflags-y += -include ${M}/../../include/uapi/linux/aufs_type.h
-+else
-+ccflags-y += -include ${srctree}/include/uapi/linux/aufs_type.h
-+endif
-+
-+obj-$(CONFIG_AUFS_FS) += aufs.o
-+aufs-y := module.o sbinfo.o super.o branch.o xino.o sysaufs.o opts.o \
-+ wkq.o vfsub.o dcsub.o \
-+ cpup.o whout.o wbr_policy.o \
-+ dinfo.o dentry.o \
-+ dynop.o \
-+ finfo.o file.o f_op.o \
-+ dir.o vdir.o \
-+ iinfo.o inode.o i_op.o i_op_add.o i_op_del.o i_op_ren.o \
-+ mvdown.o ioctl.o
-+
-+# all are boolean
-+aufs-$(CONFIG_PROC_FS) += procfs.o plink.o
-+aufs-$(CONFIG_SYSFS) += sysfs.o
-+aufs-$(CONFIG_DEBUG_FS) += dbgaufs.o
-+aufs-$(CONFIG_AUFS_BDEV_LOOP) += loop.o
-+aufs-$(CONFIG_AUFS_HNOTIFY) += hnotify.o
-+aufs-$(CONFIG_AUFS_HFSNOTIFY) += hfsnotify.o
-+aufs-$(CONFIG_AUFS_EXPORT) += export.o
-+aufs-$(CONFIG_AUFS_XATTR) += xattr.o
-+aufs-$(CONFIG_FS_POSIX_ACL) += posix_acl.o
-+aufs-$(CONFIG_AUFS_DIRREN) += dirren.o
-+aufs-$(CONFIG_AUFS_FHSM) += fhsm.o
-+aufs-$(CONFIG_AUFS_POLL) += poll.o
-+aufs-$(CONFIG_AUFS_RDU) += rdu.o
-+aufs-$(CONFIG_AUFS_BR_HFSPLUS) += hfsplus.o
-+aufs-$(CONFIG_AUFS_DEBUG) += debug.o
-+aufs-$(CONFIG_AUFS_MAGIC_SYSRQ) += sysrq.o
-diff --git a/fs/aufs/aufs.h b/fs/aufs/aufs.h
-new file mode 100644
-index 000000000000..a62a85211b88
---- /dev/null
-+++ b/fs/aufs/aufs.h
-@@ -0,0 +1,62 @@
-+/* SPDX-License-Identifier: GPL-2.0 */
-+/*
-+ * Copyright (C) 2005-2019 Junjiro R. Okajima
-+ *
-+ * This program, aufs is free software; you can redistribute it and/or modify
-+ * it under the terms of the GNU General Public License as published by
-+ * the Free Software Foundation; either version 2 of the License, or
-+ * (at your option) any later version.
-+ *
-+ * This program is distributed in the hope that it will be useful,
-+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
-+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
-+ * GNU General Public License for more details.
-+ *
-+ * You should have received a copy of the GNU General Public License
-+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
-+ */
-+
-+/*
-+ * all header files
-+ */
-+
-+#ifndef __AUFS_H__
-+#define __AUFS_H__
-+
-+#ifdef __KERNEL__
-+
-+#define AuStub(type, name, body, ...) \
-+ static inline type name(__VA_ARGS__) { body; }
-+
-+#define AuStubVoid(name, ...) \
-+ AuStub(void, name, , __VA_ARGS__)
-+#define AuStubInt0(name, ...) \
-+ AuStub(int, name, return 0, __VA_ARGS__)
-+
-+#include "debug.h"
-+
-+#include "branch.h"
-+#include "cpup.h"
-+#include "dcsub.h"
-+#include "dbgaufs.h"
-+#include "dentry.h"
-+#include "dir.h"
-+#include "dirren.h"
-+#include "dynop.h"
-+#include "file.h"
-+#include "fstype.h"
-+#include "hbl.h"
-+#include "inode.h"
-+#include "lcnt.h"
-+#include "loop.h"
-+#include "module.h"
-+#include "opts.h"
-+#include "rwsem.h"
-+#include "super.h"
-+#include "sysaufs.h"
-+#include "vfsub.h"
-+#include "whout.h"
-+#include "wkq.h"
-+
-+#endif /* __KERNEL__ */
-+#endif /* __AUFS_H__ */
-diff --git a/fs/aufs/branch.c b/fs/aufs/branch.c
-new file mode 100644
-index 000000000000..fb388a049940
---- /dev/null
-+++ b/fs/aufs/branch.c
-@@ -0,0 +1,1423 @@
-+// SPDX-License-Identifier: GPL-2.0
-+/*
-+ * Copyright (C) 2005-2019 Junjiro R. Okajima
-+ *
-+ * This program, aufs is free software; you can redistribute it and/or modify
-+ * it under the terms of the GNU General Public License as published by
-+ * the Free Software Foundation; either version 2 of the License, or
-+ * (at your option) any later version.
-+ *
-+ * This program is distributed in the hope that it will be useful,
-+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
-+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
-+ * GNU General Public License for more details.
-+ *
-+ * You should have received a copy of the GNU General Public License
-+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
-+ */
-+
-+/*
-+ * branch management
-+ */
-+
-+#include <linux/compat.h>
-+#include <linux/statfs.h>
-+#include "aufs.h"
-+
-+/*
-+ * free a single branch
-+ */
-+static void au_br_do_free(struct au_branch *br)
-+{
-+ int i;
-+ struct au_wbr *wbr;
-+ struct au_dykey **key;
-+
-+ au_hnotify_fin_br(br);
-+ /* always, regardless the mount option */
-+ au_dr_hino_free(&br->br_dirren);
-+ au_xino_put(br);
-+
-+ AuLCntZero(au_lcnt_read(&br->br_nfiles, /*do_rev*/0));
-+ au_lcnt_fin(&br->br_nfiles, /*do_sync*/0);
-+ AuLCntZero(au_lcnt_read(&br->br_count, /*do_rev*/0));
-+ au_lcnt_fin(&br->br_count, /*do_sync*/0);
-+
-+ wbr = br->br_wbr;
-+ if (wbr) {
-+ for (i = 0; i < AuBrWh_Last; i++)
-+ dput(wbr->wbr_wh[i]);
-+ AuDebugOn(atomic_read(&wbr->wbr_wh_running));
-+ AuRwDestroy(&wbr->wbr_wh_rwsem);
-+ }
-+
-+ if (br->br_fhsm) {
-+ au_br_fhsm_fin(br->br_fhsm);
-+ au_kfree_try_rcu(br->br_fhsm);
-+ }
-+
-+ key = br->br_dykey;
-+ for (i = 0; i < AuBrDynOp; i++, key++)
-+ if (*key)
-+ au_dy_put(*key);
-+ else
-+ break;
-+
-+ /* recursive lock, s_umount of branch's */
-+ /* synchronize_rcu(); */ /* why? */
-+ lockdep_off();
-+ path_put(&br->br_path);
-+ lockdep_on();
-+ au_kfree_rcu(wbr);
-+ au_lcnt_wait_for_fin(&br->br_nfiles);
-+ au_lcnt_wait_for_fin(&br->br_count);
-+ /* I don't know why, but percpu_refcount requires this */
-+ /* synchronize_rcu(); */
-+ au_kfree_rcu(br);
-+}
-+
-+/*
-+ * frees all branches
-+ */
-+void au_br_free(struct au_sbinfo *sbinfo)
-+{
-+ aufs_bindex_t bmax;
-+ struct au_branch **br;
-+
-+ AuRwMustWriteLock(&sbinfo->si_rwsem);
-+
-+ bmax = sbinfo->si_bbot + 1;
-+ br = sbinfo->si_branch;
-+ while (bmax--)
-+ au_br_do_free(*br++);
-+}
-+
-+/*
-+ * find the index of a branch which is specified by @br_id.
-+ */
-+int au_br_index(struct super_block *sb, aufs_bindex_t br_id)
-+{
-+ aufs_bindex_t bindex, bbot;
-+
-+ bbot = au_sbbot(sb);
-+ for (bindex = 0; bindex <= bbot; bindex++)
-+ if (au_sbr_id(sb, bindex) == br_id)
-+ return bindex;
-+ return -1;
-+}
-+
-+/* ---------------------------------------------------------------------- */
-+
-+/*
-+ * add a branch
-+ */
-+
-+static int test_overlap(struct super_block *sb, struct dentry *h_adding,
-+ struct dentry *h_root)
-+{
-+ if (unlikely(h_adding == h_root
-+ || au_test_loopback_overlap(sb, h_adding)))
-+ return 1;
-+ if (h_adding->d_sb != h_root->d_sb)
-+ return 0;
-+ return au_test_subdir(h_adding, h_root)
-+ || au_test_subdir(h_root, h_adding);
-+}
-+
-+/*
-+ * returns a newly allocated branch. @new_nbranch is a number of branches
-+ * after adding a branch.
-+ */
-+static struct au_branch *au_br_alloc(struct super_block *sb, int new_nbranch,
-+ int perm)
-+{
-+ struct au_branch *add_branch;
-+ struct dentry *root;
-+ struct inode *inode;
-+ int err;
-+
-+ err = -ENOMEM;
-+ add_branch = kzalloc(sizeof(*add_branch), GFP_NOFS);
-+ if (unlikely(!add_branch))
-+ goto out;
-+ add_branch->br_xino = au_xino_alloc(/*nfile*/1);
-+ if (unlikely(!add_branch->br_xino))
-+ goto out_br;
-+ err = au_hnotify_init_br(add_branch, perm);
-+ if (unlikely(err))
-+ goto out_xino;
-+
-+ if (au_br_writable(perm)) {
-+ /* may be freed separately at changing the branch permission */
-+ add_branch->br_wbr = kzalloc(sizeof(*add_branch->br_wbr),
-+ GFP_NOFS);
-+ if (unlikely(!add_branch->br_wbr))
-+ goto out_hnotify;
-+ }
-+
-+ if (au_br_fhsm(perm)) {
-+ err = au_fhsm_br_alloc(add_branch);
-+ if (unlikely(err))
-+ goto out_wbr;
-+ }
-+
-+ root = sb->s_root;
-+ err = au_sbr_realloc(au_sbi(sb), new_nbranch, /*may_shrink*/0);
-+ if (!err)
-+ err = au_di_realloc(au_di(root), new_nbranch, /*may_shrink*/0);
-+ if (!err) {
-+ inode = d_inode(root);
-+ err = au_hinode_realloc(au_ii(inode), new_nbranch,
-+ /*may_shrink*/0);
-+ }
-+ if (!err)
-+ return add_branch; /* success */
-+
-+out_wbr:
-+ au_kfree_rcu(add_branch->br_wbr);
-+out_hnotify:
-+ au_hnotify_fin_br(add_branch);
-+out_xino:
-+ au_xino_put(add_branch);
-+out_br:
-+ au_kfree_rcu(add_branch);
-+out:
-+ return ERR_PTR(err);
-+}
-+
-+/*
-+ * test if the branch permission is legal or not.
-+ */
-+static int test_br(struct inode *inode, int brperm, char *path)
-+{
-+ int err;
-+
-+ err = (au_br_writable(brperm) && IS_RDONLY(inode));
-+ if (!err)
-+ goto out;
-+
-+ err = -EINVAL;
-+ pr_err("write permission for readonly mount or inode, %s\n", path);
-+
-+out:
-+ return err;
-+}
-+
-+/*
-+ * returns:
-+ * 0: success, the caller will add it
-+ * plus: success, it is already unified, the caller should ignore it
-+ * minus: error
-+ */
-+static int test_add(struct super_block *sb, struct au_opt_add *add, int remount)
-+{
-+ int err;
-+ aufs_bindex_t bbot, bindex;
-+ struct dentry *root, *h_dentry;
-+ struct inode *inode, *h_inode;
-+
-+ root = sb->s_root;
-+ bbot = au_sbbot(sb);
-+ if (unlikely(bbot >= 0
-+ && au_find_dbindex(root, add->path.dentry) >= 0)) {
-+ err = 1;
-+ if (!remount) {
-+ err = -EINVAL;
-+ pr_err("%s duplicated\n", add->pathname);
-+ }
-+ goto out;
-+ }
-+
-+ err = -ENOSPC; /* -E2BIG; */
-+ if (unlikely(AUFS_BRANCH_MAX <= add->bindex
-+ || AUFS_BRANCH_MAX - 1 <= bbot)) {
-+ pr_err("number of branches exceeded %s\n", add->pathname);
-+ goto out;
-+ }
-+
-+ err = -EDOM;
-+ if (unlikely(add->bindex < 0 || bbot + 1 < add->bindex)) {
-+ pr_err("bad index %d\n", add->bindex);
-+ goto out;
-+ }
-+
-+ inode = d_inode(add->path.dentry);
-+ err = -ENOENT;
-+ if (unlikely(!inode->i_nlink)) {
-+ pr_err("no existence %s\n", add->pathname);
-+ goto out;
-+ }
-+
-+ err = -EINVAL;
-+ if (unlikely(inode->i_sb == sb)) {
-+ pr_err("%s must be outside\n", add->pathname);
-+ goto out;
-+ }
-+
-+ if (unlikely(au_test_fs_unsuppoted(inode->i_sb))) {
-+ pr_err("unsupported filesystem, %s (%s)\n",
-+ add->pathname, au_sbtype(inode->i_sb));
-+ goto out;
-+ }
-+
-+ if (unlikely(inode->i_sb->s_stack_depth)) {
-+ pr_err("already stacked, %s (%s)\n",
-+ add->pathname, au_sbtype(inode->i_sb));
-+ goto out;
-+ }
-+
-+ err = test_br(d_inode(add->path.dentry), add->perm, add->pathname);
-+ if (unlikely(err))
-+ goto out;
-+
-+ if (bbot < 0)
-+ return 0; /* success */
-+
-+ err = -EINVAL;
-+ for (bindex = 0; bindex <= bbot; bindex++)
-+ if (unlikely(test_overlap(sb, add->path.dentry,
-+ au_h_dptr(root, bindex)))) {
-+ pr_err("%s is overlapped\n", add->pathname);
-+ goto out;
-+ }
-+
-+ err = 0;
-+ if (au_opt_test(au_mntflags(sb), WARN_PERM)) {
-+ h_dentry = au_h_dptr(root, 0);
-+ h_inode = d_inode(h_dentry);
-+ if ((h_inode->i_mode & S_IALLUGO) != (inode->i_mode & S_IALLUGO)
-+ || !uid_eq(h_inode->i_uid, inode->i_uid)
-+ || !gid_eq(h_inode->i_gid, inode->i_gid))
-+ pr_warn("uid/gid/perm %s %u/%u/0%o, %u/%u/0%o\n",
-+ add->pathname,
-+ i_uid_read(inode), i_gid_read(inode),
-+ (inode->i_mode & S_IALLUGO),
-+ i_uid_read(h_inode), i_gid_read(h_inode),
-+ (h_inode->i_mode & S_IALLUGO));
-+ }
-+
-+out:
-+ return err;
-+}
-+
-+/*
-+ * initialize or clean the whiteouts for an adding branch
-+ */
-+static int au_br_init_wh(struct super_block *sb, struct au_branch *br,
-+ int new_perm)
-+{
-+ int err, old_perm;
-+ aufs_bindex_t bindex;
-+ struct inode *h_inode;
-+ struct au_wbr *wbr;
-+ struct au_hinode *hdir;
-+ struct dentry *h_dentry;
-+
-+ err = vfsub_mnt_want_write(au_br_mnt(br));
-+ if (unlikely(err))
-+ goto out;
-+
-+ wbr = br->br_wbr;
-+ old_perm = br->br_perm;
-+ br->br_perm = new_perm;
-+ hdir = NULL;
-+ h_inode = NULL;
-+ bindex = au_br_index(sb, br->br_id);
-+ if (0 <= bindex) {
-+ hdir = au_hi(d_inode(sb->s_root), bindex);
-+ au_hn_inode_lock_nested(hdir, AuLsc_I_PARENT);
-+ } else {
-+ h_dentry = au_br_dentry(br);
-+ h_inode = d_inode(h_dentry);
-+ inode_lock_nested(h_inode, AuLsc_I_PARENT);
-+ }
-+ if (!wbr)
-+ err = au_wh_init(br, sb);
-+ else {
-+ wbr_wh_write_lock(wbr);
-+ err = au_wh_init(br, sb);
-+ wbr_wh_write_unlock(wbr);
-+ }
-+ if (hdir)
-+ au_hn_inode_unlock(hdir);
-+ else
-+ inode_unlock(h_inode);
-+ vfsub_mnt_drop_write(au_br_mnt(br));
-+ br->br_perm = old_perm;
-+
-+ if (!err && wbr && !au_br_writable(new_perm)) {
-+ au_kfree_rcu(wbr);
-+ br->br_wbr = NULL;
-+ }
-+
-+out:
-+ return err;
-+}
-+
-+static int au_wbr_init(struct au_branch *br, struct super_block *sb,
-+ int perm)
-+{
-+ int err;
-+ struct kstatfs kst;
-+ struct au_wbr *wbr;
-+
-+ wbr = br->br_wbr;
-+ au_rw_init(&wbr->wbr_wh_rwsem);
-+ atomic_set(&wbr->wbr_wh_running, 0);
-+
-+ /*
-+ * a limit for rmdir/rename a dir
-+ * cf. AUFS_MAX_NAMELEN in include/uapi/linux/aufs_type.h
-+ */
-+ err = vfs_statfs(&br->br_path, &kst);
-+ if (unlikely(err))
-+ goto out;
-+ err = -EINVAL;
-+ if (kst.f_namelen >= NAME_MAX)
-+ err = au_br_init_wh(sb, br, perm);
-+ else
-+ pr_err("%pd(%s), unsupported namelen %ld\n",
-+ au_br_dentry(br),
-+ au_sbtype(au_br_dentry(br)->d_sb), kst.f_namelen);
-+
-+out:
-+ return err;
-+}
-+
-+/* initialize a new branch */
-+static int au_br_init(struct au_branch *br, struct super_block *sb,
-+ struct au_opt_add *add)
-+{
-+ int err;
-+ struct au_branch *brbase;
-+ struct file *xf;
-+ struct inode *h_inode;
-+
-+ err = 0;
-+ br->br_perm = add->perm;
-+ br->br_path = add->path; /* set first, path_get() later */
-+ spin_lock_init(&br->br_dykey_lock);
-+ au_lcnt_init(&br->br_nfiles, /*release*/NULL);
-+ au_lcnt_init(&br->br_count, /*release*/NULL);
-+ br->br_id = au_new_br_id(sb);
-+ AuDebugOn(br->br_id < 0);
-+
-+ /* always, regardless the given option */
-+ err = au_dr_br_init(sb, br, &add->path);
-+ if (unlikely(err))
-+ goto out_err;
-+
-+ if (au_br_writable(add->perm)) {
-+ err = au_wbr_init(br, sb, add->perm);
-+ if (unlikely(err))
-+ goto out_err;
-+ }
-+
-+ if (au_opt_test(au_mntflags(sb), XINO)) {
-+ brbase = au_sbr(sb, 0);
-+ xf = au_xino_file(brbase->br_xino, /*idx*/-1);
-+ AuDebugOn(!xf);
-+ h_inode = d_inode(add->path.dentry);
-+ err = au_xino_init_br(sb, br, h_inode->i_ino, &xf->f_path);
-+ if (unlikely(err)) {
-+ AuDebugOn(au_xino_file(br->br_xino, /*idx*/-1));
-+ goto out_err;
-+ }
-+ }
-+
-+ sysaufs_br_init(br);
-+ path_get(&br->br_path);
-+ goto out; /* success */
-+
-+out_err:
-+ memset(&br->br_path, 0, sizeof(br->br_path));
-+out:
-+ return err;
-+}
-+
-+static void au_br_do_add_brp(struct au_sbinfo *sbinfo, aufs_bindex_t bindex,
-+ struct au_branch *br, aufs_bindex_t bbot,
-+ aufs_bindex_t amount)
-+{
-+ struct au_branch **brp;
-+
-+ AuRwMustWriteLock(&sbinfo->si_rwsem);
-+
-+ brp = sbinfo->si_branch + bindex;
-+ memmove(brp + 1, brp, sizeof(*brp) * amount);
-+ *brp = br;
-+ sbinfo->si_bbot++;
-+ if (unlikely(bbot < 0))
-+ sbinfo->si_bbot = 0;
-+}
-+
-+static void au_br_do_add_hdp(struct au_dinfo *dinfo, aufs_bindex_t bindex,
-+ aufs_bindex_t bbot, aufs_bindex_t amount)
-+{
-+ struct au_hdentry *hdp;
-+
-+ AuRwMustWriteLock(&dinfo->di_rwsem);
-+
-+ hdp = au_hdentry(dinfo, bindex);
-+ memmove(hdp + 1, hdp, sizeof(*hdp) * amount);
-+ au_h_dentry_init(hdp);
-+ dinfo->di_bbot++;
-+ if (unlikely(bbot < 0))
-+ dinfo->di_btop = 0;
-+}
-+
-+static void au_br_do_add_hip(struct au_iinfo *iinfo, aufs_bindex_t bindex,
-+ aufs_bindex_t bbot, aufs_bindex_t amount)
-+{
-+ struct au_hinode *hip;
-+
-+ AuRwMustWriteLock(&iinfo->ii_rwsem);
-+
-+ hip = au_hinode(iinfo, bindex);
-+ memmove(hip + 1, hip, sizeof(*hip) * amount);
-+ au_hinode_init(hip);
-+ iinfo->ii_bbot++;
-+ if (unlikely(bbot < 0))
-+ iinfo->ii_btop = 0;
-+}
-+
-+static void au_br_do_add(struct super_block *sb, struct au_branch *br,
-+ aufs_bindex_t bindex)
-+{
-+ struct dentry *root, *h_dentry;
-+ struct inode *root_inode, *h_inode;
-+ aufs_bindex_t bbot, amount;
-+
-+ root = sb->s_root;
-+ root_inode = d_inode(root);
-+ bbot = au_sbbot(sb);
-+ amount = bbot + 1 - bindex;
-+ h_dentry = au_br_dentry(br);
-+ au_sbilist_lock();
-+ au_br_do_add_brp(au_sbi(sb), bindex, br, bbot, amount);
-+ au_br_do_add_hdp(au_di(root), bindex, bbot, amount);
-+ au_br_do_add_hip(au_ii(root_inode), bindex, bbot, amount);
-+ au_set_h_dptr(root, bindex, dget(h_dentry));
-+ h_inode = d_inode(h_dentry);
-+ au_set_h_iptr(root_inode, bindex, au_igrab(h_inode), /*flags*/0);
-+ au_sbilist_unlock();
-+}
-+
-+int au_br_add(struct super_block *sb, struct au_opt_add *add, int remount)
-+{
-+ int err;
-+ aufs_bindex_t bbot, add_bindex;
-+ struct dentry *root, *h_dentry;
-+ struct inode *root_inode;
-+ struct au_branch *add_branch;
-+
-+ root = sb->s_root;
-+ root_inode = d_inode(root);
-+ IMustLock(root_inode);
-+ IiMustWriteLock(root_inode);
-+ err = test_add(sb, add, remount);
-+ if (unlikely(err < 0))
-+ goto out;
-+ if (err) {
-+ err = 0;
-+ goto out; /* success */
-+ }
-+
-+ bbot = au_sbbot(sb);
-+ add_branch = au_br_alloc(sb, bbot + 2, add->perm);
-+ err = PTR_ERR(add_branch);
-+ if (IS_ERR(add_branch))
-+ goto out;
-+
-+ err = au_br_init(add_branch, sb, add);
-+ if (unlikely(err)) {
-+ au_br_do_free(add_branch);
-+ goto out;
-+ }
-+
-+ add_bindex = add->bindex;
-+ sysaufs_brs_del(sb, add_bindex); /* remove successors */
-+ au_br_do_add(sb, add_branch, add_bindex);
-+ sysaufs_brs_add(sb, add_bindex); /* append successors */
-+ dbgaufs_brs_add(sb, add_bindex, /*topdown*/0); /* rename successors */
-+
-+ h_dentry = add->path.dentry;
-+ if (!add_bindex) {
-+ au_cpup_attr_all(root_inode, /*force*/1);
-+ sb->s_maxbytes = h_dentry->d_sb->s_maxbytes;
-+ } else
-+ au_add_nlink(root_inode, d_inode(h_dentry));
-+
-+out:
-+ return err;
-+}
-+
-+/* ---------------------------------------------------------------------- */
-+
-+static unsigned long long au_farray_cb(struct super_block *sb, void *a,
-+ unsigned long long max __maybe_unused,
-+ void *arg)
-+{
-+ unsigned long long n;
-+ struct file **p, *f;
-+ struct hlist_bl_head *files;
-+ struct hlist_bl_node *pos;
-+ struct au_finfo *finfo;
-+
-+ n = 0;
-+ p = a;
-+ files = &au_sbi(sb)->si_files;
-+ hlist_bl_lock(files);
-+ hlist_bl_for_each_entry(finfo, pos, files, fi_hlist) {
-+ f = finfo->fi_file;
-+ if (file_count(f)
-+ && !special_file(file_inode(f)->i_mode)) {
-+ get_file(f);
-+ *p++ = f;
-+ n++;
-+ AuDebugOn(n > max);
-+ }
-+ }
-+ hlist_bl_unlock(files);
-+
-+ return n;
-+}
-+
-+static struct file **au_farray_alloc(struct super_block *sb,
-+ unsigned long long *max)
-+{
-+ struct au_sbinfo *sbi;
-+
-+ sbi = au_sbi(sb);
-+ *max = au_lcnt_read(&sbi->si_nfiles, /*do_rev*/1);
-+ return au_array_alloc(max, au_farray_cb, sb, /*arg*/NULL);
-+}
-+
-+static void au_farray_free(struct file **a, unsigned long long max)
-+{
-+ unsigned long long ull;
-+
-+ for (ull = 0; ull < max; ull++)
-+ if (a[ull])
-+ fput(a[ull]);
-+ kvfree(a);
-+}
-+
-+/* ---------------------------------------------------------------------- */
-+
-+/*
-+ * delete a branch
-+ */
-+
-+/* to show the line number, do not make it inlined function */
-+#define AuVerbose(do_info, fmt, ...) do { \
-+ if (do_info) \
-+ pr_info(fmt, ##__VA_ARGS__); \
-+} while (0)
-+
-+static int au_test_ibusy(struct inode *inode, aufs_bindex_t btop,
-+ aufs_bindex_t bbot)
-+{
-+ return (inode && !S_ISDIR(inode->i_mode)) || btop == bbot;
-+}
-+
-+static int au_test_dbusy(struct dentry *dentry, aufs_bindex_t btop,
-+ aufs_bindex_t bbot)
-+{
-+ return au_test_ibusy(d_inode(dentry), btop, bbot);
-+}
-+
-+/*
-+ * test if the branch is deletable or not.
-+ */
-+static int test_dentry_busy(struct dentry *root, aufs_bindex_t bindex,
-+ unsigned int sigen, const unsigned int verbose)
-+{
-+ int err, i, j, ndentry;
-+ aufs_bindex_t btop, bbot;
-+ struct au_dcsub_pages dpages;
-+ struct au_dpage *dpage;
-+ struct dentry *d;
-+
-+ err = au_dpages_init(&dpages, GFP_NOFS);
-+ if (unlikely(err))
-+ goto out;
-+ err = au_dcsub_pages(&dpages, root, NULL, NULL);
-+ if (unlikely(err))
-+ goto out_dpages;
-+
-+ for (i = 0; !err && i < dpages.ndpage; i++) {
-+ dpage = dpages.dpages + i;
-+ ndentry = dpage->ndentry;
-+ for (j = 0; !err && j < ndentry; j++) {
-+ d = dpage->dentries[j];
-+ AuDebugOn(au_dcount(d) <= 0);
-+ if (!au_digen_test(d, sigen)) {
-+ di_read_lock_child(d, AuLock_IR);
-+ if (unlikely(au_dbrange_test(d))) {
-+ di_read_unlock(d, AuLock_IR);
-+ continue;
-+ }
-+ } else {
-+ di_write_lock_child(d);
-+ if (unlikely(au_dbrange_test(d))) {
-+ di_write_unlock(d);
-+ continue;
-+ }
-+ err = au_reval_dpath(d, sigen);
-+ if (!err)
-+ di_downgrade_lock(d, AuLock_IR);
-+ else {
-+ di_write_unlock(d);
-+ break;
-+ }
-+ }
-+
-+ /* AuDbgDentry(d); */
-+ btop = au_dbtop(d);
-+ bbot = au_dbbot(d);
-+ if (btop <= bindex
-+ && bindex <= bbot
-+ && au_h_dptr(d, bindex)
-+ && au_test_dbusy(d, btop, bbot)) {
-+ err = -EBUSY;
-+ AuVerbose(verbose, "busy %pd\n", d);
-+ AuDbgDentry(d);
-+ }
-+ di_read_unlock(d, AuLock_IR);
-+ }
-+ }
-+
-+out_dpages:
-+ au_dpages_free(&dpages);
-+out:
-+ return err;
-+}
-+
-+static int test_inode_busy(struct super_block *sb, aufs_bindex_t bindex,
-+ unsigned int sigen, const unsigned int verbose)
-+{
-+ int err;
-+ unsigned long long max, ull;
-+ struct inode *i, **array;
-+ aufs_bindex_t btop, bbot;
-+
-+ array = au_iarray_alloc(sb, &max);
-+ err = PTR_ERR(array);
-+ if (IS_ERR(array))
-+ goto out;
-+
-+ err = 0;
-+ AuDbg("b%d\n", bindex);
-+ for (ull = 0; !err && ull < max; ull++) {
-+ i = array[ull];
-+ if (unlikely(!i))
-+ break;
-+ if (i->i_ino == AUFS_ROOT_INO)
-+ continue;
-+
-+ /* AuDbgInode(i); */
-+ if (au_iigen(i, NULL) == sigen)
-+ ii_read_lock_child(i);
-+ else {
-+ ii_write_lock_child(i);
-+ err = au_refresh_hinode_self(i);
-+ au_iigen_dec(i);
-+ if (!err)
-+ ii_downgrade_lock(i);
-+ else {
-+ ii_write_unlock(i);
-+ break;
-+ }
-+ }
-+
-+ btop = au_ibtop(i);
-+ bbot = au_ibbot(i);
-+ if (btop <= bindex
-+ && bindex <= bbot
-+ && au_h_iptr(i, bindex)
-+ && au_test_ibusy(i, btop, bbot)) {
-+ err = -EBUSY;
-+ AuVerbose(verbose, "busy i%lu\n", i->i_ino);
-+ AuDbgInode(i);
-+ }
-+ ii_read_unlock(i);
-+ }
-+ au_iarray_free(array, max);
-+
-+out:
-+ return err;
-+}
-+
-+static int test_children_busy(struct dentry *root, aufs_bindex_t bindex,
-+ const unsigned int verbose)
-+{
-+ int err;
-+ unsigned int sigen;
-+
-+ sigen = au_sigen(root->d_sb);
-+ DiMustNoWaiters(root);
-+ IiMustNoWaiters(d_inode(root));
-+ di_write_unlock(root);
-+ err = test_dentry_busy(root, bindex, sigen, verbose);
-+ if (!err)
-+ err = test_inode_busy(root->d_sb, bindex, sigen, verbose);
-+ di_write_lock_child(root); /* aufs_write_lock() calls ..._child() */
-+
-+ return err;
-+}
-+
-+static int test_dir_busy(struct file *file, aufs_bindex_t br_id,
-+ struct file **to_free, int *idx)
-+{
-+ int err;
-+ unsigned char matched, root;
-+ aufs_bindex_t bindex, bbot;
-+ struct au_fidir *fidir;
-+ struct au_hfile *hfile;
-+
-+ err = 0;
-+ root = IS_ROOT(file->f_path.dentry);
-+ if (root) {
-+ get_file(file);
-+ to_free[*idx] = file;
-+ (*idx)++;
-+ goto out;
-+ }
-+
-+ matched = 0;
-+ fidir = au_fi(file)->fi_hdir;
-+ AuDebugOn(!fidir);
-+ bbot = au_fbbot_dir(file);
-+ for (bindex = au_fbtop(file); bindex <= bbot; bindex++) {
-+ hfile = fidir->fd_hfile + bindex;
-+ if (!hfile->hf_file)
-+ continue;
-+
-+ if (hfile->hf_br->br_id == br_id) {
-+ matched = 1;
-+ break;
-+ }
-+ }
-+ if (matched)
-+ err = -EBUSY;
-+
-+out:
-+ return err;
-+}
-+
-+static int test_file_busy(struct super_block *sb, aufs_bindex_t br_id,
-+ struct file **to_free, int opened)
-+{
-+ int err, idx;
-+ unsigned long long ull, max;
-+ aufs_bindex_t btop;
-+ struct file *file, **array;
-+ struct dentry *root;
-+ struct au_hfile *hfile;
-+
-+ array = au_farray_alloc(sb, &max);
-+ err = PTR_ERR(array);
-+ if (IS_ERR(array))
-+ goto out;
-+
-+ err = 0;
-+ idx = 0;
-+ root = sb->s_root;
-+ di_write_unlock(root);
-+ for (ull = 0; ull < max; ull++) {
-+ file = array[ull];
-+ if (unlikely(!file))
-+ break;
-+
-+ /* AuDbg("%pD\n", file); */
-+ fi_read_lock(file);
-+ btop = au_fbtop(file);
-+ if (!d_is_dir(file->f_path.dentry)) {
-+ hfile = &au_fi(file)->fi_htop;
-+ if (hfile->hf_br->br_id == br_id)
-+ err = -EBUSY;
-+ } else
-+ err = test_dir_busy(file, br_id, to_free, &idx);
-+ fi_read_unlock(file);
-+ if (unlikely(err))
-+ break;
-+ }
-+ di_write_lock_child(root);
-+ au_farray_free(array, max);
-+ AuDebugOn(idx > opened);
-+
-+out:
-+ return err;
-+}
-+
-+static void br_del_file(struct file **to_free, unsigned long long opened,
-+ aufs_bindex_t br_id)
-+{
-+ unsigned long long ull;
-+ aufs_bindex_t bindex, btop, bbot, bfound;
-+ struct file *file;
-+ struct au_fidir *fidir;
-+ struct au_hfile *hfile;
-+
-+ for (ull = 0; ull < opened; ull++) {
-+ file = to_free[ull];
-+ if (unlikely(!file))
-+ break;
-+
-+ /* AuDbg("%pD\n", file); */
-+ AuDebugOn(!d_is_dir(file->f_path.dentry));
-+ bfound = -1;
-+ fidir = au_fi(file)->fi_hdir;
-+ AuDebugOn(!fidir);
-+ fi_write_lock(file);
-+ btop = au_fbtop(file);
-+ bbot = au_fbbot_dir(file);
-+ for (bindex = btop; bindex <= bbot; bindex++) {
-+ hfile = fidir->fd_hfile + bindex;
-+ if (!hfile->hf_file)
-+ continue;
-+
-+ if (hfile->hf_br->br_id == br_id) {
-+ bfound = bindex;
-+ break;
-+ }
-+ }
-+ AuDebugOn(bfound < 0);
-+ au_set_h_fptr(file, bfound, NULL);
-+ if (bfound == btop) {
-+ for (btop++; btop <= bbot; btop++)
-+ if (au_hf_dir(file, btop)) {
-+ au_set_fbtop(file, btop);
-+ break;
-+ }
-+ }
-+ fi_write_unlock(file);
-+ }
-+}
-+
-+static void au_br_do_del_brp(struct au_sbinfo *sbinfo,
-+ const aufs_bindex_t bindex,
-+ const aufs_bindex_t bbot)
-+{
-+ struct au_branch **brp, **p;
-+
-+ AuRwMustWriteLock(&sbinfo->si_rwsem);
-+
-+ brp = sbinfo->si_branch + bindex;
-+ if (bindex < bbot)
-+ memmove(brp, brp + 1, sizeof(*brp) * (bbot - bindex));
-+ sbinfo->si_branch[0 + bbot] = NULL;
-+ sbinfo->si_bbot--;
-+
-+ p = au_krealloc(sbinfo->si_branch, sizeof(*p) * bbot, AuGFP_SBILIST,
-+ /*may_shrink*/1);
-+ if (p)
-+ sbinfo->si_branch = p;
-+ /* harmless error */
-+}
-+
-+static void au_br_do_del_hdp(struct au_dinfo *dinfo, const aufs_bindex_t bindex,
-+ const aufs_bindex_t bbot)
-+{
-+ struct au_hdentry *hdp, *p;
-+
-+ AuRwMustWriteLock(&dinfo->di_rwsem);
-+
-+ hdp = au_hdentry(dinfo, bindex);
-+ if (bindex < bbot)
-+ memmove(hdp, hdp + 1, sizeof(*hdp) * (bbot - bindex));
-+ /* au_h_dentry_init(au_hdentry(dinfo, bbot); */
-+ dinfo->di_bbot--;
-+
-+ p = au_krealloc(dinfo->di_hdentry, sizeof(*p) * bbot, AuGFP_SBILIST,
-+ /*may_shrink*/1);
-+ if (p)
-+ dinfo->di_hdentry = p;
-+ /* harmless error */
-+}
-+
-+static void au_br_do_del_hip(struct au_iinfo *iinfo, const aufs_bindex_t bindex,
-+ const aufs_bindex_t bbot)
-+{
-+ struct au_hinode *hip, *p;
-+
-+ AuRwMustWriteLock(&iinfo->ii_rwsem);
-+
-+ hip = au_hinode(iinfo, bindex);
-+ if (bindex < bbot)
-+ memmove(hip, hip + 1, sizeof(*hip) * (bbot - bindex));
-+ /* au_hinode_init(au_hinode(iinfo, bbot)); */
-+ iinfo->ii_bbot--;
-+
-+ p = au_krealloc(iinfo->ii_hinode, sizeof(*p) * bbot, AuGFP_SBILIST,
-+ /*may_shrink*/1);
-+ if (p)
-+ iinfo->ii_hinode = p;
-+ /* harmless error */
-+}
-+
-+static void au_br_do_del(struct super_block *sb, aufs_bindex_t bindex,
-+ struct au_branch *br)
-+{
-+ aufs_bindex_t bbot;
-+ struct au_sbinfo *sbinfo;
-+ struct dentry *root, *h_root;
-+ struct inode *inode, *h_inode;
-+ struct au_hinode *hinode;
-+
-+ SiMustWriteLock(sb);
-+
-+ root = sb->s_root;
-+ inode = d_inode(root);
-+ sbinfo = au_sbi(sb);
-+ bbot = sbinfo->si_bbot;
-+
-+ h_root = au_h_dptr(root, bindex);
-+ hinode = au_hi(inode, bindex);
-+ h_inode = au_igrab(hinode->hi_inode);
-+ au_hiput(hinode);
-+
-+ au_sbilist_lock();
-+ au_br_do_del_brp(sbinfo, bindex, bbot);
-+ au_br_do_del_hdp(au_di(root), bindex, bbot);
-+ au_br_do_del_hip(au_ii(inode), bindex, bbot);
-+ au_sbilist_unlock();
-+
-+ /* ignore an error */
-+ au_dr_br_fin(sb, br); /* always, regardless the mount option */
-+
-+ dput(h_root);
-+ iput(h_inode);
-+ au_br_do_free(br);
-+}
-+
-+static unsigned long long empty_cb(struct super_block *sb, void *array,
-+ unsigned long long max, void *arg)
-+{
-+ return max;
-+}
-+
-+int au_br_del(struct super_block *sb, struct au_opt_del *del, int remount)
-+{
-+ int err, rerr, i;
-+ unsigned long long opened;
-+ unsigned int mnt_flags;
-+ aufs_bindex_t bindex, bbot, br_id;
-+ unsigned char do_wh, verbose;
-+ struct au_branch *br;
-+ struct au_wbr *wbr;
-+ struct dentry *root;
-+ struct file **to_free;
-+
-+ err = 0;
-+ opened = 0;
-+ to_free = NULL;
-+ root = sb->s_root;
-+ bindex = au_find_dbindex(root, del->h_path.dentry);
-+ if (bindex < 0) {
-+ if (remount)
-+ goto out; /* success */
-+ err = -ENOENT;
-+ pr_err("%s no such branch\n", del->pathname);
-+ goto out;
-+ }
-+ AuDbg("bindex b%d\n", bindex);
-+
-+ err = -EBUSY;
-+ mnt_flags = au_mntflags(sb);
-+ verbose = !!au_opt_test(mnt_flags, VERBOSE);
-+ bbot = au_sbbot(sb);
-+ if (unlikely(!bbot)) {
-+ AuVerbose(verbose, "no more branches left\n");
-+ goto out;
-+ }
-+
-+ br = au_sbr(sb, bindex);
-+ AuDebugOn(!path_equal(&br->br_path, &del->h_path));
-+ if (unlikely(au_lcnt_read(&br->br_count, /*do_rev*/1))) {
-+ AuVerbose(verbose, "br %pd2 is busy now\n", del->h_path.dentry);
-+ goto out;
-+ }
-+
-+ br_id = br->br_id;
-+ opened = au_lcnt_read(&br->br_nfiles, /*do_rev*/1);
-+ if (unlikely(opened)) {
-+ to_free = au_array_alloc(&opened, empty_cb, sb, NULL);
-+ err = PTR_ERR(to_free);
-+ if (IS_ERR(to_free))
-+ goto out;
-+
-+ err = test_file_busy(sb, br_id, to_free, opened);
-+ if (unlikely(err)) {
-+ AuVerbose(verbose, "%llu file(s) opened\n", opened);
-+ goto out;
-+ }
-+ }
-+
-+ wbr = br->br_wbr;
-+ do_wh = wbr && (wbr->wbr_whbase || wbr->wbr_plink || wbr->wbr_orph);
-+ if (do_wh) {
-+ /* instead of WbrWhMustWriteLock(wbr) */
-+ SiMustWriteLock(sb);
-+ for (i = 0; i < AuBrWh_Last; i++) {
-+ dput(wbr->wbr_wh[i]);
-+ wbr->wbr_wh[i] = NULL;
-+ }
-+ }
-+
-+ err = test_children_busy(root, bindex, verbose);
-+ if (unlikely(err)) {
-+ if (do_wh)
-+ goto out_wh;
-+ goto out;
-+ }
-+
-+ err = 0;
-+ if (to_free) {
-+ /*
-+ * now we confirmed the branch is deletable.
-+ * let's free the remaining opened dirs on the branch.
-+ */
-+ di_write_unlock(root);
-+ br_del_file(to_free, opened, br_id);
-+ di_write_lock_child(root);
-+ }
-+
-+ sysaufs_brs_del(sb, bindex); /* remove successors */
-+ dbgaufs_xino_del(br); /* remove one */
-+ au_br_do_del(sb, bindex, br);
-+ sysaufs_brs_add(sb, bindex); /* append successors */
-+ dbgaufs_brs_add(sb, bindex, /*topdown*/1); /* rename successors */
-+
-+ if (!bindex) {
-+ au_cpup_attr_all(d_inode(root), /*force*/1);
-+ sb->s_maxbytes = au_sbr_sb(sb, 0)->s_maxbytes;
-+ } else
-+ au_sub_nlink(d_inode(root), d_inode(del->h_path.dentry));
-+ if (au_opt_test(mnt_flags, PLINK))
-+ au_plink_half_refresh(sb, br_id);
-+
-+ goto out; /* success */
-+
-+out_wh:
-+ /* revert */
-+ rerr = au_br_init_wh(sb, br, br->br_perm);
-+ if (rerr)
-+ pr_warn("failed re-creating base whiteout, %s. (%d)\n",
-+ del->pathname, rerr);
-+out:
-+ if (to_free)
-+ au_farray_free(to_free, opened);
-+ return err;
-+}
-+
-+/* ---------------------------------------------------------------------- */
-+
-+static int au_ibusy(struct super_block *sb, struct aufs_ibusy __user *arg)
-+{
-+ int err;
-+ aufs_bindex_t btop, bbot;
-+ struct aufs_ibusy ibusy;
-+ struct inode *inode, *h_inode;
-+
-+ err = -EPERM;
-+ if (unlikely(!capable(CAP_SYS_ADMIN)))
-+ goto out;
-+
-+ err = copy_from_user(&ibusy, arg, sizeof(ibusy));
-+ if (!err)
-+ /* VERIFY_WRITE */
-+ err = !access_ok(&arg->h_ino, sizeof(arg->h_ino));
-+ if (unlikely(err)) {
-+ err = -EFAULT;
-+ AuTraceErr(err);
-+ goto out;
-+ }
-+
-+ err = -EINVAL;
-+ si_read_lock(sb, AuLock_FLUSH);
-+ if (unlikely(ibusy.bindex < 0 || ibusy.bindex > au_sbbot(sb)))
-+ goto out_unlock;
-+
-+ err = 0;
-+ ibusy.h_ino = 0; /* invalid */
-+ inode = ilookup(sb, ibusy.ino);
-+ if (!inode
-+ || inode->i_ino == AUFS_ROOT_INO
-+ || au_is_bad_inode(inode))
-+ goto out_unlock;
-+
-+ ii_read_lock_child(inode);
-+ btop = au_ibtop(inode);
-+ bbot = au_ibbot(inode);
-+ if (btop <= ibusy.bindex && ibusy.bindex <= bbot) {
-+ h_inode = au_h_iptr(inode, ibusy.bindex);
-+ if (h_inode && au_test_ibusy(inode, btop, bbot))
-+ ibusy.h_ino = h_inode->i_ino;
-+ }
-+ ii_read_unlock(inode);
-+ iput(inode);
-+
-+out_unlock:
-+ si_read_unlock(sb);
-+ if (!err) {
-+ err = __put_user(ibusy.h_ino, &arg->h_ino);
-+ if (unlikely(err)) {
-+ err = -EFAULT;
-+ AuTraceErr(err);
-+ }
-+ }
-+out:
-+ return err;
-+}
-+
-+long au_ibusy_ioctl(struct file *file, unsigned long arg)
-+{
-+ return au_ibusy(file->f_path.dentry->d_sb, (void __user *)arg);
-+}
-+
-+#ifdef CONFIG_COMPAT
-+long au_ibusy_compat_ioctl(struct file *file, unsigned long arg)
-+{
-+ return au_ibusy(file->f_path.dentry->d_sb, compat_ptr(arg));
-+}
-+#endif
-+
-+/* ---------------------------------------------------------------------- */
-+
-+/*
-+ * change a branch permission
-+ */
-+
-+static void au_warn_ima(void)
-+{
-+#ifdef CONFIG_IMA
-+ /* since it doesn't support mark_files_ro() */
-+ AuWarn1("RW -> RO makes IMA to produce wrong message\n");
-+#endif
-+}
-+
-+static int do_need_sigen_inc(int a, int b)
-+{
-+ return au_br_whable(a) && !au_br_whable(b);
-+}
-+
-+static int need_sigen_inc(int old, int new)
-+{
-+ return do_need_sigen_inc(old, new)
-+ || do_need_sigen_inc(new, old);
-+}
-+
-+static int au_br_mod_files_ro(struct super_block *sb, aufs_bindex_t bindex)
-+{
-+ int err, do_warn;
-+ unsigned int mnt_flags;
-+ unsigned long long ull, max;
-+ aufs_bindex_t br_id;
-+ unsigned char verbose, writer;
-+ struct file *file, *hf, **array;
-+ struct au_hfile *hfile;
-+
-+ mnt_flags = au_mntflags(sb);
-+ verbose = !!au_opt_test(mnt_flags, VERBOSE);
-+
-+ array = au_farray_alloc(sb, &max);
-+ err = PTR_ERR(array);
-+ if (IS_ERR(array))
-+ goto out;
-+
-+ do_warn = 0;
-+ br_id = au_sbr_id(sb, bindex);
-+ for (ull = 0; ull < max; ull++) {
-+ file = array[ull];
-+ if (unlikely(!file))
-+ break;
-+
-+ /* AuDbg("%pD\n", file); */
-+ fi_read_lock(file);
-+ if (unlikely(au_test_mmapped(file))) {
-+ err = -EBUSY;
-+ AuVerbose(verbose, "mmapped %pD\n", file);
-+ AuDbgFile(file);
-+ FiMustNoWaiters(file);
-+ fi_read_unlock(file);
-+ goto out_array;
-+ }
-+
-+ hfile = &au_fi(file)->fi_htop;
-+ hf = hfile->hf_file;
-+ if (!d_is_reg(file->f_path.dentry)
-+ || !(file->f_mode & FMODE_WRITE)
-+ || hfile->hf_br->br_id != br_id
-+ || !(hf->f_mode & FMODE_WRITE))
-+ array[ull] = NULL;
-+ else {
-+ do_warn = 1;
-+ get_file(file);
-+ }
-+
-+ FiMustNoWaiters(file);
-+ fi_read_unlock(file);
-+ fput(file);
-+ }
-+
-+ err = 0;
-+ if (do_warn)
-+ au_warn_ima();
-+
-+ for (ull = 0; ull < max; ull++) {
-+ file = array[ull];
-+ if (!file)
-+ continue;
-+
-+ /* todo: already flushed? */
-+ /*
-+ * fs/super.c:mark_files_ro() is gone, but aufs keeps its
-+ * approach which resets f_mode and calls mnt_drop_write() and
-+ * file_release_write() for each file, because the branch
-+ * attribute in aufs world is totally different from the native
-+ * fs rw/ro mode.
-+ */
-+ /* fi_read_lock(file); */
-+ hfile = &au_fi(file)->fi_htop;
-+ hf = hfile->hf_file;
-+ /* fi_read_unlock(file); */
-+ spin_lock(&hf->f_lock);
-+ writer = !!(hf->f_mode & FMODE_WRITER);
-+ hf->f_mode &= ~(FMODE_WRITE | FMODE_WRITER);
-+ spin_unlock(&hf->f_lock);
-+ if (writer) {
-+ put_write_access(file_inode(hf));
-+ __mnt_drop_write(hf->f_path.mnt);
-+ }
-+ }
-+
-+out_array:
-+ au_farray_free(array, max);
-+out:
-+ AuTraceErr(err);
-+ return err;
-+}
-+
-+int au_br_mod(struct super_block *sb, struct au_opt_mod *mod, int remount,
-+ int *do_refresh)
-+{
-+ int err, rerr;
-+ aufs_bindex_t bindex;
-+ struct dentry *root;
-+ struct au_branch *br;
-+ struct au_br_fhsm *bf;
-+
-+ root = sb->s_root;
-+ bindex = au_find_dbindex(root, mod->h_root);
-+ if (bindex < 0) {
-+ if (remount)
-+ return 0; /* success */
-+ err = -ENOENT;
-+ pr_err("%s no such branch\n", mod->path);
-+ goto out;
-+ }
-+ AuDbg("bindex b%d\n", bindex);
-+
-+ err = test_br(d_inode(mod->h_root), mod->perm, mod->path);
-+ if (unlikely(err))
-+ goto out;
-+
-+ br = au_sbr(sb, bindex);
-+ AuDebugOn(mod->h_root != au_br_dentry(br));
-+ if (br->br_perm == mod->perm)
-+ return 0; /* success */
-+
-+ /* pre-allocate for non-fhsm --> fhsm */
-+ bf = NULL;
-+ if (!au_br_fhsm(br->br_perm) && au_br_fhsm(mod->perm)) {
-+ err = au_fhsm_br_alloc(br);
-+ if (unlikely(err))
-+ goto out;
-+ bf = br->br_fhsm;
-+ br->br_fhsm = NULL;
-+ }
-+
-+ if (au_br_writable(br->br_perm)) {
-+ /* remove whiteout base */
-+ err = au_br_init_wh(sb, br, mod->perm);
-+ if (unlikely(err))
-+ goto out_bf;
-+
-+ if (!au_br_writable(mod->perm)) {
-+ /* rw --> ro, file might be mmapped */
-+ DiMustNoWaiters(root);
-+ IiMustNoWaiters(d_inode(root));
-+ di_write_unlock(root);
-+ err = au_br_mod_files_ro(sb, bindex);
-+ /* aufs_write_lock() calls ..._child() */
-+ di_write_lock_child(root);
-+
-+ if (unlikely(err)) {
-+ rerr = -ENOMEM;
-+ br->br_wbr = kzalloc(sizeof(*br->br_wbr),
-+ GFP_NOFS);
-+ if (br->br_wbr)
-+ rerr = au_wbr_init(br, sb, br->br_perm);
-+ if (unlikely(rerr)) {
-+ AuIOErr("nested error %d (%d)\n",
-+ rerr, err);
-+ br->br_perm = mod->perm;
-+ }
-+ }
-+ }
-+ } else if (au_br_writable(mod->perm)) {
-+ /* ro --> rw */
-+ err = -ENOMEM;
-+ br->br_wbr = kzalloc(sizeof(*br->br_wbr), GFP_NOFS);
-+ if (br->br_wbr) {
-+ err = au_wbr_init(br, sb, mod->perm);
-+ if (unlikely(err)) {
-+ au_kfree_rcu(br->br_wbr);
-+ br->br_wbr = NULL;
-+ }
-+ }
-+ }
-+ if (unlikely(err))
-+ goto out_bf;
-+
-+ if (au_br_fhsm(br->br_perm)) {
-+ if (!au_br_fhsm(mod->perm)) {
-+ /* fhsm --> non-fhsm */
-+ au_br_fhsm_fin(br->br_fhsm);
-+ au_kfree_rcu(br->br_fhsm);
-+ br->br_fhsm = NULL;
-+ }
-+ } else if (au_br_fhsm(mod->perm))
-+ /* non-fhsm --> fhsm */
-+ br->br_fhsm = bf;
-+
-+ *do_refresh |= need_sigen_inc(br->br_perm, mod->perm);
-+ br->br_perm = mod->perm;
-+ goto out; /* success */
-+
-+out_bf:
-+ au_kfree_try_rcu(bf);
-+out:
-+ AuTraceErr(err);
-+ return err;
-+}
-+
-+/* ---------------------------------------------------------------------- */
-+
-+int au_br_stfs(struct au_branch *br, struct aufs_stfs *stfs)
-+{
-+ int err;
-+ struct kstatfs kstfs;
-+
-+ err = vfs_statfs(&br->br_path, &kstfs);
-+ if (!err) {
-+ stfs->f_blocks = kstfs.f_blocks;
-+ stfs->f_bavail = kstfs.f_bavail;
-+ stfs->f_files = kstfs.f_files;
-+ stfs->f_ffree = kstfs.f_ffree;
-+ }
-+
-+ return err;
-+}
-diff --git a/fs/aufs/branch.h b/fs/aufs/branch.h
-new file mode 100644
-index 000000000000..012459ad57f3
---- /dev/null
-+++ b/fs/aufs/branch.h
-@@ -0,0 +1,366 @@
-+/* SPDX-License-Identifier: GPL-2.0 */
-+/*
-+ * Copyright (C) 2005-2019 Junjiro R. Okajima
-+ *
-+ * This program, aufs is free software; you can redistribute it and/or modify
-+ * it under the terms of the GNU General Public License as published by
-+ * the Free Software Foundation; either version 2 of the License, or
-+ * (at your option) any later version.
-+ *
-+ * This program is distributed in the hope that it will be useful,
-+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
-+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
-+ * GNU General Public License for more details.
-+ *
-+ * You should have received a copy of the GNU General Public License
-+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
-+ */
-+
-+/*
-+ * branch filesystems and xino for them
-+ */
-+
-+#ifndef __AUFS_BRANCH_H__
-+#define __AUFS_BRANCH_H__
-+
-+#ifdef __KERNEL__
-+
-+#include <linux/mount.h>
-+#include "dirren.h"
-+#include "dynop.h"
-+#include "lcnt.h"
-+#include "rwsem.h"
-+#include "super.h"
-+
-+/* ---------------------------------------------------------------------- */
-+
-+/* a xino file */
-+struct au_xino {
-+ struct file **xi_file;
-+ unsigned int xi_nfile;
-+
-+ struct {
-+ spinlock_t spin;
-+ ino_t *array;
-+ int total;
-+ /* reserved for future use */
-+ /* unsigned long *bitmap; */
-+ wait_queue_head_t wqh;
-+ } xi_nondir;
-+
-+ struct mutex xi_mtx; /* protects xi_file array */
-+ struct hlist_bl_head xi_writing;
-+
-+ atomic_t xi_truncating;
-+
-+ struct kref xi_kref;
-+};
-+
-+/* File-based Hierarchical Storage Management */
-+struct au_br_fhsm {
-+#ifdef CONFIG_AUFS_FHSM
-+ struct mutex bf_lock;
-+ unsigned long bf_jiffy;
-+ struct aufs_stfs bf_stfs;
-+ int bf_readable;
-+#endif
-+};
-+
-+/* members for writable branch only */
-+enum {AuBrWh_BASE, AuBrWh_PLINK, AuBrWh_ORPH, AuBrWh_Last};
-+struct au_wbr {
-+ struct au_rwsem wbr_wh_rwsem;
-+ struct dentry *wbr_wh[AuBrWh_Last];
-+ atomic_t wbr_wh_running;
-+#define wbr_whbase wbr_wh[AuBrWh_BASE] /* whiteout base */
-+#define wbr_plink wbr_wh[AuBrWh_PLINK] /* pseudo-link dir */
-+#define wbr_orph wbr_wh[AuBrWh_ORPH] /* dir for orphans */
-+
-+ /* mfs mode */
-+ unsigned long long wbr_bytes;
-+};
-+
-+/* ext2 has 3 types of operations at least, ext3 has 4 */
-+#define AuBrDynOp (AuDyLast * 4)
-+
-+#ifdef CONFIG_AUFS_HFSNOTIFY
-+/* support for asynchronous destruction */
-+struct au_br_hfsnotify {
-+ struct fsnotify_group *hfsn_group;
-+};
-+#endif
-+
-+/* sysfs entries */
-+struct au_brsysfs {
-+ char name[16];
-+ struct attribute attr;
-+};
-+
-+enum {
-+ AuBrSysfs_BR,
-+ AuBrSysfs_BRID,
-+ AuBrSysfs_Last
-+};
-+
-+/* protected by superblock rwsem */
-+struct au_branch {
-+ struct au_xino *br_xino;
-+
-+ aufs_bindex_t br_id;
-+
-+ int br_perm;
-+ struct path br_path;
-+ spinlock_t br_dykey_lock;
-+ struct au_dykey *br_dykey[AuBrDynOp];
-+ au_lcnt_t br_nfiles; /* opened files */
-+ au_lcnt_t br_count; /* in-use for other */
-+
-+ struct au_wbr *br_wbr;
-+ struct au_br_fhsm *br_fhsm;
-+
-+#ifdef CONFIG_AUFS_HFSNOTIFY
-+ struct au_br_hfsnotify *br_hfsn;
-+#endif
-+
-+#ifdef CONFIG_SYSFS
-+ /* entries under sysfs per mount-point */
-+ struct au_brsysfs br_sysfs[AuBrSysfs_Last];
-+#endif
-+
-+#ifdef CONFIG_DEBUG_FS
-+ struct dentry *br_dbgaufs; /* xino */
-+#endif
-+
-+ struct au_dr_br br_dirren;
-+};
-+
-+/* ---------------------------------------------------------------------- */
-+
-+static inline struct vfsmount *au_br_mnt(struct au_branch *br)
-+{
-+ return br->br_path.mnt;
-+}
-+
-+static inline struct dentry *au_br_dentry(struct au_branch *br)
-+{
-+ return br->br_path.dentry;
-+}
-+
-+static inline struct super_block *au_br_sb(struct au_branch *br)
-+{
-+ return au_br_mnt(br)->mnt_sb;
-+}
-+
-+static inline int au_br_rdonly(struct au_branch *br)
-+{
-+ return (sb_rdonly(au_br_sb(br))
-+ || !au_br_writable(br->br_perm))
-+ ? -EROFS : 0;
-+}
-+
-+static inline int au_br_hnotifyable(int brperm __maybe_unused)
-+{
-+#ifdef CONFIG_AUFS_HNOTIFY
-+ return !(brperm & AuBrPerm_RR);
-+#else
-+ return 0;
-+#endif
-+}
-+
-+static inline int au_br_test_oflag(int oflag, struct au_branch *br)
-+{
-+ int err, exec_flag;
-+
-+ err = 0;
-+ exec_flag = oflag & __FMODE_EXEC;
-+ if (unlikely(exec_flag && path_noexec(&br->br_path)))
-+ err = -EACCES;
-+
-+ return err;
-+}
-+
-+static inline void au_xino_get(struct au_branch *br)
-+{
-+ struct au_xino *xi;
-+
-+ xi = br->br_xino;
-+ if (xi)
-+ kref_get(&xi->xi_kref);
-+}
-+
-+static inline int au_xino_count(struct au_branch *br)
-+{
-+ int v;
-+ struct au_xino *xi;
-+
-+ v = 0;
-+ xi = br->br_xino;
-+ if (xi)
-+ v = kref_read(&xi->xi_kref);
-+
-+ return v;
-+}
-+
-+/* ---------------------------------------------------------------------- */
-+
-+/* branch.c */
-+struct au_sbinfo;
-+void au_br_free(struct au_sbinfo *sinfo);
-+int au_br_index(struct super_block *sb, aufs_bindex_t br_id);
-+struct au_opt_add;
-+int au_br_add(struct super_block *sb, struct au_opt_add *add, int remount);
-+struct au_opt_del;
-+int au_br_del(struct super_block *sb, struct au_opt_del *del, int remount);
-+long au_ibusy_ioctl(struct file *file, unsigned long arg);
-+#ifdef CONFIG_COMPAT
-+long au_ibusy_compat_ioctl(struct file *file, unsigned long arg);
-+#endif
-+struct au_opt_mod;
-+int au_br_mod(struct super_block *sb, struct au_opt_mod *mod, int remount,
-+ int *do_refresh);
-+struct aufs_stfs;
-+int au_br_stfs(struct au_branch *br, struct aufs_stfs *stfs);
-+
-+/* xino.c */
-+static const loff_t au_loff_max = LLONG_MAX;
-+
-+aufs_bindex_t au_xi_root(struct super_block *sb, struct dentry *dentry);
-+struct file *au_xino_create(struct super_block *sb, char *fpath, int silent,
-+ int wbrtop);
-+struct file *au_xino_create2(struct super_block *sb, struct path *base,
-+ struct file *copy_src);
-+struct au_xi_new {
-+ struct au_xino *xi; /* switch between xino and xigen */
-+ int idx;
-+ struct path *base;
-+ struct file *copy_src;
-+};
-+struct file *au_xi_new(struct super_block *sb, struct au_xi_new *xinew);
-+
-+int au_xino_read(struct super_block *sb, aufs_bindex_t bindex, ino_t h_ino,
-+ ino_t *ino);
-+int au_xino_write(struct super_block *sb, aufs_bindex_t bindex, ino_t h_ino,
-+ ino_t ino);
-+ssize_t xino_fread(vfs_readf_t func, struct file *file, void *buf, size_t size,
-+ loff_t *pos);
-+ssize_t xino_fwrite(vfs_writef_t func, struct file *file, void *buf,
-+ size_t size, loff_t *pos);
-+
-+int au_xib_trunc(struct super_block *sb);
-+int au_xino_trunc(struct super_block *sb, aufs_bindex_t bindex, int idx_begin);
-+
-+struct au_xino *au_xino_alloc(unsigned int nfile);
-+int au_xino_put(struct au_branch *br);
-+struct file *au_xino_file1(struct au_xino *xi);
-+
-+struct au_opt_xino;
-+void au_xino_clr(struct super_block *sb);
-+int au_xino_set(struct super_block *sb, struct au_opt_xino *xiopt, int remount);
-+struct file *au_xino_def(struct super_block *sb);
-+int au_xino_init_br(struct super_block *sb, struct au_branch *br, ino_t hino,
-+ struct path *base);
-+
-+ino_t au_xino_new_ino(struct super_block *sb);
-+void au_xino_delete_inode(struct inode *inode, const int unlinked);
-+
-+void au_xinondir_leave(struct super_block *sb, aufs_bindex_t bindex,
-+ ino_t h_ino, int idx);
-+int au_xinondir_enter(struct super_block *sb, aufs_bindex_t bindex, ino_t h_ino,
-+ int *idx);
-+
-+int au_xino_path(struct seq_file *seq, struct file *file);
-+
-+/* ---------------------------------------------------------------------- */
-+
-+/* @idx is signed to accept -1 meaning the first file */
-+static inline struct file *au_xino_file(struct au_xino *xi, int idx)
-+{
-+ struct file *file;
-+
-+ file = NULL;
-+ if (!xi)
-+ goto out;
-+
-+ if (idx >= 0) {
-+ if (idx < xi->xi_nfile)
-+ file = xi->xi_file[idx];
-+ } else
-+ file = au_xino_file1(xi);
-+
-+out:
-+ return file;
-+}
-+
-+/* ---------------------------------------------------------------------- */
-+
-+/* Superblock to branch */
-+static inline
-+aufs_bindex_t au_sbr_id(struct super_block *sb, aufs_bindex_t bindex)
-+{
-+ return au_sbr(sb, bindex)->br_id;
-+}
-+
-+static inline
-+struct vfsmount *au_sbr_mnt(struct super_block *sb, aufs_bindex_t bindex)
-+{
-+ return au_br_mnt(au_sbr(sb, bindex));
-+}
-+
-+static inline
-+struct super_block *au_sbr_sb(struct super_block *sb, aufs_bindex_t bindex)
-+{
-+ return au_br_sb(au_sbr(sb, bindex));
-+}
-+
-+static inline int au_sbr_perm(struct super_block *sb, aufs_bindex_t bindex)
-+{
-+ return au_sbr(sb, bindex)->br_perm;
-+}
-+
-+static inline int au_sbr_whable(struct super_block *sb, aufs_bindex_t bindex)
-+{
-+ return au_br_whable(au_sbr_perm(sb, bindex));
-+}
-+
-+/* ---------------------------------------------------------------------- */
-+
-+#define wbr_wh_read_lock(wbr) au_rw_read_lock(&(wbr)->wbr_wh_rwsem)
-+#define wbr_wh_write_lock(wbr) au_rw_write_lock(&(wbr)->wbr_wh_rwsem)
-+#define wbr_wh_read_trylock(wbr) au_rw_read_trylock(&(wbr)->wbr_wh_rwsem)
-+#define wbr_wh_write_trylock(wbr) au_rw_write_trylock(&(wbr)->wbr_wh_rwsem)
-+/*
-+#define wbr_wh_read_trylock_nested(wbr) \
-+ au_rw_read_trylock_nested(&(wbr)->wbr_wh_rwsem)
-+#define wbr_wh_write_trylock_nested(wbr) \
-+ au_rw_write_trylock_nested(&(wbr)->wbr_wh_rwsem)
-+*/
-+
-+#define wbr_wh_read_unlock(wbr) au_rw_read_unlock(&(wbr)->wbr_wh_rwsem)
-+#define wbr_wh_write_unlock(wbr) au_rw_write_unlock(&(wbr)->wbr_wh_rwsem)
-+#define wbr_wh_downgrade_lock(wbr) au_rw_dgrade_lock(&(wbr)->wbr_wh_rwsem)
-+
-+#define WbrWhMustNoWaiters(wbr) AuRwMustNoWaiters(&(wbr)->wbr_wh_rwsem)
-+#define WbrWhMustAnyLock(wbr) AuRwMustAnyLock(&(wbr)->wbr_wh_rwsem)
-+#define WbrWhMustWriteLock(wbr) AuRwMustWriteLock(&(wbr)->wbr_wh_rwsem)
-+
-+/* ---------------------------------------------------------------------- */
-+
-+#ifdef CONFIG_AUFS_FHSM
-+static inline void au_br_fhsm_init(struct au_br_fhsm *brfhsm)
-+{
-+ mutex_init(&brfhsm->bf_lock);
-+ brfhsm->bf_jiffy = 0;
-+ brfhsm->bf_readable = 0;
-+}
-+
-+static inline void au_br_fhsm_fin(struct au_br_fhsm *brfhsm)
-+{
-+ mutex_destroy(&brfhsm->bf_lock);
-+}
-+#else
-+AuStubVoid(au_br_fhsm_init, struct au_br_fhsm *brfhsm)
-+AuStubVoid(au_br_fhsm_fin, struct au_br_fhsm *brfhsm)
-+#endif
-+
-+#endif /* __KERNEL__ */
-+#endif /* __AUFS_BRANCH_H__ */
-diff --git a/fs/aufs/conf.mk b/fs/aufs/conf.mk
-new file mode 100644
-index 000000000000..12782f8e0f38
---- /dev/null
-+++ b/fs/aufs/conf.mk
-@@ -0,0 +1,40 @@
-+# SPDX-License-Identifier: GPL-2.0
-+
-+AuConfStr = CONFIG_AUFS_FS=${CONFIG_AUFS_FS}
-+
-+define AuConf
-+ifdef ${1}
-+AuConfStr += ${1}=${${1}}
-+endif
-+endef
-+
-+AuConfAll = BRANCH_MAX_127 BRANCH_MAX_511 BRANCH_MAX_1023 BRANCH_MAX_32767 \
-+ SBILIST \
-+ HNOTIFY HFSNOTIFY \
-+ EXPORT INO_T_64 \
-+ XATTR \
-+ FHSM \
-+ RDU \
-+ DIRREN \
-+ SHWH \
-+ BR_RAMFS \
-+ BR_FUSE POLL \
-+ BR_HFSPLUS \
-+ BDEV_LOOP \
-+ DEBUG MAGIC_SYSRQ
-+$(foreach i, ${AuConfAll}, \
-+ $(eval $(call AuConf,CONFIG_AUFS_${i})))
-+
-+AuConfName = ${obj}/conf.str
-+${AuConfName}.tmp: FORCE
-+ @echo ${AuConfStr} | tr ' ' '\n' | sed -e 's/^/"/' -e 's/$$/\\n"/' > $@
-+${AuConfName}: ${AuConfName}.tmp
-+ @diff -q $< $@ > /dev/null 2>&1 || { \
-+ echo ' GEN ' $@; \
-+ cp -p $< $@; \
-+ }
-+FORCE:
-+clean-files += ${AuConfName} ${AuConfName}.tmp
-+${obj}/sysfs.o: ${AuConfName}
-+
-+-include ${srctree}/${src}/conf_priv.mk
-diff --git a/fs/aufs/cpup.c b/fs/aufs/cpup.c
-new file mode 100644
-index 000000000000..21134b448967
---- /dev/null
-+++ b/fs/aufs/cpup.c
-@@ -0,0 +1,1458 @@
-+// SPDX-License-Identifier: GPL-2.0
-+/*
-+ * Copyright (C) 2005-2019 Junjiro R. Okajima
-+ *
-+ * This program, aufs is free software; you can redistribute it and/or modify
-+ * it under the terms of the GNU General Public License as published by
-+ * the Free Software Foundation; either version 2 of the License, or
-+ * (at your option) any later version.
-+ *
-+ * This program is distributed in the hope that it will be useful,
-+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
-+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
-+ * GNU General Public License for more details.
-+ *
-+ * You should have received a copy of the GNU General Public License
-+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
-+ */
-+
-+/*
-+ * copy-up functions, see wbr_policy.c for copy-down
-+ */
-+
-+#include <linux/fs_stack.h>
-+#include <linux/mm.h>
-+#include <linux/task_work.h>
-+#include "aufs.h"
-+
-+void au_cpup_attr_flags(struct inode *dst, unsigned int iflags)
-+{
-+ const unsigned int mask = S_DEAD | S_SWAPFILE | S_PRIVATE
-+ | S_NOATIME | S_NOCMTIME | S_AUTOMOUNT;
-+
-+ BUILD_BUG_ON(sizeof(iflags) != sizeof(dst->i_flags));
-+
-+ dst->i_flags |= iflags & ~mask;
-+ if (au_test_fs_notime(dst->i_sb))
-+ dst->i_flags |= S_NOATIME | S_NOCMTIME;
-+}
-+
-+void au_cpup_attr_timesizes(struct inode *inode)
-+{
-+ struct inode *h_inode;
-+
-+ h_inode = au_h_iptr(inode, au_ibtop(inode));
-+ fsstack_copy_attr_times(inode, h_inode);
-+ fsstack_copy_inode_size(inode, h_inode);
-+}
-+
-+void au_cpup_attr_nlink(struct inode *inode, int force)
-+{
-+ struct inode *h_inode;
-+ struct super_block *sb;
-+ aufs_bindex_t bindex, bbot;
-+
-+ sb = inode->i_sb;
-+ bindex = au_ibtop(inode);
-+ h_inode = au_h_iptr(inode, bindex);
-+ if (!force
-+ && !S_ISDIR(h_inode->i_mode)
-+ && au_opt_test(au_mntflags(sb), PLINK)
-+ && au_plink_test(inode))
-+ return;
-+
-+ /*
-+ * 0 can happen in revalidating.
-+ * h_inode->i_mutex may not be held here, but it is harmless since once
-+ * i_nlink reaches 0, it will never become positive except O_TMPFILE
-+ * case.
-+ * todo: O_TMPFILE+linkat(AT_SYMLINK_FOLLOW) bypassing aufs may cause
-+ * the incorrect link count.
-+ */
-+ set_nlink(inode, h_inode->i_nlink);
-+
-+ /*
-+ * fewer nlink makes find(1) noisy, but larger nlink doesn't.
-+ * it may includes whplink directory.
