-From 8dcf5b3ed788c0909dc1248a00a8997cdeefde1e Mon Sep 17 00:00:00 2001
-From: Tom Briden <tom@decompile.me.uk>
-Date: Thu, 11 Jan 2024 11:05:05 +0000
-Subject: [PATCH] Make AUFS friendly (aufs6.x-rcN 20231106)
+SPDX-License-Identifier: GPL-2.0
+aufs6.x-rcN kbuild patch
-Patches applied from sfjro/aufs5-standalone
----
- Documentation/ABI/testing/debugfs-aufs | 55 +
- Documentation/ABI/testing/sysfs-aufs | 31 +
- Documentation/filesystems/aufs/README | 409 ++++
- .../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 | 44 +
- .../filesystems/aufs/design/06dirren.txt | 102 +
- .../filesystems/aufs/design/06fhsm.txt | 118 +
- .../filesystems/aufs/design/06mmap.txt | 72 +
- .../filesystems/aufs/design/06xattr.txt | 94 +
- .../filesystems/aufs/design/07export.txt | 58 +
- .../filesystems/aufs/design/08shwh.txt | 52 +
- .../filesystems/aufs/design/10dynop.txt | 47 +
- MAINTAINERS | 13 +
- drivers/block/loop.c | 18 +
- fs/Kconfig | 1 +
- fs/Makefile | 1 +
- fs/aufs/Kconfig | 199 ++
- fs/aufs/Makefile | 46 +
- fs/aufs/aufs.h | 62 +
- fs/aufs/branch.c | 1427 ++++++++++++
- fs/aufs/branch.h | 375 ++++
- fs/aufs/conf.mk | 40 +
- fs/aufs/cpup.c | 1459 +++++++++++++
- 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 | 448 ++++
- fs/aufs/debug.h | 226 ++
- fs/aufs/dentry.c | 1168 ++++++++++
- fs/aufs/dentry.h | 270 +++
- fs/aufs/dinfo.c | 555 +++++
- fs/aufs/dir.c | 765 +++++++
- fs/aufs/dir.h | 134 ++
- fs/aufs/dirren.c | 1315 +++++++++++
- fs/aufs/dirren.h | 140 ++
- fs/aufs/dynop.c | 366 ++++
- fs/aufs/dynop.h | 77 +
- fs/aufs/export.c | 830 +++++++
- fs/aufs/f_op.c | 771 +++++++
- fs/aufs/fhsm.c | 426 ++++
- fs/aufs/file.c | 865 ++++++++
- fs/aufs/file.h | 342 +++
- fs/aufs/finfo.c | 149 ++
- fs/aufs/fsctx.c | 1242 +++++++++++
- fs/aufs/fstype.h | 401 ++++
- fs/aufs/hbl.h | 65 +
- fs/aufs/hfsnotify.c | 290 +++
- fs/aufs/hfsplus.c | 60 +
- fs/aufs/hnotify.c | 715 ++++++
- fs/aufs/i_op.c | 1516 +++++++++++++
- fs/aufs/i_op_add.c | 972 +++++++++
- fs/aufs/i_op_del.c | 523 +++++
- fs/aufs/i_op_ren.c | 1260 +++++++++++
- fs/aufs/iinfo.c | 286 +++
- fs/aufs/inode.c | 531 +++++
- fs/aufs/inode.h | 707 ++++++
- 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 | 180 ++
- fs/aufs/mvdown.c | 706 ++++++
- fs/aufs/opts.c | 1032 +++++++++
- fs/aufs/opts.h | 263 +++
- fs/aufs/plink.c | 516 +++++
- fs/aufs/poll.c | 51 +
- fs/aufs/posix_acl.c | 108 +
- fs/aufs/procfs.c | 170 ++
- fs/aufs/rdu.c | 384 ++++
- fs/aufs/rwsem.h | 85 +
- fs/aufs/sbinfo.c | 316 +++
- fs/aufs/super.c | 871 ++++++++
- fs/aufs/super.h | 592 +++++
- fs/aufs/sysaufs.c | 94 +
- fs/aufs/sysaufs.h | 102 +
- fs/aufs/sysfs.c | 374 ++++
- fs/aufs/sysrq.c | 149 ++
- fs/aufs/vdir.c | 896 ++++++++
- fs/aufs/vfsub.c | 918 ++++++++
- fs/aufs/vfsub.h | 403 ++++
- fs/aufs/wbr_policy.c | 830 +++++++
- fs/aufs/whout.c | 1072 +++++++++
- fs/aufs/whout.h | 87 +
- fs/aufs/wkq.c | 372 ++++
- fs/aufs/wkq.h | 89 +
- fs/aufs/xattr.c | 360 +++
- fs/aufs/xino.c | 1926 +++++++++++++++++
- fs/dcache.c | 4 +-
- fs/exec.c | 1 +
- fs/fcntl.c | 5 +-
- fs/file_table.c | 1 +
- fs/namespace.c | 9 +
- fs/notify/group.c | 1 +
- fs/open.c | 1 +
- fs/proc/nommu.c | 5 +-
- fs/proc/task_mmu.c | 7 +-
- fs/proc/task_nommu.c | 5 +-
- fs/read_write.c | 2 +
- fs/splice.c | 5 +-
- fs/xattr.c | 1 +
- include/linux/fs.h | 2 +
- include/linux/lockdep.h | 2 +
- include/linux/mm.h | 37 +
- include/linux/mm_types.h | 6 +
- include/linux/mnt_namespace.h | 3 +
- include/linux/splice.h | 6 +
- include/uapi/linux/aufs_type.h | 452 ++++
- kernel/fork.c | 2 +-
- kernel/locking/lockdep.c | 4 +-
- kernel/task_work.c | 1 +
- mm/Makefile | 1 +
- mm/filemap.c | 2 +-
- mm/mmap.c | 41 +-
- mm/nommu.c | 10 +-
- mm/prfile.c | 86 +
- security/security.c | 8 +
- 125 files changed, 38490 insertions(+), 23 deletions(-)
- 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/fsctx.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
- create mode 100644 mm/prfile.c
-
-diff --git a/Documentation/ABI/testing/debugfs-aufs b/Documentation/ABI/testing/debugfs-aufs
-new file mode 100644
-index 00000000000000..45b739879d7696
---- /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>/xi<branch-index>
-+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 00000000000000..48500c0569e658
---- /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>/br<idx>
-+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>/brid<idx>
-+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 00000000000000..04a4d069bb52a0
---- /dev/null
-+++ b/Documentation/filesystems/aufs/README
-@@ -0,0 +1,409 @@
-+
-+Aufs6 -- advanced multi layered unification filesystem version 6.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.
-+
-+Aufs6 supports linux-v6.0 and later, try aufs6.0 branch in
-+aufs-linux.git or aufs-standalone.git.
-+If you want older kernel version support,
-+- for linux-v5.x series, try aufs-linux.git or aufs-standalone.git
-+- 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: the name of aufs5-linux.git and aufs5-standalone.git on github
-+ were changed. Now they are aufs-linux.git and
-+ aufs-standalone.git and they contain aufs5 and later branches.
-+
-+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 aufs6.
-+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 aufs6, aufs-linux.git,
-+aufs-standalone.git, and aufs-util.git.
-+While the aufs-util is always necessary, you need either of aufs-linux
-+or aufs-standalone.
-+
-+The aufs-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 aufs6 as an external kernel module.
-+Several extra patches are not included in this tree. Only
-+aufs-standalone tree contains them. They are described in the later
-+section "Configuration and Compilation."
-+
-+On the other hand, the aufs-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 "aufs6.x" where "x"
-+represents the linux kernel version, "linux-6.x". For instance,
-+"aufs6.0" is for linux-6.0. For latest "linux-6.x-rcN", use
-+"aufs6.x-rcN" branch.
-+
-+o aufs-linux tree
-+$ git clone --reference /your/linux/git/tree \
-+ git://github.com/sfjro/aufs-linux.git aufs-linux.git
-+- if you don't have linux GIT tree, then remove "--reference ..."
-+$ cd aufs-linux.git
-+$ git checkout origin/aufs6.0
-+
-+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 aufs git://github.com/sfjro/aufs-linux.git
-+$ git fetch aufs
-+$ git checkout -b my6.0 v6.0
-+$ (add your local change...)
-+$ git pull aufs aufs6.0
-+- now you have v6.0 + your_changes + aufs6.0 in you my6.0 branch.
-+- you may need to solve some conflicts between your_changes and
-+ aufs6.0. in this case, git-rerere is recommended so that you can
-+ solve the similar conflicts automatically when you upgrade to 6.1 or
-+ later in the future.
-+
-+o aufs-standalone tree
-+$ git clone git://github.com/sfjro/aufs-standalone.git aufs-standalone.git
-+$ cd aufs-standalone.git
-+$ git checkout origin/aufs6.0
-+
-+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/aufs6.0
-+
-+Note: The 6.x-rcN branch is to be used with `rc' kernel versions ONLY.
-+The minor version number, 'x' in '6.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-6.10" and the "aufs6.10" branch
-+does not exist in aufs-util repository, then "aufs6.9", "aufs6.8"
-+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 aufs-linux tree,
-+- enable CONFIG_AUFS_FS.
-+- set other aufs configurations if necessary.
-+- for aufs5.13 and later
-+ 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 customize some LOCKDEP numbers. Here are what I use on my
-+ test environment.
-+ CONFIG_LOCKDEP_BITS=21
-+ CONFIG_LOCKDEP_CHAINS_BITS=21
-+ CONFIG_LOCKDEP_STACK_TRACE_BITS=24
-+ Also you will need to expand some constant values in LOCKDEP. Refer
-+ to lockdep-debug.patch in aufs-standalone.git.
-+
-+For aufs-standalone tree,
-+There are several ways to build.
-+
-+1.
-+- apply ./aufs6-kbuild.patch to your kernel source files.
-+- apply ./aufs6-base.patch too.
-+- apply ./aufs6-mmap.patch too.
-+- apply ./aufs6-standalone.patch too, if you have a plan to set
-+ CONFIG_AUFS_FS=m. otherwise you don't need ./aufs-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 ./aufs6-base.patch to your kernel source files.
-+- apply ./aufs6-mmap.patch too.
-+- apply ./aufs6-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 aufs6-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 aufs-standalone.git. They are all
-+optional. When you meet some problems, they will help you.
-+- aufs6-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".
-+- 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
-+ Similar to some kernel configurations for LOCKDEP (see the top of
-+ this section), you will need expand some constants in LOCKDEP for
-+ aufs if you enable CONFIG_LOCKDEP.
-+
-+
-+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)
-+- LSM (linux security module, if you are using)
-+- 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, 2015/7, and 2021/12).
-+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).
-+huronOS team: Enya Quetzalli made donations (2022/5, 2023/5 and 8).
-+Vasily Mikhaylichenko made a donation (2023/5).
-+
-+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 00000000000000..4c468b3264b56b
---- /dev/null
-+++ b/Documentation/filesystems/aufs/design/01intro.txt
-@@ -0,0 +1,171 @@
-+
-+# Copyright (C) 2005-2022 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 00000000000000..83be46121ae26f
---- /dev/null
-+++ b/Documentation/filesystems/aufs/design/02struct.txt
-@@ -0,0 +1,258 @@
-+
-+# Copyright (C) 2005-2022 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 00000000000000..4811f243246545
---- /dev/null
-+++ b/Documentation/filesystems/aufs/design/03atomic_open.txt
-@@ -0,0 +1,85 @@
-+
-+# Copyright (C) 2015-2022 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 00000000000000..766a28be02637a
---- /dev/null
-+++ b/Documentation/filesystems/aufs/design/03lookup.txt
-@@ -0,0 +1,113 @@
-+
-+# Copyright (C) 2005-2022 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 00000000000000..ffeb97dcaff350
---- /dev/null
-+++ b/Documentation/filesystems/aufs/design/04branch.txt
-@@ -0,0 +1,74 @@
-+
-+# Copyright (C) 2005-2022 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 00000000000000..a2143bfe6efc87
---- /dev/null
-+++ b/Documentation/filesystems/aufs/design/05wbr_policy.txt
-@@ -0,0 +1,64 @@
-+
-+# Copyright (C) 2005-2022 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 00000000000000..4e6c7e7c20ef13
---- /dev/null
-+++ b/Documentation/filesystems/aufs/design/06dirren.dot
-@@ -0,0 +1,44 @@
-+
-+// to view this graph, run dot(1) command in GRAPHVIZ.
-+//
-+// 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/>.
-+
-+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 00000000000000..58ec5e22fe3d00
---- /dev/null
-+++ b/Documentation/filesystems/aufs/design/06dirren.txt
-@@ -0,0 +1,102 @@
-+
-+# Copyright (C) 2017-2022 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 referred 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 00000000000000..d3b56325ff87ad
---- /dev/null
-+++ b/Documentation/filesystems/aufs/design/06fhsm.txt
-@@ -0,0 +1,118 @@
-+
-+# Copyright (C) 2011-2022 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/>.
-+
-+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 00000000000000..ddc65ce97fa3e8
---- /dev/null
-+++ b/Documentation/filesystems/aufs/design/06mmap.txt
-@@ -0,0 +1,72 @@
-+
-+# Copyright (C) 2005-2022 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 00000000000000..4e5ead3ad74194
---- /dev/null
-+++ b/Documentation/filesystems/aufs/design/06xattr.txt
-@@ -0,0 +1,94 @@
-+
-+# Copyright (C) 2014-2022 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/>.
-+
-+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 00000000000000..40b2f1f1204932
---- /dev/null
-+++ b/Documentation/filesystems/aufs/design/07export.txt
-@@ -0,0 +1,58 @@
-+
-+# Copyright (C) 2005-2022 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 00000000000000..67245e98e6b472
---- /dev/null
-+++ b/Documentation/filesystems/aufs/design/08shwh.txt
-@@ -0,0 +1,52 @@
-+
-+# Copyright (C) 2005-2022 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 00000000000000..da382ec2dc05d6
---- /dev/null
-+++ b/Documentation/filesystems/aufs/design/10dynop.txt
-@@ -0,0 +1,47 @@
-+
-+# Copyright (C) 2010-2022 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/MAINTAINERS b/MAINTAINERS
-index a7c4cf8201e012..5b377eebc87952 100644
---- a/MAINTAINERS
-+++ b/MAINTAINERS
-@@ -3347,6 +3347,19 @@ F: include/uapi/linux/audit.h
- F: kernel/audit*
- F: lib/*audit.c
-
-+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
-+S: Supported
-+W: http://aufs.sourceforge.net
-+T: git://github.com/sfjro/aufs4-linux.git
-+F: Documentation/ABI/testing/debugfs-aufs
-+F: Documentation/ABI/testing/sysfs-aufs
-+F: Documentation/filesystems/aufs/
-+F: fs/aufs/
-+F: include/uapi/linux/aufs_type.h
-+
- AUXILIARY BUS DRIVER
- M: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
- R: Dave Ertman <david.m.ertman@intel.com>
-diff --git a/drivers/block/loop.c b/drivers/block/loop.c
-index 9f2d412fc560e1..1fefc6a8d049c7 100644
---- a/drivers/block/loop.c
-+++ b/drivers/block/loop.c
-@@ -645,6 +645,24 @@ static int loop_change_fd(struct loop_device *lo, struct block_device *bdev,
- goto done;
- }
-
-+/*
-+ * 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/Kconfig b/fs/Kconfig
-index 42837617a55b54..6eaf5cde00fde8 100644
---- a/fs/Kconfig
-+++ b/fs/Kconfig
-@@ -333,6 +333,7 @@ source "fs/sysv/Kconfig"
- source "fs/ufs/Kconfig"
- source "fs/erofs/Kconfig"
- source "fs/vboxsf/Kconfig"
-+source "fs/aufs/Kconfig"
-
- endif # MISC_FILESYSTEMS
-
-diff --git a/fs/Makefile b/fs/Makefile
-index 75522f88e76367..8743be00607ec7 100644
---- a/fs/Makefile
-+++ b/fs/Makefile
-@@ -130,3 +130,4 @@ obj-$(CONFIG_EFIVAR_FS) += efivarfs/
- obj-$(CONFIG_EROFS_FS) += erofs/
- obj-$(CONFIG_VBOXSF_FS) += vboxsf/
- obj-$(CONFIG_ZONEFS_FS) += zonefs/
-+obj-$(CONFIG_AUFS_FS) += aufs/
-diff --git a/fs/aufs/Kconfig b/fs/aufs/Kconfig
-new file mode 100644
-index 00000000000000..a5008b87a55f1f
---- /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 information 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 00000000000000..4af8ecde3e3fad
---- /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 fsctx.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 00000000000000..20430cf7904263
---- /dev/null
-+++ b/fs/aufs/aufs.h
-@@ -0,0 +1,62 @@
-+/* SPDX-License-Identifier: GPL-2.0 */
-+/*
-+ * Copyright (C) 2005-2022 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/>.
-+ */
-+
-+/*
-+ * 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 00000000000000..2a85d744d2b5f7
---- /dev/null
-+++ b/fs/aufs/branch.c
-@@ -0,0 +1,1427 @@
-+// SPDX-License-Identifier: GPL-2.0
-+/*
-+ * Copyright (C) 2005-2022 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 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;
-+}
+diff --git a/fs/Kconfig b/fs/Kconfig
+index 89fdbefd1075..0038eb501478 100644
+--- a/fs/Kconfig
++++ b/fs/Kconfig
+@@ -338,6 +338,7 @@ source "fs/sysv/Kconfig"
+ source "fs/ufs/Kconfig"
+ source "fs/erofs/Kconfig"
+ source "fs/vboxsf/Kconfig"
++source "fs/aufs/Kconfig"
+
+ endif # MISC_FILESYSTEMS
+
+diff --git a/fs/Makefile b/fs/Makefile
+index c09016257f05..3899fae66d3f 100644
+--- a/fs/Makefile
++++ b/fs/Makefile
+@@ -130,3 +130,4 @@ obj-$(CONFIG_EFIVAR_FS) += efivarfs/
+ obj-$(CONFIG_EROFS_FS) += erofs/
+ obj-$(CONFIG_VBOXSF_FS) += vboxsf/
+ obj-$(CONFIG_ZONEFS_FS) += zonefs/
++obj-$(CONFIG_AUFS_FS) += aufs/
+SPDX-License-Identifier: GPL-2.0
+aufs6.x-rcN base patch
+
+diff --git a/MAINTAINERS b/MAINTAINERS
+index 9ed4d3868539..c0f45969bcf8 100644
+--- a/MAINTAINERS
++++ b/MAINTAINERS
+@@ -3365,6 +3365,19 @@ F: kernel/audit*
+ F: lib/*audit.c
+ K: \baudit_[a-z_0-9]\+\b
+
++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
++S: Supported
++W: http://aufs.sourceforge.net
++T: git://github.com/sfjro/aufs4-linux.git
++F: Documentation/ABI/testing/debugfs-aufs
++F: Documentation/ABI/testing/sysfs-aufs
++F: Documentation/filesystems/aufs/
++F: fs/aufs/
++F: include/uapi/linux/aufs_type.h
+
-+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)
+ AUXILIARY BUS DRIVER
+ M: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+ R: Dave Ertman <david.m.ertman@intel.com>
+diff --git a/drivers/block/loop.c b/drivers/block/loop.c
+index f8145499da38..333b3915fe86 100644
+--- a/drivers/block/loop.c
++++ b/drivers/block/loop.c
+@@ -641,6 +641,24 @@ static int loop_change_fd(struct loop_device *lo, struct block_device *bdev,
+ goto done;
+ }
+
++/*
++ * for AUFS
++ * no get/put for file.
++ */
++struct file *loop_backing_file(struct super_block *sb)
+{
-+ struct au_branch **brp;
-+
-+ AuRwMustWriteLock(&sbinfo->si_rwsem);
++ struct file *ret;
++ struct loop_device *l;
+
-+ 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;
++ 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);
+
-+static void au_br_do_add_hdp(struct au_dinfo *dinfo, aufs_bindex_t bindex,
-+ aufs_bindex_t bbot, aufs_bindex_t amount)
+ /* 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 b813528fb147..78e322b59b8d 100644
+--- a/fs/dcache.c
++++ b/fs/dcache.c
+@@ -1219,7 +1219,7 @@ 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, *dentry;
+diff --git a/fs/fcntl.c b/fs/fcntl.c
+index c80a6acad742..96a562b48ec7 100644
+--- a/fs/fcntl.c
++++ b/fs/fcntl.c
+@@ -34,7 +34,7 @@
+
+ #define SETFL_MASK (O_APPEND | O_NONBLOCK | O_NDELAY | O_DIRECT | O_NOATIME)
+
+-static int setfl(int fd, struct file * filp, unsigned int arg)
++int setfl(int fd, struct file * filp, unsigned int arg)
+ {
+ struct inode * inode = file_inode(filp);
+ int error = 0;
+@@ -64,6 +64,8 @@ static int setfl(int fd, struct file * filp, unsigned int 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/namespace.c b/fs/namespace.c
+index 5a51315c6678..a4b6ce51848e 100644
+--- a/fs/namespace.c
++++ b/fs/namespace.c
+@@ -860,6 +860,12 @@ 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)
+{
-+ 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;
++ return check_mnt(real_mount(mnt));
+}
+
-+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;
+ /*
+ * vfsmount lock must be held for write
+ */
+diff --git a/fs/splice.c b/fs/splice.c
+index 218e24b1ac40..7210ddc5aa81 100644
+--- a/fs/splice.c
++++ b/fs/splice.c
+@@ -933,7 +933,7 @@ static int warn_unsupported(struct file *file, const char *op)
+ /*
+ * Attempt to initiate a splice from pipe to file.
+ */
+-static ssize_t do_splice_from(struct pipe_inode_info *pipe, struct file *out,
++ssize_t do_splice_from(struct pipe_inode_info *pipe, struct file *out,
+ loff_t *ppos, size_t len, unsigned int flags)
+ {
+ if (unlikely(!out->f_op->splice_write))
+diff --git a/include/linux/fs.h b/include/linux/fs.h
+index 023f37c60709..96ca249ee1e6 100644
+--- a/include/linux/fs.h
++++ b/include/linux/fs.h
+@@ -1104,6 +1104,7 @@ 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 int arg);
+ extern void __f_setown(struct file *filp, struct pid *, enum pid_type, int force);
+ extern int f_setown(struct file *filp, int who, int force);
+ extern void f_delown(struct file *filp);
+@@ -2001,6 +2002,7 @@ struct file_operations {
+ int (*lock) (struct file *, int, struct file_lock *);
+ 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);
+diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h
+index 08b0d1d9d78b..009f69c4e09d 100644
+--- a/include/linux/lockdep.h
++++ b/include/linux/lockdep.h
+@@ -192,6 +192,8 @@ static inline int lockdep_match_key(struct lockdep_map *lock,
+ return lock->key == key;
+ }
+
++struct lock_class *lockdep_hlock_class(struct held_lock *hlock);
+
-+ AuRwMustWriteLock(&iinfo->ii_rwsem);
+ /*
+ * Acquire a lock.
+ *
+diff --git a/include/linux/mnt_namespace.h b/include/linux/mnt_namespace.h
+index 8f882f5881e8..6b9808f09843 100644
+--- a/include/linux/mnt_namespace.h
++++ b/include/linux/mnt_namespace.h
+@@ -7,12 +7,15 @@ struct mnt_namespace;
+ struct fs_struct;
+ struct user_namespace;
+ struct ns_common;
++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 struct ns_common *from_mnt_ns(struct mnt_namespace *);
+
++extern int is_current_mnt_ns(struct vfsmount *mnt);
+
-+ 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;
-+}
+ 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 9dec4861d09f..14583d846864 100644
+--- a/include/linux/splice.h
++++ b/include/linux/splice.h
+@@ -108,4 +108,7 @@ 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;
+
-+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;
++extern ssize_t do_splice_from(struct pipe_inode_info *pipe, struct file *out,
++ loff_t *ppos, size_t len, unsigned int flags);
+ #endif
+diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c
+index 151bd3de5936..2223ee909c10 100644
+--- a/kernel/locking/lockdep.c
++++ b/kernel/locking/lockdep.c
+@@ -218,7 +218,7 @@ unsigned long max_lock_class_idx;
+ struct lock_class lock_classes[MAX_LOCKDEP_KEYS];
+ DECLARE_BITMAP(lock_classes_in_use, 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)
+ {
+ unsigned int class_idx = hlock->class_idx;
+
+@@ -239,6 +239,7 @@ static inline struct lock_class *hlock_class(struct held_lock *hlock)
+ */
+ return lock_classes + class_idx;
+ }
++#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);
+SPDX-License-Identifier: GPL-2.0
+aufs6.x-rcN mmap patch
+
+diff --git a/fs/proc/base.c b/fs/proc/base.c
+index 98a031ac2648..a7a2ff2a7f61 100644
+--- a/fs/proc/base.c
++++ b/fs/proc/base.c
+@@ -2215,7 +2215,7 @@ static int map_files_get_link(struct dentry *dentry, struct path *path)
+ rc = -ENOENT;
+ vma = find_exact_vma(mm, vm_start, vm_end);
+ if (vma && vma->vm_file) {
+- *path = *file_user_path(vma->vm_file);
++ *path = vma_pr_or_file(vma)->f_path;
+ path_get(path);
+ rc = 0;
+ }
+diff --git a/fs/proc/nommu.c b/fs/proc/nommu.c
+index c6e7ebc63756..d7ccfd909764 100644
+--- a/fs/proc/nommu.c
++++ b/fs/proc/nommu.c
+@@ -39,7 +39,10 @@ static int nommu_region_show(struct seq_file *m, struct vm_region *region)
+ file = region->vm_file;
+
+ if (file) {
+- struct inode *inode = file_inode(region->vm_file);
++ struct inode *inode;
+
-+ 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();
-+}
++ file = vmr_pr_or_file(region);
++ inode = file_inode(file);
+ dev = inode->i_sb->s_dev;
+ ino = inode->i_ino;
+ }
+diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
+index 3f78ebbb795f..f96ec77db39e 100644
+--- a/fs/proc/task_mmu.c
++++ b/fs/proc/task_mmu.c
+@@ -273,7 +273,8 @@ show_map_vma(struct seq_file *m, struct vm_area_struct *vma)
+ const char *name = NULL;
+
+ if (file) {
+- const struct inode *inode = file_user_inode(vma->vm_file);
++ const struct inode *inode
++ = file_inode(file = vma_pr_or_file(vma));
+
+ dev = inode->i_sb->s_dev;
+ ino = inode->i_ino;
+@@ -2701,7 +2702,7 @@ static int show_numa_map(struct seq_file *m, void *v)
+ struct proc_maps_private *proc_priv = &numa_priv->proc_maps;
+ struct vm_area_struct *vma = v;
+ struct numa_maps *md = &numa_priv->md;
+- struct file *file = vma->vm_file;
++ struct file *file = vma_pr_or_file(vma);
+ struct mm_struct *mm = vma->vm_mm;
+ char buffer[64];
+ struct mempolicy *pol;
+diff --git a/fs/proc/task_nommu.c b/fs/proc/task_nommu.c
+index bce674533000..b12b5a75c799 100644
+--- a/fs/proc/task_nommu.c
++++ b/fs/proc/task_nommu.c
+@@ -137,7 +137,10 @@ static int nommu_vma_show(struct seq_file *m, struct vm_area_struct *vma)
+ file = vma->vm_file;
+
+ if (file) {
+- struct inode *inode = file_inode(vma->vm_file);
++ struct inode *inode;
+
-+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;
++ file = vma_pr_or_file(vma);
++ inode = file_inode(file);
+ dev = inode->i_sb->s_dev;
+ ino = inode->i_ino;
+ pgoff = (loff_t)vma->vm_pgoff << PAGE_SHIFT;
+diff --git a/include/linux/mm.h b/include/linux/mm.h
+index f5a97dec5169..a5b0edc8e290 100644
+--- a/include/linux/mm.h
++++ b/include/linux/mm.h
+@@ -2432,6 +2432,43 @@ static inline void unmap_shared_mapping_range(struct address_space *mapping,
+ static inline struct vm_area_struct *vma_lookup(struct mm_struct *mm,
+ unsigned long addr);
+
++#if 1 /* IS_ENABLED(CONFIG_AUFS_FS) */
++extern void vma_do_file_update_time(struct vm_area_struct *, const char[], int);
++extern struct file *vma_do_pr_or_file(struct vm_area_struct *, const char[],
++ int);
++extern void vma_do_get_file(struct vm_area_struct *, const char[], int);
++extern void vma_do_fput(struct vm_area_struct *, const char[], int);
+
-+ 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 */
-+ }
++#define vma_file_update_time(vma) vma_do_file_update_time(vma, __func__, \
++ __LINE__)
++#define vma_pr_or_file(vma) vma_do_pr_or_file(vma, __func__, \
++ __LINE__)
++#define vma_get_file(vma) vma_do_get_file(vma, __func__, __LINE__)
++#define vma_fput(vma) vma_do_fput(vma, __func__, __LINE__)
+
-+ 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;
++#ifndef CONFIG_MMU
++extern struct file *vmr_do_pr_or_file(struct vm_region *, const char[], int);
++extern void vmr_do_fput(struct vm_region *, const char[], int);
+
-+ err = au_br_init(add_branch, sb, add);
-+ if (unlikely(err)) {
-+ au_br_do_free(add_branch);
-+ goto out;
-+ }
++#define vmr_pr_or_file(region) vmr_do_pr_or_file(region, __func__, \
++ __LINE__)
++#define vmr_fput(region) vmr_do_fput(region, __func__, __LINE__)
++#endif /* !CONFIG_MMU */
+
-+ 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 */
++#else
+
-+ 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));
++#define vma_file_update_time(vma) file_update_time((vma)->vm_file)
++#define vma_pr_or_file(vma) (vma)->vm_file
++#define vma_get_file(vma) get_file((vma)->vm_file)
++#define vma_fput(vma) fput((vma)->vm_file)
+
-+out:
-+ return err;
-+}
++#ifndef CONFIG_MMU
++#define vmr_pr_or_file(region) (region)->vm_file
++#define vmr_fput(region) fput((region)->vm_file)
++#endif /* !CONFIG_MMU */
+
-+/* ---------------------------------------------------------------------- */
++#endif /* CONFIG_AUFS_FS */
+
-+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;
+ extern int access_process_vm(struct task_struct *tsk, unsigned long addr,
+ void *buf, int len, unsigned int gup_flags);
+ extern int access_remote_vm(struct mm_struct *mm, unsigned long addr,
+diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
+index 8b611e13153e..838af328941a 100644
+--- a/include/linux/mm_types.h
++++ b/include/linux/mm_types.h
+@@ -527,6 +527,9 @@ struct vm_region {
+ unsigned long vm_top; /* region allocated to here */
+ unsigned long vm_pgoff; /* the offset in vm_file corresponding to vm_start */
+ struct file *vm_file; /* the backing file or NULL */
++#if 1 /* IS_ENABLED(CONFIG_AUFS_FS) */
++ struct file *vm_prfile; /* the virtual backing file or NULL */
++#endif
+
+ int vm_usage; /* region usage count (access under nommu_region_sem) */
+ bool vm_icache_flushed : 1; /* true if the icache has been flushed for
+@@ -691,6 +694,9 @@ struct vm_area_struct {
+ unsigned long vm_pgoff; /* Offset (within vm_file) in PAGE_SIZE
+ units */
+ struct file * vm_file; /* File we map to (can be NULL). */
++#if 1 /* IS_ENABLED(CONFIG_AUFS_FS) */
++ struct file *vm_prfile; /* shadow of vm_file */
++#endif
+ void * vm_private_data; /* was vm_pte (shared mem) */
+
+ #ifdef CONFIG_ANON_VMA_NAME
+diff --git a/kernel/fork.c b/kernel/fork.c
+index 0d944e92a43f..bc073aaca2dc 100644
+--- a/kernel/fork.c
++++ b/kernel/fork.c
+@@ -716,7 +716,7 @@ static __latent_entropy int dup_mmap(struct mm_struct *mm,
+ if (file) {
+ struct address_space *mapping = file->f_mapping;
+
+- get_file(file);
++ vma_get_file(tmp);
+ i_mmap_lock_write(mapping);
+ if (vma_is_shared_maywrite(tmp))
+ mapping_allow_writable(mapping);
+diff --git a/mm/Makefile b/mm/Makefile
+index e4b5b75aaec9..2ec2544009fb 100644
+--- a/mm/Makefile
++++ b/mm/Makefile
+@@ -134,3 +134,4 @@ obj-$(CONFIG_IO_MAPPING) += io-mapping.o
+ obj-$(CONFIG_HAVE_BOOTMEM_INFO_NODE) += bootmem_info.o
+ obj-$(CONFIG_GENERIC_IOREMAP) += ioremap.o
+ obj-$(CONFIG_SHRINKER_DEBUG) += shrinker_debug.o
++obj-y += prfile.o
+diff --git a/mm/filemap.c b/mm/filemap.c
+index 750e779c23db..b84a752ff676 100644
+--- a/mm/filemap.c
++++ b/mm/filemap.c
+@@ -3587,7 +3587,7 @@ vm_fault_t filemap_page_mkwrite(struct vm_fault *vmf)
+ vm_fault_t ret = VM_FAULT_LOCKED;
+
+ sb_start_pagefault(mapping->host->i_sb);
+- file_update_time(vmf->vma->vm_file);
++ vma_file_update_time(vmf->vma);
+ folio_lock(folio);
+ if (folio->mapping != mapping) {
+ folio_unlock(folio);
+diff --git a/mm/mmap.c b/mm/mmap.c
+index d89770eaab6b..6bfba84b5ff0 100644
+--- a/mm/mmap.c
++++ b/mm/mmap.c
+@@ -140,7 +140,7 @@ static void remove_vma(struct vm_area_struct *vma, bool unreachable)
+ if (vma->vm_ops && vma->vm_ops->close)
+ vma->vm_ops->close(vma);
+ if (vma->vm_file)
+- fput(vma->vm_file);
++ vma_fput(vma);
+ mpol_put(vma_policy(vma));
+ if (unreachable)
+ __vm_area_free(vma);
+@@ -554,7 +554,7 @@ static inline void vma_complete(struct vma_prepare *vp,
+ if (vp->file) {
+ uprobe_munmap(vp->remove, vp->remove->vm_start,
+ vp->remove->vm_end);
+- fput(vp->file);
++ vma_fput(vp->vma);
+ }
+ if (vp->remove->anon_vma)
+ anon_vma_merge(vp->vma, vp->remove);
+@@ -2357,7 +2357,7 @@ static int __split_vma(struct vma_iterator *vmi, struct vm_area_struct *vma,
+ goto out_free_mpol;
+
+ if (new->vm_file)
+- get_file(new->vm_file);
++ vma_get_file(new);
+
+ if (new->vm_ops && new->vm_ops->open)
+ new->vm_ops->open(new);
+@@ -2855,7 +2855,7 @@ unsigned long mmap_region(struct file *file, unsigned long addr,
+ * and cause general protection fault
+ * ultimately.
+ */
+- fput(vma->vm_file);
++ vma_fput(vma);
+ vm_area_free(vma);
+ vma = merge;
+ /* Update vm_flags to pick up the change. */
+@@ -2950,7 +2950,7 @@ unsigned long mmap_region(struct file *file, unsigned long addr,
+
+ if (file || vma->vm_file) {
+ unmap_and_free_vma:
+- fput(vma->vm_file);
++ vma_fput(vma);
+ vma->vm_file = NULL;
+
+ vma_iter_set(&vmi, vma->vm_end);
+@@ -3012,6 +3012,9 @@ SYSCALL_DEFINE5(remap_file_pages, unsigned long, start, unsigned long, size,
+ unsigned long populate = 0;
+ unsigned long ret = -EINVAL;
+ struct file *file;
++#if 1 /* IS_ENABLED(CONFIG_AUFS_FS) */
++ struct file *prfile;
++#endif
+
+ pr_warn_once("%s (%d) uses deprecated remap_file_pages() syscall. See Documentation/mm/remap_file_pages.rst.\n",
+ current->comm, current->pid);
+@@ -3070,10 +3073,34 @@ SYSCALL_DEFINE5(remap_file_pages, unsigned long, start, unsigned long, size,
+ if (vma->vm_flags & VM_LOCKED)
+ flags |= MAP_LOCKED;
+
++#if 1 /* IS_ENABLED(CONFIG_AUFS_FS) */
++ vma_get_file(vma);
++ file = vma->vm_file;
++ prfile = vma->vm_prfile;
++ ret = do_mmap(vma->vm_file, start, size,
++ prot, flags, /*vm_flags*/0, pgoff, &populate, NULL);
++ if (!IS_ERR_VALUE(ret) && file && prfile) {
++ struct vm_area_struct *new_vma;
+
-+ 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);
-+ }
++ new_vma = find_vma(mm, ret);
++ if (!new_vma->vm_prfile)
++ new_vma->vm_prfile = prfile;
++ if (prfile)
++ get_file(prfile);
+ }
-+ hlist_bl_unlock(files);
++ /*
++ * two fput()s instead of vma_fput(vma),
++ * coz vma may not be available anymore.
++ */
++ fput(file);
++ if (prfile)
++ fput(prfile);
++#else
+ file = get_file(vma->vm_file);
+ ret = do_mmap(vma->vm_file, start, size,
+ prot, flags, 0, pgoff, &populate, NULL);
+ fput(file);
++#endif /* CONFIG_AUFS_FS */
+ out:
+ mmap_write_unlock(mm);
+ if (populate)
+@@ -3420,7 +3447,7 @@ struct vm_area_struct *copy_vma(struct vm_area_struct **vmap,
+ if (anon_vma_clone(new_vma, vma))
+ goto out_free_mempol;
+ if (new_vma->vm_file)
+- get_file(new_vma->vm_file);
++ vma_get_file(new_vma);
+ if (new_vma->vm_ops && new_vma->vm_ops->open)
+ new_vma->vm_ops->open(new_vma);
+ if (vma_link(mm, new_vma))
+@@ -3434,7 +3461,7 @@ struct vm_area_struct *copy_vma(struct vm_area_struct **vmap,
+ new_vma->vm_ops->close(new_vma);
+
+ if (new_vma->vm_file)
+- fput(new_vma->vm_file);
++ vma_fput(new_vma);
+
+ unlink_anon_vmas(new_vma);
+ out_free_mempol:
+diff --git a/mm/nommu.c b/mm/nommu.c
+index b6dc558d3144..d96655486468 100644
+--- a/mm/nommu.c
++++ b/mm/nommu.c
+@@ -523,7 +523,7 @@ static void __put_nommu_region(struct vm_region *region)
+ up_write(&nommu_region_sem);
+
+ if (region->vm_file)
+- fput(region->vm_file);
++ vmr_fput(region);
+
+ /* IO memory and memory shared directly out of the pagecache
+ * from ramfs/tmpfs mustn't be released here */
+@@ -603,7 +603,7 @@ static void delete_vma(struct mm_struct *mm, struct vm_area_struct *vma)
+ if (vma->vm_ops && vma->vm_ops->close)
+ vma->vm_ops->close(vma);
+ if (vma->vm_file)
+- fput(vma->vm_file);
++ vma_fput(vma);
+ put_nommu_region(vma->vm_region);
+ vm_area_free(vma);
+ }
+@@ -1135,7 +1135,7 @@ unsigned long do_mmap(struct file *file,
+ goto error_just_free;
+ }
+ }
+- fput(region->vm_file);
++ vmr_fput(region);
+ kmem_cache_free(vm_region_jar, region);
+ region = pregion;
+ result = start;
+@@ -1221,10 +1221,10 @@ unsigned long do_mmap(struct file *file,
+ error:
+ vma_iter_free(&vmi);
+ if (region->vm_file)
+- fput(region->vm_file);
++ vmr_fput(region);
+ kmem_cache_free(vm_region_jar, region);
+ if (vma->vm_file)
+- fput(vma->vm_file);
++ vma_fput(vma);
+ vm_area_free(vma);
+ return ret;
+
+diff --git a/mm/prfile.c b/mm/prfile.c
+new file mode 100644
+index 000000000000..8f820a235364
+--- /dev/null
++++ b/mm/prfile.c
+@@ -0,0 +1,86 @@
++// SPDX-License-Identifier: GPL-2.0
++/*
++ * Mainly for aufs which mmap(2) different file and wants to print different
++ * path in /proc/PID/maps.
++ * Call these functions via macros defined in linux/mm.h.
++ *
++ * See Documentation/filesystems/aufs/design/06mmap.txt
++ *
++ * Copyright (c) 2014-2022 Junjro R. Okajima
++ * Copyright (c) 2014 Ian Campbell
++ */
+
-+ return n;
-+}
++#include <linux/mm.h>
++#include <linux/file.h>
++#include <linux/fs.h>
+
-+static struct file **au_farray_alloc(struct super_block *sb,
-+ unsigned long long *max)
++/* #define PRFILE_TRACE */
++static inline void prfile_trace(struct file *f, struct file *pr,
++ const char func[], int line, const char func2[])
+{
-+ 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);
++#ifdef PRFILE_TRACE
++ if (pr)
++ pr_info("%s:%d: %s, %pD2\n", func, line, func2, f);
++#endif
+}
+
-+static void au_farray_free(struct file **a, unsigned long long max)
++void vma_do_file_update_time(struct vm_area_struct *vma, const char func[],
++ int line)
+{
-+ unsigned long long ull;
++ struct file *f = vma->vm_file, *pr = vma->vm_prfile;
+
-+ for (ull = 0; ull < max; ull++)
-+ if (a[ull])
-+ fput(a[ull]);
-+ kvfree(a);
++ prfile_trace(f, pr, func, line, __func__);
++ file_update_time(f);
++ if (f && pr)
++ file_update_time(pr);
+}
+
-+/* ---------------------------------------------------------------------- */
-+
-+/*
-+ * 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)
++struct file *vma_do_pr_or_file(struct vm_area_struct *vma, const char func[],
++ int line)
+{
-+ return (inode && !S_ISDIR(inode->i_mode)) || btop == bbot;
-+}
++ struct file *f = vma->vm_file, *pr = vma->vm_prfile;
+
-+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);
++ prfile_trace(f, pr, func, line, __func__);
++ return (f && pr) ? pr : f;
+}
+
-+/*
-+ * 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)
++void vma_do_get_file(struct vm_area_struct *vma, const char func[], int line)
+{
-+ 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);
-+ }
-+ }
++ struct file *f = vma->vm_file, *pr = vma->vm_prfile;
+
-+out_dpages:
-+ au_dpages_free(&dpages);
-+out:
-+ return err;
++ prfile_trace(f, pr, func, line, __func__);
++ get_file(f);
++ if (f && pr)
++ get_file(pr);
+}
+
-+static int test_inode_busy(struct super_block *sb, aufs_bindex_t bindex,
-+ unsigned int sigen, const unsigned int verbose)
++void vma_do_fput(struct vm_area_struct *vma, const char func[], int line)
+{
-+ 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);
++ struct file *f = vma->vm_file, *pr = vma->vm_prfile;
+
-+out:
-+ return err;
++ prfile_trace(f, pr, func, line, __func__);
++ fput(f);
++ if (f && pr)
++ fput(pr);
+}
+
-+static int test_children_busy(struct dentry *root, aufs_bindex_t bindex,
-+ const unsigned int verbose)
++#ifndef CONFIG_MMU
++struct file *vmr_do_pr_or_file(struct vm_region *region, const char func[],
++ int line)
+{
-+ 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() */
++ struct file *f = region->vm_file, *pr = region->vm_prfile;
+
-+ return err;
++ prfile_trace(f, pr, func, line, __func__);
++ return (f && pr) ? pr : f;
+}
+
-+static int test_dir_busy(struct file *file, aufs_bindex_t br_id,
-+ struct file **to_free, int *idx)
++void vmr_do_fput(struct vm_region *region, const char func[], int line)
+{
-+ 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;
++ struct file *f = region->vm_file, *pr = region->vm_prfile;
+
-+out:
-+ return err;
++ prfile_trace(f, pr, func, line, __func__);
++ fput(f);
++ if (f && pr)
++ fput(pr);
+}
++#endif /* !CONFIG_MMU */
+SPDX-License-Identifier: GPL-2.0
+aufs6.x-rcN standalone patch
+
+diff --git a/fs/dcache.c b/fs/dcache.c
+index 78e322b59b8d..7d8fbe5b7ce5 100644
+--- a/fs/dcache.c
++++ b/fs/dcache.c
+@@ -1318,6 +1318,7 @@ void d_walk(struct dentry *parent, void *data,
+ seq = 1;
+ goto again;
+ }
++EXPORT_SYMBOL_GPL(d_walk);
+
+ struct check_mount {
+ struct vfsmount *mnt;
+@@ -2880,6 +2881,7 @@ void d_exchange(struct dentry *dentry1, struct dentry *dentry2)
+
+ write_sequnlock(&rename_lock);
+ }
++EXPORT_SYMBOL_GPL(d_exchange);
+
+ /**
+ * d_ancestor - search for an ancestor
+diff --git a/fs/exec.c b/fs/exec.c
+index af4fbb61cd53..aa5161ad2c1f 100644
+--- a/fs/exec.c
++++ b/fs/exec.c
+@@ -113,6 +113,7 @@ bool path_noexec(const struct path *path)
+ return (path->mnt->mnt_flags & MNT_NOEXEC) ||
+ (path->mnt->mnt_sb->s_iflags & SB_I_NOEXEC);
+ }
++EXPORT_SYMBOL_GPL(path_noexec);
+
+ #ifdef CONFIG_USELIB
+ /*
+diff --git a/fs/fcntl.c b/fs/fcntl.c
+index 96a562b48ec7..e21a0fcff538 100644
+--- a/fs/fcntl.c
++++ b/fs/fcntl.c
+@@ -87,6 +87,7 @@ int setfl(int fd, struct file * filp, unsigned int arg)
+ out:
+ return error;
+ }
++EXPORT_SYMBOL_GPL(setfl);
+
+ static void f_modown(struct file *filp, struct pid *pid, enum pid_type type,
+ int force)
+diff --git a/fs/file_table.c b/fs/file_table.c
+index b991f90571b4..a3ba5726194a 100644
+--- a/fs/file_table.c
++++ b/fs/file_table.c
+@@ -222,6 +222,7 @@ struct file *alloc_empty_file(int flags, const struct cred *cred)
+ }
+ return ERR_PTR(-ENFILE);
+ }
++EXPORT_SYMBOL_GPL(alloc_empty_file);
+
+ /*
+ * Variant of alloc_empty_file() that doesn't check and modify nr_files.
+diff --git a/fs/namespace.c b/fs/namespace.c
+index a4b6ce51848e..c7415f75ab4c 100644
+--- a/fs/namespace.c
++++ b/fs/namespace.c
+@@ -865,6 +865,7 @@ int is_current_mnt_ns(struct vfsmount *mnt)
+ {
+ return check_mnt(real_mount(mnt));
+ }
++EXPORT_SYMBOL_GPL(is_current_mnt_ns);
+
+ /*
+ * vfsmount lock must be held for write
+@@ -2053,6 +2054,7 @@ struct vfsmount *collect_mounts(const struct path *path)
+ return ERR_CAST(tree);
+ return &tree->mnt;
+ }
++EXPORT_SYMBOL_GPL(collect_mounts);
+
+ static void free_mnt_ns(struct mnt_namespace *);
+ static struct mnt_namespace *alloc_mnt_ns(struct user_namespace *, bool);
+@@ -2083,6 +2085,7 @@ void drop_collected_mounts(struct vfsmount *mnt)
+ unlock_mount_hash();
+ namespace_unlock();
+ }
++EXPORT_SYMBOL_GPL(drop_collected_mounts);
+
+ static bool has_locked_children(struct mount *mnt, struct dentry *dentry)
+ {
+@@ -2154,6 +2157,7 @@ int iterate_mounts(int (*f)(struct vfsmount *, void *), void *arg,
+ }
+ return 0;
+ }
++EXPORT_SYMBOL_GPL(iterate_mounts);
+
+ static void lock_mnt_tree(struct mount *mnt)
+ {
+diff --git a/fs/notify/group.c b/fs/notify/group.c
+index 1de6631a3925..3008eb37a18d 100644
+--- a/fs/notify/group.c
++++ b/fs/notify/group.c
+@@ -100,6 +100,7 @@ void fsnotify_get_group(struct fsnotify_group *group)
+ {
+ refcount_inc(&group->refcnt);
+ }
++EXPORT_SYMBOL_GPL(fsnotify_get_group);
+
+ /*
+ * Drop a reference to a group. Free it if it's through.
+diff --git a/fs/open.c b/fs/open.c
+index a84d21e55c39..35183a95dafd 100644
+--- a/fs/open.c
++++ b/fs/open.c
+@@ -67,6 +67,7 @@ int do_truncate(struct mnt_idmap *idmap, struct dentry *dentry,
+ inode_unlock(dentry->d_inode);
+ return ret;
+ }
++EXPORT_SYMBOL_GPL(do_truncate);
+
+ long vfs_truncate(const struct path *path, loff_t length)
+ {
+diff --git a/fs/read_write.c b/fs/read_write.c
+index d4c036e82b6c..c61361ff5e67 100644
+--- a/fs/read_write.c
++++ b/fs/read_write.c
+@@ -483,6 +483,7 @@ ssize_t vfs_read(struct file *file, char __user *buf, size_t count, loff_t *pos)
+ inc_syscr(current);
+ return ret;
+ }
++EXPORT_SYMBOL_GPL(vfs_read);
+
+ static ssize_t new_sync_write(struct file *filp, const char __user *buf, size_t len, loff_t *ppos)
+ {
+@@ -598,6 +599,7 @@ ssize_t vfs_write(struct file *file, const char __user *buf, size_t count, loff_
+ file_end_write(file);
+ return ret;
+ }
++EXPORT_SYMBOL_GPL(vfs_write);
+
+ /* file_ppos returns &file->f_pos or NULL if file is stream */
+ static inline loff_t *file_ppos(struct file *file)
+diff --git a/fs/splice.c b/fs/splice.c
+index 7210ddc5aa81..9e83f46eacc8 100644
+--- a/fs/splice.c
++++ b/fs/splice.c
+@@ -940,6 +940,7 @@ ssize_t do_splice_from(struct pipe_inode_info *pipe, struct file *out,
+ return warn_unsupported(out, "write");
+ return out->f_op->splice_write(pipe, out, ppos, len, flags);
+ }
++EXPORT_SYMBOL_GPL(do_splice_from);
+
+ /*
+ * Indicate to the caller that there was a premature EOF when reading from the
+diff --git a/fs/xattr.c b/fs/xattr.c
+index 09d927603433..890daee95a7b 100644
+--- a/fs/xattr.c
++++ b/fs/xattr.c
+@@ -406,6 +406,7 @@ vfs_getxattr_alloc(struct mnt_idmap *idmap, struct dentry *dentry,
+ *xattr_value = value;
+ return error;
+ }
++EXPORT_SYMBOL_GPL(vfs_getxattr_alloc);
+
+ ssize_t
+ __vfs_getxattr(struct dentry *dentry, struct inode *inode, const char *name,
+diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c
+index 2223ee909c10..d0ac4fc69a31 100644
+--- a/kernel/locking/lockdep.c
++++ b/kernel/locking/lockdep.c
+@@ -239,6 +239,7 @@ inline struct lock_class *lockdep_hlock_class(struct held_lock *hlock)
+ */
+ return lock_classes + class_idx;
+ }
++EXPORT_SYMBOL_GPL(lockdep_hlock_class);
+ #define hlock_class(hlock) lockdep_hlock_class(hlock)
+
+ #ifdef CONFIG_LOCK_STAT
+diff --git a/kernel/task_work.c b/kernel/task_work.c
+index 95a7e1b7f1da..5053670775d3 100644
+--- a/kernel/task_work.c
++++ b/kernel/task_work.c
+@@ -183,3 +183,4 @@ void task_work_run(void)
+ } while (work);
+ }
+ }
++EXPORT_SYMBOL_GPL(task_work_run);
+diff --git a/security/security.c b/security/security.c
+index 7035ee35a393..eb461a68073f 100644
+--- a/security/security.c
++++ b/security/security.c
+@@ -1835,6 +1835,7 @@ int security_path_rmdir(const struct path *dir, struct dentry *dentry)
+ return 0;
+ return call_int_hook(path_rmdir, 0, dir, dentry);
+ }
++EXPORT_SYMBOL_GPL(security_path_rmdir);
+
+ /**
+ * security_path_unlink() - Check if removing a hard link is allowed
+@@ -1870,6 +1871,7 @@ int security_path_symlink(const struct path *dir, struct dentry *dentry,
+ return 0;
+ return call_int_hook(path_symlink, 0, dir, dentry, old_name);
+ }
++EXPORT_SYMBOL_GPL(security_path_symlink);
+
+ /**
+ * security_path_link - Check if creating a hard link is allowed
+@@ -1888,6 +1890,7 @@ int security_path_link(struct dentry *old_dentry, const struct path *new_dir,
+ return 0;
+ return call_int_hook(path_link, 0, old_dentry, new_dir, new_dentry);
+ }
++EXPORT_SYMBOL_GPL(security_path_link);
+
+ /**
+ * security_path_rename() - Check if renaming a file is allowed
+@@ -1949,6 +1952,7 @@ int security_path_chmod(const struct path *path, umode_t mode)
+ return 0;
+ return call_int_hook(path_chmod, 0, path, mode);
+ }
++EXPORT_SYMBOL_GPL(security_path_chmod);
+
+ /**
+ * security_path_chown() - Check if changing the file's owner/group is allowed
+@@ -1966,6 +1970,7 @@ int security_path_chown(const struct path *path, kuid_t uid, kgid_t gid)
+ return 0;
+ return call_int_hook(path_chown, 0, path, uid, gid);
+ }
++EXPORT_SYMBOL_GPL(security_path_chown);
+
+ /**
+ * security_path_chroot() - Check if changing the root directory is allowed
+@@ -2195,6 +2200,7 @@ int security_inode_permission(struct inode *inode, int mask)
+ return 0;
+ return call_int_hook(inode_permission, 0, inode, mask);
+ }
++EXPORT_SYMBOL_GPL(security_inode_permission);
+
+ /**
+ * security_inode_setattr() - Check if setting file attributes is allowed
+@@ -2667,6 +2673,7 @@ int security_file_permission(struct file *file, int mask)
+ {
+ return call_int_hook(file_permission, 0, file, mask);
+ }
++EXPORT_SYMBOL_GPL(security_file_permission);
+
+ /**
+ * security_file_alloc() - Allocate and init a file's LSM blob
+@@ -2951,6 +2958,7 @@ int security_file_truncate(struct file *file)
+ {
+ return call_int_hook(file_truncate, 0, file);
+ }
++EXPORT_SYMBOL_GPL(security_file_truncate);
+
+ /**
+ * security_task_alloc() - Allocate a task's LSM blob
+diff -urN /usr/share/empty/Documentation/ABI/testing/debugfs-aufs linux/Documentation/ABI/testing/debugfs-aufs
+--- /usr/share/empty/Documentation/ABI/testing/debugfs-aufs 1970-01-01 01:00:00.000000000 +0100
++++ linux/Documentation/ABI/testing/debugfs-aufs 2022-11-05 23:02:18.955889283 +0100
+@@ -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.
+
-+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;
++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".
+
-+ array = au_farray_alloc(sb, &max);
-+ err = PTR_ERR(array);
-+ if (IS_ERR(array))
-+ goto out;
++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.
+
-+ 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;
++What: /debug/aufs/si_<id>/xi<branch-index>
++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.
+
-+ /* 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);
++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 -urN /usr/share/empty/Documentation/ABI/testing/sysfs-aufs linux/Documentation/ABI/testing/sysfs-aufs
+--- /usr/share/empty/Documentation/ABI/testing/sysfs-aufs 1970-01-01 01:00:00.000000000 +0100
++++ linux/Documentation/ABI/testing/sysfs-aufs 2022-11-05 23:02:18.955889283 +0100
+@@ -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.
+
-+out:
-+ return err;
-+}
++What: /sys/fs/aufs/si_<id>/br<idx>
++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.
+
-+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;
++What: /sys/fs/aufs/si_<id>/brid<idx>
++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.
+
-+ for (ull = 0; ull < opened; ull++) {
-+ file = to_free[ull];
-+ if (unlikely(!file))
-+ break;
++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 -urN /usr/share/empty/Documentation/filesystems/aufs/design/01intro.txt linux/Documentation/filesystems/aufs/design/01intro.txt
+--- /usr/share/empty/Documentation/filesystems/aufs/design/01intro.txt 1970-01-01 01:00:00.000000000 +0100
++++ linux/Documentation/filesystems/aufs/design/01intro.txt 2022-11-05 23:02:18.955889283 +0100
+@@ -0,0 +1,171 @@
+
-+ /* 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;
++# Copyright (C) 2005-2022 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/>.
+
-+ 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);
-+ }
-+}
++Introduction
++----------------------------------------
+
-+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;
++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".
+
-+ AuRwMustWriteLock(&sbinfo->si_rwsem);
++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...
+
-+ 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 */
-+}
++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.
+
-+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;
++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).
+
-+ AuRwMustWriteLock(&dinfo->di_rwsem);
++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).
+
-+ 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--;
++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.
+
-+ p = au_krealloc(dinfo->di_hdentry, sizeof(*p) * bbot, AuGFP_SBILIST,
-+ /*may_shrink*/1);
-+ if (p)
-+ dinfo->di_hdentry = p;
-+ /* harmless error */
-+}
++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).
+
-+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;
++In AUFS, the structure of filesystem resembles to Unionfs, but I
++implemented my own ideas, approaches and enhancements and it became
++totally different one.
+
-+ AuRwMustWriteLock(&iinfo->ii_rwsem);
++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).
+
-+ 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--;
++You may want to read my old paper "Filesystems in LiveCD"
++(http://aufs.sourceforge.net/aufs2/report/sq/sq.pdf).
+
-+ 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;
++Several characters/aspects/persona of aufs
++----------------------------------------------------------------------
+
-+ SiMustWriteLock(sb);
++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
+
-+ root = sb->s_root;
-+ inode = d_inode(root);
-+ sbinfo = au_sbi(sb);
-+ bbot = sbinfo->si_bbot;
++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.
+
-+ h_root = au_h_dptr(root, bindex);
-+ hinode = au_hi(inode, bindex);
-+ h_inode = au_igrab(hinode->hi_inode);
-+ au_hiput(hinode);
++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
+
-+ 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();
++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.
+
-+ /* ignore an error */
-+ au_dr_br_fin(sb, br); /* always, regardless the mount option */
++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.
+
-+ dput(h_root);
-+ iput(h_inode);
-+ au_br_do_free(br);
-+}
++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 -urN /usr/share/empty/Documentation/filesystems/aufs/design/02struct.txt linux/Documentation/filesystems/aufs/design/02struct.txt
+--- /usr/share/empty/Documentation/filesystems/aufs/design/02struct.txt 1970-01-01 01:00:00.000000000 +0100
++++ linux/Documentation/filesystems/aufs/design/02struct.txt 2022-11-05 23:02:18.955889283 +0100
+@@ -0,0 +1,258 @@
+
-+static unsigned long long empty_cb(struct super_block *sb, void *array,
-+ unsigned long long max, void *arg)
-+{
-+ return max;
-+}
++# Copyright (C) 2005-2022 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/>.
+
-+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;
++Basic Aufs Internal Structure
+
-+ 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);
++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
+
-+ 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;
-+ }
++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
+
-+ 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;
-+ }
++This style of an array is essentially same to the aufs
++superblock/inode/dentry/file objects.
+
-+ 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;
++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.
+
-+ 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;
-+ }
-+ }
++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.
+
-+ 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);
-+ }
++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.
+
-+ 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 */
++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.
+
-+ 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);
++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.
+
-+ goto out; /* success */
++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.
+
-+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;
-+}
++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.
+
-+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;
++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.
+
-+ 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;
-+ }
++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.
+
-+ 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;
++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.
+
-+ 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);
++As well as XINO files, aufs has a feature to truncate/refresh XIB to
++reduce the number of consumed disk blocks for these files.
+
-+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);
-+}
++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.
+
-+#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
++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).
+
-+/*
-+ * 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
-+}
++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).
+
-+static int do_need_sigen_inc(int a, int b)
-+{
-+ return au_br_whable(a) && !au_br_whable(b);
-+}
++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.
+
-+static int need_sigen_inc(int old, int new)
-+{
-+ return do_need_sigen_inc(old, new)
-+ || do_need_sigen_inc(new, old);
-+}
++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.
+
-+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;
-+ struct inode *h_inode;
+
-+ mnt_flags = au_mntflags(sb);
-+ verbose = !!au_opt_test(mnt_flags, VERBOSE);
++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.
+
-+ array = au_farray_alloc(sb, &max);
-+ err = PTR_ERR(array);
-+ if (IS_ERR(array))
-+ goto out;
++Basically the whiteout represents "logical deletion" which stops aufs to
++lookup further, but also it represents "dir is opaque" which also stop
++further lookup.
+
-+ do_warn = 0;
-+ br_id = au_sbr_id(sb, bindex);
-+ for (ull = 0; ull < max; ull++) {
-+ file = array[ull];
-+ if (unlikely(!file))
-+ break;
++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.
+
-+ /* 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);
-+ }
++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.
+
-+ FiMustNoWaiters(file);
-+ fi_read_unlock(file);
-+ fput(file);
-+ }
+
-+ err = 0;
-+ if (do_warn)
-+ au_warn_ima();
++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.
+
-+ for (ull = 0; ull < max; ull++) {
-+ file = array[ull];
-+ if (!file)
-+ continue;
++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.
+
-+ /* 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) {
-+ h_inode = file_inode(hf);
-+ if (hf->f_mode & FMODE_READ)
-+ i_readcount_inc(h_inode);
-+ put_write_access(h_inode);
-+ __mnt_drop_write(hf->f_path.mnt);
-+ }
-+ }
++For this purpose, use "aumvdown" command in aufs-util.git.
+diff -urN /usr/share/empty/Documentation/filesystems/aufs/design/03atomic_open.txt linux/Documentation/filesystems/aufs/design/03atomic_open.txt
+--- /usr/share/empty/Documentation/filesystems/aufs/design/03atomic_open.txt 1970-01-01 01:00:00.000000000 +0100
++++ linux/Documentation/filesystems/aufs/design/03atomic_open.txt 2022-11-05 23:02:18.955889283 +0100
+@@ -0,0 +1,85 @@
+
-+out_array:
-+ au_farray_free(array, max);
-+out:
-+ AuTraceErr(err);
-+ return err;
-+}
++# Copyright (C) 2015-2022 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/>.
+
-+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;
++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.
+
-+ 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);
++In order to support ->atomic_open() for aufs, there are a few
++approaches.
+
-+ err = test_br(d_inode(mod->h_root), mod->perm, mod->path);
-+ if (unlikely(err))
-+ goto out;
++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.
+
-+ br = au_sbr(sb, bindex);
-+ AuDebugOn(mod->h_root != au_br_dentry(br));
-+ if (br->br_perm == mod->perm)
-+ return 0; /* success */
++Pros and cons for each approach.
+
-+ /* 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;
-+ }
++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.
+
-+ 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;
++The approach A is ideal, but it hard to implement. So here is a
++variation of A, which is to be implemented.
+
-+ 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);
++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 -urN /usr/share/empty/Documentation/filesystems/aufs/design/03lookup.txt linux/Documentation/filesystems/aufs/design/03lookup.txt
+--- /usr/share/empty/Documentation/filesystems/aufs/design/03lookup.txt 1970-01-01 01:00:00.000000000 +0100
++++ linux/Documentation/filesystems/aufs/design/03lookup.txt 2022-11-05 23:02:18.959222617 +0100
+@@ -0,0 +1,113 @@
+
-+ 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;
++# Copyright (C) 2005-2022 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/>.
+
-+ 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;
++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.
+
-+ *do_refresh |= need_sigen_inc(br->br_perm, mod->perm);
-+ br->br_perm = mod->perm;
-+ goto out; /* success */
++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.
+
-+out_bf:
-+ au_kfree_try_rcu(bf);
-+out:
-+ AuTraceErr(err);
-+ return err;
-+}
+
-+/* ---------------------------------------------------------------------- */
++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?
+
-+int au_br_stfs(struct au_branch *br, struct aufs_stfs *stfs)
-+{
-+ int err;
-+ struct kstatfs kstfs;
++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?
+
-+ 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;
-+ }
++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.
+
-+ return err;
-+}
-diff --git a/fs/aufs/branch.h b/fs/aufs/branch.h
-new file mode 100644
-index 00000000000000..6818ba8df8a24f
---- /dev/null
-+++ b/fs/aufs/branch.h
-@@ -0,0 +1,375 @@
-+/* SPDX-License-Identifier: GPL-2.0 */
-+/*
-+ * Copyright (C) 2005-2022 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/>.
-+ */
++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.
+
-+/*
-+ * branch filesystems and xino for them
-+ */
+
-+#ifndef __AUFS_BRANCH_H__
-+#define __AUFS_BRANCH_H__
++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
+
-+#ifdef __KERNEL__
++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.
+
-+#include <linux/mount.h>
-+#include "dirren.h"
-+#include "dynop.h"
-+#include "lcnt.h"
-+#include "rwsem.h"
-+#include "super.h"
++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 -urN /usr/share/empty/Documentation/filesystems/aufs/design/04branch.txt linux/Documentation/filesystems/aufs/design/04branch.txt
+--- /usr/share/empty/Documentation/filesystems/aufs/design/04branch.txt 1970-01-01 01:00:00.000000000 +0100
++++ linux/Documentation/filesystems/aufs/design/04branch.txt 2022-11-05 23:02:18.959222617 +0100
+@@ -0,0 +1,74 @@
+
-+/* a xino file */
-+struct au_xino {
-+ struct file **xi_file;
-+ unsigned int xi_nfile;
++# Copyright (C) 2005-2022 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/>.
+
-+ struct {
-+ spinlock_t spin;
-+ ino_t *array;
-+ int total;
-+ /* reserved for future use */
-+ /* unsigned long *bitmap; */
-+ wait_queue_head_t wqh;
-+ } xi_nondir;
++Branch Manipulation
+
-+ struct mutex xi_mtx; /* protects xi_file array */
-+ struct hlist_bl_head xi_writing;
++Since aufs supports dynamic branch manipulation, ie. add/remove a branch
++and changing its permission/attribute, there are a lot of works to do.
+
-+ atomic_t xi_truncating;
+
-+ struct kref xi_kref;
-+};
++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.
+
-+/* 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
-+};
++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.
+
-+/* 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;
-+};
++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).
+
-+/* ext2 has 3 types of operations at least, ext3 has 4 */
-+#define AuBrDynOp (AuDyLast * 4)
++ 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.
+
-+#ifdef CONFIG_AUFS_HFSNOTIFY
-+/* support for asynchronous destruction */
-+struct au_br_hfsnotify {
-+ struct fsnotify_group *hfsn_group;
-+};
-+#endif
++ If any file on the deleting branch is opened by aufs, then aufs
++ rejects deleting.
+
-+/* sysfs entries */
-+struct au_brsysfs {
-+ char name[16];
-+ struct attribute attr;
-+};
+
-+enum {
-+ AuBrSysfs_BR,
-+ AuBrSysfs_BRID,
-+ AuBrSysfs_Last
-+};
++Modify the Permission of a Branch
++----------------------------------------------------------------------
++o Re-initialize or remove the xino file and whiteout bases if necessary.
++ See struct.txt.
+
-+/* protected by superblock rwsem */
-+struct au_branch {
-+ struct au_xino *br_xino;
++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 -urN /usr/share/empty/Documentation/filesystems/aufs/design/05wbr_policy.txt linux/Documentation/filesystems/aufs/design/05wbr_policy.txt
+--- /usr/share/empty/Documentation/filesystems/aufs/design/05wbr_policy.txt 1970-01-01 01:00:00.000000000 +0100
++++ linux/Documentation/filesystems/aufs/design/05wbr_policy.txt 2022-11-05 23:02:18.959222617 +0100
+@@ -0,0 +1,64 @@
+
-+ aufs_bindex_t br_id;
++# Copyright (C) 2005-2022 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/>.
+
-+ 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 */
++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.
+
-+ struct au_wbr *br_wbr;
-+ struct au_br_fhsm *br_fhsm;
++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.
+
-+#ifdef CONFIG_AUFS_HFSNOTIFY
-+ struct au_br_hfsnotify *br_hfsn;
-+#endif
++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.
+
-+#ifdef CONFIG_SYSFS
-+ /* entries under sysfs per mount-point */
-+ struct au_brsysfs br_sysfs[AuBrSysfs_Last];
-+#endif
++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 -urN /usr/share/empty/Documentation/filesystems/aufs/design/06dirren.dot linux/Documentation/filesystems/aufs/design/06dirren.dot
+--- /usr/share/empty/Documentation/filesystems/aufs/design/06dirren.dot 1970-01-01 01:00:00.000000000 +0100
++++ linux/Documentation/filesystems/aufs/design/06dirren.dot 2022-11-05 23:02:18.959222617 +0100
+@@ -0,0 +1,44 @@
+
-+#ifdef CONFIG_DEBUG_FS
-+ struct dentry *br_dbgaufs; /* xino */
-+#endif
++// to view this graph, run dot(1) command in GRAPHVIZ.
++//
++// 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/>.
+
-+ struct au_dr_br br_dirren;
-+};
++digraph G {
++node [shape=box];
++whinfo [label="detailed info file\n(lower_brid_root-hinum, h_inum, namelen, old name)"];
+
-+/* ---------------------------------------------------------------------- */
++node [shape=oval];
+
-+static inline struct vfsmount *au_br_mnt(struct au_branch *br)
-+{
-+ return br->br_path.mnt;
-+}
++aufs_rename -> whinfo [label="store/remove"];
+
-+static inline struct dentry *au_br_dentry(struct au_branch *br)
-+{
-+ return br->br_path.dentry;
-+}
++node [shape=oval];
++inode_list [label="h_inum list in branch\ncache"];
+
-+static inline struct mnt_idmap *au_br_idmap(struct au_branch *br)
-+{
-+ return mnt_idmap(br->br_path.mnt);
-+}
++node [shape=box];
++whinode [label="h_inum list file"];
+
-+static inline struct super_block *au_br_sb(struct au_branch *br)
-+{
-+ return au_br_mnt(br)->mnt_sb;
-+}
++node [shape=oval];
++brmgmt [label="br_add/del/mod/umount"];
+
-+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;
-+}
++brmgmt -> inode_list [label="create/remove"];
++brmgmt -> whinode [label="load/store"];
+
-+static inline int au_br_hnotifyable(int brperm __maybe_unused)
-+{
-+#ifdef CONFIG_AUFS_HNOTIFY
-+ return !(brperm & AuBrPerm_RR);
-+#else
-+ return 0;
-+#endif
-+}
++inode_list -> whinode [style=dashed,dir=both];
+
-+static inline int au_br_test_oflag(int oflag, struct au_branch *br)
-+{
-+ int err, exec_flag;
++aufs_rename -> inode_list [label="add/del"];
+
-+ err = 0;
-+ exec_flag = oflag & __FMODE_EXEC;
-+ if (unlikely(exec_flag && path_noexec(&br->br_path)))
-+ err = -EACCES;
++aufs_lookup -> inode_list [label="search"];
+
-+ return err;
++aufs_lookup -> whinfo [label="load/remove"];
+}
+diff -urN /usr/share/empty/Documentation/filesystems/aufs/design/06dirren.txt linux/Documentation/filesystems/aufs/design/06dirren.txt
+--- /usr/share/empty/Documentation/filesystems/aufs/design/06dirren.txt 1970-01-01 01:00:00.000000000 +0100
++++ linux/Documentation/filesystems/aufs/design/06dirren.txt 2022-11-05 23:02:18.959222617 +0100
+@@ -0,0 +1,102 @@
+
-+static inline void au_xino_get(struct au_branch *br)
-+{
-+ struct au_xino *xi;
++# Copyright (C) 2017-2022 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/>.
+
-+ xi = br->br_xino;
-+ if (xi)
-+ kref_get(&xi->xi_kref);
-+}
++Special handling for renaming a directory (DIRREN)
++----------------------------------------------------------------------
++First, let's assume we have a simple usecase.
+
-+static inline int au_xino_count(struct au_branch *br)
-+{
-+ int v;
-+ struct au_xino *xi;
++- /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")
+
-+ v = 0;
-+ xi = br->br_xino;
-+ if (xi)
-+ v = kref_read(&xi->xi_kref);
++Now, what should aufs behave against this rename(2)?
++There are a few possible cases.
+
-+ return v;
-+}
++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.
+
-+/* 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);
++A new aufs feature called DIRREN is introduced which implements the case
++D. There are several "extra information" added.
+
-+/* xino.c */
-+static const loff_t au_loff_max = LLONG_MAX;
++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
+
-+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);
++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
+
-+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(struct file *file, void *buf, size_t size, loff_t *pos);
-+ssize_t xino_fwrite(struct file *file, void *buf, size_t size, loff_t *pos);
++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
+
-+int au_xib_trunc(struct super_block *sb);
-+int au_xino_trunc(struct super_block *sb, aufs_bindex_t bindex, int idx_begin);
++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.
+
-+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);
++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 referred 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.
+
-+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);
++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.
+
-+ino_t au_xino_new_ino(struct super_block *sb);
-+void au_xino_delete_inode(struct inode *inode, const int unlinked);
++This DIRREN feature is enabled by aufs configuration, and is activated
++by a new mount option.
+
-+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);
++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 -urN /usr/share/empty/Documentation/filesystems/aufs/design/06fhsm.txt linux/Documentation/filesystems/aufs/design/06fhsm.txt
+--- /usr/share/empty/Documentation/filesystems/aufs/design/06fhsm.txt 1970-01-01 01:00:00.000000000 +0100
++++ linux/Documentation/filesystems/aufs/design/06fhsm.txt 2022-11-05 23:02:18.959222617 +0100
+@@ -0,0 +1,118 @@
+
-+int au_xino_path(struct seq_file *seq, struct file *file);
++# Copyright (C) 2011-2022 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/>.
+
-+/* ---------------------------------------------------------------------- */
++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.
+
-+/* @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;
++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.
+
-+ file = NULL;
-+ if (!xi)
-+ goto out;
++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.
+
-+ if (idx >= 0) {
-+ if (idx < xi->xi_nfile)
-+ file = xi->xi_file[idx];
-+ } else
-+ file = au_xino_file1(xi);
++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.
+
-+out:
-+ return file;
-+}
++Currently aufs FHSM handles the regular files only. Additionally they
++must not be hard-linked nor pseudo-linked.
+
-+/* ---------------------------------------------------------------------- */
+
-+/* 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;
-+}
++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.
+
-+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 mnt_idmap *au_sbr_idmap(struct super_block *sb, aufs_bindex_t bindex)
-+{
-+ return au_br_idmap(au_sbr(sb, bindex));
-+}
++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.
+
-+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;
-+}
++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.
+
-+static inline int au_sbr_whable(struct super_block *sb, aufs_bindex_t bindex)
-+{
-+ return au_br_whable(au_sbr_perm(sb, bindex));
-+}
++And of course, in every step, an error may happen. So the operation
++should restore the original file state after an error happens.
+diff -urN /usr/share/empty/Documentation/filesystems/aufs/design/06mmap.txt linux/Documentation/filesystems/aufs/design/06mmap.txt
+--- /usr/share/empty/Documentation/filesystems/aufs/design/06mmap.txt 1970-01-01 01:00:00.000000000 +0100
++++ linux/Documentation/filesystems/aufs/design/06mmap.txt 2022-11-05 23:02:18.959222617 +0100
+@@ -0,0 +1,72 @@
+
-+/* ---------------------------------------------------------------------- */
++# Copyright (C) 2005-2022 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/>.
+
-+#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)
-+*/
++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.
+
-+#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)
++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.
+
-+#define WbrWhMustNoWaiters(wbr) AuRwMustNoWaiters(&(wbr)->wbr_wh_rwsem)
-+#define WbrWhMustAnyLock(wbr) AuRwMustAnyLock(&(wbr)->wbr_wh_rwsem)
-+#define WbrWhMustWriteLock(wbr) AuRwMustWriteLock(&(wbr)->wbr_wh_rwsem)
++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.
+
-+#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;
-+}
++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.
+
-+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
++I have to give up this "looks-smater" approach.
+diff -urN /usr/share/empty/Documentation/filesystems/aufs/design/06xattr.txt linux/Documentation/filesystems/aufs/design/06xattr.txt
+--- /usr/share/empty/Documentation/filesystems/aufs/design/06xattr.txt 1970-01-01 01:00:00.000000000 +0100
++++ linux/Documentation/filesystems/aufs/design/06xattr.txt 2022-11-05 23:02:18.959222617 +0100
+@@ -0,0 +1,94 @@
+
-+#endif /* __KERNEL__ */
-+#endif /* __AUFS_BRANCH_H__ */
-diff --git a/fs/aufs/conf.mk b/fs/aufs/conf.mk
-new file mode 100644
-index 00000000000000..12782f8e0f3819
---- /dev/null
-+++ b/fs/aufs/conf.mk
-@@ -0,0 +1,40 @@
-+# SPDX-License-Identifier: GPL-2.0
++# Copyright (C) 2014-2022 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/>.
+
-+AuConfStr = CONFIG_AUFS_FS=${CONFIG_AUFS_FS}
++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.
+
-+define AuConf
-+ifdef ${1}
-+AuConfStr += ${1}=${${1}}
-+endif
-+endef
++A similar issue can happen around XATTR.
++getxattr(2) and listxattr(2) families behave as if dirperm1 option is
++always set. Otherwise these very unpleasant situation would happen.
++- listxattr(2) may return the duplicated entries.
++- users may not be able to remove or reset the XATTR forever,
+
-+AuConfAll = BRANCH_MAX_127 BRANCH_MAX_511 BRANCH_MAX_1023 BRANCH_MAX_32767 \
-+ SBILIST \
-+ HNOTIFY HFSNOTIFY \
-+ EXPORT INO_T_64 \
-+ XATTR \
-+ FHSM \
-+ RDU \
-+ DIRREN \
-+ SHWH \
-+ BR_RAMFS \
-+ BR_FUSE POLL \
-+ BR_HFSPLUS \
-+ BDEV_LOOP \
-+ DEBUG MAGIC_SYSRQ
-+$(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}
++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.
+
-+-include ${srctree}/${src}/conf_priv.mk
-diff --git a/fs/aufs/cpup.c b/fs/aufs/cpup.c
-new file mode 100644
-index 00000000000000..8c8bd5f7b28d81
---- /dev/null
-+++ b/fs/aufs/cpup.c
-@@ -0,0 +1,1459 @@
-+// SPDX-License-Identifier: GPL-2.0
-+/*
-+ * Copyright (C) 2005-2022 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/>.
-+ */
++Moreover there are some other categories. Aufs handles these rather
++unpopular categories as the ordinary ones, ie. there is no special
++condition nor exception.
+
-+/*
-+ * copy-up functions, see wbr_policy.c for copy-down
-+ */
++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.
+
-+#include <linux/fs_stack.h>
-+#include <linux/mm.h>
-+#include <linux/task_work.h>
-+#include "aufs.h"
++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.
+
-+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;
++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.
+
-+ BUILD_BUG_ON(sizeof(iflags) != sizeof(dst->i_flags));
++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").
+
-+ dst->i_flags |= iflags & ~mask;
-+ if (au_test_fs_notime(dst->i_sb))
-+ dst->i_flags |= S_NOATIME | S_NOCMTIME;
-+}
++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.
+
-+void au_cpup_attr_timesizes(struct inode *inode)
-+{
-+ struct inode *h_inode;
++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 -urN /usr/share/empty/Documentation/filesystems/aufs/design/07export.txt linux/Documentation/filesystems/aufs/design/07export.txt
+--- /usr/share/empty/Documentation/filesystems/aufs/design/07export.txt 1970-01-01 01:00:00.000000000 +0100
++++ linux/Documentation/filesystems/aufs/design/07export.txt 2022-11-05 23:02:18.959222617 +0100
+@@ -0,0 +1,58 @@
+
-+ h_inode = au_h_iptr(inode, au_ibtop(inode));
-+ fsstack_copy_attr_times(inode, h_inode);
-+ fsstack_copy_inode_size(inode, h_inode);
-+}
++# Copyright (C) 2005-2022 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/>.
+
-+void au_cpup_attr_nlink(struct inode *inode, int force)
-+{
-+ struct inode *h_inode;
-+ struct super_block *sb;
-+ aufs_bindex_t bindex, bbot;
++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 -urN /usr/share/empty/Documentation/filesystems/aufs/design/08shwh.txt linux/Documentation/filesystems/aufs/design/08shwh.txt
+--- /usr/share/empty/Documentation/filesystems/aufs/design/08shwh.txt 1970-01-01 01:00:00.000000000 +0100
++++ linux/Documentation/filesystems/aufs/design/08shwh.txt 2022-11-05 23:02:18.959222617 +0100
+@@ -0,0 +1,52 @@
+
-+ 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;
++# Copyright (C) 2005-2022 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/>.
+
-+ /*
-+ * 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);
++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.
+
-+ /*
-+ * 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);
-+ }
-+ }
-+}
++(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
+
-+void au_cpup_attr_changeable(struct inode *inode)
-+{
-+ struct inode *h_inode;
++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.
+
-+ 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);
-+}
++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
+
-+void au_cpup_igen(struct inode *inode, struct inode *h_inode)
-+{
-+ struct au_iinfo *iinfo = au_ii(inode);
++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
+
-+ IiMustWriteLock(inode);
++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 -urN /usr/share/empty/Documentation/filesystems/aufs/design/10dynop.txt linux/Documentation/filesystems/aufs/design/10dynop.txt
+--- /usr/share/empty/Documentation/filesystems/aufs/design/10dynop.txt 1970-01-01 01:00:00.000000000 +0100
++++ linux/Documentation/filesystems/aufs/design/10dynop.txt 2022-11-05 23:02:18.959222617 +0100
+@@ -0,0 +1,47 @@
+
-+ iinfo->ii_higen = h_inode->i_generation;
-+ iinfo->ii_hsb1 = h_inode->i_sb;
-+}
++# Copyright (C) 2010-2022 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/>.
+
-+void au_cpup_attr_all(struct inode *inode, int force)
-+{
-+ struct inode *h_inode;
++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.
+
-+ 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);
-+}
++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.
+
-+/* Note: dt_dentry and dt_h_dentry are not dget/dput-ed */
++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 -urN /usr/share/empty/Documentation/filesystems/aufs/README linux/Documentation/filesystems/aufs/README
+--- /usr/share/empty/Documentation/filesystems/aufs/README 1970-01-01 01:00:00.000000000 +0100
++++ linux/Documentation/filesystems/aufs/README 2023-09-02 12:00:06.376642958 +0200
+@@ -0,0 +1,409 @@
+
-+/* 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;
++Aufs6 -- advanced multi layered unification filesystem version 6.x
++http://aufs.sf.net
++Junjiro R. Okajima
+
-+ 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;
++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.
+
-+ 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;
++Aufs6 supports linux-v6.0 and later, try aufs6.0 branch in
++aufs-linux.git or aufs-standalone.git.
++If you want older kernel version support,
++- for linux-v5.x series, try aufs-linux.git or aufs-standalone.git
++- 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.
+
-+ /* 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);
-+}
++Note: the name of aufs5-linux.git and aufs5-standalone.git on github
++ were changed. Now they are aufs-linux.git and
++ aufs-standalone.git and they contain aufs5 and later branches.
+
-+/* ---------------------------------------------------------------------- */
++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>
+
-+/* internal use only */
-+struct au_cpup_reg_attr {
-+ int valid;
-+ struct kstat st;
-+ unsigned int iflags; /* inode->i_flags */
-+};
++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>
+
-+static noinline_for_stack
-+int cpup_iattr(struct dentry *dst, aufs_bindex_t bindex, struct path *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;
+
-+ br = au_sbr(dst->d_sb, bindex);
-+ h_path.mnt = au_br_mnt(br);
-+ h_path.dentry = au_h_dptr(dst, bindex);
-+ h_idst = d_inode(h_path.dentry);
-+ h_isrc = d_inode(h_src->dentry);
-+ 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);
++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...
+
-+ /* 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);
-+ }
++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...
+
-+ 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, h_src, icex, verbose);
-+ }
++Currently these features are dropped temporary from aufs6.
++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)
+
-+ return err;
-+}
++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
+
-+/* ---------------------------------------------------------------------- */
+
-+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;
++2. Download
++----------------------------------------
++There are three GIT trees for aufs6, aufs-linux.git,
++aufs-standalone.git, and aufs-util.git.
++While the aufs-util is always necessary, you need either of aufs-linux
++or aufs-standalone.
+
-+ zp = page_address(ZERO_PAGE(0));
-+ if (unlikely(!zp))
-+ return -ENOMEM; /* possible? */
++The aufs-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 aufs6 as an external kernel module.
++Several extra patches are not included in this tree. Only
++aufs-standalone tree contains them. They are described in the later
++section "Configuration and Compilation."
+
-+ err = 0;
-+ all_zero = 0;
-+ while (len) {
-+ AuDbg("len %lld\n", len);
-+ sz = blksize;
-+ if (len < blksize)
-+ sz = len;
++On the other hand, the aufs-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.
+
-+ 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;
++You will find GIT branches whose name is in form of "aufs6.x" where "x"
++represents the linux kernel version, "linux-6.x". For instance,
++"aufs6.0" is for linux-6.0. For latest "linux-6.x-rcN", use
++"aufs6.x-rcN" branch.
+
-+ 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;
++o aufs-linux tree
++$ git clone --reference /your/linux/git/tree \
++ git://github.com/sfjro/aufs-linux.git aufs-linux.git
++- if you don't have linux GIT tree, then remove "--reference ..."
++$ cd aufs-linux.git
++$ git checkout origin/aufs6.0
+
-+ 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;
++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 aufs git://github.com/sfjro/aufs-linux.git
++$ git fetch aufs
++$ git checkout -b my6.0 v6.0
++$ (add your local change...)
++$ git pull aufs aufs6.0
++- now you have v6.0 + your_changes + aufs6.0 in you my6.0 branch.
++- you may need to solve some conflicts between your_changes and
++ aufs6.0. in this case, git-rerere is recommended so that you can
++ solve the similar conflicts automatically when you upgrade to 6.1 or
++ later in the future.
+
-+ AuLabel(hole);
-+ res = vfsub_llseek(dst, rbytes, SEEK_CUR);
-+ err = res;
-+ if (unlikely(res < 0))
-+ break;
-+ }
-+ len -= rbytes;
-+ err = 0;
-+ }
++o aufs-standalone tree
++$ git clone git://github.com/sfjro/aufs-standalone.git aufs-standalone.git
++$ cd aufs-standalone.git
++$ git checkout origin/aufs6.0
+
-+ /* the last block may be a hole */
-+ if (!err && all_zero) {
-+ AuLabel(last hole);
++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/aufs6.0
+
-+ 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--;
-+ }
++Note: The 6.x-rcN branch is to be used with `rc' kernel versions ONLY.
++The minor version number, 'x' in '6.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.
+
-+ 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);
-+ }
-+ }
++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.
+
-+ return err;
-+}
++For (an unreleased) example:
++If you are using "linux-6.10" and the "aufs6.10" branch
++does not exist in aufs-util repository, then "aufs6.9", "aufs6.8"
++or something numerically smaller is the branch for your kernel.
+
-+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;
++Also you can view all branches by
++ $ git branch -a
+
-+ 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);
++3. Configuration and Compilation
++----------------------------------------
++Make sure you have git-checkout'ed the correct branch.
+
-+ 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);
++For aufs-linux tree,
++- enable CONFIG_AUFS_FS.
++- set other aufs configurations if necessary.
++- for aufs5.13 and later
++ 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 customize some LOCKDEP numbers. Here are what I use on my
++ test environment.
++ CONFIG_LOCKDEP_BITS=21
++ CONFIG_LOCKDEP_CHAINS_BITS=21
++ CONFIG_LOCKDEP_STACK_TRACE_BITS=24
++ Also you will need to expand some constant values in LOCKDEP. Refer
++ to lockdep-debug.patch in aufs-standalone.git.
+
-+out:
-+ return err;
-+}
++For aufs-standalone tree,
++There are several ways to build.
+
-+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;
++1.
++- apply ./aufs6-kbuild.patch to your kernel source files.
++- apply ./aufs6-base.patch too.
++- apply ./aufs6-mmap.patch too.
++- apply ./aufs6-standalone.patch too, if you have a plan to set
++ CONFIG_AUFS_FS=m. otherwise you don't need ./aufs-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.
+
-+ h_src_inode = file_inode(src);
-+ h_src_sb = h_src_inode->i_sb;
++2.
++- module only (CONFIG_AUFS_FS=m).
++- apply ./aufs6-base.patch to your kernel source files.
++- apply ./aufs6-mmap.patch too.
++- apply ./aufs6-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 aufs6-kbuild.patch, nor copying source files to your
++ kernel source tree.
+
-+ /* 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);
-+ }
++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.
+
-+ return err;
-+}
++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.
+
-+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;
++There several other patches in aufs-standalone.git. They are all
++optional. When you meet some problems, they will help you.
++- aufs6-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".
