X-Git-Url: http://git.pld-linux.org/?a=blobdiff_plain;f=kernel-aufs4.patch;h=1bb19e5cde92a209044708401c35a9bbaa93ee74;hb=fa49db91a15062fa99faebbfe60a1d3092f6e525;hp=16f65cba11a7c76dd1d7cc62a77312fd9fa04d0a;hpb=f2c43d5f9be66527e3189ec126a8f04f1f4d2107;p=packages%2Fkernel.git diff --git a/kernel-aufs4.patch b/kernel-aufs4.patch index 16f65cba..1bb19e5c 100644 --- a/kernel-aufs4.patch +++ b/kernel-aufs4.patch @@ -1,2819 +1,3890 @@ -aufs4.9 kbuild patch - -diff --git a/fs/Kconfig b/fs/Kconfig -index 4bd03a2..620e01b 100644 ---- a/fs/Kconfig -+++ b/fs/Kconfig -@@ -249,6 +249,7 @@ source "fs/pstore/Kconfig" - source "fs/sysv/Kconfig" - source "fs/ufs/Kconfig" - source "fs/exofs/Kconfig" -+source "fs/aufs/Kconfig" - - endif # MISC_FILESYSTEMS - -diff --git a/fs/Makefile b/fs/Makefile -index ed2b632..aa6d14b 100644 ---- a/fs/Makefile -+++ b/fs/Makefile -@@ -129,3 +129,4 @@ obj-y += exofs/ # Multiple modules - obj-$(CONFIG_CEPH_FS) += ceph/ - obj-$(CONFIG_PSTORE) += pstore/ - obj-$(CONFIG_EFIVAR_FS) += efivarfs/ -+obj-$(CONFIG_AUFS_FS) += aufs/ -diff --git a/include/uapi/linux/Kbuild b/include/uapi/linux/Kbuild -index cd2be1c..78f3c68 100644 ---- a/include/uapi/linux/Kbuild -+++ b/include/uapi/linux/Kbuild -@@ -59,6 +59,7 @@ header-y += atmsvc.h - header-y += atm_tcp.h - header-y += atm_zatm.h - header-y += audit.h -+header-y += aufs_type.h - header-y += auto_fs4.h - header-y += auto_fs.h - header-y += auxvec.h -aufs4.9 base patch - -diff --git a/MAINTAINERS b/MAINTAINERS -index 63cefa6..d78b954 100644 ---- a/MAINTAINERS -+++ b/MAINTAINERS -@@ -2293,6 +2293,19 @@ F: include/linux/audit.h - F: include/uapi/linux/audit.h - F: kernel/audit* - -+AUFS (advanced multi layered unification filesystem) FILESYSTEM -+M: "J. R. Okajima" -+L: linux-unionfs@vger.kernel.org -+L: aufs-users@lists.sourceforge.net (members only) -+W: http://aufs.sourceforge.net -+T: git://github.com/sfjro/aufs4-linux.git -+S: Supported -+F: Documentation/filesystems/aufs/ -+F: Documentation/ABI/testing/debugfs-aufs -+F: Documentation/ABI/testing/sysfs-aufs -+F: fs/aufs/ -+F: include/uapi/linux/aufs_type.h +diff -urNp -x '*.orig' linux-4.9/Documentation/ABI/testing/debugfs-aufs linux-4.9/Documentation/ABI/testing/debugfs-aufs +--- linux-4.9/Documentation/ABI/testing/debugfs-aufs 1970-01-01 01:00:00.000000000 +0100 ++++ linux-4.9/Documentation/ABI/testing/debugfs-aufs 2021-02-24 16:15:09.518240088 +0100 +@@ -0,0 +1,50 @@ ++What: /debug/aufs/si_/ ++Date: March 2009 ++Contact: J. R. Okajima ++Description: ++ Under /debug/aufs, a directory named si_ is created ++ per aufs mount, where is a unique id generated ++ internally. ++ ++What: /debug/aufs/si_/plink ++Date: Apr 2013 ++Contact: J. R. Okajima ++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_/xib ++Date: March 2009 ++Contact: J. R. Okajima ++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_/xino0, xino1 ... xinoN ++Date: March 2009 ++Contact: J. R. Okajima ++Description: ++ It shows the consumed blocks by xino (External Inode Number ++ Translation Table), its link count, 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_/xigen ++Date: March 2009 ++Contact: J. R. Okajima ++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 -urNp -x '*.orig' linux-4.9/Documentation/ABI/testing/sysfs-aufs linux-4.9/Documentation/ABI/testing/sysfs-aufs +--- linux-4.9/Documentation/ABI/testing/sysfs-aufs 1970-01-01 01:00:00.000000000 +0100 ++++ linux-4.9/Documentation/ABI/testing/sysfs-aufs 2021-02-24 16:15:09.518240088 +0100 +@@ -0,0 +1,31 @@ ++What: /sys/fs/aufs/si_/ ++Date: March 2009 ++Contact: J. R. Okajima ++Description: ++ Under /sys/fs/aufs, a directory named si_ is created ++ per aufs mount, where is a unique id generated ++ internally. ++ ++What: /sys/fs/aufs/si_/br0, br1 ... brN ++Date: March 2009 ++Contact: J. R. Okajima ++Description: ++ It shows the abolute path of a member directory (which ++ is called branch) in aufs, and its permission. ++ ++What: /sys/fs/aufs/si_/brid0, brid1 ... bridN ++Date: July 2013 ++Contact: J. R. Okajima ++Description: ++ It shows the id of a member directory (which is called ++ branch) in aufs. ++ ++What: /sys/fs/aufs/si_/xi_path ++Date: March 2009 ++Contact: J. R. Okajima ++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 -urNp -x '*.orig' linux-4.9/Documentation/filesystems/aufs/README linux-4.9/Documentation/filesystems/aufs/README +--- linux-4.9/Documentation/filesystems/aufs/README 1970-01-01 01:00:00.000000000 +0100 ++++ linux-4.9/Documentation/filesystems/aufs/README 2021-02-24 16:15:09.521573529 +0100 +@@ -0,0 +1,393 @@ ++ ++Aufs4 -- advanced multi layered unification filesystem version 4.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 becomes totally different from ++Unionfs while keeping the basic features. ++Recently, Unionfs Version 2.x series begin taking some of the same ++approaches to aufs1's. ++Unionfs is being developed by Professor Erez Zadok at Stony Brook ++University and his team. ++ ++Aufs4 supports linux-4.0 and later, and for linux-3.x series try aufs3. ++If you want older kernel version support, try aufs2-2.6.git or ++aufs2-standalone.git repository, aufs1 from CVS on SourceForge. ++ ++Note: it becomes clear that "Aufs was rejected. Let's give it up." ++ According to Christoph Hellwig, linux rejects all union-type ++ filesystems but UnionMount. ++ ++ ++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). ++ ++ ++ ++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 /fs/aufs and /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 aufs4. ++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 aufs4, aufs4-linux.git, ++aufs4-standalone.git, and aufs-util.git. Note that there is no "4" in ++"aufs-util.git." ++While the aufs-util is always necessary, you need either of aufs4-linux ++or aufs4-standalone. ++ ++The aufs4-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 aufs4 as an external kernel module. ++Several extra patches are not included in this tree. Only ++aufs4-standalone tree contains them. They are described in the later ++section "Configuration and Compilation." ++ ++On the other hand, the aufs4-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 "aufs4.x" where "x" ++represents the linux kernel version, "linux-4.x". For instance, ++"aufs4.0" is for linux-4.0. For latest "linux-4.x-rcN", use ++"aufs4.x-rcN" branch. ++ ++o aufs4-linux tree ++$ git clone --reference /your/linux/git/tree \ ++ git://github.com/sfjro/aufs4-linux.git aufs4-linux.git ++- if you don't have linux GIT tree, then remove "--reference ..." ++$ cd aufs4-linux.git ++$ git checkout origin/aufs4.0 ++ ++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 aufs4 git://github.com/sfjro/aufs4-linux.git ++$ git fetch aufs4 ++$ git checkout -b my4.0 v4.0 ++$ (add your local change...) ++$ git pull aufs4 aufs4.0 ++- now you have v4.0 + your_changes + aufs4.0 in you my4.0 branch. ++- you may need to solve some conflicts between your_changes and ++ aufs4.0. in this case, git-rerere is recommended so that you can ++ solve the similar conflicts automatically when you upgrade to 4.1 or ++ later in the future. ++ ++o aufs4-standalone tree ++$ git clone git://github.com/sfjro/aufs4-standalone.git aufs4-standalone.git ++$ cd aufs4-standalone.git ++$ git checkout origin/aufs4.0 ++ ++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/aufs4.0 ++ ++Note: The 4.x-rcN branch is to be used with `rc' kernel versions ONLY. ++The minor version number, 'x' in '4.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-4.10" and the "aufs4.10" branch ++does not exist in aufs-util repository, then "aufs4.9", "aufs4.8" ++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 aufs4-linux tree, ++- enable CONFIG_AUFS_FS. ++- set other aufs configurations if necessary. ++ ++For aufs4-standalone tree, ++There are several ways to build. ++ ++1. ++- apply ./aufs4-kbuild.patch to your kernel source files. ++- apply ./aufs4-base.patch too. ++- apply ./aufs4-mmap.patch too. ++- apply ./aufs4-standalone.patch too, if you have a plan to set ++ CONFIG_AUFS_FS=m. otherwise you don't need ./aufs4-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. ++ Note: Since linux-3.9, every filesystem module requires an alias ++ "fs-". You should make sure that "fs-aufs" is listed in your ++ modules.aliases file if you set CONFIG_AUFS_FS=m. ++- 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 ./aufs4-base.patch to your kernel source files. ++- apply ./aufs4-mmap.patch too. ++- apply ./aufs4-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". ++ Note: Since linux-3.9, every filesystem module requires an alias ++ "fs-". You should make sure that "fs-aufs" is listed in your ++ modules.aliases file. ++- 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 aufs4-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 aufs4-standalone.git. They are all ++optional. When you meet some problems, they will help you. ++- aufs4-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 ++ Because aufs is not only an ordinary filesystem (callee of VFS), but ++ also a caller of VFS functions for branch filesystems, subclassing of ++ the internal locks for LOCKDEP is necessary. LOCKDEP is a debugging ++ feature of linux kernel. If you enable CONFIG_LOCKDEP, then you will ++ need to apply this debug patch to expand several constant values. ++ If don't know what LOCKDEP, then you don't have apply this patch. ++ ++ ++4. Usage ++---------------------------------------- ++At first, make sure aufs-util are installed, and please read the aufs ++manual, aufs.5 in aufs-util.git tree. ++$ man -l aufs.5 ++ ++And then, ++$ mkdir /tmp/rw /tmp/aufs ++# mount -t aufs -o br=/tmp/rw:${HOME} none /tmp/aufs ++ ++Here is another example. The result is equivalent. ++# mount -t aufs -o br=/tmp/rw=rw:${HOME}=ro none /tmp/aufs ++ Or ++# mount -t aufs -o br:/tmp/rw none /tmp/aufs ++# mount -o remount,append:${HOME} /tmp/aufs ++ ++Then, you can see whole tree of your home dir through /tmp/aufs. If ++you modify a file under /tmp/aufs, the one on your home directory is ++not affected, instead the same named file will be newly created under ++/tmp/rw. And all of your modification to a file will be applied to ++the one under /tmp/rw. This is called the file based Copy on Write ++(COW) method. ++Aufs mount options are described in aufs.5. ++If you run chroot or something and make your aufs as a root directory, ++then you need to customize the shutdown script. See the aufs manual in ++detail. ++ ++Additionally, there are some sample usages of aufs which are a ++diskless system with network booting, and LiveCD over NFS. ++See sample dir in CVS tree on SourceForge. ++ ++ ++5. Contact ++---------------------------------------- ++When you have any problems or strange behaviour in aufs, please let me ++know with: ++- /proc/mounts (instead of the output of mount(8)) ++- /sys/module/aufs/* ++- /sys/fs/aufs/* (if you have them) ++- /debug/aufs/* (if you have them) ++- linux kernel version ++ if your kernel is not plain, for example modified by distributor, ++ the url where i can download its source is necessary too. ++- aufs version which was printed at loading the module or booting the ++ system, instead of the date you downloaded. ++- configuration (define/undefine CONFIG_AUFS_xxx) ++- kernel configuration or /proc/config.gz (if you have it) ++- behaviour which you think to be incorrect ++- actual operation, reproducible one is better ++- mailto: aufs-users at lists.sourceforge.net ++ ++Usually, I don't watch the Public Areas(Bugs, Support Requests, Patches, ++and Feature Requests) on SourceForge. Please join and write to ++aufs-users ML. ++ ++ ++6. Acknowledgements ++---------------------------------------- ++Thanks to everyone who have tried and are using aufs, whoever ++have reported a bug or any feedback. ++ ++Especially donators: ++Tomas Matejicek(slax.org) made a donation (much more than once). ++ Since Apr 2010, Tomas M (the author of Slax and Linux Live ++ scripts) is making "doubling" donations. ++ Unfortunately I cannot list all of the donators, but I really ++ appreciate. ++ It ends Aug 2010, but the ordinary donation URL is still available. ++ ++Dai Itasaka made a donation (2007/8). ++Chuck Smith made a donation (2008/4, 10 and 12). ++Henk Schoneveld made a donation (2008/9). ++Chih-Wei Huang, ASUS, CTC donated Eee PC 4G (2008/10). ++Francois Dupoux made a donation (2008/11). ++Bruno Cesar Ribas and Luis Carlos Erpen de Bona, C3SL serves public ++ aufs2 GIT tree (2009/2). ++William Grant made a donation (2009/3). ++Patrick Lane made a donation (2009/4). ++The Mail Archive (mail-archive.com) made donations (2009/5). ++Nippy Networks (Ed Wildgoose) made a donation (2009/7). ++New Dream Network, LLC (www.dreamhost.com) made a donation (2009/11). ++Pavel Pronskiy made a donation (2011/2). ++Iridium and Inmarsat satellite phone retailer (www.mailasail.com), Nippy ++ Networks (Ed Wildgoose) made a donation for hardware (2011/3). ++Max Lekomcev (DOM-TV project) made a donation (2011/7, 12, 2012/3, 6 and ++11). ++Sam Liddicott made a donation (2011/9). ++Era Scarecrow made a donation (2013/4). ++Bor Ratajc made a donation (2013/4). ++Alessandro Gorreta made a donation (2013/4). ++POIRETTE Marc made a donation (2013/4). ++Alessandro Gorreta made a donation (2013/4). ++lauri kasvandik made a donation (2013/5). ++"pemasu from Finland" made a donation (2013/7). ++The Parted Magic Project made a donation (2013/9 and 11). ++Pavel Barta made a donation (2013/10). ++Nikolay Pertsev made a donation (2014/5). ++James B made a donation (2014/7 and 2015/7). ++Stefano Di Biase made a donation (2014/8). ++Daniel Epellei made a donation (2015/1). ++OmegaPhil made a donation (2016/1). ++Tomasz Szewczyk made a donation (2016/4). ++James Burry made a donation (2016/12). ++ ++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 -urNp -x '*.orig' linux-4.9/Documentation/filesystems/aufs/design/01intro.txt linux-4.9/Documentation/filesystems/aufs/design/01intro.txt +--- linux-4.9/Documentation/filesystems/aufs/design/01intro.txt 1970-01-01 01:00:00.000000000 +0100 ++++ linux-4.9/Documentation/filesystems/aufs/design/01intro.txt 2021-02-24 16:15:09.518240088 +0100 +@@ -0,0 +1,171 @@ ++ ++# Copyright (C) 2005-2018 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 . ++ ++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 -urNp -x '*.orig' linux-4.9/Documentation/filesystems/aufs/design/02struct.txt linux-4.9/Documentation/filesystems/aufs/design/02struct.txt +--- linux-4.9/Documentation/filesystems/aufs/design/02struct.txt 1970-01-01 01:00:00.000000000 +0100 ++++ linux-4.9/Documentation/filesystems/aufs/design/02struct.txt 2021-02-24 16:15:09.518240088 +0100 +@@ -0,0 +1,258 @@ ++ ++# Copyright (C) 2005-2018 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 . ++ ++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 -urNp -x '*.orig' linux-4.9/Documentation/filesystems/aufs/design/03atomic_open.txt linux-4.9/Documentation/filesystems/aufs/design/03atomic_open.txt +--- linux-4.9/Documentation/filesystems/aufs/design/03atomic_open.txt 1970-01-01 01:00:00.000000000 +0100 ++++ linux-4.9/Documentation/filesystems/aufs/design/03atomic_open.txt 2021-02-24 16:15:09.518240088 +0100 +@@ -0,0 +1,85 @@ ++ ++# Copyright (C) 2015-2018 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 . ++ ++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 -urNp -x '*.orig' linux-4.9/Documentation/filesystems/aufs/design/03lookup.txt linux-4.9/Documentation/filesystems/aufs/design/03lookup.txt +--- linux-4.9/Documentation/filesystems/aufs/design/03lookup.txt 1970-01-01 01:00:00.000000000 +0100 ++++ linux-4.9/Documentation/filesystems/aufs/design/03lookup.txt 2021-02-24 16:15:09.518240088 +0100 +@@ -0,0 +1,113 @@ ++ ++# Copyright (C) 2005-2018 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 . + - AUXILIARY DISPLAY DRIVERS - M: Miguel Ojeda Sandonis - W: http://miguelojeda.es/auxdisplay.htm -diff --git a/drivers/block/loop.c b/drivers/block/loop.c -index fa1b7a9..6ee9235 100644 ---- a/drivers/block/loop.c -+++ b/drivers/block/loop.c -@@ -701,6 +701,24 @@ static inline int is_loop_device(struct file *file) - return i && S_ISBLK(i->i_mode) && MAJOR(i->i_rdev) == LOOP_MAJOR; - } - -+/* -+ * for AUFS -+ * no get/put for file. -+ */ -+struct file *loop_backing_file(struct super_block *sb) -+{ -+ struct file *ret; -+ struct loop_device *l; ++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. + -+ ret = NULL; -+ if (MAJOR(sb->s_dev) == LOOP_MAJOR) { -+ l = sb->s_bdev->bd_disk->private_data; -+ ret = l->lo_backing_file; -+ } -+ return ret; ++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 -urNp -x '*.orig' linux-4.9/Documentation/filesystems/aufs/design/04branch.txt linux-4.9/Documentation/filesystems/aufs/design/04branch.txt +--- linux-4.9/Documentation/filesystems/aufs/design/04branch.txt 1970-01-01 01:00:00.000000000 +0100 ++++ linux-4.9/Documentation/filesystems/aufs/design/04branch.txt 2021-02-24 16:15:09.518240088 +0100 +@@ -0,0 +1,74 @@ ++ ++# Copyright (C) 2005-2018 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 . ++ ++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 -urNp -x '*.orig' linux-4.9/Documentation/filesystems/aufs/design/05wbr_policy.txt linux-4.9/Documentation/filesystems/aufs/design/05wbr_policy.txt +--- linux-4.9/Documentation/filesystems/aufs/design/05wbr_policy.txt 1970-01-01 01:00:00.000000000 +0100 ++++ linux-4.9/Documentation/filesystems/aufs/design/05wbr_policy.txt 2021-02-24 16:15:09.521573529 +0100 +@@ -0,0 +1,64 @@ ++ ++# Copyright (C) 2005-2018 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 . ++ ++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 -urNp -x '*.orig' linux-4.9/Documentation/filesystems/aufs/design/06dirren.dot linux-4.9/Documentation/filesystems/aufs/design/06dirren.dot +--- linux-4.9/Documentation/filesystems/aufs/design/06dirren.dot 1970-01-01 01:00:00.000000000 +0100 ++++ linux-4.9/Documentation/filesystems/aufs/design/06dirren.dot 2021-02-24 16:15:09.521573529 +0100 +@@ -0,0 +1,31 @@ ++ ++// to view this graph, run dot(1) command in GRAPHVIZ. ++ ++digraph G { ++node [shape=box]; ++whinfo [label="detailed info file\n(lower_brid_root-hinum, h_inum, namelen, old name)"]; ++ ++node [shape=oval]; ++ ++aufs_rename -> whinfo [label="store/remove"]; ++ ++node [shape=oval]; ++inode_list [label="h_inum list in branch\ncache"]; ++ ++node [shape=box]; ++whinode [label="h_inum list file"]; ++ ++node [shape=oval]; ++brmgmt [label="br_add/del/mod/umount"]; ++ ++brmgmt -> inode_list [label="create/remove"]; ++brmgmt -> whinode [label="load/store"]; ++ ++inode_list -> whinode [style=dashed,dir=both]; ++ ++aufs_rename -> inode_list [label="add/del"]; ++ ++aufs_lookup -> inode_list [label="search"]; ++ ++aufs_lookup -> whinfo [label="load/remove"]; +} -+EXPORT_SYMBOL_GPL(loop_backing_file); +diff -urNp -x '*.orig' linux-4.9/Documentation/filesystems/aufs/design/06dirren.txt linux-4.9/Documentation/filesystems/aufs/design/06dirren.txt +--- linux-4.9/Documentation/filesystems/aufs/design/06dirren.txt 1970-01-01 01:00:00.000000000 +0100 ++++ linux-4.9/Documentation/filesystems/aufs/design/06dirren.txt 2021-02-24 16:15:09.521573529 +0100 +@@ -0,0 +1,102 @@ + - /* 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 5c7cc95..df0268c 100644 ---- a/fs/dcache.c -+++ b/fs/dcache.c -@@ -1164,7 +1164,7 @@ enum d_walk_ret { - * - * The @enter() and @finish() 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 *), - void (*finish)(void *)) - { -diff --git a/fs/fcntl.c b/fs/fcntl.c -index 350a2c8..6f42279 100644 ---- a/fs/fcntl.c -+++ b/fs/fcntl.c -@@ -29,7 +29,7 @@ - - #define SETFL_MASK (O_APPEND | O_NONBLOCK | O_NDELAY | O_DIRECT | O_NOATIME) - --static int setfl(int fd, struct file * filp, unsigned long arg) -+int setfl(int fd, struct file * filp, unsigned long arg) - { - struct inode * inode = file_inode(filp); - int error = 0; -@@ -60,6 +60,8 @@ static int setfl(int fd, struct file * filp, unsigned long arg) - - if (filp->f_op->check_flags) - error = filp->f_op->check_flags(arg); -+ if (!error && filp->f_op->setfl) -+ error = filp->f_op->setfl(filp, arg); - if (error) - return error; - -diff --git a/fs/inode.c b/fs/inode.c -index 88110fd..9a9ba3a 100644 ---- a/fs/inode.c -+++ b/fs/inode.c -@@ -1642,7 +1642,7 @@ int generic_update_time(struct inode *inode, struct timespec *time, int flags) - * This does the actual work of updating an inodes time or version. Must have - * had called mnt_want_write() before calling this. - */ --static int update_time(struct inode *inode, struct timespec *time, int flags) -+int update_time(struct inode *inode, struct timespec *time, int flags) - { - int (*update_time)(struct inode *, struct timespec *, int); - -diff --git a/fs/read_write.c b/fs/read_write.c -index 190e0d36..4052813 100644 ---- a/fs/read_write.c -+++ b/fs/read_write.c -@@ -515,6 +515,28 @@ ssize_t __vfs_write(struct file *file, const char __user *p, size_t count, - } - EXPORT_SYMBOL(__vfs_write); - -+vfs_readf_t vfs_readf(struct file *file) -+{ -+ const struct file_operations *fop = file->f_op; ++# Copyright (C) 2017-2018 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 . ++ ++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. ++2. the inode-number list of directories on a branch ++ path: /rw/dirB/$AUFS_WH_DR_BRHINO ++ ++The filename of "detailed info per directory" represents the lower ++branch, and its format is ++- a type of the branch id ++ one of these. ++ + uuid (not implemented yet) ++ + fsid ++ + dev ++- the inode-number of the branch root dir ++ ++And it contains these info in a single regular file. ++- magic number ++- branch's inode-number of the logically renamed dir ++- the name of the before-renamed dir ++ ++The "detailed info per directory" file is created in aufs rename(2), and ++loaded in any lookup. ++The info is considered in lookup for the matching case only. Here ++"matching" means that the root of branch (in the info filename) is same ++to the current looking-up branch. After looking-up the before-renamed ++name, the inode-number is compared. And the matched dentry is used. ++ ++The "inode-number list of directories" is a regular file which contains ++simply the inode-numbers on the branch. The file is created or updated ++in removing the branch, and loaded in adding the branch. Its lifetime is ++equal to the branch. ++The list is refered in lookup, and when the current target inode is ++found in the list, the aufs tries loading the "detailed info per ++directory" and get the changed and valid name of the dir. ++ ++Theoretically these "extra informaiton" may be able to be put into XATTR ++in the dir inode. But aufs doesn't choose this way because ++1. XATTR may not be supported by the branch (or its configuration) ++2. XATTR may have its size limit. ++3. XATTR may be less easy to convert than a regular file, when the ++ format of the info is changed in the future. ++At the same time, I agree that the regular file approach is much slower ++than XATTR approach. So, in the future, aufs may take the XATTR or other ++better approach. ++ ++This DIRREN feature is enabled by aufs configuration, and is activated ++by a new mount option. ++ ++For the more complicated case, there is a work with UDBA option, which ++is to dected the direct access to the branches (by-passing aufs) and to ++maintain the cashes in aufs. Since a single cached aufs dentry may ++contains two names, before- and after-rename, the name comparision in ++UDBA handler may not work correctly. In this case, the behaviour will be ++equivalen to udba=reval case. +diff -urNp -x '*.orig' linux-4.9/Documentation/filesystems/aufs/design/06fhsm.txt linux-4.9/Documentation/filesystems/aufs/design/06fhsm.txt +--- linux-4.9/Documentation/filesystems/aufs/design/06fhsm.txt 1970-01-01 01:00:00.000000000 +0100 ++++ linux-4.9/Documentation/filesystems/aufs/design/06fhsm.txt 2021-02-24 16:15:09.521573529 +0100 +@@ -0,0 +1,120 @@ ++ ++# Copyright (C) 2011-2018 Junjiro R. Okajima ++# ++# This program is free software; you can redistribute it and/or modify ++# it under the terms of the GNU General Public License as published by ++# the Free Software Foundation; either version 2 of the License, or ++# (at your option) any later version. ++# ++# This program is distributed in the hope that it will be useful, ++# but WITHOUT ANY WARRANTY; without even the implied warranty of ++# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the ++# GNU General Public License for more details. ++# ++# You should have received a copy of the GNU General Public License ++# along with this program; if not, write to the Free Software ++# Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA ++ ++ ++File-based Hierarchical Storage Management (FHSM) ++---------------------------------------------------------------------- ++Hierarchical Storage Management (or HSM) is a well-known feature in the ++storage world. Aufs provides this feature as file-based with multiple ++writable branches, based upon the principle of "Colder, the Lower". ++Here the word "colder" means that the less used files, and "lower" means ++that the position in the order of the stacked branches vertically. ++These multiple writable branches are prioritized, ie. the topmost one ++should be the fastest drive and be used heavily. ++ ++o Characters in aufs FHSM story ++- aufs itself and a new branch attribute. ++- a new ioctl interface to move-down and to establish a connection with ++ the daemon ("move-down" is a converse of "copy-up"). ++- userspace tool and daemon. ++ ++The userspace daemon establishes a connection with aufs and waits for ++the notification. The notified information is very similar to struct ++statfs containing the number of consumed blocks and inodes. ++When the consumed blocks/inodes of a branch exceeds the user-specified ++upper watermark, the daemon activates its move-down process until the ++consumed blocks/inodes reaches the user-specified lower watermark. ++ ++The actual move-down is done by aufs based upon the request from ++user-space since we need to maintain the inode number and the internal ++pointer arrays in aufs. ++ ++Currently aufs FHSM handles the regular files only. Additionally they ++must not be hard-linked nor pseudo-linked. ++ ++ ++o Cowork of aufs and the user-space daemon ++ During the userspace daemon established the connection, aufs sends a ++ small notification to it whenever aufs writes something into the ++ writable branch. But it may cost high since aufs issues statfs(2) ++ internally. So user can specify a new option to cache the ++ info. Actually the notification is controlled by these factors. ++ + the specified cache time. ++ + classified as "force" by aufs internally. ++ Until the specified time expires, aufs doesn't send the info ++ except the forced cases. When aufs decide forcing, the info is always ++ notified to userspace. ++ For example, the number of free inodes is generally large enough and ++ the shortage of it happens rarely. So aufs doesn't force the ++ notification when creating a new file, directory and others. This is ++ the typical case which aufs doesn't force. ++ When aufs writes the actual filedata and the files consumes any of new ++ blocks, the aufs forces notifying. ++ ++ ++o Interfaces in aufs ++- New branch attribute. ++ + fhsm ++ Specifies that the branch is managed by FHSM feature. In other word, ++ participant in the FHSM. ++ When nofhsm is set to the branch, it will not be the source/target ++ branch of the move-down operation. This attribute is set ++ independently from coo and moo attributes, and if you want full ++ FHSM, you should specify them as well. ++- New mount option. ++ + fhsm_sec ++ Specifies a second to suppress many less important info to be ++ notified. ++- New ioctl. ++ + AUFS_CTL_FHSM_FD ++ create a new file descriptor which userspace can read the notification ++ (a subset of struct statfs) from aufs. ++- Module parameter 'brs' ++ It has to be set to 1. Otherwise the new mount option 'fhsm' will not ++ be set. ++- mount helpers /sbin/mount.aufs and /sbin/umount.aufs ++ When there are two or more branches with fhsm attributes, ++ /sbin/mount.aufs invokes the user-space daemon and /sbin/umount.aufs ++ terminates it. As a result of remounting and branch-manipulation, the ++ number of branches with fhsm attribute can be one. In this case, ++ /sbin/mount.aufs will terminate the user-space daemon. ++ ++ ++Finally the operation is done as these steps in kernel-space. ++- make sure that, ++ + no one else is using the file. ++ + the file is not hard-linked. ++ + the file is not pseudo-linked. ++ + the file is a regular file. ++ + the parent dir is not opaqued. ++- find the target writable branch. ++- make sure the file is not whiteout-ed by the upper (than the target) ++ branch. ++- make the parent dir on the target branch. ++- mutex lock the inode on the branch. ++- unlink the whiteout on the target branch (if exists). ++- lookup and create the whiteout-ed temporary name on the target branch. ++- copy the file as the whiteout-ed temporary name on the target branch. ++- rename the whiteout-ed temporary name to the original name. ++- unlink the file on the source branch. ++- maintain the internal pointer array and the external inode number ++ table (XINO). ++- maintain the timestamps and other attributes of the parent dir and the ++ file. ++ ++And of course, in every step, an error may happen. So the operation ++should restore the original file state after an error happens. +diff -urNp -x '*.orig' linux-4.9/Documentation/filesystems/aufs/design/06mmap.txt linux-4.9/Documentation/filesystems/aufs/design/06mmap.txt +--- linux-4.9/Documentation/filesystems/aufs/design/06mmap.txt 1970-01-01 01:00:00.000000000 +0100 ++++ linux-4.9/Documentation/filesystems/aufs/design/06mmap.txt 2021-02-24 16:15:09.521573529 +0100 +@@ -0,0 +1,72 @@ ++ ++# Copyright (C) 2005-2018 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 . ++ ++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. + -+ if (fop->read) -+ return fop->read; -+ if (fop->read_iter) -+ return new_sync_read; -+ return ERR_PTR(-ENOSYS); -+} ++I have to give up this "looks-smater" approach. +diff -urNp -x '*.orig' linux-4.9/Documentation/filesystems/aufs/design/06xattr.txt linux-4.9/Documentation/filesystems/aufs/design/06xattr.txt +--- linux-4.9/Documentation/filesystems/aufs/design/06xattr.txt 1970-01-01 01:00:00.000000000 +0100 ++++ linux-4.9/Documentation/filesystems/aufs/design/06xattr.txt 2021-02-24 16:15:09.521573529 +0100 +@@ -0,0 +1,96 @@ + -+vfs_writef_t vfs_writef(struct file *file) -+{ -+ const struct file_operations *fop = file->f_op; ++# Copyright (C) 2014-2018 Junjiro R. Okajima ++# ++# This program is free software; you can redistribute it and/or modify ++# it under the terms of the GNU General Public License as published by ++# the Free Software Foundation; either version 2 of the License, or ++# (at your option) any later version. ++# ++# This program is distributed in the hope that it will be useful, ++# but WITHOUT ANY WARRANTY; without even the implied warranty of ++# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the ++# GNU General Public License for more details. ++# ++# You should have received a copy of the GNU General Public License ++# along with this program; if not, write to the Free Software ++# Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA + -+ if (fop->write) -+ return fop->write; -+ if (fop->write_iter) -+ return new_sync_write; -+ return ERR_PTR(-ENOSYS); -+} + - ssize_t __kernel_write(struct file *file, const char *buf, size_t count, loff_t *pos) - { - mm_segment_t old_fs; -diff --git a/fs/splice.c b/fs/splice.c -index 5a7750b..28160a7 100644 ---- a/fs/splice.c -+++ b/fs/splice.c -@@ -855,8 +855,8 @@ ssize_t generic_splice_sendpage(struct pipe_inode_info *pipe, struct file *out, - /* - * Attempt to initiate a splice from pipe to file. - */ --static long do_splice_from(struct pipe_inode_info *pipe, struct file *out, -- loff_t *ppos, size_t len, unsigned int flags) -+long do_splice_from(struct pipe_inode_info *pipe, struct file *out, -+ loff_t *ppos, size_t len, unsigned int flags) - { - ssize_t (*splice_write)(struct pipe_inode_info *, struct file *, - loff_t *, size_t, unsigned int); -@@ -872,9 +872,9 @@ static long do_splice_from(struct pipe_inode_info *pipe, struct file *out, - /* - * Attempt to initiate a splice from a file to a pipe. - */ --static long do_splice_to(struct file *in, loff_t *ppos, -- struct pipe_inode_info *pipe, size_t len, -- unsigned int flags) -+long do_splice_to(struct file *in, loff_t *ppos, -+ struct pipe_inode_info *pipe, size_t len, -+ unsigned int flags) - { - ssize_t (*splice_read)(struct file *, loff_t *, - struct pipe_inode_info *, size_t, unsigned int); -diff --git a/include/linux/file.h b/include/linux/file.h -index 7444f5f..bdac0be 100644 ---- a/include/linux/file.h -+++ b/include/linux/file.h -@@ -19,6 +19,7 @@ - struct path; - extern struct file *alloc_file(struct path *, fmode_t mode, - const struct file_operations *fop); -+extern struct file *get_empty_filp(void); - - static inline void fput_light(struct file *file, int fput_needed) - { -diff --git a/include/linux/fs.h b/include/linux/fs.h -index dc0478c..27c05e7 100644 ---- a/include/linux/fs.h -+++ b/include/linux/fs.h -@@ -1291,6 +1291,7 @@ struct fasync_struct { - /* can be called from interrupts */ - extern void kill_fasync(struct fasync_struct **, int, int); - -+extern int setfl(int fd, struct file * filp, unsigned long arg); - extern void __f_setown(struct file *filp, struct pid *, enum pid_type, int force); - extern void f_setown(struct file *filp, unsigned long arg, int force); - extern void f_delown(struct file *filp); -@@ -1715,6 +1716,7 @@ struct file_operations { - ssize_t (*sendpage) (struct file *, struct page *, int, size_t, loff_t *, int); - unsigned long (*get_unmapped_area)(struct file *, unsigned long, unsigned long, unsigned long, unsigned long); - int (*check_flags)(int); -+ int (*setfl)(struct file *, unsigned long); - int (*flock) (struct file *, int, struct file_lock *); - ssize_t (*splice_write)(struct pipe_inode_info *, struct file *, loff_t *, size_t, unsigned int); - ssize_t (*splice_read)(struct file *, loff_t *, struct pipe_inode_info *, size_t, unsigned int); -@@ -1768,6 +1770,12 @@ ssize_t rw_copy_check_uvector(int type, const struct iovec __user * uvector, - struct iovec *fast_pointer, - struct iovec **ret_pointer); - -+typedef ssize_t (*vfs_readf_t)(struct file *, char __user *, size_t, loff_t *); -+typedef ssize_t (*vfs_writef_t)(struct file *, const char __user *, size_t, -+ loff_t *); -+vfs_readf_t vfs_readf(struct file *file); -+vfs_writef_t vfs_writef(struct file *file); ++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. + - extern ssize_t __vfs_read(struct file *, char __user *, size_t, loff_t *); - extern ssize_t __vfs_write(struct file *, const char __user *, size_t, loff_t *); - extern ssize_t vfs_read(struct file *, char __user *, size_t, loff_t *); -@@ -2140,6 +2148,7 @@ extern int iterate_mounts(int (*)(struct vfsmount *, void *), void *, - extern void ihold(struct inode * inode); - extern void iput(struct inode *); - extern int generic_update_time(struct inode *, struct timespec *, int); -+extern int update_time(struct inode *, struct timespec *, int); - - /* /sys/fs */ - extern struct kobject *fs_kobj; -diff --git a/include/linux/splice.h b/include/linux/splice.h -index 00a2116..1f0a4a2 100644 ---- a/include/linux/splice.h -+++ b/include/linux/splice.h -@@ -86,4 +86,10 @@ extern ssize_t splice_direct_to_actor(struct file *, struct splice_desc *, - - extern const struct pipe_buf_operations page_cache_pipe_buf_ops; - extern const struct pipe_buf_operations default_pipe_buf_ops; ++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, + -+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 -aufs4.9 mmap patch - -diff --git a/fs/proc/base.c b/fs/proc/base.c -index ca651ac..0e8551a 100644 ---- a/fs/proc/base.c -+++ b/fs/proc/base.c -@@ -1953,7 +1953,7 @@ static int map_files_get_link(struct dentry *dentry, struct path *path) - down_read(&mm->mmap_sem); - vma = find_exact_vma(mm, vm_start, vm_end); - if (vma && vma->vm_file) { -- *path = vma->vm_file->f_path; -+ *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 f8595e8..cb8eda0 100644 ---- a/fs/proc/nommu.c -+++ b/fs/proc/nommu.c -@@ -45,7 +45,10 @@ 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 35b92d8..5b981db 100644 ---- a/fs/proc/task_mmu.c -+++ b/fs/proc/task_mmu.c -@@ -291,7 +291,10 @@ static int is_stack(struct proc_maps_private *priv, - const char *name = NULL; - - if (file) { -- struct inode *inode = file_inode(vma->vm_file); -+ struct inode *inode; ++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. + -+ 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; -@@ -1627,7 +1630,7 @@ static int show_numa_map(struct seq_file *m, void *v, int is_pid) - 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; - struct mm_walk walk = { - .hugetlb_entry = gather_hugetlb_stats, -diff --git a/fs/proc/task_nommu.c b/fs/proc/task_nommu.c -index 3717562..6a328f1 100644 ---- a/fs/proc/task_nommu.c -+++ b/fs/proc/task_nommu.c -@@ -155,7 +155,10 @@ 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; ++Moreover there are some other categories. Aufs handles these rather ++unpopular categories as the ordinary ones, ie. there is no special ++condition nor exception. + -+ 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 a92c8d7..1d83a2a 100644 ---- a/include/linux/mm.h -+++ b/include/linux/mm.h -@@ -1266,6 +1266,28 @@ static inline int fixup_user_fault(struct task_struct *tsk, - } - #endif - -+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); ++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. + -+#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__) ++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. + -+#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); ++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. + -+#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 */ ++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"). + - 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 4a8aced..badd16b 100644 ---- a/include/linux/mm_types.h -+++ b/include/linux/mm_types.h -@@ -275,6 +275,7 @@ 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 */ -+ struct file *vm_prfile; /* the virtual backing file or NULL */ - - int vm_usage; /* region usage count (access under nommu_region_sem) */ - bool vm_icache_flushed : 1; /* true if the icache has been flushed for -@@ -349,6 +350,7 @@ 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). */ -+ struct file *vm_prfile; /* shadow of vm_file */ - void * vm_private_data; /* was vm_pte (shared mem) */ - - #ifndef CONFIG_MMU -diff --git a/kernel/fork.c b/kernel/fork.c -index 997ac1d..4d0131b 100644 ---- a/kernel/fork.c -+++ b/kernel/fork.c -@@ -624,7 +624,7 @@ static __latent_entropy int dup_mmap(struct mm_struct *mm, - struct inode *inode = file_inode(file); - struct address_space *mapping = file->f_mapping; - -- get_file(file); -+ vma_get_file(tmp); - if (tmp->vm_flags & VM_DENYWRITE) - atomic_dec(&inode->i_writecount); - i_mmap_lock_write(mapping); -diff --git a/mm/Makefile b/mm/Makefile -index 295bd7a..14fa1c8 100644 ---- a/mm/Makefile -+++ b/mm/Makefile -@@ -37,7 +37,7 @@ obj-y := filemap.o mempool.o oom_kill.o \ - mm_init.o mmu_context.o percpu.o slab_common.o \ - compaction.o vmacache.o \ - interval_tree.o list_lru.o workingset.o \ -- debug.o $(mmu-y) -+ prfile.o debug.o $(mmu-y) - - obj-y += init-mm.o - -diff --git a/mm/filemap.c b/mm/filemap.c -index 50b52fe..9e607f9 100644 ---- a/mm/filemap.c -+++ b/mm/filemap.c -@@ -2304,7 +2304,7 @@ int filemap_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf) - int ret = VM_FAULT_LOCKED; - - sb_start_pagefault(inode->i_sb); -- file_update_time(vma->vm_file); -+ vma_file_update_time(vma); - lock_page(page); - if (page->mapping != inode->i_mapping) { - unlock_page(page); -diff --git a/mm/memory.c b/mm/memory.c -index e18c57b..7be4a39 100644 ---- a/mm/memory.c -+++ b/mm/memory.c -@@ -2117,7 +2117,7 @@ static inline int wp_page_reuse(struct fault_env *fe, pte_t orig_pte, - } - - if (!page_mkwrite) -- file_update_time(vma->vm_file); -+ vma_file_update_time(vma); - } - - return VM_FAULT_WRITE; -diff --git a/mm/mmap.c b/mm/mmap.c -index 1af87c1..95b0ff4 100644 ---- a/mm/mmap.c -+++ b/mm/mmap.c -@@ -170,7 +170,7 @@ static struct vm_area_struct *remove_vma(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); - mpol_put(vma_policy(vma)); - kmem_cache_free(vm_area_cachep, vma); - return next; -@@ -879,7 +879,7 @@ int __vma_adjust(struct vm_area_struct *vma, unsigned long start, - if (remove_next) { - if (file) { - uprobe_munmap(next, next->vm_start, next->vm_end); -- fput(file); -+ vma_fput(vma); - } - if (next->anon_vma) - anon_vma_merge(vma, next); -@@ -1727,8 +1727,8 @@ unsigned long mmap_region(struct file *file, unsigned long addr, - return addr; - - unmap_and_free_vma: -+ vma_fput(vma); - vma->vm_file = NULL; -- fput(file); - - /* Undo any partial mapping done by a device driver. */ - unmap_region(mm, vma, prev, vma->vm_start, vma->vm_end); -@@ -2533,7 +2533,7 @@ static int __split_vma(struct mm_struct *mm, 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); -@@ -2552,7 +2552,7 @@ static int __split_vma(struct mm_struct *mm, struct vm_area_struct *vma, - if (new->vm_ops && new->vm_ops->close) - new->vm_ops->close(new); - if (new->vm_file) -- fput(new->vm_file); -+ vma_fput(new); - unlink_anon_vmas(new); - out_free_mpol: - mpol_put(vma_policy(new)); -@@ -2703,7 +2703,7 @@ int vm_munmap(unsigned long start, size_t len) - struct vm_area_struct *vma; - unsigned long populate = 0; - unsigned long ret = -EINVAL; -- struct file *file; -+ struct file *file, *prfile; - - pr_warn_once("%s (%d) uses deprecated remap_file_pages() syscall. See Documentation/vm/remap_file_pages.txt.\n", - current->comm, current->pid); -@@ -2778,10 +2778,27 @@ int vm_munmap(unsigned long start, size_t len) - } - } - -- file = get_file(vma->vm_file); -+ vma_get_file(vma); -+ file = vma->vm_file; -+ prfile = vma->vm_prfile; - ret = do_mmap_pgoff(vma->vm_file, start, size, - prot, flags, pgoff, &populate); -+ if (!IS_ERR_VALUE(ret) && file && prfile) { -+ struct vm_area_struct *new_vma; ++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. + -+ new_vma = find_vma(mm, ret); -+ if (!new_vma->vm_prfile) -+ new_vma->vm_prfile = prfile; -+ if (new_vma != vma) -+ get_file(prfile); -+ } -+ /* -+ * two fput()s instead of vma_fput(vma), -+ * coz vma may not be available anymore. -+ */ - fput(file); -+ if (prfile) -+ fput(prfile); - out: - up_write(&mm->mmap_sem); - if (populate) -@@ -3056,7 +3073,7 @@ 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); - vma_link(mm, new_vma, prev, rb_link, rb_parent); -diff --git a/mm/nommu.c b/mm/nommu.c -index 8b8faaf..5d26ed94 100644 ---- a/mm/nommu.c -+++ b/mm/nommu.c -@@ -636,7 +636,7 @@ 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 */ -@@ -794,7 +794,7 @@ 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); - kmem_cache_free(vm_area_cachep, vma); - } -@@ -1320,7 +1320,7 @@ 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; -@@ -1395,10 +1395,10 @@ unsigned long do_mmap(struct file *file, - up_write(&nommu_region_sem); - error: - 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); - kmem_cache_free(vm_area_cachep, vma); - return ret; - -diff --git a/mm/prfile.c b/mm/prfile.c -new file mode 100644 -index 0000000..b323b8a ---- /dev/null -+++ b/mm/prfile.c -@@ -0,0 +1,86 @@ -+/* -+ * Mainly for aufs which mmap(2) diffrent 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 Junjro R. Okajima -+ * Copyright (c) 2014 Ian Campbell -+ */ ++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 -urNp -x '*.orig' linux-4.9/Documentation/filesystems/aufs/design/07export.txt linux-4.9/Documentation/filesystems/aufs/design/07export.txt +--- linux-4.9/Documentation/filesystems/aufs/design/07export.txt 1970-01-01 01:00:00.000000000 +0100 ++++ linux-4.9/Documentation/filesystems/aufs/design/07export.txt 2021-02-24 16:15:09.521573529 +0100 +@@ -0,0 +1,58 @@ + -+#include -+#include -+#include ++# Copyright (C) 2005-2018 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 . + -+/* #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, %s\n", func, line, func2, -+ f ? (char *)f->f_path.dentry->d_name.name : "(null)"); -+#endif -+} ++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 -urNp -x '*.orig' linux-4.9/Documentation/filesystems/aufs/design/08shwh.txt linux-4.9/Documentation/filesystems/aufs/design/08shwh.txt +--- linux-4.9/Documentation/filesystems/aufs/design/08shwh.txt 1970-01-01 01:00:00.000000000 +0100 ++++ linux-4.9/Documentation/filesystems/aufs/design/08shwh.txt 2021-02-24 16:15:09.521573529 +0100 +@@ -0,0 +1,52 @@ + -+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; ++# Copyright (C) 2005-2018 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 . + -+ prfile_trace(f, pr, func, line, __func__); -+ file_update_time(f); -+ if (f && pr) -+ file_update_time(pr); -+} ++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. + -+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; ++(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 + -+ prfile_trace(f, pr, func, line, __func__); -+ return (f && pr) ? pr : f; -+} ++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. + -+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; ++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 + -+ prfile_trace(f, pr, func, line, __func__); -+ get_file(f); -+ if (f && pr) -+ get_file(pr); -+} ++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 + -+void vma_do_fput(struct vm_area_struct *vma, const char func[], int line) -+{ -+ struct file *f = vma->vm_file, *pr = vma->vm_prfile; ++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 -urNp -x '*.orig' linux-4.9/Documentation/filesystems/aufs/design/10dynop.txt linux-4.9/Documentation/filesystems/aufs/design/10dynop.txt +--- linux-4.9/Documentation/filesystems/aufs/design/10dynop.txt 1970-01-01 01:00:00.000000000 +0100 ++++ linux-4.9/Documentation/filesystems/aufs/design/10dynop.txt 2021-02-24 16:15:09.521573529 +0100 +@@ -0,0 +1,47 @@ + -+ prfile_trace(f, pr, func, line, __func__); -+ fput(f); -+ if (f && pr) -+ fput(pr); -+} ++# Copyright (C) 2010-2018 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 . + -+#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; ++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. + -+ prfile_trace(f, pr, func, line, __func__); -+ return (f && pr) ? pr : f; -+} ++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. + -+void vmr_do_fput(struct vm_region *region, const char func[], int line) -+{ -+ struct file *f = region->vm_file, *pr = region->vm_prfile; ++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. + -+ prfile_trace(f, pr, func, line, __func__); -+ fput(f); -+ if (f && pr) -+ fput(pr); -+} -+#endif /* !CONFIG_MMU */ -aufs4.9 standalone patch - -diff --git a/fs/dcache.c b/fs/dcache.c -index df0268c..755fea1 100644 ---- a/fs/dcache.c -+++ b/fs/dcache.c -@@ -1272,6 +1272,7 @@ void d_walk(struct dentry *parent, void *data, - seq = 1; - goto again; - } -+EXPORT_SYMBOL_GPL(d_walk); - - /* - * Search for at least 1 mount point in the dentry's subdirs. -@@ -2855,6 +2856,7 @@ 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 4e497b9..e27d323 100644 ---- a/fs/exec.c -+++ b/fs/exec.c -@@ -104,6 +104,7 @@ 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 6f42279..04fd33c 100644 ---- a/fs/fcntl.c -+++ b/fs/fcntl.c -@@ -82,6 +82,7 @@ int setfl(int fd, struct file * filp, unsigned long 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 ad17e05..ae9f267 100644 ---- a/fs/file_table.c -+++ b/fs/file_table.c -@@ -147,6 +147,7 @@ struct file *get_empty_filp(void) - } - return ERR_PTR(-ENFILE); - } -+EXPORT_SYMBOL_GPL(get_empty_filp); - - /** - * alloc_file - allocate and initialize a 'struct file' -@@ -258,6 +259,7 @@ void flush_delayed_fput(void) - { - delayed_fput(NULL); - } -+EXPORT_SYMBOL_GPL(flush_delayed_fput); - - static DECLARE_DELAYED_WORK(delayed_fput_work, delayed_fput); ++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 -urNp -x '*.orig' linux-4.9/MAINTAINERS linux-4.9/MAINTAINERS +--- linux-4.9/MAINTAINERS 2021-02-24 16:14:54.924432098 +0100 ++++ linux-4.9/MAINTAINERS 2021-02-24 16:15:09.504906321 +0100 +@@ -2293,6 +2293,19 @@ F: include/linux/audit.h + F: include/uapi/linux/audit.h + F: kernel/audit* -@@ -300,6 +302,7 @@ void __fput_sync(struct file *file) ++AUFS (advanced multi layered unification filesystem) FILESYSTEM ++M: "J. R. Okajima" ++L: linux-unionfs@vger.kernel.org ++L: aufs-users@lists.sourceforge.net (members only) ++W: http://aufs.sourceforge.net ++T: git://github.com/sfjro/aufs4-linux.git ++S: Supported ++F: Documentation/filesystems/aufs/ ++F: Documentation/ABI/testing/debugfs-aufs ++F: Documentation/ABI/testing/sysfs-aufs ++F: fs/aufs/ ++F: include/uapi/linux/aufs_type.h ++ + AUXILIARY DISPLAY DRIVERS + M: Miguel Ojeda Sandonis + W: http://miguelojeda.es/auxdisplay.htm +diff -urNp -x '*.orig' linux-4.9/drivers/block/loop.c linux-4.9/drivers/block/loop.c +--- linux-4.9/drivers/block/loop.c 2021-02-24 16:14:57.284508877 +0100 ++++ linux-4.9/drivers/block/loop.c 2021-02-24 16:15:09.538240738 +0100 +@@ -552,7 +552,7 @@ static int do_req_filebacked(struct loop } - EXPORT_SYMBOL(fput); -+EXPORT_SYMBOL_GPL(__fput_sync); + struct switch_request { +- struct file *file; ++ struct file *file, *virt_file; + struct completion wait; + }; - void put_filp(struct file *file) +@@ -578,6 +578,7 @@ static void do_loop_switch(struct loop_d + mapping = file->f_mapping; + mapping_set_gfp_mask(old_file->f_mapping, lo->old_gfp_mask); + lo->lo_backing_file = file; ++ lo->lo_backing_virt_file = p->virt_file; + lo->lo_blocksize = S_ISBLK(mapping->host->i_mode) ? + mapping->host->i_bdev->bd_block_size : PAGE_SIZE; + lo->old_gfp_mask = mapping_gfp_mask(mapping); +@@ -590,11 +591,13 @@ static void do_loop_switch(struct loop_d + * First it needs to flush existing IO, it does this by sending a magic + * BIO down the pipe. The completion of this BIO does the actual switch. + */ +-static int loop_switch(struct loop_device *lo, struct file *file) ++static int loop_switch(struct loop_device *lo, struct file *file, ++ struct file *virt_file) { -@@ -308,6 +311,7 @@ void put_filp(struct file *file) - file_free(file); - } - } -+EXPORT_SYMBOL_GPL(put_filp); - - void __init files_init(void) - { -diff --git a/fs/inode.c b/fs/inode.c -index 9a9ba3a..a3a18d8 100644 ---- a/fs/inode.c -+++ b/fs/inode.c -@@ -1651,6 +1651,7 @@ int update_time(struct inode *inode, struct timespec *time, int flags) - - return update_time(inode, time, flags); - } -+EXPORT_SYMBOL_GPL(update_time); + struct switch_request w; - /** - * touch_atime - update the access time -diff --git a/fs/namespace.c b/fs/namespace.c -index e6c234b..8d13f7b 100644 ---- a/fs/namespace.c -+++ b/fs/namespace.c -@@ -466,6 +466,7 @@ void __mnt_drop_write(struct vfsmount *mnt) - mnt_dec_writers(real_mount(mnt)); - preempt_enable(); - } -+EXPORT_SYMBOL_GPL(__mnt_drop_write); + w.file = file; ++ w.virt_file = virt_file; - /** - * mnt_drop_write - give up write access to a mount -@@ -1823,6 +1824,7 @@ int iterate_mounts(int (*f)(struct vfsmount *, void *), void *arg, - } - return 0; + /* freeze queue and wait for completion of scheduled requests */ + blk_mq_freeze_queue(lo->lo_queue); +@@ -616,7 +619,16 @@ static int loop_flush(struct loop_device + /* loop not yet configured, no running thread, nothing to flush */ + if (lo->lo_state != Lo_bound) + return 0; +- return loop_switch(lo, NULL); ++ return loop_switch(lo, NULL, NULL); ++} ++ ++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; } -+EXPORT_SYMBOL_GPL(iterate_mounts); - - static void cleanup_group_ids(struct mount *mnt, struct mount *end) - { -diff --git a/fs/notify/group.c b/fs/notify/group.c -index fbe3cbe..bdfc61e 100644 ---- a/fs/notify/group.c -+++ b/fs/notify/group.c -@@ -22,6 +22,7 @@ - #include - #include - #include -+#include - #include - #include "fsnotify.h" -@@ -100,6 +101,7 @@ void fsnotify_get_group(struct fsnotify_group *group) + static void loop_reread_partitions(struct loop_device *lo, +@@ -683,6 +695,7 @@ static int loop_change_fd(struct loop_de + unsigned int arg) { - atomic_inc(&group->refcnt); - } -+EXPORT_SYMBOL_GPL(fsnotify_get_group); - - /* - * Drop a reference to a group. Free it if it's through. -@@ -109,6 +111,7 @@ void fsnotify_put_group(struct fsnotify_group *group) - if (atomic_dec_and_test(&group->refcnt)) - fsnotify_final_destroy_group(group); - } -+EXPORT_SYMBOL_GPL(fsnotify_put_group); - - /* - * Create a new fsnotify_group and hold a reference for the group returned. -@@ -137,6 +140,7 @@ struct fsnotify_group *fsnotify_alloc_group(const struct fsnotify_ops *ops) - - return group; - } -+EXPORT_SYMBOL_GPL(fsnotify_alloc_group); + struct file *file, *old_file; ++ struct file *f, *virt_file = NULL, *old_virt_file; + struct inode *inode; + int error; - int fsnotify_fasync(int fd, struct file *file, int on) - { -diff --git a/fs/notify/mark.c b/fs/notify/mark.c -index d3fea0b..5fc06ad 100644 ---- a/fs/notify/mark.c -+++ b/fs/notify/mark.c -@@ -113,6 +113,7 @@ void fsnotify_put_mark(struct fsnotify_mark *mark) - mark->free_mark(mark); - } - } -+EXPORT_SYMBOL_GPL(fsnotify_put_mark); +@@ -699,6 +712,12 @@ static int loop_change_fd(struct loop_de + file = fget(arg); + if (!file) + goto out; ++ f = loop_real_file(file); ++ if (f) { ++ virt_file = file; ++ file = f; ++ get_file(file); ++ } - /* Calculate mask of events for a list of marks */ - u32 fsnotify_recalc_mask(struct hlist_head *head) -@@ -230,6 +231,7 @@ void fsnotify_destroy_mark(struct fsnotify_mark *mark, - mutex_unlock(&group->mark_mutex); - fsnotify_free_mark(mark); - } -+EXPORT_SYMBOL_GPL(fsnotify_destroy_mark); + error = loop_validate_file(file, bdev); + if (error) +@@ -706,6 +725,7 @@ static int loop_change_fd(struct loop_de - void fsnotify_destroy_marks(struct hlist_head *head, spinlock_t *lock) - { -@@ -415,6 +417,7 @@ int fsnotify_add_mark_locked(struct fsnotify_mark *mark, + inode = file->f_mapping->host; + old_file = lo->lo_backing_file; ++ old_virt_file = lo->lo_backing_virt_file; - return ret; - } -+EXPORT_SYMBOL_GPL(fsnotify_add_mark); + error = -EINVAL; - int fsnotify_add_mark(struct fsnotify_mark *mark, struct fsnotify_group *group, - struct inode *inode, struct vfsmount *mnt, int allow_dups) -@@ -533,6 +536,7 @@ void fsnotify_init_mark(struct fsnotify_mark *mark, - atomic_set(&mark->refcnt, 1); - mark->free_mark = free_mark; - } -+EXPORT_SYMBOL_GPL(fsnotify_init_mark); +@@ -714,21 +734,43 @@ static int loop_change_fd(struct loop_de + goto out_putf; - /* - * Destroy all marks in destroy_list, waits for SRCU period to finish before -diff --git a/fs/open.c b/fs/open.c -index d3ed817..20d2494 100644 ---- a/fs/open.c -+++ b/fs/open.c -@@ -64,6 +64,7 @@ int do_truncate(struct dentry *dentry, loff_t length, unsigned int time_attrs, - inode_unlock(dentry->d_inode); - return ret; - } -+EXPORT_SYMBOL_GPL(do_truncate); + /* and ... switch */ +- error = loop_switch(lo, file); ++ error = loop_switch(lo, file, virt_file); + if (error) + goto out_putf; - long vfs_truncate(const struct path *path, loff_t length) - { -@@ -695,6 +696,7 @@ int open_check_o_direct(struct file *f) - } + fput(old_file); ++ if (old_virt_file) ++ fput(old_virt_file); + if (lo->lo_flags & LO_FLAGS_PARTSCAN) + loop_reread_partitions(lo, bdev); return 0; - } -+EXPORT_SYMBOL_GPL(open_check_o_direct); - static int do_dentry_open(struct file *f, - struct inode *inode, -diff --git a/fs/read_write.c b/fs/read_write.c -index 4052813..7dfd732 100644 ---- a/fs/read_write.c -+++ b/fs/read_write.c -@@ -525,6 +525,7 @@ vfs_readf_t vfs_readf(struct file *file) - return new_sync_read; - return ERR_PTR(-ENOSYS); - } -+EXPORT_SYMBOL_GPL(vfs_readf); - - vfs_writef_t vfs_writef(struct file *file) - { -@@ -536,6 +537,7 @@ vfs_writef_t vfs_writef(struct file *file) - return new_sync_write; - return ERR_PTR(-ENOSYS); - } -+EXPORT_SYMBOL_GPL(vfs_writef); - - ssize_t __kernel_write(struct file *file, const char *buf, size_t count, loff_t *pos) - { -diff --git a/fs/splice.c b/fs/splice.c -index 28160a7..98c1902 100644 ---- a/fs/splice.c -+++ b/fs/splice.c -@@ -868,6 +868,7 @@ long do_splice_from(struct pipe_inode_info *pipe, struct file *out, - - return splice_write(pipe, out, ppos, len, flags); - } -+EXPORT_SYMBOL_GPL(do_splice_from); - - /* - * Attempt to initiate a splice from a file to a pipe. -@@ -897,6 +898,7 @@ long do_splice_to(struct file *in, loff_t *ppos, - - return splice_read(in, ppos, pipe, len, flags); - } -+EXPORT_SYMBOL_GPL(do_splice_to); - - /** - * splice_direct_to_actor - splices data directly between two non-pipes -diff --git a/fs/xattr.c b/fs/xattr.c -index 2d13b4e..41c2bcd 100644 ---- a/fs/xattr.c -+++ b/fs/xattr.c -@@ -296,6 +296,7 @@ int __vfs_setxattr_noperm(struct dentry *dentry, const char *name, - *xattr_value = value; + out_putf: + fput(file); ++ if (virt_file) ++ fput(virt_file); + out: 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/task_work.c b/kernel/task_work.c -index d513051..e056d54 100644 ---- a/kernel/task_work.c -+++ b/kernel/task_work.c -@@ -119,3 +119,4 @@ void task_work_run(void) - } while (work); - } - } -+EXPORT_SYMBOL_GPL(task_work_run); -diff --git a/security/commoncap.c b/security/commoncap.c -index 8df676f..6b5cc07 100644 ---- a/security/commoncap.c -+++ b/security/commoncap.c -@@ -1061,12 +1061,14 @@ int cap_mmap_addr(unsigned long addr) - } - return ret; - } -+EXPORT_SYMBOL_GPL(cap_mmap_addr); - - int cap_mmap_file(struct file *file, unsigned long reqprot, - unsigned long prot, unsigned long flags) - { - return 0; - } -+EXPORT_SYMBOL_GPL(cap_mmap_file); - - #ifdef CONFIG_SECURITY - -diff --git a/security/device_cgroup.c b/security/device_cgroup.c -index 03c1652..f88c84b 100644 ---- a/security/device_cgroup.c -+++ b/security/device_cgroup.c -@@ -7,6 +7,7 @@ - #include - #include - #include -+#include - #include - #include - #include -@@ -849,6 +850,7 @@ int __devcgroup_inode_permission(struct inode *inode, int mask) - return __devcgroup_check_permission(type, imajor(inode), iminor(inode), - access); - } -+EXPORT_SYMBOL_GPL(__devcgroup_inode_permission); - - int devcgroup_inode_mknod(int mode, dev_t dev) - { -diff --git a/security/security.c b/security/security.c -index f825304..8dd441d 100644 ---- a/security/security.c -+++ b/security/security.c -@@ -443,6 +443,7 @@ 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); - - int security_path_unlink(const struct path *dir, struct dentry *dentry) - { -@@ -459,6 +460,7 @@ 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); - - int security_path_link(struct dentry *old_dentry, const struct path *new_dir, - struct dentry *new_dentry) -@@ -467,6 +469,7 @@ 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); - - int security_path_rename(const struct path *old_dir, struct dentry *old_dentry, - const struct path *new_dir, struct dentry *new_dentry, -@@ -494,6 +497,7 @@ int security_path_truncate(const struct path *path) - return 0; - return call_int_hook(path_truncate, 0, path); - } -+EXPORT_SYMBOL_GPL(security_path_truncate); - - int security_path_chmod(const struct path *path, umode_t mode) - { -@@ -501,6 +505,7 @@ 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); - int security_path_chown(const struct path *path, kuid_t uid, kgid_t gid) - { -@@ -508,6 +513,7 @@ 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); ++/* ++ * 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 */ - int security_path_chroot(const struct path *path) + static ssize_t loop_attr_show(struct device *dev, char *page, +@@ -887,7 +929,7 @@ static int loop_prepare_queue(struct loo + static int loop_set_fd(struct loop_device *lo, fmode_t mode, + struct block_device *bdev, unsigned int arg) { -@@ -593,6 +599,7 @@ int security_inode_readlink(struct dentry *dentry) - return 0; - return call_int_hook(inode_readlink, 0, dentry); - } -+EXPORT_SYMBOL_GPL(security_inode_readlink); +- struct file *file; ++ struct file *file, *f, *virt_file = NULL; + struct inode *inode; + struct address_space *mapping; + unsigned lo_blocksize; +@@ -902,6 +944,12 @@ static int loop_set_fd(struct loop_devic + file = fget(arg); + if (!file) + goto out; ++ f = loop_real_file(file); ++ if (f) { ++ virt_file = file; ++ file = f; ++ get_file(file); ++ } - int security_inode_follow_link(struct dentry *dentry, struct inode *inode, - bool rcu) -@@ -608,6 +615,7 @@ 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); + error = -EBUSY; + if (lo->lo_state != Lo_unbound) +@@ -939,6 +987,7 @@ static int loop_set_fd(struct loop_devic + lo->lo_flags = lo_flags; + lo->lo_xid = vx_current_xid(); + lo->lo_backing_file = file; ++ lo->lo_backing_virt_file = virt_file; + lo->transfer = NULL; + lo->ioctl = NULL; + lo->lo_sizelimit = 0; +@@ -971,6 +1020,8 @@ static int loop_set_fd(struct loop_devic - int security_inode_setattr(struct dentry *dentry, struct iattr *attr) + out_putf: + fput(file); ++ if (virt_file) ++ fput(virt_file); + out: + /* This is safe: open() is still holding a reference. */ + module_put(THIS_MODULE); +@@ -1017,6 +1068,7 @@ loop_init_xfer(struct loop_device *lo, s + static int loop_clr_fd(struct loop_device *lo) { -@@ -779,6 +787,7 @@ int security_file_permission(struct file *file, int mask) + struct file *filp = lo->lo_backing_file; ++ struct file *virt_filp = lo->lo_backing_virt_file; + gfp_t gfp = lo->old_gfp_mask; + struct block_device *bdev = lo->lo_device; - return fsnotify_perm(file, mask); - } -+EXPORT_SYMBOL_GPL(security_file_permission); +@@ -1048,6 +1100,7 @@ static int loop_clr_fd(struct loop_devic + spin_lock_irq(&lo->lo_lock); + lo->lo_state = Lo_rundown; + lo->lo_backing_file = NULL; ++ lo->lo_backing_virt_file = NULL; + spin_unlock_irq(&lo->lo_lock); - int security_file_alloc(struct file *file) - { -@@ -838,6 +847,7 @@ int security_mmap_file(struct file *file, unsigned long prot, - return ret; - return ima_file_mmap(file, prot); + loop_release_xfer(lo); +@@ -1093,6 +1146,8 @@ static int loop_clr_fd(struct loop_devic + * bd_mutex which is usually taken before lo_ctl_mutex. + */ + fput(filp); ++ if (virt_filp) ++ fput(virt_filp); + return 0; } -+EXPORT_SYMBOL_GPL(security_mmap_file); - int security_mmap_addr(unsigned long addr) - { -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 2016-10-09 16:55:36.476034536 +0200 -@@ -0,0 +1,50 @@ -+What: /debug/aufs/si_/ -+Date: March 2009 -+Contact: J. R. Okajima -+Description: -+ Under /debug/aufs, a directory named si_ is created -+ per aufs mount, where is a unique id generated -+ internally. +diff -urNp -x '*.orig' linux-4.9/drivers/block/loop.h linux-4.9/drivers/block/loop.h +--- linux-4.9/drivers/block/loop.h 2021-02-24 16:14:57.284508877 +0100 ++++ linux-4.9/drivers/block/loop.h 2021-02-24 16:15:09.538240738 +0100 +@@ -47,7 +47,7 @@ struct loop_device { + int (*ioctl)(struct loop_device *, int cmd, + unsigned long arg); + +- struct file * lo_backing_file; ++ struct file * lo_backing_file, *lo_backing_virt_file; + struct block_device *lo_device; + unsigned lo_blocksize; + void *key_data; +diff -urNp -x '*.orig' linux-4.9/fs/Kconfig linux-4.9/fs/Kconfig +--- linux-4.9/fs/Kconfig 2016-12-11 20:17:54.000000000 +0100 ++++ linux-4.9/fs/Kconfig 2021-02-24 16:15:09.501572879 +0100 +@@ -249,6 +249,7 @@ source "fs/pstore/Kconfig" + source "fs/sysv/Kconfig" + source "fs/ufs/Kconfig" + source "fs/exofs/Kconfig" ++source "fs/aufs/Kconfig" + + endif # MISC_FILESYSTEMS + +diff -urNp -x '*.orig' linux-4.9/fs/Makefile linux-4.9/fs/Makefile +--- linux-4.9/fs/Makefile 2016-12-11 20:17:54.000000000 +0100 ++++ linux-4.9/fs/Makefile 2021-02-24 16:15:09.501572879 +0100 +@@ -129,3 +129,4 @@ obj-y += exofs/ # Multiple modules + obj-$(CONFIG_CEPH_FS) += ceph/ + obj-$(CONFIG_PSTORE) += pstore/ + obj-$(CONFIG_EFIVAR_FS) += efivarfs/ ++obj-$(CONFIG_AUFS_FS) += aufs/ +diff -urNp -x '*.orig' linux-4.9/fs/aufs/Kconfig linux-4.9/fs/aufs/Kconfig +--- linux-4.9/fs/aufs/Kconfig 1970-01-01 01:00:00.000000000 +0100 ++++ linux-4.9/fs/aufs/Kconfig 2021-02-24 16:15:09.531573855 +0100 +@@ -0,0 +1,198 @@ ++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. + -+What: /debug/aufs/si_/plink -+Date: Apr 2013 -+Contact: J. R. Okajima -+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". ++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 + -+What: /debug/aufs/si_/xib -+Date: March 2009 -+Contact: J. R. Okajima -+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. ++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. + -+What: /debug/aufs/si_/xino0, xino1 ... xinoN -+Date: March 2009 -+Contact: J. R. Okajima -+Description: -+ It shows the consumed blocks by xino (External Inode Number -+ Translation Table), its link count, block size and file -+ size. -+ When the aufs mount option 'noxino' is specified, it -+ will be empty. About XINO files, see the aufs manual. ++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. + -+What: /debug/aufs/si_/xigen -+Date: March 2009 -+Contact: J. R. Okajima -+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 2016-10-09 16:55:36.476034536 +0200 -@@ -0,0 +1,31 @@ -+What: /sys/fs/aufs/si_/ -+Date: March 2009 -+Contact: J. R. Okajima -+Description: -+ Under /sys/fs/aufs, a directory named si_ is created -+ per aufs mount, where is a unique id generated -+ internally. ++choice ++ prompt "method" if AUFS_HNOTIFY ++ default AUFS_HFSNOTIFY ++config AUFS_HFSNOTIFY ++ bool "fsnotify" ++ select FSNOTIFY ++endchoice + -+What: /sys/fs/aufs/si_/br0, br1 ... brN -+Date: March 2009 -+Contact: J. R. Okajima -+Description: -+ It shows the abolute path of a member directory (which -+ is called branch) in aufs, and its permission. ++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. + -+What: /sys/fs/aufs/si_/brid0, brid1 ... bridN -+Date: July 2013 -+Contact: J. R. Okajima -+Description: -+ It shows the id of a member directory (which is called -+ branch) in aufs. ++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 */ + -+What: /sys/fs/aufs/si_/xi_path -+Date: March 2009 -+Contact: J. R. Okajima -+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 2016-10-09 16:55:36.479367956 +0200 -@@ -0,0 +1,170 @@ ++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. + -+# Copyright (C) 2005-2016 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 . ++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. + -+Introduction -+---------------------------------------- ++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. + -+aufs [ei ju: 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. ++config AUFS_DIRREN ++ bool "Workaround for rename(2)-ing a directory" ++ help ++ By default, aufs returns EXDEV error in renameing a dir who has ++ his child on the lower branch, since it is a bad idea to issue ++ rename(2) internally for every lower branch. But user may not ++ accept this behaviour. So here is a workaround to allow such ++ rename(2) and store some extra infromation on the writable ++ branch. Obviously this costs high (and I don't like it). ++ To use this feature, you need to enable this configuration AND ++ to specify the mount option `dirren.' ++ See details in aufs.5 and the design documents. + -+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... ++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. + -+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. ++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). + -+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). ++config AUFS_POLL ++ bool ++ help ++ Automatic configuration for internal use. + -+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). ++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. + -+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. ++config AUFS_BDEV_LOOP ++ bool ++ depends on BLK_DEV_LOOP ++ default y ++ help ++ Automatic configuration for internal use. ++ Convert =[ym] into =y. + -+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). ++config AUFS_DEBUG ++ bool "Debug aufs" ++ help ++ Enable this to compile aufs internal debug