-+ */
-+ if (S_ISDIR(h_inode->i_mode)) {
-+ bbot = au_ibbot(inode);
-+ for (bindex++; bindex <= bbot; bindex++) {
-+ h_inode = au_h_iptr(inode, bindex);
-+ if (h_inode)
-+ au_add_nlink(inode, h_inode);
-+ }
-+ }
-+}
-+
-+void au_cpup_attr_changeable(struct inode *inode)
-+{
-+ struct inode *h_inode;
-+
-+ h_inode = au_h_iptr(inode, au_ibtop(inode));
-+ inode->i_mode = h_inode->i_mode;
-+ inode->i_uid = h_inode->i_uid;
-+ inode->i_gid = h_inode->i_gid;
-+ au_cpup_attr_timesizes(inode);
-+ au_cpup_attr_flags(inode, h_inode->i_flags);
-+}
-+
-+void au_cpup_igen(struct inode *inode, struct inode *h_inode)
-+{
-+ struct au_iinfo *iinfo = au_ii(inode);
-+
-+ IiMustWriteLock(inode);
-+
-+ iinfo->ii_higen = h_inode->i_generation;
-+ iinfo->ii_hsb1 = h_inode->i_sb;
-+}
-+
-+void au_cpup_attr_all(struct inode *inode, int force)
-+{
-+ struct inode *h_inode;
-+
-+ h_inode = au_h_iptr(inode, au_ibtop(inode));
-+ au_cpup_attr_changeable(inode);
-+ if (inode->i_nlink > 0)
-+ au_cpup_attr_nlink(inode, force);
-+ inode->i_rdev = h_inode->i_rdev;
-+ inode->i_blkbits = h_inode->i_blkbits;
-+ au_cpup_igen(inode, h_inode);
-+}
-+
-+/* ---------------------------------------------------------------------- */
-+
-+/* Note: dt_dentry and dt_h_dentry are not dget/dput-ed */
-+
-+/* keep the timestamps of the parent dir when cpup */
-+void au_dtime_store(struct au_dtime *dt, struct dentry *dentry,
-+ struct path *h_path)
-+{
-+ struct inode *h_inode;
-+
-+ dt->dt_dentry = dentry;
-+ dt->dt_h_path = *h_path;
-+ h_inode = d_inode(h_path->dentry);
-+ dt->dt_atime = h_inode->i_atime;
-+ dt->dt_mtime = h_inode->i_mtime;
-+ /* smp_mb(); */
-+}
-+
-+void au_dtime_revert(struct au_dtime *dt)
-+{
-+ struct iattr attr;
-+ int err;
-+
-+ attr.ia_atime = dt->dt_atime;
-+ attr.ia_mtime = dt->dt_mtime;
-+ attr.ia_valid = ATTR_FORCE | ATTR_MTIME | ATTR_MTIME_SET
-+ | ATTR_ATIME | ATTR_ATIME_SET;
-+
-+ /* no delegation since this is a directory */
-+ err = vfsub_notify_change(&dt->dt_h_path, &attr, /*delegated*/NULL);
-+ if (unlikely(err))
-+ pr_warn("restoring timestamps failed(%d). ignored\n", err);
-+}
-+
-+/* ---------------------------------------------------------------------- */
-+
-+/* internal use only */
-+struct au_cpup_reg_attr {
-+ int valid;
-+ struct kstat st;
-+ unsigned int iflags; /* inode->i_flags */
-+};
-+
-+static noinline_for_stack
-+int cpup_iattr(struct dentry *dst, aufs_bindex_t bindex, struct dentry *h_src,
-+ struct au_cpup_reg_attr *h_src_attr)
-+{
-+ int err, sbits, icex;
-+ unsigned int mnt_flags;
-+ unsigned char verbose;
-+ struct iattr ia;
-+ struct path h_path;
-+ struct inode *h_isrc, *h_idst;
-+ struct kstat *h_st;
-+ struct au_branch *br;
-+
-+ h_path.dentry = au_h_dptr(dst, bindex);
-+ h_idst = d_inode(h_path.dentry);
-+ br = au_sbr(dst->d_sb, bindex);
-+ h_path.mnt = au_br_mnt(br);
-+ h_isrc = d_inode(h_src);
-+ ia.ia_valid = ATTR_FORCE | ATTR_UID | ATTR_GID
-+ | ATTR_ATIME | ATTR_MTIME
-+ | ATTR_ATIME_SET | ATTR_MTIME_SET;
-+ if (h_src_attr && h_src_attr->valid) {
-+ h_st = &h_src_attr->st;
-+ ia.ia_uid = h_st->uid;
-+ ia.ia_gid = h_st->gid;
-+ ia.ia_atime = h_st->atime;
-+ ia.ia_mtime = h_st->mtime;
-+ if (h_idst->i_mode != h_st->mode
-+ && !S_ISLNK(h_idst->i_mode)) {
-+ ia.ia_valid |= ATTR_MODE;
-+ ia.ia_mode = h_st->mode;
-+ }
-+ sbits = !!(h_st->mode & (S_ISUID | S_ISGID));
-+ au_cpup_attr_flags(h_idst, h_src_attr->iflags);
-+ } else {
-+ ia.ia_uid = h_isrc->i_uid;
-+ ia.ia_gid = h_isrc->i_gid;
-+ ia.ia_atime = h_isrc->i_atime;
-+ ia.ia_mtime = h_isrc->i_mtime;
-+ if (h_idst->i_mode != h_isrc->i_mode
-+ && !S_ISLNK(h_idst->i_mode)) {
-+ ia.ia_valid |= ATTR_MODE;
-+ ia.ia_mode = h_isrc->i_mode;
-+ }
-+ sbits = !!(h_isrc->i_mode & (S_ISUID | S_ISGID));
-+ au_cpup_attr_flags(h_idst, h_isrc->i_flags);
-+ }
-+ /* no delegation since it is just created */
-+ err = vfsub_notify_change(&h_path, &ia, /*delegated*/NULL);
-+
-+ /* is this nfs only? */
-+ if (!err && sbits && au_test_nfs(h_path.dentry->d_sb)) {
-+ ia.ia_valid = ATTR_FORCE | ATTR_MODE;
-+ ia.ia_mode = h_isrc->i_mode;
-+ err = vfsub_notify_change(&h_path, &ia, /*delegated*/NULL);
-+ }
-+
-+ icex = br->br_perm & AuBrAttr_ICEX;
-+ if (!err) {
-+ mnt_flags = au_mntflags(dst->d_sb);
-+ verbose = !!au_opt_test(mnt_flags, VERBOSE);
-+ err = au_cpup_xattr(h_path.dentry, h_src, icex, verbose);
-+ }
-+
-+ return err;
-+}
-+
-+/* ---------------------------------------------------------------------- */
-+
-+static int au_do_copy_file(struct file *dst, struct file *src, loff_t len,
-+ char *buf, unsigned long blksize)
-+{
-+ int err;
-+ size_t sz, rbytes, wbytes;
-+ unsigned char all_zero;
-+ char *p, *zp;
-+ struct inode *h_inode;
-+ /* reduce stack usage */
-+ struct iattr *ia;
-+
-+ zp = page_address(ZERO_PAGE(0));
-+ if (unlikely(!zp))
-+ return -ENOMEM; /* possible? */
-+
-+ err = 0;
-+ all_zero = 0;
-+ while (len) {
-+ AuDbg("len %lld\n", len);
-+ sz = blksize;
-+ if (len < blksize)
-+ sz = len;
-+
-+ rbytes = 0;
-+ /* todo: signal_pending? */
-+ while (!rbytes || err == -EAGAIN || err == -EINTR) {
-+ rbytes = vfsub_read_k(src, buf, sz, &src->f_pos);
-+ err = rbytes;
-+ }
-+ if (unlikely(err < 0))
-+ break;
-+
-+ all_zero = 0;
-+ if (len >= rbytes && rbytes == blksize)
-+ all_zero = !memcmp(buf, zp, rbytes);
-+ if (!all_zero) {
-+ wbytes = rbytes;
-+ p = buf;
-+ while (wbytes) {
-+ size_t b;
-+
-+ b = vfsub_write_k(dst, p, wbytes, &dst->f_pos);
-+ err = b;
-+ /* todo: signal_pending? */
-+ if (unlikely(err == -EAGAIN || err == -EINTR))
-+ continue;
-+ if (unlikely(err < 0))
-+ break;
-+ wbytes -= b;
-+ p += b;
-+ }
-+ if (unlikely(err < 0))
-+ break;
-+ } else {
-+ loff_t res;
-+
-+ AuLabel(hole);
-+ res = vfsub_llseek(dst, rbytes, SEEK_CUR);
-+ err = res;
-+ if (unlikely(res < 0))
-+ break;
-+ }
-+ len -= rbytes;
-+ err = 0;
-+ }
-+
-+ /* the last block may be a hole */
-+ if (!err && all_zero) {
-+ AuLabel(last hole);
-+
-+ err = 1;
-+ if (au_test_nfs(dst->f_path.dentry->d_sb)) {
-+ /* nfs requires this step to make last hole */
-+ /* is this only nfs? */
-+ do {
-+ /* todo: signal_pending? */
-+ err = vfsub_write_k(dst, "\0", 1, &dst->f_pos);
-+ } while (err == -EAGAIN || err == -EINTR);
-+ if (err == 1)
-+ dst->f_pos--;
-+ }
-+
-+ if (err == 1) {
-+ ia = (void *)buf;
-+ ia->ia_size = dst->f_pos;
-+ ia->ia_valid = ATTR_SIZE | ATTR_FILE;
-+ ia->ia_file = dst;
-+ h_inode = file_inode(dst);
-+ inode_lock_nested(h_inode, AuLsc_I_CHILD2);
-+ /* no delegation since it is just created */
-+ err = vfsub_notify_change(&dst->f_path, ia,
-+ /*delegated*/NULL);
-+ inode_unlock(h_inode);
-+ }
-+ }
-+
-+ return err;
-+}
-+
-+int au_copy_file(struct file *dst, struct file *src, loff_t len)
-+{
-+ int err;
-+ unsigned long blksize;
-+ unsigned char do_kfree;
-+ char *buf;
-+ struct super_block *h_sb;
-+
-+ err = -ENOMEM;
-+ h_sb = file_inode(dst)->i_sb;
-+ blksize = h_sb->s_blocksize;
-+ if (!blksize || PAGE_SIZE < blksize)
-+ blksize = PAGE_SIZE;
-+ AuDbg("blksize %lu\n", blksize);
-+ do_kfree = (blksize != PAGE_SIZE && blksize >= sizeof(struct iattr *));
-+ if (do_kfree)
-+ buf = kmalloc(blksize, GFP_NOFS);
-+ else
-+ buf = (void *)__get_free_page(GFP_NOFS);
-+ if (unlikely(!buf))
-+ goto out;
-+
-+ if (len > (1 << 22))
-+ AuDbg("copying a large file %lld\n", (long long)len);
-+
-+ src->f_pos = 0;
-+ dst->f_pos = 0;
-+ err = au_do_copy_file(dst, src, len, buf, blksize);
-+ if (do_kfree) {
-+ AuDebugOn(!au_kfree_do_sz_test(blksize));
-+ au_kfree_do_rcu(buf);
-+ } else
-+ free_page((unsigned long)buf);
-+
-+out:
-+ return err;
-+}
-+
-+static int au_do_copy(struct file *dst, struct file *src, loff_t len)
-+{
-+ int err;
-+ struct super_block *h_src_sb;
-+ struct inode *h_src_inode;
-+
-+ h_src_inode = file_inode(src);
-+ h_src_sb = h_src_inode->i_sb;
-+
-+ /* XFS acquires inode_lock */
-+ if (!au_test_xfs(h_src_sb))
-+ err = au_copy_file(dst, src, len);
-+ else {
-+ inode_unlock_shared(h_src_inode);
-+ err = au_copy_file(dst, src, len);
-+ inode_lock_shared_nested(h_src_inode, AuLsc_I_CHILD);
-+ }
-+
-+ return err;
-+}
-+
-+static int au_clone_or_copy(struct file *dst, struct file *src, loff_t len)
-+{
-+ int err;
-+ loff_t lo;
-+ struct super_block *h_src_sb;
-+ struct inode *h_src_inode;
-+
-+ h_src_inode = file_inode(src);
-+ h_src_sb = h_src_inode->i_sb;
-+ if (h_src_sb != file_inode(dst)->i_sb
-+ || !dst->f_op->remap_file_range) {
-+ err = au_do_copy(dst, src, len);
-+ goto out;
-+ }
-+
-+ if (!au_test_nfs(h_src_sb)) {
-+ inode_unlock_shared(h_src_inode);
-+ lo = vfsub_clone_file_range(src, dst, len);
-+ inode_lock_shared_nested(h_src_inode, AuLsc_I_CHILD);
-+ } else
-+ lo = vfsub_clone_file_range(src, dst, len);
-+ if (lo == len) {
-+ err = 0;
-+ goto out; /* success */
-+ } else if (lo >= 0)
-+ /* todo: possible? */
-+ /* paritially succeeded */
-+ AuDbg("lo %lld, len %lld. Retrying.\n", lo, len);
-+ else if (lo != -EOPNOTSUPP) {
-+ /* older XFS has a condition in cloning */
-+ err = lo;
-+ goto out;
-+ }
-+
-+ /* the backend fs on NFS may not support cloning */
-+ err = au_do_copy(dst, src, len);
-+
-+out:
-+ AuTraceErr(err);
-+ return err;
-+}
-+
-+/*
-+ * to support a sparse file which is opened with O_APPEND,
-+ * we need to close the file.
-+ */
-+static int au_cp_regular(struct au_cp_generic *cpg)
-+{
-+ int err, i;
-+ enum { SRC, DST };
-+ struct {
-+ aufs_bindex_t bindex;
-+ unsigned int flags;
-+ struct dentry *dentry;
-+ int force_wr;
-+ struct file *file;
-+ } *f, file[] = {
-+ {
-+ .bindex = cpg->bsrc,
-+ .flags = O_RDONLY | O_NOATIME | O_LARGEFILE,
-+ },
-+ {
-+ .bindex = cpg->bdst,
-+ .flags = O_WRONLY | O_NOATIME | O_LARGEFILE,
-+ .force_wr = !!au_ftest_cpup(cpg->flags, RWDST),
-+ }
-+ };
-+ struct au_branch *br;
-+ struct super_block *sb, *h_src_sb;
-+ struct inode *h_src_inode;
-+ struct task_struct *tsk = current;
-+
-+ /* bsrc branch can be ro/rw. */
-+ sb = cpg->dentry->d_sb;
-+ f = file;
-+ for (i = 0; i < 2; i++, f++) {
-+ f->dentry = au_h_dptr(cpg->dentry, f->bindex);
-+ f->file = au_h_open(cpg->dentry, f->bindex, f->flags,
-+ /*file*/NULL, f->force_wr);
-+ if (IS_ERR(f->file)) {
-+ err = PTR_ERR(f->file);
-+ if (i == SRC)
-+ goto out;
-+ else
-+ goto out_src;
-+ }
-+ }
-+
-+ /* try stopping to update while we copyup */
-+ h_src_inode = d_inode(file[SRC].dentry);
-+ h_src_sb = h_src_inode->i_sb;
-+ if (!au_test_nfs(h_src_sb))
-+ IMustLock(h_src_inode);
-+ err = au_clone_or_copy(file[DST].file, file[SRC].file, cpg->len);
-+
-+ /* i wonder if we had O_NO_DELAY_FPUT flag */
-+ if (tsk->flags & PF_KTHREAD)
-+ __fput_sync(file[DST].file);
-+ else {
-+ /* it happened actually */
-+ fput(file[DST].file);
-+ /*
-+ * too bad.
-+ * we have to call both since we don't know which place the file
-+ * was added to.
-+ */
-+ task_work_run();
-+ flush_delayed_fput();
-+ }
-+ br = au_sbr(sb, file[DST].bindex);
-+ au_lcnt_dec(&br->br_nfiles);
-+
-+out_src:
-+ fput(file[SRC].file);
-+ br = au_sbr(sb, file[SRC].bindex);
-+ au_lcnt_dec(&br->br_nfiles);
-+out:
-+ return err;
-+}
-+
-+static int au_do_cpup_regular(struct au_cp_generic *cpg,
-+ struct au_cpup_reg_attr *h_src_attr)
-+{
-+ int err, rerr;
-+ loff_t l;
-+ struct path h_path;
-+ struct inode *h_src_inode, *h_dst_inode;
-+
-+ err = 0;
-+ h_src_inode = au_h_iptr(d_inode(cpg->dentry), cpg->bsrc);
-+ l = i_size_read(h_src_inode);
-+ if (cpg->len == -1 || l < cpg->len)
-+ cpg->len = l;
-+ if (cpg->len) {
-+ /* try stopping to update while we are referencing */
-+ inode_lock_shared_nested(h_src_inode, AuLsc_I_CHILD);
-+ au_pin_hdir_unlock(cpg->pin);
-+
-+ h_path.dentry = au_h_dptr(cpg->dentry, cpg->bsrc);
-+ h_path.mnt = au_sbr_mnt(cpg->dentry->d_sb, cpg->bsrc);
-+ h_src_attr->iflags = h_src_inode->i_flags;
-+ if (!au_test_nfs(h_src_inode->i_sb))
-+ err = vfsub_getattr(&h_path, &h_src_attr->st);
-+ else {
-+ inode_unlock_shared(h_src_inode);
-+ err = vfsub_getattr(&h_path, &h_src_attr->st);
-+ inode_lock_shared_nested(h_src_inode, AuLsc_I_CHILD);
-+ }
-+ if (unlikely(err)) {
-+ inode_unlock_shared(h_src_inode);
-+ goto out;
-+ }
-+ h_src_attr->valid = 1;
-+ if (!au_test_nfs(h_src_inode->i_sb)) {
-+ err = au_cp_regular(cpg);
-+ inode_unlock_shared(h_src_inode);
-+ } else {
-+ inode_unlock_shared(h_src_inode);
-+ err = au_cp_regular(cpg);
-+ }
-+ rerr = au_pin_hdir_relock(cpg->pin);
-+ if (!err && rerr)
-+ err = rerr;
-+ }
-+ if (!err && (h_src_inode->i_state & I_LINKABLE)) {
-+ h_path.dentry = au_h_dptr(cpg->dentry, cpg->bdst);
-+ h_dst_inode = d_inode(h_path.dentry);
-+ spin_lock(&h_dst_inode->i_lock);
-+ h_dst_inode->i_state |= I_LINKABLE;
-+ spin_unlock(&h_dst_inode->i_lock);
-+ }
-+
-+out:
-+ return err;
-+}
-+
-+static int au_do_cpup_symlink(struct path *h_path, struct dentry *h_src,
-+ struct inode *h_dir)
-+{
-+ int err, symlen;
-+ mm_segment_t old_fs;
-+ union {
-+ char *k;
-+ char __user *u;
-+ } sym;
-+
-+ err = -ENOMEM;
-+ sym.k = (void *)__get_free_page(GFP_NOFS);
-+ if (unlikely(!sym.k))
-+ goto out;
-+
-+ /* unnecessary to support mmap_sem since symlink is not mmap-able */
-+ old_fs = get_fs();
-+ set_fs(KERNEL_DS);
-+ symlen = vfs_readlink(h_src, sym.u, PATH_MAX);
-+ err = symlen;
-+ set_fs(old_fs);
-+
-+ if (symlen > 0) {
-+ sym.k[symlen] = 0;
-+ err = vfsub_symlink(h_dir, h_path, sym.k);
-+ }
-+ free_page((unsigned long)sym.k);
-+
-+out:
-+ return err;
-+}
-+
-+/*
-+ * regardless 'acl' option, reset all ACL.
-+ * All ACL will be copied up later from the original entry on the lower branch.
-+ */
-+static int au_reset_acl(struct inode *h_dir, struct path *h_path, umode_t mode)
-+{
-+ int err;
-+ struct dentry *h_dentry;
-+ struct inode *h_inode;
-+
-+ h_dentry = h_path->dentry;
-+ h_inode = d_inode(h_dentry);
-+ /* forget_all_cached_acls(h_inode)); */
-+ err = vfsub_removexattr(h_dentry, XATTR_NAME_POSIX_ACL_ACCESS);
-+ AuTraceErr(err);
-+ if (err == -EOPNOTSUPP)
-+ err = 0;
-+ if (!err)
-+ err = vfsub_acl_chmod(h_inode, mode);
-+
-+ AuTraceErr(err);
-+ return err;
-+}
-+
-+static int au_do_cpup_dir(struct au_cp_generic *cpg, struct dentry *dst_parent,
-+ struct inode *h_dir, struct path *h_path)
-+{
-+ int err;
-+ struct inode *dir, *inode;
-+
-+ err = vfsub_removexattr(h_path->dentry, XATTR_NAME_POSIX_ACL_DEFAULT);
-+ AuTraceErr(err);
-+ if (err == -EOPNOTSUPP)
-+ err = 0;
-+ if (unlikely(err))
-+ goto out;
-+
-+ /*
-+ * strange behaviour from the users view,
-+ * particularly setattr case
-+ */
-+ dir = d_inode(dst_parent);
-+ if (au_ibtop(dir) == cpg->bdst)
-+ au_cpup_attr_nlink(dir, /*force*/1);
-+ inode = d_inode(cpg->dentry);
-+ au_cpup_attr_nlink(inode, /*force*/1);
-+
-+out:
-+ return err;
-+}
-+
-+static noinline_for_stack
-+int cpup_entry(struct au_cp_generic *cpg, struct dentry *dst_parent,
-+ struct au_cpup_reg_attr *h_src_attr)
-+{
-+ int err;
-+ umode_t mode;
-+ unsigned int mnt_flags;
-+ unsigned char isdir, isreg, force;
-+ const unsigned char do_dt = !!au_ftest_cpup(cpg->flags, DTIME);
-+ struct au_dtime dt;
-+ struct path h_path;
-+ struct dentry *h_src, *h_dst, *h_parent;
-+ struct inode *h_inode, *h_dir;
-+ struct super_block *sb;
-+
-+ /* bsrc branch can be ro/rw. */
-+ h_src = au_h_dptr(cpg->dentry, cpg->bsrc);
-+ h_inode = d_inode(h_src);
-+ AuDebugOn(h_inode != au_h_iptr(d_inode(cpg->dentry), cpg->bsrc));
-+
-+ /* try stopping to be referenced while we are creating */
-+ h_dst = au_h_dptr(cpg->dentry, cpg->bdst);
-+ if (au_ftest_cpup(cpg->flags, RENAME))
-+ AuDebugOn(strncmp(h_dst->d_name.name, AUFS_WH_PFX,
-+ AUFS_WH_PFX_LEN));
-+ h_parent = h_dst->d_parent; /* dir inode is locked */
-+ h_dir = d_inode(h_parent);
-+ IMustLock(h_dir);
-+ AuDebugOn(h_parent != h_dst->d_parent);
-+
-+ sb = cpg->dentry->d_sb;
-+ h_path.mnt = au_sbr_mnt(sb, cpg->bdst);
-+ if (do_dt) {
-+ h_path.dentry = h_parent;
-+ au_dtime_store(&dt, dst_parent, &h_path);
-+ }
-+ h_path.dentry = h_dst;
-+
-+ isreg = 0;
-+ isdir = 0;
-+ mode = h_inode->i_mode;
-+ switch (mode & S_IFMT) {
-+ case S_IFREG:
-+ isreg = 1;
-+ err = vfsub_create(h_dir, &h_path, 0600, /*want_excl*/true);
-+ if (!err)
-+ err = au_do_cpup_regular(cpg, h_src_attr);
-+ break;
-+ case S_IFDIR:
-+ isdir = 1;
-+ err = vfsub_mkdir(h_dir, &h_path, mode);
-+ if (!err)
-+ err = au_do_cpup_dir(cpg, dst_parent, h_dir, &h_path);
-+ break;
-+ case S_IFLNK:
-+ err = au_do_cpup_symlink(&h_path, h_src, h_dir);
-+ break;
-+ case S_IFCHR:
-+ case S_IFBLK:
-+ AuDebugOn(!capable(CAP_MKNOD));
-+ /*FALLTHROUGH*/
-+ case S_IFIFO:
-+ case S_IFSOCK:
-+ err = vfsub_mknod(h_dir, &h_path, mode, h_inode->i_rdev);
-+ break;
-+ default:
-+ AuIOErr("Unknown inode type 0%o\n", mode);
-+ err = -EIO;
-+ }
-+ if (!err)
-+ err = au_reset_acl(h_dir, &h_path, mode);
-+
-+ mnt_flags = au_mntflags(sb);
-+ if (!au_opt_test(mnt_flags, UDBA_NONE)
-+ && !isdir
-+ && au_opt_test(mnt_flags, XINO)
-+ && (h_inode->i_nlink == 1
-+ || (h_inode->i_state & I_LINKABLE))
-+ /* todo: unnecessary? */
-+ /* && d_inode(cpg->dentry)->i_nlink == 1 */
-+ && cpg->bdst < cpg->bsrc
-+ && !au_ftest_cpup(cpg->flags, KEEPLINO))
-+ au_xino_write(sb, cpg->bsrc, h_inode->i_ino, /*ino*/0);
-+ /* ignore this error */
-+
-+ if (!err) {
-+ force = 0;
-+ if (isreg) {
-+ force = !!cpg->len;
-+ if (cpg->len == -1)
-+ force = !!i_size_read(h_inode);
-+ }
-+ au_fhsm_wrote(sb, cpg->bdst, force);
-+ }
-+
-+ if (do_dt)
-+ au_dtime_revert(&dt);
-+ return err;
-+}
-+
-+static int au_do_ren_after_cpup(struct au_cp_generic *cpg, struct path *h_path)
-+{
-+ int err;
-+ struct dentry *dentry, *h_dentry, *h_parent, *parent;
-+ struct inode *h_dir;
-+ aufs_bindex_t bdst;
-+
-+ dentry = cpg->dentry;
-+ bdst = cpg->bdst;
-+ h_dentry = au_h_dptr(dentry, bdst);
-+ if (!au_ftest_cpup(cpg->flags, OVERWRITE)) {
-+ dget(h_dentry);
-+ au_set_h_dptr(dentry, bdst, NULL);
-+ err = au_lkup_neg(dentry, bdst, /*wh*/0);
-+ if (!err)
-+ h_path->dentry = dget(au_h_dptr(dentry, bdst));
-+ au_set_h_dptr(dentry, bdst, h_dentry);
-+ } else {
-+ err = 0;
-+ parent = dget_parent(dentry);
-+ h_parent = au_h_dptr(parent, bdst);
-+ dput(parent);
-+ h_path->dentry = vfsub_lkup_one(&dentry->d_name, h_parent);
-+ if (IS_ERR(h_path->dentry))
-+ err = PTR_ERR(h_path->dentry);
-+ }
-+ if (unlikely(err))
-+ goto out;
-+
-+ h_parent = h_dentry->d_parent; /* dir inode is locked */
-+ h_dir = d_inode(h_parent);
-+ IMustLock(h_dir);
-+ AuDbg("%pd %pd\n", h_dentry, h_path->dentry);
-+ /* no delegation since it is just created */
-+ err = vfsub_rename(h_dir, h_dentry, h_dir, h_path, /*delegated*/NULL,
-+ /*flags*/0);
-+ dput(h_path->dentry);
-+
-+out:
-+ return err;
-+}
-+
-+/*
-+ * copyup the @dentry from @bsrc to @bdst.
-+ * the caller must set the both of lower dentries.
-+ * @len is for truncating when it is -1 copyup the entire file.
-+ * in link/rename cases, @dst_parent may be different from the real one.
-+ * basic->bsrc can be larger than basic->bdst.
-+ * aufs doesn't touch the credential so
-+ * security_inode_copy_up{,_xattr}() are unnecessary.
-+ */
-+static int au_cpup_single(struct au_cp_generic *cpg, struct dentry *dst_parent)
-+{
-+ int err, rerr;
-+ aufs_bindex_t old_ibtop;
-+ unsigned char isdir, plink;
-+ struct dentry *h_src, *h_dst, *h_parent;
-+ struct inode *dst_inode, *h_dir, *inode, *delegated, *src_inode;
-+ struct super_block *sb;
-+ struct au_branch *br;
-+ /* to reduce stack size */
-+ struct {
-+ struct au_dtime dt;
-+ struct path h_path;
-+ struct au_cpup_reg_attr h_src_attr;
-+ } *a;
-+
-+ err = -ENOMEM;
-+ a = kmalloc(sizeof(*a), GFP_NOFS);
-+ if (unlikely(!a))
-+ goto out;
-+ a->h_src_attr.valid = 0;
-+
-+ sb = cpg->dentry->d_sb;
-+ br = au_sbr(sb, cpg->bdst);
-+ a->h_path.mnt = au_br_mnt(br);
-+ h_dst = au_h_dptr(cpg->dentry, cpg->bdst);
-+ h_parent = h_dst->d_parent; /* dir inode is locked */
-+ h_dir = d_inode(h_parent);
-+ IMustLock(h_dir);
-+
-+ h_src = au_h_dptr(cpg->dentry, cpg->bsrc);
-+ inode = d_inode(cpg->dentry);
-+
-+ if (!dst_parent)
-+ dst_parent = dget_parent(cpg->dentry);
-+ else
-+ dget(dst_parent);
-+
-+ plink = !!au_opt_test(au_mntflags(sb), PLINK);
-+ dst_inode = au_h_iptr(inode, cpg->bdst);
-+ if (dst_inode) {
-+ if (unlikely(!plink)) {
-+ err = -EIO;
-+ AuIOErr("hi%lu(i%lu) exists on b%d "
-+ "but plink is disabled\n",
-+ dst_inode->i_ino, inode->i_ino, cpg->bdst);
-+ goto out_parent;
-+ }
-+
-+ if (dst_inode->i_nlink) {
-+ const int do_dt = au_ftest_cpup(cpg->flags, DTIME);
-+
-+ h_src = au_plink_lkup(inode, cpg->bdst);
-+ err = PTR_ERR(h_src);
-+ if (IS_ERR(h_src))
-+ goto out_parent;
-+ if (unlikely(d_is_negative(h_src))) {
-+ err = -EIO;
-+ AuIOErr("i%lu exists on b%d "
-+ "but not pseudo-linked\n",
-+ inode->i_ino, cpg->bdst);
-+ dput(h_src);
-+ goto out_parent;
-+ }
-+
-+ if (do_dt) {
-+ a->h_path.dentry = h_parent;
-+ au_dtime_store(&a->dt, dst_parent, &a->h_path);
-+ }
-+
-+ a->h_path.dentry = h_dst;
-+ delegated = NULL;
-+ err = vfsub_link(h_src, h_dir, &a->h_path, &delegated);
-+ if (!err && au_ftest_cpup(cpg->flags, RENAME))
-+ err = au_do_ren_after_cpup(cpg, &a->h_path);
-+ if (do_dt)
-+ au_dtime_revert(&a->dt);
-+ if (unlikely(err == -EWOULDBLOCK)) {
-+ pr_warn("cannot retry for NFSv4 delegation"
-+ " for an internal link\n");
-+ iput(delegated);
-+ }
-+ dput(h_src);
-+ goto out_parent;
-+ } else
-+ /* todo: cpup_wh_file? */
-+ /* udba work */
-+ au_update_ibrange(inode, /*do_put_zero*/1);
-+ }
-+
-+ isdir = S_ISDIR(inode->i_mode);
-+ old_ibtop = au_ibtop(inode);
-+ err = cpup_entry(cpg, dst_parent, &a->h_src_attr);
-+ if (unlikely(err))
-+ goto out_rev;
-+ dst_inode = d_inode(h_dst);
-+ inode_lock_nested(dst_inode, AuLsc_I_CHILD2);
-+ /* todo: necessary? */
-+ /* au_pin_hdir_unlock(cpg->pin); */
-+
-+ err = cpup_iattr(cpg->dentry, cpg->bdst, h_src, &a->h_src_attr);
-+ if (unlikely(err)) {
-+ /* todo: necessary? */
-+ /* au_pin_hdir_relock(cpg->pin); */ /* ignore an error */
-+ inode_unlock(dst_inode);
-+ goto out_rev;
-+ }
-+
-+ if (cpg->bdst < old_ibtop) {
-+ if (S_ISREG(inode->i_mode)) {
-+ err = au_dy_iaop(inode, cpg->bdst, dst_inode);
-+ if (unlikely(err)) {
-+ /* ignore an error */
-+ /* au_pin_hdir_relock(cpg->pin); */
-+ inode_unlock(dst_inode);
-+ goto out_rev;
-+ }
-+ }
-+ au_set_ibtop(inode, cpg->bdst);
-+ } else
-+ au_set_ibbot(inode, cpg->bdst);
-+ au_set_h_iptr(inode, cpg->bdst, au_igrab(dst_inode),
-+ au_hi_flags(inode, isdir));
-+
-+ /* todo: necessary? */
-+ /* err = au_pin_hdir_relock(cpg->pin); */
-+ inode_unlock(dst_inode);
-+ if (unlikely(err))
-+ goto out_rev;
-+
-+ src_inode = d_inode(h_src);
-+ if (!isdir
-+ && (src_inode->i_nlink > 1
-+ || src_inode->i_state & I_LINKABLE)
-+ && plink)
-+ au_plink_append(inode, cpg->bdst, h_dst);
-+
-+ if (au_ftest_cpup(cpg->flags, RENAME)) {
-+ a->h_path.dentry = h_dst;
-+ err = au_do_ren_after_cpup(cpg, &a->h_path);
-+ }
-+ if (!err)
-+ goto out_parent; /* success */
-+
-+ /* revert */
-+out_rev:
-+ a->h_path.dentry = h_parent;
-+ au_dtime_store(&a->dt, dst_parent, &a->h_path);
-+ a->h_path.dentry = h_dst;
-+ rerr = 0;
-+ if (d_is_positive(h_dst)) {
-+ if (!isdir) {
-+ /* no delegation since it is just created */
-+ rerr = vfsub_unlink(h_dir, &a->h_path,
-+ /*delegated*/NULL, /*force*/0);
-+ } else
-+ rerr = vfsub_rmdir(h_dir, &a->h_path);
-+ }
-+ au_dtime_revert(&a->dt);
-+ if (rerr) {
-+ AuIOErr("failed removing broken entry(%d, %d)\n", err, rerr);
-+ err = -EIO;
-+ }
-+out_parent:
-+ dput(dst_parent);
-+ au_kfree_rcu(a);
-+out:
-+ return err;
-+}
-+
-+#if 0 /* reserved */
-+struct au_cpup_single_args {
-+ int *errp;
-+ struct au_cp_generic *cpg;
-+ struct dentry *dst_parent;
-+};
-+
-+static void au_call_cpup_single(void *args)
-+{
-+ struct au_cpup_single_args *a = args;
-+
-+ au_pin_hdir_acquire_nest(a->cpg->pin);
-+ *a->errp = au_cpup_single(a->cpg, a->dst_parent);
-+ au_pin_hdir_release(a->cpg->pin);
-+}
-+#endif
-+
-+/*
-+ * prevent SIGXFSZ in copy-up.
-+ * testing CAP_MKNOD is for generic fs,
-+ * but CAP_FSETID is for xfs only, currently.
-+ */
-+static int au_cpup_sio_test(struct au_pin *pin, umode_t mode)
-+{
-+ int do_sio;
-+ struct super_block *sb;
-+ struct inode *h_dir;
-+
-+ do_sio = 0;
-+ sb = au_pinned_parent(pin)->d_sb;
-+ if (!au_wkq_test()
-+ && (!au_sbi(sb)->si_plink_maint_pid
-+ || au_plink_maint(sb, AuLock_NOPLM))) {
-+ switch (mode & S_IFMT) {
-+ case S_IFREG:
-+ /* no condition about RLIMIT_FSIZE and the file size */
-+ do_sio = 1;
-+ break;
-+ case S_IFCHR:
-+ case S_IFBLK:
-+ do_sio = !capable(CAP_MKNOD);
-+ break;
-+ }
-+ if (!do_sio)
-+ do_sio = ((mode & (S_ISUID | S_ISGID))
-+ && !capable(CAP_FSETID));
-+ /* this workaround may be removed in the future */
-+ if (!do_sio) {
-+ h_dir = au_pinned_h_dir(pin);
-+ do_sio = h_dir->i_mode & S_ISVTX;
-+ }
-+ }
-+
-+ return do_sio;
-+}
-+
-+#if 0 /* reserved */
-+int au_sio_cpup_single(struct au_cp_generic *cpg, struct dentry *dst_parent)
-+{
-+ int err, wkq_err;
-+ struct dentry *h_dentry;
-+
-+ h_dentry = au_h_dptr(cpg->dentry, cpg->bsrc);
-+ if (!au_cpup_sio_test(pin, d_inode(h_dentry)->i_mode))
-+ err = au_cpup_single(cpg, dst_parent);
-+ else {
-+ struct au_cpup_single_args args = {
-+ .errp = &err,
-+ .cpg = cpg,
-+ .dst_parent = dst_parent
-+ };
-+ wkq_err = au_wkq_wait(au_call_cpup_single, &args);
-+ if (unlikely(wkq_err))
-+ err = wkq_err;
-+ }
-+
-+ return err;
-+}
-+#endif
-+
-+/*
-+ * copyup the @dentry from the first active lower branch to @bdst,
-+ * using au_cpup_single().
-+ */
-+static int au_cpup_simple(struct au_cp_generic *cpg)
-+{
-+ int err;
-+ unsigned int flags_orig;
-+ struct dentry *dentry;
-+
-+ AuDebugOn(cpg->bsrc < 0);
-+
-+ dentry = cpg->dentry;
-+ DiMustWriteLock(dentry);
-+
-+ err = au_lkup_neg(dentry, cpg->bdst, /*wh*/1);
-+ if (!err) {
-+ flags_orig = cpg->flags;
-+ au_fset_cpup(cpg->flags, RENAME);
-+ err = au_cpup_single(cpg, NULL);
-+ cpg->flags = flags_orig;
-+ if (!err)
-+ return 0; /* success */
-+
-+ /* revert */
-+ au_set_h_dptr(dentry, cpg->bdst, NULL);
-+ au_set_dbtop(dentry, cpg->bsrc);
-+ }
-+
-+ return err;
-+}
-+
-+struct au_cpup_simple_args {
-+ int *errp;
-+ struct au_cp_generic *cpg;
-+};
-+
-+static void au_call_cpup_simple(void *args)
-+{
-+ struct au_cpup_simple_args *a = args;
-+
-+ au_pin_hdir_acquire_nest(a->cpg->pin);
-+ *a->errp = au_cpup_simple(a->cpg);
-+ au_pin_hdir_release(a->cpg->pin);
-+}
-+
-+static int au_do_sio_cpup_simple(struct au_cp_generic *cpg)
-+{
-+ int err, wkq_err;
-+ struct dentry *dentry, *parent;
-+ struct file *h_file;
-+ struct inode *h_dir;
-+
-+ dentry = cpg->dentry;
-+ h_file = NULL;
-+ if (au_ftest_cpup(cpg->flags, HOPEN)) {
-+ AuDebugOn(cpg->bsrc < 0);
-+ h_file = au_h_open_pre(dentry, cpg->bsrc, /*force_wr*/0);
-+ err = PTR_ERR(h_file);
-+ if (IS_ERR(h_file))
-+ goto out;
-+ }
-+
-+ parent = dget_parent(dentry);
-+ h_dir = au_h_iptr(d_inode(parent), cpg->bdst);
-+ if (!au_test_h_perm_sio(h_dir, MAY_EXEC | MAY_WRITE)
-+ && !au_cpup_sio_test(cpg->pin, d_inode(dentry)->i_mode))
-+ err = au_cpup_simple(cpg);
-+ else {
-+ struct au_cpup_simple_args args = {
-+ .errp = &err,
-+ .cpg = cpg
-+ };
-+ wkq_err = au_wkq_wait(au_call_cpup_simple, &args);
-+ if (unlikely(wkq_err))
-+ err = wkq_err;
-+ }
-+
-+ dput(parent);
-+ if (h_file)
-+ au_h_open_post(dentry, cpg->bsrc, h_file);
-+
-+out:
-+ return err;
-+}
-+
-+int au_sio_cpup_simple(struct au_cp_generic *cpg)
-+{
-+ aufs_bindex_t bsrc, bbot;
-+ struct dentry *dentry, *h_dentry;
-+
-+ if (cpg->bsrc < 0) {
-+ dentry = cpg->dentry;
-+ bbot = au_dbbot(dentry);
-+ for (bsrc = cpg->bdst + 1; bsrc <= bbot; bsrc++) {
-+ h_dentry = au_h_dptr(dentry, bsrc);
-+ if (h_dentry) {
-+ AuDebugOn(d_is_negative(h_dentry));
-+ break;
-+ }
-+ }
-+ AuDebugOn(bsrc > bbot);
-+ cpg->bsrc = bsrc;
-+ }
-+ AuDebugOn(cpg->bsrc <= cpg->bdst);
-+ return au_do_sio_cpup_simple(cpg);
-+}
-+
-+int au_sio_cpdown_simple(struct au_cp_generic *cpg)
-+{
-+ AuDebugOn(cpg->bdst <= cpg->bsrc);
-+ return au_do_sio_cpup_simple(cpg);
-+}
-+
-+/* ---------------------------------------------------------------------- */
-+
-+/*
-+ * copyup the deleted file for writing.
-+ */
-+static int au_do_cpup_wh(struct au_cp_generic *cpg, struct dentry *wh_dentry,
-+ struct file *file)
-+{
-+ int err;
-+ unsigned int flags_orig;
-+ aufs_bindex_t bsrc_orig;
-+ struct au_dinfo *dinfo;
-+ struct {
-+ struct au_hdentry *hd;
-+ struct dentry *h_dentry;
-+ } hdst, hsrc;
-+
-+ dinfo = au_di(cpg->dentry);
-+ AuRwMustWriteLock(&dinfo->di_rwsem);
-+
-+ bsrc_orig = cpg->bsrc;
-+ cpg->bsrc = dinfo->di_btop;
-+ hdst.hd = au_hdentry(dinfo, cpg->bdst);
-+ hdst.h_dentry = hdst.hd->hd_dentry;
-+ hdst.hd->hd_dentry = wh_dentry;
-+ dinfo->di_btop = cpg->bdst;
-+
-+ hsrc.h_dentry = NULL;
-+ if (file) {
-+ hsrc.hd = au_hdentry(dinfo, cpg->bsrc);
-+ hsrc.h_dentry = hsrc.hd->hd_dentry;
-+ hsrc.hd->hd_dentry = au_hf_top(file)->f_path.dentry;
-+ }
-+ flags_orig = cpg->flags;
-+ cpg->flags = !AuCpup_DTIME;
-+ err = au_cpup_single(cpg, /*h_parent*/NULL);
-+ cpg->flags = flags_orig;
-+ if (file) {
-+ if (!err)
-+ err = au_reopen_nondir(file);
-+ hsrc.hd->hd_dentry = hsrc.h_dentry;
-+ }
-+ hdst.hd->hd_dentry = hdst.h_dentry;
-+ dinfo->di_btop = cpg->bsrc;
-+ cpg->bsrc = bsrc_orig;
-+
-+ return err;
-+}
-+
-+static int au_cpup_wh(struct au_cp_generic *cpg, struct file *file)
-+{
-+ int err;
-+ aufs_bindex_t bdst;
-+ struct au_dtime dt;
-+ struct dentry *dentry, *parent, *h_parent, *wh_dentry;
-+ struct au_branch *br;
-+ struct path h_path;
-+
-+ dentry = cpg->dentry;
-+ bdst = cpg->bdst;
-+ br = au_sbr(dentry->d_sb, bdst);
-+ parent = dget_parent(dentry);
-+ h_parent = au_h_dptr(parent, bdst);
-+ wh_dentry = au_whtmp_lkup(h_parent, br, &dentry->d_name);
-+ err = PTR_ERR(wh_dentry);
-+ if (IS_ERR(wh_dentry))
-+ goto out;
-+
-+ h_path.dentry = h_parent;
-+ h_path.mnt = au_br_mnt(br);
-+ au_dtime_store(&dt, parent, &h_path);
-+ err = au_do_cpup_wh(cpg, wh_dentry, file);
-+ if (unlikely(err))
-+ goto out_wh;
-+
-+ dget(wh_dentry);
-+ h_path.dentry = wh_dentry;
-+ if (!d_is_dir(wh_dentry)) {
-+ /* no delegation since it is just created */
-+ err = vfsub_unlink(d_inode(h_parent), &h_path,
-+ /*delegated*/NULL, /*force*/0);
-+ } else
-+ err = vfsub_rmdir(d_inode(h_parent), &h_path);
-+ if (unlikely(err)) {
-+ AuIOErr("failed remove copied-up tmp file %pd(%d)\n",
-+ wh_dentry, err);
-+ err = -EIO;
-+ }
-+ au_dtime_revert(&dt);
-+ au_set_hi_wh(d_inode(dentry), bdst, wh_dentry);
-+
-+out_wh:
-+ dput(wh_dentry);
-+out:
-+ dput(parent);
-+ return err;
-+}
-+
-+struct au_cpup_wh_args {
-+ int *errp;
-+ struct au_cp_generic *cpg;
-+ struct file *file;
-+};
-+
-+static void au_call_cpup_wh(void *args)
-+{
-+ struct au_cpup_wh_args *a = args;
-+
-+ au_pin_hdir_acquire_nest(a->cpg->pin);
-+ *a->errp = au_cpup_wh(a->cpg, a->file);
-+ au_pin_hdir_release(a->cpg->pin);
-+}
-+
-+int au_sio_cpup_wh(struct au_cp_generic *cpg, struct file *file)
-+{
-+ int err, wkq_err;
-+ aufs_bindex_t bdst;
-+ struct dentry *dentry, *parent, *h_orph, *h_parent;
-+ struct inode *dir, *h_dir, *h_tmpdir;
-+ struct au_wbr *wbr;
-+ struct au_pin wh_pin, *pin_orig;
-+
-+ dentry = cpg->dentry;
-+ bdst = cpg->bdst;
-+ parent = dget_parent(dentry);
-+ dir = d_inode(parent);
-+ h_orph = NULL;
-+ h_parent = NULL;
-+ h_dir = au_igrab(au_h_iptr(dir, bdst));
-+ h_tmpdir = h_dir;
-+ pin_orig = NULL;
-+ if (!h_dir->i_nlink) {
-+ wbr = au_sbr(dentry->d_sb, bdst)->br_wbr;
-+ h_orph = wbr->wbr_orph;
-+
-+ h_parent = dget(au_h_dptr(parent, bdst));
-+ au_set_h_dptr(parent, bdst, dget(h_orph));
-+ h_tmpdir = d_inode(h_orph);
-+ au_set_h_iptr(dir, bdst, au_igrab(h_tmpdir), /*flags*/0);
-+
-+ inode_lock_nested(h_tmpdir, AuLsc_I_PARENT3);
-+ /* todo: au_h_open_pre()? */
-+
-+ pin_orig = cpg->pin;
-+ au_pin_init(&wh_pin, dentry, bdst, AuLsc_DI_PARENT,
-+ AuLsc_I_PARENT3, cpg->pin->udba, AuPin_DI_LOCKED);
-+ cpg->pin = &wh_pin;
-+ }
-+
-+ if (!au_test_h_perm_sio(h_tmpdir, MAY_EXEC | MAY_WRITE)
-+ && !au_cpup_sio_test(cpg->pin, d_inode(dentry)->i_mode))
-+ err = au_cpup_wh(cpg, file);
-+ else {
-+ struct au_cpup_wh_args args = {
-+ .errp = &err,
-+ .cpg = cpg,
-+ .file = file
-+ };
-+ wkq_err = au_wkq_wait(au_call_cpup_wh, &args);
-+ if (unlikely(wkq_err))
-+ err = wkq_err;
-+ }
-+
-+ if (h_orph) {
-+ inode_unlock(h_tmpdir);
-+ /* todo: au_h_open_post()? */
-+ au_set_h_iptr(dir, bdst, au_igrab(h_dir), /*flags*/0);
-+ au_set_h_dptr(parent, bdst, h_parent);
-+ AuDebugOn(!pin_orig);
-+ cpg->pin = pin_orig;
-+ }
-+ iput(h_dir);
-+ dput(parent);
-+
-+ return err;
-+}
-+
-+/* ---------------------------------------------------------------------- */
-+
-+/*
-+ * generic routine for both of copy-up and copy-down.
-+ */
-+/* cf. revalidate function in file.c */
-+int au_cp_dirs(struct dentry *dentry, aufs_bindex_t bdst,
-+ int (*cp)(struct dentry *dentry, aufs_bindex_t bdst,
-+ struct au_pin *pin,
-+ struct dentry *h_parent, void *arg),
-+ void *arg)
-+{
-+ int err;
-+ struct au_pin pin;
-+ struct dentry *d, *parent, *h_parent, *real_parent, *h_dentry;
-+
-+ err = 0;
-+ parent = dget_parent(dentry);
-+ if (IS_ROOT(parent))
-+ goto out;
-+
-+ au_pin_init(&pin, dentry, bdst, AuLsc_DI_PARENT2, AuLsc_I_PARENT2,
-+ au_opt_udba(dentry->d_sb), AuPin_MNT_WRITE);
-+
-+ /* do not use au_dpage */
-+ real_parent = parent;
-+ while (1) {
-+ dput(parent);
-+ parent = dget_parent(dentry);
-+ h_parent = au_h_dptr(parent, bdst);
-+ if (h_parent)
-+ goto out; /* success */
-+
-+ /* find top dir which is necessary to cpup */
-+ do {
-+ d = parent;
-+ dput(parent);
-+ parent = dget_parent(d);
-+ di_read_lock_parent3(parent, !AuLock_IR);
-+ h_parent = au_h_dptr(parent, bdst);
-+ di_read_unlock(parent, !AuLock_IR);
-+ } while (!h_parent);
-+
-+ if (d != real_parent)
-+ di_write_lock_child3(d);
-+
-+ /* somebody else might create while we were sleeping */
-+ h_dentry = au_h_dptr(d, bdst);
-+ if (!h_dentry || d_is_negative(h_dentry)) {
-+ if (h_dentry)
-+ au_update_dbtop(d);
-+
-+ au_pin_set_dentry(&pin, d);
-+ err = au_do_pin(&pin);
-+ if (!err) {
-+ err = cp(d, bdst, &pin, h_parent, arg);
-+ au_unpin(&pin);
-+ }
-+ }
-+
-+ if (d != real_parent)
-+ di_write_unlock(d);
-+ if (unlikely(err))
-+ break;
-+ }
-+
-+out:
-+ dput(parent);
-+ return err;
-+}
-+
-+static int au_cpup_dir(struct dentry *dentry, aufs_bindex_t bdst,
-+ struct au_pin *pin,
-+ struct dentry *h_parent __maybe_unused,
-+ void *arg __maybe_unused)
-+{
-+ struct au_cp_generic cpg = {
-+ .dentry = dentry,
-+ .bdst = bdst,
-+ .bsrc = -1,
-+ .len = 0,
-+ .pin = pin,
-+ .flags = AuCpup_DTIME
-+ };
-+ return au_sio_cpup_simple(&cpg);
-+}
-+
-+int au_cpup_dirs(struct dentry *dentry, aufs_bindex_t bdst)
-+{
-+ return au_cp_dirs(dentry, bdst, au_cpup_dir, NULL);
-+}
-+
-+int au_test_and_cpup_dirs(struct dentry *dentry, aufs_bindex_t bdst)
-+{
-+ int err;
-+ struct dentry *parent;
-+ struct inode *dir;
-+
-+ parent = dget_parent(dentry);
-+ dir = d_inode(parent);
-+ err = 0;
-+ if (au_h_iptr(dir, bdst))
-+ goto out;
-+
-+ di_read_unlock(parent, AuLock_IR);
-+ di_write_lock_parent(parent);
-+ /* someone else might change our inode while we were sleeping */
-+ if (!au_h_iptr(dir, bdst))
-+ err = au_cpup_dirs(dentry, bdst);
-+ di_downgrade_lock(parent, AuLock_IR);
-+
-+out:
-+ dput(parent);
-+ return err;
-+}
-diff --git a/fs/aufs/cpup.h b/fs/aufs/cpup.h
-new file mode 100644
-index 000000000000..abcbfbc55a5c
---- /dev/null
-+++ b/fs/aufs/cpup.h
-@@ -0,0 +1,100 @@
-+/* SPDX-License-Identifier: GPL-2.0 */
-+/*
-+ * Copyright (C) 2005-2019 Junjiro R. Okajima
-+ *
-+ * This program, aufs is free software; you can redistribute it and/or modify
-+ * it under the terms of the GNU General Public License as published by
-+ * the Free Software Foundation; either version 2 of the License, or
-+ * (at your option) any later version.
-+ *
-+ * This program is distributed in the hope that it will be useful,
-+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
-+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
-+ * GNU General Public License for more details.
-+ *
-+ * You should have received a copy of the GNU General Public License
-+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
-+ */
-+
-+/*
-+ * copy-up/down functions
-+ */
-+
-+#ifndef __AUFS_CPUP_H__
-+#define __AUFS_CPUP_H__
-+
-+#ifdef __KERNEL__
-+
-+#include <linux/path.h>
-+
-+struct inode;
-+struct file;
-+struct au_pin;
-+
-+void au_cpup_attr_flags(struct inode *dst, unsigned int iflags);
-+void au_cpup_attr_timesizes(struct inode *inode);
-+void au_cpup_attr_nlink(struct inode *inode, int force);
-+void au_cpup_attr_changeable(struct inode *inode);
-+void au_cpup_igen(struct inode *inode, struct inode *h_inode);
-+void au_cpup_attr_all(struct inode *inode, int force);
-+
-+/* ---------------------------------------------------------------------- */
-+
-+struct au_cp_generic {
-+ struct dentry *dentry;
-+ aufs_bindex_t bdst, bsrc;
-+ loff_t len;
-+ struct au_pin *pin;
-+ unsigned int flags;
-+};
-+
-+/* cpup flags */
-+#define AuCpup_DTIME 1 /* do dtime_store/revert */
-+#define AuCpup_KEEPLINO (1 << 1) /* do not clear the lower xino,
-+ for link(2) */
-+#define AuCpup_RENAME (1 << 2) /* rename after cpup */
-+#define AuCpup_HOPEN (1 << 3) /* call h_open_pre/post() in
-+ cpup */
-+#define AuCpup_OVERWRITE (1 << 4) /* allow overwriting the
-+ existing entry */
-+#define AuCpup_RWDST (1 << 5) /* force write target even if
-+ the branch is marked as RO */
-+
-+#ifndef CONFIG_AUFS_BR_HFSPLUS
-+#undef AuCpup_HOPEN
-+#define AuCpup_HOPEN 0
-+#endif
-+
-+#define au_ftest_cpup(flags, name) ((flags) & AuCpup_##name)
-+#define au_fset_cpup(flags, name) \
-+ do { (flags) |= AuCpup_##name; } while (0)
-+#define au_fclr_cpup(flags, name) \
-+ do { (flags) &= ~AuCpup_##name; } while (0)
-+
-+int au_copy_file(struct file *dst, struct file *src, loff_t len);
-+int au_sio_cpup_simple(struct au_cp_generic *cpg);
-+int au_sio_cpdown_simple(struct au_cp_generic *cpg);
-+int au_sio_cpup_wh(struct au_cp_generic *cpg, struct file *file);
-+
-+int au_cp_dirs(struct dentry *dentry, aufs_bindex_t bdst,
-+ int (*cp)(struct dentry *dentry, aufs_bindex_t bdst,
-+ struct au_pin *pin,
-+ struct dentry *h_parent, void *arg),
-+ void *arg);
-+int au_cpup_dirs(struct dentry *dentry, aufs_bindex_t bdst);
-+int au_test_and_cpup_dirs(struct dentry *dentry, aufs_bindex_t bdst);
-+
-+/* ---------------------------------------------------------------------- */
-+
-+/* keep timestamps when copyup */
-+struct au_dtime {
-+ struct dentry *dt_dentry;
-+ struct path dt_h_path;
-+ struct timespec64 dt_atime, dt_mtime;
-+};
-+void au_dtime_store(struct au_dtime *dt, struct dentry *dentry,
-+ struct path *h_path);
-+void au_dtime_revert(struct au_dtime *dt);
-+
-+#endif /* __KERNEL__ */
-+#endif /* __AUFS_CPUP_H__ */
-diff --git a/fs/aufs/dbgaufs.c b/fs/aufs/dbgaufs.c
-new file mode 100644
-index 000000000000..e32d91d1f638
---- /dev/null
-+++ b/fs/aufs/dbgaufs.c
-@@ -0,0 +1,526 @@
-+// SPDX-License-Identifier: GPL-2.0
-+/*
-+ * Copyright (C) 2005-2019 Junjiro R. Okajima
-+ *
-+ * This program, aufs is free software; you can redistribute it and/or modify
-+ * it under the terms of the GNU General Public License as published by
-+ * the Free Software Foundation; either version 2 of the License, or
-+ * (at your option) any later version.
-+ *
-+ * This program is distributed in the hope that it will be useful,
-+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
-+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
-+ * GNU General Public License for more details.
-+ *
-+ * You should have received a copy of the GNU General Public License
-+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
-+ */
-+
-+/*
-+ * debugfs interface
-+ */
-+
-+#include <linux/debugfs.h>
-+#include "aufs.h"
-+
-+#ifndef CONFIG_SYSFS
-+#error DEBUG_FS depends upon SYSFS
-+#endif
-+
-+static struct dentry *dbgaufs;
-+static const mode_t dbgaufs_mode = 0444;
-+
-+/* 20 is max digits length of ulong 64 */
-+struct dbgaufs_arg {
-+ int n;
-+ char a[20 * 4];
-+};
-+
-+/*
-+ * common function for all XINO files
-+ */
-+static int dbgaufs_xi_release(struct inode *inode __maybe_unused,
-+ struct file *file)
-+{
-+ void *p;
-+
-+ p = file->private_data;
-+ if (p) {
-+ /* this is struct dbgaufs_arg */
-+ AuDebugOn(!au_kfree_sz_test(p));
-+ au_kfree_do_rcu(p);
-+ }
-+ return 0;
-+}
-+
-+static int dbgaufs_xi_open(struct file *xf, struct file *file, int do_fcnt,
-+ int cnt)
-+{
-+ int err;
-+ struct kstat st;
-+ struct dbgaufs_arg *p;
-+
-+ err = -ENOMEM;
-+ p = kmalloc(sizeof(*p), GFP_NOFS);
-+ if (unlikely(!p))
-+ goto out;
-+
-+ err = 0;
-+ p->n = 0;
-+ file->private_data = p;
-+ if (!xf)
-+ goto out;
-+
-+ err = vfsub_getattr(&xf->f_path, &st);
-+ if (!err) {
-+ if (do_fcnt)
-+ p->n = snprintf
-+ (p->a, sizeof(p->a), "%d, %llux%u %lld\n",
-+ cnt, st.blocks, st.blksize,
-+ (long long)st.size);
-+ else
-+ p->n = snprintf(p->a, sizeof(p->a), "%llux%u %lld\n",
-+ st.blocks, st.blksize,
-+ (long long)st.size);
-+ AuDebugOn(p->n >= sizeof(p->a));
-+ } else {
-+ p->n = snprintf(p->a, sizeof(p->a), "err %d\n", err);
-+ err = 0;
-+ }
-+
-+out:
-+ return err;
-+}
-+
-+static ssize_t dbgaufs_xi_read(struct file *file, char __user *buf,
-+ size_t count, loff_t *ppos)
-+{
-+ struct dbgaufs_arg *p;
-+
-+ p = file->private_data;
-+ return simple_read_from_buffer(buf, count, ppos, p->a, p->n);
-+}
-+
-+/* ---------------------------------------------------------------------- */
-+
-+struct dbgaufs_plink_arg {
-+ int n;
-+ char a[];
-+};
-+
-+static int dbgaufs_plink_release(struct inode *inode __maybe_unused,
-+ struct file *file)
-+{
-+ free_page((unsigned long)file->private_data);
-+ return 0;
-+}
-+
-+static int dbgaufs_plink_open(struct inode *inode, struct file *file)
-+{
-+ int err, i, limit;
-+ unsigned long n, sum;
-+ struct dbgaufs_plink_arg *p;
-+ struct au_sbinfo *sbinfo;
-+ struct super_block *sb;
-+ struct hlist_bl_head *hbl;
-+
-+ err = -ENOMEM;
-+ p = (void *)get_zeroed_page(GFP_NOFS);
-+ if (unlikely(!p))
-+ goto out;
-+
-+ err = -EFBIG;
-+ sbinfo = inode->i_private;
-+ sb = sbinfo->si_sb;
-+ si_noflush_read_lock(sb);
-+ if (au_opt_test(au_mntflags(sb), PLINK)) {
-+ limit = PAGE_SIZE - sizeof(p->n);
-+
-+ /* the number of buckets */
-+ n = snprintf(p->a + p->n, limit, "%d\n", AuPlink_NHASH);
-+ p->n += n;
-+ limit -= n;
-+
-+ sum = 0;
-+ for (i = 0, hbl = sbinfo->si_plink; i < AuPlink_NHASH;
-+ i++, hbl++) {
-+ n = au_hbl_count(hbl);
-+ sum += n;
-+
-+ n = snprintf(p->a + p->n, limit, "%lu ", n);
-+ p->n += n;
-+ limit -= n;
-+ if (unlikely(limit <= 0))
-+ goto out_free;
-+ }
-+ p->a[p->n - 1] = '\n';
-+
-+ /* the sum of plinks */
-+ n = snprintf(p->a + p->n, limit, "%lu\n", sum);
-+ p->n += n;
-+ limit -= n;
-+ if (unlikely(limit <= 0))
-+ goto out_free;
-+ } else {
-+#define str "1\n0\n0\n"
-+ p->n = sizeof(str) - 1;
-+ strcpy(p->a, str);
-+#undef str
-+ }
-+ si_read_unlock(sb);
-+
-+ err = 0;
-+ file->private_data = p;
-+ goto out; /* success */
-+
-+out_free:
-+ free_page((unsigned long)p);
-+out:
-+ return err;
-+}
-+
-+static ssize_t dbgaufs_plink_read(struct file *file, char __user *buf,
-+ size_t count, loff_t *ppos)
-+{
-+ struct dbgaufs_plink_arg *p;
-+
-+ p = file->private_data;
-+ return simple_read_from_buffer(buf, count, ppos, p->a, p->n);
-+}
-+
-+static const struct file_operations dbgaufs_plink_fop = {
-+ .owner = THIS_MODULE,
-+ .open = dbgaufs_plink_open,
-+ .release = dbgaufs_plink_release,
-+ .read = dbgaufs_plink_read
-+};
-+
-+/* ---------------------------------------------------------------------- */
-+
-+static int dbgaufs_xib_open(struct inode *inode, struct file *file)
-+{
-+ int err;
-+ struct au_sbinfo *sbinfo;
-+ struct super_block *sb;
-+
-+ sbinfo = inode->i_private;
-+ sb = sbinfo->si_sb;
-+ si_noflush_read_lock(sb);
-+ err = dbgaufs_xi_open(sbinfo->si_xib, file, /*do_fcnt*/0, /*cnt*/0);
-+ si_read_unlock(sb);
-+ return err;
-+}
-+
-+static const struct file_operations dbgaufs_xib_fop = {
-+ .owner = THIS_MODULE,
-+ .open = dbgaufs_xib_open,
-+ .release = dbgaufs_xi_release,
-+ .read = dbgaufs_xi_read
-+};
-+
-+/* ---------------------------------------------------------------------- */
-+
-+#define DbgaufsXi_PREFIX "xi"
-+
-+static int dbgaufs_xino_open(struct inode *inode, struct file *file)
-+{
-+ int err, idx;
-+ long l;
-+ aufs_bindex_t bindex;
-+ char *p, a[sizeof(DbgaufsXi_PREFIX) + 8];
-+ struct au_sbinfo *sbinfo;
-+ struct super_block *sb;
-+ struct au_xino *xi;
-+ struct file *xf;
-+ struct qstr *name;
-+ struct au_branch *br;
-+
-+ err = -ENOENT;
-+ name = &file->f_path.dentry->d_name;
-+ if (unlikely(name->len < sizeof(DbgaufsXi_PREFIX)
-+ || memcmp(name->name, DbgaufsXi_PREFIX,
-+ sizeof(DbgaufsXi_PREFIX) - 1)))
-+ goto out;
-+
-+ AuDebugOn(name->len >= sizeof(a));
-+ memcpy(a, name->name, name->len);
-+ a[name->len] = '\0';
-+ p = strchr(a, '-');
-+ if (p)
-+ *p = '\0';
-+ err = kstrtol(a + sizeof(DbgaufsXi_PREFIX) - 1, 10, &l);
-+ if (unlikely(err))
-+ goto out;
-+ bindex = l;
-+ idx = 0;
-+ if (p) {
-+ err = kstrtol(p + 1, 10, &l);
-+ if (unlikely(err))
-+ goto out;
-+ idx = l;
-+ }
-+
-+ err = -ENOENT;
-+ sbinfo = inode->i_private;
-+ sb = sbinfo->si_sb;
-+ si_noflush_read_lock(sb);
-+ if (unlikely(bindex < 0 || bindex > au_sbbot(sb)))
-+ goto out_si;
-+ br = au_sbr(sb, bindex);
-+ xi = br->br_xino;
-+ if (unlikely(idx >= xi->xi_nfile))
-+ goto out_si;
-+ xf = au_xino_file(xi, idx);
-+ if (xf)
-+ err = dbgaufs_xi_open(xf, file, /*do_fcnt*/1,
-+ au_xino_count(br));
-+
-+out_si:
-+ si_read_unlock(sb);
-+out:
-+ AuTraceErr(err);
-+ return err;
-+}
-+
-+static const struct file_operations dbgaufs_xino_fop = {
-+ .owner = THIS_MODULE,
-+ .open = dbgaufs_xino_open,
-+ .release = dbgaufs_xi_release,
-+ .read = dbgaufs_xi_read
-+};
-+
-+void dbgaufs_xino_del(struct au_branch *br)
-+{
-+ struct dentry *dbgaufs;
-+
-+ dbgaufs = br->br_dbgaufs;
-+ if (!dbgaufs)
-+ return;
-+
-+ br->br_dbgaufs = NULL;
-+ /* debugfs acquires the parent i_mutex */
-+ lockdep_off();
-+ debugfs_remove(dbgaufs);
-+ lockdep_on();
-+}
-+
-+void dbgaufs_brs_del(struct super_block *sb, aufs_bindex_t bindex)
-+{
-+ aufs_bindex_t bbot;
-+ struct au_branch *br;
-+
-+ if (!au_sbi(sb)->si_dbgaufs)
-+ return;
-+
-+ bbot = au_sbbot(sb);
-+ for (; bindex <= bbot; bindex++) {
-+ br = au_sbr(sb, bindex);
-+ dbgaufs_xino_del(br);
-+ }
-+}
-+
-+static void dbgaufs_br_do_add(struct super_block *sb, aufs_bindex_t bindex,
-+ unsigned int idx, struct dentry *parent,
-+ struct au_sbinfo *sbinfo)
-+{
-+ struct au_branch *br;
-+ struct dentry *d;
-+ /* "xi" bindex(5) "-" idx(2) NULL */
-+ char name[sizeof(DbgaufsXi_PREFIX) + 8];
-+
-+ if (!idx)
-+ snprintf(name, sizeof(name), DbgaufsXi_PREFIX "%d", bindex);
-+ else
-+ snprintf(name, sizeof(name), DbgaufsXi_PREFIX "%d-%u",
-+ bindex, idx);
-+ br = au_sbr(sb, bindex);
-+ if (br->br_dbgaufs) {
-+ struct qstr qstr = QSTR_INIT(name, strlen(name));
-+
-+ if (!au_qstreq(&br->br_dbgaufs->d_name, &qstr)) {
-+ /* debugfs acquires the parent i_mutex */
-+ lockdep_off();
-+ d = debugfs_rename(parent, br->br_dbgaufs, parent,
-+ name);
-+ lockdep_on();
-+ if (unlikely(!d))
-+ pr_warn("failed renaming %pd/%s, ignored.\n",
-+ parent, name);
-+ }
-+ } else {
-+ lockdep_off();
-+ br->br_dbgaufs = debugfs_create_file(name, dbgaufs_mode, parent,
-+ sbinfo, &dbgaufs_xino_fop);
-+ lockdep_on();
-+ if (unlikely(!br->br_dbgaufs))
-+ pr_warn("failed creating %pd/%s, ignored.\n",
-+ parent, name);
-+ }
-+}
-+
-+static void dbgaufs_br_add(struct super_block *sb, aufs_bindex_t bindex,
-+ struct dentry *parent, struct au_sbinfo *sbinfo)
-+{
-+ struct au_branch *br;
-+ struct au_xino *xi;
-+ unsigned int u;
-+
-+ br = au_sbr(sb, bindex);
-+ xi = br->br_xino;
-+ for (u = 0; u < xi->xi_nfile; u++)
-+ dbgaufs_br_do_add(sb, bindex, u, parent, sbinfo);
-+}
-+
-+void dbgaufs_brs_add(struct super_block *sb, aufs_bindex_t bindex, int topdown)
-+{
-+ struct au_sbinfo *sbinfo;
-+ struct dentry *parent;
-+ aufs_bindex_t bbot;
-+
-+ if (!au_opt_test(au_mntflags(sb), XINO))
-+ return;
-+
-+ sbinfo = au_sbi(sb);
-+ parent = sbinfo->si_dbgaufs;
-+ if (!parent)
-+ return;
-+
-+ bbot = au_sbbot(sb);
-+ if (topdown)
-+ for (; bindex <= bbot; bindex++)
-+ dbgaufs_br_add(sb, bindex, parent, sbinfo);
-+ else
-+ for (; bbot >= bindex; bbot--)
-+ dbgaufs_br_add(sb, bbot, parent, sbinfo);
-+}
-+
-+/* ---------------------------------------------------------------------- */
-+
-+#ifdef CONFIG_AUFS_EXPORT
-+static int dbgaufs_xigen_open(struct inode *inode, struct file *file)
-+{
-+ int err;
-+ struct au_sbinfo *sbinfo;
-+ struct super_block *sb;
-+
-+ sbinfo = inode->i_private;
-+ sb = sbinfo->si_sb;
-+ si_noflush_read_lock(sb);
-+ err = dbgaufs_xi_open(sbinfo->si_xigen, file, /*do_fcnt*/0, /*cnt*/0);
-+ si_read_unlock(sb);
-+ return err;
-+}
-+
-+static const struct file_operations dbgaufs_xigen_fop = {
-+ .owner = THIS_MODULE,
-+ .open = dbgaufs_xigen_open,
-+ .release = dbgaufs_xi_release,
-+ .read = dbgaufs_xi_read
-+};
-+
-+static int dbgaufs_xigen_init(struct au_sbinfo *sbinfo)
-+{
-+ int err;
-+
-+ /*
-+ * This function is a dynamic '__init' function actually,
-+ * so the tiny check for si_rwsem is unnecessary.
-+ */
-+ /* AuRwMustWriteLock(&sbinfo->si_rwsem); */
-+
-+ err = -EIO;
-+ sbinfo->si_dbgaufs_xigen = debugfs_create_file
-+ ("xigen", dbgaufs_mode, sbinfo->si_dbgaufs, sbinfo,
-+ &dbgaufs_xigen_fop);
-+ if (sbinfo->si_dbgaufs_xigen)
-+ err = 0;
-+
-+ return err;
-+}
-+#else
-+static int dbgaufs_xigen_init(struct au_sbinfo *sbinfo)
-+{
-+ return 0;
-+}
-+#endif /* CONFIG_AUFS_EXPORT */
-+
-+/* ---------------------------------------------------------------------- */
-+
-+void dbgaufs_si_fin(struct au_sbinfo *sbinfo)
-+{
-+ /*
-+ * This function is a dynamic '__fin' function actually,
-+ * so the tiny check for si_rwsem is unnecessary.
-+ */
-+ /* AuRwMustWriteLock(&sbinfo->si_rwsem); */
-+
-+ debugfs_remove_recursive(sbinfo->si_dbgaufs);
-+ sbinfo->si_dbgaufs = NULL;
-+}
-+
-+int dbgaufs_si_init(struct au_sbinfo *sbinfo)
-+{
-+ int err;
-+ char name[SysaufsSiNameLen];
-+
-+ /*
-+ * This function is a dynamic '__init' function actually,
-+ * so the tiny check for si_rwsem is unnecessary.
-+ */
-+ /* AuRwMustWriteLock(&sbinfo->si_rwsem); */
-+
-+ err = -ENOENT;
-+ if (!dbgaufs) {
-+ AuErr1("/debug/aufs is uninitialized\n");
-+ goto out;
-+ }
-+
-+ err = -EIO;
-+ sysaufs_name(sbinfo, name);
-+ sbinfo->si_dbgaufs = debugfs_create_dir(name, dbgaufs);
-+ if (unlikely(!sbinfo->si_dbgaufs))
-+ goto out;
-+
-+ /* regardless plink/noplink option */
-+ sbinfo->si_dbgaufs_plink = debugfs_create_file
-+ ("plink", dbgaufs_mode, sbinfo->si_dbgaufs, sbinfo,
-+ &dbgaufs_plink_fop);
-+ if (unlikely(!sbinfo->si_dbgaufs_plink))
-+ goto out_dir;
-+
-+ /* regardless xino/noxino option */
-+ sbinfo->si_dbgaufs_xib = debugfs_create_file
-+ ("xib", dbgaufs_mode, sbinfo->si_dbgaufs, sbinfo,
-+ &dbgaufs_xib_fop);
-+ if (unlikely(!sbinfo->si_dbgaufs_xib))
-+ goto out_dir;
-+
-+ err = dbgaufs_xigen_init(sbinfo);
-+ if (!err)
-+ goto out; /* success */
-+
-+out_dir:
-+ dbgaufs_si_fin(sbinfo);
-+out:
-+ if (unlikely(err))
-+ pr_err("debugfs/aufs failed\n");
-+ return err;
-+}
-+
-+/* ---------------------------------------------------------------------- */
-+
-+void dbgaufs_fin(void)
-+{
-+ debugfs_remove(dbgaufs);
-+}
-+
-+int __init dbgaufs_init(void)
-+{
-+ int err;
-+
-+ err = -EIO;
-+ dbgaufs = debugfs_create_dir(AUFS_NAME, NULL);
-+ if (dbgaufs)
-+ err = 0;
-+ return err;
-+}
-diff --git a/fs/aufs/dbgaufs.h b/fs/aufs/dbgaufs.h
-new file mode 100644
-index 000000000000..1ea241bf0234
---- /dev/null
-+++ b/fs/aufs/dbgaufs.h
-@@ -0,0 +1,53 @@
-+/* SPDX-License-Identifier: GPL-2.0 */
-+/*
-+ * Copyright (C) 2005-2019 Junjiro R. Okajima
-+ *
-+ * This program, aufs is free software; you can redistribute it and/or modify
-+ * it under the terms of the GNU General Public License as published by
-+ * the Free Software Foundation; either version 2 of the License, or
-+ * (at your option) any later version.
-+ *
-+ * This program is distributed in the hope that it will be useful,
-+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
-+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
-+ * GNU General Public License for more details.
-+ *
-+ * You should have received a copy of the GNU General Public License
-+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
-+ */
-+
-+/*
-+ * debugfs interface
-+ */
-+
-+#ifndef __DBGAUFS_H__
-+#define __DBGAUFS_H__
-+
-+#ifdef __KERNEL__
-+
-+struct super_block;
-+struct au_sbinfo;
-+struct au_branch;
-+
-+#ifdef CONFIG_DEBUG_FS
-+/* dbgaufs.c */
-+void dbgaufs_xino_del(struct au_branch *br);
-+void dbgaufs_brs_del(struct super_block *sb, aufs_bindex_t bindex);
-+void dbgaufs_brs_add(struct super_block *sb, aufs_bindex_t bindex, int topdown);
-+void dbgaufs_si_fin(struct au_sbinfo *sbinfo);
-+int dbgaufs_si_init(struct au_sbinfo *sbinfo);
-+void dbgaufs_fin(void);
-+int __init dbgaufs_init(void);
-+#else
-+AuStubVoid(dbgaufs_xino_del, struct au_branch *br)
-+AuStubVoid(dbgaufs_brs_del, struct super_block *sb, aufs_bindex_t bindex)
-+AuStubVoid(dbgaufs_brs_add, struct super_block *sb, aufs_bindex_t bindex,
-+ int topdown)
-+AuStubVoid(dbgaufs_si_fin, struct au_sbinfo *sbinfo)
-+AuStubInt0(dbgaufs_si_init, struct au_sbinfo *sbinfo)
-+AuStubVoid(dbgaufs_fin, void)
-+AuStubInt0(__init dbgaufs_init, void)
-+#endif /* CONFIG_DEBUG_FS */
-+
-+#endif /* __KERNEL__ */
-+#endif /* __DBGAUFS_H__ */
-diff --git a/fs/aufs/dcsub.c b/fs/aufs/dcsub.c
-new file mode 100644
-index 000000000000..0b9122307667
---- /dev/null
-+++ b/fs/aufs/dcsub.c
-@@ -0,0 +1,225 @@
-+// SPDX-License-Identifier: GPL-2.0
-+/*
-+ * Copyright (C) 2005-2019 Junjiro R. Okajima
-+ *
-+ * This program, aufs is free software; you can redistribute it and/or modify
-+ * it under the terms of the GNU General Public License as published by
-+ * the Free Software Foundation; either version 2 of the License, or
-+ * (at your option) any later version.
-+ *
-+ * This program is distributed in the hope that it will be useful,
-+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
-+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
-+ * GNU General Public License for more details.
-+ *
-+ * You should have received a copy of the GNU General Public License
-+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
-+ */
-+
-+/*
-+ * sub-routines for dentry cache
-+ */
-+
-+#include "aufs.h"
-+
-+static void au_dpage_free(struct au_dpage *dpage)
-+{
-+ int i;
-+ struct dentry **p;
-+
-+ p = dpage->dentries;
-+ for (i = 0; i < dpage->ndentry; i++)
-+ dput(*p++);
-+ free_page((unsigned long)dpage->dentries);
-+}
-+
-+int au_dpages_init(struct au_dcsub_pages *dpages, gfp_t gfp)
-+{
-+ int err;
-+ void *p;
-+
-+ err = -ENOMEM;
-+ dpages->dpages = kmalloc(sizeof(*dpages->dpages), gfp);
-+ if (unlikely(!dpages->dpages))
-+ goto out;
-+
-+ p = (void *)__get_free_page(gfp);
-+ if (unlikely(!p))
-+ goto out_dpages;
-+
-+ dpages->dpages[0].ndentry = 0;
-+ dpages->dpages[0].dentries = p;
-+ dpages->ndpage = 1;
-+ return 0; /* success */
-+
-+out_dpages:
-+ au_kfree_try_rcu(dpages->dpages);
-+out:
-+ return err;
-+}
-+
-+void au_dpages_free(struct au_dcsub_pages *dpages)
-+{
-+ int i;
-+ struct au_dpage *p;
-+
-+ p = dpages->dpages;
-+ for (i = 0; i < dpages->ndpage; i++)
-+ au_dpage_free(p++);
-+ au_kfree_try_rcu(dpages->dpages);
-+}
-+
-+static int au_dpages_append(struct au_dcsub_pages *dpages,
-+ struct dentry *dentry, gfp_t gfp)
-+{
-+ int err, sz;
-+ struct au_dpage *dpage;
-+ void *p;
-+
-+ dpage = dpages->dpages + dpages->ndpage - 1;
-+ sz = PAGE_SIZE / sizeof(dentry);
-+ if (unlikely(dpage->ndentry >= sz)) {
-+ AuLabel(new dpage);
-+ err = -ENOMEM;
-+ sz = dpages->ndpage * sizeof(*dpages->dpages);
-+ p = au_kzrealloc(dpages->dpages, sz,
-+ sz + sizeof(*dpages->dpages), gfp,
-+ /*may_shrink*/0);
-+ if (unlikely(!p))
-+ goto out;
-+
-+ dpages->dpages = p;
-+ dpage = dpages->dpages + dpages->ndpage;
-+ p = (void *)__get_free_page(gfp);
-+ if (unlikely(!p))
-+ goto out;
-+
-+ dpage->ndentry = 0;
-+ dpage->dentries = p;
-+ dpages->ndpage++;
-+ }
-+
-+ AuDebugOn(au_dcount(dentry) <= 0);
-+ dpage->dentries[dpage->ndentry++] = dget_dlock(dentry);
-+ return 0; /* success */
-+
-+out:
-+ return err;
-+}
-+
-+/* todo: BAD approach */
-+/* copied from linux/fs/dcache.c */
-+enum d_walk_ret {
-+ D_WALK_CONTINUE,
-+ D_WALK_QUIT,
-+ D_WALK_NORETRY,
-+ D_WALK_SKIP,
-+};
-+
-+extern void d_walk(struct dentry *parent, void *data,
-+ enum d_walk_ret (*enter)(void *, struct dentry *));
-+
-+struct ac_dpages_arg {
-+ int err;
-+ struct au_dcsub_pages *dpages;
-+ struct super_block *sb;
-+ au_dpages_test test;
-+ void *arg;
-+};
-+
-+static enum d_walk_ret au_call_dpages_append(void *_arg, struct dentry *dentry)
-+{
-+ enum d_walk_ret ret;
-+ struct ac_dpages_arg *arg = _arg;
-+
-+ ret = D_WALK_CONTINUE;
-+ if (dentry->d_sb == arg->sb
-+ && !IS_ROOT(dentry)
-+ && au_dcount(dentry) > 0
-+ && au_di(dentry)
-+ && (!arg->test || arg->test(dentry, arg->arg))) {
-+ arg->err = au_dpages_append(arg->dpages, dentry, GFP_ATOMIC);
-+ if (unlikely(arg->err))
-+ ret = D_WALK_QUIT;
-+ }
-+
-+ return ret;
-+}
-+
-+int au_dcsub_pages(struct au_dcsub_pages *dpages, struct dentry *root,
-+ au_dpages_test test, void *arg)
-+{
-+ struct ac_dpages_arg args = {
-+ .err = 0,
-+ .dpages = dpages,
-+ .sb = root->d_sb,
-+ .test = test,
-+ .arg = arg
-+ };
-+
-+ d_walk(root, &args, au_call_dpages_append);
-+
-+ return args.err;
-+}
-+
-+int au_dcsub_pages_rev(struct au_dcsub_pages *dpages, struct dentry *dentry,
-+ int do_include, au_dpages_test test, void *arg)
-+{
-+ int err;
-+
-+ err = 0;
-+ write_seqlock(&rename_lock);
-+ spin_lock(&dentry->d_lock);
-+ if (do_include
-+ && au_dcount(dentry) > 0
-+ && (!test || test(dentry, arg)))
-+ err = au_dpages_append(dpages, dentry, GFP_ATOMIC);
-+ spin_unlock(&dentry->d_lock);
-+ if (unlikely(err))
-+ goto out;
-+
-+ /*
-+ * RCU for vfsmount is unnecessary since this is a traverse in a single
-+ * mount
-+ */
-+ while (!IS_ROOT(dentry)) {
-+ dentry = dentry->d_parent; /* rename_lock is locked */
-+ spin_lock(&dentry->d_lock);
-+ if (au_dcount(dentry) > 0
-+ && (!test || test(dentry, arg)))
-+ err = au_dpages_append(dpages, dentry, GFP_ATOMIC);
-+ spin_unlock(&dentry->d_lock);
-+ if (unlikely(err))
-+ break;
-+ }
-+
-+out:
-+ write_sequnlock(&rename_lock);
-+ return err;
-+}
-+
-+static inline int au_dcsub_dpages_aufs(struct dentry *dentry, void *arg)
-+{
-+ return au_di(dentry) && dentry->d_sb == arg;
-+}
-+
-+int au_dcsub_pages_rev_aufs(struct au_dcsub_pages *dpages,
-+ struct dentry *dentry, int do_include)
-+{
-+ return au_dcsub_pages_rev(dpages, dentry, do_include,
-+ au_dcsub_dpages_aufs, dentry->d_sb);
-+}
-+
-+int au_test_subdir(struct dentry *d1, struct dentry *d2)
-+{
-+ struct path path[2] = {
-+ {
-+ .dentry = d1
-+ },
-+ {
-+ .dentry = d2
-+ }
-+ };
-+
-+ return path_is_under(path + 0, path + 1);
-+}
-diff --git a/fs/aufs/dcsub.h b/fs/aufs/dcsub.h
-new file mode 100644
-index 000000000000..5e578995c256
---- /dev/null
-+++ b/fs/aufs/dcsub.h
-@@ -0,0 +1,137 @@
-+/* SPDX-License-Identifier: GPL-2.0 */
-+/*
-+ * Copyright (C) 2005-2019 Junjiro R. Okajima
-+ *
-+ * This program, aufs is free software; you can redistribute it and/or modify
-+ * it under the terms of the GNU General Public License as published by
-+ * the Free Software Foundation; either version 2 of the License, or
-+ * (at your option) any later version.