++- 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
++ Similar to some kernel configurations for LOCKDEP (see the top of
++ this section), you will need expand some constants in LOCKDEP for
++ aufs if you enable CONFIG_LOCKDEP.
+
-+ 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;
-+ }
++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
+
-+ /* the backend fs on NFS may not support cloning */
-+ err = au_do_copy(dst, src, len);
++And then,
++$ mkdir /tmp/rw /tmp/aufs
++# mount -t aufs -o br=/tmp/rw:${HOME} none /tmp/aufs
+
-+out:
-+ AuTraceErr(err);
-+ return err;
-+}
++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
+
-+/*
-+ * 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;
++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.
+
-+ /* 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;
-+ }
-+ }
++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.
+
-+ /* 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);
++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)
++- LSM (linux security module, if you are using)
++- behaviour which you think to be incorrect
++- actual operation, reproducible one is better
++- mailto: aufs-users at lists.sourceforge.net
+
-+out_src:
-+ fput(file[SRC].file);
-+ br = au_sbr(sb, file[SRC].bindex);
-+ au_lcnt_dec(&br->br_nfiles);
-+out:
-+ return err;
-+}
++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.
+
-+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);
++6. Acknowledgements
++----------------------------------------
++Thanks to everyone who have tried and are using aufs, whoever
++have reported a bug or any feedback.
+
-+ 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);
-+ }
++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, 2015/7, and 2021/12).
++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).
++huronOS team: Enya Quetzalli made donations (2022/5, 2023/5 and 8).
++Vasily Mikhaylichenko made a donation (2023/5).
+
-+out:
-+ return err;
-+}
++Thank you very much.
++Donations are always, including future donations, very important and
++helpful for me to keep on developing aufs.
+
-+static int au_do_cpup_symlink(struct path *h_path, struct dentry *h_src,
-+ struct inode *h_dir)
-+{
-+ int err;
-+ DEFINE_DELAYED_CALL(done);
-+ const char *sym;
+
-+ sym = vfs_get_link(h_src, &done);
-+ err = PTR_ERR(sym);
-+ if (IS_ERR(sym))
-+ goto out;
++7.
++----------------------------------------
++If you are an experienced user, no explanation is needed. Aufs is
++just a linux filesystem.
+
-+ err = vfsub_symlink(h_dir, h_path, sym);
+
-+out:
-+ do_delayed_call(&done);
-+ return err;
-+}
++Enjoy!
++
++# Local variables: ;
++# mode: text;
++# End: ;
+diff -urN /usr/share/empty/fs/aufs/aufs.h linux/fs/aufs/aufs.h
+--- /usr/share/empty/fs/aufs/aufs.h 1970-01-01 01:00:00.000000000 +0100
++++ linux/fs/aufs/aufs.h 2022-11-05 23:02:18.959222617 +0100
+@@ -0,0 +1,62 @@
++/* SPDX-License-Identifier: GPL-2.0 */
++/*
++ * Copyright (C) 2005-2022 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/>.
++ */
+
+/*
-+ * regardless 'acl' option, reset all ACL.
-+ * All ACL will be copied up later from the original entry on the lower branch.
++ * all header files
+ */
-+static int au_reset_acl(struct path *h_path, umode_t mode)
-+{
-+ int err;
-+ struct dentry *h_dentry;
-+ /* struct inode *h_inode; */
-+ struct mnt_idmap *h_idmap;
+
-+ h_idmap = mnt_idmap(h_path->mnt);
-+ h_dentry = h_path->dentry;
-+ /* h_inode = d_inode(h_dentry); */
-+ /* forget_all_cached_acls(h_inode)); */
-+ err = vfsub_remove_acl(h_idmap, h_dentry, XATTR_NAME_POSIX_ACL_ACCESS);
-+ AuTraceErr(err);
-+ if (err == -EOPNOTSUPP)
-+ err = 0;
-+ if (!err)
-+ err = vfsub_acl_chmod(h_idmap, h_dentry, mode);
++#ifndef __AUFS_H__
++#define __AUFS_H__
+
-+ AuTraceErr(err);
-+ return err;
-+}
++#ifdef __KERNEL__
+
-+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;
-+ struct mnt_idmap *h_idmap;
++#define AuStub(type, name, body, ...) \
++ static inline type name(__VA_ARGS__) { body; }
+
-+ h_idmap = mnt_idmap(h_path->mnt);
-+ err = vfsub_remove_acl(h_idmap, h_path->dentry,
-+ XATTR_NAME_POSIX_ACL_DEFAULT);
-+ AuTraceErr(err);
-+ if (err == -EOPNOTSUPP)
-+ err = 0;
-+ if (unlikely(err))
-+ goto out;
++#define AuStubVoid(name, ...) \
++ AuStub(void, name, , __VA_ARGS__)
++#define AuStubInt0(name, ...) \
++ AuStub(int, name, return 0, __VA_ARGS__)
+
-+ /*
-+ * 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);
++#include "debug.h"
+
-+out:
-+ return err;
-+}
++#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"
+
-+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;
++#endif /* __KERNEL__ */
++#endif /* __AUFS_H__ */
+diff -urN /usr/share/empty/fs/aufs/branch.c linux/fs/aufs/branch.c
+--- /usr/share/empty/fs/aufs/branch.c 1970-01-01 01:00:00.000000000 +0100
++++ linux/fs/aufs/branch.c 2024-03-10 23:40:47.083143450 +0100
+@@ -0,0 +1,1427 @@
++// SPDX-License-Identifier: GPL-2.0
++/*
++ * Copyright (C) 2005-2022 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/>.
++ */
+
-+ /* 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));
++/*
++ * branch management
++ */
+
-+ /* 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);
++#include <linux/compat.h>
++#include <linux/statfs.h>
++#include "aufs.h"
+
-+ 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;
++/*
++ * free a single branch
++ */
++static void au_br_do_free(struct au_branch *br)
++{
++ int i;
++ struct au_wbr *wbr;
++ struct au_dykey **key;
+
-+ 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_path, mode);
++ au_hnotify_fin_br(br);
++ /* always, regardless the mount option */
++ au_dr_hino_free(&br->br_dirren);
++ au_xino_put(br);
+
-+ 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 */
++ 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);
+
-+ 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);
++ 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 (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 path h_ppath;
-+ struct inode *h_dir;
-+ aufs_bindex_t bdst;
-+
-+ dentry = cpg->dentry;
-+ bdst = cpg->bdst;
-+ h_ppath.mnt = au_sbr_mnt(dentry->d_sb, 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_ppath.dentry = au_h_dptr(parent, bdst);
-+ dput(parent);
-+ h_path->dentry = vfsub_lkup_one(&dentry->d_name, &h_ppath);
-+ if (IS_ERR(h_path->dentry))
-+ err = PTR_ERR(h_path->dentry);
++ if (br->br_fhsm) {
++ au_br_fhsm_fin(br->br_fhsm);
++ au_kfree_try_rcu(br->br_fhsm);
+ }
-+ 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);
++ key = br->br_dykey;
++ for (i = 0; i < AuBrDynOp; i++, key++)
++ if (*key)
++ au_dy_put(*key);
++ else
++ break;
+
-+out:
-+ return err;
++ /* 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);
+}
+
+/*
-+ * 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.
++ * frees all branches
+ */
-+static int au_cpup_single(struct au_cp_generic *cpg, struct dentry *dst_parent)
++void au_br_free(struct au_sbinfo *sbinfo)
+{
-+ 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;
-+ struct path h_src_path;
-+ /* 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;
++ aufs_bindex_t bmax;
++ struct au_branch **br;
+
-+ 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);
++ AuRwMustWriteLock(&sbinfo->si_rwsem);
+
-+ h_src = au_h_dptr(cpg->dentry, cpg->bsrc);
-+ inode = d_inode(cpg->dentry);
++ bmax = sbinfo->si_bbot + 1;
++ br = sbinfo->si_branch;
++ while (bmax--)
++ au_br_do_free(*br++);
++}
+
-+ if (!dst_parent)
-+ dst_parent = dget_parent(cpg->dentry);
-+ else
-+ dget(dst_parent);
++/*
++ * 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;
+
-+ 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;
-+ }
++ bbot = au_sbbot(sb);
++ for (bindex = 0; bindex <= bbot; bindex++)
++ if (au_sbr_id(sb, bindex) == br_id)
++ return bindex;
++ return -1;
++}
+
-+ 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;
-+ }
++/*
++ * add a branch
++ */
+
-+ if (do_dt) {
-+ a->h_path.dentry = h_parent;
-+ au_dtime_store(&a->dt, dst_parent, &a->h_path);
-+ }
++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);
++}
+
-+ 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);
-+ }
++/*
++ * 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;
+
-+ isdir = S_ISDIR(inode->i_mode);
-+ old_ibtop = au_ibtop(inode);
-+ err = cpup_entry(cpg, dst_parent, &a->h_src_attr);
++ 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_rev;
-+ dst_inode = d_inode(h_dst);
-+ inode_lock_nested(dst_inode, AuLsc_I_CHILD2);
-+ /* todo: necessary? */
-+ /* au_pin_hdir_unlock(cpg->pin); */
++ goto out_xino;
+
-+ h_src_path.dentry = h_src;
-+ h_src_path.mnt = au_sbr_mnt(sb, cpg->bsrc);
-+ err = cpup_iattr(cpg->dentry, cpg->bdst, &h_src_path, &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 (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 (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 (au_br_fhsm(perm)) {
++ err = au_fhsm_br_alloc(add_branch);
++ if (unlikely(err))
++ goto out_wbr;
+ }
-+ 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;
++ 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);
+ }
-+out_parent:
-+ dput(dst_parent);
-+ au_kfree_rcu(a);
++ 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;
++ return ERR_PTR(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)
++/*
++ * test if the branch permission is legal or not.
++ */
++static int test_br(struct inode *inode, int brperm, char *path)
+{
-+ struct au_cpup_single_args *a = args;
++ int err;
+
-+ 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);
++ 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;
+}
-+#endif
+
+/*
-+ * prevent SIGXFSZ in copy-up.
-+ * testing CAP_MKNOD is for generic fs,
-+ * but CAP_FSETID is for xfs only, currently.
++ * returns:
++ * 0: success, the caller will add it
++ * plus: success, it is already unified, the caller should ignore it
++ * minus: error
+ */
-+static int au_cpup_sio_test(struct au_pin *pin, umode_t mode)
++static int test_add(struct super_block *sb, struct au_opt_add *add, int remount)
+{
-+ int do_sio;
-+ struct super_block *sb;
-+ struct inode *h_dir;
++ int err;
++ aufs_bindex_t bbot, bindex;
++ struct dentry *root, *h_dentry;
++ struct inode *inode, *h_inode;
+
-+ 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;
++ 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;
+ }
+
-+ return do_sio;
-+}
++ 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;
++ }
+
-+#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;
++ err = -EDOM;
++ if (unlikely(add->bindex < 0 || bbot + 1 < add->bindex)) {
++ pr_err("bad index %d\n", add->bindex);
++ goto out;
++ }
+
-+ 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;
++ 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;
+}
-+#endif
+
+/*
-+ * copyup the @dentry from the first active lower branch to @bdst,
-+ * using au_cpup_single().
++ * initialize or clean the whiteouts for an adding branch
+ */
-+static int au_cpup_simple(struct au_cp_generic *cpg)
++static int au_br_init_wh(struct super_block *sb, struct au_branch *br,
++ int new_perm)
+{
-+ int err;
-+ unsigned int flags_orig;
-+ struct dentry *dentry;
-+
-+ AuDebugOn(cpg->bsrc < 0);
++ int err, old_perm;
++ aufs_bindex_t bindex;
++ struct inode *h_inode;
++ struct au_wbr *wbr;
++ struct au_hinode *hdir;
++ struct dentry *h_dentry;
+
-+ dentry = cpg->dentry;
-+ DiMustWriteLock(dentry);
++ err = vfsub_mnt_want_write(au_br_mnt(br));
++ if (unlikely(err))
++ goto out;
+
-+ 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 */
++ 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;
+
-+ /* revert */
-+ au_set_h_dptr(dentry, cpg->bdst, NULL);
-+ au_set_dbtop(dentry, cpg->bsrc);
++ if (!err && wbr && !au_br_writable(new_perm)) {
++ au_kfree_rcu(wbr);
++ br->br_wbr = NULL;
+ }
+
++out:
+ return err;
+}
+
-+struct au_cpup_simple_args {
-+ int *errp;
-+ struct au_cp_generic *cpg;
-+};
-+
-+static void au_call_cpup_simple(void *args)
++static int au_wbr_init(struct au_branch *br, struct super_block *sb,
++ int perm)
+{
-+ struct au_cpup_simple_args *a = args;
++ int err;
++ struct kstatfs kst;
++ struct au_wbr *wbr;
+
-+ au_pin_hdir_acquire_nest(a->cpg->pin);
-+ *a->errp = au_cpup_simple(a->cpg);
-+ au_pin_hdir_release(a->cpg->pin);
++ 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;
+}
+
-+static int au_do_sio_cpup_simple(struct au_cp_generic *cpg)
++/* initialize a new branch */
++static int au_br_init(struct au_branch *br, struct super_block *sb,
++ struct au_opt_add *add)
+{
-+ int err, wkq_err;
-+ struct dentry *dentry, *parent;
-+ struct file *h_file;
-+ struct inode *h_dir;
-+ struct mnt_idmap *h_idmap;
++ int err;
++ struct au_branch *brbase;
++ struct file *xf;
++ struct inode *h_inode;
+
-+ 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;
++ 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;
+ }
+
-+ parent = dget_parent(dentry);
-+ h_dir = au_h_iptr(d_inode(parent), cpg->bdst);
-+ h_idmap = au_sbr_idmap(dentry->d_sb, cpg->bdst);
-+ if (!au_test_h_perm_sio(h_idmap, 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;
++ 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;
++ }
+ }
+
-+ dput(parent);
-+ if (h_file)
-+ au_h_open_post(dentry, cpg->bsrc, h_file);
++ 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;
+}
+
-+int au_sio_cpup_simple(struct au_cp_generic *cpg)
++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)
+{
-+ aufs_bindex_t bsrc, bbot;
-+ struct dentry *dentry, *h_dentry;
++ struct au_branch **brp;
+
-+ 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);
++ 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;
+}
+
-+int au_sio_cpdown_simple(struct au_cp_generic *cpg)
++static void au_br_do_add_hdp(struct au_dinfo *dinfo, aufs_bindex_t bindex,
++ aufs_bindex_t bbot, aufs_bindex_t amount)
+{
-+ AuDebugOn(cpg->bdst <= cpg->bsrc);
-+ return au_do_sio_cpup_simple(cpg);
-+}
++ struct au_hdentry *hdp;
+
-+/* ---------------------------------------------------------------------- */
++ AuRwMustWriteLock(&dinfo->di_rwsem);
+
-+/*
-+ * copyup the deleted file for writing.
-+ */
-+static int au_do_cpup_wh(struct au_cp_generic *cpg, struct dentry *wh_dentry,
-+ struct file *file)
++ 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)
+{
-+ 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;
++ struct au_hinode *hip;
+
-+ dinfo = au_di(cpg->dentry);
-+ AuRwMustWriteLock(&dinfo->di_rwsem);
++ AuRwMustWriteLock(&iinfo->ii_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;
++ 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;
++}
+
-+ 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;
++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;
+
-+ return err;
++ 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();
+}
+
-+static int au_cpup_wh(struct au_cp_generic *cpg, struct file *file)
++int au_br_add(struct super_block *sb, struct au_opt_add *add, int remount)
+{
+ 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;
++ aufs_bindex_t bbot, add_bindex;
++ struct dentry *root, *h_dentry;
++ struct inode *root_inode;
++ struct au_branch *add_branch;
+
-+ 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))
++ 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 */
++ }
+
-+ 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);
++ 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)) {
-+ AuIOErr("failed remove copied-up tmp file %pd(%d)\n",
-+ wh_dentry, err);
-+ err = -EIO;
++ au_br_do_free(add_branch);
++ goto out;
+ }
-+ au_dtime_revert(&dt);
-+ au_set_hi_wh(d_inode(dentry), bdst, wh_dentry);
+
-+out_wh:
-+ dput(wh_dentry);
++ 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:
-+ 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)
++static unsigned long long au_farray_cb(struct super_block *sb, void *a,
++ unsigned long long max __maybe_unused,
++ void *arg)
+{
-+ struct au_cpup_wh_args *a = args;
++ unsigned long long n;
++ struct file **p, *f;
++ struct hlist_bl_head *files;
++ struct hlist_bl_node *pos;
++ struct au_finfo *finfo;
+
-+ au_pin_hdir_acquire_nest(a->cpg->pin);
-+ *a->errp = au_cpup_wh(a->cpg, a->file);
-+ au_pin_hdir_release(a->cpg->pin);
++ 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;
+}
+
-+int au_sio_cpup_wh(struct au_cp_generic *cpg, struct file *file)
++static struct file **au_farray_alloc(struct super_block *sb,
++ unsigned long long *max)
+{
-+ 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;
-+ struct mnt_idmap *h_idmap;
++ struct au_sbinfo *sbi;
+
-+ 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;
++ 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);
++}
+
-+ 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);
++static void au_farray_free(struct file **a, unsigned long long max)
++{
++ unsigned long long ull;
+
-+ inode_lock_nested(h_tmpdir, AuLsc_I_PARENT3);
-+ /* todo: au_h_open_pre()? */
++ for (ull = 0; ull < max; ull++)
++ if (a[ull])
++ fput(a[ull]);
++ kvfree(a);
++}
+
-+ 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;
-+ }
++/* ---------------------------------------------------------------------- */
+
-+ h_idmap = au_sbr_idmap(dentry->d_sb, bdst);
-+ if (!au_test_h_perm_sio(h_idmap, 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;
-+ }
++/*
++ * delete a branch
++ */
+
-+ 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);
++/* 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)
+
-+ return err;
++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);
++}
+
+/*
-+ * generic routine for both of copy-up and copy-down.
++ * test if the branch is deletable or not.
+ */
-+/* 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)
++static int test_dentry_busy(struct dentry *root, aufs_bindex_t bindex,
++ unsigned int sigen, const unsigned int verbose)
+{
-+ int err;
-+ struct au_pin pin;
-+ struct dentry *d, *parent, *h_parent, *real_parent, *h_dentry;
++ int err, i, j, ndentry;
++ aufs_bindex_t btop, bbot;
++ struct au_dcsub_pages dpages;
++ struct au_dpage *dpage;
++ struct dentry *d;
+
-+ err = 0;
-+ parent = dget_parent(dentry);
-+ if (IS_ROOT(parent))
++ 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;
+
-+ 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);
++ 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;
++ }
++ }
+
-+ au_pin_set_dentry(&pin, d);
-+ err = au_do_pin(&pin);
-+ if (!err) {
-+ err = cp(d, bdst, &pin, h_parent, arg);
-+ au_unpin(&pin);
++ /* 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);
+ }
-+
-+ if (d != real_parent)
-+ di_write_unlock(d);
-+ if (unlikely(err))
-+ break;
+ }
+
++out_dpages:
++ au_dpages_free(&dpages);
+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)
++static int test_inode_busy(struct super_block *sb, aufs_bindex_t bindex,
++ unsigned int sigen, const unsigned int verbose)
+{
+ int err;
-+ struct dentry *parent;
-+ struct inode *dir;
++ unsigned long long max, ull;
++ struct inode *i, **array;
++ aufs_bindex_t btop, bbot;
+
-+ parent = dget_parent(dentry);
-+ dir = d_inode(parent);
-+ err = 0;
-+ if (au_h_iptr(dir, bdst))
++ array = au_iarray_alloc(sb, &max);
++ err = PTR_ERR(array);
++ if (IS_ERR(array))
+ 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);
++ 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:
-+ dput(parent);
+ return err;
+}
-diff --git a/fs/aufs/cpup.h b/fs/aufs/cpup.h
-new file mode 100644
-index 00000000000000..decd8f01425a05
---- /dev/null
-+++ b/fs/aufs/cpup.h
-@@ -0,0 +1,100 @@
-+/* SPDX-License-Identifier: GPL-2.0 */
-+/*
-+ * Copyright (C) 2005-2022 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/>.
-+ */
-+
-+/*
-+ * 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 00000000000000..d5811df890b5f5
---- /dev/null
-+++ b/fs/aufs/dbgaufs.c
-@@ -0,0 +1,526 @@
-+// SPDX-License-Identifier: GPL-2.0
-+/*
-+ * Copyright (C) 2005-2022 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/>.
-+ */
-+
-+/*
-+ * debugfs interface
-+ */
++static int test_children_busy(struct dentry *root, aufs_bindex_t bindex,
++ const unsigned int verbose)
++{
++ int err;
++ unsigned int sigen;
+
-+#include <linux/debugfs.h>
-+#include "aufs.h"
++ 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() */
+
-+#ifndef CONFIG_SYSFS
-+#error DEBUG_FS depends upon SYSFS
-+#endif
++ return err;
++}
+
-+static struct dentry *dbgaufs;
-+static const mode_t dbgaufs_mode = 0444;
++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;
+
-+/* 20 is max digits length of ulong 64 */
-+struct dbgaufs_arg {
-+ int n;
-+ char a[20 * 4];
-+};
++ err = 0;
++ root = IS_ROOT(file->f_path.dentry);
++ if (root) {
++ get_file(file);
++ to_free[*idx] = file;
++ (*idx)++;
++ goto out;
++ }
+
-+/*
-+ * common function for all XINO files
-+ */
-+static int dbgaufs_xi_release(struct inode *inode __maybe_unused,
-+ struct file *file)
-+{
-+ void *p;
++ 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;
+
-+ p = file->private_data;
-+ if (p) {
-+ /* this is struct dbgaufs_arg */
-+ AuDebugOn(!au_kfree_sz_test(p));
-+ au_kfree_do_rcu(p);
++ if (hfile->hf_br->br_id == br_id) {
++ matched = 1;
++ break;
++ }
+ }
-+ return 0;
++ if (matched)
++ err = -EBUSY;
++
++out:
++ return err;
+}
+
-+static int dbgaufs_xi_open(struct file *xf, struct file *file, int do_fcnt,
-+ int cnt)
++static int test_file_busy(struct super_block *sb, aufs_bindex_t br_id,
++ struct file **to_free, int opened)
+{
-+ int err;
-+ struct kstat st;
-+ struct dbgaufs_arg *p;
++ int err, idx;
++ unsigned long long ull, max;
++ aufs_bindex_t btop;
++ struct file *file, **array;
++ struct dentry *root;
++ struct au_hfile *hfile;
+
-+ err = -ENOMEM;
-+ p = kmalloc(sizeof(*p), GFP_NOFS);
-+ if (unlikely(!p))
++ array = au_farray_alloc(sb, &max);
++ err = PTR_ERR(array);
++ if (IS_ERR(array))
+ goto out;
+
+ err = 0;
-+ p->n = 0;
-+ file->private_data = p;
-+ if (!xf)
-+ goto out;
++ idx = 0;
++ root = sb->s_root;
++ di_write_unlock(root);
++ for (ull = 0; ull < max; ull++) {
++ file = array[ull];
++ if (unlikely(!file))
++ break;
+
-+ 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;
++ /* 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 ssize_t dbgaufs_xi_read(struct file *file, char __user *buf,
-+ size_t count, loff_t *ppos)
++static void br_del_file(struct file **to_free, unsigned long long opened,
++ aufs_bindex_t br_id)
+{
-+ struct dbgaufs_arg *p;
-+
-+ p = file->private_data;
-+ return simple_read_from_buffer(buf, count, ppos, p->a, p->n);
-+}
++ 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;
+
-+struct dbgaufs_plink_arg {
-+ int n;
-+ char a[];
-+};
++ /* 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;
+
-+static int dbgaufs_plink_release(struct inode *inode __maybe_unused,
-+ struct file *file)
-+{
-+ free_page((unsigned long)file->private_data);
-+ return 0;
++ 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 int dbgaufs_plink_open(struct inode *inode, struct file *file)
++static void au_br_do_del_brp(struct au_sbinfo *sbinfo,
++ const aufs_bindex_t bindex,
++ const aufs_bindex_t bbot)
+{
-+ 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;
++ struct au_branch **brp, **p;
+
-+ 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);
++ AuRwMustWriteLock(&sbinfo->si_rwsem);
+
-+ /* the number of buckets */
-+ n = snprintf(p->a + p->n, limit, "%d\n", AuPlink_NHASH);
-+ p->n += n;
-+ limit -= n;
++ 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--;
+
-+ sum = 0;
-+ for (i = 0, hbl = sbinfo->si_plink; i < AuPlink_NHASH;
-+ i++, hbl++) {
-+ n = au_hbl_count(hbl);
-+ sum += n;
++ p = au_krealloc(sbinfo->si_branch, sizeof(*p) * bbot, AuGFP_SBILIST,
++ /*may_shrink*/1);
++ if (p)
++ sbinfo->si_branch = p;
++ /* harmless error */
++}
+
-+ 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';
++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;
+
-+ /* 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;
-+ strscpy(p->a, str, sizeof(str));
-+#undef str
-+ }
-+ si_read_unlock(sb);
++ AuRwMustWriteLock(&dinfo->di_rwsem);
+
-+ err = 0;
-+ file->private_data = p;
-+ goto out; /* success */
++ 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--;
+
-+out_free:
-+ free_page((unsigned long)p);
-+out:
-+ return err;
++ p = au_krealloc(dinfo->di_hdentry, sizeof(*p) * bbot, AuGFP_SBILIST,
++ /*may_shrink*/1);
++ if (p)
++ dinfo->di_hdentry = p;
++ /* harmless error */
+}
+
-+static ssize_t dbgaufs_plink_read(struct file *file, char __user *buf,
-+ size_t count, loff_t *ppos)
++static void au_br_do_del_hip(struct au_iinfo *iinfo, const aufs_bindex_t bindex,
++ const aufs_bindex_t bbot)
+{
-+ struct dbgaufs_plink_arg *p;
++ struct au_hinode *hip, *p;
+
-+ p = file->private_data;
-+ return simple_read_from_buffer(buf, count, ppos, p->a, p->n);
-+}
++ AuRwMustWriteLock(&iinfo->ii_rwsem);
+
-+static const struct file_operations dbgaufs_plink_fop = {
-+ .owner = THIS_MODULE,
-+ .open = dbgaufs_plink_open,
-+ .release = dbgaufs_plink_release,
-+ .read = dbgaufs_plink_read
-+};
++ 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 int dbgaufs_xib_open(struct inode *inode, struct file *file)
++static void au_br_do_del(struct super_block *sb, aufs_bindex_t bindex,
++ struct au_branch *br)
+{
-+ int err;
++ aufs_bindex_t bbot;
+ struct au_sbinfo *sbinfo;
-+ struct super_block *sb;
++ struct dentry *root, *h_root;
++ struct inode *inode, *h_inode;
++ struct au_hinode *hinode;
+
-+ 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;
-+}
++ SiMustWriteLock(sb);
+
-+static const struct file_operations dbgaufs_xib_fop = {
-+ .owner = THIS_MODULE,
-+ .open = dbgaufs_xib_open,
-+ .release = dbgaufs_xi_release,
-+ .read = dbgaufs_xi_read
-+};
++ 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);
+
-+#define DbgaufsXi_PREFIX "xi"
++ 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();
+
-+static int dbgaufs_xino_open(struct inode *inode, struct file *file)
++ /* 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)
+{
-+ 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;
++ 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 = -ENOENT;
-+ name = &file->f_path.dentry->d_name;
-+ if (unlikely(name->len < sizeof(DbgaufsXi_PREFIX)
-+ || memcmp(name->name, DbgaufsXi_PREFIX,
-+ sizeof(DbgaufsXi_PREFIX) - 1)))
++ 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);
+
-+ 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))
++ 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;
-+ 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));
++ 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;
++ }
+
-+out_si:
-+ si_read_unlock(sb);
++ 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:
-+ AuTraceErr(err);
++ if (to_free)
++ au_farray_free(to_free, opened);
+ 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
-+};
++/* ---------------------------------------------------------------------- */
++
++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;
++}
+
-+void dbgaufs_xino_del(struct au_branch *br)
++long au_ibusy_ioctl(struct file *file, unsigned long arg)
+{
-+ 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();
++ return au_ibusy(file->f_path.dentry->d_sb, (void __user *)arg);
+}
+
-+void dbgaufs_brs_del(struct super_block *sb, aufs_bindex_t bindex)
++#ifdef CONFIG_COMPAT
++long au_ibusy_compat_ioctl(struct file *file, unsigned long arg)
+{
-+ 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);
-+ }
++ return au_ibusy(file->f_path.dentry->d_sb, compat_ptr(arg));
+}
++#endif
+
-+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));
++/*
++ * change a branch permission
++ */
+
-+ 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 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 void dbgaufs_br_add(struct super_block *sb, aufs_bindex_t bindex,
-+ struct dentry *parent, struct au_sbinfo *sbinfo)
++static int do_need_sigen_inc(int a, int b)
+{
-+ 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);
++ return au_br_whable(a) && !au_br_whable(b);
+}
+
-+void dbgaufs_brs_add(struct super_block *sb, aufs_bindex_t bindex, int topdown)
++static int need_sigen_inc(int old, int new)
+{
-+ struct au_sbinfo *sbinfo;
-+ struct dentry *parent;
-+ aufs_bindex_t bbot;
++ return do_need_sigen_inc(old, new)
++ || do_need_sigen_inc(new, old);
++}
+
-+ if (!au_opt_test(au_mntflags(sb), XINO))
-+ return;
++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;
++ struct inode *h_inode;
+
-+ sbinfo = au_sbi(sb);
-+ parent = sbinfo->si_dbgaufs;
-+ if (!parent)
-+ return;
++ mnt_flags = au_mntflags(sb);
++ verbose = !!au_opt_test(mnt_flags, VERBOSE);
+
-+ 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);
-+}
++ 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;
+
-+#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;
++ /* 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;
++ }
+
-+ 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;
-+}
++ 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);
++ }
+
-+static const struct file_operations dbgaufs_xigen_fop = {
-+ .owner = THIS_MODULE,
-+ .open = dbgaufs_xigen_open,
-+ .release = dbgaufs_xi_release,
-+ .read = dbgaufs_xi_read
-+};
++ FiMustNoWaiters(file);
++ fi_read_unlock(file);
++ fput(file);
++ }
+
-+static int dbgaufs_xigen_init(struct au_sbinfo *sbinfo)
-+{
-+ int err;
++ err = 0;
++ if (do_warn)
++ au_warn_ima();
+
-+ /*
-+ * This function is a dynamic '__init' function actually,
-+ * so the tiny check for si_rwsem is unnecessary.
-+ */
-+ /* AuRwMustWriteLock(&sbinfo->si_rwsem); */
++ for (ull = 0; ull < max; ull++) {
++ file = array[ull];
++ if (!file)
++ continue;
+
-+ 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;
++ /* 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) {
++ h_inode = file_inode(hf);
++ if (hf->f_mode & FMODE_READ)
++ i_readcount_inc(h_inode);
++ put_write_access(h_inode);
++ mnt_put_write_access(hf->f_path.mnt);
++ }
++ }
+
++out_array:
++ au_farray_free(array, max);
++out:
++ AuTraceErr(err);
+ 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)
++int au_br_mod(struct super_block *sb, struct au_opt_mod *mod, int remount,
++ int *do_refresh)
+{
-+ /*
-+ * This function is a dynamic '__fin' function actually,
-+ * so the tiny check for si_rwsem is unnecessary.
-+ */
-+ /* AuRwMustWriteLock(&sbinfo->si_rwsem); */
++ int err, rerr;
++ aufs_bindex_t bindex;
++ struct dentry *root;
++ struct au_branch *br;
++ struct au_br_fhsm *bf;
+
-+ debugfs_remove_recursive(sbinfo->si_dbgaufs);
-+ sbinfo->si_dbgaufs = NULL;
-+}
++ 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);
+
-+int dbgaufs_si_init(struct au_sbinfo *sbinfo)
-+{
-+ int err;
-+ char name[SysaufsSiNameLen];
++ err = test_br(d_inode(mod->h_root), mod->perm, mod->path);
++ if (unlikely(err))
++ goto out;
+
-+ /*
-+ * This function is a dynamic '__init' function actually,
-+ * so the tiny check for si_rwsem is unnecessary.
-+ */
-+ /* AuRwMustWriteLock(&sbinfo->si_rwsem); */
++ br = au_sbr(sb, bindex);
++ AuDebugOn(mod->h_root != au_br_dentry(br));
++ if (br->br_perm == mod->perm)
++ return 0; /* success */
+
-+ err = -ENOENT;
-+ if (!dbgaufs) {
-+ AuErr1("/debug/aufs is uninitialized\n");
-+ goto out;
++ /* 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;
+ }
+
-+ err = -EIO;
-+ sysaufs_name(sbinfo, name);
-+ sbinfo->si_dbgaufs = debugfs_create_dir(name, dbgaufs);
-+ if (unlikely(!sbinfo->si_dbgaufs))
-+ goto out;
++ 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;
+
-+ /* 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;
++ 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);
+
-+ /* 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;
++ 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;
+
-+ err = dbgaufs_xigen_init(sbinfo);
-+ if (!err)
-+ goto out; /* success */
++ 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;
+
-+out_dir:
-+ dbgaufs_si_fin(sbinfo);
++ *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:
-+ if (unlikely(err))
-+ pr_err("debugfs/aufs failed\n");
++ AuTraceErr(err);
+ return err;
+}
+
+/* ---------------------------------------------------------------------- */
+
-+void dbgaufs_fin(void)
-+{
-+ debugfs_remove(dbgaufs);
-+}
-+
-+int __init dbgaufs_init(void)
++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;
++ }
+
-+ 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 00000000000000..30f1694224e004
---- /dev/null
-+++ b/fs/aufs/dbgaufs.h
-@@ -0,0 +1,53 @@
+diff -urN /usr/share/empty/fs/aufs/branch.h linux/fs/aufs/branch.h
+--- /usr/share/empty/fs/aufs/branch.h 1970-01-01 01:00:00.000000000 +0100
++++ linux/fs/aufs/branch.h 2023-10-31 09:31:04.196547417 +0100
+@@ -0,0 +1,375 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2005-2022 Junjiro R. Okajima
+ */
+
+/*
-+ * debugfs interface
++ * branch filesystems and xino for them
+ */
+
-+#ifndef __DBGAUFS_H__
-+#define __DBGAUFS_H__
++#ifndef __AUFS_BRANCH_H__
++#define __AUFS_BRANCH_H__
+
+#ifdef __KERNEL__
+
-+struct super_block;
-+struct au_sbinfo;
-+struct au_branch;
++#include <linux/mount.h>
++#include "dirren.h"
++#include "dynop.h"
++#include "lcnt.h"
++#include "rwsem.h"
++#include "super.h"
+
-+#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 */
++/* ---------------------------------------------------------------------- */
++
++/* 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;
+
-+#endif /* __KERNEL__ */
-+#endif /* __DBGAUFS_H__ */
-diff --git a/fs/aufs/dcsub.c b/fs/aufs/dcsub.c
-new file mode 100644
-index 00000000000000..fa2a9ad2b49b61
---- /dev/null
-+++ b/fs/aufs/dcsub.c
-@@ -0,0 +1,225 @@
-+// SPDX-License-Identifier: GPL-2.0
-+/*
-+ * Copyright (C) 2005-2022 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/>.
-+ */
++#ifdef CONFIG_AUFS_HFSNOTIFY
++ struct au_br_hfsnotify *br_hfsn;
++#endif
+
-+/*
-+ * sub-routines for dentry cache
-+ */
++#ifdef CONFIG_SYSFS
++ /* entries under sysfs per mount-point */
++ struct au_brsysfs br_sysfs[AuBrSysfs_Last];
++#endif
+
-+#include "aufs.h"
++#ifdef CONFIG_DEBUG_FS
++ struct dentry *br_dbgaufs; /* xino */
++#endif
+
-+static void au_dpage_free(struct au_dpage *dpage)
++ struct au_dr_br br_dirren;
++};
++
++/* ---------------------------------------------------------------------- */
++
++static inline struct vfsmount *au_br_mnt(struct au_branch *br)
+{
-+ int i;
-+ struct dentry **p;
++ return br->br_path.mnt;
++}
+
-+ p = dpage->dentries;
-+ for (i = 0; i < dpage->ndentry; i++)
-+ dput(*p++);
-+ free_page((unsigned long)dpage->dentries);
++static inline struct dentry *au_br_dentry(struct au_branch *br)
++{
++ return br->br_path.dentry;
+}
+
-+int au_dpages_init(struct au_dcsub_pages *dpages, gfp_t gfp)
++static inline struct mnt_idmap *au_br_idmap(struct au_branch *br)
+{
-+ int err;
-+ void *p;
++ return mnt_idmap(br->br_path.mnt);
++}
+
-+ err = -ENOMEM;
-+ dpages->dpages = kmalloc(sizeof(*dpages->dpages), gfp);
-+ if (unlikely(!dpages->dpages))
-+ goto out;
++static inline struct super_block *au_br_sb(struct au_branch *br)
++{
++ return au_br_mnt(br)->mnt_sb;
++}
+
-+ p = (void *)__get_free_page(gfp);
-+ if (unlikely(!p))
-+ goto out_dpages;
++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;
++}
+
-+ dpages->dpages[0].ndentry = 0;
-+ dpages->dpages[0].dentries = p;
-+ dpages->ndpage = 1;
-+ return 0; /* success */
++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;
+
-+out_dpages:
-+ au_kfree_try_rcu(dpages->dpages);
-+out:
+ return err;
+}
+
-+void au_dpages_free(struct au_dcsub_pages *dpages)
++static inline void au_xino_get(struct au_branch *br)
+{
-+ int i;
-+ struct au_dpage *p;
++ struct au_xino *xi;
+
-+ p = dpages->dpages;
-+ for (i = 0; i < dpages->ndpage; i++)
-+ au_dpage_free(p++);
-+ au_kfree_try_rcu(dpages->dpages);
++ xi = br->br_xino;
++ if (xi)
++ kref_get(&xi->xi_kref);
+}
+
-+static int au_dpages_append(struct au_dcsub_pages *dpages,
-+ struct dentry *dentry, gfp_t gfp)
++static inline int au_xino_count(struct au_branch *br)
+{
-+ int err, sz;
-+ struct au_dpage *dpage;
-+ void *p;
++ int v;
++ struct au_xino *xi;
+
-+ 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;
++ v = 0;
++ xi = br->br_xino;
++ if (xi)
++ v = kref_read(&xi->xi_kref);
+
-+ dpages->dpages = p;
-+ dpage = dpages->dpages + dpages->ndpage;
-+ p = (void *)__get_free_page(gfp);
-+ if (unlikely(!p))
-+ goto out;
++ return v;
++}
+
-+ dpage->ndentry = 0;
-+ dpage->dentries = p;
-+ dpages->ndpage++;
-+ }
++/* ---------------------------------------------------------------------- */
+
-+ AuDebugOn(au_dcount(dentry) <= 0);
-+ dpage->dentries[dpage->ndentry++] = dget_dlock(dentry);
-+ return 0; /* success */
++/* 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);
+
-+out:
-+ return err;
-+}
++/* xino.c */
++static const loff_t au_loff_max = LLONG_MAX;
+
-+/* 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,
++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);
+
-+extern void d_walk(struct dentry *parent, void *data,
-+ enum d_walk_ret (*enter)(void *, struct dentry *));
++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(struct file *file, void *buf, size_t size, loff_t *pos);
++ssize_t xino_fwrite(struct file *file, void *buf, size_t size, loff_t *pos);
+
-+struct ac_dpages_arg {
-+ int err;
-+ struct au_dcsub_pages *dpages;
-+ struct super_block *sb;
-+ au_dpages_test test;
-+ void *arg;
-+};
++int au_xib_trunc(struct super_block *sb);
++int au_xino_trunc(struct super_block *sb, aufs_bindex_t bindex, int idx_begin);
+
-+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;
++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);
+
-+ 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;
-+ }
++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);
+
-+ return ret;
-+}
++ino_t au_xino_new_ino(struct super_block *sb);
++void au_xino_delete_inode(struct inode *inode, const int unlinked);
+
-+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
-+ };
++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);
+
-+ d_walk(root, &args, au_call_dpages_append);
++int au_xino_path(struct seq_file *seq, struct file *file);
+
-+ 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)
++/* @idx is signed to accept -1 meaning the first file */
++static inline struct file *au_xino_file(struct au_xino *xi, int idx)
+{
-+ int err;
++ struct file *file;
+
-+ 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))
++ file = NULL;
++ if (!xi)
+ 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;
-+ }
++ if (idx >= 0) {
++ if (idx < xi->xi_nfile)
++ file = xi->xi_file[idx];
++ } else
++ file = au_xino_file1(xi);
+
+out:
-+ write_sequnlock(&rename_lock);
-+ return err;
++ return file;
+}
+
-+static inline int au_dcsub_dpages_aufs(struct dentry *dentry, void *arg)
++/* ---------------------------------------------------------------------- */
++
++/* Superblock to branch */
++static inline
++aufs_bindex_t au_sbr_id(struct super_block *sb, aufs_bindex_t bindex)
+{
-+ return au_di(dentry) && dentry->d_sb == arg;
++ return au_sbr(sb, bindex)->br_id;
+}
+
-+int au_dcsub_pages_rev_aufs(struct au_dcsub_pages *dpages,
-+ struct dentry *dentry, int do_include)
++static inline
++struct vfsmount *au_sbr_mnt(struct super_block *sb, aufs_bindex_t bindex)
+{
-+ return au_dcsub_pages_rev(dpages, dentry, do_include,
-+ au_dcsub_dpages_aufs, dentry->d_sb);
++ return au_br_mnt(au_sbr(sb, bindex));
+}
+
-+int au_test_subdir(struct dentry *d1, struct dentry *d2)
++static inline
++struct mnt_idmap *au_sbr_idmap(struct super_block *sb, aufs_bindex_t bindex)
+{
-+ struct path path[2] = {
-+ {
-+ .dentry = d1
-+ },
-+ {
-+ .dentry = d2
-+ }
-+ };
-+
-+ return path_is_under(path + 0, path + 1);
++ return au_br_idmap(au_sbr(sb, bindex));
+}
-diff --git a/fs/aufs/dcsub.h b/fs/aufs/dcsub.h
-new file mode 100644
-index 00000000000000..7e4f4eba0343b2
---- /dev/null
-+++ b/fs/aufs/dcsub.h
-@@ -0,0 +1,137 @@
-+/* SPDX-License-Identifier: GPL-2.0 */
-+/*
-+ * Copyright (C) 2005-2022 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/>.
-+ */
-+
-+/*
-+ * sub-routines for dentry cache
-+ */
+
-+#ifndef __AUFS_DCSUB_H__
-+#define __AUFS_DCSUB_H__
++static inline
++struct super_block *au_sbr_sb(struct super_block *sb, aufs_bindex_t bindex)
++{
++ return au_br_sb(au_sbr(sb, bindex));
++}
+
-+#ifdef __KERNEL__
++static inline int au_sbr_perm(struct super_block *sb, aufs_bindex_t bindex)
++{
++ return au_sbr(sb, bindex)->br_perm;
++}
+
-+#include <linux/dcache.h>
-+#include <linux/fs.h>
++static inline int au_sbr_whable(struct super_block *sb, aufs_bindex_t bindex)
++{
++ return au_br_whable(au_sbr_perm(sb, bindex));
++}
+
-+struct au_dpage {
-+ int ndentry;
-+ struct dentry **dentries;
-+};
++/* ---------------------------------------------------------------------- */
+
-+struct au_dcsub_pages {
-+ int ndpage;
-+ struct au_dpage *dpages;
-+};
++#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)
+
-+/* 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);
++#define WbrWhMustNoWaiters(wbr) AuRwMustNoWaiters(&(wbr)->wbr_wh_rwsem)
++#define WbrWhMustAnyLock(wbr) AuRwMustAnyLock(&(wbr)->wbr_wh_rwsem)
++#define WbrWhMustWriteLock(wbr) AuRwMustWriteLock(&(wbr)->wbr_wh_rwsem)
+
+/* ---------------------------------------------------------------------- */
+
-+/*
-+ * 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)
++#ifdef CONFIG_AUFS_FHSM
++static inline void au_br_fhsm_init(struct au_br_fhsm *brfhsm)
+{
-+ 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;
++ mutex_init(&brfhsm->bf_lock);
++ brfhsm->bf_jiffy = 0;
++ brfhsm->bf_readable = 0;
+}
+
-+static inline int au_d_linkable(struct dentry *d)
++static inline void au_br_fhsm_fin(struct au_br_fhsm *brfhsm)
+{
-+ 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;
++ 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
+
-+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;
-+}
++#endif /* __KERNEL__ */
++#endif /* __AUFS_BRANCH_H__ */
+diff -urN /usr/share/empty/fs/aufs/conf.mk linux/fs/aufs/conf.mk
+--- /usr/share/empty/fs/aufs/conf.mk 1970-01-01 01:00:00.000000000 +0100
++++ linux/fs/aufs/conf.mk 2022-11-05 23:02:18.959222617 +0100
+@@ -0,0 +1,40 @@
++# SPDX-License-Identifier: GPL-2.0
+
-+static inline int au_alive_dir(struct dentry *d)
-+{
-+ int err;
++AuConfStr = CONFIG_AUFS_FS=${CONFIG_AUFS_FS}
+
-+ err = au_d_alive(d);
-+ if (unlikely(err || IS_DEADDIR(d_inode(d))))
-+ err = -ENOENT;
-+ return err;
-+}
++define AuConf
++ifdef ${1}
++AuConfStr += ${1}=${${1}}
++endif
++endef
+
-+static inline int au_qstreq(struct qstr *a, struct qstr *b)
-+{
-+ return a->len == b->len
-+ && !memcmp(a->name, b->name, a->len);
-+}
++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})))
+
-+/*
-+ * 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);
-+}
++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}
+
-+#endif /* __KERNEL__ */
-+#endif /* __AUFS_DCSUB_H__ */
-diff --git a/fs/aufs/debug.c b/fs/aufs/debug.c
-new file mode 100644
-index 00000000000000..e503bb357984ec
---- /dev/null
-+++ b/fs/aufs/debug.c
-@@ -0,0 +1,448 @@
++-include ${srctree}/${src}/conf_priv.mk
+diff -urN /usr/share/empty/fs/aufs/cpup.c linux/fs/aufs/cpup.c
+--- /usr/share/empty/fs/aufs/cpup.c 1970-01-01 01:00:00.000000000 +0100
++++ linux/fs/aufs/cpup.c 2024-03-10 23:40:47.083143450 +0100
+@@ -0,0 +1,1459 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2005-2022 Junjiro R. Okajima
+ */
+
+/*
-+ * debug print functions
++ * copy-up functions, see wbr_policy.c for copy-down
+ */
+
-+#include <linux/iversion.h>
++#include <linux/fs_stack.h>
++#include <linux/mm.h>
++#include <linux/task_work.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)
++void au_cpup_attr_flags(struct inode *dst, unsigned int iflags)
+{
-+ int err, n;
++ const unsigned int mask = S_DEAD | S_SWAPFILE | S_PRIVATE
++ | S_NOATIME | S_NOCMTIME | S_AUTOMOUNT;
+
-+ err = kstrtoint(val, 0, &n);
-+ if (!err) {
-+ if (n > 0)
-+ au_debug_on();
-+ else
-+ au_debug_off();
-+ }
-+ return err;
++ 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;
+}
+
-+/* Returns length written or -errno. Buffer is 4k (ie. be short!) */
-+static int param_atomic_t_get(char *buffer, const struct kernel_param *kp)
++void au_cpup_attr_timesizes(struct inode *inode)
+{
-+ atomic_t *a;
++ struct inode *h_inode;
+
-+ a = kp->arg;
-+ return sprintf(buffer, "%d", atomic_read(a));
++ h_inode = au_h_iptr(inode, au_ibtop(inode));
++ fsstack_copy_attr_times(inode, h_inode);
++ fsstack_copy_inode_size(inode, h_inode);
+}
+
-+static const struct kernel_param_ops param_ops_atomic_t = {
-+ .set = param_atomic_t_set,
-+ .get = param_atomic_t_get
-+ /* void (*free)(void *arg) */
-+};
++void au_cpup_attr_nlink(struct inode *inode, int force)
++{
++ struct inode *h_inode;
++ struct super_block *sb;
++ aufs_bindex_t bindex, bbot;
+
-+atomic_t aufs_debug = ATOMIC_INIT(0);
-+MODULE_PARM_DESC(debug, "debug print");
-+module_param_named(debug, aufs_debug, atomic_t, 0664);
++ 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;
+
-+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)
++ /*
++ * 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_dpri_whlist(struct au_nhash *whlist)
++void au_cpup_attr_changeable(struct inode *inode)
+{
-+ unsigned long ul, n;
-+ struct hlist_head *head;
-+ struct au_vdir_wh *pos;
++ struct inode *h_inode;
+
-+ 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++;
-+ }
++ 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_dpri_vdir(struct au_vdir *vdir)
++void au_cpup_igen(struct inode *inode, struct inode *h_inode)
+{
-+ unsigned long ul;
-+ union au_vdir_deblk_p p;
-+ unsigned char *o;
++ struct au_iinfo *iinfo = au_ii(inode);
+
-+ if (!vdir || IS_ERR(vdir)) {
-+ dpri("err %ld\n", PTR_ERR(vdir));
-+ return;
-+ }
++ IiMustWriteLock(inode);
+
-+ 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);
-+ }
++ iinfo->ii_higen = h_inode->i_generation;
++ iinfo->ii_hsb1 = h_inode->i_sb;
+}
+
-+static int do_pri_inode(aufs_bindex_t bindex, struct inode *inode, int hn,
-+ struct dentry *wh)
++void au_cpup_attr_all(struct inode *inode, int force)
+{
-+ char *n = NULL;
-+ int l = 0;
-+ struct timespec64 ctime;
++ struct inode *h_inode;
+
-+ if (!inode || IS_ERR(inode)) {
-+ dpri("i%d: err %ld\n", bindex, PTR_ERR(inode));
-+ return -1;
-+ }
++ 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);
++}
+
-+ /* 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;
-+ }
++/* ---------------------------------------------------------------------- */
+
-+ ctime = inode_get_ctime(inode);
-+ dpri("i%d: %p, i%lu, %s, cnt %d, nl %u, 0%o, sz %llu, blk %llu,"
-+ " acl %p, def_acl %p,"
-+ " 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,
-+ inode->i_acl, inode->i_default_acl,
-+ hn, (long long)timespec64_to_ns(&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;
-+}
++/* Note: dt_dentry and dt_h_dentry are not dget/dput-ed */
+
-+void au_dpri_inode(struct inode *inode)
++/* 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 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;
++ struct inode *h_inode;
+
-+ 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);
-+ }
++ dt->dt_dentry = dentry;
++ dt->dt_h_path = *h_path;
++ h_inode = d_inode(h_path->dentry);
++ dt->dt_atime = inode_get_atime(h_inode);
++ dt->dt_mtime = inode_get_mtime(h_inode);
++ /* smp_mb(); */
+}
+
-+void au_dpri_dalias(struct inode *inode)
++void au_dtime_revert(struct au_dtime *dt)
+{
-+ struct dentry *d;
++ struct iattr attr;
++ int err;
+
-+ 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);
++ 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);
+}
+
-+static int do_pri_dentry(aufs_bindex_t bindex, struct dentry *dentry)
++/* ---------------------------------------------------------------------- */
++
++/* 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 path *h_src,
++ struct au_cpup_reg_attr *h_src_attr)
+{
-+ struct dentry *wh = NULL;
-+ int hn;
-+ struct inode *inode;
-+ struct au_iinfo *iinfo;
-+ struct au_hinode *hi;
++ 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;
+
-+ if (!dentry || IS_ERR(dentry)) {
-+ dpri("d%d: err %ld\n", bindex, PTR_ERR(dentry));
-+ return -1;
++ br = au_sbr(dst->d_sb, bindex);
++ h_path.mnt = au_br_mnt(br);
++ h_path.dentry = au_h_dptr(dst, bindex);
++ h_idst = d_inode(h_path.dentry);
++ h_isrc = d_inode(h_src->dentry);
++ 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 = inode_get_atime(h_isrc);
++ ia.ia_mtime = inode_get_mtime(h_isrc);
++ 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);
+ }
-+ /* 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;
++ /* 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);
+ }
-+ do_pri_inode(bindex, inode, hn, wh);
-+ return 0;
++
++ 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, h_src, icex, verbose);
++ }
++
++ return err;
+}
+
-+void au_dpri_dentry(struct dentry *dentry)
++/* ---------------------------------------------------------------------- */
++
++static int au_do_copy_file(struct file *dst, struct file *src, loff_t len,
++ char *buf, unsigned long blksize)
+{
-+ struct au_dinfo *dinfo;
-+ aufs_bindex_t bindex;
+ int err;
++ size_t sz, rbytes, wbytes;
++ unsigned char all_zero;
++ char *p, *zp;
++ struct inode *h_inode;
++ /* reduce stack usage */
++ struct iattr *ia;
+
-+ err = do_pri_dentry(-1, dentry);
-+ if (err || !au_test_aufs(dentry->d_sb))
-+ return;
++ zp = page_address(ZERO_PAGE(0));
++ if (unlikely(!zp))
++ return -ENOMEM; /* possible? */
+
-+ 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);
-+}
++ err = 0;
++ all_zero = 0;
++ while (len) {
++ AuDbg("len %lld\n", len);
++ sz = blksize;
++ if (len < blksize)
++ sz = len;
+
-+static int do_pri_file(aufs_bindex_t bindex, struct file *file)
-+{
-+ char a[32];
++ 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;
+
-+ if (!file || IS_ERR(file)) {
-+ dpri("f%d: err %ld\n", bindex, PTR_ERR(file));
-+ return -1;
++ 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;
+ }
-+ 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;
++
++ /* 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;
+}
+
-+void au_dpri_file(struct file *file)
++int au_copy_file(struct file *dst, struct file *src, loff_t len)
+{
-+ struct au_finfo *finfo;
-+ struct au_fidir *fidir;
-+ struct au_hfile *hfile;
-+ aufs_bindex_t bindex;
+ int err;
++ unsigned long blksize;
++ unsigned char do_kfree;
++ char *buf;
++ struct super_block *h_sb;
+
-+ 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);
++ 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
-+ 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);
-+ }
++ 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 do_pri_br(aufs_bindex_t bindex, struct au_branch *br)
++static int au_do_copy(struct file *dst, struct file *src, loff_t len)
+{
-+ struct vfsmount *mnt;
-+ struct super_block *sb;
++ int err;
++ struct super_block *h_src_sb;
++ struct inode *h_src_inode;
+
-+ 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;
++ h_src_inode = file_inode(src);
++ h_src_sb = h_src_inode->i_sb;
+
-+ 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;
++ /* 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);
++ }
+
-+out:
-+ dpri("s%d: err %ld\n", bindex, PTR_ERR(br));
-+ return -1;
++ return err;
+}
+
-+void au_dpri_sb(struct super_block *sb)
++static int au_clone_or_copy(struct file *dst, struct file *src, loff_t len)
+{
-+ struct au_sbinfo *sbinfo;
-+ aufs_bindex_t bindex;
+ int err;
-+ /* to reduce stack size */
-+ struct {
-+ struct vfsmount mnt;
-+ struct au_branch fake;
-+ } *a;
++ loff_t lo;
++ struct super_block *h_src_sb;
++ struct inode *h_src_inode;
+
-+ /* this function can be called from magic sysrq */
-+ a = kzalloc(sizeof(*a), GFP_ATOMIC);
-+ if (unlikely(!a)) {
-+ dpri("no memory\n");
-+ return;
++ 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;
+ }
+
-+ 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;
++ 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;
++ }
+
-+ 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]);
-+}
++ /* the backend fs on NFS may not support cloning */
++ err = au_do_copy(dst, src, len);
+
-+/* ---------------------------------------------------------------------- */
++out:
++ AuTraceErr(err);
++ return err;
++}
+
-+void __au_dbg_verify_dinode(struct dentry *dentry, const char *func, int line)
++/*
++ * 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)
+{
-+ 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;
++ 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;
+
-+ 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();
-+ if (au_test_fuse(h_inode->i_sb))
-+ WARN_ON_ONCE(1);
++ /* 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
-+ BUG();
++ goto out_src;
+ }
+ }
-+}
+
-+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;
++ /* 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);
+
-+ 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));
++ /* 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();
+ }
-+ au_dpages_free(&dpages);
++ 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;
+}
+
-+void au_dbg_verify_kthread(void)
++static int au_do_cpup_regular(struct au_cp_generic *cpg,
++ struct au_cpup_reg_attr *h_src_attr)
+{
-+ 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 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;
++}
+
-+int __init au_debug_init(void)
++static int au_do_cpup_symlink(struct path *h_path, struct dentry *h_src,
++ struct inode *h_dir)
+{
-+ aufs_bindex_t bindex;
-+ struct au_vdir_destr destr;
-+
-+ bindex = -1;
-+ AuDebugOn(bindex >= 0);
++ int err;
++ DEFINE_DELAYED_CALL(done);
++ const char *sym;
+
-+ destr.len = -1;
-+ AuDebugOn(destr.len < NAME_MAX);
++ sym = vfs_get_link(h_src, &done);
++ err = PTR_ERR(sym);
++ if (IS_ERR(sym))
++ goto out;
+
-+#ifdef CONFIG_4KSTACKS
-+ pr_warn("CONFIG_4KSTACKS is defined.\n");
-+#endif
++ err = vfsub_symlink(h_dir, h_path, sym);
+
-+ return 0;
++out:
++ do_delayed_call(&done);
++ return err;
+}
-diff --git a/fs/aufs/debug.h b/fs/aufs/debug.h
-new file mode 100644
-index 00000000000000..f757588e5000ac
---- /dev/null
-+++ b/fs/aufs/debug.h
-@@ -0,0 +1,226 @@
-+/* SPDX-License-Identifier: GPL-2.0 */
-+/*
-+ * Copyright (C) 2005-2022 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/>.
-+ */
+
+/*
-+ * debug print functions
++ * 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 path *h_path, umode_t mode)
++{
++ int err;
++ struct dentry *h_dentry;
++ /* struct inode *h_inode; */
++ struct mnt_idmap *h_idmap;
+
-+#ifndef __AUFS_DEBUG_H__
-+#define __AUFS_DEBUG_H__
++ h_idmap = mnt_idmap(h_path->mnt);
++ h_dentry = h_path->dentry;
++ /* h_inode = d_inode(h_dentry); */
++ /* forget_all_cached_acls(h_inode)); */
++ err = vfsub_remove_acl(h_idmap, h_dentry, XATTR_NAME_POSIX_ACL_ACCESS);
++ AuTraceErr(err);
++ if (err == -EOPNOTSUPP)
++ err = 0;
++ if (!err)
++ err = vfsub_acl_chmod(h_idmap, h_dentry, mode);
+
-+#ifdef __KERNEL__
++ AuTraceErr(err);
++ return err;
++}
+
-+#include <linux/atomic.h>
-+#include <linux/module.h>
-+#include <linux/kallsyms.h>
-+#include <linux/sysrq.h>
++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;
++ struct mnt_idmap *h_idmap;
+
-+#ifdef CONFIG_AUFS_DEBUG
-+#define AuDebugOn(a) BUG_ON(a)
++ h_idmap = mnt_idmap(h_path->mnt);
++ err = vfsub_remove_acl(h_idmap, h_path->dentry,
++ XATTR_NAME_POSIX_ACL_DEFAULT);
++ AuTraceErr(err);
++ if (err == -EOPNOTSUPP)
++ err = 0;
++ if (unlikely(err))
++ goto out;
+
-+/* 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);
++ /*
++ * 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 inline int au_debug_test(void)
++static noinline_for_stack
++int cpup_entry(struct au_cp_generic *cpg, struct dentry *dst_parent,
++ struct au_cpup_reg_attr *h_src_attr)
+{
-+ 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 */
++ 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;
+
-+#define param_check_atomic_t(name, p) __param_check(name, p, atomic_t)
++ /* 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);
+
-+/* debug print */
++ 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;
+
-+#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)
++ 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_path, mode);
+
-+#define AuErr1(fmt, ...) do { \
-+ static unsigned char _c; \
-+ if (!_c++) \
-+ pr_err(fmt, ##__VA_ARGS__); \
-+} while (0)
++ 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 */
+
-+#define AuIOErr1(fmt, ...) do { \
-+ static unsigned char _c; \
-+ if (!_c++) \
-+ AuIOErr(fmt, ##__VA_ARGS__); \
-+} while (0)
++ 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);
++ }
+
-+#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)
++ if (do_dt)
++ au_dtime_revert(&dt);
++ return err;
++}
+
-+#define AuTraceErr(e) do { \
-+ if (unlikely((e) < 0)) \
-+ AuDbg("err %d\n", (int)(e)); \
-+} while (0)
++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 path h_ppath;
++ struct inode *h_dir;
++ aufs_bindex_t bdst;
+
-+#define AuTraceErrPtr(p) do { \
-+ if (IS_ERR(p)) \
-+ AuDbg("err %ld\n", PTR_ERR(p)); \
-+} while (0)
++ dentry = cpg->dentry;
++ bdst = cpg->bdst;
++ h_ppath.mnt = au_sbr_mnt(dentry->d_sb, 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_ppath.dentry = au_h_dptr(parent, bdst);
++ dput(parent);
++ h_path->dentry = vfsub_lkup_one(&dentry->d_name, &h_ppath);
++ if (IS_ERR(h_path->dentry))
++ err = PTR_ERR(h_path->dentry);
++ }
++ if (unlikely(err))
++ goto out;
+
-+/* dirty macros for debug print, use with "%.*s" and caution */
-+#define AuLNPair(qstr) (qstr)->len, (qstr)->name
++ 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;
++}
+
-+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);
++/*
++ * 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;
++ struct path h_src_path;
++ /* to reduce stack size */
++ struct {
++ struct au_dtime dt;
++ struct path h_path;
++ struct au_cpup_reg_attr h_src_attr;
++ } *a;
+
-+#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);
++ err = -ENOMEM;
++ a = kmalloc(sizeof(*a), GFP_NOFS);
++ if (unlikely(!a))
++ goto out;
++ a->h_src_attr.valid = 0;
+
-+int __init au_debug_init(void);
++ 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);
+
-+#define AuDbgWhlist(w) do { \
-+ mutex_lock(&au_dbg_mtx); \
-+ AuDbg(#w "\n"); \
-+ au_dpri_whlist(w); \
-+ mutex_unlock(&au_dbg_mtx); \
-+} while (0)
++ h_src = au_h_dptr(cpg->dentry, cpg->bsrc);
++ inode = d_inode(cpg->dentry);
+
-+#define AuDbgVdir(v) do { \
-+ mutex_lock(&au_dbg_mtx); \
-+ AuDbg(#v "\n"); \
-+ au_dpri_vdir(v); \
-+ mutex_unlock(&au_dbg_mtx); \
-+} while (0)
++ if (!dst_parent)
++ dst_parent = dget_parent(cpg->dentry);
++ else
++ dget(dst_parent);
+
-+#define AuDbgInode(i) do { \
-+ mutex_lock(&au_dbg_mtx); \
-+ AuDbg(#i "\n"); \
-+ au_dpri_inode(i); \
-+ mutex_unlock(&au_dbg_mtx); \
-+} while (0)
++ 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;
++ }
+
-+#define AuDbgDAlias(i) do { \
-+ mutex_lock(&au_dbg_mtx); \
-+ AuDbg(#i "\n"); \
-+ au_dpri_dalias(i); \
-+ mutex_unlock(&au_dbg_mtx); \
-+} while (0)
++ if (dst_inode->i_nlink) {
++ const int do_dt = au_ftest_cpup(cpg->flags, DTIME);
+
-+#define AuDbgDentry(d) do { \
-+ mutex_lock(&au_dbg_mtx); \
-+ AuDbg(#d "\n"); \
-+ au_dpri_dentry(d); \
-+ mutex_unlock(&au_dbg_mtx); \
-+} while (0)
++ 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;
++ }
+
-+#define AuDbgFile(f) do { \
-+ mutex_lock(&au_dbg_mtx); \
-+ AuDbg(#f "\n"); \
-+ au_dpri_file(f); \
-+ mutex_unlock(&au_dbg_mtx); \
-+} while (0)
++ if (do_dt) {
++ a->h_path.dentry = h_parent;
++ au_dtime_store(&a->dt, dst_parent, &a->h_path);
++ }
+
-+#define AuDbgSb(sb) do { \
-+ mutex_lock(&au_dbg_mtx); \
-+ AuDbg(#sb "\n"); \
-+ au_dpri_sb(sb); \
-+ mutex_unlock(&au_dbg_mtx); \
-+} while (0)
++ 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);
++ }
+
-+#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)
++ 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); */
+
-+#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 */
++ h_src_path.dentry = h_src;
++ h_src_path.mnt = au_sbr_mnt(sb, cpg->bsrc);
++ err = cpup_iattr(cpg->dentry, cpg->bdst, &h_src_path, &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));
+
-+#ifdef CONFIG_AUFS_MAGIC_SYSRQ
-+int __init au_sysrq_init(void);
-+void au_sysrq_fin(void);
++ /* todo: necessary? */
++ /* err = au_pin_hdir_relock(cpg->pin); */
++ inode_unlock(dst_inode);
++ if (unlikely(err))
++ goto out_rev;
+
-+#ifdef CONFIG_HW_CONSOLE
-+#define au_dbg_blocked() do { \
-+ WARN_ON(1); \
-+ handle_sysrq('w'); \
-+} while (0)
-+#else
-+AuStubVoid(au_dbg_blocked, void)
-+#endif
++ 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);
+
-+#else
-+AuStubInt0(__init au_sysrq_init, void)
-+AuStubVoid(au_sysrq_fin, void)
-+AuStubVoid(au_dbg_blocked, void)
-+#endif /* CONFIG_AUFS_MAGIC_SYSRQ */
++ 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 */
+
-+#endif /* __KERNEL__ */
-+#endif /* __AUFS_DEBUG_H__ */
-diff --git a/fs/aufs/dentry.c b/fs/aufs/dentry.c
-new file mode 100644
-index 00000000000000..ed7ce8f6d1a1bf
---- /dev/null
-+++ b/fs/aufs/dentry.c
-@@ -0,0 +1,1168 @@
-+// SPDX-License-Identifier: GPL-2.0
-+/*
-+ * Copyright (C) 2005-2022 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/>.
-+ */
++ /* 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;
++}
+
-+/*
-+ * lookup and dentry operations
-+ */
++#if 0 /* reserved */
++struct au_cpup_single_args {
++ int *errp;
++ struct au_cp_generic *cpg;
++ struct dentry *dst_parent;
++};
+
-+#include <linux/iversion.h>
-+#include "aufs.h"
++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
+
+/*
-+ * returns positive/negative dentry, NULL or an error.
-+ * NULL means whiteout-ed or not-found.
++ * prevent SIGXFSZ in copy-up.
++ * testing CAP_MKNOD is for generic fs,
++ * but CAP_FSETID is for xfs only, currently.
+ */
-+static struct dentry*
-+au_do_lookup(struct dentry *h_parent, struct dentry *dentry,
-+ aufs_bindex_t bindex, struct au_do_lookup_args *args)
++static int au_cpup_sio_test(struct au_pin *pin, umode_t mode)
+{
-+ struct dentry *h_dentry;
-+ struct inode *h_inode;
-+ struct au_branch *br;
-+ struct mnt_idmap *h_idmap;
-+ struct path h_path;
-+ 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);
-+ h_path.dentry = h_parent;
-+ h_path.mnt = au_br_mnt(br);
-+ h_idmap = au_br_idmap(br);
-+ wh_able = !!au_br_whable(br->br_perm);
-+ if (wh_able)
-+ wh_found = au_wh_test(h_idmap, &h_path, &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_path);
-+ else
-+ h_dentry = au_sio_lkup_one(h_idmap, args->name, &h_path);
-+ if (IS_ERR(h_dentry)) {
-+ if (PTR_ERR(h_dentry) == -ENAMETOOLONG
-+ && !allow_neg)
-+ h_dentry = NULL;
-+ goto out;
-+ }
++ int do_sio;
++ struct super_block *sb;
++ struct inode *h_dir;
+
-+ 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;
++ 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;
++ }
+ }
+
-+ 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);
++ return do_sio;
++}
+
-+ if (!d_is_dir(h_dentry)
-+ || !wh_able
-+ || (d_really_is_positive(dentry) && !d_is_dir(dentry)))
-+ goto out; /* success */
++#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_path.dentry = h_dentry;
-+ inode_lock_shared_nested(h_inode, AuLsc_I_CHILD);
-+ opq = au_diropq_test(h_idmap, &h_path);
-+ 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);
++ 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;
+ }
-+ 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;
++ return err;
+}
++#endif
+
+/*
-+ * returns the number of lower positive dentries,
-+ * otherwise an error.
-+ * can be called at unlinking with @type is zero.
++ * copyup the @dentry from the first active lower branch to @bdst,
++ * using au_cpup_single().
+ */
-+int au_lkup_dentry(struct dentry *dentry, aufs_bindex_t btop,
-+ unsigned int flags)
++static int au_cpup_simple(struct au_cp_generic *cpg)
+{
-+ 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;
++ int err;
++ unsigned int flags_orig;
++ struct dentry *dentry;
+
-+ sb = dentry->d_sb;
-+ err = au_test_shwh(sb, args.name);
-+ if (unlikely(err))
-+ goto out;
++ AuDebugOn(cpg->bsrc < 0);
+
-+ err = au_wh_name_alloc(&args.whname, args.name);
-+ if (unlikely(err))
-+ goto out;
++ dentry = cpg->dentry;
++ DiMustWriteLock(dentry);
+
-+ 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);
++ 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 */
+
-+ 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;
++ /* revert */
++ au_set_h_dptr(dentry, cpg->bdst, NULL);
++ au_set_dbtop(dentry, cpg->bsrc);
++ }
+
-+ 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;
++ return err;
++}
+
-+ if (dirren) {
-+ /* if the inum matches, then use the prepared name */
-+ err = au_dr_lkup_name(&args, bindex);
-+ if (unlikely(err))
-+ goto out_parent;
-+ }
++struct au_cpup_simple_args {
++ int *errp;
++ struct au_cp_generic *cpg;
++};
+
-+ 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);
++static void au_call_cpup_simple(void *args)
++{
++ struct au_cpup_simple_args *a = args;
+
-+ 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;
-+ }
-+ }
++ au_pin_hdir_acquire_nest(a->cpg->pin);
++ *a->errp = au_cpup_simple(a->cpg);
++ au_pin_hdir_release(a->cpg->pin);
++}
+
-+ if (npositive) {
-+ AuLabel(positive);
-+ au_update_dbtop(dentry);
++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;
++ struct mnt_idmap *h_idmap;
++
++ 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;
+ }
-+ 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);
++
++ parent = dget_parent(dentry);
++ h_dir = au_h_iptr(d_inode(parent), cpg->bdst);
++ h_idmap = au_sbr_idmap(dentry->d_sb, cpg->bdst);
++ if (!au_test_h_perm_sio(h_idmap, 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;
+ }
+
-+out_parent:
+ dput(parent);
-+ au_kfree_try_rcu(args.whname.name);
-+ if (dirren)
-+ au_dr_lkup_fin(&args);
++ if (h_file)
++ au_h_open_post(dentry, cpg->bsrc, h_file);
++
+out:
+ return err;
+}
+
-+struct dentry *au_sio_lkup_one(struct mnt_idmap *idmap, struct qstr *name,
-+ struct path *ppath)
++int au_sio_cpup_simple(struct au_cp_generic *cpg)
+{
-+ struct dentry *dentry;
-+ int wkq_err;
-+
-+ if (!au_test_h_perm_sio(idmap, d_inode(ppath->dentry), MAY_EXEC))
-+ dentry = vfsub_lkup_one(name, ppath);
-+ else {
-+ struct vfsub_lkup_one_args args = {
-+ .errp = &dentry,
-+ .name = name,
-+ .ppath = ppath
-+ };
++ aufs_bindex_t bsrc, bbot;
++ struct dentry *dentry, *h_dentry;
+
-+ wkq_err = au_wkq_wait(vfsub_call_lkup_one, &args);
-+ if (unlikely(wkq_err))
-+ dentry = ERR_PTR(wkq_err);
++ 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);
++}
+
-+ return dentry;
++int au_sio_cpdown_simple(struct au_cp_generic *cpg)
++{
++ AuDebugOn(cpg->bdst <= cpg->bsrc);
++ return au_do_sio_cpup_simple(cpg);
+}
+
++/* ---------------------------------------------------------------------- */
++
+/*
-+ * lookup @dentry on @bindex which should be negative.
++ * copyup the deleted file for writing.
+ */
-+int au_lkup_neg(struct dentry *dentry, aufs_bindex_t bindex, int wh)
++static int au_do_cpup_wh(struct au_cp_generic *cpg, struct dentry *wh_dentry,
++ struct file *file)
+{
+ int err;
-+ struct dentry *parent, *h_dentry;
++ 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 mnt_idmap *h_idmap;
-+ struct path h_ppath;
++ struct path h_path;
+
++ dentry = cpg->dentry;
++ bdst = cpg->bdst;
++ br = au_sbr(dentry->d_sb, bdst);
+ parent = dget_parent(dentry);
-+ br = au_sbr(dentry->d_sb, bindex);
-+ h_ppath.dentry = au_h_dptr(parent, bindex);
-+ h_ppath.mnt = au_br_mnt(br);
-+ h_idmap = au_br_idmap(br);
-+ if (wh)
-+ h_dentry = au_whtmp_lkup(h_ppath.dentry, br, &dentry->d_name);
-+ else
-+ h_dentry = au_sio_lkup_one(h_idmap, &dentry->d_name, &h_ppath);
-+ err = PTR_ERR(h_dentry);
-+ if (IS_ERR(h_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;
-+ if (unlikely(d_is_positive(h_dentry))) {
++
++ 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;
-+ AuIOErr("%pd should be negative on b%d.\n", h_dentry, bindex);
-+ dput(h_dentry);
-+ goto out;
+ }
++ au_dtime_revert(&dt);
++ au_set_hi_wh(d_inode(dentry), bdst, wh_dentry);
+
-+ 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_wh:
++ dput(wh_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;
++struct au_cpup_wh_args {
++ int *errp;
++ struct au_cp_generic *cpg;
++ struct file *file;
+};
+
-+static void au_iattr_save(struct au_iattr *ia, struct inode *h_inode)
++static void au_call_cpup_wh(void *args)
+{
-+ 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);
++ 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);
+}
+
-+static int au_iattr_test(struct au_iattr *ia, struct inode *h_inode)
++int au_sio_cpup_wh(struct au_cp_generic *cpg, struct file *file)
+{
-+ 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);
++ 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;
++ struct mnt_idmap *h_idmap;
++
++ 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;
++ }
++
++ h_idmap = au_sbr_idmap(dentry->d_sb, bdst);
++ if (!au_test_h_perm_sio(h_idmap, 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;
+}
+
-+static int au_h_verify_dentry(struct dentry *h_dentry, struct dentry *h_parent,
-+ struct au_branch *br)
++/* ---------------------------------------------------------------------- */
++
++/*
++ * 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_iattr ia;
-+ struct inode *h_inode;
-+ struct dentry *h_d;
-+ struct super_block *h_sb;
-+ struct path h_ppath;
++ struct au_pin pin;
++ struct dentry *d, *parent, *h_parent, *real_parent, *h_dentry;
+
+ 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 */
++ parent = dget_parent(dentry);
++ if (IS_ROOT(parent))
+ goto out;
+
-+ /* main purpose is namei.c:cached_lookup() and d_revalidate */
-+ h_ppath.dentry = h_parent;
-+ h_ppath.mnt = au_br_mnt(br);
-+ h_d = vfsub_lkup_one(&h_dentry->d_name, &h_ppath);
-+ err = PTR_ERR(h_d);
-+ if (IS_ERR(h_d))
-+ goto out;
++ au_pin_init(&pin, dentry, bdst, AuLsc_DI_PARENT2, AuLsc_I_PARENT2,
++ au_opt_udba(dentry->d_sb), AuPin_MNT_WRITE);
+
-+ 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);
++ /* 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:
-+ AuTraceErr(err);
++ dput(parent);
+ 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)
++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 (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);
++ 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 -urN /usr/share/empty/fs/aufs/cpup.h linux/fs/aufs/cpup.h
+--- /usr/share/empty/fs/aufs/cpup.h 1970-01-01 01:00:00.000000000 +0100
++++ linux/fs/aufs/cpup.h 2024-03-10 23:40:47.083143450 +0100
+@@ -0,0 +1,100 @@
++/* SPDX-License-Identifier: GPL-2.0 */
++/*
++ * Copyright (C) 2005-2022 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/>.
++ */
++
++/*
++ * 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);
+
+/* ---------------------------------------------------------------------- */
+
-+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;
++struct au_cp_generic {
++ struct dentry *dentry;
++ aufs_bindex_t bdst, bsrc;
++ loff_t len;
++ struct au_pin *pin;
++ unsigned int flags;
++};
+
-+ DiMustWriteLock(dentry);
++/* cpup flags */
++#define AuCpup_DTIME BIT(0) /* do dtime_store/revert */
++#define AuCpup_KEEPLINO BIT(1) /* do not clear the lower xino,
++ for link(2) */
++#define AuCpup_RENAME BIT(2) /* rename after cpup */
++#define AuCpup_HOPEN BIT(3) /* call h_open_pre/post() in
++ cpup */
++#define AuCpup_OVERWRITE BIT(4) /* allow overwriting the
++ existing entry */
++#define AuCpup_RWDST BIT(5) /* force write target even if
++ the branch is marked as RO */
+
-+ 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;
++#ifndef CONFIG_AUFS_BR_HFSPLUS
++#undef AuCpup_HOPEN
++#define AuCpup_HOPEN 0
++#endif
+
-+ new_bindex = au_br_index(sb, p->hd_id);
-+ if (new_bindex == bindex)
-+ continue;
++#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)
+
-+ 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;
-+ }
++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);
+
-+ /* 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--;
-+ }
-+ }
++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);
+
-+ 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;
++/* 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);
+
-+ 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;
-+ }
++#endif /* __KERNEL__ */
++#endif /* __AUFS_CPUP_H__ */
+diff -urN /usr/share/empty/fs/aufs/dbgaufs.c linux/fs/aufs/dbgaufs.c
+--- /usr/share/empty/fs/aufs/dbgaufs.c 1970-01-01 01:00:00.000000000 +0100
++++ linux/fs/aufs/dbgaufs.c 2023-10-10 22:51:18.033248030 +0200
+@@ -0,0 +1,526 @@
++// SPDX-License-Identifier: GPL-2.0
++/*
++ * Copyright (C) 2005-2022 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/>.
++ */
+
-+ 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;
-+ }
-+ }
++/*
++ * debugfs interface
++ */
+
-+ return err;
-+}
++#include <linux/debugfs.h>
++#include "aufs.h"
+
-+static void au_do_hide(struct dentry *dentry)
++#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)
+{
-+ struct inode *inode;
++ void *p;
+
-+ 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? */
++ p = file->private_data;
++ if (p) {
++ /* this is struct dbgaufs_arg */
++ AuDebugOn(!au_kfree_sz_test(p));
++ au_kfree_do_rcu(p);
+ }
-+ d_drop(dentry);
++ return 0;
+}
+
-+static int au_hide_children(struct dentry *parent)
++static int dbgaufs_xi_open(struct file *xf, struct file *file, int do_fcnt,
++ int cnt)
+{
-+ int err, i, j, ndentry;
-+ struct au_dcsub_pages dpages;
-+ struct au_dpage *dpage;
-+ struct dentry *dentry;
++ int err;
++ struct kstat st;
++ struct dbgaufs_arg *p;
+
-+ err = au_dpages_init(&dpages, GFP_NOFS);
-+ if (unlikely(err))
++ err = -ENOMEM;
++ p = kmalloc(sizeof(*p), GFP_NOFS);
++ if (unlikely(!p))
+ 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);
-+ }
++ 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_dpages:
-+ au_dpages_free(&dpages);
+out:
+ return err;
+}
+
-+static void au_hide(struct dentry *dentry)
++static ssize_t dbgaufs_xi_read(struct file *file, char __user *buf,
++ size_t count, loff_t *ppos)
+{
-+ int err;
++ struct dbgaufs_arg *p;
+
-+ 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);
++ p = file->private_data;
++ return simple_read_from_buffer(buf, count, ppos, p->a, p->n);
+}
+
-+/*
-+ * 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)
++/* ---------------------------------------------------------------------- */
++
++struct dbgaufs_plink_arg {
++ int n;
++ char a[];
++};
++
++static int dbgaufs_plink_release(struct inode *inode __maybe_unused,
++ struct file *file)
+{
-+ 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;
++ free_page((unsigned long)file->private_data);
++ return 0;
++}
+
-+ 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;
-+ }
-+ }
++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;
+
-+ 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);
++ err = -ENOMEM;
++ p = (void *)get_zeroed_page(GFP_NOFS);
++ if (unlikely(!p))
++ goto out;
+
-+ 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);
++ 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;
++ strscpy(p->a, str, sizeof(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;
+}
+
-+void au_refresh_dop(struct dentry *dentry, int force_reval)
++static ssize_t dbgaufs_plink_read(struct file *file, char __user *buf,
++ size_t count, loff_t *ppos)
+{
-+ 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;
++ struct dbgaufs_plink_arg *p;
+
-+ BUILD_BUG_ON(sizeof(mask) != sizeof(dentry->d_flags));
++ p = file->private_data;
++ return simple_read_from_buffer(buf, count, ppos, p->a, p->n);
++}
+
-+ if (dentry->d_op == dop)
-+ return;
++static const struct file_operations dbgaufs_plink_fop = {
++ .owner = THIS_MODULE,
++ .open = dbgaufs_plink_open,
++ .release = dbgaufs_plink_release,
++ .read = dbgaufs_plink_read
++};
+
-+ 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)
++static int dbgaufs_xib_open(struct inode *inode, struct file *file)
+{
-+ int err, ebrange, nbr;
-+ unsigned int sigen;
-+ struct au_dinfo *dinfo, *tmp;
++ int err;
++ struct au_sbinfo *sbinfo;
+ struct super_block *sb;
-+ struct inode *inode;
+
-+ DiMustWriteLock(dentry);
-+ AuDebugOn(IS_ROOT(dentry));
-+ AuDebugOn(d_really_is_negative(parent));
++ 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;
++}
+
-+ sb = dentry->d_sb;
-+ sigen = au_sigen(sb);
-+ err = au_digen_test(parent, sigen);
-+ if (unlikely(err))
-+ goto out;
++static const struct file_operations dbgaufs_xib_fop = {
++ .owner = THIS_MODULE,
++ .open = dbgaufs_xib_open,
++ .release = dbgaufs_xi_release,
++ .read = dbgaufs_xi_read
++};
+
-+ 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;
-+ }
++#define DbgaufsXi_PREFIX "xi"
+
-+ /* temporary dinfo */
-+ AuDbgDentry(dentry);
-+ err = -ENOMEM;
-+ tmp = au_di_alloc(sb, AuLsc_DI_TMP);
-+ if (unlikely(!tmp))
++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;
-+ 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);
++
++ 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;
++ }
+
-+out_dgen:
-+ au_update_digen(dentry);
++ 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:
-+ 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;
++static const struct file_operations dbgaufs_xino_fop = {
++ .owner = THIS_MODULE,
++ .open = dbgaufs_xino_open,
++ .release = dbgaufs_xi_release,
++ .read = dbgaufs_xi_read
++};
+
-+ 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);
++void dbgaufs_xino_del(struct au_branch *br)
++{
++ struct dentry *dbgaufs;
+
-+ if (unlikely(valid < 0))
-+ err = valid;
-+ else if (!valid)
-+ err = -EINVAL;
++ dbgaufs = br->br_dbgaufs;
++ if (!dbgaufs)
++ return;
+
-+out:
-+ AuTraceErr(err);
-+ return err;
++ br->br_dbgaufs = NULL;
++ /* debugfs acquires the parent i_mutex */
++ lockdep_off();
++ debugfs_remove(dbgaufs);
++ lockdep_on();
+}
+
-+/* todo: remove this */
-+static int h_d_revalidate(struct dentry *dentry, struct inode *inode,
-+ unsigned int flags, int do_udba, int dirren)
++void dbgaufs_brs_del(struct super_block *sb, aufs_bindex_t bindex)
+{
-+ 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;
++ aufs_bindex_t bbot;
++ struct au_branch *br;
+
-+ 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;
++ if (!au_sbi(sb)->si_dbgaufs)
++ return;
+
-+ /*
-+ * 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);
++ bbot = au_sbbot(sb);
++ for (; bindex <= bbot; bindex++) {
++ br = au_sbr(sb, bindex);
++ dbgaufs_xino_del(br);
+ }
++}
+
-+ 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;
++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];
+
-+ 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;
++ 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));
+
-+ 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;
++ 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);
+ }
-+ 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;
++ } 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);
++ }
++}
+
-+ /* todo: plink too? */
-+ if (!do_udba)
-+ continue;
++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;
+
-+ /* UDBA tests */
-+ if (unlikely(!!inode != d_is_positive(h_dentry)))
-+ goto err;
++ 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);
++}
+
-+ 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);
++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 (!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;
++ if (!au_opt_test(au_mntflags(sb), XINO))
++ return;
+
-+err:
-+ err = -EINVAL;
-+ break;
-+ }
++ sbinfo = au_sbi(sb);
++ parent = sbinfo->si_dbgaufs;
++ if (!parent)
++ return;
+
-+ AuTraceErr(err);
-+ return err;
++ 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);
+}
+
-+/* todo: consolidate with do_refresh() and au_reval_for_attr() */
-+static int simple_reval_dpath(struct dentry *dentry, unsigned int sigen)
++/* ---------------------------------------------------------------------- */
++
++#ifdef CONFIG_AUFS_EXPORT
++static int dbgaufs_xigen_open(struct inode *inode, struct file *file)
+{
+ int err;
-+ struct dentry *parent;
-+
-+ if (!au_digen_test(dentry, sigen))
-+ return 0;
++ struct au_sbinfo *sbinfo;
++ struct super_block *sb;
+
-+ 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);
++ 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;
+}
+
-+int au_reval_dpath(struct dentry *dentry, unsigned int sigen)
++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;
-+ struct dentry *d, *parent;
+
-+ if (!au_ftest_si(au_sbi(dentry->d_sb), FAILED_REFRESH_DIR))
-+ return simple_reval_dpath(dentry, sigen);
++ /*
++ * This function is a dynamic '__init' function actually,
++ * so the tiny check for si_rwsem is unnecessary.
++ */
++ /* AuRwMustWriteLock(&sbinfo->si_rwsem); */
+
-+ /* 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;
-+ }
++ 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;
+
-+ if (d != dentry)
-+ di_write_lock_child2(d);
++ return err;
++}
++#else
++static int dbgaufs_xigen_init(struct au_sbinfo *sbinfo)
++{
++ return 0;
++}
++#endif /* CONFIG_AUFS_EXPORT */
+
-+ /* 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;
-+ }
++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); */
+
-+ return err;
++ debugfs_remove_recursive(sbinfo->si_dbgaufs);
++ sbinfo->si_dbgaufs = NULL;
+}
+
-+/*
-+ * if valid returns 1, otherwise 0.
-+ */
-+static int aufs_d_revalidate(struct dentry *dentry, unsigned int flags)
++int dbgaufs_si_init(struct au_sbinfo *sbinfo)
+{
-+ 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;
++ int err;
++ char name[SysaufsSiNameLen];
+
-+ 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.
++ * This function is a dynamic '__init' function actually,
++ * so the tiny check for si_rwsem is unnecessary.