code. ++ It will have a negative impact to the performance. + -+In AUFS, the structure of filesystem resembles to Unionfs, but I -+implemented my own ideas, approaches and enhancements and it became -+totally different one. ++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 -urNp -x '*.orig' linux-4.9/fs/aufs/Makefile linux-4.9/fs/aufs/Makefile +--- linux-4.9/fs/aufs/Makefile 1970-01-01 01:00:00.000000000 +0100 ++++ linux-4.9/fs/aufs/Makefile 2021-02-24 16:15:09.531573855 +0100 +@@ -0,0 +1,45 @@ + -+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). ++include ${src}/magic.mk ++ifeq (${CONFIG_AUFS_FS},m) ++include ${src}/conf.mk ++endif ++-include ${src}/priv_def.mk + -+You may want to read my old paper "Filesystems in LiveCD" -+(http://aufs.sourceforge.net/aufs2/report/sq/sq.pdf). ++# cf. include/linux/kernel.h ++# enable pr_debug ++ccflags-y += -DDEBUG ++# sparse requires the full pathname ++ifdef M ++ccflags-y += -include ${M}/../../include/uapi/linux/aufs_type.h ++else ++ccflags-y += -include ${srctree}/include/uapi/linux/aufs_type.h ++endif + ++obj-$(CONFIG_AUFS_FS) += aufs.o ++aufs-y := module.o sbinfo.o super.o branch.o xino.o sysaufs.o opts.o \ ++ wkq.o vfsub.o dcsub.o \ ++ cpup.o whout.o wbr_policy.o \ ++ dinfo.o dentry.o \ ++ dynop.o \ ++ finfo.o file.o f_op.o \ ++ dir.o vdir.o \ ++ iinfo.o inode.o i_op.o i_op_add.o i_op_del.o i_op_ren.o \ ++ mvdown.o ioctl.o + -+Several characters/aspects/persona of aufs -+---------------------------------------------------------------------- ++# 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 -urNp -x '*.orig' linux-4.9/fs/aufs/aufs.h linux-4.9/fs/aufs/aufs.h +--- linux-4.9/fs/aufs/aufs.h 1970-01-01 01:00:00.000000000 +0100 ++++ linux-4.9/fs/aufs/aufs.h 2021-02-24 16:15:09.521573529 +0100 +@@ -0,0 +1,60 @@ ++/* ++ * Copyright (C) 2005-2018 Junjiro R. Okajima ++ * ++ * This program, aufs is free software; you can redistribute it and/or modify ++ * it under the terms of the GNU General Public License as published by ++ * the Free Software Foundation; either version 2 of the License, or ++ * (at your option) any later version. ++ * ++ * This program is distributed in the hope that it will be useful, ++ * but WITHOUT ANY WARRANTY; without even the implied warranty of ++ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the ++ * GNU General Public License for more details. ++ * ++ * You should have received a copy of the GNU General Public License ++ * along with this program. If not, see . ++ */ + -+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 ++/* ++ * all header files ++ */ + -+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. ++#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 "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 -urNp -x '*.orig' linux-4.9/fs/aufs/branch.c linux-4.9/fs/aufs/branch.c +--- linux-4.9/fs/aufs/branch.c 1970-01-01 01:00:00.000000000 +0100 ++++ linux-4.9/fs/aufs/branch.c 2021-02-24 16:15:09.521573529 +0100 +@@ -0,0 +1,1432 @@ ++/* ++ * Copyright (C) 2005-2018 Junjiro R. Okajima ++ * ++ * This program, aufs is free software; you can redistribute it and/or modify ++ * it under the terms of the GNU General Public License as published by ++ * the Free Software Foundation; either version 2 of the License, or ++ * (at your option) any later version. ++ * ++ * This program is distributed in the hope that it will be useful, ++ * but WITHOUT ANY WARRANTY; without even the implied warranty of ++ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the ++ * GNU General Public License for more details. ++ * ++ * You should have received a copy of the GNU General Public License ++ * along with this program. If not, see . ++ */ ++ ++/* ++ * branch management ++ */ ++ ++#include ++#include ++#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); + -+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 ++ if (br->br_xino.xi_file) ++ fput(br->br_xino.xi_file); ++ for (i = br->br_xino.xi_nondir.total - 1; i >= 0; i--) ++ AuDebugOn(br->br_xino.xi_nondir.array[i]); ++ kfree(br->br_xino.xi_nondir.array); + -+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. ++ AuDebugOn(au_br_count(br)); ++ au_br_count_fin(br); + -+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. ++ 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); ++ } + -+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 2016-10-09 16:55:36.479367956 +0200 -@@ -0,0 +1,258 @@ ++ if (br->br_fhsm) { ++ au_br_fhsm_fin(br->br_fhsm); ++ kfree(br->br_fhsm); ++ } + -+# Copyright (C) 2005-2016 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 . ++ key = br->br_dykey; ++ for (i = 0; i < AuBrDynOp; i++, key++) ++ if (*key) ++ au_dy_put(*key); ++ else ++ break; + -+Basic Aufs Internal Structure ++ /* recursive lock, s_umount of branch's */ ++ lockdep_off(); ++ path_put(&br->br_path); ++ lockdep_on(); ++ kfree(wbr); ++ kfree(br); ++} + -+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 ++/* ++ * frees all branches ++ */ ++void au_br_free(struct au_sbinfo *sbinfo) ++{ ++ aufs_bindex_t bmax; ++ struct au_branch **br; + -+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 ++ AuRwMustWriteLock(&sbinfo->si_rwsem); + -+This style of an array is essentially same to the aufs -+superblock/inode/dentry/file objects. ++ bmax = sbinfo->si_bbot + 1; ++ br = sbinfo->si_branch; ++ while (bmax--) ++ au_br_do_free(*br++); ++} + -+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. ++/* ++ * 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; ++} + -+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. ++/* ---------------------------------------------------------------------- */ + ++/* ++ * add a branch ++ */ + -+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. ++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); ++} + -+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. ++/* ++ * 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; + -+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. ++ err = -ENOMEM; ++ add_branch = kzalloc(sizeof(*add_branch), GFP_NOFS); ++ if (unlikely(!add_branch)) ++ goto out; ++ add_branch->br_xino.xi_nondir.total = 8; /* initial size */ ++ add_branch->br_xino.xi_nondir.array ++ = kcalloc(add_branch->br_xino.xi_nondir.total, sizeof(ino_t), ++ GFP_NOFS); ++ if (unlikely(!add_branch->br_xino.xi_nondir.array)) ++ goto out_br; + -+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. ++ err = au_hnotify_init_br(add_branch, perm); ++ if (unlikely(err)) ++ goto out_xinondir; + -+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. ++ 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; ++ } + -+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. ++ 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 */ + -+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. ++out_wbr: ++ kfree(add_branch->br_wbr); ++out_hnotify: ++ au_hnotify_fin_br(add_branch); ++out_xinondir: ++ kfree(add_branch->br_xino.xi_nondir.array); ++out_br: ++ kfree(add_branch); ++out: ++ return ERR_PTR(err); ++} + -+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. ++/* ++ * 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; + -+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. ++ err = -EINVAL; ++ pr_err("write permission for readonly mount or inode, %s\n", path); + -+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: ++ 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; + -+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. ++ 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; ++ } + -+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. ++ 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; ++ } + -+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). ++ 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; ++ } + -+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). ++ err = -EINVAL; ++ if (unlikely(inode->i_sb == sb)) { ++ pr_err("%s must be outside\n", add->pathname); ++ goto out; ++ } + -+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. ++ 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; ++ } + -+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. ++ 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; + -+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. ++ if (bbot < 0) ++ return 0; /* success */ + -+Basically the whiteout represents "logical deletion" which stops aufs to -+lookup further, but also it represents "dir is opaque" which also stop -+further lookup. ++ 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; ++ } + -+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. ++ 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; ++} + -+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. ++/* ++ * 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; + -+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. ++ 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; + -+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. ++ if (!err && wbr && !au_br_writable(new_perm)) { ++ kfree(wbr); ++ br->br_wbr = NULL; ++ } + -+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 2016-10-09 16:55:36.479367956 +0200 -@@ -0,0 +1,85 @@ ++out: ++ return err; ++} + -+# Copyright (C) 2015-2016 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 . ++static int au_wbr_init(struct au_branch *br, struct super_block *sb, ++ int perm) ++{ ++ int err; ++ struct kstatfs kst; ++ struct au_wbr *wbr; + -+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. ++ wbr = br->br_wbr; ++ au_rw_init(&wbr->wbr_wh_rwsem); ++ atomic_set(&wbr->wbr_wh_running, 0); + -+In order to support ->atomic_open() for aufs, there are a few -+approaches. ++ /* ++ * 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); + -+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. ++out: ++ return err; ++} + -+Pros and cons for each approach. ++/* 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 inode *h_inode; + -+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. ++ err = 0; ++ spin_lock_init(&br->br_xino.xi_nondir.spin); ++ init_waitqueue_head(&br->br_xino.xi_nondir.wqh); ++ br->br_perm = add->perm; ++ br->br_path = add->path; /* set first, path_get() later */ ++ spin_lock_init(&br->br_dykey_lock); ++ au_br_count_init(br); ++ atomic_set(&br->br_xino_running, 0); ++ br->br_id = au_new_br_id(sb); ++ AuDebugOn(br->br_id < 0); + -+The approach A is ideal, but it hard to implement. So here is a -+variation of A, which is to be implemented. ++ /* always, regardless the given option */ ++ err = au_dr_br_init(sb, br, &add->path); ++ if (unlikely(err)) ++ goto out_err; + -+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 2016-10-09 16:55:36.479367956 +0200 -@@ -0,0 +1,113 @@ ++ if (au_br_writable(add->perm)) { ++ err = au_wbr_init(br, sb, add->perm); ++ if (unlikely(err)) ++ goto out_err; ++ } + -+# Copyright (C) 2005-2016 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 . ++ if (au_opt_test(au_mntflags(sb), XINO)) { ++ h_inode = d_inode(add->path.dentry); ++ err = au_xino_br(sb, br, h_inode->i_ino, ++ au_sbr(sb, 0)->br_xino.xi_file, /*do_test*/1); ++ if (unlikely(err)) { ++ AuDebugOn(br->br_xino.xi_file); ++ goto out_err; ++ } ++ } + -+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. ++ sysaufs_br_init(br); ++ path_get(&br->br_path); ++ 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_err: ++ memset(&br->br_path, 0, sizeof(br->br_path)); ++out: ++ return err; ++} + ++static void au_br_do_add_brp(struct au_sbinfo *sbinfo, aufs_bindex_t bindex, ++ struct au_branch *br, aufs_bindex_t bbot, ++ aufs_bindex_t amount) ++{ ++ struct au_branch **brp; + -+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? ++ AuRwMustWriteLock(&sbinfo->si_rwsem); + -+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? ++ 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; ++} + -+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. ++static void au_br_do_add_hdp(struct au_dinfo *dinfo, aufs_bindex_t bindex, ++ aufs_bindex_t bbot, aufs_bindex_t amount) ++{ ++ struct au_hdentry *hdp; + -+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. ++ 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; ++} + -+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 ++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; + -+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. ++ AuRwMustWriteLock(&iinfo->ii_rwsem); + -+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. ++ 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; ++} + -+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 2016-10-09 16:55:36.482701377 +0200 -@@ -0,0 +1,74 @@ ++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; + -+# Copyright (C) 2005-2016 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 . ++ 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(); ++} + -+Branch Manipulation ++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; + -+Since aufs supports dynamic branch manipulation, ie. add/remove a branch -+and changing its permission/attribute, there are a lot of works to do. ++ root = sb->s_root; ++ root_inode = d_inode(root); ++ IMustLock(root_inode); ++ IiMustWriteLock(root_inode); ++ err = test_add(sb, add, remount); ++ if (unlikely(err < 0)) ++ goto out; ++ if (err) { ++ err = 0; ++ goto out; /* success */ ++ } + ++ bbot = au_sbbot(sb); ++ add_branch = au_br_alloc(sb, bbot + 2, add->perm); ++ err = PTR_ERR(add_branch); ++ if (IS_ERR(add_branch)) ++ goto out; + -+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. ++ err = au_br_init(add_branch, sb, add); ++ if (unlikely(err)) { ++ au_br_do_free(add_branch); ++ goto out; ++ } + -+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. ++ add_bindex = add->bindex; ++ if (!remount) ++ au_br_do_add(sb, add_branch, add_bindex); ++ else { ++ sysaufs_brs_del(sb, add_bindex); ++ au_br_do_add(sb, add_branch, add_bindex); ++ sysaufs_brs_add(sb, add_bindex); ++ } + ++ 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)); + -+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). ++ /* ++ * this test/set prevents aufs from handling unnecesary notify events ++ * of xino files, in case of re-adding a writable branch which was ++ * once detached from aufs. ++ */ ++ if (au_xino_brid(sb) < 0 ++ && au_br_writable(add_branch->br_perm) ++ && !au_test_fs_bad_xino(h_dentry->d_sb) ++ && add_branch->br_xino.xi_file ++ && add_branch->br_xino.xi_file->f_path.dentry->d_parent == h_dentry) ++ au_xino_brid_set(sb, add_branch->br_id); + -+ 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. ++out: ++ return err; ++} + -+ If any file on the deleting branch is opened by aufs, then aufs -+ rejects deleting. ++/* ---------------------------------------------------------------------- */ + ++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; + -+Modify the Permission of a Branch -+---------------------------------------------------------------------- -+o Re-initialize or remove the xino file and whiteout bases if necessary. -+ See struct.txt. ++ 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); + -+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 2016-10-09 16:55:36.482701377 +0200 -@@ -0,0 +1,64 @@ ++ return n; ++} + -+# Copyright (C) 2005-2016 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 . ++static struct file **au_farray_alloc(struct super_block *sb, ++ unsigned long long *max) ++{ ++ *max = au_nfiles(sb); ++ return au_array_alloc(max, au_farray_cb, sb, /*arg*/NULL); ++} + -+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. ++static void au_farray_free(struct file **a, unsigned long long max) ++{ ++ unsigned long long ull; + -+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. ++ for (ull = 0; ull < max; ull++) ++ if (a[ull]) ++ fput(a[ull]); ++ kvfree(a); ++} + -+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 -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 2016-10-09 16:55:36.482701377 +0200 -@@ -0,0 +1,120 @@ ++/* ++ * delete a branch ++ */ + -+# Copyright (C) 2011-2016 Junjiro R. Okajima -+# -+# This program is free software; you can redistribute it and/or modify -+# it under the terms of the GNU General Public License as published by -+# the Free Software Foundation; either version 2 of the License, or -+# (at your option) any later version. -+# -+# This program is distributed in the hope that it will be useful, -+# but WITHOUT ANY WARRANTY; without even the implied warranty of -+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the -+# GNU General Public License for more details. -+# -+# You should have received a copy of the GNU General Public License -+# along with this program; if not, write to the Free Software -+# Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA ++/* to show the line number, do not make it inlined function */ ++#define AuVerbose(do_info, fmt, ...) do { \ ++ if (do_info) \ ++ pr_info(fmt, ##__VA_ARGS__); \ ++} while (0) + ++static int au_test_ibusy(struct inode *inode, aufs_bindex_t btop, ++ aufs_bindex_t bbot) ++{ ++ return (inode && !S_ISDIR(inode->i_mode)) || btop == bbot; ++} + -+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. ++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); ++} + -+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. ++/* ++ * test if the branch is deletable or not. ++ */ ++static int test_dentry_busy(struct dentry *root, aufs_bindex_t bindex, ++ unsigned int sigen, const unsigned int verbose) ++{ ++ int err, i, j, ndentry; ++ aufs_bindex_t btop, bbot; ++ struct au_dcsub_pages dpages; ++ struct au_dpage *dpage; ++ struct dentry *d; + -+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. ++ 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; + -+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. ++ 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; ++ } ++ } + -+Currently aufs FHSM handles the regular files only. Additionally they -+must not be hard-linked nor pseudo-linked. ++ /* AuDbgDentry(d); */ ++ btop = au_dbtop(d); ++ bbot = au_dbbot(d); ++ if (btop <= bindex ++ && bindex <= bbot ++ && au_h_dptr(d, bindex) ++ && au_test_dbusy(d, btop, bbot)) { ++ err = -EBUSY; ++ AuVerbose(verbose, "busy %pd\n", d); ++ AuDbgDentry(d); ++ } ++ di_read_unlock(d, AuLock_IR); ++ } ++ } + ++out_dpages: ++ au_dpages_free(&dpages); ++out: ++ return err; ++} + -+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 int test_inode_busy(struct super_block *sb, aufs_bindex_t bindex, ++ unsigned int sigen, const unsigned int verbose) ++{ ++ int err; ++ unsigned long long max, ull; ++ struct inode *i, **array; ++ aufs_bindex_t btop, bbot; + ++ array = au_iarray_alloc(sb, &max); ++ err = PTR_ERR(array); ++ if (IS_ERR(array)) ++ goto out; + -+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. ++ 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; ++ } ++ } + -+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. ++ 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); + -+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 2016-10-09 16:55:36.482701377 +0200 -@@ -0,0 +1,72 @@ ++out: ++ return err; ++} + -+# Copyright (C) 2005-2016 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 . ++static int test_children_busy(struct dentry *root, aufs_bindex_t bindex, ++ const unsigned int verbose) ++{ ++ int err; ++ unsigned int sigen; + -+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. ++ 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() */ + -+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. ++ return err; ++} + -+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. ++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; + -+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. ++ err = 0; ++ root = IS_ROOT(file->f_path.dentry); ++ if (root) { ++ get_file(file); ++ to_free[*idx] = file; ++ (*idx)++; ++ goto out; ++ } + -+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. ++ 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; + -+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 2016-10-09 16:55:36.482701377 +0200 -@@ -0,0 +1,96 @@ ++ if (hfile->hf_br->br_id == br_id) { ++ matched = 1; ++ break; ++ } ++ } ++ if (matched) ++ err = -EBUSY; + -+# Copyright (C) 2014-2016 Junjiro R. Okajima -+# -+# This program is free software; you can redistribute it and/or modify -+# it under the terms of the GNU General Public License as published by -+# the Free Software Foundation; either version 2 of the License, or -+# (at your option) any later version. -+# -+# This program is distributed in the hope that it will be useful, -+# but WITHOUT ANY WARRANTY; without even the implied warranty of -+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the -+# GNU General Public License for more details. -+# -+# You should have received a copy of the GNU General Public License -+# along with this program; if not, write to the Free Software -+# Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA ++out: ++ return err; ++} + ++static int test_file_busy(struct super_block *sb, aufs_bindex_t br_id, ++ struct file **to_free, int opened) ++{ ++ int err, idx; ++ unsigned long long ull, max; ++ aufs_bindex_t btop; ++ struct file *file, **array; ++ struct dentry *root; ++ struct au_hfile *hfile; + -+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. ++ array = au_farray_alloc(sb, &max); ++ err = PTR_ERR(array); ++ if (IS_ERR(array)) ++ goto out; + -+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, ++ err = 0; ++ idx = 0; ++ root = sb->s_root; ++ di_write_unlock(root); ++ for (ull = 0; ull < max; ull++) { ++ file = array[ull]; ++ if (unlikely(!file)) ++ break; + ++ /* AuDbg("%pD\n", file); */ ++ fi_read_lock(file); ++ btop = au_fbtop(file); ++ if (!d_is_dir(file->f_path.dentry)) { ++ hfile = &au_fi(file)->fi_htop; ++ if (hfile->hf_br->br_id == br_id) ++ err = -EBUSY; ++ } else ++ err = test_dir_busy(file, br_id, to_free, &idx); ++ fi_read_unlock(file); ++ if (unlikely(err)) ++ break; ++ } ++ di_write_lock_child(root); ++ au_farray_free(array, max); ++ AuDebugOn(idx > opened); + -+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. ++out: ++ return err; ++} + -+Moreover there are some other categories. Aufs handles these rather -+unpopular categories as the ordinary ones, ie. there is no special -+condition nor exception. ++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; + -+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. ++ for (ull = 0; ull < opened; ull++) { ++ file = to_free[ull]; ++ if (unlikely(!file)) ++ break; + -+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. ++ /* 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; + -+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. ++ if (hfile->hf_br->br_id == br_id) { ++ bfound = bindex; ++ break; ++ } ++ } ++ AuDebugOn(bfound < 0); ++ au_set_h_fptr(file, bfound, NULL); ++ if (bfound == btop) { ++ for (btop++; btop <= bbot; btop++) ++ if (au_hf_dir(file, btop)) { ++ au_set_fbtop(file, btop); ++ break; ++ } ++ } ++ fi_write_unlock(file); ++ } ++} ++ ++static void au_br_do_del_brp(struct au_sbinfo *sbinfo, ++ const aufs_bindex_t bindex, ++ const aufs_bindex_t bbot) ++{ ++ struct au_branch **brp, **p; ++ ++ AuRwMustWriteLock(&sbinfo->si_rwsem); ++ ++ brp = sbinfo->si_branch + bindex; ++ if (bindex < bbot) ++ memmove(brp, brp + 1, sizeof(*brp) * (bbot - bindex)); ++ sbinfo->si_branch[0 + bbot] = NULL; ++ sbinfo->si_bbot--; ++ ++ p = au_krealloc(sbinfo->si_branch, sizeof(*p) * bbot, AuGFP_SBILIST, ++ /*may_shrink*/1); ++ if (p) ++ sbinfo->si_branch = p; ++ /* harmless error */ ++} + -+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"). ++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 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. ++ AuRwMustWriteLock(&dinfo->di_rwsem); + -+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 2016-10-09 16:55:36.482701377 +0200 -@@ -0,0 +1,58 @@ ++ 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--; + -+# Copyright (C) 2005-2016 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 . ++ p = au_krealloc(dinfo->di_hdentry, sizeof(*p) * bbot, AuGFP_SBILIST, ++ /*may_shrink*/1); ++ if (p) ++ dinfo->di_hdentry = p; ++ /* harmless error */ ++} + -+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 2016-10-09 16:55:36.482701377 +0200 -@@ -0,0 +1,52 @@ ++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; + -+# Copyright (C) 2005-2016 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 . ++ AuRwMustWriteLock(&iinfo->ii_rwsem); + -+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. ++ 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--; + -+(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 ++ p = au_krealloc(iinfo->ii_hinode, sizeof(*p) * bbot, AuGFP_SBILIST, ++ /*may_shrink*/1); ++ if (p) ++ iinfo->ii_hinode = p; ++ /* harmless error */ ++} + -+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. ++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; + -+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 ++ SiMustWriteLock(sb); + -+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 ++ root = sb->s_root; ++ inode = d_inode(root); ++ sbinfo = au_sbi(sb); ++ bbot = sbinfo->si_bbot; + -+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 2016-10-09 16:55:36.482701377 +0200 -@@ -0,0 +1,47 @@ ++ h_root = au_h_dptr(root, bindex); ++ hinode = au_hi(inode, bindex); ++ h_inode = au_igrab(hinode->hi_inode); ++ au_hiput(hinode); + -+# Copyright (C) 2010-2016 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 . ++ 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(); + -+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. ++ /* ignore an error */ ++ au_dr_br_fin(sb, br); /* always, regardless the mount option */ + -+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. ++ dput(h_root); ++ iput(h_inode); ++ au_br_do_free(br); ++} + -+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. ++static unsigned long long empty_cb(struct super_block *sb, void *array, ++ unsigned long long max, void *arg) ++{ ++ return max; ++} + -+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 2016-12-17 12:28:17.595211562 +0100 -@@ -0,0 +1,393 @@ ++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; + -+Aufs4 -- advanced multi layered unification filesystem version 4.x -+http://aufs.sf.net -+Junjiro R. Okajima ++ err = 0; ++ opened = 0; ++ to_free = NULL; ++ root = sb->s_root; ++ bindex = au_find_dbindex(root, del->h_path.dentry); ++ if (bindex < 0) { ++ if (remount) ++ goto out; /* success */ ++ err = -ENOENT; ++ pr_err("%s no such branch\n", del->pathname); ++ goto out; ++ } ++ AuDbg("bindex b%d\n", bindex); + ++ err = -EBUSY; ++ mnt_flags = au_mntflags(sb); ++ verbose = !!au_opt_test(mnt_flags, VERBOSE); ++ bbot = au_sbbot(sb); ++ if (unlikely(!bbot)) { ++ AuVerbose(verbose, "no more branches left\n"); ++ goto out; ++ } ++ br = au_sbr(sb, bindex); ++ AuDebugOn(!path_equal(&br->br_path, &del->h_path)); + -+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 becomes totally different from -+Unionfs while keeping the basic features. -+Recently, Unionfs Version 2.x series begin taking some of the same -+approaches to aufs1's. -+Unionfs is being developed by Professor Erez Zadok at Stony Brook -+University and his team. ++ br_id = br->br_id; ++ opened = au_br_count(br); ++ 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; + -+Aufs4 supports linux-4.0 and later, and for linux-3.x series try aufs3. -+If you want older kernel version support, try aufs2-2.6.git or -+aufs2-standalone.git repository, aufs1 from CVS on SourceForge. ++ err = test_file_busy(sb, br_id, to_free, opened); ++ if (unlikely(err)) { ++ AuVerbose(verbose, "%llu file(s) opened\n", opened); ++ goto out; ++ } ++ } + -+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. -+ ++ 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; ++ } ++ } + -+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). -+ ++ 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); ++ } + -+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... ++ if (!remount) ++ au_br_do_del(sb, bindex, br); ++ else { ++ sysaufs_brs_del(sb, bindex); ++ au_br_do_del(sb, bindex, br); ++ sysaufs_brs_add(sb, bindex); ++ } + -+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 /fs/aufs and /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... ++ 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); + -+Currently these features are dropped temporary from aufs4. -+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) ++ if (au_xino_brid(sb) == br_id) ++ au_xino_brid_set(sb, -1); ++ goto out; /* success */ + -+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 ++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; ++} + ++/* ---------------------------------------------------------------------- */ + -+2. Download -+---------------------------------------- -+There are three GIT trees for aufs4, aufs4-linux.git, -+aufs4-standalone.git, and aufs-util.git. Note that there is no "4" in -+"aufs-util.git." -+While the aufs-util is always necessary, you need either of aufs4-linux -+or aufs4-standalone. ++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; + -+The aufs4-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 aufs4 as an external kernel module. -+Several extra patches are not included in this tree. Only -+aufs4-standalone tree contains them. They are described in the later -+section "Configuration and Compilation." ++ err = -EPERM; ++ if (unlikely(!capable(CAP_SYS_ADMIN))) ++ goto out; + -+On the other hand, the aufs4-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. ++ err = copy_from_user(&ibusy, arg, sizeof(ibusy)); ++ if (!err) ++ err = !access_ok(VERIFY_WRITE, &arg->h_ino, sizeof(arg->h_ino)); ++ if (unlikely(err)) { ++ err = -EFAULT; ++ AuTraceErr(err); ++ goto out; ++ } + -+You will find GIT branches whose name is in form of "aufs4.x" where "x" -+represents the linux kernel version, "linux-4.x". For instance, -+"aufs4.0" is for linux-4.0. For latest "linux-4.x-rcN", use -+"aufs4.x-rcN" branch. ++ err = -EINVAL; ++ si_read_lock(sb, AuLock_FLUSH); ++ if (unlikely(ibusy.bindex < 0 || ibusy.bindex > au_sbbot(sb))) ++ goto out_unlock; + -+o aufs4-linux tree -+$ git clone --reference /your/linux/git/tree \ -+ git://github.com/sfjro/aufs4-linux.git aufs4-linux.git -+- if you don't have linux GIT tree, then remove "--reference ..." -+$ cd aufs4-linux.git -+$ git checkout origin/aufs4.0 ++ 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; + -+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 aufs4 git://github.com/sfjro/aufs4-linux.git -+$ git fetch aufs4 -+$ git checkout -b my4.0 v4.0 -+$ (add your local change...) -+$ git pull aufs4 aufs4.0 -+- now you have v4.0 + your_changes + aufs4.0 in you my4.0 branch. -+- you may need to solve some conflicts between your_changes and -+ aufs4.0. in this case, git-rerere is recommended so that you can -+ solve the similar conflicts automatically when you upgrade to 4.1 or -+ later in the future. ++ 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); + -+o aufs4-standalone tree -+$ git clone git://github.com/sfjro/aufs4-standalone.git aufs4-standalone.git -+$ cd aufs4-standalone.git -+$ git checkout origin/aufs4.0 ++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; ++} + -+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/aufs4.0 ++long au_ibusy_ioctl(struct file *file, unsigned long arg) ++{ ++ return au_ibusy(file->f_path.dentry->d_sb, (void __user *)arg); ++} + -+Note: The 4.x-rcN branch is to be used with `rc' kernel versions ONLY. -+The minor version number, 'x' in '4.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. ++#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 + -+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-4.10" and the "aufs4.10" branch -+does not exist in aufs-util repository, then "aufs4.9", "aufs4.8" -+or something numerically smaller is the branch for your kernel. ++/* ++ * change a branch permission ++ */ + -+Also you can view all branches by -+ $ git branch -a ++static void au_warn_ima(void) ++{ ++#ifdef CONFIG_IMA ++ /* since it doesn't support mark_files_ro() */ ++ AuWarn1("RW -> RO makes IMA to produce wrong message\n"); ++#endif ++} + ++static int do_need_sigen_inc(int a, int b) ++{ ++ return au_br_whable(a) && !au_br_whable(b); ++} + -+3. Configuration and Compilation -+---------------------------------------- -+Make sure you have git-checkout'ed the correct branch. ++static int need_sigen_inc(int old, int new) ++{ ++ return do_need_sigen_inc(old, new) ++ || do_need_sigen_inc(new, old); ++} + -+For aufs4-linux tree, -+- enable CONFIG_AUFS_FS. -+- set other aufs configurations if necessary. ++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; + -+For aufs4-standalone tree, -+There are several ways to build. ++ mnt_flags = au_mntflags(sb); ++ verbose = !!au_opt_test(mnt_flags, VERBOSE); + -+1. -+- apply ./aufs4-kbuild.patch to your kernel source files. -+- apply ./aufs4-base.patch too. -+- apply ./aufs4-mmap.patch too. -+- apply ./aufs4-standalone.patch too, if you have a plan to set -+ CONFIG_AUFS_FS=m. otherwise you don't need ./aufs4-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. -+ Note: Since linux-3.9, every filesystem module requires an alias -+ "fs-". You should make sure that "fs-aufs" is listed in your -+ modules.aliases file if you set CONFIG_AUFS_FS=m. -+- 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. ++ array = au_farray_alloc(sb, &max); ++ err = PTR_ERR(array); ++ if (IS_ERR(array)) ++ goto out; + -+2. -+- module only (CONFIG_AUFS_FS=m). -+- apply ./aufs4-base.patch to your kernel source files. -+- apply ./aufs4-mmap.patch too. -+- apply ./aufs4-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". -+ Note: Since linux-3.9, every filesystem module requires an alias -+ "fs-". You should make sure that "fs-aufs" is listed in your -+ modules.aliases file. -+- 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 aufs4-kbuild.patch, nor copying source files to your -+ kernel source tree. ++ do_warn = 0; ++ br_id = au_sbr_id(sb, bindex); ++ for (ull = 0; ull < max; ull++) { ++ file = array[ull]; ++ if (unlikely(!file)) ++ break; + -+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. ++ /* 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; ++ } + -+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. ++ 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); ++ } + -+There several other patches in aufs4-standalone.git. They are all -+optional. When you meet some problems, they will help you. -+- aufs4-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 -+ Because aufs is not only an ordinary filesystem (callee of VFS), but -+ also a caller of VFS functions for branch filesystems, subclassing of -+ the internal locks for LOCKDEP is necessary. LOCKDEP is a debugging -+ feature of linux kernel. If you enable CONFIG_LOCKDEP, then you will -+ need to apply this debug patch to expand several constant values. -+ If don't know what LOCKDEP, then you don't have apply this patch. ++ FiMustNoWaiters(file); ++ fi_read_unlock(file); ++ fput(file); ++ } + ++ err = 0; ++ if (do_warn) ++ au_warn_ima(); + -+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 ++ for (ull = 0; ull < max; ull++) { ++ file = array[ull]; ++ if (!file) ++ continue; + -+And then, -+$ mkdir /tmp/rw /tmp/aufs -+# mount -t aufs -o br=/tmp/rw:${HOME} none /tmp/aufs ++ /* todo: already flushed? */ ++ /* ++ * fs/super.c:mark_files_ro() is gone, but aufs keeps its ++ * approach which resets f_mode and calls mnt_drop_write() and ++ * file_release_write() for each file, because the branch ++ * attribute in aufs world is totally different from the native ++ * fs rw/ro mode. ++ */ ++ /* fi_read_lock(file); */ ++ hfile = &au_fi(file)->fi_htop; ++ hf = hfile->hf_file; ++ /* fi_read_unlock(file); */ ++ spin_lock(&hf->f_lock); ++ writer = !!(hf->f_mode & FMODE_WRITER); ++ hf->f_mode &= ~(FMODE_WRITE | FMODE_WRITER); ++ spin_unlock(&hf->f_lock); ++ if (writer) { ++ put_write_access(file_inode(hf)); ++ __mnt_drop_write(hf->f_path.mnt); ++ } ++ } + -+Here is another example. The result is equivalent. -+# mount -t aufs -o br=/tmp/rw=rw:${HOME}=ro none /tmp/aufs -+ Or -+# mount -t aufs -o br:/tmp/rw none /tmp/aufs -+# mount -o remount,append:${HOME} /tmp/aufs ++out_array: ++ au_farray_free(array, max); ++out: ++ AuTraceErr(err); ++ return err; ++} + -+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. ++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; + -+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. ++ root = sb->s_root; ++ bindex = au_find_dbindex(root, mod->h_root); ++ if (bindex < 0) { ++ if (remount) ++ return 0; /* success */ ++ err = -ENOENT; ++ pr_err("%s no such branch\n", mod->path); ++ goto out; ++ } ++ AuDbg("bindex b%d\n", bindex); + ++ err = test_br(d_inode(mod->h_root), mod->perm, mod->path); ++ if (unlikely(err)) ++ goto out; + -+5. Contact -+---------------------------------------- -+When you have any problems or strange behaviour in aufs, please let me -+know with: -+- /proc/mounts (instead of the output of mount(8)) -+- /sys/module/aufs/* -+- /sys/fs/aufs/* (if you have them) -+- /debug/aufs/* (if you have them) -+- linux kernel version -+ if your kernel is not plain, for example modified by distributor, -+ the url where i can download its source is necessary too. -+- aufs version which was printed at loading the module or booting the -+ system, instead of the date you downloaded. -+- configuration (define/undefine CONFIG_AUFS_xxx) -+- kernel configuration or /proc/config.gz (if you have it) -+- behaviour which you think to be incorrect -+- actual operation, reproducible one is better -+- mailto: aufs-users at lists.sourceforge.net ++ br = au_sbr(sb, bindex); ++ AuDebugOn(mod->h_root != au_br_dentry(br)); ++ if (br->br_perm == mod->perm) ++ return 0; /* success */ + -+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. ++ /* pre-allocate for non-fhsm --> fhsm */ ++ bf = NULL; ++ if (!au_br_fhsm(br->br_perm) && au_br_fhsm(mod->perm)) { ++ err = au_fhsm_br_alloc(br); ++ if (unlikely(err)) ++ goto out; ++ bf = br->br_fhsm; ++ br->br_fhsm = NULL; ++ } + ++ if (au_br_writable(br->br_perm)) { ++ /* remove whiteout base */ ++ err = au_br_init_wh(sb, br, mod->perm); ++ if (unlikely(err)) ++ goto out_bf; + -+6. Acknowledgements -+---------------------------------------- -+Thanks to everyone who have tried and are using aufs, whoever -+have reported a bug or any feedback. ++ 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); + -+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. -+ -+Dai Itasaka made a donation (2007/8). -+Chuck Smith made a donation (2008/4, 10 and 12). -+Henk Schoneveld made a donation (2008/9). -+Chih-Wei Huang, ASUS, CTC donated Eee PC 4G (2008/10). -+Francois Dupoux made a donation (2008/11). -+Bruno Cesar Ribas and Luis Carlos Erpen de Bona, C3SL serves public -+ aufs2 GIT tree (2009/2). -+William Grant made a donation (2009/3). -+Patrick Lane made a donation (2009/4). -+The Mail Archive (mail-archive.com) made donations (2009/5). -+Nippy Networks (Ed Wildgoose) made a donation (2009/7). -+New Dream Network, LLC (www.dreamhost.com) made a donation (2009/11). -+Pavel Pronskiy made a donation (2011/2). -+Iridium and Inmarsat satellite phone retailer (www.mailasail.com), Nippy -+ Networks (Ed Wildgoose) made a donation for hardware (2011/3). -+Max Lekomcev (DOM-TV project) made a donation (2011/7, 12, 2012/3, 6 and -+11). -+Sam Liddicott made a donation (2011/9). -+Era Scarecrow made a donation (2013/4). -+Bor Ratajc made a donation (2013/4). -+Alessandro Gorreta made a donation (2013/4). -+POIRETTE Marc made a donation (2013/4). -+Alessandro Gorreta made a donation (2013/4). -+lauri kasvandik made a donation (2013/5). -+"pemasu from Finland" made a donation (2013/7). -+The Parted Magic Project made a donation (2013/9 and 11). -+Pavel Barta made a donation (2013/10). -+Nikolay Pertsev made a donation (2014/5). -+James B made a donation (2014/7 and 2015/7). -+Stefano Di Biase made a donation (2014/8). -+Daniel Epellei made a donation (2015/1). -+OmegaPhil made a donation (2016/1). -+Tomasz Szewczyk made a donation (2016/4). -+James Burry made a donation (2016/12). ++ 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)) { ++ kfree(br->br_wbr); ++ br->br_wbr = NULL; ++ } ++ } ++ } ++ if (unlikely(err)) ++ goto out_bf; + -+Thank you very much. -+Donations are always, including future donations, very important and -+helpful for me to keep on developing aufs. ++ if (au_br_fhsm(br->br_perm)) { ++ if (!au_br_fhsm(mod->perm)) { ++ /* fhsm --> non-fhsm */ ++ au_br_fhsm_fin(br->br_fhsm); ++ kfree(br->br_fhsm); ++ br->br_fhsm = NULL; ++ } ++ } else if (au_br_fhsm(mod->perm)) ++ /* non-fhsm --> fhsm */ ++ br->br_fhsm = bf; + ++ *do_refresh |= need_sigen_inc(br->br_perm, mod->perm); ++ br->br_perm = mod->perm; ++ goto out; /* success */ + -+7. -+---------------------------------------- -+If you are an experienced user, no explanation is needed. Aufs is -+just a linux filesystem. ++out_bf: ++ kfree(bf); ++out: ++ AuTraceErr(err); ++ return err; ++} + ++/* ---------------------------------------------------------------------- */ + -+Enjoy! ++int au_br_stfs(struct au_branch *br, struct aufs_stfs *stfs) ++{ ++ int err; ++ struct kstatfs kstfs; + -+# 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 2016-10-09 16:55:36.486034798 +0200 -@@ -0,0 +1,59 @@ ++ err = vfs_statfs(&br->br_path, &kstfs); ++ if (!err) { ++ stfs->f_blocks = kstfs.f_blocks; ++ stfs->f_bavail = kstfs.f_bavail; ++ stfs->f_files = kstfs.f_files; ++ stfs->f_ffree = kstfs.f_ffree; ++ } ++ ++ return err; ++} +diff -urNp -x '*.orig' linux-4.9/fs/aufs/branch.h linux-4.9/fs/aufs/branch.h +--- linux-4.9/fs/aufs/branch.h 1970-01-01 01:00:00.000000000 +0100 ++++ linux-4.9/fs/aufs/branch.h 2021-02-24 16:15:09.521573529 +0100 +@@ -0,0 +1,324 @@ +/* -+ * Copyright (C) 2005-2016 Junjiro R. Okajima ++ * Copyright (C) 2005-2018 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by @@ -2830,1824 +3901,1882 @@ diff -urN /usr/share/empty/fs/aufs/aufs.h linux/fs/aufs/aufs.h + */ + +/* -+ * all header files ++ * branch filesystems and xino for them + */ + -+#ifndef __AUFS_H__ -+#define __AUFS_H__ ++#ifndef __AUFS_BRANCH_H__ ++#define __AUFS_BRANCH_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 ++#include "dirren.h" +#include "dynop.h" -+#include "file.h" -+#include "fstype.h" -+#include "inode.h" -+#include "loop.h" -+#include "module.h" -+#include "opts.h" +#include "rwsem.h" -+#include "spl.h" +#include "super.h" -+#include "sysaufs.h" -+#include "vfsub.h" -+#include "whout.h" -+#include "wkq.h" + -+#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 2016-10-09 16:55:38.886097714 +0200 -@@ -0,0 +1,1412 @@ -+/* -+ * Copyright (C) 2005-2016 Junjiro R. Okajima -+ * -+ * This program, aufs is free software; you can redistribute it and/or modify -+ * it under the terms of the GNU General Public License as published by -+ * the Free Software Foundation; either version 2 of the License, or -+ * (at your option) any later version. -+ * -+ * This program is distributed in the hope that it will be useful, -+ * but WITHOUT ANY WARRANTY; without even the implied warranty of -+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the -+ * GNU General Public License for more details. -+ * -+ * You should have received a copy of the GNU General Public License -+ * along with this program. If not, see . -+ */ ++/* ---------------------------------------------------------------------- */ + -+/* -+ * branch management -+ */ ++/* a xino file */ ++struct au_xino_file { ++ struct file *xi_file; ++ struct { ++ spinlock_t spin; ++ ino_t *array; ++ int total; ++ /* reserved for future use */ ++ /* unsigned long *bitmap; */ ++ wait_queue_head_t wqh; ++ } xi_nondir; + -+#include -+#include -+#include "aufs.h" ++ /* todo: make xino files an array to support huge inode number */ ++ ++#ifdef CONFIG_DEBUG_FS ++ struct dentry *xi_dbgaufs; ++#endif ++}; ++ ++/* 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 */ + -+/* -+ * free a single branch -+ */ -+static void au_br_do_free(struct au_branch *br) -+{ -+ int i; -+ struct au_wbr *wbr; -+ struct au_dykey **key; ++ /* mfs mode */ ++ unsigned long long wbr_bytes; ++}; + -+ au_hnotify_fin_br(br); ++/* ext2 has 3 types of operations at least, ext3 has 4 */ ++#define AuBrDynOp (AuDyLast * 4) + -+ if (br->br_xino.xi_file) -+ fput(br->br_xino.xi_file); -+ mutex_destroy(&br->br_xino.xi_nondir_mtx); ++#ifdef CONFIG_AUFS_HFSNOTIFY ++/* support for asynchronous destruction */ ++struct au_br_hfsnotify { ++ struct fsnotify_group *hfsn_group; ++}; ++#endif + -+ AuDebugOn(au_br_count(br)); -+ au_br_count_fin(br); ++/* sysfs entries */ ++struct au_brsysfs { ++ char name[16]; ++ struct attribute attr; ++}; + -+ 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); -+ } ++enum { ++ AuBrSysfs_BR, ++ AuBrSysfs_BRID, ++ AuBrSysfs_Last ++}; + -+ if (br->br_fhsm) { -+ au_br_fhsm_fin(br->br_fhsm); -+ au_delayed_kfree(br->br_fhsm); -+ } ++/* protected by superblock rwsem */ ++struct au_branch { ++ struct au_xino_file br_xino; + -+ key = br->br_dykey; -+ for (i = 0; i < AuBrDynOp; i++, key++) -+ if (*key) -+ au_dy_put(*key); -+ else -+ break; ++ aufs_bindex_t br_id; + -+ /* recursive lock, s_umount of branch's */ -+ lockdep_off(); -+ path_put(&br->br_path); -+ lockdep_on(); -+ if (wbr) -+ au_delayed_kfree(wbr); -+ au_delayed_kfree(br); -+} ++ int br_perm; ++ struct path br_path; ++ spinlock_t br_dykey_lock; ++ struct au_dykey *br_dykey[AuBrDynOp]; ++ struct percpu_counter br_count; + -+/* -+ * frees all branches -+ */ -+void au_br_free(struct au_sbinfo *sbinfo) -+{ -+ aufs_bindex_t bmax; -+ struct au_branch **br; ++ struct au_wbr *br_wbr; ++ struct au_br_fhsm *br_fhsm; + -+ AuRwMustWriteLock(&sbinfo->si_rwsem); ++ /* xino truncation */ ++ atomic_t br_xino_running; + -+ bmax = sbinfo->si_bbot + 1; -+ br = sbinfo->si_branch; -+ while (bmax--) -+ au_br_do_free(*br++); -+} ++#ifdef CONFIG_AUFS_HFSNOTIFY ++ struct au_br_hfsnotify *br_hfsn; ++#endif + -+/* -+ * 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; ++#ifdef CONFIG_SYSFS ++ /* entries under sysfs per mount-point */ ++ struct au_brsysfs br_sysfs[AuBrSysfs_Last]; ++#endif + -+ bbot = au_sbbot(sb); -+ for (bindex = 0; bindex <= bbot; bindex++) -+ if (au_sbr_id(sb, bindex) == br_id) -+ return bindex; -+ return -1; -+} ++ struct au_dr_br br_dirren; ++}; + +/* ---------------------------------------------------------------------- */ + -+/* -+ * add a branch -+ */ ++static inline struct vfsmount *au_br_mnt(struct au_branch *br) ++{ ++ return br->br_path.mnt; ++} + -+static int test_overlap(struct super_block *sb, struct dentry *h_adding, -+ struct dentry *h_root) ++static inline struct dentry *au_br_dentry(struct au_branch *br) +{ -+ 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); ++ return br->br_path.dentry; +} + -+/* -+ * 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) ++static inline struct super_block *au_br_sb(struct au_branch *br) +{ -+ struct au_branch *add_branch; -+ struct dentry *root; -+ struct inode *inode; -+ int err; ++ return au_br_mnt(br)->mnt_sb; ++} + -+ err = -ENOMEM; -+ root = sb->s_root; -+ add_branch = kzalloc(sizeof(*add_branch), GFP_NOFS); -+ if (unlikely(!add_branch)) -+ goto out; ++static inline void au_br_get(struct au_branch *br) ++{ ++ percpu_counter_inc(&br->br_count); ++} + -+ err = au_hnotify_init_br(add_branch, perm); -+ if (unlikely(err)) -+ goto out_br; ++static inline void au_br_put(struct au_branch *br) ++{ ++ percpu_counter_dec(&br->br_count); ++} + -+ 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; -+ } ++static inline s64 au_br_count(struct au_branch *br) ++{ ++ return percpu_counter_sum(&br->br_count); ++} + -+ if (au_br_fhsm(perm)) { -+ err = au_fhsm_br_alloc(add_branch); -+ if (unlikely(err)) -+ goto out_wbr; -+ } ++static inline void au_br_count_init(struct au_branch *br) ++{ ++ percpu_counter_init(&br->br_count, 0, GFP_NOFS); ++} + -+ 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 */ ++static inline void au_br_count_fin(struct au_branch *br) ++{ ++ percpu_counter_destroy(&br->br_count); ++} + -+out_wbr: -+ if (add_branch->br_wbr) -+ au_delayed_kfree(add_branch->br_wbr); -+out_hnotify: -+ au_hnotify_fin_br(add_branch); -+out_br: -+ au_delayed_kfree(add_branch); -+out: -+ return ERR_PTR(err); ++static inline int au_br_rdonly(struct au_branch *br) ++{ ++ return ((au_br_sb(br)->s_flags & MS_RDONLY) ++ || !au_br_writable(br->br_perm)) ++ ? -EROFS : 0; +} + -+/* -+ * test if the branch permission is legal or not. -+ */ -+static int test_br(struct inode *inode, int brperm, char *path) ++static inline int au_br_hnotifyable(int brperm __maybe_unused) +{ -+ int err; ++#ifdef CONFIG_AUFS_HNOTIFY ++ return !