-+ *
-+ * This program is distributed in the hope that it will be useful,
-+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
-+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
-+ * GNU General Public License for more details.
-+ *
-+ * You should have received a copy of the GNU General Public License
-+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
-+ */
-+
-+/*
-+ * sub-routines for dentry cache
-+ */
-+
-+#ifndef __AUFS_DCSUB_H__
-+#define __AUFS_DCSUB_H__
-+
-+#ifdef __KERNEL__
-+
-+#include <linux/dcache.h>
-+#include <linux/fs.h>
-+
-+struct au_dpage {
-+ int ndentry;
-+ struct dentry **dentries;
-+};
-+
-+struct au_dcsub_pages {
-+ int ndpage;
-+ struct au_dpage *dpages;
-+};
-+
-+/* ---------------------------------------------------------------------- */
-+
-+/* dcsub.c */
-+int au_dpages_init(struct au_dcsub_pages *dpages, gfp_t gfp);
-+void au_dpages_free(struct au_dcsub_pages *dpages);
-+typedef int (*au_dpages_test)(struct dentry *dentry, void *arg);
-+int au_dcsub_pages(struct au_dcsub_pages *dpages, struct dentry *root,
-+ au_dpages_test test, void *arg);
-+int au_dcsub_pages_rev(struct au_dcsub_pages *dpages, struct dentry *dentry,
-+ int do_include, au_dpages_test test, void *arg);
-+int au_dcsub_pages_rev_aufs(struct au_dcsub_pages *dpages,
-+ struct dentry *dentry, int do_include);
-+int au_test_subdir(struct dentry *d1, struct dentry *d2);
-+
-+/* ---------------------------------------------------------------------- */
-+
-+/*
-+ * todo: in linux-3.13, several similar (but faster) helpers are added to
-+ * include/linux/dcache.h. Try them (in the future).
-+ */
-+
-+static inline int au_d_hashed_positive(struct dentry *d)
-+{
-+ int err;
-+ struct inode *inode = d_inode(d);
-+
-+ err = 0;
-+ if (unlikely(d_unhashed(d)
-+ || d_is_negative(d)
-+ || !inode->i_nlink))
-+ err = -ENOENT;
-+ return err;
-+}
-+
-+static inline int au_d_linkable(struct dentry *d)
-+{
-+ int err;
-+ struct inode *inode = d_inode(d);
-+
-+ err = au_d_hashed_positive(d);
-+ if (err
-+ && d_is_positive(d)
-+ && (inode->i_state & I_LINKABLE))
-+ err = 0;
-+ return err;
-+}
-+
-+static inline int au_d_alive(struct dentry *d)
-+{
-+ int err;
-+ struct inode *inode;
-+
-+ err = 0;
-+ if (!IS_ROOT(d))
-+ err = au_d_hashed_positive(d);
-+ else {
-+ inode = d_inode(d);
-+ if (unlikely(d_unlinked(d)
-+ || d_is_negative(d)
-+ || !inode->i_nlink))
-+ err = -ENOENT;
-+ }
-+ return err;
-+}
-+
-+static inline int au_alive_dir(struct dentry *d)
-+{
-+ int err;
-+
-+ err = au_d_alive(d);
-+ if (unlikely(err || IS_DEADDIR(d_inode(d))))
-+ err = -ENOENT;
-+ return err;
-+}
-+
-+static inline int au_qstreq(struct qstr *a, struct qstr *b)
-+{
-+ return a->len == b->len
-+ && !memcmp(a->name, b->name, a->len);
-+}
-+
-+/*
-+ * by the commit
-+ * 360f547 2015-01-25 dcache: let the dentry count go down to zero without
-+ * taking d_lock
-+ * the type of d_lockref.count became int, but the inlined function d_count()
-+ * still returns unsigned int.
-+ * I don't know why. Maybe it is for every d_count() users?
-+ * Anyway au_dcount() lives on.
-+ */
-+static inline int au_dcount(struct dentry *d)
-+{
-+ return (int)d_count(d);
-+}
-+
-+#endif /* __KERNEL__ */
-+#endif /* __AUFS_DCSUB_H__ */
-diff --git a/fs/aufs/debug.c b/fs/aufs/debug.c
-new file mode 100644
-index 000000000000..b93bb4f565bf
---- /dev/null
-+++ b/fs/aufs/debug.c
-@@ -0,0 +1,441 @@
-+// SPDX-License-Identifier: GPL-2.0
-+/*
-+ * Copyright (C) 2005-2019 Junjiro R. Okajima
-+ *
-+ * This program, aufs is free software; you can redistribute it and/or modify
-+ * it under the terms of the GNU General Public License as published by
-+ * the Free Software Foundation; either version 2 of the License, or
-+ * (at your option) any later version.
-+ *
-+ * This program is distributed in the hope that it will be useful,
-+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
-+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
-+ * GNU General Public License for more details.
-+ *
-+ * You should have received a copy of the GNU General Public License
-+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
-+ */
-+
-+/*
-+ * debug print functions
-+ */
-+
-+#include <linux/iversion.h>
-+#include "aufs.h"
-+
-+/* Returns 0, or -errno. arg is in kp->arg. */
-+static int param_atomic_t_set(const char *val, const struct kernel_param *kp)
-+{
-+ int err, n;
-+
-+ err = kstrtoint(val, 0, &n);
-+ if (!err) {
-+ if (n > 0)
-+ au_debug_on();
-+ else
-+ au_debug_off();
-+ }
-+ return err;
-+}
-+
-+/* Returns length written or -errno. Buffer is 4k (ie. be short!) */
-+static int param_atomic_t_get(char *buffer, const struct kernel_param *kp)
-+{
-+ atomic_t *a;
-+
-+ a = kp->arg;
-+ return sprintf(buffer, "%d", atomic_read(a));
-+}
-+
-+static struct kernel_param_ops param_ops_atomic_t = {
-+ .set = param_atomic_t_set,
-+ .get = param_atomic_t_get
-+ /* void (*free)(void *arg) */
-+};
-+
-+atomic_t aufs_debug = ATOMIC_INIT(0);
-+MODULE_PARM_DESC(debug, "debug print");
-+module_param_named(debug, aufs_debug, atomic_t, 0664);
-+
-+DEFINE_MUTEX(au_dbg_mtx); /* just to serialize the dbg msgs */
-+char *au_plevel = KERN_DEBUG;
-+#define dpri(fmt, ...) do { \
-+ if ((au_plevel \
-+ && strcmp(au_plevel, KERN_DEBUG)) \
-+ || au_debug_test()) \
-+ printk("%s" fmt, au_plevel, ##__VA_ARGS__); \
-+} while (0)
-+
-+/* ---------------------------------------------------------------------- */
-+
-+void au_dpri_whlist(struct au_nhash *whlist)
-+{
-+ unsigned long ul, n;
-+ struct hlist_head *head;
-+ struct au_vdir_wh *pos;
-+
-+ n = whlist->nh_num;
-+ head = whlist->nh_head;
-+ for (ul = 0; ul < n; ul++) {
-+ hlist_for_each_entry(pos, head, wh_hash)
-+ dpri("b%d, %.*s, %d\n",
-+ pos->wh_bindex,
-+ pos->wh_str.len, pos->wh_str.name,
-+ pos->wh_str.len);
-+ head++;
-+ }
-+}
-+
-+void au_dpri_vdir(struct au_vdir *vdir)
-+{
-+ unsigned long ul;
-+ union au_vdir_deblk_p p;
-+ unsigned char *o;
-+
-+ if (!vdir || IS_ERR(vdir)) {
-+ dpri("err %ld\n", PTR_ERR(vdir));
-+ return;
-+ }
-+
-+ dpri("deblk %u, nblk %lu, deblk %p, last{%lu, %p}, ver %llu\n",
-+ vdir->vd_deblk_sz, vdir->vd_nblk, vdir->vd_deblk,
-+ vdir->vd_last.ul, vdir->vd_last.p.deblk, vdir->vd_version);
-+ for (ul = 0; ul < vdir->vd_nblk; ul++) {
-+ p.deblk = vdir->vd_deblk[ul];
-+ o = p.deblk;
-+ dpri("[%lu]: %p\n", ul, o);
-+ }
-+}
-+
-+static int do_pri_inode(aufs_bindex_t bindex, struct inode *inode, int hn,
-+ struct dentry *wh)
-+{
-+ char *n = NULL;
-+ int l = 0;
-+
-+ if (!inode || IS_ERR(inode)) {
-+ dpri("i%d: err %ld\n", bindex, PTR_ERR(inode));
-+ return -1;
-+ }
-+
-+ /* the type of i_blocks depends upon CONFIG_LBDAF */
-+ BUILD_BUG_ON(sizeof(inode->i_blocks) != sizeof(unsigned long)
-+ && sizeof(inode->i_blocks) != sizeof(u64));
-+ if (wh) {
-+ n = (void *)wh->d_name.name;
-+ l = wh->d_name.len;
-+ }
-+
-+ dpri("i%d: %p, i%lu, %s, cnt %d, nl %u, 0%o, sz %llu, blk %llu,"
-+ " hn %d, ct %lld, np %lu, st 0x%lx, f 0x%x, v %llu, g %x%s%.*s\n",
-+ bindex, inode,
-+ inode->i_ino, inode->i_sb ? au_sbtype(inode->i_sb) : "??",
-+ atomic_read(&inode->i_count), inode->i_nlink, inode->i_mode,
-+ i_size_read(inode), (unsigned long long)inode->i_blocks,
-+ hn, (long long)timespec64_to_ns(&inode->i_ctime) & 0x0ffff,
-+ inode->i_mapping ? inode->i_mapping->nrpages : 0,
-+ inode->i_state, inode->i_flags, inode_peek_iversion(inode),
-+ inode->i_generation,
-+ l ? ", wh " : "", l, n);
-+ return 0;
-+}
-+
-+void au_dpri_inode(struct inode *inode)
-+{
-+ struct au_iinfo *iinfo;
-+ struct au_hinode *hi;
-+ aufs_bindex_t bindex;
-+ int err, hn;
-+
-+ err = do_pri_inode(-1, inode, -1, NULL);
-+ if (err || !au_test_aufs(inode->i_sb) || au_is_bad_inode(inode))
-+ return;
-+
-+ iinfo = au_ii(inode);
-+ dpri("i-1: btop %d, bbot %d, gen %d\n",
-+ iinfo->ii_btop, iinfo->ii_bbot, au_iigen(inode, NULL));
-+ if (iinfo->ii_btop < 0)
-+ return;
-+ hn = 0;
-+ for (bindex = iinfo->ii_btop; bindex <= iinfo->ii_bbot; bindex++) {
-+ hi = au_hinode(iinfo, bindex);
-+ hn = !!au_hn(hi);
-+ do_pri_inode(bindex, hi->hi_inode, hn, hi->hi_whdentry);
-+ }
-+}
-+
-+void au_dpri_dalias(struct inode *inode)
-+{
-+ struct dentry *d;
-+
-+ spin_lock(&inode->i_lock);
-+ hlist_for_each_entry(d, &inode->i_dentry, d_u.d_alias)
-+ au_dpri_dentry(d);
-+ spin_unlock(&inode->i_lock);
-+}
-+
-+static int do_pri_dentry(aufs_bindex_t bindex, struct dentry *dentry)
-+{
-+ struct dentry *wh = NULL;
-+ int hn;
-+ struct inode *inode;
-+ struct au_iinfo *iinfo;
-+ struct au_hinode *hi;
-+
-+ if (!dentry || IS_ERR(dentry)) {
-+ dpri("d%d: err %ld\n", bindex, PTR_ERR(dentry));
-+ return -1;
-+ }
-+ /* do not call dget_parent() here */
-+ /* note: access d_xxx without d_lock */
-+ dpri("d%d: %p, %pd2?, %s, cnt %d, flags 0x%x, %shashed\n",
-+ bindex, dentry, dentry,
-+ dentry->d_sb ? au_sbtype(dentry->d_sb) : "??",
-+ au_dcount(dentry), dentry->d_flags,
-+ d_unhashed(dentry) ? "un" : "");
-+ hn = -1;
-+ inode = NULL;
-+ if (d_is_positive(dentry))
-+ inode = d_inode(dentry);
-+ if (inode
-+ && au_test_aufs(dentry->d_sb)
-+ && bindex >= 0
-+ && !au_is_bad_inode(inode)) {
-+ iinfo = au_ii(inode);
-+ hi = au_hinode(iinfo, bindex);
-+ hn = !!au_hn(hi);
-+ wh = hi->hi_whdentry;
-+ }
-+ do_pri_inode(bindex, inode, hn, wh);
-+ return 0;
-+}
-+
-+void au_dpri_dentry(struct dentry *dentry)
-+{
-+ struct au_dinfo *dinfo;
-+ aufs_bindex_t bindex;
-+ int err;
-+
-+ err = do_pri_dentry(-1, dentry);
-+ if (err || !au_test_aufs(dentry->d_sb))
-+ return;
-+
-+ dinfo = au_di(dentry);
-+ if (!dinfo)
-+ return;
-+ dpri("d-1: btop %d, bbot %d, bwh %d, bdiropq %d, gen %d, tmp %d\n",
-+ dinfo->di_btop, dinfo->di_bbot,
-+ dinfo->di_bwh, dinfo->di_bdiropq, au_digen(dentry),
-+ dinfo->di_tmpfile);
-+ if (dinfo->di_btop < 0)
-+ return;
-+ for (bindex = dinfo->di_btop; bindex <= dinfo->di_bbot; bindex++)
-+ do_pri_dentry(bindex, au_hdentry(dinfo, bindex)->hd_dentry);
-+}
-+
-+static int do_pri_file(aufs_bindex_t bindex, struct file *file)
-+{
-+ char a[32];
-+
-+ if (!file || IS_ERR(file)) {
-+ dpri("f%d: err %ld\n", bindex, PTR_ERR(file));
-+ return -1;
-+ }
-+ a[0] = 0;
-+ if (bindex < 0
-+ && !IS_ERR_OR_NULL(file->f_path.dentry)
-+ && au_test_aufs(file->f_path.dentry->d_sb)
-+ && au_fi(file))
-+ snprintf(a, sizeof(a), ", gen %d, mmapped %d",
-+ au_figen(file), atomic_read(&au_fi(file)->fi_mmapped));
-+ dpri("f%d: mode 0x%x, flags 0%o, cnt %ld, v %llu, pos %llu%s\n",
-+ bindex, file->f_mode, file->f_flags, (long)file_count(file),
-+ file->f_version, file->f_pos, a);
-+ if (!IS_ERR_OR_NULL(file->f_path.dentry))
-+ do_pri_dentry(bindex, file->f_path.dentry);
-+ return 0;
-+}
-+
-+void au_dpri_file(struct file *file)
-+{
-+ struct au_finfo *finfo;
-+ struct au_fidir *fidir;
-+ struct au_hfile *hfile;
-+ aufs_bindex_t bindex;
-+ int err;
-+
-+ err = do_pri_file(-1, file);
-+ if (err
-+ || IS_ERR_OR_NULL(file->f_path.dentry)
-+ || !au_test_aufs(file->f_path.dentry->d_sb))
-+ return;
-+
-+ finfo = au_fi(file);
-+ if (!finfo)
-+ return;
-+ if (finfo->fi_btop < 0)
-+ return;
-+ fidir = finfo->fi_hdir;
-+ if (!fidir)
-+ do_pri_file(finfo->fi_btop, finfo->fi_htop.hf_file);
-+ else
-+ for (bindex = finfo->fi_btop;
-+ bindex >= 0 && bindex <= fidir->fd_bbot;
-+ bindex++) {
-+ hfile = fidir->fd_hfile + bindex;
-+ do_pri_file(bindex, hfile ? hfile->hf_file : NULL);
-+ }
-+}
-+
-+static int do_pri_br(aufs_bindex_t bindex, struct au_branch *br)
-+{
-+ struct vfsmount *mnt;
-+ struct super_block *sb;
-+
-+ if (!br || IS_ERR(br))
-+ goto out;
-+ mnt = au_br_mnt(br);
-+ if (!mnt || IS_ERR(mnt))
-+ goto out;
-+ sb = mnt->mnt_sb;
-+ if (!sb || IS_ERR(sb))
-+ goto out;
-+
-+ dpri("s%d: {perm 0x%x, id %d, wbr %p}, "
-+ "%s, dev 0x%02x%02x, flags 0x%lx, cnt %d, active %d, "
-+ "xino %d\n",
-+ bindex, br->br_perm, br->br_id, br->br_wbr,
-+ au_sbtype(sb), MAJOR(sb->s_dev), MINOR(sb->s_dev),
-+ sb->s_flags, sb->s_count,
-+ atomic_read(&sb->s_active),
-+ !!au_xino_file(br->br_xino, /*idx*/-1));
-+ return 0;
-+
-+out:
-+ dpri("s%d: err %ld\n", bindex, PTR_ERR(br));
-+ return -1;
-+}
-+
-+void au_dpri_sb(struct super_block *sb)
-+{
-+ struct au_sbinfo *sbinfo;
-+ aufs_bindex_t bindex;
-+ int err;
-+ /* to reduce stack size */
-+ struct {
-+ struct vfsmount mnt;
-+ struct au_branch fake;
-+ } *a;
-+
-+ /* this function can be called from magic sysrq */
-+ a = kzalloc(sizeof(*a), GFP_ATOMIC);
-+ if (unlikely(!a)) {
-+ dpri("no memory\n");
-+ return;
-+ }
-+
-+ a->mnt.mnt_sb = sb;
-+ a->fake.br_path.mnt = &a->mnt;
-+ err = do_pri_br(-1, &a->fake);
-+ au_kfree_rcu(a);
-+ dpri("dev 0x%x\n", sb->s_dev);
-+ if (err || !au_test_aufs(sb))
-+ return;
-+
-+ sbinfo = au_sbi(sb);
-+ if (!sbinfo)
-+ return;
-+ dpri("nw %d, gen %u, kobj %d\n",
-+ atomic_read(&sbinfo->si_nowait.nw_len), sbinfo->si_generation,
-+ kref_read(&sbinfo->si_kobj.kref));
-+ for (bindex = 0; bindex <= sbinfo->si_bbot; bindex++)
-+ do_pri_br(bindex, sbinfo->si_branch[0 + bindex]);
-+}
-+
-+/* ---------------------------------------------------------------------- */
-+
-+void __au_dbg_verify_dinode(struct dentry *dentry, const char *func, int line)
-+{
-+ struct inode *h_inode, *inode = d_inode(dentry);
-+ struct dentry *h_dentry;
-+ aufs_bindex_t bindex, bbot, bi;
-+
-+ if (!inode /* || au_di(dentry)->di_lsc == AuLsc_DI_TMP */)
-+ return;
-+
-+ bbot = au_dbbot(dentry);
-+ bi = au_ibbot(inode);
-+ if (bi < bbot)
-+ bbot = bi;
-+ bindex = au_dbtop(dentry);
-+ bi = au_ibtop(inode);
-+ if (bi > bindex)
-+ bindex = bi;
-+
-+ for (; bindex <= bbot; bindex++) {
-+ h_dentry = au_h_dptr(dentry, bindex);
-+ if (!h_dentry)
-+ continue;
-+ h_inode = au_h_iptr(inode, bindex);
-+ if (unlikely(h_inode != d_inode(h_dentry))) {
-+ au_debug_on();
-+ AuDbg("b%d, %s:%d\n", bindex, func, line);
-+ AuDbgDentry(dentry);
-+ AuDbgInode(inode);
-+ au_debug_off();
-+ BUG();
-+ }
-+ }
-+}
-+
-+void au_dbg_verify_gen(struct dentry *parent, unsigned int sigen)
-+{
-+ int err, i, j;
-+ struct au_dcsub_pages dpages;
-+ struct au_dpage *dpage;
-+ struct dentry **dentries;
-+
-+ err = au_dpages_init(&dpages, GFP_NOFS);
-+ AuDebugOn(err);
-+ err = au_dcsub_pages_rev_aufs(&dpages, parent, /*do_include*/1);
-+ AuDebugOn(err);
-+ for (i = dpages.ndpage - 1; !err && i >= 0; i--) {
-+ dpage = dpages.dpages + i;
-+ dentries = dpage->dentries;
-+ for (j = dpage->ndentry - 1; !err && j >= 0; j--)
-+ AuDebugOn(au_digen_test(dentries[j], sigen));
-+ }
-+ au_dpages_free(&dpages);
-+}
-+
-+void au_dbg_verify_kthread(void)
-+{
-+ if (au_wkq_test()) {
-+ au_dbg_blocked();
-+ /*
-+ * It may be recursive, but udba=notify between two aufs mounts,
-+ * where a single ro branch is shared, is not a problem.
-+ */
-+ /* WARN_ON(1); */
-+ }
-+}
-+
-+/* ---------------------------------------------------------------------- */
-+
-+int __init au_debug_init(void)
-+{
-+ aufs_bindex_t bindex;
-+ struct au_vdir_destr destr;
-+
-+ bindex = -1;
-+ AuDebugOn(bindex >= 0);
-+
-+ destr.len = -1;
-+ AuDebugOn(destr.len < NAME_MAX);
-+
-+#ifdef CONFIG_4KSTACKS
-+ pr_warn("CONFIG_4KSTACKS is defined.\n");
-+#endif
-+
-+ return 0;
-+}
-diff --git a/fs/aufs/debug.h b/fs/aufs/debug.h
-new file mode 100644
-index 000000000000..9c52470a61fb
---- /dev/null
-+++ b/fs/aufs/debug.h
-@@ -0,0 +1,226 @@
-+/* SPDX-License-Identifier: GPL-2.0 */
-+/*
-+ * Copyright (C) 2005-2019 Junjiro R. Okajima
-+ *
-+ * This program, aufs is free software; you can redistribute it and/or modify
-+ * it under the terms of the GNU General Public License as published by
-+ * the Free Software Foundation; either version 2 of the License, or
-+ * (at your option) any later version.
-+ *
-+ * This program is distributed in the hope that it will be useful,
-+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
-+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
-+ * GNU General Public License for more details.
-+ *
-+ * You should have received a copy of the GNU General Public License
-+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
-+ */
-+
-+/*
-+ * debug print functions
-+ */
-+
-+#ifndef __AUFS_DEBUG_H__
-+#define __AUFS_DEBUG_H__
-+
-+#ifdef __KERNEL__
-+
-+#include <linux/atomic.h>
-+#include <linux/module.h>
-+#include <linux/kallsyms.h>
-+#include <linux/sysrq.h>
-+
-+#ifdef CONFIG_AUFS_DEBUG
-+#define AuDebugOn(a) BUG_ON(a)
-+
-+/* module parameter */
-+extern atomic_t aufs_debug;
-+static inline void au_debug_on(void)
-+{
-+ atomic_inc(&aufs_debug);
-+}
-+static inline void au_debug_off(void)
-+{
-+ atomic_dec_if_positive(&aufs_debug);
-+}
-+
-+static inline int au_debug_test(void)
-+{
-+ return atomic_read(&aufs_debug) > 0;
-+}
-+#else
-+#define AuDebugOn(a) do {} while (0)
-+AuStubVoid(au_debug_on, void)
-+AuStubVoid(au_debug_off, void)
-+AuStubInt0(au_debug_test, void)
-+#endif /* CONFIG_AUFS_DEBUG */
-+
-+#define param_check_atomic_t(name, p) __param_check(name, p, atomic_t)
-+
-+/* ---------------------------------------------------------------------- */
-+
-+/* debug print */
-+
-+#define AuDbg(fmt, ...) do { \
-+ if (au_debug_test()) \
-+ pr_debug("DEBUG: " fmt, ##__VA_ARGS__); \
-+} while (0)
-+#define AuLabel(l) AuDbg(#l "\n")
-+#define AuIOErr(fmt, ...) pr_err("I/O Error, " fmt, ##__VA_ARGS__)
-+#define AuWarn1(fmt, ...) do { \
-+ static unsigned char _c; \
-+ if (!_c++) \
-+ pr_warn(fmt, ##__VA_ARGS__); \
-+} while (0)
-+
-+#define AuErr1(fmt, ...) do { \
-+ static unsigned char _c; \
-+ if (!_c++) \
-+ pr_err(fmt, ##__VA_ARGS__); \
-+} while (0)
-+
-+#define AuIOErr1(fmt, ...) do { \
-+ static unsigned char _c; \
-+ if (!_c++) \
-+ AuIOErr(fmt, ##__VA_ARGS__); \
-+} while (0)
-+
-+#define AuUnsupportMsg "This operation is not supported." \
-+ " Please report this application to aufs-users ML."
-+#define AuUnsupport(fmt, ...) do { \
-+ pr_err(AuUnsupportMsg "\n" fmt, ##__VA_ARGS__); \
-+ dump_stack(); \
-+} while (0)
-+
-+#define AuTraceErr(e) do { \
-+ if (unlikely((e) < 0)) \
-+ AuDbg("err %d\n", (int)(e)); \
-+} while (0)
-+
-+#define AuTraceErrPtr(p) do { \
-+ if (IS_ERR(p)) \
-+ AuDbg("err %ld\n", PTR_ERR(p)); \
-+} while (0)
-+
-+/* dirty macros for debug print, use with "%.*s" and caution */
-+#define AuLNPair(qstr) (qstr)->len, (qstr)->name
-+
-+/* ---------------------------------------------------------------------- */
-+
-+struct dentry;
-+#ifdef CONFIG_AUFS_DEBUG
-+extern struct mutex au_dbg_mtx;
-+extern char *au_plevel;
-+struct au_nhash;
-+void au_dpri_whlist(struct au_nhash *whlist);
-+struct au_vdir;
-+void au_dpri_vdir(struct au_vdir *vdir);
-+struct inode;
-+void au_dpri_inode(struct inode *inode);
-+void au_dpri_dalias(struct inode *inode);
-+void au_dpri_dentry(struct dentry *dentry);
-+struct file;
-+void au_dpri_file(struct file *filp);
-+struct super_block;
-+void au_dpri_sb(struct super_block *sb);
-+
-+#define au_dbg_verify_dinode(d) __au_dbg_verify_dinode(d, __func__, __LINE__)
-+void __au_dbg_verify_dinode(struct dentry *dentry, const char *func, int line);
-+void au_dbg_verify_gen(struct dentry *parent, unsigned int sigen);
-+void au_dbg_verify_kthread(void);
-+
-+int __init au_debug_init(void);
-+
-+#define AuDbgWhlist(w) do { \
-+ mutex_lock(&au_dbg_mtx); \
-+ AuDbg(#w "\n"); \
-+ au_dpri_whlist(w); \
-+ mutex_unlock(&au_dbg_mtx); \
-+} while (0)
-+
-+#define AuDbgVdir(v) do { \
-+ mutex_lock(&au_dbg_mtx); \
-+ AuDbg(#v "\n"); \
-+ au_dpri_vdir(v); \
-+ mutex_unlock(&au_dbg_mtx); \
-+} while (0)
-+
-+#define AuDbgInode(i) do { \
-+ mutex_lock(&au_dbg_mtx); \
-+ AuDbg(#i "\n"); \
-+ au_dpri_inode(i); \
-+ mutex_unlock(&au_dbg_mtx); \
-+} while (0)
-+
-+#define AuDbgDAlias(i) do { \
-+ mutex_lock(&au_dbg_mtx); \
-+ AuDbg(#i "\n"); \
-+ au_dpri_dalias(i); \
-+ mutex_unlock(&au_dbg_mtx); \
-+} while (0)
-+
-+#define AuDbgDentry(d) do { \
-+ mutex_lock(&au_dbg_mtx); \
-+ AuDbg(#d "\n"); \
-+ au_dpri_dentry(d); \
-+ mutex_unlock(&au_dbg_mtx); \
-+} while (0)
-+
-+#define AuDbgFile(f) do { \
-+ mutex_lock(&au_dbg_mtx); \
-+ AuDbg(#f "\n"); \
-+ au_dpri_file(f); \
-+ mutex_unlock(&au_dbg_mtx); \
-+} while (0)
-+
-+#define AuDbgSb(sb) do { \
-+ mutex_lock(&au_dbg_mtx); \
-+ AuDbg(#sb "\n"); \
-+ au_dpri_sb(sb); \
-+ mutex_unlock(&au_dbg_mtx); \
-+} while (0)
-+
-+#define AuDbgSym(addr) do { \
-+ char sym[KSYM_SYMBOL_LEN]; \
-+ sprint_symbol(sym, (unsigned long)addr); \
-+ AuDbg("%s\n", sym); \
-+} while (0)
-+#else
-+AuStubVoid(au_dbg_verify_dinode, struct dentry *dentry)
-+AuStubVoid(au_dbg_verify_gen, struct dentry *parent, unsigned int sigen)
-+AuStubVoid(au_dbg_verify_kthread, void)
-+AuStubInt0(__init au_debug_init, void)
-+
-+#define AuDbgWhlist(w) do {} while (0)
-+#define AuDbgVdir(v) do {} while (0)
-+#define AuDbgInode(i) do {} while (0)
-+#define AuDbgDAlias(i) do {} while (0)
-+#define AuDbgDentry(d) do {} while (0)
-+#define AuDbgFile(f) do {} while (0)
-+#define AuDbgSb(sb) do {} while (0)
-+#define AuDbgSym(addr) do {} while (0)
-+#endif /* CONFIG_AUFS_DEBUG */
-+
-+/* ---------------------------------------------------------------------- */
-+
-+#ifdef CONFIG_AUFS_MAGIC_SYSRQ
-+int __init au_sysrq_init(void);
-+void au_sysrq_fin(void);
-+
-+#ifdef CONFIG_HW_CONSOLE
-+#define au_dbg_blocked() do { \
-+ WARN_ON(1); \
-+ handle_sysrq('w'); \
-+} while (0)
-+#else
-+AuStubVoid(au_dbg_blocked, void)
-+#endif
-+
-+#else
-+AuStubInt0(__init au_sysrq_init, void)
-+AuStubVoid(au_sysrq_fin, void)
-+AuStubVoid(au_dbg_blocked, void)
-+#endif /* CONFIG_AUFS_MAGIC_SYSRQ */
-+
-+#endif /* __KERNEL__ */
-+#endif /* __AUFS_DEBUG_H__ */
-diff --git a/fs/aufs/dentry.c b/fs/aufs/dentry.c
-new file mode 100644
-index 000000000000..faf664508e64
---- /dev/null
-+++ b/fs/aufs/dentry.c
-@@ -0,0 +1,1154 @@
-+// SPDX-License-Identifier: GPL-2.0
-+/*
-+ * Copyright (C) 2005-2019 Junjiro R. Okajima
-+ *
-+ * This program, aufs is free software; you can redistribute it and/or modify
-+ * it under the terms of the GNU General Public License as published by
-+ * the Free Software Foundation; either version 2 of the License, or
-+ * (at your option) any later version.
-+ *
-+ * This program is distributed in the hope that it will be useful,
-+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
-+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
-+ * GNU General Public License for more details.
-+ *
-+ * You should have received a copy of the GNU General Public License
-+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
-+ */
-+
-+/*
-+ * lookup and dentry operations
-+ */
-+
-+#include <linux/iversion.h>
-+#include <linux/namei.h>
-+#include "aufs.h"
-+
-+/*
-+ * returns positive/negative dentry, NULL or an error.
-+ * NULL means whiteout-ed or not-found.
-+ */
-+static struct dentry*
-+au_do_lookup(struct dentry *h_parent, struct dentry *dentry,
-+ aufs_bindex_t bindex, struct au_do_lookup_args *args)
-+{
-+ struct dentry *h_dentry;
-+ struct inode *h_inode;
-+ struct au_branch *br;
-+ int wh_found, opq;
-+ unsigned char wh_able;
-+ const unsigned char allow_neg = !!au_ftest_lkup(args->flags, ALLOW_NEG);
-+ const unsigned char ignore_perm = !!au_ftest_lkup(args->flags,
-+ IGNORE_PERM);
-+
-+ wh_found = 0;
-+ br = au_sbr(dentry->d_sb, bindex);
-+ wh_able = !!au_br_whable(br->br_perm);
-+ if (wh_able)
-+ wh_found = au_wh_test(h_parent, &args->whname, ignore_perm);
-+ h_dentry = ERR_PTR(wh_found);
-+ if (!wh_found)
-+ goto real_lookup;
-+ if (unlikely(wh_found < 0))
-+ goto out;
-+
-+ /* We found a whiteout */
-+ /* au_set_dbbot(dentry, bindex); */
-+ au_set_dbwh(dentry, bindex);
-+ if (!allow_neg)
-+ return NULL; /* success */
-+
-+real_lookup:
-+ if (!ignore_perm)
-+ h_dentry = vfsub_lkup_one(args->name, h_parent);
-+ else
-+ h_dentry = au_sio_lkup_one(args->name, h_parent);
-+ if (IS_ERR(h_dentry)) {
-+ if (PTR_ERR(h_dentry) == -ENAMETOOLONG
-+ && !allow_neg)
-+ h_dentry = NULL;
-+ goto out;
-+ }
-+
-+ h_inode = d_inode(h_dentry);
-+ if (d_is_negative(h_dentry)) {
-+ if (!allow_neg)
-+ goto out_neg;
-+ } else if (wh_found
-+ || (args->type && args->type != (h_inode->i_mode & S_IFMT)))
-+ goto out_neg;
-+ else if (au_ftest_lkup(args->flags, DIRREN)
-+ /* && h_inode */
-+ && !au_dr_lkup_h_ino(args, bindex, h_inode->i_ino)) {
-+ AuDbg("b%d %pd ignored hi%llu\n", bindex, h_dentry,
-+ (unsigned long long)h_inode->i_ino);
-+ goto out_neg;
-+ }
-+
-+ if (au_dbbot(dentry) <= bindex)
-+ au_set_dbbot(dentry, bindex);
-+ if (au_dbtop(dentry) < 0 || bindex < au_dbtop(dentry))
-+ au_set_dbtop(dentry, bindex);
-+ au_set_h_dptr(dentry, bindex, h_dentry);
-+
-+ if (!d_is_dir(h_dentry)
-+ || !wh_able
-+ || (d_really_is_positive(dentry) && !d_is_dir(dentry)))
-+ goto out; /* success */
-+
-+ inode_lock_shared_nested(h_inode, AuLsc_I_CHILD);
-+ opq = au_diropq_test(h_dentry);
-+ inode_unlock_shared(h_inode);
-+ if (opq > 0)
-+ au_set_dbdiropq(dentry, bindex);
-+ else if (unlikely(opq < 0)) {
-+ au_set_h_dptr(dentry, bindex, NULL);
-+ h_dentry = ERR_PTR(opq);
-+ }
-+ goto out;
-+
-+out_neg:
-+ dput(h_dentry);
-+ h_dentry = NULL;
-+out:
-+ return h_dentry;
-+}
-+
-+static int au_test_shwh(struct super_block *sb, const struct qstr *name)
-+{
-+ if (unlikely(!au_opt_test(au_mntflags(sb), SHWH)
-+ && !strncmp(name->name, AUFS_WH_PFX, AUFS_WH_PFX_LEN)))
-+ return -EPERM;
-+ return 0;
-+}
-+
-+/*
-+ * returns the number of lower positive dentries,
-+ * otherwise an error.
-+ * can be called at unlinking with @type is zero.
-+ */
-+int au_lkup_dentry(struct dentry *dentry, aufs_bindex_t btop,
-+ unsigned int flags)
-+{
-+ int npositive, err;
-+ aufs_bindex_t bindex, btail, bdiropq;
-+ unsigned char isdir, dirperm1, dirren;
-+ struct au_do_lookup_args args = {
-+ .flags = flags,
-+ .name = &dentry->d_name
-+ };
-+ struct dentry *parent;
-+ struct super_block *sb;
-+
-+ sb = dentry->d_sb;
-+ err = au_test_shwh(sb, args.name);
-+ if (unlikely(err))
-+ goto out;
-+
-+ err = au_wh_name_alloc(&args.whname, args.name);
-+ if (unlikely(err))
-+ goto out;
-+
-+ isdir = !!d_is_dir(dentry);
-+ dirperm1 = !!au_opt_test(au_mntflags(sb), DIRPERM1);
-+ dirren = !!au_opt_test(au_mntflags(sb), DIRREN);
-+ if (dirren)
-+ au_fset_lkup(args.flags, DIRREN);
-+
-+ npositive = 0;
-+ parent = dget_parent(dentry);
-+ btail = au_dbtaildir(parent);
-+ for (bindex = btop; bindex <= btail; bindex++) {
-+ struct dentry *h_parent, *h_dentry;
-+ struct inode *h_inode, *h_dir;
-+ struct au_branch *br;
-+
-+ h_dentry = au_h_dptr(dentry, bindex);
-+ if (h_dentry) {
-+ if (d_is_positive(h_dentry))
-+ npositive++;
-+ break;
-+ }
-+ h_parent = au_h_dptr(parent, bindex);
-+ if (!h_parent || !d_is_dir(h_parent))
-+ continue;
-+
-+ if (dirren) {
-+ /* if the inum matches, then use the prepared name */
-+ err = au_dr_lkup_name(&args, bindex);
-+ if (unlikely(err))
-+ goto out_parent;
-+ }
-+
-+ h_dir = d_inode(h_parent);
-+ inode_lock_shared_nested(h_dir, AuLsc_I_PARENT);
-+ h_dentry = au_do_lookup(h_parent, dentry, bindex, &args);
-+ inode_unlock_shared(h_dir);
-+ err = PTR_ERR(h_dentry);
-+ if (IS_ERR(h_dentry))
-+ goto out_parent;
-+ if (h_dentry)
-+ au_fclr_lkup(args.flags, ALLOW_NEG);
-+ if (dirperm1)
-+ au_fset_lkup(args.flags, IGNORE_PERM);
-+
-+ if (au_dbwh(dentry) == bindex)
-+ break;
-+ if (!h_dentry)
-+ continue;
-+ if (d_is_negative(h_dentry))
-+ continue;
-+ h_inode = d_inode(h_dentry);
-+ npositive++;
-+ if (!args.type)
-+ args.type = h_inode->i_mode & S_IFMT;
-+ if (args.type != S_IFDIR)
-+ break;
-+ else if (isdir) {
-+ /* the type of lower may be different */
-+ bdiropq = au_dbdiropq(dentry);
-+ if (bdiropq >= 0 && bdiropq <= bindex)
-+ break;
-+ }
-+ br = au_sbr(sb, bindex);
-+ if (dirren
-+ && au_dr_hino_test_add(&br->br_dirren, h_inode->i_ino,
-+ /*add_ent*/NULL)) {
-+ /* prepare next name to lookup */
-+ err = au_dr_lkup(&args, dentry, bindex);
-+ if (unlikely(err))
-+ goto out_parent;
-+ }
-+ }
-+
-+ if (npositive) {
-+ AuLabel(positive);
-+ au_update_dbtop(dentry);
-+ }
-+ err = npositive;
-+ if (unlikely(!au_opt_test(au_mntflags(sb), UDBA_NONE)
-+ && au_dbtop(dentry) < 0)) {
-+ err = -EIO;
-+ AuIOErr("both of real entry and whiteout found, %pd, err %d\n",
-+ dentry, err);
-+ }
-+
-+out_parent:
-+ dput(parent);
-+ au_kfree_try_rcu(args.whname.name);
-+ if (dirren)
-+ au_dr_lkup_fin(&args);
-+out:
-+ return err;
-+}
-+
-+struct dentry *au_sio_lkup_one(struct qstr *name, struct dentry *parent)
-+{
-+ struct dentry *dentry;
-+ int wkq_err;
-+
-+ if (!au_test_h_perm_sio(d_inode(parent), MAY_EXEC))
-+ dentry = vfsub_lkup_one(name, parent);
-+ else {
-+ struct vfsub_lkup_one_args args = {
-+ .errp = &dentry,
-+ .name = name,
-+ .parent = parent
-+ };
-+
-+ wkq_err = au_wkq_wait(vfsub_call_lkup_one, &args);
-+ if (unlikely(wkq_err))
-+ dentry = ERR_PTR(wkq_err);
-+ }
-+
-+ return dentry;
-+}
-+
-+/*
-+ * lookup @dentry on @bindex which should be negative.
-+ */
-+int au_lkup_neg(struct dentry *dentry, aufs_bindex_t bindex, int wh)
-+{
-+ int err;
-+ struct dentry *parent, *h_parent, *h_dentry;
-+ struct au_branch *br;
-+
-+ parent = dget_parent(dentry);
-+ h_parent = au_h_dptr(parent, bindex);
-+ br = au_sbr(dentry->d_sb, bindex);
-+ if (wh)
-+ h_dentry = au_whtmp_lkup(h_parent, br, &dentry->d_name);
-+ else
-+ h_dentry = au_sio_lkup_one(&dentry->d_name, h_parent);
-+ err = PTR_ERR(h_dentry);
-+ if (IS_ERR(h_dentry))
-+ goto out;
-+ if (unlikely(d_is_positive(h_dentry))) {
-+ err = -EIO;
-+ AuIOErr("%pd should be negative on b%d.\n", h_dentry, bindex);
-+ dput(h_dentry);
-+ goto out;
-+ }
-+
-+ err = 0;
-+ if (bindex < au_dbtop(dentry))
-+ au_set_dbtop(dentry, bindex);
-+ if (au_dbbot(dentry) < bindex)
-+ au_set_dbbot(dentry, bindex);
-+ au_set_h_dptr(dentry, bindex, h_dentry);
-+
-+out:
-+ dput(parent);
-+ return err;
-+}
-+
-+/* ---------------------------------------------------------------------- */
-+
-+/* subset of struct inode */
-+struct au_iattr {
-+ unsigned long i_ino;
-+ /* unsigned int i_nlink; */
-+ kuid_t i_uid;
-+ kgid_t i_gid;
-+ u64 i_version;
-+/*
-+ loff_t i_size;
-+ blkcnt_t i_blocks;
-+*/
-+ umode_t i_mode;
-+};
-+
-+static void au_iattr_save(struct au_iattr *ia, struct inode *h_inode)
-+{
-+ ia->i_ino = h_inode->i_ino;
-+ /* ia->i_nlink = h_inode->i_nlink; */
-+ ia->i_uid = h_inode->i_uid;
-+ ia->i_gid = h_inode->i_gid;
-+ ia->i_version = inode_query_iversion(h_inode);
-+/*
-+ ia->i_size = h_inode->i_size;
-+ ia->i_blocks = h_inode->i_blocks;
-+*/
-+ ia->i_mode = (h_inode->i_mode & S_IFMT);
-+}
-+
-+static int au_iattr_test(struct au_iattr *ia, struct inode *h_inode)
-+{
-+ return ia->i_ino != h_inode->i_ino
-+ /* || ia->i_nlink != h_inode->i_nlink */
-+ || !uid_eq(ia->i_uid, h_inode->i_uid)
-+ || !gid_eq(ia->i_gid, h_inode->i_gid)
-+ || !inode_eq_iversion(h_inode, ia->i_version)
-+/*
-+ || ia->i_size != h_inode->i_size
-+ || ia->i_blocks != h_inode->i_blocks
-+*/
-+ || ia->i_mode != (h_inode->i_mode & S_IFMT);
-+}
-+
-+static int au_h_verify_dentry(struct dentry *h_dentry, struct dentry *h_parent,
-+ struct au_branch *br)
-+{
-+ int err;
-+ struct au_iattr ia;
-+ struct inode *h_inode;
-+ struct dentry *h_d;
-+ struct super_block *h_sb;
-+
-+ err = 0;
-+ memset(&ia, -1, sizeof(ia));
-+ h_sb = h_dentry->d_sb;
-+ h_inode = NULL;
-+ if (d_is_positive(h_dentry)) {
-+ h_inode = d_inode(h_dentry);
-+ au_iattr_save(&ia, h_inode);
-+ } else if (au_test_nfs(h_sb) || au_test_fuse(h_sb))
-+ /* nfs d_revalidate may return 0 for negative dentry */
-+ /* fuse d_revalidate always return 0 for negative dentry */
-+ goto out;
-+
-+ /* main purpose is namei.c:cached_lookup() and d_revalidate */
-+ h_d = vfsub_lkup_one(&h_dentry->d_name, h_parent);
-+ err = PTR_ERR(h_d);
-+ if (IS_ERR(h_d))
-+ goto out;
-+
-+ err = 0;
-+ if (unlikely(h_d != h_dentry
-+ || d_inode(h_d) != h_inode
-+ || (h_inode && au_iattr_test(&ia, h_inode))))
-+ err = au_busy_or_stale();
-+ dput(h_d);
-+
-+out:
-+ AuTraceErr(err);
-+ return err;
-+}
-+
-+int au_h_verify(struct dentry *h_dentry, unsigned int udba, struct inode *h_dir,
-+ struct dentry *h_parent, struct au_branch *br)
-+{
-+ int err;
-+
-+ err = 0;
-+ if (udba == AuOpt_UDBA_REVAL
-+ && !au_test_fs_remote(h_dentry->d_sb)) {
-+ IMustLock(h_dir);
-+ err = (d_inode(h_dentry->d_parent) != h_dir);
-+ } else if (udba != AuOpt_UDBA_NONE)
-+ err = au_h_verify_dentry(h_dentry, h_parent, br);
-+
-+ return err;
-+}
-+
-+/* ---------------------------------------------------------------------- */
-+
-+static int au_do_refresh_hdentry(struct dentry *dentry, struct dentry *parent)
-+{
-+ int err;
-+ aufs_bindex_t new_bindex, bindex, bbot, bwh, bdiropq;
-+ struct au_hdentry tmp, *p, *q;
-+ struct au_dinfo *dinfo;
-+ struct super_block *sb;
-+
-+ DiMustWriteLock(dentry);
-+
-+ sb = dentry->d_sb;
-+ dinfo = au_di(dentry);
-+ bbot = dinfo->di_bbot;
-+ bwh = dinfo->di_bwh;
-+ bdiropq = dinfo->di_bdiropq;
-+ bindex = dinfo->di_btop;
-+ p = au_hdentry(dinfo, bindex);
-+ for (; bindex <= bbot; bindex++, p++) {
-+ if (!p->hd_dentry)
-+ continue;
-+
-+ new_bindex = au_br_index(sb, p->hd_id);
-+ if (new_bindex == bindex)
-+ continue;
-+
-+ if (dinfo->di_bwh == bindex)
-+ bwh = new_bindex;
-+ if (dinfo->di_bdiropq == bindex)
-+ bdiropq = new_bindex;
-+ if (new_bindex < 0) {
-+ au_hdput(p);
-+ p->hd_dentry = NULL;
-+ continue;
-+ }
-+
-+ /* swap two lower dentries, and loop again */
-+ q = au_hdentry(dinfo, new_bindex);
-+ tmp = *q;
-+ *q = *p;
-+ *p = tmp;
-+ if (tmp.hd_dentry) {
-+ bindex--;
-+ p--;
-+ }
-+ }
-+
-+ dinfo->di_bwh = -1;
-+ if (bwh >= 0 && bwh <= au_sbbot(sb) && au_sbr_whable(sb, bwh))
-+ dinfo->di_bwh = bwh;
-+
-+ dinfo->di_bdiropq = -1;
-+ if (bdiropq >= 0
-+ && bdiropq <= au_sbbot(sb)
-+ && au_sbr_whable(sb, bdiropq))
-+ dinfo->di_bdiropq = bdiropq;
-+
-+ err = -EIO;
-+ dinfo->di_btop = -1;
-+ dinfo->di_bbot = -1;
-+ bbot = au_dbbot(parent);
-+ bindex = 0;
-+ p = au_hdentry(dinfo, bindex);
-+ for (; bindex <= bbot; bindex++, p++)
-+ if (p->hd_dentry) {
-+ dinfo->di_btop = bindex;
-+ break;
-+ }
-+
-+ if (dinfo->di_btop >= 0) {
-+ bindex = bbot;
-+ p = au_hdentry(dinfo, bindex);
-+ for (; bindex >= 0; bindex--, p--)
-+ if (p->hd_dentry) {
-+ dinfo->di_bbot = bindex;
-+ err = 0;
-+ break;
-+ }
-+ }
-+
-+ return err;
-+}
-+
-+static void au_do_hide(struct dentry *dentry)
-+{
-+ struct inode *inode;
-+
-+ if (d_really_is_positive(dentry)) {
-+ inode = d_inode(dentry);
-+ if (!d_is_dir(dentry)) {
-+ if (inode->i_nlink && !d_unhashed(dentry))
-+ drop_nlink(inode);
-+ } else {
-+ clear_nlink(inode);
-+ /* stop next lookup */
-+ inode->i_flags |= S_DEAD;
-+ }
-+ smp_mb(); /* necessary? */
-+ }
-+ d_drop(dentry);
-+}
-+
-+static int au_hide_children(struct dentry *parent)
-+{
-+ int err, i, j, ndentry;
-+ struct au_dcsub_pages dpages;
-+ struct au_dpage *dpage;
-+ struct dentry *dentry;
-+
-+ err = au_dpages_init(&dpages, GFP_NOFS);
-+ if (unlikely(err))
-+ goto out;
-+ err = au_dcsub_pages(&dpages, parent, NULL, NULL);
-+ if (unlikely(err))
-+ goto out_dpages;
-+
-+ /* in reverse order */
-+ for (i = dpages.ndpage - 1; i >= 0; i--) {
-+ dpage = dpages.dpages + i;
-+ ndentry = dpage->ndentry;
-+ for (j = ndentry - 1; j >= 0; j--) {
-+ dentry = dpage->dentries[j];
-+ if (dentry != parent)
-+ au_do_hide(dentry);
-+ }
-+ }
-+
-+out_dpages:
-+ au_dpages_free(&dpages);
-+out:
-+ return err;
-+}
-+
-+static void au_hide(struct dentry *dentry)
-+{
-+ int err;
-+
-+ AuDbgDentry(dentry);
-+ if (d_is_dir(dentry)) {
-+ /* shrink_dcache_parent(dentry); */
-+ err = au_hide_children(dentry);
-+ if (unlikely(err))
-+ AuIOErr("%pd, failed hiding children, ignored %d\n",
-+ dentry, err);
-+ }
-+ au_do_hide(dentry);
-+}
-+
-+/*
-+ * By adding a dirty branch, a cached dentry may be affected in various ways.
-+ *
-+ * a dirty branch is added
-+ * - on the top of layers
-+ * - in the middle of layers
-+ * - to the bottom of layers
-+ *
-+ * on the added branch there exists
-+ * - a whiteout
-+ * - a diropq
-+ * - a same named entry
-+ * + exist
-+ * * negative --> positive
-+ * * positive --> positive
-+ * - type is unchanged
-+ * - type is changed
-+ * + doesn't exist
-+ * * negative --> negative
-+ * * positive --> negative (rejected by au_br_del() for non-dir case)
-+ * - none
-+ */
-+static int au_refresh_by_dinfo(struct dentry *dentry, struct au_dinfo *dinfo,
-+ struct au_dinfo *tmp)
-+{
-+ int err;
-+ aufs_bindex_t bindex, bbot;
-+ struct {
-+ struct dentry *dentry;
-+ struct inode *inode;
-+ mode_t mode;
-+ } orig_h, tmp_h = {
-+ .dentry = NULL
-+ };
-+ struct au_hdentry *hd;
-+ struct inode *inode, *h_inode;
-+ struct dentry *h_dentry;
-+
-+ err = 0;
-+ AuDebugOn(dinfo->di_btop < 0);
-+ orig_h.mode = 0;
-+ orig_h.dentry = au_hdentry(dinfo, dinfo->di_btop)->hd_dentry;
-+ orig_h.inode = NULL;
-+ if (d_is_positive(orig_h.dentry)) {
-+ orig_h.inode = d_inode(orig_h.dentry);
-+ orig_h.mode = orig_h.inode->i_mode & S_IFMT;
-+ }
-+ if (tmp->di_btop >= 0) {
-+ tmp_h.dentry = au_hdentry(tmp, tmp->di_btop)->hd_dentry;
-+ if (d_is_positive(tmp_h.dentry)) {
-+ tmp_h.inode = d_inode(tmp_h.dentry);
-+ tmp_h.mode = tmp_h.inode->i_mode & S_IFMT;
-+ }
-+ }
-+
-+ inode = NULL;
-+ if (d_really_is_positive(dentry))
-+ inode = d_inode(dentry);
-+ if (!orig_h.inode) {
-+ AuDbg("negative originally\n");
-+ if (inode) {
-+ au_hide(dentry);
-+ goto out;
-+ }
-+ AuDebugOn(inode);
-+ AuDebugOn(dinfo->di_btop != dinfo->di_bbot);
-+ AuDebugOn(dinfo->di_bdiropq != -1);
-+
-+ if (!tmp_h.inode) {
-+ AuDbg("negative --> negative\n");
-+ /* should have only one negative lower */
-+ if (tmp->di_btop >= 0
-+ && tmp->di_btop < dinfo->di_btop) {
-+ AuDebugOn(tmp->di_btop != tmp->di_bbot);
-+ AuDebugOn(dinfo->di_btop != dinfo->di_bbot);
-+ au_set_h_dptr(dentry, dinfo->di_btop, NULL);
-+ au_di_cp(dinfo, tmp);
-+ hd = au_hdentry(tmp, tmp->di_btop);
-+ au_set_h_dptr(dentry, tmp->di_btop,
-+ dget(hd->hd_dentry));
-+ }
-+ au_dbg_verify_dinode(dentry);
-+ } else {
-+ AuDbg("negative --> positive\n");
-+ /*
-+ * similar to the behaviour of creating with bypassing
-+ * aufs.
-+ * unhash it in order to force an error in the
-+ * succeeding create operation.
-+ * we should not set S_DEAD here.
-+ */
-+ d_drop(dentry);
-+ /* au_di_swap(tmp, dinfo); */
-+ au_dbg_verify_dinode(dentry);
-+ }
-+ } else {
-+ AuDbg("positive originally\n");
-+ /* inode may be NULL */
-+ AuDebugOn(inode && (inode->i_mode & S_IFMT) != orig_h.mode);
-+ if (!tmp_h.inode) {
-+ AuDbg("positive --> negative\n");
-+ /* or bypassing aufs */
-+ au_hide(dentry);
-+ if (tmp->di_bwh >= 0 && tmp->di_bwh <= dinfo->di_btop)
-+ dinfo->di_bwh = tmp->di_bwh;
-+ if (inode)
-+ err = au_refresh_hinode_self(inode);
-+ au_dbg_verify_dinode(dentry);
-+ } else if (orig_h.mode == tmp_h.mode) {
-+ AuDbg("positive --> positive, same type\n");
-+ if (!S_ISDIR(orig_h.mode)
-+ && dinfo->di_btop > tmp->di_btop) {
-+ /*
-+ * similar to the behaviour of removing and
-+ * creating.
-+ */
-+ au_hide(dentry);
-+ if (inode)
-+ err = au_refresh_hinode_self(inode);
-+ au_dbg_verify_dinode(dentry);
-+ } else {
-+ /* fill empty slots */
-+ if (dinfo->di_btop > tmp->di_btop)
-+ dinfo->di_btop = tmp->di_btop;
-+ if (dinfo->di_bbot < tmp->di_bbot)
-+ dinfo->di_bbot = tmp->di_bbot;
-+ dinfo->di_bwh = tmp->di_bwh;
-+ dinfo->di_bdiropq = tmp->di_bdiropq;
-+ bbot = dinfo->di_bbot;
-+ bindex = tmp->di_btop;
-+ hd = au_hdentry(tmp, bindex);
-+ for (; bindex <= bbot; bindex++, hd++) {
-+ if (au_h_dptr(dentry, bindex))
-+ continue;
-+ h_dentry = hd->hd_dentry;
-+ if (!h_dentry)
-+ continue;
-+ AuDebugOn(d_is_negative(h_dentry));
-+ h_inode = d_inode(h_dentry);
-+ AuDebugOn(orig_h.mode
-+ != (h_inode->i_mode
-+ & S_IFMT));
-+ au_set_h_dptr(dentry, bindex,
-+ dget(h_dentry));
-+ }
-+ if (inode)
-+ err = au_refresh_hinode(inode, dentry);
-+ au_dbg_verify_dinode(dentry);
-+ }
-+ } else {
-+ AuDbg("positive --> positive, different type\n");
-+ /* similar to the behaviour of removing and creating */
-+ au_hide(dentry);
-+ if (inode)
-+ err = au_refresh_hinode_self(inode);
-+ au_dbg_verify_dinode(dentry);
-+ }
-+ }
-+
-+out:
-+ return err;
-+}
-+
-+void au_refresh_dop(struct dentry *dentry, int force_reval)
-+{
-+ const struct dentry_operations *dop
-+ = force_reval ? &aufs_dop : dentry->d_sb->s_d_op;
-+ static const unsigned int mask
-+ = DCACHE_OP_REVALIDATE | DCACHE_OP_WEAK_REVALIDATE;
-+
-+ BUILD_BUG_ON(sizeof(mask) != sizeof(dentry->d_flags));
-+
-+ if (dentry->d_op == dop)
-+ return;
-+
-+ AuDbg("%pd\n", dentry);
-+ spin_lock(&dentry->d_lock);
-+ if (dop == &aufs_dop)
-+ dentry->d_flags |= mask;
-+ else
-+ dentry->d_flags &= ~mask;
-+ dentry->d_op = dop;
-+ spin_unlock(&dentry->d_lock);
-+}
-+
-+int au_refresh_dentry(struct dentry *dentry, struct dentry *parent)
-+{
-+ int err, ebrange, nbr;
-+ unsigned int sigen;
-+ struct au_dinfo *dinfo, *tmp;
-+ struct super_block *sb;
-+ struct inode *inode;
-+
-+ DiMustWriteLock(dentry);
-+ AuDebugOn(IS_ROOT(dentry));
-+ AuDebugOn(d_really_is_negative(parent));
-+
-+ sb = dentry->d_sb;
-+ sigen = au_sigen(sb);
-+ err = au_digen_test(parent, sigen);
-+ if (unlikely(err))
-+ goto out;
-+
-+ nbr = au_sbbot(sb) + 1;
-+ dinfo = au_di(dentry);
-+ err = au_di_realloc(dinfo, nbr, /*may_shrink*/0);
-+ if (unlikely(err))
-+ goto out;
-+ ebrange = au_dbrange_test(dentry);
-+ if (!ebrange)
-+ ebrange = au_do_refresh_hdentry(dentry, parent);
-+
-+ if (d_unhashed(dentry) || ebrange /* || dinfo->di_tmpfile */) {
-+ AuDebugOn(au_dbtop(dentry) < 0 && au_dbbot(dentry) >= 0);
-+ if (d_really_is_positive(dentry)) {
-+ inode = d_inode(dentry);
-+ err = au_refresh_hinode_self(inode);
-+ }
-+ au_dbg_verify_dinode(dentry);
-+ if (!err)
-+ goto out_dgen; /* success */
-+ goto out;
-+ }
-+
-+ /* temporary dinfo */
-+ AuDbgDentry(dentry);
-+ err = -ENOMEM;
-+ tmp = au_di_alloc(sb, AuLsc_DI_TMP);
-+ if (unlikely(!tmp))
-+ goto out;
-+ au_di_swap(tmp, dinfo);
-+ /* returns the number of positive dentries */
-+ /*
-+ * if current working dir is removed, it returns an error.
-+ * but the dentry is legal.
-+ */
-+ err = au_lkup_dentry(dentry, /*btop*/0, AuLkup_ALLOW_NEG);
-+ AuDbgDentry(dentry);
-+ au_di_swap(tmp, dinfo);
-+ if (err == -ENOENT)
-+ err = 0;
-+ if (err >= 0) {
-+ /* compare/refresh by dinfo */
-+ AuDbgDentry(dentry);
-+ err = au_refresh_by_dinfo(dentry, dinfo, tmp);
-+ au_dbg_verify_dinode(dentry);
-+ AuTraceErr(err);
-+ }
-+ au_di_realloc(dinfo, nbr, /*may_shrink*/1); /* harmless if err */
-+ au_rw_write_unlock(&tmp->di_rwsem);
-+ au_di_free(tmp);
-+ if (unlikely(err))
-+ goto out;
-+
-+out_dgen:
-+ au_update_digen(dentry);
-+out:
-+ if (unlikely(err && !(dentry->d_flags & DCACHE_NFSFS_RENAMED))) {
-+ AuIOErr("failed refreshing %pd, %d\n", dentry, err);
-+ AuDbgDentry(dentry);
-+ }
-+ AuTraceErr(err);
-+ return err;
-+}
-+
-+static int au_do_h_d_reval(struct dentry *h_dentry, unsigned int flags,
-+ struct dentry *dentry, aufs_bindex_t bindex)
-+{
-+ int err, valid;
-+
-+ err = 0;
-+ if (!(h_dentry->d_flags & DCACHE_OP_REVALIDATE))
-+ goto out;
-+
-+ AuDbg("b%d\n", bindex);
-+ /*
-+ * gave up supporting LOOKUP_CREATE/OPEN for lower fs,
-+ * due to whiteout and branch permission.
-+ */
-+ flags &= ~(/*LOOKUP_PARENT |*/ LOOKUP_OPEN | LOOKUP_CREATE
-+ | LOOKUP_FOLLOW | LOOKUP_EXCL);
-+ /* it may return tri-state */
-+ valid = h_dentry->d_op->d_revalidate(h_dentry, flags);
-+
-+ if (unlikely(valid < 0))
-+ err = valid;
-+ else if (!valid)
-+ err = -EINVAL;
-+
-+out:
-+ AuTraceErr(err);
-+ return err;
-+}
-+
-+/* todo: remove this */
-+static int h_d_revalidate(struct dentry *dentry, struct inode *inode,
-+ unsigned int flags, int do_udba, int dirren)
-+{
-+ int err;
-+ umode_t mode, h_mode;
-+ aufs_bindex_t bindex, btail, btop, ibs, ibe;
-+ unsigned char plus, unhashed, is_root, h_plus, h_nfs, tmpfile;
-+ struct inode *h_inode, *h_cached_inode;
-+ struct dentry *h_dentry;
-+ struct qstr *name, *h_name;
-+
-+ err = 0;
-+ plus = 0;
-+ mode = 0;
-+ ibs = -1;
-+ ibe = -1;
-+ unhashed = !!d_unhashed(dentry);
-+ is_root = !!IS_ROOT(dentry);
-+ name = &dentry->d_name;
-+ tmpfile = au_di(dentry)->di_tmpfile;
-+
-+ /*
-+ * Theoretically, REVAL test should be unnecessary in case of
-+ * {FS,I}NOTIFY.
-+ * But {fs,i}notify doesn't fire some necessary events,
-+ * IN_ATTRIB for atime/nlink/pageio
-+ * Let's do REVAL test too.
-+ */
-+ if (do_udba && inode) {
-+ mode = (inode->i_mode & S_IFMT);
-+ plus = (inode->i_nlink > 0);
-+ ibs = au_ibtop(inode);
-+ ibe = au_ibbot(inode);
-+ }
-+
-+ btop = au_dbtop(dentry);
-+ btail = btop;
-+ if (inode && S_ISDIR(inode->i_mode))
-+ btail = au_dbtaildir(dentry);
-+ for (bindex = btop; bindex <= btail; bindex++) {
-+ h_dentry = au_h_dptr(dentry, bindex);
-+ if (!h_dentry)
-+ continue;
-+
-+ AuDbg("b%d, %pd\n", bindex, h_dentry);
-+ h_nfs = !!au_test_nfs(h_dentry->d_sb);
-+ spin_lock(&h_dentry->d_lock);
-+ h_name = &h_dentry->d_name;
-+ if (unlikely(do_udba
-+ && !is_root
-+ && ((!h_nfs
-+ && (unhashed != !!d_unhashed(h_dentry)
-+ || (!tmpfile && !dirren
-+ && !au_qstreq(name, h_name))
-+ ))
-+ || (h_nfs
-+ && !(flags & LOOKUP_OPEN)
-+ && (h_dentry->d_flags
-+ & DCACHE_NFSFS_RENAMED)))
-+ )) {
-+ int h_unhashed;
-+
-+ h_unhashed = d_unhashed(h_dentry);
-+ spin_unlock(&h_dentry->d_lock);
-+ AuDbg("unhash 0x%x 0x%x, %pd %pd\n",
-+ unhashed, h_unhashed, dentry, h_dentry);
-+ goto err;
-+ }
-+ spin_unlock(&h_dentry->d_lock);
-+
-+ err = au_do_h_d_reval(h_dentry, flags, dentry, bindex);
-+ if (unlikely(err))
-+ /* do not goto err, to keep the errno */
-+ break;
-+
-+ /* todo: plink too? */
-+ if (!do_udba)
-+ continue;
-+
-+ /* UDBA tests */
-+ if (unlikely(!!inode != d_is_positive(h_dentry)))
-+ goto err;
-+
-+ h_inode = NULL;
-+ if (d_is_positive(h_dentry))
-+ h_inode = d_inode(h_dentry);
-+ h_plus = plus;
-+ h_mode = mode;
-+ h_cached_inode = h_inode;
-+ if (h_inode) {
-+ h_mode = (h_inode->i_mode & S_IFMT);
-+ h_plus = (h_inode->i_nlink > 0);
-+ }
-+ if (inode && ibs <= bindex && bindex <= ibe)
-+ h_cached_inode = au_h_iptr(inode, bindex);
-+
-+ if (!h_nfs) {
-+ if (unlikely(plus != h_plus && !tmpfile))
-+ goto err;
-+ } else {
-+ if (unlikely(!(h_dentry->d_flags & DCACHE_NFSFS_RENAMED)
-+ && !is_root
-+ && !IS_ROOT(h_dentry)
-+ && unhashed != d_unhashed(h_dentry)))
-+ goto err;
-+ }
-+ if (unlikely(mode != h_mode
-+ || h_cached_inode != h_inode))
-+ goto err;
-+ continue;
-+
-+err:
-+ err = -EINVAL;
-+ break;
-+ }
-+
-+ AuTraceErr(err);
-+ return err;
-+}
-+
-+/* todo: consolidate with do_refresh() and au_reval_for_attr() */
-+static int simple_reval_dpath(struct dentry *dentry, unsigned int sigen)
-+{
-+ int err;
-+ struct dentry *parent;
-+
-+ if (!au_digen_test(dentry, sigen))
-+ return 0;
-+
-+ parent = dget_parent(dentry);
-+ di_read_lock_parent(parent, AuLock_IR);
-+ AuDebugOn(au_digen_test(parent, sigen));
-+ au_dbg_verify_gen(parent, sigen);
-+ err = au_refresh_dentry(dentry, parent);
-+ di_read_unlock(parent, AuLock_IR);
-+ dput(parent);
-+ AuTraceErr(err);
-+ return err;
-+}
-+
-+int au_reval_dpath(struct dentry *dentry, unsigned int sigen)
-+{
-+ int err;
-+ struct dentry *d, *parent;
-+
-+ if (!au_ftest_si(au_sbi(dentry->d_sb), FAILED_REFRESH_DIR))
-+ return simple_reval_dpath(dentry, sigen);
-+
-+ /* slow loop, keep it simple and stupid */
-+ /* cf: au_cpup_dirs() */
-+ err = 0;
-+ parent = NULL;
-+ while (au_digen_test(dentry, sigen)) {
-+ d = dentry;
-+ while (1) {
-+ dput(parent);
-+ parent = dget_parent(d);
-+ if (!au_digen_test(parent, sigen))
-+ break;
-+ d = parent;
-+ }
-+
-+ if (d != dentry)
-+ di_write_lock_child2(d);
-+
-+ /* someone might update our dentry while we were sleeping */
-+ if (au_digen_test(d, sigen)) {
-+ /*
-+ * todo: consolidate with simple_reval_dpath(),
-+ * do_refresh() and au_reval_for_attr().
-+ */
-+ di_read_lock_parent(parent, AuLock_IR);
-+ err = au_refresh_dentry(d, parent);
-+ di_read_unlock(parent, AuLock_IR);
-+ }
-+
-+ if (d != dentry)
-+ di_write_unlock(d);
-+ dput(parent);
-+ if (unlikely(err))
-+ break;
-+ }
-+
-+ return err;
-+}
-+
-+/*
-+ * if valid returns 1, otherwise 0.
-+ */
-+static int aufs_d_revalidate(struct dentry *dentry, unsigned int flags)
-+{
-+ int valid, err;
-+ unsigned int sigen;
-+ unsigned char do_udba, dirren;
-+ struct super_block *sb;
-+ struct inode *inode;
-+
-+ /* todo: support rcu-walk? */
-+ if (flags & LOOKUP_RCU)
-+ return -ECHILD;
-+
-+ valid = 0;
-+ if (unlikely(!au_di(dentry)))
-+ goto out;
-+
-+ valid = 1;
-+ sb = dentry->d_sb;
-+ /*
-+ * todo: very ugly
-+ * i_mutex of parent dir may be held,
-+ * but we should not return 'invalid' due to busy.
-+ */
-+ err = aufs_read_lock(dentry, AuLock_FLUSH | AuLock_DW | AuLock_NOPLM);
-+ if (unlikely(err)) {
-+ valid = err;
-+ AuTraceErr(err);
-+ goto out;
-+ }
-+ inode = NULL;
-+ if (d_really_is_positive(dentry))
-+ inode = d_inode(dentry);
-+ if (unlikely(inode && au_is_bad_inode(inode))) {
-+ err = -EINVAL;
-+ AuTraceErr(err);
-+ goto out_dgrade;
-+ }
-+ if (unlikely(au_dbrange_test(dentry))) {
-+ err = -EINVAL;
-+ AuTraceErr(err);
-+ goto out_dgrade;
-+ }
-+
-+ sigen = au_sigen(sb);
-+ if (au_digen_test(dentry, sigen)) {
-+ AuDebugOn(IS_ROOT(dentry));
-+ err = au_reval_dpath(dentry, sigen);
-+ if (unlikely(err)) {
-+ AuTraceErr(err);
-+ goto out_dgrade;
-+ }
-+ }
-+ di_downgrade_lock(dentry, AuLock_IR);
-+
-+ err = -EINVAL;
-+ if (!(flags & (LOOKUP_OPEN | LOOKUP_EMPTY))
-+ && inode
-+ && !(inode->i_state && I_LINKABLE)
-+ && (IS_DEADDIR(inode) || !inode->i_nlink)) {
-+ AuTraceErr(err);
-+ goto out_inval;
-+ }
-+
-+ do_udba = !au_opt_test(au_mntflags(sb), UDBA_NONE);
-+ if (do_udba && inode) {
-+ aufs_bindex_t btop = au_ibtop(inode);
-+ struct inode *h_inode;
-+
-+ if (btop >= 0) {
-+ h_inode = au_h_iptr(inode, btop);
-+ if (h_inode && au_test_higen(inode, h_inode)) {
-+ AuTraceErr(err);
-+ goto out_inval;
-+ }
-+ }
-+ }
-+
-+ dirren = !!au_opt_test(au_mntflags(sb), DIRREN);
-+ err = h_d_revalidate(dentry, inode, flags, do_udba, dirren);
-+ if (unlikely(!err && do_udba && au_dbtop(dentry) < 0)) {
-+ err = -EIO;
-+ AuDbg("both of real entry and whiteout found, %p, err %d\n",
-+ dentry, err);
-+ }
-+ goto out_inval;
-+
-+out_dgrade:
-+ di_downgrade_lock(dentry, AuLock_IR);
-+out_inval:
-+ aufs_read_unlock(dentry, AuLock_IR);
-+ AuTraceErr(err);
-+ valid = !err;
-+out:
-+ if (!valid) {
-+ AuDbg("%pd invalid, %d\n", dentry, valid);
-+ d_drop(dentry);
-+ }
-+ return valid;
-+}
-+
-+static void aufs_d_release(struct dentry *dentry)
-+{
-+ if (au_di(dentry)) {
-+ au_di_fin(dentry);
-+ au_hn_di_reinit(dentry);
-+ }
-+}
-+
-+const struct dentry_operations aufs_dop = {
-+ .d_revalidate = aufs_d_revalidate,
-+ .d_weak_revalidate = aufs_d_revalidate,
-+ .d_release = aufs_d_release
-+};
-+
-+/* aufs_dop without d_revalidate */
-+const struct dentry_operations aufs_dop_noreval = {
-+ .d_release = aufs_d_release
-+};
-diff --git a/fs/aufs/dentry.h b/fs/aufs/dentry.h
-new file mode 100644
-index 000000000000..3b443fc7eef0
---- /dev/null
-+++ b/fs/aufs/dentry.h
-@@ -0,0 +1,268 @@
-+/* SPDX-License-Identifier: GPL-2.0 */
-+/*
-+ * Copyright (C) 2005-2019 Junjiro R. Okajima
-+ *
-+ * This program, aufs is free software; you can redistribute it and/or modify
-+ * it under the terms of the GNU General Public License as published by
-+ * the Free Software Foundation; either version 2 of the License, or
-+ * (at your option) any later version.
-+ *
-+ * This program is distributed in the hope that it will be useful,
-+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
-+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
-+ * GNU General Public License for more details.