+ */
-+ 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;
-+ }
++ /* AuRwMustWriteLock(&sbinfo->si_rwsem); */
+
-+ 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;
-+ }
++ err = -ENOENT;
++ if (!dbgaufs) {
++ AuErr1("/debug/aufs is uninitialized\n");
++ goto out;
+ }
-+ 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;
-+ }
++ err = -EIO;
++ sysaufs_name(sbinfo, name);
++ sbinfo->si_dbgaufs = debugfs_create_dir(name, dbgaufs);
++ if (unlikely(!sbinfo->si_dbgaufs))
++ goto out;
+
-+ 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;
++ /* 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;
+
-+ if (btop >= 0) {
-+ h_inode = au_h_iptr(inode, btop);
-+ if (h_inode && au_test_higen(inode, h_inode)) {
-+ AuTraceErr(err);
-+ goto out_inval;
-+ }
-+ }
-+ }
++ /* 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;
+
-+ 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;
++ err = dbgaufs_xigen_init(sbinfo);
++ if (!err)
++ goto out; /* success */
+
-+out_dgrade:
-+ di_downgrade_lock(dentry, AuLock_IR);
-+out_inval:
-+ aufs_read_unlock(dentry, AuLock_IR);
-+ AuTraceErr(err);
-+ valid = !err;
++out_dir:
++ dbgaufs_si_fin(sbinfo);
+out:
-+ if (!valid) {
-+ AuDbg("%pd invalid, %d\n", dentry, valid);
-+ d_drop(dentry);
-+ }
-+ return valid;
++ if (unlikely(err))
++ pr_err("debugfs/aufs failed\n");
++ return err;
+}
+
-+static void aufs_d_release(struct dentry *dentry)
++/* ---------------------------------------------------------------------- */
++
++void dbgaufs_fin(void)
+{
-+ if (au_di(dentry)) {
-+ au_di_fin(dentry);
-+ au_hn_di_reinit(dentry);
-+ }
++ debugfs_remove(dbgaufs);
+}
+
-+const struct dentry_operations aufs_dop = {
-+ .d_revalidate = aufs_d_revalidate,
-+ .d_weak_revalidate = aufs_d_revalidate,
-+ .d_release = aufs_d_release
-+};
++int __init dbgaufs_init(void)
++{
++ int err;
+
-+/* 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 00000000000000..da4c9063d7e1c8
---- /dev/null
-+++ b/fs/aufs/dentry.h
-@@ -0,0 +1,270 @@
++ err = -EIO;
++ dbgaufs = debugfs_create_dir(AUFS_NAME, NULL);
++ if (dbgaufs)
++ err = 0;
++ return err;
++}
+diff -urN /usr/share/empty/fs/aufs/dbgaufs.h linux/fs/aufs/dbgaufs.h
+--- /usr/share/empty/fs/aufs/dbgaufs.h 1970-01-01 01:00:00.000000000 +0100
++++ linux/fs/aufs/dbgaufs.h 2022-11-05 23:02:18.962555950 +0100
+@@ -0,0 +1,53 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2005-2022 Junjiro R. Okajima
+ */
+
+/*
-+ * lookup and dentry operations
++ * debugfs interface
+ */
+
-+#ifndef __AUFS_DENTRY_H__
-+#define __AUFS_DENTRY_H__
++#ifndef __DBGAUFS_H__
++#define __DBGAUFS_H__
+
+#ifdef __KERNEL__
+
-+#include <linux/dcache.h>
-+#include "dirren.h"
-+#include "rwsem.h"
++struct super_block;
++struct au_sbinfo;
++struct au_branch;
+
-+struct au_hdentry {
-+ struct dentry *hd_dentry;
-+ aufs_bindex_t hd_id;
-+};
++#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 */
+
-+struct au_dinfo {
-+ atomic_t di_generation;
++#endif /* __KERNEL__ */
++#endif /* __DBGAUFS_H__ */
+diff -urN /usr/share/empty/fs/aufs/dcsub.c linux/fs/aufs/dcsub.c
+--- /usr/share/empty/fs/aufs/dcsub.c 1970-01-01 01:00:00.000000000 +0100
++++ linux/fs/aufs/dcsub.c 2022-11-05 23:02:18.962555950 +0100
+@@ -0,0 +1,225 @@
++// SPDX-License-Identifier: GPL-2.0
++/*
++ * Copyright (C) 2005-2022 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/>.
++ */
+
-+ 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 file *di_htmpfile;
-+ struct rcu_head rcu;
-+} ____cacheline_aligned_in_smp;
++/*
++ * sub-routines for dentry cache
++ */
+
-+/* ---------------------------------------------------------------------- */
++#include "aufs.h"
+
-+/* 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)
++static void au_dpage_free(struct au_dpage *dpage)
++{
++ int i;
++ struct dentry **p;
+
-+#ifndef CONFIG_AUFS_DIRREN
-+#undef AuLkup_DIRREN
-+#define AuLkup_DIRREN 0
-+#endif
++ p = dpage->dentries;
++ for (i = 0; i < dpage->ndentry; i++)
++ dput(*p++);
++ free_page((unsigned long)dpage->dentries);
++}
+
-+struct au_do_lookup_args {
-+ unsigned int flags;
-+ mode_t type;
-+ struct qstr whname, *name;
-+ struct au_dr_lookup dirren;
++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 *));
+
-+/* dentry.c */
-+extern const struct dentry_operations aufs_dop, aufs_dop_noreval;
-+struct au_branch;
-+struct dentry *au_sio_lkup_one(struct mnt_idmap *idmap, struct qstr *name,
-+ struct path *ppath);
-+int au_h_verify(struct dentry *h_dentry, unsigned int udba, struct inode *h_dir,
-+ struct dentry *h_parent, struct au_branch *br);
++struct ac_dpages_arg {
++ int err;
++ struct au_dcsub_pages *dpages;
++ struct super_block *sb;
++ au_dpages_test test;
++ void *arg;
++};
+
-+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);
++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;
+
-+/* 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);
++ 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;
++ }
+
-+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);
++ return ret;
++}
+
-+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);
++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
++ };
+
-+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);
++ d_walk(root, &args, au_call_dpages_append);
+
-+/* ---------------------------------------------------------------------- */
++ return args.err;
++}
+
-+static inline struct au_dinfo *au_di(struct dentry *dentry)
++int au_dcsub_pages_rev(struct au_dcsub_pages *dpages, struct dentry *dentry,
++ int do_include, au_dpages_test test, void *arg)
+{
-+ return dentry->d_fsdata;
++ 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;
++}
+
-+/* 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 */
-+};
++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 -urN /usr/share/empty/fs/aufs/dcsub.h linux/fs/aufs/dcsub.h
+--- /usr/share/empty/fs/aufs/dcsub.h 1970-01-01 01:00:00.000000000 +0100
++++ linux/fs/aufs/dcsub.h 2022-11-05 23:02:18.962555950 +0100
+@@ -0,0 +1,137 @@
++/* SPDX-License-Identifier: GPL-2.0 */
+/*
-+ * 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,
++ * Copyright (C) 2005-2022 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/>.
++ */
++
++/*
++ * sub-routines for dentry cache
+ */
-+#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); }
++#ifndef __AUFS_DCSUB_H__
++#define __AUFS_DCSUB_H__
+
-+#define AuRWLockFuncs(name, lsc) \
-+ AuReadLockFunc(name, lsc) \
-+ AuWriteLockFunc(name, lsc)
++#ifdef __KERNEL__
+
-+AuRWLockFuncs(child, CHILD);
-+AuRWLockFuncs(child2, CHILD2);
-+AuRWLockFuncs(child3, CHILD3);
-+AuRWLockFuncs(parent, PARENT);
-+AuRWLockFuncs(parent2, PARENT2);
-+AuRWLockFuncs(parent3, PARENT3);
++#include <linux/dcache.h>
++#include <linux/fs.h>
+
-+#undef AuReadLockFunc
-+#undef AuWriteLockFunc
-+#undef AuRWLockFuncs
++struct au_dpage {
++ int ndentry;
++ struct dentry **dentries;
++};
+
-+#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)
++struct au_dcsub_pages {
++ int ndpage;
++ struct au_dpage *dpages;
++};
+
+/* ---------------------------------------------------------------------- */
+
-+/* 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;
-+}
++/* 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);
+
-+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);
-+}
++/*
++ * todo: in linux-3.13, several similar (but faster) helpers are added to
++ * include/linux/dcache.h. Try them (in the future).
++ */
+
-+static inline aufs_bindex_t au_dbtop(struct dentry *dentry)
++static inline int au_d_hashed_positive(struct dentry *d)
+{
-+ DiMustAnyLock(dentry);
-+ return au_di(dentry)->di_btop;
-+}
++ int err;
++ struct inode *inode = d_inode(d);
+
-+static inline aufs_bindex_t au_dbbot(struct dentry *dentry)
-+{
-+ DiMustAnyLock(dentry);
-+ return au_di(dentry)->di_bbot;
++ err = 0;
++ if (unlikely(d_unhashed(d)
++ || d_is_negative(d)
++ || !inode->i_nlink))
++ err = -ENOENT;
++ return err;
+}
+
-+static inline aufs_bindex_t au_dbwh(struct dentry *dentry)
++static inline int au_d_linkable(struct dentry *d)
+{
-+ DiMustAnyLock(dentry);
-+ return au_di(dentry)->di_bwh;
-+}
++ int err;
++ struct inode *inode = d_inode(d);
+
-+static inline aufs_bindex_t au_dbdiropq(struct dentry *dentry)
-+{
-+ DiMustAnyLock(dentry);
-+ return au_di(dentry)->di_bdiropq;
++ err = au_d_hashed_positive(d);
++ if (err
++ && d_is_positive(d)
++ && (inode->i_state & I_LINKABLE))
++ err = 0;
++ return err;
+}
+
-+/* todo: hard/soft set? */
-+static inline void au_set_dbtop(struct dentry *dentry, aufs_bindex_t bindex)
++static inline int au_d_alive(struct dentry *d)
+{
-+ DiMustWriteLock(dentry);
-+ au_di(dentry)->di_btop = bindex;
-+}
++ int err;
++ struct inode *inode;
+
-+static inline void au_set_dbbot(struct dentry *dentry, aufs_bindex_t bindex)
-+{
-+ DiMustWriteLock(dentry);
-+ au_di(dentry)->di_bbot = bindex;
++ 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 void au_set_dbwh(struct dentry *dentry, aufs_bindex_t bindex)
++static inline int au_alive_dir(struct dentry *d)
+{
-+ DiMustWriteLock(dentry);
-+ /* dbwh can be outside of btop - bbot range */
-+ au_di(dentry)->di_bwh = bindex;
-+}
++ int err;
+
-+static inline void au_set_dbdiropq(struct dentry *dentry, aufs_bindex_t bindex)
-+{
-+ DiMustWriteLock(dentry);
-+ au_di(dentry)->di_bdiropq = bindex;
++ err = au_d_alive(d);
++ if (unlikely(err || IS_DEADDIR(d_inode(d))))
++ err = -ENOENT;
++ return err;
+}
+
-+/* ---------------------------------------------------------------------- */
-+
-+#ifdef CONFIG_AUFS_HNOTIFY
-+static inline void au_digen_dec(struct dentry *d)
++static inline int au_qstreq(struct qstr *a, struct qstr *b)
+{
-+ atomic_dec(&au_di(d)->di_generation);
++ return a->len == b->len
++ && !memcmp(a->name, b->name, a->len);
+}
+
-+static inline void au_hn_di_reinit(struct dentry *dentry)
++/*
++ * 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)
+{
-+ dentry->d_fsdata = NULL;
++ return (int)d_count(d);
+}
-+#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 00000000000000..bf4a94414309dc
---- /dev/null
-+++ b/fs/aufs/dinfo.c
-@@ -0,0 +1,555 @@
++#endif /* __AUFS_DCSUB_H__ */
+diff -urN /usr/share/empty/fs/aufs/debug.c linux/fs/aufs/debug.c
+--- /usr/share/empty/fs/aufs/debug.c 1970-01-01 01:00:00.000000000 +0100
++++ linux/fs/aufs/debug.c 2023-10-31 09:31:04.196547417 +0100
+@@ -0,0 +1,448 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2005-2022 Junjiro R. Okajima
+ */
+
+/*
-+ * dentry private data
++ * debug print functions
+ */
+
++#include <linux/iversion.h>
+#include "aufs.h"
+
-+void au_di_init_once(void *_dinfo)
++/* Returns 0, or -errno. arg is in kp->arg. */
++static int param_atomic_t_set(const char *val, const struct kernel_param *kp)
+{
-+ struct au_dinfo *dinfo = _dinfo;
++ int err, n;
+
-+ au_rw_init(&dinfo->di_rwsem);
++ err = kstrtoint(val, 0, &n);
++ if (!err) {
++ if (n > 0)
++ au_debug_on();
++ else
++ au_debug_off();
++ }
++ return err;
+}
+
-+struct au_dinfo *au_di_alloc(struct super_block *sb, unsigned int lsc)
++/* Returns length written or -errno. Buffer is 4k (ie. be short!) */
++static int param_atomic_t_get(char *buffer, const struct kernel_param *kp)
+{
-+ struct au_dinfo *dinfo;
-+ int nbr, i;
++ atomic_t *a;
+
-+ dinfo = au_cache_alloc_dinfo();
-+ if (unlikely(!dinfo))
-+ goto out;
++ a = kp->arg;
++ return sprintf(buffer, "%d", atomic_read(a));
++}
+
-+ 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;
-+ dinfo->di_htmpfile = NULL;
-+ goto out;
-+ }
++static const struct kernel_param_ops param_ops_atomic_t = {
++ .set = param_atomic_t_set,
++ .get = param_atomic_t_get
++ /* void (*free)(void *arg) */
++};
+
-+ au_cache_free_dinfo(dinfo);
-+ dinfo = NULL;
++atomic_t aufs_debug = ATOMIC_INIT(0);
++MODULE_PARM_DESC(debug, "debug print");
++module_param_named(debug, aufs_debug, atomic_t, 0664);
+
-+out:
-+ return dinfo;
-+}
++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_di_free(struct au_dinfo *dinfo)
++/* ---------------------------------------------------------------------- */
++
++void au_dpri_whlist(struct au_nhash *whlist)
+{
-+ struct au_hdentry *p;
-+ aufs_bindex_t bbot, bindex;
++ unsigned long ul, n;
++ struct hlist_head *head;
++ struct au_vdir_wh *pos;
+
-+ /* 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++);
++ 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++;
+ }
-+ au_kfree_try_rcu(dinfo->di_hdentry);
-+ au_cache_free_dinfo(dinfo);
+}
+
-+void au_di_swap(struct au_dinfo *a, struct au_dinfo *b)
++void au_dpri_vdir(struct au_vdir *vdir)
+{
-+ 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)
++ unsigned long ul;
++ union au_vdir_deblk_p p;
++ unsigned char *o;
+
-+ DiSwap(p, hdentry);
-+ DiSwap(bi, btop);
-+ DiSwap(bi, bbot);
-+ DiSwap(bi, bwh);
-+ DiSwap(bi, bdiropq);
-+ /* smp_mb(); */
++ if (!vdir || IS_ERR(vdir)) {
++ dpri("err %ld\n", PTR_ERR(vdir));
++ return;
++ }
+
-+#undef DiSwap
++ 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);
++ }
+}
+
-+void au_di_cp(struct au_dinfo *dst, struct au_dinfo *src)
++static int do_pri_inode(aufs_bindex_t bindex, struct inode *inode, int hn,
++ struct dentry *wh)
+{
-+ AuRwMustWriteLock(&dst->di_rwsem);
-+ AuRwMustWriteLock(&src->di_rwsem);
++ char *n = NULL;
++ int l = 0;
++ struct timespec64 ctime;
+
-+ 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(); */
++ 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;
++ }
++
++ ctime = inode_get_ctime(inode);
++ dpri("i%d: %p, i%lu, %s, cnt %d, nl %u, 0%o, sz %llu, blk %llu,"
++ " acl %p, def_acl %p,"
++ " 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,
++ inode->i_acl, inode->i_default_acl,
++ hn, (long long)timespec64_to_ns(&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;
+}
+
-+int au_di_init(struct dentry *dentry)
++void au_dpri_inode(struct inode *inode)
+{
-+ int err;
-+ struct super_block *sb;
-+ struct au_dinfo *dinfo;
++ struct au_iinfo *iinfo;
++ struct au_hinode *hi;
++ aufs_bindex_t bindex;
++ int err, hn;
+
-+ 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;
++ err = do_pri_inode(-1, inode, -1, NULL);
++ if (err || !au_test_aufs(inode->i_sb) || au_is_bad_inode(inode))
++ return;
+
-+ return err;
++ 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_di_fin(struct dentry *dentry)
++void au_dpri_dalias(struct inode *inode)
+{
-+ struct au_dinfo *dinfo;
++ struct dentry *d;
+
-+ dinfo = au_di(dentry);
-+ AuRwDestroy(&dinfo->di_rwsem);
-+ au_di_free(dinfo);
++ 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);
+}
+
-+int au_di_realloc(struct au_dinfo *dinfo, int nbr, int may_shrink)
++static int do_pri_dentry(aufs_bindex_t bindex, struct dentry *dentry)
+{
-+ int err, sz;
-+ struct au_hdentry *hdp;
-+
-+ AuRwMustWriteLock(&dinfo->di_rwsem);
++ struct dentry *wh = NULL;
++ int hn;
++ struct inode *inode;
++ struct au_iinfo *iinfo;
++ struct au_hinode *hi;
+
-+ 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;
++ if (!dentry || IS_ERR(dentry)) {
++ dpri("d%d: err %ld\n", bindex, PTR_ERR(dentry));
++ return -1;
+ }
-+
-+ 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();
++ /* 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;
+}
+
-+static void do_ii_read_lock(struct inode *inode, unsigned int lsc)
++void au_dpri_dentry(struct dentry *dentry)
+{
-+ 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();
-+ }
-+}
++ struct au_dinfo *dinfo;
++ aufs_bindex_t bindex;
++ int err;
+
-+void di_read_lock(struct dentry *d, int flags, unsigned int lsc)
-+{
-+ struct inode *inode;
++ err = do_pri_dentry(-1, dentry);
++ if (err || !au_test_aufs(dentry->d_sb))
++ return;
+
-+ 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);
-+ }
++ 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);
+}
+
-+void di_read_unlock(struct dentry *d, int flags)
++static int do_pri_file(aufs_bindex_t bindex, struct file *file)
+{
-+ struct inode *inode;
++ char a[32];
+
-+ 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);
-+ }
++ if (!file || IS_ERR(file)) {
++ dpri("f%d: err %ld\n", bindex, PTR_ERR(file));
++ return -1;
+ }
-+ au_rw_read_unlock(&au_di(d)->di_rwsem);
++ 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 di_downgrade_lock(struct dentry *d, int flags)
++void au_dpri_file(struct file *file)
+{
-+ 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);
++ 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);
++ }
+}
+
-+void di_write_lock(struct dentry *d, unsigned int lsc)
++static int do_pri_br(aufs_bindex_t bindex, struct au_branch *br)
+{
-+ 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);
++ 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 di_write_unlock(struct dentry *d)
++void au_dpri_sb(struct super_block *sb)
+{
-+ 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);
++ 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 di_write_lock2_child(struct dentry *d1, struct dentry *d2, int isdir)
++/* ---------------------------------------------------------------------- */
++
++void __au_dbg_verify_dinode(struct dentry *dentry, const char *func, int line)
+{
-+ AuDebugOn(d1 == d2
-+ || d_inode(d1) == d_inode(d2)
-+ || d1->d_sb != d2->d_sb);
++ struct inode *h_inode, *inode = d_inode(dentry);
++ struct dentry *h_dentry;
++ aufs_bindex_t bindex, bbot, bi;
+
-+ 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);
++ 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();
++ if (au_test_fuse(h_inode->i_sb))
++ WARN_ON_ONCE(1);
++ else
++ BUG();
++ }
+ }
+}
+
-+void di_write_lock2_parent(struct dentry *d1, struct dentry *d2, int isdir)
++void au_dbg_verify_gen(struct dentry *parent, unsigned int sigen)
+{
-+ AuDebugOn(d1 == d2
-+ || d_inode(d1) == d_inode(d2)
-+ || d1->d_sb != d2->d_sb);
++ int err, i, j;
++ struct au_dcsub_pages dpages;
++ struct au_dpage *dpage;
++ struct dentry **dentries;
+
-+ 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);
++ 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 di_write_unlock2(struct dentry *d1, struct dentry *d2)
++void au_dbg_verify_kthread(void)
+{
-+ 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);
++ 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); */
++ }
+}
+
+/* ---------------------------------------------------------------------- */
+
-+struct dentry *au_h_dptr(struct dentry *dentry, aufs_bindex_t bindex)
++int __init au_debug_init(void)
+{
-+ struct dentry *d;
++ aufs_bindex_t bindex;
++ struct au_vdir_destr destr;
+
-+ DiMustAnyLock(dentry);
++ bindex = -1;
++ AuDebugOn(bindex >= 0);
+
-+ 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;
++ destr.len = -1;
++ AuDebugOn(destr.len < NAME_MAX);
++
++#ifdef CONFIG_4KSTACKS
++ pr_warn("CONFIG_4KSTACKS is defined.\n");
++#endif
++
++ return 0;
+}
+diff -urN /usr/share/empty/fs/aufs/debug.h linux/fs/aufs/debug.h
+--- /usr/share/empty/fs/aufs/debug.h 1970-01-01 01:00:00.000000000 +0100
++++ linux/fs/aufs/debug.h 2022-11-05 23:02:18.962555950 +0100
+@@ -0,0 +1,226 @@
++/* SPDX-License-Identifier: GPL-2.0 */
++/*
++ * Copyright (C) 2005-2022 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/>.
++ */
+
+/*
-+ * extended version of au_h_dptr().
-+ * returns a hashed and positive (or linkable) h_dentry in bindex, NULL, or
-+ * error.
++ * debug print functions
+ */
-+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));
++#ifndef __AUFS_DEBUG_H__
++#define __AUFS_DEBUG_H__
+
-+ 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 */
-+ }
++#ifdef __KERNEL__
+
-+ 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;
-+ }
++#include <linux/atomic.h>
++#include <linux/module.h>
++#include <linux/kallsyms.h>
++#include <linux/sysrq.h>
+
-+ 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;
-+ }
-+ }
++#ifdef CONFIG_AUFS_DEBUG
++#define AuDebugOn(a) BUG_ON(a)
+
-+out:
-+ AuDbgDentry(h_dentry);
-+ return h_dentry;
++/* module parameter */
++extern atomic_t aufs_debug;
++static inline void au_debug_on(void)
++{
++ atomic_inc(&aufs_debug);
+}
-+
-+aufs_bindex_t au_dbtail(struct dentry *dentry)
++static inline void au_debug_off(void)
+{
-+ 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;
++ atomic_dec_if_positive(&aufs_debug);
+}
+
-+aufs_bindex_t au_dbtaildir(struct dentry *dentry)
++static inline int au_debug_test(void)
+{
-+ 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;
++ 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)
+
+/* ---------------------------------------------------------------------- */
+
-+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;
++/* debug print */
+
-+ DiMustWriteLock(dentry);
++#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)
+
-+ 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;
-+ }
-+}
++#define AuErr1(fmt, ...) do { \
++ static unsigned char _c; \
++ if (!_c++) \
++ pr_err(fmt, ##__VA_ARGS__); \
++} while (0)
+
-+int au_dbrange_test(struct dentry *dentry)
-+{
-+ int err;
-+ aufs_bindex_t btop, bbot;
++#define AuIOErr1(fmt, ...) do { \
++ static unsigned char _c; \
++ if (!_c++) \
++ AuIOErr(fmt, ##__VA_ARGS__); \
++} while (0)
+
-+ err = 0;
-+ btop = au_dbtop(dentry);
-+ bbot = au_dbbot(dentry);
-+ if (btop >= 0)
-+ AuDebugOn(bbot < 0 && btop > bbot);
-+ else {
-+ err = -EIO;
-+ AuDebugOn(bbot >= 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)
+
-+ return err;
-+}
++#define AuTraceErr(e) do { \
++ if (unlikely((e) < 0)) \
++ AuDbg("err %d\n", (int)(e)); \
++} while (0)
+
-+int au_digen_test(struct dentry *dentry, unsigned int sigen)
-+{
-+ int err;
++#define AuTraceErrPtr(p) do { \
++ if (IS_ERR(p)) \
++ AuDbg("err %ld\n", PTR_ERR(p)); \
++} while (0)
+
-+ err = 0;
-+ if (unlikely(au_digen(dentry) != sigen
-+ || au_iigen_test(d_inode(dentry), sigen)))
-+ err = -EIO;
++/* dirty macros for debug print, use with "%.*s" and caution */
++#define AuLNPair(qstr) (qstr)->len, (qstr)->name
+
-+ 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 */
-+}
++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);
+
-+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;
++#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);
+
-+ DiMustWriteLock(dentry);
++int __init au_debug_init(void);
+
-+ dinfo = au_di(dentry);
-+ if (!dinfo || dinfo->di_btop < 0)
-+ return;
++#define AuDbgWhlist(w) do { \
++ mutex_lock(&au_dbg_mtx); \
++ AuDbg(#w "\n"); \
++ au_dpri_whlist(w); \
++ mutex_unlock(&au_dbg_mtx); \
++} while (0)
+
-+ 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);
-+ }
-+ }
++#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)
+
-+ 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;
-+ }
++#define AuDbgSb(sb) do { \
++ mutex_lock(&au_dbg_mtx); \
++ AuDbg(#sb "\n"); \
++ au_dpri_sb(sb); \
++ mutex_unlock(&au_dbg_mtx); \
++} while (0)
+
-+ 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);
-+}
++#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)
+
-+void au_update_dbtop(struct dentry *dentry)
-+{
-+ aufs_bindex_t bindex, bbot;
-+ struct dentry *h_dentry;
++#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 */
+
-+ 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;
++#ifdef CONFIG_AUFS_MAGIC_SYSRQ
++int __init au_sysrq_init(void);
++void au_sysrq_fin(void);
+
-+ 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);
-+ }
-+}
++#ifdef CONFIG_HW_CONSOLE
++#define au_dbg_blocked() do { \
++ WARN_ON(1); \
++ handle_sysrq('w'); \
++} while (0)
++#else
++AuStubVoid(au_dbg_blocked, void)
++#endif
+
-+int au_find_dbindex(struct dentry *dentry, struct dentry *h_dentry)
-+{
-+ aufs_bindex_t bindex, bbot;
++#else
++AuStubInt0(__init au_sysrq_init, void)
++AuStubVoid(au_sysrq_fin, void)
++AuStubVoid(au_dbg_blocked, void)
++#endif /* CONFIG_AUFS_MAGIC_SYSRQ */
+
-+ 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 00000000000000..ee900ea3264b22
---- /dev/null
-+++ b/fs/aufs/dir.c
-@@ -0,0 +1,765 @@
++#endif /* __KERNEL__ */
++#endif /* __AUFS_DEBUG_H__ */
+diff -urN /usr/share/empty/fs/aufs/dentry.c linux/fs/aufs/dentry.c
+--- /usr/share/empty/fs/aufs/dentry.c 1970-01-01 01:00:00.000000000 +0100
++++ linux/fs/aufs/dentry.c 2023-10-31 09:31:04.196547417 +0100
+@@ -0,0 +1,1168 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2005-2022 Junjiro R. Okajima
+ */
+
+/*
-+ * directory operations
++ * lookup and dentry operations
+ */
+
-+#include <linux/fs_stack.h>
+#include <linux/iversion.h>
+#include "aufs.h"
+
-+void au_add_nlink(struct inode *dir, struct inode *h_dir)
++/*
++ * 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)
+{
-+ unsigned int nlink;
++ struct dentry *h_dentry;
++ struct inode *h_inode;
++ struct au_branch *br;
++ struct mnt_idmap *h_idmap;
++ struct path h_path;
++ 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);
+
-+ AuDebugOn(!S_ISDIR(dir->i_mode) || !S_ISDIR(h_dir->i_mode));
++ wh_found = 0;
++ br = au_sbr(dentry->d_sb, bindex);
++ h_path.dentry = h_parent;
++ h_path.mnt = au_br_mnt(br);
++ h_idmap = au_br_idmap(br);
++ wh_able = !!au_br_whable(br->br_perm);
++ if (wh_able)
++ wh_found = au_wh_test(h_idmap, &h_path, &args->whname,
++ ignore_perm);
++ h_dentry = ERR_PTR(wh_found);
++ if (!wh_found)
++ goto real_lookup;
++ if (unlikely(wh_found < 0))
++ goto out;
+
-+ 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);
-+}
++ /* We found a whiteout */
++ /* au_set_dbbot(dentry, bindex); */
++ au_set_dbwh(dentry, bindex);
++ if (!allow_neg)
++ return NULL; /* success */
+
-+void au_sub_nlink(struct inode *dir, struct inode *h_dir)
-+{
-+ unsigned int nlink;
++real_lookup:
++ if (!ignore_perm)
++ h_dentry = vfsub_lkup_one(args->name, &h_path);
++ else
++ h_dentry = au_sio_lkup_one(h_idmap, args->name, &h_path);
++ if (IS_ERR(h_dentry)) {
++ if (PTR_ERR(h_dentry) == -ENAMETOOLONG
++ && !allow_neg)
++ h_dentry = NULL;
++ goto out;
++ }
+
-+ AuDebugOn(!S_ISDIR(dir->i_mode) || !S_ISDIR(h_dir->i_mode));
++ 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;
++ }
+
-+ 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);
++ 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 */
++
++ h_path.dentry = h_dentry;
++ inode_lock_shared_nested(h_inode, AuLsc_I_CHILD);
++ opq = au_diropq_test(h_idmap, &h_path);
++ 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;
+}
+
-+loff_t au_dir_size(struct file *file, struct dentry *dentry)
++static int au_test_shwh(struct super_block *sb, const struct qstr *name)
+{
-+ loff_t sz;
-+ aufs_bindex_t bindex, bbot;
-+ struct file *h_file;
-+ struct dentry *h_dentry;
++ if (unlikely(!au_opt_test(au_mntflags(sb), SHWH)
++ && !strncmp(name->name, AUFS_WH_PFX, AUFS_WH_PFX_LEN)))
++ return -EPERM;
++ return 0;
++}
+
-+ sz = 0;
-+ if (file) {
-+ AuDebugOn(!d_is_dir(file->f_path.dentry));
++/*
++ * 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;
+
-+ 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);
++ 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;
+ }
-+ } else {
-+ AuDebugOn(!dentry);
-+ AuDebugOn(!d_is_dir(dentry));
++ h_parent = au_h_dptr(parent, bindex);
++ if (!h_parent || !d_is_dir(h_parent))
++ continue;
+
-+ 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 (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 (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;
++
++ if (npositive) {
++ AuLabel(positive);
++ au_update_dbtop(dentry);
+ }
-+ return sz;
++ 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 au_dir_ts_arg {
++struct dentry *au_sio_lkup_one(struct mnt_idmap *idmap, struct qstr *name,
++ struct path *ppath)
++{
+ struct dentry *dentry;
-+ aufs_bindex_t brid;
-+};
++ int wkq_err;
+
-+static void au_do_dir_ts(void *arg)
++ if (!au_test_h_perm_sio(idmap, d_inode(ppath->dentry), MAY_EXEC))
++ dentry = vfsub_lkup_one(name, ppath);
++ else {
++ struct vfsub_lkup_one_args args = {
++ .errp = &dentry,
++ .name = name,
++ .ppath = ppath
++ };
++
++ 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)
+{
-+ 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;
++ struct dentry *parent, *h_dentry;
++ struct au_branch *br;
++ struct mnt_idmap *h_idmap;
++ struct path h_ppath;
+
-+ sb = a->dentry->d_sb;
-+ if (d_really_is_negative(a->dentry))
++ parent = dget_parent(dentry);
++ br = au_sbr(dentry->d_sb, bindex);
++ h_ppath.dentry = au_h_dptr(parent, bindex);
++ h_ppath.mnt = au_br_mnt(br);
++ h_idmap = au_br_idmap(br);
++ if (wh)
++ h_dentry = au_whtmp_lkup(h_ppath.dentry, br, &dentry->d_name);
++ else
++ h_dentry = au_sio_lkup_one(h_idmap, &dentry->d_name, &h_ppath);
++ err = PTR_ERR(h_dentry);
++ if (IS_ERR(h_dentry))
+ goto out;
-+ /* no dir->i_mutex lock */
-+ aufs_read_lock(a->dentry, AuLock_DW); /* noflush */
++ 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;
++ }
+
-+ dir = d_inode(a->dentry);
-+ btop = au_ibtop(dir);
-+ bindex = au_br_index(sb, a->brid);
-+ if (bindex < btop)
-+ goto out_unlock;
++ 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);
+
-+ 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);
++out:
++ dput(parent);
++ return err;
++}
+
-+ 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);
++/* 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);
+}
+
-+void au_dir_ts(struct inode *dir, aufs_bindex_t bindex)
++static int au_h_verify_dentry(struct dentry *h_dentry, struct dentry *h_parent,
++ struct au_branch *br)
+{
-+ 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;
-+ }
++ int err;
++ struct au_iattr ia;
++ struct inode *h_inode;
++ struct dentry *h_d;
++ struct super_block *h_sb;
++ struct path h_ppath;
+
-+ perm = au_sbr_perm(sb, btop);
-+ if (!au_br_writable(perm))
++ 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;
+
-+ arg = kmalloc(sizeof(*arg), GFP_NOFS);
-+ if (!arg)
++ /* main purpose is namei.c:cached_lookup() and d_revalidate */
++ h_ppath.dentry = h_parent;
++ h_ppath.mnt = au_br_mnt(br);
++ h_d = vfsub_lkup_one(&h_dentry->d_name, &h_ppath);
++ err = PTR_ERR(h_d);
++ if (IS_ERR(h_d))
+ 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);
-+ }
++ 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:
-+ dput(dentry);
++ 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 reopen_dir(struct file *file)
++static int au_do_refresh_hdentry(struct dentry *dentry, struct dentry *parent)
+{
+ int err;
-+ unsigned int flags;
-+ aufs_bindex_t bindex, btail, btop;
-+ struct dentry *dentry, *h_dentry;
-+ struct file *h_file;
++ aufs_bindex_t new_bindex, bindex, bbot, bwh, bdiropq;
++ struct au_hdentry tmp, *p, *q;
++ struct au_dinfo *dinfo;
++ struct super_block *sb;
+
-+ /* 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);
++ DiMustWriteLock(dentry);
+
-+ 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);
++ 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;
+
-+ flags = vfsub_file_flags(file);
-+ for (bindex = btop; bindex <= btail; bindex++) {
-+ h_dentry = au_h_dptr(dentry, bindex);
-+ if (!h_dentry)
++ new_bindex = au_br_index(sb, p->hd_id);
++ if (new_bindex == bindex)
+ continue;
-+ h_file = au_hf_dir(file, bindex);
-+ if (h_file)
++
++ 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;
++ }
+
-+ 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);
++ /* 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;
++ }
+ }
-+ 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)
++static void au_do_hide(struct dentry *dentry)
+{
-+ int err;
-+ aufs_bindex_t bindex, btail;
-+ struct dentry *dentry, *h_dentry;
-+ struct vfsmount *mnt;
++ struct inode *inode;
+
-+ FiMustWriteLock(file);
-+ AuDebugOn(h_file);
++ 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);
++}
+
-+ 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;
++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 = 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;
++ 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);
+ }
-+ 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);
+
++out_dpages:
++ au_dpages_free(&dpages);
++out:
+ return err;
+}
+
-+static int aufs_open_dir(struct inode *inode __maybe_unused,
-+ struct file *file)
++static void au_hide(struct dentry *dentry)
+{
+ 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);
++ AuDbgDentry(dentry);
++ if (d_is_dir(dentry)) {
++ /* shrink_dcache_parent(dentry); */
++ err = au_hide_children(dentry);
+ if (unlikely(err))
-+ au_kfree_rcu(fidir);
++ AuIOErr("%pd, failed hiding children, ignored %d\n",
++ dentry, err);
+ }
-+ si_read_unlock(sb);
-+ return err;
++ au_do_hide(dentry);
+}
+
-+static int aufs_release_dir(struct inode *inode __maybe_unused,
-+ struct file *file)
++/*
++ * 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)
+{
-+ struct au_vdir *vdir_cache;
-+ struct au_finfo *finfo;
-+ struct au_fidir *fidir;
-+ struct au_hfile *hf;
++ 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;
+
-+ 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);
++ 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;
++ }
++ }
+
-+ bindex = finfo->fi_btop;
-+ if (bindex >= 0) {
-+ hf = fidir->fd_hfile + bindex;
++ 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");
+ /*
-+ * calls fput() instead of filp_close(),
-+ * since no dnotify or lock for the lower file.
++ * 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.
+ */
-+ bbot = fidir->fd_bbot;
-+ for (; bindex <= bbot; bindex++, hf++)
-+ if (hf->hf_file)
-+ au_hfput(hf, /*execed*/0);
++ 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);
+ }
-+ 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);
-+ }
++out:
+ 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)
++void au_refresh_dop(struct dentry *dentry, int force_reval)
+{
-+ 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;
++ 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;
+
-+ h_path.mnt = au_sbr_mnt(sb, bindex);
-+ err = vfsub_fsync(NULL, &h_path, datasync);
-+ }
++ BUILD_BUG_ON(sizeof(mask) != sizeof(dentry->d_flags));
+
-+ return err;
++ 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);
+}
+
-+static int au_do_fsync_dir(struct file *file, int datasync)
++int au_refresh_dentry(struct dentry *dentry, struct dentry *parent)
+{
-+ int err;
-+ aufs_bindex_t bbot, bindex;
-+ struct file *h_file;
++ int err, ebrange, nbr;
++ unsigned int sigen;
++ struct au_dinfo *dinfo, *tmp;
+ struct super_block *sb;
+ struct inode *inode;
+
-+ err = au_reval_and_lock_fdi(file, reopen_dir, /*wlock*/1, /*fi_lsc*/0);
++ 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;
+
-+ 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;
++ 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);
+
-+ err = vfsub_fsync(h_file, &h_file->f_path, datasync);
++ 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;
+}
+
-+/*
-+ * @file may be NULL
-+ */
-+static int aufs_fsync_dir(struct file *file, loff_t start, loff_t end,
-+ int datasync)
++static int au_do_h_d_reval(struct dentry *h_dentry, unsigned int flags,
++ struct dentry *dentry, aufs_bindex_t bindex)
+{
-+ int err;
-+ struct dentry *dentry;
-+ struct inode *inode;
-+ struct super_block *sb;
++ int err, valid;
+
+ 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);
++ if (!(h_dentry->d_flags & DCACHE_OP_REVALIDATE))
++ goto out;
+
-+ si_read_unlock(sb);
-+ inode_unlock(inode);
++ 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;
+}
+
-+/* ---------------------------------------------------------------------- */
-+
-+static int aufs_iterate_shared(struct file *file, struct dir_context *ctx)
++/* todo: remove this */
++static int h_d_revalidate(struct dentry *dentry, struct inode *inode,
++ unsigned int flags, int do_udba, int dirren)
+{
+ 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;
++ 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;
+
-+ 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);
++ 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;
+
-+ AuTraceErr(err);
-+ return err;
++ /*
++ * 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);
+ }
+
-+out_unlock:
-+ di_read_unlock(dentry, AuLock_IR);
-+ fi_write_unlock(file);
-+out:
-+ si_read_unlock(sb);
-+ return err;
-+}
++ 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;
+
-+#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)
++ 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);
+
-+#ifndef CONFIG_AUFS_SHWH
-+#undef AuTestEmpty_SHWH
-+#define AuTestEmpty_SHWH 0
-+#endif
++ err = au_do_h_d_reval(h_dentry, flags, dentry, bindex);
++ if (unlikely(err))
++ /* do not goto err, to keep the errno */
++ break;
+
-+struct test_empty_arg {
-+ struct dir_context ctx;
-+ struct au_nhash *whlist;
-+ unsigned int flags;
-+ int err;
-+ aufs_bindex_t bindex;
-+};
++ /* todo: plink too? */
++ if (!do_udba)
++ continue;
+
-+static bool 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;
++ /* UDBA tests */
++ if (unlikely(!!inode != d_is_positive(h_dentry)))
++ goto err;
+
-+ arg->err = 0;
-+ au_fset_testempty(arg->flags, CALLED);
-+ /* smp_mb(); */
-+ if (name[0] == '.'
-+ && (namelen == 1 || (name[1] == '.' && namelen == 2)))
-+ goto out; /* success */
++ 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 (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;
-+ }
++ 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;
+
-+ 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));
++err:
++ err = -EINVAL;
++ break;
++ }
+
-+out:
-+ /* smp_mb(); */
-+ AuTraceErr(arg->err);
-+ return !arg->err;
++ AuTraceErr(err);
++ return err;
+}
+
-+static int do_test_empty(struct dentry *dentry, struct test_empty_arg *arg)
++/* todo: consolidate with do_refresh() and au_reval_for_attr() */
++static int simple_reval_dpath(struct dentry *dentry, unsigned int sigen)
+{
+ 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;
++ struct dentry *parent;
+
-+ 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));
++ if (!au_digen_test(dentry, sigen))
++ return 0;
+
-+out_put:
-+ fput(h_file);
-+ br = au_sbr(dentry->d_sb, arg->bindex);
-+ au_lcnt_dec(&br->br_nfiles);
-+out:
++ 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;
+}
+
-+struct do_test_empty_args {
-+ int *errp;
-+ struct dentry *dentry;
-+ struct test_empty_arg *arg;
-+};
-+
-+static void call_do_test_empty(void *args)
++int au_reval_dpath(struct dentry *dentry, unsigned int sigen)
+{
-+ struct do_test_empty_args *a = args;
-+ *a->errp = do_test_empty(a->dentry, a->arg);
-+}
++ int err;
++ struct dentry *d, *parent;
+
-+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;
-+ struct mnt_idmap *h_idmap;
++ if (!au_ftest_si(au_sbi(dentry->d_sb), FAILED_REFRESH_DIR))
++ return simple_reval_dpath(dentry, sigen);
+
-+ h_idmap = au_sbr_idmap(dentry->d_sb, arg->bindex);
-+ 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_idmap, 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;
++ /* 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;
++ }
+
-+ wkq_err = au_wkq_wait(call_do_test_empty, &args);
-+ if (unlikely(wkq_err))
-+ err = wkq_err;
-+ arg->flags = flags;
++ 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;
+}
+
-+int au_test_empty_lower(struct dentry *dentry)
++/*
++ * if valid returns 1, otherwise 0.
++ */
++static int aufs_d_revalidate(struct dentry *dentry, unsigned int flags)
+{
-+ 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);
++ int valid, err;
++ unsigned int sigen;
++ unsigned char do_udba, dirren;
++ struct super_block *sb;
++ struct inode *inode;
+
-+ SiMustAnyLock(dentry->d_sb);
++ /* 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;
++ }
+
-+ 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;
++ 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);
+
-+ 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;
++ 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;
++ }
+
-+ au_fset_testempty(arg.flags, WHONLY);
-+ btail = au_dbtaildir(dentry);
-+ for (bindex = btop + 1; !err && bindex <= btail; bindex++) {
-+ struct dentry *h_dentry;
++ 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;
+
-+ h_dentry = au_h_dptr(dentry, bindex);
-+ if (h_dentry && d_is_positive(h_dentry)) {
-+ arg.bindex = bindex;
-+ err = test_empty(dentry, &arg);
++ if (btop >= 0) {
++ h_inode = au_h_iptr(inode, btop);
++ if (h_inode && au_test_higen(inode, h_inode)) {
++ AuTraceErr(err);
++ goto out_inval;
++ }
+ }
+ }
+
-+out_whlist:
-+ au_nhash_wh_free(&whlist);
++ 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:
-+ return err;
++ if (!valid) {
++ AuDbg("%pd invalid, %d\n", dentry, valid);
++ d_drop(dentry);
++ }
++ return valid;
+}
+
-+int au_test_empty(struct dentry *dentry, struct au_nhash *whlist)
++static void aufs_d_release(struct dentry *dentry)
+{
-+ 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);
-+ }
++ if (au_di(dentry)) {
++ au_di_fin(dentry);
++ au_hn_di_reinit(dentry);
+ }
-+
-+ return err;
+}
+
-+/* ---------------------------------------------------------------------- */
++const struct dentry_operations aufs_dop = {
++ .d_revalidate = aufs_d_revalidate,
++ .d_weak_revalidate = aufs_d_revalidate,
++ .d_release = aufs_d_release
++};
+
-+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
++/* aufs_dop without d_revalidate */
++const struct dentry_operations aufs_dop_noreval = {
++ .d_release = aufs_d_release
+};
-diff --git a/fs/aufs/dir.h b/fs/aufs/dir.h
-new file mode 100644
-index 00000000000000..382342bd6ecff3
---- /dev/null
-+++ b/fs/aufs/dir.h
-@@ -0,0 +1,134 @@
+diff -urN /usr/share/empty/fs/aufs/dentry.h linux/fs/aufs/dentry.h
+--- /usr/share/empty/fs/aufs/dentry.h 1970-01-01 01:00:00.000000000 +0100
++++ linux/fs/aufs/dentry.h 2024-03-10 23:40:47.083143450 +0100
+@@ -0,0 +1,270 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2005-2022 Junjiro R. Okajima
+ */
+
+/*
-+ * directory operations
++ * lookup and dentry operations
+ */
+
-+#ifndef __AUFS_DIR_H__
-+#define __AUFS_DIR_H__
++#ifndef __AUFS_DENTRY_H__
++#define __AUFS_DENTRY_H__
+
+#ifdef __KERNEL__
+
-+#include <linux/fs.h>
-+
-+/* ---------------------------------------------------------------------- */
-+
-+/* need to be faster and smaller */
++#include <linux/dcache.h>
++#include "dirren.h"
++#include "rwsem.h"
+
-+struct au_nhash {
-+ unsigned int nh_num;
-+ struct hlist_head *nh_head;
++struct au_hdentry {
++ struct dentry *hd_dentry;
++ aufs_bindex_t hd_id;
+};
+
-+struct au_vdir_destr {
-+ unsigned char len;
-+ unsigned char name[];
-+} __packed;
++struct au_dinfo {
++ atomic_t di_generation;
+
-+struct au_vdir_dehstr {
-+ struct hlist_node hash;
-+ struct au_vdir_destr *str;
++ 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 file *di_htmpfile;
+ 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;
++/* flags for au_lkup_dentry() */
++#define AuLkup_ALLOW_NEG BIT(0)
++#define AuLkup_IGNORE_PERM BIT(1)
++#define AuLkup_DIRREN BIT(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
-+ /* caution: packed */
-+ struct au_vdir_destr wh_str;
-+} __packed;
+
-+union au_vdir_deblk_p {
-+ unsigned char *deblk;
-+ struct au_vdir_de *de;
++struct au_do_lookup_args {
++ unsigned int flags;
++ mode_t type;
++ struct qstr whname, *name;
++ struct au_dr_lookup dirren;
+};
+
-+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;
++/* dentry.c */
++extern const struct dentry_operations aufs_dop, aufs_dop_noreval;
++struct au_branch;
++struct dentry *au_sio_lkup_one(struct mnt_idmap *idmap, struct qstr *name,
++ struct path *ppath);
++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);
+
+/* ---------------------------------------------------------------------- */
+
-+/* 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);
++static inline struct au_dinfo *au_di(struct dentry *dentry)
++{
++ return dentry->d_fsdata;
++}
+
-+/* 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);
++/* 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 */
++};
+
-+#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
++/*
++ * 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
-+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
++AuStubVoid(au_hn_di_reinit, struct dentry *dentry __maybe_unused)
++#endif /* CONFIG_AUFS_HNOTIFY */
+
+#endif /* __KERNEL__ */
-+#endif /* __AUFS_DIR_H__ */
-diff --git a/fs/aufs/dirren.c b/fs/aufs/dirren.c
-new file mode 100644
-index 00000000000000..2a6295ab6576b8
---- /dev/null
-+++ b/fs/aufs/dirren.c
-@@ -0,0 +1,1315 @@
++#endif /* __AUFS_DENTRY_H__ */
+diff -urN /usr/share/empty/fs/aufs/dinfo.c linux/fs/aufs/dinfo.c
+--- /usr/share/empty/fs/aufs/dinfo.c 1970-01-01 01:00:00.000000000 +0100
++++ linux/fs/aufs/dinfo.c 2022-12-17 09:21:34.796521861 +0100
+@@ -0,0 +1,555 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
-+ * Copyright (C) 2017-2022 Junjiro R. Okajima
++ * Copyright (C) 2005-2022 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
+ * 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
-+ */
++/*
++ * 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;
++ dinfo->di_htmpfile = NULL;
++ 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;
+
-+#include <linux/byteorder/generic.h>
-+#include "aufs.h"
++ AuRwMustWriteLock(&a->di_rwsem);
++ AuRwMustWriteLock(&b->di_rwsem);
+
-+static void au_dr_hino_del(struct au_dr_br *dr, struct au_dr_hino *ent)
++#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)
+{
-+ int idx;
++ AuRwMustWriteLock(&dst->di_rwsem);
++ AuRwMustWriteLock(&src->di_rwsem);
+
-+ idx = au_dr_ihash(ent->dr_h_ino);
-+ au_hbl_del(&ent->dr_hnode, dr->dr_h_ino + idx);
++ 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(); */
+}
+
-+static int au_dr_hino_test_empty(struct au_dr_br *dr)
++int au_di_init(struct dentry *dentry)
+{
-+ int ret, i;
-+ struct hlist_bl_head *hbl;
++ int err;
++ struct super_block *sb;
++ struct au_dinfo *dinfo;
+
-+ 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);
-+ }
++ 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 ret;
++ return err;
+}
+
-+static struct au_dr_hino *au_dr_hino_find(struct au_dr_br *dr, ino_t ino)
++void au_di_fin(struct dentry *dentry)
+{
-+ 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);
++ struct au_dinfo *dinfo;
+
-+ return found;
++ dinfo = au_di(dentry);
++ AuRwDestroy(&dinfo->di_rwsem);
++ au_di_free(dinfo);
+}
+
-+int au_dr_hino_test_add(struct au_dr_br *dr, ino_t ino,
-+ struct au_dr_hino *add_ent)
++int au_di_realloc(struct au_dinfo *dinfo, int nbr, int may_shrink)
+{
-+ int found, idx;
-+ struct hlist_bl_head *hbl;
-+ struct hlist_bl_node *pos;
-+ struct au_dr_hino *ent;
++ int err, sz;
++ struct au_hdentry *hdp;
+
-+ found = 0;
-+ idx = au_dr_ihash(ino);
-+ hbl = dr->dr_h_ino + idx;
-+#if 0 /* debug print */
-+ {
-+ struct hlist_bl_node *tmp;
++ AuRwMustWriteLock(&dinfo->di_rwsem);
+
-+ hlist_bl_for_each_entry_safe(ent, pos, tmp, hbl, dr_hnode)
-+ AuDbg("hi%llu\n", (unsigned long long)ent->dr_h_ino);
++ 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;
+ }
-+#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 err;
++}
+
-+ return found;
++/* ---------------------------------------------------------------------- */
++
++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();
++ }
+}
+
-+void au_dr_hino_free(struct au_dr_br *dr)
++static void do_ii_read_lock(struct inode *inode, unsigned int lsc)
+{
-+ int i;
-+ struct hlist_bl_head *hbl;
-+ struct hlist_bl_node *pos, *tmp;
-+ struct au_dr_hino *ent;
++ 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();
++ }
++}
+
-+ /* SiMustWriteLock(sb); */
++void di_read_lock(struct dentry *d, int flags, unsigned int lsc)
++{
++ struct inode *inode;
+
-+ 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);
++ 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);
+ }
+}
+
-+/* 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)
++void di_read_unlock(struct dentry *d, int flags)
+{
-+ 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;
++ struct inode *inode;
+
-+ SiMustWriteLock(sb);
-+ AuDebugOn(!au_br_writable(br->br_perm));
++ 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);
++}
+
-+ hinoinode = file_inode(hinofile);
-+ oldsize = i_size_read(hinoinode);
++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);
++}
+
-+ 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;
++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);
++}
+
-+ /* 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);
++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);
+ }
++}
+
-+ AuTraceErr(err);
-+ return err;
++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);
++ }
+}
+
-+static int au_dr_hino_load(struct au_dr_br *dr, struct file *hinofile)
++void di_write_unlock2(struct dentry *d1, struct dentry *d2)
+{
-+ 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;
++ 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);
++}
+
-+ 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 */
++struct dentry *au_h_dptr(struct dentry *dentry, aufs_bindex_t bindex)
++{
++ struct dentry *d;
+
-+out_free:
-+ au_dr_hino_free(dr);
-+out:
-+ AuTraceErr(err);
-+ return err;
++ 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;
+}
+
+/*
-+ * @bindex/@br is a switch to distinguish whether suspending hnotify or not.
-+ * @path is a switch to distinguish load and store.
++ * extended version of au_h_dptr().
++ * returns a hashed and positive (or linkable) h_dentry in bindex, NULL, or
++ * error.
+ */
-+static int au_dr_hino(struct super_block *sb, aufs_bindex_t bindex,
-+ struct au_branch *br, const struct path *path)
++struct dentry *au_h_d_alias(struct dentry *dentry, aufs_bindex_t bindex)
+{
-+ 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);
++ struct dentry *h_dentry;
++ struct inode *inode, *h_inode;
+
-+ AuDebugOn(bindex < 0 && !br);
-+ AuDebugOn(bindex >= 0 && br);
++ AuDebugOn(d_really_is_negative(dentry));
+
-+ 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;
++ 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 */
+ }
+
-+ 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);
++ 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;
+ }
-+ hinopath.mnt = path->mnt;
-+ hinopath.dentry = vfsub_lkup_one(&hinoname, (struct path *)path);
-+ 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;
++ 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;
+ }
-+ flags = O_WRONLY;
-+ }
-+ 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;
++ 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;
+}
+
+/* ---------------------------------------------------------------------- */
+
-+static int au_dr_brid_init(struct au_dr_brid *brid, const struct path *path)
++void au_set_h_dptr(struct dentry *dentry, aufs_bindex_t bindex,
++ struct dentry *h_dentry)
+{
-+ 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;
++ struct au_dinfo *dinfo;
++ struct au_hdentry *hd;
++ struct au_branch *br;
+
-+ /* todo: support for UUID */
++ DiMustWriteLock(dentry);
+
-+ 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;
-+ }
++ 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;
+ }
-+
-+out:
-+ return err;
+}
+
-+int au_dr_br_init(struct super_block *sb, struct au_branch *br,
-+ const struct path *path)
++int au_dbrange_test(struct dentry *dentry)
+{
-+ 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;
++ int err;
++ aufs_bindex_t btop, bbot;
+
-+ if (au_opt_test(au_mntflags(sb), DIRREN))
-+ err = au_dr_hino(sb, /*bindex*/-1, br, path);
++ err = 0;
++ btop = au_dbtop(dentry);
++ bbot = au_dbbot(dentry);
++ if (btop >= 0)
++ AuDebugOn(bbot < 0 && btop > bbot);
++ else {
++ err = -EIO;
++ AuDebugOn(bbot >= 0);
++ }
+
-+out:
-+ AuTraceErr(err);
+ return err;
+}
+
-+int au_dr_br_fin(struct super_block *sb, struct au_branch *br)
++int au_digen_test(struct dentry *dentry, unsigned int sigen)
+{
+ 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);
++ 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 */
++}
+
-+static int au_brid_str(struct au_dr_brid *brid, struct inode *h_inode,
-+ char *buf, size_t sz)
++void au_update_dbrange(struct dentry *dentry, int do_put_zero)
+{
-+ int err;
-+ unsigned int major, minor;
-+ char *p;
++ struct au_dinfo *dinfo;
++ struct dentry *h_d;
++ struct au_hdentry *hdp;
++ aufs_bindex_t bindex, bbot;
+
-+ 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;
++ 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);
++ }
+ }
-+ 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;
++ 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);
+}
+
-+static int au_drinfo_name(struct au_branch *br, char *name, int len)
++void au_update_dbtop(struct dentry *dentry)
+{
-+ int rlen;
-+ struct dentry *br_dentry;
-+ struct inode *br_inode;
++ aufs_bindex_t bindex, bbot;
++ struct dentry *h_dentry;
+
-+ 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);
++ 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);
++ }
++}
+
-+ return rlen;
++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 -urN /usr/share/empty/fs/aufs/dir.c linux/fs/aufs/dir.c
+--- /usr/share/empty/fs/aufs/dir.c 1970-01-01 01:00:00.000000000 +0100
++++ linux/fs/aufs/dir.c 2024-03-10 23:40:47.083143450 +0100
+@@ -0,0 +1,767 @@
++// SPDX-License-Identifier: GPL-2.0
+/*
-+ * from the given @h_dentry, construct drinfo at @*fdata.
-+ * when the size of @*fdata is not enough, reallocate and return new @fdata and
-+ * @allocated.
++ * Copyright (C) 2005-2022 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/>.
+ */
-+static int au_drinfo_construct(struct au_drinfo_fdata **fdata,
-+ struct dentry *h_dentry,
-+ unsigned char *allocated)
++
++/*
++ * 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)
+{
-+ int err, v;
-+ struct au_drinfo_fdata *f, *p;
-+ struct au_drinfo *drinfo;
-+ struct inode *h_inode;
-+ struct qstr *qname;
++ unsigned int nlink;
+
-+ 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;
++ 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));
+ }
-+ 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);
++ 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 timespec64 ts;
++ 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);
++ ts = inode_get_mtime(h_dir);
++ if (h_dir->i_nlink
++ && timespec64_compare(&ts, &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:
-+ AuTraceErr(err);
-+ return err;
++ dput(a->dentry);
++ au_nwt_done(&au_sbi(sb)->si_nowait);
++ au_kfree_try_rcu(arg);
+}
+
-+/* callers have to free the return value */
-+static struct au_drinfo *au_drinfo_read_k(struct file *file, ino_t h_ino)
++void au_dir_ts(struct inode *dir, aufs_bindex_t bindex)
+{
-+ struct au_drinfo *ret, *drinfo;
-+ struct au_drinfo_fdata fdata;
-+ int len;
-+ loff_t pos;
-+ ssize_t ssz;
++ int perm, wkq_err;
++ aufs_bindex_t btop;
++ struct au_dir_ts_arg *arg;
++ struct dentry *dentry;
++ struct super_block *sb;
+
-+ 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);
++ 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;
+ }
+
-+ 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);
++ perm = au_sbr_perm(sb, btop);
++ if (!au_br_writable(perm))
+ goto out;
-+ }
+
-+ drinfo = &fdata.drinfo;
-+ len = drinfo->oldnamelen;
-+ if (!len) {
-+ AuIOErr("broken drinfo %pD2\n", file);
++ arg = kmalloc(sizeof(*arg), GFP_NOFS);
++ if (!arg)
+ 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 */
++ 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);
+ }
+
-+ ret = kmalloc(sizeof(*ret) + len, GFP_NOFS);
-+ if (unlikely(!ret)) {
-+ ret = ERR_PTR(-ENOMEM);
-+ AuTraceErrPtr(ret);
-+ goto out;
-+ }
++out:
++ dput(dentry);
++}
+
-+ *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;
++/* ---------------------------------------------------------------------- */
++
++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);
+ }
-+
-+ AuDbg("oldname %.*s\n", ret->oldnamelen, ret->oldname);
++ au_update_figen(file);
++ /* todo: necessary? */
++ /* file->f_ra = h_file->f_ra; */
++ err = 0;
+
+out:
-+ return ret;
++ 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;
+
-+/* in order to be revertible */
-+struct au_drinfo_rev_elm {
-+ int created;
-+ struct dentry *info_dentry;
-+ struct au_drinfo *info_last;
-+};
++ FiMustWriteLock(file);
++ AuDebugOn(h_file);
+
-+struct au_drinfo_rev {
-+ unsigned char already;
-+ aufs_bindex_t nelm;
-+ struct au_drinfo_rev_elm elm[];
-+};
++ 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;
+
-+/* 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 */
-+};
++ 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 */
+
-+/* 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;
++ /* 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);
+
-+ AuDebugOn(elm
-+ && memcmp(elm, page_address(ZERO_PAGE(0)), sizeof(*elm)));
++ return err;
++}
+
-+ infopath.dentry = vfsub_lookup_one_len(w->whname, &w->h_ppath,
-+ w->whnamelen);
-+ AuTraceErrPtr(infopath.dentry);
-+ if (IS_ERR(infopath.dentry)) {
-+ err = PTR_ERR(infopath.dentry);
-+ goto out;
-+ }
++static int aufs_open_dir(struct inode *inode __maybe_unused,
++ struct file *file)
++{
++ int err;
++ struct super_block *sb;
++ struct au_fidir *fidir;
+
-+ 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);
++ 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))
-+ goto out_dput;
-+ elm->created = 1;
-+ elm->info_dentry = dget(infopath.dentry);
++ au_kfree_rcu(fidir);
+ }
++ si_read_unlock(sb);
++ return err;
++}
+
-+ infofile = vfsub_dentry_open(&infopath, O_RDWR);
-+ AuTraceErrPtr(infofile);
-+ if (IS_ERR(infofile)) {
-+ err = PTR_ERR(infofile);
-+ goto out_dput;
-+ }
++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;
+
-+ 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;
++ 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;
++}
+
-+ 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 */
-+ }
++static int au_do_flush_dir(struct file *file, fl_owner_t id)
++{
++ int err;
++ aufs_bindex_t bindex, bbot;
++ struct file *h_file;
+
-+out_fput:
-+ fput(infofile);
-+out_dput:
-+ dput(infopath.dentry);
-+out:
-+ AuTraceErr(err);
++ 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;
+}
+
-+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)
++static int aufs_flush_dir(struct file *file, fl_owner_t id)
+{
-+ struct au_call_drinfo_do_store_args *a = args;
-+
-+ *a->errp = au_drinfo_do_store(a->w, a->elm);
++ return au_do_flush(file, id, au_do_flush_dir);
+}
+
-+static int au_drinfo_store_sio(struct au_drinfo_store *w,
-+ struct au_drinfo_rev_elm *elm)
++/* ---------------------------------------------------------------------- */
++
++static int au_do_fsync_dir_no_file(struct dentry *dentry, int datasync)
+{
-+ int err, wkq_err;
++ int err;
++ aufs_bindex_t bbot, bindex;
++ struct inode *inode;
++ struct super_block *sb;
+
-+ 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;
++ 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);
+ }
-+ AuTraceErr(err);
+
+ return err;
+}
+
-+static int au_drinfo_store_work_init(struct au_drinfo_store *w,
-+ aufs_bindex_t btgt)
++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;
+
-+ memset(w, 0, sizeof(*w));
-+ w->allocated = roundup_pow_of_two(sizeof(*w->fdata) + 40);
-+ strscpy(w->whname, AUFS_WH_DR_INFO_PFX, sizeof(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);
++ 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);
+ }
-+ 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)
++/*
++ * @file may be NULL
++ */
++static int aufs_fsync_dir(struct file *file, loff_t start, loff_t end,
++ int datasync)
+{
-+ 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);
++ int err;
++ struct dentry *dentry;
++ struct inode *inode;
++ struct super_block *sb;
+
+ 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 */
++ 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;
+}
+
-+/* 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)
++/* ---------------------------------------------------------------------- */
++
++static int aufs_iterate_shared(struct file *file, struct dir_context *ctx)
+{
-+ 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;
++ int err;
++ struct dentry *dentry;
++ struct inode *inode, *h_inode;
+ struct super_block *sb;
-+ struct au_branch *br;
-+ struct au_hinode *hdir;
+
-+ err = au_drinfo_store_work_init(&work, btgt);
-+ AuTraceErr(err);
++ 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);
+
-+ 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;
++ return err;
+ }
-+ 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;
++out_unlock:
++ di_read_unlock(dentry, AuLock_IR);
++ fi_write_unlock(file);
++out:
++ si_read_unlock(sb);
++ return err;
++}
+
-+ 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);
++#define AuTestEmpty_WHONLY BIT(0)
++#define AuTestEmpty_CALLED BIT(1)
++#define AuTestEmpty_SHWH BIT(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)
+
-+ 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;
++#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 bool 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;
+ }
-+ au_hn_inode_unlock(hdir);
+
-+out_args:
-+ au_drinfo_store_work_fin(&work);
++ 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:
-+ return err;
++ /* smp_mb(); */
++ AuTraceErr(arg->err);
++ return !arg->err;
+}
+
-+/* ---------------------------------------------------------------------- */
-+
-+int au_dr_rename(struct dentry *src, aufs_bindex_t bindex,
-+ struct qstr *dst_name, void *_rev)
++static int do_test_empty(struct dentry *dentry, struct test_empty_arg *arg)
+{
-+ int err, already;
-+ ino_t ino;
-+ struct super_block *sb;
++ int err;
++ struct file *h_file;
+ 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))
++ 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;
+
-+ 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 */
-+ }
++ err = 0;
++ if (!au_opt_test(au_mntflags(dentry->d_sb), UDBA_NONE)
++ && !file_inode(h_file)->i_nlink)
++ goto out_put;
+
-+ /* revert */
-+ if (!already)
-+ au_dr_hino_del(dr, ent);
-+ au_kfree_rcu(ent);
++ 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:
-+ AuTraceErr(err);
+ return err;
+}
+
-+void au_dr_rename_fin(struct dentry *src, aufs_bindex_t btgt, void *_rev)
++struct do_test_empty_args {
++ int *errp;
++ struct dentry *dentry;
++ struct test_empty_arg *arg;
++};
++
++static void call_do_test_empty(void *args)
+{
-+ struct au_drinfo_rev *rev;
-+ struct au_drinfo_rev_elm *elm;
-+ int nelm;
++ struct do_test_empty_args *a = args;
++ *a->errp = do_test_empty(a->dentry, a->arg);
++}
+
-+ rev = _rev;
-+ elm = rev->elm;
-+ for (nelm = rev->nelm; nelm > 0; nelm--, elm++) {
-+ dput(elm->info_dentry);
-+ au_kfree_rcu(elm->info_last);
++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;
++ struct mnt_idmap *h_idmap;
++
++ h_idmap = au_sbr_idmap(dentry->d_sb, arg->bindex);
++ 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_idmap, 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;
+ }
-+ au_kfree_try_rcu(rev);
++
++ return err;
+}
+
-+void au_dr_rename_rev(struct dentry *src, aufs_bindex_t btgt, void *_rev)
++int au_test_empty_lower(struct dentry *dentry)
+{
+ 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;
++ 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);
+
-+ err = au_drinfo_store_work_init(&work, btgt);
++ 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;
+
-+ 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;
++ 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;
+
-+ 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);
++ 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:
-+ au_kfree_try_rcu(rev);
-+ if (unlikely(err))
-+ pr_err("failed to remove dirren info\n");
++ return err;
+}
+
-+/* ---------------------------------------------------------------------- */
-+
-+static struct au_drinfo *au_drinfo_do_load(struct path *h_ppath,
-+ char *whname, int whnamelen,
-+ struct dentry **info_dentry)
++int au_test_empty(struct dentry *dentry, struct au_nhash *whlist)
+{
-+ struct au_drinfo *drinfo;
-+ struct file *f;
-+ struct inode *h_dir;
-+ struct path infopath;
-+ int unlocked;
++ int err;
++ struct test_empty_arg arg = {
++ .ctx = {
++ .actor = test_empty_cb
++ }
++ };
++ aufs_bindex_t bindex, btail;
+
-+ AuDbg("%pd/%.*s\n", h_ppath->dentry, whnamelen, whname);
++ 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;
+
-+ *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, whnamelen);
-+ if (IS_ERR(infopath.dentry)) {
-+ drinfo = (void *)infopath.dentry;
-+ goto out;
++ h_dentry = au_h_dptr(dentry, bindex);
++ if (h_dentry && d_is_positive(h_dentry)) {
++ arg.bindex = bindex;
++ err = sio_test_empty(dentry, &arg);
++ }
+ }
+
-+ if (d_is_negative(infopath.dentry))
-+ goto out_dput; /* success */
++ return err;
++}
+
-+ 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;
++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 -urN /usr/share/empty/fs/aufs/dir.h linux/fs/aufs/dir.h
+--- /usr/share/empty/fs/aufs/dir.h 1970-01-01 01:00:00.000000000 +0100
++++ linux/fs/aufs/dir.h 2022-11-05 23:02:18.962555950 +0100
+@@ -0,0 +1,134 @@
++/* SPDX-License-Identifier: GPL-2.0 */
++/*
++ * Copyright (C) 2005-2022 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/>.
++ */
+
-+ AuDbg("oldname %.*s\n", drinfo->oldnamelen, drinfo->oldname);
-+ *info_dentry = dget(infopath.dentry); /* keep it alive */
++/*
++ * directory operations
++ */
+
-+out_fput:
-+ fput(f);
-+out_dput:
-+ dput(infopath.dentry);
-+out:
-+ if (!unlocked)
-+ inode_unlock_shared(h_dir);
-+ AuTraceErrPtr(drinfo);
-+ return drinfo;
-+}
++#ifndef __AUFS_DIR_H__
++#define __AUFS_DIR_H__
+
-+struct au_drinfo_do_load_args {
-+ struct au_drinfo **drinfop;
-+ struct path *h_ppath;
-+ char *whname;
-+ int whnamelen;
-+ struct dentry **info_dentry;
-+};
++#ifdef __KERNEL__
+
-+static void au_call_drinfo_do_load(void *args)
-+{
-+ struct au_drinfo_do_load_args *a = args;
++#include <linux/fs.h>
+
-+ *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;
++/* need to be faster and smaller */
+
-+ aufs_bindex_t ninfo;
-+ struct au_drinfo **drinfo;
++struct au_nhash {
++ unsigned int nh_num;
++ struct hlist_head *nh_head;
+};
+
-+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;
++struct au_vdir_destr {
++ unsigned char len;
++ unsigned char name[];
++} __packed;
+
-+ 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;
++struct au_vdir_dehstr {
++ struct hlist_node hash;
++ struct au_vdir_destr *str;
++ struct rcu_head rcu;
++} ____cacheline_aligned_in_smp;
+
-+ 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;
++struct au_vdir_de {
++ ino_t de_ino;
++ unsigned char de_type;
++ /* caution: packed */
++ struct au_vdir_destr de_str;
++} __packed;
+
-+ 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);
++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;
+
-+out:
-+ AuTraceErr(err);
-+ return err;
-+}
++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;
+
+/* ---------------------------------------------------------------------- */
+
-+static void au_dr_lkup_free(struct au_drinfo **drinfo, int n)
-+{
-+ struct au_drinfo **p = drinfo;
++/* 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);
+
-+ while (n-- > 0)
-+ au_kfree_rcu(*drinfo++);
-+ au_kfree_try_rcu(p);
-+}
++/* 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);
+
-+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;
++/* 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 -urN /usr/share/empty/fs/aufs/dirren.c linux/fs/aufs/dirren.c
+--- /usr/share/empty/fs/aufs/dirren.c 1970-01-01 01:00:00.000000000 +0100
++++ linux/fs/aufs/dirren.c 2023-10-10 22:51:18.033248030 +0200
+@@ -0,0 +1,1315 @@
++// SPDX-License-Identifier: GPL-2.0
++/*
++ * Copyright (C) 2017-2022 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/>.
++ */
+
-+ AuDbg("%.*s, name %.*s, whname %.*s, b%d\n",
-+ AuLNPair(&dentry->d_name), AuLNPair(&lkup->dirren.dr_name),
-+ AuLNPair(&lkup->whname), btgt);
++/*
++ * special handling in renaming a directory
++ * in order to support looking-up the before-renamed name on the lower readonly
++ * branches
++ */
+
-+ 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;
++#include <linux/byteorder/generic.h>
++#include "aufs.h"
+
-+ 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 */
++static void au_dr_hino_del(struct au_dr_br *dr, struct au_dr_hino *ent)
++{
++ int idx;
+
-+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;
++ idx = au_dr_ihash(ent->dr_h_ino);
++ au_hbl_del(&ent->dr_hnode, dr->dr_h_ino + idx);
+}
+
-+void au_dr_lkup_fin(struct au_do_lookup_args *lkup)
++static int au_dr_hino_test_empty(struct au_dr_br *dr)
+{
-+ au_dr_lkup_free(lkup->dirren.drinfo, lkup->dirren.ninfo);
++ 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;
+}
+
-+int au_dr_lkup_name(struct au_do_lookup_args *lkup, aufs_bindex_t btgt)
++static struct au_dr_hino *au_dr_hino_find(struct au_dr_br *dr, ino_t ino)
+{
-+ int err;
-+ struct au_drinfo *drinfo;
-+
-+ err = 0;
-+ if (!lkup->dirren.drinfo)
-+ goto out;
-+ AuDebugOn(lkup->dirren.ninfo <= btgt);
-+ drinfo = lkup->dirren.drinfo[btgt];
-+ if (!drinfo)
-+ goto out;
++ struct au_dr_hino *found, *ent;
++ struct hlist_bl_head *hbl;
++ struct hlist_bl_node *pos;
++ int idx;
+
-+ 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);
++ 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);
+
-+out:
-+ AuTraceErr(err);
-+ return err;
++ return found;
+}
+
-+int au_dr_lkup_h_ino(struct au_do_lookup_args *lkup, aufs_bindex_t bindex,
-+ ino_t h_ino)
++int au_dr_hino_test_add(struct au_dr_br *dr, ino_t ino,
++ struct au_dr_hino *add_ent)
+{
-+ int match;
-+ struct au_drinfo *drinfo;
++ int found, idx;
++ struct hlist_bl_head *hbl;
++ struct hlist_bl_node *pos;
++ struct au_dr_hino *ent;
+
-+ match = 1;
-+ if (!lkup->dirren.drinfo)
-+ goto out;
-+ AuDebugOn(lkup->dirren.ninfo <= bindex);
-+ drinfo = lkup->dirren.drinfo[bindex];
-+ if (!drinfo)
-+ goto out;
++ found = 0;
++ idx = au_dr_ihash(ino);
++ hbl = dr->dr_h_ino + idx;
++#if 0 /* debug print */
++ {
++ struct hlist_bl_node *tmp;
+
-+ match = (drinfo->ino == h_ino);
-+ AuDbg("match %d\n", match);
++ 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);
+
-+out:
-+ return match;
-+}
++ if (!found && add_ent)
++ AuDbg("i%llu added\n", (unsigned long long)add_ent->dr_h_ino);
+
-+/* ---------------------------------------------------------------------- */
++ return found;
++}
+
-+int au_dr_opt_set(struct super_block *sb)
++void au_dr_hino_free(struct au_dr_br *dr)
+{
-+ int err;
-+ aufs_bindex_t bindex, bbot;
-+ struct au_branch *br;
++ int i;
++ struct hlist_bl_head *hbl;
++ struct hlist_bl_node *pos, *tmp;
++ struct au_dr_hino *ent;
+
-+ 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);
-+ }
++ /* SiMustWriteLock(sb); */
+
-+ return err;
++ 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);
++ }
+}
+
-+int au_dr_opt_flush(struct super_block *sb)
++/* 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;
-+ aufs_bindex_t bindex, bbot;
-+ struct au_branch *br;
++ 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;
-+ 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);
++ 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;
+}
+
-+int au_dr_opt_clr(struct super_block *sb, int no_flush)
++static int au_dr_hino_load(struct au_dr_br *dr, struct file *hinofile)
+{
-+ int err;
-+ aufs_bindex_t bindex, bbot;
-+ struct au_branch *br;
++ 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;
-+ if (!no_flush) {
-+ err = au_dr_opt_flush(sb);
-+ if (unlikely(err))
-+ goto out;
-+ }
++ 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;
++ }
+
-+ bbot = au_sbbot(sb);
-+ for (bindex = 0; bindex <= bbot; bindex++) {
-+ br = au_sbr(sb, bindex);
-+ au_dr_hino_free(&br->br_dirren);
++ 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;
+}
-diff --git a/fs/aufs/dirren.h b/fs/aufs/dirren.h
-new file mode 100644
-index 00000000000000..d2d57d95a77ecc
---- /dev/null
-+++ b/fs/aufs/dirren.h
-@@ -0,0 +1,140 @@
-+/* SPDX-License-Identifier: GPL-2.0 */
-+/*
-+ * Copyright (C) 2017-2022 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/>.
-+ */
+
+/*
-+ * renamed dir info
++ * @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);
+
-+#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
-+};
++ AuDebugOn(bindex < 0 && !br);
++ AuDebugOn(bindex >= 0 && br);
+
-+struct au_dr_brid {
-+ enum au_brid_type type;
-+ union {
-+ uuid_t uuid; /* unimplemented yet */
-+ fsid_t fsid;
-+ dev_t dev;
-+ };
-+};
++ 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;
++ }
+
-+/* 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)
++ 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.mnt = path->mnt;
++ hinopath.dentry = vfsub_lkup_one(&hinoname, (struct path *)path);
++ err = PTR_ERR(hinopath.dentry);
++ if (IS_ERR(hinopath.dentry))
++ goto out_unlock;
+
-+struct au_dr_hino {
-+ struct hlist_bl_node dr_hnode;
-+ ino_t dr_h_ino;
-+};
++ 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;
++ }
++ 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;
++ }
+
-+struct au_dr_br {
-+ struct hlist_bl_head dr_h_ino[AuDirren_NHASH];
-+ struct au_dr_brid dr_brid;
-+};
++ if (load)
++ err = au_dr_hino_load(&br->br_dirren, hinofile);
++ else
++ err = au_dr_hino_store(sb, br, hinofile);
++ fput(hinofile);
++ goto out;
+
-+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
++out_dput:
++ dput(hinopath.dentry);
++out_unlock:
++ if (suspend)
++ au_hn_inode_unlock(hdir);
++ else
++ inode_unlock(dir);
++out:
++ AuTraceErr(err);
++ return err;
++}
+
+/* ---------------------------------------------------------------------- */
+
-+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
++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 */
+
-+#ifdef CONFIG_AUFS_DIRREN
-+static inline int au_dr_ihash(ino_t h_ino)
-+{
-+ return h_ino % AuDirren_NHASH;
++ 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;
+}
-+#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 00000000000000..54fd16ecb6d340
---- /dev/null
-+++ b/fs/aufs/dynop.c
-@@ -0,0 +1,366 @@
-+// SPDX-License-Identifier: GPL-2.0
-+/*
-+ * Copyright (C) 2010-2022 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/>.
-+ */
++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;
+
-+/*
-+ * dynamically customizable operations for regular files
-+ */
++ dr = &br->br_dirren;
++ hbl = dr->dr_h_ino;
++ for (i = 0; i < AuDirren_NHASH; i++, hbl++)
++ INIT_HLIST_BL_HEAD(hbl);
+
-+#include "aufs.h"
++ err = au_dr_brid_init(&dr->dr_brid, path);
++ if (unlikely(err))
++ goto out;
+
-+#define DyPrSym(key) AuDbgSym(key->dk_op.dy_hop)
++ if (au_opt_test(au_mntflags(sb), DIRREN))
++ err = au_dr_hino(sb, /*bindex*/-1, br, path);
+
-+/*
-+ * 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];
++out:
++ AuTraceErr(err);
++ return err;
++}
+
-+static struct au_dykey *dy_gfind_get(struct hlist_bl_head *hbl,
-+ const void *h_op)
++int au_dr_br_fin(struct super_block *sb, struct au_branch *br)
+{
-+ struct au_dykey *key, *tmp;
-+ struct hlist_bl_node *pos;
++ int err;
+
-+ 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);
++ 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 key;
++ return err;
+}
+
-+static struct au_dykey *dy_bradd(struct au_branch *br, struct au_dykey *key)
++/* ---------------------------------------------------------------------- */
++
++static int au_brid_str(struct au_dr_brid *brid, struct inode *h_inode,
++ char *buf, size_t sz)
+{
-+ struct au_dykey **k, *found;
-+ const void *h_op = key->dk_op.dy_hop;
-+ int i;
++ int err;
++ unsigned int major, minor;
++ char *p;
+
-+ 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 */
++ 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 found;
++ return p - buf;
+}
+
-+/* kref_get() if @key is already added */
-+static struct au_dykey *dy_gadd(struct hlist_bl_head *hbl, struct au_dykey *key)
++static int au_drinfo_name(struct au_branch *br, char *name, int len)
+{
-+ struct au_dykey *tmp, *found;
-+ struct hlist_bl_node *pos;
-+ const void *h_op = key->dk_op.dy_hop;
++ int rlen;
++ struct dentry *br_dentry;
++ struct inode *br_inode;
+
-+ 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);
++ 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);
+
-+ if (!found)
-+ DyPrSym(key);
-+ return found;
++ return rlen;
+}
+
-+static void dy_free_rcu(struct rcu_head *rcu)
++/* ---------------------------------------------------------------------- */
++
++/*
++ * 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)
+{
-+ struct au_dykey *key;
++ int err, v;
++ struct au_drinfo_fdata *f, *p;
++ struct au_drinfo *drinfo;
++ struct inode *h_inode;
++ struct qstr *qname;
+
-+ key = container_of(rcu, struct au_dykey, dk_rcu);
-+ DyPrSym(key);
-+ kfree(key);
++ 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;
+}
+
-+static void dy_free(struct kref *kref)
++/* callers have to free the return value */
++static struct au_drinfo *au_drinfo_read_k(struct file *file, ino_t h_ino)
+{
-+ struct au_dykey *key;
-+ struct hlist_bl_head *hbl;
++ struct au_drinfo *ret, *drinfo;
++ struct au_drinfo_fdata fdata;
++ int len;
++ loff_t pos;
++ ssize_t ssz;
+
-+ 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);
-+}
++ 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;
++ }
+
-+void au_dy_put(struct au_dykey *key)
-+{
-+ kref_put(&key->dk_kref, dy_free);
++ 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;
+}
+
+/* ---------------------------------------------------------------------- */
+
-+#define DyDbgSize(cnt, op) AuDebugOn(cnt != sizeof(op)/sizeof(void *))
++/* in order to be revertible */
++struct au_drinfo_rev_elm {
++ int created;
++ struct dentry *info_dentry;
++ struct au_drinfo *info_last;
++};
+
-+#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
++struct au_drinfo_rev {
++ unsigned char already;
++ aufs_bindex_t nelm;
++ struct au_drinfo_rev_elm elm[];
++};
+
-+#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)
++/* 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 */
++};
+
-+#define DySetForce(func, dst, src) do { \
-+ AuDebugOn(!src.func); \
-+ DyDbgInc(cnt); \
-+ dst.func = src.func; \
-+} while (0)
++/* 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;
+
-+#define DySetAop(func) \
-+ DySet(func, dyaop->da_op, aufs_aop, h_aop, h_sb)
-+#define DySetAopForce(func) \
-+ DySetForce(func, dyaop->da_op, aufs_aop)
++ AuDebugOn(elm
++ && memcmp(elm, page_address(ZERO_PAGE(0)), sizeof(*elm)));
+
-+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);
++ infopath.dentry = vfsub_lookup_one_len(w->whname, &w->h_ppath,
++ w->whnamelen);
++ AuTraceErrPtr(infopath.dentry);
++ if (IS_ERR(infopath.dentry)) {
++ err = PTR_ERR(infopath.dentry);
++ goto out;
++ }
+
-+ AuDbg("%s\n", au_sbtype(h_sb));
++ 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);
++ }
+
-+ DySetAop(writepage);
-+ DySetAopForce(read_folio); /* force */
-+ DySetAop(writepages);
-+ DySetAop(dirty_folio);
-+ DySetAop(invalidate_folio);
-+ DySetAop(readahead);
-+ DySetAop(write_begin);
-+ DySetAop(write_end);
-+ DySetAop(bmap);
-+ DySetAop(release_folio);
-+ DySetAop(free_folio);
-+ /* this one will be changed according to an aufs mount option */
-+ DySetAop(direct_IO);
-+ DySetAop(migrate_folio);
-+ DySetAop(launder_folio);
-+ DySetAop(is_partially_uptodate);
-+ DySetAop(is_dirty_writeback);
-+ DySetAop(error_remove_page);
-+ DySetAop(swap_activate);
-+ DySetAop(swap_deactivate);
-+ DySetAop(swap_rw);
++ infofile = vfsub_dentry_open(&infopath, O_RDWR);
++ AuTraceErrPtr(infofile);
++ if (IS_ERR(infofile)) {
++ err = PTR_ERR(infofile);
++ goto out_dput;
++ }
+
-+ DyDbgSize(cnt, *h_aop);
++ 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);
+
-+static void dy_bug(struct kref *kref)
-+{
-+ BUG();
++ return err;
+}
+
-+static struct au_dykey *dy_get(struct au_dynop *op, struct au_branch *br)
++static int au_drinfo_store_work_init(struct au_drinfo_store *w,
++ aufs_bindex_t btgt)
+{
-+ 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;
++ int err;
+
-+ hbl = dynop + op->dy_type;
-+ key = dy_gfind_get(hbl, op->dy_hop);
-+ if (key)
-+ goto out_add; /* success */
++ memset(w, 0, sizeof(*w));
++ w->allocated = roundup_pow_of_two(sizeof(*w->fdata) + 40);
++ strscpy(w->whname, AUFS_WH_DR_INFO_PFX, sizeof(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);
+
-+ p = a + op->dy_type;
-+ key = kzalloc(p->sz, GFP_NOFS);
-+ if (unlikely(!key)) {
-+ key = ERR_PTR(-ENOMEM);
++ 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;
+
-+ 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;
++ return err;
+}
+
-+/* ---------------------------------------------------------------------- */
-+/*
-+ * 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)
++static void au_drinfo_store_work_fin(struct au_drinfo_store *w)
+{
-+ if (!do_dx)
-+ dyaop->da_op.direct_IO = NULL;
-+ else
-+ dyaop->da_op.direct_IO = aufs_aop.direct_IO;
++ au_kfree_rcu(w->fdata);
+}
+
-+static struct au_dyaop *dy_aget(struct au_branch *br,
-+ const struct address_space_operations *h_aop,
-+ int do_dx)
++static void au_drinfo_store_rev(struct au_drinfo_rev *rev,
++ struct au_drinfo_store *w)
+{
-+ struct au_dyaop *dyaop;
-+ struct au_dynop op;
++ struct au_drinfo_rev_elm *elm;
++ struct inode *h_dir, *delegated;
++ int err, nelm;
++ struct path infopath = {
++ .mnt = w->h_ppath.mnt
++ };
+
-+ 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);
++ h_dir = d_inode(w->h_ppath.dentry);
++ IMustLock(h_dir);
+
-+out:
-+ return dyaop;
++ 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 */
++ }
+}
+
-+int au_dy_iaop(struct inode *inode, aufs_bindex_t bindex,
-+ struct inode *h_inode)
++/* 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, do_dx;
++ 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_dyaop *dyaop;
-+
-+ AuDebugOn(!S_ISREG(h_inode->i_mode));
-+ IiMustWriteLock(inode);
++ struct au_hinode *hdir;
+
-+ 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() */
++ 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;
-+ inode->i_mapping->a_ops = &dyaop->da_op;
++ 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;
+}
+
-+/*
-+ * 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 au_dr_rename(struct dentry *src, aufs_bindex_t bindex,
++ struct qstr *dst_name, void *_rev)
+{
-+ int err;
-+ aufs_bindex_t btop;
++ 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;
+
-+ 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;
-+}
++ AuDbg("bindex %d\n", bindex);
+
-+void au_dy_arefresh(int do_dx)
-+{
-+ struct hlist_bl_head *hbl;
-+ struct hlist_bl_node *pos;
-+ struct au_dykey *key;
++ err = -ENOMEM;
++ ent = kmalloc(sizeof(*ent), GFP_NOFS);
++ if (unlikely(!ent))
++ goto out;
+
-+ 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);
-+}
++ 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 */
++ }
+
-+void __init au_dy_init(void)
-+{
-+ int i;
++ /* revert */
++ if (!already)
++ au_dr_hino_del(dr, ent);
++ au_kfree_rcu(ent);
+
-+ for (i = 0; i < AuDyLast; i++)
-+ INIT_HLIST_BL_HEAD(dynop + i);
++out:
++ AuTraceErr(err);
++ return err;
+}
+
-+void au_dy_fin(void)
++void au_dr_rename_fin(struct dentry *src, aufs_bindex_t btgt, void *_rev)
+{
-+ int i;
++ struct au_drinfo_rev *rev;
++ struct au_drinfo_rev_elm *elm;
++ int nelm;
+
-+ for (i = 0; i < AuDyLast; i++)
-+ WARN_ON(!hlist_bl_empty(dynop + i));
++ 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);
+}
-diff --git a/fs/aufs/dynop.h b/fs/aufs/dynop.h
-new file mode 100644
-index 00000000000000..60d89364b67600
---- /dev/null
-+++ b/fs/aufs/dynop.h
-@@ -0,0 +1,77 @@
-+/* SPDX-License-Identifier: GPL-2.0 */
-+/*
-+ * Copyright (C) 2010-2022 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 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};
++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;
+
-+struct au_dynop {
-+ int dy_type;
-+ union {
-+ const void *dy_hop;
-+ const struct address_space_operations *dy_haop;
-+ };
-+};
++ err = au_drinfo_store_work_init(&work, btgt);
++ if (unlikely(err))
++ goto out;
+
-+struct au_dykey {
-+ union {
-+ struct hlist_bl_node dk_hnode;
-+ struct rcu_head dk_rcu;
-+ };
-+ struct au_dynop dk_op;
++ 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;
+
-+ /*
-+ * during I am in the branch local array, kref is gotten. when the
-+ * branch is removed, kref is put.