(brperm & AuBrPerm_RR); ++#else ++ return 0; ++#endif ++} + -+ err = (au_br_writable(brperm) && IS_RDONLY(inode)); -+ if (!err) -+ goto out; ++static inline int au_br_test_oflag(int oflag, struct au_branch *br) ++{ ++ int err, exec_flag; + -+ err = -EINVAL; -+ pr_err("write permission for readonly mount or inode, %s\n", path); ++ err = 0; ++ exec_flag = oflag & __FMODE_EXEC; ++ if (unlikely(exec_flag && path_noexec(&br->br_path))) ++ err = -EACCES; + -+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; -+ } ++/* 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); + -+ 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; -+ } ++/* xino.c */ ++static const loff_t au_loff_max = LLONG_MAX; + -+ err = -EDOM; -+ if (unlikely(add->bindex < 0 || bbot + 1 < add->bindex)) { -+ pr_err("bad index %d\n", add->bindex); -+ goto out; -+ } ++int au_xib_trunc(struct super_block *sb); ++ssize_t xino_fread(vfs_readf_t func, struct file *file, void *buf, size_t size, ++ loff_t *pos); ++ssize_t xino_fwrite(vfs_writef_t func, struct file *file, void *buf, ++ size_t size, loff_t *pos); ++struct file *au_xino_create2(struct file *base_file, struct file *copy_src); ++struct file *au_xino_create(struct super_block *sb, char *fname, int silent); ++ino_t au_xino_new_ino(struct super_block *sb); ++void au_xino_delete_inode(struct inode *inode, const int unlinked); ++int au_xino_write(struct super_block *sb, aufs_bindex_t bindex, ino_t h_ino, ++ ino_t ino); ++int au_xino_read(struct super_block *sb, aufs_bindex_t bindex, ino_t h_ino, ++ ino_t *ino); ++int au_xino_br(struct super_block *sb, struct au_branch *br, ino_t hino, ++ struct file *base_file, int do_test); ++int au_xino_trunc(struct super_block *sb, aufs_bindex_t bindex); + -+ inode = d_inode(add->path.dentry); -+ err = -ENOENT; -+ if (unlikely(!inode->i_nlink)) { -+ pr_err("no existence %s\n", add->pathname); -+ goto out; -+ } ++struct au_opt_xino; ++int au_xino_set(struct super_block *sb, struct au_opt_xino *xino, int remount); ++void au_xino_clr(struct super_block *sb); ++struct file *au_xino_def(struct super_block *sb); ++int au_xino_path(struct seq_file *seq, struct file *file); + -+ err = -EINVAL; -+ if (unlikely(inode->i_sb == sb)) { -+ pr_err("%s must be outside\n", add->pathname); -+ goto out; -+ } ++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); + -+ 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; -+ } ++/* 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; ++} + -+ err = test_br(d_inode(add->path.dentry), add->perm, add->pathname); -+ if (unlikely(err)) -+ goto out; ++static inline ++struct vfsmount *au_sbr_mnt(struct super_block *sb, aufs_bindex_t bindex) ++{ ++ return au_br_mnt(au_sbr(sb, bindex)); ++} + -+ if (bbot < 0) -+ return 0; /* success */ ++static inline ++struct super_block *au_sbr_sb(struct super_block *sb, aufs_bindex_t bindex) ++{ ++ return au_br_sb(au_sbr(sb, bindex)); ++} + -+ 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; -+ } ++static inline void au_sbr_get(struct super_block *sb, aufs_bindex_t bindex) ++{ ++ au_br_get(au_sbr(sb, bindex)); ++} + -+ 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)); -+ } ++static inline void au_sbr_put(struct super_block *sb, aufs_bindex_t bindex) ++{ ++ au_br_put(au_sbr(sb, bindex)); ++} + -+out: -+ return err; ++static inline int au_sbr_perm(struct super_block *sb, aufs_bindex_t bindex) ++{ ++ return au_sbr(sb, bindex)->br_perm; +} + -+/* -+ * 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) ++static inline int au_sbr_whable(struct super_block *sb, aufs_bindex_t bindex) +{ -+ int err, old_perm; -+ aufs_bindex_t bindex; -+ struct inode *h_inode; -+ struct au_wbr *wbr; -+ struct au_hinode *hdir; -+ struct dentry *h_dentry; ++ return au_br_whable(au_sbr_perm(sb, bindex)); ++} + -+ 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; ++/* ++ * wbr_wh_read_lock, wbr_wh_write_lock ++ * wbr_wh_read_unlock, wbr_wh_write_unlock, wbr_wh_downgrade_lock ++ */ ++AuSimpleRwsemFuncs(wbr_wh, struct au_wbr *wbr, &wbr->wbr_wh_rwsem); + -+ if (!err && wbr && !au_br_writable(new_perm)) { -+ au_delayed_kfree(wbr); -+ br->br_wbr = NULL; -+ } ++#define WbrWhMustNoWaiters(wbr) AuRwMustNoWaiters(&wbr->wbr_wh_rwsem) ++#define WbrWhMustAnyLock(wbr) AuRwMustAnyLock(&wbr->wbr_wh_rwsem) ++#define WbrWhMustWriteLock(wbr) AuRwMustWriteLock(&wbr->wbr_wh_rwsem) + -+out: -+ return err; -+} ++/* ---------------------------------------------------------------------- */ + -+static int au_wbr_init(struct au_branch *br, struct super_block *sb, -+ int perm) ++#ifdef CONFIG_AUFS_FHSM ++static inline void au_br_fhsm_init(struct au_br_fhsm *brfhsm) +{ -+ int err; -+ struct kstatfs kst; -+ struct au_wbr *wbr; ++ mutex_init(&brfhsm->bf_lock); ++ brfhsm->bf_jiffy = 0; ++ brfhsm->bf_readable = 0; ++} + -+ wbr = br->br_wbr; -+ au_rw_init(&wbr->wbr_wh_rwsem); -+ atomic_set(&wbr->wbr_wh_running, 0); ++static inline void au_br_fhsm_fin(struct au_br_fhsm *brfhsm) ++{ ++ mutex_destroy(&brfhsm->bf_lock); ++} ++#else ++AuStubVoid(au_br_fhsm_init, struct au_br_fhsm *brfhsm) ++AuStubVoid(au_br_fhsm_fin, struct au_br_fhsm *brfhsm) ++#endif + -+ /* -+ * 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); ++#endif /* __KERNEL__ */ ++#endif /* __AUFS_BRANCH_H__ */ +diff -urNp -x '*.orig' linux-4.9/fs/aufs/conf.mk linux-4.9/fs/aufs/conf.mk +--- linux-4.9/fs/aufs/conf.mk 1970-01-01 01:00:00.000000000 +0100 ++++ linux-4.9/fs/aufs/conf.mk 2021-02-24 16:15:09.521573529 +0100 +@@ -0,0 +1,39 @@ + -+out: -+ return err; -+} ++AuConfStr = CONFIG_AUFS_FS=${CONFIG_AUFS_FS} + -+/* 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 inode *h_inode; ++define AuConf ++ifdef ${1} ++AuConfStr += ${1}=${${1}} ++endif ++endef + -+ err = 0; -+ mutex_init(&br->br_xino.xi_nondir_mtx); -+ br->br_perm = add->perm; -+ br->br_path = add->path; /* set first, path_get() later */ -+ spin_lock_init(&br->br_dykey_lock); -+ au_br_count_init(br); -+ atomic_set(&br->br_xino_running, 0); -+ br->br_id = au_new_br_id(sb); -+ AuDebugOn(br->br_id < 0); ++AuConfAll = BRANCH_MAX_127 BRANCH_MAX_511 BRANCH_MAX_1023 BRANCH_MAX_32767 \ ++ SBILIST \ ++ HNOTIFY HFSNOTIFY \ ++ EXPORT INO_T_64 \ ++ XATTR \ ++ FHSM \ ++ RDU \ ++ DIRREN \ ++ SHWH \ ++ BR_RAMFS \ ++ BR_FUSE POLL \ ++ BR_HFSPLUS \ ++ BDEV_LOOP \ ++ DEBUG MAGIC_SYSRQ ++$(foreach i, ${AuConfAll}, \ ++ $(eval $(call AuConf,CONFIG_AUFS_${i}))) + -+ if (au_br_writable(add->perm)) { -+ err = au_wbr_init(br, sb, add->perm); -+ if (unlikely(err)) -+ goto out_err; ++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} + -+ if (au_opt_test(au_mntflags(sb), XINO)) { -+ h_inode = d_inode(add->path.dentry); -+ err = au_xino_br(sb, br, h_inode->i_ino, -+ au_sbr(sb, 0)->br_xino.xi_file, /*do_test*/1); -+ if (unlikely(err)) { -+ AuDebugOn(br->br_xino.xi_file); -+ goto out_err; -+ } -+ } ++-include ${srctree}/${src}/conf_priv.mk +diff -urNp -x '*.orig' linux-4.9/fs/aufs/cpup.c linux-4.9/fs/aufs/cpup.c +--- linux-4.9/fs/aufs/cpup.c 1970-01-01 01:00:00.000000000 +0100 ++++ linux-4.9/fs/aufs/cpup.c 2021-02-24 16:15:09.521573529 +0100 +@@ -0,0 +1,1414 @@ ++/* ++ * Copyright (C) 2005-2018 Junjiro R. Okajima ++ * ++ * This program, aufs is free software; you can redistribute it and/or modify ++ * it under the terms of the GNU General Public License as published by ++ * the Free Software Foundation; either version 2 of the License, or ++ * (at your option) any later version. ++ * ++ * This program is distributed in the hope that it will be useful, ++ * but WITHOUT ANY WARRANTY; without even the implied warranty of ++ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the ++ * GNU General Public License for more details. ++ * ++ * You should have received a copy of the GNU General Public License ++ * along with this program. If not, see . ++ */ + -+ sysaufs_br_init(br); -+ path_get(&br->br_path); -+ goto out; /* success */ ++/* ++ * copy-up functions, see wbr_policy.c for copy-down ++ */ + -+out_err: -+ memset(&br->br_path, 0, sizeof(br->br_path)); -+out: -+ return err; -+} ++#include ++#include ++#include ++#include "aufs.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) ++void au_cpup_attr_flags(struct inode *dst, unsigned int iflags) +{ -+ struct au_branch **brp; ++ const unsigned int mask = S_DEAD | S_SWAPFILE | S_PRIVATE ++ | S_NOATIME | S_NOCMTIME | S_AUTOMOUNT; + -+ AuRwMustWriteLock(&sbinfo->si_rwsem); ++ BUILD_BUG_ON(sizeof(iflags) != sizeof(dst->i_flags)); + -+ 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; ++ dst->i_flags |= iflags & ~mask; ++ if (au_test_fs_notime(dst->i_sb)) ++ dst->i_flags |= S_NOATIME | S_NOCMTIME; +} + -+static void au_br_do_add_hdp(struct au_dinfo *dinfo, aufs_bindex_t bindex, -+ aufs_bindex_t bbot, aufs_bindex_t amount) ++void au_cpup_attr_timesizes(struct inode *inode) +{ -+ struct au_hdentry *hdp; -+ -+ AuRwMustWriteLock(&dinfo->di_rwsem); ++ struct inode *h_inode; + -+ 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; ++ h_inode = au_h_iptr(inode, au_ibtop(inode)); ++ fsstack_copy_attr_times(inode, h_inode); ++ fsstack_copy_inode_size(inode, h_inode); +} + -+static void au_br_do_add_hip(struct au_iinfo *iinfo, aufs_bindex_t bindex, -+ aufs_bindex_t bbot, aufs_bindex_t amount) ++void au_cpup_attr_nlink(struct inode *inode, int force) +{ -+ struct au_hinode *hip; ++ struct inode *h_inode; ++ struct super_block *sb; ++ aufs_bindex_t bindex, bbot; + -+ AuRwMustWriteLock(&iinfo->ii_rwsem); ++ 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; + -+ 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; ++ /* ++ * 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); ++ } ++ } +} + -+static void au_br_do_add(struct super_block *sb, struct au_branch *br, -+ aufs_bindex_t bindex) ++void au_cpup_attr_changeable(struct inode *inode) +{ -+ struct dentry *root, *h_dentry; -+ struct inode *root_inode, *h_inode; -+ aufs_bindex_t bbot, amount; ++ struct inode *h_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(); ++ 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); +} + -+int au_br_add(struct super_block *sb, struct au_opt_add *add, int remount) ++void au_cpup_igen(struct inode *inode, struct inode *h_inode) +{ -+ int err; -+ aufs_bindex_t bbot, add_bindex; -+ struct dentry *root, *h_dentry; -+ struct inode *root_inode; -+ struct au_branch *add_branch; -+ -+ root = sb->s_root; -+ root_inode = d_inode(root); -+ IMustLock(root_inode); -+ IiMustWriteLock(root_inode); -+ err = test_add(sb, add, remount); -+ if (unlikely(err < 0)) -+ goto out; -+ if (err) { -+ err = 0; -+ goto out; /* success */ -+ } -+ -+ bbot = au_sbbot(sb); -+ add_branch = au_br_alloc(sb, bbot + 2, add->perm); -+ err = PTR_ERR(add_branch); -+ if (IS_ERR(add_branch)) -+ goto out; -+ -+ err = au_br_init(add_branch, sb, add); -+ if (unlikely(err)) { -+ au_br_do_free(add_branch); -+ goto out; -+ } ++ struct au_iinfo *iinfo = au_ii(inode); + -+ add_bindex = add->bindex; -+ if (!remount) -+ au_br_do_add(sb, add_branch, add_bindex); -+ else { -+ sysaufs_brs_del(sb, add_bindex); -+ au_br_do_add(sb, add_branch, add_bindex); -+ sysaufs_brs_add(sb, add_bindex); -+ } ++ IiMustWriteLock(inode); + -+ 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)); ++ iinfo->ii_higen = h_inode->i_generation; ++ iinfo->ii_hsb1 = h_inode->i_sb; ++} + -+ /* -+ * this test/set prevents aufs from handling unnecesary notify events -+ * of xino files, in case of re-adding a writable branch which was -+ * once detached from aufs. -+ */ -+ if (au_xino_brid(sb) < 0 -+ && au_br_writable(add_branch->br_perm) -+ && !au_test_fs_bad_xino(h_dentry->d_sb) -+ && add_branch->br_xino.xi_file -+ && add_branch->br_xino.xi_file->f_path.dentry->d_parent == h_dentry) -+ au_xino_brid_set(sb, add_branch->br_id); ++void au_cpup_attr_all(struct inode *inode, int force) ++{ ++ struct inode *h_inode; + -+out: -+ return err; ++ 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); +} + +/* ---------------------------------------------------------------------- */ + -+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 au_sphlhead *files; -+ struct au_finfo *finfo; ++/* Note: dt_dentry and dt_h_dentry are not dget/dput-ed */ + -+ n = 0; -+ p = a; -+ files = &au_sbi(sb)->si_files; -+ spin_lock(&files->spin); -+ hlist_for_each_entry(finfo, &files->head, 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); -+ } -+ } -+ spin_unlock(&files->spin); ++/* 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; + -+ return n; ++ 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(); */ +} + -+static struct file **au_farray_alloc(struct super_block *sb, -+ unsigned long long *max) ++void au_dtime_revert(struct au_dtime *dt) +{ -+ *max = au_nfiles(sb); -+ return au_array_alloc(max, au_farray_cb, sb, /*arg*/NULL); -+} ++ struct iattr attr; ++ int err; + -+static void au_farray_free(struct file **a, unsigned long long max) -+{ -+ unsigned long long ull; ++ 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; + -+ for (ull = 0; ull < max; ull++) -+ if (a[ull]) -+ fput(a[ull]); -+ kvfree(a); ++ /* 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); +} + +/* ---------------------------------------------------------------------- */ + -+/* -+ * delete a branch -+ */ -+ -+/* to show the line number, do not make it inlined function */ -+#define AuVerbose(do_info, fmt, ...) do { \ -+ if (do_info) \ -+ pr_info(fmt, ##__VA_ARGS__); \ -+} while (0) -+ -+static int au_test_ibusy(struct inode *inode, aufs_bindex_t btop, -+ aufs_bindex_t bbot) -+{ -+ return (inode && !S_ISDIR(inode->i_mode)) || btop == bbot; -+} -+ -+static int au_test_dbusy(struct dentry *dentry, aufs_bindex_t btop, -+ aufs_bindex_t bbot) -+{ -+ return au_test_ibusy(d_inode(dentry), btop, bbot); -+} ++/* internal use only */ ++struct au_cpup_reg_attr { ++ int valid; ++ struct kstat st; ++ unsigned int iflags; /* inode->i_flags */ ++}; + -+/* -+ * 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) ++static noinline_for_stack ++int cpup_iattr(struct dentry *dst, aufs_bindex_t bindex, struct dentry *h_src, ++ struct au_cpup_reg_attr *h_src_attr) +{ -+ int err, i, j, ndentry; -+ aufs_bindex_t btop, bbot; -+ struct au_dcsub_pages dpages; -+ struct au_dpage *dpage; -+ struct dentry *d; ++ 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; + -+ 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; ++ h_path.dentry = au_h_dptr(dst, bindex); ++ h_idst = d_inode(h_path.dentry); ++ br = au_sbr(dst->d_sb, bindex); ++ h_path.mnt = au_br_mnt(br); ++ h_isrc = d_inode(h_src); ++ ia.ia_valid = ATTR_FORCE | ATTR_UID | ATTR_GID ++ | ATTR_ATIME | ATTR_MTIME ++ | ATTR_ATIME_SET | ATTR_MTIME_SET; ++ if (h_src_attr && h_src_attr->valid) { ++ h_st = &h_src_attr->st; ++ ia.ia_uid = h_st->uid; ++ ia.ia_gid = h_st->gid; ++ ia.ia_atime = h_st->atime; ++ ia.ia_mtime = h_st->mtime; ++ if (h_idst->i_mode != h_st->mode ++ && !S_ISLNK(h_idst->i_mode)) { ++ ia.ia_valid |= ATTR_MODE; ++ ia.ia_mode = h_st->mode; ++ } ++ sbits = !!(h_st->mode & (S_ISUID | S_ISGID)); ++ au_cpup_attr_flags(h_idst, h_src_attr->iflags); ++ } else { ++ ia.ia_uid = h_isrc->i_uid; ++ ia.ia_gid = h_isrc->i_gid; ++ ia.ia_atime = h_isrc->i_atime; ++ ia.ia_mtime = h_isrc->i_mtime; ++ if (h_idst->i_mode != h_isrc->i_mode ++ && !S_ISLNK(h_idst->i_mode)) { ++ ia.ia_valid |= ATTR_MODE; ++ ia.ia_mode = h_isrc->i_mode; ++ } ++ sbits = !!(h_isrc->i_mode & (S_ISUID | S_ISGID)); ++ au_cpup_attr_flags(h_idst, h_isrc->i_flags); ++ } ++ /* no delegation since it is just created */ ++ err = vfsub_notify_change(&h_path, &ia, /*delegated*/NULL); + -+ 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; -+ } -+ } ++ /* 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); ++ } + -+ /* 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); -+ } ++ icex = br->br_perm & AuBrAttr_ICEX; ++ if (!err) { ++ mnt_flags = au_mntflags(dst->d_sb); ++ verbose = !!au_opt_test(mnt_flags, VERBOSE); ++ err = au_cpup_xattr(h_path.dentry, h_src, icex, verbose); + } + -+out_dpages: -+ au_dpages_free(&dpages); -+out: + return err; +} + -+static int test_inode_busy(struct super_block *sb, aufs_bindex_t bindex, -+ unsigned int sigen, const unsigned int verbose) ++/* ---------------------------------------------------------------------- */ ++ ++static int au_do_copy_file(struct file *dst, struct file *src, loff_t len, ++ char *buf, unsigned long blksize) +{ + int err; -+ unsigned long long max, ull; -+ struct inode *i, **array; -+ aufs_bindex_t btop, bbot; ++ size_t sz, rbytes, wbytes; ++ unsigned char all_zero; ++ char *p, *zp; ++ struct inode *h_inode; ++ /* reduce stack usage */ ++ struct iattr *ia; + -+ array = au_iarray_alloc(sb, &max); -+ err = PTR_ERR(array); -+ if (IS_ERR(array)) -+ goto out; ++ zp = page_address(ZERO_PAGE(0)); ++ if (unlikely(!zp)) ++ return -ENOMEM; /* possible? */ + + err = 0; -+ AuDbg("b%d\n", bindex); -+ for (ull = 0; !err && ull < max; ull++) { -+ i = array[ull]; -+ if (unlikely(!i)) ++ all_zero = 0; ++ while (len) { ++ AuDbg("len %lld\n", len); ++ sz = blksize; ++ if (len < blksize) ++ sz = len; ++ ++ rbytes = 0; ++ /* todo: signal_pending? */ ++ while (!rbytes || err == -EAGAIN || err == -EINTR) { ++ rbytes = vfsub_read_k(src, buf, sz, &src->f_pos); ++ err = rbytes; ++ } ++ if (unlikely(err < 0)) + break; -+ 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; ++ 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; + -+ 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); ++ AuLabel(hole); ++ res = vfsub_llseek(dst, rbytes, SEEK_CUR); ++ err = res; ++ if (unlikely(res < 0)) ++ break; + } -+ ii_read_unlock(i); ++ len -= rbytes; ++ err = 0; + } -+ au_iarray_free(array, max); + -+out: -+ return err; -+} ++ /* the last block may be a hole */ ++ if (!err && all_zero) { ++ AuLabel(last hole); + -+static int test_children_busy(struct dentry *root, aufs_bindex_t bindex, -+ const unsigned int verbose) -+{ -+ int err; -+ unsigned int sigen; ++ 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--; ++ } + -+ 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() */ ++ 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; +} + -+static int test_dir_busy(struct file *file, aufs_bindex_t br_id, -+ struct file **to_free, int *idx) ++int au_copy_file(struct file *dst, struct file *src, loff_t len) +{ + int err; -+ unsigned char matched, root; -+ aufs_bindex_t bindex, bbot; -+ struct au_fidir *fidir; -+ struct au_hfile *hfile; ++ unsigned long blksize; ++ unsigned char do_kfree; ++ char *buf; + -+ err = 0; -+ root = IS_ROOT(file->f_path.dentry); -+ if (root) { -+ get_file(file); -+ to_free[*idx] = file; -+ (*idx)++; ++ err = -ENOMEM; ++ blksize = dst->f_path.dentry->d_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; -+ } + -+ 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 (len > (1 << 22)) ++ AuDbg("copying a large file %lld\n", (long long)len); + -+ if (hfile->hf_br->br_id == br_id) { -+ matched = 1; -+ break; -+ } -+ } -+ if (matched) -+ err = -EBUSY; ++ src->f_pos = 0; ++ dst->f_pos = 0; ++ err = au_do_copy_file(dst, src, len, buf, blksize); ++ if (do_kfree) ++ kfree(buf); ++ else ++ free_page((unsigned long)buf); + +out: + return err; +} + -+static int test_file_busy(struct super_block *sb, aufs_bindex_t br_id, -+ struct file **to_free, int opened) ++/* ++ * 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, idx; -+ unsigned long long ull, max; -+ aufs_bindex_t btop; -+ struct file *file, **array; -+ struct dentry *root; -+ struct au_hfile *hfile; ++ int err, i; ++ enum { SRC, DST }; ++ struct { ++ aufs_bindex_t bindex; ++ unsigned int flags; ++ struct dentry *dentry; ++ int force_wr; ++ struct