-+ *
-+ * You should have received a copy of the GNU General Public License
-+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
-+ */
-+
-+/*
-+ * lookup and dentry operations
-+ */
-+
-+#ifndef __AUFS_DENTRY_H__
-+#define __AUFS_DENTRY_H__
-+
-+#ifdef __KERNEL__
-+
-+#include <linux/dcache.h>
-+#include "dirren.h"
-+#include "rwsem.h"
-+
-+struct au_hdentry {
-+ struct dentry *hd_dentry;
-+ aufs_bindex_t hd_id;
-+};
-+
-+struct au_dinfo {
-+ atomic_t di_generation;
-+
-+ struct au_rwsem di_rwsem;
-+ aufs_bindex_t di_btop, di_bbot, di_bwh, di_bdiropq;
-+ unsigned char di_tmpfile; /* to allow the different name */
-+ struct au_hdentry *di_hdentry;
-+ struct rcu_head rcu;
-+} ____cacheline_aligned_in_smp;
-+
-+/* ---------------------------------------------------------------------- */
-+
-+/* flags for au_lkup_dentry() */
-+#define AuLkup_ALLOW_NEG 1
-+#define AuLkup_IGNORE_PERM (1 << 1)
-+#define AuLkup_DIRREN (1 << 2)
-+#define au_ftest_lkup(flags, name) ((flags) & AuLkup_##name)
-+#define au_fset_lkup(flags, name) \
-+ do { (flags) |= AuLkup_##name; } while (0)
-+#define au_fclr_lkup(flags, name) \
-+ do { (flags) &= ~AuLkup_##name; } while (0)
-+
-+#ifndef CONFIG_AUFS_DIRREN
-+#undef AuLkup_DIRREN
-+#define AuLkup_DIRREN 0
-+#endif
-+
-+struct au_do_lookup_args {
-+ unsigned int flags;
-+ mode_t type;
-+ struct qstr whname, *name;
-+ struct au_dr_lookup dirren;
-+};
-+
-+/* ---------------------------------------------------------------------- */
-+
-+/* dentry.c */
-+extern const struct dentry_operations aufs_dop, aufs_dop_noreval;
-+struct au_branch;
-+struct dentry *au_sio_lkup_one(struct qstr *name, struct dentry *parent);
-+int au_h_verify(struct dentry *h_dentry, unsigned int udba, struct inode *h_dir,
-+ struct dentry *h_parent, struct au_branch *br);
-+
-+int au_lkup_dentry(struct dentry *dentry, aufs_bindex_t btop,
-+ unsigned int flags);
-+int au_lkup_neg(struct dentry *dentry, aufs_bindex_t bindex, int wh);
-+int au_refresh_dentry(struct dentry *dentry, struct dentry *parent);
-+int au_reval_dpath(struct dentry *dentry, unsigned int sigen);
-+void au_refresh_dop(struct dentry *dentry, int force_reval);
-+
-+/* dinfo.c */
-+void au_di_init_once(void *_di);
-+struct au_dinfo *au_di_alloc(struct super_block *sb, unsigned int lsc);
-+void au_di_free(struct au_dinfo *dinfo);
-+void au_di_swap(struct au_dinfo *a, struct au_dinfo *b);
-+void au_di_cp(struct au_dinfo *dst, struct au_dinfo *src);
-+int au_di_init(struct dentry *dentry);
-+void au_di_fin(struct dentry *dentry);
-+int au_di_realloc(struct au_dinfo *dinfo, int nbr, int may_shrink);
-+
-+void di_read_lock(struct dentry *d, int flags, unsigned int lsc);
-+void di_read_unlock(struct dentry *d, int flags);
-+void di_downgrade_lock(struct dentry *d, int flags);
-+void di_write_lock(struct dentry *d, unsigned int lsc);
-+void di_write_unlock(struct dentry *d);
-+void di_write_lock2_child(struct dentry *d1, struct dentry *d2, int isdir);
-+void di_write_lock2_parent(struct dentry *d1, struct dentry *d2, int isdir);
-+void di_write_unlock2(struct dentry *d1, struct dentry *d2);
-+
-+struct dentry *au_h_dptr(struct dentry *dentry, aufs_bindex_t bindex);
-+struct dentry *au_h_d_alias(struct dentry *dentry, aufs_bindex_t bindex);
-+aufs_bindex_t au_dbtail(struct dentry *dentry);
-+aufs_bindex_t au_dbtaildir(struct dentry *dentry);
-+
-+void au_set_h_dptr(struct dentry *dentry, aufs_bindex_t bindex,
-+ struct dentry *h_dentry);
-+int au_digen_test(struct dentry *dentry, unsigned int sigen);
-+int au_dbrange_test(struct dentry *dentry);
-+void au_update_digen(struct dentry *dentry);
-+void au_update_dbrange(struct dentry *dentry, int do_put_zero);
-+void au_update_dbtop(struct dentry *dentry);
-+void au_update_dbbot(struct dentry *dentry);
-+int au_find_dbindex(struct dentry *dentry, struct dentry *h_dentry);
-+
-+/* ---------------------------------------------------------------------- */
-+
-+static inline struct au_dinfo *au_di(struct dentry *dentry)
-+{
-+ return dentry->d_fsdata;
-+}
-+
-+/* ---------------------------------------------------------------------- */
-+
-+/* lock subclass for dinfo */
-+enum {
-+ AuLsc_DI_CHILD, /* child first */
-+ AuLsc_DI_CHILD2, /* rename(2), link(2), and cpup at hnotify */
-+ AuLsc_DI_CHILD3, /* copyup dirs */
-+ AuLsc_DI_PARENT,
-+ AuLsc_DI_PARENT2,
-+ AuLsc_DI_PARENT3,
-+ AuLsc_DI_TMP /* temp for replacing dinfo */
-+};
-+
-+/*
-+ * di_read_lock_child, di_write_lock_child,
-+ * di_read_lock_child2, di_write_lock_child2,
-+ * di_read_lock_child3, di_write_lock_child3,
-+ * di_read_lock_parent, di_write_lock_parent,
-+ * di_read_lock_parent2, di_write_lock_parent2,
-+ * di_read_lock_parent3, di_write_lock_parent3,
-+ */
-+#define AuReadLockFunc(name, lsc) \
-+static inline void di_read_lock_##name(struct dentry *d, int flags) \
-+{ di_read_lock(d, flags, AuLsc_DI_##lsc); }
-+
-+#define AuWriteLockFunc(name, lsc) \
-+static inline void di_write_lock_##name(struct dentry *d) \
-+{ di_write_lock(d, AuLsc_DI_##lsc); }
-+
-+#define AuRWLockFuncs(name, lsc) \
-+ AuReadLockFunc(name, lsc) \
-+ AuWriteLockFunc(name, lsc)
-+
-+AuRWLockFuncs(child, CHILD);
-+AuRWLockFuncs(child2, CHILD2);
-+AuRWLockFuncs(child3, CHILD3);
-+AuRWLockFuncs(parent, PARENT);
-+AuRWLockFuncs(parent2, PARENT2);
-+AuRWLockFuncs(parent3, PARENT3);
-+
-+#undef AuReadLockFunc
-+#undef AuWriteLockFunc
-+#undef AuRWLockFuncs
-+
-+#define DiMustNoWaiters(d) AuRwMustNoWaiters(&au_di(d)->di_rwsem)
-+#define DiMustAnyLock(d) AuRwMustAnyLock(&au_di(d)->di_rwsem)
-+#define DiMustWriteLock(d) AuRwMustWriteLock(&au_di(d)->di_rwsem)
-+
-+/* ---------------------------------------------------------------------- */
-+
-+/* todo: memory barrier? */
-+static inline unsigned int au_digen(struct dentry *d)
-+{
-+ return atomic_read(&au_di(d)->di_generation);
-+}
-+
-+static inline void au_h_dentry_init(struct au_hdentry *hdentry)
-+{
-+ hdentry->hd_dentry = NULL;
-+}
-+
-+static inline struct au_hdentry *au_hdentry(struct au_dinfo *di,
-+ aufs_bindex_t bindex)
-+{
-+ return di->di_hdentry + bindex;
-+}
-+
-+static inline void au_hdput(struct au_hdentry *hd)
-+{
-+ if (hd)
-+ dput(hd->hd_dentry);
-+}
-+
-+static inline aufs_bindex_t au_dbtop(struct dentry *dentry)
-+{
-+ DiMustAnyLock(dentry);
-+ return au_di(dentry)->di_btop;
-+}
-+
-+static inline aufs_bindex_t au_dbbot(struct dentry *dentry)
-+{
-+ DiMustAnyLock(dentry);
-+ return au_di(dentry)->di_bbot;
-+}
-+
-+static inline aufs_bindex_t au_dbwh(struct dentry *dentry)
-+{
-+ DiMustAnyLock(dentry);
-+ return au_di(dentry)->di_bwh;
-+}
-+
-+static inline aufs_bindex_t au_dbdiropq(struct dentry *dentry)
-+{
-+ DiMustAnyLock(dentry);
-+ return au_di(dentry)->di_bdiropq;
-+}
-+
-+/* todo: hard/soft set? */
-+static inline void au_set_dbtop(struct dentry *dentry, aufs_bindex_t bindex)
-+{
-+ DiMustWriteLock(dentry);
-+ au_di(dentry)->di_btop = bindex;
-+}
-+
-+static inline void au_set_dbbot(struct dentry *dentry, aufs_bindex_t bindex)
-+{
-+ DiMustWriteLock(dentry);
-+ au_di(dentry)->di_bbot = bindex;
-+}
-+
-+static inline void au_set_dbwh(struct dentry *dentry, aufs_bindex_t bindex)
-+{
-+ DiMustWriteLock(dentry);
-+ /* dbwh can be outside of btop - bbot range */
-+ au_di(dentry)->di_bwh = bindex;
-+}
-+
-+static inline void au_set_dbdiropq(struct dentry *dentry, aufs_bindex_t bindex)
-+{
-+ DiMustWriteLock(dentry);
-+ au_di(dentry)->di_bdiropq = bindex;
-+}
-+
-+/* ---------------------------------------------------------------------- */
-+
-+#ifdef CONFIG_AUFS_HNOTIFY
-+static inline void au_digen_dec(struct dentry *d)
-+{
-+ atomic_dec(&au_di(d)->di_generation);
-+}
-+
-+static inline void au_hn_di_reinit(struct dentry *dentry)
-+{
-+ dentry->d_fsdata = NULL;
-+}
-+#else
-+AuStubVoid(au_hn_di_reinit, struct dentry *dentry __maybe_unused)
-+#endif /* CONFIG_AUFS_HNOTIFY */
-+
-+#endif /* __KERNEL__ */
-+#endif /* __AUFS_DENTRY_H__ */
-diff --git a/fs/aufs/dinfo.c b/fs/aufs/dinfo.c
-new file mode 100644
-index 000000000000..86140548f046
---- /dev/null
-+++ b/fs/aufs/dinfo.c
-@@ -0,0 +1,554 @@
-+// SPDX-License-Identifier: GPL-2.0
-+/*
-+ * Copyright (C) 2005-2019 Junjiro R. Okajima
-+ *
-+ * This program, aufs is free software; you can redistribute it and/or modify
-+ * it under the terms of the GNU General Public License as published by
-+ * the Free Software Foundation; either version 2 of the License, or
-+ * (at your option) any later version.
-+ *
-+ * This program is distributed in the hope that it will be useful,
-+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
-+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
-+ * GNU General Public License for more details.
-+ *
-+ * You should have received a copy of the GNU General Public License
-+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
-+ */
-+
-+/*
-+ * dentry private data
-+ */
-+
-+#include "aufs.h"
-+
-+void au_di_init_once(void *_dinfo)
-+{
-+ struct au_dinfo *dinfo = _dinfo;
-+
-+ au_rw_init(&dinfo->di_rwsem);
-+}
-+
-+struct au_dinfo *au_di_alloc(struct super_block *sb, unsigned int lsc)
-+{
-+ struct au_dinfo *dinfo;
-+ int nbr, i;
-+
-+ dinfo = au_cache_alloc_dinfo();
-+ if (unlikely(!dinfo))
-+ goto out;
-+
-+ nbr = au_sbbot(sb) + 1;
-+ if (nbr <= 0)
-+ nbr = 1;
-+ dinfo->di_hdentry = kcalloc(nbr, sizeof(*dinfo->di_hdentry), GFP_NOFS);
-+ if (dinfo->di_hdentry) {
-+ au_rw_write_lock_nested(&dinfo->di_rwsem, lsc);
-+ dinfo->di_btop = -1;
-+ dinfo->di_bbot = -1;
-+ dinfo->di_bwh = -1;
-+ dinfo->di_bdiropq = -1;
-+ dinfo->di_tmpfile = 0;
-+ for (i = 0; i < nbr; i++)
-+ dinfo->di_hdentry[i].hd_id = -1;
-+ goto out;
-+ }
-+
-+ au_cache_free_dinfo(dinfo);
-+ dinfo = NULL;
-+
-+out:
-+ return dinfo;
-+}
-+
-+void au_di_free(struct au_dinfo *dinfo)
-+{
-+ struct au_hdentry *p;
-+ aufs_bindex_t bbot, bindex;
-+
-+ /* dentry may not be revalidated */
-+ bindex = dinfo->di_btop;
-+ if (bindex >= 0) {
-+ bbot = dinfo->di_bbot;
-+ p = au_hdentry(dinfo, bindex);
-+ while (bindex++ <= bbot)
-+ au_hdput(p++);
-+ }
-+ au_kfree_try_rcu(dinfo->di_hdentry);
-+ au_cache_free_dinfo(dinfo);
-+}
-+
-+void au_di_swap(struct au_dinfo *a, struct au_dinfo *b)
-+{
-+ struct au_hdentry *p;
-+ aufs_bindex_t bi;
-+
-+ AuRwMustWriteLock(&a->di_rwsem);
-+ AuRwMustWriteLock(&b->di_rwsem);
-+
-+#define DiSwap(v, name) \
-+ do { \
-+ v = a->di_##name; \
-+ a->di_##name = b->di_##name; \
-+ b->di_##name = v; \
-+ } while (0)
-+
-+ DiSwap(p, hdentry);
-+ DiSwap(bi, btop);
-+ DiSwap(bi, bbot);
-+ DiSwap(bi, bwh);
-+ DiSwap(bi, bdiropq);
-+ /* smp_mb(); */
-+
-+#undef DiSwap
-+}
-+
-+void au_di_cp(struct au_dinfo *dst, struct au_dinfo *src)
-+{
-+ AuRwMustWriteLock(&dst->di_rwsem);
-+ AuRwMustWriteLock(&src->di_rwsem);
-+
-+ dst->di_btop = src->di_btop;
-+ dst->di_bbot = src->di_bbot;
-+ dst->di_bwh = src->di_bwh;
-+ dst->di_bdiropq = src->di_bdiropq;
-+ /* smp_mb(); */
-+}
-+
-+int au_di_init(struct dentry *dentry)
-+{
-+ int err;
-+ struct super_block *sb;
-+ struct au_dinfo *dinfo;
-+
-+ err = 0;
-+ sb = dentry->d_sb;
-+ dinfo = au_di_alloc(sb, AuLsc_DI_CHILD);
-+ if (dinfo) {
-+ atomic_set(&dinfo->di_generation, au_sigen(sb));
-+ /* smp_mb(); */ /* atomic_set */
-+ dentry->d_fsdata = dinfo;
-+ } else
-+ err = -ENOMEM;
-+
-+ return err;
-+}
-+
-+void au_di_fin(struct dentry *dentry)
-+{
-+ struct au_dinfo *dinfo;
-+
-+ dinfo = au_di(dentry);
-+ AuRwDestroy(&dinfo->di_rwsem);
-+ au_di_free(dinfo);
-+}
-+
-+int au_di_realloc(struct au_dinfo *dinfo, int nbr, int may_shrink)
-+{
-+ int err, sz;
-+ struct au_hdentry *hdp;
-+
-+ AuRwMustWriteLock(&dinfo->di_rwsem);
-+
-+ err = -ENOMEM;
-+ sz = sizeof(*hdp) * (dinfo->di_bbot + 1);
-+ if (!sz)
-+ sz = sizeof(*hdp);
-+ hdp = au_kzrealloc(dinfo->di_hdentry, sz, sizeof(*hdp) * nbr, GFP_NOFS,
-+ may_shrink);
-+ if (hdp) {
-+ dinfo->di_hdentry = hdp;
-+ err = 0;
-+ }
-+
-+ return err;
-+}
-+
-+/* ---------------------------------------------------------------------- */
-+
-+static void do_ii_write_lock(struct inode *inode, unsigned int lsc)
-+{
-+ switch (lsc) {
-+ case AuLsc_DI_CHILD:
-+ ii_write_lock_child(inode);
-+ break;
-+ case AuLsc_DI_CHILD2:
-+ ii_write_lock_child2(inode);
-+ break;
-+ case AuLsc_DI_CHILD3:
-+ ii_write_lock_child3(inode);
-+ break;
-+ case AuLsc_DI_PARENT:
-+ ii_write_lock_parent(inode);
-+ break;
-+ case AuLsc_DI_PARENT2:
-+ ii_write_lock_parent2(inode);
-+ break;
-+ case AuLsc_DI_PARENT3:
-+ ii_write_lock_parent3(inode);
-+ break;
-+ default:
-+ BUG();
-+ }
-+}
-+
-+static void do_ii_read_lock(struct inode *inode, unsigned int lsc)
-+{
-+ switch (lsc) {
-+ case AuLsc_DI_CHILD:
-+ ii_read_lock_child(inode);
-+ break;
-+ case AuLsc_DI_CHILD2:
-+ ii_read_lock_child2(inode);
-+ break;
-+ case AuLsc_DI_CHILD3:
-+ ii_read_lock_child3(inode);
-+ break;
-+ case AuLsc_DI_PARENT:
-+ ii_read_lock_parent(inode);
-+ break;
-+ case AuLsc_DI_PARENT2:
-+ ii_read_lock_parent2(inode);
-+ break;
-+ case AuLsc_DI_PARENT3:
-+ ii_read_lock_parent3(inode);
-+ break;
-+ default:
-+ BUG();
-+ }
-+}
-+
-+void di_read_lock(struct dentry *d, int flags, unsigned int lsc)
-+{
-+ struct inode *inode;
-+
-+ au_rw_read_lock_nested(&au_di(d)->di_rwsem, lsc);
-+ if (d_really_is_positive(d)) {
-+ inode = d_inode(d);
-+ if (au_ftest_lock(flags, IW))
-+ do_ii_write_lock(inode, lsc);
-+ else if (au_ftest_lock(flags, IR))
-+ do_ii_read_lock(inode, lsc);
-+ }
-+}
-+
-+void di_read_unlock(struct dentry *d, int flags)
-+{
-+ struct inode *inode;
-+
-+ if (d_really_is_positive(d)) {
-+ inode = d_inode(d);
-+ if (au_ftest_lock(flags, IW)) {
-+ au_dbg_verify_dinode(d);
-+ ii_write_unlock(inode);
-+ } else if (au_ftest_lock(flags, IR)) {
-+ au_dbg_verify_dinode(d);
-+ ii_read_unlock(inode);
-+ }
-+ }
-+ au_rw_read_unlock(&au_di(d)->di_rwsem);
-+}
-+
-+void di_downgrade_lock(struct dentry *d, int flags)
-+{
-+ if (d_really_is_positive(d) && au_ftest_lock(flags, IR))
-+ ii_downgrade_lock(d_inode(d));
-+ au_rw_dgrade_lock(&au_di(d)->di_rwsem);
-+}
-+
-+void di_write_lock(struct dentry *d, unsigned int lsc)
-+{
-+ au_rw_write_lock_nested(&au_di(d)->di_rwsem, lsc);
-+ if (d_really_is_positive(d))
-+ do_ii_write_lock(d_inode(d), lsc);
-+}
-+
-+void di_write_unlock(struct dentry *d)
-+{
-+ au_dbg_verify_dinode(d);
-+ if (d_really_is_positive(d))
-+ ii_write_unlock(d_inode(d));
-+ au_rw_write_unlock(&au_di(d)->di_rwsem);
-+}
-+
-+void di_write_lock2_child(struct dentry *d1, struct dentry *d2, int isdir)
-+{
-+ AuDebugOn(d1 == d2
-+ || d_inode(d1) == d_inode(d2)
-+ || d1->d_sb != d2->d_sb);
-+
-+ if ((isdir && au_test_subdir(d1, d2))
-+ || d1 < d2) {
-+ di_write_lock_child(d1);
-+ di_write_lock_child2(d2);
-+ } else {
-+ di_write_lock_child(d2);
-+ di_write_lock_child2(d1);
-+ }
-+}
-+
-+void di_write_lock2_parent(struct dentry *d1, struct dentry *d2, int isdir)
-+{
-+ AuDebugOn(d1 == d2
-+ || d_inode(d1) == d_inode(d2)
-+ || d1->d_sb != d2->d_sb);
-+
-+ if ((isdir && au_test_subdir(d1, d2))
-+ || d1 < d2) {
-+ di_write_lock_parent(d1);
-+ di_write_lock_parent2(d2);
-+ } else {
-+ di_write_lock_parent(d2);
-+ di_write_lock_parent2(d1);
-+ }
-+}
-+
-+void di_write_unlock2(struct dentry *d1, struct dentry *d2)
-+{
-+ di_write_unlock(d1);
-+ if (d_inode(d1) == d_inode(d2))
-+ au_rw_write_unlock(&au_di(d2)->di_rwsem);
-+ else
-+ di_write_unlock(d2);
-+}
-+
-+/* ---------------------------------------------------------------------- */
-+
-+struct dentry *au_h_dptr(struct dentry *dentry, aufs_bindex_t bindex)
-+{
-+ struct dentry *d;
-+
-+ DiMustAnyLock(dentry);
-+
-+ if (au_dbtop(dentry) < 0 || bindex < au_dbtop(dentry))
-+ return NULL;
-+ AuDebugOn(bindex < 0);
-+ d = au_hdentry(au_di(dentry), bindex)->hd_dentry;
-+ AuDebugOn(d && au_dcount(d) <= 0);
-+ return d;
-+}
-+
-+/*
-+ * extended version of au_h_dptr().
-+ * returns a hashed and positive (or linkable) h_dentry in bindex, NULL, or
-+ * error.
-+ */
-+struct dentry *au_h_d_alias(struct dentry *dentry, aufs_bindex_t bindex)
-+{
-+ struct dentry *h_dentry;
-+ struct inode *inode, *h_inode;
-+
-+ AuDebugOn(d_really_is_negative(dentry));
-+
-+ h_dentry = NULL;
-+ if (au_dbtop(dentry) <= bindex
-+ && bindex <= au_dbbot(dentry))
-+ h_dentry = au_h_dptr(dentry, bindex);
-+ if (h_dentry && !au_d_linkable(h_dentry)) {
-+ dget(h_dentry);
-+ goto out; /* success */
-+ }
-+
-+ inode = d_inode(dentry);
-+ AuDebugOn(bindex < au_ibtop(inode));
-+ AuDebugOn(au_ibbot(inode) < bindex);
-+ h_inode = au_h_iptr(inode, bindex);
-+ h_dentry = d_find_alias(h_inode);
-+ if (h_dentry) {
-+ if (!IS_ERR(h_dentry)) {
-+ if (!au_d_linkable(h_dentry))
-+ goto out; /* success */
-+ dput(h_dentry);
-+ } else
-+ goto out;
-+ }
-+
-+ if (au_opt_test(au_mntflags(dentry->d_sb), PLINK)) {
-+ h_dentry = au_plink_lkup(inode, bindex);
-+ AuDebugOn(!h_dentry);
-+ if (!IS_ERR(h_dentry)) {
-+ if (!au_d_hashed_positive(h_dentry))
-+ goto out; /* success */
-+ dput(h_dentry);
-+ h_dentry = NULL;
-+ }
-+ }
-+
-+out:
-+ AuDbgDentry(h_dentry);
-+ return h_dentry;
-+}
-+
-+aufs_bindex_t au_dbtail(struct dentry *dentry)
-+{
-+ aufs_bindex_t bbot, bwh;
-+
-+ bbot = au_dbbot(dentry);
-+ if (0 <= bbot) {
-+ bwh = au_dbwh(dentry);
-+ if (!bwh)
-+ return bwh;
-+ if (0 < bwh && bwh < bbot)
-+ return bwh - 1;
-+ }
-+ return bbot;
-+}
-+
-+aufs_bindex_t au_dbtaildir(struct dentry *dentry)
-+{
-+ aufs_bindex_t bbot, bopq;
-+
-+ bbot = au_dbtail(dentry);
-+ if (0 <= bbot) {
-+ bopq = au_dbdiropq(dentry);
-+ if (0 <= bopq && bopq < bbot)
-+ bbot = bopq;
-+ }
-+ return bbot;
-+}
-+
-+/* ---------------------------------------------------------------------- */
-+
-+void au_set_h_dptr(struct dentry *dentry, aufs_bindex_t bindex,
-+ struct dentry *h_dentry)
-+{
-+ struct au_dinfo *dinfo;
-+ struct au_hdentry *hd;
-+ struct au_branch *br;
-+
-+ DiMustWriteLock(dentry);
-+
-+ dinfo = au_di(dentry);
-+ hd = au_hdentry(dinfo, bindex);
-+ au_hdput(hd);
-+ hd->hd_dentry = h_dentry;
-+ if (h_dentry) {
-+ br = au_sbr(dentry->d_sb, bindex);
-+ hd->hd_id = br->br_id;
-+ }
-+}
-+
-+int au_dbrange_test(struct dentry *dentry)
-+{
-+ int err;
-+ aufs_bindex_t btop, bbot;
-+
-+ err = 0;
-+ btop = au_dbtop(dentry);
-+ bbot = au_dbbot(dentry);
-+ if (btop >= 0)
-+ AuDebugOn(bbot < 0 && btop > bbot);
-+ else {
-+ err = -EIO;
-+ AuDebugOn(bbot >= 0);
-+ }
-+
-+ return err;
-+}
-+
-+int au_digen_test(struct dentry *dentry, unsigned int sigen)
-+{
-+ int err;
-+
-+ err = 0;
-+ if (unlikely(au_digen(dentry) != sigen
-+ || au_iigen_test(d_inode(dentry), sigen)))
-+ err = -EIO;
-+
-+ return err;
-+}
-+
-+void au_update_digen(struct dentry *dentry)
-+{
-+ atomic_set(&au_di(dentry)->di_generation, au_sigen(dentry->d_sb));
-+ /* smp_mb(); */ /* atomic_set */
-+}
-+
-+void au_update_dbrange(struct dentry *dentry, int do_put_zero)
-+{
-+ struct au_dinfo *dinfo;
-+ struct dentry *h_d;
-+ struct au_hdentry *hdp;
-+ aufs_bindex_t bindex, bbot;
-+
-+ DiMustWriteLock(dentry);
-+
-+ dinfo = au_di(dentry);
-+ if (!dinfo || dinfo->di_btop < 0)
-+ return;
-+
-+ if (do_put_zero) {
-+ bbot = dinfo->di_bbot;
-+ bindex = dinfo->di_btop;
-+ hdp = au_hdentry(dinfo, bindex);
-+ for (; bindex <= bbot; bindex++, hdp++) {
-+ h_d = hdp->hd_dentry;
-+ if (h_d && d_is_negative(h_d))
-+ au_set_h_dptr(dentry, bindex, NULL);
-+ }
-+ }
-+
-+ dinfo->di_btop = 0;
-+ hdp = au_hdentry(dinfo, dinfo->di_btop);
-+ for (; dinfo->di_btop <= dinfo->di_bbot; dinfo->di_btop++, hdp++)
-+ if (hdp->hd_dentry)
-+ break;
-+ if (dinfo->di_btop > dinfo->di_bbot) {
-+ dinfo->di_btop = -1;
-+ dinfo->di_bbot = -1;
-+ return;
-+ }
-+
-+ hdp = au_hdentry(dinfo, dinfo->di_bbot);
-+ for (; dinfo->di_bbot >= 0; dinfo->di_bbot--, hdp--)
-+ if (hdp->hd_dentry)
-+ break;
-+ AuDebugOn(dinfo->di_btop > dinfo->di_bbot || dinfo->di_bbot < 0);
-+}
-+
-+void au_update_dbtop(struct dentry *dentry)
-+{
-+ aufs_bindex_t bindex, bbot;
-+ struct dentry *h_dentry;
-+
-+ bbot = au_dbbot(dentry);
-+ for (bindex = au_dbtop(dentry); bindex <= bbot; bindex++) {
-+ h_dentry = au_h_dptr(dentry, bindex);
-+ if (!h_dentry)
-+ continue;
-+ if (d_is_positive(h_dentry)) {
-+ au_set_dbtop(dentry, bindex);
-+ return;
-+ }
-+ au_set_h_dptr(dentry, bindex, NULL);
-+ }
-+}
-+
-+void au_update_dbbot(struct dentry *dentry)
-+{
-+ aufs_bindex_t bindex, btop;
-+ struct dentry *h_dentry;
-+
-+ btop = au_dbtop(dentry);
-+ for (bindex = au_dbbot(dentry); bindex >= btop; bindex--) {
-+ h_dentry = au_h_dptr(dentry, bindex);
-+ if (!h_dentry)
-+ continue;
-+ if (d_is_positive(h_dentry)) {
-+ au_set_dbbot(dentry, bindex);
-+ return;
-+ }
-+ au_set_h_dptr(dentry, bindex, NULL);
-+ }
-+}
-+
-+int au_find_dbindex(struct dentry *dentry, struct dentry *h_dentry)
-+{
-+ aufs_bindex_t bindex, bbot;
-+
-+ bbot = au_dbbot(dentry);
-+ for (bindex = au_dbtop(dentry); bindex <= bbot; bindex++)
-+ if (au_h_dptr(dentry, bindex) == h_dentry)
-+ return bindex;
-+ return -1;
-+}
-diff --git a/fs/aufs/dir.c b/fs/aufs/dir.c
-new file mode 100644
-index 000000000000..68e87d6f287e
---- /dev/null
-+++ b/fs/aufs/dir.c
-@@ -0,0 +1,763 @@
-+// SPDX-License-Identifier: GPL-2.0
-+/*
-+ * Copyright (C) 2005-2019 Junjiro R. Okajima
-+ *
-+ * This program, aufs is free software; you can redistribute it and/or modify
-+ * it under the terms of the GNU General Public License as published by
-+ * the Free Software Foundation; either version 2 of the License, or
-+ * (at your option) any later version.
-+ *
-+ * This program is distributed in the hope that it will be useful,
-+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
-+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
-+ * GNU General Public License for more details.
-+ *
-+ * You should have received a copy of the GNU General Public License
-+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
-+ */
-+
-+/*
-+ * directory operations
-+ */
-+
-+#include <linux/fs_stack.h>
-+#include <linux/iversion.h>
-+#include "aufs.h"
-+
-+void au_add_nlink(struct inode *dir, struct inode *h_dir)
-+{
-+ unsigned int nlink;
-+
-+ AuDebugOn(!S_ISDIR(dir->i_mode) || !S_ISDIR(h_dir->i_mode));
-+
-+ nlink = dir->i_nlink;
-+ nlink += h_dir->i_nlink - 2;
-+ if (h_dir->i_nlink < 2)
-+ nlink += 2;
-+ smp_mb(); /* for i_nlink */
-+ /* 0 can happen in revaliding */
-+ set_nlink(dir, nlink);
-+}
-+
-+void au_sub_nlink(struct inode *dir, struct inode *h_dir)
-+{
-+ unsigned int nlink;
-+
-+ AuDebugOn(!S_ISDIR(dir->i_mode) || !S_ISDIR(h_dir->i_mode));
-+
-+ nlink = dir->i_nlink;
-+ nlink -= h_dir->i_nlink - 2;
-+ if (h_dir->i_nlink < 2)
-+ nlink -= 2;
-+ smp_mb(); /* for i_nlink */
-+ /* nlink == 0 means the branch-fs is broken */
-+ set_nlink(dir, nlink);
-+}
-+
-+loff_t au_dir_size(struct file *file, struct dentry *dentry)
-+{
-+ loff_t sz;
-+ aufs_bindex_t bindex, bbot;
-+ struct file *h_file;
-+ struct dentry *h_dentry;
-+
-+ sz = 0;
-+ if (file) {
-+ AuDebugOn(!d_is_dir(file->f_path.dentry));
-+
-+ bbot = au_fbbot_dir(file);
-+ for (bindex = au_fbtop(file);
-+ bindex <= bbot && sz < KMALLOC_MAX_SIZE;
-+ bindex++) {
-+ h_file = au_hf_dir(file, bindex);
-+ if (h_file && file_inode(h_file))
-+ sz += vfsub_f_size_read(h_file);
-+ }
-+ } else {
-+ AuDebugOn(!dentry);
-+ AuDebugOn(!d_is_dir(dentry));
-+
-+ bbot = au_dbtaildir(dentry);
-+ for (bindex = au_dbtop(dentry);
-+ bindex <= bbot && sz < KMALLOC_MAX_SIZE;
-+ bindex++) {
-+ h_dentry = au_h_dptr(dentry, bindex);
-+ if (h_dentry && d_is_positive(h_dentry))
-+ sz += i_size_read(d_inode(h_dentry));
-+ }
-+ }
-+ if (sz < KMALLOC_MAX_SIZE)
-+ sz = roundup_pow_of_two(sz);
-+ if (sz > KMALLOC_MAX_SIZE)
-+ sz = KMALLOC_MAX_SIZE;
-+ else if (sz < NAME_MAX) {
-+ BUILD_BUG_ON(AUFS_RDBLK_DEF < NAME_MAX);
-+ sz = AUFS_RDBLK_DEF;
-+ }
-+ return sz;
-+}
-+
-+struct au_dir_ts_arg {
-+ struct dentry *dentry;
-+ aufs_bindex_t brid;
-+};
-+
-+static void au_do_dir_ts(void *arg)
-+{
-+ struct au_dir_ts_arg *a = arg;
-+ struct au_dtime dt;
-+ struct path h_path;
-+ struct inode *dir, *h_dir;
-+ struct super_block *sb;
-+ struct au_branch *br;
-+ struct au_hinode *hdir;
-+ int err;
-+ aufs_bindex_t btop, bindex;
-+
-+ sb = a->dentry->d_sb;
-+ if (d_really_is_negative(a->dentry))
-+ goto out;
-+ /* no dir->i_mutex lock */
-+ aufs_read_lock(a->dentry, AuLock_DW); /* noflush */
-+
-+ dir = d_inode(a->dentry);
-+ btop = au_ibtop(dir);
-+ bindex = au_br_index(sb, a->brid);
-+ if (bindex < btop)
-+ goto out_unlock;
-+
-+ br = au_sbr(sb, bindex);
-+ h_path.dentry = au_h_dptr(a->dentry, bindex);
-+ if (!h_path.dentry)
-+ goto out_unlock;
-+ h_path.mnt = au_br_mnt(br);
-+ au_dtime_store(&dt, a->dentry, &h_path);
-+
-+ br = au_sbr(sb, btop);
-+ if (!au_br_writable(br->br_perm))
-+ goto out_unlock;
-+ h_path.dentry = au_h_dptr(a->dentry, btop);
-+ h_path.mnt = au_br_mnt(br);
-+ err = vfsub_mnt_want_write(h_path.mnt);
-+ if (err)
-+ goto out_unlock;
-+ hdir = au_hi(dir, btop);
-+ au_hn_inode_lock_nested(hdir, AuLsc_I_PARENT);
-+ h_dir = au_h_iptr(dir, btop);
-+ if (h_dir->i_nlink
-+ && timespec64_compare(&h_dir->i_mtime, &dt.dt_mtime) < 0) {
-+ dt.dt_h_path = h_path;
-+ au_dtime_revert(&dt);
-+ }
-+ au_hn_inode_unlock(hdir);
-+ vfsub_mnt_drop_write(h_path.mnt);
-+ au_cpup_attr_timesizes(dir);
-+
-+out_unlock:
-+ aufs_read_unlock(a->dentry, AuLock_DW);
-+out:
-+ dput(a->dentry);
-+ au_nwt_done(&au_sbi(sb)->si_nowait);
-+ au_kfree_try_rcu(arg);
-+}
-+
-+void au_dir_ts(struct inode *dir, aufs_bindex_t bindex)
-+{
-+ int perm, wkq_err;
-+ aufs_bindex_t btop;
-+ struct au_dir_ts_arg *arg;
-+ struct dentry *dentry;
-+ struct super_block *sb;
-+
-+ IMustLock(dir);
-+
-+ dentry = d_find_any_alias(dir);
-+ AuDebugOn(!dentry);
-+ sb = dentry->d_sb;
-+ btop = au_ibtop(dir);
-+ if (btop == bindex) {
-+ au_cpup_attr_timesizes(dir);
-+ goto out;
-+ }
-+
-+ perm = au_sbr_perm(sb, btop);
-+ if (!au_br_writable(perm))
-+ goto out;
-+
-+ arg = kmalloc(sizeof(*arg), GFP_NOFS);
-+ if (!arg)
-+ goto out;
-+
-+ arg->dentry = dget(dentry); /* will be dput-ted by au_do_dir_ts() */
-+ arg->brid = au_sbr_id(sb, bindex);
-+ wkq_err = au_wkq_nowait(au_do_dir_ts, arg, sb, /*flags*/0);
-+ if (unlikely(wkq_err)) {
-+ pr_err("wkq %d\n", wkq_err);
-+ dput(dentry);
-+ au_kfree_try_rcu(arg);
-+ }
-+
-+out:
-+ dput(dentry);
-+}
-+
-+/* ---------------------------------------------------------------------- */
-+
-+static int reopen_dir(struct file *file)
-+{
-+ int err;
-+ unsigned int flags;
-+ aufs_bindex_t bindex, btail, btop;
-+ struct dentry *dentry, *h_dentry;
-+ struct file *h_file;
-+
-+ /* open all lower dirs */
-+ dentry = file->f_path.dentry;
-+ btop = au_dbtop(dentry);
-+ for (bindex = au_fbtop(file); bindex < btop; bindex++)
-+ au_set_h_fptr(file, bindex, NULL);
-+ au_set_fbtop(file, btop);
-+
-+ btail = au_dbtaildir(dentry);
-+ for (bindex = au_fbbot_dir(file); btail < bindex; bindex--)
-+ au_set_h_fptr(file, bindex, NULL);
-+ au_set_fbbot_dir(file, btail);
-+
-+ flags = vfsub_file_flags(file);
-+ for (bindex = btop; bindex <= btail; bindex++) {
-+ h_dentry = au_h_dptr(dentry, bindex);
-+ if (!h_dentry)
-+ continue;
-+ h_file = au_hf_dir(file, bindex);
-+ if (h_file)
-+ continue;
-+
-+ h_file = au_h_open(dentry, bindex, flags, file, /*force_wr*/0);
-+ err = PTR_ERR(h_file);
-+ if (IS_ERR(h_file))
-+ goto out; /* close all? */
-+ au_set_h_fptr(file, bindex, h_file);
-+ }
-+ au_update_figen(file);
-+ /* todo: necessary? */
-+ /* file->f_ra = h_file->f_ra; */
-+ err = 0;
-+
-+out:
-+ return err;
-+}
-+
-+static int do_open_dir(struct file *file, int flags, struct file *h_file)
-+{
-+ int err;
-+ aufs_bindex_t bindex, btail;
-+ struct dentry *dentry, *h_dentry;
-+ struct vfsmount *mnt;
-+
-+ FiMustWriteLock(file);
-+ AuDebugOn(h_file);
-+
-+ err = 0;
-+ mnt = file->f_path.mnt;
-+ dentry = file->f_path.dentry;
-+ file->f_version = inode_query_iversion(d_inode(dentry));
-+ bindex = au_dbtop(dentry);
-+ au_set_fbtop(file, bindex);
-+ btail = au_dbtaildir(dentry);
-+ au_set_fbbot_dir(file, btail);
-+ for (; !err && bindex <= btail; bindex++) {
-+ h_dentry = au_h_dptr(dentry, bindex);
-+ if (!h_dentry)
-+ continue;
-+
-+ err = vfsub_test_mntns(mnt, h_dentry->d_sb);
-+ if (unlikely(err))
-+ break;
-+ h_file = au_h_open(dentry, bindex, flags, file, /*force_wr*/0);
-+ if (IS_ERR(h_file)) {
-+ err = PTR_ERR(h_file);
-+ break;
-+ }
-+ au_set_h_fptr(file, bindex, h_file);
-+ }
-+ au_update_figen(file);
-+ /* todo: necessary? */
-+ /* file->f_ra = h_file->f_ra; */
-+ if (!err)
-+ return 0; /* success */
-+
-+ /* close all */
-+ for (bindex = au_fbtop(file); bindex <= btail; bindex++)
-+ au_set_h_fptr(file, bindex, NULL);
-+ au_set_fbtop(file, -1);
-+ au_set_fbbot_dir(file, -1);
-+
-+ return err;
-+}
-+
-+static int aufs_open_dir(struct inode *inode __maybe_unused,
-+ struct file *file)
-+{
-+ int err;
-+ struct super_block *sb;
-+ struct au_fidir *fidir;
-+
-+ err = -ENOMEM;
-+ sb = file->f_path.dentry->d_sb;
-+ si_read_lock(sb, AuLock_FLUSH);
-+ fidir = au_fidir_alloc(sb);
-+ if (fidir) {
-+ struct au_do_open_args args = {
-+ .open = do_open_dir,
-+ .fidir = fidir
-+ };
-+ err = au_do_open(file, &args);
-+ if (unlikely(err))
-+ au_kfree_rcu(fidir);
-+ }
-+ si_read_unlock(sb);
-+ return err;
-+}
-+
-+static int aufs_release_dir(struct inode *inode __maybe_unused,
-+ struct file *file)
-+{
-+ struct au_vdir *vdir_cache;
-+ struct au_finfo *finfo;
-+ struct au_fidir *fidir;
-+ struct au_hfile *hf;
-+ aufs_bindex_t bindex, bbot;
-+
-+ finfo = au_fi(file);
-+ fidir = finfo->fi_hdir;
-+ if (fidir) {
-+ au_hbl_del(&finfo->fi_hlist,
-+ &au_sbi(file->f_path.dentry->d_sb)->si_files);
-+ vdir_cache = fidir->fd_vdir_cache; /* lock-free */
-+ if (vdir_cache)
-+ au_vdir_free(vdir_cache);
-+
-+ bindex = finfo->fi_btop;
-+ if (bindex >= 0) {
-+ hf = fidir->fd_hfile + bindex;
-+ /*
-+ * calls fput() instead of filp_close(),
-+ * since no dnotify or lock for the lower file.
-+ */
-+ bbot = fidir->fd_bbot;
-+ for (; bindex <= bbot; bindex++, hf++)
-+ if (hf->hf_file)
-+ au_hfput(hf, /*execed*/0);
-+ }
-+ au_kfree_rcu(fidir);
-+ finfo->fi_hdir = NULL;
-+ }
-+ au_finfo_fin(file);
-+ return 0;
-+}
-+
-+/* ---------------------------------------------------------------------- */
-+
-+static int au_do_flush_dir(struct file *file, fl_owner_t id)
-+{
-+ int err;
-+ aufs_bindex_t bindex, bbot;
-+ struct file *h_file;
-+
-+ err = 0;
-+ bbot = au_fbbot_dir(file);
-+ for (bindex = au_fbtop(file); !err && bindex <= bbot; bindex++) {
-+ h_file = au_hf_dir(file, bindex);
-+ if (h_file)
-+ err = vfsub_flush(h_file, id);
-+ }
-+ return err;
-+}
-+
-+static int aufs_flush_dir(struct file *file, fl_owner_t id)
-+{
-+ return au_do_flush(file, id, au_do_flush_dir);
-+}
-+
-+/* ---------------------------------------------------------------------- */
-+
-+static int au_do_fsync_dir_no_file(struct dentry *dentry, int datasync)
-+{
-+ int err;
-+ aufs_bindex_t bbot, bindex;
-+ struct inode *inode;
-+ struct super_block *sb;
-+
-+ err = 0;
-+ sb = dentry->d_sb;
-+ inode = d_inode(dentry);
-+ IMustLock(inode);
-+ bbot = au_dbbot(dentry);
-+ for (bindex = au_dbtop(dentry); !err && bindex <= bbot; bindex++) {
-+ struct path h_path;
-+
-+ if (au_test_ro(sb, bindex, inode))
-+ continue;
-+ h_path.dentry = au_h_dptr(dentry, bindex);
-+ if (!h_path.dentry)
-+ continue;
-+
-+ h_path.mnt = au_sbr_mnt(sb, bindex);
-+ err = vfsub_fsync(NULL, &h_path, datasync);
-+ }
-+
-+ return err;
-+}
-+
-+static int au_do_fsync_dir(struct file *file, int datasync)
-+{
-+ int err;
-+ aufs_bindex_t bbot, bindex;
-+ struct file *h_file;
-+ struct super_block *sb;
-+ struct inode *inode;
-+
-+ err = au_reval_and_lock_fdi(file, reopen_dir, /*wlock*/1, /*fi_lsc*/0);
-+ if (unlikely(err))
-+ goto out;
-+
-+ inode = file_inode(file);
-+ sb = inode->i_sb;
-+ bbot = au_fbbot_dir(file);
-+ for (bindex = au_fbtop(file); !err && bindex <= bbot; bindex++) {
-+ h_file = au_hf_dir(file, bindex);
-+ if (!h_file || au_test_ro(sb, bindex, inode))
-+ continue;
-+
-+ err = vfsub_fsync(h_file, &h_file->f_path, datasync);
-+ }
-+
-+out:
-+ return err;
-+}
-+
-+/*
-+ * @file may be NULL
-+ */
-+static int aufs_fsync_dir(struct file *file, loff_t start, loff_t end,
-+ int datasync)
-+{
-+ int err;
-+ struct dentry *dentry;
-+ struct inode *inode;
-+ struct super_block *sb;
-+
-+ err = 0;
-+ dentry = file->f_path.dentry;
-+ inode = d_inode(dentry);
-+ inode_lock(inode);
-+ sb = dentry->d_sb;
-+ si_noflush_read_lock(sb);
-+ if (file)
-+ err = au_do_fsync_dir(file, datasync);
-+ else {
-+ di_write_lock_child(dentry);
-+ err = au_do_fsync_dir_no_file(dentry, datasync);
-+ }
-+ au_cpup_attr_timesizes(inode);
-+ di_write_unlock(dentry);
-+ if (file)
-+ fi_write_unlock(file);
-+
-+ si_read_unlock(sb);
-+ inode_unlock(inode);
-+ return err;
-+}
-+
-+/* ---------------------------------------------------------------------- */
-+
-+static int aufs_iterate_shared(struct file *file, struct dir_context *ctx)
-+{
-+ int err;
-+ struct dentry *dentry;
-+ struct inode *inode, *h_inode;
-+ struct super_block *sb;
-+
-+ AuDbg("%pD, ctx{%ps, %llu}\n", file, ctx->actor, ctx->pos);
-+
-+ dentry = file->f_path.dentry;
-+ inode = d_inode(dentry);
-+ IMustLock(inode);
-+
-+ sb = dentry->d_sb;
-+ si_read_lock(sb, AuLock_FLUSH);
-+ err = au_reval_and_lock_fdi(file, reopen_dir, /*wlock*/1, /*fi_lsc*/0);
-+ if (unlikely(err))
-+ goto out;
-+ err = au_alive_dir(dentry);
-+ if (!err)
-+ err = au_vdir_init(file);
-+ di_downgrade_lock(dentry, AuLock_IR);
-+ if (unlikely(err))
-+ goto out_unlock;
-+
-+ h_inode = au_h_iptr(inode, au_ibtop(inode));
-+ if (!au_test_nfsd()) {
-+ err = au_vdir_fill_de(file, ctx);
-+ fsstack_copy_attr_atime(inode, h_inode);
-+ } else {
-+ /*
-+ * nfsd filldir may call lookup_one_len(), vfs_getattr(),
-+ * encode_fh() and others.
-+ */
-+ atomic_inc(&h_inode->i_count);
-+ di_read_unlock(dentry, AuLock_IR);
-+ si_read_unlock(sb);
-+ err = au_vdir_fill_de(file, ctx);
-+ fsstack_copy_attr_atime(inode, h_inode);
-+ fi_write_unlock(file);
-+ iput(h_inode);
-+
-+ AuTraceErr(err);
-+ return err;
-+ }
-+
-+out_unlock:
-+ di_read_unlock(dentry, AuLock_IR);
-+ fi_write_unlock(file);
-+out:
-+ si_read_unlock(sb);
-+ return err;
-+}
-+
-+/* ---------------------------------------------------------------------- */
-+
-+#define AuTestEmpty_WHONLY 1
-+#define AuTestEmpty_CALLED (1 << 1)
-+#define AuTestEmpty_SHWH (1 << 2)
-+#define au_ftest_testempty(flags, name) ((flags) & AuTestEmpty_##name)
-+#define au_fset_testempty(flags, name) \
-+ do { (flags) |= AuTestEmpty_##name; } while (0)
-+#define au_fclr_testempty(flags, name) \
-+ do { (flags) &= ~AuTestEmpty_##name; } while (0)
-+
-+#ifndef CONFIG_AUFS_SHWH
-+#undef AuTestEmpty_SHWH
-+#define AuTestEmpty_SHWH 0
-+#endif
-+
-+struct test_empty_arg {
-+ struct dir_context ctx;
-+ struct au_nhash *whlist;
-+ unsigned int flags;
-+ int err;
-+ aufs_bindex_t bindex;
-+};
-+
-+static int test_empty_cb(struct dir_context *ctx, const char *__name,
-+ int namelen, loff_t offset __maybe_unused, u64 ino,
-+ unsigned int d_type)
-+{
-+ struct test_empty_arg *arg = container_of(ctx, struct test_empty_arg,
-+ ctx);
-+ char *name = (void *)__name;
-+
-+ arg->err = 0;
-+ au_fset_testempty(arg->flags, CALLED);
-+ /* smp_mb(); */
-+ if (name[0] == '.'
-+ && (namelen == 1 || (name[1] == '.' && namelen == 2)))
-+ goto out; /* success */
-+
-+ if (namelen <= AUFS_WH_PFX_LEN
-+ || memcmp(name, AUFS_WH_PFX, AUFS_WH_PFX_LEN)) {
-+ if (au_ftest_testempty(arg->flags, WHONLY)
-+ && !au_nhash_test_known_wh(arg->whlist, name, namelen))
-+ arg->err = -ENOTEMPTY;
-+ goto out;
-+ }
-+
-+ name += AUFS_WH_PFX_LEN;
-+ namelen -= AUFS_WH_PFX_LEN;
-+ if (!au_nhash_test_known_wh(arg->whlist, name, namelen))
-+ arg->err = au_nhash_append_wh
-+ (arg->whlist, name, namelen, ino, d_type, arg->bindex,
-+ au_ftest_testempty(arg->flags, SHWH));
-+
-+out:
-+ /* smp_mb(); */
-+ AuTraceErr(arg->err);
-+ return arg->err;
-+}
-+
-+static int do_test_empty(struct dentry *dentry, struct test_empty_arg *arg)
-+{
-+ int err;
-+ struct file *h_file;
-+ struct au_branch *br;
-+
-+ h_file = au_h_open(dentry, arg->bindex,
-+ O_RDONLY | O_NONBLOCK | O_DIRECTORY | O_LARGEFILE,
-+ /*file*/NULL, /*force_wr*/0);
-+ err = PTR_ERR(h_file);
-+ if (IS_ERR(h_file))
-+ goto out;
-+
-+ err = 0;
-+ if (!au_opt_test(au_mntflags(dentry->d_sb), UDBA_NONE)
-+ && !file_inode(h_file)->i_nlink)
-+ goto out_put;
-+
-+ do {
-+ arg->err = 0;
-+ au_fclr_testempty(arg->flags, CALLED);
-+ /* smp_mb(); */
-+ err = vfsub_iterate_dir(h_file, &arg->ctx);
-+ if (err >= 0)
-+ err = arg->err;
-+ } while (!err && au_ftest_testempty(arg->flags, CALLED));
-+
-+out_put:
-+ fput(h_file);
-+ br = au_sbr(dentry->d_sb, arg->bindex);
-+ au_lcnt_dec(&br->br_nfiles);
-+out:
-+ return err;
-+}
-+
-+struct do_test_empty_args {
-+ int *errp;
-+ struct dentry *dentry;
-+ struct test_empty_arg *arg;
-+};
-+
-+static void call_do_test_empty(void *args)
-+{
-+ struct do_test_empty_args *a = args;
-+ *a->errp = do_test_empty(a->dentry, a->arg);
-+}
-+
-+static int sio_test_empty(struct dentry *dentry, struct test_empty_arg *arg)
-+{
-+ int err, wkq_err;
-+ struct dentry *h_dentry;
-+ struct inode *h_inode;
-+
-+ h_dentry = au_h_dptr(dentry, arg->bindex);
-+ h_inode = d_inode(h_dentry);
-+ /* todo: i_mode changes anytime? */
-+ inode_lock_shared_nested(h_inode, AuLsc_I_CHILD);
-+ err = au_test_h_perm_sio(h_inode, MAY_EXEC | MAY_READ);
-+ inode_unlock_shared(h_inode);
-+ if (!err)
-+ err = do_test_empty(dentry, arg);
-+ else {
-+ struct do_test_empty_args args = {
-+ .errp = &err,
-+ .dentry = dentry,
-+ .arg = arg
-+ };
-+ unsigned int flags = arg->flags;
-+
-+ wkq_err = au_wkq_wait(call_do_test_empty, &args);
-+ if (unlikely(wkq_err))
-+ err = wkq_err;
-+ arg->flags = flags;
-+ }
-+
-+ return err;
-+}
-+
-+int au_test_empty_lower(struct dentry *dentry)
-+{
-+ int err;
-+ unsigned int rdhash;
-+ aufs_bindex_t bindex, btop, btail;
-+ struct au_nhash whlist;
-+ struct test_empty_arg arg = {
-+ .ctx = {
-+ .actor = test_empty_cb
-+ }
-+ };
-+ int (*test_empty)(struct dentry *dentry, struct test_empty_arg *arg);
-+
-+ SiMustAnyLock(dentry->d_sb);
-+
-+ rdhash = au_sbi(dentry->d_sb)->si_rdhash;
-+ if (!rdhash)
-+ rdhash = au_rdhash_est(au_dir_size(/*file*/NULL, dentry));
-+ err = au_nhash_alloc(&whlist, rdhash, GFP_NOFS);
-+ if (unlikely(err))
-+ goto out;
-+
-+ arg.flags = 0;
-+ arg.whlist = &whlist;
-+ btop = au_dbtop(dentry);
-+ if (au_opt_test(au_mntflags(dentry->d_sb), SHWH))
-+ au_fset_testempty(arg.flags, SHWH);
-+ test_empty = do_test_empty;
-+ if (au_opt_test(au_mntflags(dentry->d_sb), DIRPERM1))
-+ test_empty = sio_test_empty;
-+ arg.bindex = btop;
-+ err = test_empty(dentry, &arg);
-+ if (unlikely(err))
-+ goto out_whlist;
-+
-+ au_fset_testempty(arg.flags, WHONLY);
-+ btail = au_dbtaildir(dentry);
-+ for (bindex = btop + 1; !err && bindex <= btail; bindex++) {
-+ struct dentry *h_dentry;
-+
-+ h_dentry = au_h_dptr(dentry, bindex);
-+ if (h_dentry && d_is_positive(h_dentry)) {
-+ arg.bindex = bindex;
-+ err = test_empty(dentry, &arg);
-+ }
-+ }
-+
-+out_whlist:
-+ au_nhash_wh_free(&whlist);
-+out:
-+ return err;
-+}
-+
-+int au_test_empty(struct dentry *dentry, struct au_nhash *whlist)
-+{
-+ int err;
-+ struct test_empty_arg arg = {
-+ .ctx = {
-+ .actor = test_empty_cb
-+ }
-+ };
-+ aufs_bindex_t bindex, btail;
-+
-+ err = 0;
-+ arg.whlist = whlist;
-+ arg.flags = AuTestEmpty_WHONLY;
-+ if (au_opt_test(au_mntflags(dentry->d_sb), SHWH))
-+ au_fset_testempty(arg.flags, SHWH);
-+ btail = au_dbtaildir(dentry);
-+ for (bindex = au_dbtop(dentry); !err && bindex <= btail; bindex++) {
-+ struct dentry *h_dentry;
-+
-+ h_dentry = au_h_dptr(dentry, bindex);
-+ if (h_dentry && d_is_positive(h_dentry)) {
-+ arg.bindex = bindex;
-+ err = sio_test_empty(dentry, &arg);
-+ }
-+ }
-+
-+ return err;
-+}
-+
-+/* ---------------------------------------------------------------------- */
-+
-+const struct file_operations aufs_dir_fop = {
-+ .owner = THIS_MODULE,
-+ .llseek = default_llseek,
-+ .read = generic_read_dir,
-+ .iterate_shared = aufs_iterate_shared,
-+ .unlocked_ioctl = aufs_ioctl_dir,
-+#ifdef CONFIG_COMPAT
-+ .compat_ioctl = aufs_compat_ioctl_dir,
-+#endif
-+ .open = aufs_open_dir,
-+ .release = aufs_release_dir,
-+ .flush = aufs_flush_dir,
-+ .fsync = aufs_fsync_dir
-+};
-diff --git a/fs/aufs/dir.h b/fs/aufs/dir.h
-new file mode 100644
-index 000000000000..5c8065d258bf
---- /dev/null
-+++ b/fs/aufs/dir.h
-@@ -0,0 +1,134 @@
-+/* SPDX-License-Identifier: GPL-2.0 */
-+/*
-+ * Copyright (C) 2005-2019 Junjiro R. Okajima
-+ *
-+ * This program, aufs is free software; you can redistribute it and/or modify
-+ * it under the terms of the GNU General Public License as published by
-+ * the Free Software Foundation; either version 2 of the License, or
-+ * (at your option) any later version.
-+ *
-+ * This program is distributed in the hope that it will be useful,
-+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
-+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
-+ * GNU General Public License for more details.
-+ *
-+ * You should have received a copy of the GNU General Public License
-+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
-+ */
-+
-+/*
-+ * directory operations
-+ */
-+
-+#ifndef __AUFS_DIR_H__
-+#define __AUFS_DIR_H__
-+
-+#ifdef __KERNEL__
-+
-+#include <linux/fs.h>
-+
-+/* ---------------------------------------------------------------------- */
-+
-+/* need to be faster and smaller */
-+
-+struct au_nhash {
-+ unsigned int nh_num;
-+ struct hlist_head *nh_head;
-+};
-+
-+struct au_vdir_destr {
-+ unsigned char len;
-+ unsigned char name[0];
-+} __packed;
-+
-+struct au_vdir_dehstr {
-+ struct hlist_node hash;
-+ struct au_vdir_destr *str;
-+ struct rcu_head rcu;
-+} ____cacheline_aligned_in_smp;
-+
-+struct au_vdir_de {
-+ ino_t de_ino;
-+ unsigned char de_type;
-+ /* caution: packed */
-+ struct au_vdir_destr de_str;
-+} __packed;
-+
-+struct au_vdir_wh {
-+ struct hlist_node wh_hash;
-+#ifdef CONFIG_AUFS_SHWH
-+ ino_t wh_ino;
-+ aufs_bindex_t wh_bindex;
-+ unsigned char wh_type;
-+#else
-+ aufs_bindex_t wh_bindex;
-+#endif
-+ /* caution: packed */
-+ struct au_vdir_destr wh_str;
-+} __packed;
-+
-+union au_vdir_deblk_p {
-+ unsigned char *deblk;
-+ struct au_vdir_de *de;
-+};
-+
-+struct au_vdir {
-+ unsigned char **vd_deblk;
-+ unsigned long vd_nblk;
-+ struct {
-+ unsigned long ul;
-+ union au_vdir_deblk_p p;
-+ } vd_last;
-+
-+ u64 vd_version;
-+ unsigned int vd_deblk_sz;
-+ unsigned long vd_jiffy;
-+ struct rcu_head rcu;
-+} ____cacheline_aligned_in_smp;
-+
-+/* ---------------------------------------------------------------------- */
-+
-+/* dir.c */
-+extern const struct file_operations aufs_dir_fop;
-+void au_add_nlink(struct inode *dir, struct inode *h_dir);
-+void au_sub_nlink(struct inode *dir, struct inode *h_dir);
-+loff_t au_dir_size(struct file *file, struct dentry *dentry);
-+void au_dir_ts(struct inode *dir, aufs_bindex_t bsrc);
-+int au_test_empty_lower(struct dentry *dentry);
-+int au_test_empty(struct dentry *dentry, struct au_nhash *whlist);
-+
-+/* vdir.c */
-+unsigned int au_rdhash_est(loff_t sz);
-+int au_nhash_alloc(struct au_nhash *nhash, unsigned int num_hash, gfp_t gfp);
-+void au_nhash_wh_free(struct au_nhash *whlist);
-+int au_nhash_test_longer_wh(struct au_nhash *whlist, aufs_bindex_t btgt,
-+ int limit);
-+int au_nhash_test_known_wh(struct au_nhash *whlist, char *name, int nlen);
-+int au_nhash_append_wh(struct au_nhash *whlist, char *name, int nlen, ino_t ino,
-+ unsigned int d_type, aufs_bindex_t bindex,
-+ unsigned char shwh);
-+void au_vdir_free(struct au_vdir *vdir);
-+int au_vdir_init(struct file *file);
-+int au_vdir_fill_de(struct file *file, struct dir_context *ctx);
-+
-+/* ioctl.c */
-+long aufs_ioctl_dir(struct file *file, unsigned int cmd, unsigned long arg);
-+
-+#ifdef CONFIG_AUFS_RDU
-+/* rdu.c */
-+long au_rdu_ioctl(struct file *file, unsigned int cmd, unsigned long arg);
-+#ifdef CONFIG_COMPAT
-+long au_rdu_compat_ioctl(struct file *file, unsigned int cmd,
-+ unsigned long arg);
-+#endif
-+#else
-+AuStub(long, au_rdu_ioctl, return -EINVAL, struct file *file,
-+ unsigned int cmd, unsigned long arg)
-+#ifdef CONFIG_COMPAT
-+AuStub(long, au_rdu_compat_ioctl, return -EINVAL, struct file *file,
-+ unsigned int cmd, unsigned long arg)
-+#endif
-+#endif
-+
-+#endif /* __KERNEL__ */
-+#endif /* __AUFS_DIR_H__ */
-diff --git a/fs/aufs/dirren.c b/fs/aufs/dirren.c
-new file mode 100644
-index 000000000000..0bd412ab68c9
---- /dev/null
-+++ b/fs/aufs/dirren.c
-@@ -0,0 +1,1316 @@
-+// SPDX-License-Identifier: GPL-2.0
-+/*
-+ * Copyright (C) 2017-2019 Junjiro R. Okajima
-+ *
-+ * This program, aufs is free software; you can redistribute it and/or modify
-+ * it under the terms of the GNU General Public License as published by
-+ * the Free Software Foundation; either version 2 of the License, or
-+ * (at your option) any later version.
-+ *
-+ * This program is distributed in the hope that it will be useful,
-+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
-+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
-+ * GNU General Public License for more details.
-+ *
-+ * You should have received a copy of the GNU General Public License
-+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
-+ */
-+
-+/*
-+ * special handling in renaming a directory
-+ * in order to support looking-up the before-renamed name on the lower readonly
-+ * branches
-+ */
-+
-+#include <linux/byteorder/generic.h>
-+#include "aufs.h"
-+
-+static void au_dr_hino_del(struct au_dr_br *dr, struct au_dr_hino *ent)
-+{
-+ int idx;
-+
-+ idx = au_dr_ihash(ent->dr_h_ino);
-+ au_hbl_del(&ent->dr_hnode, dr->dr_h_ino + idx);
-+}
-+
-+static int au_dr_hino_test_empty(struct au_dr_br *dr)
-+{
-+ int ret, i;
-+ struct hlist_bl_head *hbl;
-+
-+ ret = 1;
-+ for (i = 0; ret && i < AuDirren_NHASH; i++) {
-+ hbl = dr->dr_h_ino + i;
-+ hlist_bl_lock(hbl);
-+ ret &= hlist_bl_empty(hbl);
-+ hlist_bl_unlock(hbl);
-+ }
-+
-+ return ret;
-+}
-+
-+static struct au_dr_hino *au_dr_hino_find(struct au_dr_br *dr, ino_t ino)
-+{
-+ struct au_dr_hino *found, *ent;
-+ struct hlist_bl_head *hbl;
-+ struct hlist_bl_node *pos;
-+ int idx;
-+
-+ found = NULL;
-+ idx = au_dr_ihash(ino);
-+ hbl = dr->dr_h_ino + idx;
-+ hlist_bl_lock(hbl);
-+ hlist_bl_for_each_entry(ent, pos, hbl, dr_hnode)
-+ if (ent->dr_h_ino == ino) {
-+ found = ent;
-+ break;
-+ }
-+ hlist_bl_unlock(hbl);
-+
-+ return found;
-+}
-+
-+int au_dr_hino_test_add(struct au_dr_br *dr, ino_t ino,
-+ struct au_dr_hino *add_ent)
-+{
-+ int found, idx;
-+ struct hlist_bl_head *hbl;
-+ struct hlist_bl_node *pos;
-+ struct au_dr_hino *ent;
-+
-+ found = 0;
-+ idx = au_dr_ihash(ino);
-+ hbl = dr->dr_h_ino + idx;
-+#if 0
-+ {
-+ struct hlist_bl_node *tmp;
-+
-+ hlist_bl_for_each_entry_safe(ent, pos, tmp, hbl, dr_hnode)
-+ AuDbg("hi%llu\n", (unsigned long long)ent->dr_h_ino);
-+ }
-+#endif
-+ hlist_bl_lock(hbl);
-+ hlist_bl_for_each_entry(ent, pos, hbl, dr_hnode)
-+ if (ent->dr_h_ino == ino) {
-+ found = 1;
-+ break;
-+ }
-+ if (!found && add_ent)
-+ hlist_bl_add_head(&add_ent->dr_hnode, hbl);
-+ hlist_bl_unlock(hbl);
-+
-+ if (!found && add_ent)
-+ AuDbg("i%llu added\n", (unsigned long long)add_ent->dr_h_ino);
-+
-+ return found;
-+}
-+
-+void au_dr_hino_free(struct au_dr_br *dr)
-+{
-+ int i;
-+ struct hlist_bl_head *hbl;
-+ struct hlist_bl_node *pos, *tmp;
-+ struct au_dr_hino *ent;
-+
-+ /* SiMustWriteLock(sb); */
-+
-+ for (i = 0; i < AuDirren_NHASH; i++) {
-+ hbl = dr->dr_h_ino + i;
-+ /* no spinlock since sbinfo must be write-locked */
-+ hlist_bl_for_each_entry_safe(ent, pos, tmp, hbl, dr_hnode)
-+ au_kfree_rcu(ent);
-+ INIT_HLIST_BL_HEAD(hbl);
-+ }
-+}
-+
-+/* returns the number of inodes or an error */
-+static int au_dr_hino_store(struct super_block *sb, struct au_branch *br,
-+ struct file *hinofile)
-+{
-+ int err, i;
-+ ssize_t ssz;
-+ loff_t pos, oldsize;
-+ __be64 u64;
-+ struct inode *hinoinode;
-+ struct hlist_bl_head *hbl;
-+ struct hlist_bl_node *n1, *n2;
-+ struct au_dr_hino *ent;
-+
-+ SiMustWriteLock(sb);
-+ AuDebugOn(!au_br_writable(br->br_perm));
-+
-+ hinoinode = file_inode(hinofile);
-+ oldsize = i_size_read(hinoinode);
-+
-+ err = 0;
-+ pos = 0;
-+ hbl = br->br_dirren.dr_h_ino;
-+ for (i = 0; !err && i < AuDirren_NHASH; i++, hbl++) {
-+ /* no bit-lock since sbinfo must be write-locked */
-+ hlist_bl_for_each_entry_safe(ent, n1, n2, hbl, dr_hnode) {
-+ AuDbg("hi%llu, %pD2\n",
-+ (unsigned long long)ent->dr_h_ino, hinofile);
-+ u64 = cpu_to_be64(ent->dr_h_ino);
-+ ssz = vfsub_write_k(hinofile, &u64, sizeof(u64), &pos);
-+ if (ssz == sizeof(u64))
-+ continue;
-+
-+ /* write error */
-+ pr_err("ssz %zd, %pD2\n", ssz, hinofile);
-+ err = -ENOSPC;
-+ if (ssz < 0)
-+ err = ssz;
-+ break;
-+ }
-+ }
-+ /* regardless the error */
-+ if (pos < oldsize) {
-+ err = vfsub_trunc(&hinofile->f_path, pos, /*attr*/0, hinofile);
-+ AuTraceErr(err);
-+ }
-+
-+ AuTraceErr(err);
-+ return err;
-+}
-+
-+static int au_dr_hino_load(struct au_dr_br *dr, struct file *hinofile)
-+{
-+ int err, hidx;
-+ ssize_t ssz;
-+ size_t sz, n;
-+ loff_t pos;
-+ uint64_t u64;
-+ struct au_dr_hino *ent;
-+ struct inode *hinoinode;
-+ struct hlist_bl_head *hbl;
-+
-+ err = 0;
-+ pos = 0;
-+ hbl = dr->dr_h_ino;
-+ hinoinode = file_inode(hinofile);
-+ sz = i_size_read(hinoinode);
-+ AuDebugOn(sz % sizeof(u64));
-+ n = sz / sizeof(u64);
-+ while (n--) {
-+ ssz = vfsub_read_k(hinofile, &u64, sizeof(u64), &pos);
-+ if (unlikely(ssz != sizeof(u64))) {
-+ pr_err("ssz %zd, %pD2\n", ssz, hinofile);
-+ err = -EINVAL;
-+ if (ssz < 0)
-+ err = ssz;
-+ goto out_free;
-+ }
-+
-+ ent = kmalloc(sizeof(*ent), GFP_NOFS);
-+ if (!ent) {
-+ err = -ENOMEM;
-+ AuTraceErr(err);
-+ goto out_free;
-+ }
-+ ent->dr_h_ino = be64_to_cpu((__force __be64)u64);
-+ AuDbg("hi%llu, %pD2\n",
-+ (unsigned long long)ent->dr_h_ino, hinofile);
-+ hidx = au_dr_ihash(ent->dr_h_ino);
-+ au_hbl_add(&ent->dr_hnode, hbl + hidx);
-+ }
-+ goto out; /* success */
-+
-+out_free:
-+ au_dr_hino_free(dr);
-+out:
-+ AuTraceErr(err);
-+ return err;
-+}
-+
-+/*
-+ * @bindex/@br is a switch to distinguish whether suspending hnotify or not.
-+ * @path is a switch to distinguish load and store.
-+ */
-+static int au_dr_hino(struct super_block *sb, aufs_bindex_t bindex,
-+ struct au_branch *br, const struct path *path)
-+{
-+ int err, flags;
-+ unsigned char load, suspend;
-+ struct file *hinofile;
-+ struct au_hinode *hdir;
-+ struct inode *dir, *delegated;
-+ struct path hinopath;
-+ struct qstr hinoname = QSTR_INIT(AUFS_WH_DR_BRHINO,
-+ sizeof(AUFS_WH_DR_BRHINO) - 1);
-+
-+ AuDebugOn(bindex < 0 && !br);
-+ AuDebugOn(bindex >= 0 && br);
-+
-+ err = -EINVAL;
-+ suspend = !br;
-+ if (suspend)
-+ br = au_sbr(sb, bindex);
-+ load = !!path;
-+ if (!load) {
-+ path = &br->br_path;
-+ AuDebugOn(!au_br_writable(br->br_perm));
-+ if (unlikely(!au_br_writable(br->br_perm)))
-+ goto out;
-+ }
-+
-+ hdir = NULL;
-+ if (suspend) {
-+ dir = d_inode(sb->s_root);
-+ hdir = au_hinode(au_ii(dir), bindex);
-+ dir = hdir->hi_inode;
-+ au_hn_inode_lock_nested(hdir, AuLsc_I_CHILD);
-+ } else {
-+ dir = d_inode(path->dentry);
-+ inode_lock_nested(dir, AuLsc_I_CHILD);
-+ }
-+ hinopath.dentry = vfsub_lkup_one(&hinoname, path->dentry);
-+ err = PTR_ERR(hinopath.dentry);
-+ if (IS_ERR(hinopath.dentry))
-+ goto out_unlock;
-+
-+ err = 0;
-+ flags = O_RDONLY;
-+ if (load) {
-+ if (d_is_negative(hinopath.dentry))
-+ goto out_dput; /* success */
-+ } else {
-+ if (au_dr_hino_test_empty(&br->br_dirren)) {
-+ if (d_is_positive(hinopath.dentry)) {
-+ delegated = NULL;
-+ err = vfsub_unlink(dir, &hinopath, &delegated,
-+ /*force*/0);
-+ AuTraceErr(err);
-+ if (unlikely(err))
-+ pr_err("ignored err %d, %pd2\n",
-+ err, hinopath.dentry);
-+ if (unlikely(err == -EWOULDBLOCK))
-+ iput(delegated);
-+ err = 0;
-+ }
-+ goto out_dput;
-+ } else if (!d_is_positive(hinopath.dentry)) {
-+ err = vfsub_create(dir, &hinopath, 0600,
-+ /*want_excl*/false);
-+ AuTraceErr(err);
-+ if (unlikely(err))
-+ goto out_dput;
-+ }
-+ flags = O_WRONLY;
-+ }
-+ hinopath.mnt = path->mnt;
-+ hinofile = vfsub_dentry_open(&hinopath, flags);
-+ if (suspend)
-+ au_hn_inode_unlock(hdir);
-+ else
-+ inode_unlock(dir);
-+ dput(hinopath.dentry);
-+ AuTraceErrPtr(hinofile);
-+ if (IS_ERR(hinofile)) {
-+ err = PTR_ERR(hinofile);
-+ goto out;
-+ }
-+
-+ if (load)
-+ err = au_dr_hino_load(&br->br_dirren, hinofile);
-+ else
-+ err = au_dr_hino_store(sb, br, hinofile);
-+ fput(hinofile);
-+ goto out;
-+
-+out_dput:
-+ dput(hinopath.dentry);
-+out_unlock:
-+ if (suspend)
-+ au_hn_inode_unlock(hdir);
-+ else
-+ inode_unlock(dir);
-+out:
-+ AuTraceErr(err);
-+ return err;
-+}
-+
-+/* ---------------------------------------------------------------------- */
-+
-+static int au_dr_brid_init(struct au_dr_brid *brid, const struct path *path)
-+{
-+ int err;
-+ struct kstatfs kstfs;
-+ dev_t dev;
-+ struct dentry *dentry;
-+ struct super_block *sb;
-+
-+ err = vfs_statfs((void *)path, &kstfs);
-+ AuTraceErr(err);
-+ if (unlikely(err))
-+ goto out;
-+
-+ /* todo: support for UUID */
-+
-+ if (kstfs.f_fsid.val[0] || kstfs.f_fsid.val[1]) {
-+ brid->type = AuBrid_FSID;
-+ brid->fsid = kstfs.f_fsid;
-+ } else {
-+ dentry = path->dentry;
-+ sb = dentry->d_sb;
-+ dev = sb->s_dev;
-+ if (dev) {
-+ brid->type = AuBrid_DEV;
-+ brid->dev = dev;
-+ }
-+ }
-+
-+out:
-+ return err;
-+}
-+
-+int au_dr_br_init(struct super_block *sb, struct au_branch *br,
-+ const struct path *path)
-+{
-+ int err, i;
-+ struct au_dr_br *dr;
-+ struct hlist_bl_head *hbl;
-+
-+ dr = &br->br_dirren;
-+ hbl = dr->dr_h_ino;
-+ for (i = 0; i < AuDirren_NHASH; i++, hbl++)
-+ INIT_HLIST_BL_HEAD(hbl);
-+
-+ err = au_dr_brid_init(&dr->dr_brid, path);
-+ if (unlikely(err))
-+ goto out;
-+
-+ if (au_opt_test(au_mntflags(sb), DIRREN))
-+ err = au_dr_hino(sb, /*bindex*/-1, br, path);
-+
-+out:
-+ AuTraceErr(err);
-+ return err;
-+}
-+
-+int au_dr_br_fin(struct super_block *sb, struct au_branch *br)
-+{
-+ int err;
-+
-+ err = 0;
-+ if (au_br_writable(br->br_perm))
-+ err = au_dr_hino(sb, /*bindex*/-1, br, /*path*/NULL);
-+ if (!err)
-+ au_dr_hino_free(&br->br_dirren);
-+
-+ return err;
-+}
-+
-+/* ---------------------------------------------------------------------- */
-+
-+static int au_brid_str(struct au_dr_brid *brid, struct inode *h_inode,
-+ char *buf, size_t sz)
-+{
-+ int err;
-+ unsigned int major, minor;
-+ char *p;
-+
-+ p = buf;
-+ err = snprintf(p, sz, "%d_", brid->type);
-+ AuDebugOn(err > sz);
-+ p += err;
-+ sz -= err;
-+ switch (brid->type) {
-+ case AuBrid_Unset:
-+ return -EINVAL;
-+ case AuBrid_UUID:
-+ err = snprintf(p, sz, "%pU", brid->uuid.b);
-+ break;
-+ case AuBrid_FSID:
-+ err = snprintf(p, sz, "%08x-%08x",
-+ brid->fsid.val[0], brid->fsid.val[1]);
-+ break;
-+ case AuBrid_DEV:
-+ major = MAJOR(brid->dev);
-+ minor = MINOR(brid->dev);
-+ if (major <= 0xff && minor <= 0xff)
-+ err = snprintf(p, sz, "%02x%02x", major, minor);
-+ else
-+ err = snprintf(p, sz, "%03x:%05x", major, minor);
-+ break;
-+ }
-+ AuDebugOn(err > sz);
-+ p += err;
-+ sz -= err;
-+ err = snprintf(p, sz, "_%llu", (unsigned long long)h_inode->i_ino);
-+ AuDebugOn(err > sz);
-+ p += err;
-+ sz -= err;
-+
-+ return p - buf;
-+}
-+
-+static int au_drinfo_name(struct au_branch *br, char *name, int len)
-+{
-+ int rlen;
-+ struct dentry *br_dentry;
-+ struct inode *br_inode;
-+
-+ br_dentry = au_br_dentry(br);
-+ br_inode = d_inode(br_dentry);
-+ rlen = au_brid_str(&br->br_dirren.dr_brid, br_inode, name, len);
-+ AuDebugOn(rlen >= AUFS_DIRREN_ENV_VAL_SZ);
-+ AuDebugOn(rlen > len);
-+
-+ return rlen;
-+}
-+
-+/* ---------------------------------------------------------------------- */
-+
-+/*
-+ * from the given @h_dentry, construct drinfo at @*fdata.
-+ * when the size of @*fdata is not enough, reallocate and return new @fdata and
-+ * @allocated.