-+ */
-+ struct kref dk_kref;
-+};
++ 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);
+
-+/* 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));
++out:
++ au_kfree_try_rcu(rev);
++ if (unlikely(err))
++ pr_err("failed to remove dirren info\n");
++}
+
+/* ---------------------------------------------------------------------- */
+
-+/* 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 00000000000000..4c639e5d40f6bf
---- /dev/null
-+++ b/fs/aufs/export.c
-@@ -0,0 +1,830 @@
-+// SPDX-License-Identifier: GPL-2.0
-+/*
-+ * Copyright (C) 2005-2022 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 via nfs
-+ */
++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;
+
-+#include <linux/exportfs.h>
-+#include <linux/fs_struct.h>
-+#include <linux/nsproxy.h>
-+#include <linux/random.h>
-+#include <linux/writeback.h>
-+#include "aufs.h"
++ AuDbg("%pd/%.*s\n", h_ppath->dentry, whnamelen, whname);
+
-+union conv {
-+#ifdef CONFIG_AUFS_INO_T_64
-+ __u32 a[2];
-+#else
-+ __u32 a[1];
-+#endif
-+ ino_t ino;
-+};
++ *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, whnamelen);
++ if (IS_ERR(infopath.dentry)) {
++ drinfo = (void *)infopath.dentry;
++ goto out;
++ }
+
-+static ino_t decode_ino(__u32 *a)
-+{
-+ union conv u;
++ if (d_is_negative(infopath.dentry))
++ goto out_dput; /* success */
+
-+ 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;
-+}
++ 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;
++ }
+
-+static void encode_ino(__u32 *a, ino_t ino)
-+{
-+ union conv u;
++ drinfo = au_drinfo_read_k(f, /*h_ino*/0);
++ if (IS_ERR_OR_NULL(drinfo))
++ goto out_fput;
+
-+ u.ino = ino;
-+ a[0] = u.a[0];
-+#ifdef CONFIG_AUFS_INO_T_64
-+ a[1] = u.a[1];
-+#endif
-+}
++ AuDbg("oldname %.*s\n", drinfo->oldnamelen, drinfo->oldname);
++ *info_dentry = dget(infopath.dentry); /* keep it alive */
+
-+/* 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,
++out_fput:
++ fput(f);
++out_dput:
++ dput(infopath.dentry);
++out:
++ if (!unlocked)
++ inode_unlock_shared(h_dir);
++ AuTraceErrPtr(drinfo);
++ return drinfo;
++}
+
-+ Fh_ino = Fh_ino1,
-+ Fh_dir_ino = Fh_dir_ino1
++struct au_drinfo_do_load_args {
++ struct au_drinfo **drinfop;
++ struct path *h_ppath;
++ char *whname;
++ int whnamelen;
++ struct dentry **info_dentry;
+};
+
-+static int au_test_anon(struct dentry *dentry)
++static void au_call_drinfo_do_load(void *args)
+{
-+ /* note: read d_flags without d_lock */
-+ return !!(dentry->d_flags & DCACHE_DISCONNECTED);
++ struct au_drinfo_do_load_args *a = args;
++
++ *a->drinfop = au_drinfo_do_load(a->h_ppath, a->whname, a->whnamelen,
++ a->info_dentry);
+}
+
-+int au_test_nfsd(void)
++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 ret;
-+ struct task_struct *tsk = current;
-+ char comm[sizeof(tsk->comm)];
++ 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;
+
-+ ret = 0;
-+ if (tsk->flags & PF_KTHREAD) {
-+ get_task_comm(comm, tsk);
-+ ret = !strcmp(comm, "nfsd");
++ 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;
+
-+ return ret;
++ 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;
+}
+
+/* ---------------------------------------------------------------------- */
-+/* inode generation external table */
+
-+void au_xigen_inc(struct inode *inode)
++static void au_dr_lkup_free(struct au_drinfo **drinfo, int n)
+{
-+ 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_xigen, &igen, sizeof(igen), &pos);
-+ if (sz == sizeof(igen))
-+ return; /* success */
++ struct au_drinfo **p = drinfo;
+
-+ if (unlikely(sz >= 0))
-+ AuIOErr("xigen error (%zd)\n", sz);
++ while (n-- > 0)
++ au_kfree_rcu(*drinfo++);
++ au_kfree_try_rcu(p);
+}
+
-+int au_xigen_new(struct inode *inode)
++int au_dr_lkup(struct au_do_lookup_args *lkup, struct dentry *dentry,
++ aufs_bindex_t btgt)
+{
-+ int err;
-+ loff_t pos;
-+ ssize_t sz;
++ 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;
-+ 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;
++ AuDbg("%.*s, name %.*s, whname %.*s, b%d\n",
++ AuLNPair(&dentry->d_name), AuLNPair(&lkup->dirren.dr_name),
++ AuLNPair(&lkup->whname), btgt);
+
-+ 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;
++ 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;
+ }
-+ 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(file, &inode->i_generation,
-+ sizeof(inode->i_generation), &pos);
-+ } else
-+ sz = xino_fread(file, &inode->i_generation,
-+ sizeof(inode->i_generation), &pos);
-+ if (sz == sizeof(inode->i_generation))
-+ goto out; /* success */
++ 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;
+
-+ err = sz;
-+ if (unlikely(sz >= 0)) {
-+ err = -EIO;
-+ AuIOErr("xigen error (%zd)\n", sz);
++ 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;
+}
+
-+int au_xigen_set(struct super_block *sb, struct path *path)
++void au_dr_lkup_fin(struct au_do_lookup_args *lkup)
+{
-+ int err;
-+ struct au_sbinfo *sbinfo;
-+ struct file *file;
++ au_dr_lkup_free(lkup->dirren.drinfo, lkup->dirren.ninfo);
++}
+
-+ SiMustWriteLock(sb);
++int au_dr_lkup_name(struct au_do_lookup_args *lkup, aufs_bindex_t btgt)
++{
++ int err;
++ struct au_drinfo *drinfo;
+
-+ 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;
++ if (!lkup->dirren.drinfo)
++ goto out;
++ AuDebugOn(lkup->dirren.ninfo <= btgt);
++ drinfo = lkup->dirren.drinfo[btgt];
++ 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;
+}
+
-+void au_xigen_clr(struct super_block *sb)
++int au_dr_lkup_h_ino(struct au_do_lookup_args *lkup, aufs_bindex_t bindex,
++ ino_t h_ino)
+{
-+ struct au_sbinfo *sbinfo;
++ int match;
++ struct au_drinfo *drinfo;
+
-+ SiMustWriteLock(sb);
++ match = 1;
++ if (!lkup->dirren.drinfo)
++ goto out;
++ AuDebugOn(lkup->dirren.ninfo <= bindex);
++ drinfo = lkup->dirren.drinfo[bindex];
++ if (!drinfo)
++ goto out;
+
-+ sbinfo = au_sbi(sb);
-+ if (sbinfo->si_xigen) {
-+ fput(sbinfo->si_xigen);
-+ sbinfo->si_xigen = NULL;
-+ }
++ match = (drinfo->ino == h_ino);
++ AuDbg("match %d\n", match);
++
++out:
++ return match;
+}
+
+/* ---------------------------------------------------------------------- */
+
-+static struct dentry *decode_by_ino(struct super_block *sb, ino_t ino,
-+ ino_t dir_ino)
++int au_dr_opt_set(struct super_block *sb)
+{
-+ struct dentry *dentry, *d;
-+ struct inode *inode;
-+ unsigned int sigen;
++ int err;
++ aufs_bindex_t bindex, bbot;
++ struct au_branch *br;
+
-+ dentry = NULL;
-+ inode = ilookup(sb, ino);
-+ if (!inode)
-+ goto out;
++ 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);
++ }
+
-+ 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;
++ return err;
++}
+
-+ 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);
++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);
+ }
-+ if (unlikely(dentry && au_digen_test(dentry, sigen))) {
-+ /* need to refresh */
-+ dput(dentry);
-+ dentry = 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_iput:
-+ iput(inode);
+out:
-+ AuTraceErrPtr(dentry);
-+ return dentry;
++ return err;
+}
+diff -urN /usr/share/empty/fs/aufs/dirren.h linux/fs/aufs/dirren.h
+--- /usr/share/empty/fs/aufs/dirren.h 1970-01-01 01:00:00.000000000 +0100
++++ linux/fs/aufs/dirren.h 2022-11-05 23:02:18.962555950 +0100
+@@ -0,0 +1,140 @@
++/* SPDX-License-Identifier: GPL-2.0 */
++/*
++ * Copyright (C) 2017-2022 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/>.
++ */
+
-+/* ---------------------------------------------------------------------- */
++/*
++ * renamed dir info
++ */
+
-+/* todo: dirty? */
-+/* if exportfs_decode_fh() passed vfsmount*, we could be happy */
++#ifndef __AUFS_DIRREN_H__
++#define __AUFS_DIRREN_H__
+
-+struct au_compare_mnt_args {
-+ /* input */
-+ struct super_block *sb;
++#ifdef __KERNEL__
+
-+ /* output */
-+ struct vfsmount *mnt;
-+};
++#include <linux/dcache.h>
++#include <linux/statfs.h>
++#include <linux/uuid.h>
++#include "hbl.h"
+
-+static int au_compare_mnt(struct vfsmount *mnt, void *arg)
-+{
-+ struct au_compare_mnt_args *a = arg;
++#define AuDirren_NHASH 100
+
-+ if (mnt->mnt_sb != a->sb)
-+ return 0;
-+ a->mnt = mntget(mnt);
-+ return 1;
-+}
++#ifdef CONFIG_AUFS_DIRREN
++enum au_brid_type {
++ AuBrid_Unset,
++ AuBrid_UUID,
++ AuBrid_FSID,
++ AuBrid_DEV
++};
+
-+static struct vfsmount *au_mnt_get(struct super_block *sb)
-+{
-+ int err;
-+ struct path root;
-+ struct au_compare_mnt_args args = {
-+ .sb = sb
++struct au_dr_brid {
++ enum au_brid_type type;
++ union {
++ uuid_t uuid; /* unimplemented yet */
++ fsid_t fsid;
++ dev_t dev;
+ };
++};
+
-+ 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;
-+}
++/* 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_nfsd_si_lock {
-+ unsigned int sigen;
-+ aufs_bindex_t bindex, br_id;
-+ unsigned char force_lock;
++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
++
++/* ---------------------------------------------------------------------- */
+
-+static int si_nfsd_read_lock(struct super_block *sb,
-+ struct au_nfsd_si_lock *nsi_lock)
++#ifdef CONFIG_AUFS_DIRREN
++static inline int au_dr_ihash(ino_t h_ino)
+{
-+ int err;
-+ aufs_bindex_t bindex;
++ return h_ino % AuDirren_NHASH;
++}
++#else
++AuStubInt0(au_dr_ihash, ino_t h_ino);
++#endif
+
-+ si_read_lock(sb, AuLock_FLUSH);
++#endif /* __KERNEL__ */
++#endif /* __AUFS_DIRREN_H__ */
+diff -urN /usr/share/empty/fs/aufs/dynop.c linux/fs/aufs/dynop.c
+--- /usr/share/empty/fs/aufs/dynop.c 1970-01-01 01:00:00.000000000 +0100
++++ linux/fs/aufs/dynop.c 2024-03-10 23:40:47.083143450 +0100
+@@ -0,0 +1,366 @@
++// SPDX-License-Identifier: GPL-2.0
++/*
++ * Copyright (C) 2010-2022 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 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 */
++/*
++ * dynamically customizable operations for regular files
++ */
+
-+ err = -ESTALE;
-+ bindex = -1;
-+ if (!nsi_lock->force_lock)
-+ si_read_unlock(sb);
++#include "aufs.h"
+
-+out:
-+ nsi_lock->bindex = bindex;
-+ return err;
-+}
++#define DyPrSym(key) AuDbgSym(key->dk_op.dy_hop)
+
-+struct find_name_by_ino {
-+ struct dir_context ctx;
-+ int called, found;
-+ ino_t ino;
-+ char *name;
-+ int namelen;
-+};
++/*
++ * 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 bool
-+find_name_by_ino(struct dir_context *ctx, const char *name, int namelen,
-+ loff_t offset, u64 ino, unsigned int d_type)
++static struct au_dykey *dy_gfind_get(struct hlist_bl_head *hbl,
++ const void *h_op)
+{
-+ struct find_name_by_ino *a = container_of(ctx, struct find_name_by_ino,
-+ ctx);
++ struct au_dykey *key, *tmp;
++ struct hlist_bl_node *pos;
+
-+ a->called++;
-+ if (a->ino != ino)
-+ return true;
++ 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);
+
-+ memcpy(a->name, name, namelen);
-+ a->namelen = namelen;
-+ a->found = 1;
-+ return false;
++ return key;
+}
+
-+static struct dentry *au_lkup_by_ino(struct path *path, ino_t ino,
-+ struct au_nfsd_si_lock *nsi_lock)
++static struct au_dykey *dy_bradd(struct au_branch *br, struct au_dykey *key)
+{
-+ 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;
++ struct au_dykey **k, *found;
++ const void *h_op = key->dk_op.dy_hop;
++ int i;
+
-+ /* do not call vfsub_lkup_one() */
-+ dir = d_inode(parent);
-+ dentry = vfsub_lookup_one_len_unlocked(arg.name, path, 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);
++ 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 */
+ }
+
-+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;
++ return found;
+}
+
-+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)
++/* kref_get() if @key is already added */
++static struct au_dykey *dy_gadd(struct hlist_bl_head *hbl, struct au_dykey *key)
+{
-+ 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);
++ struct au_dykey *tmp, *found;
++ struct hlist_bl_node *pos;
++ const void *h_op = key->dk_op.dy_hop;
+
-+ path.mnt = au_mnt_get(sb);
-+ dentry = au_lkup_by_ino(&path, ino, nsi_lock);
-+ path_put(&path);
++ 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);
+
-+out:
-+ AuTraceErrPtr(dentry);
-+ return dentry;
++ if (!found)
++ DyPrSym(key);
++ return found;
+}
+
-+/* ---------------------------------------------------------------------- */
-+
-+static int h_acceptable(void *expv, struct dentry *dentry)
++static void dy_free_rcu(struct rcu_head *rcu)
+{
-+ return 1;
++ struct au_dykey *key;
++
++ key = container_of(rcu, struct au_dykey, dk_rcu);
++ DyPrSym(key);
++ kfree(key);
+}
+
-+static char *au_build_path(struct dentry *h_parent, struct path *h_rootpath,
-+ char *buf, int len, struct super_block *sb)
++static void dy_free(struct kref *kref)
+{
-+ char *p;
-+ int n;
-+ struct path path;
++ struct au_dykey *key;
++ struct hlist_bl_head *hbl;
+
-+ p = d_path(h_rootpath, buf, len);
-+ if (IS_ERR(p))
-+ goto out;
-+ n = strlen(p);
++ 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);
++}
+
-+ 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;
++void au_dy_put(struct au_dykey *key)
++{
++ kref_put(&key->dk_kref, dy_free);
++}
+
-+ 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;
-+}
++#define DyDbgSize(cnt, op) AuDebugOn(cnt != sizeof(op)/sizeof(void *))
+
-+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;
++#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
+
-+ 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;
-+ }
++#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)
+
-+ dentry = ERR_PTR(-ENOMEM);
-+ pathname = (void *)__get_free_page(GFP_NOFS);
-+ if (unlikely(!pathname))
-+ goto out_h_parent;
++#define DySetForce(func, dst, src) do { \
++ AuDebugOn(!src.func); \
++ DyDbgInc(cnt); \
++ dst.func = src.func; \
++} while (0)
+
-+ 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;
++#define DySetAop(func) \
++ DySet(func, dyaop->da_op, aufs_aop, h_aop, h_sb)
++#define DySetAopForce(func) \
++ DySetForce(func, dyaop->da_op, aufs_aop)
+
-+ si_read_unlock(sb);
-+ err = vfsub_kern_path(p, LOOKUP_FOLLOW | LOOKUP_DIRECTORY, &path);
-+ dentry = ERR_PTR(err);
-+ if (unlikely(err))
-+ goto out_relock;
++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);
+
-+ dentry = ERR_PTR(-ENOENT);
-+ AuDebugOn(au_test_anon(path.dentry));
-+ if (unlikely(d_really_is_negative(path.dentry)))
-+ goto out_path;
++ AuDbg("%s\n", au_sbtype(h_sb));
+
-+ if (ino != d_inode(path.dentry)->i_ino)
-+ dentry = au_lkup_by_ino(&path, ino, /*nsi_lock*/NULL);
-+ else
-+ dentry = dget(path.dentry);
++ DySetAop(writepage);
++ DySetAopForce(read_folio); /* force */
++ DySetAop(writepages);
++ DySetAop(dirty_folio);
++ DySetAop(invalidate_folio);
++ DySetAop(readahead);
++ DySetAop(write_begin);
++ DySetAop(write_end);
++ DySetAop(bmap);
++ DySetAop(release_folio);
++ DySetAop(free_folio);
++ /* this one will be changed according to an aufs mount option */
++ DySetAop(direct_IO);
++ DySetAop(migrate_folio);
++ DySetAop(launder_folio);
++ DySetAop(is_partially_uptodate);
++ DySetAop(is_dirty_writeback);
++ DySetAop(error_remove_folio);
++ DySetAop(swap_activate);
++ DySetAop(swap_deactivate);
++ DySetAop(swap_rw);
+
-+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;
++ DyDbgSize(cnt, *h_aop);
+}
+
+/* ---------------------------------------------------------------------- */
+
-+static struct dentry *
-+aufs_fh_to_dentry(struct super_block *sb, struct fid *fid, int fh_len,
-+ int fh_type)
++static void dy_bug(struct kref *kref)
+{
-+ 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
++ 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;
+
-+ 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];
++ hbl = dynop + op->dy_type;
++ key = dy_gfind_get(hbl, op->dy_hop);
++ if (key)
++ goto out_add; /* success */
+
-+ /* branch id may be wrapped around */
-+ br = NULL;
-+ if (unlikely(si_nfsd_read_lock(sb, &nsi_lock)))
++ p = a + op->dy_type;
++ key = kzalloc(p->sz, GFP_NOFS);
++ if (unlikely(!key)) {
++ key = ERR_PTR(-ENOMEM);
+ 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 */
++ 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;
++ }
+
-+ dput(dentry);
-+ dentry = ERR_PTR(-ESTALE);
-+out_unlock:
-+ if (br)
-+ au_lcnt_dec(&br->br_nfiles);
-+ si_read_unlock(sb);
++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:
-+ AuTraceErrPtr(dentry);
-+ return dentry;
++ 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;
+}
+
-+#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)
++static struct au_dyaop *dy_aget(struct au_branch *br,
++ const struct address_space_operations *h_aop,
++ int do_dx)
+{
-+ struct dentry *parent;
-+ __u32 *fh = fid->raw;
-+ ino_t dir_ino;
++ struct au_dyaop *dyaop;
++ struct au_dynop op;
+
-+ dir_ino = decode_ino(fh + Fh_dir_ino);
-+ parent = decode_by_ino(sb, dir_ino, 0);
-+ if (IS_ERR(parent))
++ op.dy_type = AuDy_AOP;
++ op.dy_haop = h_aop;
++ dyaop = (void *)dy_get(&op, br);
++ if (IS_ERR(dyaop))
+ goto out;
-+ if (!parent)
-+ parent = decode_by_path(sb, au_br_index(sb, fh[Fh_br_id]),
-+ dir_ino, fh, fh_len);
++ dy_adx(dyaop, do_dx);
+
+out:
-+ AuTraceErrPtr(parent);
-+ return parent;
++ return dyaop;
+}
-+#endif
-+
-+/* ---------------------------------------------------------------------- */
+
-+static int aufs_encode_fh(struct inode *inode, __u32 *fh, int *max_len,
-+ struct inode *dir)
++int au_dy_iaop(struct inode *inode, aufs_bindex_t bindex,
++ struct inode *h_inode)
+{
-+ int err;
-+ aufs_bindex_t bindex;
-+ struct super_block *sb, *h_sb;
-+ struct dentry *dentry, *parent, *h_parent;
-+ struct inode *h_dir;
++ int err, do_dx;
++ struct super_block *sb;
+ struct au_branch *br;
++ struct au_dyaop *dyaop;
+
-+ 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;
-+ }
++ AuDebugOn(!S_ISREG(h_inode->i_mode));
++ IiMustWriteLock(inode);
+
-+ 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;
++ 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;
+
-+ *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));
++ err = 0;
++ inode->i_mapping->a_ops = &dyaop->da_op;
+
-+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)
++/*
++ * 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 bindex;
-+ struct super_block *sb;
++ aufs_bindex_t btop;
+ 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);
++ 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;
++}
+
-+ f = h_inode->i_sb->s_export_op->commit_metadata;
-+ if (f)
-+ err = f(h_inode);
-+ else
-+ err = sync_inode_metadata(h_inode, /*wait*/1);
++void au_dy_arefresh(int do_dx)
++{
++ struct hlist_bl_head *hbl;
++ struct hlist_bl_node *pos;
++ struct au_dykey *key;
+
-+ au_cpup_attr_timesizes(inode);
-+ ii_write_unlock(inode);
-+ si_read_unlock(sb);
-+ return err;
++ 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);
+}
+
+/* ---------------------------------------------------------------------- */
+
-+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)
++void __init au_dy_init(void)
+{
-+ struct au_sbinfo *sbinfo;
-+ __u32 u;
++ int i;
+
-+ 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");
++ for (i = 0; i < AuDyLast; i++)
++ INIT_HLIST_BL_HEAD(dynop + i);
++}
+
-+ 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);
++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/f_op.c b/fs/aufs/f_op.c
-new file mode 100644
-index 00000000000000..320ad8a9334d30
---- /dev/null
-+++ b/fs/aufs/f_op.c
-@@ -0,0 +1,771 @@
-+// SPDX-License-Identifier: GPL-2.0
+diff -urN /usr/share/empty/fs/aufs/dynop.h linux/fs/aufs/dynop.h
+--- /usr/share/empty/fs/aufs/dynop.h 1970-01-01 01:00:00.000000000 +0100
++++ linux/fs/aufs/dynop.h 2022-11-05 23:02:18.962555950 +0100
+@@ -0,0 +1,77 @@
++/* SPDX-License-Identifier: GPL-2.0 */
+/*
-+ * Copyright (C) 2005-2022 Junjiro R. Okajima
++ * Copyright (C) 2010-2022 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
+ */
+
+/*
-+ * file and vm operations
++ * dynamically customizable operations (for regular files only)
+ */
+
-+#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 */
-+ }
++#ifndef __AUFS_DYNOP_H__
++#define __AUFS_DYNOP_H__
+
-+ if (flags & __O_TMPFILE) {
-+ AuDebugOn(!h_file);
-+ AuDebugOn(h_file != au_di(dentry)->di_htmpfile);
-+ au_di(dentry)->di_htmpfile = NULL;
++#ifdef __KERNEL__
+
-+ if (!(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; */
++#include <linux/fs.h>
++#include <linux/kref.h>
+
-+out:
-+ return err;
-+}
++enum {AuDy_AOP, AuDyLast};
+
-+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
++struct au_dynop {
++ int dy_type;
++ union {
++ const void *dy_hop;
++ const struct address_space_operations *dy_haop;
+ };
++};
+
-+ 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;
++struct au_dykey {
++ union {
++ struct hlist_bl_node dk_hnode;
++ struct rcu_head dk_rcu;
++ };
++ struct au_dynop dk_op;
+
-+ 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);
++ /*
++ * during I am in the branch local array, kref is gotten. when the
++ * branch is removed, kref is put.
++ */
++ struct kref dk_kref;
++};
+
-+ au_finfo_fin(file);
-+ return 0;
-+}
++/* 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));
+
+/* ---------------------------------------------------------------------- */
+
-+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;
-+}
++/* 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);
+
-+static int aufs_flush_nondir(struct file *file, fl_owner_t id)
-+{
-+ return au_do_flush(file, id, au_do_flush_nondir);
-+}
++void __init au_dy_init(void);
++void au_dy_fin(void);
+
-+/* ---------------------------------------------------------------------- */
++#endif /* __KERNEL__ */
++#endif /* __AUFS_DYNOP_H__ */
+diff -urN /usr/share/empty/fs/aufs/export.c linux/fs/aufs/export.c
+--- /usr/share/empty/fs/aufs/export.c 1970-01-01 01:00:00.000000000 +0100
++++ linux/fs/aufs/export.c 2024-03-10 23:40:47.083143450 +0100
+@@ -0,0 +1,846 @@
++// SPDX-License-Identifier: GPL-2.0
+/*
-+ * 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.
++ * Copyright (C) 2005-2022 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/>.
+ */
+
-+/* 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);
-+}
++/*
++ * export via nfs
++ */
+
-+struct au_write_pre {
-+ /* input */
-+ unsigned int lsc;
++#include <linux/exportfs.h>
++#include <linux/fs_struct.h>
++#include <linux/nsproxy.h>
++#include <linux/random.h>
++#include <linux/writeback.h>
++#include "aufs.h"
+
-+ /* output */
-+ blkcnt_t blks;
-+ aufs_bindex_t btop;
++union conv {
++#ifdef CONFIG_AUFS_INO_T_64
++ __u32 a[2];
++#else
++ __u32 a[1];
++#endif
++ ino_t ino;
+};
+
-+/*
-+ * 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)
++static ino_t decode_ino(__u32 *a)
+{
-+ 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;
++ union conv u;
+
-+ 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;
-+ }
-+ }
++ 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;
++}
+
-+ 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);
-+ vfsub_file_start_write(h_file);
++static void encode_ino(__u32 *a, ino_t ino)
++{
++ union conv u;
+
-+out_fi:
-+ fi_write_unlock(file);
-+out:
-+ return h_file;
++ u.ino = ino;
++ a[0] = u.a[0];
++#ifdef CONFIG_AUFS_INO_T_64
++ a[1] = u.a[1];
++#endif
+}
+
-+static void au_write_post(struct inode *inode, struct file *h_file,
-+ struct au_write_pre *wpre, ssize_t written)
-+{
-+ struct inode *h_inode;
++/* 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
++};
+
-+ vfsub_file_end_write(h_file);
-+ 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 int au_test_anon(struct dentry *dentry)
++{
++ /* note: read d_flags without d_lock */
++ return !!(dentry->d_flags & DCACHE_DISCONNECTED);
+}
+
-+/*
-+ * 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 au_test_nfsd(void)
+{
-+ int err;
-+ struct super_block *sb = inode->i_sb;
++ int ret;
++ struct task_struct *tsk = current;
++ char comm[sizeof(tsk->comm)];
+
-+ 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);
++ ret = 0;
++ if (tsk->flags & PF_KTHREAD) {
++ get_task_comm(comm, tsk);
++ ret = !strcmp(comm, "nfsd");
+ }
++
++ return ret;
+}
+
-+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 *);
++/* ---------------------------------------------------------------------- */
++/* inode generation external table */
+
-+ err = security_file_permission(h_file, rw);
-+ if (unlikely(err))
-+ goto out;
++void au_xigen_inc(struct inode *inode)
++{
++ loff_t pos;
++ ssize_t sz;
++ __u32 igen;
++ struct super_block *sb;
++ struct au_sbinfo *sbinfo;
+
-+ err = -ENOSYS; /* the branch doesn't have its ->(read|write)_iter() */
-+ 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;
++ sb = inode->i_sb;
++ AuDebugOn(!au_opt_test(au_mntflags(sb), XINO));
+
-+ 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;
++ sbinfo = au_sbi(sb);
++ pos = inode->i_ino;
++ pos *= sizeof(igen);
++ igen = inode->i_generation + 1;
++ sz = xino_fwrite(sbinfo->si_xigen, &igen, sizeof(igen), &pos);
++ if (sz == sizeof(igen))
++ return; /* success */
+
-+out:
-+ return err;
++ if (unlikely(sz >= 0))
++ AuIOErr("xigen error (%zd)\n", sz);
+}
+
-+static ssize_t aufs_read_iter(struct kiocb *kio, struct iov_iter *iov_iter)
++int au_xigen_new(struct inode *inode)
+{
-+ ssize_t err;
-+ struct file *file, *h_file;
-+ struct inode *inode;
++ int err;
++ loff_t pos;
++ ssize_t sz;
+ struct super_block *sb;
++ struct au_sbinfo *sbinfo;
++ struct file *file;
+
-+ file = kio->ki_filp;
-+ inode = file_inode(file);
++ err = 0;
++ /* todo: dirty, at mount time */
++ if (inode->i_ino == AUFS_ROOT_INO)
++ goto out;
+ 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))
++ SiMustAnyLock(sb);
++ if (unlikely(!au_opt_test(au_mntflags(sb), XINO)))
+ 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? */
-+ }
++ 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;
+ }
-+ fi_read_unlock(file);
++ pos *= sizeof(inode->i_generation);
+
-+ 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);
++ 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(file, &inode->i_generation,
++ sizeof(inode->i_generation), &pos);
++ } else
++ sz = xino_fread(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:
-+ si_read_unlock(sb);
+ return err;
+}
+
-+static ssize_t aufs_write_iter(struct kiocb *kio, struct iov_iter *iov_iter)
++int au_xigen_set(struct super_block *sb, struct path *path)
+{
-+ ssize_t err;
-+ struct au_write_pre wpre;
-+ struct inode *inode;
-+ struct file *file, *h_file;
++ int err;
++ struct au_sbinfo *sbinfo;
++ struct file *file;
+
-+ file = kio->ki_filp;
-+ inode = file_inode(file);
-+ au_mtx_and_read_lock(inode);
++ SiMustWriteLock(sb);
+
-+ wpre.lsc = 0;
-+ h_file = au_write_pre(file, /*do_ready*/1, &wpre);
-+ err = PTR_ERR(h_file);
-+ if (IS_ERR(h_file))
++ sbinfo = au_sbi(sb);
++ file = au_xino_create2(sb, path, sbinfo->si_xigen);
++ err = PTR_ERR(file);
++ if (IS_ERR(file))
+ goto out;
-+
-+ err = au_do_iter(h_file, MAY_WRITE, kio, iov_iter);
-+ au_write_post(inode, h_file, &wpre, err);
++ err = 0;
++ if (sbinfo->si_xigen)
++ fput(sbinfo->si_xigen);
++ sbinfo->si_xigen = file;
+
+out:
-+ si_read_unlock(inode->i_sb);
-+ inode_unlock(inode);
++ AuTraceErr(err);
+ return err;
+}
+
-+/*
-+ * We may be able to remove aufs_splice_{read,write}() since almost all FSes
-+ * don't have their own .splice_{read,write} implimentations, and they use
-+ * generic_file_splice_read() and iter_file_splice_write() who can act like the
-+ * simple converters to f_op->iter_read() and ->iter_write().
-+ * But we keep our own implementations because some non-mainlined FSes may have
-+ * their own .splice_{read,write} implimentations and aufs doesn't want to take
-+ * away an opportunity to co-work with aufs from them.
-+ */
-+static ssize_t aufs_splice_read(struct file *file, loff_t *ppos,
-+ struct pipe_inode_info *pipe, size_t len,
-+ unsigned int flags)
++void au_xigen_clr(struct super_block *sb)
+{
-+ ssize_t err;
-+ struct file *h_file;
-+ struct inode *inode;
-+ struct super_block *sb;
++ struct au_sbinfo *sbinfo;
+
-+ inode = file_inode(file);
-+ sb = inode->i_sb;
-+ si_read_lock(sb, AuLock_FLUSH | AuLock_NOPLMW);
++ SiMustWriteLock(sb);
+
-+ h_file = au_read_pre(file, /*keep_fi*/0, /*lsc*/0);
-+ err = PTR_ERR(h_file);
-+ if (IS_ERR(h_file))
++ 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;
+
-+ err = vfsub_splice_read(h_file, ppos, pipe, len, flags);
-+ /* todo: necessary? */
-+ /* file->f_ra = h_file->f_ra; */
-+ au_read_post(inode, h_file);
++ 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:
-+ si_read_unlock(sb);
-+ return err;
++ AuTraceErrPtr(dentry);
++ return dentry;
+}
+
-+static ssize_t
-+aufs_splice_write(struct pipe_inode_info *pipe, struct file *file, loff_t *ppos,
-+ size_t len, unsigned int flags)
++/* ---------------------------------------------------------------------- */
++
++/* 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)
+{
-+ ssize_t err;
-+ struct au_write_pre wpre;
-+ struct inode *inode;
-+ struct file *h_file;
++ struct au_compare_mnt_args *a = arg;
+
-+ inode = file_inode(file);
-+ au_mtx_and_read_lock(inode);
++ if (mnt->mnt_sb != a->sb)
++ return 0;
++ a->mnt = mntget(mnt);
++ return 1;
++}
+
-+ wpre.lsc = 0;
-+ h_file = au_write_pre(file, /*do_ready*/1, &wpre);
-+ err = PTR_ERR(h_file);
-+ if (IS_ERR(h_file))
++static struct vfsmount *au_mnt_get(struct super_block *sb)
++{
++ int err;
++ struct path root;
++ struct vfsmount *mnt;
++ struct au_compare_mnt_args args = {
++ .sb = sb
++ };
++
++ get_fs_root(current->fs, &root);
++ /*
++ * as long as this sb is alive, this temporary unlock is safe.
++ * Really?
++ */
++ si_read_unlock(sb);
++ mnt = collect_mounts(&root);
++ if (IS_ERR(mnt)) {
++ args.mnt = mnt;
+ goto out;
++ }
+
-+ err = vfsub_splice_from(pipe, h_file, ppos, len, flags);
-+ au_write_post(inode, h_file, &wpre, err);
++ rcu_read_lock();
++ err = iterate_mounts(au_compare_mnt, &args, mnt);
++ rcu_read_unlock();
++ drop_collected_mounts(mnt);
++ AuDebugOn(!err);
+
+out:
-+ si_read_unlock(inode->i_sb);
-+ inode_unlock(inode);
-+ return err;
++ si_noflush_read_lock(sb);
++ AuDebugOn(!args.mnt);
++ path_put(&root);
++ return args.mnt;
+}
+
-+static long aufs_fallocate(struct file *file, int mode, loff_t offset,
-+ loff_t len)
++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)
+{
-+ long err;
-+ struct au_write_pre wpre;
-+ struct inode *inode;
-+ struct file *h_file;
++ int err;
++ aufs_bindex_t bindex;
+
-+ inode = file_inode(file);
-+ au_mtx_and_read_lock(inode);
++ si_read_lock(sb, AuLock_FLUSH);
+
-+ 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;
++ /* 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 */
+
-+ lockdep_off();
-+ err = vfs_fallocate(h_file, mode, offset, len);
-+ lockdep_on();
-+ /*
-+ * we don't need to call file_modifed() here since au_write_post()
-+ * is equivalent and copies-up all timestamps and permission bits.
-+ */
-+ au_write_post(inode, h_file, &wpre, /*written*/1);
++ err = -ESTALE;
++ bindex = -1;
++ if (!nsi_lock->force_lock)
++ si_read_unlock(sb);
+
+out:
-+ si_read_unlock(inode->i_sb);
-+ inode_unlock(inode);
++ nsi_lock->bindex = bindex;
+ 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)
++struct find_name_by_ino {
++ struct dir_context ctx;
++ int called, found;
++ ino_t ino;
++ char *name;
++ int namelen;
++};
++
++static bool
++find_name_by_ino(struct dir_context *ctx, const char *name, int namelen,
++ loff_t offset, u64 ino, unsigned int d_type)
+{
-+ 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]
++ struct find_name_by_ino *a = container_of(ctx, struct find_name_by_ino,
++ ctx);
+
-+ 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;
++ a->called++;
++ if (a->ino != ino)
++ return true;
+
-+ 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;
++ memcpy(a->name, name, namelen);
++ a->namelen = namelen;
++ a->found = 1;
++ return false;
++}
+
-+ 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;
++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
+ }
-+ } 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;
++ };
++ int err;
+
-+ 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;
-+ }
++ 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, path, 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);
+ }
+
-+ 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;
-+ }
++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);
+
-+ err = vfsub_copy_file_range(a_src.h_file, src_pos, a_dst.h_file,
-+ dst_pos, len, flags);
++ path.mnt = au_mnt_get(sb);
++ dentry = au_lkup_by_ino(&path, ino, nsi_lock);
++ path_put(&path);
+
-+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
++ AuTraceErrPtr(dentry);
++ return dentry;
+}
+
+/* ---------------------------------------------------------------------- */
+
-+/*
-+ * 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)
++static int h_acceptable(void *expv, struct dentry *dentry)
+{
-+ /* 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
++ return 1;
+}
+
-+static unsigned long au_prot_conv(unsigned long flags)
++static char *au_build_path(struct dentry *h_parent, struct path *h_rootpath,
++ char *buf, int len, struct super_block *sb)
+{
-+ return AuConv_VM_PROT(flags, READ)
-+ | AuConv_VM_PROT(flags, WRITE)
-+ | AuConv_VM_PROT(flags, EXEC)
-+ | au_arch_prot_conv(flags);
-+}
++ char *p;
++ int n;
++ struct path path;
+
-+/* cf. linux/include/linux/mman.h: calc_vm_flag_bits() */
-+#define AuConv_VM_MAP(f, b) _calc_vm_trans(f, VM_##b, MAP_##b)
++ p = d_path(h_rootpath, buf, len);
++ if (IS_ERR(p))
++ goto out;
++ n = strlen(p);
+
-+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);
++ 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;
+}
-+#endif
+
-+static int aufs_mmap(struct file *file, struct vm_area_struct *vma)
++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;
-+ 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);
++ struct path path;
+
-+ inode = file_inode(file);
-+ sb = inode->i_sb;
++ 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();
-+ si_read_lock(sb, AuLock_NOPLMW);
-+
-+ h_file = au_write_pre(file, wlock, /*wpre*/NULL);
++ 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();
-+ err = PTR_ERR(h_file);
-+ if (IS_ERR(h_file))
++ 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;
-+
-+ 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);
++ 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;
+
-+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;
++ 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 int aufs_fsync_nondir(struct file *file, loff_t start, loff_t end,
-+ int datasync)
++static struct dentry *
++aufs_fh_to_dentry(struct super_block *sb, struct fid *fid, int fh_len,
++ int fh_type)
+{
-+ int err;
-+ struct au_write_pre wpre;
-+ struct inode *inode;
-+ struct file *h_file;
++ 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
++ };
+
-+ err = 0; /* -EBADF; */ /* posix? */
-+ if (unlikely(!(file->f_mode & FMODE_WRITE)))
++ 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];
+
-+ inode = file_inode(file);
-+ au_mtx_and_read_lock(inode);
++ /* branch id may be wrapped around */
++ br = NULL;
++ if (unlikely(si_nfsd_read_lock(sb, &nsi_lock)))
++ goto out;
++ nsi_lock.force_lock = 1;
+
-+ wpre.lsc = 0;
-+ h_file = au_write_pre(file, /*do_ready*/1, &wpre);
-+ err = PTR_ERR(h_file);
-+ if (IS_ERR(h_file))
++ /* is this inode still cached? */
++ ino = decode_ino(fh + Fh_ino);
++ /* it should never happen */
++ if (unlikely(ino == AUFS_ROOT_INO))
+ goto out_unlock;
+
-+ err = vfsub_fsync(h_file, &h_file->f_path, datasync);
-+ au_write_post(inode, h_file, &wpre, /*written*/0);
++ 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:
-+ si_read_unlock(inode->i_sb);
-+ inode_unlock(inode);
++ if (br)
++ au_lcnt_dec(&br->br_nfiles);
++ si_read_unlock(sb);
+out:
-+ return err;
++ AuTraceErrPtr(dentry);
++ return dentry;
+}
+
-+static int aufs_fasync(int fd, struct file *file, int flag)
++#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;
-+ struct file *h_file;
-+ struct super_block *sb;
++ aufs_bindex_t bindex;
++ struct super_block *sb, *h_sb;
++ struct dentry *dentry, *parent, *h_parent;
++ struct inode *h_dir;
++ struct au_branch *br;
+
-+ sb = file->f_path.dentry->d_sb;
-+ si_read_lock(sb, AuLock_FLUSH | AuLock_NOPLMW);
++ err = -ENOSPC;
++ if (unlikely(*max_len <= Fh_tail)) {
++ AuWarn1("NFSv2 client (max_len %d)?\n", *max_len);
++ goto out;
++ }
+
-+ h_file = au_read_pre(file, /*keep_fi*/0, /*lsc*/0);
-+ err = PTR_ERR(h_file);
-+ if (IS_ERR(h_file))
++ err = FILEID_ROOT;
++ if (inode->i_ino == AUFS_ROOT_INO) {
++ AuDebugOn(inode->i_ino != AUFS_ROOT_INO);
+ 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() */
++ h_parent = NULL;
++ sb = inode->i_sb;
++ err = si_read_lock(sb, AuLock_FLUSH);
++ if (unlikely(err))
++ goto out;
+
-+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_setfl(struct file *file, unsigned long arg)
++/* ---------------------------------------------------------------------- */
++
++static int aufs_commit_metadata(struct inode *inode)
+{
+ int err;
-+ struct file *h_file;
++ aufs_bindex_t bindex;
+ struct super_block *sb;
++ struct inode *h_inode;
++ int (*f)(struct inode *inode);
+
-+ sb = file->f_path.dentry->d_sb;
++ 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);
+
-+ 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() */
++ f = h_inode->i_sb->s_export_op->commit_metadata;
++ if (f)
++ err = f(h_inode);
++ else
++ err = sync_inode_metadata(h_inode, /*wait*/1);
+
-+out:
++ au_cpup_attr_timesizes(inode);
++ ii_write_unlock(inode);
+ si_read_unlock(sb);
+ return err;
+}
+
+/* ---------------------------------------------------------------------- */
+
-+const struct file_operations aufs_file_fop = {
-+ .owner = THIS_MODULE,
++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
++};
+
-+ .llseek = default_llseek,
++void au_export_init(struct super_block *sb)
++{
++ struct au_sbinfo *sbinfo;
++ __u32 u;
+
-+ .read_iter = aufs_read_iter,
-+ .write_iter = aufs_write_iter,
++ 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");
+
-+#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,
-+ .setfl = aufs_setfl,
-+ .splice_write = aufs_splice_write,
-+ .splice_read = aufs_splice_read,
-+#if 0 /* reserved for future use */
-+ .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 00000000000000..91262fbbbfaed0
---- /dev/null
-+++ b/fs/aufs/fhsm.c
++ 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 -urN /usr/share/empty/fs/aufs/fhsm.c linux/fs/aufs/fhsm.c
+--- /usr/share/empty/fs/aufs/fhsm.c 1970-01-01 01:00:00.000000000 +0100
++++ linux/fs/aufs/fhsm.c 2022-11-05 23:02:18.962555950 +0100
@@ -0,0 +1,426 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ 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 00000000000000..76ad444328db50
---- /dev/null
-+++ b/fs/aufs/file.c
+diff -urN /usr/share/empty/fs/aufs/file.c linux/fs/aufs/file.c
+--- /usr/share/empty/fs/aufs/file.c 1970-01-01 01:00:00.000000000 +0100
++++ linux/fs/aufs/file.c 2024-03-10 23:40:47.083143450 +0100
@@ -0,0 +1,865 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+static void aufs_is_dirty_writeback(struct folio *folio, bool *dirty,
+ bool *writeback)
+{ AuUnsupport(); }
-+static int aufs_error_remove_page(struct address_space *mapping,
-+ struct page *page)
++static int aufs_error_remove_folio(struct address_space *mapping,
++ struct folio *folio)
+{ AuUnsupport(); return 0; }
+static int aufs_swap_activate(struct swap_info_struct *sis, struct file *file,
+ sector_t *span)
+ .launder_folio = aufs_launder_folio,
+ .is_partially_uptodate = aufs_is_partially_uptodate,
+ .is_dirty_writeback = aufs_is_dirty_writeback,
-+ .error_remove_page = aufs_error_remove_page,
++ .error_remove_folio = aufs_error_remove_folio,
+ .swap_activate = aufs_swap_activate,
+ .swap_deactivate = aufs_swap_deactivate,
+ .swap_rw = aufs_swap_rw
+#endif /* CONFIG_AUFS_DEBUG */
+};
-diff --git a/fs/aufs/file.h b/fs/aufs/file.h
-new file mode 100644
-index 00000000000000..b16f31e364a837
---- /dev/null
-+++ b/fs/aufs/file.h
+diff -urN /usr/share/empty/fs/aufs/file.h linux/fs/aufs/file.h
+--- /usr/share/empty/fs/aufs/file.h 1970-01-01 01:00:00.000000000 +0100
++++ linux/fs/aufs/file.h 2022-11-05 23:02:18.965889284 +0100
@@ -0,0 +1,342 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ */
+
+/*
-+ * file operations
++ * 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 -urN /usr/share/empty/fs/aufs/finfo.c linux/fs/aufs/finfo.c
+--- /usr/share/empty/fs/aufs/finfo.c 1970-01-01 01:00:00.000000000 +0100
++++ linux/fs/aufs/finfo.c 2022-11-05 23:02:18.965889284 +0100
+@@ -0,0 +1,149 @@
++// SPDX-License-Identifier: GPL-2.0
++/*
++ * Copyright (C) 2005-2022 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/>.
++ */
++
++/*
++ * 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 -urN /usr/share/empty/fs/aufs/f_op.c linux/fs/aufs/f_op.c
+--- /usr/share/empty/fs/aufs/f_op.c 1970-01-01 01:00:00.000000000 +0100
++++ linux/fs/aufs/f_op.c 2023-10-31 09:31:04.196547417 +0100
+@@ -0,0 +1,771 @@
++// SPDX-License-Identifier: GPL-2.0
++/*
++ * Copyright (C) 2005-2022 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/>.
++ */
++
++/*
++ * file and vm operations
+ */
+
-+#ifndef __AUFS_FILE_H__
-+#define __AUFS_FILE_H__
++#include <linux/aio.h>
++#include <linux/fs_stack.h>
++#include <linux/mman.h>
++#include <linux/security.h>
++#include "aufs.h"
+
-+#ifdef __KERNEL__
++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;
+
-+#include <linux/file.h>
-+#include <linux/fs.h>
-+#include <linux/mm_types.h>
-+#include <linux/poll.h>
-+#include "rwsem.h"
++ FiMustWriteLock(file);
+
-+struct au_branch;
-+struct au_hfile {
-+ struct file *hf_file;
-+ struct au_branch *hf_br;
-+};
++ 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 */
++ }
+
-+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[];
-+};
++ if (flags & __O_TMPFILE) {
++ AuDebugOn(!h_file);
++ AuDebugOn(h_file != au_di(dentry)->di_htmpfile);
++ au_di(dentry)->di_htmpfile = NULL;
+
-+static inline int au_fidir_sz(int nent)
-+{
-+ AuDebugOn(nent < 0);
-+ return sizeof(struct au_fidir) + sizeof(struct au_hfile) * nent;
++ if (!(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;
+}
+
-+struct au_finfo {
-+ atomic_t fi_generation;
++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
++ };
+
-+ struct au_rwsem fi_rwsem;
-+ aufs_bindex_t fi_btop;
++ AuDbg("%pD, f_flags 0x%x, f_mode 0x%x\n",
++ file, vfsub_file_flags(file), file->f_mode);
+
-+ /* 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 */
++ 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;
++}
+
-+ struct hlist_bl_node fi_hlist;
-+ struct file *fi_file; /* very ugly */
-+ struct rcu_head rcu;
-+} ____cacheline_aligned_in_smp;
++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);
+
-+/* 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));
++ au_finfo_fin(file);
++ return 0;
++}
+
-+/* 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
++static int au_do_flush_nondir(struct file *file, fl_owner_t id)
++{
++ int err;
++ struct file *h_file;
+
-+/* 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);
++ err = 0;
++ h_file = au_hf_top(file);
++ if (h_file)
++ err = vfsub_flush(h_file, id);
++ return err;
++}
+
-+/* 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);
++static int aufs_flush_nondir(struct file *file, fl_owner_t id)
++{
++ return au_do_flush(file, id, au_do_flush_nondir);
++}
+
-+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);
++/* ---------------------------------------------------------------------- */
++/*
++ * 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.
++ */
+
-+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);
++/* 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;
+
-+/* 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
++ 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 inline struct au_finfo *au_fi(struct file *file)
++static void au_read_post(struct inode *inode, struct file *h_file)
+{
-+ return file->private_data;
++ /* 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;
++};
+
-+#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)
-+*/
++ * 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;
+
-+#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)
++ 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;
+
-+/* lock subclass for finfo */
-+enum {
-+ AuLsc_FI_1,
-+ AuLsc_FI_2
-+};
++ 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;
++ }
++ }
+
-+static inline void fi_read_lock_nested(struct file *f, unsigned int lsc)
-+{
-+ au_rw_read_lock_nested(&au_fi(f)->fi_rwsem, lsc);
++ 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);
++ vfsub_file_start_write(h_file);
++
++out_fi:
++ fi_write_unlock(file);
++out:
++ return h_file;
+}
+
-+static inline void fi_write_lock_nested(struct file *f, unsigned int lsc)
++static void au_write_post(struct inode *inode, struct file *h_file,
++ struct au_write_pre *wpre, ssize_t written)
+{
-+ au_rw_write_lock_nested(&au_fi(f)->fi_rwsem, lsc);
++ struct inode *h_inode;
++
++ vfsub_file_end_write(h_file);
++ 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);
+}
+
+/*
-+ * fi_read_lock_1, fi_write_lock_1,
-+ * fi_read_lock_2, fi_write_lock_2
++ * 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.
+ */
-+#define AuReadLockFunc(name) \
-+static inline void fi_read_lock_##name(struct file *f) \
-+{ fi_read_lock_nested(f, AuLsc_FI_##name); }
++static void au_mtx_and_read_lock(struct inode *inode)
++{
++ int err;
++ struct super_block *sb = inode->i_sb;
+
-+#define AuWriteLockFunc(name) \
-+static inline void fi_write_lock_##name(struct file *f) \
-+{ fi_write_lock_nested(f, AuLsc_FI_##name); }
++ 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);
++ }
++}
+
-+#define AuRWLockFuncs(name) \
-+ AuReadLockFunc(name) \
-+ AuWriteLockFunc(name)
++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 *);
+
-+AuRWLockFuncs(1);
-+AuRWLockFuncs(2);
++ err = security_file_permission(h_file, rw);
++ if (unlikely(err))
++ goto out;
+
-+#undef AuReadLockFunc
-+#undef AuWriteLockFunc
-+#undef AuRWLockFuncs
++ err = -ENOSYS; /* the branch doesn't have its ->(read|write)_iter() */
++ 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;
+
-+#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)
++ 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;
++}
+
-+/* todo: hard/soft set? */
-+static inline aufs_bindex_t au_fbtop(struct file *file)
++static ssize_t aufs_read_iter(struct kiocb *kio, struct iov_iter *iov_iter)
+{
-+ FiMustAnyLock(file);
-+ return au_fi(file)->fi_btop;
++ 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 inline aufs_bindex_t au_fbbot_dir(struct file *file)
++static ssize_t aufs_write_iter(struct kiocb *kio, struct iov_iter *iov_iter)
+{
-+ FiMustAnyLock(file);
-+ AuDebugOn(!au_fi(file)->fi_hdir);
-+ return au_fi(file)->fi_hdir->fd_bbot;
++ 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;
++}
++
++/*
++ * We may be able to remove aufs_splice_{read,write}() since almost all FSes
++ * don't have their own .splice_{read,write} implimentations, and they use
++ * generic_file_splice_read() and iter_file_splice_write() who can act like the
++ * simple converters to f_op->iter_read() and ->iter_write().
++ * But we keep our own implementations because some non-mainlined FSes may have
++ * their own .splice_{read,write} implimentations and aufs doesn't want to take
++ * away an opportunity to co-work with aufs from them.
++ */
++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_read(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 inline struct au_vdir *au_fvdir_cache(struct file *file)
++static ssize_t
++aufs_splice_write(struct pipe_inode_info *pipe, struct file *file, loff_t *ppos,
++ size_t len, unsigned int flags)
+{
-+ FiMustAnyLock(file);
-+ AuDebugOn(!au_fi(file)->fi_hdir);
-+ return au_fi(file)->fi_hdir->fd_vdir_cache;
-+}
++ ssize_t err;
++ struct au_write_pre wpre;
++ struct inode *inode;
++ struct file *h_file;
+
-+static inline void au_set_fbtop(struct file *file, aufs_bindex_t bindex)
-+{
-+ FiMustWriteLock(file);
-+ au_fi(file)->fi_btop = bindex;
-+}
++ inode = file_inode(file);
++ au_mtx_and_read_lock(inode);
+
-+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;
-+}
++ 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;
+
-+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;
-+}
++ err = vfsub_splice_from(pipe, h_file, ppos, len, flags);
++ au_write_post(inode, h_file, &wpre, err);
+
-+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;
++out:
++ si_read_unlock(inode->i_sb);
++ inode_unlock(inode);
++ return err;
+}
+
-+static inline struct file *au_hf_dir(struct file *file, aufs_bindex_t bindex)
++static long aufs_fallocate(struct file *file, int mode, loff_t offset,
++ loff_t len)
+{
-+ FiMustAnyLock(file);
-+ AuDebugOn(!au_fi(file)->fi_hdir);
-+ return au_fi(file)->fi_hdir->fd_hfile[0 + bindex].hf_file;
-+}
++ long err;
++ struct au_write_pre wpre;
++ struct inode *inode;
++ struct file *h_file;
+
-+/* todo: memory barrier? */
-+static inline unsigned int au_figen(struct file *f)
-+{
-+ return atomic_read(&au_fi(f)->fi_generation);
-+}
++ inode = file_inode(file);
++ au_mtx_and_read_lock(inode);
+
-+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))
-+ ;
-+}
++ 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;
+
-+static inline void au_unset_mmapped(struct file *f)
-+{
-+ atomic_dec(&au_fi(f)->fi_mmapped);
++ lockdep_off();
++ err = vfs_fallocate(h_file, mode, offset, len);
++ lockdep_on();
++ /*
++ * we don't need to call file_modifed() here since au_write_post()
++ * is equivalent and copies-up all timestamps and permission bits.
++ */
++ au_write_post(inode, h_file, &wpre, /*written*/1);
++
++out:
++ si_read_unlock(inode->i_sb);
++ inode_unlock(inode);
++ return err;
+}
+
-+static inline int au_test_mmapped(struct file *f)
++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)
+{
-+ return atomic_read(&au_fi(f)->fi_mmapped);
-+}
++ 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]
+
-+/* customize vma->vm_file */
++ 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;
+
-+static inline void au_do_vm_file_reset(struct vm_area_struct *vma,
-+ struct file *file)
-+{
-+ struct file *f;
++ 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;
+
-+ f = vma->vm_file;
-+ get_file(file);
-+ vma->vm_file = file;
-+ fput(f);
-+}
++ 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;
+
-+#ifdef CONFIG_MMU
-+#define AuDbgVmRegion(file, vma) do {} while (0)
++ 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;
++ }
++ }
+
-+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))
++ 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;
++ }
+
-+static inline void au_vm_file_reset(struct vm_area_struct *vma,
-+ struct file *file)
-+{
-+ struct file *f;
++ err = vfsub_copy_file_range(a_src.h_file, src_pos, a_dst.h_file,
++ dst_pos, len, flags);
+
-+ au_do_vm_file_reset(vma, file);
-+ f = vma->vm_region->vm_file;
-+ get_file(file);
-+ vma->vm_region->vm_file = file;
-+ fput(f);
++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
+}
-+#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 00000000000000..7da7b286c006fc
---- /dev/null
-+++ b/fs/aufs/finfo.c
-@@ -0,0 +1,149 @@
-+// SPDX-License-Identifier: GPL-2.0
+/*
-+ * Copyright (C) 2005-2022 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.
++ * 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.
+ *
-+ * 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
++ * 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.
+ */
+
-+#include "aufs.h"
++#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)
+
-+void au_hfput(struct au_hfile *hf, int execed)
++static unsigned long au_arch_prot_conv(unsigned long flags)
+{
-+ 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;
++ /* 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
+}
+
-+void au_set_h_fptr(struct file *file, aufs_bindex_t bindex, struct file *val)
++static unsigned long au_prot_conv(unsigned long flags)
+{
-+ struct au_finfo *finfo = au_fi(file);
-+ struct au_hfile *hf;
-+ struct au_fidir *fidir;
++ return AuConv_VM_PROT(flags, READ)
++ | AuConv_VM_PROT(flags, WRITE)
++ | AuConv_VM_PROT(flags, EXEC)
++ | au_arch_prot_conv(flags);
++}
+
-+ fidir = finfo->fi_hdir;
-+ if (!fidir) {
-+ AuDebugOn(finfo->fi_btop != bindex);
-+ hf = &finfo->fi_htop;
-+ } else
-+ hf = fidir->fd_hfile + bindex;
++/* cf. linux/include/linux/mman.h: calc_vm_flag_bits() */
++#define AuConv_VM_MAP(f, b) _calc_vm_trans(f, VM_##b, MAP_##b)
+
-+ 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);
-+ }
++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
+
-+void au_update_figen(struct file *file)
++static int aufs_mmap(struct file *file, struct vm_area_struct *vma)
+{
-+ atomic_set(&au_fi(file)->fi_generation, au_digen(file->f_path.dentry));
-+ /* smp_mb(); */ /* atomic_set */
-+}
++ 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);
+
-+struct au_fidir *au_fidir_alloc(struct super_block *sb)
-+{
-+ struct au_fidir *fidir;
-+ int nbr;
++ inode = file_inode(file);
++ sb = inode->i_sb;
++ lockdep_off();
++ si_read_lock(sb, AuLock_NOPLMW);
+
-+ 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;
++ 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);
+
-+ return fidir;
++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;
+}
+
-+int au_fidir_realloc(struct au_finfo *finfo, int nbr, int may_shrink)
++/* ---------------------------------------------------------------------- */
++
++static int aufs_fsync_nondir(struct file *file, loff_t start, loff_t end,
++ int datasync)
+{
+ int err;
-+ struct au_fidir *fidir, *p;
++ struct au_write_pre wpre;
++ struct inode *inode;
++ struct file *h_file;
+
-+ AuRwMustWriteLock(&finfo->fi_rwsem);
-+ fidir = finfo->fi_hdir;
-+ AuDebugOn(!fidir);
++ err = 0; /* -EBADF; */ /* posix? */
++ if (unlikely(!(file->f_mode & FMODE_WRITE)))
++ goto out;
+
-+ 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;
-+ }
++ 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;
+}
+
-+/* ---------------------------------------------------------------------- */
-+
-+void au_finfo_fin(struct file *file)
++static int aufs_fasync(int fd, struct file *file, int flag)
+{
-+ struct au_finfo *finfo;
++ int err;
++ struct file *h_file;
++ struct super_block *sb;
+
-+ au_lcnt_dec(&au_sbi(file->f_path.dentry->d_sb)->si_nfiles);
++ sb = file->f_path.dentry->d_sb;
++ si_read_lock(sb, AuLock_FLUSH | AuLock_NOPLMW);
+
-+ finfo = au_fi(file);
-+ AuDebugOn(finfo->fi_hdir);
-+ AuRwDestroy(&finfo->fi_rwsem);
-+ au_cache_free_finfo(finfo);
-+}
++ h_file = au_read_pre(file, /*keep_fi*/0, /*lsc*/0);
++ err = PTR_ERR(h_file);
++ if (IS_ERR(h_file))
++ goto out;
+
-+void au_fi_init_once(void *_finfo)
-+{
-+ struct au_finfo *finfo = _finfo;
++ if (h_file->f_op->fasync)
++ err = h_file->f_op->fasync(fd, h_file, flag);
++ fput(h_file); /* instead of au_read_post() */
+
-+ au_rw_init(&finfo->fi_rwsem);
++out:
++ si_read_unlock(sb);
++ return err;
+}
+
-+int au_finfo_init(struct file *file, struct au_fidir *fidir)
++static int aufs_setfl(struct file *file, unsigned long arg)
+{
+ int err;
-+ struct au_finfo *finfo;
-+ struct dentry *dentry;
++ struct file *h_file;
++ struct super_block *sb;
+
-+ err = -ENOMEM;
-+ dentry = file->f_path.dentry;
-+ finfo = au_cache_alloc_finfo();
-+ if (unlikely(!finfo))
-+ goto out;
++ sb = file->f_path.dentry->d_sb;
++ si_read_lock(sb, AuLock_FLUSH | AuLock_NOPLMW);
+
-+ 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 */
++ h_file = au_read_pre(file, /*keep_fi*/0, /*lsc*/0);
++ err = PTR_ERR(h_file);
++ if (IS_ERR(h_file))
++ goto out;
+
-+ file->private_data = finfo;
++ /* 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;
+}
-diff --git a/fs/aufs/fsctx.c b/fs/aufs/fsctx.c
-new file mode 100644
-index 00000000000000..e14fe4d381c5c9
---- /dev/null
-+++ b/fs/aufs/fsctx.c
++
++/* ---------------------------------------------------------------------- */
++
++const struct file_operations aufs_file_fop = {
++ .owner = THIS_MODULE,
++
++ .llseek = default_llseek,
++
++ .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,
++ .setfl = aufs_setfl,
++ .splice_write = aufs_splice_write,
++ .splice_read = aufs_splice_read,
++#if 0 /* reserved for future use */
++ .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 -urN /usr/share/empty/fs/aufs/fsctx.c linux/fs/aufs/fsctx.c
+--- /usr/share/empty/fs/aufs/fsctx.c 1970-01-01 01:00:00.000000000 +0100
++++ linux/fs/aufs/fsctx.c 2022-11-05 23:02:18.965889284 +0100
@@ -0,0 +1,1242 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ AuTraceErr(err);
+ return err;
+}
-diff --git a/fs/aufs/fstype.h b/fs/aufs/fstype.h
-new file mode 100644
-index 00000000000000..24ff0d64c219bc
---- /dev/null
-+++ b/fs/aufs/fstype.h
+diff -urN /usr/share/empty/fs/aufs/fstype.h linux/fs/aufs/fstype.h
+--- /usr/share/empty/fs/aufs/fstype.h 1970-01-01 01:00:00.000000000 +0100
++++ linux/fs/aufs/fstype.h 2022-11-05 23:02:18.965889284 +0100
@@ -0,0 +1,401 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+
+#endif /* __KERNEL__ */
+#endif /* __AUFS_FSTYPE_H__ */
-diff --git a/fs/aufs/hbl.h b/fs/aufs/hbl.h
-new file mode 100644
-index 00000000000000..7e1e66db0264ba
---- /dev/null
-+++ b/fs/aufs/hbl.h
+diff -urN /usr/share/empty/fs/aufs/hbl.h linux/fs/aufs/hbl.h
+--- /usr/share/empty/fs/aufs/hbl.h 1970-01-01 01:00:00.000000000 +0100
++++ linux/fs/aufs/hbl.h 2022-11-05 23:02:18.965889284 +0100
@@ -0,0 +1,65 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+
+#endif /* __KERNEL__ */
+#endif /* __AUFS_HBL_H__ */
-diff --git a/fs/aufs/hfsnotify.c b/fs/aufs/hfsnotify.c
-new file mode 100644
-index 00000000000000..caa900cea3a0c4
---- /dev/null
-+++ b/fs/aufs/hfsnotify.c
+diff -urN /usr/share/empty/fs/aufs/hfsnotify.c linux/fs/aufs/hfsnotify.c
+--- /usr/share/empty/fs/aufs/hfsnotify.c 1970-01-01 01:00:00.000000000 +0100
++++ linux/fs/aufs/hfsnotify.c 2022-11-05 23:02:18.965889284 +0100
@@ -0,0 +1,290 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ .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 00000000000000..c626ff2128c6b3
---- /dev/null
-+++ b/fs/aufs/hfsplus.c
+diff -urN /usr/share/empty/fs/aufs/hfsplus.c linux/fs/aufs/hfsplus.c
+--- /usr/share/empty/fs/aufs/hfsplus.c 1970-01-01 01:00:00.000000000 +0100
++++ linux/fs/aufs/hfsplus.c 2022-11-05 23:02:18.965889284 +0100
@@ -0,0 +1,60 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ au_lcnt_dec(&br->br_nfiles);
+ }
+}
-diff --git a/fs/aufs/hnotify.c b/fs/aufs/hnotify.c
-new file mode 100644
-index 00000000000000..8ca8c98d40a330
---- /dev/null
-+++ b/fs/aufs/hnotify.c
+diff -urN /usr/share/empty/fs/aufs/hnotify.c linux/fs/aufs/hnotify.c
+--- /usr/share/empty/fs/aufs/hnotify.c 1970-01-01 01:00:00.000000000 +0100
++++ linux/fs/aufs/hnotify.c 2024-03-10 23:40:47.083143450 +0100
@@ -0,0 +1,715 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+/* ---------------------------------------------------------------------- */
+
+/* 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 AuHnJob_XINO0 BIT(0)
++#define AuHnJob_GEN BIT(1)
++#define AuHnJob_DIRENT BIT(2)
++#define AuHnJob_ISDIR BIT(3)
++#define AuHnJob_TRYXINO0 BIT(4)
++#define AuHnJob_MNTPNT BIT(5)
+#define au_ftest_hnjob(flags, name) ((flags) & AuHnJob_##name)
+#define au_fset_hnjob(flags, name) \
+ do { (flags) |= AuHnJob_##name; } while (0)
+
+ dentry = NULL;
+ spin_lock(&parent->d_lock);
-+ list_for_each_entry(d, &parent->d_subdirs, d_child) {
++ hlist_for_each_entry(d, &parent->d_children, d_sib) {
+ /* AuDbg("%pd\n", d); */
+ spin_lock_nested(&d->d_lock, DENTRY_D_LOCK_NESTED);
+ dname = &d->d_name;
+ 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 00000000000000..a5cc8743c2bca4
---- /dev/null
-+++ b/fs/aufs/i_op.c
-@@ -0,0 +1,1516 @@
+diff -urN /usr/share/empty/fs/aufs/iinfo.c linux/fs/aufs/iinfo.c
+--- /usr/share/empty/fs/aufs/iinfo.c 1970-01-01 01:00:00.000000000 +0100
++++ linux/fs/aufs/iinfo.c 2022-11-05 23:02:18.965889284 +0100
+@@ -0,0 +1,286 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2005-2022 Junjiro R. Okajima
+ */
+
+/*
-+ * inode operations (except add/del/rename)
++ * inode private data
+ */
+
-+#include <linux/device_cgroup.h>
-+#include <linux/filelock.h>
-+#include <linux/fs_stack.h>
-+#include <linux/iversion.h>
-+#include <linux/security.h>
+#include "aufs.h"
+
-+static int h_permission(struct inode *h_inode, int mask,
-+ struct path *h_path, int brperm)
++struct inode *au_h_iptr(struct inode *inode, aufs_bindex_t bindex)
+{
-+ int err;
-+ const unsigned char write_mask = !!(mask & (MAY_WRITE | MAY_APPEND));
-+ struct mnt_idmap *h_idmap;
++ struct inode *h_inode;
++ struct au_hinode *hinode;
+
-+ err = -EPERM;
-+ if (write_mask && IS_IMMUTABLE(h_inode))
-+ goto out;
++ IiMustAnyLock(inode);
+
-+ err = -EACCES;
-+ if (((mask & MAY_EXEC)
-+ && S_ISREG(h_inode->i_mode)
-+ && (path_noexec(h_path)
-+ || !(h_inode->i_mode & 0111))))
-+ goto out;
++ hinode = au_hinode(au_ii(inode), bindex);
++ h_inode = hinode->hi_inode;
++ AuDebugOn(h_inode && atomic_read(&h_inode->i_count) <= 0);
++ return h_inode;
++}
+
-+ /*
-+ * - 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.
-+ */
-+ h_idmap = mnt_idmap(h_path->mnt);
-+ 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_inode_acl %ps\n",
-+ h_inode->i_op->get_inode_acl); */
-+ err = generic_permission(h_idmap, h_inode, mask);
-+ if (err == -EOPNOTSUPP && au_test_nfs_noacl(h_inode))
-+ err = h_inode->i_op->permission(h_idmap, h_inode,
-+ mask);
-+ AuTraceErr(err);
-+ } else {
-+ /* AuLabel(h_inode->permission); */
-+ err = h_inode->i_op->permission(h_idmap, h_inode, mask);
-+ AuTraceErr(err);
-+ }
++/* todo: hard/soft set? */
++void au_hiput(struct au_hinode *hinode)
++{
++ au_hn_free(hinode);
++ dput(hinode->hi_whdentry);
++ iput(hinode->hi_inode);
++}
+
-+ if (!err)
-+ err = devcgroup_inode_permission(h_inode, mask);
-+ if (!err)
-+ err = security_inode_permission(h_inode, mask);
++unsigned int au_hi_flags(struct inode *inode, int isdir)
++{
++ unsigned int flags;
++ const unsigned int mnt_flags = au_mntflags(inode->i_sb);
+
-+out:
-+ return err;
++ flags = 0;
++ if (au_opt_test(mnt_flags, XINO))
++ au_fset_hi(flags, XINO);
++ if (isdir && au_opt_test(mnt_flags, UDBA_HNOTIFY))
++ au_fset_hi(flags, HNOTIFY);
++ return flags;
+}
+
-+static int aufs_permission(struct mnt_idmap *idmap, struct inode *inode,
-+ int mask)
++void au_set_h_iptr(struct inode *inode, aufs_bindex_t bindex,
++ struct inode *h_inode, unsigned int flags)
+{
-+ 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;
++ struct au_hinode *hinode;
++ struct inode *hi;
++ struct au_iinfo *iinfo = au_ii(inode);
+
-+ /* todo: support rcu-walk? */
-+ if (mask & MAY_NOT_BLOCK)
-+ return -ECHILD;
++ IiMustWriteLock(inode);
+
-+ sb = inode->i_sb;
-+ si_read_lock(sb, AuLock_FLUSH);
-+ ii_read_lock_child(inode);
-+#if 0 /* reserved for future use */
-+ /*
-+ * This test may be rather 'too much' since the test is essentially done
-+ * in the aufs_lookup(). Theoretically it is possible that the inode
-+ * generation doesn't match to the superblock's here. But it isn't a
-+ * big deal I suppose.
-+ */
-+ err = au_iigen_test(inode, au_sigen(sb));
-+ if (unlikely(err))
-+ goto out;
-+#endif
++ hinode = au_hinode(iinfo, bindex);
++ hi = hinode->hi_inode;
++ AuDebugOn(h_inode && atomic_read(&h_inode->i_count) <= 0);
+
-+ 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;
++ if (hi)
++ au_hiput(hinode);
++ hinode->hi_inode = h_inode;
++ if (h_inode) {
++ int err;
++ struct super_block *sb = inode->i_sb;
++ struct au_branch *br;
+
-+ err = 0;
-+ bindex = au_ibtop(inode);
++ AuDebugOn(inode->i_mode
++ && (h_inode->i_mode & S_IFMT)
++ != (inode->i_mode & S_IFMT));
++ if (bindex == iinfo->ii_btop)
++ au_cpup_igen(inode, h_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;
-+ }
++ hinode->hi_id = br->br_id;
++ if (au_ftest_hi(flags, XINO)) {
++ err = au_xino_write(sb, bindex, h_inode->i_ino,
++ inode->i_ino);
++ if (unlikely(err))
++ AuIOErr1("failed au_xino_write() %d\n", err);
++ }
++
++ if (au_ftest_hi(flags, HNOTIFY)
++ && au_br_hnotifyable(br->br_perm)) {
++ err = au_hn_alloc(hinode, inode);
++ if (unlikely(err))
++ AuIOErr1("au_hn_alloc() %d\n", err);
+ }
-+ 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;
++void au_set_hi_wh(struct inode *inode, aufs_bindex_t bindex,
++ struct dentry *h_wh)
++{
++ struct au_hinode *hinode;
+
-+ br = au_sbr(sb, bindex);
-+ err = h_permission(h_inode, mask, &br->br_path,
-+ br->br_perm);
++ IiMustWriteLock(inode);
++
++ hinode = au_hinode(au_ii(inode), bindex);
++ AuDebugOn(hinode->hi_whdentry);
++ hinode->hi_whdentry = h_wh;
++}
++
++void au_update_iigen(struct inode *inode, int half)
++{
++ struct au_iinfo *iinfo;
++ struct au_iigen *iigen;
++ unsigned int sigen;
++
++ sigen = au_sigen(inode->i_sb);
++ iinfo = au_ii(inode);
++ iigen = &iinfo->ii_generation;
++ spin_lock(&iigen->ig_spin);
++ iigen->ig_generation = sigen;
++ if (half)
++ au_ig_fset(iigen->ig_flags, HALF_REFRESHED);
++ else
++ au_ig_fclr(iigen->ig_flags, HALF_REFRESHED);
++ spin_unlock(&iigen->ig_spin);
++}
++
++/* it may be called at remount time, too */
++void au_update_ibrange(struct inode *inode, int do_put_zero)
++{
++ struct au_iinfo *iinfo;
++ aufs_bindex_t bindex, bbot;
++
++ AuDebugOn(au_is_bad_inode(inode));
++ IiMustWriteLock(inode);
++
++ iinfo = au_ii(inode);
++ if (do_put_zero && iinfo->ii_btop >= 0) {
++ for (bindex = iinfo->ii_btop; bindex <= iinfo->ii_bbot;
++ bindex++) {
++ struct inode *h_i;
++
++ h_i = au_hinode(iinfo, bindex)->hi_inode;
++ if (h_i
++ && !h_i->i_nlink
++ && !(h_i->i_state & I_LINKABLE))
++ au_set_h_iptr(inode, bindex, NULL, 0);
+ }
+ }
+
-+out:
-+ ii_read_unlock(inode);
-+ si_read_unlock(sb);
-+ return err;
++ iinfo->ii_btop = -1;
++ iinfo->ii_bbot = -1;
++ bbot = au_sbbot(inode->i_sb);
++ for (bindex = 0; bindex <= bbot; bindex++)
++ if (au_hinode(iinfo, bindex)->hi_inode) {
++ iinfo->ii_btop = bindex;
++ break;
++ }
++ if (iinfo->ii_btop >= 0)
++ for (bindex = bbot; bindex >= iinfo->ii_btop; bindex--)
++ if (au_hinode(iinfo, bindex)->hi_inode) {
++ iinfo->ii_bbot = bindex;
++ break;
++ }
++ AuDebugOn(iinfo->ii_btop > iinfo->ii_bbot);
++}
++
++/* ---------------------------------------------------------------------- */
++
++void au_icntnr_init_once(void *_c)
++{
++ struct au_icntnr *c = _c;
++ struct au_iinfo *iinfo = &c->iinfo;
++
++ spin_lock_init(&iinfo->ii_generation.ig_spin);
++ au_rw_init(&iinfo->ii_rwsem);
++ inode_init_once(&c->vfs_inode);
++}
++
++void au_hinode_init(struct au_hinode *hinode)
++{
++ hinode->hi_inode = NULL;
++ hinode->hi_id = -1;
++ au_hn_init(hinode);
++ hinode->hi_whdentry = NULL;
++}
++
++int au_iinfo_init(struct inode *inode)
++{
++ struct au_iinfo *iinfo;
++ struct super_block *sb;
++ struct au_hinode *hi;
++ int nbr, i;
++
++ sb = inode->i_sb;
++ iinfo = &(container_of(inode, struct au_icntnr, vfs_inode)->iinfo);
++ nbr = au_sbbot(sb) + 1;
++ if (unlikely(nbr <= 0))
++ nbr = 1;
++ hi = kmalloc_array(nbr, sizeof(*iinfo->ii_hinode), GFP_NOFS);
++ if (hi) {
++ au_lcnt_inc(&au_sbi(sb)->si_ninodes);
++
++ iinfo->ii_hinode = hi;
++ for (i = 0; i < nbr; i++, hi++)
++ au_hinode_init(hi);
++
++ iinfo->ii_generation.ig_generation = au_sigen(sb);
++ iinfo->ii_btop = -1;
++ iinfo->ii_bbot = -1;
++ iinfo->ii_vdir = NULL;
++ return 0;
++ }
++ return -ENOMEM;
+}
+
-+/* ---------------------------------------------------------------------- */
-+
-+static struct dentry *aufs_lookup(struct inode *dir, struct dentry *dentry,
-+ unsigned int flags)
++int au_hinode_realloc(struct au_iinfo *iinfo, int nbr, int may_shrink)
+{
-+ struct dentry *ret, *parent;
-+ struct inode *inode;
-+ struct super_block *sb;
-+ int err, npositive;
++ int err, i;
++ struct au_hinode *hip;
+
-+ IMustLock(dir);
++ AuRwMustWriteLock(&iinfo->ii_rwsem);
+
-+ /* todo: support rcu-walk? */
-+ ret = ERR_PTR(-ECHILD);
-+ if (flags & LOOKUP_RCU)
-+ goto out;
++ err = -ENOMEM;
++ hip = au_krealloc(iinfo->ii_hinode, sizeof(*hip) * nbr, GFP_NOFS,
++ may_shrink);
++ if (hip) {
++ iinfo->ii_hinode = hip;
++ i = iinfo->ii_bbot + 1;
++ hip += i;
++ for (; i < nbr; i++, hip++)
++ au_hinode_init(hip);
++ err = 0;
++ }
+
-+ ret = ERR_PTR(-ENAMETOOLONG);
-+ if (unlikely(dentry->d_name.len > AUFS_MAX_NAMELEN))
-+ goto out;
++ return err;
++}
+
-+ sb = dir->i_sb;
-+ err = si_read_lock(sb, AuLock_FLUSH | AuLock_NOPLM);
-+ ret = ERR_PTR(err);
-+ if (unlikely(err))
-+ goto out;
++void au_iinfo_fin(struct inode *inode)
++{
++ struct au_iinfo *iinfo;
++ struct au_hinode *hi;
++ struct super_block *sb;
++ aufs_bindex_t bindex, bbot;
++ const unsigned char unlinked = !inode->i_nlink;
+
-+ err = au_di_init(dentry);
-+ ret = ERR_PTR(err);
-+ if (unlikely(err))
-+ goto out_si;
++ AuDebugOn(au_is_bad_inode(inode));
+
-+ 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;
++ sb = inode->i_sb;
++ au_lcnt_dec(&au_sbi(sb)->si_ninodes);
++ if (si_pid_test(sb))
++ au_xino_delete_inode(inode, unlinked);
++ else {
++ /*
++ * it is safe to hide the dependency between sbinfo and
++ * sb->s_umount.
++ */
++ lockdep_off();
++ si_noflush_read_lock(sb);
++ au_xino_delete_inode(inode, unlinked);
++ si_read_unlock(sb);
++ lockdep_on();
+ }
-+ 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;
-+ }
-+ }
++ iinfo = au_ii(inode);
++ if (iinfo->ii_vdir)
++ au_vdir_free(iinfo->ii_vdir);
+
-+ if (inode)
-+ atomic_inc(&inode->i_count);
-+ ret = d_splice_alias(inode, dentry);
-+#if 0 /* reserved for future use */
-+ 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;
++ bindex = iinfo->ii_btop;
++ if (bindex >= 0) {
++ hi = au_hinode(iinfo, bindex);
++ bbot = iinfo->ii_bbot;
++ while (bindex++ <= bbot) {
++ if (hi->hi_inode)
++ au_hiput(hi);
++ hi++;
+ }
+ }
-+
-+out_unlock:
-+ di_write_unlock(dentry);
-+out_si:
-+ si_read_unlock(sb);
-+out:
-+ return ret;
++ au_kfree_rcu(iinfo->ii_hinode);
++ AuRwDestroy(&iinfo->ii_rwsem);
+}
-+
-+/* ---------------------------------------------------------------------- */
-+
+diff -urN /usr/share/empty/fs/aufs/inode.c linux/fs/aufs/inode.c
+--- /usr/share/empty/fs/aufs/inode.c 1970-01-01 01:00:00.000000000 +0100
++++ linux/fs/aufs/inode.c 2023-10-31 09:31:04.199880750 +0100
+@@ -0,0 +1,531 @@
++// SPDX-License-Identifier: GPL-2.0
+/*
-+ * 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()
++ * Copyright (C) 2005-2022 Junjiro R. Okajima
+ *
-+ * 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
++ * 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.
+ *
-+ * au_aopen_no_open()
-+ * + finish_no_open()
++ * 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/>.
+ */
+
-+struct aopen_node {
-+ struct hlist_bl_node hblist;
-+ struct file *file, *h_file;
-+};
++/*
++ * inode functions
++ */
+
-+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
-+ };
++#include <linux/iversion.h>
++#include "aufs.h"
+
-+ 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); */
++struct inode *au_igrab(struct inode *inode)
++{
++ if (inode) {
++ AuDebugOn(!atomic_read(&inode->i_count));
++ ihold(inode);
++ }
++ return inode;
++}
+
-+ return au_do_open(file, &args);
++static void au_refresh_hinode_attr(struct inode *inode, int do_version)
++{
++ au_cpup_attr_all(inode, /*force*/0);
++ au_update_iigen(inode, /*half*/1);
++ if (do_version)
++ inode_inc_iversion(inode);
+}
+
-+static int au_aopen_do_open(struct file *file, struct dentry *dentry,
-+ struct aopen_node *aopen_node)
++static int au_ii_refresh(struct inode *inode, int *update)
+{
-+ int err;
-+ struct hlist_bl_head *aopen;
++ int err, e, nbr;
++ umode_t type;
++ aufs_bindex_t bindex, new_bindex;
++ struct super_block *sb;
++ struct au_iinfo *iinfo;
++ struct au_hinode *p, *q, tmp;
+
-+ 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" : "");
++ AuDebugOn(au_is_bad_inode(inode));
++ IiMustWriteLock(inode);
++
++ *update = 0;
++ sb = inode->i_sb;
++ nbr = au_sbbot(sb) + 1;
++ type = inode->i_mode & S_IFMT;
++ iinfo = au_ii(inode);
++ err = au_hinode_realloc(iinfo, nbr, /*may_shrink*/0);
++ if (unlikely(err))
++ goto out;
++
++ AuDebugOn(iinfo->ii_btop < 0);
++ p = au_hinode(iinfo, iinfo->ii_btop);
++ for (bindex = iinfo->ii_btop; bindex <= iinfo->ii_bbot;
++ bindex++, p++) {
++ if (!p->hi_inode)
++ continue;
++
++ AuDebugOn(type != (p->hi_inode->i_mode & S_IFMT));
++ new_bindex = au_br_index(sb, p->hi_id);
++ if (new_bindex == bindex)
++ continue;
++
++ if (new_bindex < 0) {
++ *update = 1;
++ au_hiput(p);
++ p->hi_inode = NULL;
++ continue;
++ }
++
++ if (new_bindex < iinfo->ii_btop)
++ iinfo->ii_btop = new_bindex;
++ if (iinfo->ii_bbot < new_bindex)
++ iinfo->ii_bbot = new_bindex;
++ /* swap two lower inode, and loop again */
++ q = au_hinode(iinfo, new_bindex);
++ tmp = *q;
++ *q = *p;
++ *p = tmp;
++ if (tmp.hi_inode) {
++ bindex--;
++ p--;
++ }
++ }
++ au_update_ibrange(inode, /*do_put_zero*/0);
++ au_hinode_realloc(iinfo, nbr, /*may_shrink*/1); /* harmless if err */
++ e = au_dy_irefresh(inode);
++ if (unlikely(e && !err))
++ err = e;
+
++out:
+ AuTraceErr(err);
+ return err;
+}
+
-+static int au_aopen_no_open(struct file *file, struct dentry *dentry)
++void au_refresh_iop(struct inode *inode, int force_getattr)
+{
-+ int err;
++ int type;
++ struct au_sbinfo *sbi = au_sbi(inode->i_sb);
++ const struct inode_operations *iop
++ = force_getattr ? aufs_iop : sbi->si_iop_array;
+
-+ AuLabel(here);
-+ dget(dentry);
-+ err = finish_no_open(file, dentry);
++ if (inode->i_op == iop)
++ return;
+
-+ AuTraceErr(err);
-+ return err;
++ switch (inode->i_mode & S_IFMT) {
++ case S_IFDIR:
++ type = AuIop_DIR;
++ break;
++ case S_IFLNK:
++ type = AuIop_SYMLINK;
++ break;
++ default:
++ type = AuIop_OTHER;
++ break;
++ }
++
++ inode->i_op = iop + type;
++ /* unnecessary smp_wmb() */
+}
+
-+static int aufs_atomic_open(struct inode *dir, struct dentry *dentry,
-+ struct file *file, unsigned int open_flag,
-+ umode_t create_mode)
++int au_refresh_hinode_self(struct inode *inode)
+{
-+ 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
-+ };
++ int err, update;
+
-+ IMustLock(dir);
-+ AuDbg("open_flag 0%o\n", open_flag);
-+ AuDbgDentry(dentry);
++ err = au_ii_refresh(inode, &update);
++ if (!err)
++ au_refresh_hinode_attr(inode, update && S_ISDIR(inode->i_mode));
+
-+ 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);
-+ }
++ AuTraceErr(err);
++ return err;
++}
+
-+ 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 */
-+ }
++int au_refresh_hinode(struct inode *inode, struct dentry *dentry)
++{
++ int err, e, update;
++ unsigned int flags;
++ umode_t mode;
++ aufs_bindex_t bindex, bbot;
++ unsigned char isdir;
++ struct au_hinode *p;
++ struct au_iinfo *iinfo;
+
-+ err = aufs_read_lock(dentry, AuLock_DW | AuLock_FLUSH | AuLock_GEN);
++ err = au_ii_refresh(inode, &update);
+ 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;
++ update = 0;
++ iinfo = au_ii(inode);
++ p = au_hinode(iinfo, iinfo->ii_btop);
++ mode = (inode->i_mode & S_IFMT);
++ isdir = S_ISDIR(mode);
++ flags = au_hi_flags(inode, isdir);
++ bbot = au_dbbot(dentry);
++ for (bindex = au_dbtop(dentry); bindex <= bbot; bindex++) {
++ struct inode *h_i, *h_inode;
++ struct dentry *h_d;
+
-+ 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;
-+ }
++ h_d = au_h_dptr(dentry, bindex);
++ if (!h_d || d_is_negative(h_d))
++ continue;
+
-+ 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);
++ h_inode = d_inode(h_d);
++ AuDebugOn(mode != (h_inode->i_mode & S_IFMT));
++ if (iinfo->ii_btop <= bindex && bindex <= iinfo->ii_bbot) {
++ h_i = au_h_iptr(inode, bindex);
++ if (h_i) {
++ if (h_i == h_inode)
++ continue;
++ err = -EIO;
++ break;
++ }
++ }
++ if (bindex < iinfo->ii_btop)
++ iinfo->ii_btop = bindex;
++ if (iinfo->ii_bbot < bindex)
++ iinfo->ii_bbot = bindex;
++ au_set_h_iptr(inode, bindex, au_igrab(h_inode), flags);
++ update = 1;
+ }
-+ goto out_sb; /* success */
++ au_update_ibrange(inode, /*do_put_zero*/0);
++ e = au_dy_irefresh(inode);
++ if (unlikely(e && !err))
++ err = e;
++ if (!err)
++ au_refresh_hinode_attr(inode, update && isdir);
+
-+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)
++static int set_inode(struct inode *inode, struct dentry *dentry)
+{
+ int err;
-+ struct dentry *h_parent;
-+ struct inode *h_dir;
++ unsigned int flags;
++ umode_t mode;
++ aufs_bindex_t bindex, btop, btail;
++ unsigned char isdir;
++ struct dentry *h_dentry;
++ struct inode *h_inode;
++ struct au_iinfo *iinfo;
++ const struct inode_operations *iop;
+
-+ if (add_entry)
-+ IMustLock(d_inode(parent));
-+ else
-+ di_write_lock_parent(parent);
++ IiMustWriteLock(inode);
+
+ 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();
++ isdir = 0;
++ iop = au_sbi(inode->i_sb)->si_iop_array;
++ btop = au_dbtop(dentry);
++ h_dentry = au_h_dptr(dentry, btop);
++ h_inode = d_inode(h_dentry);
++ mode = h_inode->i_mode;
++ switch (mode & S_IFMT) {
++ case S_IFREG:
++ btail = au_dbtail(dentry);
++ inode->i_op = iop + AuIop_OTHER;
++ inode->i_fop = &aufs_file_fop;
++ err = au_dy_iaop(inode, btop, h_inode);
++ if (unlikely(err))
++ goto out;
++ break;
++ case S_IFDIR:
++ isdir = 1;
++ btail = au_dbtaildir(dentry);
++ inode->i_op = iop + AuIop_DIR;
++ inode->i_fop = &aufs_dir_fop;
++ break;
++ case S_IFLNK:
++ btail = au_dbtail(dentry);
++ inode->i_op = iop + AuIop_SYMLINK;
++ break;
++ case S_IFBLK:
++ case S_IFCHR:
++ case S_IFIFO:
++ case S_IFSOCK:
++ btail = au_dbtail(dentry);
++ inode->i_op = iop + AuIop_OTHER;
++ init_special_inode(inode, mode, h_inode->i_rdev);
++ break;
++ default:
++ AuIOErr("Unknown file type 0%o\n", mode);
++ err = -EIO;
++ goto out;
+ }
-+ 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);
-+ }
++ /* do not set hnotify for whiteouted dirs (SHWH mode) */
++ flags = au_hi_flags(inode, isdir);
++ if (au_opt_test(au_mntflags(dentry->d_sb), SHWH)
++ && au_ftest_hi(flags, HNOTIFY)
++ && dentry->d_name.len > AUFS_WH_PFX_LEN
++ && !memcmp(dentry->d_name.name, AUFS_WH_PFX, AUFS_WH_PFX_LEN))
++ au_fclr_hi(flags, HNOTIFY);
++ iinfo = au_ii(inode);
++ iinfo->ii_btop = btop;
++ iinfo->ii_bbot = btail;
++ for (bindex = btop; bindex <= btail; bindex++) {
++ h_dentry = au_h_dptr(dentry, bindex);
++ if (h_dentry)
++ au_set_h_iptr(inode, bindex,
++ au_igrab(d_inode(h_dentry)), flags);
+ }
++ au_cpup_attr_all(inode, /*force*/1);
++ /*
++ * to force calling aufs_get_inode_acl() every time,
++ * do not call cache_no_acl() for aufs inode.
++ */
+
-+ if (!add_entry)
-+ di_write_unlock(parent);
-+ if (!err)
-+ err = bcpup; /* success */
-+
-+ AuTraceErr(err);
++out:
+ 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.
++ * successful returns with iinfo write_locked
++ * minus: errno
++ * zero: success, matched
++ * plus: no error, but unmatched
+ */
-+int au_wr_dir(struct dentry *dentry, struct dentry *src_dentry,
-+ struct au_wr_dir_args *args)
++static int reval_inode(struct inode *inode, struct dentry *dentry)
+{
+ 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;
++ unsigned int gen, igflags;
++ aufs_bindex_t bindex, bbot;
++ struct inode *h_inode, *h_dinode;
++ struct dentry *h_dentry;
+
-+ 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;
-+ }
++ /*
++ * before this function, if aufs got any iinfo lock, it must be only
++ * one, the parent dir.
++ * it can happen by UDBA and the obsoleted inode number.
++ */
++ err = -EIO;
++ if (unlikely(inode->i_ino == parent_ino(dentry)))
++ goto out;
+
-+ 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)));
-+ }
++ err = 1;
++ ii_write_lock_new_child(inode);
++ h_dentry = au_h_dptr(dentry, au_dbtop(dentry));
++ h_dinode = d_inode(h_dentry);
++ bbot = au_ibbot(inode);
++ for (bindex = au_ibtop(inode); bindex <= bbot; bindex++) {
++ h_inode = au_h_iptr(inode, bindex);
++ if (!h_inode || h_inode != h_dinode)
++ continue;
+
-+ AuDbg("btop %d, bcpup %d\n", btop, bcpup);
-+ err = bcpup;
-+ if (bcpup == btop)
-+ goto out; /* success */
++ err = 0;
++ gen = au_iigen(inode, &igflags);
++ if (gen == au_digen(dentry)
++ && !au_ig_ftest(igflags, HALF_REFRESHED))
++ break;
+
-+ /* 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));
++ /* fully refresh inode using dentry */
++ err = au_refresh_hinode(inode, dentry);
++ if (!err)
++ au_update_iigen(inode, /*half*/0);
++ break;
+ }
+
++ if (unlikely(err))
++ ii_write_unlock(inode);
+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 au_ino(struct super_block *sb, aufs_bindex_t bindex, ino_t h_ino,
++ unsigned int d_type, ino_t *ino)
+{
-+ int err;
-+
-+ err = 0;
-+ if (!p->hdir)
-+ goto out;
++ int err, idx;
++ const int isnondir = d_type != DT_DIR;
+
-+ /* even if an error happens later, keep this lock */
-+ au_hn_inode_lock_nested(p->hdir, p->lsc_hi);
++ /* prevent hardlinked inode number from race condition */
++ if (isnondir) {
++ err = au_xinondir_enter(sb, bindex, h_ino, &idx);
++ if (unlikely(err))
++ goto out;
++ }
+
-+ err = -EBUSY;
-+ if (unlikely(p->hdir->hi_inode != d_inode(p->h_parent)))
-+ goto out;
++ err = au_xino_read(sb, bindex, h_ino, ino);
++ if (unlikely(err))
++ goto out_xinondir;
+
-+ err = 0;
-+ if (p->h_dentry)
-+ err = au_h_verify(p->h_dentry, p->udba, p->hdir->hi_inode,
-+ p->h_parent, p->br);
++ if (!*ino) {
++ err = -EIO;
++ *ino = au_xino_new_ino(sb);
++ if (unlikely(!*ino))
++ goto out_xinondir;
++ err = au_xino_write(sb, bindex, h_ino, *ino);
++ if (unlikely(err))
++ goto out_xinondir;
++ }
+
++out_xinondir:
++ if (isnondir && idx >= 0)
++ au_xinondir_leave(sb, bindex, h_ino, idx);
+out:
+ return err;
+}
+
-+int au_pin_hdir_relock(struct au_pin *p)
++/* successful returns with iinfo write_locked */
++/* todo: return with unlocked? */
++struct inode *au_new_inode(struct dentry *dentry, int must_new)
+{
-+ int err, i;
-+ struct inode *h_i;
-+ struct dentry *h_d[] = {
-+ p->h_dentry,
-+ p->h_parent
-+ };
++ struct inode *inode, *h_inode;
++ struct dentry *h_dentry;
++ struct super_block *sb;
++ ino_t h_ino, ino;
++ int err, idx, hlinked;
++ aufs_bindex_t btop;
+
-+ err = au_pin_hdir_lock(p);
++ sb = dentry->d_sb;
++ btop = au_dbtop(dentry);
++ h_dentry = au_h_dptr(dentry, btop);
++ h_inode = d_inode(h_dentry);
++ h_ino = h_inode->i_ino;
++ hlinked = !d_is_dir(h_dentry) && h_inode->i_nlink > 1;
++
++new_ino:
++ /*
++ * stop 'race'-ing between hardlinks under different
++ * parents.
++ */
++ if (hlinked) {
++ err = au_xinondir_enter(sb, btop, h_ino, &idx);
++ inode = ERR_PTR(err);
++ if (unlikely(err))
++ goto out;
++ }
++
++ err = au_xino_read(sb, btop, h_ino, &ino);
++ inode = ERR_PTR(err);
+ if (unlikely(err))
-+ goto out;
++ goto out_xinondir;
+
-+ 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;
++ if (!ino) {
++ ino = au_xino_new_ino(sb);
++ if (unlikely(!ino)) {
++ inode = ERR_PTR(-EIO);
++ goto out_xinondir;
+ }
+ }
+
-+out:
-+ return err;
-+}
++ AuDbg("i%lu\n", (unsigned long)ino);
++ inode = au_iget_locked(sb, ino);
++ err = PTR_ERR(inode);
++ if (IS_ERR(inode))
++ goto out_xinondir;
+
-+static void au_pin_hdir_set_owner(struct au_pin *p, struct task_struct *task)
-+{
-+ atomic_long_set(&p->hdir->hi_inode->i_rwsem.owner, (long)task);
-+}
++ AuDbg("%lx, new %d\n", inode->i_state, !!(inode->i_state & I_NEW));
++ if (inode->i_state & I_NEW) {
++ ii_write_lock_new_child(inode);
++ err = set_inode(inode, dentry);
++ if (!err) {
++ unlock_new_inode(inode);
++ goto out_xinondir; /* success */
++ }
+
-+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);
++ /*
++ * iget_failed() calls iput(), but we need to call
++ * ii_write_unlock() after iget_failed(). so dirty hack for
++ * i_count.
++ */
++ atomic_inc(&inode->i_count);
++ iget_failed(inode);
++ ii_write_unlock(inode);
++ au_xino_write(sb, btop, h_ino, /*ino*/0);
++ /* ignore this error */
++ goto out_iput;
++ } else if (!must_new && !IS_DEADDIR(inode) && inode->i_nlink) {
++ /*
++ * horrible race condition between lookup, readdir and copyup
++ * (or something).
++ */
++ if (hlinked && idx >= 0)
++ au_xinondir_leave(sb, btop, h_ino, idx);
++ err = reval_inode(inode, dentry);
++ if (unlikely(err < 0)) {
++ hlinked = 0;
++ goto out_iput;
++ }
++ if (!err)
++ goto out; /* success */
++ else if (hlinked && idx >= 0) {
++ err = au_xinondir_enter(sb, btop, h_ino, &idx);
++ if (unlikely(err)) {
++ iput(inode);
++ inode = ERR_PTR(err);
++ goto out;
++ }
++ }
++ }
++
++ if (unlikely(au_test_fs_unique_ino(h_inode)))
++ AuWarn1("Warning: Un-notified UDBA or repeatedly renamed dir,"
++ " b%d, %s, %pd, hi%lu, i%lu.\n",
++ btop, au_sbtype(h_dentry->d_sb), dentry,
++ (unsigned long)h_ino, (unsigned long)ino);
++ ino = 0;
++ err = au_xino_write(sb, btop, h_ino, /*ino*/0);
++ if (!err) {
++ iput(inode);
++ if (hlinked && idx >= 0)
++ au_xinondir_leave(sb, btop, h_ino, idx);
++ goto new_ino;
+ }
++
++out_iput:
++ iput(inode);
++ inode = ERR_PTR(err);
++out_xinondir:
++ if (hlinked && idx >= 0)
++ au_xinondir_leave(sb, btop, h_ino, idx);
++out:
++ return inode;
+}
+
-+void au_pin_hdir_release(struct au_pin *p)
++/* ---------------------------------------------------------------------- */
++
++int au_test_ro(struct super_block *sb, aufs_bindex_t bindex,
++ struct inode *inode)
+{
-+ if (p->hdir) {
-+ au_pin_hdir_set_owner(p, p->task);
-+ rwsem_release(&p->hdir->hi_inode->i_rwsem.dep_map, _RET_IP_);
++ int err;
++ struct inode *hi;
++
++ err = au_br_rdonly(au_sbr(sb, bindex));
++
++ /* pseudo-link after flushed may happen out of bounds */
++ if (!err
++ && inode
++ && au_ibtop(inode) <= bindex
++ && bindex <= au_ibbot(inode)) {
++ /*
++ * permission check is unnecessary since vfsub routine
++ * will be called later
++ */
++ hi = au_h_iptr(inode, bindex);
++ if (hi)
++ err = IS_IMMUTABLE(hi) ? -EROFS : 0;
+ }
++
++ return err;
+}
+
-+struct dentry *au_pinned_h_parent(struct au_pin *pin)
++int au_test_h_perm(struct mnt_idmap *h_idmap, struct inode *h_inode,
++ int mask)
+{
-+ if (pin && pin->parent)
-+ return au_h_dptr(pin->parent, pin->bindex);
-+ return NULL;
++ if (uid_eq(current_fsuid(), GLOBAL_ROOT_UID))
++ return 0;
++ return inode_permission(h_idmap, h_inode, mask);
+}
+
-+void au_unpin(struct au_pin *p)
++int au_test_h_perm_sio(struct mnt_idmap *h_idmap, struct inode *h_inode,
++ int mask)
+{
-+ 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 */
++ if (au_test_nfs(h_inode->i_sb)
++ && (mask & MAY_WRITE)
++ && S_ISDIR(h_inode->i_mode))
++ mask |= MAY_READ; /* force permission check */
++ return au_test_h_perm(h_idmap, h_inode, mask);
+}
+diff -urN /usr/share/empty/fs/aufs/inode.h linux/fs/aufs/inode.h
+--- /usr/share/empty/fs/aufs/inode.h 1970-01-01 01:00:00.000000000 +0100
++++ linux/fs/aufs/inode.h 2024-03-10 23:40:47.086476782 +0100
+@@ -0,0 +1,707 @@
++/* SPDX-License-Identifier: GPL-2.0 */
++/*
++ * Copyright (C) 2005-2022 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/>.
++ */
+
-+int au_do_pin(struct au_pin *p)
-+{
-+ int err;
-+ struct super_block *sb;
-+ struct inode *h_dir;
++/*
++ * inode operations
++ */
+
-+ 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;
-+ }
++#ifndef __AUFS_INODE_H__
++#define __AUFS_INODE_H__
+
-+ p->h_dentry = NULL;
-+ if (p->bindex <= au_dbbot(p->dentry))
-+ p->h_dentry = au_h_dptr(p->dentry, p->bindex);
++#ifdef __KERNEL__
+
-+ p->parent = dget_parent(p->dentry);
-+ if (!au_ftest_pin(p->flags, DI_LOCKED))
-+ di_read_lock(p->parent, AuLock_IR, p->lsc_di);
++#include <linux/fsnotify.h>
++#include "rwsem.h"
+
-+ 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;
++struct vfsmount;
+
-+ /*
-+ * 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;
-+ }
++struct au_hnotify {
++#ifdef CONFIG_AUFS_HNOTIFY
++#ifdef CONFIG_AUFS_HFSNOTIFY
++ /* never use fsnotify_add_vfsmount_mark() */
++ struct fsnotify_mark hn_mark;
++#endif
++ struct inode *hn_aufs_inode; /* no get/put */
++ struct rcu_head rcu;
++#endif
++} ____cacheline_aligned_in_smp;
+
-+ 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;
-+ }
-+ }
++struct au_hinode {
++ struct inode *hi_inode;
++ aufs_bindex_t hi_id;
++#ifdef CONFIG_AUFS_HNOTIFY
++ struct au_hnotify *hi_notify;
++#endif
+
-+ au_igrab(h_dir);
-+ err = au_pin_hdir_lock(p);
-+ if (!err)
-+ goto out; /* success */
++ /* reference to the copied-up whiteout with get/put */
++ struct dentry *hi_whdentry;
++};
+
-+ au_unpin(p);
++/* ig_flags */
++#define AuIG_HALF_REFRESHED 1
++#define au_ig_ftest(flags, name) ((flags) & AuIG_##name)
++#define au_ig_fset(flags, name) \
++ do { (flags) |= AuIG_##name; } while (0)
++#define au_ig_fclr(flags, name) \
++ do { (flags) &= ~AuIG_##name; } while (0)
+
-+out_err:
-+ pr_err("err %d\n", err);
-+ err = au_busy_or_stale();
-+out:
-+ return err;
-+}
++struct au_iigen {
++ spinlock_t ig_spin;
++ __u32 ig_generation, ig_flags;
++};
+
-+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;
++struct au_vdir;
++struct au_iinfo {
++ struct au_iigen ii_generation;
++ struct super_block *ii_hsb1; /* no get/put */
+
-+ p->parent = NULL;
-+ p->hdir = NULL;
-+ p->h_mnt = NULL;
++ struct au_rwsem ii_rwsem;
++ aufs_bindex_t ii_btop, ii_bbot;
++ __u32 ii_higen;
++ struct au_hinode *ii_hinode;
++ struct au_vdir *ii_vdir;
++};
+
-+ p->h_dentry = NULL;
-+ p->h_parent = NULL;
-+ p->br = NULL;
-+ p->task = current;
-+}
++struct au_icntnr {
++ struct au_iinfo iinfo;
++ struct inode vfs_inode;
++ struct hlist_bl_node plink;
++ struct rcu_head rcu;
++} ____cacheline_aligned_in_smp;
+
-+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);
-+}
++/* au_pin flags */
++#define AuPin_DI_LOCKED BIT(0)
++#define AuPin_MNT_WRITE BIT(1)
++#define au_ftest_pin(flags, name) ((flags) & AuPin_##name)
++#define au_fset_pin(flags, name) \
++ do { (flags) |= AuPin_##name; } while (0)
++#define au_fclr_pin(flags, name) \
++ do { (flags) &= ~AuPin_##name; } while (0)
+
-+/* ---------------------------------------------------------------------- */
++struct au_pin {
++ /* input */
++ struct dentry *dentry;
++ unsigned int udba;
++ unsigned char lsc_di, lsc_hi, flags;
++ aufs_bindex_t bindex;
+
-+/*
-+ * ->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;
++ /* output */
+ struct dentry *parent;
++ struct au_hinode *hdir;
++ struct vfsmount *h_mnt;
+
-+ 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);
-+ }
++ /* temporary unlock/relock for copyup */
++ struct dentry *h_dentry, *h_parent;
++ struct au_branch *br;
++ struct task_struct *task;
++};
+
-+ AuTraceErr(err);
-+ return err;
-+}
++void au_pin_hdir_unlock(struct au_pin *p);
++int au_pin_hdir_lock(struct au_pin *p);
++int au_pin_hdir_relock(struct au_pin *p);
++void au_pin_hdir_acquire_nest(struct au_pin *p);
++void au_pin_hdir_release(struct au_pin *p);
+
-+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);
++static inline struct au_iinfo *au_ii(struct inode *inode)
++{
++ BUG_ON(is_bad_inode(inode));
++ return &(container_of(inode, struct au_icntnr, vfs_inode)->iinfo);
++}
+
-+ 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;
++/* inode.c */
++struct inode *au_igrab(struct inode *inode);
++void au_refresh_iop(struct inode *inode, int force_getattr);
++int au_refresh_hinode_self(struct inode *inode);
++int au_refresh_hinode(struct inode *inode, struct dentry *dentry);
++int au_ino(struct super_block *sb, aufs_bindex_t bindex, ino_t h_ino,
++ unsigned int d_type, ino_t *ino);
++struct inode *au_new_inode(struct dentry *dentry, int must_new);
++int au_test_ro(struct super_block *sb, aufs_bindex_t bindex,
++ struct inode *inode);
++int au_test_h_perm(struct mnt_idmap *h_idmap, struct inode *h_inode,
++ int mask);
++int au_test_h_perm_sio(struct mnt_idmap *h_idmap, struct inode *h_inode,
++ int mask);
+
-+ 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);
-+ }
++static inline int au_wh_ino(struct super_block *sb, aufs_bindex_t bindex,
++ ino_t h_ino, unsigned int d_type, ino_t *ino)
++{
++#ifdef CONFIG_AUFS_SHWH
++ return au_ino(sb, bindex, h_ino, d_type, ino);
++#else
++ return 0;
++#endif
++}
+
-+ 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? */
-+ }
-+ }
++/* i_op.c */
++enum {
++ AuIop_SYMLINK,
++ AuIop_DIR,
++ AuIop_OTHER,
++ AuIop_Last
++};
++extern struct inode_operations aufs_iop[AuIop_Last], /* not const */
++ aufs_iop_nogetattr[AuIop_Last];
+
-+ 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 */
++/* au_wr_dir flags */
++#define AuWrDir_ADD_ENTRY BIT(0)
++#define AuWrDir_ISDIR BIT(1)
++#define AuWrDir_TMPFILE BIT(2)
++#define au_ftest_wrdir(flags, name) ((flags) & AuWrDir_##name)
++#define au_fset_wrdir(flags, name) \
++ do { (flags) |= AuWrDir_##name; } while (0)
++#define au_fclr_wrdir(flags, name) \
++ do { (flags) &= ~AuWrDir_##name; } while (0)
+
-+ 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 */
++struct au_wr_dir_args {
++ aufs_bindex_t force_btgt;
++ unsigned char flags;
++};
++int au_wr_dir(struct dentry *dentry, struct dentry *src_dentry,
++ struct au_wr_dir_args *args);
+
-+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;
-+}
++struct dentry *au_pinned_h_parent(struct au_pin *pin);
++void au_pin_init(struct au_pin *pin, struct dentry *dentry,
++ aufs_bindex_t bindex, int lsc_di, int lsc_hi,
++ unsigned int udba, unsigned char flags);
++int au_pin(struct au_pin *pin, struct dentry *dentry, aufs_bindex_t bindex,
++ unsigned int udba, unsigned char flags) __must_check;
++int au_do_pin(struct au_pin *pin) __must_check;
++void au_unpin(struct au_pin *pin);
++int au_reval_for_attr(struct dentry *dentry, unsigned int sigen);
+
-+static int aufs_setattr(struct mnt_idmap *idmap, struct dentry *dentry,
-+ struct iattr *ia)
-+{
-+ int err;
-+ struct inode *inode, *delegated;
-+ struct super_block *sb;
-+ struct file *file;
-+ struct au_icpup_args *a;
-+ struct mnt_idmap *h_idmap;
++#define AuIcpup_DID_CPUP 1
++#define au_ftest_icpup(flags, name) ((flags) & AuIcpup_##name)
++#define au_fset_icpup(flags, name) \
++ do { (flags) |= AuIcpup_##name; } while (0)
++#define au_fclr_icpup(flags, name) \
++ do { (flags) &= ~AuIcpup_##name; } while (0)
+
-+ inode = d_inode(dentry);
-+ IMustLock(inode);
++struct au_icpup_args {
++ unsigned char flags;
++ unsigned char pin_flags;
++ aufs_bindex_t btgt;
++ unsigned int udba;
++ struct au_pin pin;
++ struct path h_path;
++ struct inode *h_inode;
++};
+
-+ err = setattr_prepare(idmap, dentry, ia);
-+ if (unlikely(err))
-+ goto out;
++int au_pin_and_icpup(struct dentry *dentry, struct iattr *ia,
++ struct au_icpup_args *a);
+
-+ err = -ENOMEM;
-+ a = kzalloc(sizeof(*a), GFP_NOFS);
-+ if (unlikely(!a))
-+ goto out;
++int au_h_path_getattr(struct dentry *dentry, struct inode *inode, int force,
++ struct path *h_path, int locked);
+
-+ if (ia->ia_valid & (ATTR_KILL_SUID | ATTR_KILL_SGID))
-+ ia->ia_valid &= ~ATTR_MODE;
++/* i_op_add.c */
++int au_may_add(struct dentry *dentry, aufs_bindex_t bindex,
++ struct dentry *h_parent, int isdir);
++int aufs_mknod(struct mnt_idmap *idmap, struct inode *dir,
++ struct dentry *dentry, umode_t mode, dev_t dev);
++int aufs_symlink(struct mnt_idmap *idmap, struct inode *dir,
++ struct dentry *dentry, const char *symname);
++int aufs_create(struct mnt_idmap *idmap, struct inode *dir,
++ struct dentry *dentry, umode_t mode, bool want_excl);
++struct vfsub_aopen_args;
++int au_aopen_or_create(struct inode *dir, struct dentry *dentry,
++ struct vfsub_aopen_args *args);
++int aufs_tmpfile(struct mnt_idmap *idmap, struct inode *dir,
++ struct file *file, umode_t mode);
++int aufs_link(struct dentry *src_dentry, struct inode *dir,
++ struct dentry *dentry);
++int aufs_mkdir(struct mnt_idmap *idmap, struct inode *dir,
++ struct dentry *dentry, umode_t mode);
+
-+ file = NULL;
-+ sb = dentry->d_sb;
-+ err = si_read_lock(sb, AuLock_FLUSH | AuLock_NOPLM);
-+ if (unlikely(err))
-+ goto out_kfree;
++/* i_op_del.c */
++int au_wr_dir_need_wh(struct dentry *dentry, int isdir, aufs_bindex_t *bcpup);
++int au_may_del(struct dentry *dentry, aufs_bindex_t bindex,
++ struct dentry *h_parent, int isdir);
++int aufs_unlink(struct inode *dir, struct dentry *dentry);
++int aufs_rmdir(struct inode *dir, struct dentry *dentry);
+
-+ 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;
-+ }
-+ }
++/* i_op_ren.c */
++int au_wbr(struct dentry *dentry, aufs_bindex_t btgt);
++int aufs_rename(struct mnt_idmap *idmap,
++ struct inode *_src_dir, struct dentry *_src_dentry,
++ struct inode *_dst_dir, struct dentry *_dst_dentry,
++ unsigned int _flags);
+
-+ 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;
-+ }
++/* iinfo.c */
++struct inode *au_h_iptr(struct inode *inode, aufs_bindex_t bindex);
++void au_hiput(struct au_hinode *hinode);
++void au_set_hi_wh(struct inode *inode, aufs_bindex_t bindex,
++ struct dentry *h_wh);
++unsigned int au_hi_flags(struct inode *inode, int isdir);
+
-+ 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;
-+ }
++/* hinode flags */
++#define AuHi_XINO BIT(0)
++#define AuHi_HNOTIFY BIT(1)
++#define au_ftest_hi(flags, name) ((flags) & AuHi_##name)
++#define au_fset_hi(flags, name) \
++ do { (flags) |= AuHi_##name; } while (0)
++#define au_fclr_hi(flags, name) \
++ do { (flags) &= ~AuHi_##name; } while (0)
+
-+ if (ia->ia_valid & ATTR_SIZE) {
-+ struct file *f;
++#ifndef CONFIG_AUFS_HNOTIFY
++#undef AuHi_HNOTIFY
++#define AuHi_HNOTIFY 0
++#endif
+
-+ if (ia->ia_size < i_size_read(inode))
-+ /* unmap only */
-+ truncate_setsize(inode, ia->ia_size);
++void au_set_h_iptr(struct inode *inode, aufs_bindex_t bindex,
++ struct inode *h_inode, unsigned int flags);
+
-+ 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)) {
-+ h_idmap = mnt_idmap(a->h_path.mnt);
-+ err = vfsub_acl_chmod(h_idmap, a->h_path.dentry, ia->ia_mode);
-+ }
-+ if (!err)
-+ au_cpup_attr_changeable(inode);
++void au_update_iigen(struct inode *inode, int half);
++void au_update_ibrange(struct inode *inode, int do_put_zero);
+
-+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;
-+}
++void au_icntnr_init_once(void *_c);
++void au_hinode_init(struct au_hinode *hinode);
++int au_iinfo_init(struct inode *inode);
++void au_iinfo_fin(struct inode *inode);
++int au_hinode_realloc(struct au_iinfo *iinfo, int nbr, int may_shrink);
+
-+#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;
++#ifdef CONFIG_PROC_FS
++/* plink.c */
++int au_plink_maint(struct super_block *sb, int flags);
++struct au_sbinfo;
++void au_plink_maint_leave(struct au_sbinfo *sbinfo);
++int au_plink_maint_enter(struct super_block *sb);
++#ifdef CONFIG_AUFS_DEBUG
++void au_plink_list(struct super_block *sb);
++#else
++AuStubVoid(au_plink_list, struct super_block *sb)
++#endif
++int au_plink_test(struct inode *inode);
++struct dentry *au_plink_lkup(struct inode *inode, aufs_bindex_t bindex);
++void au_plink_append(struct inode *inode, aufs_bindex_t bindex,
++ struct dentry *h_dentry);
++void au_plink_put(struct super_block *sb, int verbose);
++void au_plink_clean(struct super_block *sb, int verbose);
++void au_plink_half_refresh(struct super_block *sb, aufs_bindex_t br_id);
++#else
++AuStubInt0(au_plink_maint, struct super_block *sb, int flags);
++AuStubVoid(au_plink_maint_leave, struct au_sbinfo *sbinfo);
++AuStubInt0(au_plink_maint_enter, struct super_block *sb);
++AuStubVoid(au_plink_list, struct super_block *sb);
++AuStubInt0(au_plink_test, struct inode *inode);
++AuStub(struct dentry *, au_plink_lkup, return NULL,
++ struct inode *inode, aufs_bindex_t bindex);
++AuStubVoid(au_plink_append, struct inode *inode, aufs_bindex_t bindex,
++ struct dentry *h_dentry);
++AuStubVoid(au_plink_put, struct super_block *sb, int verbose);
++AuStubVoid(au_plink_clean, struct super_block *sb, int verbose);
++AuStubVoid(au_plink_half_refresh, struct super_block *sb, aufs_bindex_t br_id);
++#endif /* CONFIG_PROC_FS */
+
-+ 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;
++#ifdef CONFIG_AUFS_XATTR
++/* xattr.c */
++int au_cpup_xattr(struct path *h_dst, struct path *h_src, int ignore_flags,
++ unsigned int verbose);
++ssize_t aufs_listxattr(struct dentry *dentry, char *list, size_t size);
++void au_xattr_init(struct super_block *sb);
++#else
++AuStubInt0(au_cpup_xattr, struct path *h_dst, struct path *h_src,
++ int ignore_flags, unsigned int verbose);
++AuStubVoid(au_xattr_init, struct super_block *sb);
++#endif
+
-+ h_path->dentry = a->h_path.dentry;
-+ h_path->mnt = au_sbr_mnt(sb, a->btgt);
++#ifdef CONFIG_FS_POSIX_ACL
++struct posix_acl *aufs_get_inode_acl(struct inode *inode, int type, bool rcu);
++struct posix_acl *aufs_get_acl(struct mnt_idmap *idmap,
++ struct dentry *dentry, int type);
++int aufs_set_acl(struct mnt_idmap *idmap, struct dentry *dentry,
++ struct posix_acl *acl, int type);
++#endif
+
-+out:
-+ return err;
-+}
++#if IS_ENABLED(CONFIG_AUFS_XATTR) || IS_ENABLED(CONFIG_FS_POSIX_ACL)
++enum {
++ AU_XATTR_SET,
++ AU_ACL_SET
++};
+
++struct au_sxattr {
++ int type;
++ union {
++ struct {
++ const char *name;
++ const void *value;
++ size_t size;
++ int flags;
++ } set;
++ struct {
++ struct posix_acl *acl;
++ int type;
++ } acl_set;
++ } u;
++};
+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;
-+ struct mnt_idmap *h_idmap;
++ struct au_sxattr *arg);
++#endif
+
-+ IMustLock(inode);
++/* ---------------------------------------------------------------------- */
+
-+ err = -ENOMEM;
-+ a = kzalloc(sizeof(*a), GFP_NOFS);
-+ if (unlikely(!a))
-+ goto out;
++/* lock subclass for iinfo */
++enum {
++ AuLsc_II_CHILD, /* child first */
++ AuLsc_II_CHILD2, /* rename(2), link(2), and cpup at hnotify */
++ AuLsc_II_CHILD3, /* copyup dirs */
++ AuLsc_II_PARENT, /* see AuLsc_I_PARENT in vfsub.h */
++ AuLsc_II_PARENT2,
++ AuLsc_II_PARENT3, /* copyup dirs */
++ AuLsc_II_NEW_CHILD
++};
+
-+ sb = dentry->d_sb;
-+ err = si_read_lock(sb, AuLock_FLUSH | AuLock_NOPLM);
-+ if (unlikely(err))
-+ goto out_kfree;
++/*
++ * ii_read_lock_child, ii_write_lock_child,
++ * ii_read_lock_child2, ii_write_lock_child2,
++ * ii_read_lock_child3, ii_write_lock_child3,
++ * ii_read_lock_parent, ii_write_lock_parent,
++ * ii_read_lock_parent2, ii_write_lock_parent2,
++ * ii_read_lock_parent3, ii_write_lock_parent3,
++ * ii_read_lock_new_child, ii_write_lock_new_child,
++ */
++#define AuReadLockFunc(name, lsc) \
++static inline void ii_read_lock_##name(struct inode *i) \
++{ \
++ au_rw_read_lock_nested(&au_ii(i)->ii_rwsem, AuLsc_II_##lsc); \
++}
+
-+ 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;
-+ h_idmap = mnt_idmap(h_path.mnt);
++#define AuWriteLockFunc(name, lsc) \
++static inline void ii_write_lock_##name(struct inode *i) \
++{ \
++ au_rw_write_lock_nested(&au_ii(i)->ii_rwsem, AuLsc_II_##lsc); \
++}
+
-+ inode_unlock(a->h_inode);
-+ switch (arg->type) {
-+ case AU_XATTR_SET:
-+ AuDebugOn(d_is_negative(h_path.dentry));
-+ err = vfsub_setxattr(h_idmap, 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_idmap, h_path.dentry,
-+ arg->u.acl_set.acl,
-+ arg->u.acl_set.type);
-+ }
-+ break;
-+ }
-+ if (!err)
-+ au_cpup_attr_timesizes(inode);
++#define AuRWLockFuncs(name, lsc) \
++ AuReadLockFunc(name, lsc) \
++ AuWriteLockFunc(name, lsc)
+
-+ au_unpin(&a->pin);
-+ if (unlikely(err))
-+ au_update_dbtop(dentry);
++AuRWLockFuncs(child, CHILD);
++AuRWLockFuncs(child2, CHILD2);
++AuRWLockFuncs(child3, CHILD3);
++AuRWLockFuncs(parent, PARENT);
++AuRWLockFuncs(parent2, PARENT2);
++AuRWLockFuncs(parent3, PARENT3);
++AuRWLockFuncs(new_child, NEW_CHILD);
+
-+out_di:
-+ di_write_unlock(dentry);
-+ si_read_unlock(sb);
-+out_kfree:
-+ au_kfree_rcu(a);
-+out:
-+ AuTraceErr(err);
-+ return err;
-+}
-+#endif
++#undef AuReadLockFunc
++#undef AuWriteLockFunc
++#undef AuRWLockFuncs
+
-+static void au_refresh_iattr(struct inode *inode, struct kstat *st,
-+ unsigned int nlink)
-+{
-+ unsigned int n;
++#define ii_read_unlock(i) au_rw_read_unlock(&au_ii(i)->ii_rwsem)
++#define ii_write_unlock(i) au_rw_write_unlock(&au_ii(i)->ii_rwsem)
++#define ii_downgrade_lock(i) au_rw_dgrade_lock(&au_ii(i)->ii_rwsem)
+
-+ 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_set_ctime_to_ts(inode, st->ctime);
++#define IiMustNoWaiters(i) AuRwMustNoWaiters(&au_ii(i)->ii_rwsem)
++#define IiMustAnyLock(i) AuRwMustAnyLock(&au_ii(i)->ii_rwsem)
++#define IiMustWriteLock(i) AuRwMustWriteLock(&au_ii(i)->ii_rwsem)
+
-+ 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);
++static inline void au_icntnr_init(struct au_icntnr *c)
++{
++#ifdef CONFIG_AUFS_DEBUG
++ c->vfs_inode.i_mode = 0;
++#endif
+}
+
-+/*
-+ * 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, struct inode *inode, int force,
-+ struct path *h_path, int locked)
++static inline unsigned int au_iigen(struct inode *inode, unsigned int *igflags)
+{
-+ int err;
-+ unsigned int mnt_flags, sigen;
-+ unsigned char udba_none;
-+ aufs_bindex_t bindex;
-+ struct super_block *sb, *h_sb;
-+
-+ h_path->mnt = NULL;
-+ h_path->dentry = NULL;
++ unsigned int gen;
++ struct au_iinfo *iinfo;
++ struct au_iigen *iigen;
+
-+ err = 0;
-+ sb = dentry->d_sb;
-+ mnt_flags = au_mntflags(sb);
-+ udba_none = !!au_opt_test(mnt_flags, UDBA_NONE);
++ iinfo = au_ii(inode);
++ iigen = &iinfo->ii_generation;
++ spin_lock(&iigen->ig_spin);
++ if (igflags)
++ *igflags = iigen->ig_flags;
++ gen = iigen->ig_generation;
++ spin_unlock(&iigen->ig_spin);
+
-+ if (unlikely(locked))
-+ goto body; /* skip locking dinfo */
++ return gen;
++}
+
-+ /* 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);
++/* tiny test for inode number */
++/* tmpfs generation is too rough */
++static inline int au_test_higen(struct inode *inode, struct inode *h_inode)
++{
++ struct au_iinfo *iinfo;
+
-+body:
-+ if (!inode) {
-+ inode = d_inode(dentry);
-+ if (unlikely(!inode))
-+ goto out;
-+ }
-+ 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 */
++ iinfo = au_ii(inode);
++ AuRwMustAnyLock(&iinfo->ii_rwsem);
++ return !(iinfo->ii_hsb1 == h_inode->i_sb
++ && iinfo->ii_higen == h_inode->i_generation);
++}
+
-+ 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);
-+ }
++static inline void au_iigen_dec(struct inode *inode)
++{
++ struct au_iinfo *iinfo;
++ struct au_iigen *iigen;
+
-+out:
-+ return err;
++ iinfo = au_ii(inode);
++ iigen = &iinfo->ii_generation;
++ spin_lock(&iigen->ig_spin);
++ iigen->ig_generation--;
++ spin_unlock(&iigen->ig_spin);
+}
+
-+static int aufs_getattr(struct mnt_idmap *idmap, const struct path *path,
-+ struct kstat *st, u32 request, unsigned int query)
++static inline int au_iigen_test(struct inode *inode, unsigned int sigen)
+{
+ 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, /*inode*/NULL, /*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;
++ err = 0;
++ if (unlikely(inode && au_iigen(inode, NULL) != sigen))
++ err = -EIO;
+
-+out_fill:
-+ generic_fillattr(idmap, request, 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)
++static inline struct au_hinode *au_hinode(struct au_iinfo *iinfo,
++ aufs_bindex_t bindex)
+{
-+ const char *ret;
-+ struct dentry *h_dentry;
-+ struct inode *h_inode;
-+ int err;
-+ aufs_bindex_t bindex;
++ return iinfo->ii_hinode + bindex;
++}
+
-+ ret = NULL; /* suppress a warning */
-+ err = -ECHILD;
-+ if (!dentry)
-+ goto out;
++static inline int au_is_bad_inode(struct inode *inode)
++{
++ return !!(is_bad_inode(inode) || !au_hinode(au_ii(inode), 0));
++}
+
-+ err = aufs_read_lock(dentry, AuLock_IR | AuLock_GEN);
-+ if (unlikely(err))
-+ goto out;
++static inline aufs_bindex_t au_ii_br_id(struct inode *inode,
++ aufs_bindex_t bindex)
++{
++ IiMustAnyLock(inode);
++ return au_hinode(au_ii(inode), bindex)->hi_id;
++}
+
-+ err = au_d_hashed_positive(dentry);
-+ if (unlikely(err))
-+ goto out_unlock;
++static inline aufs_bindex_t au_ibtop(struct inode *inode)
++{
++ IiMustAnyLock(inode);
++ return au_ii(inode)->ii_btop;
++}
+
-+ 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;
++static inline aufs_bindex_t au_ibbot(struct inode *inode)
++{
++ IiMustAnyLock(inode);
++ return au_ii(inode)->ii_bbot;
++}
+
-+ 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;
++static inline struct au_vdir *au_ivdir(struct inode *inode)
++{
++ IiMustAnyLock(inode);
++ return au_ii(inode)->ii_vdir;
++}
+
-+ 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);
++static inline struct dentry *au_hi_wh(struct inode *inode, aufs_bindex_t bindex)
++{
++ IiMustAnyLock(inode);
++ return au_hinode(au_ii(inode), bindex)->hi_whdentry;
++}
+
-+out_unlock:
-+ aufs_read_unlock(dentry, AuLock_IR);
-+out:
-+ if (unlikely(err))
-+ ret = ERR_PTR(err);
-+ AuTraceErrPtr(ret);
-+ return ret;
++static inline void au_set_ibtop(struct inode *inode, aufs_bindex_t bindex)
++{
++ IiMustWriteLock(inode);
++ au_ii(inode)->ii_btop = bindex;
++}
++
++static inline void au_set_ibbot(struct inode *inode, aufs_bindex_t bindex)
++{
++ IiMustWriteLock(inode);
++ au_ii(inode)->ii_bbot = bindex;
++}
++
++static inline void au_set_ivdir(struct inode *inode, struct au_vdir *vdir)
++{
++ IiMustWriteLock(inode);
++ au_ii(inode)->ii_vdir = vdir;
++}
++
++static inline struct au_hinode *au_hi(struct inode *inode, aufs_bindex_t bindex)
++{
++ IiMustAnyLock(inode);
++ return au_hinode(au_ii(inode), bindex);
+}
+
+/* ---------------------------------------------------------------------- */
+
-+static int au_is_special(struct inode *inode)
++static inline struct dentry *au_pinned_parent(struct au_pin *pin)
+{
-+ return (inode->i_mode & (S_IFBLK | S_IFCHR | S_IFIFO | S_IFSOCK));
++ if (pin)
++ return pin->parent;
++ return NULL;
+}
+
-+static int aufs_update_time(struct inode *inode, int flags)
++static inline struct inode *au_pinned_h_dir(struct au_pin *pin)
+{
-+ int err;
-+ aufs_bindex_t bindex;
-+ struct super_block *sb;
-+ struct inode *h_inode;
-+ struct vfsmount *h_mnt;
++ if (pin && pin->hdir)
++ return pin->hdir->hi_inode;
++ return NULL;
++}
+
-+ sb = inode->i_sb;
-+ WARN_ONCE((flags & S_ATIME) && !IS_NOATIME(inode),
-+ "unexpected s_flags 0x%lx", sb->s_flags);
++static inline struct au_hinode *au_pinned_hdir(struct au_pin *pin)
++{
++ if (pin)
++ return pin->hdir;
++ return NULL;
++}
+
-+ /* mmap_sem might be acquired already, cf. aufs_mmap() */
-+ lockdep_off();
-+ si_read_lock(sb, AuLock_FLUSH);
-+ ii_write_lock_child(inode);
++static inline void au_pin_set_dentry(struct au_pin *pin, struct dentry *dentry)
++{
++ if (pin)
++ pin->dentry = dentry;
++}
+
-+ 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, 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);
++static inline void au_pin_set_parent_lflag(struct au_pin *pin,
++ unsigned char lflag)
++{
++ if (pin) {
++ if (lflag)
++ au_fset_pin(pin->flags, DI_LOCKED);
++ else
++ au_fclr_pin(pin->flags, DI_LOCKED);
+ }
++}
+
-+ if (!err)
-+ au_cpup_attr_timesizes(inode);
-+ ii_write_unlock(inode);
-+ si_read_unlock(sb);
-+ lockdep_on();
++#if 0 /* reserved */
++static inline void au_pin_set_parent(struct au_pin *pin, struct dentry *parent)
++{
++ if (pin) {
++ dput(pin->parent);
++ pin->parent = dget(parent);
++ }
++}
++#endif
+
-+ if (!err && (flags & S_VERSION))
-+ inode_inc_iversion(inode);
++/* ---------------------------------------------------------------------- */
++
++struct au_branch;
++#ifdef CONFIG_AUFS_HNOTIFY
++struct au_hnotify_op {
++ void (*ctl)(struct au_hinode *hinode, int do_set);
++ int (*alloc)(struct au_hinode *hinode);
+
-+ return err;
-+}
++ /*
++ * if it returns true, the caller should free hinode->hi_notify,
++ * otherwise ->free() frees it.
++ */
++ int (*free)(struct au_hinode *hinode,
++ struct au_hnotify *hn) __must_check;
+
-+/* ---------------------------------------------------------------------- */
++ void (*fin)(void);
++ int (*init)(void);
+
-+/* 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_inode_acl = aufs_get_inode_acl,
-+ .get_acl = aufs_get_acl,
-+ .set_acl = aufs_set_acl, /* unsupport for symlink? */
-+#endif
++ int (*reset_br)(unsigned int udba, struct au_branch *br, int perm);
++ void (*fin_br)(struct au_branch *br);
++ int (*init_br)(struct au_branch *br, int perm);
++};
+
-+ .setattr = aufs_setattr,
-+ .getattr = aufs_getattr,
++/* hnotify.c */
++int au_hn_alloc(struct au_hinode *hinode, struct inode *inode);
++void au_hn_free(struct au_hinode *hinode);
++void au_hn_ctl(struct au_hinode *hinode, int do_set);
++void au_hn_reset(struct inode *inode, unsigned int flags);
++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 au_hnotify_reset_br(unsigned int udba, struct au_branch *br, int perm);
++int au_hnotify_init_br(struct au_branch *br, int perm);
++void au_hnotify_fin_br(struct au_branch *br);
++int __init au_hnotify_init(void);
++void au_hnotify_fin(void);
+
-+#ifdef CONFIG_AUFS_XATTR
-+ .listxattr = aufs_listxattr,
-+#endif
++/* hfsnotify.c */
++extern const struct au_hnotify_op au_hnotify_op;
+
-+ .get_link = aufs_get_link
++static inline
++void au_hn_init(struct au_hinode *hinode)
++{
++ hinode->hi_notify = NULL;
++}
+
-+ /* .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,
++static inline struct au_hnotify *au_hn(struct au_hinode *hinode)
++{
++ return hinode->hi_notify;
++}
+
-+ .permission = aufs_permission,
-+#ifdef CONFIG_FS_POSIX_ACL
-+ .get_inode_acl = aufs_get_inode_acl,
-+ .get_acl = aufs_get_acl,
-+ .set_acl = aufs_set_acl,
-+#endif
++#else
++AuStub(int, au_hn_alloc, return -EOPNOTSUPP,
++ struct au_hinode *hinode __maybe_unused,
++ struct inode *inode __maybe_unused)
++AuStub(struct au_hnotify *, au_hn, return NULL, struct au_hinode *hinode)
++AuStubVoid(au_hn_free, struct au_hinode *hinode __maybe_unused)
++AuStubVoid(au_hn_ctl, struct au_hinode *hinode __maybe_unused,
++ int do_set __maybe_unused)
++AuStubVoid(au_hn_reset, struct inode *inode __maybe_unused,
++ unsigned int flags __maybe_unused)
++AuStubInt0(au_hnotify_reset_br, unsigned int udba __maybe_unused,
++ struct au_branch *br __maybe_unused,
++ int perm __maybe_unused)
++AuStubInt0(au_hnotify_init_br, struct au_branch *br __maybe_unused,
++ int perm __maybe_unused)
++AuStubVoid(au_hnotify_fin_br, struct au_branch *br __maybe_unused)
++AuStubInt0(__init au_hnotify_init, void)
++AuStubVoid(au_hnotify_fin, void)
++AuStubVoid(au_hn_init, struct au_hinode *hinode __maybe_unused)
++#endif /* CONFIG_AUFS_HNOTIFY */
+
-+ .setattr = aufs_setattr,
-+ .getattr = aufs_getattr,
++static inline void au_hn_suspend(struct au_hinode *hdir)
++{
++ au_hn_ctl(hdir, /*do_set*/0);
++}
+
-+#ifdef CONFIG_AUFS_XATTR
-+ .listxattr = aufs_listxattr,
-+#endif
++static inline void au_hn_resume(struct au_hinode *hdir)
++{
++ au_hn_ctl(hdir, /*do_set*/1);
++}
+
-+ .update_time = aufs_update_time,
-+ .atomic_open = aufs_atomic_open,
-+ .tmpfile = aufs_tmpfile
-+ },
-+ [AuIop_OTHER] = {
-+ .permission = aufs_permission,
-+#ifdef CONFIG_FS_POSIX_ACL
-+ .get_inode_acl = aufs_get_inode_acl,
-+ .get_acl = aufs_get_acl,
-+ .set_acl = aufs_set_acl,
-+#endif
++static inline void au_hn_inode_lock(struct au_hinode *hdir)
++{
++ inode_lock(hdir->hi_inode);
++ au_hn_suspend(hdir);
++}
+
-+ .setattr = aufs_setattr,
-+ .getattr = aufs_getattr,
++static inline void au_hn_inode_lock_nested(struct au_hinode *hdir,
++ unsigned int sc __maybe_unused)
++{
++ inode_lock_nested(hdir->hi_inode, sc);
++ au_hn_suspend(hdir);
++}
+
-+#ifdef CONFIG_AUFS_XATTR
-+ .listxattr = aufs_listxattr,
++#if 0 /* unused */
++#include "vfsub.h"
++static inline void au_hn_inode_lock_shared_nested(struct au_hinode *hdir,
++ unsigned int sc)
++{
++ inode_lock_shared_nested(hdir->hi_inode, sc);
++ au_hn_suspend(hdir);
++}
+#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 00000000000000..f238050b802f29
---- /dev/null
-+++ b/fs/aufs/i_op_add.c
-@@ -0,0 +1,972 @@
++static inline void au_hn_inode_unlock(struct au_hinode *hdir)
++{
++ au_hn_resume(hdir);
++ inode_unlock(hdir->hi_inode);
++}
++
++#endif /* __KERNEL__ */
++#endif /* __AUFS_INODE_H__ */
+diff -urN /usr/share/empty/fs/aufs/ioctl.c linux/fs/aufs/ioctl.c
+--- /usr/share/empty/fs/aufs/ioctl.c 1970-01-01 01:00:00.000000000 +0100
++++ linux/fs/aufs/ioctl.c 2022-11-05 23:02:18.965889284 +0100
+@@ -0,0 +1,220 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2005-2022 Junjiro R. Okajima
+ */
+
+/*
-+ * inode operations (add entry)
++ * ioctl
++ * plink-management and readdir in userspace.
++ * assist the pathconf(3) wrapper library.
++ * move-down
++ * File-based Hierarchical Storage Management.
+ */
+
-+#include <linux/iversion.h>
++#include <linux/compat.h>
++#include <linux/file.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)
++static int au_wbr_fd(struct path *path, struct aufs_wbr_fd __user *arg)
+{
-+ int err, rerr;
-+ aufs_bindex_t bwh;
-+ struct path h_path;
++ int err, fd;
++ aufs_bindex_t wbi, bindex, bbot;
++ struct file *h_file;
+ 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;
++ struct dentry *root;
++ struct au_branch *br;
++ struct aufs_wbr_fd wbrfd = {
++ .oflags = au_dir_roflags,
++ .brid = -1
++ };
++ const int valid = O_RDONLY | O_NONBLOCK | O_LARGEFILE | O_DIRECTORY
++ | O_NOATIME | O_CLOEXEC;
+
-+ err = -ENAMETOOLONG;
-+ if (unlikely(dentry->d_name.len > AUFS_MAX_NAMELEN))
-+ goto out;
++ AuDebugOn(wbrfd.oflags & ~valid);
+
-+ 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))
++ if (arg) {
++ err = copy_from_user(&wbrfd, arg, sizeof(wbrfd));
++ if (unlikely(err)) {
++ err = -EFAULT;
+ 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;
++ err = -EINVAL;
++ AuDbg("wbrfd{0%o, %d}\n", wbrfd.oflags, wbrfd.brid);
++ wbrfd.oflags |= au_dir_roflags;
++ AuDbg("0%o\n", wbrfd.oflags);
++ if (unlikely(wbrfd.oflags & ~valid))
+ 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))
++ fd = get_unused_fd_flags(0);
++ err = fd;
++ if (unlikely(fd < 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_file = ERR_PTR(-EINVAL);
++ wbi = 0;
++ br = NULL;
++ sb = path->dentry->d_sb;
++ root = sb->s_root;
++ aufs_read_lock(root, AuLock_IR);
++ bbot = au_sbbot(sb);
++ if (wbrfd.brid >= 0) {
++ wbi = au_br_index(sb, wbrfd.brid);
++ if (unlikely(wbi < 0 || wbi > bbot))
++ goto out_unlock;
++ }
+
-+ 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;
++ h_file = ERR_PTR(-ENOENT);
++ br = au_sbr(sb, wbi);
++ if (!au_br_writable(br->br_perm)) {
++ if (arg)
++ goto out_unlock;
+
-+ 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);
++ bindex = wbi + 1;
++ wbi = -1;
++ for (; bindex <= bbot; bindex++) {
++ br = au_sbr(sb, bindex);
++ if (au_br_writable(br->br_perm)) {
++ wbi = bindex;
++ br = au_sbr(sb, wbi);
++ break;
++ }
++ }
+ }
++ AuDbg("wbi %d\n", wbi);
++ if (wbi >= 0)
++ h_file = au_h_open(root, wbi, wbrfd.oflags, NULL,
++ /*force_wr*/0);
+
-+ wh_dentry = NULL;
-+ if (bcpup != au_dbwh(dentry))
-+ goto out; /* success */
++out_unlock:
++ aufs_read_unlock(root, AuLock_IR);
++ err = PTR_ERR(h_file);
++ if (IS_ERR(h_file))
++ goto out_fd;
+
-+ /*
-+ * 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);
++ au_lcnt_dec(&br->br_nfiles); /* cf. au_h_open() */
++ fd_install(fd, h_file);
++ err = fd;
++ goto out; /* success */
+
-+out_unpin:
-+ if (IS_ERR(wh_dentry))
-+ au_unpin(pin);
++out_fd:
++ put_unused_fd(fd);
+out:
-+ return wh_dentry;
++ AuTraceErr(err);
++ return err;
+}
+
+/* ---------------------------------------------------------------------- */
+
-+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)
++long aufs_ioctl_dir(struct file *file, unsigned int cmd, unsigned long 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;
++ long err;
++ struct dentry *dentry;
+
-+ 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);
-+ }
++ switch (cmd) {
++ case AUFS_CTL_RDU:
++ case AUFS_CTL_RDU_INO:
++ err = au_rdu_ioctl(file, cmd, arg);
+ break;
-+ case Symlink:
-+ err = vfsub_symlink(h_dir, &a->h_path, arg->u.s.symname);
-+ created = !err;
++
++ case AUFS_CTL_WBR_FD:
++ err = au_wbr_fd(&file->f_path, (void __user *)arg);
+ break;
-+ case Mknod:
-+ err = vfsub_mknod(h_dir, &a->h_path, arg->u.m.mode,
-+ arg->u.m.dev);
-+ created = !err;
++
++ case AUFS_CTL_IBUSY:
++ err = au_ibusy_ioctl(file, arg);
+ break;
-+ default:
-+ BUG();
-+ }
-+ if (unlikely(err < 0))
-+ goto out_unpin;
+
-+ err = epilog(dir, btop, wh_dentry, dentry);
-+ if (!err)
-+ goto out_unpin; /* success */
++ case AUFS_CTL_BRINFO:
++ err = au_brinfo_ioctl(file, arg);
++ break;
+
-+ /* 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);
++ case AUFS_CTL_FHSM_FD:
++ dentry = file->f_path.dentry;
++ if (IS_ROOT(dentry))
++ err = au_fhsm_fd(dentry->d_sb, arg);
++ else
++ err = -ENOTTY;
++ break;
+
-+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);
++ default:
++ /* do not call the lower */
++ AuDbg("0x%x\n", cmd);
++ err = -ENOTTY;
+ }
-+ if (!try_aopen)
-+ aufs_read_unlock(dentry, AuLock_DW);
-+out_free:
-+ au_kfree_rcu(a);
-+out:
++
++ AuTraceErr(err);
+ return err;
+}
+
-+int aufs_mknod(struct mnt_idmap *idmap, struct inode *dir,
-+ struct dentry *dentry, umode_t mode, dev_t dev)
++long aufs_ioctl_nondir(struct file *file, unsigned int cmd, unsigned long arg)
+{
-+ struct simple_arg arg = {
-+ .type = Mknod,
-+ .u.m = {
-+ .mode = mode,
-+ .dev = dev
-+ }
-+ };
-+ return add_simple(dir, dentry, &arg);
-+}
++ long err;
+
-+int aufs_symlink(struct mnt_idmap *idmap, 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);
-+}
++ switch (cmd) {
++ case AUFS_CTL_MVDOWN:
++ err = au_mvdown(file->f_path.dentry, (void __user *)arg);
++ break;
+
-+int aufs_create(struct mnt_idmap *idmap, 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);
-+}
++ case AUFS_CTL_WBR_FD:
++ err = au_wbr_fd(&file->f_path, (void __user *)arg);
++ break;
+
-+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);
++ default:
++ /* do not call the lower */
++ AuDbg("0x%x\n", cmd);
++ err = -ENOTTY;
++ }
++
++ AuTraceErr(err);
++ return err;
+}
+
-+int aufs_tmpfile(struct mnt_idmap *idmap, struct inode *dir,
-+ struct file *file, umode_t mode)
++#ifdef CONFIG_COMPAT
++long aufs_compat_ioctl_dir(struct file *file, unsigned int cmd,
++ unsigned long arg)
+{
-+ int err;
-+ aufs_bindex_t bindex;
-+ struct path h_ppath;
-+ struct super_block *sb;
-+ struct au_branch *br;
-+ struct dentry *dentry, *parent, *h_parent, *h_dentry;
-+ struct inode *h_dir, *inode;
-+ struct vfsmount *h_mnt;
-+ struct mnt_idmap *h_idmap;
-+ struct file *h_file;
-+ struct au_wr_dir_args wr_dir_args = {
-+ .force_btgt = -1,
-+ .flags = AuWrDir_TMPFILE
-+ };
++ long err;
+
-+ /* copy-up may happen */
-+ inode_lock(dir);
++ switch (cmd) {
++ case AUFS_CTL_RDU:
++ case AUFS_CTL_RDU_INO:
++ err = au_rdu_compat_ioctl(file, cmd, arg);
++ break;
+
-+ h_file = NULL;
-+ sb = dir->i_sb;
-+ err = si_read_lock(sb, AuLock_FLUSH | AuLock_NOPLM);
-+ if (unlikely(err))
-+ goto out;
++ case AUFS_CTL_IBUSY:
++ err = au_ibusy_compat_ioctl(file, arg);
++ break;
+
-+ dentry = file->f_path.dentry;
-+ err = au_di_init(dentry);
-+ if (unlikely(err))
-+ goto out_si;
++ case AUFS_CTL_BRINFO:
++ err = au_brinfo_compat_ioctl(file, arg);
++ break;
+
-+ err = -EBUSY;
-+ parent = d_find_any_alias(dir);
-+ AuDebugOn(!parent);
-+ di_write_lock_parent(parent);
-+ if (unlikely(d_inode(parent) != dir))
-+ goto out_parent;
++ default:
++ err = aufs_ioctl_dir(file, cmd, arg);
++ }
+
-+ err = au_digen_test(parent, au_sigen(sb));
-+ if (unlikely(err))
-+ goto out_parent;
++ AuTraceErr(err);
++ return err;
++}
+
-+ 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;
++long aufs_compat_ioctl_nondir(struct file *file, unsigned int cmd,
++ unsigned long arg)
++{
++ return aufs_ioctl_nondir(file, cmd, (unsigned long)compat_ptr(arg));
++}
++#endif
+diff -urN /usr/share/empty/fs/aufs/i_op_add.c linux/fs/aufs/i_op_add.c
+--- /usr/share/empty/fs/aufs/i_op_add.c 1970-01-01 01:00:00.000000000 +0100
++++ linux/fs/aufs/i_op_add.c 2023-10-31 09:31:04.199880750 +0100
+@@ -0,0 +1,972 @@
++// SPDX-License-Identifier: GPL-2.0
++/*
++ * Copyright (C) 2005-2022 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/>.
++ */
+
-+ err = -EOPNOTSUPP;
-+ h_dir = au_h_iptr(dir, bindex);
-+ if (unlikely(!h_dir->i_op->tmpfile))
-+ goto out_parent;
++/*
++ * inode operations (add entry)
++ */
+
-+ br = au_sbr(sb, bindex);
-+ h_mnt = au_br_mnt(br);
-+ err = vfsub_mnt_want_write(h_mnt);
-+ if (unlikely(err))
-+ goto out_parent;
++#include <linux/iversion.h>
++#include "aufs.h"
+
-+ h_idmap = mnt_idmap(h_mnt);
-+ h_parent = au_h_dptr(parent, bindex);
-+ h_ppath.mnt = h_mnt;
-+ h_ppath.dentry = h_parent;
-+ h_file = kernel_tmpfile_open(h_idmap, &h_ppath, mode, /*open_flag*/0,
-+ current_cred());
-+ if (IS_ERR(h_file)) {
-+ err = PTR_ERR(h_file);
-+ h_file = NULL;
-+ goto out_mnt;
++/*
++ * 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;
+ }
+
-+ h_dentry = h_file->f_path.dentry;
-+ 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);
-+ goto out_h_file;
++ 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 */
+ }
+
-+ if (!inode->i_nlink)
-+ set_nlink(inode, 1);
-+ d_tmpfile(file, inode);
-+ au_di(dentry)->di_tmpfile = 1;
-+ get_file(h_file);
-+ au_di(dentry)->di_htmpfile = h_file;
++ err = PTR_ERR(inode);
++ if (!wh_dentry)
++ goto out;
+
-+ /* update without i_mutex */
-+ if (au_ibtop(dir) == au_dbtop(dentry))
-+ au_cpup_attr_timesizes(dir);
++ /* 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_h_file:
-+ fput(h_file);
-+out_mnt:
-+ vfsub_mnt_drop_write(h_mnt);
-+out_parent:
-+ di_write_unlock(parent);
-+ dput(parent);
-+ di_write_unlock(dentry);
-+ if (!err)
-+ goto out_si;
-+ if (h_file)
-+ fput(h_file);
-+ au_di(dentry)->di_htmpfile = NULL;
-+ au_di_fin(dentry);
-+ dentry->d_fsdata = NULL;
-+out_si:
-+ si_read_unlock(sb);
-+ if (!err && h_file) {
-+ /* finally... */
-+ err = finish_open_simple(file, err);
-+ if (!err)
-+ au_lcnt_inc(&br->br_nfiles);
-+ else {
-+ fput(h_file);
-+ au_di(dentry)->di_htmpfile = NULL;
-+ au_di_fin(dentry);
-+ dentry->d_fsdata = NULL;
-+ }
-+ }
+out:
-+ inode_unlock(dir);
-+ AuTraceErr(err);
+ 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)
++static int au_d_may_add(struct dentry *dentry)
+{
+ 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);
++ err = 0;
++ if (unlikely(d_unhashed(dentry)))
++ err = -ENOENT;
++ if (unlikely(d_really_is_positive(dentry)))
++ err = -EEXIST;
+ return err;
+}
+
-+static int au_cpup_or_link(struct dentry *src_dentry, struct dentry *dentry,
-+ struct au_link_args *a)
++/*
++ * 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;
-+ 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;
++ umode_t h_mode;
++ struct dentry *h_dentry;
++ struct inode *h_inode;
+
-+ 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;
++ err = -ENAMETOOLONG;
++ if (unlikely(dentry->d_name.len > AUFS_MAX_NAMELEN))
++ goto out;
+
-+ if (unlikely(d_is_negative(h_src_dentry))) {
-+ dput(h_src_dentry);
-+ h_src_dentry = NULL;
-+ }
++ 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;
+
-+ }
-+ 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;
++ 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;
+ }
+ }
+
-+ if (!err && !plink)
-+ au_plink_append(inode, a->bdst, a->h_path.dentry);
++ err = 0;
++ /* expected parent dir is locked */
++ if (unlikely(h_parent != h_dentry->d_parent))
++ err = -EIO;
+
+out:
+ AuTraceErr(err);
+ return err;
+}
+
-+int aufs_link(struct dentry *src_dentry, struct inode *dir,
-+ struct dentry *dentry)
++/*
++ * 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)
+{
-+ int err, rerr;
-+ struct au_dtime dt;
-+ struct au_link_args *a;
-+ struct dentry *wh_dentry, *h_src_dentry;
-+ struct inode *inode, *delegated;
++ struct dentry *wh_dentry, *h_parent;
+ struct super_block *sb;
-+ struct au_wr_dir_args wr_dir_args = {
-+ /* .force_btgt = -1, */
-+ .flags = AuWrDir_ADD_ENTRY
-+ };
++ struct au_branch *br;
++ int err;
++ unsigned int udba;
++ aufs_bindex_t bcpup;
+
-+ IMustLock(dir);
-+ inode = d_inode(src_dentry);
-+ IMustLock(inode);
++ AuDbg("%pd\n", dentry);
+
-+ err = -ENOMEM;
-+ a = kzalloc(sizeof(*a), GFP_NOFS);
-+ if (unlikely(!a))
++ err = au_wr_dir(dentry, src_dentry, wr_dir_args);
++ bcpup = err;
++ wh_dentry = ERR_PTR(err);
++ if (unlikely(err < 0))
+ 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;
-+ }
++ 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;
+
-+ /*
-+ * 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);
-+ }
-+ }
-+ }
-+ }
++ 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;
+
-+ 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;
++ 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);
+ }
+
-+ au_dir_ts(dir, a->bdst);
-+ inode_inc_iversion(dir);
-+ inc_nlink(inode);
-+ inode_set_ctime_to_ts(inode, inode_get_ctime(dir));
-+ 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 */
++ 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_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);
++ if (IS_ERR(wh_dentry))
++ au_unpin(pin);
+out:
-+ AuTraceErr(err);
-+ return err;
++ return wh_dentry;
+}
+
-+int aufs_mkdir(struct mnt_idmap *idmap, struct inode *dir,
-+ struct dentry *dentry, umode_t mode)
++/* ---------------------------------------------------------------------- */
++
++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 bindex;
-+ unsigned char diropq;
-+ struct path h_path;
-+ struct dentry *wh_dentry, *parent, *opq_dentry;
-+ struct inode *h_inode;
++ 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_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
-+ };
++ 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;
+
-+ err = aufs_read_lock(dentry, AuLock_DW | AuLock_GEN);
-+ if (unlikely(err))
-+ goto out_free;
++ 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;
-+
-+ parent = dentry->d_parent; /* dir inode is locked */
-+ di_write_lock_parent(parent);
++ if (!try_aopen)
++ di_write_lock_parent(parent);
+ wh_dentry = lock_hdir_lkup_wh(dentry, &a->dt, /*src_dentry*/NULL,
-+ &a->pin, &wr_dir_args);
++ &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;
-+ 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;
++ 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, bindex, wh_dentry, dentry);
-+ if (!err) {
-+ inc_nlink(dir);
++ err = epilog(dir, btop, wh_dentry, dentry);
++ if (!err)
+ goto out_unpin; /* success */
-+ }
+
+ /* revert */
-+ if (diropq) {
-+ AuLabel(revert opq);
-+ inode_lock_nested(h_inode, AuLsc_I_CHILD);
-+ rerr = au_diropq_remove(dentry, bindex);
-+ inode_unlock(h_inode);
++ 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 reverting diropq failed(%d, %d)\n",
++ 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_dir:
-+ AuLabel(revert dir);
-+ rerr = vfsub_rmdir(au_pinned_h_dir(&a->pin), &h_path);
-+ if (rerr) {
-+ AuIOErr("%pd reverting dir failed(%d, %d)\n",
-+ dentry, err, rerr);
-+ err = -EIO;
-+ }
-+ au_dtime_revert(&a->dt);
+out_unpin:
+ au_unpin(&a->pin);
+ dput(wh_dentry);
+out_parent:
-+ di_write_unlock(parent);
++ if (!try_aopen)
++ di_write_unlock(parent);
+out_unlock:
+ if (unlikely(err)) {
+ au_update_dbtop(dentry);
+ d_drop(dentry);
+ }
-+ aufs_read_unlock(dentry, AuLock_DW);
++ if (!try_aopen)
++ aufs_read_unlock(dentry, AuLock_DW);
+out_free:
+ au_kfree_rcu(a);
+out:
+ return err;
+}
-diff --git a/fs/aufs/i_op_del.c b/fs/aufs/i_op_del.c
-new file mode 100644
-index 00000000000000..8d9631492b930a
---- /dev/null
-+++ b/fs/aufs/i_op_del.c
-@@ -0,0 +1,523 @@
-+// SPDX-License-Identifier: GPL-2.0
-+/*
-+ * Copyright (C) 2005-2022 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/>.
-+ */
+
-+/*
-+ * inode operations (del entry)
-+ */
-+
-+#include <linux/iversion.h>
-+#include "aufs.h"
-+
-+/*
-+ * decide if a new whiteout for @dentry is necessary or not.
-+ * when it is necessary, prepare the parent dir for the upper branch whose
-+ * branch index is @bcpup for creation. the actual creation of the whiteout will
-+ * be done by caller.
-+ * return value:
-+ * 0: wh is unnecessary
-+ * plus: wh is necessary
-+ * minus: error
-+ */
-+int au_wr_dir_need_wh(struct dentry *dentry, int isdir, aufs_bindex_t *bcpup)
++int aufs_mknod(struct mnt_idmap *idmap, struct inode *dir,
++ struct dentry *dentry, umode_t mode, dev_t dev)
+{
-+ int need_wh, err;
-+ aufs_bindex_t btop;
-+ struct super_block *sb;
-+
-+ sb = dentry->d_sb;
-+ btop = au_dbtop(dentry);
-+ if (*bcpup < 0) {
-+ *bcpup = btop;
-+ if (au_test_ro(sb, btop, d_inode(dentry))) {
-+ err = AuWbrCopyup(au_sbi(sb), dentry);
-+ *bcpup = err;
-+ if (unlikely(err < 0))
-+ goto out;
++ struct simple_arg arg = {
++ .type = Mknod,
++ .u.m = {
++ .mode = mode,
++ .dev = dev
+ }
-+ } else
-+ AuDebugOn(btop < *bcpup
-+ || au_test_ro(sb, *bcpup, d_inode(dentry)));
-+ AuDbg("bcpup %d, btop %d\n", *bcpup, btop);
++ };
++ return add_simple(dir, dentry, &arg);
++}
+
-+ if (*bcpup != btop) {
-+ err = au_cpup_dirs(dentry, *bcpup);
-+ if (unlikely(err))
-+ goto out;
-+ need_wh = 1;
-+ } else {
-+ struct au_dinfo *dinfo, *tmp;
++int aufs_symlink(struct mnt_idmap *idmap, 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);
++}
+
-+ need_wh = -ENOMEM;
-+ dinfo = au_di(dentry);
-+ tmp = au_di_alloc(sb, AuLsc_DI_TMP);
-+ if (tmp) {
-+ au_di_cp(tmp, dinfo);
-+ au_di_swap(tmp, dinfo);
-+ /* returns the number of positive dentries */
-+ need_wh = au_lkup_dentry(dentry, btop + 1,
-+ /* AuLkup_IGNORE_PERM */ 0);
-+ au_di_swap(tmp, dinfo);
-+ au_rw_write_unlock(&tmp->di_rwsem);
-+ au_di_free(tmp);
++int aufs_create(struct mnt_idmap *idmap, 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
+ }
-+ }
-+ AuDbg("need_wh %d\n", need_wh);
-+ err = need_wh;
++ };
++ return add_simple(dir, dentry, &arg);
++}
+
-+out:
-+ return err;
++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);
+}
+
-+/*
-+ * simple tests for the del-entry operations.
-+ * following the checks in vfs, plus the parent-child relationship.
-+ */
-+int au_may_del(struct dentry *dentry, aufs_bindex_t bindex,
-+ struct dentry *h_parent, int isdir)
++int aufs_tmpfile(struct mnt_idmap *idmap, struct inode *dir,
++ struct file *file, umode_t mode)
+{
+ int err;
-+ umode_t h_mode;
-+ struct dentry *h_dentry, *h_latest;
-+ struct inode *h_inode;
++ aufs_bindex_t bindex;
+ struct path h_ppath;
+ struct super_block *sb;
+ struct au_branch *br;
++ struct dentry *dentry, *parent, *h_parent, *h_dentry;
++ struct inode *h_dir, *inode;
++ struct vfsmount *h_mnt;
+ struct mnt_idmap *h_idmap;
++ struct file *h_file;
++ struct au_wr_dir_args wr_dir_args = {
++ .force_btgt = -1,
++ .flags = AuWrDir_TMPFILE
++ };
++
++ /* copy-up may happen */
++ inode_lock(dir);
++
++ h_file = NULL;
++ sb = dir->i_sb;
++ err = si_read_lock(sb, AuLock_FLUSH | AuLock_NOPLM);
++ if (unlikely(err))
++ goto out;
++
++ dentry = file->f_path.dentry;
++ err = au_di_init(dentry);
++ if (unlikely(err))
++ goto out_si;
+
-+ h_dentry = au_h_dptr(dentry, bindex);
-+ if (d_really_is_positive(dentry)) {
-+ err = -ENOENT;
-+ if (unlikely(d_is_negative(h_dentry)))
-+ goto out;
-+ h_inode = d_inode(h_dentry);
-+ if (unlikely(!h_inode->i_nlink))
-+ goto out;
++ err = -EBUSY;
++ parent = d_find_any_alias(dir);
++ AuDebugOn(!parent);
++ di_write_lock_parent(parent);
++ if (unlikely(d_inode(parent) != dir))
++ goto out_parent;
+
-+ 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;
-+ }
-+ } else {
-+ /* rename(2) case */
-+ err = -EIO;
-+ if (unlikely(d_is_positive(h_dentry)))
-+ goto out;
-+ }
++ err = au_digen_test(parent, au_sigen(sb));
++ if (unlikely(err))
++ goto out_parent;
+
-+ err = -ENOENT;
-+ /* expected parent dir is locked */
-+ if (unlikely(h_parent != h_dentry->d_parent))
-+ goto out;
-+ err = 0;
++ 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;
+
-+ /*
-+ * rmdir a dir may break the consistency on some filesystem.
-+ * let's try heavy test.
-+ */
-+ err = -EACCES;
-+ sb = dentry->d_sb;
+ br = au_sbr(sb, bindex);
-+ h_idmap = au_br_idmap(br);
-+ if (unlikely(!au_opt_test(au_mntflags(sb), DIRPERM1)
-+ && au_test_h_perm(h_idmap, d_inode(h_parent),
-+ MAY_EXEC | MAY_WRITE)))
-+ goto out;
++ h_mnt = au_br_mnt(br);
++ err = vfsub_mnt_want_write(h_mnt);
++ if (unlikely(err))
++ goto out_parent;
+
++ h_idmap = mnt_idmap(h_mnt);
++ h_parent = au_h_dptr(parent, bindex);
++ h_ppath.mnt = h_mnt;
+ h_ppath.dentry = h_parent;
-+ h_ppath.mnt = au_br_mnt(br);
-+ h_latest = au_sio_lkup_one(h_idmap, &dentry->d_name, &h_ppath);
-+ err = -EIO;
-+ if (IS_ERR(h_latest))
-+ goto out;
-+ if (h_latest == h_dentry)
-+ err = 0;
-+ dput(h_latest);
++ h_file = kernel_tmpfile_open(h_idmap, &h_ppath, mode, /*open_flag*/0,
++ current_cred());
++ if (IS_ERR(h_file)) {
++ err = PTR_ERR(h_file);
++ h_file = NULL;
++ goto out_mnt;
++ }
++
++ h_dentry = h_file->f_path.dentry;
++ 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);
++ goto out_h_file;
++ }
++
++ if (!inode->i_nlink)
++ set_nlink(inode, 1);
++ d_tmpfile(file, inode);
++ au_di(dentry)->di_tmpfile = 1;
++ get_file(h_file);
++ au_di(dentry)->di_htmpfile = h_file;
++
++ /* update without i_mutex */
++ if (au_ibtop(dir) == au_dbtop(dentry))
++ au_cpup_attr_timesizes(dir);
+
++out_h_file:
++ fput(h_file);
++out_mnt:
++ vfsub_mnt_drop_write(h_mnt);
++out_parent:
++ di_write_unlock(parent);
++ dput(parent);
++ di_write_unlock(dentry);
++ if (!err)
++ goto out_si;
++ if (h_file)
++ fput(h_file);
++ au_di(dentry)->di_htmpfile = NULL;
++ au_di_fin(dentry);
++ dentry->d_fsdata = NULL;
++out_si:
++ si_read_unlock(sb);
++ if (!err && h_file) {
++ /* finally... */
++ err = finish_open_simple(file, err);
++ if (!err)
++ au_lcnt_inc(&br->br_nfiles);
++ else {
++ fput(h_file);
++ au_di(dentry)->di_htmpfile = NULL;
++ au_di_fin(dentry);
++ dentry->d_fsdata = NULL;
++ }
++ }
+out:
++ inode_unlock(dir);
++ AuTraceErr(err);
+ return err;
+}
+
-+/*
-+ * decide the branch where we operate for @dentry. the branch index will be set
-+ * @rbcpup. after deciding it, 'pin' it and store the timestamps of the parent
-+ * dir for reverting.
-+ * when a new whiteout is necessary, create it.
-+ */
-+static struct dentry*
-+lock_hdir_create_wh(struct dentry *dentry, int isdir, aufs_bindex_t *rbcpup,
-+ struct au_dtime *dt, struct au_pin *pin)
-+{
-+ struct dentry *wh_dentry;
-+ struct super_block *sb;
++/* ---------------------------------------------------------------------- */
++
++struct au_link_args {
++ aufs_bindex_t bdst, bsrc;
++ struct au_pin pin;
+ struct path h_path;
-+ int err, need_wh;
-+ unsigned int udba;
-+ aufs_bindex_t bcpup;
++ struct dentry *src_parent, *parent;
++};
+
-+ need_wh = au_wr_dir_need_wh(dentry, isdir, rbcpup);
-+ wh_dentry = ERR_PTR(need_wh);
-+ if (unlikely(need_wh < 0))
++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;
+
-+ sb = dentry->d_sb;
-+ udba = au_opt_udba(sb);
-+ bcpup = *rbcpup;
-+ err = au_pin(pin, dentry, bcpup, udba,
++ 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);
-+ wh_dentry = ERR_PTR(err);
+ if (unlikely(err))
+ goto out;
+
-+ h_path.dentry = au_pinned_h_parent(pin);
-+ if (udba != AuOpt_UDBA_NONE
-+ && au_dbtop(dentry) == bcpup) {
-+ err = au_may_del(dentry, bcpup, h_path.dentry, isdir);
-+ wh_dentry = ERR_PTR(err);
-+ if (unlikely(err))
-+ goto out_unpin;
-+ }
-+
-+ h_path.mnt = au_sbr_mnt(sb, bcpup);
-+ au_dtime_store(dt, au_pinned_parent(pin), &h_path);
-+ wh_dentry = NULL;
-+ if (!need_wh)
-+ goto out; /* success, no need to create whiteout */
-+
-+ wh_dentry = au_wh_create(dentry, bcpup, h_path.dentry);
-+ if (IS_ERR(wh_dentry))
-+ goto out_unpin;
-+
-+ /* returns with the parent is locked and wh_dentry is dget-ed */
-+ goto out; /* success */
++ err = au_sio_cpup_simple(&cpg);
++ au_unpin(&a->pin);
+
-+out_unpin:
-+ au_unpin(pin);
+out:
-+ return wh_dentry;
++ di_read_unlock(a->src_parent, AuLock_IR);
++ return err;
+}
+
-+/*
-+ * when removing a dir, rename it to a unique temporary whiteout-ed name first
-+ * in order to be revertible and save time for removing many child whiteouts
-+ * under the dir.
-+ * returns 1 when there are too many child whiteout and caller should remove
-+ * them asynchronously. returns 0 when the number of children is enough small to
-+ * remove now or the branch fs is a remote fs.
-+ * otherwise return an error.
-+ */
-+static int renwh_and_rmdir(struct dentry *dentry, aufs_bindex_t bindex,
-+ struct au_nhash *whlist, struct inode *dir)
++static int au_cpup_or_link(struct dentry *src_dentry, struct dentry *dentry,
++ struct au_link_args *a)
+{
-+ int rmdir_later, err, dirwh;
-+ struct dentry *h_dentry;
++ 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 inode *inode;
++ struct file *h_file;
+
-+ sb = dentry->d_sb;
-+ SiMustAnyLock(sb);
-+ h_dentry = au_h_dptr(dentry, bindex);
-+ err = au_whtmp_ren(h_dentry, au_sbr(sb, bindex));
-+ if (unlikely(err))
-+ goto out;
++ 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;
+
-+ /* stop monitoring */
-+ inode = d_inode(dentry);
-+ au_hn_free(au_hi(inode, bindex));
++ if (unlikely(d_is_negative(h_src_dentry))) {
++ dput(h_src_dentry);
++ h_src_dentry = NULL;
++ }
+
-+ if (!au_test_fs_remote(h_dentry->d_sb)) {
-+ dirwh = au_sbi(sb)->si_dirwh;
-+ rmdir_later = (dirwh <= 1);
-+ if (!rmdir_later)
-+ rmdir_later = au_nhash_test_longer_wh(whlist, bindex,
-+ dirwh);
-+ if (rmdir_later)
-+ return rmdir_later;
++ }
++ 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;
++ }
+ }
+
-+ err = au_whtmp_rmdir(dir, bindex, h_dentry, whlist);
-+ if (unlikely(err)) {
-+ AuIOErr("rmdir %pd, b%d failed, %d. ignored\n",
-+ h_dentry, bindex, err);
-+ err = 0;
-+ }
++ if (!err && !plink)
++ au_plink_append(inode, a->bdst, a->h_path.dentry);
+
+out:
+ AuTraceErr(err);
+ return err;
+}
+
-+/*
-+ * final procedure for deleting a entry.
-+ * maintain dentry and iattr.
-+ */
-+static void epilog(struct inode *dir, struct dentry *dentry,
-+ aufs_bindex_t bindex)
-+{
-+ struct inode *inode;
-+
-+ inode = d_inode(dentry);
-+ d_drop(dentry);
-+ inode_set_ctime_to_ts(inode, inode_get_ctime(dir));
-+
-+ au_dir_ts(dir, bindex);
-+ inode_inc_iversion(dir);
-+}
-+
-+/*
-+ * when an error happened, remove the created whiteout and revert everything.
-+ */
-+static int do_revert(int err, struct inode *dir, aufs_bindex_t bindex,
-+ aufs_bindex_t bwh, struct dentry *wh_dentry,
-+ struct dentry *dentry, struct au_dtime *dt)
++int aufs_link(struct dentry *src_dentry, struct inode *dir,
++ struct dentry *dentry)
+{
-+ int rerr;
-+ struct path h_path = {
-+ .dentry = wh_dentry,
-+ .mnt = au_sbr_mnt(dir->i_sb, bindex)
++ 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
+ };
+
-+ rerr = au_wh_unlink_dentry(au_h_iptr(dir, bindex), &h_path, dentry);
-+ if (!rerr) {
-+ au_set_dbwh(dentry, bwh);
-+ au_dtime_revert(dt);
-+ return 0;
-+ }
-+
-+ AuIOErr("%pd reverting whiteout failed(%d, %d)\n", dentry, err, rerr);
-+ return -EIO;
-+}
-+
-+/* ---------------------------------------------------------------------- */
-+
-+int aufs_unlink(struct inode *dir, struct dentry *dentry)
-+{
-+ int err;
-+ aufs_bindex_t bwh, bindex, btop;
-+ struct inode *inode, *h_dir, *delegated, *h_inode;
-+ struct dentry *parent, *wh_dentry;
-+ /* to reduce stack size */
-+ struct {
-+ struct au_dtime dt;
-+ struct au_pin pin;
-+ struct path h_path;
-+ } *a;
-+
+ IMustLock(dir);
++ inode = d_inode(src_dentry);
++ IMustLock(inode);
+
+ err = -ENOMEM;
-+ a = kmalloc(sizeof(*a), GFP_NOFS);
++ a = kzalloc(sizeof(*a), GFP_NOFS);
+ if (unlikely(!a))
+ goto out;
+
-+ err = aufs_read_lock(dentry, AuLock_DW | AuLock_GEN);
++ 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_free;
-+ err = au_d_hashed_positive(dentry);
++ 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;
-+ inode = d_inode(dentry);
-+ IMustLock(inode);
-+ err = -EISDIR;
-+ if (unlikely(d_is_dir(dentry)))
-+ goto out_unlock; /* possible? */
+
-+ btop = au_dbtop(dentry);
-+ bwh = au_dbwh(dentry);
-+ bindex = -1;
-+ parent = dentry->d_parent; /* dir inode is locked */
-+ di_write_lock_parent(parent);
-+ wh_dentry = lock_hdir_create_wh(dentry, /*isdir*/0, &bindex, &a->dt,
-+ &a->pin);
++ 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;
+
-+ a->h_path.mnt = au_sbr_mnt(dentry->d_sb, btop);
-+ a->h_path.dentry = au_h_dptr(dentry, btop);
-+ dget(a->h_path.dentry);
-+ if (bindex == btop) {
-+ h_dir = au_pinned_h_dir(&a->pin);
-+ delegated = NULL;
-+ err = vfsub_unlink(h_dir, &a->h_path, &delegated, /*force*/0);
-+ if (unlikely(err == -EWOULDBLOCK)) {
-+ pr_warn("cannot retry for NFSv4 delegation"
-+ " for an internal unlink\n");
-+ iput(delegated);
++ 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);
++ }
++ }
+ }
-+ } else {
-+ /* dir inode is locked */
-+ h_dir = d_inode(wh_dentry->d_parent);
-+ IMustLock(h_dir);
-+ err = 0;
+ }
++ if (unlikely(err))
++ goto out_unpin;
+
-+ if (!err) {
-+ vfsub_drop_nlink(inode);
-+ epilog(dir, dentry, bindex);
-+
-+ /* update target timestamps */
-+ if (bindex == btop) {
-+ vfsub_update_h_iattr(&a->h_path, /*did*/NULL);
-+ /*ignore*/
-+ h_inode = d_inode(a->h_path.dentry);
-+ inode_set_ctime_to_ts(inode, inode_get_ctime(h_inode));
-+ } else
-+ /* todo: this timestamp may be reverted later */
-+ inode_set_ctime_to_ts(inode, inode_get_ctime(h_dir));
-+ goto out_unpin; /* success */
++ 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;
+ }
+
-+ /* revert */
-+ if (wh_dentry) {
-+ int rerr;
++ au_dir_ts(dir, a->bdst);
++ inode_inc_iversion(dir);
++ inc_nlink(inode);
++ inode_set_ctime_to_ts(inode, inode_get_ctime(dir));
++ 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 */
+
-+ rerr = do_revert(err, dir, bindex, bwh, wh_dentry, dentry,
-+ &a->dt);
-+ if (rerr)
-+ err = rerr;
++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);
-+ dput(a->h_path.dentry);
+out_parent:
-+ di_write_unlock(parent);
++ di_write_unlock(a->parent);
++ dput(a->src_parent);
+out_unlock:
-+ aufs_read_unlock(dentry, AuLock_DW);
-+out_free:
++ 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_rmdir(struct inode *dir, struct dentry *dentry)
++int aufs_mkdir(struct mnt_idmap *idmap, struct inode *dir,
++ struct dentry *dentry, umode_t mode)
+{
-+ int err, rmdir_later;
-+ aufs_bindex_t bwh, bindex, btop;
-+ struct inode *inode;
-+ struct dentry *parent, *wh_dentry, *h_dentry;
-+ struct au_whtmp_rmdir *args;
-+ /* to reduce stack size */
++ 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_dtime dt;
+ struct au_pin pin;
-+ } *a;
++ 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);
+
+ if (unlikely(!a))
+ goto out;
+
-+ err = aufs_read_lock(dentry, AuLock_DW | AuLock_FLUSH | AuLock_GEN);
++ err = aufs_read_lock(dentry, AuLock_DW | AuLock_GEN);
+ if (unlikely(err))
+ goto out_free;
-+ err = au_alive_dir(dentry);
++ err = au_d_may_add(dentry);
+ if (unlikely(err))
+ goto out_unlock;
-+ inode = d_inode(dentry);
-+ IMustLock(inode);
-+ err = -ENOTDIR;
-+ if (unlikely(!d_is_dir(dentry)))
-+ goto out_unlock; /* possible? */
-+
-+ err = -ENOMEM;
-+ args = au_whtmp_rmdir_alloc(dir->i_sb, GFP_NOFS);
-+ if (unlikely(!args))
-+ goto out_unlock;
+
+ parent = dentry->d_parent; /* dir inode is locked */
+ di_write_lock_parent(parent);
-+ err = au_test_empty(dentry, &args->whlist);
-+ if (unlikely(err))
-+ goto out_parent;
-+
-+ btop = au_dbtop(dentry);
-+ bwh = au_dbwh(dentry);
-+ bindex = -1;
-+ wh_dentry = lock_hdir_create_wh(dentry, /*isdir*/1, &bindex, &a->dt,
-+ &a->pin);
++ 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;
+
-+ h_dentry = au_h_dptr(dentry, btop);
-+ dget(h_dentry);
-+ rmdir_later = 0;
-+ if (bindex == btop) {
-+ err = renwh_and_rmdir(dentry, btop, &args->whlist, dir);
-+ if (err > 0) {
-+ rmdir_later = err;
-+ err = 0;
-+ }
-+ } else {
-+ /* stop monitoring */
-+ au_hn_free(au_hi(inode, btop));
++ 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;
+
-+ /* dir inode is locked */
-+ IMustLock(d_inode(wh_dentry->d_parent));
-+ err = 0;
++ /* 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) {
-+ vfsub_dead_dir(inode);
-+ au_set_dbdiropq(dentry, -1);
-+ epilog(dir, dentry, bindex);
-+
-+ if (rmdir_later) {
-+ au_whtmp_kick_rmdir(dir, btop, h_dentry, args);
-+ args = NULL;
-+ }
-+
++ inc_nlink(dir);
+ goto out_unpin; /* success */
+ }
+
+ /* revert */
-+ AuLabel(revert);
-+ if (wh_dentry) {
-+ int rerr;
-+
-+ rerr = do_revert(err, dir, bindex, bwh, wh_dentry, dentry,
-+ &a->dt);
-+ if (rerr)
-+ err = rerr;
++ if (diropq) {
++ AuLabel(revert opq);
++ inode_lock_nested(h_inode, AuLsc_I_CHILD);
++ rerr = au_diropq_remove(dentry, bindex);
++ inode_unlock(h_inode);
++ if (rerr) {
++ AuIOErr("%pd reverting diropq failed(%d, %d)\n",
++ dentry, err, rerr);
++ err = -EIO;
++ }
+ }
+
++out_dir:
++ AuLabel(revert dir);
++ rerr = vfsub_rmdir(au_pinned_h_dir(&a->pin), &h_path);
++ if (rerr) {
++ AuIOErr("%pd reverting dir failed(%d, %d)\n",
++ dentry, err, rerr);
++ err = -EIO;
++ }
++ au_dtime_revert(&a->dt);
+out_unpin:
+ au_unpin(&a->pin);
+ dput(wh_dentry);
-+ dput(h_dentry);
+out_parent:
+ di_write_unlock(parent);
-+ if (args)
-+ au_whtmp_rmdir_free(args);
+out_unlock:
++ if (unlikely(err)) {
++ au_update_dbtop(dentry);
++ d_drop(dentry);
++ }
+ aufs_read_unlock(dentry, AuLock_DW);
+out_free:
+ au_kfree_rcu(a);
+out:
-+ AuTraceErr(err);
+ return err;
+}
-diff --git a/fs/aufs/i_op_ren.c b/fs/aufs/i_op_ren.c
-new file mode 100644
-index 00000000000000..e5a3d5549ac7ae
---- /dev/null
-+++ b/fs/aufs/i_op_ren.c
-@@ -0,0 +1,1260 @@
+diff -urN /usr/share/empty/fs/aufs/i_op.c linux/fs/aufs/i_op.c
+--- /usr/share/empty/fs/aufs/i_op.c 1970-01-01 01:00:00.000000000 +0100
++++ linux/fs/aufs/i_op.c 2024-03-10 23:40:47.083143450 +0100
+@@ -0,0 +1,1520 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2005-2022 Junjiro R. Okajima
+ */
+
+/*
-+ * inode operation (rename entry)
-+ * todo: this is crazy monster
++ * inode operations (except add/del/rename)
+ */
+
++#include <linux/device_cgroup.h>
++#include <linux/filelock.h>
++#include <linux/fs_stack.h>
+#include <linux/iversion.h>
++#include <linux/security.h>
+#include "aufs.h"
+
-+enum { AuSRC, AuDST, AuSrcDst };
-+enum { AuPARENT, AuCHILD, AuParentChild };
++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));
++ struct mnt_idmap *h_idmap;
+
-+#define AuRen_ISDIR_SRC 1
-+#define AuRen_ISDIR_DST (1 << 1)
-+#define AuRen_ISSAMEDIR (1 << 2)
-+#define AuRen_WHSRC (1 << 3)
-+#define AuRen_WHDST (1 << 4)
-+#define AuRen_MNT_WRITE (1 << 5)
-+#define AuRen_DT_DSTDIR (1 << 6)
-+#define AuRen_DIROPQ_SRC (1 << 7)
-+#define AuRen_DIROPQ_DST (1 << 8)
-+#define AuRen_DIRREN (1 << 9)
-+#define AuRen_DROPPED_SRC (1 << 10)
-+#define AuRen_DROPPED_DST (1 << 11)
-+#define au_ftest_ren(flags, name) ((flags) & AuRen_##name)
-+#define au_fset_ren(flags, name) \
-+ do { (flags) |= AuRen_##name; } while (0)
-+#define au_fclr_ren(flags, name) \
-+ do { (flags) &= ~AuRen_##name; } while (0)
++ err = -EPERM;
++ if (write_mask && IS_IMMUTABLE(h_inode))
++ goto out;
+
-+#ifndef CONFIG_AUFS_DIRREN
-+#undef AuRen_DIRREN
-+#define AuRen_DIRREN 0
-+#endif
++ err = -EACCES;
++ if (((mask & MAY_EXEC)
++ && S_ISREG(h_inode->i_mode)
++ && (path_noexec(h_path)
++ || !(h_inode->i_mode & 0111))))
++ goto out;
+
-+struct au_ren_args {
-+ struct {
-+ struct dentry *dentry, *h_dentry, *parent, *h_parent,
-+ *wh_dentry;
-+ struct inode *dir, *inode;
-+ struct au_hinode *hdir, *hinode;
-+ struct au_dtime dt[AuParentChild];
-+ aufs_bindex_t btop, bdiropq;
-+ } sd[AuSrcDst];
++ /*
++ * - 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.