-+ */
-+static int au_drinfo_construct(struct au_drinfo_fdata **fdata,
-+ struct dentry *h_dentry,
-+ unsigned char *allocated)
-+{
-+ int err, v;
-+ struct au_drinfo_fdata *f, *p;
-+ struct au_drinfo *drinfo;
-+ struct inode *h_inode;
-+ struct qstr *qname;
-+
-+ err = 0;
-+ f = *fdata;
-+ h_inode = d_inode(h_dentry);
-+ qname = &h_dentry->d_name;
-+ drinfo = &f->drinfo;
-+ drinfo->ino = (__force uint64_t)cpu_to_be64(h_inode->i_ino);
-+ drinfo->oldnamelen = qname->len;
-+ if (*allocated < sizeof(*f) + qname->len) {
-+ v = roundup_pow_of_two(*allocated + qname->len);
-+ p = au_krealloc(f, v, GFP_NOFS, /*may_shrink*/0);
-+ if (unlikely(!p)) {
-+ err = -ENOMEM;
-+ AuTraceErr(err);
-+ goto out;
-+ }
-+ f = p;
-+ *fdata = f;
-+ *allocated = v;
-+ drinfo = &f->drinfo;
-+ }
-+ memcpy(drinfo->oldname, qname->name, qname->len);
-+ AuDbg("i%llu, %.*s\n",
-+ be64_to_cpu((__force __be64)drinfo->ino), drinfo->oldnamelen,
-+ drinfo->oldname);
-+
-+out:
-+ AuTraceErr(err);
-+ return err;
-+}
-+
-+/* callers have to free the return value */
-+static struct au_drinfo *au_drinfo_read_k(struct file *file, ino_t h_ino)
-+{
-+ struct au_drinfo *ret, *drinfo;
-+ struct au_drinfo_fdata fdata;
-+ int len;
-+ loff_t pos;
-+ ssize_t ssz;
-+
-+ ret = ERR_PTR(-EIO);
-+ pos = 0;
-+ ssz = vfsub_read_k(file, &fdata, sizeof(fdata), &pos);
-+ if (unlikely(ssz != sizeof(fdata))) {
-+ AuIOErr("ssz %zd, %u, %pD2\n",
-+ ssz, (unsigned int)sizeof(fdata), file);
-+ goto out;
-+ }
-+
-+ fdata.magic = ntohl((__force __be32)fdata.magic);
-+ switch (fdata.magic) {
-+ case AUFS_DRINFO_MAGIC_V1:
-+ break;
-+ default:
-+ AuIOErr("magic-num 0x%x, 0x%x, %pD2\n",
-+ fdata.magic, AUFS_DRINFO_MAGIC_V1, file);
-+ goto out;
-+ }
-+
-+ drinfo = &fdata.drinfo;
-+ len = drinfo->oldnamelen;
-+ if (!len) {
-+ AuIOErr("broken drinfo %pD2\n", file);
-+ goto out;
-+ }
-+
-+ ret = NULL;
-+ drinfo->ino = be64_to_cpu((__force __be64)drinfo->ino);
-+ if (unlikely(h_ino && drinfo->ino != h_ino)) {
-+ AuDbg("ignored i%llu, i%llu, %pD2\n",
-+ (unsigned long long)drinfo->ino,
-+ (unsigned long long)h_ino, file);
-+ goto out; /* success */
-+ }
-+
-+ ret = kmalloc(sizeof(*ret) + len, GFP_NOFS);
-+ if (unlikely(!ret)) {
-+ ret = ERR_PTR(-ENOMEM);
-+ AuTraceErrPtr(ret);
-+ goto out;
-+ }
-+
-+ *ret = *drinfo;
-+ ssz = vfsub_read_k(file, (void *)ret->oldname, len, &pos);
-+ if (unlikely(ssz != len)) {
-+ au_kfree_rcu(ret);
-+ ret = ERR_PTR(-EIO);
-+ AuIOErr("ssz %zd, %u, %pD2\n", ssz, len, file);
-+ goto out;
-+ }
-+
-+ AuDbg("oldname %.*s\n", ret->oldnamelen, ret->oldname);
-+
-+out:
-+ return ret;
-+}
-+
-+/* ---------------------------------------------------------------------- */
-+
-+/* in order to be revertible */
-+struct au_drinfo_rev_elm {
-+ int created;
-+ struct dentry *info_dentry;
-+ struct au_drinfo *info_last;
-+};
-+
-+struct au_drinfo_rev {
-+ unsigned char already;
-+ aufs_bindex_t nelm;
-+ struct au_drinfo_rev_elm elm[0];
-+};
-+
-+/* todo: isn't it too large? */
-+struct au_drinfo_store {
-+ struct path h_ppath;
-+ struct dentry *h_dentry;
-+ struct au_drinfo_fdata *fdata;
-+ char *infoname; /* inside of whname, just after PFX */
-+ char whname[sizeof(AUFS_WH_DR_INFO_PFX) + AUFS_DIRREN_ENV_VAL_SZ];
-+ aufs_bindex_t btgt, btail;
-+ unsigned char no_sio,
-+ allocated, /* current size of *fdata */
-+ infonamelen, /* room size for p */
-+ whnamelen, /* length of the generated name */
-+ renameback; /* renamed back */
-+};
-+
-+/* on rename(2) error, the caller should revert it using @elm */
-+static int au_drinfo_do_store(struct au_drinfo_store *w,
-+ struct au_drinfo_rev_elm *elm)
-+{
-+ int err, len;
-+ ssize_t ssz;
-+ loff_t pos;
-+ struct path infopath = {
-+ .mnt = w->h_ppath.mnt
-+ };
-+ struct inode *h_dir, *h_inode, *delegated;
-+ struct file *infofile;
-+ struct qstr *qname;
-+
-+ AuDebugOn(elm
-+ && memcmp(elm, page_address(ZERO_PAGE(0)), sizeof(*elm)));
-+
-+ infopath.dentry = vfsub_lookup_one_len(w->whname, w->h_ppath.dentry,
-+ w->whnamelen);
-+ AuTraceErrPtr(infopath.dentry);
-+ if (IS_ERR(infopath.dentry)) {
-+ err = PTR_ERR(infopath.dentry);
-+ goto out;
-+ }
-+
-+ err = 0;
-+ h_dir = d_inode(w->h_ppath.dentry);
-+ if (elm && d_is_negative(infopath.dentry)) {
-+ err = vfsub_create(h_dir, &infopath, 0600, /*want_excl*/true);
-+ AuTraceErr(err);
-+ if (unlikely(err))
-+ goto out_dput;
-+ elm->created = 1;
-+ elm->info_dentry = dget(infopath.dentry);
-+ }
-+
-+ infofile = vfsub_dentry_open(&infopath, O_RDWR);
-+ AuTraceErrPtr(infofile);
-+ if (IS_ERR(infofile)) {
-+ err = PTR_ERR(infofile);
-+ goto out_dput;
-+ }
-+
-+ h_inode = d_inode(infopath.dentry);
-+ if (elm && i_size_read(h_inode)) {
-+ h_inode = d_inode(w->h_dentry);
-+ elm->info_last = au_drinfo_read_k(infofile, h_inode->i_ino);
-+ AuTraceErrPtr(elm->info_last);
-+ if (IS_ERR(elm->info_last)) {
-+ err = PTR_ERR(elm->info_last);
-+ elm->info_last = NULL;
-+ AuDebugOn(elm->info_dentry);
-+ goto out_fput;
-+ }
-+ }
-+
-+ if (elm && w->renameback) {
-+ delegated = NULL;
-+ err = vfsub_unlink(h_dir, &infopath, &delegated, /*force*/0);
-+ AuTraceErr(err);
-+ if (unlikely(err == -EWOULDBLOCK))
-+ iput(delegated);
-+ goto out_fput;
-+ }
-+
-+ pos = 0;
-+ qname = &w->h_dentry->d_name;
-+ len = sizeof(*w->fdata) + qname->len;
-+ if (!elm)
-+ len = sizeof(*w->fdata) + w->fdata->drinfo.oldnamelen;
-+ ssz = vfsub_write_k(infofile, w->fdata, len, &pos);
-+ if (ssz == len) {
-+ AuDbg("hi%llu, %.*s\n", w->fdata->drinfo.ino,
-+ w->fdata->drinfo.oldnamelen, w->fdata->drinfo.oldname);
-+ goto out_fput; /* success */
-+ } else {
-+ err = -EIO;
-+ if (ssz < 0)
-+ err = ssz;
-+ /* the caller should revert it using @elm */
-+ }
-+
-+out_fput:
-+ fput(infofile);
-+out_dput:
-+ dput(infopath.dentry);
-+out:
-+ AuTraceErr(err);
-+ return err;
-+}
-+
-+struct au_call_drinfo_do_store_args {
-+ int *errp;
-+ struct au_drinfo_store *w;
-+ struct au_drinfo_rev_elm *elm;
-+};
-+
-+static void au_call_drinfo_do_store(void *args)
-+{
-+ struct au_call_drinfo_do_store_args *a = args;
-+
-+ *a->errp = au_drinfo_do_store(a->w, a->elm);
-+}
-+
-+static int au_drinfo_store_sio(struct au_drinfo_store *w,
-+ struct au_drinfo_rev_elm *elm)
-+{
-+ int err, wkq_err;
-+
-+ if (w->no_sio)
-+ err = au_drinfo_do_store(w, elm);
-+ else {
-+ struct au_call_drinfo_do_store_args a = {
-+ .errp = &err,
-+ .w = w,
-+ .elm = elm
-+ };
-+ wkq_err = au_wkq_wait(au_call_drinfo_do_store, &a);
-+ if (unlikely(wkq_err))
-+ err = wkq_err;
-+ }
-+ AuTraceErr(err);
-+
-+ return err;
-+}
-+
-+static int au_drinfo_store_work_init(struct au_drinfo_store *w,
-+ aufs_bindex_t btgt)
-+{
-+ int err;
-+
-+ memset(w, 0, sizeof(*w));
-+ w->allocated = roundup_pow_of_two(sizeof(*w->fdata) + 40);
-+ strcpy(w->whname, AUFS_WH_DR_INFO_PFX);
-+ w->infoname = w->whname + sizeof(AUFS_WH_DR_INFO_PFX) - 1;
-+ w->infonamelen = sizeof(w->whname) - sizeof(AUFS_WH_DR_INFO_PFX);
-+ w->btgt = btgt;
-+ w->no_sio = !!uid_eq(current_fsuid(), GLOBAL_ROOT_UID);
-+
-+ err = -ENOMEM;
-+ w->fdata = kcalloc(1, w->allocated, GFP_NOFS);
-+ if (unlikely(!w->fdata)) {
-+ AuTraceErr(err);
-+ goto out;
-+ }
-+ w->fdata->magic = (__force uint32_t)htonl(AUFS_DRINFO_MAGIC_V1);
-+ err = 0;
-+
-+out:
-+ return err;
-+}
-+
-+static void au_drinfo_store_work_fin(struct au_drinfo_store *w)
-+{
-+ au_kfree_rcu(w->fdata);
-+}
-+
-+static void au_drinfo_store_rev(struct au_drinfo_rev *rev,
-+ struct au_drinfo_store *w)
-+{
-+ struct au_drinfo_rev_elm *elm;
-+ struct inode *h_dir, *delegated;
-+ int err, nelm;
-+ struct path infopath = {
-+ .mnt = w->h_ppath.mnt
-+ };
-+
-+ h_dir = d_inode(w->h_ppath.dentry);
-+ IMustLock(h_dir);
-+
-+ err = 0;
-+ elm = rev->elm;
-+ for (nelm = rev->nelm; nelm > 0; nelm--, elm++) {
-+ AuDebugOn(elm->created && elm->info_last);
-+ if (elm->created) {
-+ AuDbg("here\n");
-+ delegated = NULL;
-+ infopath.dentry = elm->info_dentry;
-+ err = vfsub_unlink(h_dir, &infopath, &delegated,
-+ !w->no_sio);
-+ AuTraceErr(err);
-+ if (unlikely(err == -EWOULDBLOCK))
-+ iput(delegated);
-+ dput(elm->info_dentry);
-+ } else if (elm->info_last) {
-+ AuDbg("here\n");
-+ w->fdata->drinfo = *elm->info_last;
-+ memcpy(w->fdata->drinfo.oldname,
-+ elm->info_last->oldname,
-+ elm->info_last->oldnamelen);
-+ err = au_drinfo_store_sio(w, /*elm*/NULL);
-+ au_kfree_rcu(elm->info_last);
-+ }
-+ if (unlikely(err))
-+ AuIOErr("%d, %s\n", err, w->whname);
-+ /* go on even if err */
-+ }
-+}
-+
-+/* caller has to call au_dr_rename_fin() later */
-+static int au_drinfo_store(struct dentry *dentry, aufs_bindex_t btgt,
-+ struct qstr *dst_name, void *_rev)
-+{
-+ int err, sz, nelm;
-+ aufs_bindex_t bindex, btail;
-+ struct au_drinfo_store work;
-+ struct au_drinfo_rev *rev, **p;
-+ struct au_drinfo_rev_elm *elm;
-+ struct super_block *sb;
-+ struct au_branch *br;
-+ struct au_hinode *hdir;
-+
-+ err = au_drinfo_store_work_init(&work, btgt);
-+ AuTraceErr(err);
-+ if (unlikely(err))
-+ goto out;
-+
-+ err = -ENOMEM;
-+ btail = au_dbtaildir(dentry);
-+ nelm = btail - btgt;
-+ sz = sizeof(*rev) + sizeof(*elm) * nelm;
-+ rev = kcalloc(1, sz, GFP_NOFS);
-+ if (unlikely(!rev)) {
-+ AuTraceErr(err);
-+ goto out_args;
-+ }
-+ rev->nelm = nelm;
-+ elm = rev->elm;
-+ p = _rev;
-+ *p = rev;
-+
-+ err = 0;
-+ sb = dentry->d_sb;
-+ work.h_ppath.dentry = au_h_dptr(dentry, btgt);
-+ work.h_ppath.mnt = au_sbr_mnt(sb, btgt);
-+ hdir = au_hi(d_inode(dentry), btgt);
-+ au_hn_inode_lock_nested(hdir, AuLsc_I_CHILD);
-+ for (bindex = btgt + 1; bindex <= btail; bindex++, elm++) {
-+ work.h_dentry = au_h_dptr(dentry, bindex);
-+ if (!work.h_dentry)
-+ continue;
-+
-+ err = au_drinfo_construct(&work.fdata, work.h_dentry,
-+ &work.allocated);
-+ AuTraceErr(err);
-+ if (unlikely(err))
-+ break;
-+
-+ work.renameback = au_qstreq(&work.h_dentry->d_name, dst_name);
-+ br = au_sbr(sb, bindex);
-+ work.whnamelen = sizeof(AUFS_WH_DR_INFO_PFX) - 1;
-+ work.whnamelen += au_drinfo_name(br, work.infoname,
-+ work.infonamelen);
-+ AuDbg("whname %.*s, i%llu, %.*s\n",
-+ work.whnamelen, work.whname,
-+ be64_to_cpu((__force __be64)work.fdata->drinfo.ino),
-+ work.fdata->drinfo.oldnamelen,
-+ work.fdata->drinfo.oldname);
-+
-+ err = au_drinfo_store_sio(&work, elm);
-+ AuTraceErr(err);
-+ if (unlikely(err))
-+ break;
-+ }
-+ if (unlikely(err)) {
-+ /* revert all drinfo */
-+ au_drinfo_store_rev(rev, &work);
-+ au_kfree_try_rcu(rev);
-+ *p = NULL;
-+ }
-+ au_hn_inode_unlock(hdir);
-+
-+out_args:
-+ au_drinfo_store_work_fin(&work);
-+out:
-+ return err;
-+}
-+
-+/* ---------------------------------------------------------------------- */
-+
-+int au_dr_rename(struct dentry *src, aufs_bindex_t bindex,
-+ struct qstr *dst_name, void *_rev)
-+{
-+ int err, already;
-+ ino_t ino;
-+ struct super_block *sb;
-+ struct au_branch *br;
-+ struct au_dr_br *dr;
-+ struct dentry *h_dentry;
-+ struct inode *h_inode;
-+ struct au_dr_hino *ent;
-+ struct au_drinfo_rev *rev, **p;
-+
-+ AuDbg("bindex %d\n", bindex);
-+
-+ err = -ENOMEM;
-+ ent = kmalloc(sizeof(*ent), GFP_NOFS);
-+ if (unlikely(!ent))
-+ goto out;
-+
-+ sb = src->d_sb;
-+ br = au_sbr(sb, bindex);
-+ dr = &br->br_dirren;
-+ h_dentry = au_h_dptr(src, bindex);
-+ h_inode = d_inode(h_dentry);
-+ ino = h_inode->i_ino;
-+ ent->dr_h_ino = ino;
-+ already = au_dr_hino_test_add(dr, ino, ent);
-+ AuDbg("b%d, hi%llu, already %d\n",
-+ bindex, (unsigned long long)ino, already);
-+
-+ err = au_drinfo_store(src, bindex, dst_name, _rev);
-+ AuTraceErr(err);
-+ if (!err) {
-+ p = _rev;
-+ rev = *p;
-+ rev->already = already;
-+ goto out; /* success */
-+ }
-+
-+ /* revert */
-+ if (!already)
-+ au_dr_hino_del(dr, ent);
-+ au_kfree_rcu(ent);
-+
-+out:
-+ AuTraceErr(err);
-+ return err;
-+}
-+
-+void au_dr_rename_fin(struct dentry *src, aufs_bindex_t btgt, void *_rev)
-+{
-+ struct au_drinfo_rev *rev;
-+ struct au_drinfo_rev_elm *elm;
-+ int nelm;
-+
-+ rev = _rev;
-+ elm = rev->elm;
-+ for (nelm = rev->nelm; nelm > 0; nelm--, elm++) {
-+ dput(elm->info_dentry);
-+ au_kfree_rcu(elm->info_last);
-+ }
-+ au_kfree_try_rcu(rev);
-+}
-+
-+void au_dr_rename_rev(struct dentry *src, aufs_bindex_t btgt, void *_rev)
-+{
-+ int err;
-+ struct au_drinfo_store work;
-+ struct au_drinfo_rev *rev = _rev;
-+ struct super_block *sb;
-+ struct au_branch *br;
-+ struct inode *h_inode;
-+ struct au_dr_br *dr;
-+ struct au_dr_hino *ent;
-+
-+ err = au_drinfo_store_work_init(&work, btgt);
-+ if (unlikely(err))
-+ goto out;
-+
-+ sb = src->d_sb;
-+ br = au_sbr(sb, btgt);
-+ work.h_ppath.dentry = au_h_dptr(src, btgt);
-+ work.h_ppath.mnt = au_br_mnt(br);
-+ au_drinfo_store_rev(rev, &work);
-+ au_drinfo_store_work_fin(&work);
-+ if (rev->already)
-+ goto out;
-+
-+ dr = &br->br_dirren;
-+ h_inode = d_inode(work.h_ppath.dentry);
-+ ent = au_dr_hino_find(dr, h_inode->i_ino);
-+ BUG_ON(!ent);
-+ au_dr_hino_del(dr, ent);
-+ au_kfree_rcu(ent);
-+
-+out:
-+ au_kfree_try_rcu(rev);
-+ if (unlikely(err))
-+ pr_err("failed to remove dirren info\n");
-+}
-+
-+/* ---------------------------------------------------------------------- */
-+
-+static struct au_drinfo *au_drinfo_do_load(struct path *h_ppath,
-+ char *whname, int whnamelen,
-+ struct dentry **info_dentry)
-+{
-+ struct au_drinfo *drinfo;
-+ struct file *f;
-+ struct inode *h_dir;
-+ struct path infopath;
-+ int unlocked;
-+
-+ AuDbg("%pd/%.*s\n", h_ppath->dentry, whnamelen, whname);
-+
-+ *info_dentry = NULL;
-+ drinfo = NULL;
-+ unlocked = 0;
-+ h_dir = d_inode(h_ppath->dentry);
-+ inode_lock_shared_nested(h_dir, AuLsc_I_PARENT);
-+ infopath.dentry = vfsub_lookup_one_len(whname, h_ppath->dentry,
-+ whnamelen);
-+ if (IS_ERR(infopath.dentry)) {
-+ drinfo = (void *)infopath.dentry;
-+ goto out;
-+ }
-+
-+ if (d_is_negative(infopath.dentry))
-+ goto out_dput; /* success */
-+
-+ infopath.mnt = h_ppath->mnt;
-+ f = vfsub_dentry_open(&infopath, O_RDONLY);
-+ inode_unlock_shared(h_dir);
-+ unlocked = 1;
-+ if (IS_ERR(f)) {
-+ drinfo = (void *)f;
-+ goto out_dput;
-+ }
-+
-+ drinfo = au_drinfo_read_k(f, /*h_ino*/0);
-+ if (IS_ERR_OR_NULL(drinfo))
-+ goto out_fput;
-+
-+ AuDbg("oldname %.*s\n", drinfo->oldnamelen, drinfo->oldname);
-+ *info_dentry = dget(infopath.dentry); /* keep it alive */
-+
-+out_fput:
-+ fput(f);
-+out_dput:
-+ dput(infopath.dentry);
-+out:
-+ if (!unlocked)
-+ inode_unlock_shared(h_dir);
-+ AuTraceErrPtr(drinfo);
-+ return drinfo;
-+}
-+
-+struct au_drinfo_do_load_args {
-+ struct au_drinfo **drinfop;
-+ struct path *h_ppath;
-+ char *whname;
-+ int whnamelen;
-+ struct dentry **info_dentry;
-+};
-+
-+static void au_call_drinfo_do_load(void *args)
-+{
-+ struct au_drinfo_do_load_args *a = args;
-+
-+ *a->drinfop = au_drinfo_do_load(a->h_ppath, a->whname, a->whnamelen,
-+ a->info_dentry);
-+}
-+
-+struct au_drinfo_load {
-+ struct path h_ppath;
-+ struct qstr *qname;
-+ unsigned char no_sio;
-+
-+ aufs_bindex_t ninfo;
-+ struct au_drinfo **drinfo;
-+};
-+
-+static int au_drinfo_load(struct au_drinfo_load *w, aufs_bindex_t bindex,
-+ struct au_branch *br)
-+{
-+ int err, wkq_err, whnamelen, e;
-+ char whname[sizeof(AUFS_WH_DR_INFO_PFX) + AUFS_DIRREN_ENV_VAL_SZ]
-+ = AUFS_WH_DR_INFO_PFX;
-+ struct au_drinfo *drinfo;
-+ struct qstr oldname;
-+ struct inode *h_dir, *delegated;
-+ struct dentry *info_dentry;
-+ struct path infopath;
-+
-+ whnamelen = sizeof(AUFS_WH_DR_INFO_PFX) - 1;
-+ whnamelen += au_drinfo_name(br, whname + whnamelen,
-+ sizeof(whname) - whnamelen);
-+ if (w->no_sio)
-+ drinfo = au_drinfo_do_load(&w->h_ppath, whname, whnamelen,
-+ &info_dentry);
-+ else {
-+ struct au_drinfo_do_load_args args = {
-+ .drinfop = &drinfo,
-+ .h_ppath = &w->h_ppath,
-+ .whname = whname,
-+ .whnamelen = whnamelen,
-+ .info_dentry = &info_dentry
-+ };
-+ wkq_err = au_wkq_wait(au_call_drinfo_do_load, &args);
-+ if (unlikely(wkq_err))
-+ drinfo = ERR_PTR(wkq_err);
-+ }
-+ err = PTR_ERR(drinfo);
-+ if (IS_ERR_OR_NULL(drinfo))
-+ goto out;
-+
-+ err = 0;
-+ oldname.len = drinfo->oldnamelen;
-+ oldname.name = drinfo->oldname;
-+ if (au_qstreq(w->qname, &oldname)) {
-+ /* the name is renamed back */
-+ au_kfree_rcu(drinfo);
-+ drinfo = NULL;
-+
-+ infopath.dentry = info_dentry;
-+ infopath.mnt = w->h_ppath.mnt;
-+ h_dir = d_inode(w->h_ppath.dentry);
-+ delegated = NULL;
-+ inode_lock_nested(h_dir, AuLsc_I_PARENT);
-+ e = vfsub_unlink(h_dir, &infopath, &delegated, !w->no_sio);
-+ inode_unlock(h_dir);
-+ if (unlikely(e))
-+ AuIOErr("ignored %d, %pd2\n", e, &infopath.dentry);
-+ if (unlikely(e == -EWOULDBLOCK))
-+ iput(delegated);
-+ }
-+ au_kfree_rcu(w->drinfo[bindex]);
-+ w->drinfo[bindex] = drinfo;
-+ dput(info_dentry);
-+
-+out:
-+ AuTraceErr(err);
-+ return err;
-+}
-+
-+/* ---------------------------------------------------------------------- */
-+
-+static void au_dr_lkup_free(struct au_drinfo **drinfo, int n)
-+{
-+ struct au_drinfo **p = drinfo;
-+
-+ while (n-- > 0)
-+ au_kfree_rcu(*drinfo++);
-+ au_kfree_try_rcu(p);
-+}
-+
-+int au_dr_lkup(struct au_do_lookup_args *lkup, struct dentry *dentry,
-+ aufs_bindex_t btgt)
-+{
-+ int err, ninfo;
-+ struct au_drinfo_load w;
-+ aufs_bindex_t bindex, bbot;
-+ struct au_branch *br;
-+ struct inode *h_dir;
-+ struct au_dr_hino *ent;
-+ struct super_block *sb;
-+
-+ AuDbg("%.*s, name %.*s, whname %.*s, b%d\n",
-+ AuLNPair(&dentry->d_name), AuLNPair(&lkup->dirren.dr_name),
-+ AuLNPair(&lkup->whname), btgt);
-+
-+ sb = dentry->d_sb;
-+ bbot = au_sbbot(sb);
-+ w.ninfo = bbot + 1;
-+ if (!lkup->dirren.drinfo) {
-+ lkup->dirren.drinfo = kcalloc(w.ninfo,
-+ sizeof(*lkup->dirren.drinfo),
-+ GFP_NOFS);
-+ if (unlikely(!lkup->dirren.drinfo)) {
-+ err = -ENOMEM;
-+ goto out;
-+ }
-+ lkup->dirren.ninfo = w.ninfo;
-+ }
-+ w.drinfo = lkup->dirren.drinfo;
-+ w.no_sio = !!uid_eq(current_fsuid(), GLOBAL_ROOT_UID);
-+ w.h_ppath.dentry = au_h_dptr(dentry, btgt);
-+ AuDebugOn(!w.h_ppath.dentry);
-+ w.h_ppath.mnt = au_sbr_mnt(sb, btgt);
-+ w.qname = &dentry->d_name;
-+
-+ ninfo = 0;
-+ for (bindex = btgt + 1; bindex <= bbot; bindex++) {
-+ br = au_sbr(sb, bindex);
-+ err = au_drinfo_load(&w, bindex, br);
-+ if (unlikely(err))
-+ goto out_free;
-+ if (w.drinfo[bindex])
-+ ninfo++;
-+ }
-+ if (!ninfo) {
-+ br = au_sbr(sb, btgt);
-+ h_dir = d_inode(w.h_ppath.dentry);
-+ ent = au_dr_hino_find(&br->br_dirren, h_dir->i_ino);
-+ AuDebugOn(!ent);
-+ au_dr_hino_del(&br->br_dirren, ent);
-+ au_kfree_rcu(ent);
-+ }
-+ goto out; /* success */
-+
-+out_free:
-+ au_dr_lkup_free(lkup->dirren.drinfo, lkup->dirren.ninfo);
-+ lkup->dirren.ninfo = 0;
-+ lkup->dirren.drinfo = NULL;
-+out:
-+ AuTraceErr(err);
-+ return err;
-+}
-+
-+void au_dr_lkup_fin(struct au_do_lookup_args *lkup)
-+{
-+ au_dr_lkup_free(lkup->dirren.drinfo, lkup->dirren.ninfo);
-+}
-+
-+int au_dr_lkup_name(struct au_do_lookup_args *lkup, aufs_bindex_t btgt)
-+{
-+ int err;
-+ struct au_drinfo *drinfo;
-+
-+ err = 0;
-+ if (!lkup->dirren.drinfo)
-+ goto out;
-+ AuDebugOn(lkup->dirren.ninfo < btgt + 1);
-+ drinfo = lkup->dirren.drinfo[btgt + 1];
-+ if (!drinfo)
-+ goto out;
-+
-+ au_kfree_try_rcu(lkup->whname.name);
-+ lkup->whname.name = NULL;
-+ lkup->dirren.dr_name.len = drinfo->oldnamelen;
-+ lkup->dirren.dr_name.name = drinfo->oldname;
-+ lkup->name = &lkup->dirren.dr_name;
-+ err = au_wh_name_alloc(&lkup->whname, lkup->name);
-+ if (!err)
-+ AuDbg("name %.*s, whname %.*s, b%d\n",
-+ AuLNPair(lkup->name), AuLNPair(&lkup->whname),
-+ btgt);
-+
-+out:
-+ AuTraceErr(err);
-+ return err;
-+}
-+
-+int au_dr_lkup_h_ino(struct au_do_lookup_args *lkup, aufs_bindex_t bindex,
-+ ino_t h_ino)
-+{
-+ int match;
-+ struct au_drinfo *drinfo;
-+
-+ match = 1;
-+ if (!lkup->dirren.drinfo)
-+ goto out;
-+ AuDebugOn(lkup->dirren.ninfo < bindex + 1);
-+ drinfo = lkup->dirren.drinfo[bindex + 1];
-+ if (!drinfo)
-+ goto out;
-+
-+ match = (drinfo->ino == h_ino);
-+ AuDbg("match %d\n", match);
-+
-+out:
-+ return match;
-+}
-+
-+/* ---------------------------------------------------------------------- */
-+
-+int au_dr_opt_set(struct super_block *sb)
-+{
-+ int err;
-+ aufs_bindex_t bindex, bbot;
-+ struct au_branch *br;
-+
-+ err = 0;
-+ bbot = au_sbbot(sb);
-+ for (bindex = 0; !err && bindex <= bbot; bindex++) {
-+ br = au_sbr(sb, bindex);
-+ err = au_dr_hino(sb, bindex, /*br*/NULL, &br->br_path);
-+ }
-+
-+ return err;
-+}
-+
-+int au_dr_opt_flush(struct super_block *sb)
-+{
-+ int err;
-+ aufs_bindex_t bindex, bbot;
-+ struct au_branch *br;
-+
-+ err = 0;
-+ bbot = au_sbbot(sb);
-+ for (bindex = 0; !err && bindex <= bbot; bindex++) {
-+ br = au_sbr(sb, bindex);
-+ if (au_br_writable(br->br_perm))
-+ err = au_dr_hino(sb, bindex, /*br*/NULL, /*path*/NULL);
-+ }
-+
-+ return err;
-+}
-+
-+int au_dr_opt_clr(struct super_block *sb, int no_flush)
-+{
-+ int err;
-+ aufs_bindex_t bindex, bbot;
-+ struct au_branch *br;
-+
-+ err = 0;
-+ if (!no_flush) {
-+ err = au_dr_opt_flush(sb);
-+ if (unlikely(err))
-+ goto out;
-+ }
-+
-+ bbot = au_sbbot(sb);
-+ for (bindex = 0; bindex <= bbot; bindex++) {
-+ br = au_sbr(sb, bindex);
-+ au_dr_hino_free(&br->br_dirren);
-+ }
-+
-+out:
-+ return err;
-+}
-diff --git a/fs/aufs/dirren.h b/fs/aufs/dirren.h
-new file mode 100644
-index 000000000000..a986736462c3
---- /dev/null
-+++ b/fs/aufs/dirren.h
-@@ -0,0 +1,140 @@
-+/* SPDX-License-Identifier: GPL-2.0 */
-+/*
-+ * Copyright (C) 2017-2019 Junjiro R. Okajima
-+ *
-+ * This program, aufs is free software; you can redistribute it and/or modify
-+ * it under the terms of the GNU General Public License as published by
-+ * the Free Software Foundation; either version 2 of the License, or
-+ * (at your option) any later version.
-+ *
-+ * This program is distributed in the hope that it will be useful,
-+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
-+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
-+ * GNU General Public License for more details.
-+ *
-+ * You should have received a copy of the GNU General Public License
-+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
-+ */
-+
-+/*
-+ * renamed dir info
-+ */
-+
-+#ifndef __AUFS_DIRREN_H__
-+#define __AUFS_DIRREN_H__
-+
-+#ifdef __KERNEL__
-+
-+#include <linux/dcache.h>
-+#include <linux/statfs.h>
-+#include <linux/uuid.h>
-+#include "hbl.h"
-+
-+#define AuDirren_NHASH 100
-+
-+#ifdef CONFIG_AUFS_DIRREN
-+enum au_brid_type {
-+ AuBrid_Unset,
-+ AuBrid_UUID,
-+ AuBrid_FSID,
-+ AuBrid_DEV
-+};
-+
-+struct au_dr_brid {
-+ enum au_brid_type type;
-+ union {
-+ uuid_t uuid; /* unimplemented yet */
-+ fsid_t fsid;
-+ dev_t dev;
-+ };
-+};
-+
-+/* 20 is the max digits length of ulong 64 */
-+/* brid-type "_" uuid "_" inum */
-+#define AUFS_DIRREN_FNAME_SZ (1 + 1 + UUID_STRING_LEN + 20)
-+#define AUFS_DIRREN_ENV_VAL_SZ (AUFS_DIRREN_FNAME_SZ + 1 + 20)
-+
-+struct au_dr_hino {
-+ struct hlist_bl_node dr_hnode;
-+ ino_t dr_h_ino;
-+};
-+
-+struct au_dr_br {
-+ struct hlist_bl_head dr_h_ino[AuDirren_NHASH];
-+ struct au_dr_brid dr_brid;
-+};
-+
-+struct au_dr_lookup {
-+ /* dr_name is pointed by struct au_do_lookup_args.name */
-+ struct qstr dr_name; /* subset of dr_info */
-+ aufs_bindex_t ninfo;
-+ struct au_drinfo **drinfo;
-+};
-+#else
-+struct au_dr_hino;
-+/* empty */
-+struct au_dr_br { };
-+struct au_dr_lookup { };
-+#endif
-+
-+/* ---------------------------------------------------------------------- */
-+
-+struct au_branch;
-+struct au_do_lookup_args;
-+struct au_hinode;
-+#ifdef CONFIG_AUFS_DIRREN
-+int au_dr_hino_test_add(struct au_dr_br *dr, ino_t h_ino,
-+ struct au_dr_hino *add_ent);
-+void au_dr_hino_free(struct au_dr_br *dr);
-+int au_dr_br_init(struct super_block *sb, struct au_branch *br,
-+ const struct path *path);
-+int au_dr_br_fin(struct super_block *sb, struct au_branch *br);
-+int au_dr_rename(struct dentry *src, aufs_bindex_t bindex,
-+ struct qstr *dst_name, void *_rev);
-+void au_dr_rename_fin(struct dentry *src, aufs_bindex_t btgt, void *rev);
-+void au_dr_rename_rev(struct dentry *src, aufs_bindex_t bindex, void *rev);
-+int au_dr_lkup(struct au_do_lookup_args *lkup, struct dentry *dentry,
-+ aufs_bindex_t bindex);
-+int au_dr_lkup_name(struct au_do_lookup_args *lkup, aufs_bindex_t btgt);
-+int au_dr_lkup_h_ino(struct au_do_lookup_args *lkup, aufs_bindex_t bindex,
-+ ino_t h_ino);
-+void au_dr_lkup_fin(struct au_do_lookup_args *lkup);
-+int au_dr_opt_set(struct super_block *sb);
-+int au_dr_opt_flush(struct super_block *sb);
-+int au_dr_opt_clr(struct super_block *sb, int no_flush);
-+#else
-+AuStubInt0(au_dr_hino_test_add, struct au_dr_br *dr, ino_t h_ino,
-+ struct au_dr_hino *add_ent);
-+AuStubVoid(au_dr_hino_free, struct au_dr_br *dr);
-+AuStubInt0(au_dr_br_init, struct super_block *sb, struct au_branch *br,
-+ const struct path *path);
-+AuStubInt0(au_dr_br_fin, struct super_block *sb, struct au_branch *br);
-+AuStubInt0(au_dr_rename, struct dentry *src, aufs_bindex_t bindex,
-+ struct qstr *dst_name, void *_rev);
-+AuStubVoid(au_dr_rename_fin, struct dentry *src, aufs_bindex_t btgt, void *rev);
-+AuStubVoid(au_dr_rename_rev, struct dentry *src, aufs_bindex_t bindex,
-+ void *rev);
-+AuStubInt0(au_dr_lkup, struct au_do_lookup_args *lkup, struct dentry *dentry,
-+ aufs_bindex_t bindex);
-+AuStubInt0(au_dr_lkup_name, struct au_do_lookup_args *lkup, aufs_bindex_t btgt);
-+AuStubInt0(au_dr_lkup_h_ino, struct au_do_lookup_args *lkup,
-+ aufs_bindex_t bindex, ino_t h_ino);
-+AuStubVoid(au_dr_lkup_fin, struct au_do_lookup_args *lkup);
-+AuStubInt0(au_dr_opt_set, struct super_block *sb);
-+AuStubInt0(au_dr_opt_flush, struct super_block *sb);
-+AuStubInt0(au_dr_opt_clr, struct super_block *sb, int no_flush);
-+#endif
-+
-+/* ---------------------------------------------------------------------- */
-+
-+#ifdef CONFIG_AUFS_DIRREN
-+static inline int au_dr_ihash(ino_t h_ino)
-+{
-+ return h_ino % AuDirren_NHASH;
-+}
-+#else
-+AuStubInt0(au_dr_ihash, ino_t h_ino);
-+#endif
-+
-+#endif /* __KERNEL__ */
-+#endif /* __AUFS_DIRREN_H__ */
-diff --git a/fs/aufs/dynop.c b/fs/aufs/dynop.c
-new file mode 100644
-index 000000000000..ed79f8255a8f
---- /dev/null
-+++ b/fs/aufs/dynop.c
-@@ -0,0 +1,367 @@
-+// SPDX-License-Identifier: GPL-2.0
-+/*
-+ * Copyright (C) 2010-2019 Junjiro R. Okajima
-+ *
-+ * This program, aufs is free software; you can redistribute it and/or modify
-+ * it under the terms of the GNU General Public License as published by
-+ * the Free Software Foundation; either version 2 of the License, or
-+ * (at your option) any later version.
-+ *
-+ * This program is distributed in the hope that it will be useful,
-+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
-+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
-+ * GNU General Public License for more details.
-+ *
-+ * You should have received a copy of the GNU General Public License
-+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
-+ */
-+
-+/*
-+ * dynamically customizable operations for regular files
-+ */
-+
-+#include "aufs.h"
-+
-+#define DyPrSym(key) AuDbgSym(key->dk_op.dy_hop)
-+
-+/*
-+ * How large will these lists be?
-+ * Usually just a few elements, 20-30 at most for each, I guess.
-+ */
-+static struct hlist_bl_head dynop[AuDyLast];
-+
-+static struct au_dykey *dy_gfind_get(struct hlist_bl_head *hbl,
-+ const void *h_op)
-+{
-+ struct au_dykey *key, *tmp;
-+ struct hlist_bl_node *pos;
-+
-+ key = NULL;
-+ hlist_bl_lock(hbl);
-+ hlist_bl_for_each_entry(tmp, pos, hbl, dk_hnode)
-+ if (tmp->dk_op.dy_hop == h_op) {
-+ if (kref_get_unless_zero(&tmp->dk_kref))
-+ key = tmp;
-+ break;
-+ }
-+ hlist_bl_unlock(hbl);
-+
-+ return key;
-+}
-+
-+static struct au_dykey *dy_bradd(struct au_branch *br, struct au_dykey *key)
-+{
-+ struct au_dykey **k, *found;
-+ const void *h_op = key->dk_op.dy_hop;
-+ int i;
-+
-+ found = NULL;
-+ k = br->br_dykey;
-+ for (i = 0; i < AuBrDynOp; i++)
-+ if (k[i]) {
-+ if (k[i]->dk_op.dy_hop == h_op) {
-+ found = k[i];
-+ break;
-+ }
-+ } else
-+ break;
-+ if (!found) {
-+ spin_lock(&br->br_dykey_lock);
-+ for (; i < AuBrDynOp; i++)
-+ if (k[i]) {
-+ if (k[i]->dk_op.dy_hop == h_op) {
-+ found = k[i];
-+ break;
-+ }
-+ } else {
-+ k[i] = key;
-+ break;
-+ }
-+ spin_unlock(&br->br_dykey_lock);
-+ BUG_ON(i == AuBrDynOp); /* expand the array */
-+ }
-+
-+ return found;
-+}
-+
-+/* kref_get() if @key is already added */
-+static struct au_dykey *dy_gadd(struct hlist_bl_head *hbl, struct au_dykey *key)
-+{
-+ struct au_dykey *tmp, *found;
-+ struct hlist_bl_node *pos;
-+ const void *h_op = key->dk_op.dy_hop;
-+
-+ found = NULL;
-+ hlist_bl_lock(hbl);
-+ hlist_bl_for_each_entry(tmp, pos, hbl, dk_hnode)
-+ if (tmp->dk_op.dy_hop == h_op) {
-+ if (kref_get_unless_zero(&tmp->dk_kref))
-+ found = tmp;
-+ break;
-+ }
-+ if (!found)
-+ hlist_bl_add_head(&key->dk_hnode, hbl);
-+ hlist_bl_unlock(hbl);
-+
-+ if (!found)
-+ DyPrSym(key);
-+ return found;
-+}
-+
-+static void dy_free_rcu(struct rcu_head *rcu)
-+{
-+ struct au_dykey *key;
-+
-+ key = container_of(rcu, struct au_dykey, dk_rcu);
-+ DyPrSym(key);
-+ kfree(key);
-+}
-+
-+static void dy_free(struct kref *kref)
-+{
-+ struct au_dykey *key;
-+ struct hlist_bl_head *hbl;
-+
-+ key = container_of(kref, struct au_dykey, dk_kref);
-+ hbl = dynop + key->dk_op.dy_type;
-+ au_hbl_del(&key->dk_hnode, hbl);
-+ call_rcu(&key->dk_rcu, dy_free_rcu);
-+}
-+
-+void au_dy_put(struct au_dykey *key)
-+{
-+ kref_put(&key->dk_kref, dy_free);
-+}
-+
-+/* ---------------------------------------------------------------------- */
-+
-+#define DyDbgSize(cnt, op) AuDebugOn(cnt != sizeof(op)/sizeof(void *))
-+
-+#ifdef CONFIG_AUFS_DEBUG
-+#define DyDbgDeclare(cnt) unsigned int cnt = 0
-+#define DyDbgInc(cnt) do { cnt++; } while (0)
-+#else
-+#define DyDbgDeclare(cnt) do {} while (0)
-+#define DyDbgInc(cnt) do {} while (0)
-+#endif
-+
-+#define DySet(func, dst, src, h_op, h_sb) do { \
-+ DyDbgInc(cnt); \
-+ if (h_op->func) { \
-+ if (src.func) \
-+ dst.func = src.func; \
-+ else \
-+ AuDbg("%s %s\n", au_sbtype(h_sb), #func); \
-+ } \
-+} while (0)
-+
-+#define DySetForce(func, dst, src) do { \
-+ AuDebugOn(!src.func); \
-+ DyDbgInc(cnt); \
-+ dst.func = src.func; \
-+} while (0)
-+
-+#define DySetAop(func) \
-+ DySet(func, dyaop->da_op, aufs_aop, h_aop, h_sb)
-+#define DySetAopForce(func) \
-+ DySetForce(func, dyaop->da_op, aufs_aop)
-+
-+static void dy_aop(struct au_dykey *key, const void *h_op,
-+ struct super_block *h_sb __maybe_unused)
-+{
-+ struct au_dyaop *dyaop = (void *)key;
-+ const struct address_space_operations *h_aop = h_op;
-+ DyDbgDeclare(cnt);
-+
-+ AuDbg("%s\n", au_sbtype(h_sb));
-+
-+ DySetAop(writepage);
-+ DySetAopForce(readpage); /* force */
-+ DySetAop(writepages);
-+ DySetAop(set_page_dirty);
-+ DySetAop(readpages);
-+ DySetAop(write_begin);
-+ DySetAop(write_end);
-+ DySetAop(bmap);
-+ DySetAop(invalidatepage);
-+ DySetAop(releasepage);
-+ DySetAop(freepage);
-+ /* this one will be changed according to an aufs mount option */
-+ DySetAop(direct_IO);
-+ DySetAop(migratepage);
-+ DySetAop(isolate_page);
-+ DySetAop(putback_page);
-+ DySetAop(launder_page);
-+ DySetAop(is_partially_uptodate);
-+ DySetAop(is_dirty_writeback);
-+ DySetAop(error_remove_page);
-+ DySetAop(swap_activate);
-+ DySetAop(swap_deactivate);
-+
-+ DyDbgSize(cnt, *h_aop);
-+}
-+
-+/* ---------------------------------------------------------------------- */
-+
-+static void dy_bug(struct kref *kref)
-+{
-+ BUG();
-+}
-+
-+static struct au_dykey *dy_get(struct au_dynop *op, struct au_branch *br)
-+{
-+ struct au_dykey *key, *old;
-+ struct hlist_bl_head *hbl;
-+ struct op {
-+ unsigned int sz;
-+ void (*set)(struct au_dykey *key, const void *h_op,
-+ struct super_block *h_sb __maybe_unused);
-+ };
-+ static const struct op a[] = {
-+ [AuDy_AOP] = {
-+ .sz = sizeof(struct au_dyaop),
-+ .set = dy_aop
-+ }
-+ };
-+ const struct op *p;
-+
-+ hbl = dynop + op->dy_type;
-+ key = dy_gfind_get(hbl, op->dy_hop);
-+ if (key)
-+ goto out_add; /* success */
-+
-+ p = a + op->dy_type;
-+ key = kzalloc(p->sz, GFP_NOFS);
-+ if (unlikely(!key)) {
-+ key = ERR_PTR(-ENOMEM);
-+ goto out;
-+ }
-+
-+ key->dk_op.dy_hop = op->dy_hop;
-+ kref_init(&key->dk_kref);
-+ p->set(key, op->dy_hop, au_br_sb(br));
-+ old = dy_gadd(hbl, key);
-+ if (old) {
-+ au_kfree_rcu(key);
-+ key = old;
-+ }
-+
-+out_add:
-+ old = dy_bradd(br, key);
-+ if (old)
-+ /* its ref-count should never be zero here */
-+ kref_put(&key->dk_kref, dy_bug);
-+out:
-+ return key;
-+}
-+
-+/* ---------------------------------------------------------------------- */
-+/*
-+ * Aufs prohibits O_DIRECT by default even if the branch supports it.
-+ * This behaviour is necessary to return an error from open(O_DIRECT) instead
-+ * of the succeeding I/O. The dio mount option enables O_DIRECT and makes
-+ * open(O_DIRECT) always succeed, but the succeeding I/O may return an error.
-+ * See the aufs manual in detail.
-+ */
-+static void dy_adx(struct au_dyaop *dyaop, int do_dx)
-+{
-+ if (!do_dx)
-+ dyaop->da_op.direct_IO = NULL;
-+ else
-+ dyaop->da_op.direct_IO = aufs_aop.direct_IO;
-+}
-+
-+static struct au_dyaop *dy_aget(struct au_branch *br,
-+ const struct address_space_operations *h_aop,
-+ int do_dx)
-+{
-+ struct au_dyaop *dyaop;
-+ struct au_dynop op;
-+
-+ op.dy_type = AuDy_AOP;
-+ op.dy_haop = h_aop;
-+ dyaop = (void *)dy_get(&op, br);
-+ if (IS_ERR(dyaop))
-+ goto out;
-+ dy_adx(dyaop, do_dx);
-+
-+out:
-+ return dyaop;
-+}
-+
-+int au_dy_iaop(struct inode *inode, aufs_bindex_t bindex,
-+ struct inode *h_inode)
-+{
-+ int err, do_dx;
-+ struct super_block *sb;
-+ struct au_branch *br;
-+ struct au_dyaop *dyaop;
-+
-+ AuDebugOn(!S_ISREG(h_inode->i_mode));
-+ IiMustWriteLock(inode);
-+
-+ sb = inode->i_sb;
-+ br = au_sbr(sb, bindex);
-+ do_dx = !!au_opt_test(au_mntflags(sb), DIO);
-+ dyaop = dy_aget(br, h_inode->i_mapping->a_ops, do_dx);
-+ err = PTR_ERR(dyaop);
-+ if (IS_ERR(dyaop))
-+ /* unnecessary to call dy_fput() */
-+ goto out;
-+
-+ err = 0;
-+ inode->i_mapping->a_ops = &dyaop->da_op;
-+
-+out:
-+ return err;
-+}
-+
-+/*
-+ * Is it safe to replace a_ops during the inode/file is in operation?
-+ * Yes, I hope so.
-+ */
-+int au_dy_irefresh(struct inode *inode)
-+{
-+ int err;
-+ aufs_bindex_t btop;
-+ struct inode *h_inode;
-+
-+ err = 0;
-+ if (S_ISREG(inode->i_mode)) {
-+ btop = au_ibtop(inode);
-+ h_inode = au_h_iptr(inode, btop);
-+ err = au_dy_iaop(inode, btop, h_inode);
-+ }
-+ return err;
-+}
-+
-+void au_dy_arefresh(int do_dx)
-+{
-+ struct hlist_bl_head *hbl;
-+ struct hlist_bl_node *pos;
-+ struct au_dykey *key;
-+
-+ hbl = dynop + AuDy_AOP;
-+ hlist_bl_lock(hbl);
-+ hlist_bl_for_each_entry(key, pos, hbl, dk_hnode)
-+ dy_adx((void *)key, do_dx);
-+ hlist_bl_unlock(hbl);
-+}
-+
-+/* ---------------------------------------------------------------------- */
-+
-+void __init au_dy_init(void)
-+{
-+ int i;
-+
-+ for (i = 0; i < AuDyLast; i++)
-+ INIT_HLIST_BL_HEAD(dynop + i);
-+}
-+
-+void au_dy_fin(void)
-+{
-+ int i;
-+
-+ for (i = 0; i < AuDyLast; i++)
-+ WARN_ON(!hlist_bl_empty(dynop + i));
-+}
-diff --git a/fs/aufs/dynop.h b/fs/aufs/dynop.h
-new file mode 100644
-index 000000000000..5d0b36559425
---- /dev/null
-+++ b/fs/aufs/dynop.h
-@@ -0,0 +1,77 @@
-+/* SPDX-License-Identifier: GPL-2.0 */
-+/*
-+ * Copyright (C) 2010-2019 Junjiro R. Okajima
-+ *
-+ * This program, aufs is free software; you can redistribute it and/or modify
-+ * it under the terms of the GNU General Public License as published by
-+ * the Free Software Foundation; either version 2 of the License, or
-+ * (at your option) any later version.
-+ *
-+ * This program is distributed in the hope that it will be useful,
-+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
-+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
-+ * GNU General Public License for more details.
-+ *
-+ * You should have received a copy of the GNU General Public License
-+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
-+ */
-+
-+/*
-+ * dynamically customizable operations (for regular files only)
-+ */
-+
-+#ifndef __AUFS_DYNOP_H__
-+#define __AUFS_DYNOP_H__
-+
-+#ifdef __KERNEL__
-+
-+#include <linux/fs.h>
-+#include <linux/kref.h>
-+
-+enum {AuDy_AOP, AuDyLast};
-+
-+struct au_dynop {
-+ int dy_type;
-+ union {
-+ const void *dy_hop;
-+ const struct address_space_operations *dy_haop;
-+ };
-+};
-+
-+struct au_dykey {
-+ union {
-+ struct hlist_bl_node dk_hnode;
-+ struct rcu_head dk_rcu;
-+ };
-+ struct au_dynop dk_op;
-+
-+ /*
-+ * during I am in the branch local array, kref is gotten. when the
-+ * branch is removed, kref is put.
-+ */
-+ struct kref dk_kref;
-+};
-+
-+/* stop unioning since their sizes are very different from each other */
-+struct au_dyaop {
-+ struct au_dykey da_key;
-+ struct address_space_operations da_op; /* not const */
-+};
-+/* make sure that 'struct au_dykey *' can be any type */
-+static_assert(!offsetof(struct au_dyaop, da_key));
-+
-+/* ---------------------------------------------------------------------- */
-+
-+/* dynop.c */
-+struct au_branch;
-+void au_dy_put(struct au_dykey *key);
-+int au_dy_iaop(struct inode *inode, aufs_bindex_t bindex,
-+ struct inode *h_inode);
-+int au_dy_irefresh(struct inode *inode);
-+void au_dy_arefresh(int do_dio);
-+
-+void __init au_dy_init(void);
-+void au_dy_fin(void);
-+
-+#endif /* __KERNEL__ */
-+#endif /* __AUFS_DYNOP_H__ */
-diff --git a/fs/aufs/export.c b/fs/aufs/export.c
-new file mode 100644
-index 000000000000..1da2ca0a969b
---- /dev/null
-+++ b/fs/aufs/export.c
-@@ -0,0 +1,838 @@
-+// SPDX-License-Identifier: GPL-2.0
-+/*
-+ * Copyright (C) 2005-2019 Junjiro R. Okajima
-+ *
-+ * This program, aufs is free software; you can redistribute it and/or modify
-+ * it under the terms of the GNU General Public License as published by
-+ * the Free Software Foundation; either version 2 of the License, or
-+ * (at your option) any later version.
-+ *
-+ * This program is distributed in the hope that it will be useful,
-+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
-+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
-+ * GNU General Public License for more details.
-+ *
-+ * You should have received a copy of the GNU General Public License
-+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
-+ */
-+
-+/*
-+ * export via nfs
-+ */
-+
-+#include <linux/exportfs.h>
-+#include <linux/fs_struct.h>
-+#include <linux/namei.h>
-+#include <linux/nsproxy.h>
-+#include <linux/random.h>
-+#include <linux/writeback.h>
-+#include "aufs.h"
-+
-+union conv {
-+#ifdef CONFIG_AUFS_INO_T_64
-+ __u32 a[2];
-+#else
-+ __u32 a[1];
-+#endif
-+ ino_t ino;
-+};
-+
-+static ino_t decode_ino(__u32 *a)
-+{
-+ union conv u;
-+
-+ BUILD_BUG_ON(sizeof(u.ino) != sizeof(u.a));
-+ u.a[0] = a[0];
-+#ifdef CONFIG_AUFS_INO_T_64
-+ u.a[1] = a[1];
-+#endif
-+ return u.ino;
-+}
-+
-+static void encode_ino(__u32 *a, ino_t ino)
-+{
-+ union conv u;
-+
-+ u.ino = ino;
-+ a[0] = u.a[0];
-+#ifdef CONFIG_AUFS_INO_T_64
-+ a[1] = u.a[1];
-+#endif
-+}
-+
-+/* NFS file handle */
-+enum {
-+ Fh_br_id,
-+ Fh_sigen,
-+#ifdef CONFIG_AUFS_INO_T_64
-+ /* support 64bit inode number */
-+ Fh_ino1,
-+ Fh_ino2,
-+ Fh_dir_ino1,
-+ Fh_dir_ino2,
-+#else
-+ Fh_ino1,
-+ Fh_dir_ino1,
-+#endif
-+ Fh_igen,
-+ Fh_h_type,
-+ Fh_tail,
-+
-+ Fh_ino = Fh_ino1,
-+ Fh_dir_ino = Fh_dir_ino1
-+};
-+
-+static int au_test_anon(struct dentry *dentry)
-+{
-+ /* note: read d_flags without d_lock */
-+ return !!(dentry->d_flags & DCACHE_DISCONNECTED);
-+}
-+
-+int au_test_nfsd(void)
-+{
-+ int ret;
-+ struct task_struct *tsk = current;
-+ char comm[sizeof(tsk->comm)];
-+
-+ ret = 0;
-+ if (tsk->flags & PF_KTHREAD) {
-+ get_task_comm(comm, tsk);
-+ ret = !strcmp(comm, "nfsd");
-+ }
-+
-+ return ret;
-+}
-+
-+/* ---------------------------------------------------------------------- */
-+/* inode generation external table */
-+
-+void au_xigen_inc(struct inode *inode)
-+{
-+ loff_t pos;
-+ ssize_t sz;
-+ __u32 igen;
-+ struct super_block *sb;
-+ struct au_sbinfo *sbinfo;
-+
-+ sb = inode->i_sb;
-+ AuDebugOn(!au_opt_test(au_mntflags(sb), XINO));
-+
-+ sbinfo = au_sbi(sb);
-+ pos = inode->i_ino;
-+ pos *= sizeof(igen);
-+ igen = inode->i_generation + 1;
-+ sz = xino_fwrite(sbinfo->si_xwrite, sbinfo->si_xigen, &igen,
-+ sizeof(igen), &pos);
-+ if (sz == sizeof(igen))
-+ return; /* success */
-+
-+ if (unlikely(sz >= 0))
-+ AuIOErr("xigen error (%zd)\n", sz);
-+}
-+
-+int au_xigen_new(struct inode *inode)
-+{
-+ int err;
-+ loff_t pos;
-+ ssize_t sz;
-+ struct super_block *sb;
-+ struct au_sbinfo *sbinfo;
-+ struct file *file;
-+
-+ err = 0;
-+ /* todo: dirty, at mount time */
-+ if (inode->i_ino == AUFS_ROOT_INO)
-+ goto out;
-+ sb = inode->i_sb;
-+ SiMustAnyLock(sb);
-+ if (unlikely(!au_opt_test(au_mntflags(sb), XINO)))
-+ goto out;
-+
-+ err = -EFBIG;
-+ pos = inode->i_ino;
-+ if (unlikely(au_loff_max / sizeof(inode->i_generation) - 1 < pos)) {
-+ AuIOErr1("too large i%lld\n", pos);
-+ goto out;
-+ }
-+ pos *= sizeof(inode->i_generation);
-+
-+ err = 0;
-+ sbinfo = au_sbi(sb);
-+ file = sbinfo->si_xigen;
-+ BUG_ON(!file);
-+
-+ if (vfsub_f_size_read(file)
-+ < pos + sizeof(inode->i_generation)) {
-+ inode->i_generation = atomic_inc_return(&sbinfo->si_xigen_next);
-+ sz = xino_fwrite(sbinfo->si_xwrite, file, &inode->i_generation,
-+ sizeof(inode->i_generation), &pos);
-+ } else
-+ sz = xino_fread(sbinfo->si_xread, file, &inode->i_generation,
-+ sizeof(inode->i_generation), &pos);
-+ if (sz == sizeof(inode->i_generation))
-+ goto out; /* success */
-+
-+ err = sz;
-+ if (unlikely(sz >= 0)) {
-+ err = -EIO;
-+ AuIOErr("xigen error (%zd)\n", sz);
-+ }
-+
-+out:
-+ return err;
-+}
-+
-+int au_xigen_set(struct super_block *sb, struct path *path)
-+{
-+ int err;
-+ struct au_sbinfo *sbinfo;
-+ struct file *file;
-+
-+ SiMustWriteLock(sb);
-+
-+ sbinfo = au_sbi(sb);
-+ file = au_xino_create2(sb, path, sbinfo->si_xigen);
-+ err = PTR_ERR(file);
-+ if (IS_ERR(file))
-+ goto out;
-+ err = 0;
-+ if (sbinfo->si_xigen)
-+ fput(sbinfo->si_xigen);
-+ sbinfo->si_xigen = file;
-+
-+out:
-+ AuTraceErr(err);
-+ return err;
-+}
-+
-+void au_xigen_clr(struct super_block *sb)
-+{
-+ struct au_sbinfo *sbinfo;
-+
-+ SiMustWriteLock(sb);
-+
-+ sbinfo = au_sbi(sb);
-+ if (sbinfo->si_xigen) {
-+ fput(sbinfo->si_xigen);
-+ sbinfo->si_xigen = NULL;
-+ }
-+}
-+
-+/* ---------------------------------------------------------------------- */
-+
-+static struct dentry *decode_by_ino(struct super_block *sb, ino_t ino,
-+ ino_t dir_ino)
-+{
-+ struct dentry *dentry, *d;
-+ struct inode *inode;
-+ unsigned int sigen;
-+
-+ dentry = NULL;
-+ inode = ilookup(sb, ino);
-+ if (!inode)
-+ goto out;
-+
-+ dentry = ERR_PTR(-ESTALE);
-+ sigen = au_sigen(sb);
-+ if (unlikely(au_is_bad_inode(inode)
-+ || IS_DEADDIR(inode)
-+ || sigen != au_iigen(inode, NULL)))
-+ goto out_iput;
-+
-+ dentry = NULL;
-+ if (!dir_ino || S_ISDIR(inode->i_mode))
-+ dentry = d_find_alias(inode);
-+ else {
-+ spin_lock(&inode->i_lock);
-+ hlist_for_each_entry(d, &inode->i_dentry, d_u.d_alias) {
-+ spin_lock(&d->d_lock);
-+ if (!au_test_anon(d)
-+ && d_inode(d->d_parent)->i_ino == dir_ino) {
-+ dentry = dget_dlock(d);
-+ spin_unlock(&d->d_lock);
-+ break;
-+ }
-+ spin_unlock(&d->d_lock);
-+ }
-+ spin_unlock(&inode->i_lock);
-+ }
-+ if (unlikely(dentry && au_digen_test(dentry, sigen))) {
-+ /* need to refresh */
-+ dput(dentry);
-+ dentry = NULL;
-+ }
-+
-+out_iput:
-+ iput(inode);
-+out:
-+ AuTraceErrPtr(dentry);
-+ return dentry;
-+}
-+
-+/* ---------------------------------------------------------------------- */
-+
-+/* todo: dirty? */
-+/* if exportfs_decode_fh() passed vfsmount*, we could be happy */
-+
-+struct au_compare_mnt_args {
-+ /* input */
-+ struct super_block *sb;
-+
-+ /* output */
-+ struct vfsmount *mnt;
-+};
-+
-+static int au_compare_mnt(struct vfsmount *mnt, void *arg)
-+{
-+ struct au_compare_mnt_args *a = arg;
-+
-+ if (mnt->mnt_sb != a->sb)
-+ return 0;
-+ a->mnt = mntget(mnt);
-+ return 1;
-+}
-+
-+static struct vfsmount *au_mnt_get(struct super_block *sb)
-+{
-+ int err;
-+ struct path root;
-+ struct au_compare_mnt_args args = {
-+ .sb = sb
-+ };
-+
-+ get_fs_root(current->fs, &root);
-+ rcu_read_lock();
-+ err = iterate_mounts(au_compare_mnt, &args, root.mnt);
-+ rcu_read_unlock();
-+ path_put(&root);
-+ AuDebugOn(!err);
-+ AuDebugOn(!args.mnt);
-+ return args.mnt;
-+}
-+
-+struct au_nfsd_si_lock {
-+ unsigned int sigen;
-+ aufs_bindex_t bindex, br_id;
-+ unsigned char force_lock;
-+};
-+
-+static int si_nfsd_read_lock(struct super_block *sb,
-+ struct au_nfsd_si_lock *nsi_lock)
-+{
-+ int err;
-+ aufs_bindex_t bindex;
-+
-+ si_read_lock(sb, AuLock_FLUSH);
-+
-+ /* branch id may be wrapped around */
-+ err = 0;
-+ bindex = au_br_index(sb, nsi_lock->br_id);
-+ if (bindex >= 0 && nsi_lock->sigen + AUFS_BRANCH_MAX > au_sigen(sb))
-+ goto out; /* success */
-+
-+ err = -ESTALE;
-+ bindex = -1;
-+ if (!nsi_lock->force_lock)
-+ si_read_unlock(sb);
-+
-+out:
-+ nsi_lock->bindex = bindex;
-+ return err;
-+}
-+
-+struct find_name_by_ino {
-+ struct dir_context ctx;
-+ int called, found;
-+ ino_t ino;
-+ char *name;
-+ int namelen;
-+};
-+
-+static int
-+find_name_by_ino(struct dir_context *ctx, const char *name, int namelen,
-+ loff_t offset, u64 ino, unsigned int d_type)
-+{
-+ struct find_name_by_ino *a = container_of(ctx, struct find_name_by_ino,
-+ ctx);
-+
-+ a->called++;
-+ if (a->ino != ino)
-+ return 0;
-+
-+ memcpy(a->name, name, namelen);
-+ a->namelen = namelen;
-+ a->found = 1;
-+ return 1;
-+}
-+
-+static struct dentry *au_lkup_by_ino(struct path *path, ino_t ino,
-+ struct au_nfsd_si_lock *nsi_lock)
-+{
-+ struct dentry *dentry, *parent;
-+ struct file *file;
-+ struct inode *dir;
-+ struct find_name_by_ino arg = {
-+ .ctx = {
-+ .actor = find_name_by_ino
-+ }
-+ };
-+ int err;
-+
-+ parent = path->dentry;
-+ if (nsi_lock)
-+ si_read_unlock(parent->d_sb);
-+ file = vfsub_dentry_open(path, au_dir_roflags);
-+ dentry = (void *)file;
-+ if (IS_ERR(file))
-+ goto out;
-+
-+ dentry = ERR_PTR(-ENOMEM);
-+ arg.name = (void *)__get_free_page(GFP_NOFS);
-+ if (unlikely(!arg.name))
-+ goto out_file;
-+ arg.ino = ino;
-+ arg.found = 0;
-+ do {
-+ arg.called = 0;
-+ /* smp_mb(); */
-+ err = vfsub_iterate_dir(file, &arg.ctx);
-+ } while (!err && !arg.found && arg.called);
-+ dentry = ERR_PTR(err);
-+ if (unlikely(err))
-+ goto out_name;
-+ /* instead of ENOENT */
-+ dentry = ERR_PTR(-ESTALE);
-+ if (!arg.found)
-+ goto out_name;
-+
-+ /* do not call vfsub_lkup_one() */
-+ dir = d_inode(parent);
-+ dentry = vfsub_lookup_one_len_unlocked(arg.name, parent, arg.namelen);
-+ AuTraceErrPtr(dentry);
-+ if (IS_ERR(dentry))
-+ goto out_name;
-+ AuDebugOn(au_test_anon(dentry));
-+ if (unlikely(d_really_is_negative(dentry))) {
-+ dput(dentry);
-+ dentry = ERR_PTR(-ENOENT);
-+ }
-+
-+out_name:
-+ free_page((unsigned long)arg.name);
-+out_file:
-+ fput(file);
-+out:
-+ if (unlikely(nsi_lock
-+ && si_nfsd_read_lock(parent->d_sb, nsi_lock) < 0))
-+ if (!IS_ERR(dentry)) {
-+ dput(dentry);
-+ dentry = ERR_PTR(-ESTALE);
-+ }
-+ AuTraceErrPtr(dentry);
-+ return dentry;
-+}
-+
-+static struct dentry *decode_by_dir_ino(struct super_block *sb, ino_t ino,
-+ ino_t dir_ino,
-+ struct au_nfsd_si_lock *nsi_lock)
-+{
-+ struct dentry *dentry;
-+ struct path path;
-+
-+ if (dir_ino != AUFS_ROOT_INO) {
-+ path.dentry = decode_by_ino(sb, dir_ino, 0);
-+ dentry = path.dentry;
-+ if (!path.dentry || IS_ERR(path.dentry))
-+ goto out;
-+ AuDebugOn(au_test_anon(path.dentry));
-+ } else
-+ path.dentry = dget(sb->s_root);
-+
-+ path.mnt = au_mnt_get(sb);
-+ dentry = au_lkup_by_ino(&path, ino, nsi_lock);
-+ path_put(&path);
-+
-+out:
-+ AuTraceErrPtr(dentry);
-+ return dentry;
-+}
-+
-+/* ---------------------------------------------------------------------- */
-+
-+static int h_acceptable(void *expv, struct dentry *dentry)
-+{
-+ return 1;
-+}
-+
-+static char *au_build_path(struct dentry *h_parent, struct path *h_rootpath,
-+ char *buf, int len, struct super_block *sb)
-+{
-+ char *p;
-+ int n;
-+ struct path path;
-+
-+ p = d_path(h_rootpath, buf, len);
-+ if (IS_ERR(p))
-+ goto out;
-+ n = strlen(p);
-+
-+ path.mnt = h_rootpath->mnt;
-+ path.dentry = h_parent;
-+ p = d_path(&path, buf, len);
-+ if (IS_ERR(p))
-+ goto out;
-+ if (n != 1)
-+ p += n;
-+
-+ path.mnt = au_mnt_get(sb);
-+ path.dentry = sb->s_root;
-+ p = d_path(&path, buf, len - strlen(p));
-+ mntput(path.mnt);
-+ if (IS_ERR(p))
-+ goto out;
-+ if (n != 1)
-+ p[strlen(p)] = '/';
-+
-+out:
-+ AuTraceErrPtr(p);
-+ return p;
-+}
-+
-+static
-+struct dentry *decode_by_path(struct super_block *sb, ino_t ino, __u32 *fh,
-+ int fh_len, struct au_nfsd_si_lock *nsi_lock)
-+{
-+ struct dentry *dentry, *h_parent, *root;
-+ struct super_block *h_sb;
-+ char *pathname, *p;
-+ struct vfsmount *h_mnt;
-+ struct au_branch *br;
-+ int err;
-+ struct path path;
-+
-+ br = au_sbr(sb, nsi_lock->bindex);
-+ h_mnt = au_br_mnt(br);
-+ h_sb = h_mnt->mnt_sb;
-+ /* todo: call lower fh_to_dentry()? fh_to_parent()? */
-+ lockdep_off();
-+ h_parent = exportfs_decode_fh(h_mnt, (void *)(fh + Fh_tail),
-+ fh_len - Fh_tail, fh[Fh_h_type],
-+ h_acceptable, /*context*/NULL);
-+ lockdep_on();
-+ dentry = h_parent;
-+ if (unlikely(!h_parent || IS_ERR(h_parent))) {
-+ AuWarn1("%s decode_fh failed, %ld\n",
-+ au_sbtype(h_sb), PTR_ERR(h_parent));
-+ goto out;
-+ }
-+ dentry = NULL;
-+ if (unlikely(au_test_anon(h_parent))) {
-+ AuWarn1("%s decode_fh returned a disconnected dentry\n",
-+ au_sbtype(h_sb));
-+ goto out_h_parent;
-+ }
-+
-+ dentry = ERR_PTR(-ENOMEM);
-+ pathname = (void *)__get_free_page(GFP_NOFS);
-+ if (unlikely(!pathname))
-+ goto out_h_parent;
-+
-+ root = sb->s_root;
-+ path.mnt = h_mnt;
-+ di_read_lock_parent(root, !AuLock_IR);
-+ path.dentry = au_h_dptr(root, nsi_lock->bindex);
-+ di_read_unlock(root, !AuLock_IR);
-+ p = au_build_path(h_parent, &path, pathname, PAGE_SIZE, sb);
-+ dentry = (void *)p;
-+ if (IS_ERR(p))
-+ goto out_pathname;
-+
-+ si_read_unlock(sb);
-+ err = vfsub_kern_path(p, LOOKUP_FOLLOW | LOOKUP_DIRECTORY, &path);
-+ dentry = ERR_PTR(err);
-+ if (unlikely(err))
-+ goto out_relock;
-+
-+ dentry = ERR_PTR(-ENOENT);
-+ AuDebugOn(au_test_anon(path.dentry));
-+ if (unlikely(d_really_is_negative(path.dentry)))
-+ goto out_path;
-+
-+ if (ino != d_inode(path.dentry)->i_ino)
-+ dentry = au_lkup_by_ino(&path, ino, /*nsi_lock*/NULL);
-+ else
-+ dentry = dget(path.dentry);
-+
-+out_path:
-+ path_put(&path);
-+out_relock:
-+ if (unlikely(si_nfsd_read_lock(sb, nsi_lock) < 0))
-+ if (!IS_ERR(dentry)) {
-+ dput(dentry);
-+ dentry = ERR_PTR(-ESTALE);
-+ }
-+out_pathname:
-+ free_page((unsigned long)pathname);
-+out_h_parent:
-+ dput(h_parent);
-+out:
-+ AuTraceErrPtr(dentry);
-+ return dentry;
-+}
-+
-+/* ---------------------------------------------------------------------- */
-+
-+static struct dentry *
-+aufs_fh_to_dentry(struct super_block *sb, struct fid *fid, int fh_len,
-+ int fh_type)
-+{
-+ struct dentry *dentry;
-+ __u32 *fh = fid->raw;
-+ struct au_branch *br;
-+ ino_t ino, dir_ino;
-+ struct au_nfsd_si_lock nsi_lock = {
-+ .force_lock = 0
-+ };
-+
-+ dentry = ERR_PTR(-ESTALE);
-+ /* it should never happen, but the file handle is unreliable */
-+ if (unlikely(fh_len < Fh_tail))
-+ goto out;
-+ nsi_lock.sigen = fh[Fh_sigen];
-+ nsi_lock.br_id = fh[Fh_br_id];
-+
-+ /* branch id may be wrapped around */
-+ br = NULL;
-+ if (unlikely(si_nfsd_read_lock(sb, &nsi_lock)))
-+ goto out;
-+ nsi_lock.force_lock = 1;
-+
-+ /* is this inode still cached? */
-+ ino = decode_ino(fh + Fh_ino);
-+ /* it should never happen */
-+ if (unlikely(ino == AUFS_ROOT_INO))
-+ goto out_unlock;
-+
-+ dir_ino = decode_ino(fh + Fh_dir_ino);
-+ dentry = decode_by_ino(sb, ino, dir_ino);
-+ if (IS_ERR(dentry))
-+ goto out_unlock;
-+ if (dentry)
-+ goto accept;
-+
-+ /* is the parent dir cached? */
-+ br = au_sbr(sb, nsi_lock.bindex);
-+ au_lcnt_inc(&br->br_nfiles);
-+ dentry = decode_by_dir_ino(sb, ino, dir_ino, &nsi_lock);
-+ if (IS_ERR(dentry))
-+ goto out_unlock;
-+ if (dentry)
-+ goto accept;
-+
-+ /* lookup path */
-+ dentry = decode_by_path(sb, ino, fh, fh_len, &nsi_lock);
-+ if (IS_ERR(dentry))
-+ goto out_unlock;
-+ if (unlikely(!dentry))
-+ /* todo?: make it ESTALE */
-+ goto out_unlock;
-+
-+accept:
-+ if (!au_digen_test(dentry, au_sigen(sb))
-+ && d_inode(dentry)->i_generation == fh[Fh_igen])
-+ goto out_unlock; /* success */
-+
-+ dput(dentry);
-+ dentry = ERR_PTR(-ESTALE);
-+out_unlock:
-+ if (br)
-+ au_lcnt_dec(&br->br_nfiles);
-+ si_read_unlock(sb);
-+out:
-+ AuTraceErrPtr(dentry);
-+ return dentry;
-+}
-+
-+#if 0 /* reserved for future use */
-+/* support subtreecheck option */
-+static struct dentry *aufs_fh_to_parent(struct super_block *sb, struct fid *fid,
-+ int fh_len, int fh_type)
-+{
-+ struct dentry *parent;
-+ __u32 *fh = fid->raw;
-+ ino_t dir_ino;
-+
-+ dir_ino = decode_ino(fh + Fh_dir_ino);
-+ parent = decode_by_ino(sb, dir_ino, 0);
-+ if (IS_ERR(parent))
-+ goto out;
-+ if (!parent)
-+ parent = decode_by_path(sb, au_br_index(sb, fh[Fh_br_id]),
-+ dir_ino, fh, fh_len);
-+
-+out:
-+ AuTraceErrPtr(parent);
-+ return parent;
-+}
-+#endif
-+
-+/* ---------------------------------------------------------------------- */
-+
-+static int aufs_encode_fh(struct inode *inode, __u32 *fh, int *max_len,
-+ struct inode *dir)
-+{
-+ int err;
-+ aufs_bindex_t bindex;
-+ struct super_block *sb, *h_sb;
-+ struct dentry *dentry, *parent, *h_parent;
-+ struct inode *h_dir;
-+ struct au_branch *br;
-+
-+ err = -ENOSPC;
-+ if (unlikely(*max_len <= Fh_tail)) {
-+ AuWarn1("NFSv2 client (max_len %d)?\n", *max_len);
-+ goto out;
-+ }
-+
-+ err = FILEID_ROOT;
-+ if (inode->i_ino == AUFS_ROOT_INO) {
-+ AuDebugOn(inode->i_ino != AUFS_ROOT_INO);
-+ goto out;
-+ }
-+
-+ h_parent = NULL;
-+ sb = inode->i_sb;
-+ err = si_read_lock(sb, AuLock_FLUSH);
-+ if (unlikely(err))
-+ goto out;
-+
-+#ifdef CONFIG_AUFS_DEBUG
-+ if (unlikely(!au_opt_test(au_mntflags(sb), XINO)))
-+ AuWarn1("NFS-exporting requires xino\n");
-+#endif
-+ err = -EIO;
-+ parent = NULL;
-+ ii_read_lock_child(inode);
-+ bindex = au_ibtop(inode);
-+ if (!dir) {
-+ dentry = d_find_any_alias(inode);
-+ if (unlikely(!dentry))
-+ goto out_unlock;
-+ AuDebugOn(au_test_anon(dentry));
-+ parent = dget_parent(dentry);
-+ dput(dentry);
-+ if (unlikely(!parent))
-+ goto out_unlock;
-+ if (d_really_is_positive(parent))
-+ dir = d_inode(parent);
-+ }
-+
-+ ii_read_lock_parent(dir);
-+ h_dir = au_h_iptr(dir, bindex);
-+ ii_read_unlock(dir);
-+ if (unlikely(!h_dir))
-+ goto out_parent;
-+ h_parent = d_find_any_alias(h_dir);
-+ if (unlikely(!h_parent))
-+ goto out_hparent;
-+
-+ err = -EPERM;
-+ br = au_sbr(sb, bindex);
-+ h_sb = au_br_sb(br);
-+ if (unlikely(!h_sb->s_export_op)) {
-+ AuErr1("%s branch is not exportable\n", au_sbtype(h_sb));
-+ goto out_hparent;
-+ }
-+
-+ fh[Fh_br_id] = br->br_id;
-+ fh[Fh_sigen] = au_sigen(sb);
-+ encode_ino(fh + Fh_ino, inode->i_ino);
-+ encode_ino(fh + Fh_dir_ino, dir->i_ino);
-+ fh[Fh_igen] = inode->i_generation;
-+
-+ *max_len -= Fh_tail;
-+ fh[Fh_h_type] = exportfs_encode_fh(h_parent, (void *)(fh + Fh_tail),
-+ max_len,
-+ /*connectable or subtreecheck*/0);
-+ err = fh[Fh_h_type];
-+ *max_len += Fh_tail;
-+ /* todo: macros? */
-+ if (err != FILEID_INVALID)
-+ err = 99;
-+ else
-+ AuWarn1("%s encode_fh failed\n", au_sbtype(h_sb));
-+
-+out_hparent:
-+ dput(h_parent);
-+out_parent:
-+ dput(parent);
-+out_unlock:
-+ ii_read_unlock(inode);
-+ si_read_unlock(sb);
-+out:
-+ if (unlikely(err < 0))
-+ err = FILEID_INVALID;
-+ return err;
-+}
-+
-+/* ---------------------------------------------------------------------- */
-+
-+static int aufs_commit_metadata(struct inode *inode)
-+{
-+ int err;
-+ aufs_bindex_t bindex;
-+ struct super_block *sb;
-+ struct inode *h_inode;
-+ int (*f)(struct inode *inode);
-+
-+ sb = inode->i_sb;
-+ si_read_lock(sb, AuLock_FLUSH | AuLock_NOPLMW);
-+ ii_write_lock_child(inode);
-+ bindex = au_ibtop(inode);
-+ AuDebugOn(bindex < 0);
-+ h_inode = au_h_iptr(inode, bindex);
-+
-+ f = h_inode->i_sb->s_export_op->commit_metadata;
-+ if (f)
-+ err = f(h_inode);
-+ else {
-+ struct writeback_control wbc = {
-+ .sync_mode = WB_SYNC_ALL,
-+ .nr_to_write = 0 /* metadata only */
-+ };
-+
-+ err = sync_inode(h_inode, &wbc);
-+ }
-+
-+ au_cpup_attr_timesizes(inode);
-+ ii_write_unlock(inode);
-+ si_read_unlock(sb);
-+ return err;
-+}
-+
-+/* ---------------------------------------------------------------------- */
-+
-+static struct export_operations aufs_export_op = {
-+ .fh_to_dentry = aufs_fh_to_dentry,
-+ /* .fh_to_parent = aufs_fh_to_parent, */
-+ .encode_fh = aufs_encode_fh,
-+ .commit_metadata = aufs_commit_metadata
-+};
-+
-+void au_export_init(struct super_block *sb)
-+{
-+ struct au_sbinfo *sbinfo;
-+ __u32 u;
-+
-+ BUILD_BUG_ON_MSG(IS_BUILTIN(CONFIG_AUFS_FS)
-+ && IS_MODULE(CONFIG_EXPORTFS),
-+ AUFS_NAME ": unsupported configuration "
-+ "CONFIG_EXPORTFS=m and CONFIG_AUFS_FS=y");
-+
-+ sb->s_export_op = &aufs_export_op;
-+ sbinfo = au_sbi(sb);
-+ sbinfo->si_xigen = NULL;
-+ get_random_bytes(&u, sizeof(u));
-+ BUILD_BUG_ON(sizeof(u) != sizeof(int));
-+ atomic_set(&sbinfo->si_xigen_next, u);
-+}
-diff --git a/fs/aufs/f_op.c b/fs/aufs/f_op.c
-new file mode 100644
-index 000000000000..5254b5cd3942
---- /dev/null
-+++ b/fs/aufs/f_op.c
-@@ -0,0 +1,819 @@
-+// SPDX-License-Identifier: GPL-2.0
-+/*
-+ * Copyright (C) 2005-2019 Junjiro R. Okajima
-+ *
-+ * This program, aufs is free software; you can redistribute it and/or modify
-+ * it under the terms of the GNU General Public License as published by
-+ * the Free Software Foundation; either version 2 of the License, or
-+ * (at your option) any later version.