++ */
++ h_idmap = mnt_idmap(h_path->mnt);
++ 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_inode_acl %ps\n",
++ h_inode->i_op->get_inode_acl); */
++ err = generic_permission(h_idmap, h_inode, mask);
++ if (err == -EOPNOTSUPP && au_test_nfs_noacl(h_inode))
++ err = h_inode->i_op->permission(h_idmap, h_inode,
++ mask);
++ AuTraceErr(err);
++ } else {
++ /* AuLabel(h_inode->permission); */
++ err = h_inode->i_op->permission(h_idmap, h_inode, mask);
++ AuTraceErr(err);
++ }
+
-+#define src_dentry sd[AuSRC].dentry
-+#define src_dir sd[AuSRC].dir
-+#define src_inode sd[AuSRC].inode
-+#define src_h_dentry sd[AuSRC].h_dentry
-+#define src_parent sd[AuSRC].parent
-+#define src_h_parent sd[AuSRC].h_parent
-+#define src_wh_dentry sd[AuSRC].wh_dentry
-+#define src_hdir sd[AuSRC].hdir
-+#define src_hinode sd[AuSRC].hinode
-+#define src_h_dir sd[AuSRC].hdir->hi_inode
-+#define src_dt sd[AuSRC].dt
-+#define src_btop sd[AuSRC].btop
-+#define src_bdiropq sd[AuSRC].bdiropq
++ if (!err)
++ err = devcgroup_inode_permission(h_inode, mask);
++ if (!err)
++ err = security_inode_permission(h_inode, mask);
+
-+#define dst_dentry sd[AuDST].dentry
-+#define dst_dir sd[AuDST].dir
-+#define dst_inode sd[AuDST].inode
-+#define dst_h_dentry sd[AuDST].h_dentry
-+#define dst_parent sd[AuDST].parent
-+#define dst_h_parent sd[AuDST].h_parent
-+#define dst_wh_dentry sd[AuDST].wh_dentry
-+#define dst_hdir sd[AuDST].hdir
-+#define dst_hinode sd[AuDST].hinode
-+#define dst_h_dir sd[AuDST].hdir->hi_inode
-+#define dst_dt sd[AuDST].dt
-+#define dst_btop sd[AuDST].btop
-+#define dst_bdiropq sd[AuDST].bdiropq
++out:
++ return err;
++}
+
-+ struct dentry *h_trap;
++static int aufs_permission(struct mnt_idmap *idmap, 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;
-+ struct path h_path;
-+ struct au_nhash whlist;
-+ aufs_bindex_t btgt, src_bwh;
-+
-+ struct {
-+ unsigned short auren_flags;
-+ unsigned char flags; /* syscall parameter */
-+ unsigned char exchange;
-+ } __packed;
+
-+ struct au_whtmp_rmdir *thargs;
-+ struct dentry *h_dst;
-+ struct au_hinode *h_root;
-+};
++ /* 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 /* reserved for future use */
++ /*
++ * This test may be rather 'too much' since the test is essentially done
++ * in the aufs_lookup(). Theoretically it is possible that the inode
++ * generation doesn't match to the superblock's here. But it isn't a
++ * big deal I suppose.
++ */
++ err = au_iigen_test(inode, au_sigen(sb));
++ if (unlikely(err))
++ goto out;
++#endif
+
-+/*
-+ * functions for reverting.
-+ * when an error happened in a single rename systemcall, we should revert
-+ * everything as if nothing happened.
-+ * we don't need to revert the copied-up/down the parent dir since they are
-+ * harmless.
-+ */
++ 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;
+
-+#define RevertFailure(fmt, ...) do { \
-+ AuIOErr("revert failure: " fmt " (%d, %d)\n", \
-+ ##__VA_ARGS__, err, rerr); \
-+ err = -EIO; \
-+} while (0)
++ 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;
++ }
+
-+static void au_ren_do_rev_diropq(int err, struct au_ren_args *a, int idx)
-+{
-+ int rerr;
-+ struct dentry *d;
-+#define src_or_dst(member) a->sd[idx].member
++ /* 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;
+
-+ d = src_or_dst(dentry); /* {src,dst}_dentry */
-+ au_hn_inode_lock_nested(src_or_dst(hinode), AuLsc_I_CHILD);
-+ rerr = au_diropq_remove(d, a->btgt);
-+ au_hn_inode_unlock(src_or_dst(hinode));
-+ au_set_dbdiropq(d, src_or_dst(bdiropq));
-+ if (rerr)
-+ RevertFailure("remove diropq %pd", d);
++ br = au_sbr(sb, bindex);
++ err = h_permission(h_inode, mask, &br->br_path,
++ br->br_perm);
++ }
++ }
+
-+#undef src_or_dst_
++out:
++ ii_read_unlock(inode);
++ si_read_unlock(sb);
++ return err;
+}
+
-+static void au_ren_rev_diropq(int err, struct au_ren_args *a)
-+{
-+ if (au_ftest_ren(a->auren_flags, DIROPQ_SRC))
-+ au_ren_do_rev_diropq(err, a, AuSRC);
-+ if (au_ftest_ren(a->auren_flags, DIROPQ_DST))
-+ au_ren_do_rev_diropq(err, a, AuDST);
-+}
++/* ---------------------------------------------------------------------- */
+
-+static void au_ren_rev_rename(int err, struct au_ren_args *a)
++static struct dentry *aufs_lookup(struct inode *dir, struct dentry *dentry,
++ unsigned int flags)
+{
-+ int rerr;
-+ struct inode *delegated;
-+ struct path h_ppath = {
-+ .dentry = a->src_h_parent,
-+ .mnt = a->h_path.mnt
-+ };
++ struct dentry *ret, *parent;
++ struct inode *inode;
++ struct super_block *sb;
++ int err, npositive;
+
-+ a->h_path.dentry = vfsub_lkup_one(&a->src_dentry->d_name, &h_ppath);
-+ rerr = PTR_ERR(a->h_path.dentry);
-+ if (IS_ERR(a->h_path.dentry)) {
-+ RevertFailure("lkup one %pd", a->src_dentry);
-+ return;
-+ }
++ IMustLock(dir);
+
-+ delegated = NULL;
-+ rerr = vfsub_rename(a->dst_h_dir,
-+ au_h_dptr(a->src_dentry, a->btgt),
-+ a->src_h_dir, &a->h_path, &delegated, a->flags);
-+ if (unlikely(rerr == -EWOULDBLOCK)) {
-+ pr_warn("cannot retry for NFSv4 delegation"
-+ " for an internal rename\n");
-+ iput(delegated);
-+ }
-+ d_drop(a->h_path.dentry);
-+ dput(a->h_path.dentry);
-+ /* au_set_h_dptr(a->src_dentry, a->btgt, NULL); */
-+ if (rerr)
-+ RevertFailure("rename %pd", a->src_dentry);
-+}
++ /* todo: support rcu-walk? */
++ ret = ERR_PTR(-ECHILD);
++ if (flags & LOOKUP_RCU)
++ goto out;
+
-+static void au_ren_rev_whtmp(int err, struct au_ren_args *a)
-+{
-+ int rerr;
-+ struct inode *delegated;
-+ struct path h_ppath = {
-+ .dentry = a->dst_h_parent,
-+ .mnt = a->h_path.mnt
-+ };
++ ret = ERR_PTR(-ENAMETOOLONG);
++ if (unlikely(dentry->d_name.len > AUFS_MAX_NAMELEN))
++ goto out;
+
-+ a->h_path.dentry = vfsub_lkup_one(&a->dst_dentry->d_name, &h_ppath);
-+ rerr = PTR_ERR(a->h_path.dentry);
-+ if (IS_ERR(a->h_path.dentry)) {
-+ RevertFailure("lkup one %pd", a->dst_dentry);
-+ return;
++ 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;
+ }
-+ if (d_is_positive(a->h_path.dentry)) {
-+ d_drop(a->h_path.dentry);
-+ dput(a->h_path.dentry);
-+ return;
++ 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;
++ }
+ }
+
-+ delegated = NULL;
-+ rerr = vfsub_rename(a->dst_h_dir, a->h_dst, a->dst_h_dir, &a->h_path,
-+ &delegated, a->flags);
-+ if (unlikely(rerr == -EWOULDBLOCK)) {
-+ pr_warn("cannot retry for NFSv4 delegation"
-+ " for an internal rename\n");
-+ iput(delegated);
++ if (inode)
++ atomic_inc(&inode->i_count);
++ ret = d_splice_alias(inode, dentry);
++#if 0 /* reserved for future use */
++ 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;
++ }
+ }
-+ d_drop(a->h_path.dentry);
-+ dput(a->h_path.dentry);
-+ if (!rerr)
-+ au_set_h_dptr(a->dst_dentry, a->btgt, dget(a->h_dst));
-+ else
-+ RevertFailure("rename %pd", a->h_dst);
-+}
-+
-+static void au_ren_rev_whsrc(int err, struct au_ren_args *a)
-+{
-+ int rerr;
+
-+ a->h_path.dentry = a->src_wh_dentry;
-+ rerr = au_wh_unlink_dentry(a->src_h_dir, &a->h_path, a->src_dentry);
-+ au_set_dbwh(a->src_dentry, a->src_bwh);
-+ if (rerr)
-+ RevertFailure("unlink %pd", a->src_wh_dentry);
++out_unlock:
++ di_write_unlock(dentry);
++out_si:
++ si_read_unlock(sb);
++out:
++ return ret;
+}
-+#undef RevertFailure
+
+/* ---------------------------------------------------------------------- */
+
+/*
-+ * when we have to copyup the renaming entry, do it with the rename-target name
-+ * in order to minimize the cost (the later actual rename is unnecessary).
-+ * otherwise rename it on the target branch.
++ * 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()
+ */
-+static int au_ren_or_cpup(struct au_ren_args *a)
++
++struct aopen_node {
++ struct hlist_bl_node hblist;
++ struct file *file, *h_file;
++};
++
++static int au_do_aopen(struct inode *inode, struct file *file)
+{
-+ int err;
-+ struct dentry *d;
-+ struct inode *delegated;
++ 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
++ };
+
-+ d = a->src_dentry;
-+ if (au_dbtop(d) == a->btgt) {
-+ a->h_path.dentry = a->dst_h_dentry;
-+ AuDebugOn(au_dbtop(d) != a->btgt);
-+ delegated = NULL;
-+ err = vfsub_rename(a->src_h_dir, au_h_dptr(d, a->btgt),
-+ a->dst_h_dir, &a->h_path, &delegated,
-+ a->flags);
-+ if (unlikely(err == -EWOULDBLOCK)) {
-+ pr_warn("cannot retry for NFSv4 delegation"
-+ " for an internal rename\n");
-+ iput(delegated);
++ 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;
+ }
-+ } else
-+ BUG();
-+
-+ if (!err && a->h_dst)
-+ /* it will be set to dinfo later */
-+ dget(a->h_dst);
++ hlist_bl_unlock(aopen);
++ /* AuDebugOn(!args.h_file); */
+
-+ return err;
++ return au_do_open(file, &args);
+}
+
-+/* cf. aufs_rmdir() */
-+static int au_ren_del_whtmp(struct au_ren_args *a)
++static int au_aopen_do_open(struct file *file, struct dentry *dentry,
++ struct aopen_node *aopen_node)
+{
+ int err;
-+ struct inode *dir;
++ struct hlist_bl_head *aopen;
+
-+ dir = a->dst_dir;
-+ SiMustAnyLock(dir->i_sb);
-+ if (!au_nhash_test_longer_wh(&a->whlist, a->btgt,
-+ au_sbi(dir->i_sb)->si_dirwh)
-+ || au_test_fs_remote(a->h_dst->d_sb)) {
-+ err = au_whtmp_rmdir(dir, a->btgt, a->h_dst, &a->whlist);
-+ if (unlikely(err))
-+ pr_warn("failed removing whtmp dir %pd (%d), "
-+ "ignored.\n", a->h_dst, err);
-+ } else {
-+ au_nhash_wh_free(&a->thargs->whlist);
-+ a->thargs->whlist = a->whlist;
-+ a->whlist.nh_num = 0;
-+ au_whtmp_kick_rmdir(dir, a->btgt, a->h_dst, a->thargs);
-+ dput(a->h_dst);
-+ a->thargs = NULL;
-+ }
++ 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" : "");
+
-+ return 0;
++ AuTraceErr(err);
++ return err;
+}
+
-+/* make it 'opaque' dir. */
-+static int au_ren_do_diropq(struct au_ren_args *a, int idx)
++static int au_aopen_no_open(struct file *file, struct dentry *dentry)
+{
+ int err;
-+ struct dentry *d, *diropq;
-+#define src_or_dst(member) a->sd[idx].member
+
-+ err = 0;
-+ d = src_or_dst(dentry); /* {src,dst}_dentry */
-+ src_or_dst(bdiropq) = au_dbdiropq(d);
-+ src_or_dst(hinode) = au_hi(src_or_dst(inode), a->btgt);
-+ au_hn_inode_lock_nested(src_or_dst(hinode), AuLsc_I_CHILD);
-+ diropq = au_diropq_create(d, a->btgt);
-+ au_hn_inode_unlock(src_or_dst(hinode));
-+ if (IS_ERR(diropq))
-+ err = PTR_ERR(diropq);
-+ else
-+ dput(diropq);
++ AuLabel(here);
++ dget(dentry);
++ err = finish_no_open(file, dentry);
+
-+#undef src_or_dst_
++ AuTraceErr(err);
+ return err;
+}
+
-+static int au_ren_diropq(struct au_ren_args *a)
++static int aufs_atomic_open(struct inode *dir, struct dentry *dentry,
++ struct file *file, unsigned int open_flag,
++ umode_t create_mode)
+{
-+ int err;
-+ unsigned char always;
-+ struct dentry *d;
++ 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;
-+ d = a->dst_dentry; /* already renamed on the branch */
-+ always = !!au_opt_test(au_mntflags(d->d_sb), ALWAYS_DIROPQ);
-+ if (au_ftest_ren(a->auren_flags, ISDIR_SRC)
-+ && !au_ftest_ren(a->auren_flags, DIRREN)
-+ && a->btgt != au_dbdiropq(a->src_dentry)
-+ && (a->dst_wh_dentry
-+ || a->btgt <= au_dbdiropq(d)
-+ /* hide the lower to keep xino */
-+ /* the lowers may not be a dir, but we hide them anyway */
-+ || a->btgt < au_dbbot(d)
-+ || always)) {
-+ AuDbg("here\n");
-+ err = au_ren_do_diropq(a, AuSRC);
-+ if (unlikely(err))
++ 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;
-+ au_fset_ren(a->auren_flags, DIROPQ_SRC);
++ } else if (d) {
++ /*
++ * obsoleted dentry found.
++ * another error will be returned later.
++ */
++ d_drop(d);
++ AuDbgDentry(d);
++ dput(d);
++ }
++ AuDbgDentry(dentry);
+ }
-+ if (!a->exchange)
++
++ 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 */
++ }
+
-+ d = a->src_dentry; /* already renamed on the branch */
-+ if (au_ftest_ren(a->auren_flags, ISDIR_DST)
-+ && a->btgt != au_dbdiropq(a->dst_dentry)
-+ && (a->btgt < au_dbdiropq(d)
-+ || a->btgt < au_dbbot(d)
-+ || always)) {
-+ AuDbgDentry(a->src_dentry);
-+ AuDbgDentry(a->dst_dentry);
-+ err = au_ren_do_diropq(a, AuDST);
-+ if (unlikely(err))
-+ goto out_rev_src;
-+ au_fset_ren(a->auren_flags, DIROPQ_DST);
++ 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 */
+ }
-+ goto out; /* success */
+
-+out_rev_src:
-+ AuDbg("err %d, reverting src\n", err);
-+ au_ren_rev_diropq(err, a);
++ 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 do_rename(struct au_ren_args *a)
-+{
-+ int err;
-+ struct dentry *d, *h_d;
-+ struct inode *h_inode;
+
-+ if (!a->exchange) {
-+ /* prepare workqueue args for asynchronous rmdir */
-+ h_d = a->dst_h_dentry;
-+ if (au_ftest_ren(a->auren_flags, ISDIR_DST)
-+ /* && !au_ftest_ren(a->auren_flags, DIRREN) */
-+ && d_is_positive(h_d)) {
-+ err = -ENOMEM;
-+ a->thargs = au_whtmp_rmdir_alloc(a->src_dentry->d_sb,
-+ GFP_NOFS);
-+ if (unlikely(!a->thargs))
-+ goto out;
-+ a->h_dst = dget(h_d);
-+ }
++/* ---------------------------------------------------------------------- */
+
-+ /* create whiteout for src_dentry */
-+ if (au_ftest_ren(a->auren_flags, WHSRC)) {
-+ a->src_bwh = au_dbwh(a->src_dentry);
-+ AuDebugOn(a->src_bwh >= 0);
-+ a->src_wh_dentry = au_wh_create(a->src_dentry, a->btgt,
-+ a->src_h_parent);
-+ err = PTR_ERR(a->src_wh_dentry);
-+ if (IS_ERR(a->src_wh_dentry))
-+ goto out_thargs;
-+ }
++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;
+
-+ /* lookup whiteout for dentry */
-+ if (au_ftest_ren(a->auren_flags, WHDST)) {
-+ h_d = au_wh_lkup(a->dst_h_parent,
-+ &a->dst_dentry->d_name, a->br);
-+ err = PTR_ERR(h_d);
-+ if (IS_ERR(h_d))
-+ goto out_whsrc;
-+ if (d_is_negative(h_d))
-+ dput(h_d);
-+ else
-+ a->dst_wh_dentry = h_d;
-+ }
++ if (add_entry)
++ IMustLock(d_inode(parent));
++ else
++ di_write_lock_parent(parent);
+
-+ /* rename dentry to tmpwh */
-+ if (a->thargs) {
-+ err = au_whtmp_ren(a->dst_h_dentry, a->br);
-+ if (unlikely(err))
-+ goto out_whdst;
++ 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);
+
-+ d = a->dst_dentry;
-+ au_set_h_dptr(d, a->btgt, NULL);
-+ err = au_lkup_neg(d, a->btgt, /*wh*/0);
-+ if (unlikely(err))
-+ goto out_whtmp;
-+ a->dst_h_dentry = au_h_dptr(d, a->btgt);
++ 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);
+ }
+ }
+
-+ BUG_ON(d_is_positive(a->dst_h_dentry) && a->src_btop != a->btgt);
-+#if 0 /* debugging */
-+ BUG_ON(!au_ftest_ren(a->auren_flags, DIRREN)
-+ && d_is_positive(a->dst_h_dentry)
-+ && a->src_btop != a->btgt);
-+#endif
++ if (!add_entry)
++ di_write_unlock(parent);
++ if (!err)
++ err = bcpup; /* success */
+
-+ /* rename by vfs_rename or cpup */
-+ err = au_ren_or_cpup(a);
-+ if (unlikely(err))
-+ /* leave the copied-up one */
-+ goto out_whtmp;
++ AuTraceErr(err);
++ return err;
++}
+
-+ /* make dir opaque */
-+ err = au_ren_diropq(a);
-+ if (unlikely(err))
-+ goto out_rename;
++/*
++ * 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;
+
-+ /* update target timestamps */
-+ if (a->exchange) {
-+ AuDebugOn(au_dbtop(a->dst_dentry) != a->btgt);
-+ a->h_path.dentry = au_h_dptr(a->dst_dentry, a->btgt);
-+ vfsub_update_h_iattr(&a->h_path, /*did*/NULL); /*ignore*/
-+ h_inode = d_inode(a->h_path.dentry);
-+ inode_set_ctime_to_ts(a->dst_inode, inode_get_ctime(h_inode));
-+ }
-+ AuDebugOn(au_dbtop(a->src_dentry) != a->btgt);
-+ a->h_path.dentry = au_h_dptr(a->src_dentry, a->btgt);
-+ vfsub_update_h_iattr(&a->h_path, /*did*/NULL); /*ignore*/
-+ h_inode = d_inode(a->h_path.dentry);
-+ inode_set_ctime_to_ts(a->src_inode, inode_get_ctime(h_inode));
++ 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 (!a->exchange) {
-+ /* remove whiteout for dentry */
-+ if (a->dst_wh_dentry) {
-+ a->h_path.dentry = a->dst_wh_dentry;
-+ err = au_wh_unlink_dentry(a->dst_h_dir, &a->h_path,
-+ a->dst_dentry);
-+ if (unlikely(err))
-+ goto out_diropq;
++ 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)));
++ }
+
-+ /* remove whtmp */
-+ if (a->thargs)
-+ au_ren_del_whtmp(a); /* ignore this error */
++ AuDbg("btop %d, bcpup %d\n", btop, bcpup);
++ err = bcpup;
++ if (bcpup == btop)
++ goto out; /* success */
+
-+ au_fhsm_wrote(a->src_dentry->d_sb, a->btgt, /*force*/0);
++ /* 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));
+ }
-+ err = 0;
-+ goto out_success;
+
-+out_diropq:
-+ au_ren_rev_diropq(err, a);
-+out_rename:
-+ au_ren_rev_rename(err, a);
-+ dput(a->h_dst);
-+out_whtmp:
-+ if (a->thargs)
-+ au_ren_rev_whtmp(err, a);
-+out_whdst:
-+ dput(a->dst_wh_dentry);
-+ a->dst_wh_dentry = NULL;
-+out_whsrc:
-+ if (a->src_wh_dentry)
-+ au_ren_rev_whsrc(err, a);
-+out_success:
-+ dput(a->src_wh_dentry);
-+ dput(a->dst_wh_dentry);
-+out_thargs:
-+ if (a->thargs) {
-+ dput(a->h_dst);
-+ au_whtmp_rmdir_free(a->thargs);
-+ a->thargs = NULL;
-+ }
+out:
++ dput(parent);
+ return err;
+}
+
+/* ---------------------------------------------------------------------- */
+
-+/*
-+ * test if @dentry dir can be rename destination or not.
-+ * success means, it is a logically empty dir.
-+ */
-+static int may_rename_dstdir(struct dentry *dentry, struct au_nhash *whlist)
++void au_pin_hdir_unlock(struct au_pin *p)
+{
-+ return au_test_empty(dentry, whlist);
++ if (p->hdir)
++ au_hn_inode_unlock(p->hdir);
+}
+
-+/*
-+ * test if @a->src_dentry dir can be rename source or not.
-+ * if it can, return 0.
-+ * success means,
-+ * - it is a logically empty dir.
-+ * - or, it exists on writable branch and has no children including whiteouts
-+ * on the lower branch unless DIRREN is on.
-+ */
-+static int may_rename_srcdir(struct au_ren_args *a)
++int au_pin_hdir_lock(struct au_pin *p)
+{
+ int err;
-+ unsigned int rdhash;
-+ aufs_bindex_t btop, btgt;
-+ struct dentry *dentry;
-+ struct super_block *sb;
-+ struct au_sbinfo *sbinfo;
+
-+ dentry = a->src_dentry;
-+ sb = dentry->d_sb;
-+ sbinfo = au_sbi(sb);
-+ if (au_opt_test(sbinfo->si_mntflags, DIRREN))
-+ au_fset_ren(a->auren_flags, DIRREN);
++ err = 0;
++ if (!p->hdir)
++ goto out;
+
-+ btgt = a->btgt;
-+ btop = au_dbtop(dentry);
-+ if (btop != btgt) {
-+ struct au_nhash whlist;
++ /* even if an error happens later, keep this lock */
++ au_hn_inode_lock_nested(p->hdir, p->lsc_hi);
+
-+ SiMustAnyLock(sb);
-+ rdhash = sbinfo->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;
-+ err = au_test_empty(dentry, &whlist);
-+ au_nhash_wh_free(&whlist);
++ err = -EBUSY;
++ if (unlikely(p->hdir->hi_inode != d_inode(p->h_parent)))
+ goto out;
-+ }
-+
-+ if (btop == au_dbtaildir(dentry))
-+ return 0; /* success */
+
-+ err = au_test_empty_lower(dentry);
++ 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:
-+ if (err == -ENOTEMPTY) {
-+ if (au_ftest_ren(a->auren_flags, DIRREN)) {
-+ err = 0;
-+ } else {
-+ AuWarn1("renaming dir who has child(ren) on multiple "
-+ "branches, is not supported\n");
-+ err = -EXDEV;
-+ }
-+ }
+ return err;
+}
+
-+/* side effect: sets whlist and h_dentry */
-+static int au_ren_may_dir(struct au_ren_args *a)
++int au_pin_hdir_relock(struct au_pin *p)
+{
-+ int err;
-+ unsigned int rdhash;
-+ struct dentry *d;
-+
-+ d = a->dst_dentry;
-+ SiMustAnyLock(d->d_sb);
-+
-+ err = 0;
-+ if (au_ftest_ren(a->auren_flags, ISDIR_DST) && a->dst_inode) {
-+ rdhash = au_sbi(d->d_sb)->si_rdhash;
-+ if (!rdhash)
-+ rdhash = au_rdhash_est(au_dir_size(/*file*/NULL, d));
-+ err = au_nhash_alloc(&a->whlist, rdhash, GFP_NOFS);
-+ if (unlikely(err))
-+ goto out;
++ int err, i;
++ struct inode *h_i;
++ struct dentry *h_d[] = {
++ p->h_dentry,
++ p->h_parent
++ };
+
-+ if (!a->exchange) {
-+ au_set_dbtop(d, a->dst_btop);
-+ err = may_rename_dstdir(d, &a->whlist);
-+ au_set_dbtop(d, a->btgt);
-+ } else
-+ err = may_rename_srcdir(a);
-+ }
-+ a->dst_h_dentry = au_h_dptr(d, au_dbtop(d));
++ err = au_pin_hdir_lock(p);
+ if (unlikely(err))
+ goto out;
+
-+ d = a->src_dentry;
-+ a->src_h_dentry = au_h_dptr(d, au_dbtop(d));
-+ if (au_ftest_ren(a->auren_flags, ISDIR_SRC)) {
-+ err = may_rename_srcdir(a);
-+ if (unlikely(err)) {
-+ au_nhash_wh_free(&a->whlist);
-+ a->whlist.nh_num = 0;
++ 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;
+}
+
-+/* ---------------------------------------------------------------------- */
-+
-+/*
-+ * simple tests for rename.
-+ * following the checks in vfs, plus the parent-child relationship.
-+ */
-+static int au_may_ren(struct au_ren_args *a)
++static void au_pin_hdir_set_owner(struct au_pin *p, struct task_struct *task)
+{
-+ int err, isdir;
-+ struct inode *h_inode;
++ atomic_long_set(&p->hdir->hi_inode->i_rwsem.owner, (long)task);
++}
+
-+ if (a->src_btop == a->btgt) {
-+ err = au_may_del(a->src_dentry, a->btgt, a->src_h_parent,
-+ au_ftest_ren(a->auren_flags, ISDIR_SRC));
-+ if (unlikely(err))
-+ goto out;
-+ err = -EINVAL;
-+ if (unlikely(a->src_h_dentry == a->h_trap))
-+ goto out;
++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);
+ }
++}
+
-+ err = 0;
-+ if (a->dst_btop != a->btgt)
-+ goto out;
-+
-+ err = -ENOTEMPTY;
-+ if (unlikely(a->dst_h_dentry == a->h_trap))
-+ goto out;
-+
-+ err = -EIO;
-+ isdir = !!au_ftest_ren(a->auren_flags, ISDIR_DST);
-+ if (d_really_is_negative(a->dst_dentry)) {
-+ if (d_is_negative(a->dst_h_dentry))
-+ err = au_may_add(a->dst_dentry, a->btgt,
-+ a->dst_h_parent, isdir);
-+ } else {
-+ if (unlikely(d_is_negative(a->dst_h_dentry)))
-+ goto out;
-+ h_inode = d_inode(a->dst_h_dentry);
-+ if (h_inode->i_nlink)
-+ err = au_may_del(a->dst_dentry, a->btgt,
-+ a->dst_h_parent, isdir);
++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, _RET_IP_);
+ }
-+
-+out:
-+ if (unlikely(err == -ENOENT || err == -EEXIST))
-+ err = -EIO;
-+ AuTraceErr(err);
-+ return err;
+}
+
-+/* ---------------------------------------------------------------------- */
++struct dentry *au_pinned_h_parent(struct au_pin *pin)
++{
++ if (pin && pin->parent)
++ return au_h_dptr(pin->parent, pin->bindex);
++ return NULL;
++}
+
-+/*
-+ * locking order
-+ * (VFS)
-+ * - src_dir and dir by lock_rename()
-+ * - inode if exists
-+ * (aufs)
-+ * - lock all
-+ * + src_dentry and dentry by aufs_read_and_write_lock2() which calls,
-+ * + si_read_lock
-+ * + di_write_lock2_child()
-+ * + di_write_lock_child()
-+ * + ii_write_lock_child()
-+ * + di_write_lock_child2()
-+ * + ii_write_lock_child2()
-+ * + src_parent and parent
-+ * + di_write_lock_parent()
-+ * + ii_write_lock_parent()
-+ * + di_write_lock_parent2()
-+ * + ii_write_lock_parent2()
-+ * + lower src_dir and dir by vfsub_lock_rename()
-+ * + verify the every relationships between child and parent. if any
-+ * of them failed, unlock all and return -EBUSY.
-+ */
-+static void au_ren_unlock(struct au_ren_args *a)
++void au_unpin(struct au_pin *p)
+{
-+ vfsub_unlock_rename(a->src_h_parent, a->src_hdir,
-+ a->dst_h_parent, a->dst_hdir);
-+ if (au_ftest_ren(a->auren_flags, DIRREN)
-+ && a->h_root)
-+ au_hn_inode_unlock(a->h_root);
-+ if (au_ftest_ren(a->auren_flags, MNT_WRITE))
-+ vfsub_mnt_drop_write(au_br_mnt(a->br));
++ 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 */
+}
+
-+static int au_ren_lock(struct au_ren_args *a)
++int au_do_pin(struct au_pin *p)
+{
+ int err;
-+ unsigned int udba;
++ struct super_block *sb;
++ struct inode *h_dir;
+
+ err = 0;
-+ a->src_h_parent = au_h_dptr(a->src_parent, a->btgt);
-+ a->src_hdir = au_hi(a->src_dir, a->btgt);
-+ a->dst_h_parent = au_h_dptr(a->dst_parent, a->btgt);
-+ a->dst_hdir = au_hi(a->dst_dir, a->btgt);
-+
-+ err = vfsub_mnt_want_write(au_br_mnt(a->br));
-+ if (unlikely(err))
-+ goto out;
-+ au_fset_ren(a->auren_flags, MNT_WRITE);
-+ if (au_ftest_ren(a->auren_flags, DIRREN)) {
-+ struct dentry *root;
-+ struct inode *dir;
-+
-+ /*
-+ * sbinfo is already locked, so this ii_read_lock is
-+ * unnecessary. but our debugging feature checks it.
-+ */
-+ root = a->src_inode->i_sb->s_root;
-+ if (root != a->src_parent && root != a->dst_parent) {
-+ dir = d_inode(root);
-+ ii_read_lock_parent3(dir);
-+ a->h_root = au_hi(dir, a->btgt);
-+ ii_read_unlock(dir);
-+ au_hn_inode_lock_nested(a->h_root, AuLsc_I_PARENT3);
++ 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;
+ }
-+ a->h_trap = vfsub_lock_rename(a->src_h_parent, a->src_hdir,
-+ a->dst_h_parent, a->dst_hdir);
-+ udba = au_opt_udba(a->src_dentry->d_sb);
-+ if (unlikely(a->src_hdir->hi_inode != d_inode(a->src_h_parent)
-+ || a->dst_hdir->hi_inode != d_inode(a->dst_h_parent)))
-+ err = au_busy_or_stale();
-+ if (!err && au_dbtop(a->src_dentry) == a->btgt)
-+ err = au_h_verify(a->src_h_dentry, udba,
-+ d_inode(a->src_h_parent), a->src_h_parent,
-+ a->br);
-+ if (!err && au_dbtop(a->dst_dentry) == a->btgt)
-+ err = au_h_verify(a->dst_h_dentry, udba,
-+ d_inode(a->dst_h_parent), a->dst_h_parent,
-+ a->br);
-+ if (!err)
-+ goto out; /* success */
-+
-+ err = au_busy_or_stale();
-+ au_ren_unlock(a);
+
-+out:
-+ return err;
-+}
++ 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);
+
-+static void au_ren_refresh_dir(struct au_ren_args *a)
-+{
-+ struct inode *dir;
++ 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;
+
-+ dir = a->dst_dir;
-+ inode_inc_iversion(dir);
-+ if (au_ftest_ren(a->auren_flags, ISDIR_SRC)) {
-+ /* is this updating defined in POSIX? */
-+ au_cpup_attr_timesizes(a->src_inode);
-+ au_cpup_attr_nlink(dir, /*force*/1);
++ /*
++ * 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;
+ }
-+ au_dir_ts(dir, a->btgt);
+
-+ if (a->exchange) {
-+ dir = a->src_dir;
-+ inode_inc_iversion(dir);
-+ if (au_ftest_ren(a->auren_flags, ISDIR_DST)) {
-+ /* is this updating defined in POSIX? */
-+ au_cpup_attr_timesizes(a->dst_inode);
-+ au_cpup_attr_nlink(dir, /*force*/1);
++ 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_dir_ts(dir, a->btgt);
+ }
+
-+ if (au_ftest_ren(a->auren_flags, ISSAMEDIR))
-+ return;
++ au_igrab(h_dir);
++ err = au_pin_hdir_lock(p);
++ if (!err)
++ goto out; /* success */
+
-+ dir = a->src_dir;
-+ inode_inc_iversion(dir);
-+ if (au_ftest_ren(a->auren_flags, ISDIR_SRC))
-+ au_cpup_attr_nlink(dir, /*force*/1);
-+ au_dir_ts(dir, a->btgt);
++ au_unpin(p);
++
++out_err:
++ pr_err("err %d\n", err);
++ err = au_busy_or_stale();
++out:
++ return err;
+}
+
-+static void au_ren_refresh(struct au_ren_args *a)
++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)
+{
-+ aufs_bindex_t bbot, bindex;
-+ struct dentry *d, *h_d;
-+ struct inode *i, *h_i;
-+ struct super_block *sb;
-+
-+ d = a->dst_dentry;
-+ d_drop(d);
-+ if (a->h_dst)
-+ /* already dget-ed by au_ren_or_cpup() */
-+ au_set_h_dptr(d, a->btgt, a->h_dst);
-+
-+ i = a->dst_inode;
-+ if (i) {
-+ if (!a->exchange) {
-+ if (!au_ftest_ren(a->auren_flags, ISDIR_DST))
-+ vfsub_drop_nlink(i);
-+ else {
-+ vfsub_dead_dir(i);
-+ au_cpup_attr_timesizes(i);
-+ }
-+ au_update_dbrange(d, /*do_put_zero*/1);
-+ } else
-+ au_cpup_attr_nlink(i, /*force*/1);
-+ } else {
-+ bbot = a->btgt;
-+ for (bindex = au_dbtop(d); bindex < bbot; bindex++)
-+ au_set_h_dptr(d, bindex, NULL);
-+ bbot = au_dbbot(d);
-+ for (bindex = a->btgt + 1; bindex <= bbot; bindex++)
-+ au_set_h_dptr(d, bindex, NULL);
-+ au_update_dbrange(d, /*do_put_zero*/0);
-+ }
-+
-+ if (a->exchange
-+ || au_ftest_ren(a->auren_flags, DIRREN)) {
-+ d_drop(a->src_dentry);
-+ if (au_ftest_ren(a->auren_flags, DIRREN))
-+ au_set_dbwh(a->src_dentry, -1);
-+ return;
-+ }
++ p->dentry = dentry;
++ p->udba = udba;
++ p->lsc_di = lsc_di;
++ p->lsc_hi = lsc_hi;
++ p->flags = flags;
++ p->bindex = bindex;
+
-+ d = a->src_dentry;
-+ au_set_dbwh(d, -1);
-+ bbot = au_dbbot(d);
-+ for (bindex = a->btgt + 1; bindex <= bbot; bindex++) {
-+ h_d = au_h_dptr(d, bindex);
-+ if (h_d)
-+ au_set_h_dptr(d, bindex, NULL);
-+ }
-+ au_set_dbbot(d, a->btgt);
++ p->parent = NULL;
++ p->hdir = NULL;
++ p->h_mnt = NULL;
+
-+ sb = d->d_sb;
-+ i = a->src_inode;
-+ if (au_opt_test(au_mntflags(sb), PLINK) && au_plink_test(i))
-+ return; /* success */
++ p->h_dentry = NULL;
++ p->h_parent = NULL;
++ p->br = NULL;
++ p->task = current;
++}
+
-+ bbot = au_ibbot(i);
-+ for (bindex = a->btgt + 1; bindex <= bbot; bindex++) {
-+ h_i = au_h_iptr(i, bindex);
-+ if (h_i) {
-+ au_xino_write(sb, bindex, h_i->i_ino, /*ino*/0);
-+ /* ignore this error */
-+ au_set_h_iptr(i, bindex, NULL, 0);
-+ }
-+ }
-+ au_set_ibbot(i, a->btgt);
++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);
+}
+
+/* ---------------------------------------------------------------------- */
+
-+/* mainly for link(2) and rename(2) */
-+int au_wbr(struct dentry *dentry, aufs_bindex_t btgt)
++/*
++ * ->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)
+{
-+ aufs_bindex_t bdiropq, bwh;
++ int err;
+ struct dentry *parent;
-+ struct au_branch *br;
-+
-+ parent = dentry->d_parent;
-+ IMustLock(d_inode(parent)); /* dir is locked */
+
-+ bdiropq = au_dbdiropq(parent);
-+ bwh = au_dbwh(dentry);
-+ br = au_sbr(dentry->d_sb, btgt);
-+ if (au_br_rdonly(br)
-+ || (0 <= bdiropq && bdiropq < btgt)
-+ || (0 <= bwh && bwh < btgt))
-+ btgt = -1;
++ 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);
++ }
+
-+ AuDbg("btgt %d\n", btgt);
-+ return btgt;
++ AuTraceErr(err);
++ return err;
+}
+
-+/* sets src_btop, dst_btop and btgt */
-+static int au_ren_wbr(struct au_ren_args *a)
++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 = AuWrDir_ADD_ENTRY
++ .force_btgt = -1,
++ .flags = 0
+ };
+
-+ a->src_btop = au_dbtop(a->src_dentry);
-+ a->dst_btop = au_dbtop(a->dst_dentry);
-+ if (au_ftest_ren(a->auren_flags, ISDIR_SRC)
-+ || au_ftest_ren(a->auren_flags, ISDIR_DST))
++ if (d_is_dir(dentry))
+ au_fset_wrdir(wr_dir_args.flags, ISDIR);
-+ wr_dir_args.force_btgt = a->src_btop;
-+ if (a->dst_inode && a->dst_btop < a->src_btop)
-+ wr_dir_args.force_btgt = a->dst_btop;
-+ wr_dir_args.force_btgt = au_wbr(a->dst_dentry, wr_dir_args.force_btgt);
-+ err = au_wr_dir(a->dst_dentry, a->src_dentry, &wr_dir_args);
++ /* 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 (a->exchange)
-+ au_update_dbtop(a->dst_dentry);
-+
-+ return err;
-+}
++ if (err != btop)
++ au_fset_icpup(a->flags, DID_CPUP);
+
-+static void au_ren_dt(struct au_ren_args *a)
-+{
-+ a->h_path.dentry = a->src_h_parent;
-+ au_dtime_store(a->src_dt + AuPARENT, a->src_parent, &a->h_path);
-+ if (!au_ftest_ren(a->auren_flags, ISSAMEDIR)) {
-+ a->h_path.dentry = a->dst_h_parent;
-+ au_dtime_store(a->dst_dt + AuPARENT, a->dst_parent, &a->h_path);
++ 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);
+ }
+
-+ au_fclr_ren(a->auren_flags, DT_DSTDIR);
-+ if (!au_ftest_ren(a->auren_flags, ISDIR_SRC)
-+ && !a->exchange)
-+ return;
++ err = au_pin(&a->pin, dentry, a->btgt, a->udba, a->pin_flags);
++ if (unlikely(err))
++ goto out_parent;
+
-+ a->h_path.dentry = a->src_h_dentry;
-+ au_dtime_store(a->src_dt + AuCHILD, a->src_dentry, &a->h_path);
-+ if (d_is_positive(a->dst_h_dentry)) {
-+ au_fset_ren(a->auren_flags, DT_DSTDIR);
-+ a->h_path.dentry = a->dst_h_dentry;
-+ au_dtime_store(a->dst_dt + AuCHILD, a->dst_dentry, &a->h_path);
++ 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);
+ }
-+}
+
-+static void au_ren_rev_dt(int err, struct au_ren_args *a)
-+{
-+ struct dentry *h_d;
-+ struct inode *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? */
++ }
++ }
+
-+ au_dtime_revert(a->src_dt + AuPARENT);
-+ if (!au_ftest_ren(a->auren_flags, ISSAMEDIR))
-+ au_dtime_revert(a->dst_dt + AuPARENT);
++ 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 (au_ftest_ren(a->auren_flags, ISDIR_SRC) && err != -EIO) {
-+ h_d = a->src_dt[AuCHILD].dt_h_path.dentry;
-+ h_inode = d_inode(h_d);
-+ inode_lock_nested(h_inode, AuLsc_I_CHILD);
-+ au_dtime_revert(a->src_dt + AuCHILD);
-+ inode_unlock(h_inode);
++ 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 */
+
-+ if (au_ftest_ren(a->auren_flags, DT_DSTDIR)) {
-+ h_d = a->dst_dt[AuCHILD].dt_h_path.dentry;
-+ h_inode = d_inode(h_d);
-+ inode_lock_nested(h_inode, AuLsc_I_CHILD);
-+ au_dtime_revert(a->dst_dt + AuCHILD);
-+ inode_unlock(h_inode);
-+ }
++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;
+}
+
-+/* ---------------------------------------------------------------------- */
-+
-+int aufs_rename(struct mnt_idmap *idmap,
-+ struct inode *_src_dir, struct dentry *_src_dentry,
-+ struct inode *_dst_dir, struct dentry *_dst_dentry,
-+ unsigned int _flags)
++static int aufs_setattr(struct mnt_idmap *idmap, struct dentry *dentry,
++ struct iattr *ia)
+{
-+ int err, lock_flags;
-+ void *rev;
-+ /* reduce stack space */
-+ struct au_ren_args *a;
-+ struct au_pin pin;
++ int err;
++ struct inode *inode, *delegated;
++ struct super_block *sb;
++ struct file *file;
++ struct au_icpup_args *a;
++ struct mnt_idmap *h_idmap;
+
-+ AuDbg("%pd, %pd, 0x%x\n", _src_dentry, _dst_dentry, _flags);
-+ IMustLock(_src_dir);
-+ IMustLock(_dst_dir);
++ inode = d_inode(dentry);
++ IMustLock(inode);
+
-+ err = -EINVAL;
-+ if (unlikely(_flags & RENAME_WHITEOUT))
++ err = setattr_prepare(idmap, dentry, ia);
++ if (unlikely(err))
+ goto out;
+
+ err = -ENOMEM;
-+ BUILD_BUG_ON(sizeof(*a) > PAGE_SIZE);
+ a = kzalloc(sizeof(*a), GFP_NOFS);
+ if (unlikely(!a))
+ goto out;
+
-+ a->flags = _flags;
-+ BUILD_BUG_ON(sizeof(a->exchange) == sizeof(u8)
-+ && RENAME_EXCHANGE > U8_MAX);
-+ a->exchange = _flags & RENAME_EXCHANGE;
-+ a->src_dir = _src_dir;
-+ a->src_dentry = _src_dentry;
-+ a->src_inode = NULL;
-+ if (d_really_is_positive(a->src_dentry))
-+ a->src_inode = d_inode(a->src_dentry);
-+ a->src_parent = a->src_dentry->d_parent; /* dir inode is locked */
-+ a->dst_dir = _dst_dir;
-+ a->dst_dentry = _dst_dentry;
-+ a->dst_inode = NULL;
-+ if (d_really_is_positive(a->dst_dentry))
-+ a->dst_inode = d_inode(a->dst_dentry);
-+ a->dst_parent = a->dst_dentry->d_parent; /* dir inode is locked */
-+ if (a->dst_inode) {
-+ /*
-+ * if EXCHANGE && src is non-dir && dst is dir,
-+ * dst is not locked.
-+ */
-+ /* IMustLock(a->dst_inode); */
-+ au_igrab(a->dst_inode);
-+ }
-+
-+ err = -ENOTDIR;
-+ lock_flags = AuLock_FLUSH | AuLock_NOPLM | AuLock_GEN;
-+ if (d_is_dir(a->src_dentry)) {
-+ au_fset_ren(a->auren_flags, ISDIR_SRC);
-+ if (unlikely(!a->exchange
-+ && d_really_is_positive(a->dst_dentry)
-+ && !d_is_dir(a->dst_dentry)))
-+ goto out_free;
-+ lock_flags |= AuLock_DIRS;
-+ }
-+ if (a->dst_inode && d_is_dir(a->dst_dentry)) {
-+ au_fset_ren(a->auren_flags, ISDIR_DST);
-+ if (unlikely(!a->exchange
-+ && d_really_is_positive(a->src_dentry)
-+ && !d_is_dir(a->src_dentry)))
-+ goto out_free;
-+ lock_flags |= AuLock_DIRS;
-+ }
-+ err = aufs_read_and_write_lock2(a->dst_dentry, a->src_dentry,
-+ lock_flags);
-+ if (unlikely(err))
-+ goto out_free;
-+
-+ err = au_d_hashed_positive(a->src_dentry);
-+ if (unlikely(err))
-+ goto out_unlock;
-+ err = -ENOENT;
-+ if (a->dst_inode) {
-+ /*
-+ * If it is a dir, VFS unhash it before this
-+ * function. It means we cannot rely upon d_unhashed().
-+ */
-+ if (unlikely(!a->dst_inode->i_nlink))
-+ goto out_unlock;
-+ if (!au_ftest_ren(a->auren_flags, ISDIR_DST)) {
-+ err = au_d_hashed_positive(a->dst_dentry);
-+ if (unlikely(err && !a->exchange))
-+ goto out_unlock;
-+ } else if (unlikely(IS_DEADDIR(a->dst_inode)))
-+ goto out_unlock;
-+ } else if (unlikely(d_unhashed(a->dst_dentry)))
-+ goto out_unlock;
-+
-+ /*
-+ * is it possible?
-+ * yes, it happened (in linux-3.3-rcN) but I don't know why.
-+ * there may exist a problem somewhere else.
-+ */
-+ err = -EINVAL;
-+ if (unlikely(d_inode(a->dst_parent) == d_inode(a->src_dentry)))
-+ goto out_unlock;
-+
-+ au_fset_ren(a->auren_flags, ISSAMEDIR); /* temporary */
-+ di_write_lock_parent(a->dst_parent);
-+
-+ /* which branch we process */
-+ err = au_ren_wbr(a);
-+ if (unlikely(err < 0))
-+ goto out_parent;
-+ a->br = au_sbr(a->dst_dentry->d_sb, a->btgt);
-+ a->h_path.mnt = au_br_mnt(a->br);
++ if (ia->ia_valid & (ATTR_KILL_SUID | ATTR_KILL_SGID))
++ ia->ia_valid &= ~ATTR_MODE;
+
-+ /* are they available to be renamed */
-+ err = au_ren_may_dir(a);
++ file = NULL;
++ sb = dentry->d_sb;
++ err = si_read_lock(sb, AuLock_FLUSH | AuLock_NOPLM);
+ if (unlikely(err))
-+ goto out_children;
++ goto out_kfree;
+
-+ /* prepare the writable parent dir on the same branch */
-+ if (a->dst_btop == a->btgt) {
-+ au_fset_ren(a->auren_flags, WHDST);
-+ } else {
-+ err = au_cpup_dirs(a->dst_dentry, a->btgt);
++ 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_children;
-+ }
-+
-+ err = 0;
-+ if (!a->exchange) {
-+ if (a->src_dir != a->dst_dir) {
-+ /*
-+ * this temporary unlock is safe,
-+ * because both dir->i_mutex are locked.
-+ */
-+ di_write_unlock(a->dst_parent);
-+ di_write_lock_parent(a->src_parent);
-+ err = au_wr_dir_need_wh(a->src_dentry,
-+ au_ftest_ren(a->auren_flags,
-+ ISDIR_SRC),
-+ &a->btgt);
-+ di_write_unlock(a->src_parent);
-+ di_write_lock2_parent(a->src_parent, a->dst_parent,
-+ /*isdir*/1);
-+ au_fclr_ren(a->auren_flags, ISSAMEDIR);
-+ } else
-+ err = au_wr_dir_need_wh(a->src_dentry,
-+ au_ftest_ren(a->auren_flags,
-+ ISDIR_SRC),
-+ &a->btgt);
-+ }
-+ if (unlikely(err < 0))
-+ goto out_children;
-+ if (err)
-+ au_fset_ren(a->auren_flags, WHSRC);
-+
-+ /* cpup src */
-+ if (a->src_btop != a->btgt) {
-+ err = au_pin(&pin, a->src_dentry, a->btgt,
-+ au_opt_udba(a->src_dentry->d_sb),
-+ AuPin_DI_LOCKED | AuPin_MNT_WRITE);
-+ if (!err) {
-+ struct au_cp_generic cpg = {
-+ .dentry = a->src_dentry,
-+ .bdst = a->btgt,
-+ .bsrc = a->src_btop,
-+ .len = -1,
-+ .pin = &pin,
-+ .flags = AuCpup_DTIME | AuCpup_HOPEN
-+ };
-+ AuDebugOn(au_dbtop(a->src_dentry) != a->src_btop);
-+ err = au_sio_cpup_simple(&cpg);
-+ au_unpin(&pin);
++ 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;
+ }
-+ if (unlikely(err))
-+ goto out_children;
-+ a->src_btop = a->btgt;
-+ a->src_h_dentry = au_h_dptr(a->src_dentry, a->btgt);
-+ if (!a->exchange)
-+ au_fset_ren(a->auren_flags, WHSRC);
+ }
+
-+ /* cpup dst */
-+ if (a->exchange && a->dst_inode
-+ && a->dst_btop != a->btgt) {
-+ err = au_pin(&pin, a->dst_dentry, a->btgt,
-+ au_opt_udba(a->dst_dentry->d_sb),
-+ AuPin_DI_LOCKED | AuPin_MNT_WRITE);
-+ if (!err) {
-+ struct au_cp_generic cpg = {
-+ .dentry = a->dst_dentry,
-+ .bdst = a->btgt,
-+ .bsrc = a->dst_btop,
-+ .len = -1,
-+ .pin = &pin,
-+ .flags = AuCpup_DTIME | AuCpup_HOPEN
-+ };
-+ err = au_sio_cpup_simple(&cpg);
-+ au_unpin(&pin);
-+ }
-+ if (unlikely(err))
-+ goto out_children;
-+ a->dst_btop = a->btgt;
-+ a->dst_h_dentry = au_h_dptr(a->dst_dentry, a->btgt);
++ 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;
+ }
+
-+ /* lock them all */
-+ err = au_ren_lock(a);
-+ if (unlikely(err))
-+ /* leave the copied-up one */
-+ goto out_children;
-+
-+ if (!a->exchange) {
-+ if (!au_opt_test(au_mntflags(a->dst_dir->i_sb), UDBA_NONE))
-+ err = au_may_ren(a);
-+ else if (unlikely(a->dst_dentry->d_name.len > AUFS_MAX_NAMELEN))
-+ err = -ENAMETOOLONG;
++ 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_hdir;
-+ }
-+
-+ /* store timestamps to be revertible */
-+ au_ren_dt(a);
-+
-+ /* store dirren info */
-+ if (au_ftest_ren(a->auren_flags, DIRREN)) {
-+ err = au_dr_rename(a->src_dentry, a->btgt,
-+ &a->dst_dentry->d_name, &rev);
-+ AuTraceErr(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_dt;
++ goto out_unlock;
+ }
+
-+ /* here we go */
-+ err = do_rename(a);
-+ if (unlikely(err))
-+ goto out_dirren;
-+
-+ if (au_ftest_ren(a->auren_flags, DIRREN))
-+ au_dr_rename_fin(a->src_dentry, a->btgt, rev);
-+
-+ /* update dir attributes */
-+ au_ren_refresh_dir(a);
-+
-+ /* dput/iput all lower dentries */
-+ au_ren_refresh(a);
++ if (ia->ia_valid & ATTR_SIZE) {
++ struct file *f;
+
-+ goto out_hdir; /* success */
++ if (ia->ia_size < i_size_read(inode))
++ /* unmap only */
++ truncate_setsize(inode, ia->ia_size);
+
-+out_dirren:
-+ if (au_ftest_ren(a->auren_flags, DIRREN))
-+ au_dr_rename_rev(a->src_dentry, a->btgt, rev);
-+out_dt:
-+ au_ren_rev_dt(err, a);
-+out_hdir:
-+ au_ren_unlock(a);
-+out_children:
-+ au_nhash_wh_free(&a->whlist);
-+ if (err && a->dst_inode && a->dst_btop != a->btgt) {
-+ AuDbg("btop %d, btgt %d\n", a->dst_btop, a->btgt);
-+ au_set_h_dptr(a->dst_dentry, a->btgt, NULL);
-+ au_set_dbtop(a->dst_dentry, a->dst_btop);
-+ }
-+out_parent:
-+ if (!err) {
-+ if (d_unhashed(a->src_dentry))
-+ au_fset_ren(a->auren_flags, DROPPED_SRC);
-+ if (d_unhashed(a->dst_dentry))
-+ au_fset_ren(a->auren_flags, DROPPED_DST);
-+ if (!a->exchange)
-+ d_move(a->src_dentry, a->dst_dentry);
-+ else {
-+ d_exchange(a->src_dentry, a->dst_dentry);
-+ if (au_ftest_ren(a->auren_flags, DROPPED_DST))
-+ d_drop(a->dst_dentry);
-+ }
-+ if (au_ftest_ren(a->auren_flags, DROPPED_SRC))
-+ d_drop(a->src_dentry);
++ 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 {
-+ au_update_dbtop(a->dst_dentry);
-+ if (!a->dst_inode)
-+ d_drop(a->dst_dentry);
++ delegated = NULL;
++ while (1) {
++ err = vfsub_notify_change(&a->h_path, ia, &delegated);
++ if (delegated) {
++ err = break_deleg_wait(&delegated);
++ if (!err)
++ continue;
++ }
++ break;
++ }
+ }
-+ if (au_ftest_ren(a->auren_flags, ISSAMEDIR))
-+ di_write_unlock(a->dst_parent);
-+ else
-+ di_write_unlock2(a->src_parent, a->dst_parent);
++ /*
++ * 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)) {
++ h_idmap = mnt_idmap(a->h_path.mnt);
++ err = vfsub_acl_chmod(h_idmap, a->h_path.dentry, ia->ia_mode);
++ }
++ if (!err)
++ au_cpup_attr_changeable(inode);
++
+out_unlock:
-+ aufs_read_and_write_unlock2(a->dst_dentry, a->src_dentry);
-+out_free:
-+ iput(a->dst_inode);
-+ if (a->thargs)
-+ au_whtmp_rmdir_free(a->thargs);
++ 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;
+}
-diff --git a/fs/aufs/iinfo.c b/fs/aufs/iinfo.c
-new file mode 100644
-index 00000000000000..0d3a2487643bdc
---- /dev/null
-+++ b/fs/aufs/iinfo.c
-@@ -0,0 +1,286 @@
-+// SPDX-License-Identifier: GPL-2.0
-+/*
-+ * Copyright (C) 2005-2022 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/>.
-+ */
+
-+/*
-+ * inode private data
-+ */
++#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;
+
-+#include "aufs.h"
++ 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;
+
-+struct inode *au_h_iptr(struct inode *inode, aufs_bindex_t bindex)
++ 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;
-+ struct au_hinode *hinode;
++ struct mnt_idmap *h_idmap;
+
-+ IiMustAnyLock(inode);
++ IMustLock(inode);
+
-+ hinode = au_hinode(au_ii(inode), bindex);
-+ h_inode = hinode->hi_inode;
-+ AuDebugOn(h_inode && atomic_read(&h_inode->i_count) <= 0);
-+ return h_inode;
-+}
++ err = -ENOMEM;
++ a = kzalloc(sizeof(*a), GFP_NOFS);
++ if (unlikely(!a))
++ goto out;
+
-+/* todo: hard/soft set? */
-+void au_hiput(struct au_hinode *hinode)
-+{
-+ au_hn_free(hinode);
-+ dput(hinode->hi_whdentry);
-+ iput(hinode->hi_inode);
++ 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;
++ h_idmap = mnt_idmap(h_path.mnt);
++
++ inode_unlock(a->h_inode);
++ switch (arg->type) {
++ case AU_XATTR_SET:
++ AuDebugOn(d_is_negative(h_path.dentry));
++ err = vfsub_setxattr(h_idmap, 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_idmap, h_path.dentry,
++ 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
+
-+unsigned int au_hi_flags(struct inode *inode, int isdir)
++static void au_refresh_iattr(struct inode *inode, struct kstat *st,
++ unsigned int nlink)
+{
-+ unsigned int flags;
-+ const unsigned int mnt_flags = au_mntflags(inode->i_sb);
++ unsigned int n;
+
-+ flags = 0;
-+ if (au_opt_test(mnt_flags, XINO))
-+ au_fset_hi(flags, XINO);
-+ if (isdir && au_opt_test(mnt_flags, UDBA_HNOTIFY))
-+ au_fset_hi(flags, HNOTIFY);
-+ return flags;
++ inode->i_mode = st->mode;
++ /* don't i_[ug]id_write() here */
++ inode->i_uid = st->uid;
++ inode->i_gid = st->gid;
++ inode_set_atime_to_ts(inode, st->atime);
++ inode_set_mtime_to_ts(inode, st->mtime);
++ inode_set_ctime_to_ts(inode, 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);
+}
+
-+void au_set_h_iptr(struct inode *inode, aufs_bindex_t bindex,
-+ struct inode *h_inode, unsigned int flags)
++/*
++ * 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, struct inode *inode, int force,
++ struct path *h_path, int locked)
+{
-+ struct au_hinode *hinode;
-+ struct inode *hi;
-+ struct au_iinfo *iinfo = au_ii(inode);
++ int err;
++ unsigned int mnt_flags, sigen;
++ unsigned char udba_none;
++ aufs_bindex_t bindex;
++ struct super_block *sb, *h_sb;
+
-+ IiMustWriteLock(inode);
++ h_path->mnt = NULL;
++ h_path->dentry = NULL;
+
-+ hinode = au_hinode(iinfo, bindex);
-+ hi = hinode->hi_inode;
-+ AuDebugOn(h_inode && atomic_read(&h_inode->i_count) <= 0);
++ err = 0;
++ sb = dentry->d_sb;
++ mnt_flags = au_mntflags(sb);
++ udba_none = !!au_opt_test(mnt_flags, UDBA_NONE);
+
-+ if (hi)
-+ au_hiput(hinode);
-+ hinode->hi_inode = h_inode;
-+ if (h_inode) {
-+ int err;
-+ struct super_block *sb = inode->i_sb;
-+ struct au_branch *br;
++ if (unlikely(locked))
++ goto body; /* skip locking dinfo */
+
-+ AuDebugOn(inode->i_mode
-+ && (h_inode->i_mode & S_IFMT)
-+ != (inode->i_mode & S_IFMT));
-+ if (bindex == iinfo->ii_btop)
-+ au_cpup_igen(inode, h_inode);
-+ br = au_sbr(sb, bindex);
-+ hinode->hi_id = br->br_id;
-+ if (au_ftest_hi(flags, XINO)) {
-+ err = au_xino_write(sb, bindex, h_inode->i_ino,
-+ inode->i_ino);
-+ if (unlikely(err))
-+ AuIOErr1("failed au_xino_write() %d\n", err);
++ /* 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);
+
-+ if (au_ftest_hi(flags, HNOTIFY)
-+ && au_br_hnotifyable(br->br_perm)) {
-+ err = au_hn_alloc(hinode, inode);
-+ if (unlikely(err))
-+ AuIOErr1("au_hn_alloc() %d\n", err);
-+ }
++body:
++ if (!inode) {
++ inode = d_inode(dentry);
++ if (unlikely(!inode))
++ goto out;
++ }
++ 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;
+}
+
-+void au_set_hi_wh(struct inode *inode, aufs_bindex_t bindex,
-+ struct dentry *h_wh)
++static int aufs_getattr(struct mnt_idmap *idmap, const struct path *path,
++ struct kstat *st, u32 request, unsigned int query)
+{
-+ struct au_hinode *hinode;
++ int err;
++ unsigned char positive;
++ struct path h_path;
++ struct dentry *dentry;
++ struct inode *inode;
++ struct super_block *sb;
+
-+ IiMustWriteLock(inode);
++ 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, /*inode*/NULL, /*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 */
+
-+ hinode = au_hinode(au_ii(inode), bindex);
-+ AuDebugOn(hinode->hi_whdentry);
-+ hinode->hi_whdentry = h_wh;
++ positive = d_is_positive(h_path.dentry);
++ if (positive) {
++ /* no vfsub version */
++ if (query & AT_GETATTR_NOSEC)
++ err = vfs_getattr_nosec(&h_path, st, request, query);
++ else
++ 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(idmap, request, inode, st);
++out_di:
++ di_read_unlock(dentry, AuLock_IR);
++out_si:
++ si_read_unlock(sb);
++out:
++ AuTraceErr(err);
++ return err;
+}
+
-+void au_update_iigen(struct inode *inode, int half)
++/* ---------------------------------------------------------------------- */
++
++static const char *aufs_get_link(struct dentry *dentry, struct inode *inode,
++ struct delayed_call *done)
+{
-+ struct au_iinfo *iinfo;
-+ struct au_iigen *iigen;
-+ unsigned int sigen;
++ const char *ret;
++ struct dentry *h_dentry;
++ struct inode *h_inode;
++ int err;
++ aufs_bindex_t bindex;
+
-+ sigen = au_sigen(inode->i_sb);
-+ iinfo = au_ii(inode);
-+ iigen = &iinfo->ii_generation;
-+ spin_lock(&iigen->ig_spin);
-+ iigen->ig_generation = sigen;
-+ if (half)
-+ au_ig_fset(iigen->ig_flags, HALF_REFRESHED);
-+ else
-+ au_ig_fclr(iigen->ig_flags, HALF_REFRESHED);
-+ spin_unlock(&iigen->ig_spin);
-+}
++ ret = NULL; /* suppress a warning */
++ err = -ECHILD;
++ if (!dentry)
++ goto out;
+
-+/* it may be called at remount time, too */
-+void au_update_ibrange(struct inode *inode, int do_put_zero)
-+{
-+ struct au_iinfo *iinfo;
-+ aufs_bindex_t bindex, bbot;
++ err = aufs_read_lock(dentry, AuLock_IR | AuLock_GEN);
++ if (unlikely(err))
++ goto out;
+
-+ AuDebugOn(au_is_bad_inode(inode));
-+ IiMustWriteLock(inode);
++ err = au_d_hashed_positive(dentry);
++ if (unlikely(err))
++ goto out_unlock;
+
-+ iinfo = au_ii(inode);
-+ if (do_put_zero && iinfo->ii_btop >= 0) {
-+ for (bindex = iinfo->ii_btop; bindex <= iinfo->ii_bbot;
-+ bindex++) {
-+ struct inode *h_i;
++ 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;
+
-+ h_i = au_hinode(iinfo, bindex)->hi_inode;
-+ if (h_i
-+ && !h_i->i_nlink
-+ && !(h_i->i_state & I_LINKABLE))
-+ au_set_h_iptr(inode, bindex, NULL, 0);
++ 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;
+
-+ iinfo->ii_btop = -1;
-+ iinfo->ii_bbot = -1;
-+ bbot = au_sbbot(inode->i_sb);
-+ for (bindex = 0; bindex <= bbot; bindex++)
-+ if (au_hinode(iinfo, bindex)->hi_inode) {
-+ iinfo->ii_btop = bindex;
-+ break;
-+ }
-+ if (iinfo->ii_btop >= 0)
-+ for (bindex = bbot; bindex >= iinfo->ii_btop; bindex--)
-+ if (au_hinode(iinfo, bindex)->hi_inode) {
-+ iinfo->ii_bbot = bindex;
-+ break;
-+ }
-+ AuDebugOn(iinfo->ii_btop > iinfo->ii_bbot);
++ 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;
+}
+
+/* ---------------------------------------------------------------------- */
+
-+void au_icntnr_init_once(void *_c)
-+{
-+ struct au_icntnr *c = _c;
-+ struct au_iinfo *iinfo = &c->iinfo;
-+
-+ spin_lock_init(&iinfo->ii_generation.ig_spin);
-+ au_rw_init(&iinfo->ii_rwsem);
-+ inode_init_once(&c->vfs_inode);
-+}
-+
-+void au_hinode_init(struct au_hinode *hinode)
++static int au_is_special(struct inode *inode)
+{
-+ hinode->hi_inode = NULL;
-+ hinode->hi_id = -1;
-+ au_hn_init(hinode);
-+ hinode->hi_whdentry = NULL;
++ return (inode->i_mode & (S_IFBLK | S_IFCHR | S_IFIFO | S_IFSOCK));
+}
+
-+int au_iinfo_init(struct inode *inode)
++static int aufs_update_time(struct inode *inode, int flags)
+{
-+ struct au_iinfo *iinfo;
++ int err;
++ aufs_bindex_t bindex;
+ struct super_block *sb;
-+ struct au_hinode *hi;
-+ int nbr, i;
++ struct inode *h_inode;
++ struct vfsmount *h_mnt;
+
+ sb = inode->i_sb;
-+ iinfo = &(container_of(inode, struct au_icntnr, vfs_inode)->iinfo);
-+ nbr = au_sbbot(sb) + 1;
-+ if (unlikely(nbr <= 0))
-+ nbr = 1;
-+ hi = kmalloc_array(nbr, sizeof(*iinfo->ii_hinode), GFP_NOFS);
-+ if (hi) {
-+ au_lcnt_inc(&au_sbi(sb)->si_ninodes);
++ WARN_ONCE((flags & S_ATIME) && !IS_NOATIME(inode),
++ "unexpected s_flags 0x%lx", sb->s_flags);
+
-+ iinfo->ii_hinode = hi;
-+ for (i = 0; i < nbr; i++, hi++)
-+ au_hinode_init(hi);
++ /* mmap_sem might be acquired already, cf. aufs_mmap() */
++ lockdep_off();
++ si_read_lock(sb, AuLock_FLUSH);
++ ii_write_lock_child(inode);
+
-+ iinfo->ii_generation.ig_generation = au_sigen(sb);
-+ iinfo->ii_btop = -1;
-+ iinfo->ii_bbot = -1;
-+ iinfo->ii_vdir = NULL;
-+ return 0;
++ 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, 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);
+ }
-+ return -ENOMEM;
++
++ 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;
+}
+
-+int au_hinode_realloc(struct au_iinfo *iinfo, int nbr, int may_shrink)
-+{
-+ int err, i;
-+ struct au_hinode *hip;
++/* ---------------------------------------------------------------------- */
++
++/* 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_inode_acl = aufs_get_inode_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
+
-+ AuRwMustWriteLock(&iinfo->ii_rwsem);
++ .get_link = aufs_get_link
+
-+ err = -ENOMEM;
-+ hip = au_krealloc(iinfo->ii_hinode, sizeof(*hip) * nbr, GFP_NOFS,
-+ may_shrink);
-+ if (hip) {
-+ iinfo->ii_hinode = hip;
-+ i = iinfo->ii_bbot + 1;
-+ hip += i;
-+ for (; i < nbr; i++, hip++)
-+ au_hinode_init(hip);
-+ err = 0;
-+ }
++ /* .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,
+
-+ return err;
-+}
++ .permission = aufs_permission,
++#ifdef CONFIG_FS_POSIX_ACL
++ .get_inode_acl = aufs_get_inode_acl,
++ .get_acl = aufs_get_acl,
++ .set_acl = aufs_set_acl,
++#endif
+
-+void au_iinfo_fin(struct inode *inode)
-+{
-+ struct au_iinfo *iinfo;
-+ struct au_hinode *hi;
-+ struct super_block *sb;
-+ aufs_bindex_t bindex, bbot;
-+ const unsigned char unlinked = !inode->i_nlink;
++ .setattr = aufs_setattr,
++ .getattr = aufs_getattr,
+
-+ AuDebugOn(au_is_bad_inode(inode));
++#ifdef CONFIG_AUFS_XATTR
++ .listxattr = aufs_listxattr,
++#endif
+
-+ sb = inode->i_sb;
-+ au_lcnt_dec(&au_sbi(sb)->si_ninodes);
-+ if (si_pid_test(sb))
-+ au_xino_delete_inode(inode, unlinked);
-+ else {
-+ /*
-+ * it is safe to hide the dependency between sbinfo and
-+ * sb->s_umount.
-+ */
-+ lockdep_off();
-+ si_noflush_read_lock(sb);
-+ au_xino_delete_inode(inode, unlinked);
-+ si_read_unlock(sb);
-+ lockdep_on();
-+ }
++ .update_time = aufs_update_time,
++ .atomic_open = aufs_atomic_open,
++ .tmpfile = aufs_tmpfile
++ },
++ [AuIop_OTHER] = {
++ .permission = aufs_permission,
++#ifdef CONFIG_FS_POSIX_ACL
++ .get_inode_acl = aufs_get_inode_acl,
++ .get_acl = aufs_get_acl,
++ .set_acl = aufs_set_acl,
++#endif
+
-+ iinfo = au_ii(inode);
-+ if (iinfo->ii_vdir)
-+ au_vdir_free(iinfo->ii_vdir);
++ .setattr = aufs_setattr,
++ .getattr = aufs_getattr,
+
-+ bindex = iinfo->ii_btop;
-+ if (bindex >= 0) {
-+ hi = au_hinode(iinfo, bindex);
-+ bbot = iinfo->ii_bbot;
-+ while (bindex++ <= bbot) {
-+ if (hi->hi_inode)
-+ au_hiput(hi);
-+ hi++;
-+ }
++#ifdef CONFIG_AUFS_XATTR
++ .listxattr = aufs_listxattr,
++#endif
++
++ .update_time = aufs_update_time
+ }
-+ au_kfree_rcu(iinfo->ii_hinode);
-+ AuRwDestroy(&iinfo->ii_rwsem);
-+}
-diff --git a/fs/aufs/inode.c b/fs/aufs/inode.c
-new file mode 100644
-index 00000000000000..7dbf6a6f2feec3
---- /dev/null
-+++ b/fs/aufs/inode.c
-@@ -0,0 +1,531 @@
++};
+diff -urN /usr/share/empty/fs/aufs/i_op_del.c linux/fs/aufs/i_op_del.c
+--- /usr/share/empty/fs/aufs/i_op_del.c 1970-01-01 01:00:00.000000000 +0100
++++ linux/fs/aufs/i_op_del.c 2023-10-31 09:31:04.199880750 +0100
+@@ -0,0 +1,523 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2005-2022 Junjiro R. Okajima
+ */
+
+/*
-+ * inode functions
++ * inode operations (del entry)
+ */
+
+#include <linux/iversion.h>
+#include "aufs.h"
+
-+struct inode *au_igrab(struct inode *inode)
-+{
-+ if (inode) {
-+ AuDebugOn(!atomic_read(&inode->i_count));
-+ ihold(inode);
-+ }
-+ return inode;
-+}
-+
-+static void au_refresh_hinode_attr(struct inode *inode, int do_version)
-+{
-+ au_cpup_attr_all(inode, /*force*/0);
-+ au_update_iigen(inode, /*half*/1);
-+ if (do_version)
-+ inode_inc_iversion(inode);
-+}
-+
-+static int au_ii_refresh(struct inode *inode, int *update)
++/*
++ * decide if a new whiteout for @dentry is necessary or not.
++ * when it is necessary, prepare the parent dir for the upper branch whose
++ * branch index is @bcpup for creation. the actual creation of the whiteout will
++ * be done by caller.
++ * return value:
++ * 0: wh is unnecessary
++ * plus: wh is necessary
++ * minus: error
++ */
++int au_wr_dir_need_wh(struct dentry *dentry, int isdir, aufs_bindex_t *bcpup)
+{
-+ int err, e, nbr;
-+ umode_t type;
-+ aufs_bindex_t bindex, new_bindex;
++ int need_wh, err;
++ aufs_bindex_t btop;
+ struct super_block *sb;
-+ struct au_iinfo *iinfo;
-+ struct au_hinode *p, *q, tmp;
-+
-+ AuDebugOn(au_is_bad_inode(inode));
-+ IiMustWriteLock(inode);
-+
-+ *update = 0;
-+ sb = inode->i_sb;
-+ nbr = au_sbbot(sb) + 1;
-+ type = inode->i_mode & S_IFMT;
-+ iinfo = au_ii(inode);
-+ err = au_hinode_realloc(iinfo, nbr, /*may_shrink*/0);
-+ if (unlikely(err))
-+ goto out;
-+
-+ AuDebugOn(iinfo->ii_btop < 0);
-+ p = au_hinode(iinfo, iinfo->ii_btop);
-+ for (bindex = iinfo->ii_btop; bindex <= iinfo->ii_bbot;
-+ bindex++, p++) {
-+ if (!p->hi_inode)
-+ continue;
-+
-+ AuDebugOn(type != (p->hi_inode->i_mode & S_IFMT));
-+ new_bindex = au_br_index(sb, p->hi_id);
-+ if (new_bindex == bindex)
-+ continue;
+
-+ if (new_bindex < 0) {
-+ *update = 1;
-+ au_hiput(p);
-+ p->hi_inode = NULL;
-+ continue;
++ sb = dentry->d_sb;
++ btop = au_dbtop(dentry);
++ if (*bcpup < 0) {
++ *bcpup = btop;
++ if (au_test_ro(sb, btop, d_inode(dentry))) {
++ err = AuWbrCopyup(au_sbi(sb), dentry);
++ *bcpup = err;
++ if (unlikely(err < 0))
++ goto out;
+ }
++ } else
++ AuDebugOn(btop < *bcpup
++ || au_test_ro(sb, *bcpup, d_inode(dentry)));
++ AuDbg("bcpup %d, btop %d\n", *bcpup, btop);
+
-+ if (new_bindex < iinfo->ii_btop)
-+ iinfo->ii_btop = new_bindex;
-+ if (iinfo->ii_bbot < new_bindex)
-+ iinfo->ii_bbot = new_bindex;
-+ /* swap two lower inode, and loop again */
-+ q = au_hinode(iinfo, new_bindex);
-+ tmp = *q;
-+ *q = *p;
-+ *p = tmp;
-+ if (tmp.hi_inode) {
-+ bindex--;
-+ p--;
++ if (*bcpup != btop) {
++ err = au_cpup_dirs(dentry, *bcpup);
++ if (unlikely(err))
++ goto out;
++ need_wh = 1;
++ } else {
++ struct au_dinfo *dinfo, *tmp;
++
++ need_wh = -ENOMEM;
++ dinfo = au_di(dentry);
++ tmp = au_di_alloc(sb, AuLsc_DI_TMP);
++ if (tmp) {
++ au_di_cp(tmp, dinfo);
++ au_di_swap(tmp, dinfo);
++ /* returns the number of positive dentries */
++ need_wh = au_lkup_dentry(dentry, btop + 1,
++ /* AuLkup_IGNORE_PERM */ 0);
++ au_di_swap(tmp, dinfo);
++ au_rw_write_unlock(&tmp->di_rwsem);
++ au_di_free(tmp);
+ }
+ }
-+ au_update_ibrange(inode, /*do_put_zero*/0);
-+ au_hinode_realloc(iinfo, nbr, /*may_shrink*/1); /* harmless if err */
-+ e = au_dy_irefresh(inode);
-+ if (unlikely(e && !err))
-+ err = e;
++ AuDbg("need_wh %d\n", need_wh);
++ err = need_wh;
+
+out:
-+ AuTraceErr(err);
+ return err;
+}
+
-+void au_refresh_iop(struct inode *inode, int force_getattr)
++/*
++ * simple tests for the del-entry operations.
++ * following the checks in vfs, plus the parent-child relationship.
++ */
++int au_may_del(struct dentry *dentry, aufs_bindex_t bindex,
++ struct dentry *h_parent, int isdir)
+{
-+ int type;
-+ struct au_sbinfo *sbi = au_sbi(inode->i_sb);
-+ const struct inode_operations *iop
-+ = force_getattr ? aufs_iop : sbi->si_iop_array;
++ int err;
++ umode_t h_mode;
++ struct dentry *h_dentry, *h_latest;
++ struct inode *h_inode;
++ struct path h_ppath;
++ struct super_block *sb;
++ struct au_branch *br;
++ struct mnt_idmap *h_idmap;
+
-+ if (inode->i_op == iop)
-+ return;
++ h_dentry = au_h_dptr(dentry, bindex);
++ if (d_really_is_positive(dentry)) {
++ err = -ENOENT;
++ if (unlikely(d_is_negative(h_dentry)))
++ goto out;
++ h_inode = d_inode(h_dentry);
++ if (unlikely(!h_inode->i_nlink))
++ goto out;
+
-+ switch (inode->i_mode & S_IFMT) {
-+ case S_IFDIR:
-+ type = AuIop_DIR;
-+ break;
-+ case S_IFLNK:
-+ type = AuIop_SYMLINK;
-+ break;
-+ default:
-+ type = AuIop_OTHER;
-+ break;
++ 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;
++ }
++ } else {
++ /* rename(2) case */
++ err = -EIO;
++ if (unlikely(d_is_positive(h_dentry)))
++ goto out;
+ }
+
-+ inode->i_op = iop + type;
-+ /* unnecessary smp_wmb() */
-+}
++ err = -ENOENT;
++ /* expected parent dir is locked */
++ if (unlikely(h_parent != h_dentry->d_parent))
++ goto out;
++ err = 0;
+
-+int au_refresh_hinode_self(struct inode *inode)
-+{
-+ int err, update;
++ /*
++ * rmdir a dir may break the consistency on some filesystem.
++ * let's try heavy test.
++ */
++ err = -EACCES;
++ sb = dentry->d_sb;
++ br = au_sbr(sb, bindex);
++ h_idmap = au_br_idmap(br);
++ if (unlikely(!au_opt_test(au_mntflags(sb), DIRPERM1)
++ && au_test_h_perm(h_idmap, d_inode(h_parent),
++ MAY_EXEC | MAY_WRITE)))
++ goto out;
+
-+ err = au_ii_refresh(inode, &update);
-+ if (!err)
-+ au_refresh_hinode_attr(inode, update && S_ISDIR(inode->i_mode));
++ h_ppath.dentry = h_parent;
++ h_ppath.mnt = au_br_mnt(br);
++ h_latest = au_sio_lkup_one(h_idmap, &dentry->d_name, &h_ppath);
++ err = -EIO;
++ if (IS_ERR(h_latest))
++ goto out;
++ if (h_latest == h_dentry)
++ err = 0;
++ dput(h_latest);
+
-+ AuTraceErr(err);
++out:
+ return err;
+}
+
-+int au_refresh_hinode(struct inode *inode, struct dentry *dentry)
++/*
++ * decide the branch where we operate for @dentry. the branch index will be set
++ * @rbcpup. after deciding it, 'pin' it and store the timestamps of the parent
++ * dir for reverting.
++ * when a new whiteout is necessary, create it.
++ */
++static struct dentry*
++lock_hdir_create_wh(struct dentry *dentry, int isdir, aufs_bindex_t *rbcpup,
++ struct au_dtime *dt, struct au_pin *pin)
+{
-+ int err, e, update;
-+ unsigned int flags;
-+ umode_t mode;
-+ aufs_bindex_t bindex, bbot;
-+ unsigned char isdir;
-+ struct au_hinode *p;
-+ struct au_iinfo *iinfo;
++ struct dentry *wh_dentry;
++ struct super_block *sb;
++ struct path h_path;
++ int err, need_wh;
++ unsigned int udba;
++ aufs_bindex_t bcpup;
+
-+ err = au_ii_refresh(inode, &update);
++ need_wh = au_wr_dir_need_wh(dentry, isdir, rbcpup);
++ wh_dentry = ERR_PTR(need_wh);
++ if (unlikely(need_wh < 0))
++ goto out;
++
++ sb = dentry->d_sb;
++ udba = au_opt_udba(sb);
++ bcpup = *rbcpup;
++ err = au_pin(pin, dentry, bcpup, udba,
++ AuPin_DI_LOCKED | AuPin_MNT_WRITE);
++ wh_dentry = ERR_PTR(err);
+ if (unlikely(err))
+ goto out;
+
-+ update = 0;
-+ iinfo = au_ii(inode);
-+ p = au_hinode(iinfo, iinfo->ii_btop);
-+ mode = (inode->i_mode & S_IFMT);
-+ isdir = S_ISDIR(mode);
-+ flags = au_hi_flags(inode, isdir);
-+ bbot = au_dbbot(dentry);
-+ for (bindex = au_dbtop(dentry); bindex <= bbot; bindex++) {
-+ struct inode *h_i, *h_inode;
-+ struct dentry *h_d;
++ h_path.dentry = au_pinned_h_parent(pin);
++ if (udba != AuOpt_UDBA_NONE
++ && au_dbtop(dentry) == bcpup) {
++ err = au_may_del(dentry, bcpup, h_path.dentry, isdir);
++ wh_dentry = ERR_PTR(err);
++ if (unlikely(err))
++ goto out_unpin;
++ }
+
-+ h_d = au_h_dptr(dentry, bindex);
-+ if (!h_d || d_is_negative(h_d))
-+ continue;
++ h_path.mnt = au_sbr_mnt(sb, bcpup);
++ au_dtime_store(dt, au_pinned_parent(pin), &h_path);
++ wh_dentry = NULL;
++ if (!need_wh)
++ goto out; /* success, no need to create whiteout */
+
-+ h_inode = d_inode(h_d);
-+ AuDebugOn(mode != (h_inode->i_mode & S_IFMT));
-+ if (iinfo->ii_btop <= bindex && bindex <= iinfo->ii_bbot) {
-+ h_i = au_h_iptr(inode, bindex);
-+ if (h_i) {
-+ if (h_i == h_inode)
-+ continue;
-+ err = -EIO;
-+ break;
-+ }
-+ }
-+ if (bindex < iinfo->ii_btop)
-+ iinfo->ii_btop = bindex;
-+ if (iinfo->ii_bbot < bindex)
-+ iinfo->ii_bbot = bindex;
-+ au_set_h_iptr(inode, bindex, au_igrab(h_inode), flags);
-+ update = 1;
-+ }
-+ au_update_ibrange(inode, /*do_put_zero*/0);
-+ e = au_dy_irefresh(inode);
-+ if (unlikely(e && !err))
-+ err = e;
-+ if (!err)
-+ au_refresh_hinode_attr(inode, update && isdir);
++ wh_dentry = au_wh_create(dentry, bcpup, h_path.dentry);
++ if (IS_ERR(wh_dentry))
++ goto out_unpin;
++
++ /* returns with the parent is locked and wh_dentry is dget-ed */
++ goto out; /* success */
+
++out_unpin:
++ au_unpin(pin);
+out:
-+ AuTraceErr(err);
-+ return err;
++ return wh_dentry;
+}
+
-+static int set_inode(struct inode *inode, struct dentry *dentry)
++/*
++ * when removing a dir, rename it to a unique temporary whiteout-ed name first
++ * in order to be revertible and save time for removing many child whiteouts
++ * under the dir.
++ * returns 1 when there are too many child whiteout and caller should remove
++ * them asynchronously. returns 0 when the number of children is enough small to
++ * remove now or the branch fs is a remote fs.
++ * otherwise return an error.
++ */
++static int renwh_and_rmdir(struct dentry *dentry, aufs_bindex_t bindex,
++ struct au_nhash *whlist, struct inode *dir)
+{
-+ int err;
-+ unsigned int flags;
-+ umode_t mode;
-+ aufs_bindex_t bindex, btop, btail;
-+ unsigned char isdir;
++ int rmdir_later, err, dirwh;
+ struct dentry *h_dentry;
-+ struct inode *h_inode;
-+ struct au_iinfo *iinfo;
-+ const struct inode_operations *iop;
-+
-+ IiMustWriteLock(inode);
++ struct super_block *sb;
++ struct inode *inode;
+
-+ err = 0;
-+ isdir = 0;
-+ iop = au_sbi(inode->i_sb)->si_iop_array;
-+ btop = au_dbtop(dentry);
-+ h_dentry = au_h_dptr(dentry, btop);
-+ h_inode = d_inode(h_dentry);
-+ mode = h_inode->i_mode;
-+ switch (mode & S_IFMT) {
-+ case S_IFREG:
-+ btail = au_dbtail(dentry);
-+ inode->i_op = iop + AuIop_OTHER;
-+ inode->i_fop = &aufs_file_fop;
-+ err = au_dy_iaop(inode, btop, h_inode);
-+ if (unlikely(err))
-+ goto out;
-+ break;
-+ case S_IFDIR:
-+ isdir = 1;
-+ btail = au_dbtaildir(dentry);
-+ inode->i_op = iop + AuIop_DIR;
-+ inode->i_fop = &aufs_dir_fop;
-+ break;
-+ case S_IFLNK:
-+ btail = au_dbtail(dentry);
-+ inode->i_op = iop + AuIop_SYMLINK;
-+ break;
-+ case S_IFBLK:
-+ case S_IFCHR:
-+ case S_IFIFO:
-+ case S_IFSOCK:
-+ btail = au_dbtail(dentry);
-+ inode->i_op = iop + AuIop_OTHER;
-+ init_special_inode(inode, mode, h_inode->i_rdev);
-+ break;
-+ default:
-+ AuIOErr("Unknown file type 0%o\n", mode);
-+ err = -EIO;
++ sb = dentry->d_sb;
++ SiMustAnyLock(sb);
++ h_dentry = au_h_dptr(dentry, bindex);
++ err = au_whtmp_ren(h_dentry, au_sbr(sb, bindex));
++ if (unlikely(err))
+ goto out;
++
++ /* stop monitoring */
++ inode = d_inode(dentry);
++ au_hn_free(au_hi(inode, bindex));
++
++ if (!au_test_fs_remote(h_dentry->d_sb)) {
++ dirwh = au_sbi(sb)->si_dirwh;
++ rmdir_later = (dirwh <= 1);
++ if (!rmdir_later)
++ rmdir_later = au_nhash_test_longer_wh(whlist, bindex,
++ dirwh);
++ if (rmdir_later)
++ return rmdir_later;
+ }
+
-+ /* do not set hnotify for whiteouted dirs (SHWH mode) */
-+ flags = au_hi_flags(inode, isdir);
-+ if (au_opt_test(au_mntflags(dentry->d_sb), SHWH)
-+ && au_ftest_hi(flags, HNOTIFY)
-+ && dentry->d_name.len > AUFS_WH_PFX_LEN
-+ && !memcmp(dentry->d_name.name, AUFS_WH_PFX, AUFS_WH_PFX_LEN))
-+ au_fclr_hi(flags, HNOTIFY);
-+ iinfo = au_ii(inode);
-+ iinfo->ii_btop = btop;
-+ iinfo->ii_bbot = btail;
-+ for (bindex = btop; bindex <= btail; bindex++) {
-+ h_dentry = au_h_dptr(dentry, bindex);
-+ if (h_dentry)
-+ au_set_h_iptr(inode, bindex,
-+ au_igrab(d_inode(h_dentry)), flags);
++ err = au_whtmp_rmdir(dir, bindex, h_dentry, whlist);
++ if (unlikely(err)) {
++ AuIOErr("rmdir %pd, b%d failed, %d. ignored\n",
++ h_dentry, bindex, err);
++ err = 0;
+ }
-+ au_cpup_attr_all(inode, /*force*/1);
-+ /*
-+ * to force calling aufs_get_inode_acl() every time,
-+ * do not call cache_no_acl() for aufs inode.
-+ */
+
+out:
++ AuTraceErr(err);
+ return err;
+}
+
+/*
-+ * successful returns with iinfo write_locked
-+ * minus: errno
-+ * zero: success, matched
-+ * plus: no error, but unmatched
++ * final procedure for deleting a entry.
++ * maintain dentry and iattr.
+ */
-+static int reval_inode(struct inode *inode, struct dentry *dentry)
++static void epilog(struct inode *dir, struct dentry *dentry,
++ aufs_bindex_t bindex)
+{
-+ int err;
-+ unsigned int gen, igflags;
-+ aufs_bindex_t bindex, bbot;
-+ struct inode *h_inode, *h_dinode;
-+ struct dentry *h_dentry;
++ struct inode *inode;
+
-+ /*
-+ * before this function, if aufs got any iinfo lock, it must be only
-+ * one, the parent dir.
-+ * it can happen by UDBA and the obsoleted inode number.
-+ */
-+ err = -EIO;
-+ if (unlikely(inode->i_ino == parent_ino(dentry)))
-+ goto out;
++ inode = d_inode(dentry);
++ d_drop(dentry);
++ inode_set_ctime_to_ts(inode, inode_get_ctime(dir));
+
-+ err = 1;
-+ ii_write_lock_new_child(inode);
-+ h_dentry = au_h_dptr(dentry, au_dbtop(dentry));
-+ h_dinode = d_inode(h_dentry);
-+ bbot = au_ibbot(inode);
-+ for (bindex = au_ibtop(inode); bindex <= bbot; bindex++) {
-+ h_inode = au_h_iptr(inode, bindex);
-+ if (!h_inode || h_inode != h_dinode)
-+ continue;
++ au_dir_ts(dir, bindex);
++ inode_inc_iversion(dir);
++}
+
-+ err = 0;
-+ gen = au_iigen(inode, &igflags);
-+ if (gen == au_digen(dentry)
-+ && !au_ig_ftest(igflags, HALF_REFRESHED))
-+ break;
++/*
++ * when an error happened, remove the created whiteout and revert everything.
++ */
++static int do_revert(int err, struct inode *dir, aufs_bindex_t bindex,
++ aufs_bindex_t bwh, struct dentry *wh_dentry,
++ struct dentry *dentry, struct au_dtime *dt)
++{
++ int rerr;
++ struct path h_path = {
++ .dentry = wh_dentry,
++ .mnt = au_sbr_mnt(dir->i_sb, bindex)
++ };
+
-+ /* fully refresh inode using dentry */
-+ err = au_refresh_hinode(inode, dentry);
-+ if (!err)
-+ au_update_iigen(inode, /*half*/0);
-+ break;
++ rerr = au_wh_unlink_dentry(au_h_iptr(dir, bindex), &h_path, dentry);
++ if (!rerr) {
++ au_set_dbwh(dentry, bwh);
++ au_dtime_revert(dt);
++ return 0;
+ }
+
-+ if (unlikely(err))
-+ ii_write_unlock(inode);
-+out:
-+ return err;
++ AuIOErr("%pd reverting whiteout failed(%d, %d)\n", dentry, err, rerr);
++ return -EIO;
+}
+
-+int au_ino(struct super_block *sb, aufs_bindex_t bindex, ino_t h_ino,
-+ unsigned int d_type, ino_t *ino)
++/* ---------------------------------------------------------------------- */
++
++int aufs_unlink(struct inode *dir, struct dentry *dentry)
+{
-+ int err, idx;
-+ const int isnondir = d_type != DT_DIR;
++ int err;
++ aufs_bindex_t bwh, bindex, btop;
++ struct inode *inode, *h_dir, *delegated, *h_inode;
++ struct dentry *parent, *wh_dentry;
++ /* to reduce stack size */
++ struct {
++ struct au_dtime dt;
++ struct au_pin pin;
++ struct path h_path;
++ } *a;
+
-+ /* prevent hardlinked inode number from race condition */
-+ if (isnondir) {
-+ err = au_xinondir_enter(sb, bindex, h_ino, &idx);
-+ if (unlikely(err))
-+ goto out;
-+ }
++ IMustLock(dir);
+
-+ err = au_xino_read(sb, bindex, h_ino, ino);
++ 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_xinondir;
++ goto out_free;
++ err = au_d_hashed_positive(dentry);
++ if (unlikely(err))
++ goto out_unlock;
++ inode = d_inode(dentry);
++ IMustLock(inode);
++ err = -EISDIR;
++ if (unlikely(d_is_dir(dentry)))
++ goto out_unlock; /* possible? */
+
-+ if (!*ino) {
-+ err = -EIO;
-+ *ino = au_xino_new_ino(sb);
-+ if (unlikely(!*ino))
-+ goto out_xinondir;
-+ err = au_xino_write(sb, bindex, h_ino, *ino);
-+ if (unlikely(err))
-+ goto out_xinondir;
++ btop = au_dbtop(dentry);
++ bwh = au_dbwh(dentry);
++ bindex = -1;
++ parent = dentry->d_parent; /* dir inode is locked */
++ di_write_lock_parent(parent);
++ wh_dentry = lock_hdir_create_wh(dentry, /*isdir*/0, &bindex, &a->dt,
++ &a->pin);
++ err = PTR_ERR(wh_dentry);
++ if (IS_ERR(wh_dentry))
++ goto out_parent;
++
++ a->h_path.mnt = au_sbr_mnt(dentry->d_sb, btop);
++ a->h_path.dentry = au_h_dptr(dentry, btop);
++ dget(a->h_path.dentry);
++ if (bindex == btop) {
++ h_dir = au_pinned_h_dir(&a->pin);
++ delegated = NULL;
++ err = vfsub_unlink(h_dir, &a->h_path, &delegated, /*force*/0);
++ if (unlikely(err == -EWOULDBLOCK)) {
++ pr_warn("cannot retry for NFSv4 delegation"
++ " for an internal unlink\n");
++ iput(delegated);
++ }
++ } else {
++ /* dir inode is locked */
++ h_dir = d_inode(wh_dentry->d_parent);
++ IMustLock(h_dir);
++ err = 0;
+ }
+
-+out_xinondir:
-+ if (isnondir && idx >= 0)
-+ au_xinondir_leave(sb, bindex, h_ino, idx);
++ if (!err) {
++ vfsub_drop_nlink(inode);
++ epilog(dir, dentry, bindex);
++
++ /* update target timestamps */
++ if (bindex == btop) {
++ vfsub_update_h_iattr(&a->h_path, /*did*/NULL);
++ /*ignore*/
++ h_inode = d_inode(a->h_path.dentry);
++ inode_set_ctime_to_ts(inode, inode_get_ctime(h_inode));
++ } else
++ /* todo: this timestamp may be reverted later */
++ inode_set_ctime_to_ts(inode, inode_get_ctime(h_dir));
++ goto out_unpin; /* success */
++ }
++
++ /* revert */
++ if (wh_dentry) {
++ int rerr;
++
++ rerr = do_revert(err, dir, bindex, bwh, wh_dentry, dentry,
++ &a->dt);
++ if (rerr)
++ err = rerr;
++ }
++
++out_unpin:
++ au_unpin(&a->pin);
++ dput(wh_dentry);
++ dput(a->h_path.dentry);
++out_parent:
++ di_write_unlock(parent);
++out_unlock:
++ aufs_read_unlock(dentry, AuLock_DW);
++out_free:
++ au_kfree_rcu(a);
+out:
+ return err;
+}
+
-+/* successful returns with iinfo write_locked */
-+/* todo: return with unlocked? */
-+struct inode *au_new_inode(struct dentry *dentry, int must_new)
++int aufs_rmdir(struct inode *dir, struct dentry *dentry)
+{
-+ struct inode *inode, *h_inode;
-+ struct dentry *h_dentry;
-+ struct super_block *sb;
-+ ino_t h_ino, ino;
-+ int err, idx, hlinked;
-+ aufs_bindex_t btop;
++ int err, rmdir_later;
++ aufs_bindex_t bwh, bindex, btop;
++ struct inode *inode;
++ struct dentry *parent, *wh_dentry, *h_dentry;
++ struct au_whtmp_rmdir *args;
++ /* to reduce stack size */
++ struct {
++ struct au_dtime dt;
++ struct au_pin pin;
++ } *a;
+
-+ sb = dentry->d_sb;
-+ btop = au_dbtop(dentry);
-+ h_dentry = au_h_dptr(dentry, btop);
-+ h_inode = d_inode(h_dentry);
-+ h_ino = h_inode->i_ino;
-+ hlinked = !d_is_dir(h_dentry) && h_inode->i_nlink > 1;
++ IMustLock(dir);
+
-+new_ino:
-+ /*
-+ * stop 'race'-ing between hardlinks under different
-+ * parents.
-+ */
-+ if (hlinked) {
-+ err = au_xinondir_enter(sb, btop, h_ino, &idx);
-+ inode = ERR_PTR(err);
-+ if (unlikely(err))
-+ goto out;
-+ }
++ err = -ENOMEM;
++ a = kmalloc(sizeof(*a), GFP_NOFS);
++ if (unlikely(!a))
++ goto out;
+
-+ err = au_xino_read(sb, btop, h_ino, &ino);
-+ inode = ERR_PTR(err);
++ err = aufs_read_lock(dentry, AuLock_DW | AuLock_FLUSH | AuLock_GEN);
+ if (unlikely(err))
-+ goto out_xinondir;
++ goto out_free;
++ err = au_alive_dir(dentry);
++ if (unlikely(err))
++ goto out_unlock;
++ inode = d_inode(dentry);
++ IMustLock(inode);
++ err = -ENOTDIR;
++ if (unlikely(!d_is_dir(dentry)))
++ goto out_unlock; /* possible? */
+
-+ if (!ino) {
-+ ino = au_xino_new_ino(sb);
-+ if (unlikely(!ino)) {
-+ inode = ERR_PTR(-EIO);
-+ goto out_xinondir;
-+ }
-+ }
++ err = -ENOMEM;
++ args = au_whtmp_rmdir_alloc(dir->i_sb, GFP_NOFS);
++ if (unlikely(!args))
++ goto out_unlock;
+
-+ AuDbg("i%lu\n", (unsigned long)ino);
-+ inode = au_iget_locked(sb, ino);
-+ err = PTR_ERR(inode);
-+ if (IS_ERR(inode))
-+ goto out_xinondir;
++ parent = dentry->d_parent; /* dir inode is locked */
++ di_write_lock_parent(parent);
++ err = au_test_empty(dentry, &args->whlist);
++ if (unlikely(err))
++ goto out_parent;
+
-+ AuDbg("%lx, new %d\n", inode->i_state, !!(inode->i_state & I_NEW));
-+ if (inode->i_state & I_NEW) {
-+ ii_write_lock_new_child(inode);
-+ err = set_inode(inode, dentry);
-+ if (!err) {
-+ unlock_new_inode(inode);
-+ goto out_xinondir; /* success */
-+ }
++ btop = au_dbtop(dentry);
++ bwh = au_dbwh(dentry);
++ bindex = -1;
++ wh_dentry = lock_hdir_create_wh(dentry, /*isdir*/1, &bindex, &a->dt,
++ &a->pin);
++ err = PTR_ERR(wh_dentry);
++ if (IS_ERR(wh_dentry))
++ goto out_parent;
+
-+ /*
-+ * iget_failed() calls iput(), but we need to call
-+ * ii_write_unlock() after iget_failed(). so dirty hack for
-+ * i_count.
-+ */
-+ atomic_inc(&inode->i_count);
-+ iget_failed(inode);
-+ ii_write_unlock(inode);
-+ au_xino_write(sb, btop, h_ino, /*ino*/0);
-+ /* ignore this error */
-+ goto out_iput;
-+ } else if (!must_new && !IS_DEADDIR(inode) && inode->i_nlink) {
-+ /*
-+ * horrible race condition between lookup, readdir and copyup
-+ * (or something).
-+ */
-+ if (hlinked && idx >= 0)
-+ au_xinondir_leave(sb, btop, h_ino, idx);
-+ err = reval_inode(inode, dentry);
-+ if (unlikely(err < 0)) {
-+ hlinked = 0;
-+ goto out_iput;
-+ }
-+ if (!err)
-+ goto out; /* success */
-+ else if (hlinked && idx >= 0) {
-+ err = au_xinondir_enter(sb, btop, h_ino, &idx);
-+ if (unlikely(err)) {
-+ iput(inode);
-+ inode = ERR_PTR(err);
-+ goto out;
-+ }
++ h_dentry = au_h_dptr(dentry, btop);
++ dget(h_dentry);
++ rmdir_later = 0;
++ if (bindex == btop) {
++ err = renwh_and_rmdir(dentry, btop, &args->whlist, dir);
++ if (err > 0) {
++ rmdir_later = err;
++ err = 0;
+ }
-+ }
++ } else {
++ /* stop monitoring */
++ au_hn_free(au_hi(inode, btop));
+
-+ if (unlikely(au_test_fs_unique_ino(h_inode)))
-+ AuWarn1("Warning: Un-notified UDBA or repeatedly renamed dir,"
-+ " b%d, %s, %pd, hi%lu, i%lu.\n",
-+ btop, au_sbtype(h_dentry->d_sb), dentry,
-+ (unsigned long)h_ino, (unsigned long)ino);
-+ ino = 0;
-+ err = au_xino_write(sb, btop, h_ino, /*ino*/0);
-+ if (!err) {
-+ iput(inode);
-+ if (hlinked && idx >= 0)
-+ au_xinondir_leave(sb, btop, h_ino, idx);
-+ goto new_ino;
++ /* dir inode is locked */
++ IMustLock(d_inode(wh_dentry->d_parent));
++ err = 0;
+ }
+
-+out_iput:
-+ iput(inode);
-+ inode = ERR_PTR(err);
-+out_xinondir:
-+ if (hlinked && idx >= 0)
-+ au_xinondir_leave(sb, btop, h_ino, idx);
-+out:
-+ return inode;
-+}
++ if (!err) {
++ vfsub_dead_dir(inode);
++ au_set_dbdiropq(dentry, -1);
++ epilog(dir, dentry, bindex);
+
-+/* ---------------------------------------------------------------------- */
++ if (rmdir_later) {
++ au_whtmp_kick_rmdir(dir, btop, h_dentry, args);
++ args = NULL;
++ }
+
-+int au_test_ro(struct super_block *sb, aufs_bindex_t bindex,
-+ struct inode *inode)
-+{
-+ int err;
-+ struct inode *hi;
++ goto out_unpin; /* success */
++ }
+
-+ err = au_br_rdonly(au_sbr(sb, bindex));
++ /* revert */
++ AuLabel(revert);
++ if (wh_dentry) {
++ int rerr;
+
-+ /* pseudo-link after flushed may happen out of bounds */
-+ if (!err
-+ && inode
-+ && au_ibtop(inode) <= bindex
-+ && bindex <= au_ibbot(inode)) {
-+ /*
-+ * permission check is unnecessary since vfsub routine
-+ * will be called later
-+ */
-+ hi = au_h_iptr(inode, bindex);
-+ if (hi)
-+ err = IS_IMMUTABLE(hi) ? -EROFS : 0;
++ rerr = do_revert(err, dir, bindex, bwh, wh_dentry, dentry,
++ &a->dt);
++ if (rerr)
++ err = rerr;
+ }
+
++out_unpin:
++ au_unpin(&a->pin);
++ dput(wh_dentry);
++ dput(h_dentry);
++out_parent:
++ di_write_unlock(parent);
++ if (args)
++ au_whtmp_rmdir_free(args);
++out_unlock:
++ aufs_read_unlock(dentry, AuLock_DW);
++out_free:
++ au_kfree_rcu(a);
++out:
++ AuTraceErr(err);
+ return err;
+}
-+
-+int au_test_h_perm(struct mnt_idmap *h_idmap, struct inode *h_inode,
-+ int mask)
-+{
-+ if (uid_eq(current_fsuid(), GLOBAL_ROOT_UID))
-+ return 0;
-+ return inode_permission(h_idmap, h_inode, mask);
-+}
-+
-+int au_test_h_perm_sio(struct mnt_idmap *h_idmap, struct inode *h_inode,
-+ int mask)
-+{
-+ if (au_test_nfs(h_inode->i_sb)
-+ && (mask & MAY_WRITE)
-+ && S_ISDIR(h_inode->i_mode))
-+ mask |= MAY_READ; /* force permission check */
-+ return au_test_h_perm(h_idmap, h_inode, mask);
-+}
-diff --git a/fs/aufs/inode.h b/fs/aufs/inode.h
-new file mode 100644
-index 00000000000000..76c3bd49674a29
---- /dev/null
-+++ b/fs/aufs/inode.h
-@@ -0,0 +1,707 @@
-+/* SPDX-License-Identifier: GPL-2.0 */
+diff -urN /usr/share/empty/fs/aufs/i_op_ren.c linux/fs/aufs/i_op_ren.c
+--- /usr/share/empty/fs/aufs/i_op_ren.c 1970-01-01 01:00:00.000000000 +0100
++++ linux/fs/aufs/i_op_ren.c 2024-03-10 23:40:47.083143450 +0100
+@@ -0,0 +1,1264 @@
++// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2005-2022 Junjiro R. Okajima
+ *
+ */
+
+/*
-+ * inode operations
++ * inode operation (rename entry)
++ * todo: this is crazy monster
+ */
+
-+#ifndef __AUFS_INODE_H__
-+#define __AUFS_INODE_H__
-+
-+#ifdef __KERNEL__
++#include <linux/iversion.h>
++#include "aufs.h"
+
-+#include <linux/fsnotify.h>
-+#include "rwsem.h"
++enum { AuSRC, AuDST, AuSrcDst };
++enum { AuPARENT, AuCHILD, AuParentChild };
+
-+struct vfsmount;
++#define AuRen_ISDIR_SRC BIT(0)
++#define AuRen_ISDIR_DST BIT(1)
++#define AuRen_ISSAMEDIR BIT(2)
++#define AuRen_WHSRC BIT(3)
++#define AuRen_WHDST BIT(4)
++#define AuRen_MNT_WRITE BIT(5)
++#define AuRen_DT_DSTDIR BIT(6)
++#define AuRen_DIROPQ_SRC BIT(7)
++#define AuRen_DIROPQ_DST BIT(8)
++#define AuRen_DIRREN BIT(9)
++#define AuRen_DROPPED_SRC BIT(10)
++#define AuRen_DROPPED_DST BIT(11)
++#define au_ftest_ren(flags, name) ((flags) & AuRen_##name)
++#define au_fset_ren(flags, name) \
++ do { (flags) |= AuRen_##name; } while (0)
++#define au_fclr_ren(flags, name) \
++ do { (flags) &= ~AuRen_##name; } while (0)
+
-+struct au_hnotify {
-+#ifdef CONFIG_AUFS_HNOTIFY
-+#ifdef CONFIG_AUFS_HFSNOTIFY
-+ /* never use fsnotify_add_vfsmount_mark() */
-+ struct fsnotify_mark hn_mark;
-+#endif
-+ struct inode *hn_aufs_inode; /* no get/put */
-+ struct rcu_head rcu;
++#ifndef CONFIG_AUFS_DIRREN
++#undef AuRen_DIRREN
++#define AuRen_DIRREN 0
+#endif
-+} ____cacheline_aligned_in_smp;
+
-+struct au_hinode {
-+ struct inode *hi_inode;
-+ aufs_bindex_t hi_id;
-+#ifdef CONFIG_AUFS_HNOTIFY
-+ struct au_hnotify *hi_notify;
-+#endif
++struct au_ren_args {
++ struct {
++ struct dentry *dentry, *h_dentry, *parent, *h_parent,
++ *wh_dentry;
++ struct inode *dir, *inode;
++ struct au_hinode *hdir, *hinode;
++ struct au_dtime dt[AuParentChild];
++ aufs_bindex_t btop, bdiropq;
++ } sd[AuSrcDst];
++
++#define src_dentry sd[AuSRC].dentry
++#define src_dir sd[AuSRC].dir
++#define src_inode sd[AuSRC].inode
++#define src_h_dentry sd[AuSRC].h_dentry
++#define src_parent sd[AuSRC].parent
++#define src_h_parent sd[AuSRC].h_parent
++#define src_wh_dentry sd[AuSRC].wh_dentry
++#define src_hdir sd[AuSRC].hdir
++#define src_hinode sd[AuSRC].hinode
++#define src_h_dir sd[AuSRC].hdir->hi_inode
++#define src_dt sd[AuSRC].dt
++#define src_btop sd[AuSRC].btop
++#define src_bdiropq sd[AuSRC].bdiropq
++
++#define dst_dentry sd[AuDST].dentry
++#define dst_dir sd[AuDST].dir
++#define dst_inode sd[AuDST].inode
++#define dst_h_dentry sd[AuDST].h_dentry
++#define dst_parent sd[AuDST].parent
++#define dst_h_parent sd[AuDST].h_parent
++#define dst_wh_dentry sd[AuDST].wh_dentry
++#define dst_hdir sd[AuDST].hdir
++#define dst_hinode sd[AuDST].hinode
++#define dst_h_dir sd[AuDST].hdir->hi_inode
++#define dst_dt sd[AuDST].dt
++#define dst_btop sd[AuDST].btop
++#define dst_bdiropq sd[AuDST].bdiropq
++
++ struct dentry *h_trap;
++ struct au_branch *br;
++ struct path h_path;
++ struct au_nhash whlist;
++ aufs_bindex_t btgt, src_bwh;
++
++ struct {
++ unsigned short auren_flags;
++ unsigned char flags; /* syscall parameter */
++ unsigned char exchange;
++ } __packed;
+
-+ /* reference to the copied-up whiteout with get/put */
-+ struct dentry *hi_whdentry;
++ struct au_whtmp_rmdir *thargs;
++ struct dentry *h_dst;
++ struct au_hinode *h_root;
+};
+
-+/* ig_flags */
-+#define AuIG_HALF_REFRESHED 1
-+#define au_ig_ftest(flags, name) ((flags) & AuIG_##name)
-+#define au_ig_fset(flags, name) \
-+ do { (flags) |= AuIG_##name; } while (0)
-+#define au_ig_fclr(flags, name) \
-+ do { (flags) &= ~AuIG_##name; } while (0)
++/* ---------------------------------------------------------------------- */
+
-+struct au_iigen {
-+ spinlock_t ig_spin;
-+ __u32 ig_generation, ig_flags;
-+};
++/*
++ * functions for reverting.
++ * when an error happened in a single rename systemcall, we should revert
++ * everything as if nothing happened.
++ * we don't need to revert the copied-up/down the parent dir since they are
++ * harmless.
++ */
+
-+struct au_vdir;
-+struct au_iinfo {
-+ struct au_iigen ii_generation;
-+ struct super_block *ii_hsb1; /* no get/put */
++#define RevertFailure(fmt, ...) do { \
++ AuIOErr("revert failure: " fmt " (%d, %d)\n", \
++ ##__VA_ARGS__, err, rerr); \
++ err = -EIO; \
++} while (0)
+
-+ struct au_rwsem ii_rwsem;
-+ aufs_bindex_t ii_btop, ii_bbot;
-+ __u32 ii_higen;
-+ struct au_hinode *ii_hinode;
-+ struct au_vdir *ii_vdir;
-+};
++static void au_ren_do_rev_diropq(int err, struct au_ren_args *a, int idx)
++{
++ int rerr;
++ struct dentry *d;
++#define src_or_dst(member) a->sd[idx].member
+
-+struct au_icntnr {
-+ struct au_iinfo iinfo;
-+ struct inode vfs_inode;
-+ struct hlist_bl_node plink;
-+ struct rcu_head rcu;
-+} ____cacheline_aligned_in_smp;
++ d = src_or_dst(dentry); /* {src,dst}_dentry */
++ au_hn_inode_lock_nested(src_or_dst(hinode), AuLsc_I_CHILD);
++ rerr = au_diropq_remove(d, a->btgt);
++ au_hn_inode_unlock(src_or_dst(hinode));
++ au_set_dbdiropq(d, src_or_dst(bdiropq));
++ if (rerr)
++ RevertFailure("remove diropq %pd", d);
+
-+/* au_pin flags */
-+#define AuPin_DI_LOCKED 1
-+#define AuPin_MNT_WRITE (1 << 1)
-+#define au_ftest_pin(flags, name) ((flags) & AuPin_##name)
-+#define au_fset_pin(flags, name) \
-+ do { (flags) |= AuPin_##name; } while (0)
-+#define au_fclr_pin(flags, name) \
-+ do { (flags) &= ~AuPin_##name; } while (0)
++#undef src_or_dst_
++}
+
-+struct au_pin {
-+ /* input */
-+ struct dentry *dentry;
-+ unsigned int udba;
-+ unsigned char lsc_di, lsc_hi, flags;
-+ aufs_bindex_t bindex;
++static void au_ren_rev_diropq(int err, struct au_ren_args *a)
++{
++ if (au_ftest_ren(a->auren_flags, DIROPQ_SRC))
++ au_ren_do_rev_diropq(err, a, AuSRC);
++ if (au_ftest_ren(a->auren_flags, DIROPQ_DST))
++ au_ren_do_rev_diropq(err, a, AuDST);
++}
+
-+ /* output */
-+ struct dentry *parent;
-+ struct au_hinode *hdir;
-+ struct vfsmount *h_mnt;
++static void au_ren_rev_rename(int err, struct au_ren_args *a)
++{
++ int rerr;
++ struct inode *delegated;
++ struct path h_ppath = {
++ .dentry = a->src_h_parent,
++ .mnt = a->h_path.mnt
++ };
+
-+ /* temporary unlock/relock for copyup */
-+ struct dentry *h_dentry, *h_parent;
-+ struct au_branch *br;
-+ struct task_struct *task;
-+};
++ a->h_path.dentry = vfsub_lkup_one(&a->src_dentry->d_name, &h_ppath);
++ rerr = PTR_ERR(a->h_path.dentry);
++ if (IS_ERR(a->h_path.dentry)) {
++ RevertFailure("lkup one %pd", a->src_dentry);
++ return;
++ }
+
-+void au_pin_hdir_unlock(struct au_pin *p);
-+int au_pin_hdir_lock(struct au_pin *p);
-+int au_pin_hdir_relock(struct au_pin *p);
-+void au_pin_hdir_acquire_nest(struct au_pin *p);
-+void au_pin_hdir_release(struct au_pin *p);
++ delegated = NULL;
++ rerr = vfsub_rename(a->dst_h_dir,
++ au_h_dptr(a->src_dentry, a->btgt),
++ a->src_h_dir, &a->h_path, &delegated, a->flags);
++ if (unlikely(rerr == -EWOULDBLOCK)) {
++ pr_warn("cannot retry for NFSv4 delegation"
++ " for an internal rename\n");
++ iput(delegated);
++ }
++ d_drop(a->h_path.dentry);
++ dput(a->h_path.dentry);
++ /* au_set_h_dptr(a->src_dentry, a->btgt, NULL); */
++ if (rerr)
++ RevertFailure("rename %pd", a->src_dentry);
++}
+
-+/* ---------------------------------------------------------------------- */
++static void au_ren_rev_whtmp(int err, struct au_ren_args *a)
++{
++ int rerr;
++ struct inode *delegated;
++ struct path h_ppath = {
++ .dentry = a->dst_h_parent,
++ .mnt = a->h_path.mnt
++ };
+
-+static inline struct au_iinfo *au_ii(struct inode *inode)
++ a->h_path.dentry = vfsub_lkup_one(&a->dst_dentry->d_name, &h_ppath);
++ rerr = PTR_ERR(a->h_path.dentry);
++ if (IS_ERR(a->h_path.dentry)) {
++ RevertFailure("lkup one %pd", a->dst_dentry);
++ return;
++ }
++ if (d_is_positive(a->h_path.dentry)) {
++ d_drop(a->h_path.dentry);
++ dput(a->h_path.dentry);
++ return;
++ }
++
++ delegated = NULL;
++ rerr = vfsub_rename(a->dst_h_dir, a->h_dst, a->dst_h_dir, &a->h_path,
++ &delegated, a->flags);
++ if (unlikely(rerr == -EWOULDBLOCK)) {
++ pr_warn("cannot retry for NFSv4 delegation"
++ " for an internal rename\n");
++ iput(delegated);
++ }
++ d_drop(a->h_path.dentry);
++ dput(a->h_path.dentry);
++ if (!rerr)
++ au_set_h_dptr(a->dst_dentry, a->btgt, dget(a->h_dst));
++ else
++ RevertFailure("rename %pd", a->h_dst);
++}
++
++static void au_ren_rev_whsrc(int err, struct au_ren_args *a)
+{
-+ BUG_ON(is_bad_inode(inode));
-+ return &(container_of(inode, struct au_icntnr, vfs_inode)->iinfo);
++ int rerr;
++
++ a->h_path.dentry = a->src_wh_dentry;
++ rerr = au_wh_unlink_dentry(a->src_h_dir, &a->h_path, a->src_dentry);
++ au_set_dbwh(a->src_dentry, a->src_bwh);
++ if (rerr)
++ RevertFailure("unlink %pd", a->src_wh_dentry);
+}
++#undef RevertFailure
+
+/* ---------------------------------------------------------------------- */
+
-+/* inode.c */
-+struct inode *au_igrab(struct inode *inode);
-+void au_refresh_iop(struct inode *inode, int force_getattr);
-+int au_refresh_hinode_self(struct inode *inode);
-+int au_refresh_hinode(struct inode *inode, struct dentry *dentry);
-+int au_ino(struct super_block *sb, aufs_bindex_t bindex, ino_t h_ino,
-+ unsigned int d_type, ino_t *ino);
-+struct inode *au_new_inode(struct dentry *dentry, int must_new);
-+int au_test_ro(struct super_block *sb, aufs_bindex_t bindex,
-+ struct inode *inode);
-+int au_test_h_perm(struct mnt_idmap *h_idmap, struct inode *h_inode,
-+ int mask);
-+int au_test_h_perm_sio(struct mnt_idmap *h_idmap, struct inode *h_inode,
-+ int mask);
-+
-+static inline int au_wh_ino(struct super_block *sb, aufs_bindex_t bindex,
-+ ino_t h_ino, unsigned int d_type, ino_t *ino)
++/*
++ * when we have to copyup the renaming entry, do it with the rename-target name
++ * in order to minimize the cost (the later actual rename is unnecessary).
++ * otherwise rename it on the target branch.
++ */
++static int au_ren_or_cpup(struct au_ren_args *a)
+{
-+#ifdef CONFIG_AUFS_SHWH
-+ return au_ino(sb, bindex, h_ino, d_type, ino);
-+#else
-+ return 0;
-+#endif
-+}
++ int err;
++ struct dentry *d;
++ struct inode *delegated;
+
-+/* i_op.c */
-+enum {
-+ AuIop_SYMLINK,
-+ AuIop_DIR,
-+ AuIop_OTHER,
-+ AuIop_Last
-+};
-+extern struct inode_operations aufs_iop[AuIop_Last], /* not const */
-+ aufs_iop_nogetattr[AuIop_Last];
++ d = a->src_dentry;
++ if (au_dbtop(d) == a->btgt) {
++ a->h_path.dentry = a->dst_h_dentry;
++ AuDebugOn(au_dbtop(d) != a->btgt);
++ delegated = NULL;
++ err = vfsub_rename(a->src_h_dir, au_h_dptr(d, a->btgt),
++ a->dst_h_dir, &a->h_path, &delegated,
++ a->flags);
++ if (unlikely(err == -EWOULDBLOCK)) {
++ pr_warn("cannot retry for NFSv4 delegation"
++ " for an internal rename\n");
++ iput(delegated);
++ }
++ } else
++ BUG();
+
-+/* au_wr_dir flags */
-+#define AuWrDir_ADD_ENTRY 1
-+#define AuWrDir_ISDIR (1 << 1)
-+#define AuWrDir_TMPFILE (1 << 2)
-+#define au_ftest_wrdir(flags, name) ((flags) & AuWrDir_##name)
-+#define au_fset_wrdir(flags, name) \
-+ do { (flags) |= AuWrDir_##name; } while (0)
-+#define au_fclr_wrdir(flags, name) \
-+ do { (flags) &= ~AuWrDir_##name; } while (0)
++ if (!err && a->h_dst)
++ /* it will be set to dinfo later */
++ dget(a->h_dst);
+
-+struct au_wr_dir_args {
-+ aufs_bindex_t force_btgt;
-+ unsigned char flags;
-+};
-+int au_wr_dir(struct dentry *dentry, struct dentry *src_dentry,
-+ struct au_wr_dir_args *args);
++ return err;
++}
+
-+struct dentry *au_pinned_h_parent(struct au_pin *pin);
-+void au_pin_init(struct au_pin *pin, struct dentry *dentry,
-+ aufs_bindex_t bindex, int lsc_di, int lsc_hi,
-+ unsigned int udba, unsigned char flags);
-+int au_pin(struct au_pin *pin, struct dentry *dentry, aufs_bindex_t bindex,
-+ unsigned int udba, unsigned char flags) __must_check;
-+int au_do_pin(struct au_pin *pin) __must_check;
-+void au_unpin(struct au_pin *pin);
-+int au_reval_for_attr(struct dentry *dentry, unsigned int sigen);
++/* cf. aufs_rmdir() */
++static int au_ren_del_whtmp(struct au_ren_args *a)
++{
++ int err;
++ struct inode *dir;
+
-+#define AuIcpup_DID_CPUP 1
-+#define au_ftest_icpup(flags, name) ((flags) & AuIcpup_##name)
-+#define au_fset_icpup(flags, name) \
-+ do { (flags) |= AuIcpup_##name; } while (0)
-+#define au_fclr_icpup(flags, name) \
-+ do { (flags) &= ~AuIcpup_##name; } while (0)
++ dir = a->dst_dir;
++ SiMustAnyLock(dir->i_sb);
++ if (!au_nhash_test_longer_wh(&a->whlist, a->btgt,
++ au_sbi(dir->i_sb)->si_dirwh)
++ || au_test_fs_remote(a->h_dst->d_sb)) {
++ err = au_whtmp_rmdir(dir, a->btgt, a->h_dst, &a->whlist);
++ if (unlikely(err))
++ pr_warn("failed removing whtmp dir %pd (%d), "
++ "ignored.\n", a->h_dst, err);
++ } else {
++ au_nhash_wh_free(&a->thargs->whlist);
++ a->thargs->whlist = a->whlist;
++ a->whlist.nh_num = 0;
++ au_whtmp_kick_rmdir(dir, a->btgt, a->h_dst, a->thargs);
++ dput(a->h_dst);
++ a->thargs = NULL;
++ }
+
-+struct au_icpup_args {
-+ unsigned char flags;
-+ unsigned char pin_flags;
-+ aufs_bindex_t btgt;
-+ unsigned int udba;
-+ struct au_pin pin;
-+ struct path h_path;
-+ struct inode *h_inode;
-+};
++ return 0;
++}
+
-+int au_pin_and_icpup(struct dentry *dentry, struct iattr *ia,
-+ struct au_icpup_args *a);
++/* make it 'opaque' dir. */
++static int au_ren_do_diropq(struct au_ren_args *a, int idx)
++{
++ int err;
++ struct dentry *d, *diropq;
++#define src_or_dst(member) a->sd[idx].member
+
-+int au_h_path_getattr(struct dentry *dentry, struct inode *inode, int force,
-+ struct path *h_path, int locked);
++ err = 0;
++ d = src_or_dst(dentry); /* {src,dst}_dentry */
++ src_or_dst(bdiropq) = au_dbdiropq(d);
++ src_or_dst(hinode) = au_hi(src_or_dst(inode), a->btgt);
++ au_hn_inode_lock_nested(src_or_dst(hinode), AuLsc_I_CHILD);
++ diropq = au_diropq_create(d, a->btgt);
++ au_hn_inode_unlock(src_or_dst(hinode));
++ if (IS_ERR(diropq))
++ err = PTR_ERR(diropq);
++ else
++ dput(diropq);
+
-+/* i_op_add.c */
-+int au_may_add(struct dentry *dentry, aufs_bindex_t bindex,
-+ struct dentry *h_parent, int isdir);
-+int aufs_mknod(struct mnt_idmap *idmap, struct inode *dir,
-+ struct dentry *dentry, umode_t mode, dev_t dev);
-+int aufs_symlink(struct mnt_idmap *idmap, struct inode *dir,
-+ struct dentry *dentry, const char *symname);
-+int aufs_create(struct mnt_idmap *idmap, struct inode *dir,
-+ struct dentry *dentry, umode_t mode, bool want_excl);
-+struct vfsub_aopen_args;
-+int au_aopen_or_create(struct inode *dir, struct dentry *dentry,
-+ struct vfsub_aopen_args *args);
-+int aufs_tmpfile(struct mnt_idmap *idmap, struct inode *dir,
-+ struct file *file, umode_t mode);
-+int aufs_link(struct dentry *src_dentry, struct inode *dir,
-+ struct dentry *dentry);
-+int aufs_mkdir(struct mnt_idmap *idmap, struct inode *dir,
-+ struct dentry *dentry, umode_t mode);
++#undef src_or_dst_
++ return err;
++}
+
-+/* i_op_del.c */
-+int au_wr_dir_need_wh(struct dentry *dentry, int isdir, aufs_bindex_t *bcpup);
-+int au_may_del(struct dentry *dentry, aufs_bindex_t bindex,
-+ struct dentry *h_parent, int isdir);
-+int aufs_unlink(struct inode *dir, struct dentry *dentry);
-+int aufs_rmdir(struct inode *dir, struct dentry *dentry);
++static int au_ren_diropq(struct au_ren_args *a)
++{
++ int err;
++ unsigned char always;
++ struct dentry *d;
+
-+/* i_op_ren.c */
-+int au_wbr(struct dentry *dentry, aufs_bindex_t btgt);
-+int aufs_rename(struct mnt_idmap *idmap,
-+ struct inode *_src_dir, struct dentry *_src_dentry,
-+ struct inode *_dst_dir, struct dentry *_dst_dentry,
-+ unsigned int _flags);
++ err = 0;
++ d = a->dst_dentry; /* already renamed on the branch */
++ always = !!au_opt_test(au_mntflags(d->d_sb), ALWAYS_DIROPQ);
++ if (au_ftest_ren(a->auren_flags, ISDIR_SRC)
++ && !au_ftest_ren(a->auren_flags, DIRREN)
++ && a->btgt != au_dbdiropq(a->src_dentry)
++ && (a->dst_wh_dentry
++ || a->btgt <= au_dbdiropq(d)
++ /* hide the lower to keep xino */
++ /* the lowers may not be a dir, but we hide them anyway */
++ || a->btgt < au_dbbot(d)
++ || always)) {
++ AuDbg("here\n");
++ err = au_ren_do_diropq(a, AuSRC);
++ if (unlikely(err))
++ goto out;
++ au_fset_ren(a->auren_flags, DIROPQ_SRC);
++ }
++ if (!a->exchange)
++ goto out; /* success */
+
-+/* iinfo.c */
-+struct inode *au_h_iptr(struct inode *inode, aufs_bindex_t bindex);
-+void au_hiput(struct au_hinode *hinode);
-+void au_set_hi_wh(struct inode *inode, aufs_bindex_t bindex,
-+ struct dentry *h_wh);
-+unsigned int au_hi_flags(struct inode *inode, int isdir);
++ d = a->src_dentry; /* already renamed on the branch */
++ if (au_ftest_ren(a->auren_flags, ISDIR_DST)
++ && a->btgt != au_dbdiropq(a->dst_dentry)
++ && (a->btgt < au_dbdiropq(d)
++ || a->btgt < au_dbbot(d)
++ || always)) {
++ AuDbgDentry(a->src_dentry);
++ AuDbgDentry(a->dst_dentry);
++ err = au_ren_do_diropq(a, AuDST);
++ if (unlikely(err))
++ goto out_rev_src;
++ au_fset_ren(a->auren_flags, DIROPQ_DST);
++ }
++ goto out; /* success */
+
-+/* hinode flags */
-+#define AuHi_XINO 1
-+#define AuHi_HNOTIFY (1 << 1)
-+#define au_ftest_hi(flags, name) ((flags) & AuHi_##name)
-+#define au_fset_hi(flags, name) \
-+ do { (flags) |= AuHi_##name; } while (0)
-+#define au_fclr_hi(flags, name) \
-+ do { (flags) &= ~AuHi_##name; } while (0)
++out_rev_src:
++ AuDbg("err %d, reverting src\n", err);
++ au_ren_rev_diropq(err, a);
++out:
++ return err;
++}
+
-+#ifndef CONFIG_AUFS_HNOTIFY
-+#undef AuHi_HNOTIFY
-+#define AuHi_HNOTIFY 0
-+#endif
++static int do_rename(struct au_ren_args *a)
++{
++ int err;
++ struct dentry *d, *h_d;
++ struct inode *h_inode;
+
-+void au_set_h_iptr(struct inode *inode, aufs_bindex_t bindex,
-+ struct inode *h_inode, unsigned int flags);
++ if (!a->exchange) {
++ /* prepare workqueue args for asynchronous rmdir */
++ h_d = a->dst_h_dentry;
++ if (au_ftest_ren(a->auren_flags, ISDIR_DST)
++ /* && !au_ftest_ren(a->auren_flags, DIRREN) */
++ && d_is_positive(h_d)) {
++ err = -ENOMEM;
++ a->thargs = au_whtmp_rmdir_alloc(a->src_dentry->d_sb,
++ GFP_NOFS);
++ if (unlikely(!a->thargs))
++ goto out;
++ a->h_dst = dget(h_d);
++ }
+
-+void au_update_iigen(struct inode *inode, int half);
-+void au_update_ibrange(struct inode *inode, int do_put_zero);
++ /* create whiteout for src_dentry */
++ if (au_ftest_ren(a->auren_flags, WHSRC)) {
++ a->src_bwh = au_dbwh(a->src_dentry);
++ AuDebugOn(a->src_bwh >= 0);
++ a->src_wh_dentry = au_wh_create(a->src_dentry, a->btgt,
++ a->src_h_parent);
++ err = PTR_ERR(a->src_wh_dentry);
++ if (IS_ERR(a->src_wh_dentry))
++ goto out_thargs;
++ }
+
-+void au_icntnr_init_once(void *_c);
-+void au_hinode_init(struct au_hinode *hinode);
-+int au_iinfo_init(struct inode *inode);
-+void au_iinfo_fin(struct inode *inode);
-+int au_hinode_realloc(struct au_iinfo *iinfo, int nbr, int may_shrink);
++ /* lookup whiteout for dentry */
++ if (au_ftest_ren(a->auren_flags, WHDST)) {
++ h_d = au_wh_lkup(a->dst_h_parent,
++ &a->dst_dentry->d_name, a->br);
++ err = PTR_ERR(h_d);
++ if (IS_ERR(h_d))
++ goto out_whsrc;
++ if (d_is_negative(h_d))
++ dput(h_d);
++ else
++ a->dst_wh_dentry = h_d;
++ }
+
-+#ifdef CONFIG_PROC_FS
-+/* plink.c */
-+int au_plink_maint(struct super_block *sb, int flags);
-+struct au_sbinfo;
-+void au_plink_maint_leave(struct au_sbinfo *sbinfo);
-+int au_plink_maint_enter(struct super_block *sb);
-+#ifdef CONFIG_AUFS_DEBUG
-+void au_plink_list(struct super_block *sb);
-+#else
-+AuStubVoid(au_plink_list, struct super_block *sb)
-+#endif
-+int au_plink_test(struct inode *inode);
-+struct dentry *au_plink_lkup(struct inode *inode, aufs_bindex_t bindex);
-+void au_plink_append(struct inode *inode, aufs_bindex_t bindex,
-+ struct dentry *h_dentry);
-+void au_plink_put(struct super_block *sb, int verbose);
-+void au_plink_clean(struct super_block *sb, int verbose);
-+void au_plink_half_refresh(struct super_block *sb, aufs_bindex_t br_id);
-+#else
-+AuStubInt0(au_plink_maint, struct super_block *sb, int flags);
-+AuStubVoid(au_plink_maint_leave, struct au_sbinfo *sbinfo);
-+AuStubInt0(au_plink_maint_enter, struct super_block *sb);
-+AuStubVoid(au_plink_list, struct super_block *sb);
-+AuStubInt0(au_plink_test, struct inode *inode);
-+AuStub(struct dentry *, au_plink_lkup, return NULL,
-+ struct inode *inode, aufs_bindex_t bindex);
-+AuStubVoid(au_plink_append, struct inode *inode, aufs_bindex_t bindex,
-+ struct dentry *h_dentry);
-+AuStubVoid(au_plink_put, struct super_block *sb, int verbose);
-+AuStubVoid(au_plink_clean, struct super_block *sb, int verbose);
-+AuStubVoid(au_plink_half_refresh, struct super_block *sb, aufs_bindex_t br_id);
-+#endif /* CONFIG_PROC_FS */
++ /* rename dentry to tmpwh */
++ if (a->thargs) {
++ err = au_whtmp_ren(a->dst_h_dentry, a->br);
++ if (unlikely(err))
++ goto out_whdst;
+
-+#ifdef CONFIG_AUFS_XATTR
-+/* xattr.c */
-+int au_cpup_xattr(struct path *h_dst, struct path *h_src, int ignore_flags,
-+ unsigned int verbose);
-+ssize_t aufs_listxattr(struct dentry *dentry, char *list, size_t size);
-+void au_xattr_init(struct super_block *sb);
-+#else
-+AuStubInt0(au_cpup_xattr, struct path *h_dst, struct path *h_src,
-+ int ignore_flags, unsigned int verbose);
-+AuStubVoid(au_xattr_init, struct super_block *sb);
-+#endif
++ d = a->dst_dentry;
++ au_set_h_dptr(d, a->btgt, NULL);
++ err = au_lkup_neg(d, a->btgt, /*wh*/0);
++ if (unlikely(err))
++ goto out_whtmp;
++ a->dst_h_dentry = au_h_dptr(d, a->btgt);
++ }
++ }
+
-+#ifdef CONFIG_FS_POSIX_ACL
-+struct posix_acl *aufs_get_inode_acl(struct inode *inode, int type, bool rcu);
-+struct posix_acl *aufs_get_acl(struct mnt_idmap *idmap,
-+ struct dentry *dentry, int type);
-+int aufs_set_acl(struct mnt_idmap *idmap, struct dentry *dentry,
-+ struct posix_acl *acl, int type);
++ BUG_ON(d_is_positive(a->dst_h_dentry) && a->src_btop != a->btgt);
++#if 0 /* debugging */
++ BUG_ON(!au_ftest_ren(a->auren_flags, DIRREN)
++ && d_is_positive(a->dst_h_dentry)
++ && a->src_btop != a->btgt);
+#endif
+
-+#if IS_ENABLED(CONFIG_AUFS_XATTR) || IS_ENABLED(CONFIG_FS_POSIX_ACL)
-+enum {
-+ AU_XATTR_SET,
-+ AU_ACL_SET
-+};
++ /* rename by vfs_rename or cpup */
++ err = au_ren_or_cpup(a);
++ if (unlikely(err))
++ /* leave the copied-up one */
++ goto out_whtmp;
+
-+struct au_sxattr {
-+ int type;
-+ union {
-+ struct {
-+ const char *name;
-+ const void *value;
-+ size_t size;
-+ int flags;
-+ } set;
-+ struct {
-+ struct posix_acl *acl;
-+ int type;
-+ } acl_set;
-+ } u;
-+};
-+ssize_t au_sxattr(struct dentry *dentry, struct inode *inode,
-+ struct au_sxattr *arg);
-+#endif
++ /* make dir opaque */
++ err = au_ren_diropq(a);
++ if (unlikely(err))
++ goto out_rename;
+
-+/* ---------------------------------------------------------------------- */
++ /* update target timestamps */
++ if (a->exchange) {
++ AuDebugOn(au_dbtop(a->dst_dentry) != a->btgt);
++ a->h_path.dentry = au_h_dptr(a->dst_dentry, a->btgt);
++ vfsub_update_h_iattr(&a->h_path, /*did*/NULL); /*ignore*/
++ h_inode = d_inode(a->h_path.dentry);
++ inode_set_ctime_to_ts(a->dst_inode, inode_get_ctime(h_inode));
++ }
++ AuDebugOn(au_dbtop(a->src_dentry) != a->btgt);
++ a->h_path.dentry = au_h_dptr(a->src_dentry, a->btgt);
++ vfsub_update_h_iattr(&a->h_path, /*did*/NULL); /*ignore*/
++ h_inode = d_inode(a->h_path.dentry);
++ inode_set_ctime_to_ts(a->src_inode, inode_get_ctime(h_inode));
+
-+/* lock subclass for iinfo */
-+enum {
-+ AuLsc_II_CHILD, /* child first */
-+ AuLsc_II_CHILD2, /* rename(2), link(2), and cpup at hnotify */
-+ AuLsc_II_CHILD3, /* copyup dirs */
-+ AuLsc_II_PARENT, /* see AuLsc_I_PARENT in vfsub.h */
-+ AuLsc_II_PARENT2,
-+ AuLsc_II_PARENT3, /* copyup dirs */
-+ AuLsc_II_NEW_CHILD
-+};
++ if (!a->exchange) {
++ /* remove whiteout for dentry */
++ if (a->dst_wh_dentry) {
++ a->h_path.dentry = a->dst_wh_dentry;
++ err = au_wh_unlink_dentry(a->dst_h_dir, &a->h_path,
++ a->dst_dentry);
++ if (unlikely(err))
++ goto out_diropq;
++ }
+
-+/*
-+ * ii_read_lock_child, ii_write_lock_child,
-+ * ii_read_lock_child2, ii_write_lock_child2,
-+ * ii_read_lock_child3, ii_write_lock_child3,
-+ * ii_read_lock_parent, ii_write_lock_parent,
-+ * ii_read_lock_parent2, ii_write_lock_parent2,
-+ * ii_read_lock_parent3, ii_write_lock_parent3,
-+ * ii_read_lock_new_child, ii_write_lock_new_child,
-+ */
-+#define AuReadLockFunc(name, lsc) \
-+static inline void ii_read_lock_##name(struct inode *i) \
-+{ \
-+ au_rw_read_lock_nested(&au_ii(i)->ii_rwsem, AuLsc_II_##lsc); \
++ /* remove whtmp */
++ if (a->thargs)
++ au_ren_del_whtmp(a); /* ignore this error */
++
++ au_fhsm_wrote(a->src_dentry->d_sb, a->btgt, /*force*/0);
++ }
++ err = 0;
++ goto out_success;
++
++out_diropq:
++ au_ren_rev_diropq(err, a);
++out_rename:
++ au_ren_rev_rename(err, a);
++ dput(a->h_dst);
++out_whtmp:
++ if (a->thargs)
++ au_ren_rev_whtmp(err, a);
++out_whdst:
++ dput(a->dst_wh_dentry);
++ a->dst_wh_dentry = NULL;
++out_whsrc:
++ if (a->src_wh_dentry)
++ au_ren_rev_whsrc(err, a);
++out_success:
++ dput(a->src_wh_dentry);
++ dput(a->dst_wh_dentry);
++out_thargs:
++ if (a->thargs) {
++ dput(a->h_dst);
++ au_whtmp_rmdir_free(a->thargs);
++ a->thargs = NULL;
++ }
++out:
++ return err;
+}
+
-+#define AuWriteLockFunc(name, lsc) \
-+static inline void ii_write_lock_##name(struct inode *i) \
-+{ \
-+ au_rw_write_lock_nested(&au_ii(i)->ii_rwsem, AuLsc_II_##lsc); \
++/* ---------------------------------------------------------------------- */
++
++/*
++ * test if @dentry dir can be rename destination or not.
++ * success means, it is a logically empty dir.
++ */
++static int may_rename_dstdir(struct dentry *dentry, struct au_nhash *whlist)
++{
++ return au_test_empty(dentry, whlist);
+}
+
-+#define AuRWLockFuncs(name, lsc) \
-+ AuReadLockFunc(name, lsc) \
-+ AuWriteLockFunc(name, lsc)
++/*
++ * test if @a->src_dentry dir can be rename source or not.
++ * if it can, return 0.
++ * success means,
++ * - it is a logically empty dir.
++ * - or, it exists on writable branch and has no children including whiteouts
++ * on the lower branch unless DIRREN is on.
++ */
++static int may_rename_srcdir(struct au_ren_args *a)
++{
++ int err;
++ unsigned int rdhash;
++ aufs_bindex_t btop, btgt;
++ struct dentry *dentry;
++ struct super_block *sb;
++ struct au_sbinfo *sbinfo;
+
-+AuRWLockFuncs(child, CHILD);
-+AuRWLockFuncs(child2, CHILD2);
-+AuRWLockFuncs(child3, CHILD3);
-+AuRWLockFuncs(parent, PARENT);
-+AuRWLockFuncs(parent2, PARENT2);
-+AuRWLockFuncs(parent3, PARENT3);
-+AuRWLockFuncs(new_child, NEW_CHILD);
++ dentry = a->src_dentry;
++ sb = dentry->d_sb;
++ sbinfo = au_sbi(sb);
++ if (au_opt_test(sbinfo->si_mntflags, DIRREN))
++ au_fset_ren(a->auren_flags, DIRREN);
+
-+#undef AuReadLockFunc
-+#undef AuWriteLockFunc
-+#undef AuRWLockFuncs
++ btgt = a->btgt;
++ btop = au_dbtop(dentry);
++ if (btop != btgt) {
++ struct au_nhash whlist;
+
-+#define ii_read_unlock(i) au_rw_read_unlock(&au_ii(i)->ii_rwsem)
-+#define ii_write_unlock(i) au_rw_write_unlock(&au_ii(i)->ii_rwsem)
-+#define ii_downgrade_lock(i) au_rw_dgrade_lock(&au_ii(i)->ii_rwsem)
++ SiMustAnyLock(sb);
++ rdhash = sbinfo->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;
++ err = au_test_empty(dentry, &whlist);
++ au_nhash_wh_free(&whlist);
++ goto out;
++ }
+
-+#define IiMustNoWaiters(i) AuRwMustNoWaiters(&au_ii(i)->ii_rwsem)
-+#define IiMustAnyLock(i) AuRwMustAnyLock(&au_ii(i)->ii_rwsem)
-+#define IiMustWriteLock(i) AuRwMustWriteLock(&au_ii(i)->ii_rwsem)
++ if (btop == au_dbtaildir(dentry))
++ return 0; /* success */
+
-+/* ---------------------------------------------------------------------- */
++ err = au_test_empty_lower(dentry);
+
-+static inline void au_icntnr_init(struct au_icntnr *c)
-+{
-+#ifdef CONFIG_AUFS_DEBUG
-+ c->vfs_inode.i_mode = 0;
-+#endif
++out:
++ if (err == -ENOTEMPTY) {
++ if (au_ftest_ren(a->auren_flags, DIRREN)) {
++ err = 0;
++ } else {
++ AuWarn1("renaming dir who has child(ren) on multiple "
++ "branches, is not supported\n");
++ err = -EXDEV;
++ }
++ }
++ return err;
+}
+
-+static inline unsigned int au_iigen(struct inode *inode, unsigned int *igflags)
++/* side effect: sets whlist and h_dentry */
++static int au_ren_may_dir(struct au_ren_args *a)
+{
-+ unsigned int gen;
-+ struct au_iinfo *iinfo;
-+ struct au_iigen *iigen;
++ int err;
++ unsigned int rdhash;
++ struct dentry *d;
+
-+ iinfo = au_ii(inode);
-+ iigen = &iinfo->ii_generation;
-+ spin_lock(&iigen->ig_spin);
-+ if (igflags)
-+ *igflags = iigen->ig_flags;
-+ gen = iigen->ig_generation;
-+ spin_unlock(&iigen->ig_spin);
++ d = a->dst_dentry;
++ SiMustAnyLock(d->d_sb);
+
-+ return gen;
++ err = 0;
++ if (au_ftest_ren(a->auren_flags, ISDIR_DST) && a->dst_inode) {
++ rdhash = au_sbi(d->d_sb)->si_rdhash;
++ if (!rdhash)
++ rdhash = au_rdhash_est(au_dir_size(/*file*/NULL, d));
++ err = au_nhash_alloc(&a->whlist, rdhash, GFP_NOFS);
++ if (unlikely(err))
++ goto out;
++
++ if (!a->exchange) {
++ au_set_dbtop(d, a->dst_btop);
++ err = may_rename_dstdir(d, &a->whlist);
++ au_set_dbtop(d, a->btgt);
++ } else
++ err = may_rename_srcdir(a);
++ }
++ a->dst_h_dentry = au_h_dptr(d, au_dbtop(d));
++ if (unlikely(err))
++ goto out;
++
++ d = a->src_dentry;
++ a->src_h_dentry = au_h_dptr(d, au_dbtop(d));
++ if (au_ftest_ren(a->auren_flags, ISDIR_SRC)) {
++ err = may_rename_srcdir(a);
++ if (unlikely(err)) {
++ au_nhash_wh_free(&a->whlist);
++ a->whlist.nh_num = 0;
++ }
++ }
++out:
++ return err;
+}
+
-+/* tiny test for inode number */
-+/* tmpfs generation is too rough */
-+static inline int au_test_higen(struct inode *inode, struct inode *h_inode)
++/* ---------------------------------------------------------------------- */
++
++/*
++ * simple tests for rename.
++ * following the checks in vfs, plus the parent-child relationship.
++ */
++static int au_may_ren(struct au_ren_args *a)
+{
-+ struct au_iinfo *iinfo;
++ int err, isdir;
++ struct inode *h_inode;
+
-+ iinfo = au_ii(inode);
-+ AuRwMustAnyLock(&iinfo->ii_rwsem);
-+ return !(iinfo->ii_hsb1 == h_inode->i_sb
-+ && iinfo->ii_higen == h_inode->i_generation);
++ if (a->src_btop == a->btgt) {
++ err = au_may_del(a->src_dentry, a->btgt, a->src_h_parent,
++ au_ftest_ren(a->auren_flags, ISDIR_SRC));
++ if (unlikely(err))
++ goto out;
++ err = -EINVAL;
++ if (unlikely(a->src_h_dentry == a->h_trap))
++ goto out;
++ }
++
++ err = 0;
++ if (a->dst_btop != a->btgt)
++ goto out;
++
++ err = -ENOTEMPTY;
++ if (unlikely(a->dst_h_dentry == a->h_trap))
++ goto out;
++
++ err = -EIO;
++ isdir = !!au_ftest_ren(a->auren_flags, ISDIR_DST);
++ if (d_really_is_negative(a->dst_dentry)) {
++ if (d_is_negative(a->dst_h_dentry))
++ err = au_may_add(a->dst_dentry, a->btgt,
++ a->dst_h_parent, isdir);
++ } else {
++ if (unlikely(d_is_negative(a->dst_h_dentry)))
++ goto out;
++ h_inode = d_inode(a->dst_h_dentry);
++ if (h_inode->i_nlink)
++ err = au_may_del(a->dst_dentry, a->btgt,
++ a->dst_h_parent, isdir);
++ }
++
++out:
++ if (unlikely(err == -ENOENT || err == -EEXIST))
++ err = -EIO;
++ AuTraceErr(err);
++ return err;
+}
+
-+static inline void au_iigen_dec(struct inode *inode)
-+{
-+ struct au_iinfo *iinfo;
-+ struct au_iigen *iigen;
++/* ---------------------------------------------------------------------- */
+
-+ iinfo = au_ii(inode);
-+ iigen = &iinfo->ii_generation;
-+ spin_lock(&iigen->ig_spin);
-+ iigen->ig_generation--;
-+ spin_unlock(&iigen->ig_spin);
++/*
++ * locking order
++ * (VFS)
++ * - src_dir and dir by lock_rename()
++ * - inode if exists
++ * (aufs)
++ * - lock all
++ * + src_dentry and dentry by aufs_read_and_write_lock2() which calls,
++ * + si_read_lock
++ * + di_write_lock2_child()
++ * + di_write_lock_child()
++ * + ii_write_lock_child()
++ * + di_write_lock_child2()
++ * + ii_write_lock_child2()
++ * + src_parent and parent
++ * + di_write_lock_parent()
++ * + ii_write_lock_parent()
++ * + di_write_lock_parent2()
++ * + ii_write_lock_parent2()
++ * + lower src_dir and dir by vfsub_lock_rename()
++ * + verify the every relationships between child and parent. if any
++ * of them failed, unlock all and return -EBUSY.
++ */
++static void au_ren_unlock(struct au_ren_args *a)
++{
++ vfsub_unlock_rename(a->src_h_parent, a->src_hdir,
++ a->dst_h_parent, a->dst_hdir);
++ if (au_ftest_ren(a->auren_flags, DIRREN)
++ && a->h_root)
++ au_hn_inode_unlock(a->h_root);
++ if (au_ftest_ren(a->auren_flags, MNT_WRITE))
++ vfsub_mnt_drop_write(au_br_mnt(a->br));
+}
+
-+static inline int au_iigen_test(struct inode *inode, unsigned int sigen)
++static int au_ren_lock(struct au_ren_args *a)
+{
+ int err;
++ unsigned int udba;
+
+ err = 0;
-+ if (unlikely(inode && au_iigen(inode, NULL) != sigen))
-+ err = -EIO;
++ a->src_h_parent = au_h_dptr(a->src_parent, a->btgt);
++ a->src_hdir = au_hi(a->src_dir, a->btgt);
++ a->dst_h_parent = au_h_dptr(a->dst_parent, a->btgt);
++ a->dst_hdir = au_hi(a->dst_dir, a->btgt);
++
++ err = vfsub_mnt_want_write(au_br_mnt(a->br));
++ if (unlikely(err))
++ goto out;
++ au_fset_ren(a->auren_flags, MNT_WRITE);
++ if (au_ftest_ren(a->auren_flags, DIRREN)) {
++ struct dentry *root;
++ struct inode *dir;
++
++ /*
++ * sbinfo is already locked, so this ii_read_lock is
++ * unnecessary. but our debugging feature checks it.
++ */
++ root = a->src_inode->i_sb->s_root;
++ if (root != a->src_parent && root != a->dst_parent) {
++ dir = d_inode(root);
++ ii_read_lock_parent3(dir);
++ a->h_root = au_hi(dir, a->btgt);
++ ii_read_unlock(dir);
++ au_hn_inode_lock_nested(a->h_root, AuLsc_I_PARENT3);
++ }
++ }
++ a->h_trap = vfsub_lock_rename(a->src_h_parent, a->src_hdir,
++ a->dst_h_parent, a->dst_hdir);
++ if (IS_ERR(a->h_trap)) {
++ err = PTR_ERR(a->h_trap);
++ goto out;
++ }
++ udba = au_opt_udba(a->src_dentry->d_sb);
++ if (unlikely(a->src_hdir->hi_inode != d_inode(a->src_h_parent)
++ || a->dst_hdir->hi_inode != d_inode(a->dst_h_parent)))
++ err = au_busy_or_stale();
++ if (!err && au_dbtop(a->src_dentry) == a->btgt)
++ err = au_h_verify(a->src_h_dentry, udba,
++ d_inode(a->src_h_parent), a->src_h_parent,
++ a->br);
++ if (!err && au_dbtop(a->dst_dentry) == a->btgt)
++ err = au_h_verify(a->dst_h_dentry, udba,
++ d_inode(a->dst_h_parent), a->dst_h_parent,
++ a->br);
++ if (!err)
++ goto out; /* success */
++
++ err = au_busy_or_stale();
++ au_ren_unlock(a);
+
++out:
+ return err;
+}
+
+/* ---------------------------------------------------------------------- */
+
-+static inline struct au_hinode *au_hinode(struct au_iinfo *iinfo,
-+ aufs_bindex_t bindex)
++static void au_ren_refresh_dir(struct au_ren_args *a)
+{
-+ return iinfo->ii_hinode + bindex;
++ struct inode *dir;
++
++ dir = a->dst_dir;
++ inode_inc_iversion(dir);
++ if (au_ftest_ren(a->auren_flags, ISDIR_SRC)) {
++ /* is this updating defined in POSIX? */
++ au_cpup_attr_timesizes(a->src_inode);
++ au_cpup_attr_nlink(dir, /*force*/1);
++ }
++ au_dir_ts(dir, a->btgt);
++
++ if (a->exchange) {
++ dir = a->src_dir;
++ inode_inc_iversion(dir);
++ if (au_ftest_ren(a->auren_flags, ISDIR_DST)) {
++ /* is this updating defined in POSIX? */
++ au_cpup_attr_timesizes(a->dst_inode);
++ au_cpup_attr_nlink(dir, /*force*/1);
++ }
++ au_dir_ts(dir, a->btgt);
++ }
++
++ if (au_ftest_ren(a->auren_flags, ISSAMEDIR))
++ return;
++
++ dir = a->src_dir;
++ inode_inc_iversion(dir);
++ if (au_ftest_ren(a->auren_flags, ISDIR_SRC))
++ au_cpup_attr_nlink(dir, /*force*/1);
++ au_dir_ts(dir, a->btgt);
+}
+
-+static inline int au_is_bad_inode(struct inode *inode)
++static void au_ren_refresh(struct au_ren_args *a)
+{
-+ return !!(is_bad_inode(inode) || !au_hinode(au_ii(inode), 0));
++ aufs_bindex_t bbot, bindex;
++ struct dentry *d, *h_d;
++ struct inode *i, *h_i;
++ struct super_block *sb;
++
++ d = a->dst_dentry;
++ d_drop(d);
++ if (a->h_dst)
++ /* already dget-ed by au_ren_or_cpup() */
++ au_set_h_dptr(d, a->btgt, a->h_dst);
++
++ i = a->dst_inode;
++ if (i) {
++ if (!a->exchange) {
++ if (!au_ftest_ren(a->auren_flags, ISDIR_DST))
++ vfsub_drop_nlink(i);
++ else {
++ vfsub_dead_dir(i);
++ au_cpup_attr_timesizes(i);
++ }
++ au_update_dbrange(d, /*do_put_zero*/1);
++ } else
++ au_cpup_attr_nlink(i, /*force*/1);
++ } else {
++ bbot = a->btgt;
++ for (bindex = au_dbtop(d); bindex < bbot; bindex++)
++ au_set_h_dptr(d, bindex, NULL);
++ bbot = au_dbbot(d);
++ for (bindex = a->btgt + 1; bindex <= bbot; bindex++)
++ au_set_h_dptr(d, bindex, NULL);
++ au_update_dbrange(d, /*do_put_zero*/0);
++ }
++
++ if (a->exchange
++ || au_ftest_ren(a->auren_flags, DIRREN)) {
++ d_drop(a->src_dentry);
++ if (au_ftest_ren(a->auren_flags, DIRREN))
++ au_set_dbwh(a->src_dentry, -1);
++ return;
++ }
++
++ d = a->src_dentry;
++ au_set_dbwh(d, -1);
++ bbot = au_dbbot(d);
++ for (bindex = a->btgt + 1; bindex <= bbot; bindex++) {
++ h_d = au_h_dptr(d, bindex);
++ if (h_d)
++ au_set_h_dptr(d, bindex, NULL);
++ }
++ au_set_dbbot(d, a->btgt);
++
++ sb = d->d_sb;
++ i = a->src_inode;
++ if (au_opt_test(au_mntflags(sb), PLINK) && au_plink_test(i))
++ return; /* success */
++
++ bbot = au_ibbot(i);
++ for (bindex = a->btgt + 1; bindex <= bbot; bindex++) {
++ h_i = au_h_iptr(i, bindex);
++ if (h_i) {
++ au_xino_write(sb, bindex, h_i->i_ino, /*ino*/0);
++ /* ignore this error */
++ au_set_h_iptr(i, bindex, NULL, 0);
++ }
++ }
++ au_set_ibbot(i, a->btgt);
+}
+
-+static inline aufs_bindex_t au_ii_br_id(struct inode *inode,
-+ aufs_bindex_t bindex)
-+{
-+ IiMustAnyLock(inode);
-+ return au_hinode(au_ii(inode), bindex)->hi_id;
-+}
++/* ---------------------------------------------------------------------- */
+
-+static inline aufs_bindex_t au_ibtop(struct inode *inode)
++/* mainly for link(2) and rename(2) */
++int au_wbr(struct dentry *dentry, aufs_bindex_t btgt)
+{
-+ IiMustAnyLock(inode);
-+ return au_ii(inode)->ii_btop;
-+}
++ aufs_bindex_t bdiropq, bwh;
++ struct dentry *parent;
++ struct au_branch *br;
+
-+static inline aufs_bindex_t au_ibbot(struct inode *inode)
-+{
-+ IiMustAnyLock(inode);
-+ return au_ii(inode)->ii_bbot;
-+}
++ parent = dentry->d_parent;
++ IMustLock(d_inode(parent)); /* dir is locked */
+
-+static inline struct au_vdir *au_ivdir(struct inode *inode)
-+{
-+ IiMustAnyLock(inode);
-+ return au_ii(inode)->ii_vdir;
-+}
++ bdiropq = au_dbdiropq(parent);
++ bwh = au_dbwh(dentry);
++ br = au_sbr(dentry->d_sb, btgt);
++ if (au_br_rdonly(br)
++ || (0 <= bdiropq && bdiropq < btgt)
++ || (0 <= bwh && bwh < btgt))
++ btgt = -1;
+
-+static inline struct dentry *au_hi_wh(struct inode *inode, aufs_bindex_t bindex)
-+{
-+ IiMustAnyLock(inode);
-+ return au_hinode(au_ii(inode), bindex)->hi_whdentry;
++ AuDbg("btgt %d\n", btgt);
++ return btgt;
+}
+
-+static inline void au_set_ibtop(struct inode *inode, aufs_bindex_t bindex)
++/* sets src_btop, dst_btop and btgt */
++static int au_ren_wbr(struct au_ren_args *a)
+{
-+ IiMustWriteLock(inode);
-+ au_ii(inode)->ii_btop = bindex;
-+}
++ int err;
++ struct au_wr_dir_args wr_dir_args = {
++ /* .force_btgt = -1, */
++ .flags = AuWrDir_ADD_ENTRY
++ };
+
-+static inline void au_set_ibbot(struct inode *inode, aufs_bindex_t bindex)
-+{
-+ IiMustWriteLock(inode);
-+ au_ii(inode)->ii_bbot = bindex;
-+}
++ a->src_btop = au_dbtop(a->src_dentry);
++ a->dst_btop = au_dbtop(a->dst_dentry);
++ if (au_ftest_ren(a->auren_flags, ISDIR_SRC)
++ || au_ftest_ren(a->auren_flags, ISDIR_DST))
++ au_fset_wrdir(wr_dir_args.flags, ISDIR);
++ wr_dir_args.force_btgt = a->src_btop;
++ if (a->dst_inode && a->dst_btop < a->src_btop)
++ wr_dir_args.force_btgt = a->dst_btop;
++ wr_dir_args.force_btgt = au_wbr(a->dst_dentry, wr_dir_args.force_btgt);
++ err = au_wr_dir(a->dst_dentry, a->src_dentry, &wr_dir_args);
++ a->btgt = err;
++ if (a->exchange)
++ au_update_dbtop(a->dst_dentry);
+
-+static inline void au_set_ivdir(struct inode *inode, struct au_vdir *vdir)
-+{
-+ IiMustWriteLock(inode);
-+ au_ii(inode)->ii_vdir = vdir;
++ return err;
+}
+
-+static inline struct au_hinode *au_hi(struct inode *inode, aufs_bindex_t bindex)
++static void au_ren_dt(struct au_ren_args *a)
+{
-+ IiMustAnyLock(inode);
-+ return au_hinode(au_ii(inode), bindex);
-+}
-+
-+/* ---------------------------------------------------------------------- */
++ a->h_path.dentry = a->src_h_parent;
++ au_dtime_store(a->src_dt + AuPARENT, a->src_parent, &a->h_path);
++ if (!au_ftest_ren(a->auren_flags, ISSAMEDIR)) {
++ a->h_path.dentry = a->dst_h_parent;
++ au_dtime_store(a->dst_dt + AuPARENT, a->dst_parent, &a->h_path);
++ }
+
-+static inline struct dentry *au_pinned_parent(struct au_pin *pin)
-+{
-+ if (pin)
-+ return pin->parent;
-+ return NULL;
-+}
++ au_fclr_ren(a->auren_flags, DT_DSTDIR);
++ if (!au_ftest_ren(a->auren_flags, ISDIR_SRC)
++ && !a->exchange)
++ return;
+
-+static inline struct inode *au_pinned_h_dir(struct au_pin *pin)
-+{
-+ if (pin && pin->hdir)
-+ return pin->hdir->hi_inode;
-+ return NULL;
++ a->h_path.dentry = a->src_h_dentry;
++ au_dtime_store(a->src_dt + AuCHILD, a->src_dentry, &a->h_path);
++ if (d_is_positive(a->dst_h_dentry)) {
++ au_fset_ren(a->auren_flags, DT_DSTDIR);
++ a->h_path.dentry = a->dst_h_dentry;
++ au_dtime_store(a->dst_dt + AuCHILD, a->dst_dentry, &a->h_path);
++ }
+}
+
-+static inline struct au_hinode *au_pinned_hdir(struct au_pin *pin)
++static void au_ren_rev_dt(int err, struct au_ren_args *a)
+{
-+ if (pin)
-+ return pin->hdir;
-+ return NULL;
-+}
++ struct dentry *h_d;
++ struct inode *h_inode;
+
-+static inline void au_pin_set_dentry(struct au_pin *pin, struct dentry *dentry)
-+{
-+ if (pin)
-+ pin->dentry = dentry;
-+}
++ au_dtime_revert(a->src_dt + AuPARENT);
++ if (!au_ftest_ren(a->auren_flags, ISSAMEDIR))
++ au_dtime_revert(a->dst_dt + AuPARENT);
+
-+static inline void au_pin_set_parent_lflag(struct au_pin *pin,
-+ unsigned char lflag)
-+{
-+ if (pin) {
-+ if (lflag)
-+ au_fset_pin(pin->flags, DI_LOCKED);
-+ else
-+ au_fclr_pin(pin->flags, DI_LOCKED);
-+ }
-+}
++ if (au_ftest_ren(a->auren_flags, ISDIR_SRC) && err != -EIO) {
++ h_d = a->src_dt[AuCHILD].dt_h_path.dentry;
++ h_inode = d_inode(h_d);
++ inode_lock_nested(h_inode, AuLsc_I_CHILD);
++ au_dtime_revert(a->src_dt + AuCHILD);
++ inode_unlock(h_inode);
+
-+#if 0 /* reserved */
-+static inline void au_pin_set_parent(struct au_pin *pin, struct dentry *parent)
-+{
-+ if (pin) {
-+ dput(pin->parent);
-+ pin->parent = dget(parent);
++ if (au_ftest_ren(a->auren_flags, DT_DSTDIR)) {
++ h_d = a->dst_dt[AuCHILD].dt_h_path.dentry;
++ h_inode = d_inode(h_d);
++ inode_lock_nested(h_inode, AuLsc_I_CHILD);
++ au_dtime_revert(a->dst_dt + AuCHILD);
++ inode_unlock(h_inode);
++ }
+ }
+}
-+#endif
+
+/* ---------------------------------------------------------------------- */
+
-+struct au_branch;
-+#ifdef CONFIG_AUFS_HNOTIFY
-+struct au_hnotify_op {
-+ void (*ctl)(struct au_hinode *hinode, int do_set);
-+ int (*alloc)(struct au_hinode *hinode);
-+
-+ /*
-+ * if it returns true, the caller should free hinode->hi_notify,
-+ * otherwise ->free() frees it.
-+ */
-+ int (*free)(struct au_hinode *hinode,
-+ struct au_hnotify *hn) __must_check;
-+
-+ void (*fin)(void);
-+ int (*init)(void);
-+
-+ int (*reset_br)(unsigned int udba, struct au_branch *br, int perm);
-+ void (*fin_br)(struct au_branch *br);
-+ int (*init_br)(struct au_branch *br, int perm);
-+};
-+
-+/* hnotify.c */
-+int au_hn_alloc(struct au_hinode *hinode, struct inode *inode);
-+void au_hn_free(struct au_hinode *hinode);
-+void au_hn_ctl(struct au_hinode *hinode, int do_set);
-+void au_hn_reset(struct inode *inode, unsigned int flags);
-+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 au_hnotify_reset_br(unsigned int udba, struct au_branch *br, int perm);
-+int au_hnotify_init_br(struct au_branch *br, int perm);
-+void au_hnotify_fin_br(struct au_branch *br);
-+int __init au_hnotify_init(void);
-+void au_hnotify_fin(void);
-+
-+/* hfsnotify.c */
-+extern const struct au_hnotify_op au_hnotify_op;
-+
-+static inline
-+void au_hn_init(struct au_hinode *hinode)
++int aufs_rename(struct mnt_idmap *idmap,
++ struct inode *_src_dir, struct dentry *_src_dentry,
++ struct inode *_dst_dir, struct dentry *_dst_dentry,
++ unsigned int _flags)
+{
-+ hinode->hi_notify = NULL;
-+}
++ int err, lock_flags;
++ void *rev;
++ /* reduce stack space */
++ struct au_ren_args *a;
++ struct au_pin pin;
+
-+static inline struct au_hnotify *au_hn(struct au_hinode *hinode)
-+{
-+ return hinode->hi_notify;
-+}
++ AuDbg("%pd, %pd, 0x%x\n", _src_dentry, _dst_dentry, _flags);
++ IMustLock(_src_dir);
++ IMustLock(_dst_dir);
+
-+#else
-+AuStub(int, au_hn_alloc, return -EOPNOTSUPP,
-+ struct au_hinode *hinode __maybe_unused,
-+ struct inode *inode __maybe_unused)
-+AuStub(struct au_hnotify *, au_hn, return NULL, struct au_hinode *hinode)
-+AuStubVoid(au_hn_free, struct au_hinode *hinode __maybe_unused)
-+AuStubVoid(au_hn_ctl, struct au_hinode *hinode __maybe_unused,
-+ int do_set __maybe_unused)
-+AuStubVoid(au_hn_reset, struct inode *inode __maybe_unused,
-+ unsigned int flags __maybe_unused)
-+AuStubInt0(au_hnotify_reset_br, unsigned int udba __maybe_unused,
-+ struct au_branch *br __maybe_unused,
-+ int perm __maybe_unused)
-+AuStubInt0(au_hnotify_init_br, struct au_branch *br __maybe_unused,
-+ int perm __maybe_unused)
-+AuStubVoid(au_hnotify_fin_br, struct au_branch *br __maybe_unused)
-+AuStubInt0(__init au_hnotify_init, void)
-+AuStubVoid(au_hnotify_fin, void)
-+AuStubVoid(au_hn_init, struct au_hinode *hinode __maybe_unused)
-+#endif /* CONFIG_AUFS_HNOTIFY */
++ err = -EINVAL;
++ if (unlikely(_flags & RENAME_WHITEOUT))
++ goto out;
+
-+static inline void au_hn_suspend(struct au_hinode *hdir)
-+{
-+ au_hn_ctl(hdir, /*do_set*/0);
-+}
++ err = -ENOMEM;
++ BUILD_BUG_ON(sizeof(*a) > PAGE_SIZE);
++ a = kzalloc(sizeof(*a), GFP_NOFS);
++ if (unlikely(!a))
++ goto out;
+
-+static inline void au_hn_resume(struct au_hinode *hdir)
-+{
-+ au_hn_ctl(hdir, /*do_set*/1);
-+}
++ a->flags = _flags;
++ BUILD_BUG_ON(sizeof(a->exchange) == sizeof(u8)
++ && RENAME_EXCHANGE > U8_MAX);
++ a->exchange = _flags & RENAME_EXCHANGE;
++ a->src_dir = _src_dir;
++ a->src_dentry = _src_dentry;
++ a->src_inode = NULL;
++ if (d_really_is_positive(a->src_dentry))
++ a->src_inode = d_inode(a->src_dentry);
++ a->src_parent = a->src_dentry->d_parent; /* dir inode is locked */
++ a->dst_dir = _dst_dir;
++ a->dst_dentry = _dst_dentry;
++ a->dst_inode = NULL;
++ if (d_really_is_positive(a->dst_dentry))
++ a->dst_inode = d_inode(a->dst_dentry);
++ a->dst_parent = a->dst_dentry->d_parent; /* dir inode is locked */
++ if (a->dst_inode) {
++ /*
++ * if EXCHANGE && src is non-dir && dst is dir,
++ * dst is not locked.
++ */
++ /* IMustLock(a->dst_inode); */
++ au_igrab(a->dst_inode);
++ }
+
-+static inline void au_hn_inode_lock(struct au_hinode *hdir)
-+{
-+ inode_lock(hdir->hi_inode);
-+ au_hn_suspend(hdir);
-+}
++ err = -ENOTDIR;
++ lock_flags = AuLock_FLUSH | AuLock_NOPLM | AuLock_GEN;
++ if (d_is_dir(a->src_dentry)) {
++ au_fset_ren(a->auren_flags, ISDIR_SRC);
++ if (unlikely(!a->exchange
++ && d_really_is_positive(a->dst_dentry)
++ && !d_is_dir(a->dst_dentry)))
++ goto out_free;
++ lock_flags |= AuLock_DIRS;
++ }
++ if (a->dst_inode && d_is_dir(a->dst_dentry)) {
++ au_fset_ren(a->auren_flags, ISDIR_DST);
++ if (unlikely(!a->exchange
++ && d_really_is_positive(a->src_dentry)
++ && !d_is_dir(a->src_dentry)))
++ goto out_free;
++ lock_flags |= AuLock_DIRS;
++ }
++ err = aufs_read_and_write_lock2(a->dst_dentry, a->src_dentry,
++ lock_flags);
++ if (unlikely(err))
++ goto out_free;
+
-+static inline void au_hn_inode_lock_nested(struct au_hinode *hdir,
-+ unsigned int sc __maybe_unused)
-+{
-+ inode_lock_nested(hdir->hi_inode, sc);
-+ au_hn_suspend(hdir);
-+}
++ err = au_d_hashed_positive(a->src_dentry);
++ if (unlikely(err))
++ goto out_unlock;
++ err = -ENOENT;
++ if (a->dst_inode) {
++ /*
++ * If it is a dir, VFS unhash it before this
++ * function. It means we cannot rely upon d_unhashed().
++ */
++ if (unlikely(!a->dst_inode->i_nlink))
++ goto out_unlock;
++ if (!au_ftest_ren(a->auren_flags, ISDIR_DST)) {
++ err = au_d_hashed_positive(a->dst_dentry);
++ if (unlikely(err && !a->exchange))
++ goto out_unlock;
++ } else if (unlikely(IS_DEADDIR(a->dst_inode)))
++ goto out_unlock;
++ } else if (unlikely(d_unhashed(a->dst_dentry)))
++ goto out_unlock;
+
-+#if 0 /* unused */
-+#include "vfsub.h"
-+static inline void au_hn_inode_lock_shared_nested(struct au_hinode *hdir,
-+ unsigned int sc)
-+{
-+ inode_lock_shared_nested(hdir->hi_inode, sc);
-+ au_hn_suspend(hdir);
-+}
-+#endif
++ /*
++ * is it possible?
++ * yes, it happened (in linux-3.3-rcN) but I don't know why.
++ * there may exist a problem somewhere else.
++ */
++ err = -EINVAL;
++ if (unlikely(d_inode(a->dst_parent) == d_inode(a->src_dentry)))
++ goto out_unlock;
+
-+static inline void au_hn_inode_unlock(struct au_hinode *hdir)
-+{
-+ au_hn_resume(hdir);
-+ inode_unlock(hdir->hi_inode);
-+}
++ au_fset_ren(a->auren_flags, ISSAMEDIR); /* temporary */
++ di_write_lock_parent(a->dst_parent);
+
-+#endif /* __KERNEL__ */
-+#endif /* __AUFS_INODE_H__ */
-diff --git a/fs/aufs/ioctl.c b/fs/aufs/ioctl.c
-new file mode 100644
-index 00000000000000..2d8d91084099f9
---- /dev/null
-+++ b/fs/aufs/ioctl.c
-@@ -0,0 +1,220 @@
-+// SPDX-License-Identifier: GPL-2.0
-+/*
-+ * Copyright (C) 2005-2022 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/>.
-+ */
++ /* which branch we process */
++ err = au_ren_wbr(a);
++ if (unlikely(err < 0))
++ goto out_parent;
++ a->br = au_sbr(a->dst_dentry->d_sb, a->btgt);
++ a->h_path.mnt = au_br_mnt(a->br);
+
-+/*
-+ * ioctl
-+ * plink-management and readdir in userspace.
-+ * assist the pathconf(3) wrapper library.
-+ * move-down
-+ * File-based Hierarchical Storage Management.
-+ */
++ /* are they available to be renamed */
++ err = au_ren_may_dir(a);
++ if (unlikely(err))
++ goto out_children;
+
-+#include <linux/compat.h>
-+#include <linux/file.h>
-+#include "aufs.h"
++ /* prepare the writable parent dir on the same branch */
++ if (a->dst_btop == a->btgt) {
++ au_fset_ren(a->auren_flags, WHDST);
++ } else {
++ err = au_cpup_dirs(a->dst_dentry, a->btgt);
++ if (unlikely(err))
++ goto out_children;
++ }
+
-+static int au_wbr_fd(struct path *path, struct aufs_wbr_fd __user *arg)
-+{
-+ int err, fd;
-+ aufs_bindex_t wbi, bindex, bbot;
-+ struct file *h_file;
-+ struct super_block *sb;
-+ struct dentry *root;
-+ struct au_branch *br;
-+ struct aufs_wbr_fd wbrfd = {
-+ .oflags = au_dir_roflags,
-+ .brid = -1
-+ };
-+ const int valid = O_RDONLY | O_NONBLOCK | O_LARGEFILE | O_DIRECTORY
-+ | O_NOATIME | O_CLOEXEC;
++ err = 0;
++ if (!a->exchange) {
++ if (a->src_dir != a->dst_dir) {
++ /*
++ * this temporary unlock is safe,
++ * because both dir->i_mutex are locked.