-+ *
-+ * This program is distributed in the hope that it will be useful,
-+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
-+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
-+ * GNU General Public License for more details.
-+ *
-+ * You should have received a copy of the GNU General Public License
-+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
-+ */
-+
-+/*
-+ * file and vm operations
-+ */
-+
-+#include <linux/aio.h>
-+#include <linux/fs_stack.h>
-+#include <linux/mman.h>
-+#include <linux/security.h>
-+#include "aufs.h"
-+
-+int au_do_open_nondir(struct file *file, int flags, struct file *h_file)
-+{
-+ int err;
-+ aufs_bindex_t bindex;
-+ struct dentry *dentry, *h_dentry;
-+ struct au_finfo *finfo;
-+ struct inode *h_inode;
-+
-+ FiMustWriteLock(file);
-+
-+ err = 0;
-+ dentry = file->f_path.dentry;
-+ AuDebugOn(IS_ERR_OR_NULL(dentry));
-+ finfo = au_fi(file);
-+ memset(&finfo->fi_htop, 0, sizeof(finfo->fi_htop));
-+ atomic_set(&finfo->fi_mmapped, 0);
-+ bindex = au_dbtop(dentry);
-+ if (!h_file) {
-+ h_dentry = au_h_dptr(dentry, bindex);
-+ err = vfsub_test_mntns(file->f_path.mnt, h_dentry->d_sb);
-+ if (unlikely(err))
-+ goto out;
-+ h_file = au_h_open(dentry, bindex, flags, file, /*force_wr*/0);
-+ if (IS_ERR(h_file)) {
-+ err = PTR_ERR(h_file);
-+ goto out;
-+ }
-+ } else {
-+ h_dentry = h_file->f_path.dentry;
-+ err = vfsub_test_mntns(file->f_path.mnt, h_dentry->d_sb);
-+ if (unlikely(err))
-+ goto out;
-+ /* br ref is already inc-ed */
-+ }
-+
-+ if ((flags & __O_TMPFILE)
-+ && !(flags & O_EXCL)) {
-+ h_inode = file_inode(h_file);
-+ spin_lock(&h_inode->i_lock);
-+ h_inode->i_state |= I_LINKABLE;
-+ spin_unlock(&h_inode->i_lock);
-+ }
-+ au_set_fbtop(file, bindex);
-+ au_set_h_fptr(file, bindex, h_file);
-+ au_update_figen(file);
-+ /* todo: necessary? */
-+ /* file->f_ra = h_file->f_ra; */
-+
-+out:
-+ return err;
-+}
-+
-+static int aufs_open_nondir(struct inode *inode __maybe_unused,
-+ struct file *file)
-+{
-+ int err;
-+ struct super_block *sb;
-+ struct au_do_open_args args = {
-+ .open = au_do_open_nondir
-+ };
-+
-+ AuDbg("%pD, f_flags 0x%x, f_mode 0x%x\n",
-+ file, vfsub_file_flags(file), file->f_mode);
-+
-+ sb = file->f_path.dentry->d_sb;
-+ si_read_lock(sb, AuLock_FLUSH);
-+ err = au_do_open(file, &args);
-+ si_read_unlock(sb);
-+ return err;
-+}
-+
-+int aufs_release_nondir(struct inode *inode __maybe_unused, struct file *file)
-+{
-+ struct au_finfo *finfo;
-+ aufs_bindex_t bindex;
-+
-+ finfo = au_fi(file);
-+ au_hbl_del(&finfo->fi_hlist,
-+ &au_sbi(file->f_path.dentry->d_sb)->si_files);
-+ bindex = finfo->fi_btop;
-+ if (bindex >= 0)
-+ au_set_h_fptr(file, bindex, NULL);
-+
-+ au_finfo_fin(file);
-+ return 0;
-+}
-+
-+/* ---------------------------------------------------------------------- */
-+
-+static int au_do_flush_nondir(struct file *file, fl_owner_t id)
-+{
-+ int err;
-+ struct file *h_file;
-+
-+ err = 0;
-+ h_file = au_hf_top(file);
-+ if (h_file)
-+ err = vfsub_flush(h_file, id);
-+ return err;
-+}
-+
-+static int aufs_flush_nondir(struct file *file, fl_owner_t id)
-+{
-+ return au_do_flush(file, id, au_do_flush_nondir);
-+}
-+
-+/* ---------------------------------------------------------------------- */
-+/*
-+ * read and write functions acquire [fdi]_rwsem once, but release before
-+ * mmap_sem. This is because to stop a race condition between mmap(2).
-+ * Releasing these aufs-rwsem should be safe, no branch-management (by keeping
-+ * si_rwsem), no harmful copy-up should happen. Actually copy-up may happen in
-+ * read functions after [fdi]_rwsem are released, but it should be harmless.
-+ */
-+
-+/* Callers should call au_read_post() or fput() in the end */
-+struct file *au_read_pre(struct file *file, int keep_fi, unsigned int lsc)
-+{
-+ struct file *h_file;
-+ int err;
-+
-+ err = au_reval_and_lock_fdi(file, au_reopen_nondir, /*wlock*/0, lsc);
-+ if (!err) {
-+ di_read_unlock(file->f_path.dentry, AuLock_IR);
-+ h_file = au_hf_top(file);
-+ get_file(h_file);
-+ if (!keep_fi)
-+ fi_read_unlock(file);
-+ } else
-+ h_file = ERR_PTR(err);
-+
-+ return h_file;
-+}
-+
-+static void au_read_post(struct inode *inode, struct file *h_file)
-+{
-+ /* update without lock, I don't think it a problem */
-+ fsstack_copy_attr_atime(inode, file_inode(h_file));
-+ fput(h_file);
-+}
-+
-+struct au_write_pre {
-+ /* input */
-+ unsigned int lsc;
-+
-+ /* output */
-+ blkcnt_t blks;
-+ aufs_bindex_t btop;
-+};
-+
-+/*
-+ * return with iinfo is write-locked
-+ * callers should call au_write_post() or iinfo_write_unlock() + fput() in the
-+ * end
-+ */
-+static struct file *au_write_pre(struct file *file, int do_ready,
-+ struct au_write_pre *wpre)
-+{
-+ struct file *h_file;
-+ struct dentry *dentry;
-+ int err;
-+ unsigned int lsc;
-+ struct au_pin pin;
-+
-+ lsc = 0;
-+ if (wpre)
-+ lsc = wpre->lsc;
-+ err = au_reval_and_lock_fdi(file, au_reopen_nondir, /*wlock*/1, lsc);
-+ h_file = ERR_PTR(err);
-+ if (unlikely(err))
-+ goto out;
-+
-+ dentry = file->f_path.dentry;
-+ if (do_ready) {
-+ err = au_ready_to_write(file, -1, &pin);
-+ if (unlikely(err)) {
-+ h_file = ERR_PTR(err);
-+ di_write_unlock(dentry);
-+ goto out_fi;
-+ }
-+ }
-+
-+ di_downgrade_lock(dentry, /*flags*/0);
-+ if (wpre)
-+ wpre->btop = au_fbtop(file);
-+ h_file = au_hf_top(file);
-+ get_file(h_file);
-+ if (wpre)
-+ wpre->blks = file_inode(h_file)->i_blocks;
-+ if (do_ready)
-+ au_unpin(&pin);
-+ di_read_unlock(dentry, /*flags*/0);
-+
-+out_fi:
-+ fi_write_unlock(file);
-+out:
-+ return h_file;
-+}
-+
-+static void au_write_post(struct inode *inode, struct file *h_file,
-+ struct au_write_pre *wpre, ssize_t written)
-+{
-+ struct inode *h_inode;
-+
-+ au_cpup_attr_timesizes(inode);
-+ AuDebugOn(au_ibtop(inode) != wpre->btop);
-+ h_inode = file_inode(h_file);
-+ inode->i_mode = h_inode->i_mode;
-+ ii_write_unlock(inode);
-+ /* AuDbg("blks %llu, %llu\n", (u64)blks, (u64)h_inode->i_blocks); */
-+ if (written > 0)
-+ au_fhsm_wrote(inode->i_sb, wpre->btop,
-+ /*force*/h_inode->i_blocks > wpre->blks);
-+ fput(h_file);
-+}
-+
-+static ssize_t aufs_read(struct file *file, char __user *buf, size_t count,
-+ loff_t *ppos)
-+{
-+ ssize_t err;
-+ struct inode *inode;
-+ struct file *h_file;
-+ struct super_block *sb;
-+
-+ inode = file_inode(file);
-+ sb = inode->i_sb;
-+ si_read_lock(sb, AuLock_FLUSH | AuLock_NOPLMW);
-+
-+ h_file = au_read_pre(file, /*keep_fi*/0, /*lsc*/0);
-+ err = PTR_ERR(h_file);
-+ if (IS_ERR(h_file))
-+ goto out;
-+
-+ /* filedata may be obsoleted by concurrent copyup, but no problem */
-+ err = vfsub_read_u(h_file, buf, count, ppos);
-+ /* todo: necessary? */
-+ /* file->f_ra = h_file->f_ra; */
-+ au_read_post(inode, h_file);
-+
-+out:
-+ si_read_unlock(sb);
-+ return err;
-+}
-+
-+/*
-+ * todo: very ugly
-+ * it locks both of i_mutex and si_rwsem for read in safe.
-+ * if the plink maintenance mode continues forever (that is the problem),
-+ * may loop forever.
-+ */
-+static void au_mtx_and_read_lock(struct inode *inode)
-+{
-+ int err;
-+ struct super_block *sb = inode->i_sb;
-+
-+ while (1) {
-+ inode_lock(inode);
-+ err = si_read_lock(sb, AuLock_FLUSH | AuLock_NOPLM);
-+ if (!err)
-+ break;
-+ inode_unlock(inode);
-+ si_read_lock(sb, AuLock_NOPLMW);
-+ si_read_unlock(sb);
-+ }
-+}
-+
-+static ssize_t aufs_write(struct file *file, const char __user *ubuf,
-+ size_t count, loff_t *ppos)
-+{
-+ ssize_t err;
-+ struct au_write_pre wpre;
-+ struct inode *inode;
-+ struct file *h_file;
-+ char __user *buf = (char __user *)ubuf;
-+
-+ inode = file_inode(file);
-+ au_mtx_and_read_lock(inode);
-+
-+ wpre.lsc = 0;
-+ h_file = au_write_pre(file, /*do_ready*/1, &wpre);
-+ err = PTR_ERR(h_file);
-+ if (IS_ERR(h_file))
-+ goto out;
-+
-+ err = vfsub_write_u(h_file, buf, count, ppos);
-+ au_write_post(inode, h_file, &wpre, err);
-+
-+out:
-+ si_read_unlock(inode->i_sb);
-+ inode_unlock(inode);
-+ return err;
-+}
-+
-+static ssize_t au_do_iter(struct file *h_file, int rw, struct kiocb *kio,
-+ struct iov_iter *iov_iter)
-+{
-+ ssize_t err;
-+ struct file *file;
-+ ssize_t (*iter)(struct kiocb *, struct iov_iter *);
-+
-+ err = security_file_permission(h_file, rw);
-+ if (unlikely(err))
-+ goto out;
-+
-+ err = -ENOSYS;
-+ iter = NULL;
-+ if (rw == MAY_READ)
-+ iter = h_file->f_op->read_iter;
-+ else if (rw == MAY_WRITE)
-+ iter = h_file->f_op->write_iter;
-+
-+ file = kio->ki_filp;
-+ kio->ki_filp = h_file;
-+ if (iter) {
-+ lockdep_off();
-+ err = iter(kio, iov_iter);
-+ lockdep_on();
-+ } else
-+ /* currently there is no such fs */
-+ WARN_ON_ONCE(1);
-+ kio->ki_filp = file;
-+
-+out:
-+ return err;
-+}
-+
-+static ssize_t aufs_read_iter(struct kiocb *kio, struct iov_iter *iov_iter)
-+{
-+ ssize_t err;
-+ struct file *file, *h_file;
-+ struct inode *inode;
-+ struct super_block *sb;
-+
-+ file = kio->ki_filp;
-+ inode = file_inode(file);
-+ sb = inode->i_sb;
-+ si_read_lock(sb, AuLock_FLUSH | AuLock_NOPLMW);
-+
-+ h_file = au_read_pre(file, /*keep_fi*/1, /*lsc*/0);
-+ err = PTR_ERR(h_file);
-+ if (IS_ERR(h_file))
-+ goto out;
-+
-+ if (au_test_loopback_kthread()) {
-+ au_warn_loopback(h_file->f_path.dentry->d_sb);
-+ if (file->f_mapping != h_file->f_mapping) {
-+ file->f_mapping = h_file->f_mapping;
-+ smp_mb(); /* unnecessary? */
-+ }
-+ }
-+ fi_read_unlock(file);
-+
-+ err = au_do_iter(h_file, MAY_READ, kio, iov_iter);
-+ /* todo: necessary? */
-+ /* file->f_ra = h_file->f_ra; */
-+ au_read_post(inode, h_file);
-+
-+out:
-+ si_read_unlock(sb);
-+ return err;
-+}
-+
-+static ssize_t aufs_write_iter(struct kiocb *kio, struct iov_iter *iov_iter)
-+{
-+ ssize_t err;
-+ struct au_write_pre wpre;
-+ struct inode *inode;
-+ struct file *file, *h_file;
-+
-+ file = kio->ki_filp;
-+ inode = file_inode(file);
-+ au_mtx_and_read_lock(inode);
-+
-+ wpre.lsc = 0;
-+ h_file = au_write_pre(file, /*do_ready*/1, &wpre);
-+ err = PTR_ERR(h_file);
-+ if (IS_ERR(h_file))
-+ goto out;
-+
-+ err = au_do_iter(h_file, MAY_WRITE, kio, iov_iter);
-+ au_write_post(inode, h_file, &wpre, err);
-+
-+out:
-+ si_read_unlock(inode->i_sb);
-+ inode_unlock(inode);
-+ return err;
-+}
-+
-+static ssize_t aufs_splice_read(struct file *file, loff_t *ppos,
-+ struct pipe_inode_info *pipe, size_t len,
-+ unsigned int flags)
-+{
-+ ssize_t err;
-+ struct file *h_file;
-+ struct inode *inode;
-+ struct super_block *sb;
-+
-+ inode = file_inode(file);
-+ sb = inode->i_sb;
-+ si_read_lock(sb, AuLock_FLUSH | AuLock_NOPLMW);
-+
-+ h_file = au_read_pre(file, /*keep_fi*/0, /*lsc*/0);
-+ err = PTR_ERR(h_file);
-+ if (IS_ERR(h_file))
-+ goto out;
-+
-+ err = vfsub_splice_to(h_file, ppos, pipe, len, flags);
-+ /* todo: necessary? */
-+ /* file->f_ra = h_file->f_ra; */
-+ au_read_post(inode, h_file);
-+
-+out:
-+ si_read_unlock(sb);
-+ return err;
-+}
-+
-+static ssize_t
-+aufs_splice_write(struct pipe_inode_info *pipe, struct file *file, loff_t *ppos,
-+ size_t len, unsigned int flags)
-+{
-+ ssize_t err;
-+ struct au_write_pre wpre;
-+ struct inode *inode;
-+ struct file *h_file;
-+
-+ inode = file_inode(file);
-+ au_mtx_and_read_lock(inode);
-+
-+ wpre.lsc = 0;
-+ h_file = au_write_pre(file, /*do_ready*/1, &wpre);
-+ err = PTR_ERR(h_file);
-+ if (IS_ERR(h_file))
-+ goto out;
-+
-+ err = vfsub_splice_from(pipe, h_file, ppos, len, flags);
-+ au_write_post(inode, h_file, &wpre, err);
-+
-+out:
-+ si_read_unlock(inode->i_sb);
-+ inode_unlock(inode);
-+ return err;
-+}
-+
-+static long aufs_fallocate(struct file *file, int mode, loff_t offset,
-+ loff_t len)
-+{
-+ long err;
-+ struct au_write_pre wpre;
-+ struct inode *inode;
-+ struct file *h_file;
-+
-+ inode = file_inode(file);
-+ au_mtx_and_read_lock(inode);
-+
-+ wpre.lsc = 0;
-+ h_file = au_write_pre(file, /*do_ready*/1, &wpre);
-+ err = PTR_ERR(h_file);
-+ if (IS_ERR(h_file))
-+ goto out;
-+
-+ lockdep_off();
-+ err = vfs_fallocate(h_file, mode, offset, len);
-+ lockdep_on();
-+ au_write_post(inode, h_file, &wpre, /*written*/1);
-+
-+out:
-+ si_read_unlock(inode->i_sb);
-+ inode_unlock(inode);
-+ return err;
-+}
-+
-+static ssize_t aufs_copy_file_range(struct file *src, loff_t src_pos,
-+ struct file *dst, loff_t dst_pos,
-+ size_t len, unsigned int flags)
-+{
-+ ssize_t err;
-+ struct au_write_pre wpre;
-+ enum { SRC, DST };
-+ struct {
-+ struct inode *inode;
-+ struct file *h_file;
-+ struct super_block *h_sb;
-+ } a[2];
-+#define a_src a[SRC]
-+#define a_dst a[DST]
-+
-+ err = -EINVAL;
-+ a_src.inode = file_inode(src);
-+ if (unlikely(!S_ISREG(a_src.inode->i_mode)))
-+ goto out;
-+ a_dst.inode = file_inode(dst);
-+ if (unlikely(!S_ISREG(a_dst.inode->i_mode)))
-+ goto out;
-+
-+ au_mtx_and_read_lock(a_dst.inode);
-+ /*
-+ * in order to match the order in di_write_lock2_{child,parent}(),
-+ * use f_path.dentry for this comparison.
-+ */
-+ if (src->f_path.dentry < dst->f_path.dentry) {
-+ a_src.h_file = au_read_pre(src, /*keep_fi*/1, AuLsc_FI_1);
-+ err = PTR_ERR(a_src.h_file);
-+ if (IS_ERR(a_src.h_file))
-+ goto out_si;
-+
-+ wpre.lsc = AuLsc_FI_2;
-+ a_dst.h_file = au_write_pre(dst, /*do_ready*/1, &wpre);
-+ err = PTR_ERR(a_dst.h_file);
-+ if (IS_ERR(a_dst.h_file)) {
-+ au_read_post(a_src.inode, a_src.h_file);
-+ goto out_si;
-+ }
-+ } else {
-+ wpre.lsc = AuLsc_FI_1;
-+ a_dst.h_file = au_write_pre(dst, /*do_ready*/1, &wpre);
-+ err = PTR_ERR(a_dst.h_file);
-+ if (IS_ERR(a_dst.h_file))
-+ goto out_si;
-+
-+ a_src.h_file = au_read_pre(src, /*keep_fi*/1, AuLsc_FI_2);
-+ err = PTR_ERR(a_src.h_file);
-+ if (IS_ERR(a_src.h_file)) {
-+ au_write_post(a_dst.inode, a_dst.h_file, &wpre,
-+ /*written*/0);
-+ goto out_si;
-+ }
-+ }
-+
-+ err = -EXDEV;
-+ a_src.h_sb = file_inode(a_src.h_file)->i_sb;
-+ a_dst.h_sb = file_inode(a_dst.h_file)->i_sb;
-+ if (unlikely(a_src.h_sb != a_dst.h_sb)) {
-+ AuDbgFile(src);
-+ AuDbgFile(dst);
-+ goto out_file;
-+ }
-+
-+ err = vfsub_copy_file_range(a_src.h_file, src_pos, a_dst.h_file,
-+ dst_pos, len, flags);
-+
-+out_file:
-+ au_write_post(a_dst.inode, a_dst.h_file, &wpre, err);
-+ fi_read_unlock(src);
-+ au_read_post(a_src.inode, a_src.h_file);
-+out_si:
-+ si_read_unlock(a_dst.inode->i_sb);
-+ inode_unlock(a_dst.inode);
-+out:
-+ return err;
-+#undef a_src
-+#undef a_dst
-+}
-+
-+/* ---------------------------------------------------------------------- */
-+
-+/*
-+ * The locking order around current->mmap_sem.
-+ * - in most and regular cases
-+ * file I/O syscall -- aufs_read() or something
-+ * -- si_rwsem for read -- mmap_sem
-+ * (Note that [fdi]i_rwsem are released before mmap_sem).
-+ * - in mmap case
-+ * mmap(2) -- mmap_sem -- aufs_mmap() -- si_rwsem for read -- [fdi]i_rwsem
-+ * This AB-BA order is definitely bad, but is not a problem since "si_rwsem for
-+ * read" allows multiple processes to acquire it and [fdi]i_rwsem are not held
-+ * in file I/O. Aufs needs to stop lockdep in aufs_mmap() though.
-+ * It means that when aufs acquires si_rwsem for write, the process should never
-+ * acquire mmap_sem.
-+ *
-+ * Actually aufs_iterate() holds [fdi]i_rwsem before mmap_sem, but this is not a
-+ * problem either since any directory is not able to be mmap-ed.
-+ * The similar scenario is applied to aufs_readlink() too.
-+ */
-+
-+#if 0 /* stop calling security_file_mmap() */
-+/* cf. linux/include/linux/mman.h: calc_vm_prot_bits() */
-+#define AuConv_VM_PROT(f, b) _calc_vm_trans(f, VM_##b, PROT_##b)
-+
-+static unsigned long au_arch_prot_conv(unsigned long flags)
-+{
-+ /* currently ppc64 only */
-+#ifdef CONFIG_PPC64
-+ /* cf. linux/arch/powerpc/include/asm/mman.h */
-+ AuDebugOn(arch_calc_vm_prot_bits(-1) != VM_SAO);
-+ return AuConv_VM_PROT(flags, SAO);
-+#else
-+ AuDebugOn(arch_calc_vm_prot_bits(-1));
-+ return 0;
-+#endif
-+}
-+
-+static unsigned long au_prot_conv(unsigned long flags)
-+{
-+ return AuConv_VM_PROT(flags, READ)
-+ | AuConv_VM_PROT(flags, WRITE)
-+ | AuConv_VM_PROT(flags, EXEC)
-+ | au_arch_prot_conv(flags);
-+}
-+
-+/* cf. linux/include/linux/mman.h: calc_vm_flag_bits() */
-+#define AuConv_VM_MAP(f, b) _calc_vm_trans(f, VM_##b, MAP_##b)
-+
-+static unsigned long au_flag_conv(unsigned long flags)
-+{
-+ return AuConv_VM_MAP(flags, GROWSDOWN)
-+ | AuConv_VM_MAP(flags, DENYWRITE)
-+ | AuConv_VM_MAP(flags, LOCKED);
-+}
-+#endif
-+
-+static int aufs_mmap(struct file *file, struct vm_area_struct *vma)
-+{
-+ int err;
-+ const unsigned char wlock
-+ = (file->f_mode & FMODE_WRITE) && (vma->vm_flags & VM_SHARED);
-+ struct super_block *sb;
-+ struct file *h_file;
-+ struct inode *inode;
-+
-+ AuDbgVmRegion(file, vma);
-+
-+ inode = file_inode(file);
-+ sb = inode->i_sb;
-+ lockdep_off();
-+ si_read_lock(sb, AuLock_NOPLMW);
-+
-+ h_file = au_write_pre(file, wlock, /*wpre*/NULL);
-+ lockdep_on();
-+ err = PTR_ERR(h_file);
-+ if (IS_ERR(h_file))
-+ goto out;
-+
-+ err = 0;
-+ au_set_mmapped(file);
-+ au_vm_file_reset(vma, h_file);
-+ /*
-+ * we cannot call security_mmap_file() here since it may acquire
-+ * mmap_sem or i_mutex.
-+ *
-+ * err = security_mmap_file(h_file, au_prot_conv(vma->vm_flags),
-+ * au_flag_conv(vma->vm_flags));
-+ */
-+ if (!err)
-+ err = call_mmap(h_file, vma);
-+ if (!err) {
-+ au_vm_prfile_set(vma, file);
-+ fsstack_copy_attr_atime(inode, file_inode(h_file));
-+ goto out_fput; /* success */
-+ }
-+ au_unset_mmapped(file);
-+ au_vm_file_reset(vma, file);
-+
-+out_fput:
-+ lockdep_off();
-+ ii_write_unlock(inode);
-+ lockdep_on();
-+ fput(h_file);
-+out:
-+ lockdep_off();
-+ si_read_unlock(sb);
-+ lockdep_on();
-+ AuTraceErr(err);
-+ return err;
-+}
-+
-+/* ---------------------------------------------------------------------- */
-+
-+static int aufs_fsync_nondir(struct file *file, loff_t start, loff_t end,
-+ int datasync)
-+{
-+ int err;
-+ struct au_write_pre wpre;
-+ struct inode *inode;
-+ struct file *h_file;
-+
-+ err = 0; /* -EBADF; */ /* posix? */
-+ if (unlikely(!(file->f_mode & FMODE_WRITE)))
-+ goto out;
-+
-+ inode = file_inode(file);
-+ au_mtx_and_read_lock(inode);
-+
-+ wpre.lsc = 0;
-+ h_file = au_write_pre(file, /*do_ready*/1, &wpre);
-+ err = PTR_ERR(h_file);
-+ if (IS_ERR(h_file))
-+ goto out_unlock;
-+
-+ err = vfsub_fsync(h_file, &h_file->f_path, datasync);
-+ au_write_post(inode, h_file, &wpre, /*written*/0);
-+
-+out_unlock:
-+ si_read_unlock(inode->i_sb);
-+ inode_unlock(inode);
-+out:
-+ return err;
-+}
-+
-+static int aufs_fasync(int fd, struct file *file, int flag)
-+{
-+ int err;
-+ struct file *h_file;
-+ struct super_block *sb;
-+
-+ sb = file->f_path.dentry->d_sb;
-+ si_read_lock(sb, AuLock_FLUSH | AuLock_NOPLMW);
-+
-+ h_file = au_read_pre(file, /*keep_fi*/0, /*lsc*/0);
-+ err = PTR_ERR(h_file);
-+ if (IS_ERR(h_file))
-+ goto out;
-+
-+ if (h_file->f_op->fasync)
-+ err = h_file->f_op->fasync(fd, h_file, flag);
-+ fput(h_file); /* instead of au_read_post() */
-+
-+out:
-+ si_read_unlock(sb);
-+ return err;
-+}
-+
-+static int aufs_setfl(struct file *file, unsigned long arg)
-+{
-+ int err;
-+ struct file *h_file;
-+ struct super_block *sb;
-+
-+ sb = file->f_path.dentry->d_sb;
-+ si_read_lock(sb, AuLock_FLUSH | AuLock_NOPLMW);
-+
-+ h_file = au_read_pre(file, /*keep_fi*/0, /*lsc*/0);
-+ err = PTR_ERR(h_file);
-+ if (IS_ERR(h_file))
-+ goto out;
-+
-+ /* stop calling h_file->fasync */
-+ arg |= vfsub_file_flags(file) & FASYNC;
-+ err = setfl(/*unused fd*/-1, h_file, arg);
-+ fput(h_file); /* instead of au_read_post() */
-+
-+out:
-+ si_read_unlock(sb);
-+ return err;
-+}
-+
-+/* ---------------------------------------------------------------------- */
-+
-+/* no one supports this operation, currently */
-+#if 0
-+static ssize_t aufs_sendpage(struct file *file, struct page *page, int offset,
-+ size_t len, loff_t *pos, int more)
-+{
-+}
-+#endif
-+
-+/* ---------------------------------------------------------------------- */
-+
-+const struct file_operations aufs_file_fop = {
-+ .owner = THIS_MODULE,
-+
-+ .llseek = default_llseek,
-+
-+ .read = aufs_read,
-+ .write = aufs_write,
-+ .read_iter = aufs_read_iter,
-+ .write_iter = aufs_write_iter,
-+
-+#ifdef CONFIG_AUFS_POLL
-+ .poll = aufs_poll,
-+#endif
-+ .unlocked_ioctl = aufs_ioctl_nondir,
-+#ifdef CONFIG_COMPAT
-+ .compat_ioctl = aufs_compat_ioctl_nondir,
-+#endif
-+ .mmap = aufs_mmap,
-+ .open = aufs_open_nondir,
-+ .flush = aufs_flush_nondir,
-+ .release = aufs_release_nondir,
-+ .fsync = aufs_fsync_nondir,
-+ .fasync = aufs_fasync,
-+ /* .sendpage = aufs_sendpage, */
-+ .setfl = aufs_setfl,
-+ .splice_write = aufs_splice_write,
-+ .splice_read = aufs_splice_read,
-+#if 0
-+ .aio_splice_write = aufs_aio_splice_write,
-+ .aio_splice_read = aufs_aio_splice_read,
-+#endif
-+ .fallocate = aufs_fallocate,
-+ .copy_file_range = aufs_copy_file_range
-+};
-diff --git a/fs/aufs/fhsm.c b/fs/aufs/fhsm.c
-new file mode 100644
-index 000000000000..f86a4c24fb26
---- /dev/null
-+++ b/fs/aufs/fhsm.c
-@@ -0,0 +1,427 @@
-+// SPDX-License-Identifier: GPL-2.0
-+/*
-+ * Copyright (C) 2011-2019 Junjiro R. Okajima
-+ *
-+ * This program, aufs is free software; you can redistribute it and/or modify
-+ * it under the terms of the GNU General Public License as published by
-+ * the Free Software Foundation; either version 2 of the License, or
-+ * (at your option) any later version.
-+ *
-+ * This program is distributed in the hope that it will be useful,
-+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
-+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
-+ * GNU General Public License for more details.
-+ *
-+ * You should have received a copy of the GNU General Public License
-+ * along with this program; if not, write to the Free Software
-+ * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
-+ */
-+
-+/*
-+ * File-based Hierarchy Storage Management
-+ */
-+
-+#include <linux/anon_inodes.h>
-+#include <linux/poll.h>
-+#include <linux/seq_file.h>
-+#include <linux/statfs.h>
-+#include "aufs.h"
-+
-+static aufs_bindex_t au_fhsm_bottom(struct super_block *sb)
-+{
-+ struct au_sbinfo *sbinfo;
-+ struct au_fhsm *fhsm;
-+
-+ SiMustAnyLock(sb);
-+
-+ sbinfo = au_sbi(sb);
-+ fhsm = &sbinfo->si_fhsm;
-+ AuDebugOn(!fhsm);
-+ return fhsm->fhsm_bottom;
-+}
-+
-+void au_fhsm_set_bottom(struct super_block *sb, aufs_bindex_t bindex)
-+{
-+ struct au_sbinfo *sbinfo;
-+ struct au_fhsm *fhsm;
-+
-+ SiMustWriteLock(sb);
-+
-+ sbinfo = au_sbi(sb);
-+ fhsm = &sbinfo->si_fhsm;
-+ AuDebugOn(!fhsm);
-+ fhsm->fhsm_bottom = bindex;
-+}
-+
-+/* ---------------------------------------------------------------------- */
-+
-+static int au_fhsm_test_jiffy(struct au_sbinfo *sbinfo, struct au_branch *br)
-+{
-+ struct au_br_fhsm *bf;
-+
-+ bf = br->br_fhsm;
-+ MtxMustLock(&bf->bf_lock);
-+
-+ return !bf->bf_readable
-+ || time_after(jiffies,
-+ bf->bf_jiffy + sbinfo->si_fhsm.fhsm_expire);
-+}
-+
-+/* ---------------------------------------------------------------------- */
-+
-+static void au_fhsm_notify(struct super_block *sb, int val)
-+{
-+ struct au_sbinfo *sbinfo;
-+ struct au_fhsm *fhsm;
-+
-+ SiMustAnyLock(sb);
-+
-+ sbinfo = au_sbi(sb);
-+ fhsm = &sbinfo->si_fhsm;
-+ if (au_fhsm_pid(fhsm)
-+ && atomic_read(&fhsm->fhsm_readable) != -1) {
-+ atomic_set(&fhsm->fhsm_readable, val);
-+ if (val)
-+ wake_up(&fhsm->fhsm_wqh);
-+ }
-+}
-+
-+static int au_fhsm_stfs(struct super_block *sb, aufs_bindex_t bindex,
-+ struct aufs_stfs *rstfs, int do_lock, int do_notify)
-+{
-+ int err;
-+ struct au_branch *br;
-+ struct au_br_fhsm *bf;
-+
-+ br = au_sbr(sb, bindex);
-+ AuDebugOn(au_br_rdonly(br));
-+ bf = br->br_fhsm;
-+ AuDebugOn(!bf);
-+
-+ if (do_lock)
-+ mutex_lock(&bf->bf_lock);
-+ else
-+ MtxMustLock(&bf->bf_lock);
-+
-+ /* sb->s_root for NFS is unreliable */
-+ err = au_br_stfs(br, &bf->bf_stfs);
-+ if (unlikely(err)) {
-+ AuErr1("FHSM failed (%d), b%d, ignored.\n", bindex, err);
-+ goto out;
-+ }
-+
-+ bf->bf_jiffy = jiffies;
-+ bf->bf_readable = 1;
-+ if (do_notify)
-+ au_fhsm_notify(sb, /*val*/1);
-+ if (rstfs)
-+ *rstfs = bf->bf_stfs;
-+
-+out:
-+ if (do_lock)
-+ mutex_unlock(&bf->bf_lock);
-+ au_fhsm_notify(sb, /*val*/1);
-+
-+ return err;
-+}
-+
-+void au_fhsm_wrote(struct super_block *sb, aufs_bindex_t bindex, int force)
-+{
-+ int err;
-+ struct au_sbinfo *sbinfo;
-+ struct au_fhsm *fhsm;
-+ struct au_branch *br;
-+ struct au_br_fhsm *bf;
-+
-+ AuDbg("b%d, force %d\n", bindex, force);
-+ SiMustAnyLock(sb);
-+
-+ sbinfo = au_sbi(sb);
-+ fhsm = &sbinfo->si_fhsm;
-+ if (!au_ftest_si(sbinfo, FHSM)
-+ || fhsm->fhsm_bottom == bindex)
-+ return;
-+
-+ br = au_sbr(sb, bindex);
-+ bf = br->br_fhsm;
-+ AuDebugOn(!bf);
-+ mutex_lock(&bf->bf_lock);
-+ if (force
-+ || au_fhsm_pid(fhsm)
-+ || au_fhsm_test_jiffy(sbinfo, br))
-+ err = au_fhsm_stfs(sb, bindex, /*rstfs*/NULL, /*do_lock*/0,
-+ /*do_notify*/1);
-+ mutex_unlock(&bf->bf_lock);
-+}
-+
-+void au_fhsm_wrote_all(struct super_block *sb, int force)
-+{
-+ aufs_bindex_t bindex, bbot;
-+ struct au_branch *br;
-+
-+ /* exclude the bottom */
-+ bbot = au_fhsm_bottom(sb);
-+ for (bindex = 0; bindex < bbot; bindex++) {
-+ br = au_sbr(sb, bindex);
-+ if (au_br_fhsm(br->br_perm))
-+ au_fhsm_wrote(sb, bindex, force);
-+ }
-+}
-+
-+/* ---------------------------------------------------------------------- */
-+
-+static __poll_t au_fhsm_poll(struct file *file, struct poll_table_struct *wait)
-+{
-+ __poll_t mask;
-+ struct au_sbinfo *sbinfo;
-+ struct au_fhsm *fhsm;
-+
-+ mask = 0;
-+ sbinfo = file->private_data;
-+ fhsm = &sbinfo->si_fhsm;
-+ poll_wait(file, &fhsm->fhsm_wqh, wait);
-+ if (atomic_read(&fhsm->fhsm_readable))
-+ mask = EPOLLIN /* | EPOLLRDNORM */;
-+
-+ if (!mask)
-+ AuDbg("mask 0x%x\n", mask);
-+ return mask;
-+}
-+
-+static int au_fhsm_do_read_one(struct aufs_stbr __user *stbr,
-+ struct aufs_stfs *stfs, __s16 brid)
-+{
-+ int err;
-+
-+ err = copy_to_user(&stbr->stfs, stfs, sizeof(*stfs));
-+ if (!err)
-+ err = __put_user(brid, &stbr->brid);
-+ if (unlikely(err))
-+ err = -EFAULT;
-+
-+ return err;
-+}
-+
-+static ssize_t au_fhsm_do_read(struct super_block *sb,
-+ struct aufs_stbr __user *stbr, size_t count)
-+{
-+ ssize_t err;
-+ int nstbr;
-+ aufs_bindex_t bindex, bbot;
-+ struct au_branch *br;
-+ struct au_br_fhsm *bf;
-+
-+ /* except the bottom branch */
-+ err = 0;
-+ nstbr = 0;
-+ bbot = au_fhsm_bottom(sb);
-+ for (bindex = 0; !err && bindex < bbot; bindex++) {
-+ br = au_sbr(sb, bindex);
-+ if (!au_br_fhsm(br->br_perm))
-+ continue;
-+
-+ bf = br->br_fhsm;
-+ mutex_lock(&bf->bf_lock);
-+ if (bf->bf_readable) {
-+ err = -EFAULT;
-+ if (count >= sizeof(*stbr))
-+ err = au_fhsm_do_read_one(stbr++, &bf->bf_stfs,
-+ br->br_id);
-+ if (!err) {
-+ bf->bf_readable = 0;
-+ count -= sizeof(*stbr);
-+ nstbr++;
-+ }
-+ }
-+ mutex_unlock(&bf->bf_lock);
-+ }
-+ if (!err)
-+ err = sizeof(*stbr) * nstbr;
-+
-+ return err;
-+}
-+
-+static ssize_t au_fhsm_read(struct file *file, char __user *buf, size_t count,
-+ loff_t *pos)
-+{
-+ ssize_t err;
-+ int readable;
-+ aufs_bindex_t nfhsm, bindex, bbot;
-+ struct au_sbinfo *sbinfo;
-+ struct au_fhsm *fhsm;
-+ struct au_branch *br;
-+ struct super_block *sb;
-+
-+ err = 0;
-+ sbinfo = file->private_data;
-+ fhsm = &sbinfo->si_fhsm;
-+need_data:
-+ spin_lock_irq(&fhsm->fhsm_wqh.lock);
-+ if (!atomic_read(&fhsm->fhsm_readable)) {
-+ if (vfsub_file_flags(file) & O_NONBLOCK)
-+ err = -EAGAIN;
-+ else
-+ err = wait_event_interruptible_locked_irq
-+ (fhsm->fhsm_wqh,
-+ atomic_read(&fhsm->fhsm_readable));
-+ }
-+ spin_unlock_irq(&fhsm->fhsm_wqh.lock);
-+ if (unlikely(err))
-+ goto out;
-+
-+ /* sb may already be dead */
-+ au_rw_read_lock(&sbinfo->si_rwsem);
-+ readable = atomic_read(&fhsm->fhsm_readable);
-+ if (readable > 0) {
-+ sb = sbinfo->si_sb;
-+ AuDebugOn(!sb);
-+ /* exclude the bottom branch */
-+ nfhsm = 0;
-+ bbot = au_fhsm_bottom(sb);
-+ for (bindex = 0; bindex < bbot; bindex++) {
-+ br = au_sbr(sb, bindex);
-+ if (au_br_fhsm(br->br_perm))
-+ nfhsm++;
-+ }
-+ err = -EMSGSIZE;
-+ if (nfhsm * sizeof(struct aufs_stbr) <= count) {
-+ atomic_set(&fhsm->fhsm_readable, 0);
-+ err = au_fhsm_do_read(sbinfo->si_sb, (void __user *)buf,
-+ count);
-+ }
-+ }
-+ au_rw_read_unlock(&sbinfo->si_rwsem);
-+ if (!readable)
-+ goto need_data;
-+
-+out:
-+ return err;
-+}
-+
-+static int au_fhsm_release(struct inode *inode, struct file *file)
-+{
-+ struct au_sbinfo *sbinfo;
-+ struct au_fhsm *fhsm;
-+
-+ /* sb may already be dead */
-+ sbinfo = file->private_data;
-+ fhsm = &sbinfo->si_fhsm;
-+ spin_lock(&fhsm->fhsm_spin);
-+ fhsm->fhsm_pid = 0;
-+ spin_unlock(&fhsm->fhsm_spin);
-+ kobject_put(&sbinfo->si_kobj);
-+
-+ return 0;
-+}
-+
-+static const struct file_operations au_fhsm_fops = {
-+ .owner = THIS_MODULE,
-+ .llseek = noop_llseek,
-+ .read = au_fhsm_read,
-+ .poll = au_fhsm_poll,
-+ .release = au_fhsm_release
-+};
-+
-+int au_fhsm_fd(struct super_block *sb, int oflags)
-+{
-+ int err, fd;
-+ struct au_sbinfo *sbinfo;
-+ struct au_fhsm *fhsm;
-+
-+ err = -EPERM;
-+ if (unlikely(!capable(CAP_SYS_ADMIN)))
-+ goto out;
-+
-+ err = -EINVAL;
-+ if (unlikely(oflags & ~(O_CLOEXEC | O_NONBLOCK)))
-+ goto out;
-+
-+ err = 0;
-+ sbinfo = au_sbi(sb);
-+ fhsm = &sbinfo->si_fhsm;
-+ spin_lock(&fhsm->fhsm_spin);
-+ if (!fhsm->fhsm_pid)
-+ fhsm->fhsm_pid = current->pid;
-+ else
-+ err = -EBUSY;
-+ spin_unlock(&fhsm->fhsm_spin);
-+ if (unlikely(err))
-+ goto out;
-+
-+ oflags |= O_RDONLY;
-+ /* oflags |= FMODE_NONOTIFY; */
-+ fd = anon_inode_getfd("[aufs_fhsm]", &au_fhsm_fops, sbinfo, oflags);
-+ err = fd;
-+ if (unlikely(fd < 0))
-+ goto out_pid;
-+
-+ /* succeed regardless 'fhsm' status */
-+ kobject_get(&sbinfo->si_kobj);
-+ si_noflush_read_lock(sb);
-+ if (au_ftest_si(sbinfo, FHSM))
-+ au_fhsm_wrote_all(sb, /*force*/0);
-+ si_read_unlock(sb);
-+ goto out; /* success */
-+
-+out_pid:
-+ spin_lock(&fhsm->fhsm_spin);
-+ fhsm->fhsm_pid = 0;
-+ spin_unlock(&fhsm->fhsm_spin);
-+out:
-+ AuTraceErr(err);
-+ return err;
-+}
-+
-+/* ---------------------------------------------------------------------- */
-+
-+int au_fhsm_br_alloc(struct au_branch *br)
-+{
-+ int err;
-+
-+ err = 0;
-+ br->br_fhsm = kmalloc(sizeof(*br->br_fhsm), GFP_NOFS);
-+ if (br->br_fhsm)
-+ au_br_fhsm_init(br->br_fhsm);
-+ else
-+ err = -ENOMEM;
-+
-+ return err;
-+}
-+
-+/* ---------------------------------------------------------------------- */
-+
-+void au_fhsm_fin(struct super_block *sb)
-+{
-+ au_fhsm_notify(sb, /*val*/-1);
-+}
-+
-+void au_fhsm_init(struct au_sbinfo *sbinfo)
-+{
-+ struct au_fhsm *fhsm;
-+
-+ fhsm = &sbinfo->si_fhsm;
-+ spin_lock_init(&fhsm->fhsm_spin);
-+ init_waitqueue_head(&fhsm->fhsm_wqh);
-+ atomic_set(&fhsm->fhsm_readable, 0);
-+ fhsm->fhsm_expire
-+ = msecs_to_jiffies(AUFS_FHSM_CACHE_DEF_SEC * MSEC_PER_SEC);
-+ fhsm->fhsm_bottom = -1;
-+}
-+
-+void au_fhsm_set(struct au_sbinfo *sbinfo, unsigned int sec)
-+{
-+ sbinfo->si_fhsm.fhsm_expire
-+ = msecs_to_jiffies(sec * MSEC_PER_SEC);
-+}
-+
-+void au_fhsm_show(struct seq_file *seq, struct au_sbinfo *sbinfo)
-+{
-+ unsigned int u;
-+
-+ if (!au_ftest_si(sbinfo, FHSM))
-+ return;
-+
-+ u = jiffies_to_msecs(sbinfo->si_fhsm.fhsm_expire) / MSEC_PER_SEC;
-+ if (u != AUFS_FHSM_CACHE_DEF_SEC)
-+ seq_printf(seq, ",fhsm_sec=%u", u);
-+}
-diff --git a/fs/aufs/file.c b/fs/aufs/file.c
-new file mode 100644
-index 000000000000..dbb33855d226
---- /dev/null
-+++ b/fs/aufs/file.c
-@@ -0,0 +1,863 @@
-+// SPDX-License-Identifier: GPL-2.0
-+/*
-+ * Copyright (C) 2005-2019 Junjiro R. Okajima
-+ *
-+ * This program, aufs is free software; you can redistribute it and/or modify
-+ * it under the terms of the GNU General Public License as published by
-+ * the Free Software Foundation; either version 2 of the License, or
-+ * (at your option) any later version.
-+ *
-+ * This program is distributed in the hope that it will be useful,
-+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
-+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
-+ * GNU General Public License for more details.
-+ *
-+ * You should have received a copy of the GNU General Public License
-+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
-+ */
-+
-+/*
-+ * handling file/dir, and address_space operation
-+ */
-+
-+#ifdef CONFIG_AUFS_DEBUG
-+#include <linux/migrate.h>
-+#endif
-+#include <linux/pagemap.h>
-+#include "aufs.h"
-+
-+/* drop flags for writing */
-+unsigned int au_file_roflags(unsigned int flags)
-+{
-+ flags &= ~(O_WRONLY | O_RDWR | O_APPEND | O_CREAT | O_TRUNC);
-+ flags |= O_RDONLY | O_NOATIME;
-+ return flags;
-+}
-+
-+/* common functions to regular file and dir */
-+struct file *au_h_open(struct dentry *dentry, aufs_bindex_t bindex, int flags,
-+ struct file *file, int force_wr)
-+{
-+ struct file *h_file;
-+ struct dentry *h_dentry;
-+ struct inode *h_inode;
-+ struct super_block *sb;
-+ struct au_branch *br;
-+ struct path h_path;
-+ int err;
-+
-+ /* a race condition can happen between open and unlink/rmdir */
-+ h_file = ERR_PTR(-ENOENT);
-+ h_dentry = au_h_dptr(dentry, bindex);
-+ if (au_test_nfsd() && (!h_dentry || d_is_negative(h_dentry)))
-+ goto out;
-+ h_inode = d_inode(h_dentry);
-+ spin_lock(&h_dentry->d_lock);
-+ err = (!d_unhashed(dentry) && d_unlinked(h_dentry))
-+ /* || !d_inode(dentry)->i_nlink */
-+ ;
-+ spin_unlock(&h_dentry->d_lock);
-+ if (unlikely(err))
-+ goto out;
-+
-+ sb = dentry->d_sb;
-+ br = au_sbr(sb, bindex);
-+ err = au_br_test_oflag(flags, br);
-+ h_file = ERR_PTR(err);
-+ if (unlikely(err))
-+ goto out;
-+
-+ /* drop flags for writing */
-+ if (au_test_ro(sb, bindex, d_inode(dentry))) {
-+ if (force_wr && !(flags & O_WRONLY))
-+ force_wr = 0;
-+ flags = au_file_roflags(flags);
-+ if (force_wr) {
-+ h_file = ERR_PTR(-EROFS);
-+ flags = au_file_roflags(flags);
-+ if (unlikely(vfsub_native_ro(h_inode)
-+ || IS_APPEND(h_inode)))
-+ goto out;
-+ flags &= ~O_ACCMODE;
-+ flags |= O_WRONLY;
-+ }
-+ }
-+ flags &= ~O_CREAT;
-+ au_lcnt_inc(&br->br_nfiles);
-+ h_path.dentry = h_dentry;
-+ h_path.mnt = au_br_mnt(br);
-+ h_file = vfsub_dentry_open(&h_path, flags);
-+ if (IS_ERR(h_file))
-+ goto out_br;
-+
-+ if (flags & __FMODE_EXEC) {
-+ err = deny_write_access(h_file);
-+ if (unlikely(err)) {
-+ fput(h_file);
-+ h_file = ERR_PTR(err);
-+ goto out_br;
-+ }
-+ }
-+ fsnotify_open(h_file);
-+ goto out; /* success */
-+
-+out_br:
-+ au_lcnt_dec(&br->br_nfiles);
-+out:
-+ return h_file;
-+}
-+
-+static int au_cmoo(struct dentry *dentry)
-+{
-+ int err, cmoo, matched;
-+ unsigned int udba;
-+ struct path h_path;
-+ struct au_pin pin;
-+ struct au_cp_generic cpg = {
-+ .dentry = dentry,
-+ .bdst = -1,
-+ .bsrc = -1,
-+ .len = -1,
-+ .pin = &pin,
-+ .flags = AuCpup_DTIME | AuCpup_HOPEN
-+ };
-+ struct inode *delegated;
-+ struct super_block *sb;
-+ struct au_sbinfo *sbinfo;
-+ struct au_fhsm *fhsm;
-+ pid_t pid;
-+ struct au_branch *br;
-+ struct dentry *parent;
-+ struct au_hinode *hdir;
-+
-+ DiMustWriteLock(dentry);
-+ IiMustWriteLock(d_inode(dentry));
-+
-+ err = 0;
-+ if (IS_ROOT(dentry))
-+ goto out;
-+ cpg.bsrc = au_dbtop(dentry);
-+ if (!cpg.bsrc)
-+ goto out;
-+
-+ sb = dentry->d_sb;
-+ sbinfo = au_sbi(sb);
-+ fhsm = &sbinfo->si_fhsm;
-+ pid = au_fhsm_pid(fhsm);
-+ rcu_read_lock();
-+ matched = (pid
-+ && (current->pid == pid
-+ || rcu_dereference(current->real_parent)->pid == pid));
-+ rcu_read_unlock();
-+ if (matched)
-+ goto out;
-+
-+ br = au_sbr(sb, cpg.bsrc);
-+ cmoo = au_br_cmoo(br->br_perm);
-+ if (!cmoo)
-+ goto out;
-+ if (!d_is_reg(dentry))
-+ cmoo &= AuBrAttr_COO_ALL;
-+ if (!cmoo)
-+ goto out;
-+
-+ parent = dget_parent(dentry);
-+ di_write_lock_parent(parent);
-+ err = au_wbr_do_copyup_bu(dentry, cpg.bsrc - 1);
-+ cpg.bdst = err;
-+ if (unlikely(err < 0)) {
-+ err = 0; /* there is no upper writable branch */
-+ goto out_dgrade;
-+ }
-+ AuDbg("bsrc %d, bdst %d\n", cpg.bsrc, cpg.bdst);
-+
-+ /* do not respect the coo attrib for the target branch */
-+ err = au_cpup_dirs(dentry, cpg.bdst);
-+ if (unlikely(err))
-+ goto out_dgrade;
-+
-+ di_downgrade_lock(parent, AuLock_IR);
-+ udba = au_opt_udba(sb);
-+ err = au_pin(&pin, dentry, cpg.bdst, udba,
-+ AuPin_DI_LOCKED | AuPin_MNT_WRITE);
-+ if (unlikely(err))
-+ goto out_parent;
-+
-+ err = au_sio_cpup_simple(&cpg);
-+ au_unpin(&pin);
-+ if (unlikely(err))
-+ goto out_parent;
-+ if (!(cmoo & AuBrWAttr_MOO))
-+ goto out_parent; /* success */
-+
-+ err = au_pin(&pin, dentry, cpg.bsrc, udba,
-+ AuPin_DI_LOCKED | AuPin_MNT_WRITE);
-+ if (unlikely(err))
-+ goto out_parent;
-+
-+ h_path.mnt = au_br_mnt(br);
-+ h_path.dentry = au_h_dptr(dentry, cpg.bsrc);
-+ hdir = au_hi(d_inode(parent), cpg.bsrc);
-+ delegated = NULL;
-+ err = vfsub_unlink(hdir->hi_inode, &h_path, &delegated, /*force*/1);
-+ au_unpin(&pin);
-+ /* todo: keep h_dentry or not? */
-+ if (unlikely(err == -EWOULDBLOCK)) {
-+ pr_warn("cannot retry for NFSv4 delegation"
-+ " for an internal unlink\n");
-+ iput(delegated);
-+ }
-+ if (unlikely(err)) {
-+ pr_err("unlink %pd after coo failed (%d), ignored\n",
-+ dentry, err);
-+ err = 0;
-+ }
-+ goto out_parent; /* success */
-+
-+out_dgrade:
-+ di_downgrade_lock(parent, AuLock_IR);
-+out_parent:
-+ di_read_unlock(parent, AuLock_IR);
-+ dput(parent);
-+out:
-+ AuTraceErr(err);
-+ return err;
-+}
-+
-+int au_do_open(struct file *file, struct au_do_open_args *args)
-+{
-+ int err, aopen = args->aopen;
-+ struct dentry *dentry;
-+ struct au_finfo *finfo;
-+
-+ if (!aopen)
-+ err = au_finfo_init(file, args->fidir);
-+ else {
-+ lockdep_off();
-+ err = au_finfo_init(file, args->fidir);
-+ lockdep_on();
-+ }
-+ if (unlikely(err))
-+ goto out;
-+
-+ dentry = file->f_path.dentry;
-+ AuDebugOn(IS_ERR_OR_NULL(dentry));
-+ di_write_lock_child(dentry);
-+ err = au_cmoo(dentry);
-+ di_downgrade_lock(dentry, AuLock_IR);
-+ if (!err) {
-+ if (!aopen)
-+ err = args->open(file, vfsub_file_flags(file), NULL);
-+ else {
-+ lockdep_off();
-+ err = args->open(file, vfsub_file_flags(file),
-+ args->h_file);
-+ lockdep_on();
-+ }
-+ }
-+ di_read_unlock(dentry, AuLock_IR);
-+
-+ finfo = au_fi(file);
-+ if (!err) {
-+ finfo->fi_file = file;
-+ au_hbl_add(&finfo->fi_hlist,
-+ &au_sbi(file->f_path.dentry->d_sb)->si_files);
-+ }
-+ if (!aopen)
-+ fi_write_unlock(file);
-+ else {
-+ lockdep_off();
-+ fi_write_unlock(file);
-+ lockdep_on();
-+ }
-+ if (unlikely(err)) {
-+ finfo->fi_hdir = NULL;
-+ au_finfo_fin(file);
-+ }
-+
-+out:
-+ AuTraceErr(err);
-+ return err;
-+}
-+
-+int au_reopen_nondir(struct file *file)
-+{
-+ int err;
-+ aufs_bindex_t btop;
-+ struct dentry *dentry;
-+ struct au_branch *br;
-+ struct file *h_file, *h_file_tmp;
-+
-+ dentry = file->f_path.dentry;
-+ btop = au_dbtop(dentry);
-+ br = au_sbr(dentry->d_sb, btop);
-+ h_file_tmp = NULL;
-+ if (au_fbtop(file) == btop) {
-+ h_file = au_hf_top(file);
-+ if (file->f_mode == h_file->f_mode)
-+ return 0; /* success */
-+ h_file_tmp = h_file;
-+ get_file(h_file_tmp);
-+ au_lcnt_inc(&br->br_nfiles);
-+ au_set_h_fptr(file, btop, NULL);
-+ }
-+ AuDebugOn(au_fi(file)->fi_hdir);
-+ /*
-+ * it can happen
-+ * file exists on both of rw and ro
-+ * open --> dbtop and fbtop are both 0
-+ * prepend a branch as rw, "rw" become ro
-+ * remove rw/file
-+ * delete the top branch, "rw" becomes rw again
-+ * --> dbtop is 1, fbtop is still 0
-+ * write --> fbtop is 0 but dbtop is 1
-+ */
-+ /* AuDebugOn(au_fbtop(file) < btop); */
-+
-+ h_file = au_h_open(dentry, btop, vfsub_file_flags(file) & ~O_TRUNC,
-+ file, /*force_wr*/0);
-+ err = PTR_ERR(h_file);
-+ if (IS_ERR(h_file)) {
-+ if (h_file_tmp) {
-+ /* revert */
-+ au_set_h_fptr(file, btop, h_file_tmp);
-+ h_file_tmp = NULL;
-+ }
-+ goto out; /* todo: close all? */
-+ }
-+
-+ err = 0;
-+ au_set_fbtop(file, btop);
-+ au_set_h_fptr(file, btop, h_file);
-+ au_update_figen(file);
-+ /* todo: necessary? */
-+ /* file->f_ra = h_file->f_ra; */
-+
-+out:
-+ if (h_file_tmp) {
-+ fput(h_file_tmp);
-+ au_lcnt_dec(&br->br_nfiles);
-+ }
-+ return err;
-+}
-+
-+/* ---------------------------------------------------------------------- */
-+
-+static int au_reopen_wh(struct file *file, aufs_bindex_t btgt,
-+ struct dentry *hi_wh)
-+{
-+ int err;
-+ aufs_bindex_t btop;
-+ struct au_dinfo *dinfo;
-+ struct dentry *h_dentry;
-+ struct au_hdentry *hdp;
-+
-+ dinfo = au_di(file->f_path.dentry);
-+ AuRwMustWriteLock(&dinfo->di_rwsem);
-+
-+ btop = dinfo->di_btop;
-+ dinfo->di_btop = btgt;
-+ hdp = au_hdentry(dinfo, btgt);
-+ h_dentry = hdp->hd_dentry;
-+ hdp->hd_dentry = hi_wh;
-+ err = au_reopen_nondir(file);
-+ hdp->hd_dentry = h_dentry;
-+ dinfo->di_btop = btop;
-+
-+ return err;
-+}
-+
-+static int au_ready_to_write_wh(struct file *file, loff_t len,
-+ aufs_bindex_t bcpup, struct au_pin *pin)
-+{
-+ int err;
-+ struct inode *inode, *h_inode;
-+ struct dentry *h_dentry, *hi_wh;
-+ struct au_cp_generic cpg = {
-+ .dentry = file->f_path.dentry,
-+ .bdst = bcpup,
-+ .bsrc = -1,
-+ .len = len,
-+ .pin = pin
-+ };
-+
-+ au_update_dbtop(cpg.dentry);
-+ inode = d_inode(cpg.dentry);
-+ h_inode = NULL;
-+ if (au_dbtop(cpg.dentry) <= bcpup
-+ && au_dbbot(cpg.dentry) >= bcpup) {
-+ h_dentry = au_h_dptr(cpg.dentry, bcpup);
-+ if (h_dentry && d_is_positive(h_dentry))
-+ h_inode = d_inode(h_dentry);
-+ }
-+ hi_wh = au_hi_wh(inode, bcpup);
-+ if (!hi_wh && !h_inode)
-+ err = au_sio_cpup_wh(&cpg, file);
-+ else
-+ /* already copied-up after unlink */
-+ err = au_reopen_wh(file, bcpup, hi_wh);
-+
-+ if (!err
-+ && (inode->i_nlink > 1
-+ || (inode->i_state & I_LINKABLE))
-+ && au_opt_test(au_mntflags(cpg.dentry->d_sb), PLINK))
-+ au_plink_append(inode, bcpup, au_h_dptr(cpg.dentry, bcpup));
-+
-+ return err;
-+}
-+
-+/*
-+ * prepare the @file for writing.
-+ */
-+int au_ready_to_write(struct file *file, loff_t len, struct au_pin *pin)
-+{
-+ int err;
-+ aufs_bindex_t dbtop;
-+ struct dentry *parent;
-+ struct inode *inode;
-+ struct super_block *sb;
-+ struct file *h_file;
-+ struct au_cp_generic cpg = {
-+ .dentry = file->f_path.dentry,
-+ .bdst = -1,
-+ .bsrc = -1,
-+ .len = len,
-+ .pin = pin,
-+ .flags = AuCpup_DTIME
-+ };
-+
-+ sb = cpg.dentry->d_sb;
-+ inode = d_inode(cpg.dentry);
-+ cpg.bsrc = au_fbtop(file);
-+ err = au_test_ro(sb, cpg.bsrc, inode);
-+ if (!err && (au_hf_top(file)->f_mode & FMODE_WRITE)) {
-+ err = au_pin(pin, cpg.dentry, cpg.bsrc, AuOpt_UDBA_NONE,
-+ /*flags*/0);
-+ goto out;
-+ }
-+
-+ /* need to cpup or reopen */
-+ parent = dget_parent(cpg.dentry);
-+ di_write_lock_parent(parent);
-+ err = AuWbrCopyup(au_sbi(sb), cpg.dentry);
-+ cpg.bdst = err;
-+ if (unlikely(err < 0))
-+ goto out_dgrade;
-+ err = 0;
-+
-+ if (!d_unhashed(cpg.dentry) && !au_h_dptr(parent, cpg.bdst)) {
-+ err = au_cpup_dirs(cpg.dentry, cpg.bdst);
-+ if (unlikely(err))
-+ goto out_dgrade;
-+ }
-+
-+ err = au_pin(pin, cpg.dentry, cpg.bdst, AuOpt_UDBA_NONE,
-+ AuPin_DI_LOCKED | AuPin_MNT_WRITE);
-+ if (unlikely(err))
-+ goto out_dgrade;
-+
-+ dbtop = au_dbtop(cpg.dentry);
-+ if (dbtop <= cpg.bdst)
-+ cpg.bsrc = cpg.bdst;
-+
-+ if (dbtop <= cpg.bdst /* just reopen */
-+ || !d_unhashed(cpg.dentry) /* copyup and reopen */
-+ ) {
-+ h_file = au_h_open_pre(cpg.dentry, cpg.bsrc, /*force_wr*/0);
-+ if (IS_ERR(h_file))
-+ err = PTR_ERR(h_file);
-+ else {
-+ di_downgrade_lock(parent, AuLock_IR);
-+ if (dbtop > cpg.bdst)
-+ err = au_sio_cpup_simple(&cpg);
-+ if (!err)
-+ err = au_reopen_nondir(file);
-+ au_h_open_post(cpg.dentry, cpg.bsrc, h_file);
-+ }
-+ } else { /* copyup as wh and reopen */
-+ /*
-+ * since writable hfsplus branch is not supported,
-+ * h_open_pre/post() are unnecessary.
-+ */
-+ err = au_ready_to_write_wh(file, len, cpg.bdst, pin);
-+ di_downgrade_lock(parent, AuLock_IR);
-+ }
-+
-+ if (!err) {
-+ au_pin_set_parent_lflag(pin, /*lflag*/0);
-+ goto out_dput; /* success */
-+ }
-+ au_unpin(pin);
-+ goto out_unlock;
-+
-+out_dgrade:
-+ di_downgrade_lock(parent, AuLock_IR);
-+out_unlock:
-+ di_read_unlock(parent, AuLock_IR);
-+out_dput:
-+ dput(parent);
-+out:
-+ return err;
-+}
-+
-+/* ---------------------------------------------------------------------- */
-+
-+int au_do_flush(struct file *file, fl_owner_t id,
-+ int (*flush)(struct file *file, fl_owner_t id))
-+{
-+ int err;
-+ struct super_block *sb;
-+ struct inode *inode;
-+
-+ inode = file_inode(file);
-+ sb = inode->i_sb;
-+ si_noflush_read_lock(sb);
-+ fi_read_lock(file);
-+ ii_read_lock_child(inode);
-+
-+ err = flush(file, id);
-+ au_cpup_attr_timesizes(inode);
-+
-+ ii_read_unlock(inode);
-+ fi_read_unlock(file);
-+ si_read_unlock(sb);
-+ return err;
-+}
-+
-+/* ---------------------------------------------------------------------- */
-+
-+static int au_file_refresh_by_inode(struct file *file, int *need_reopen)
-+{
-+ int err;
-+ struct au_pin pin;
-+ struct au_finfo *finfo;
-+ struct dentry *parent, *hi_wh;
-+ struct inode *inode;
-+ struct super_block *sb;
-+ struct au_cp_generic cpg = {
-+ .dentry = file->f_path.dentry,
-+ .bdst = -1,
-+ .bsrc = -1,
-+ .len = -1,
-+ .pin = &pin,
-+ .flags = AuCpup_DTIME
-+ };
-+
-+ FiMustWriteLock(file);
-+
-+ err = 0;
-+ finfo = au_fi(file);
-+ sb = cpg.dentry->d_sb;
-+ inode = d_inode(cpg.dentry);
-+ cpg.bdst = au_ibtop(inode);
-+ if (cpg.bdst == finfo->fi_btop || IS_ROOT(cpg.dentry))
-+ goto out;
-+
-+ parent = dget_parent(cpg.dentry);
-+ if (au_test_ro(sb, cpg.bdst, inode)) {
-+ di_read_lock_parent(parent, !AuLock_IR);
-+ err = AuWbrCopyup(au_sbi(sb), cpg.dentry);
-+ cpg.bdst = err;
-+ di_read_unlock(parent, !AuLock_IR);
-+ if (unlikely(err < 0))
-+ goto out_parent;
-+ err = 0;
-+ }
-+
-+ di_read_lock_parent(parent, AuLock_IR);
-+ hi_wh = au_hi_wh(inode, cpg.bdst);
-+ if (!S_ISDIR(inode->i_mode)
-+ && au_opt_test(au_mntflags(sb), PLINK)
-+ && au_plink_test(inode)
-+ && !d_unhashed(cpg.dentry)
-+ && cpg.bdst < au_dbtop(cpg.dentry)) {
-+ err = au_test_and_cpup_dirs(cpg.dentry, cpg.bdst);
-+ if (unlikely(err))
-+ goto out_unlock;
-+
-+ /* always superio. */
-+ err = au_pin(&pin, cpg.dentry, cpg.bdst, AuOpt_UDBA_NONE,
-+ AuPin_DI_LOCKED | AuPin_MNT_WRITE);
-+ if (!err) {
-+ err = au_sio_cpup_simple(&cpg);
-+ au_unpin(&pin);
-+ }
-+ } else if (hi_wh) {
-+ /* already copied-up after unlink */
-+ err = au_reopen_wh(file, cpg.bdst, hi_wh);
-+ *need_reopen = 0;
-+ }
-+
-+out_unlock:
-+ di_read_unlock(parent, AuLock_IR);
-+out_parent:
-+ dput(parent);
-+out:
-+ return err;
-+}
-+
-+static void au_do_refresh_dir(struct file *file)
-+{
-+ aufs_bindex_t bindex, bbot, new_bindex, brid;
-+ struct au_hfile *p, tmp, *q;
-+ struct au_finfo *finfo;
-+ struct super_block *sb;
-+ struct au_fidir *fidir;
-+
-+ FiMustWriteLock(file);
-+
-+ sb = file->f_path.dentry->d_sb;
-+ finfo = au_fi(file);
-+ fidir = finfo->fi_hdir;
-+ AuDebugOn(!fidir);
-+ p = fidir->fd_hfile + finfo->fi_btop;
-+ brid = p->hf_br->br_id;
-+ bbot = fidir->fd_bbot;
-+ for (bindex = finfo->fi_btop; bindex <= bbot; bindex++, p++) {
-+ if (!p->hf_file)
-+ continue;
-+
-+ new_bindex = au_br_index(sb, p->hf_br->br_id);
-+ if (new_bindex == bindex)
-+ continue;
-+ if (new_bindex < 0) {
-+ au_set_h_fptr(file, bindex, NULL);
-+ continue;
-+ }
-+
-+ /* swap two lower inode, and loop again */
-+ q = fidir->fd_hfile + new_bindex;
-+ tmp = *q;
-+ *q = *p;
-+ *p = tmp;
-+ if (tmp.hf_file) {
-+ bindex--;
-+ p--;
-+ }
-+ }
-+
-+ p = fidir->fd_hfile;
-+ if (!au_test_mmapped(file) && !d_unlinked(file->f_path.dentry)) {
-+ bbot = au_sbbot(sb);
-+ for (finfo->fi_btop = 0; finfo->fi_btop <= bbot;
-+ finfo->fi_btop++, p++)
-+ if (p->hf_file) {
-+ if (file_inode(p->hf_file))
-+ break;
-+ au_hfput(p, /*execed*/0);
-+ }
-+ } else {
-+ bbot = au_br_index(sb, brid);
-+ for (finfo->fi_btop = 0; finfo->fi_btop < bbot;
-+ finfo->fi_btop++, p++)
-+ if (p->hf_file)
-+ au_hfput(p, /*execed*/0);
-+ bbot = au_sbbot(sb);
-+ }
-+
-+ p = fidir->fd_hfile + bbot;
-+ for (fidir->fd_bbot = bbot; fidir->fd_bbot >= finfo->fi_btop;
-+ fidir->fd_bbot--, p--)
-+ if (p->hf_file) {
-+ if (file_inode(p->hf_file))
-+ break;
-+ au_hfput(p, /*execed*/0);
-+ }
-+ AuDebugOn(fidir->fd_bbot < finfo->fi_btop);
-+}
-+
-+/*
-+ * after branch manipulating, refresh the file.
-+ */
-+static int refresh_file(struct file *file, int (*reopen)(struct file *file))
-+{
-+ int err, need_reopen, nbr;
-+ aufs_bindex_t bbot, bindex;
-+ struct dentry *dentry;
-+ struct super_block *sb;
-+ struct au_finfo *finfo;
-+ struct au_hfile *hfile;
-+
-+ dentry = file->f_path.dentry;
-+ sb = dentry->d_sb;
-+ nbr = au_sbbot(sb) + 1;
-+ finfo = au_fi(file);
-+ if (!finfo->fi_hdir) {
-+ hfile = &finfo->fi_htop;
-+ AuDebugOn(!hfile->hf_file);
-+ bindex = au_br_index(sb, hfile->hf_br->br_id);
-+ AuDebugOn(bindex < 0);
-+ if (bindex != finfo->fi_btop)
-+ au_set_fbtop(file, bindex);
-+ } else {
-+ err = au_fidir_realloc(finfo, nbr, /*may_shrink*/0);
-+ if (unlikely(err))
-+ goto out;
-+ au_do_refresh_dir(file);
-+ }
-+
-+ err = 0;
-+ need_reopen = 1;
-+ if (!au_test_mmapped(file))
-+ err = au_file_refresh_by_inode(file, &need_reopen);
-+ if (finfo->fi_hdir)
-+ /* harmless if err */
-+ au_fidir_realloc(finfo, nbr, /*may_shrink*/1);
-+ if (!err && need_reopen && !d_unlinked(dentry))
-+ err = reopen(file);
-+ if (!err) {
-+ au_update_figen(file);
-+ goto out; /* success */
-+ }
-+
-+ /* error, close all lower files */
-+ if (finfo->fi_hdir) {
-+ bbot = au_fbbot_dir(file);
-+ for (bindex = au_fbtop(file); bindex <= bbot; bindex++)
-+ au_set_h_fptr(file, bindex, NULL);
-+ }
-+
-+out:
-+ return err;
-+}
-+
-+/* common function to regular file and dir */
-+int au_reval_and_lock_fdi(struct file *file, int (*reopen)(struct file *file),
-+ int wlock, unsigned int fi_lsc)
-+{
-+ int err;
-+ unsigned int sigen, figen;
-+ aufs_bindex_t btop;
-+ unsigned char pseudo_link;
-+ struct dentry *dentry;
-+ struct inode *inode;
-+
-+ err = 0;
-+ dentry = file->f_path.dentry;
-+ inode = d_inode(dentry);
-+ sigen = au_sigen(dentry->d_sb);
-+ fi_write_lock_nested(file, fi_lsc);
-+ figen = au_figen(file);
-+ if (!fi_lsc)
-+ di_write_lock_child(dentry);
-+ else
-+ di_write_lock_child2(dentry);
-+ btop = au_dbtop(dentry);
-+ pseudo_link = (btop != au_ibtop(inode));
-+ if (sigen == figen && !pseudo_link && au_fbtop(file) == btop) {
-+ if (!wlock) {
-+ di_downgrade_lock(dentry, AuLock_IR);
-+ fi_downgrade_lock(file);
-+ }
-+ goto out; /* success */
-+ }
-+
-+ AuDbg("sigen %d, figen %d\n", sigen, figen);
-+ if (au_digen_test(dentry, sigen)) {
-+ err = au_reval_dpath(dentry, sigen);
-+ AuDebugOn(!err && au_digen_test(dentry, sigen));
-+ }
-+
-+ if (!err)
-+ err = refresh_file(file, reopen);
-+ if (!err) {
-+ if (!wlock) {
-+ di_downgrade_lock(dentry, AuLock_IR);
-+ fi_downgrade_lock(file);
-+ }
-+ } else {
-+ di_write_unlock(dentry);
-+ fi_write_unlock(file);
-+ }
-+
-+out:
-+ return err;
-+}
-+
-+/* ---------------------------------------------------------------------- */
-+
-+/* cf. aufs_nopage() */
-+/* for madvise(2) */
-+static int aufs_readpage(struct file *file __maybe_unused, struct page *page)
-+{
-+ unlock_page(page);
-+ return 0;
-+}
-+
-+/* it will never be called, but necessary to support O_DIRECT */
-+static ssize_t aufs_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
-+{ BUG(); return 0; }
-+
-+/* they will never be called. */
-+#ifdef CONFIG_AUFS_DEBUG
-+static int aufs_write_begin(struct file *file, struct address_space *mapping,
-+ loff_t pos, unsigned len, unsigned flags,
-+ struct page **pagep, void **fsdata)
-+{ AuUnsupport(); return 0; }
-+static int aufs_write_end(struct file *file, struct address_space *mapping,
-+ loff_t pos, unsigned len, unsigned copied,
-+ struct page *page, void *fsdata)
-+{ AuUnsupport(); return 0; }
-+static int aufs_writepage(struct page *page, struct writeback_control *wbc)
-+{ AuUnsupport(); return 0; }
-+
-+static int aufs_set_page_dirty(struct page *page)
-+{ AuUnsupport(); return 0; }
-+static void aufs_invalidatepage(struct page *page, unsigned int offset,
-+ unsigned int length)
-+{ AuUnsupport(); }
-+static int aufs_releasepage(struct page *page, gfp_t gfp)
-+{ AuUnsupport(); return 0; }
-+#if 0 /* called by memory compaction regardless file */
-+static int aufs_migratepage(struct address_space *mapping, struct page *newpage,
-+ struct page *page, enum migrate_mode mode)
-+{ AuUnsupport(); return 0; }
-+#endif
-+static bool aufs_isolate_page(struct page *page, isolate_mode_t mode)
-+{ AuUnsupport(); return true; }
-+static void aufs_putback_page(struct page *page)
-+{ AuUnsupport(); }
-+static int aufs_launder_page(struct page *page)
-+{ AuUnsupport(); return 0; }
-+static int aufs_is_partially_uptodate(struct page *page,
-+ unsigned long from,
-+ unsigned long count)
-+{ AuUnsupport(); return 0; }
-+static void aufs_is_dirty_writeback(struct page *page, bool *dirty,
-+ bool *writeback)
-+{ AuUnsupport(); }
-+static int aufs_error_remove_page(struct address_space *mapping,
-+ struct page *page)
-+{ AuUnsupport(); return 0; }
-+static int aufs_swap_activate(struct swap_info_struct *sis, struct file *file,
-+ sector_t *span)
-+{ AuUnsupport(); return 0; }
-+static void aufs_swap_deactivate(struct file *file)
-+{ AuUnsupport(); }
-+#endif /* CONFIG_AUFS_DEBUG */
-+
-+const struct address_space_operations aufs_aop = {
-+ .readpage = aufs_readpage,
-+ .direct_IO = aufs_direct_IO,
-+#ifdef CONFIG_AUFS_DEBUG
-+ .writepage = aufs_writepage,
-+ /* no writepages, because of writepage */
-+ .set_page_dirty = aufs_set_page_dirty,
-+ /* no readpages, because of readpage */
-+ .write_begin = aufs_write_begin,
-+ .write_end = aufs_write_end,
-+ /* no bmap, no block device */
-+ .invalidatepage = aufs_invalidatepage,
-+ .releasepage = aufs_releasepage,
-+ /* is fallback_migrate_page ok? */
-+ /* .migratepage = aufs_migratepage, */
-+ .isolate_page = aufs_isolate_page,
-+ .putback_page = aufs_putback_page,
-+ .launder_page = aufs_launder_page,
-+ .is_partially_uptodate = aufs_is_partially_uptodate,
-+ .is_dirty_writeback = aufs_is_dirty_writeback,
-+ .error_remove_page = aufs_error_remove_page,
-+ .swap_activate = aufs_swap_activate,
-+ .swap_deactivate = aufs_swap_deactivate
-+#endif /* CONFIG_AUFS_DEBUG */
-+};
-diff --git a/fs/aufs/file.h b/fs/aufs/file.h
-new file mode 100644
-index 000000000000..c679a19df528
---- /dev/null
-+++ b/fs/aufs/file.h
-@@ -0,0 +1,342 @@
-+/* SPDX-License-Identifier: GPL-2.0 */
-+/*
-+ * Copyright (C) 2005-2019 Junjiro R. Okajima
-+ *
-+ * This program, aufs is free software; you can redistribute it and/or modify
-+ * it under the terms of the GNU General Public License as published by
-+ * the Free Software Foundation; either version 2 of the License, or
-+ * (at your option) any later version.
-+ *
-+ * This program is distributed in the hope that it will be useful,
-+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
-+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
-+ * GNU General Public License for more details.
-+ *
-+ * You should have received a copy of the GNU General Public License
-+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
-+ */
-+
-+/*
-+ * file operations
-+ */
-+
-+#ifndef __AUFS_FILE_H__
-+#define __AUFS_FILE_H__
-+
-+#ifdef __KERNEL__
-+
-+#include <linux/file.h>
-+#include <linux/fs.h>
-+#include <linux/mm_types.h>
-+#include <linux/poll.h>
-+#include "rwsem.h"
-+
-+struct au_branch;
-+struct au_hfile {
-+ struct file *hf_file;
-+ struct au_branch *hf_br;
-+};
-+
-+struct au_vdir;
-+struct au_fidir {
-+ aufs_bindex_t fd_bbot;
-+ aufs_bindex_t fd_nent;
-+ struct au_vdir *fd_vdir_cache;
-+ struct au_hfile fd_hfile[];
-+};
-+
-+static inline int au_fidir_sz(int nent)
-+{
-+ AuDebugOn(nent < 0);
-+ return sizeof(struct au_fidir) + sizeof(struct au_hfile) * nent;
-+}
-+
-+struct au_finfo {
-+ atomic_t fi_generation;
-+
-+ struct au_rwsem fi_rwsem;
-+ aufs_bindex_t fi_btop;
-+
-+ /* do not union them */
-+ struct { /* for non-dir */
-+ struct au_hfile fi_htop;
-+ atomic_t fi_mmapped;
-+ };
-+ struct au_fidir *fi_hdir; /* for dir only */
-+
-+ struct hlist_bl_node fi_hlist;
-+ struct file *fi_file; /* very ugly */
-+ struct rcu_head rcu;
-+} ____cacheline_aligned_in_smp;
-+
-+/* ---------------------------------------------------------------------- */
-+
-+/* file.c */
-+extern const struct address_space_operations aufs_aop;
-+unsigned int au_file_roflags(unsigned int flags);
-+struct file *au_h_open(struct dentry *dentry, aufs_bindex_t bindex, int flags,
-+ struct file *file, int force_wr);
-+struct au_do_open_args {
-+ int aopen;
-+ int (*open)(struct file *file, int flags,
-+ struct file *h_file);
-+ struct au_fidir *fidir;
-+ struct file *h_file;
-+};
-+int au_do_open(struct file *file, struct au_do_open_args *args);
-+int au_reopen_nondir(struct file *file);
-+struct au_pin;
-+int au_ready_to_write(struct file *file, loff_t len, struct au_pin *pin);
-+int au_reval_and_lock_fdi(struct file *file, int (*reopen)(struct file *file),
-+ int wlock, unsigned int fi_lsc);
-+int au_do_flush(struct file *file, fl_owner_t id,
-+ int (*flush)(struct file *file, fl_owner_t id));
-+
-+/* poll.c */
-+#ifdef CONFIG_AUFS_POLL
-+__poll_t aufs_poll(struct file *file, struct poll_table_struct *pt);
-+#endif
-+
-+#ifdef CONFIG_AUFS_BR_HFSPLUS
-+/* hfsplus.c */
-+struct file *au_h_open_pre(struct dentry *dentry, aufs_bindex_t bindex,
-+ int force_wr);
-+void au_h_open_post(struct dentry *dentry, aufs_bindex_t bindex,
-+ struct file *h_file);
-+#else
-+AuStub(struct file *, au_h_open_pre, return NULL, struct dentry *dentry,
-+ aufs_bindex_t bindex, int force_wr)
-+AuStubVoid(au_h_open_post, struct dentry *dentry, aufs_bindex_t bindex,
-+ struct file *h_file);
-+#endif
-+
-+/* f_op.c */
-+extern const struct file_operations aufs_file_fop;
-+int au_do_open_nondir(struct file *file, int flags, struct file *h_file);
-+int aufs_release_nondir(struct inode *inode __maybe_unused, struct file *file);
-+struct file *au_read_pre(struct file *file, int keep_fi, unsigned int lsc);
-+
-+/* finfo.c */
-+void au_hfput(struct au_hfile *hf, int execed);
-+void au_set_h_fptr(struct file *file, aufs_bindex_t bindex,
-+ struct file *h_file);
-+
-+void au_update_figen(struct file *file);
-+struct au_fidir *au_fidir_alloc(struct super_block *sb);
-+int au_fidir_realloc(struct au_finfo *finfo, int nbr, int may_shrink);
-+
-+void au_fi_init_once(void *_fi);
-+void au_finfo_fin(struct file *file);
-+int au_finfo_init(struct file *file, struct au_fidir *fidir);
-+
-+/* ioctl.c */
-+long aufs_ioctl_nondir(struct file *file, unsigned int cmd, unsigned long arg);
-+#ifdef CONFIG_COMPAT
-+long aufs_compat_ioctl_dir(struct file *file, unsigned int cmd,
-+ unsigned long arg);
-+long aufs_compat_ioctl_nondir(struct file *file, unsigned int cmd,
-+ unsigned long arg);
-+#endif
-+
-+/* ---------------------------------------------------------------------- */
-+
-+static inline struct au_finfo *au_fi(struct file *file)
-+{
-+ return file->private_data;
-+}
-+
-+/* ---------------------------------------------------------------------- */
-+
-+#define fi_read_lock(f) au_rw_read_lock(&au_fi(f)->fi_rwsem)
-+#define fi_write_lock(f) au_rw_write_lock(&au_fi(f)->fi_rwsem)
-+#define fi_read_trylock(f) au_rw_read_trylock(&au_fi(f)->fi_rwsem)
-+#define fi_write_trylock(f) au_rw_write_trylock(&au_fi(f)->fi_rwsem)
-+/*
-+#define fi_read_trylock_nested(f) \
-+ au_rw_read_trylock_nested(&au_fi(f)->fi_rwsem)
-+#define fi_write_trylock_nested(f) \
-+ au_rw_write_trylock_nested(&au_fi(f)->fi_rwsem)
-+*/
-+
-+#define fi_read_unlock(f) au_rw_read_unlock(&au_fi(f)->fi_rwsem)
-+#define fi_write_unlock(f) au_rw_write_unlock(&au_fi(f)->fi_rwsem)
-+#define fi_downgrade_lock(f) au_rw_dgrade_lock(&au_fi(f)->fi_rwsem)
-+
-+/* lock subclass for finfo */
-+enum {
-+ AuLsc_FI_1,
-+ AuLsc_FI_2
-+};
-+
-+static inline void fi_read_lock_nested(struct file *f, unsigned int lsc)
-+{
-+ au_rw_read_lock_nested(&au_fi(f)->fi_rwsem, lsc);
-+}
-+
-+static inline void fi_write_lock_nested(struct file *f, unsigned int lsc)
-+{
-+ au_rw_write_lock_nested(&au_fi(f)->fi_rwsem, lsc);
-+}
-+
-+/*
-+ * fi_read_lock_1, fi_write_lock_1,
-+ * fi_read_lock_2, fi_write_lock_2
-+ */
-+#define AuReadLockFunc(name) \
-+static inline void fi_read_lock_##name(struct file *f) \
-+{ fi_read_lock_nested(f, AuLsc_FI_##name); }
-+
-+#define AuWriteLockFunc(name) \
-+static inline void fi_write_lock_##name(struct file *f) \
-+{ fi_write_lock_nested(f, AuLsc_FI_##name); }
-+
-+#define AuRWLockFuncs(name) \
-+ AuReadLockFunc(name) \
-+ AuWriteLockFunc(name)
-+
-+AuRWLockFuncs(1);
-+AuRWLockFuncs(2);
-+
-+#undef AuReadLockFunc
-+#undef AuWriteLockFunc
-+#undef AuRWLockFuncs
-+
-+#define FiMustNoWaiters(f) AuRwMustNoWaiters(&au_fi(f)->fi_rwsem)
-+#define FiMustAnyLock(f) AuRwMustAnyLock(&au_fi(f)->fi_rwsem)
-+#define FiMustWriteLock(f) AuRwMustWriteLock(&au_fi(f)->fi_rwsem)
-+
-+/* ---------------------------------------------------------------------- */
-+
-+/* todo: hard/soft set? */
-+static inline aufs_bindex_t au_fbtop(struct file *file)
-+{
-+ FiMustAnyLock(file);
-+ return au_fi(file)->fi_btop;
-+}
-+
-+static inline aufs_bindex_t au_fbbot_dir(struct file *file)
-+{
-+ FiMustAnyLock(file);
-+ AuDebugOn(!au_fi(file)->fi_hdir);
-+ return au_fi(file)->fi_hdir->fd_bbot;
-+}
-+
-+static inline struct au_vdir *au_fvdir_cache(struct file *file)
-+{
-+ FiMustAnyLock(file);
-+ AuDebugOn(!au_fi(file)->fi_hdir);
-+ return au_fi(file)->fi_hdir->fd_vdir_cache;
-+}
-+
-+static inline void au_set_fbtop(struct file *file, aufs_bindex_t bindex)
-+{
-+ FiMustWriteLock(file);
-+ au_fi(file)->fi_btop = bindex;
-+}
-+
-+static inline void au_set_fbbot_dir(struct file *file, aufs_bindex_t bindex)
-+{
-+ FiMustWriteLock(file);
-+ AuDebugOn(!au_fi(file)->fi_hdir);
-+ au_fi(file)->fi_hdir->fd_bbot = bindex;
-+}
-+
-+static inline void au_set_fvdir_cache(struct file *file,
-+ struct au_vdir *vdir_cache)
-+{
-+ FiMustWriteLock(file);
-+ AuDebugOn(!au_fi(file)->fi_hdir);
-+ au_fi(file)->fi_hdir->fd_vdir_cache = vdir_cache;
-+}
-+
-+static inline struct file *au_hf_top(struct file *file)
-+{
-+ FiMustAnyLock(file);
-+ AuDebugOn(au_fi(file)->fi_hdir);
-+ return au_fi(file)->fi_htop.hf_file;
-+}
-+
-+static inline struct file *au_hf_dir(struct file *file, aufs_bindex_t bindex)
-+{
-+ FiMustAnyLock(file);
-+ AuDebugOn(!au_fi(file)->fi_hdir);
-+ return au_fi(file)->fi_hdir->fd_hfile[0 + bindex].hf_file;
-+}
-+
-+/* todo: memory barrier? */
-+static inline unsigned int au_figen(struct file *f)
-+{
-+ return atomic_read(&au_fi(f)->fi_generation);
-+}
-+
-+static inline void au_set_mmapped(struct file *f)
-+{
-+ if (atomic_inc_return(&au_fi(f)->fi_mmapped))
-+ return;
-+ pr_warn("fi_mmapped wrapped around\n");
-+ while (!atomic_inc_return(&au_fi(f)->fi_mmapped))
-+ ;
-+}
-+
-+static inline void au_unset_mmapped(struct file *f)
-+{
-+ atomic_dec(&au_fi(f)->fi_mmapped);
-+}
-+
-+static inline int au_test_mmapped(struct file *f)
-+{
-+ return atomic_read(&au_fi(f)->fi_mmapped);
-+}
-+
-+/* customize vma->vm_file */
-+
-+static inline void au_do_vm_file_reset(struct vm_area_struct *vma,
-+ struct file *file)
-+{
-+ struct file *f;
-+
-+ f = vma->vm_file;
-+ get_file(file);
-+ vma->vm_file = file;
-+ fput(f);
-+}
-+
-+#ifdef CONFIG_MMU
-+#define AuDbgVmRegion(file, vma) do {} while (0)
-+
-+static inline void au_vm_file_reset(struct vm_area_struct *vma,
-+ struct file *file)
-+{
-+ au_do_vm_file_reset(vma, file);
-+}
-+#else
-+#define AuDbgVmRegion(file, vma) \
-+ AuDebugOn((vma)->vm_region && (vma)->vm_region->vm_file != (file))
-+
-+static inline void au_vm_file_reset(struct vm_area_struct *vma,
-+ struct file *file)
-+{
-+ struct file *f;
-+
-+ au_do_vm_file_reset(vma, file);
-+ f = vma->vm_region->vm_file;
-+ get_file(file);
-+ vma->vm_region->vm_file = file;
-+ fput(f);
-+}
-+#endif /* CONFIG_MMU */
-+
-+/* handle vma->vm_prfile */
-+static inline void au_vm_prfile_set(struct vm_area_struct *vma,
-+ struct file *file)
-+{
-+ get_file(file);
-+ vma->vm_prfile = file;
-+#ifndef CONFIG_MMU
-+ get_file(file);
-+ vma->vm_region->vm_prfile = file;
-+#endif
-+}
-+
-+#endif /* __KERNEL__ */
-+#endif /* __AUFS_FILE_H__ */
-diff --git a/fs/aufs/finfo.c b/fs/aufs/finfo.c
-new file mode 100644
-index 000000000000..448c5e9cd85d
---- /dev/null
-+++ b/fs/aufs/finfo.c
-@@ -0,0 +1,149 @@
-+// SPDX-License-Identifier: GPL-2.0
-+/*
-+ * Copyright (C) 2005-2019 Junjiro R. Okajima
-+ *
-+ * This program, aufs is free software; you can redistribute it and/or modify
-+ * it under the terms of the GNU General Public License as published by
-+ * the Free Software Foundation; either version 2 of the License, or
-+ * (at your option) any later version.
-+ *
-+ * This program is distributed in the hope that it will be useful,
-+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
-+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
-+ * GNU General Public License for more details.
-+ *
-+ * You should have received a copy of the GNU General Public License
-+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
-+ */
-+
-+/*
-+ * file private data
-+ */
-+
-+#include "aufs.h"
-+
-+void au_hfput(struct au_hfile *hf, int execed)
-+{
-+ if (execed)
-+ allow_write_access(hf->hf_file);
-+ fput(hf->hf_file);
-+ hf->hf_file = NULL;
-+ au_lcnt_dec(&hf->hf_br->br_nfiles);
-+ hf->hf_br = NULL;
-+}
-+
-+void au_set_h_fptr(struct file *file, aufs_bindex_t bindex, struct file *val)
-+{
-+ struct au_finfo *finfo = au_fi(file);
-+ struct au_hfile *hf;
-+ struct au_fidir *fidir;
-+
-+ fidir = finfo->fi_hdir;
-+ if (!fidir) {
-+ AuDebugOn(finfo->fi_btop != bindex);
-+ hf = &finfo->fi_htop;
-+ } else
-+ hf = fidir->fd_hfile + bindex;
-+
-+ if (hf && hf->hf_file)
-+ au_hfput(hf, vfsub_file_execed(file));
-+ if (val) {
-+ FiMustWriteLock(file);
-+ AuDebugOn(IS_ERR_OR_NULL(file->f_path.dentry));
-+ hf->hf_file = val;
-+ hf->hf_br = au_sbr(file->f_path.dentry->d_sb, bindex);
-+ }
-+}
-+
-+void au_update_figen(struct file *file)
-+{
-+ atomic_set(&au_fi(file)->fi_generation, au_digen(file->f_path.dentry));
-+ /* smp_mb(); */ /* atomic_set */
-+}
-+
-+/* ---------------------------------------------------------------------- */
-+
-+struct au_fidir *au_fidir_alloc(struct super_block *sb)
-+{
-+ struct au_fidir *fidir;
-+ int nbr;
-+
-+ nbr = au_sbbot(sb) + 1;
-+ if (nbr < 2)
-+ nbr = 2; /* initial allocate for 2 branches */
-+ fidir = kzalloc(au_fidir_sz(nbr), GFP_NOFS);
-+ if (fidir) {
-+ fidir->fd_bbot = -1;
-+ fidir->fd_nent = nbr;
-+ }
-+
-+ return fidir;
-+}
-+
-+int au_fidir_realloc(struct au_finfo *finfo, int nbr, int may_shrink)
-+{
-+ int err;
-+ struct au_fidir *fidir, *p;
-+
-+ AuRwMustWriteLock(&finfo->fi_rwsem);
-+ fidir = finfo->fi_hdir;
-+ AuDebugOn(!fidir);
-+
-+ err = -ENOMEM;
-+ p = au_kzrealloc(fidir, au_fidir_sz(fidir->fd_nent), au_fidir_sz(nbr),
-+ GFP_NOFS, may_shrink);
-+ if (p) {
-+ p->fd_nent = nbr;
-+ finfo->fi_hdir = p;
-+ err = 0;
-+ }
-+
-+ return err;
-+}
-+
-+/* ---------------------------------------------------------------------- */
-+
-+void au_finfo_fin(struct file *file)
-+{
-+ struct au_finfo *finfo;
-+
-+ au_lcnt_dec(&au_sbi(file->f_path.dentry->d_sb)->si_nfiles);
-+
-+ finfo = au_fi(file);
-+ AuDebugOn(finfo->fi_hdir);
-+ AuRwDestroy(&finfo->fi_rwsem);
-+ au_cache_free_finfo(finfo);
-+}
-+
-+void au_fi_init_once(void *_finfo)
-+{
-+ struct au_finfo *finfo = _finfo;
-+
-+ au_rw_init(&finfo->fi_rwsem);
-+}
-+
-+int au_finfo_init(struct file *file, struct au_fidir *fidir)
-+{
-+ int err;
-+ struct au_finfo *finfo;
-+ struct dentry *dentry;
-+
-+ err = -ENOMEM;
-+ dentry = file->f_path.dentry;
-+ finfo = au_cache_alloc_finfo();
-+ if (unlikely(!finfo))
-+ goto out;
-+
-+ err = 0;
-+ au_lcnt_inc(&au_sbi(dentry->d_sb)->si_nfiles);
-+ au_rw_write_lock(&finfo->fi_rwsem);
-+ finfo->fi_btop = -1;
-+ finfo->fi_hdir = fidir;
-+ atomic_set(&finfo->fi_generation, au_digen(dentry));
-+ /* smp_mb(); */ /* atomic_set */
-+
-+ file->private_data = finfo;
-+
-+out:
-+ return err;
-+}
-diff --git a/fs/aufs/fstype.h b/fs/aufs/fstype.h
-new file mode 100644
-index 000000000000..510bd87e9404
---- /dev/null
-+++ b/fs/aufs/fstype.h
-@@ -0,0 +1,401 @@
-+/* SPDX-License-Identifier: GPL-2.0 */
-+/*
-+ * Copyright (C) 2005-2019 Junjiro R. Okajima
-+ *
-+ * This program, aufs is free software; you can redistribute it and/or modify
-+ * it under the terms of the GNU General Public License as published by
-+ * the Free Software Foundation; either version 2 of the License, or
-+ * (at your option) any later version.
-+ *
-+ * This program is distributed in the hope that it will be useful,
-+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
-+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
-+ * GNU General Public License for more details.
-+ *
-+ * You should have received a copy of the GNU General Public License
-+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
-+ */
-+
-+/*
-+ * judging filesystem type
-+ */
-+
-+#ifndef __AUFS_FSTYPE_H__
-+#define __AUFS_FSTYPE_H__
-+
-+#ifdef __KERNEL__
-+
-+#include <linux/fs.h>
-+#include <linux/magic.h>
-+#include <linux/nfs_fs.h>
-+#include <linux/romfs_fs.h>
-+
-+static inline int au_test_aufs(struct super_block *sb)
-+{
-+ return sb->s_magic == AUFS_SUPER_MAGIC;
-+}
-+
-+static inline const char *au_sbtype(struct super_block *sb)
-+{
-+ return sb->s_type->name;
-+}
-+
-+static inline int au_test_iso9660(struct super_block *sb __maybe_unused)
-+{
-+#if IS_ENABLED(CONFIG_ISO9660_FS)
-+ return sb->s_magic == ISOFS_SUPER_MAGIC;
-+#else
-+ return 0;
-+#endif
-+}
-+
-+static inline int au_test_romfs(struct super_block *sb __maybe_unused)
-+{
-+#if IS_ENABLED(CONFIG_ROMFS_FS)
-+ return sb->s_magic == ROMFS_MAGIC;
-+#else
-+ return 0;
-+#endif
-+}
-+
-+static inline int au_test_cramfs(struct super_block *sb __maybe_unused)
-+{
-+#if IS_ENABLED(CONFIG_CRAMFS)
-+ return sb->s_magic == CRAMFS_MAGIC;
-+#endif
-+ return 0;
-+}
-+
-+static inline int au_test_nfs(struct super_block *sb __maybe_unused)
-+{
-+#if IS_ENABLED(CONFIG_NFS_FS)
-+ return sb->s_magic == NFS_SUPER_MAGIC;
-+#else
-+ return 0;
-+#endif
-+}
-+
-+static inline int au_test_fuse(struct super_block *sb __maybe_unused)
-+{
-+#if IS_ENABLED(CONFIG_FUSE_FS)
-+ return sb->s_magic == FUSE_SUPER_MAGIC;
-+#else
-+ return 0;
-+#endif
-+}
-+
-+static inline int au_test_xfs(struct super_block *sb __maybe_unused)
-+{
-+#if IS_ENABLED(CONFIG_XFS_FS)
-+ return sb->s_magic == XFS_SB_MAGIC;
-+#else
-+ return 0;
-+#endif
-+}
-+
-+static inline int au_test_tmpfs(struct super_block *sb __maybe_unused)
-+{
-+#ifdef CONFIG_TMPFS
-+ return sb->s_magic == TMPFS_MAGIC;
-+#else
-+ return 0;
-+#endif
-+}
-+
-+static inline int au_test_ecryptfs(struct super_block *sb __maybe_unused)
-+{
-+#if IS_ENABLED(CONFIG_ECRYPT_FS)
-+ return !strcmp(au_sbtype(sb), "ecryptfs");
-+#else
-+ return 0;
-+#endif
-+}
-+
-+static inline int au_test_ramfs(struct super_block *sb)
-+{
-+ return sb->s_magic == RAMFS_MAGIC;
-+}
-+
-+static inline int au_test_ubifs(struct super_block *sb __maybe_unused)
-+{
-+#if IS_ENABLED(CONFIG_UBIFS_FS)
-+ return sb->s_magic == UBIFS_SUPER_MAGIC;
-+#else
-+ return 0;
-+#endif
-+}
-+
-+static inline int au_test_procfs(struct super_block *sb __maybe_unused)
-+{
-+#ifdef CONFIG_PROC_FS
-+ return sb->s_magic == PROC_SUPER_MAGIC;
-+#else
-+ return 0;
-+#endif
-+}
-+
-+static inline int au_test_sysfs(struct super_block *sb __maybe_unused)
-+{
-+#ifdef CONFIG_SYSFS
-+ return sb->s_magic == SYSFS_MAGIC;
-+#else
-+ return 0;
-+#endif
-+}
-+
-+static inline int au_test_configfs(struct super_block *sb __maybe_unused)
-+{
-+#if IS_ENABLED(CONFIG_CONFIGFS_FS)
-+ return sb->s_magic == CONFIGFS_MAGIC;
-+#else
-+ return 0;
-+#endif
-+}
-+
-+static inline int au_test_minix(struct super_block *sb __maybe_unused)
-+{
-+#if IS_ENABLED(CONFIG_MINIX_FS)
-+ return sb->s_magic == MINIX3_SUPER_MAGIC
-+ || sb->s_magic == MINIX2_SUPER_MAGIC
-+ || sb->s_magic == MINIX2_SUPER_MAGIC2
-+ || sb->s_magic == MINIX_SUPER_MAGIC
-+ || sb->s_magic == MINIX_SUPER_MAGIC2;
-+#else
-+ return 0;
-+#endif
-+}
-+
-+static inline int au_test_fat(struct super_block *sb __maybe_unused)
-+{
-+#if IS_ENABLED(CONFIG_FAT_FS)
-+ return sb->s_magic == MSDOS_SUPER_MAGIC;
-+#else
-+ return 0;
-+#endif
-+}
-+
-+static inline int au_test_msdos(struct super_block *sb)
-+{
-+ return au_test_fat(sb);
-+}
-+
-+static inline int au_test_vfat(struct super_block *sb)
-+{
-+ return au_test_fat(sb);
-+}
-+
-+static inline int au_test_securityfs(struct super_block *sb __maybe_unused)
-+{
-+#ifdef CONFIG_SECURITYFS
-+ return sb->s_magic == SECURITYFS_MAGIC;
-+#else
-+ return 0;
-+#endif
-+}
-+
-+static inline int au_test_squashfs(struct super_block *sb __maybe_unused)
-+{
-+#if IS_ENABLED(CONFIG_SQUASHFS)
-+ return sb->s_magic == SQUASHFS_MAGIC;
-+#else
-+ return 0;
-+#endif
-+}
-+
-+static inline int au_test_btrfs(struct super_block *sb __maybe_unused)
-+{
-+#if IS_ENABLED(CONFIG_BTRFS_FS)
-+ return sb->s_magic == BTRFS_SUPER_MAGIC;
-+#else
-+ return 0;
-+#endif
-+}
-+
-+static inline int au_test_xenfs(struct super_block *sb __maybe_unused)
-+{
-+#if IS_ENABLED(CONFIG_XENFS)
-+ return sb->s_magic == XENFS_SUPER_MAGIC;
-+#else
-+ return 0;
-+#endif
-+}
-+
-+static inline int au_test_debugfs(struct super_block *sb __maybe_unused)
-+{
-+#ifdef CONFIG_DEBUG_FS
-+ return sb->s_magic == DEBUGFS_MAGIC;
-+#else
-+ return 0;
-+#endif
-+}
-+
-+static inline int au_test_nilfs(struct super_block *sb __maybe_unused)
-+{
-+#if IS_ENABLED(CONFIG_NILFS)
-+ return sb->s_magic == NILFS_SUPER_MAGIC;
-+#else
-+ return 0;
-+#endif
-+}
-+
-+static inline int au_test_hfsplus(struct super_block *sb __maybe_unused)
-+{
-+#if IS_ENABLED(CONFIG_HFSPLUS_FS)
-+ return sb->s_magic == HFSPLUS_SUPER_MAGIC;
-+#else
-+ return 0;
-+#endif
-+}
-+
-+/* ---------------------------------------------------------------------- */
-+/*
-+ * they can't be an aufs branch.
-+ */
-+static inline int au_test_fs_unsuppoted(struct super_block *sb)
-+{
-+ return
-+#ifndef CONFIG_AUFS_BR_RAMFS
-+ au_test_ramfs(sb) ||
-+#endif
-+ au_test_procfs(sb)
-+ || au_test_sysfs(sb)
-+ || au_test_configfs(sb)
-+ || au_test_debugfs(sb)
-+ || au_test_securityfs(sb)
-+ || au_test_xenfs(sb)
-+ || au_test_ecryptfs(sb)
-+ /* || !strcmp(au_sbtype(sb), "unionfs") */
-+ || au_test_aufs(sb); /* will be supported in next version */
-+}
-+
-+static inline int au_test_fs_remote(struct super_block *sb)
-+{
-+ return !au_test_tmpfs(sb)
-+#ifdef CONFIG_AUFS_BR_RAMFS
-+ && !au_test_ramfs(sb)
-+#endif
-+ && !(sb->s_type->fs_flags & FS_REQUIRES_DEV);
-+}
-+
-+/* ---------------------------------------------------------------------- */
-+
-+/*
-+ * Note: these functions (below) are created after reading ->getattr() in all
-+ * filesystems under linux/fs. it means we have to do so in every update...
-+ */
-+
-+/*
-+ * some filesystems require getattr to refresh the inode attributes before
-+ * referencing.
-+ * in most cases, we can rely on the inode attribute in NFS (or every remote fs)
-+ * and leave the work for d_revalidate()
-+ */
-+static inline int au_test_fs_refresh_iattr(struct super_block *sb)
-+{
-+ return au_test_nfs(sb)
-+ || au_test_fuse(sb)
-+ /* || au_test_btrfs(sb) */ /* untested */
-+ ;
-+}
-+
-+/*
-+ * filesystems which don't maintain i_size or i_blocks.
-+ */
-+static inline int au_test_fs_bad_iattr_size(struct super_block *sb)
-+{
-+ return au_test_xfs(sb)
-+ || au_test_btrfs(sb)
-+ || au_test_ubifs(sb)
-+ || au_test_hfsplus(sb) /* maintained, but incorrect */
-+ /* || au_test_minix(sb) */ /* untested */
-+ ;
-+}
-+
-+/*
-+ * filesystems which don't store the correct value in some of their inode
-+ * attributes.
-+ */
-+static inline int au_test_fs_bad_iattr(struct super_block *sb)
-+{
-+ return au_test_fs_bad_iattr_size(sb)
-+ || au_test_fat(sb)
-+ || au_test_msdos(sb)
-+ || au_test_vfat(sb);
-+}
-+
-+/* they don't check i_nlink in link(2) */
-+static inline int au_test_fs_no_limit_nlink(struct super_block *sb)
-+{
-+ return au_test_tmpfs(sb)
-+#ifdef CONFIG_AUFS_BR_RAMFS
-+ || au_test_ramfs(sb)
-+#endif
-+ || au_test_ubifs(sb)
-+ || au_test_hfsplus(sb);
-+}
-+
-+/*
-+ * filesystems which sets S_NOATIME and S_NOCMTIME.
-+ */
-+static inline int au_test_fs_notime(struct super_block *sb)
-+{
-+ return au_test_nfs(sb)
-+ || au_test_fuse(sb)
-+ || au_test_ubifs(sb)
-+ ;
-+}
-+
-+/* temporary support for i#1 in cramfs */
-+static inline int au_test_fs_unique_ino(struct inode *inode)
-+{
-+ if (au_test_cramfs(inode->i_sb))
-+ return inode->i_ino != 1;
-+ return 1;
-+}
-+
-+/* ---------------------------------------------------------------------- */
-+
-+/*
-+ * the filesystem where the xino files placed must support i/o after unlink and
-+ * maintain i_size and i_blocks.
-+ */
-+static inline int au_test_fs_bad_xino(struct super_block *sb)
-+{
-+ return au_test_fs_remote(sb)
-+ || au_test_fs_bad_iattr_size(sb)
-+ /* don't want unnecessary work for xino */
-+ || au_test_aufs(sb)
-+ || au_test_ecryptfs(sb)
-+ || au_test_nilfs(sb);
-+}
-+
-+static inline int au_test_fs_trunc_xino(struct super_block *sb)
-+{
-+ return au_test_tmpfs(sb)
-+ || au_test_ramfs(sb);
-+}
-+
-+/*
-+ * test if the @sb is real-readonly.
-+ */
-+static inline int au_test_fs_rr(struct super_block *sb)
-+{
-+ return au_test_squashfs(sb)
-+ || au_test_iso9660(sb)
-+ || au_test_cramfs(sb)
-+ || au_test_romfs(sb);
-+}
-+
-+/*
-+ * test if the @inode is nfs with 'noacl' option
-+ * NFS always sets SB_POSIXACL regardless its mount option 'noacl.'
-+ */
-+static inline int au_test_nfs_noacl(struct inode *inode)
-+{
-+ return au_test_nfs(inode->i_sb)
-+ /* && IS_POSIXACL(inode) */
-+ && !nfs_server_capable(inode, NFS_CAP_ACLS);
-+}
-+
-+#endif /* __KERNEL__ */
-+#endif /* __AUFS_FSTYPE_H__ */
-diff --git a/fs/aufs/hbl.h b/fs/aufs/hbl.h
-new file mode 100644
-index 000000000000..6db65b16b08a
---- /dev/null
-+++ b/fs/aufs/hbl.h
-@@ -0,0 +1,65 @@
-+/* SPDX-License-Identifier: GPL-2.0 */
-+/*
-+ * Copyright (C) 2017-2019 Junjiro R. Okajima
-+ *
-+ * This program, aufs is free software; you can redistribute it and/or modify
-+ * it under the terms of the GNU General Public License as published by
-+ * the Free Software Foundation; either version 2 of the License, or
-+ * (at your option) any later version.
-+ *
-+ * This program is distributed in the hope that it will be useful,
-+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
-+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
-+ * GNU General Public License for more details.
-+ *
-+ * You should have received a copy of the GNU General Public License
-+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
-+ */
-+
-+/*
-+ * helpers for hlist_bl.h
-+ */
-+
-+#ifndef __AUFS_HBL_H__
-+#define __AUFS_HBL_H__
-+
-+#ifdef __KERNEL__
-+
-+#include <linux/list_bl.h>
-+
-+static inline void au_hbl_add(struct hlist_bl_node *node,
-+ struct hlist_bl_head *hbl)
-+{
-+ hlist_bl_lock(hbl);
-+ hlist_bl_add_head(node, hbl);
-+ hlist_bl_unlock(hbl);
-+}
-+
-+static inline void au_hbl_del(struct hlist_bl_node *node,
-+ struct hlist_bl_head *hbl)
-+{
-+ hlist_bl_lock(hbl);
-+ hlist_bl_del(node);
-+ hlist_bl_unlock(hbl);
-+}
-+
-+#define au_hbl_for_each(pos, head) \
-+ for (pos = hlist_bl_first(head); \
-+ pos; \
-+ pos = pos->next)
-+
-+static inline unsigned long au_hbl_count(struct hlist_bl_head *hbl)
-+{
-+ unsigned long cnt;
-+ struct hlist_bl_node *pos;
-+
-+ cnt = 0;
-+ hlist_bl_lock(hbl);
-+ au_hbl_for_each(pos, hbl)
-+ cnt++;
-+ hlist_bl_unlock(hbl);
-+ return cnt;
-+}
-+
-+#endif /* __KERNEL__ */
-+#endif /* __AUFS_HBL_H__ */
-diff --git a/fs/aufs/hfsnotify.c b/fs/aufs/hfsnotify.c
-new file mode 100644
-index 000000000000..7945ae3ca073
---- /dev/null
-+++ b/fs/aufs/hfsnotify.c
-@@ -0,0 +1,288 @@
-+// SPDX-License-Identifier: GPL-2.0
-+/*
-+ * Copyright (C) 2005-2019 Junjiro R. Okajima
-+ *
-+ * This program, aufs is free software; you can redistribute it and/or modify
-+ * it under the terms of the GNU General Public License as published by
-+ * the Free Software Foundation; either version 2 of the License, or
-+ * (at your option) any later version.
-+ *
-+ * This program is distributed in the hope that it will be useful,
-+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
-+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
-+ * GNU General Public License for more details.
-+ *
-+ * You should have received a copy of the GNU General Public License
-+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
-+ */
-+
-+/*
-+ * fsnotify for the lower directories
-+ */
-+
-+#include "aufs.h"
-+
-+/* FS_IN_IGNORED is unnecessary */
-+static const __u32 AuHfsnMask = (FS_MOVED_TO | FS_MOVED_FROM | FS_DELETE
-+ | FS_CREATE | FS_EVENT_ON_CHILD);
-+static DECLARE_WAIT_QUEUE_HEAD(au_hfsn_wq);
-+static __cacheline_aligned_in_smp atomic64_t au_hfsn_ifree = ATOMIC64_INIT(0);
-+
-+static void au_hfsn_free_mark(struct fsnotify_mark *mark)
-+{
-+ struct au_hnotify *hn = container_of(mark, struct au_hnotify,
-+ hn_mark);
-+ /* AuDbg("here\n"); */
-+ au_cache_free_hnotify(hn);
-+ smp_mb__before_atomic(); /* for atomic64_dec */
-+ if (atomic64_dec_and_test(&au_hfsn_ifree))
-+ wake_up(&au_hfsn_wq);
-+}
-+
-+static int au_hfsn_alloc(struct au_hinode *hinode)
-+{
-+ int err;
-+ struct au_hnotify *hn;
-+ struct super_block *sb;
-+ struct au_branch *br;
-+ struct fsnotify_mark *mark;
-+ aufs_bindex_t bindex;
-+
-+ hn = hinode->hi_notify;
-+ sb = hn->hn_aufs_inode->i_sb;
-+ bindex = au_br_index(sb, hinode->hi_id);
-+ br = au_sbr(sb, bindex);
-+ AuDebugOn(!br->br_hfsn);
-+
-+ mark = &hn->hn_mark;
-+ fsnotify_init_mark(mark, br->br_hfsn->hfsn_group);
-+ mark->mask = AuHfsnMask;
-+ /*
-+ * by udba rename or rmdir, aufs assign a new inode to the known
-+ * h_inode, so specify 1 to allow dups.
-+ */
-+ lockdep_off();
-+ err = fsnotify_add_inode_mark(mark, hinode->hi_inode, /*allow_dups*/1);
-+ lockdep_on();
-+
-+ return err;
-+}
-+
-+static int au_hfsn_free(struct au_hinode *hinode, struct au_hnotify *hn)
-+{
-+ struct fsnotify_mark *mark;
-+ unsigned long long ull;
-+ struct fsnotify_group *group;
-+
-+ ull = atomic64_inc_return(&au_hfsn_ifree);
-+ BUG_ON(!ull);
-+
-+ mark = &hn->hn_mark;
-+ spin_lock(&mark->lock);
-+ group = mark->group;
-+ fsnotify_get_group(group);
-+ spin_unlock(&mark->lock);
-+ lockdep_off();
-+ fsnotify_destroy_mark(mark, group);
-+ fsnotify_put_mark(mark);
-+ fsnotify_put_group(group);
-+ lockdep_on();
-+
-+ /* free hn by myself */
-+ return 0;
-+}
-+
-+/* ---------------------------------------------------------------------- */
-+
-+static void au_hfsn_ctl(struct au_hinode *hinode, int do_set)
-+{
-+ struct fsnotify_mark *mark;
-+
-+ mark = &hinode->hi_notify->hn_mark;
-+ spin_lock(&mark->lock);
-+ if (do_set) {
-+ AuDebugOn(mark->mask & AuHfsnMask);
-+ mark->mask |= AuHfsnMask;
-+ } else {
-+ AuDebugOn(!(mark->mask & AuHfsnMask));
-+ mark->mask &= ~AuHfsnMask;
-+ }
-+ spin_unlock(&mark->lock);
-+ /* fsnotify_recalc_inode_mask(hinode->hi_inode); */
-+}
-+
-+/* ---------------------------------------------------------------------- */
-+
-+/* #define AuDbgHnotify */
-+#ifdef AuDbgHnotify
-+static char *au_hfsn_name(u32 mask)
-+{
-+#ifdef CONFIG_AUFS_DEBUG
-+#define test_ret(flag) \
-+ do { \
-+ if (mask & flag) \
-+ return #flag; \
-+ } while (0)
-+ test_ret(FS_ACCESS);
-+ test_ret(FS_MODIFY);
-+ test_ret(FS_ATTRIB);
-+ test_ret(FS_CLOSE_WRITE);
-+ test_ret(FS_CLOSE_NOWRITE);
-+ test_ret(FS_OPEN);
-+ test_ret(FS_MOVED_FROM);
-+ test_ret(FS_MOVED_TO);
-+ test_ret(FS_CREATE);
-+ test_ret(FS_DELETE);
-+ test_ret(FS_DELETE_SELF);
-+ test_ret(FS_MOVE_SELF);
-+ test_ret(FS_UNMOUNT);
-+ test_ret(FS_Q_OVERFLOW);
-+ test_ret(FS_IN_IGNORED);
-+ test_ret(FS_ISDIR);
-+ test_ret(FS_IN_ONESHOT);
-+ test_ret(FS_EVENT_ON_CHILD);
-+ return "";
-+#undef test_ret
-+#else
-+ return "??";
-+#endif
-+}
-+#endif
-+
-+/* ---------------------------------------------------------------------- */
-+
-+static void au_hfsn_free_group(struct fsnotify_group *group)
-+{
-+ struct au_br_hfsnotify *hfsn = group->private;
-+
-+ /* AuDbg("here\n"); */
-+ au_kfree_try_rcu(hfsn);
-+}
-+
-+static int au_hfsn_handle_event(struct fsnotify_group *group,
-+ struct inode *inode,
-+ u32 mask, const void *data, int data_type,
-+ const struct qstr *file_name, u32 cookie,
-+ struct fsnotify_iter_info *iter_info)
-+{
-+ int err;
-+ struct au_hnotify *hnotify;
-+ struct inode *h_dir, *h_inode;
-+ struct fsnotify_mark *inode_mark;
-+
-+ AuDebugOn(data_type != FSNOTIFY_EVENT_INODE);
-+
-+ err = 0;
-+ /* if FS_UNMOUNT happens, there must be another bug */
-+ AuDebugOn(mask & FS_UNMOUNT);
-+ if (mask & (FS_IN_IGNORED | FS_UNMOUNT))
-+ goto out;
-+
-+ h_dir = inode;
-+ h_inode = NULL;
-+#ifdef AuDbgHnotify
-+ au_debug_on();
-+ if (1 || h_child_qstr.len != sizeof(AUFS_XINO_FNAME) - 1
-+ || strncmp(h_child_qstr.name, AUFS_XINO_FNAME, h_child_qstr.len)) {
-+ AuDbg("i%lu, mask 0x%x %s, hcname %.*s, hi%lu\n",
-+ h_dir->i_ino, mask, au_hfsn_name(mask),
-+ AuLNPair(&h_child_qstr), h_inode ? h_inode->i_ino : 0);
-+ /* WARN_ON(1); */
-+ }
-+ au_debug_off();
-+#endif
-+
-+ inode_mark = fsnotify_iter_inode_mark(iter_info);
-+ AuDebugOn(!inode_mark);
-+ hnotify = container_of(inode_mark, struct au_hnotify, hn_mark);
-+ err = au_hnotify(h_dir, hnotify, mask, file_name, h_inode);
-+
-+out:
-+ return err;
-+}
-+
-+static struct fsnotify_ops au_hfsn_ops = {
-+ .handle_event = au_hfsn_handle_event,
-+ .free_group_priv = au_hfsn_free_group,
-+ .free_mark = au_hfsn_free_mark
-+};
-+
-+/* ---------------------------------------------------------------------- */
-+
-+static void au_hfsn_fin_br(struct au_branch *br)
-+{
-+ struct au_br_hfsnotify *hfsn;
-+
-+ hfsn = br->br_hfsn;
-+ if (hfsn) {
-+ lockdep_off();
-+ fsnotify_put_group(hfsn->hfsn_group);
-+ lockdep_on();
-+ }
-+}
-+
-+static int au_hfsn_init_br(struct au_branch *br, int perm)
-+{
-+ int err;
-+ struct fsnotify_group *group;
-+ struct au_br_hfsnotify *hfsn;
-+
-+ err = 0;
-+ br->br_hfsn = NULL;
-+ if (!au_br_hnotifyable(perm))
-+ goto out;
-+
-+ err = -ENOMEM;
-+ hfsn = kmalloc(sizeof(*hfsn), GFP_NOFS);
-+ if (unlikely(!hfsn))
-+ goto out;
-+
-+ err = 0;
-+ group = fsnotify_alloc_group(&au_hfsn_ops);
-+ if (IS_ERR(group)) {
-+ err = PTR_ERR(group);
-+ pr_err("fsnotify_alloc_group() failed, %d\n", err);
-+ goto out_hfsn;
-+ }
-+
-+ group->private = hfsn;
-+ hfsn->hfsn_group = group;
-+ br->br_hfsn = hfsn;
-+ goto out; /* success */
-+
-+out_hfsn:
-+ au_kfree_try_rcu(hfsn);
-+out:
-+ return err;
-+}
-+
-+static int au_hfsn_reset_br(unsigned int udba, struct au_branch *br, int perm)
-+{
-+ int err;
-+
-+ err = 0;
-+ if (!br->br_hfsn)
-+ err = au_hfsn_init_br(br, perm);
-+
-+ return err;
-+}
-+
-+/* ---------------------------------------------------------------------- */
-+
-+static void au_hfsn_fin(void)
-+{
-+ AuDbg("au_hfsn_ifree %lld\n", (long long)atomic64_read(&au_hfsn_ifree));
-+ wait_event(au_hfsn_wq, !atomic64_read(&au_hfsn_ifree));
-+}
-+
-+const struct au_hnotify_op au_hnotify_op = {
-+ .ctl = au_hfsn_ctl,
-+ .alloc = au_hfsn_alloc,
-+ .free = au_hfsn_free,
-+
-+ .fin = au_hfsn_fin,
-+
-+ .reset_br = au_hfsn_reset_br,
-+ .fin_br = au_hfsn_fin_br,
-+ .init_br = au_hfsn_init_br
-+};
-diff --git a/fs/aufs/hfsplus.c b/fs/aufs/hfsplus.c
-new file mode 100644
-index 000000000000..3bd869a69c8f
---- /dev/null
-+++ b/fs/aufs/hfsplus.c
-@@ -0,0 +1,60 @@
-+// SPDX-License-Identifier: GPL-2.0
-+/*
-+ * Copyright (C) 2010-2019 Junjiro R. Okajima
-+ *
-+ * This program, aufs is free software; you can redistribute it and/or modify
-+ * it under the terms of the GNU General Public License as published by
-+ * the Free Software Foundation; either version 2 of the License, or
-+ * (at your option) any later version.
-+ *
-+ * This program is distributed in the hope that it will be useful,
-+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
-+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
-+ * GNU General Public License for more details.
-+ *
-+ * You should have received a copy of the GNU General Public License
-+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
-+ */
-+
-+/*
-+ * special support for filesystems which acquires an inode mutex
-+ * at final closing a file, eg, hfsplus.
-+ *
-+ * This trick is very simple and stupid, just to open the file before really
-+ * necessary open to tell hfsplus that this is not the final closing.
-+ * The caller should call au_h_open_pre() after acquiring the inode mutex,
-+ * and au_h_open_post() after releasing it.
-+ */
-+
-+#include "aufs.h"
-+
-+struct file *au_h_open_pre(struct dentry *dentry, aufs_bindex_t bindex,
-+ int force_wr)
-+{
-+ struct file *h_file;
-+ struct dentry *h_dentry;
-+
-+ h_dentry = au_h_dptr(dentry, bindex);
-+ AuDebugOn(!h_dentry);
-+ AuDebugOn(d_is_negative(h_dentry));
-+
-+ h_file = NULL;
-+ if (au_test_hfsplus(h_dentry->d_sb)
-+ && d_is_reg(h_dentry))
-+ h_file = au_h_open(dentry, bindex,
-+ O_RDONLY | O_NOATIME | O_LARGEFILE,
-+ /*file*/NULL, force_wr);
-+ return h_file;
-+}
-+
-+void au_h_open_post(struct dentry *dentry, aufs_bindex_t bindex,
-+ struct file *h_file)
-+{
-+ struct au_branch *br;
-+
-+ if (h_file) {
-+ fput(h_file);
-+ br = au_sbr(dentry->d_sb, bindex);
-+ au_lcnt_dec(&br->br_nfiles);
-+ }
-+}
-diff --git a/fs/aufs/hnotify.c b/fs/aufs/hnotify.c
-new file mode 100644
-index 000000000000..2e7c2cdb8202
---- /dev/null
-+++ b/fs/aufs/hnotify.c
-@@ -0,0 +1,721 @@
-+// SPDX-License-Identifier: GPL-2.0
-+/*
-+ * Copyright (C) 2005-2019 Junjiro R. Okajima
-+ *
-+ * This program, aufs is free software; you can redistribute it and/or modify
-+ * it under the terms of the GNU General Public License as published by
-+ * the Free Software Foundation; either version 2 of the License, or
-+ * (at your option) any later version.
-+ *
-+ * This program is distributed in the hope that it will be useful,
-+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
-+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
-+ * GNU General Public License for more details.
-+ *
-+ * You should have received a copy of the GNU General Public License
-+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
-+ */
-+
-+/*
-+ * abstraction to notify the direct changes on lower directories
-+ */
-+
-+/* #include <linux/iversion.h> */
-+#include "aufs.h"
-+
-+int au_hn_alloc(struct au_hinode *hinode, struct inode *inode)
-+{
-+ int err;
-+ struct au_hnotify *hn;
-+
-+ err = -ENOMEM;
-+ hn = au_cache_alloc_hnotify();
-+ if (hn) {
-+ hn->hn_aufs_inode = inode;
-+ hinode->hi_notify = hn;
-+ err = au_hnotify_op.alloc(hinode);
-+ AuTraceErr(err);
-+ if (unlikely(err)) {
-+ hinode->hi_notify = NULL;
-+ au_cache_free_hnotify(hn);
-+ /*
-+ * The upper dir was removed by udba, but the same named
-+ * dir left. In this case, aufs assigns a new inode
-+ * number and set the monitor again.
-+ * For the lower dir, the old monitor is still left.
-+ */
-+ if (err == -EEXIST)
-+ err = 0;
-+ }
-+ }
-+
-+ AuTraceErr(err);
-+ return err;
-+}
-+
-+void au_hn_free(struct au_hinode *hinode)
-+{
-+ struct au_hnotify *hn;
-+
-+ hn = hinode->hi_notify;
-+ if (hn) {
-+ hinode->hi_notify = NULL;
-+ if (au_hnotify_op.free(hinode, hn))
-+ au_cache_free_hnotify(hn);
-+ }
-+}
-+
-+/* ---------------------------------------------------------------------- */
-+
-+void au_hn_ctl(struct au_hinode *hinode, int do_set)
-+{
-+ if (hinode->hi_notify)
-+ au_hnotify_op.ctl(hinode, do_set);
-+}
-+
-+void au_hn_reset(struct inode *inode, unsigned int flags)
-+{
-+ aufs_bindex_t bindex, bbot;
-+ struct inode *hi;
-+ struct dentry *iwhdentry;
-+
-+ bbot = au_ibbot(inode);
-+ for (bindex = au_ibtop(inode); bindex <= bbot; bindex++) {
-+ hi = au_h_iptr(inode, bindex);
-+ if (!hi)
-+ continue;
-+
-+ /* inode_lock_nested(hi, AuLsc_I_CHILD); */
-+ iwhdentry = au_hi_wh(inode, bindex);
-+ if (iwhdentry)
-+ dget(iwhdentry);
-+ au_igrab(hi);
-+ au_set_h_iptr(inode, bindex, NULL, 0);
-+ au_set_h_iptr(inode, bindex, au_igrab(hi),
-+ flags & ~AuHi_XINO);
-+ iput(hi);
-+ dput(iwhdentry);
-+ /* inode_unlock(hi); */
-+ }
-+}
-+
-+/* ---------------------------------------------------------------------- */
-+
-+static int hn_xino(struct inode *inode, struct inode *h_inode)
-+{
-+ int err;
-+ aufs_bindex_t bindex, bbot, bfound, btop;
-+ struct inode *h_i;
-+
-+ err = 0;
-+ if (unlikely(inode->i_ino == AUFS_ROOT_INO)) {
-+ pr_warn("branch root dir was changed\n");
-+ goto out;
-+ }
-+
-+ bfound = -1;
-+ bbot = au_ibbot(inode);
-+ btop = au_ibtop(inode);
-+#if 0 /* reserved for future use */
-+ if (bindex == bbot) {
-+ /* keep this ino in rename case */
-+ goto out;
-+ }
-+#endif
-+ for (bindex = btop; bindex <= bbot; bindex++)
-+ if (au_h_iptr(inode, bindex) == h_inode) {
-+ bfound = bindex;
-+ break;
-+ }
-+ if (bfound < 0)
-+ goto out;
-+
-+ for (bindex = btop; bindex <= bbot; bindex++) {
-+ h_i = au_h_iptr(inode, bindex);
-+ if (!h_i)
-+ continue;
-+
-+ err = au_xino_write(inode->i_sb, bindex, h_i->i_ino, /*ino*/0);
-+ /* ignore this error */
-+ /* bad action? */
-+ }
-+
-+ /* children inode number will be broken */
-+
-+out:
-+ AuTraceErr(err);
-+ return err;
-+}
-+
-+static int hn_gen_tree(struct dentry *dentry)
-+{
-+ int err, i, j, ndentry;
-+ struct au_dcsub_pages dpages;
-+ struct au_dpage *dpage;
-+ struct dentry **dentries;
-+
-+ err = au_dpages_init(&dpages, GFP_NOFS);
-+ if (unlikely(err))
-+ goto out;
-+ err = au_dcsub_pages(&dpages, dentry, NULL, NULL);
-+ if (unlikely(err))
-+ goto out_dpages;
-+
-+ for (i = 0; i < dpages.ndpage; i++) {
-+ dpage = dpages.dpages + i;
-+ dentries = dpage->dentries;
-+ ndentry = dpage->ndentry;
-+ for (j = 0; j < ndentry; j++) {
-+ struct dentry *d;
-+
-+ d = dentries[j];
-+ if (IS_ROOT(d))
-+ continue;
-+
-+ au_digen_dec(d);
-+ if (d_really_is_positive(d))
-+ /* todo: reset children xino?
-+ cached children only? */
-+ au_iigen_dec(d_inode(d));
-+ }
-+ }
-+
-+out_dpages:
-+ au_dpages_free(&dpages);
-+
-+#if 0
-+ /* discard children */
-+ dentry_unhash(dentry);
-+ dput(dentry);
-+#endif
-+out:
-+ return err;
-+}
-+
-+/*
-+ * return 0 if processed.
-+ */
-+static int hn_gen_by_inode(char *name, unsigned int nlen, struct inode *inode,
-+ const unsigned int isdir)
-+{
-+ int err;
-+ struct dentry *d;
-+ struct qstr *dname;
-+
-+ err = 1;
-+ if (unlikely(inode->i_ino == AUFS_ROOT_INO)) {
-+ pr_warn("branch root dir was changed\n");
-+ err = 0;
-+ goto out;
-+ }
-+
-+ if (!isdir) {
-+ AuDebugOn(!name);
-+ au_iigen_dec(inode);
-+ spin_lock(&inode->i_lock);
-+ hlist_for_each_entry(d, &inode->i_dentry, d_u.d_alias) {
-+ spin_lock(&d->d_lock);
-+ dname = &d->d_name;
-+ if (dname->len != nlen
-+ && memcmp(dname->name, name, nlen)) {
-+ spin_unlock(&d->d_lock);
-+ continue;
-+ }
-+ err = 0;
-+ au_digen_dec(d);
-+ spin_unlock(&d->d_lock);
-+ break;
-+ }
-+ spin_unlock(&inode->i_lock);
-+ } else {
-+ au_fset_si(au_sbi(inode->i_sb), FAILED_REFRESH_DIR);
-+ d = d_find_any_alias(inode);
-+ if (!d) {
-+ au_iigen_dec(inode);
-+ goto out;
-+ }
-+
-+ spin_lock(&d->d_lock);
-+ dname = &d->d_name;
-+ if (dname->len == nlen && !memcmp(dname->name, name, nlen)) {
-+ spin_unlock(&d->d_lock);
-+ err = hn_gen_tree(d);
-+ spin_lock(&d->d_lock);
-+ }
-+ spin_unlock(&d->d_lock);
-+ dput(d);
-+ }
-+
-+out:
-+ AuTraceErr(err);
-+ return err;
-+}
-+
-+static int hn_gen_by_name(struct dentry *dentry, const unsigned int isdir)
-+{
-+ int err;
-+
-+ if (IS_ROOT(dentry)) {
-+ pr_warn("branch root dir was changed\n");
-+ return 0;
-+ }
-+
-+ err = 0;
-+ if (!isdir) {
-+ au_digen_dec(dentry);
-+ if (d_really_is_positive(dentry))
-+ au_iigen_dec(d_inode(dentry));
-+ } else {
-+ au_fset_si(au_sbi(dentry->d_sb), FAILED_REFRESH_DIR);
-+ if (d_really_is_positive(dentry))
-+ err = hn_gen_tree(dentry);
-+ }
-+
-+ AuTraceErr(err);
-+ return err;
-+}
-+
-+/* ---------------------------------------------------------------------- */
-+
-+/* hnotify job flags */
-+#define AuHnJob_XINO0 1
-+#define AuHnJob_GEN (1 << 1)
-+#define AuHnJob_DIRENT (1 << 2)
-+#define AuHnJob_ISDIR (1 << 3)
-+#define AuHnJob_TRYXINO0 (1 << 4)
-+#define AuHnJob_MNTPNT (1 << 5)
-+#define au_ftest_hnjob(flags, name) ((flags) & AuHnJob_##name)
-+#define au_fset_hnjob(flags, name) \
-+ do { (flags) |= AuHnJob_##name; } while (0)
-+#define au_fclr_hnjob(flags, name) \
-+ do { (flags) &= ~AuHnJob_##name; } while (0)
-+
-+enum {
-+ AuHn_CHILD,
-+ AuHn_PARENT,
-+ AuHnLast
-+};
-+
-+struct au_hnotify_args {
-+ struct inode *h_dir, *dir, *h_child_inode;
-+ u32 mask;
-+ unsigned int flags[AuHnLast];
-+ unsigned int h_child_nlen;
-+ char h_child_name[];
-+};
-+
-+struct hn_job_args {
-+ unsigned int flags;
-+ struct inode *inode, *h_inode, *dir, *h_dir;
-+ struct dentry *dentry;
-+ char *h_name;
-+ int h_nlen;
-+};
-+
-+static int hn_job(struct hn_job_args *a)
-+{
-+ const unsigned int isdir = au_ftest_hnjob(a->flags, ISDIR);
-+ int e;
-+
-+ /* reset xino */
-+ if (au_ftest_hnjob(a->flags, XINO0) && a->inode)
-+ hn_xino(a->inode, a->h_inode); /* ignore this error */
-+
-+ if (au_ftest_hnjob(a->flags, TRYXINO0)
-+ && a->inode
-+ && a->h_inode) {
-+ inode_lock_shared_nested(a->h_inode, AuLsc_I_CHILD);
-+ if (!a->h_inode->i_nlink
-+ && !(a->h_inode->i_state & I_LINKABLE))
-+ hn_xino(a->inode, a->h_inode); /* ignore this error */
-+ inode_unlock_shared(a->h_inode);
-+ }
-+
-+ /* make the generation obsolete */
-+ if (au_ftest_hnjob(a->flags, GEN)) {
-+ e = -1;
-+ if (a->inode)
-+ e = hn_gen_by_inode(a->h_name, a->h_nlen, a->inode,
-+ isdir);
-+ if (e && a->dentry)
-+ hn_gen_by_name(a->dentry, isdir);
-+ /* ignore this error */
-+ }
-+
-+ /* make dir entries obsolete */
-+ if (au_ftest_hnjob(a->flags, DIRENT) && a->inode) {
-+ struct au_vdir *vdir;
-+
-+ vdir = au_ivdir(a->inode);
-+ if (vdir)
-+ vdir->vd_jiffy = 0;
-+ /* IMustLock(a->inode); */
-+ /* inode_inc_iversion(a->inode); */
-+ }
-+
-+ /* can do nothing but warn */
-+ if (au_ftest_hnjob(a->flags, MNTPNT)
-+ && a->dentry
-+ && d_mountpoint(a->dentry))
-+ pr_warn("mount-point %pd is removed or renamed\n", a->dentry);
-+
-+ return 0;
-+}
-+
-+/* ---------------------------------------------------------------------- */
-+
-+static struct dentry *lookup_wlock_by_name(char *name, unsigned int nlen,
-+ struct inode *dir)
-+{
-+ struct dentry *dentry, *d, *parent;
-+ struct qstr *dname;
-+
-+ parent = d_find_any_alias(dir);
-+ if (!parent)
-+ return NULL;
-+
-+ dentry = NULL;
-+ spin_lock(&parent->d_lock);
-+ list_for_each_entry(d, &parent->d_subdirs, d_child) {
-+ /* AuDbg("%pd\n", d); */
-+ spin_lock_nested(&d->d_lock, DENTRY_D_LOCK_NESTED);
-+ dname = &d->d_name;
-+ if (dname->len != nlen || memcmp(dname->name, name, nlen))
-+ goto cont_unlock;
-+ if (au_di(d))
-+ au_digen_dec(d);
-+ else
-+ goto cont_unlock;
-+ if (au_dcount(d) > 0) {
-+ dentry = dget_dlock(d);
-+ spin_unlock(&d->d_lock);
-+ break;
-+ }
-+
-+cont_unlock:
-+ spin_unlock(&d->d_lock);
-+ }
-+ spin_unlock(&parent->d_lock);
-+ dput(parent);
-+
-+ if (dentry)
-+ di_write_lock_child(dentry);
-+
-+ return dentry;
-+}
-+
-+static struct inode *lookup_wlock_by_ino(struct super_block *sb,
-+ aufs_bindex_t bindex, ino_t h_ino)
-+{
-+ struct inode *inode;
-+ ino_t ino;
-+ int err;
-+
-+ inode = NULL;
-+ err = au_xino_read(sb, bindex, h_ino, &ino);
-+ if (!err && ino)
-+ inode = ilookup(sb, ino);
-+ if (!inode)
-+ goto out;
-+
-+ if (unlikely(inode->i_ino == AUFS_ROOT_INO)) {
-+ pr_warn("wrong root branch\n");
-+ iput(inode);
-+ inode = NULL;
-+ goto out;
-+ }
-+
-+ ii_write_lock_child(inode);
-+
-+out:
-+ return inode;
-+}
-+
-+static void au_hn_bh(void *_args)
-+{
-+ struct au_hnotify_args *a = _args;
-+ struct super_block *sb;
-+ aufs_bindex_t bindex, bbot, bfound;
-+ unsigned char xino, try_iput;
-+ int err;
-+ struct inode *inode;
-+ ino_t h_ino;
-+ struct hn_job_args args;
-+ struct dentry *dentry;
-+ struct au_sbinfo *sbinfo;
-+
-+ AuDebugOn(!_args);
-+ AuDebugOn(!a->h_dir);
-+ AuDebugOn(!a->dir);
-+ AuDebugOn(!a->mask);
-+ AuDbg("mask 0x%x, i%lu, hi%lu, hci%lu\n",
-+ a->mask, a->dir->i_ino, a->h_dir->i_ino,
-+ a->h_child_inode ? a->h_child_inode->i_ino : 0);
-+
-+ inode = NULL;
-+ dentry = NULL;
-+ /*
-+ * do not lock a->dir->i_mutex here
-+ * because of d_revalidate() may cause a deadlock.
-+ */
-+ sb = a->dir->i_sb;
-+ AuDebugOn(!sb);
-+ sbinfo = au_sbi(sb);
-+ AuDebugOn(!sbinfo);
-+ si_write_lock(sb, AuLock_NOPLMW);
-+
-+ if (au_opt_test(sbinfo->si_mntflags, DIRREN))
-+ switch (a->mask & FS_EVENTS_POSS_ON_CHILD) {
-+ case FS_MOVED_FROM:
-+ case FS_MOVED_TO:
-+ AuWarn1("DIRREN with UDBA may not work correctly "
-+ "for the direct rename(2)\n");
-+ }
-+
-+ ii_read_lock_parent(a->dir);
-+ bfound = -1;
-+ bbot = au_ibbot(a->dir);
-+ for (bindex = au_ibtop(a->dir); bindex <= bbot; bindex++)
-+ if (au_h_iptr(a->dir, bindex) == a->h_dir) {
-+ bfound = bindex;
-+ break;
-+ }
-+ ii_read_unlock(a->dir);
-+ if (unlikely(bfound < 0))
-+ goto out;
-+
-+ xino = !!au_opt_test(au_mntflags(sb), XINO);
-+ h_ino = 0;
-+ if (a->h_child_inode)
-+ h_ino = a->h_child_inode->i_ino;
-+
-+ if (a->h_child_nlen
-+ && (au_ftest_hnjob(a->flags[AuHn_CHILD], GEN)
-+ || au_ftest_hnjob(a->flags[AuHn_CHILD], MNTPNT)))
-+ dentry = lookup_wlock_by_name(a->h_child_name, a->h_child_nlen,
-+ a->dir);
-+ try_iput = 0;
-+ if (dentry && d_really_is_positive(dentry))
-+ inode = d_inode(dentry);
-+ if (xino && !inode && h_ino
-+ && (au_ftest_hnjob(a->flags[AuHn_CHILD], XINO0)
-+ || au_ftest_hnjob(a->flags[AuHn_CHILD], TRYXINO0)
-+ || au_ftest_hnjob(a->flags[AuHn_CHILD], GEN))) {
-+ inode = lookup_wlock_by_ino(sb, bfound, h_ino);
-+ try_iput = 1;
-+ }
-+
-+ args.flags = a->flags[AuHn_CHILD];
-+ args.dentry = dentry;
-+ args.inode = inode;
-+ args.h_inode = a->h_child_inode;
-+ args.dir = a->dir;
-+ args.h_dir = a->h_dir;
-+ args.h_name = a->h_child_name;
-+ args.h_nlen = a->h_child_nlen;
-+ err = hn_job(&args);
-+ if (dentry) {
-+ if (au_di(dentry))
-+ di_write_unlock(dentry);
-+ dput(dentry);
-+ }
-+ if (inode && try_iput) {
-+ ii_write_unlock(inode);
-+ iput(inode);
-+ }
-+
-+ ii_write_lock_parent(a->dir);
-+ args.flags = a->flags[AuHn_PARENT];
-+ args.dentry = NULL;
-+ args.inode = a->dir;
-+ args.h_inode = a->h_dir;
-+ args.dir = NULL;
-+ args.h_dir = NULL;
-+ args.h_name = NULL;
-+ args.h_nlen = 0;
-+ err = hn_job(&args);
-+ ii_write_unlock(a->dir);
-+
-+out:
-+ iput(a->h_child_inode);
-+ iput(a->h_dir);
-+ iput(a->dir);
-+ si_write_unlock(sb);
-+ au_nwt_done(&sbinfo->si_nowait);
-+ au_kfree_rcu(a);
-+}
-+
-+/* ---------------------------------------------------------------------- */
-+
-+int au_hnotify(struct inode *h_dir, struct au_hnotify *hnotify, u32 mask,
-+ const struct qstr *h_child_qstr, struct inode *h_child_inode)
-+{
-+ int err, len;
-+ unsigned int flags[AuHnLast], f;
-+ unsigned char isdir, isroot, wh;
-+ struct inode *dir;
-+ struct au_hnotify_args *args;
-+ char *p, *h_child_name;
-+
-+ err = 0;
-+ AuDebugOn(!hnotify || !hnotify->hn_aufs_inode);
-+ dir = igrab(hnotify->hn_aufs_inode);
-+ if (!dir)
-+ goto out;
-+
-+ isroot = (dir->i_ino == AUFS_ROOT_INO);
-+ wh = 0;
-+ h_child_name = (void *)h_child_qstr->name;
-+ len = h_child_qstr->len;
-+ if (h_child_name) {
-+ if (len > AUFS_WH_PFX_LEN
-+ && !memcmp(h_child_name, AUFS_WH_PFX, AUFS_WH_PFX_LEN)) {
-+ h_child_name += AUFS_WH_PFX_LEN;
-+ len -= AUFS_WH_PFX_LEN;
-+ wh = 1;
-+ }
-+ }
-+
-+ isdir = 0;
-+ if (h_child_inode)
-+ isdir = !!S_ISDIR(h_child_inode->i_mode);
-+ flags[AuHn_PARENT] = AuHnJob_ISDIR;
-+ flags[AuHn_CHILD] = 0;
-+ if (isdir)
-+ flags[AuHn_CHILD] = AuHnJob_ISDIR;
-+ au_fset_hnjob(flags[AuHn_PARENT], DIRENT);
-+ au_fset_hnjob(flags[AuHn_CHILD], GEN);
-+ switch (mask & ALL_FSNOTIFY_DIRENT_EVENTS) {
-+ case FS_MOVED_FROM:
-+ case FS_MOVED_TO:
-+ au_fset_hnjob(flags[AuHn_CHILD], XINO0);
-+ au_fset_hnjob(flags[AuHn_CHILD], MNTPNT);
-+ /*FALLTHROUGH*/
-+ case FS_CREATE:
-+ AuDebugOn(!h_child_name);
-+ break;
-+
-+ case FS_DELETE:
-+ /*
-+ * aufs never be able to get this child inode.
-+ * revalidation should be in d_revalidate()
-+ * by checking i_nlink, i_generation or d_unhashed().
-+ */
-+ AuDebugOn(!h_child_name);
-+ au_fset_hnjob(flags[AuHn_CHILD], TRYXINO0);
-+ au_fset_hnjob(flags[AuHn_CHILD], MNTPNT);
-+ break;
-+
-+ default:
-+ AuDebugOn(1);
-+ }
-+
-+ if (wh)
-+ h_child_inode = NULL;
-+
-+ err = -ENOMEM;
-+ /* iput() and kfree() will be called in au_hnotify() */
-+ args = kmalloc(sizeof(*args) + len + 1, GFP_NOFS);
-+ if (unlikely(!args)) {
-+ AuErr1("no memory\n");
-+ iput(dir);
-+ goto out;
-+ }
-+ args->flags[AuHn_PARENT] = flags[AuHn_PARENT];
-+ args->flags[AuHn_CHILD] = flags[AuHn_CHILD];
-+ args->mask = mask;
-+ args->dir = dir;
-+ args->h_dir = igrab(h_dir);
-+ if (h_child_inode)
-+ h_child_inode = igrab(h_child_inode); /* can be NULL */
-+ args->h_child_inode = h_child_inode;
-+ args->h_child_nlen = len;
-+ if (len) {
-+ p = (void *)args;
-+ p += sizeof(*args);
-+ memcpy(p, h_child_name, len);
-+ p[len] = 0;
-+ }
-+
-+ /* NFS fires the event for silly-renamed one from kworker */
-+ f = 0;
-+ if (!dir->i_nlink
-+ || (au_test_nfs(h_dir->i_sb) && (mask & FS_DELETE)))
-+ f = AuWkq_NEST;
-+ err = au_wkq_nowait(au_hn_bh, args, dir->i_sb, f);
-+ if (unlikely(err)) {
-+ pr_err("wkq %d\n", err);
-+ iput(args->h_child_inode);
-+ iput(args->h_dir);
-+ iput(args->dir);
-+ au_kfree_rcu(args);
-+ }
-+
-+out:
-+ return err;
-+}
-+
-+/* ---------------------------------------------------------------------- */
-+
-+int au_hnotify_reset_br(unsigned int udba, struct au_branch *br, int perm)
-+{
-+ int err;
-+
-+ AuDebugOn(!(udba & AuOptMask_UDBA));
-+
-+ err = 0;
-+ if (au_hnotify_op.reset_br)
-+ err = au_hnotify_op.reset_br(udba, br, perm);
-+
-+ return err;
-+}
-+
-+int au_hnotify_init_br(struct au_branch *br, int perm)
-+{
-+ int err;
-+
-+ err = 0;
-+ if (au_hnotify_op.init_br)
-+ err = au_hnotify_op.init_br(br, perm);
-+
-+ return err;
-+}
-+
-+void au_hnotify_fin_br(struct au_branch *br)
-+{
-+ if (au_hnotify_op.fin_br)
-+ au_hnotify_op.fin_br(br);
-+}
-+
-+static void au_hn_destroy_cache(void)
-+{
-+ kmem_cache_destroy(au_cache[AuCache_HNOTIFY]);
-+ au_cache[AuCache_HNOTIFY] = NULL;
-+}
-+
-+int __init au_hnotify_init(void)
-+{
-+ int err;
-+
-+ err = -ENOMEM;
-+ au_cache[AuCache_HNOTIFY] = AuCache(au_hnotify);
-+ if (au_cache[AuCache_HNOTIFY]) {
-+ err = 0;
-+ if (au_hnotify_op.init)
-+ err = au_hnotify_op.init();
-+ if (unlikely(err))
-+ au_hn_destroy_cache();
-+ }
-+ AuTraceErr(err);
-+ return err;
-+}
-+
-+void au_hnotify_fin(void)
-+{
-+ if (au_hnotify_op.fin)
-+ au_hnotify_op.fin();
-+
-+ /* cf. au_cache_fin() */
-+ if (au_cache[AuCache_HNOTIFY])
-+ au_hn_destroy_cache();
-+}
-diff --git a/fs/aufs/i_op.c b/fs/aufs/i_op.c
-new file mode 100644
-index 000000000000..4f5001ebd0f4
---- /dev/null
-+++ b/fs/aufs/i_op.c
-@@ -0,0 +1,1507 @@
-+// SPDX-License-Identifier: GPL-2.0
-+/*
-+ * Copyright (C) 2005-2019 Junjiro R. Okajima
-+ *
-+ * This program, aufs is free software; you can redistribute it and/or modify
-+ * it under the terms of the GNU General Public License as published by
-+ * the Free Software Foundation; either version 2 of the License, or
-+ * (at your option) any later version.
-+ *
-+ * This program is distributed in the hope that it will be useful,
-+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
-+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
-+ * GNU General Public License for more details.
-+ *
-+ * You should have received a copy of the GNU General Public License
-+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
-+ */
-+
-+/*
-+ * inode operations (except add/del/rename)
-+ */
-+
-+#include <linux/device_cgroup.h>
-+#include <linux/fs_stack.h>
-+#include <linux/iversion.h>
-+#include <linux/namei.h>
-+#include <linux/security.h>
-+#include "aufs.h"
-+
-+static int h_permission(struct inode *h_inode, int mask,
-+ struct path *h_path, int brperm)
-+{
-+ int err;
-+ const unsigned char write_mask = !!(mask & (MAY_WRITE | MAY_APPEND));
-+
-+ err = -EPERM;
-+ if (write_mask && IS_IMMUTABLE(h_inode))
-+ goto out;
-+
-+ err = -EACCES;
-+ if (((mask & MAY_EXEC)
-+ && S_ISREG(h_inode->i_mode)
-+ && (path_noexec(h_path)
-+ || !(h_inode->i_mode & 0111))))
-+ goto out;
-+
-+ /*
-+ * - skip the lower fs test in the case of write to ro branch.
-+ * - nfs dir permission write check is optimized, but a policy for
-+ * link/rename requires a real check.
-+ * - nfs always sets SB_POSIXACL regardless its mount option 'noacl.'
-+ * in this case, generic_permission() returns -EOPNOTSUPP.
-+ */
-+ if ((write_mask && !au_br_writable(brperm))
-+ || (au_test_nfs(h_inode->i_sb) && S_ISDIR(h_inode->i_mode)
-+ && write_mask && !(mask & MAY_READ))
-+ || !h_inode->i_op->permission) {
-+ /* AuLabel(generic_permission); */
-+ /* AuDbg("get_acl %ps\n", h_inode->i_op->get_acl); */
-+ err = generic_permission(h_inode, mask);
-+ if (err == -EOPNOTSUPP && au_test_nfs_noacl(h_inode))
-+ err = h_inode->i_op->permission(h_inode, mask);
-+ AuTraceErr(err);
-+ } else {
-+ /* AuLabel(h_inode->permission); */
-+ err = h_inode->i_op->permission(h_inode, mask);
-+ AuTraceErr(err);
-+ }
-+
-+ if (!err)
-+ err = devcgroup_inode_permission(h_inode, mask);
-+ if (!err)
-+ err = security_inode_permission(h_inode, mask);
-+
-+#if 0
-+ if (!err) {
-+ /* todo: do we need to call ima_path_check()? */
-+ struct path h_path = {
-+ .dentry =
-+ .mnt = h_mnt
-+ };
-+ err = ima_path_check(&h_path,
-+ mask & (MAY_READ | MAY_WRITE | MAY_EXEC),
-+ IMA_COUNT_LEAVE);
-+ }
-+#endif
-+
-+out:
-+ return err;
-+}
-+
-+static int aufs_permission(struct inode *inode, int mask)
-+{
-+ int err;
-+ aufs_bindex_t bindex, bbot;
-+ const unsigned char isdir = !!S_ISDIR(inode->i_mode),
-+ write_mask = !!(mask & (MAY_WRITE | MAY_APPEND));
-+ struct inode *h_inode;
-+ struct super_block *sb;
-+ struct au_branch *br;
-+
-+ /* todo: support rcu-walk? */
-+ if (mask & MAY_NOT_BLOCK)
-+ return -ECHILD;
-+
-+ sb = inode->i_sb;
-+ si_read_lock(sb, AuLock_FLUSH);
-+ ii_read_lock_child(inode);
-+#if 0
-+ err = au_iigen_test(inode, au_sigen(sb));
-+ if (unlikely(err))
-+ goto out;
-+#endif
-+
-+ if (!isdir
-+ || write_mask
-+ || au_opt_test(au_mntflags(sb), DIRPERM1)) {
-+ err = au_busy_or_stale();
-+ h_inode = au_h_iptr(inode, au_ibtop(inode));
-+ if (unlikely(!h_inode
-+ || (h_inode->i_mode & S_IFMT)
-+ != (inode->i_mode & S_IFMT)))
-+ goto out;
-+
-+ err = 0;
-+ bindex = au_ibtop(inode);
-+ br = au_sbr(sb, bindex);
-+ err = h_permission(h_inode, mask, &br->br_path, br->br_perm);
-+ if (write_mask
-+ && !err
-+ && !special_file(h_inode->i_mode)) {
-+ /* test whether the upper writable branch exists */
-+ err = -EROFS;
-+ for (; bindex >= 0; bindex--)
-+ if (!au_br_rdonly(au_sbr(sb, bindex))) {
-+ err = 0;
-+ break;
-+ }
-+ }
-+ goto out;
-+ }
-+
-+ /* non-write to dir */
-+ err = 0;
-+ bbot = au_ibbot(inode);
-+ for (bindex = au_ibtop(inode); !err && bindex <= bbot; bindex++) {
-+ h_inode = au_h_iptr(inode, bindex);
-+ if (h_inode) {
-+ err = au_busy_or_stale();
-+ if (unlikely(!S_ISDIR(h_inode->i_mode)))
-+ break;
-+
-+ br = au_sbr(sb, bindex);
-+ err = h_permission(h_inode, mask, &br->br_path,
-+ br->br_perm);
-+ }
-+ }
-+
-+out:
-+ ii_read_unlock(inode);
-+ si_read_unlock(sb);
-+ return err;
-+}
-+
-+/* ---------------------------------------------------------------------- */
-+
-+static struct dentry *aufs_lookup(struct inode *dir, struct dentry *dentry,
-+ unsigned int flags)
-+{
-+ struct dentry *ret, *parent;
-+ struct inode *inode;
-+ struct super_block *sb;
-+ int err, npositive;
-+
-+ IMustLock(dir);
-+
-+ /* todo: support rcu-walk? */
-+ ret = ERR_PTR(-ECHILD);
-+ if (flags & LOOKUP_RCU)
-+ goto out;
-+
-+ ret = ERR_PTR(-ENAMETOOLONG);
-+ if (unlikely(dentry->d_name.len > AUFS_MAX_NAMELEN))
-+ goto out;
-+
-+ sb = dir->i_sb;
-+ err = si_read_lock(sb, AuLock_FLUSH | AuLock_NOPLM);
-+ ret = ERR_PTR(err);
-+ if (unlikely(err))
-+ goto out;
-+
-+ err = au_di_init(dentry);
-+ ret = ERR_PTR(err);
-+ if (unlikely(err))
-+ goto out_si;
-+
-+ inode = NULL;
-+ npositive = 0; /* suppress a warning */
-+ parent = dentry->d_parent; /* dir inode is locked */
-+ di_read_lock_parent(parent, AuLock_IR);
-+ err = au_alive_dir(parent);
-+ if (!err)
-+ err = au_digen_test(parent, au_sigen(sb));
-+ if (!err) {
-+ /* regardless LOOKUP_CREATE, always ALLOW_NEG */
-+ npositive = au_lkup_dentry(dentry, au_dbtop(parent),
-+ AuLkup_ALLOW_NEG);
-+ err = npositive;
-+ }
-+ di_read_unlock(parent, AuLock_IR);
-+ ret = ERR_PTR(err);
-+ if (unlikely(err < 0))
-+ goto out_unlock;
-+
-+ if (npositive) {
-+ inode = au_new_inode(dentry, /*must_new*/0);
-+ if (IS_ERR(inode)) {
-+ ret = (void *)inode;
-+ inode = NULL;
-+ goto out_unlock;
-+ }
-+ }
-+
-+ if (inode)
-+ atomic_inc(&inode->i_count);
-+ ret = d_splice_alias(inode, dentry);
-+#if 0
-+ if (unlikely(d_need_lookup(dentry))) {
-+ spin_lock(&dentry->d_lock);
-+ dentry->d_flags &= ~DCACHE_NEED_LOOKUP;
-+ spin_unlock(&dentry->d_lock);
-+ } else
-+#endif
-+ if (inode) {
-+ if (!IS_ERR(ret)) {
-+ iput(inode);
-+ if (ret && ret != dentry)
-+ ii_write_unlock(inode);
-+ } else {
-+ ii_write_unlock(inode);
-+ iput(inode);
-+ inode = NULL;
-+ }
-+ }
-+
-+out_unlock:
-+ di_write_unlock(dentry);
-+out_si:
-+ si_read_unlock(sb);
-+out:
-+ return ret;
-+}
-+
-+/* ---------------------------------------------------------------------- */
-+
-+/*
-+ * very dirty and complicated aufs ->atomic_open().