++ */
++ di_write_unlock(a->dst_parent);
++ di_write_lock_parent(a->src_parent);
++ err = au_wr_dir_need_wh(a->src_dentry,
++ au_ftest_ren(a->auren_flags,
++ ISDIR_SRC),
++ &a->btgt);
++ di_write_unlock(a->src_parent);
++ di_write_lock2_parent(a->src_parent, a->dst_parent,
++ /*isdir*/1);
++ au_fclr_ren(a->auren_flags, ISSAMEDIR);
++ } else
++ err = au_wr_dir_need_wh(a->src_dentry,
++ au_ftest_ren(a->auren_flags,
++ ISDIR_SRC),
++ &a->btgt);
++ }
++ if (unlikely(err < 0))
++ goto out_children;
++ if (err)
++ au_fset_ren(a->auren_flags, WHSRC);
+
-+ AuDebugOn(wbrfd.oflags & ~valid);
++ /* cpup src */
++ if (a->src_btop != a->btgt) {
++ err = au_pin(&pin, a->src_dentry, a->btgt,
++ au_opt_udba(a->src_dentry->d_sb),
++ AuPin_DI_LOCKED | AuPin_MNT_WRITE);
++ if (!err) {
++ struct au_cp_generic cpg = {
++ .dentry = a->src_dentry,
++ .bdst = a->btgt,
++ .bsrc = a->src_btop,
++ .len = -1,
++ .pin = &pin,
++ .flags = AuCpup_DTIME | AuCpup_HOPEN
++ };
++ AuDebugOn(au_dbtop(a->src_dentry) != a->src_btop);
++ err = au_sio_cpup_simple(&cpg);
++ au_unpin(&pin);
++ }
++ if (unlikely(err))
++ goto out_children;
++ a->src_btop = a->btgt;
++ a->src_h_dentry = au_h_dptr(a->src_dentry, a->btgt);
++ if (!a->exchange)
++ au_fset_ren(a->auren_flags, WHSRC);
++ }
+
-+ if (arg) {
-+ err = copy_from_user(&wbrfd, arg, sizeof(wbrfd));
-+ if (unlikely(err)) {
-+ err = -EFAULT;
-+ goto out;
++ /* cpup dst */
++ if (a->exchange && a->dst_inode
++ && a->dst_btop != a->btgt) {
++ err = au_pin(&pin, a->dst_dentry, a->btgt,
++ au_opt_udba(a->dst_dentry->d_sb),
++ AuPin_DI_LOCKED | AuPin_MNT_WRITE);
++ if (!err) {
++ struct au_cp_generic cpg = {
++ .dentry = a->dst_dentry,
++ .bdst = a->btgt,
++ .bsrc = a->dst_btop,
++ .len = -1,
++ .pin = &pin,
++ .flags = AuCpup_DTIME | AuCpup_HOPEN
++ };
++ err = au_sio_cpup_simple(&cpg);
++ au_unpin(&pin);
+ }
++ if (unlikely(err))
++ goto out_children;
++ a->dst_btop = a->btgt;
++ a->dst_h_dentry = au_h_dptr(a->dst_dentry, a->btgt);
++ }
+
-+ err = -EINVAL;
-+ AuDbg("wbrfd{0%o, %d}\n", wbrfd.oflags, wbrfd.brid);
-+ wbrfd.oflags |= au_dir_roflags;
-+ AuDbg("0%o\n", wbrfd.oflags);
-+ if (unlikely(wbrfd.oflags & ~valid))
-+ goto out;
++ /* lock them all */
++ err = au_ren_lock(a);
++ if (unlikely(err))
++ /* leave the copied-up one */
++ goto out_children;
++
++ if (!a->exchange) {
++ if (!au_opt_test(au_mntflags(a->dst_dir->i_sb), UDBA_NONE))
++ err = au_may_ren(a);
++ else if (unlikely(a->dst_dentry->d_name.len > AUFS_MAX_NAMELEN))
++ err = -ENAMETOOLONG;
++ if (unlikely(err))
++ goto out_hdir;
+ }
+
-+ fd = get_unused_fd_flags(0);
-+ err = fd;
-+ if (unlikely(fd < 0))
-+ goto out;
++ /* store timestamps to be revertible */
++ au_ren_dt(a);
+
-+ h_file = ERR_PTR(-EINVAL);
-+ wbi = 0;
-+ br = NULL;
-+ sb = path->dentry->d_sb;
-+ root = sb->s_root;
-+ aufs_read_lock(root, AuLock_IR);
-+ bbot = au_sbbot(sb);
-+ if (wbrfd.brid >= 0) {
-+ wbi = au_br_index(sb, wbrfd.brid);
-+ if (unlikely(wbi < 0 || wbi > bbot))
-+ goto out_unlock;
++ /* store dirren info */
++ if (au_ftest_ren(a->auren_flags, DIRREN)) {
++ err = au_dr_rename(a->src_dentry, a->btgt,
++ &a->dst_dentry->d_name, &rev);
++ AuTraceErr(err);
++ if (unlikely(err))
++ goto out_dt;
+ }
+
-+ h_file = ERR_PTR(-ENOENT);
-+ br = au_sbr(sb, wbi);
-+ if (!au_br_writable(br->br_perm)) {
-+ if (arg)
-+ goto out_unlock;
++ /* here we go */
++ err = do_rename(a);
++ if (unlikely(err))
++ goto out_dirren;
+
-+ bindex = wbi + 1;
-+ wbi = -1;
-+ for (; bindex <= bbot; bindex++) {
-+ br = au_sbr(sb, bindex);
-+ if (au_br_writable(br->br_perm)) {
-+ wbi = bindex;
-+ br = au_sbr(sb, wbi);
-+ break;
-+ }
-+ }
-+ }
-+ AuDbg("wbi %d\n", wbi);
-+ if (wbi >= 0)
-+ h_file = au_h_open(root, wbi, wbrfd.oflags, NULL,
-+ /*force_wr*/0);
++ if (au_ftest_ren(a->auren_flags, DIRREN))
++ au_dr_rename_fin(a->src_dentry, a->btgt, rev);
+
-+out_unlock:
-+ aufs_read_unlock(root, AuLock_IR);
-+ err = PTR_ERR(h_file);
-+ if (IS_ERR(h_file))
-+ goto out_fd;
++ /* update dir attributes */
++ au_ren_refresh_dir(a);
+
-+ au_lcnt_dec(&br->br_nfiles); /* cf. au_h_open() */
-+ fd_install(fd, h_file);
-+ err = fd;
-+ goto out; /* success */
++ /* dput/iput all lower dentries */
++ au_ren_refresh(a);
+
-+out_fd:
-+ put_unused_fd(fd);
++ goto out_hdir; /* success */
++
++out_dirren:
++ if (au_ftest_ren(a->auren_flags, DIRREN))
++ au_dr_rename_rev(a->src_dentry, a->btgt, rev);
++out_dt:
++ au_ren_rev_dt(err, a);
++out_hdir:
++ au_ren_unlock(a);
++out_children:
++ au_nhash_wh_free(&a->whlist);
++ if (err && a->dst_inode && a->dst_btop != a->btgt) {
++ AuDbg("btop %d, btgt %d\n", a->dst_btop, a->btgt);
++ au_set_h_dptr(a->dst_dentry, a->btgt, NULL);
++ au_set_dbtop(a->dst_dentry, a->dst_btop);
++ }
++out_parent:
++ if (!err) {
++ if (d_unhashed(a->src_dentry))
++ au_fset_ren(a->auren_flags, DROPPED_SRC);
++ if (d_unhashed(a->dst_dentry))
++ au_fset_ren(a->auren_flags, DROPPED_DST);
++ if (!a->exchange)
++ d_move(a->src_dentry, a->dst_dentry);
++ else {
++ d_exchange(a->src_dentry, a->dst_dentry);
++ if (au_ftest_ren(a->auren_flags, DROPPED_DST))
++ d_drop(a->dst_dentry);
++ }
++ if (au_ftest_ren(a->auren_flags, DROPPED_SRC))
++ d_drop(a->src_dentry);
++ } else {
++ au_update_dbtop(a->dst_dentry);
++ if (!a->dst_inode)
++ d_drop(a->dst_dentry);
++ }
++ if (au_ftest_ren(a->auren_flags, ISSAMEDIR))
++ di_write_unlock(a->dst_parent);
++ else
++ di_write_unlock2(a->src_parent, a->dst_parent);
++out_unlock:
++ aufs_read_and_write_unlock2(a->dst_dentry, a->src_dentry);
++out_free:
++ iput(a->dst_inode);
++ if (a->thargs)
++ au_whtmp_rmdir_free(a->thargs);
++ au_kfree_rcu(a);
+out:
+ AuTraceErr(err);
+ return err;
+}
+diff -urN /usr/share/empty/fs/aufs/Kconfig linux/fs/aufs/Kconfig
+--- /usr/share/empty/fs/aufs/Kconfig 1970-01-01 01:00:00.000000000 +0100
++++ linux/fs/aufs/Kconfig 2022-11-05 23:02:18.959222617 +0100
+@@ -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.
+
-+/* ---------------------------------------------------------------------- */
-+
-+long aufs_ioctl_dir(struct file *file, unsigned int cmd, unsigned long arg)
-+{
-+ long err;
-+ struct dentry *dentry;
-+
-+ switch (cmd) {
-+ case AUFS_CTL_RDU:
-+ case AUFS_CTL_RDU_INO:
-+ err = au_rdu_ioctl(file, cmd, arg);
-+ break;
-+
-+ case AUFS_CTL_WBR_FD:
-+ err = au_wbr_fd(&file->f_path, (void __user *)arg);
-+ break;
++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
+
-+ case AUFS_CTL_IBUSY:
-+ err = au_ibusy_ioctl(file, arg);
-+ break;
++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.
+
-+ case AUFS_CTL_BRINFO:
-+ err = au_brinfo_ioctl(file, arg);
-+ break;
++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.
+
-+ case AUFS_CTL_FHSM_FD:
-+ dentry = file->f_path.dentry;
-+ if (IS_ROOT(dentry))
-+ err = au_fhsm_fd(dentry->d_sb, arg);
-+ else
-+ err = -ENOTTY;
-+ break;
++choice
++ prompt "method" if AUFS_HNOTIFY
++ default AUFS_HFSNOTIFY
++config AUFS_HFSNOTIFY
++ bool "fsnotify"
++ select FSNOTIFY
++endchoice
+
-+ default:
-+ /* do not call the lower */
-+ AuDbg("0x%x\n", cmd);
-+ err = -ENOTTY;
-+ }
++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.
+
-+ AuTraceErr(err);
-+ return err;
-+}
++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 */
+
-+long aufs_ioctl_nondir(struct file *file, unsigned int cmd, unsigned long arg)
-+{
-+ long err;
++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.
+
-+ switch (cmd) {
-+ case AUFS_CTL_MVDOWN:
-+ err = au_mvdown(file->f_path.dentry, (void __user *)arg);
-+ break;
++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.
+
-+ case AUFS_CTL_WBR_FD:
-+ err = au_wbr_fd(&file->f_path, (void __user *)arg);
-+ break;
++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.
+
-+ default:
-+ /* do not call the lower */
-+ AuDbg("0x%x\n", cmd);
-+ err = -ENOTTY;
-+ }
++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 information 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.
+
-+ AuTraceErr(err);
-+ return err;
-+}
++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.
+
-+#ifdef CONFIG_COMPAT
-+long aufs_compat_ioctl_dir(struct file *file, unsigned int cmd,
-+ unsigned long arg)
-+{
-+ long err;
++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.
+
-+ switch (cmd) {
-+ case AUFS_CTL_RDU:
-+ case AUFS_CTL_RDU_INO:
-+ err = au_rdu_compat_ioctl(file, cmd, arg);
-+ break;
++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).
+
-+ case AUFS_CTL_IBUSY:
-+ err = au_ibusy_compat_ioctl(file, arg);
-+ break;
++config AUFS_POLL
++ bool
++ help
++ Automatic configuration for internal use.
+
-+ case AUFS_CTL_BRINFO:
-+ err = au_brinfo_compat_ioctl(file, arg);
-+ break;
++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.
+
-+ default:
-+ err = aufs_ioctl_dir(file, cmd, arg);
-+ }
++config AUFS_BDEV_LOOP
++ bool
++ depends on BLK_DEV_LOOP
++ default y
++ help
++ Automatic configuration for internal use.
++ Convert =[ym] into =y.
+
-+ AuTraceErr(err);
-+ return err;
-+}
++config AUFS_DEBUG
++ bool "Debug aufs"
++ help
++ Enable this to compile aufs internal debug code.
++ It will have a negative impact to the performance.
+
-+long aufs_compat_ioctl_nondir(struct file *file, unsigned int cmd,
-+ unsigned long arg)
-+{
-+ return aufs_ioctl_nondir(file, cmd, (unsigned long)compat_ptr(arg));
-+}
-+#endif
-diff --git a/fs/aufs/lcnt.h b/fs/aufs/lcnt.h
-new file mode 100644
-index 00000000000000..6dc37108565fa2
---- /dev/null
-+++ b/fs/aufs/lcnt.h
++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 -urN /usr/share/empty/fs/aufs/lcnt.h linux/fs/aufs/lcnt.h
+--- /usr/share/empty/fs/aufs/lcnt.h 1970-01-01 01:00:00.000000000 +0100
++++ linux/fs/aufs/lcnt.h 2022-11-05 23:02:18.965889284 +0100
@@ -0,0 +1,186 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+
+#endif /* __KERNEL__ */
+#endif /* __AUFS_LCNT_H__ */
-diff --git a/fs/aufs/loop.c b/fs/aufs/loop.c
-new file mode 100644
-index 00000000000000..38319058859501
---- /dev/null
-+++ b/fs/aufs/loop.c
+diff -urN /usr/share/empty/fs/aufs/loop.c linux/fs/aufs/loop.c
+--- /usr/share/empty/fs/aufs/loop.c 1970-01-01 01:00:00.000000000 +0100
++++ linux/fs/aufs/loop.c 2022-11-05 23:02:18.965889284 +0100
@@ -0,0 +1,148 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ symbol_put(loop_backing_file);
+ au_kfree_try_rcu(au_warn_loopback_array);
+}
-diff --git a/fs/aufs/loop.h b/fs/aufs/loop.h
-new file mode 100644
-index 00000000000000..9726b8354e00db
---- /dev/null
-+++ b/fs/aufs/loop.h
+diff -urN /usr/share/empty/fs/aufs/loop.h linux/fs/aufs/loop.h
+--- /usr/share/empty/fs/aufs/loop.h 1970-01-01 01:00:00.000000000 +0100
++++ linux/fs/aufs/loop.h 2022-11-05 23:02:18.965889284 +0100
@@ -0,0 +1,55 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+
+#endif /* __KERNEL__ */
+#endif /* __AUFS_LOOP_H__ */
-diff --git a/fs/aufs/magic.mk b/fs/aufs/magic.mk
-new file mode 100644
-index 00000000000000..7bc9eef3ffec55
---- /dev/null
-+++ b/fs/aufs/magic.mk
+diff -urN /usr/share/empty/fs/aufs/magic.mk linux/fs/aufs/magic.mk
+--- /usr/share/empty/fs/aufs/magic.mk 1970-01-01 01:00:00.000000000 +0100
++++ linux/fs/aufs/magic.mk 2022-11-05 23:02:18.965889284 +0100
@@ -0,0 +1,31 @@
+# SPDX-License-Identifier: GPL-2.0
+
+ifdef CONFIG_HFSPLUS_FS
+ccflags-y += -DHFSPLUS_SUPER_MAGIC=0x482b
+endif
-diff --git a/fs/aufs/module.c b/fs/aufs/module.c
-new file mode 100644
-index 00000000000000..c2815fffb5c6ae
---- /dev/null
-+++ b/fs/aufs/module.c
+diff -urN /usr/share/empty/fs/aufs/Makefile linux/fs/aufs/Makefile
+--- /usr/share/empty/fs/aufs/Makefile 1970-01-01 01:00:00.000000000 +0100
++++ linux/fs/aufs/Makefile 2022-11-05 23:02:18.959222617 +0100
+@@ -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 fsctx.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 -urN /usr/share/empty/fs/aufs/module.c linux/fs/aufs/module.c
+--- /usr/share/empty/fs/aufs/module.c 1970-01-01 01:00:00.000000000 +0100
++++ linux/fs/aufs/module.c 2022-11-05 23:02:18.965889284 +0100
@@ -0,0 +1,273 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+
+module_init(aufs_init);
+module_exit(aufs_exit);
-diff --git a/fs/aufs/module.h b/fs/aufs/module.h
-new file mode 100644
-index 00000000000000..a9d21d3e5414ea
---- /dev/null
-+++ b/fs/aufs/module.h
+diff -urN /usr/share/empty/fs/aufs/module.h linux/fs/aufs/module.h
+--- /usr/share/empty/fs/aufs/module.h 1970-01-01 01:00:00.000000000 +0100
++++ linux/fs/aufs/module.h 2022-11-05 23:02:18.969222617 +0100
@@ -0,0 +1,180 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+
+#endif /* __KERNEL__ */
+#endif /* __AUFS_MODULE_H__ */
-diff --git a/fs/aufs/mvdown.c b/fs/aufs/mvdown.c
-new file mode 100644
-index 00000000000000..daafc27e64b0aa
---- /dev/null
-+++ b/fs/aufs/mvdown.c
-@@ -0,0 +1,706 @@
+diff -urN /usr/share/empty/fs/aufs/mvdown.c linux/fs/aufs/mvdown.c
+--- /usr/share/empty/fs/aufs/mvdown.c 1970-01-01 01:00:00.000000000 +0100
++++ linux/fs/aufs/mvdown.c 2024-03-10 23:40:47.086476782 +0100
+@@ -0,0 +1,713 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2011-2022 Junjiro R. Okajima
+ au_pin_hdir_unlock(&a->mvd_pin_src);
+ h_trap = vfsub_lock_rename(a->mvd_h_src_parent, a->mvd_hdir_src,
+ a->mvd_h_dst_parent, a->mvd_hdir_dst);
++ if (IS_ERR(h_trap)) {
++ err = PTR_ERR(h_trap);
++ au_pin_hdir_lock(&a->mvd_pin_src);
++ au_unpin(&a->mvd_pin_src);
++ au_pin_hdir_lock(&a->mvd_pin_dst);
++ goto out_dst;
++ }
+ if (h_trap) {
+ err = (h_trap != a->mvd_h_src_parent);
+ if (err)
+ AuTraceErr(err);
+ return err;
+}
-diff --git a/fs/aufs/opts.c b/fs/aufs/opts.c
-new file mode 100644
-index 00000000000000..20421440c00417
---- /dev/null
-+++ b/fs/aufs/opts.c
+diff -urN /usr/share/empty/fs/aufs/opts.c linux/fs/aufs/opts.c
+--- /usr/share/empty/fs/aufs/opts.c 1970-01-01 01:00:00.000000000 +0100
++++ linux/fs/aufs/opts.c 2024-03-10 23:40:47.086476782 +0100
@@ -0,0 +1,1032 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ case Opt_prepend:
+ opt->add.bindex = 0;
+ fallthrough;
-+ add: /* indented label */
+ case Opt_add:
++ add: /* indented label */
+ err = au_br_add(sb, &opt->add,
+ au_ftest_opts(opts->flags, REMOUNT));
+ if (!err) {
+{
+ return au_mntflags(sb) & AuOptMask_UDBA;
+}
-diff --git a/fs/aufs/opts.h b/fs/aufs/opts.h
-new file mode 100644
-index 00000000000000..d8bbdbf0560ae9
---- /dev/null
-+++ b/fs/aufs/opts.h
+diff -urN /usr/share/empty/fs/aufs/opts.h linux/fs/aufs/opts.h
+--- /usr/share/empty/fs/aufs/opts.h 1970-01-01 01:00:00.000000000 +0100
++++ linux/fs/aufs/opts.h 2024-03-10 23:40:47.086476782 +0100
@@ -0,0 +1,263 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+/* ---------------------------------------------------------------------- */
+
+/* mount flags */
-+#define AuOpt_XINO 1 /* external inode number bitmap
++#define AuOpt_XINO BIT(0) /* external inode number bitmap
+ and translation table */
-+#define AuOpt_TRUNC_XINO (1 << 1) /* truncate xino files */
-+#define AuOpt_UDBA_NONE (1 << 2) /* users direct branch access */
-+#define AuOpt_UDBA_REVAL (1 << 3)
-+#define AuOpt_UDBA_HNOTIFY (1 << 4)
-+#define AuOpt_SHWH (1 << 5) /* show whiteout */
-+#define AuOpt_PLINK (1 << 6) /* pseudo-link */
-+#define AuOpt_DIRPERM1 (1 << 7) /* ignore the lower dir's perm
++#define AuOpt_TRUNC_XINO BIT(1) /* truncate xino files */
++#define AuOpt_UDBA_NONE BIT(2) /* users direct branch access */
++#define AuOpt_UDBA_REVAL BIT(3)
++#define AuOpt_UDBA_HNOTIFY BIT(4)
++#define AuOpt_SHWH BIT(5) /* show whiteout */
++#define AuOpt_PLINK BIT(6) /* pseudo-link */
++#define AuOpt_DIRPERM1 BIT(7) /* ignore the lower dir's perm
+ bits */
-+#define AuOpt_ALWAYS_DIROPQ (1 << 9) /* policy to creating diropq */
-+#define AuOpt_SUM (1 << 10) /* summation for statfs(2) */
-+#define AuOpt_SUM_W (1 << 11) /* unimplemented */
-+#define AuOpt_WARN_PERM (1 << 12) /* warn when add-branch */
-+#define AuOpt_VERBOSE (1 << 13) /* print the cause of error */
-+#define AuOpt_DIO (1 << 14) /* direct io */
-+#define AuOpt_DIRREN (1 << 15) /* directory rename */
++#define AuOpt_ALWAYS_DIROPQ BIT(8) /* policy to creating diropq */
++#define AuOpt_SUM BIT(9) /* summation for statfs(2) */
++#define AuOpt_SUM_W BIT(10) /* unimplemented */
++#define AuOpt_WARN_PERM BIT(11) /* warn when add-branch */
++#define AuOpt_VERBOSE BIT(12) /* print the cause of error */
++#define AuOpt_DIO BIT(13) /* direct io */
++#define AuOpt_DIRREN BIT(14) /* directory rename */
+
+#ifndef CONFIG_AUFS_HNOTIFY
+#undef AuOpt_UDBA_HNOTIFY
+};
+
+/* opts flags */
-+#define AuOpts_REMOUNT 1
-+#define AuOpts_REFRESH (1 << 1)
-+#define AuOpts_TRUNC_XIB (1 << 2)
-+#define AuOpts_REFRESH_DYAOP (1 << 3)
-+#define AuOpts_REFRESH_IDOP (1 << 4)
-+#define AuOpts_DR_FLUSHED (1 << 5)
++#define AuOpts_REMOUNT BIT(0)
++#define AuOpts_REFRESH BIT(1)
++#define AuOpts_TRUNC_XIB BIT(2)
++#define AuOpts_REFRESH_DYAOP BIT(3)
++#define AuOpts_REFRESH_IDOP BIT(4)
++#define AuOpts_DR_FLUSHED BIT(5)
+#define au_ftest_opts(flags, name) ((flags) & AuOpts_##name)
+#define au_fset_opts(flags, name) \
+ do { (flags) |= AuOpts_##name; } while (0)
+
+#endif /* __KERNEL__ */
+#endif /* __AUFS_OPTS_H__ */
-diff --git a/fs/aufs/plink.c b/fs/aufs/plink.c
-new file mode 100644
-index 00000000000000..5f9a5b50dcc6ba
---- /dev/null
-+++ b/fs/aufs/plink.c
+diff -urN /usr/share/empty/fs/aufs/plink.c linux/fs/aufs/plink.c
+--- /usr/share/empty/fs/aufs/plink.c 1970-01-01 01:00:00.000000000 +0100
++++ linux/fs/aufs/plink.c 2022-11-05 23:02:18.969222617 +0100
@@ -0,0 +1,516 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ }
+ }
+}
-diff --git a/fs/aufs/poll.c b/fs/aufs/poll.c
-new file mode 100644
-index 00000000000000..83defa454c8e18
---- /dev/null
-+++ b/fs/aufs/poll.c
+diff -urN /usr/share/empty/fs/aufs/poll.c linux/fs/aufs/poll.c
+--- /usr/share/empty/fs/aufs/poll.c 1970-01-01 01:00:00.000000000 +0100
++++ linux/fs/aufs/poll.c 2022-11-05 23:02:18.969222617 +0100
@@ -0,0 +1,51 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ AuDbg("mask 0x%x\n", mask);
+ return mask;
+}
-diff --git a/fs/aufs/posix_acl.c b/fs/aufs/posix_acl.c
-new file mode 100644
-index 00000000000000..03742bcc66035e
---- /dev/null
-+++ b/fs/aufs/posix_acl.c
+diff -urN /usr/share/empty/fs/aufs/posix_acl.c linux/fs/aufs/posix_acl.c
+--- /usr/share/empty/fs/aufs/posix_acl.c 1970-01-01 01:00:00.000000000 +0100
++++ linux/fs/aufs/posix_acl.c 2023-10-31 09:31:04.199880750 +0100
@@ -0,0 +1,108 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+
+ return err;
+}
-diff --git a/fs/aufs/procfs.c b/fs/aufs/procfs.c
-new file mode 100644
-index 00000000000000..0fca104ac554b3
---- /dev/null
-+++ b/fs/aufs/procfs.c
+diff -urN /usr/share/empty/fs/aufs/procfs.c linux/fs/aufs/procfs.c
+--- /usr/share/empty/fs/aufs/procfs.c 1970-01-01 01:00:00.000000000 +0100
++++ linux/fs/aufs/procfs.c 2022-11-05 23:02:18.969222617 +0100
@@ -0,0 +1,170 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+out:
+ return err;
+}
-diff --git a/fs/aufs/rdu.c b/fs/aufs/rdu.c
-new file mode 100644
-index 00000000000000..144251c02c3f31
---- /dev/null
-+++ b/fs/aufs/rdu.c
+diff -urN /usr/share/empty/fs/aufs/rdu.c linux/fs/aufs/rdu.c
+--- /usr/share/empty/fs/aufs/rdu.c 1970-01-01 01:00:00.000000000 +0100
++++ linux/fs/aufs/rdu.c 2024-03-10 23:40:47.086476782 +0100
@@ -0,0 +1,384 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+#include "aufs.h"
+
+/* bits for struct aufs_rdu.flags */
-+#define AuRdu_CALLED 1
-+#define AuRdu_CONT (1 << 1)
-+#define AuRdu_FULL (1 << 2)
++#define AuRdu_CALLED BIT(0)
++#define AuRdu_CONT BIT(1)
++#define AuRdu_FULL BIT(2)
+#define au_ftest_rdu(flags, name) ((flags) & AuRdu_##name)
+#define au_fset_rdu(flags, name) \
+ do { (flags) |= AuRdu_##name; } while (0)
+ return err;
+}
+#endif
-diff --git a/fs/aufs/rwsem.h b/fs/aufs/rwsem.h
-new file mode 100644
-index 00000000000000..9d9cd50ef15587
---- /dev/null
-+++ b/fs/aufs/rwsem.h
+diff -urN /usr/share/empty/fs/aufs/rwsem.h linux/fs/aufs/rwsem.h
+--- /usr/share/empty/fs/aufs/rwsem.h 1970-01-01 01:00:00.000000000 +0100
++++ linux/fs/aufs/rwsem.h 2022-11-05 23:02:18.969222617 +0100
@@ -0,0 +1,85 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+
+#endif /* __KERNEL__ */
+#endif /* __AUFS_RWSEM_H__ */
-diff --git a/fs/aufs/sbinfo.c b/fs/aufs/sbinfo.c
-new file mode 100644
-index 00000000000000..dde9f9c17b18db
---- /dev/null
-+++ b/fs/aufs/sbinfo.c
+diff -urN /usr/share/empty/fs/aufs/sbinfo.c linux/fs/aufs/sbinfo.c
+--- /usr/share/empty/fs/aufs/sbinfo.c 1970-01-01 01:00:00.000000000 +0100
++++ linux/fs/aufs/sbinfo.c 2022-11-05 23:02:18.969222617 +0100
@@ -0,0 +1,316 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ di_write_unlock2(d1, d2);
+ si_read_unlock(d1->d_sb);
+}
-diff --git a/fs/aufs/super.c b/fs/aufs/super.c
-new file mode 100644
-index 00000000000000..77c6d90808bb3f
---- /dev/null
-+++ b/fs/aufs/super.c
+diff -urN /usr/share/empty/fs/aufs/super.c linux/fs/aufs/super.c
+--- /usr/share/empty/fs/aufs/super.c 1970-01-01 01:00:00.000000000 +0100
++++ linux/fs/aufs/super.c 2023-10-10 22:51:18.033248030 +0200
@@ -0,0 +1,871 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ /* no need to __module_get() and module_put(). */
+ .owner = THIS_MODULE,
+};
-diff --git a/fs/aufs/super.h b/fs/aufs/super.h
-new file mode 100644
-index 00000000000000..f1d9aedcbca4f3
---- /dev/null
-+++ b/fs/aufs/super.h
+diff -urN /usr/share/empty/fs/aufs/super.h linux/fs/aufs/super.h
+--- /usr/share/empty/fs/aufs/super.h 1970-01-01 01:00:00.000000000 +0100
++++ linux/fs/aufs/super.h 2024-03-10 23:40:47.086476782 +0100
@@ -0,0 +1,592 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ int (*copyup)(struct dentry *dentry);
+};
+
-+#define AuWbr_DIR 1 /* target is a dir */
-+#define AuWbr_PARENT (1 << 1) /* always require a parent */
++#define AuWbr_DIR BIT(0) /* target is a dir */
++#define AuWbr_PARENT BIT(1) /* always require a parent */
+
+#define au_ftest_wbr(flags, name) ((flags) & AuWbr_##name)
+#define au_fset_wbr(flags, name) { (flags) |= AuWbr_##name; }
+ * then try refreshing dirs at access time again.
+ * if it is false, refreshing dirs at access time is unnecessary
+ */
-+#define AuSi_FAILED_REFRESH_DIR 1
-+#define AuSi_FHSM (1 << 1) /* fhsm is active now */
-+#define AuSi_NO_DREVAL (1 << 2) /* disable all d_revalidate */
++#define AuSi_FAILED_REFRESH_DIR BIT(0)
++#define AuSi_FHSM BIT(1) /* fhsm is active now */
++#define AuSi_NO_DREVAL BIT(2) /* disable all d_revalidate */
+
+#ifndef CONFIG_AUFS_FHSM
+#undef AuSi_FHSM
+ ((sbinfo)->si_wbr_create_ops->create(__VA_ARGS__))
+
+/* flags for si_read_lock()/aufs_read_lock()/di_read_lock() */
-+#define AuLock_DW 1 /* write-lock dentry */
-+#define AuLock_IR (1 << 1) /* read-lock inode */
-+#define AuLock_IW (1 << 2) /* write-lock inode */
-+#define AuLock_FLUSH (1 << 3) /* wait for 'nowait' tasks */
-+#define AuLock_DIRS (1 << 4) /* target is a pair of dirs */
++#define AuLock_DW BIT(0) /* write-lock dentry */
++#define AuLock_IR BIT(1) /* read-lock inode */
++#define AuLock_IW BIT(2) /* write-lock inode */
++#define AuLock_FLUSH BIT(3) /* wait for 'nowait' tasks */
++#define AuLock_DIRS BIT(4) /* target is a pair of dirs */
+ /* except RENAME_EXCHANGE */
-+#define AuLock_NOPLM (1 << 5) /* return err in plm mode */
-+#define AuLock_NOPLMW (1 << 6) /* wait for plm mode ends */
-+#define AuLock_GEN (1 << 7) /* test digen/iigen */
++#define AuLock_NOPLM BIT(5) /* return err in plm mode */
++#define AuLock_NOPLMW BIT(6) /* wait for plm mode ends */
++#define AuLock_GEN BIT(7) /* test digen/iigen */
+#define au_ftest_lock(flags, name) ((flags) & AuLock_##name)
+#define au_fset_lock(flags, name) \
+ do { (flags) |= AuLock_##name; } while (0)
+
+#endif /* __KERNEL__ */
+#endif /* __AUFS_SUPER_H__ */
-diff --git a/fs/aufs/sysaufs.c b/fs/aufs/sysaufs.c
-new file mode 100644
-index 00000000000000..ab109d55040c31
---- /dev/null
-+++ b/fs/aufs/sysaufs.c
+diff -urN /usr/share/empty/fs/aufs/sysaufs.c linux/fs/aufs/sysaufs.c
+--- /usr/share/empty/fs/aufs/sysaufs.c 1970-01-01 01:00:00.000000000 +0100
++++ linux/fs/aufs/sysaufs.c 2023-10-10 22:51:18.033248030 +0200
@@ -0,0 +1,94 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+out:
+ return err;
+}
-diff --git a/fs/aufs/sysaufs.h b/fs/aufs/sysaufs.h
-new file mode 100644
-index 00000000000000..3f7efd4510be61
---- /dev/null
-+++ b/fs/aufs/sysaufs.h
+diff -urN /usr/share/empty/fs/aufs/sysaufs.h linux/fs/aufs/sysaufs.h
+--- /usr/share/empty/fs/aufs/sysaufs.h 1970-01-01 01:00:00.000000000 +0100
++++ linux/fs/aufs/sysaufs.h 2022-11-05 23:02:18.969222617 +0100
@@ -0,0 +1,102 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+
+#endif /* __KERNEL__ */
+#endif /* __SYSAUFS_H__ */
-diff --git a/fs/aufs/sysfs.c b/fs/aufs/sysfs.c
-new file mode 100644
-index 00000000000000..4e8a4cfa9faa22
---- /dev/null
-+++ b/fs/aufs/sysfs.c
+diff -urN /usr/share/empty/fs/aufs/sysfs.c linux/fs/aufs/sysfs.c
+--- /usr/share/empty/fs/aufs/sysfs.c 1970-01-01 01:00:00.000000000 +0100
++++ linux/fs/aufs/sysfs.c 2022-11-05 23:02:18.969222617 +0100
@@ -0,0 +1,374 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ }
+ }
+}
-diff --git a/fs/aufs/sysrq.c b/fs/aufs/sysrq.c
-new file mode 100644
-index 00000000000000..c03d87e414c50f
---- /dev/null
-+++ b/fs/aufs/sysrq.c
+diff -urN /usr/share/empty/fs/aufs/sysrq.c linux/fs/aufs/sysrq.c
+--- /usr/share/empty/fs/aufs/sysrq.c 1970-01-01 01:00:00.000000000 +0100
++++ linux/fs/aufs/sysrq.c 2023-10-31 09:31:04.199880750 +0100
@@ -0,0 +1,149 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ if (unlikely(err))
+ pr_err("err %d (ignored)\n", err);
+}
-diff --git a/fs/aufs/vdir.c b/fs/aufs/vdir.c
-new file mode 100644
-index 00000000000000..fdf7644049c5d2
---- /dev/null
-+++ b/fs/aufs/vdir.c
+diff -urN /usr/share/empty/fs/aufs/vdir.c linux/fs/aufs/vdir.c
+--- /usr/share/empty/fs/aufs/vdir.c 1970-01-01 01:00:00.000000000 +0100
++++ linux/fs/aufs/vdir.c 2024-03-10 23:40:47.086476782 +0100
@@ -0,0 +1,896 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+
+/* ---------------------------------------------------------------------- */
+
-+#define AuFillVdir_CALLED 1
-+#define AuFillVdir_WHABLE (1 << 1)
-+#define AuFillVdir_SHWH (1 << 2)
++#define AuFillVdir_CALLED BIT(0)
++#define AuFillVdir_WHABLE BIT(1)
++#define AuFillVdir_SHWH BIT(2)
+#define au_ftest_fillvdir(flags, name) ((flags) & AuFillVdir_##name)
+#define au_fset_fillvdir(flags, name) \
+ do { (flags) |= AuFillVdir_##name; } while (0)
+ /* smp_mb(); */
+ return 0;
+}
-diff --git a/fs/aufs/vfsub.c b/fs/aufs/vfsub.c
-new file mode 100644
-index 00000000000000..2fb5f1ac0b31c6
---- /dev/null
-+++ b/fs/aufs/vfsub.c
-@@ -0,0 +1,918 @@
+diff -urN /usr/share/empty/fs/aufs/vfsub.c linux/fs/aufs/vfsub.c
+--- /usr/share/empty/fs/aufs/vfsub.c 1970-01-01 01:00:00.000000000 +0100
++++ linux/fs/aufs/vfsub.c 2024-03-10 23:40:47.086476782 +0100
+@@ -0,0 +1,921 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2005-2022 Junjiro R. Okajima
+ lockdep_off();
+ d = lock_rename(d1, d2);
+ lockdep_on();
++ if (IS_ERR(d))
++ goto out;
+ au_hn_suspend(hdir1);
+ if (hdir1 != hdir2)
+ au_hn_suspend(hdir2);
+
++out:
+ return d;
+}
+
+ return err;
+}
+
-+long vfsub_splice_read(struct file *in, loff_t *ppos,
-+ struct pipe_inode_info *pipe, size_t len,
-+ unsigned int flags)
++ssize_t vfsub_splice_read(struct file *in, loff_t *ppos,
++ struct pipe_inode_info *pipe, size_t len,
++ unsigned int flags)
+{
-+ long err;
++ ssize_t err;
+
+ lockdep_off();
+ err = vfs_splice_read(in, ppos, pipe, len, flags);
+ return err;
+}
+
-+long vfsub_splice_from(struct pipe_inode_info *pipe, struct file *out,
-+ loff_t *ppos, size_t len, unsigned int flags)
++ssize_t vfsub_splice_from(struct pipe_inode_info *pipe, struct file *out,
++ loff_t *ppos, size_t len, unsigned int flags)
+{
-+ long err;
++ ssize_t err;
+
+ lockdep_off();
+ err = do_splice_from(pipe, out, ppos, len, flags);
+
+ return err;
+}
-diff --git a/fs/aufs/vfsub.h b/fs/aufs/vfsub.h
-new file mode 100644
-index 00000000000000..ed218d95770d0c
---- /dev/null
-+++ b/fs/aufs/vfsub.h
-@@ -0,0 +1,403 @@
+diff -urN /usr/share/empty/fs/aufs/vfsub.h linux/fs/aufs/vfsub.h
+--- /usr/share/empty/fs/aufs/vfsub.h 1970-01-01 01:00:00.000000000 +0100
++++ linux/fs/aufs/vfsub.h 2024-03-10 23:40:47.086476782 +0100
+@@ -0,0 +1,402 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2005-2022 Junjiro R. Okajima
+
+/* copied from linux/fs/internal.h */
+/* todo: BAD approach!! */
-+extern void __mnt_drop_write(struct vfsmount *);
+extern struct file *alloc_empty_file(int, const struct cred *);
+
+/* ---------------------------------------------------------------------- */
+ struct dentry *h_dentry, umode_t h_mode);
+#endif
+
-+long vfsub_splice_read(struct file *in, loff_t *ppos,
-+ struct pipe_inode_info *pipe, size_t len,
-+ unsigned int flags);
-+long vfsub_splice_from(struct pipe_inode_info *pipe, struct file *out,
-+ loff_t *ppos, size_t len, unsigned int flags);
++ssize_t vfsub_splice_read(struct file *in, loff_t *ppos,
++ struct pipe_inode_info *pipe, size_t len,
++ unsigned int flags);
++ssize_t vfsub_splice_from(struct pipe_inode_info *pipe, struct file *out,
++ loff_t *ppos, size_t len, unsigned int flags);
+
+static inline long vfsub_truncate(struct path *path, loff_t length)
+{
+
+#endif /* __KERNEL__ */
+#endif /* __AUFS_VFSUB_H__ */
-diff --git a/fs/aufs/wbr_policy.c b/fs/aufs/wbr_policy.c
-new file mode 100644
-index 00000000000000..c726f96b7bd538
---- /dev/null
-+++ b/fs/aufs/wbr_policy.c
+diff -urN /usr/share/empty/fs/aufs/wbr_policy.c linux/fs/aufs/wbr_policy.c
+--- /usr/share/empty/fs/aufs/wbr_policy.c 1970-01-01 01:00:00.000000000 +0100
++++ linux/fs/aufs/wbr_policy.c 2024-03-10 23:40:47.086476782 +0100
@@ -0,0 +1,830 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ return err;
+}
+
-+#define AuCpdown_PARENT_OPQ 1
-+#define AuCpdown_WHED (1 << 1)
-+#define AuCpdown_MADE_DIR (1 << 2)
-+#define AuCpdown_DIROPQ (1 << 3)
++#define AuCpdown_PARENT_OPQ BIT(0)
++#define AuCpdown_WHED BIT(1)
++#define AuCpdown_MADE_DIR BIT(2)
++#define AuCpdown_DIROPQ BIT(3)
+#define au_ftest_cpdown(flags, name) ((flags) & AuCpdown_##name)
+#define au_fset_cpdown(flags, name) \
+ do { (flags) |= AuCpdown_##name; } while (0)
+ .fin = au_wbr_create_fin_mfs
+ }
+};
-diff --git a/fs/aufs/whout.c b/fs/aufs/whout.c
-new file mode 100644
-index 00000000000000..7bd0392eeb875e
---- /dev/null
-+++ b/fs/aufs/whout.c
+diff -urN /usr/share/empty/fs/aufs/whout.c linux/fs/aufs/whout.c
+--- /usr/share/empty/fs/aufs/whout.c 1970-01-01 01:00:00.000000000 +0100
++++ linux/fs/aufs/whout.c 2023-10-31 09:31:04.199880750 +0100
@@ -0,0 +1,1072 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ au_whtmp_rmdir_free(args);
+ }
+}
-diff --git a/fs/aufs/whout.h b/fs/aufs/whout.h
-new file mode 100644
-index 00000000000000..a7ae8702e7a5cb
---- /dev/null
-+++ b/fs/aufs/whout.h
+diff -urN /usr/share/empty/fs/aufs/whout.h linux/fs/aufs/whout.h
+--- /usr/share/empty/fs/aufs/whout.h 1970-01-01 01:00:00.000000000 +0100
++++ linux/fs/aufs/whout.h 2023-10-31 09:31:04.199880750 +0100
@@ -0,0 +1,87 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+
+#endif /* __KERNEL__ */
+#endif /* __AUFS_WHOUT_H__ */
-diff --git a/fs/aufs/wkq.c b/fs/aufs/wkq.c
-new file mode 100644
-index 00000000000000..cb71ca3bf51b79
---- /dev/null
-+++ b/fs/aufs/wkq.c
+diff -urN /usr/share/empty/fs/aufs/wkq.c linux/fs/aufs/wkq.c
+--- /usr/share/empty/fs/aufs/wkq.c 1970-01-01 01:00:00.000000000 +0100
++++ linux/fs/aufs/wkq.c 2022-11-05 23:02:18.972555950 +0100
@@ -0,0 +1,372 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+
+ return err;
+}
-diff --git a/fs/aufs/wkq.h b/fs/aufs/wkq.h
-new file mode 100644
-index 00000000000000..f8bb8e12395ed5
---- /dev/null
-+++ b/fs/aufs/wkq.h
+diff -urN /usr/share/empty/fs/aufs/wkq.h linux/fs/aufs/wkq.h
+--- /usr/share/empty/fs/aufs/wkq.h 1970-01-01 01:00:00.000000000 +0100
++++ linux/fs/aufs/wkq.h 2024-03-10 23:40:47.086476782 +0100
@@ -0,0 +1,89 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+typedef void (*au_wkq_func_t)(void *args);
+
+/* wkq flags */
-+#define AuWkq_WAIT 1
-+#define AuWkq_NEST (1 << 1)
++#define AuWkq_WAIT BIT(0)
++#define AuWkq_NEST BIT(1)
+#define au_ftest_wkq(flags, name) ((flags) & AuWkq_##name)
+#define au_fset_wkq(flags, name) \
+ do { (flags) |= AuWkq_##name; } while (0)
+
+#endif /* __KERNEL__ */
+#endif /* __AUFS_WKQ_H__ */
-diff --git a/fs/aufs/xattr.c b/fs/aufs/xattr.c
-new file mode 100644
-index 00000000000000..9e08665728aeed
---- /dev/null
-+++ b/fs/aufs/xattr.c
+diff -urN /usr/share/empty/fs/aufs/xattr.c linux/fs/aufs/xattr.c
+--- /usr/share/empty/fs/aufs/xattr.c 1970-01-01 01:00:00.000000000 +0100
++++ linux/fs/aufs/xattr.c 2024-03-10 23:40:47.086476782 +0100
@@ -0,0 +1,360 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ if (is_acl) {
+ acl = vfs_get_acl(h_src_idmap, h_src_dentry, name);
+ AuDebugOn(!acl);
-+ if (unlikely(IS_ERR(acl))) {
++ if (IS_ERR(acl)) {
+ err = PTR_ERR(acl);
+ if (err == -ENODATA)
+ err = 0;
+{
+ sb->s_xattr = au_xattr_handlers;
+}
-diff --git a/fs/aufs/xino.c b/fs/aufs/xino.c
-new file mode 100644
-index 00000000000000..e1db09b3541d1b
---- /dev/null
-+++ b/fs/aufs/xino.c
+diff -urN /usr/share/empty/fs/aufs/xino.c linux/fs/aufs/xino.c
+--- /usr/share/empty/fs/aufs/xino.c 1970-01-01 01:00:00.000000000 +0100
++++ linux/fs/aufs/xino.c 2023-10-31 09:31:04.203214083 +0100
@@ -0,0 +1,1926 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ }
+
+out:
-+ return err;
-+}
-+
-+void au_xinondir_leave(struct super_block *sb, aufs_bindex_t bindex,
-+ ino_t h_ino, int idx)
-+{
-+ struct au_xino *xi;
-+
-+ AuDebugOn(!au_opt_test(au_mntflags(sb), XINO));
-+ xi = au_sbr(sb, bindex)->br_xino;
-+ AuDebugOn(idx < 0 || xi->xi_nondir.total <= idx);
-+
-+ spin_lock(&xi->xi_nondir.spin);
-+ AuDebugOn(xi->xi_nondir.array[idx] != h_ino);
-+ xi->xi_nondir.array[idx] = 0;
-+ spin_unlock(&xi->xi_nondir.spin);
-+ wake_up_all(&xi->xi_nondir.wqh);
-+}
-+
-+int au_xinondir_enter(struct super_block *sb, aufs_bindex_t bindex, ino_t h_ino,
-+ int *idx)
-+{
-+ int err, found, empty;
-+ struct au_xino *xi;
-+
-+ err = 0;
-+ *idx = -1;
-+ if (!au_opt_test(au_mntflags(sb), XINO))
-+ goto out; /* no xino */
-+
-+ xi = au_sbr(sb, bindex)->br_xino;
-+
-+again:
-+ spin_lock(&xi->xi_nondir.spin);
-+ found = au_xinondir_find(xi, h_ino);
-+ if (found == -1) {
-+ empty = au_xinondir_find(xi, /*h_ino*/0);
-+ if (empty == -1) {
-+ empty = xi->xi_nondir.total;
-+ err = au_xinondir_expand(xi);
-+ if (unlikely(err))
-+ goto out_unlock;
-+ }
-+ xi->xi_nondir.array[empty] = h_ino;
-+ *idx = empty;
-+ } else {
-+ spin_unlock(&xi->xi_nondir.spin);
-+ wait_event(xi->xi_nondir.wqh,
-+ xi->xi_nondir.array[found] != h_ino);
-+ goto again;
-+ }
-+
-+out_unlock:
-+ spin_unlock(&xi->xi_nondir.spin);
-+out:
-+ return err;
-+}
-+
-+/* ---------------------------------------------------------------------- */
-+
-+int au_xino_path(struct seq_file *seq, struct file *file)
-+{
-+ int err;
-+
-+ err = au_seq_path(seq, &file->f_path);
-+ if (unlikely(err))
-+ goto out;
-+
-+#define Deleted "\\040(deleted)"
-+ seq->count -= sizeof(Deleted) - 1;
-+ AuDebugOn(memcmp(seq->buf + seq->count, Deleted,
-+ sizeof(Deleted) - 1));
-+#undef Deleted
-+
-+out:
-+ return err;
-+}
-diff --git a/fs/dcache.c b/fs/dcache.c
-index c82ae731df9af7..411c9acbdca754 100644
---- a/fs/dcache.c
-+++ b/fs/dcache.c
-@@ -1345,7 +1345,7 @@ 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;
-@@ -1450,6 +1450,7 @@ static void d_walk(struct dentry *parent, void *data,
- seq = 1;
- goto again;
- }
-+EXPORT_SYMBOL_GPL(d_walk);
-
- struct check_mount {
- struct vfsmount *mnt;
-@@ -3051,6 +3052,7 @@ void d_exchange(struct dentry *dentry1, struct dentry *dentry2)
-
- write_sequnlock(&rename_lock);
- }
-+EXPORT_SYMBOL_GPL(d_exchange);
-
- /**
- * d_ancestor - search for an ancestor
-diff --git a/fs/exec.c b/fs/exec.c
-index 4aa19b24f2810a..013bc5896529ca 100644
---- a/fs/exec.c
-+++ b/fs/exec.c
-@@ -112,6 +112,7 @@ bool path_noexec(const struct path *path)
- return (path->mnt->mnt_flags & MNT_NOEXEC) ||
- (path->mnt->mnt_sb->s_iflags & SB_I_NOEXEC);
- }
-+EXPORT_SYMBOL_GPL(path_noexec);
-
- #ifdef CONFIG_USELIB
- /*
-diff --git a/fs/fcntl.c b/fs/fcntl.c
-index c80a6acad742fb..e21a0fcff53801 100644
---- a/fs/fcntl.c
-+++ b/fs/fcntl.c
-@@ -34,7 +34,7 @@
-
- #define SETFL_MASK (O_APPEND | O_NONBLOCK | O_NDELAY | O_DIRECT | O_NOATIME)
-
--static int setfl(int fd, struct file * filp, unsigned int arg)
-+int setfl(int fd, struct file * filp, unsigned int arg)
- {
- struct inode * inode = file_inode(filp);
- int error = 0;
-@@ -64,6 +64,8 @@ static int setfl(int fd, struct file * filp, unsigned int 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;
-
-@@ -85,6 +87,7 @@ static int setfl(int fd, struct file * filp, unsigned int arg)
- out:
- return error;
- }
-+EXPORT_SYMBOL_GPL(setfl);
-
- static void f_modown(struct file *filp, struct pid *pid, enum pid_type type,
- int force)
-diff --git a/fs/file_table.c b/fs/file_table.c
-index de4a2915bfd494..475f3f9c787607 100644
---- a/fs/file_table.c
-+++ b/fs/file_table.c
-@@ -235,6 +235,7 @@ struct file *alloc_empty_file(int flags, const struct cred *cred)
- }
- return ERR_PTR(-ENFILE);
- }
-+EXPORT_SYMBOL_GPL(alloc_empty_file);
-
- /*
- * Variant of alloc_empty_file() that doesn't check and modify nr_files.
-diff --git a/fs/namespace.c b/fs/namespace.c
-index fbf0e596fcd30c..1b942a6b72fa9f 100644
---- a/fs/namespace.c
-+++ b/fs/namespace.c
-@@ -489,6 +489,7 @@ void mnt_put_write_access_file(struct file *file)
- if (!(file->f_mode & FMODE_WRITER))
- mnt_put_write_access(file->f_path.mnt);
- }
-+EXPORT_SYMBOL_GPL(__mnt_drop_write);
-
- void mnt_drop_write_file(struct file *file)
- {
-@@ -874,6 +875,13 @@ 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));
-+}
-+EXPORT_SYMBOL_GPL(is_current_mnt_ns);
-+
- /*
- * vfsmount lock must be held for write
- */
-@@ -2148,6 +2156,7 @@ int iterate_mounts(int (*f)(struct vfsmount *, void *), void *arg,
- }
- return 0;
- }
-+EXPORT_SYMBOL_GPL(iterate_mounts);
-
- static void lock_mnt_tree(struct mount *mnt)
- {
-diff --git a/fs/notify/group.c b/fs/notify/group.c
-index 1de6631a3925ee..3008eb37a18d46 100644
---- a/fs/notify/group.c
-+++ b/fs/notify/group.c
-@@ -100,6 +100,7 @@ void fsnotify_get_group(struct fsnotify_group *group)
- {
- refcount_inc(&group->refcnt);
- }
-+EXPORT_SYMBOL_GPL(fsnotify_get_group);
-
- /*
- * Drop a reference to a group. Free it if it's through.
-diff --git a/fs/open.c b/fs/open.c
-index 3494a9cd8046c4..dc6a1779c44d8c 100644
---- a/fs/open.c
-+++ b/fs/open.c
-@@ -67,6 +67,7 @@ int do_truncate(struct mnt_idmap *idmap, struct dentry *dentry,
- inode_unlock(dentry->d_inode);
- return ret;
- }
-+EXPORT_SYMBOL_GPL(do_truncate);
-
- long vfs_truncate(const struct path *path, loff_t length)
- {
-diff --git a/fs/proc/nommu.c b/fs/proc/nommu.c
-index c6e7ebc637562d..d7ccfd90976464 100644
---- a/fs/proc/nommu.c
-+++ b/fs/proc/nommu.c
-@@ -39,7 +39,10 @@ static int nommu_region_show(struct seq_file *m, struct vm_region *region)
- file = region->vm_file;
-
- if (file) {
-- struct inode *inode = file_inode(region->vm_file);
-+ struct inode *inode;
-+
-+ file = vmr_pr_or_file(region);
-+ inode = file_inode(file);
- dev = inode->i_sb->s_dev;
- ino = inode->i_ino;
- }
-diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
-index 435b61054b5b9e..e67bb5fc412535 100644
---- a/fs/proc/task_mmu.c
-+++ b/fs/proc/task_mmu.c
-@@ -273,7 +273,10 @@ show_map_vma(struct seq_file *m, struct vm_area_struct *vma)
- const char *name = NULL;
-
- if (file) {
-- struct inode *inode = file_inode(vma->vm_file);
-+ struct inode *inode;
-+
-+ file = vma_pr_or_file(vma);
-+ inode = file_inode(file);
- dev = inode->i_sb->s_dev;
- ino = inode->i_ino;
- pgoff = ((loff_t)vma->vm_pgoff) << PAGE_SHIFT;
-@@ -2682,7 +2685,7 @@ static int show_numa_map(struct seq_file *m, void *v)
- struct proc_maps_private *proc_priv = &numa_priv->proc_maps;
- struct vm_area_struct *vma = v;
- struct numa_maps *md = &numa_priv->md;
-- struct file *file = vma->vm_file;
-+ struct file *file = vma_pr_or_file(vma);
- struct mm_struct *mm = vma->vm_mm;
- char buffer[64];
- struct mempolicy *pol;
-diff --git a/fs/proc/task_nommu.c b/fs/proc/task_nommu.c
-index bce67453300031..b12b5a75c799ca 100644
---- a/fs/proc/task_nommu.c
-+++ b/fs/proc/task_nommu.c
-@@ -137,7 +137,10 @@ static int nommu_vma_show(struct seq_file *m, struct vm_area_struct *vma)
- file = vma->vm_file;
-
- if (file) {
-- struct inode *inode = file_inode(vma->vm_file);
-+ struct inode *inode;
-+
-+ file = vma_pr_or_file(vma);
-+ inode = file_inode(file);
- dev = inode->i_sb->s_dev;
- ino = inode->i_ino;
- pgoff = (loff_t)vma->vm_pgoff << PAGE_SHIFT;
-diff --git a/fs/read_write.c b/fs/read_write.c
-index 4771701c896bad..c79270aba79246 100644
---- a/fs/read_write.c
-+++ b/fs/read_write.c
-@@ -477,6 +477,7 @@ ssize_t vfs_read(struct file *file, char __user *buf, size_t count, loff_t *pos)
- inc_syscr(current);
- return ret;
- }
-+EXPORT_SYMBOL_GPL(vfs_read);
-
- static ssize_t new_sync_write(struct file *filp, const char __user *buf, size_t len, loff_t *ppos)
- {
-@@ -592,6 +593,7 @@ ssize_t vfs_write(struct file *file, const char __user *buf, size_t count, loff_
- file_end_write(file);
- return ret;
- }
-+EXPORT_SYMBOL_GPL(vfs_write);
-
- /* file_ppos returns &file->f_pos or NULL if file is stream */
- static inline loff_t *file_ppos(struct file *file)
-diff --git a/fs/splice.c b/fs/splice.c
-index d983d375ff1130..7ce1f1bc42684d 100644
---- a/fs/splice.c
-+++ b/fs/splice.c
-@@ -925,13 +925,14 @@ static int warn_unsupported(struct file *file, const char *op)
- /*
- * 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)
- {
- if (unlikely(!out->f_op->splice_write))
- return warn_unsupported(out, "write");
- return out->f_op->splice_write(pipe, out, ppos, len, flags);
- }
-+EXPORT_SYMBOL_GPL(do_splice_from);
-
- /*
- * Indicate to the caller that there was a premature EOF when reading from the
-diff --git a/fs/xattr.c b/fs/xattr.c
-index 09d9276034335f..890daee95a7bf3 100644
---- a/fs/xattr.c
-+++ b/fs/xattr.c
-@@ -406,6 +406,7 @@ vfs_getxattr_alloc(struct mnt_idmap *idmap, struct dentry *dentry,
- *xattr_value = value;
- return error;
- }
-+EXPORT_SYMBOL_GPL(vfs_getxattr_alloc);
-
- ssize_t
- __vfs_getxattr(struct dentry *dentry, struct inode *inode, const char *name,
-diff --git a/include/linux/fs.h b/include/linux/fs.h
-index 98b7a7a8c42e36..7bf7c5d0b4c9d8 100644
---- a/include/linux/fs.h
-+++ b/include/linux/fs.h
-@@ -1102,6 +1102,7 @@ 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 int arg);
- extern void __f_setown(struct file *filp, struct pid *, enum pid_type, int force);
- extern int f_setown(struct file *filp, int who, int force);
- extern void f_delown(struct file *filp);
-@@ -1936,6 +1937,7 @@ struct file_operations {
- int (*lock) (struct file *, int, struct file_lock *);
- 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);
-diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h
-index dc2844b071c2c2..069ffb776c2c12 100644
---- a/include/linux/lockdep.h
-+++ b/include/linux/lockdep.h
-@@ -249,6 +249,8 @@ 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.
- *
-diff --git a/include/linux/mm.h b/include/linux/mm.h
-index da5219b48d5229..ba625a96957fed 100644
---- a/include/linux/mm.h
-+++ b/include/linux/mm.h
-@@ -2420,6 +2420,43 @@ static inline void unmap_shared_mapping_range(struct address_space *mapping,
- static inline struct vm_area_struct *vma_lookup(struct mm_struct *mm,
- unsigned long addr);
-
-+#if 1 /* IS_ENABLED(CONFIG_AUFS_FS) */
-+extern void vma_do_file_update_time(struct vm_area_struct *, const char[], int);
-+extern struct file *vma_do_pr_or_file(struct vm_area_struct *, const char[],
-+ int);
-+extern void vma_do_get_file(struct vm_area_struct *, const char[], int);
-+extern void vma_do_fput(struct vm_area_struct *, const char[], int);
++ return err;
++}
+
-+#define vma_file_update_time(vma) vma_do_file_update_time(vma, __func__, \
-+ __LINE__)
-+#define vma_pr_or_file(vma) vma_do_pr_or_file(vma, __func__, \
-+ __LINE__)
-+#define vma_get_file(vma) vma_do_get_file(vma, __func__, __LINE__)
-+#define vma_fput(vma) vma_do_fput(vma, __func__, __LINE__)
++void au_xinondir_leave(struct super_block *sb, aufs_bindex_t bindex,
++ ino_t h_ino, int idx)
++{
++ struct au_xino *xi;
+
-+#ifndef CONFIG_MMU
-+extern struct file *vmr_do_pr_or_file(struct vm_region *, const char[], int);
-+extern void vmr_do_fput(struct vm_region *, const char[], int);
++ AuDebugOn(!au_opt_test(au_mntflags(sb), XINO));
++ xi = au_sbr(sb, bindex)->br_xino;
++ AuDebugOn(idx < 0 || xi->xi_nondir.total <= idx);
+
-+#define vmr_pr_or_file(region) vmr_do_pr_or_file(region, __func__, \
-+ __LINE__)
-+#define vmr_fput(region) vmr_do_fput(region, __func__, __LINE__)
-+#endif /* !CONFIG_MMU */
++ spin_lock(&xi->xi_nondir.spin);
++ AuDebugOn(xi->xi_nondir.array[idx] != h_ino);
++ xi->xi_nondir.array[idx] = 0;
++ spin_unlock(&xi->xi_nondir.spin);
++ wake_up_all(&xi->xi_nondir.wqh);
++}
+
-+#else
++int au_xinondir_enter(struct super_block *sb, aufs_bindex_t bindex, ino_t h_ino,
++ int *idx)
++{
++ int err, found, empty;
++ struct au_xino *xi;
+
-+#define vma_file_update_time(vma) file_update_time((vma)->vm_file)
-+#define vma_pr_or_file(vma) (vma)->vm_file
-+#define vma_get_file(vma) get_file((vma)->vm_file)
-+#define vma_fput(vma) fput((vma)->vm_file)
++ err = 0;
++ *idx = -1;
++ if (!au_opt_test(au_mntflags(sb), XINO))
++ goto out; /* no xino */
+
-+#ifndef CONFIG_MMU
-+#define vmr_pr_or_file(region) (region)->vm_file
-+#define vmr_fput(region) fput((region)->vm_file)
-+#endif /* !CONFIG_MMU */
++ xi = au_sbr(sb, bindex)->br_xino;
+
-+#endif /* CONFIG_AUFS_FS */
++again:
++ spin_lock(&xi->xi_nondir.spin);
++ found = au_xinondir_find(xi, h_ino);
++ if (found == -1) {
++ empty = au_xinondir_find(xi, /*h_ino*/0);
++ if (empty == -1) {
++ empty = xi->xi_nondir.total;
++ err = au_xinondir_expand(xi);
++ if (unlikely(err))
++ goto out_unlock;
++ }
++ xi->xi_nondir.array[empty] = h_ino;
++ *idx = empty;
++ } else {
++ spin_unlock(&xi->xi_nondir.spin);
++ wait_event(xi->xi_nondir.wqh,
++ xi->xi_nondir.array[found] != h_ino);
++ goto again;
++ }
+
- extern int access_process_vm(struct task_struct *tsk, unsigned long addr,
- void *buf, int len, unsigned int gup_flags);
- extern int access_remote_vm(struct mm_struct *mm, unsigned long addr,
-diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
-index 957ce38768b2a8..cc556e47ea1727 100644
---- a/include/linux/mm_types.h
-+++ b/include/linux/mm_types.h
-@@ -527,6 +527,9 @@ struct vm_region {
- unsigned long vm_top; /* region allocated to here */
- unsigned long vm_pgoff; /* the offset in vm_file corresponding to vm_start */
- struct file *vm_file; /* the backing file or NULL */
-+#if 1 /* IS_ENABLED(CONFIG_AUFS_FS) */
-+ struct file *vm_prfile; /* the virtual backing file or NULL */
-+#endif
-
- int vm_usage; /* region usage count (access under nommu_region_sem) */
- bool vm_icache_flushed : 1; /* true if the icache has been flushed for
-@@ -688,6 +691,9 @@ struct vm_area_struct {
- unsigned long vm_pgoff; /* Offset (within vm_file) in PAGE_SIZE
- units */
- struct file * vm_file; /* File we map to (can be NULL). */
-+#if 1 /* IS_ENABLED(CONFIG_AUFS_FS) */
-+ struct file *vm_prfile; /* shadow of vm_file */
-+#endif
- void * vm_private_data; /* was vm_pte (shared mem) */
-
- #ifdef CONFIG_ANON_VMA_NAME
-diff --git a/include/linux/mnt_namespace.h b/include/linux/mnt_namespace.h
-index 8f882f5881e879..6b9808f0984351 100644
---- a/include/linux/mnt_namespace.h
-+++ b/include/linux/mnt_namespace.h
-@@ -7,12 +7,15 @@ struct mnt_namespace;
- struct fs_struct;
- struct user_namespace;
- struct ns_common;
-+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 struct ns_common *from_mnt_ns(struct mnt_namespace *);
-
-+extern int is_current_mnt_ns(struct vfsmount *mnt);
++out_unlock:
++ spin_unlock(&xi->xi_nondir.spin);
++out:
++ return err;
++}
+
- 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 6c461573434dde..7416cf375ad126 100644
---- a/include/linux/splice.h
-+++ b/include/linux/splice.h
-@@ -99,4 +99,10 @@ 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/include/uapi/linux/aufs_type.h b/include/uapi/linux/aufs_type.h
-new file mode 100644
-index 00000000000000..207ee8ae216206
---- /dev/null
-+++ b/include/uapi/linux/aufs_type.h
++int au_xino_path(struct seq_file *seq, struct file *file)
++{
++ int err;
++
++ err = au_seq_path(seq, &file->f_path);
++ if (unlikely(err))
++ goto out;
++
++#define Deleted "\\040(deleted)"
++ seq->count -= sizeof(Deleted) - 1;
++ AuDebugOn(memcmp(seq->buf + seq->count, Deleted,
++ sizeof(Deleted) - 1));
++#undef Deleted
++
++out:
++ return err;
++}
+diff -urN /usr/share/empty/include/uapi/linux/aufs_type.h linux/include/uapi/linux/aufs_type.h
+--- /usr/share/empty/include/uapi/linux/aufs_type.h 1970-01-01 01:00:00.000000000 +0100
++++ linux/include/uapi/linux/aufs_type.h 2024-03-10 23:40:47.086476782 +0100
@@ -0,0 +1,452 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/*
+#include <limits.h>
+#endif /* __KERNEL__ */
+
-+#define AUFS_VERSION "6.x-rcN-20231106"
++#define AUFS_VERSION "6.x-rcN-20240226"
+
+/* todo? move this to linux-2.6.19/include/magic.h */
+#define AUFS_SUPER_MAGIC ('a' << 24 | 'u' << 16 | 'f' << 8 | 's')
+#define AUFS_CTL_FHSM_FD _IOW(AuCtlType, AuCtl_FHSM_FD, int)
+
+#endif /* __AUFS_TYPE_H__ */
-diff --git a/kernel/fork.c b/kernel/fork.c
-index 10917c3e1f0366..6018e512fb9c32 100644
---- a/kernel/fork.c
-+++ b/kernel/fork.c
-@@ -731,7 +731,7 @@ static __latent_entropy int dup_mmap(struct mm_struct *mm,
- if (file) {
- struct address_space *mapping = file->f_mapping;
-
-- get_file(file);
-+ vma_get_file(tmp);
- i_mmap_lock_write(mapping);
- if (vma_is_shared_maywrite(tmp))
- mapping_allow_writable(mapping);
-diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c
-index 151bd3de59363a..d0ac4fc69a31dc 100644
---- a/kernel/locking/lockdep.c
-+++ b/kernel/locking/lockdep.c
-@@ -218,7 +218,7 @@ unsigned long max_lock_class_idx;
- struct lock_class lock_classes[MAX_LOCKDEP_KEYS];
- DECLARE_BITMAP(lock_classes_in_use, MAX_LOCKDEP_KEYS);
+SPDX-License-Identifier: GPL-2.0
+aufs6.x-rcN loopback patch
+
+diff --git a/drivers/block/loop.c b/drivers/block/loop.c
+index 333b3915fe86..1eb5bde57477 100644
+--- a/drivers/block/loop.c
++++ b/drivers/block/loop.c
+@@ -54,7 +54,7 @@ struct loop_device {
+ int lo_flags;
+ char lo_file_name[LO_NAME_SIZE];
--static inline struct lock_class *hlock_class(struct held_lock *hlock)
-+inline struct lock_class *lockdep_hlock_class(struct held_lock *hlock)
- {
- unsigned int class_idx = hlock->class_idx;
+- struct file * lo_backing_file;
++ struct file *lo_backing_file, *lo_backing_virt_file;
+ struct block_device *lo_device;
-@@ -239,6 +239,8 @@ static inline struct lock_class *hlock_class(struct held_lock *hlock)
- */
- return lock_classes + class_idx;
+ gfp_t old_gfp_mask;
+@@ -506,6 +506,15 @@ static inline void loop_update_dio(struct loop_device *lo)
+ lo->use_dio);
}
-+EXPORT_SYMBOL_GPL(lockdep_hlock_class);
-+#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);
-diff --git a/kernel/task_work.c b/kernel/task_work.c
-index 95a7e1b7f1dab2..5053670775d3ce 100644
---- a/kernel/task_work.c
-+++ b/kernel/task_work.c
-@@ -183,3 +183,4 @@ void task_work_run(void)
- } while (work);
- }
- }
-+EXPORT_SYMBOL_GPL(task_work_run);
-diff --git a/mm/Makefile b/mm/Makefile
-index 33873c8aedb399..ae036592066aa6 100644
---- a/mm/Makefile
-+++ b/mm/Makefile
-@@ -138,3 +138,4 @@ obj-$(CONFIG_IO_MAPPING) += io-mapping.o
- obj-$(CONFIG_HAVE_BOOTMEM_INFO_NODE) += bootmem_info.o
- obj-$(CONFIG_GENERIC_IOREMAP) += ioremap.o
- obj-$(CONFIG_SHRINKER_DEBUG) += shrinker_debug.o
-+obj-y += prfile.o
-diff --git a/mm/filemap.c b/mm/filemap.c
-index ad5b4aa049a380..e855d6c72168fe 100644
---- a/mm/filemap.c
-+++ b/mm/filemap.c
-@@ -3584,7 +3584,7 @@ vm_fault_t filemap_page_mkwrite(struct vm_fault *vmf)
- vm_fault_t ret = VM_FAULT_LOCKED;
++static struct file *loop_real_file(struct file *file)
++{
++ struct file *f = NULL;
++
++ if (file->f_path.dentry->d_sb->s_op->real_loop)
++ f = file->f_path.dentry->d_sb->s_op->real_loop(file);
++ return f;
++}
++
+ static void loop_reread_partitions(struct loop_device *lo)
+ {
+ int rc;
+@@ -563,6 +572,7 @@ static int loop_change_fd(struct loop_device *lo, struct block_device *bdev,
+ {
+ struct file *file = fget(arg);
+ struct file *old_file;
++ struct file *f, *virt_file = NULL, *old_virt_file;
+ int error;
+ bool partscan;
+ bool is_loop;
+@@ -586,11 +596,19 @@ static int loop_change_fd(struct loop_device *lo, struct block_device *bdev,
+ if (!(lo->lo_flags & LO_FLAGS_READ_ONLY))
+ goto out_err;
- sb_start_pagefault(mapping->host->i_sb);
-- file_update_time(vmf->vma->vm_file);
-+ vma_file_update_time(vmf->vma);
- folio_lock(folio);
- if (folio->mapping != mapping) {
- folio_unlock(folio);
-diff --git a/mm/mmap.c b/mm/mmap.c
-index aa82eec17489ca..a37484d87ff0b3 100644
---- a/mm/mmap.c
-+++ b/mm/mmap.c
-@@ -140,7 +140,7 @@ static void remove_vma(struct vm_area_struct *vma, bool unreachable)
- if (vma->vm_ops && vma->vm_ops->close)
- vma->vm_ops->close(vma);
- if (vma->vm_file)
-- fput(vma->vm_file);
-+ vma_fput(vma);
- mpol_put(vma_policy(vma));
- if (unreachable)
- __vm_area_free(vma);
-@@ -554,7 +554,7 @@ static inline void vma_complete(struct vma_prepare *vp,
- if (vp->file) {
- uprobe_munmap(vp->remove, vp->remove->vm_start,
- vp->remove->vm_end);
-- fput(vp->file);
-+ vma_fput(vp->vma);
- }
- if (vp->remove->anon_vma)
- anon_vma_merge(vp->vma, vp->remove);
-@@ -2390,7 +2390,7 @@ static int __split_vma(struct vma_iterator *vmi, struct vm_area_struct *vma,
- goto out_free_mpol;
++ f = loop_real_file(file);
++ if (f) {
++ virt_file = file;
++ file = f;
++ get_file(file);
++ }
++
+ error = loop_validate_file(file, bdev);
+ if (error)
+ goto out_err;
- if (new->vm_file)
-- get_file(new->vm_file);
-+ vma_get_file(new);
+ old_file = lo->lo_backing_file;
++ old_virt_file = lo->lo_backing_virt_file;
- if (new->vm_ops && new->vm_ops->open)
- new->vm_ops->open(new);
-@@ -2888,7 +2888,7 @@ unsigned long mmap_region(struct file *file, unsigned long addr,
- * and cause general protection fault
- * ultimately.
- */
-- fput(vma->vm_file);
-+ vma_fput(vma);
- vm_area_free(vma);
- vma = merge;
- /* Update vm_flags to pick up the change. */
-@@ -2983,7 +2983,7 @@ unsigned long mmap_region(struct file *file, unsigned long addr,
+ error = -EINVAL;
- if (file || vma->vm_file) {
- unmap_and_free_vma:
-- fput(vma->vm_file);
-+ vma_fput(vma);
- vma->vm_file = NULL;
+@@ -603,6 +621,7 @@ static int loop_change_fd(struct loop_device *lo, struct block_device *bdev,
+ blk_mq_freeze_queue(lo->lo_queue);
+ mapping_set_gfp_mask(old_file->f_mapping, lo->old_gfp_mask);
+ lo->lo_backing_file = file;
++ lo->lo_backing_virt_file = virt_file;
+ lo->old_gfp_mask = mapping_gfp_mask(file->f_mapping);
+ mapping_set_gfp_mask(file->f_mapping,
+ lo->old_gfp_mask & ~(__GFP_IO|__GFP_FS));
+@@ -625,6 +644,8 @@ static int loop_change_fd(struct loop_device *lo, struct block_device *bdev,
+ * dependency.
+ */
+ fput(old_file);
++ if (old_virt_file)
++ fput(old_virt_file);
+ if (partscan)
+ loop_reread_partitions(lo);
- vma_iter_set(&vmi, vma->vm_end);
-@@ -3045,6 +3045,9 @@ SYSCALL_DEFINE5(remap_file_pages, unsigned long, start, unsigned long, size,
- unsigned long populate = 0;
- unsigned long ret = -EINVAL;
- struct file *file;
-+#if 1 /* IS_ENABLED(CONFIG_AUFS_FS) */
-+ struct file *prfile;
-+#endif
+@@ -638,6 +659,8 @@ static int loop_change_fd(struct loop_device *lo, struct block_device *bdev,
+ loop_global_unlock(lo, is_loop);
+ out_putf:
+ fput(file);
++ if (virt_file)
++ fput(virt_file);
+ goto done;
+ }
- pr_warn_once("%s (%d) uses deprecated remap_file_pages() syscall. See Documentation/mm/remap_file_pages.rst.\n",
- current->comm, current->pid);
-@@ -3103,10 +3106,34 @@ SYSCALL_DEFINE5(remap_file_pages, unsigned long, start, unsigned long, size,
- if (vma->vm_flags & VM_LOCKED)
- flags |= MAP_LOCKED;
+@@ -1009,6 +1032,7 @@ static int loop_configure(struct loop_device *lo, blk_mode_t mode,
+ const struct loop_config *config)
+ {
+ struct file *file = fget(config->fd);
++ struct file *f, *virt_file = NULL;
+ struct inode *inode;
+ struct address_space *mapping;
+ int error;
+@@ -1024,6 +1048,13 @@ static int loop_configure(struct loop_device *lo, blk_mode_t mode,
+ /* This is safe, since we have a reference from open(). */
+ __module_get(THIS_MODULE);
-+#if 1 /* IS_ENABLED(CONFIG_AUFS_FS) */
-+ vma_get_file(vma);
-+ file = vma->vm_file;
-+ prfile = vma->vm_prfile;
-+ ret = do_mmap(vma->vm_file, start, size,
-+ prot, flags, /*vm_flags*/0, pgoff, &populate, NULL);
-+ if (!IS_ERR_VALUE(ret) && file && prfile) {
-+ struct vm_area_struct *new_vma;
-+
-+ new_vma = find_vma(mm, ret);
-+ if (!new_vma->vm_prfile)
-+ new_vma->vm_prfile = prfile;
-+ if (prfile)
-+ get_file(prfile);
++ f = loop_real_file(file);
++ if (f) {
++ virt_file = file;
++ file = f;
++ get_file(file);
+ }
-+ /*
-+ * two fput()s instead of vma_fput(vma),
-+ * coz vma may not be available anymore.
-+ */
-+ fput(file);
-+ if (prfile)
-+ fput(prfile);
-+#else
- file = get_file(vma->vm_file);
- ret = do_mmap(vma->vm_file, start, size,
- prot, flags, 0, pgoff, &populate, NULL);
++
+ /*
+ * If we don't hold exclusive handle for the device, upgrade to it
+ * here to avoid changing device under exclusive owner.
+@@ -1087,6 +1118,7 @@ static int loop_configure(struct loop_device *lo, blk_mode_t mode,
+ lo->use_dio = lo->lo_flags & LO_FLAGS_DIRECT_IO;
+ lo->lo_device = bdev;
+ lo->lo_backing_file = file;
++ lo->lo_backing_virt_file = virt_file;
+ lo->old_gfp_mask = mapping_gfp_mask(mapping);
+ mapping_set_gfp_mask(mapping, lo->old_gfp_mask & ~(__GFP_IO|__GFP_FS));
+
+@@ -1142,6 +1174,8 @@ static int loop_configure(struct loop_device *lo, blk_mode_t mode,
+ bd_abort_claiming(bdev, loop_configure);
+ out_putf:
fput(file);
-+#endif /* CONFIG_AUFS_FS */
- out:
- mmap_write_unlock(mm);
- if (populate)
-@@ -3450,7 +3477,7 @@ struct vm_area_struct *copy_vma(struct vm_area_struct **vmap,
- if (anon_vma_clone(new_vma, vma))
- goto out_free_mempol;
- if (new_vma->vm_file)
-- get_file(new_vma->vm_file);
-+ vma_get_file(new_vma);
- if (new_vma->vm_ops && new_vma->vm_ops->open)
- new_vma->vm_ops->open(new_vma);
- if (vma_link(mm, new_vma))
-@@ -3464,7 +3491,7 @@ struct vm_area_struct *copy_vma(struct vm_area_struct **vmap,
- new_vma->vm_ops->close(new_vma);
++ if (virt_file)
++ fput(virt_file);
+ /* This is safe: open() is still holding a reference. */
+ module_put(THIS_MODULE);
+ return error;
+@@ -1150,6 +1184,7 @@ static int loop_configure(struct loop_device *lo, blk_mode_t mode,
+ static void __loop_clr_fd(struct loop_device *lo, bool release)
+ {
+ struct file *filp;
++ struct file *virt_filp = lo->lo_backing_virt_file;
+ gfp_t gfp = lo->old_gfp_mask;
- if (new_vma->vm_file)
-- fput(new_vma->vm_file);
-+ vma_fput(new_vma);
+ if (test_bit(QUEUE_FLAG_WC, &lo->lo_queue->queue_flags))
+@@ -1166,6 +1201,7 @@ static void __loop_clr_fd(struct loop_device *lo, bool release)
+ spin_lock_irq(&lo->lo_lock);
+ filp = lo->lo_backing_file;
+ lo->lo_backing_file = NULL;
++ lo->lo_backing_virt_file = NULL;
+ spin_unlock_irq(&lo->lo_lock);
- unlink_anon_vmas(new_vma);
- out_free_mempol:
-diff --git a/mm/nommu.c b/mm/nommu.c
-index b6dc558d314408..d96655486468e4 100644
---- a/mm/nommu.c
-+++ b/mm/nommu.c
-@@ -523,7 +523,7 @@ static void __put_nommu_region(struct vm_region *region)
- up_write(&nommu_region_sem);
+ lo->lo_device = NULL;
+@@ -1228,6 +1264,8 @@ static void __loop_clr_fd(struct loop_device *lo, bool release)
+ * fput can take open_mutex which is usually taken before lo_mutex.
+ */
+ fput(filp);
++ if (virt_filp)
++ fput(virt_filp);
+ }
- if (region->vm_file)
-- fput(region->vm_file);
-+ vmr_fput(region);
+ static int loop_clr_fd(struct loop_device *lo)
+diff --git a/fs/aufs/f_op.c b/fs/aufs/f_op.c
+index fa8a517ffd0c..c18f7bcef81b 100644
+--- a/fs/aufs/f_op.c
++++ b/fs/aufs/f_op.c
+@@ -311,7 +311,7 @@ static ssize_t aufs_read_iter(struct kiocb *kio, struct iov_iter *iov_iter)
+ if (IS_ERR(h_file))
+ goto out;
- /* IO memory and memory shared directly out of the pagecache
- * from ramfs/tmpfs mustn't be released here */
-@@ -603,7 +603,7 @@ static void delete_vma(struct mm_struct *mm, struct vm_area_struct *vma)
- if (vma->vm_ops && vma->vm_ops->close)
- vma->vm_ops->close(vma);
- if (vma->vm_file)
-- fput(vma->vm_file);
-+ vma_fput(vma);
- put_nommu_region(vma->vm_region);
- vm_area_free(vma);
+- if (au_test_loopback_kthread()) {
++ if (0 && 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;
+diff --git a/fs/aufs/loop.c b/fs/aufs/loop.c
+index 58043e31e5f3..e2bfae6f9d59 100644
+--- a/fs/aufs/loop.c
++++ b/fs/aufs/loop.c
+@@ -133,3 +133,19 @@ void au_loopback_fin(void)
+ symbol_put(loop_backing_file);
+ au_kfree_try_rcu(au_warn_loopback_array);
}
-@@ -1135,7 +1135,7 @@ unsigned long do_mmap(struct file *file,
- goto error_just_free;
- }
- }
-- fput(region->vm_file);
-+ vmr_fput(region);
- kmem_cache_free(vm_region_jar, region);
- region = pregion;
- result = start;
-@@ -1221,10 +1221,10 @@ unsigned long do_mmap(struct file *file,
- error:
- vma_iter_free(&vmi);
- if (region->vm_file)
-- fput(region->vm_file);
-+ vmr_fput(region);
- kmem_cache_free(vm_region_jar, region);
- if (vma->vm_file)
-- fput(vma->vm_file);
-+ vma_fput(vma);
- vm_area_free(vma);
- return ret;
-
-diff --git a/mm/prfile.c b/mm/prfile.c
-new file mode 100644
-index 00000000000000..8f820a2353646f
---- /dev/null
-+++ b/mm/prfile.c
-@@ -0,0 +1,86 @@
-+// SPDX-License-Identifier: GPL-2.0
-+/*
-+ * Mainly for aufs which mmap(2) different file and wants to print different
-+ * path in /proc/PID/maps.
-+ * Call these functions via macros defined in linux/mm.h.
-+ *
-+ * See Documentation/filesystems/aufs/design/06mmap.txt
-+ *
-+ * Copyright (c) 2014-2022 Junjro R. Okajima
-+ * Copyright (c) 2014 Ian Campbell
-+ */
-+
-+#include <linux/mm.h>
-+#include <linux/file.h>
-+#include <linux/fs.h>
-+
-+/* #define PRFILE_TRACE */
-+static inline void prfile_trace(struct file *f, struct file *pr,
-+ const char func[], int line, const char func2[])
-+{
-+#ifdef PRFILE_TRACE
-+ if (pr)
-+ pr_info("%s:%d: %s, %pD2\n", func, line, func2, f);
-+#endif
-+}
-+
-+void vma_do_file_update_time(struct vm_area_struct *vma, const char func[],
-+ int line)
-+{
-+ struct file *f = vma->vm_file, *pr = vma->vm_prfile;
-+
-+ prfile_trace(f, pr, func, line, __func__);
-+ file_update_time(f);
-+ if (f && pr)
-+ file_update_time(pr);
-+}
-+
-+struct file *vma_do_pr_or_file(struct vm_area_struct *vma, const char func[],
-+ int line)
-+{
-+ struct file *f = vma->vm_file, *pr = vma->vm_prfile;
-+
-+ prfile_trace(f, pr, func, line, __func__);
-+ return (f && pr) ? pr : f;
-+}
-+
-+void vma_do_get_file(struct vm_area_struct *vma, const char func[], int line)
-+{
-+ struct file *f = vma->vm_file, *pr = vma->vm_prfile;
-+
-+ prfile_trace(f, pr, func, line, __func__);
-+ get_file(f);
-+ if (f && pr)
-+ get_file(pr);
-+}
-+
-+void vma_do_fput(struct vm_area_struct *vma, const char func[], int line)
-+{
-+ struct file *f = vma->vm_file, *pr = vma->vm_prfile;
-+
-+ prfile_trace(f, pr, func, line, __func__);
-+ fput(f);
-+ if (f && pr)
-+ fput(pr);
-+}
+
-+#ifndef CONFIG_MMU
-+struct file *vmr_do_pr_or_file(struct vm_region *region, const char func[],
-+ int line)
-+{
-+ struct file *f = region->vm_file, *pr = region->vm_prfile;
++/* ---------------------------------------------------------------------- */
+
-+ prfile_trace(f, pr, func, line, __func__);
-+ return (f && pr) ? pr : f;
-+}
++/* support the loopback block device insude aufs */
+
-+void vmr_do_fput(struct vm_region *region, const char func[], int line)
++struct file *aufs_real_loop(struct file *file)
+{
-+ struct file *f = region->vm_file, *pr = region->vm_prfile;
++ struct file *f;
+
-+ prfile_trace(f, pr, func, line, __func__);
-+ fput(f);
-+ if (f && pr)
-+ fput(pr);
++ BUG_ON(!au_test_aufs(file->f_path.dentry->d_sb));
++ fi_read_lock(file);
++ f = au_hf_top(file);
++ fi_read_unlock(file);
++ AuDebugOn(!f);
++ return f;
+}
-+#endif /* !CONFIG_MMU */
-diff --git a/security/security.c b/security/security.c
-index dcb3e7014f9bdd..a7135660dd2c70 100644
---- a/security/security.c
-+++ b/security/security.c
-@@ -1750,6 +1750,7 @@ int security_path_rmdir(const struct path *dir, struct dentry *dentry)
- return 0;
- return call_int_hook(path_rmdir, 0, dir, dentry);
- }
-+EXPORT_SYMBOL_GPL(security_path_rmdir);
-
- /**
- * security_path_unlink() - Check if removing a hard link is allowed
-@@ -1785,6 +1786,7 @@ int security_path_symlink(const struct path *dir, struct dentry *dentry,
- return 0;
- return call_int_hook(path_symlink, 0, dir, dentry, old_name);
- }
-+EXPORT_SYMBOL_GPL(security_path_symlink);
-
- /**
- * security_path_link - Check if creating a hard link is allowed
-@@ -1803,6 +1805,7 @@ int security_path_link(struct dentry *old_dentry, const struct path *new_dir,
- return 0;
- return call_int_hook(path_link, 0, old_dentry, new_dir, new_dentry);
- }
-+EXPORT_SYMBOL_GPL(security_path_link);
-
- /**
- * security_path_rename() - Check if renaming a file is allowed
-@@ -1864,6 +1867,7 @@ int security_path_chmod(const struct path *path, umode_t mode)
- return 0;
- return call_int_hook(path_chmod, 0, path, mode);
- }
-+EXPORT_SYMBOL_GPL(security_path_chmod);
+diff --git a/fs/aufs/loop.h b/fs/aufs/loop.h
+index 03d4908a6c03..34d356e181d5 100644
+--- a/fs/aufs/loop.h
++++ b/fs/aufs/loop.h
+@@ -26,6 +26,8 @@ void au_warn_loopback(struct super_block *h_sb);
- /**
- * security_path_chown() - Check if changing the file's owner/group is allowed
-@@ -1881,6 +1885,7 @@ int security_path_chown(const struct path *path, kuid_t uid, kgid_t gid)
- return 0;
- return call_int_hook(path_chown, 0, path, uid, gid);
- }
-+EXPORT_SYMBOL_GPL(security_path_chown);
+ int au_loopback_init(void);
+ void au_loopback_fin(void);
++
++struct file *aufs_real_loop(struct file *file);
+ #else
+ AuStub(struct file *, loop_backing_file, return NULL, struct super_block *sb)
- /**
- * security_path_chroot() - Check if changing the root directory is allowed
-@@ -2110,6 +2115,7 @@ int security_inode_permission(struct inode *inode, int mask)
- return 0;
- return call_int_hook(inode_permission, 0, inode, mask);
- }
-+EXPORT_SYMBOL_GPL(security_inode_permission);
+@@ -36,6 +38,8 @@ AuStubVoid(au_warn_loopback, struct super_block *h_sb)
- /**
- * security_inode_setattr() - Check if setting file attributes is allowed
-@@ -2588,6 +2594,7 @@ int security_file_permission(struct file *file, int mask)
+ AuStubInt0(au_loopback_init, void)
+ AuStubVoid(au_loopback_fin, void)
++
++AuStub(struct file *, aufs_real_loop, return NULL, struct file *file)
+ #endif /* BLK_DEV_LOOP */
- return fsnotify_perm(file, mask);
- }
-+EXPORT_SYMBOL_GPL(security_file_permission);
+ #endif /* __KERNEL__ */
+diff --git a/fs/aufs/super.c b/fs/aufs/super.c
+index 07d3412e950f..c4a00f620e57 100644
+--- a/fs/aufs/super.c
++++ b/fs/aufs/super.c
+@@ -758,7 +758,10 @@ const struct super_operations aufs_sop = {
+ .show_options = aufs_show_options,
+ .statfs = aufs_statfs,
+ .put_super = aufs_put_super,
+- .sync_fs = aufs_sync_fs
++ .sync_fs = aufs_sync_fs,
++#ifdef CONFIG_AUFS_BDEV_LOOP
++ .real_loop = aufs_real_loop
++#endif
+ };
- /**
- * security_file_alloc() - Allocate and init a file's LSM blob
-@@ -2854,6 +2861,7 @@ int security_file_truncate(struct file *file)
- {
- return call_int_hook(file_truncate, 0, file);
- }
-+EXPORT_SYMBOL_GPL(security_file_truncate);
+ /* ---------------------------------------------------------------------- */
+diff --git a/include/linux/fs.h b/include/linux/fs.h
+index 96ca249ee1e6..b21abb1a2134 100644
+--- a/include/linux/fs.h
++++ b/include/linux/fs.h
+@@ -2165,6 +2165,11 @@ struct super_operations {
+ long (*free_cached_objects)(struct super_block *,
+ struct shrink_control *);
+ void (*shutdown)(struct super_block *sb);
++
++#if IS_ENABLED(CONFIG_BLK_DEV_LOOP) || IS_ENABLED(CONFIG_BLK_DEV_LOOP_MODULE)
++ /* and aufs */
++ struct file *(*real_loop)(struct file *);
++#endif
+ };
- /**
- * security_task_alloc() - Allocate a task's LSM blob
+ /*
projects / packages / kernel.git / commitdiff