-+ * aufs_atomic_open()
-+ * + au_aopen_or_create()
-+ * + add_simple()
-+ * + vfsub_atomic_open()
-+ * + branch fs ->atomic_open()
-+ * may call the actual 'open' for h_file
-+ * + inc br_nfiles only if opened
-+ * + au_aopen_no_open() or au_aopen_do_open()
-+ *
-+ * au_aopen_do_open()
-+ * + finish_open()
-+ * + au_do_aopen()
-+ * + au_do_open() the body of all 'open'
-+ * + au_do_open_nondir()
-+ * set the passed h_file
-+ *
-+ * au_aopen_no_open()
-+ * + finish_no_open()
-+ */
-+
-+struct aopen_node {
-+ struct hlist_bl_node hblist;
-+ struct file *file, *h_file;
-+};
-+
-+static int au_do_aopen(struct inode *inode, struct file *file)
-+{
-+ struct hlist_bl_head *aopen;
-+ struct hlist_bl_node *pos;
-+ struct aopen_node *node;
-+ struct au_do_open_args args = {
-+ .aopen = 1,
-+ .open = au_do_open_nondir
-+ };
-+
-+ aopen = &au_sbi(inode->i_sb)->si_aopen;
-+ hlist_bl_lock(aopen);
-+ hlist_bl_for_each_entry(node, pos, aopen, hblist)
-+ if (node->file == file) {
-+ args.h_file = node->h_file;
-+ break;
-+ }
-+ hlist_bl_unlock(aopen);
-+ /* AuDebugOn(!args.h_file); */
-+
-+ return au_do_open(file, &args);
-+}
-+
-+static int au_aopen_do_open(struct file *file, struct dentry *dentry,
-+ struct aopen_node *aopen_node)
-+{
-+ int err;
-+ struct hlist_bl_head *aopen;
-+
-+ AuLabel(here);
-+ aopen = &au_sbi(dentry->d_sb)->si_aopen;
-+ au_hbl_add(&aopen_node->hblist, aopen);
-+ err = finish_open(file, dentry, au_do_aopen);
-+ au_hbl_del(&aopen_node->hblist, aopen);
-+ /* AuDbgFile(file); */
-+ AuDbg("%pd%s%s\n", dentry,
-+ (file->f_mode & FMODE_CREATED) ? " created" : "",
-+ (file->f_mode & FMODE_OPENED) ? " opened" : "");
-+
-+ AuTraceErr(err);
-+ return err;
-+}
-+
-+static int au_aopen_no_open(struct file *file, struct dentry *dentry)
-+{
-+ int err;
-+
-+ AuLabel(here);
-+ dget(dentry);
-+ err = finish_no_open(file, dentry);
-+
-+ AuTraceErr(err);
-+ return err;
-+}
-+
-+static int aufs_atomic_open(struct inode *dir, struct dentry *dentry,
-+ struct file *file, unsigned int open_flag,
-+ umode_t create_mode)
-+{
-+ int err, did_open;
-+ unsigned int lkup_flags;
-+ aufs_bindex_t bindex;
-+ struct super_block *sb;
-+ struct dentry *parent, *d;
-+ struct vfsub_aopen_args args = {
-+ .open_flag = open_flag,
-+ .create_mode = create_mode
-+ };
-+ struct aopen_node aopen_node = {
-+ .file = file
-+ };
-+
-+ IMustLock(dir);
-+ AuDbg("open_flag 0%o\n", open_flag);
-+ AuDbgDentry(dentry);
-+
-+ err = 0;
-+ if (!au_di(dentry)) {
-+ lkup_flags = LOOKUP_OPEN;
-+ if (open_flag & O_CREAT)
-+ lkup_flags |= LOOKUP_CREATE;
-+ d = aufs_lookup(dir, dentry, lkup_flags);
-+ if (IS_ERR(d)) {
-+ err = PTR_ERR(d);
-+ AuTraceErr(err);
-+ goto out;
-+ } else if (d) {
-+ /*
-+ * obsoleted dentry found.
-+ * another error will be returned later.
-+ */
-+ d_drop(d);
-+ AuDbgDentry(d);
-+ dput(d);
-+ }
-+ AuDbgDentry(dentry);
-+ }
-+
-+ if (d_is_positive(dentry)
-+ || d_unhashed(dentry)
-+ || d_unlinked(dentry)
-+ || !(open_flag & O_CREAT)) {
-+ err = au_aopen_no_open(file, dentry);
-+ goto out; /* success */
-+ }
-+
-+ err = aufs_read_lock(dentry, AuLock_DW | AuLock_FLUSH | AuLock_GEN);
-+ if (unlikely(err))
-+ goto out;
-+
-+ sb = dentry->d_sb;
-+ parent = dentry->d_parent; /* dir is locked */
-+ di_write_lock_parent(parent);
-+ err = au_lkup_dentry(dentry, /*btop*/0, AuLkup_ALLOW_NEG);
-+ if (unlikely(err < 0))
-+ goto out_parent;
-+
-+ AuDbgDentry(dentry);
-+ if (d_is_positive(dentry)) {
-+ err = au_aopen_no_open(file, dentry);
-+ goto out_parent; /* success */
-+ }
-+
-+ args.file = alloc_empty_file(file->f_flags, current_cred());
-+ err = PTR_ERR(args.file);
-+ if (IS_ERR(args.file))
-+ goto out_parent;
-+
-+ bindex = au_dbtop(dentry);
-+ err = au_aopen_or_create(dir, dentry, &args);
-+ AuTraceErr(err);
-+ AuDbgFile(args.file);
-+ file->f_mode = args.file->f_mode & ~FMODE_OPENED;
-+ did_open = !!(args.file->f_mode & FMODE_OPENED);
-+ if (!did_open) {
-+ fput(args.file);
-+ args.file = NULL;
-+ }
-+ di_write_unlock(parent);
-+ di_write_unlock(dentry);
-+ if (unlikely(err < 0)) {
-+ if (args.file)
-+ fput(args.file);
-+ goto out_sb;
-+ }
-+
-+ if (!did_open)
-+ err = au_aopen_no_open(file, dentry);
-+ else {
-+ aopen_node.h_file = args.file;
-+ err = au_aopen_do_open(file, dentry, &aopen_node);
-+ }
-+ if (unlikely(err < 0)) {
-+ if (args.file)
-+ fput(args.file);
-+ if (did_open)
-+ au_lcnt_dec(&args.br->br_nfiles);
-+ }
-+ goto out_sb; /* success */
-+
-+out_parent:
-+ di_write_unlock(parent);
-+ di_write_unlock(dentry);
-+out_sb:
-+ si_read_unlock(sb);
-+out:
-+ AuTraceErr(err);
-+ AuDbgFile(file);
-+ return err;
-+}
-+
-+
-+/* ---------------------------------------------------------------------- */
-+
-+static int au_wr_dir_cpup(struct dentry *dentry, struct dentry *parent,
-+ const unsigned char add_entry, aufs_bindex_t bcpup,
-+ aufs_bindex_t btop)
-+{
-+ int err;
-+ struct dentry *h_parent;
-+ struct inode *h_dir;
-+
-+ if (add_entry)
-+ IMustLock(d_inode(parent));
-+ else
-+ di_write_lock_parent(parent);
-+
-+ err = 0;
-+ if (!au_h_dptr(parent, bcpup)) {
-+ if (btop > bcpup)
-+ err = au_cpup_dirs(dentry, bcpup);
-+ else if (btop < bcpup)
-+ err = au_cpdown_dirs(dentry, bcpup);
-+ else
-+ BUG();
-+ }
-+ if (!err && add_entry && !au_ftest_wrdir(add_entry, TMPFILE)) {
-+ h_parent = au_h_dptr(parent, bcpup);
-+ h_dir = d_inode(h_parent);
-+ inode_lock_shared_nested(h_dir, AuLsc_I_PARENT);
-+ err = au_lkup_neg(dentry, bcpup, /*wh*/0);
-+ /* todo: no unlock here */
-+ inode_unlock_shared(h_dir);
-+
-+ AuDbg("bcpup %d\n", bcpup);
-+ if (!err) {
-+ if (d_really_is_negative(dentry))
-+ au_set_h_dptr(dentry, btop, NULL);
-+ au_update_dbrange(dentry, /*do_put_zero*/0);
-+ }
-+ }
-+
-+ if (!add_entry)
-+ di_write_unlock(parent);
-+ if (!err)
-+ err = bcpup; /* success */
-+
-+ AuTraceErr(err);
-+ return err;
-+}
-+
-+/*
-+ * decide the branch and the parent dir where we will create a new entry.
-+ * returns new bindex or an error.
-+ * copyup the parent dir if needed.
-+ */
-+int au_wr_dir(struct dentry *dentry, struct dentry *src_dentry,
-+ struct au_wr_dir_args *args)
-+{
-+ int err;
-+ unsigned int flags;
-+ aufs_bindex_t bcpup, btop, src_btop;
-+ const unsigned char add_entry
-+ = au_ftest_wrdir(args->flags, ADD_ENTRY)
-+ | au_ftest_wrdir(args->flags, TMPFILE);
-+ struct super_block *sb;
-+ struct dentry *parent;
-+ struct au_sbinfo *sbinfo;
-+
-+ sb = dentry->d_sb;
-+ sbinfo = au_sbi(sb);
-+ parent = dget_parent(dentry);
-+ btop = au_dbtop(dentry);
-+ bcpup = btop;
-+ if (args->force_btgt < 0) {
-+ if (src_dentry) {
-+ src_btop = au_dbtop(src_dentry);
-+ if (src_btop < btop)
-+ bcpup = src_btop;
-+ } else if (add_entry) {
-+ flags = 0;
-+ if (au_ftest_wrdir(args->flags, ISDIR))
-+ au_fset_wbr(flags, DIR);
-+ err = AuWbrCreate(sbinfo, dentry, flags);
-+ bcpup = err;
-+ }
-+
-+ if (bcpup < 0 || au_test_ro(sb, bcpup, d_inode(dentry))) {
-+ if (add_entry)
-+ err = AuWbrCopyup(sbinfo, dentry);
-+ else {
-+ if (!IS_ROOT(dentry)) {
-+ di_read_lock_parent(parent, !AuLock_IR);
-+ err = AuWbrCopyup(sbinfo, dentry);
-+ di_read_unlock(parent, !AuLock_IR);
-+ } else
-+ err = AuWbrCopyup(sbinfo, dentry);
-+ }
-+ bcpup = err;
-+ if (unlikely(err < 0))
-+ goto out;
-+ }
-+ } else {
-+ bcpup = args->force_btgt;
-+ AuDebugOn(au_test_ro(sb, bcpup, d_inode(dentry)));
-+ }
-+
-+ AuDbg("btop %d, bcpup %d\n", btop, bcpup);
-+ err = bcpup;
-+ if (bcpup == btop)
-+ goto out; /* success */
-+
-+ /* copyup the new parent into the branch we process */
-+ err = au_wr_dir_cpup(dentry, parent, add_entry, bcpup, btop);
-+ if (err >= 0) {
-+ if (d_really_is_negative(dentry)) {
-+ au_set_h_dptr(dentry, btop, NULL);
-+ au_set_dbtop(dentry, bcpup);
-+ au_set_dbbot(dentry, bcpup);
-+ }
-+ AuDebugOn(add_entry
-+ && !au_ftest_wrdir(args->flags, TMPFILE)
-+ && !au_h_dptr(dentry, bcpup));
-+ }
-+
-+out:
-+ dput(parent);
-+ return err;
-+}
-+
-+/* ---------------------------------------------------------------------- */
-+
-+void au_pin_hdir_unlock(struct au_pin *p)
-+{
-+ if (p->hdir)
-+ au_hn_inode_unlock(p->hdir);
-+}
-+
-+int au_pin_hdir_lock(struct au_pin *p)
-+{
-+ int err;
-+
-+ err = 0;
-+ if (!p->hdir)
-+ goto out;
-+
-+ /* even if an error happens later, keep this lock */
-+ au_hn_inode_lock_nested(p->hdir, p->lsc_hi);
-+
-+ err = -EBUSY;
-+ if (unlikely(p->hdir->hi_inode != d_inode(p->h_parent)))
-+ goto out;
-+
-+ err = 0;
-+ if (p->h_dentry)
-+ err = au_h_verify(p->h_dentry, p->udba, p->hdir->hi_inode,
-+ p->h_parent, p->br);
-+
-+out:
-+ return err;
-+}
-+
-+int au_pin_hdir_relock(struct au_pin *p)
-+{
-+ int err, i;
-+ struct inode *h_i;
-+ struct dentry *h_d[] = {
-+ p->h_dentry,
-+ p->h_parent
-+ };
-+
-+ err = au_pin_hdir_lock(p);
-+ if (unlikely(err))
-+ goto out;
-+
-+ for (i = 0; !err && i < sizeof(h_d)/sizeof(*h_d); i++) {
-+ if (!h_d[i])
-+ continue;
-+ if (d_is_positive(h_d[i])) {
-+ h_i = d_inode(h_d[i]);
-+ err = !h_i->i_nlink;
-+ }
-+ }
-+
-+out:
-+ return err;
-+}
-+
-+static void au_pin_hdir_set_owner(struct au_pin *p, struct task_struct *task)
-+{
-+#if !defined(CONFIG_RWSEM_GENERIC_SPINLOCK) && defined(CONFIG_RWSEM_SPIN_ON_OWNER)
-+ p->hdir->hi_inode->i_rwsem.owner = task;
-+#endif
-+}
-+
-+void au_pin_hdir_acquire_nest(struct au_pin *p)
-+{
-+ if (p->hdir) {
-+ rwsem_acquire_nest(&p->hdir->hi_inode->i_rwsem.dep_map,
-+ p->lsc_hi, 0, NULL, _RET_IP_);
-+ au_pin_hdir_set_owner(p, current);
-+ }
-+}
-+
-+void au_pin_hdir_release(struct au_pin *p)
-+{
-+ if (p->hdir) {
-+ au_pin_hdir_set_owner(p, p->task);
-+ rwsem_release(&p->hdir->hi_inode->i_rwsem.dep_map, 1, _RET_IP_);
-+ }
-+}
-+
-+struct dentry *au_pinned_h_parent(struct au_pin *pin)
-+{
-+ if (pin && pin->parent)
-+ return au_h_dptr(pin->parent, pin->bindex);
-+ return NULL;
-+}
-+
-+void au_unpin(struct au_pin *p)
-+{
-+ if (p->hdir)
-+ au_pin_hdir_unlock(p);
-+ if (p->h_mnt && au_ftest_pin(p->flags, MNT_WRITE))
-+ vfsub_mnt_drop_write(p->h_mnt);
-+ if (!p->hdir)
-+ return;
-+
-+ if (!au_ftest_pin(p->flags, DI_LOCKED))
-+ di_read_unlock(p->parent, AuLock_IR);
-+ iput(p->hdir->hi_inode);
-+ dput(p->parent);
-+ p->parent = NULL;
-+ p->hdir = NULL;
-+ p->h_mnt = NULL;
-+ /* do not clear p->task */
-+}
-+
-+int au_do_pin(struct au_pin *p)
-+{
-+ int err;
-+ struct super_block *sb;
-+ struct inode *h_dir;
-+
-+ err = 0;
-+ sb = p->dentry->d_sb;
-+ p->br = au_sbr(sb, p->bindex);
-+ if (IS_ROOT(p->dentry)) {
-+ if (au_ftest_pin(p->flags, MNT_WRITE)) {
-+ p->h_mnt = au_br_mnt(p->br);
-+ err = vfsub_mnt_want_write(p->h_mnt);
-+ if (unlikely(err)) {
-+ au_fclr_pin(p->flags, MNT_WRITE);
-+ goto out_err;
-+ }
-+ }
-+ goto out;
-+ }
-+
-+ p->h_dentry = NULL;
-+ if (p->bindex <= au_dbbot(p->dentry))
-+ p->h_dentry = au_h_dptr(p->dentry, p->bindex);
-+
-+ p->parent = dget_parent(p->dentry);
-+ if (!au_ftest_pin(p->flags, DI_LOCKED))
-+ di_read_lock(p->parent, AuLock_IR, p->lsc_di);
-+
-+ h_dir = NULL;
-+ p->h_parent = au_h_dptr(p->parent, p->bindex);
-+ p->hdir = au_hi(d_inode(p->parent), p->bindex);
-+ if (p->hdir)
-+ h_dir = p->hdir->hi_inode;
-+
-+ /*
-+ * udba case, or
-+ * if DI_LOCKED is not set, then p->parent may be different
-+ * and h_parent can be NULL.
-+ */
-+ if (unlikely(!p->hdir || !h_dir || !p->h_parent)) {
-+ err = -EBUSY;
-+ if (!au_ftest_pin(p->flags, DI_LOCKED))
-+ di_read_unlock(p->parent, AuLock_IR);
-+ dput(p->parent);
-+ p->parent = NULL;
-+ goto out_err;
-+ }
-+
-+ if (au_ftest_pin(p->flags, MNT_WRITE)) {
-+ p->h_mnt = au_br_mnt(p->br);
-+ err = vfsub_mnt_want_write(p->h_mnt);
-+ if (unlikely(err)) {
-+ au_fclr_pin(p->flags, MNT_WRITE);
-+ if (!au_ftest_pin(p->flags, DI_LOCKED))
-+ di_read_unlock(p->parent, AuLock_IR);
-+ dput(p->parent);
-+ p->parent = NULL;
-+ goto out_err;
-+ }
-+ }
-+
-+ au_igrab(h_dir);
-+ err = au_pin_hdir_lock(p);
-+ if (!err)
-+ goto out; /* success */
-+
-+ au_unpin(p);
-+
-+out_err:
-+ pr_err("err %d\n", err);
-+ err = au_busy_or_stale();
-+out:
-+ return err;
-+}
-+
-+void au_pin_init(struct au_pin *p, struct dentry *dentry,
-+ aufs_bindex_t bindex, int lsc_di, int lsc_hi,
-+ unsigned int udba, unsigned char flags)
-+{
-+ p->dentry = dentry;
-+ p->udba = udba;
-+ p->lsc_di = lsc_di;
-+ p->lsc_hi = lsc_hi;
-+ p->flags = flags;
-+ p->bindex = bindex;
-+
-+ p->parent = NULL;
-+ p->hdir = NULL;
-+ p->h_mnt = NULL;
-+
-+ p->h_dentry = NULL;
-+ p->h_parent = NULL;
-+ p->br = NULL;
-+ p->task = current;
-+}
-+
-+int au_pin(struct au_pin *pin, struct dentry *dentry, aufs_bindex_t bindex,
-+ unsigned int udba, unsigned char flags)
-+{
-+ au_pin_init(pin, dentry, bindex, AuLsc_DI_PARENT, AuLsc_I_PARENT2,
-+ udba, flags);
-+ return au_do_pin(pin);
-+}
-+
-+/* ---------------------------------------------------------------------- */
-+
-+/*
-+ * ->setattr() and ->getattr() are called in various cases.
-+ * chmod, stat: dentry is revalidated.
-+ * fchmod, fstat: file and dentry are not revalidated, additionally they may be
-+ * unhashed.
-+ * for ->setattr(), ia->ia_file is passed from ftruncate only.
-+ */
-+/* todo: consolidate with do_refresh() and simple_reval_dpath() */
-+int au_reval_for_attr(struct dentry *dentry, unsigned int sigen)
-+{
-+ int err;
-+ struct dentry *parent;
-+
-+ err = 0;
-+ if (au_digen_test(dentry, sigen)) {
-+ parent = dget_parent(dentry);
-+ di_read_lock_parent(parent, AuLock_IR);
-+ err = au_refresh_dentry(dentry, parent);
-+ di_read_unlock(parent, AuLock_IR);
-+ dput(parent);
-+ }
-+
-+ AuTraceErr(err);
-+ return err;
-+}
-+
-+int au_pin_and_icpup(struct dentry *dentry, struct iattr *ia,
-+ struct au_icpup_args *a)
-+{
-+ int err;
-+ loff_t sz;
-+ aufs_bindex_t btop, ibtop;
-+ struct dentry *hi_wh, *parent;
-+ struct inode *inode;
-+ struct au_wr_dir_args wr_dir_args = {
-+ .force_btgt = -1,
-+ .flags = 0
-+ };
-+
-+ if (d_is_dir(dentry))
-+ au_fset_wrdir(wr_dir_args.flags, ISDIR);
-+ /* plink or hi_wh() case */
-+ btop = au_dbtop(dentry);
-+ inode = d_inode(dentry);
-+ ibtop = au_ibtop(inode);
-+ if (btop != ibtop && !au_test_ro(inode->i_sb, ibtop, inode))
-+ wr_dir_args.force_btgt = ibtop;
-+ err = au_wr_dir(dentry, /*src_dentry*/NULL, &wr_dir_args);
-+ if (unlikely(err < 0))
-+ goto out;
-+ a->btgt = err;
-+ if (err != btop)
-+ au_fset_icpup(a->flags, DID_CPUP);
-+
-+ err = 0;
-+ a->pin_flags = AuPin_MNT_WRITE;
-+ parent = NULL;
-+ if (!IS_ROOT(dentry)) {
-+ au_fset_pin(a->pin_flags, DI_LOCKED);
-+ parent = dget_parent(dentry);
-+ di_write_lock_parent(parent);
-+ }
-+
-+ err = au_pin(&a->pin, dentry, a->btgt, a->udba, a->pin_flags);
-+ if (unlikely(err))
-+ goto out_parent;
-+
-+ sz = -1;
-+ a->h_path.dentry = au_h_dptr(dentry, btop);
-+ a->h_inode = d_inode(a->h_path.dentry);
-+ if (ia && (ia->ia_valid & ATTR_SIZE)) {
-+ inode_lock_shared_nested(a->h_inode, AuLsc_I_CHILD);
-+ if (ia->ia_size < i_size_read(a->h_inode))
-+ sz = ia->ia_size;
-+ inode_unlock_shared(a->h_inode);
-+ }
-+
-+ hi_wh = NULL;
-+ if (au_ftest_icpup(a->flags, DID_CPUP) && d_unlinked(dentry)) {
-+ hi_wh = au_hi_wh(inode, a->btgt);
-+ if (!hi_wh) {
-+ struct au_cp_generic cpg = {
-+ .dentry = dentry,
-+ .bdst = a->btgt,
-+ .bsrc = -1,
-+ .len = sz,
-+ .pin = &a->pin
-+ };
-+ err = au_sio_cpup_wh(&cpg, /*file*/NULL);
-+ if (unlikely(err))
-+ goto out_unlock;
-+ hi_wh = au_hi_wh(inode, a->btgt);
-+ /* todo: revalidate hi_wh? */
-+ }
-+ }
-+
-+ if (parent) {
-+ au_pin_set_parent_lflag(&a->pin, /*lflag*/0);
-+ di_downgrade_lock(parent, AuLock_IR);
-+ dput(parent);
-+ parent = NULL;
-+ }
-+ if (!au_ftest_icpup(a->flags, DID_CPUP))
-+ goto out; /* success */
-+
-+ if (!d_unhashed(dentry)) {
-+ struct au_cp_generic cpg = {
-+ .dentry = dentry,
-+ .bdst = a->btgt,
-+ .bsrc = btop,
-+ .len = sz,
-+ .pin = &a->pin,
-+ .flags = AuCpup_DTIME | AuCpup_HOPEN
-+ };
-+ err = au_sio_cpup_simple(&cpg);
-+ if (!err)
-+ a->h_path.dentry = au_h_dptr(dentry, a->btgt);
-+ } else if (!hi_wh)
-+ a->h_path.dentry = au_h_dptr(dentry, a->btgt);
-+ else
-+ a->h_path.dentry = hi_wh; /* do not dget here */
-+
-+out_unlock:
-+ a->h_inode = d_inode(a->h_path.dentry);
-+ if (!err)
-+ goto out; /* success */
-+ au_unpin(&a->pin);
-+out_parent:
-+ if (parent) {
-+ di_write_unlock(parent);
-+ dput(parent);
-+ }
-+out:
-+ if (!err)
-+ inode_lock_nested(a->h_inode, AuLsc_I_CHILD);
-+ return err;
-+}
-+
-+static int aufs_setattr(struct dentry *dentry, struct iattr *ia)
-+{
-+ int err;
-+ struct inode *inode, *delegated;
-+ struct super_block *sb;
-+ struct file *file;
-+ struct au_icpup_args *a;
-+
-+ inode = d_inode(dentry);
-+ IMustLock(inode);
-+
-+ err = setattr_prepare(dentry, ia);
-+ if (unlikely(err))
-+ goto out;
-+
-+ err = -ENOMEM;
-+ a = kzalloc(sizeof(*a), GFP_NOFS);
-+ if (unlikely(!a))
-+ goto out;
-+
-+ if (ia->ia_valid & (ATTR_KILL_SUID | ATTR_KILL_SGID))
-+ ia->ia_valid &= ~ATTR_MODE;
-+
-+ file = NULL;
-+ sb = dentry->d_sb;
-+ err = si_read_lock(sb, AuLock_FLUSH | AuLock_NOPLM);
-+ if (unlikely(err))
-+ goto out_kfree;
-+
-+ if (ia->ia_valid & ATTR_FILE) {
-+ /* currently ftruncate(2) only */
-+ AuDebugOn(!d_is_reg(dentry));
-+ file = ia->ia_file;
-+ err = au_reval_and_lock_fdi(file, au_reopen_nondir, /*wlock*/1,
-+ /*fi_lsc*/0);
-+ if (unlikely(err))
-+ goto out_si;
-+ ia->ia_file = au_hf_top(file);
-+ a->udba = AuOpt_UDBA_NONE;
-+ } else {
-+ /* fchmod() doesn't pass ia_file */
-+ a->udba = au_opt_udba(sb);
-+ di_write_lock_child(dentry);
-+ /* no d_unlinked(), to set UDBA_NONE for root */
-+ if (d_unhashed(dentry))
-+ a->udba = AuOpt_UDBA_NONE;
-+ if (a->udba != AuOpt_UDBA_NONE) {
-+ AuDebugOn(IS_ROOT(dentry));
-+ err = au_reval_for_attr(dentry, au_sigen(sb));
-+ if (unlikely(err))
-+ goto out_dentry;
-+ }
-+ }
-+
-+ err = au_pin_and_icpup(dentry, ia, a);
-+ if (unlikely(err < 0))
-+ goto out_dentry;
-+ if (au_ftest_icpup(a->flags, DID_CPUP)) {
-+ ia->ia_file = NULL;
-+ ia->ia_valid &= ~ATTR_FILE;
-+ }
-+
-+ a->h_path.mnt = au_sbr_mnt(sb, a->btgt);
-+ if ((ia->ia_valid & (ATTR_MODE | ATTR_CTIME))
-+ == (ATTR_MODE | ATTR_CTIME)) {
-+ err = security_path_chmod(&a->h_path, ia->ia_mode);
-+ if (unlikely(err))
-+ goto out_unlock;
-+ } else if ((ia->ia_valid & (ATTR_UID | ATTR_GID))
-+ && (ia->ia_valid & ATTR_CTIME)) {
-+ err = security_path_chown(&a->h_path, ia->ia_uid, ia->ia_gid);
-+ if (unlikely(err))
-+ goto out_unlock;
-+ }
-+
-+ if (ia->ia_valid & ATTR_SIZE) {
-+ struct file *f;
-+
-+ if (ia->ia_size < i_size_read(inode))
-+ /* unmap only */
-+ truncate_setsize(inode, ia->ia_size);
-+
-+ f = NULL;
-+ if (ia->ia_valid & ATTR_FILE)
-+ f = ia->ia_file;
-+ inode_unlock(a->h_inode);
-+ err = vfsub_trunc(&a->h_path, ia->ia_size, ia->ia_valid, f);
-+ inode_lock_nested(a->h_inode, AuLsc_I_CHILD);
-+ } else {
-+ delegated = NULL;
-+ while (1) {
-+ err = vfsub_notify_change(&a->h_path, ia, &delegated);
-+ if (delegated) {
-+ err = break_deleg_wait(&delegated);
-+ if (!err)
-+ continue;
-+ }
-+ break;
-+ }
-+ }
-+ /*
-+ * regardless aufs 'acl' option setting.
-+ * why don't all acl-aware fs call this func from their ->setattr()?
-+ */
-+ if (!err && (ia->ia_valid & ATTR_MODE))
-+ err = vfsub_acl_chmod(a->h_inode, ia->ia_mode);
-+ if (!err)
-+ au_cpup_attr_changeable(inode);
-+
-+out_unlock:
-+ inode_unlock(a->h_inode);
-+ au_unpin(&a->pin);
-+ if (unlikely(err))
-+ au_update_dbtop(dentry);
-+out_dentry:
-+ di_write_unlock(dentry);
-+ if (file) {
-+ fi_write_unlock(file);
-+ ia->ia_file = file;
-+ ia->ia_valid |= ATTR_FILE;
-+ }
-+out_si:
-+ si_read_unlock(sb);
-+out_kfree:
-+ au_kfree_rcu(a);
-+out:
-+ AuTraceErr(err);
-+ return err;
-+}
-+
-+#if IS_ENABLED(CONFIG_AUFS_XATTR) || IS_ENABLED(CONFIG_FS_POSIX_ACL)
-+static int au_h_path_to_set_attr(struct dentry *dentry,
-+ struct au_icpup_args *a, struct path *h_path)
-+{
-+ int err;
-+ struct super_block *sb;
-+
-+ sb = dentry->d_sb;
-+ a->udba = au_opt_udba(sb);
-+ /* no d_unlinked(), to set UDBA_NONE for root */
-+ if (d_unhashed(dentry))
-+ a->udba = AuOpt_UDBA_NONE;
-+ if (a->udba != AuOpt_UDBA_NONE) {
-+ AuDebugOn(IS_ROOT(dentry));
-+ err = au_reval_for_attr(dentry, au_sigen(sb));
-+ if (unlikely(err))
-+ goto out;
-+ }
-+ err = au_pin_and_icpup(dentry, /*ia*/NULL, a);
-+ if (unlikely(err < 0))
-+ goto out;
-+
-+ h_path->dentry = a->h_path.dentry;
-+ h_path->mnt = au_sbr_mnt(sb, a->btgt);
-+
-+out:
-+ return err;
-+}
-+
-+ssize_t au_sxattr(struct dentry *dentry, struct inode *inode,
-+ struct au_sxattr *arg)
-+{
-+ int err;
-+ struct path h_path;
-+ struct super_block *sb;
-+ struct au_icpup_args *a;
-+ struct inode *h_inode;
-+
-+ IMustLock(inode);
-+
-+ err = -ENOMEM;
-+ a = kzalloc(sizeof(*a), GFP_NOFS);
-+ if (unlikely(!a))
-+ goto out;
-+
-+ sb = dentry->d_sb;
-+ err = si_read_lock(sb, AuLock_FLUSH | AuLock_NOPLM);
-+ if (unlikely(err))
-+ goto out_kfree;
-+
-+ h_path.dentry = NULL; /* silence gcc */
-+ di_write_lock_child(dentry);
-+ err = au_h_path_to_set_attr(dentry, a, &h_path);
-+ if (unlikely(err))
-+ goto out_di;
-+
-+ inode_unlock(a->h_inode);
-+ switch (arg->type) {
-+ case AU_XATTR_SET:
-+ AuDebugOn(d_is_negative(h_path.dentry));
-+ err = vfsub_setxattr(h_path.dentry,
-+ arg->u.set.name, arg->u.set.value,
-+ arg->u.set.size, arg->u.set.flags);
-+ break;
-+ case AU_ACL_SET:
-+ err = -EOPNOTSUPP;
-+ h_inode = d_inode(h_path.dentry);
-+ if (h_inode->i_op->set_acl)
-+ /* this will call posix_acl_update_mode */
-+ err = h_inode->i_op->set_acl(h_inode,
-+ arg->u.acl_set.acl,
-+ arg->u.acl_set.type);
-+ break;
-+ }
-+ if (!err)
-+ au_cpup_attr_timesizes(inode);
-+
-+ au_unpin(&a->pin);
-+ if (unlikely(err))
-+ au_update_dbtop(dentry);
-+
-+out_di:
-+ di_write_unlock(dentry);
-+ si_read_unlock(sb);
-+out_kfree:
-+ au_kfree_rcu(a);
-+out:
-+ AuTraceErr(err);
-+ return err;
-+}
-+#endif
-+
-+static void au_refresh_iattr(struct inode *inode, struct kstat *st,
-+ unsigned int nlink)
-+{
-+ unsigned int n;
-+
-+ inode->i_mode = st->mode;
-+ /* don't i_[ug]id_write() here */
-+ inode->i_uid = st->uid;
-+ inode->i_gid = st->gid;
-+ inode->i_atime = st->atime;
-+ inode->i_mtime = st->mtime;
-+ inode->i_ctime = st->ctime;
-+
-+ au_cpup_attr_nlink(inode, /*force*/0);
-+ if (S_ISDIR(inode->i_mode)) {
-+ n = inode->i_nlink;
-+ n -= nlink;
-+ n += st->nlink;
-+ smp_mb(); /* for i_nlink */
-+ /* 0 can happen */
-+ set_nlink(inode, n);
-+ }
-+
-+ spin_lock(&inode->i_lock);
-+ inode->i_blocks = st->blocks;
-+ i_size_write(inode, st->size);
-+ spin_unlock(&inode->i_lock);
-+}
-+
-+/*
-+ * common routine for aufs_getattr() and au_getxattr().
-+ * returns zero or negative (an error).
-+ * @dentry will be read-locked in success.
-+ */
-+int au_h_path_getattr(struct dentry *dentry, int force, struct path *h_path,
-+ int locked)
-+{
-+ int err;
-+ unsigned int mnt_flags, sigen;
-+ unsigned char udba_none;
-+ aufs_bindex_t bindex;
-+ struct super_block *sb, *h_sb;
-+ struct inode *inode;
-+
-+ h_path->mnt = NULL;
-+ h_path->dentry = NULL;
-+
-+ err = 0;
-+ sb = dentry->d_sb;
-+ mnt_flags = au_mntflags(sb);
-+ udba_none = !!au_opt_test(mnt_flags, UDBA_NONE);
-+
-+ if (unlikely(locked))
-+ goto body; /* skip locking dinfo */
-+
-+ /* support fstat(2) */
-+ if (!d_unlinked(dentry) && !udba_none) {
-+ sigen = au_sigen(sb);
-+ err = au_digen_test(dentry, sigen);
-+ if (!err) {
-+ di_read_lock_child(dentry, AuLock_IR);
-+ err = au_dbrange_test(dentry);
-+ if (unlikely(err)) {
-+ di_read_unlock(dentry, AuLock_IR);
-+ goto out;
-+ }
-+ } else {
-+ AuDebugOn(IS_ROOT(dentry));
-+ di_write_lock_child(dentry);
-+ err = au_dbrange_test(dentry);
-+ if (!err)
-+ err = au_reval_for_attr(dentry, sigen);
-+ if (!err)
-+ di_downgrade_lock(dentry, AuLock_IR);
-+ else {
-+ di_write_unlock(dentry);
-+ goto out;
-+ }
-+ }
-+ } else
-+ di_read_lock_child(dentry, AuLock_IR);
-+
-+body:
-+ inode = d_inode(dentry);
-+ bindex = au_ibtop(inode);
-+ h_path->mnt = au_sbr_mnt(sb, bindex);
-+ h_sb = h_path->mnt->mnt_sb;
-+ if (!force
-+ && !au_test_fs_bad_iattr(h_sb)
-+ && udba_none)
-+ goto out; /* success */
-+
-+ if (au_dbtop(dentry) == bindex)
-+ h_path->dentry = au_h_dptr(dentry, bindex);
-+ else if (au_opt_test(mnt_flags, PLINK) && au_plink_test(inode)) {
-+ h_path->dentry = au_plink_lkup(inode, bindex);
-+ if (IS_ERR(h_path->dentry))
-+ /* pretending success */
-+ h_path->dentry = NULL;
-+ else
-+ dput(h_path->dentry);
-+ }
-+
-+out:
-+ return err;
-+}
-+
-+static int aufs_getattr(const struct path *path, struct kstat *st,
-+ u32 request, unsigned int query)
-+{
-+ int err;
-+ unsigned char positive;
-+ struct path h_path;
-+ struct dentry *dentry;
-+ struct inode *inode;
-+ struct super_block *sb;
-+
-+ dentry = path->dentry;
-+ inode = d_inode(dentry);
-+ sb = dentry->d_sb;
-+ err = si_read_lock(sb, AuLock_FLUSH | AuLock_NOPLM);
-+ if (unlikely(err))
-+ goto out;
-+ err = au_h_path_getattr(dentry, /*force*/0, &h_path, /*locked*/0);
-+ if (unlikely(err))
-+ goto out_si;
-+ if (unlikely(!h_path.dentry))
-+ /* illegally overlapped or something */
-+ goto out_fill; /* pretending success */
-+
-+ positive = d_is_positive(h_path.dentry);
-+ if (positive)
-+ /* no vfsub version */
-+ err = vfs_getattr(&h_path, st, request, query);
-+ if (!err) {
-+ if (positive)
-+ au_refresh_iattr(inode, st,
-+ d_inode(h_path.dentry)->i_nlink);
-+ goto out_fill; /* success */
-+ }
-+ AuTraceErr(err);
-+ goto out_di;
-+
-+out_fill:
-+ generic_fillattr(inode, st);
-+out_di:
-+ di_read_unlock(dentry, AuLock_IR);
-+out_si:
-+ si_read_unlock(sb);
-+out:
-+ AuTraceErr(err);
-+ return err;
-+}
-+
-+/* ---------------------------------------------------------------------- */
-+
-+static const char *aufs_get_link(struct dentry *dentry, struct inode *inode,
-+ struct delayed_call *done)
-+{
-+ const char *ret;
-+ struct dentry *h_dentry;
-+ struct inode *h_inode;
-+ int err;
-+ aufs_bindex_t bindex;
-+
-+ ret = NULL; /* suppress a warning */
-+ err = -ECHILD;
-+ if (!dentry)
-+ goto out;
-+
-+ err = aufs_read_lock(dentry, AuLock_IR | AuLock_GEN);
-+ if (unlikely(err))
-+ goto out;
-+
-+ err = au_d_hashed_positive(dentry);
-+ if (unlikely(err))
-+ goto out_unlock;
-+
-+ err = -EINVAL;
-+ inode = d_inode(dentry);
-+ bindex = au_ibtop(inode);
-+ h_inode = au_h_iptr(inode, bindex);
-+ if (unlikely(!h_inode->i_op->get_link))
-+ goto out_unlock;
-+
-+ err = -EBUSY;
-+ h_dentry = NULL;
-+ if (au_dbtop(dentry) <= bindex) {
-+ h_dentry = au_h_dptr(dentry, bindex);
-+ if (h_dentry)
-+ dget(h_dentry);
-+ }
-+ if (!h_dentry) {
-+ h_dentry = d_find_any_alias(h_inode);
-+ if (IS_ERR(h_dentry)) {
-+ err = PTR_ERR(h_dentry);
-+ goto out_unlock;
-+ }
-+ }
-+ if (unlikely(!h_dentry))
-+ goto out_unlock;
-+
-+ err = 0;
-+ AuDbg("%ps\n", h_inode->i_op->get_link);
-+ AuDbgDentry(h_dentry);
-+ ret = vfs_get_link(h_dentry, done);
-+ dput(h_dentry);
-+ if (IS_ERR(ret))
-+ err = PTR_ERR(ret);
-+
-+out_unlock:
-+ aufs_read_unlock(dentry, AuLock_IR);
-+out:
-+ if (unlikely(err))
-+ ret = ERR_PTR(err);
-+ AuTraceErrPtr(ret);
-+ return ret;
-+}
-+
-+/* ---------------------------------------------------------------------- */
-+
-+static int au_is_special(struct inode *inode)
-+{
-+ return (inode->i_mode & (S_IFBLK | S_IFCHR | S_IFIFO | S_IFSOCK));
-+}
-+
-+static int aufs_update_time(struct inode *inode, struct timespec64 *ts,
-+ int flags)
-+{
-+ int err;
-+ aufs_bindex_t bindex;
-+ struct super_block *sb;
-+ struct inode *h_inode;
-+ struct vfsmount *h_mnt;
-+
-+ sb = inode->i_sb;
-+ WARN_ONCE((flags & S_ATIME) && !IS_NOATIME(inode),
-+ "unexpected s_flags 0x%lx", sb->s_flags);
-+
-+ /* mmap_sem might be acquired already, cf. aufs_mmap() */
-+ lockdep_off();
-+ si_read_lock(sb, AuLock_FLUSH);
-+ ii_write_lock_child(inode);
-+
-+ err = 0;
-+ bindex = au_ibtop(inode);
-+ h_inode = au_h_iptr(inode, bindex);
-+ if (!au_test_ro(sb, bindex, inode)) {
-+ h_mnt = au_sbr_mnt(sb, bindex);
-+ err = vfsub_mnt_want_write(h_mnt);
-+ if (!err) {
-+ err = vfsub_update_time(h_inode, ts, flags);
-+ vfsub_mnt_drop_write(h_mnt);
-+ }
-+ } else if (au_is_special(h_inode)) {
-+ /*
-+ * Never copy-up here.
-+ * These special files may already be opened and used for
-+ * communicating. If we copied it up, then the communication
-+ * would be corrupted.
-+ */
-+ AuWarn1("timestamps for i%lu are ignored "
-+ "since it is on readonly branch (hi%lu).\n",
-+ inode->i_ino, h_inode->i_ino);
-+ } else if (flags & ~S_ATIME) {
-+ err = -EIO;
-+ AuIOErr1("unexpected flags 0x%x\n", flags);
-+ AuDebugOn(1);
-+ }
-+
-+ if (!err)
-+ au_cpup_attr_timesizes(inode);
-+ ii_write_unlock(inode);
-+ si_read_unlock(sb);
-+ lockdep_on();
-+
-+ if (!err && (flags & S_VERSION))
-+ inode_inc_iversion(inode);
-+
-+ return err;
-+}
-+
-+/* ---------------------------------------------------------------------- */
-+
-+/* no getattr version will be set by module.c:aufs_init() */
-+struct inode_operations aufs_iop_nogetattr[AuIop_Last],
-+ aufs_iop[] = {
-+ [AuIop_SYMLINK] = {
-+ .permission = aufs_permission,
-+#ifdef CONFIG_FS_POSIX_ACL
-+ .get_acl = aufs_get_acl,
-+ .set_acl = aufs_set_acl, /* unsupport for symlink? */
-+#endif
-+
-+ .setattr = aufs_setattr,
-+ .getattr = aufs_getattr,
-+
-+#ifdef CONFIG_AUFS_XATTR
-+ .listxattr = aufs_listxattr,
-+#endif
-+
-+ .get_link = aufs_get_link,
-+
-+ /* .update_time = aufs_update_time */
-+ },
-+ [AuIop_DIR] = {
-+ .create = aufs_create,
-+ .lookup = aufs_lookup,
-+ .link = aufs_link,
-+ .unlink = aufs_unlink,
-+ .symlink = aufs_symlink,
-+ .mkdir = aufs_mkdir,
-+ .rmdir = aufs_rmdir,
-+ .mknod = aufs_mknod,
-+ .rename = aufs_rename,
-+
-+ .permission = aufs_permission,
-+#ifdef CONFIG_FS_POSIX_ACL
-+ .get_acl = aufs_get_acl,
-+ .set_acl = aufs_set_acl,
-+#endif
-+
-+ .setattr = aufs_setattr,
-+ .getattr = aufs_getattr,
-+
-+#ifdef CONFIG_AUFS_XATTR
-+ .listxattr = aufs_listxattr,
-+#endif
-+
-+ .update_time = aufs_update_time,
-+ .atomic_open = aufs_atomic_open,
-+ .tmpfile = aufs_tmpfile
-+ },
-+ [AuIop_OTHER] = {
-+ .permission = aufs_permission,
-+#ifdef CONFIG_FS_POSIX_ACL
-+ .get_acl = aufs_get_acl,
-+ .set_acl = aufs_set_acl,
-+#endif
-+
-+ .setattr = aufs_setattr,
-+ .getattr = aufs_getattr,
-+
-+#ifdef CONFIG_AUFS_XATTR
-+ .listxattr = aufs_listxattr,
-+#endif
-+
-+ .update_time = aufs_update_time
-+ }
-+};
-diff --git a/fs/aufs/i_op_add.c b/fs/aufs/i_op_add.c
-new file mode 100644
-index 000000000000..af6893e61066
---- /dev/null
-+++ b/fs/aufs/i_op_add.c
-@@ -0,0 +1,936 @@
-+// SPDX-License-Identifier: GPL-2.0
-+/*
-+ * Copyright (C) 2005-2019 Junjiro R. Okajima
-+ *
-+ * This program, aufs is free software; you can redistribute it and/or modify
-+ * it under the terms of the GNU General Public License as published by
-+ * the Free Software Foundation; either version 2 of the License, or
-+ * (at your option) any later version.
-+ *
-+ * This program is distributed in the hope that it will be useful,
-+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
-+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
-+ * GNU General Public License for more details.
-+ *
-+ * You should have received a copy of the GNU General Public License
-+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
-+ */
-+
-+/*
-+ * inode operations (add entry)
-+ */
-+
-+#include <linux/iversion.h>
-+#include "aufs.h"
-+
-+/*
-+ * final procedure of adding a new entry, except link(2).
-+ * remove whiteout, instantiate, copyup the parent dir's times and size
-+ * and update version.
-+ * if it failed, re-create the removed whiteout.
-+ */
-+static int epilog(struct inode *dir, aufs_bindex_t bindex,
-+ struct dentry *wh_dentry, struct dentry *dentry)
-+{
-+ int err, rerr;
-+ aufs_bindex_t bwh;
-+ struct path h_path;
-+ struct super_block *sb;
-+ struct inode *inode, *h_dir;
-+ struct dentry *wh;
-+
-+ bwh = -1;
-+ sb = dir->i_sb;
-+ if (wh_dentry) {
-+ h_dir = d_inode(wh_dentry->d_parent); /* dir inode is locked */
-+ IMustLock(h_dir);
-+ AuDebugOn(au_h_iptr(dir, bindex) != h_dir);
-+ bwh = au_dbwh(dentry);
-+ h_path.dentry = wh_dentry;
-+ h_path.mnt = au_sbr_mnt(sb, bindex);
-+ err = au_wh_unlink_dentry(au_h_iptr(dir, bindex), &h_path,
-+ dentry);
-+ if (unlikely(err))
-+ goto out;
-+ }
-+
-+ inode = au_new_inode(dentry, /*must_new*/1);
-+ if (!IS_ERR(inode)) {
-+ d_instantiate(dentry, inode);
-+ dir = d_inode(dentry->d_parent); /* dir inode is locked */
-+ IMustLock(dir);
-+ au_dir_ts(dir, bindex);
-+ inode_inc_iversion(dir);
-+ au_fhsm_wrote(sb, bindex, /*force*/0);
-+ return 0; /* success */
-+ }
-+
-+ err = PTR_ERR(inode);
-+ if (!wh_dentry)
-+ goto out;
-+
-+ /* revert */
-+ /* dir inode is locked */
-+ wh = au_wh_create(dentry, bwh, wh_dentry->d_parent);
-+ rerr = PTR_ERR(wh);
-+ if (IS_ERR(wh)) {
-+ AuIOErr("%pd reverting whiteout failed(%d, %d)\n",
-+ dentry, err, rerr);
-+ err = -EIO;
-+ } else
-+ dput(wh);
-+
-+out:
-+ return err;
-+}
-+
-+static int au_d_may_add(struct dentry *dentry)
-+{
-+ int err;
-+
-+ err = 0;
-+ if (unlikely(d_unhashed(dentry)))
-+ err = -ENOENT;
-+ if (unlikely(d_really_is_positive(dentry)))
-+ err = -EEXIST;
-+ return err;
-+}
-+
-+/*
-+ * simple tests for the adding inode operations.
-+ * following the checks in vfs, plus the parent-child relationship.
-+ */
-+int au_may_add(struct dentry *dentry, aufs_bindex_t bindex,
-+ struct dentry *h_parent, int isdir)
-+{
-+ int err;
-+ umode_t h_mode;
-+ struct dentry *h_dentry;
-+ struct inode *h_inode;
-+
-+ err = -ENAMETOOLONG;
-+ if (unlikely(dentry->d_name.len > AUFS_MAX_NAMELEN))
-+ goto out;
-+
-+ h_dentry = au_h_dptr(dentry, bindex);
-+ if (d_really_is_negative(dentry)) {
-+ err = -EEXIST;
-+ if (unlikely(d_is_positive(h_dentry)))
-+ goto out;
-+ } else {
-+ /* rename(2) case */
-+ err = -EIO;
-+ if (unlikely(d_is_negative(h_dentry)))
-+ goto out;
-+ h_inode = d_inode(h_dentry);
-+ if (unlikely(!h_inode->i_nlink))
-+ goto out;
-+
-+ h_mode = h_inode->i_mode;
-+ if (!isdir) {
-+ err = -EISDIR;
-+ if (unlikely(S_ISDIR(h_mode)))
-+ goto out;
-+ } else if (unlikely(!S_ISDIR(h_mode))) {
-+ err = -ENOTDIR;
-+ goto out;
-+ }
-+ }
-+
-+ err = 0;
-+ /* expected parent dir is locked */
-+ if (unlikely(h_parent != h_dentry->d_parent))
-+ err = -EIO;
-+
-+out:
-+ AuTraceErr(err);
-+ return err;
-+}
-+
-+/*
-+ * initial procedure of adding a new entry.
-+ * prepare writable branch and the parent dir, lock it,
-+ * and lookup whiteout for the new entry.
-+ */
-+static struct dentry*
-+lock_hdir_lkup_wh(struct dentry *dentry, struct au_dtime *dt,
-+ struct dentry *src_dentry, struct au_pin *pin,
-+ struct au_wr_dir_args *wr_dir_args)
-+{
-+ struct dentry *wh_dentry, *h_parent;
-+ struct super_block *sb;
-+ struct au_branch *br;
-+ int err;
-+ unsigned int udba;
-+ aufs_bindex_t bcpup;
-+
-+ AuDbg("%pd\n", dentry);
-+
-+ err = au_wr_dir(dentry, src_dentry, wr_dir_args);
-+ bcpup = err;
-+ wh_dentry = ERR_PTR(err);
-+ if (unlikely(err < 0))
-+ goto out;
-+
-+ sb = dentry->d_sb;
-+ udba = au_opt_udba(sb);
-+ err = au_pin(pin, dentry, bcpup, udba,
-+ AuPin_DI_LOCKED | AuPin_MNT_WRITE);
-+ wh_dentry = ERR_PTR(err);
-+ if (unlikely(err))
-+ goto out;
-+
-+ h_parent = au_pinned_h_parent(pin);
-+ if (udba != AuOpt_UDBA_NONE
-+ && au_dbtop(dentry) == bcpup)
-+ err = au_may_add(dentry, bcpup, h_parent,
-+ au_ftest_wrdir(wr_dir_args->flags, ISDIR));
-+ else if (unlikely(dentry->d_name.len > AUFS_MAX_NAMELEN))
-+ err = -ENAMETOOLONG;
-+ wh_dentry = ERR_PTR(err);
-+ if (unlikely(err))
-+ goto out_unpin;
-+
-+ br = au_sbr(sb, bcpup);
-+ if (dt) {
-+ struct path tmp = {
-+ .dentry = h_parent,
-+ .mnt = au_br_mnt(br)
-+ };
-+ au_dtime_store(dt, au_pinned_parent(pin), &tmp);
-+ }
-+
-+ wh_dentry = NULL;
-+ if (bcpup != au_dbwh(dentry))
-+ goto out; /* success */
-+
-+ /*
-+ * ENAMETOOLONG here means that if we allowed create such name, then it
-+ * would not be able to removed in the future. So we don't allow such
-+ * name here and we don't handle ENAMETOOLONG differently here.
-+ */
-+ wh_dentry = au_wh_lkup(h_parent, &dentry->d_name, br);
-+
-+out_unpin:
-+ if (IS_ERR(wh_dentry))
-+ au_unpin(pin);
-+out:
-+ return wh_dentry;
-+}
-+
-+/* ---------------------------------------------------------------------- */
-+
-+enum { Mknod, Symlink, Creat };
-+struct simple_arg {
-+ int type;
-+ union {
-+ struct {
-+ umode_t mode;
-+ bool want_excl;
-+ bool try_aopen;
-+ struct vfsub_aopen_args *aopen;
-+ } c;
-+ struct {
-+ const char *symname;
-+ } s;
-+ struct {
-+ umode_t mode;
-+ dev_t dev;
-+ } m;
-+ } u;
-+};
-+
-+static int add_simple(struct inode *dir, struct dentry *dentry,
-+ struct simple_arg *arg)
-+{
-+ int err, rerr;
-+ aufs_bindex_t btop;
-+ unsigned char created;
-+ const unsigned char try_aopen
-+ = (arg->type == Creat && arg->u.c.try_aopen);
-+ struct vfsub_aopen_args *aopen = arg->u.c.aopen;
-+ struct dentry *wh_dentry, *parent;
-+ struct inode *h_dir;
-+ struct super_block *sb;
-+ struct au_branch *br;
-+ /* to reduce stack size */
-+ struct {
-+ struct au_dtime dt;
-+ struct au_pin pin;
-+ struct path h_path;
-+ struct au_wr_dir_args wr_dir_args;
-+ } *a;
-+
-+ AuDbg("%pd\n", dentry);
-+ IMustLock(dir);
-+
-+ err = -ENOMEM;
-+ a = kmalloc(sizeof(*a), GFP_NOFS);
-+ if (unlikely(!a))
-+ goto out;
-+ a->wr_dir_args.force_btgt = -1;
-+ a->wr_dir_args.flags = AuWrDir_ADD_ENTRY;
-+
-+ parent = dentry->d_parent; /* dir inode is locked */
-+ if (!try_aopen) {
-+ err = aufs_read_lock(dentry, AuLock_DW | AuLock_GEN);
-+ if (unlikely(err))
-+ goto out_free;
-+ }
-+ err = au_d_may_add(dentry);
-+ if (unlikely(err))
-+ goto out_unlock;
-+ if (!try_aopen)
-+ di_write_lock_parent(parent);
-+ wh_dentry = lock_hdir_lkup_wh(dentry, &a->dt, /*src_dentry*/NULL,
-+ &a->pin, &a->wr_dir_args);
-+ err = PTR_ERR(wh_dentry);
-+ if (IS_ERR(wh_dentry))
-+ goto out_parent;
-+
-+ btop = au_dbtop(dentry);
-+ sb = dentry->d_sb;
-+ br = au_sbr(sb, btop);
-+ a->h_path.dentry = au_h_dptr(dentry, btop);
-+ a->h_path.mnt = au_br_mnt(br);
-+ h_dir = au_pinned_h_dir(&a->pin);
-+ switch (arg->type) {
-+ case Creat:
-+ if (!try_aopen || !h_dir->i_op->atomic_open) {
-+ err = vfsub_create(h_dir, &a->h_path, arg->u.c.mode,
-+ arg->u.c.want_excl);
-+ created = !err;
-+ if (!err && try_aopen)
-+ aopen->file->f_mode |= FMODE_CREATED;
-+ } else {
-+ aopen->br = br;
-+ err = vfsub_atomic_open(h_dir, a->h_path.dentry, aopen);
-+ AuDbg("err %d\n", err);
-+ AuDbgFile(aopen->file);
-+ created = err >= 0
-+ && !!(aopen->file->f_mode & FMODE_CREATED);
-+ }
-+ break;
-+ case Symlink:
-+ err = vfsub_symlink(h_dir, &a->h_path, arg->u.s.symname);
-+ created = !err;
-+ break;
-+ case Mknod:
-+ err = vfsub_mknod(h_dir, &a->h_path, arg->u.m.mode,
-+ arg->u.m.dev);
-+ created = !err;
-+ break;
-+ default:
-+ BUG();
-+ }
-+ if (unlikely(err < 0))
-+ goto out_unpin;
-+
-+ err = epilog(dir, btop, wh_dentry, dentry);
-+ if (!err)
-+ goto out_unpin; /* success */
-+
-+ /* revert */
-+ if (created /* && d_is_positive(a->h_path.dentry) */) {
-+ /* no delegation since it is just created */
-+ rerr = vfsub_unlink(h_dir, &a->h_path, /*delegated*/NULL,
-+ /*force*/0);
-+ if (rerr) {
-+ AuIOErr("%pd revert failure(%d, %d)\n",
-+ dentry, err, rerr);
-+ err = -EIO;
-+ }
-+ au_dtime_revert(&a->dt);
-+ }
-+ if (try_aopen && h_dir->i_op->atomic_open
-+ && (aopen->file->f_mode & FMODE_OPENED))
-+ /* aopen->file is still opened */
-+ au_lcnt_dec(&aopen->br->br_nfiles);
-+
-+out_unpin:
-+ au_unpin(&a->pin);
-+ dput(wh_dentry);
-+out_parent:
-+ if (!try_aopen)
-+ di_write_unlock(parent);
-+out_unlock:
-+ if (unlikely(err)) {
-+ au_update_dbtop(dentry);
-+ d_drop(dentry);
-+ }
-+ if (!try_aopen)
-+ aufs_read_unlock(dentry, AuLock_DW);
-+out_free:
-+ au_kfree_rcu(a);
-+out:
-+ return err;
-+}
-+
-+int aufs_mknod(struct inode *dir, struct dentry *dentry, umode_t mode,
-+ dev_t dev)
-+{
-+ struct simple_arg arg = {
-+ .type = Mknod,
-+ .u.m = {
-+ .mode = mode,
-+ .dev = dev
-+ }
-+ };
-+ return add_simple(dir, dentry, &arg);
-+}
-+
-+int aufs_symlink(struct inode *dir, struct dentry *dentry, const char *symname)
-+{
-+ struct simple_arg arg = {
-+ .type = Symlink,
-+ .u.s.symname = symname
-+ };
-+ return add_simple(dir, dentry, &arg);
-+}
-+
-+int aufs_create(struct inode *dir, struct dentry *dentry, umode_t mode,
-+ bool want_excl)
-+{
-+ struct simple_arg arg = {
-+ .type = Creat,
-+ .u.c = {
-+ .mode = mode,
-+ .want_excl = want_excl
-+ }
-+ };
-+ return add_simple(dir, dentry, &arg);
-+}
-+
-+int au_aopen_or_create(struct inode *dir, struct dentry *dentry,
-+ struct vfsub_aopen_args *aopen_args)
-+{
-+ struct simple_arg arg = {
-+ .type = Creat,
-+ .u.c = {
-+ .mode = aopen_args->create_mode,
-+ .want_excl = aopen_args->open_flag & O_EXCL,
-+ .try_aopen = true,
-+ .aopen = aopen_args
-+ }
-+ };
-+ return add_simple(dir, dentry, &arg);
-+}
-+
-+int aufs_tmpfile(struct inode *dir, struct dentry *dentry, umode_t mode)
-+{
-+ int err;
-+ aufs_bindex_t bindex;
-+ struct super_block *sb;
-+ struct dentry *parent, *h_parent, *h_dentry;
-+ struct inode *h_dir, *inode;
-+ struct vfsmount *h_mnt;
-+ struct au_wr_dir_args wr_dir_args = {
-+ .force_btgt = -1,
-+ .flags = AuWrDir_TMPFILE
-+ };
-+
-+ /* copy-up may happen */
-+ inode_lock(dir);
-+
-+ sb = dir->i_sb;
-+ err = si_read_lock(sb, AuLock_FLUSH | AuLock_NOPLM);
-+ if (unlikely(err))
-+ goto out;
-+
-+ err = au_di_init(dentry);
-+ if (unlikely(err))
-+ goto out_si;
-+
-+ err = -EBUSY;
-+ parent = d_find_any_alias(dir);
-+ AuDebugOn(!parent);
-+ di_write_lock_parent(parent);
-+ if (unlikely(d_inode(parent) != dir))
-+ goto out_parent;
-+
-+ err = au_digen_test(parent, au_sigen(sb));
-+ if (unlikely(err))
-+ goto out_parent;
-+
-+ bindex = au_dbtop(parent);
-+ au_set_dbtop(dentry, bindex);
-+ au_set_dbbot(dentry, bindex);
-+ err = au_wr_dir(dentry, /*src_dentry*/NULL, &wr_dir_args);
-+ bindex = err;
-+ if (unlikely(err < 0))
-+ goto out_parent;
-+
-+ err = -EOPNOTSUPP;
-+ h_dir = au_h_iptr(dir, bindex);
-+ if (unlikely(!h_dir->i_op->tmpfile))
-+ goto out_parent;
-+
-+ h_mnt = au_sbr_mnt(sb, bindex);
-+ err = vfsub_mnt_want_write(h_mnt);
-+ if (unlikely(err))
-+ goto out_parent;
-+
-+ h_parent = au_h_dptr(parent, bindex);
-+ h_dentry = vfs_tmpfile(h_parent, mode, /*open_flag*/0);
-+ if (IS_ERR(h_dentry)) {
-+ err = PTR_ERR(h_dentry);
-+ goto out_mnt;
-+ }
-+
-+ au_set_dbtop(dentry, bindex);
-+ au_set_dbbot(dentry, bindex);
-+ au_set_h_dptr(dentry, bindex, dget(h_dentry));
-+ inode = au_new_inode(dentry, /*must_new*/1);
-+ if (IS_ERR(inode)) {
-+ err = PTR_ERR(inode);
-+ au_set_h_dptr(dentry, bindex, NULL);
-+ au_set_dbtop(dentry, -1);
-+ au_set_dbbot(dentry, -1);
-+ } else {
-+ if (!inode->i_nlink)
-+ set_nlink(inode, 1);
-+ d_tmpfile(dentry, inode);
-+ au_di(dentry)->di_tmpfile = 1;
-+
-+ /* update without i_mutex */
-+ if (au_ibtop(dir) == au_dbtop(dentry))
-+ au_cpup_attr_timesizes(dir);
-+ }
-+ dput(h_dentry);
-+
-+out_mnt:
-+ vfsub_mnt_drop_write(h_mnt);
-+out_parent:
-+ di_write_unlock(parent);
-+ dput(parent);
-+ di_write_unlock(dentry);
-+ if (unlikely(err)) {
-+ au_di_fin(dentry);
-+ dentry->d_fsdata = NULL;
-+ }
-+out_si:
-+ si_read_unlock(sb);
-+out:
-+ inode_unlock(dir);
-+ return err;
-+}
-+
-+/* ---------------------------------------------------------------------- */
-+
-+struct au_link_args {
-+ aufs_bindex_t bdst, bsrc;
-+ struct au_pin pin;
-+ struct path h_path;
-+ struct dentry *src_parent, *parent;
-+};
-+
-+static int au_cpup_before_link(struct dentry *src_dentry,
-+ struct au_link_args *a)
-+{
-+ int err;
-+ struct dentry *h_src_dentry;
-+ struct au_cp_generic cpg = {
-+ .dentry = src_dentry,
-+ .bdst = a->bdst,
-+ .bsrc = a->bsrc,
-+ .len = -1,
-+ .pin = &a->pin,
-+ .flags = AuCpup_DTIME | AuCpup_HOPEN /* | AuCpup_KEEPLINO */
-+ };
-+
-+ di_read_lock_parent(a->src_parent, AuLock_IR);
-+ err = au_test_and_cpup_dirs(src_dentry, a->bdst);
-+ if (unlikely(err))
-+ goto out;
-+
-+ h_src_dentry = au_h_dptr(src_dentry, a->bsrc);
-+ err = au_pin(&a->pin, src_dentry, a->bdst,
-+ au_opt_udba(src_dentry->d_sb),
-+ AuPin_DI_LOCKED | AuPin_MNT_WRITE);
-+ if (unlikely(err))
-+ goto out;
-+
-+ err = au_sio_cpup_simple(&cpg);
-+ au_unpin(&a->pin);
-+
-+out:
-+ di_read_unlock(a->src_parent, AuLock_IR);
-+ return err;
-+}
-+
-+static int au_cpup_or_link(struct dentry *src_dentry, struct dentry *dentry,
-+ struct au_link_args *a)
-+{
-+ int err;
-+ unsigned char plink;
-+ aufs_bindex_t bbot;
-+ struct dentry *h_src_dentry;
-+ struct inode *h_inode, *inode, *delegated;
-+ struct super_block *sb;
-+ struct file *h_file;
-+
-+ plink = 0;
-+ h_inode = NULL;
-+ sb = src_dentry->d_sb;
-+ inode = d_inode(src_dentry);
-+ if (au_ibtop(inode) <= a->bdst)
-+ h_inode = au_h_iptr(inode, a->bdst);
-+ if (!h_inode || !h_inode->i_nlink) {
-+ /* copyup src_dentry as the name of dentry. */
-+ bbot = au_dbbot(dentry);
-+ if (bbot < a->bsrc)
-+ au_set_dbbot(dentry, a->bsrc);
-+ au_set_h_dptr(dentry, a->bsrc,
-+ dget(au_h_dptr(src_dentry, a->bsrc)));
-+ dget(a->h_path.dentry);
-+ au_set_h_dptr(dentry, a->bdst, NULL);
-+ AuDbg("temporary d_inode...\n");
-+ spin_lock(&dentry->d_lock);
-+ dentry->d_inode = d_inode(src_dentry); /* tmp */
-+ spin_unlock(&dentry->d_lock);
-+ h_file = au_h_open_pre(dentry, a->bsrc, /*force_wr*/0);
-+ if (IS_ERR(h_file))
-+ err = PTR_ERR(h_file);
-+ else {
-+ struct au_cp_generic cpg = {
-+ .dentry = dentry,
-+ .bdst = a->bdst,
-+ .bsrc = -1,
-+ .len = -1,
-+ .pin = &a->pin,
-+ .flags = AuCpup_KEEPLINO
-+ };
-+ err = au_sio_cpup_simple(&cpg);
-+ au_h_open_post(dentry, a->bsrc, h_file);
-+ if (!err) {
-+ dput(a->h_path.dentry);
-+ a->h_path.dentry = au_h_dptr(dentry, a->bdst);
-+ } else
-+ au_set_h_dptr(dentry, a->bdst,
-+ a->h_path.dentry);
-+ }
-+ spin_lock(&dentry->d_lock);
-+ dentry->d_inode = NULL; /* restore */
-+ spin_unlock(&dentry->d_lock);
-+ AuDbg("temporary d_inode...done\n");
-+ au_set_h_dptr(dentry, a->bsrc, NULL);
-+ au_set_dbbot(dentry, bbot);
-+ } else {
-+ /* the inode of src_dentry already exists on a.bdst branch */
-+ h_src_dentry = d_find_alias(h_inode);
-+ if (!h_src_dentry && au_plink_test(inode)) {
-+ plink = 1;
-+ h_src_dentry = au_plink_lkup(inode, a->bdst);
-+ err = PTR_ERR(h_src_dentry);
-+ if (IS_ERR(h_src_dentry))
-+ goto out;
-+
-+ if (unlikely(d_is_negative(h_src_dentry))) {
-+ dput(h_src_dentry);
-+ h_src_dentry = NULL;
-+ }
-+
-+ }
-+ if (h_src_dentry) {
-+ delegated = NULL;
-+ err = vfsub_link(h_src_dentry, au_pinned_h_dir(&a->pin),
-+ &a->h_path, &delegated);
-+ if (unlikely(err == -EWOULDBLOCK)) {
-+ pr_warn("cannot retry for NFSv4 delegation"
-+ " for an internal link\n");
-+ iput(delegated);
-+ }
-+ dput(h_src_dentry);
-+ } else {
-+ AuIOErr("no dentry found for hi%lu on b%d\n",
-+ h_inode->i_ino, a->bdst);
-+ err = -EIO;
-+ }
-+ }
-+
-+ if (!err && !plink)
-+ au_plink_append(inode, a->bdst, a->h_path.dentry);
-+
-+out:
-+ AuTraceErr(err);
-+ return err;
-+}
-+
-+int aufs_link(struct dentry *src_dentry, struct inode *dir,
-+ struct dentry *dentry)
-+{
-+ int err, rerr;
-+ struct au_dtime dt;
-+ struct au_link_args *a;
-+ struct dentry *wh_dentry, *h_src_dentry;
-+ struct inode *inode, *delegated;
-+ struct super_block *sb;
-+ struct au_wr_dir_args wr_dir_args = {
-+ /* .force_btgt = -1, */
-+ .flags = AuWrDir_ADD_ENTRY
-+ };
-+
-+ IMustLock(dir);
-+ inode = d_inode(src_dentry);
-+ IMustLock(inode);
-+
-+ err = -ENOMEM;
-+ a = kzalloc(sizeof(*a), GFP_NOFS);
-+ if (unlikely(!a))
-+ goto out;
-+
-+ a->parent = dentry->d_parent; /* dir inode is locked */
-+ err = aufs_read_and_write_lock2(dentry, src_dentry,
-+ AuLock_NOPLM | AuLock_GEN);
-+ if (unlikely(err))
-+ goto out_kfree;
-+ err = au_d_linkable(src_dentry);
-+ if (unlikely(err))
-+ goto out_unlock;
-+ err = au_d_may_add(dentry);
-+ if (unlikely(err))
-+ goto out_unlock;
-+
-+ a->src_parent = dget_parent(src_dentry);
-+ wr_dir_args.force_btgt = au_ibtop(inode);
-+
-+ di_write_lock_parent(a->parent);
-+ wr_dir_args.force_btgt = au_wbr(dentry, wr_dir_args.force_btgt);
-+ wh_dentry = lock_hdir_lkup_wh(dentry, &dt, src_dentry, &a->pin,
-+ &wr_dir_args);
-+ err = PTR_ERR(wh_dentry);
-+ if (IS_ERR(wh_dentry))
-+ goto out_parent;
-+
-+ err = 0;
-+ sb = dentry->d_sb;
-+ a->bdst = au_dbtop(dentry);
-+ a->h_path.dentry = au_h_dptr(dentry, a->bdst);
-+ a->h_path.mnt = au_sbr_mnt(sb, a->bdst);
-+ a->bsrc = au_ibtop(inode);
-+ h_src_dentry = au_h_d_alias(src_dentry, a->bsrc);
-+ if (!h_src_dentry && au_di(src_dentry)->di_tmpfile)
-+ h_src_dentry = dget(au_hi_wh(inode, a->bsrc));
-+ if (!h_src_dentry) {
-+ a->bsrc = au_dbtop(src_dentry);
-+ h_src_dentry = au_h_d_alias(src_dentry, a->bsrc);
-+ AuDebugOn(!h_src_dentry);
-+ } else if (IS_ERR(h_src_dentry)) {
-+ err = PTR_ERR(h_src_dentry);
-+ goto out_parent;
-+ }
-+
-+ /*
-+ * aufs doesn't touch the credential so
-+ * security_dentry_create_files_as() is unnecessary.
-+ */
-+ if (au_opt_test(au_mntflags(sb), PLINK)) {
-+ if (a->bdst < a->bsrc
-+ /* && h_src_dentry->d_sb != a->h_path.dentry->d_sb */)
-+ err = au_cpup_or_link(src_dentry, dentry, a);
-+ else {
-+ delegated = NULL;
-+ err = vfsub_link(h_src_dentry, au_pinned_h_dir(&a->pin),
-+ &a->h_path, &delegated);
-+ if (unlikely(err == -EWOULDBLOCK)) {
-+ pr_warn("cannot retry for NFSv4 delegation"
-+ " for an internal link\n");
-+ iput(delegated);
-+ }
-+ }
-+ dput(h_src_dentry);
-+ } else {
-+ /*
-+ * copyup src_dentry to the branch we process,
-+ * and then link(2) to it.
-+ */
-+ dput(h_src_dentry);
-+ if (a->bdst < a->bsrc
-+ /* && h_src_dentry->d_sb != a->h_path.dentry->d_sb */) {
-+ au_unpin(&a->pin);
-+ di_write_unlock(a->parent);
-+ err = au_cpup_before_link(src_dentry, a);
-+ di_write_lock_parent(a->parent);
-+ if (!err)
-+ err = au_pin(&a->pin, dentry, a->bdst,
-+ au_opt_udba(sb),
-+ AuPin_DI_LOCKED | AuPin_MNT_WRITE);
-+ if (unlikely(err))
-+ goto out_wh;
-+ }
-+ if (!err) {
-+ h_src_dentry = au_h_dptr(src_dentry, a->bdst);
-+ err = -ENOENT;
-+ if (h_src_dentry && d_is_positive(h_src_dentry)) {
-+ delegated = NULL;
-+ err = vfsub_link(h_src_dentry,
-+ au_pinned_h_dir(&a->pin),
-+ &a->h_path, &delegated);
-+ if (unlikely(err == -EWOULDBLOCK)) {
-+ pr_warn("cannot retry"
-+ " for NFSv4 delegation"
-+ " for an internal link\n");
-+ iput(delegated);
-+ }
-+ }
-+ }
-+ }
-+ if (unlikely(err))
-+ goto out_unpin;
-+
-+ if (wh_dentry) {
-+ a->h_path.dentry = wh_dentry;
-+ err = au_wh_unlink_dentry(au_pinned_h_dir(&a->pin), &a->h_path,
-+ dentry);
-+ if (unlikely(err))
-+ goto out_revert;
-+ }
-+
-+ au_dir_ts(dir, a->bdst);
-+ inode_inc_iversion(dir);
-+ inc_nlink(inode);
-+ inode->i_ctime = dir->i_ctime;
-+ d_instantiate(dentry, au_igrab(inode));
-+ if (d_unhashed(a->h_path.dentry))
-+ /* some filesystem calls d_drop() */
-+ d_drop(dentry);
-+ /* some filesystems consume an inode even hardlink */
-+ au_fhsm_wrote(sb, a->bdst, /*force*/0);
-+ goto out_unpin; /* success */
-+
-+out_revert:
-+ /* no delegation since it is just created */
-+ rerr = vfsub_unlink(au_pinned_h_dir(&a->pin), &a->h_path,
-+ /*delegated*/NULL, /*force*/0);
-+ if (unlikely(rerr)) {
-+ AuIOErr("%pd reverting failed(%d, %d)\n", dentry, err, rerr);
-+ err = -EIO;
-+ }
-+ au_dtime_revert(&dt);
-+out_unpin:
-+ au_unpin(&a->pin);
-+out_wh:
-+ dput(wh_dentry);
-+out_parent:
-+ di_write_unlock(a->parent);
-+ dput(a->src_parent);
-+out_unlock:
-+ if (unlikely(err)) {
-+ au_update_dbtop(dentry);
-+ d_drop(dentry);
-+ }
-+ aufs_read_and_write_unlock2(dentry, src_dentry);
-+out_kfree:
-+ au_kfree_rcu(a);
-+out:
-+ AuTraceErr(err);
-+ return err;
-+}
-+
-+int aufs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
-+{
-+ int err, rerr;
-+ aufs_bindex_t bindex;
-+ unsigned char diropq;
-+ struct path h_path;
-+ struct dentry *wh_dentry, *parent, *opq_dentry;
-+ struct inode *h_inode;
-+ struct super_block *sb;
-+ struct {
-+ struct au_pin pin;
-+ struct au_dtime dt;
-+ } *a; /* reduce the stack usage */
-+ struct au_wr_dir_args wr_dir_args = {
-+ .force_btgt = -1,
-+ .flags = AuWrDir_ADD_ENTRY | AuWrDir_ISDIR
-+ };
-+
-+ IMustLock(dir);
-+
-+ err = -ENOMEM;
-+ a = kmalloc(sizeof(*a), GFP_NOFS);
-+ if (unlikely(!a))
-+ goto out;
-+
-+ err = aufs_read_lock(dentry, AuLock_DW | AuLock_GEN);
-+ if (unlikely(err))
-+ goto out_free;
-+ err = au_d_may_add(dentry);
-+ if (unlikely(err))
-+ goto out_unlock;
-+
-+ parent = dentry->d_parent; /* dir inode is locked */
-+ di_write_lock_parent(parent);
-+ wh_dentry = lock_hdir_lkup_wh(dentry, &a->dt, /*src_dentry*/NULL,
-+ &a->pin, &wr_dir_args);
-+ err = PTR_ERR(wh_dentry);
-+ if (IS_ERR(wh_dentry))
-+ goto out_parent;
-+
-+ sb = dentry->d_sb;
-+ bindex = au_dbtop(dentry);
-+ h_path.dentry = au_h_dptr(dentry, bindex);
-+ h_path.mnt = au_sbr_mnt(sb, bindex);
-+ err = vfsub_mkdir(au_pinned_h_dir(&a->pin), &h_path, mode);
-+ if (unlikely(err))
-+ goto out_unpin;
-+
-+ /* make the dir opaque */
-+ diropq = 0;
-+ h_inode = d_inode(h_path.dentry);
-+ if (wh_dentry
-+ || au_opt_test(au_mntflags(sb), ALWAYS_DIROPQ)) {
-+ inode_lock_nested(h_inode, AuLsc_I_CHILD);
-+ opq_dentry = au_diropq_create(dentry, bindex);
-+ inode_unlock(h_inode);
-+ err = PTR_ERR(opq_dentry);
-+ if (IS_ERR(opq_dentry))
-+ goto out_dir;
-+ dput(opq_dentry);
-+ diropq = 1;
-+ }
-+
-+ err = epilog(dir, bindex, wh_dentry, dentry);
-+ if (!err) {
-+ inc_nlink(dir);
-+ goto out_unpin; /* success */
-+ }
-+
-+ /* revert */
-+ if (diropq) {
-