file *file; ++ void *label; ++ } *f, file[] = { ++ { ++ .bindex = cpg->bsrc, ++ .flags = O_RDONLY | O_NOATIME | O_LARGEFILE, ++ .label = &&out ++ }, ++ { ++ .bindex = cpg->bdst, ++ .flags = O_WRONLY | O_NOATIME | O_LARGEFILE, ++ .force_wr = !!au_ftest_cpup(cpg->flags, RWDST), ++ .label = &&out_src ++ } ++ }; ++ struct super_block *sb, *h_src_sb; ++ struct inode *h_src_inode; ++ struct task_struct *tsk = current; + -+ array = au_farray_alloc(sb, &max); -+ err = PTR_ERR(array); -+ if (IS_ERR(array)) -+ goto out; ++ /* 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); ++ err = PTR_ERR(f->file); ++ if (IS_ERR(f->file)) ++ goto *f->label; ++ } + -+ 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; ++ /* 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); + -+ /* 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; ++ if (h_src_sb != file_inode(file[DST].file)->i_sb ++ || !file[DST].file->f_op->clone_file_range) ++ err = au_copy_file(file[DST].file, file[SRC].file, cpg->len); ++ else { ++ if (!au_test_nfs(h_src_sb)) { ++ inode_unlock_shared(h_src_inode); ++ err = vfsub_clone_file_range(file[SRC].file, ++ file[DST].file, cpg->len); ++ vfsub_inode_lock_shared_nested(h_src_inode, ++ AuLsc_I_CHILD); + } else -+ err = test_dir_busy(file, br_id, to_free, &idx); -+ fi_read_unlock(file); -+ if (unlikely(err)) -+ break; ++ err = vfsub_clone_file_range(file[SRC].file, ++ file[DST].file, cpg->len); ++ if (unlikely(err == -EOPNOTSUPP && au_test_nfs(h_src_sb))) ++ /* the backend fs on NFS may not support cloning */ ++ err = au_copy_file(file[DST].file, file[SRC].file, ++ cpg->len); ++ AuTraceErr(err); + } -+ di_write_lock_child(root); -+ au_farray_free(array, max); -+ AuDebugOn(idx > opened); + ++ /* i wonder if we had O_NO_DELAY_FPUT flag */ ++ if (tsk->flags & PF_KTHREAD) ++ __fput_sync(file[DST].file); ++ else { ++ /* it happend 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_sbr_put(sb, file[DST].bindex); ++ ++out_src: ++ fput(file[SRC].file); ++ au_sbr_put(sb, file[SRC].bindex); +out: + return err; +} + -+static void br_del_file(struct file **to_free, unsigned long long opened, -+ aufs_bindex_t br_id) ++static int au_do_cpup_regular(struct au_cp_generic *cpg, ++ struct au_cpup_reg_attr *h_src_attr) +{ -+ 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; ++ int err, rerr; ++ loff_t l; ++ struct path h_path; ++ struct inode *h_src_inode, *h_dst_inode; + -+ /* 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; ++ 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 */ ++ vfsub_inode_lock_shared_nested(h_src_inode, AuLsc_I_CHILD); ++ au_pin_hdir_unlock(cpg->pin); + -+ if (hfile->hf_br->br_id == br_id) { -+ bfound = bindex; -+ break; -+ } ++ 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 = vfs_getattr(&h_path, &h_src_attr->st); ++ else { ++ inode_unlock_shared(h_src_inode); ++ err = vfs_getattr(&h_path, &h_src_attr->st); ++ vfsub_inode_lock_shared_nested(h_src_inode, ++ AuLsc_I_CHILD); + } -+ 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; -+ } ++ if (unlikely(err)) { ++ inode_unlock_shared(h_src_inode); ++ goto out; + } -+ fi_write_unlock(file); ++ 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); + } -+} -+ -+static void au_br_do_del_brp(struct au_sbinfo *sbinfo, -+ const aufs_bindex_t bindex, -+ const aufs_bindex_t bbot) -+{ -+ struct au_branch **brp, **p; -+ -+ AuRwMustWriteLock(&sbinfo->si_rwsem); -+ -+ brp = sbinfo->si_branch + bindex; -+ if (bindex < bbot) -+ memmove(brp, brp + 1, sizeof(*brp) * (bbot - bindex)); -+ sbinfo->si_branch[0 + bbot] = NULL; -+ sbinfo->si_bbot--; + -+ p = au_krealloc(sbinfo->si_branch, sizeof(*p) * bbot, AuGFP_SBILIST, -+ /*may_shrink*/1); -+ if (p) -+ sbinfo->si_branch = p; -+ /* harmless error */ ++out: ++ return err; +} + -+static void au_br_do_del_hdp(struct au_dinfo *dinfo, const aufs_bindex_t bindex, -+ const aufs_bindex_t bbot) ++static int au_do_cpup_symlink(struct path *h_path, struct dentry *h_src, ++ struct inode *h_dir) +{ -+ struct au_hdentry *hdp, *p; -+ -+ AuRwMustWriteLock(&dinfo->di_rwsem); -+ -+ hdp = au_hdentry(dinfo, bindex); -+ if (bindex < bbot) -+ memmove(hdp, hdp + 1, sizeof(*hdp) * (bbot - bindex)); -+ /* au_h_dentry_init(au_hdentry(dinfo, bbot); */ -+ dinfo->di_bbot--; ++ int err, symlen; ++ mm_segment_t old_fs; ++ union { ++ char *k; ++ char __user *u; ++ } sym; ++ struct inode *h_inode = d_inode(h_src); ++ const struct inode_operations *h_iop = h_inode->i_op; + -+ p = au_krealloc(dinfo->di_hdentry, sizeof(*p) * bbot, AuGFP_SBILIST, -+ /*may_shrink*/1); -+ if (p) -+ dinfo->di_hdentry = p; -+ /* harmless error */ -+} ++ err = -ENOSYS; ++ if (unlikely(!h_iop->readlink)) ++ goto out; + -+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; ++ err = -ENOMEM; ++ sym.k = (void *)__get_free_page(GFP_NOFS); ++ if (unlikely(!sym.k)) ++ goto out; + -+ AuRwMustWriteLock(&iinfo->ii_rwsem); ++ /* unnecessary to support mmap_sem since symlink is not mmap-able */ ++ old_fs = get_fs(); ++ set_fs(KERNEL_DS); ++ symlen = h_iop->readlink(h_src, sym.u, PATH_MAX); ++ err = symlen; ++ set_fs(old_fs); + -+ 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--; ++ if (symlen > 0) { ++ sym.k[symlen] = 0; ++ err = vfsub_symlink(h_dir, h_path, sym.k); ++ } ++ free_page((unsigned long)sym.k); + -+ p = au_krealloc(iinfo->ii_hinode, sizeof(*p) * bbot, AuGFP_SBILIST, -+ /*may_shrink*/1); -+ if (p) -+ iinfo->ii_hinode = p; -+ /* harmless error */ ++out: ++ return err; +} + -+static void au_br_do_del(struct super_block *sb, aufs_bindex_t bindex, -+ struct au_branch *br) ++/* ++ * regardless 'acl' option, reset all ACL. ++ * All ACL will be copied up later from the original entry on the lower branch. ++ */ ++static int au_reset_acl(struct inode *h_dir, struct path *h_path, umode_t mode) +{ -+ aufs_bindex_t bbot; -+ struct au_sbinfo *sbinfo; -+ struct dentry *root, *h_root; -+ struct inode *inode, *h_inode; -+ struct au_hinode *hinode; -+ -+ SiMustWriteLock(sb); -+ -+ root = sb->s_root; -+ inode = d_inode(root); -+ sbinfo = au_sbi(sb); -+ bbot = sbinfo->si_bbot; -+ -+ h_root = au_h_dptr(root, bindex); -+ hinode = au_hi(inode, bindex); -+ h_inode = au_igrab(hinode->hi_inode); -+ au_hiput(hinode); -+ -+ au_sbilist_lock(); -+ au_br_do_del_brp(sbinfo, bindex, bbot); -+ au_br_do_del_hdp(au_di(root), bindex, bbot); -+ au_br_do_del_hip(au_ii(inode), bindex, bbot); -+ au_sbilist_unlock(); ++ int err; ++ struct dentry *h_dentry; ++ struct inode *h_inode; + -+ dput(h_root); -+ iput(h_inode); -+ au_br_do_free(br); -+} ++ h_dentry = h_path->dentry; ++ h_inode = d_inode(h_dentry); ++ /* forget_all_cached_acls(h_inode)); */ ++ err = vfsub_removexattr(h_dentry, XATTR_NAME_POSIX_ACL_ACCESS); ++ AuTraceErr(err); ++ if (err == -EOPNOTSUPP) ++ err = 0; ++ if (!err) ++ err = vfsub_acl_chmod(h_inode, mode); + -+static unsigned long long empty_cb(struct super_block *sb, void *array, -+ unsigned long long max, void *arg) -+{ -+ return max; ++ AuTraceErr(err); ++ return err; +} + -+int au_br_del(struct super_block *sb, struct au_opt_del *del, int remount) ++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, rerr, i; -+ unsigned long long opened; -+ unsigned int mnt_flags; -+ aufs_bindex_t bindex, bbot, br_id; -+ unsigned char do_wh, verbose; -+ struct au_branch *br; -+ struct au_wbr *wbr; -+ struct dentry *root; -+ struct file **to_free; -+ -+ err = 0; -+ opened = 0; -+ to_free = NULL; -+ root = sb->s_root; -+ bindex = au_find_dbindex(root, del->h_path.dentry); -+ if (bindex < 0) { -+ if (remount) -+ goto out; /* success */ -+ err = -ENOENT; -+ pr_err("%s no such branch\n", del->pathname); -+ goto out; -+ } -+ AuDbg("bindex b%d\n", bindex); -+ -+ err = -EBUSY; -+ mnt_flags = au_mntflags(sb); -+ verbose = !!au_opt_test(mnt_flags, VERBOSE); -+ bbot = au_sbbot(sb); -+ if (unlikely(!bbot)) { -+ AuVerbose(verbose, "no more branches left\n"); -+ goto out; -+ } -+ br = au_sbr(sb, bindex); -+ AuDebugOn(!path_equal(&br->br_path, &del->h_path)); -+ -+ br_id = br->br_id; -+ opened = au_br_count(br); -+ 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; -+ } -+ } ++ int err; ++ struct inode *dir, *inode; + -+ err = test_children_busy(root, bindex, verbose); -+ if (unlikely(err)) { -+ if (do_wh) -+ goto out_wh; ++ err = vfsub_removexattr(h_path->dentry, XATTR_NAME_POSIX_ACL_DEFAULT); ++ AuTraceErr(err); ++ if (err == -EOPNOTSUPP) ++ err = 0; ++ if (unlikely(err)) + 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); -+ } -+ -+ if (!remount) -+ au_br_do_del(sb, bindex, br); -+ else { -+ sysaufs_brs_del(sb, bindex); -+ au_br_do_del(sb, bindex, br); -+ sysaufs_brs_add(sb, bindex); -+ } -+ -+ 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); -+ -+ if (au_xino_brid(sb) == br_id) -+ au_xino_brid_set(sb, -1); -+ 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); ++ /* ++ * strange behaviour from the users view, ++ * particularry 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: -+ if (to_free) -+ au_farray_free(to_free, opened); + return err; +} + -+/* ---------------------------------------------------------------------- */ -+ -+static int au_ibusy(struct super_block *sb, struct aufs_ibusy __user *arg) ++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; -+ aufs_bindex_t btop, bbot; -+ struct aufs_ibusy ibusy; -+ struct inode *inode, *h_inode; -+ -+ err = -EPERM; -+ if (unlikely(!capable(CAP_SYS_ADMIN))) -+ goto out; ++ 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; + -+ err = copy_from_user(&ibusy, arg, sizeof(ibusy)); -+ if (!err) -+ err = !access_ok(VERIFY_WRITE, &arg->h_ino, sizeof(arg->h_ino)); -+ if (unlikely(err)) { -+ err = -EFAULT; -+ AuTraceErr(err); -+ goto out; -+ } ++ /* 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)); + -+ err = -EINVAL; -+ si_read_lock(sb, AuLock_FLUSH); -+ if (unlikely(ibusy.bindex < 0 || ibusy.bindex > au_sbbot(sb))) -+ goto out_unlock; ++ /* 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); + -+ 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; ++ 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; + -+ 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; ++ 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, S_IRUSR | S_IWUSR, ++ /*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; + } -+ ii_read_unlock(inode); -+ iput(inode); ++ if (!err) ++ err = au_reset_acl(h_dir, &h_path, mode); ++ ++ mnt_flags = au_mntflags(sb); ++ if (!au_opt_test(mnt_flags, UDBA_NONE) ++ && !isdir ++ && au_opt_test(mnt_flags, XINO) ++ && (h_inode->i_nlink == 1 ++ || (h_inode->i_state & I_LINKABLE)) ++ /* todo: unnecessary? */ ++ /* && d_inode(cpg->dentry)->i_nlink == 1 */ ++ && cpg->bdst < cpg->bsrc ++ && !au_ftest_cpup(cpg->flags, KEEPLINO)) ++ au_xino_write(sb, cpg->bsrc, h_inode->i_ino, /*ino*/0); ++ /* ignore this error */ + -+out_unlock: -+ si_read_unlock(sb); + if (!err) { -+ err = __put_user(ibusy.h_ino, &arg->h_ino); -+ if (unlikely(err)) { -+ err = -EFAULT; -+ AuTraceErr(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); + } -+out: ++ ++ if (do_dt) ++ au_dtime_revert(&dt); + return err; +} + -+long au_ibusy_ioctl(struct file *file, unsigned long arg) ++static int au_do_ren_after_cpup(struct au_cp_generic *cpg, struct path *h_path) +{ -+ return au_ibusy(file->f_path.dentry->d_sb, (void __user *)arg); -+} ++ int err; ++ struct dentry *dentry, *h_dentry, *h_parent, *parent; ++ struct inode *h_dir; ++ aufs_bindex_t bdst; + -+#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 ++ dentry = cpg->dentry; ++ bdst = cpg->bdst; ++ h_dentry = au_h_dptr(dentry, bdst); ++ if (!au_ftest_cpup(cpg->flags, OVERWRITE)) { ++ dget(h_dentry); ++ au_set_h_dptr(dentry, bdst, NULL); ++ err = au_lkup_neg(dentry, bdst, /*wh*/0); ++ if (!err) ++ h_path->dentry = dget(au_h_dptr(dentry, bdst)); ++ au_set_h_dptr(dentry, bdst, h_dentry); ++ } else { ++ err = 0; ++ parent = dget_parent(dentry); ++ h_parent = au_h_dptr(parent, bdst); ++ dput(parent); ++ h_path->dentry = vfsub_lkup_one(&dentry->d_name, h_parent); ++ if (IS_ERR(h_path->dentry)) ++ err = PTR_ERR(h_path->dentry); ++ } ++ if (unlikely(err)) ++ goto out; + -+/* ---------------------------------------------------------------------- */ ++ h_parent = h_dentry->d_parent; /* dir inode is locked */ ++ h_dir = d_inode(h_parent); ++ IMustLock(h_dir); ++ AuDbg("%pd %pd\n", h_dentry, h_path->dentry); ++ /* no delegation since it is just created */ ++ err = vfsub_rename(h_dir, h_dentry, h_dir, h_path, /*delegated*/NULL, ++ /*flags*/0); ++ dput(h_path->dentry); ++ ++out: ++ return err; ++} + +/* -+ * change a branch permission ++ * 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 unnecrssary. + */ -+ -+static void au_warn_ima(void) ++static int au_cpup_single(struct au_cp_generic *cpg, struct dentry *dst_parent) +{ -+#ifdef CONFIG_IMA -+ /* since it doesn't support mark_files_ro() */ -+ AuWarn1("RW -> RO makes IMA to produce wrong message\n"); -+#endif -+} ++ int err, rerr; ++ aufs_bindex_t old_ibtop; ++ unsigned char isdir, plink; ++ struct dentry *h_src, *h_dst, *h_parent; ++ struct inode *dst_inode, *h_dir, *inode, *delegated, *src_inode; ++ struct super_block *sb; ++ struct au_branch *br; ++ /* to reuduce stack size */ ++ struct { ++ struct au_dtime dt; ++ struct path h_path; ++ struct au_cpup_reg_attr h_src_attr; ++ } *a; + -+static int do_need_sigen_inc(int a, int b) -+{ -+ return au_br_whable(a) && !au_br_whable(b); -+} ++ err = -ENOMEM; ++ a = kmalloc(sizeof(*a), GFP_NOFS); ++ if (unlikely(!a)) ++ goto out; ++ a->h_src_attr.valid = 0; + -+static int need_sigen_inc(int old, int new) -+{ -+ return do_need_sigen_inc(old, new) -+ || do_need_sigen_inc(new, old); -+} ++ 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); + -+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; ++ h_src = au_h_dptr(cpg->dentry, cpg->bsrc); ++ inode = d_inode(cpg->dentry); + -+ mnt_flags = au_mntflags(sb); -+ verbose = !!au_opt_test(mnt_flags, VERBOSE); ++ if (!dst_parent) ++ dst_parent = dget_parent(cpg->dentry); ++ else ++ dget(dst_parent); + -+ array = au_farray_alloc(sb, &max); -+ err = PTR_ERR(array); -+ if (IS_ERR(array)) -+ goto out; ++ 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; ++ } + -+ do_warn = 0; -+ br_id = au_sbr_id(sb, bindex); -+ for (ull = 0; ull < max; ull++) { -+ file = array[ull]; -+ if (unlikely(!file)) -+ break; ++ if (dst_inode->i_nlink) { ++ const int do_dt = au_ftest_cpup(cpg->flags, DTIME); + -+ /* 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; -+ } ++ 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; ++ } + -+ 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); -+ } ++ if (do_dt) { ++ a->h_path.dentry = h_parent; ++ au_dtime_store(&a->dt, dst_parent, &a->h_path); ++ } + -+ FiMustNoWaiters(file); -+ fi_read_unlock(file); -+ fput(file); ++ 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); + } + -+ err = 0; -+ if (do_warn) -+ au_warn_ima(); ++ 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); */ + -+ for (ull = 0; ull < max; ull++) { -+ file = array[ull]; -+ if (!file) -+ continue; ++ err = cpup_iattr(cpg->dentry, cpg->bdst, h_src, &a->h_src_attr); ++ if (unlikely(err)) { ++ /* todo: necessary? */ ++ /* au_pin_hdir_relock(cpg->pin); */ /* ignore an error */ ++ inode_unlock(dst_inode); ++ goto out_rev; ++ } + -+ /* todo: already flushed? */ -+ /* -+ * fs/super.c:mark_files_ro() is gone, but aufs keeps its -+ * approach which resets f_mode and calls mnt_drop_write() and -+ * file_release_write() for each file, because the branch -+ * attribute in aufs world is totally different from the native -+ * fs rw/ro mode. -+ */ -+ /* fi_read_lock(file); */ -+ hfile = &au_fi(file)->fi_htop; -+ hf = hfile->hf_file; -+ /* fi_read_unlock(file); */ -+ spin_lock(&hf->f_lock); -+ writer = !!(hf->f_mode & FMODE_WRITER); -+ hf->f_mode &= ~(FMODE_WRITE | FMODE_WRITER); -+ spin_unlock(&hf->f_lock); -+ if (writer) { -+ put_write_access(file_inode(hf)); -+ __mnt_drop_write(hf->f_path.mnt); ++ 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)); + -+out_array: -+ au_farray_free(array, max); -+out: -+ AuTraceErr(err); -+ return err; -+} ++ /* todo: necessary? */ ++ /* err = au_pin_hdir_relock(cpg->pin); */ ++ inode_unlock(dst_inode); ++ if (unlikely(err)) ++ goto out_rev; + -+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; ++ 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); + -+ 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; ++ if (au_ftest_cpup(cpg->flags, RENAME)) { ++ a->h_path.dentry = h_dst; ++ err = au_do_ren_after_cpup(cpg, &a->h_path); + } -+ AuDbg("bindex b%d\n", bindex); ++ if (!err) ++ goto out_parent; /* success */ + -+ err = test_br(d_inode(mod->h_root), mod->perm, mod->path); -+ if (unlikely(err)) -+ goto out; ++ /* 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); ++ kfree(a); ++out: ++ return err; ++} + -+ br = au_sbr(sb, bindex); -+ AuDebugOn(mod->h_root != au_br_dentry(br)); -+ if (br->br_perm == mod->perm) -+ return 0; /* success */ ++#if 0 /* reserved */ ++struct au_cpup_single_args { ++ int *errp; ++ struct au_cp_generic *cpg; ++ struct dentry *dst_parent; ++}; + -+ /* 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; -+ } ++static void au_call_cpup_single(void *args) ++{ ++ struct au_cpup_single_args *a = args; + -+ 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; ++ 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 + -+ 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); ++/* ++ * prevent SIGXFSZ in copy-up. ++ * testing CAP_MKNOD is for generic fs, ++ * but CAP_FSETID is for xfs only, currently. ++ */ ++static int au_cpup_sio_test(struct au_pin *pin, umode_t mode) ++{ ++ int do_sio; ++ struct super_block *sb; ++ struct inode *h_dir; + -+ 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; -+ } -+ } ++ 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; + } -+ } 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_delayed_kfree(br->br_wbr); -+ br->br_wbr = NULL; -+ } ++ 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 (unlikely(err)) -+ goto out_bf; -+ -+ if (au_br_fhsm(br->br_perm)) { -+ if (!au_br_fhsm(mod->perm)) { -+ /* fhsm --> non-fhsm */ -+ au_br_fhsm_fin(br->br_fhsm); -+ au_delayed_kfree(br->br_fhsm); -+ br->br_fhsm = NULL; -+ } -+ } else if (au_br_fhsm(mod->perm)) -+ /* non-fhsm --> fhsm */ -+ br->br_fhsm = bf; -+ -+ *do_refresh |= need_sigen_inc(br->br_perm, mod->perm); -+ br->br_perm = mod->perm; -+ goto out; /* success */ + -+out_bf: -+ if (bf) -+ au_delayed_kfree(bf); -+out: -+ AuTraceErr(err); -+ return err; ++ return do_sio; +} + -+/* ---------------------------------------------------------------------- */ -+ -+int au_br_stfs(struct au_branch *br, struct aufs_stfs *stfs) ++#if 0 /* reserved */ ++int au_sio_cpup_single(struct au_cp_generic *cpg, struct dentry *dst_parent) +{ -+ int err; -+ struct kstatfs kstfs; ++ int err, wkq_err; ++ struct dentry *h_dentry; + -+ 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; ++ h_dentry = au_h_dptr(cpg->dentry, cpg->bsrc); ++ if (!au_cpup_sio_test(pin, d_inode(h_dentry)->i_mode)) ++ err = au_cpup_single(cpg, dst_parent); ++ else { ++ struct au_cpup_single_args args = { ++ .errp = &err, ++ .cpg = cpg, ++ .dst_parent = dst_parent ++ }; ++ wkq_err = au_wkq_wait(au_call_cpup_single, &args); ++ if (unlikely(wkq_err)) ++ err = wkq_err; + } + + return err; +} -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 2016-10-09 16:55:36.486034798 +0200 -@@ -0,0 +1,309 @@ -+/* -+ * Copyright (C) 2005-2016 Junjiro R. Okajima -+ * -+ * This program, aufs is free software; you can redistribute it and/or modify -+ * it under the terms of the GNU General Public License as published by -+ * the Free Software Foundation; either version 2 of the License, or -+ * (at your option) any later version. -+ * -+ * This program is distributed in the hope that it will be useful, -+ * but WITHOUT ANY WARRANTY; without even the implied warranty of -+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the -+ * GNU General Public License for more details. -+ * -+ * You should have received a copy of the GNU General Public License -+ * along with this program. If not, see . -+ */ ++#endif + +/* -+ * branch filesystems and xino for them ++ * copyup the @dentry from the first active lower branch to @bdst, ++ * using au_cpup_single(). + */ ++static int au_cpup_simple(struct au_cp_generic *cpg) ++{ ++ int err; ++ unsigned int flags_orig; ++ struct dentry *dentry; + -+#ifndef __AUFS_BRANCH_H__ -+#define __AUFS_BRANCH_H__ -+ -+#ifdef __KERNEL__ ++ AuDebugOn(cpg->bsrc < 0); + -+#include -+#include "dynop.h" -+#include "rwsem.h" -+#include "super.h" ++ dentry = cpg->dentry; ++ DiMustWriteLock(dentry); + -+/* ---------------------------------------------------------------------- */ ++ err = au_lkup_neg(dentry, cpg->bdst, /*wh*/1); ++ if (!err) { ++ flags_orig = cpg->flags; ++ au_fset_cpup(cpg->flags, RENAME); ++ err = au_cpup_single(cpg, NULL); ++ cpg->flags = flags_orig; ++ if (!err) ++ return 0; /* success */ + -+/* a xino file */ -+struct au_xino_file { -+ struct file *xi_file; -+ struct mutex xi_nondir_mtx; ++ /* revert */ ++ au_set_h_dptr(dentry, cpg->bdst, NULL); ++ au_set_dbtop(dentry, cpg->bsrc); ++ } + -+ /* todo: make xino files an array to support huge inode number */ ++ return err; ++} + -+#ifdef CONFIG_DEBUG_FS -+ struct dentry *xi_dbgaufs; -+#endif ++struct au_cpup_simple_args { ++ int *errp; ++ struct au_cp_generic *cpg; +}; + -+/* 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 -+}; ++static void au_call_cpup_simple(void *args) ++{ ++ struct au_cpup_simple_args *a = args; + -+/* 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 */ ++ au_pin_hdir_acquire_nest(a->cpg->pin); ++ *a->errp = au_cpup_simple(a->cpg); ++ au_pin_hdir_release(a->cpg->pin); ++} + -+ /* mfs mode */ -+ unsigned long long wbr_bytes; -+}; ++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; + -+/* ext2 has 3 types of operations at least, ext3 has 4 */ -+#define AuBrDynOp (AuDyLast * 4) ++ 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; ++ } + -+#ifdef CONFIG_AUFS_HFSNOTIFY -+/* support for asynchronous destruction */ -+struct au_br_hfsnotify { -+ struct fsnotify_group *hfsn_group; -+}; -+#endif ++ parent = dget_parent(dentry); ++ h_dir = au_h_iptr(d_inode(parent), cpg->bdst); ++ if (!au_test_h_perm_sio(h_dir, MAY_EXEC | MAY_WRITE) ++ && !au_cpup_sio_test(cpg->pin, d_inode(dentry)->i_mode)) ++ err = au_cpup_simple(cpg); ++ else { ++ struct au_cpup_simple_args args = { ++ .errp = &err, ++ .cpg = cpg ++ }; ++ wkq_err = au_wkq_wait(au_call_cpup_simple, &args); ++ if (unlikely(wkq_err)) ++ err = wkq_err; ++ } + -+/* sysfs entries */ -+struct au_brsysfs { -+ char name[16]; -+ struct attribute attr; -+}; ++ dput(parent); ++ if (h_file) ++ au_h_open_post(dentry, cpg->bsrc, h_file); + -+enum { -+ AuBrSysfs_BR, -+ AuBrSysfs_BRID, -+ AuBrSysfs_Last -+}; ++out: ++ return err; ++} + -+/* protected by superblock rwsem */ -+struct au_branch { -+ struct au_xino_file br_xino; ++int au_sio_cpup_simple(struct au_cp_generic *cpg) ++{ ++ aufs_bindex_t bsrc, bbot; ++ struct dentry *dentry, *h_dentry; + -+ aufs_bindex_t br_id; ++ if (cpg->bsrc < 0) { ++ dentry = cpg->dentry; ++ bbot = au_dbbot(dentry); ++ for (bsrc = cpg->bdst + 1; bsrc <= bbot; bsrc++) { ++ h_dentry = au_h_dptr(dentry, bsrc); ++ if (h_dentry) { ++ AuDebugOn(d_is_negative(h_dentry)); ++ break; ++ } ++ } ++ AuDebugOn(bsrc > bbot); ++ cpg->bsrc = bsrc; ++ } ++ AuDebugOn(cpg->bsrc <= cpg->bdst); ++ return au_do_sio_cpup_simple(cpg); ++} + -+ int br_perm; -+ struct path br_path; -+ spinlock_t br_dykey_lock; -+ struct au_dykey *br_dykey[AuBrDynOp]; -+ struct percpu_counter br_count; ++int au_sio_cpdown_simple(struct au_cp_generic *cpg) ++{ ++ AuDebugOn(cpg->bdst <= cpg->bsrc); ++ return au_do_sio_cpup_simple(cpg); ++} + -+ struct au_wbr *br_wbr; -+ struct au_br_fhsm *br_fhsm; ++/* ---------------------------------------------------------------------- */ + -+ /* xino truncation */ -+ atomic_t br_xino_running; ++/* ++ * copyup the deleted file for writing. ++ */ ++static int au_do_cpup_wh(struct au_cp_generic *cpg, struct dentry *wh_dentry, ++ struct file *file) ++{ ++ int err; ++ unsigned int flags_orig; ++ aufs_bindex_t bsrc_orig; ++ struct au_dinfo *dinfo; ++ struct { ++ struct au_hdentry *hd; ++ struct dentry *h_dentry; ++ } hdst, hsrc; + -+#ifdef CONFIG_AUFS_HFSNOTIFY -+ struct au_br_hfsnotify *br_hfsn; -+#endif ++ dinfo = au_di(cpg->dentry); ++ AuRwMustWriteLock(&dinfo->di_rwsem); + -+#ifdef CONFIG_SYSFS -+ /* entries under sysfs per mount-point */ -+ struct au_brsysfs br_sysfs[AuBrSysfs_Last]; -+#endif -+}; ++ 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; + -+static inline struct vfsmount *au_br_mnt(struct au_branch *br) -+{ -+ return br->br_path.mnt; ++ return err; +} + -+static inline struct dentry *au_br_dentry(struct au_branch *br) ++static int au_cpup_wh(struct au_cp_generic *cpg, struct file *file) +{ -+ return br->br_path.dentry; -+} ++ 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; + -+static inline struct super_block *au_br_sb(struct au_branch *br) -+{ -+ return au_br_mnt(br)->mnt_sb; -+} ++ dentry = cpg->dentry; ++ bdst = cpg->bdst; ++ br = au_sbr(dentry->d_sb, bdst); ++ parent = dget_parent(dentry); ++ h_parent = au_h_dptr(parent, bdst); ++ wh_dentry = au_whtmp_lkup(h_parent, br, &dentry->d_name); ++ err = PTR_ERR(wh_dentry); ++ if (IS_ERR(wh_dentry)) ++ goto out; + -+static inline void au_br_get(struct au_branch *br) -+{ -+ percpu_counter_inc(&br->br_count); -+} ++ 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; + -+static inline void au_br_put(struct au_branch *br) -+{ -+ percpu_counter_dec(&br->br_count); -+} ++ dget(wh_dentry); ++ h_path.dentry = wh_dentry; ++ if (!d_is_dir(wh_dentry)) { ++ /* no delegation since it is just created */ ++ err = vfsub_unlink(d_inode(h_parent), &h_path, ++ /*delegated*/NULL, /*force*/0); ++ } else ++ err = vfsub_rmdir(d_inode(h_parent), &h_path); ++ if (unlikely(err)) { ++ AuIOErr("failed remove copied-up tmp file %pd(%d)\n", ++ wh_dentry, err); ++ err = -EIO; ++ } ++ au_dtime_revert(&dt); ++ au_set_hi_wh(d_inode(dentry), bdst, wh_dentry); + -+static inline s64 au_br_count(struct au_branch *br) -+{ -+ return percpu_counter_sum(&br->br_count); ++out_wh: ++ dput(wh_dentry); ++out: ++ dput(parent); ++ return err; +} + -+static inline void au_br_count_init(struct au_branch *br) -+{ -+ percpu_counter_init(&br->br_count, 0, GFP_NOFS); -+} ++struct au_cpup_wh_args { ++ int *errp; ++ struct au_cp_generic *cpg; ++ struct file *file; ++}; + -+static inline void au_br_count_fin(struct au_branch *br) ++static void au_call_cpup_wh(void *args) +{ -+ percpu_counter_destroy(&br->br_count); -+} ++ struct au_cpup_wh_args *a = args; + -+static inline int au_br_rdonly(struct au_branch *br) -+{ -+ return ((au_br_sb(br)->s_flags & MS_RDONLY) -+ || !au_br_writable(br->br_perm)) -+ ? -EROFS : 0; ++ 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 inline int au_br_hnotifyable(int brperm __maybe_unused) ++int au_sio_cpup_wh(struct au_cp_generic *cpg, struct file *file) +{ -+#ifdef CONFIG_AUFS_HNOTIFY -+ return !(brperm & AuBrPerm_RR); -+#else -+ return 0; -+#endif -+} ++ 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; + -+static inline int au_br_test_oflag(int oflag, struct au_branch *br) -+{ -+ int err, exec_flag; ++ 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; + -+ err = 0; -+ exec_flag = oflag & __FMODE_EXEC; -+ if (unlikely(exec_flag && path_noexec(&br->br_path))) -+ err = -EACCES; ++ h_parent = dget(au_h_dptr(parent, bdst)); ++ au_set_h_dptr(parent, bdst, dget(h_orph)); ++ h_tmpdir = d_inode(h_orph); ++ au_set_h_iptr(dir, bdst, au_igrab(h_tmpdir), /*flags*/0); ++ ++ inode_lock_nested(h_tmpdir, AuLsc_I_PARENT3); ++ /* todo: au_h_open_pre()? */ ++ ++ pin_orig = cpg->pin; ++ au_pin_init(&wh_pin, dentry, bdst, AuLsc_DI_PARENT, ++ AuLsc_I_PARENT3, cpg->pin->udba, AuPin_DI_LOCKED); ++ cpg->pin = &wh_pin; ++ } ++ ++ if (!au_test_h_perm_sio(h_tmpdir, MAY_EXEC | MAY_WRITE) ++ && !au_cpup_sio_test(cpg->pin, d_inode(dentry)->i_mode)) ++ err = au_cpup_wh(cpg, file); ++ else { ++ struct au_cpup_wh_args args = { ++ .errp = &err, ++ .cpg = cpg, ++ .file = file ++ }; ++ wkq_err = au_wkq_wait(au_call_cpup_wh, &args); ++ if (unlikely(wkq_err)) ++ err = wkq_err; ++ } ++ ++ if (h_orph) { ++ inode_unlock(h_tmpdir); ++ /* todo: au_h_open_post()? */ ++ au_set_h_iptr(dir, bdst, au_igrab(h_dir), /*flags*/0); ++ au_set_h_dptr(parent, bdst, h_parent); ++ AuDebugOn(!pin_orig); ++ cpg->pin = pin_orig; ++ } ++ iput(h_dir); ++ dput(parent); + + return err; +} + +/* ---------------------------------------------------------------------- */ + -+/* 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); ++/* ++ * generic routine for both of copy-up and copy-down. ++ */ ++/* cf. revalidate function in file.c */ ++int au_cp_dirs(struct dentry *dentry, aufs_bindex_t bdst, ++ int (*cp)(struct dentry *dentry, aufs_bindex_t bdst, ++ struct au_pin *pin, ++ struct dentry *h_parent, void *arg), ++ void *arg) ++{ ++ int err; ++ struct au_pin pin; ++ struct dentry *d, *parent, *h_parent, *real_parent, *h_dentry; ++ ++ err = 0; ++ parent = dget_parent(dentry); ++ if (IS_ROOT(parent)) ++ goto out; ++ ++ au_pin_init(&pin, dentry, bdst, AuLsc_DI_PARENT2, AuLsc_I_PARENT2, ++ au_opt_udba(dentry->d_sb), AuPin_MNT_WRITE); ++ ++ /* do not use au_dpage */ ++ real_parent = parent; ++ while (1) { ++ dput(parent); ++ parent = dget_parent(dentry); ++ h_parent = au_h_dptr(parent, bdst); ++ if (h_parent) ++ goto out; /* success */ ++ ++ /* find top dir which is necessary to cpup */ ++ do { ++ d = parent; ++ dput(parent); ++ parent = dget_parent(d); ++ di_read_lock_parent3(parent, !AuLock_IR); ++ h_parent = au_h_dptr(parent, bdst); ++ di_read_unlock(parent, !AuLock_IR); ++ } while (!h_parent); + -+/* xino.c */ -+static const loff_t au_loff_max = LLONG_MAX; ++ if (d != real_parent) ++ di_write_lock_child3(d); + -+int au_xib_trunc(struct super_block *sb); -+ssize_t xino_fread(vfs_readf_t func, struct file *file, void *buf, size_t size, -+ loff_t *pos); -+ssize_t xino_fwrite(vfs_writef_t func, struct file *file, void *buf, -+ size_t size, loff_t *pos); -+struct file *au_xino_create2(struct file *base_file, struct file *copy_src); -+struct file *au_xino_create(struct super_block *sb, char *fname, int silent); -+ino_t au_xino_new_ino(struct super_block *sb); -+void au_xino_delete_inode(struct inode *inode, const int unlinked); -+int au_xino_write(struct super_block *sb, aufs_bindex_t bindex, ino_t h_ino, -+ ino_t ino); -+int au_xino_read(struct super_block *sb, aufs_bindex_t bindex, ino_t h_ino, -+ ino_t *ino); -+int au_xino_br(struct super_block *sb, struct au_branch *br, ino_t hino, -+ struct file *base_file, int do_test); -+int au_xino_trunc(struct super_block *sb, aufs_bindex_t bindex); ++ /* 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); + -+struct au_opt_xino; -+int au_xino_set(struct super_block *sb, struct au_opt_xino *xino, int remount); -+void au_xino_clr(struct super_block *sb); -+struct file *au_xino_def(struct super_block *sb); -+int au_xino_path(struct seq_file *seq, struct file *file); ++ 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; ++ } + -+/* 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; ++out: ++ dput(parent); ++ return err; +} + -+static inline -+struct vfsmount *au_sbr_mnt(struct super_block *sb, aufs_bindex_t bindex) ++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) +{ -+ return au_br_mnt(au_sbr(sb, bindex)); ++ struct au_cp_generic cpg = { ++ .dentry = dentry, ++ .bdst = bdst, ++ .bsrc = -1, ++ .len = 0, ++ .pin = pin, ++ .flags = AuCpup_DTIME ++ }; ++ return au_sio_cpup_simple(&cpg); +} + -+static inline -+struct super_block *au_sbr_sb(struct super_block *sb, aufs_bindex_t bindex) ++int au_cpup_dirs(struct dentry *dentry, aufs_bindex_t bdst) +{ -+ return au_br_sb(au_sbr(sb, bindex)); ++ return au_cp_dirs(dentry, bdst, au_cpup_dir, NULL); +} + -+static inline void au_sbr_get(struct super_block *sb, aufs_bindex_t bindex) ++int au_test_and_cpup_dirs(struct dentry *dentry, aufs_bindex_t bdst) +{ -+ au_br_get(au_sbr(sb, bindex)); -+} ++ int err; ++ struct dentry *parent; ++ struct inode *dir; + -+static inline void au_sbr_put(struct super_block *sb, aufs_bindex_t bindex) -+{ -+ au_br_put(au_sbr(sb, bindex)); -+} ++ parent = dget_parent(dentry); ++ dir = d_inode(parent); ++ err = 0; ++ if (au_h_iptr(dir, bdst)) ++ goto out; + -+static inline int au_sbr_perm(struct super_block *sb, aufs_bindex_t bindex) -+{ -+ return au_sbr(sb, bindex)->br_perm; -+} ++ 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); + -+static inline int au_sbr_whable(struct super_block *sb, aufs_bindex_t bindex) -+{ -+ return au_br_whable(au_sbr_perm(sb, bindex)); ++out: ++ dput(parent); ++ return err; +} -+ -+/* ---------------------------------------------------------------------- */ +diff -urNp -x '*.orig' linux-4.9/fs/aufs/cpup.h linux-4.9/fs/aufs/cpup.h +--- linux-4.9/fs/aufs/cpup.h 1970-01-01 01:00:00.000000000 +0100 ++++ linux-4.9/fs/aufs/cpup.h 2021-02-24 16:15:09.521573529 +0100 +@@ -0,0 +1,99 @@ ++/* ++ * Copyright (C) 2005-2018 Junjiro R. Okajima ++ * ++ * This program, aufs is free software; you can redistribute it and/or modify ++ * it under the terms of the GNU General Public License as published by ++ * the Free Software Foundation; either version 2 of the License, or ++ * (at your option) any later version. ++ * ++ * This program is distributed in the hope that it will be useful, ++ * but WITHOUT ANY WARRANTY; without even the implied warranty of ++ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the ++ * GNU General Public License for more details. ++ * ++ * You should have received a copy of the GNU General Public License ++ * along with this program. If not, see . ++ */ + +/* -+ * wbr_wh_read_lock, wbr_wh_write_lock -+ * wbr_wh_read_unlock, wbr_wh_write_unlock, wbr_wh_downgrade_lock ++ * copy-up/down functions + */ -+AuSimpleRwsemFuncs(wbr_wh, struct au_wbr *wbr, &wbr->wbr_wh_rwsem); + -+#define WbrWhMustNoWaiters(wbr) AuRwMustNoWaiters(&wbr->wbr_wh_rwsem) -+#define WbrWhMustAnyLock(wbr) AuRwMustAnyLock(&wbr->wbr_wh_rwsem) -+#define WbrWhMustWriteLock(wbr) AuRwMustWriteLock(&wbr->wbr_wh_rwsem) ++#ifndef __AUFS_CPUP_H__ ++#define __AUFS_CPUP_H__ ++ ++#ifdef __KERNEL__ ++ ++#include ++ ++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); + +/* ---------------------------------------------------------------------- */ + -+#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; -+} ++struct au_cp_generic { ++ struct dentry *dentry; ++ aufs_bindex_t bdst, bsrc; ++ loff_t len; ++ struct au_pin *pin; ++ unsigned int flags; ++}; + -+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) ++/* 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 + -+#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 2016-10-09 16:55:36.486034798 +0200 -@@ -0,0 +1,38 @@ ++#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) + -+AuConfStr = CONFIG_AUFS_FS=${CONFIG_AUFS_FS} ++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); + -+define AuConf -+ifdef ${1} -+AuConfStr += ${1}=${${1}} -+endif -+endef ++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); + -+AuConfAll = BRANCH_MAX_127 BRANCH_MAX_511 BRANCH_MAX_1023 BRANCH_MAX_32767 \ -+ SBILIST \ -+ HNOTIFY HFSNOTIFY \ -+ EXPORT INO_T_64 \ -+ XATTR \ -+ FHSM \ -+ RDU \ -+ 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} ++/* keep timestamps when copyup */ ++struct au_dtime { ++ struct dentry *dt_dentry; ++ struct path dt_h_path; ++ struct timespec 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); + -+-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 2016-12-17 12:28:17.595211562 +0100 -@@ -0,0 +1,1394 @@ ++#endif /* __KERNEL__ */ ++#endif /* __AUFS_CPUP_H__ */ +diff -urNp -x '*.orig' linux-4.9/fs/aufs/dbgaufs.c linux-4.9/fs/aufs/dbgaufs.c +--- linux-4.9/fs/aufs/dbgaufs.c 1970-01-01 01:00:00.000000000 +0100 ++++ linux-4.9/fs/aufs/dbgaufs.c 2021-02-24 16:15:09.524906971 +0100 +@@ -0,0 +1,437 @@ +/* -+ * Copyright (C) 2005-2016 Junjiro R. Okajima ++ * Copyright (C) 2005-2018 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by @@ -4664,1388 +5793,1296 @@ diff -urN /usr/share/empty/fs/aufs/cpup.c linux/fs/aufs/cpup.c + */ + +/* -+ * copy-up functions, see wbr_policy.c for copy-down ++ * debugfs interface + */ + -+#include -+#include -+#include ++#include +#include "aufs.h" + -+void au_cpup_attr_flags(struct inode *dst, unsigned int iflags) ++#ifndef CONFIG_SYSFS ++#error DEBUG_FS depends upon SYSFS ++#endif ++ ++static struct dentry *dbgaufs; ++static const mode_t dbgaufs_mode = S_IRUSR | S_IRGRP | S_IROTH; ++ ++/* 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) +{ -+ const unsigned int mask = S_DEAD | S_SWAPFILE | S_PRIVATE -+ | S_NOATIME | S_NOCMTIME | S_AUTOMOUNT; ++ kfree(file->private_data); ++ return 0; ++} + -+ BUILD_BUG_ON(sizeof(iflags) != sizeof(dst->i_flags)); ++static int dbgaufs_xi_open(struct file *xf, struct file *file, int do_fcnt) ++{ ++ int err; ++ struct kstat st; ++ struct dbgaufs_arg *p; ++ ++ err = -ENOMEM; ++ p = kmalloc(sizeof(*p), GFP_NOFS); ++ if (unlikely(!p)) ++ goto out; ++ ++ err = 0; ++ p->n = 0; ++ file->private_data = p; ++ if (!xf) ++ goto out; ++ ++ err = vfs_getattr(&xf->f_path, &st); ++ if (!err) { ++ if (do_fcnt) ++ p->n = snprintf ++ (p->a, sizeof(p->a), "%ld, %llux%lu %lld\n", ++ (long)file_count(xf), st.blocks, st.blksize, ++ (long long)st.size); ++ else ++ p->n = snprintf(p->a, sizeof(p->a), "%llux%lu %lld\n", ++ st.blocks, st.blksize, ++ (long long)st.size); ++ AuDebugOn(p->n >= sizeof(p->a)); ++ } else { ++ p->n = snprintf(p->a, sizeof(p->a), "err %d\n", err); ++ err = 0; ++ } ++ ++out: ++ return err; + -+ dst->i_flags |= iflags & ~mask; -+ if (au_test_fs_notime(dst->i_sb)) -+ dst->i_flags |= S_NOATIME | S_NOCMTIME; +} + -+void au_cpup_attr_timesizes(struct inode *inode) ++static ssize_t dbgaufs_xi_read(struct file *file, char __user *buf, ++ size_t count, loff_t *ppos) +{ -+ struct inode *h_inode; ++ struct dbgaufs_arg *p; + -+ h_inode = au_h_iptr(inode, au_ibtop(inode)); -+ fsstack_copy_attr_times(inode, h_inode); -+ fsstack_copy_inode_size(inode, h_inode); ++ p = file->private_data; ++ return simple_read_from_buffer(buf, count, ppos, p->a, p->n); +} + -+void au_cpup_attr_nlink(struct inode *inode, int force) ++/* ---------------------------------------------------------------------- */ ++ ++struct dbgaufs_plink_arg { ++ int n; ++ char a[]; ++}; ++ ++static int dbgaufs_plink_release(struct inode *inode __maybe_unused, ++ struct file *file) +{ -+ struct inode *h_inode; ++ free_page((unsigned long)file->private_data); ++ return 0; ++} ++ ++static int dbgaufs_plink_open(struct inode *inode, struct file *file) ++{ ++ int err, i, limit; ++ unsigned long n, sum; ++ struct dbgaufs_plink_arg *p; ++ struct au_sbinfo *sbinfo; + struct super_block *sb; -+ aufs_bindex_t bindex, bbot; ++ struct hlist_bl_head *hbl; + -+ 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; ++ err = -ENOMEM; ++ p = (void *)get_zeroed_page(GFP_NOFS); ++ if (unlikely(!p)) ++ goto out; + -+ /* -+ * 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); ++ 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); + -+ /* -+ * 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); ++ /* the number of buckets */ ++ n = snprintf(p->a + p->n, limit, "%d\n", AuPlink_NHASH); ++ p->n += n; ++ limit -= n; ++ ++ sum = 0; ++ for (i = 0, hbl = sbinfo->si_plink; i < AuPlink_NHASH; ++ i++, hbl++) { ++ n = au_hbl_count(hbl); ++ sum += n; ++ ++ n = snprintf(p->a + p->n, limit, "%lu ", n); ++ p->n += n; ++ limit -= n; ++ if (unlikely(limit <= 0)) ++ goto out_free; + } ++ p->a[p->n - 1] = '\n'; ++ ++ /* the sum of plinks */ ++ n = snprintf(p->a + p->n, limit, "%lu\n", sum); ++ p->n += n; ++ limit -= n; ++ if (unlikely(limit <= 0)) ++ goto out_free; ++ } else { ++#define str "1\n0\n0\n" ++ p->n = sizeof(str) - 1; ++ strcpy(p->a, str); ++#undef str + } ++ si_read_unlock(sb); ++ ++ err = 0; ++ file->private_data = p; ++ goto out; /* success */ ++ ++out_free: ++ free_page((unsigned long)p); ++out: ++ return err; +} + -+void au_cpup_attr_changeable(struct inode *inode) ++static ssize_t dbgaufs_plink_read(struct file *file, char __user *buf, ++ size_t count, loff_t *ppos) +{ -+ struct inode *h_inode; ++ struct dbgaufs_plink_arg *p; ++ ++ p = file->private_data; ++ return simple_read_from_buffer(buf, count, ppos, p->a, p->n); ++} ++ ++static const struct file_operations dbgaufs_plink_fop = { ++ .owner = THIS_MODULE, ++ .open = dbgaufs_plink_open, ++ .release = dbgaufs_plink_release, ++ .read = dbgaufs_plink_read ++}; ++ ++/* ---------------------------------------------------------------------- */ ++ ++static int dbgaufs_xib_open(struct inode *inode, struct file *file) ++{ ++ int err; ++ struct au_sbinfo *sbinfo; ++ struct super_block *sb; ++ ++ sbinfo = inode->i_private; ++ sb = sbinfo->si_sb; ++ si_noflush_read_lock(sb); ++ err = dbgaufs_xi_open(sbinfo->si_xib, file, /*do_fcnt*/0); ++ si_read_unlock(sb); ++ return err; ++} ++ ++static const struct file_operations dbgaufs_xib_fop = { ++ .owner = THIS_MODULE, ++ .open = dbgaufs_xib_open, ++ .release = dbgaufs_xi_release, ++ .read = dbgaufs_xi_read ++}; ++ ++/* ---------------------------------------------------------------------- */ ++ ++#define DbgaufsXi_PREFIX "xi" ++ ++static int dbgaufs_xino_open(struct inode *inode, struct file *file) ++{ ++ int err; ++ long l; ++ struct au_sbinfo *sbinfo; ++ struct super_block *sb; ++ struct file *xf; ++ struct qstr *name; ++ ++ err = -ENOENT; ++ xf = NULL; ++ 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; ++ err = kstrtol(name->name + sizeof(DbgaufsXi_PREFIX) - 1, 10, &l); ++ if (unlikely(err)) ++ goto out; ++ ++ sbinfo = inode->i_private; ++ sb = sbinfo->si_sb; ++ si_noflush_read_lock(sb); ++ if (l <= au_sbbot(sb)) { ++ xf = au_sbr(sb, (aufs_bindex_t)l)->br_xino.xi_file; ++ err = dbgaufs_xi_open(xf, file, /*do_fcnt*/1); ++ } else ++ err = -ENOENT; ++ si_read_unlock(sb); + -+ 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); ++out: ++ return err; +} + -+void au_cpup_igen(struct inode *inode, struct inode *h_inode) ++static const struct file_operations dbgaufs_xino_fop = { ++ .owner = THIS_MODULE, ++ .open = dbgaufs_xino_open, ++ .release = dbgaufs_xi_release, ++ .read = dbgaufs_xi_read ++}; ++ ++void dbgaufs_brs_del(struct super_block *sb, aufs_bindex_t bindex) +{ -+ struct au_iinfo *iinfo = au_ii(inode); ++ aufs_bindex_t bbot; ++ struct au_branch *br; ++ struct au_xino_file *xi; + -+ IiMustWriteLock(inode); ++ if (!au_sbi(sb)->si_dbgaufs) ++ return; + -+ iinfo->ii_higen = h_inode->i_generation; -+ iinfo->ii_hsb1 = h_inode->i_sb; ++ bbot = au_sbbot(sb); ++ for (; bindex <= bbot; bindex++) { ++ br = au_sbr(sb, bindex); ++ xi = &br->br_xino; ++ /* debugfs acquires the parent i_mutex */ ++ lockdep_off(); ++ debugfs_remove(xi->xi_dbgaufs); ++ lockdep_on(); ++ xi->xi_dbgaufs = NULL; ++ } +} + -+void au_cpup_attr_all(struct inode *inode, int force) ++void dbgaufs_brs_add(struct super_block *sb, aufs_bindex_t bindex) +{ -+ struct inode *h_inode; ++ struct au_sbinfo *sbinfo; ++ struct dentry *parent; ++ struct au_branch *br; ++ struct au_xino_file *xi; ++ aufs_bindex_t bbot; ++ char name[sizeof(DbgaufsXi_PREFIX) + 5]; /* "xi" bindex NULL */ + -+ 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); ++ sbinfo = au_sbi(sb); ++ parent = sbinfo->si_dbgaufs; ++ if (!parent) ++ return; ++ ++ bbot = au_sbbot(sb); ++ for (; bindex <= bbot; bindex++) { ++ snprintf(name, sizeof(name), DbgaufsXi_PREFIX "%d", bindex); ++ br = au_sbr(sb, bindex); ++ xi = &br->br_xino; ++ AuDebugOn(xi->xi_dbgaufs); ++ /* debugfs acquires the parent i_mutex */ ++ lockdep_off(); ++ xi->xi_dbgaufs = debugfs_create_file(name, dbgaufs_mode, parent, ++ sbinfo, &dbgaufs_xino_fop); ++ lockdep_on(); ++ /* ignore an error */ ++ if (unlikely(!xi->xi_dbgaufs)) ++ AuWarn1("failed %s under debugfs\n", name); ++ } +} + +/* ---------------------------------------------------------------------- */ + -+/* Note: dt_dentry and dt_h_dentry are not dget/dput-ed */ -+ -+/* keep the timestamps of the parent dir when cpup */ -+void au_dtime_store(struct au_dtime *dt, struct dentry *dentry, -+ struct path *h_path) -+{ -+ struct inode *h_inode; -+ -+ dt->dt_dentry = dentry; -+ dt->dt_h_path = *h_path; -+ h_inode = d_inode(h_path->dentry); -+ dt->dt_atime = h_inode->i_atime; -+ dt->dt_mtime = h_inode->i_mtime; -+ /* smp_mb(); */ -+} -+ -+void au_dtime_revert(struct au_dtime *dt) ++#ifdef CONFIG_AUFS_EXPORT ++static int dbgaufs_xigen_open(struct inode *inode, struct file *file) +{ -+ struct iattr attr; + int err; ++ struct au_sbinfo *sbinfo; ++ struct super_block *sb; + -+ 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); ++ sbinfo = inode->i_private; ++ sb = sbinfo->si_sb; ++ si_noflush_read_lock(sb); ++ err = dbgaufs_xi_open(sbinfo->si_xigen, file, /*do_fcnt*/0); ++ si_read_unlock(sb); ++ return err; +} + -+/* ---------------------------------------------------------------------- */ -+ -+/* internal use only */ -+struct au_cpup_reg_attr { -+ int valid; -+ struct kstat st; -+ unsigned int iflags; /* inode->i_flags */ ++static const struct file_operations dbgaufs_xigen_fop = { ++ .owner = THIS_MODULE, ++ .open = dbgaufs_xigen_open, ++ .release = dbgaufs_xi_release, ++ .read = dbgaufs_xi_read +}; + -+static noinline_for_stack -+int cpup_iattr(struct dentry *dst, aufs_bindex_t bindex, struct dentry *h_src, -+ struct au_cpup_reg_attr *h_src_attr) ++static int dbgaufs_xigen_init(struct au_sbinfo *sbinfo) +{ -+ int err, sbits, icex; -+ unsigned int mnt_flags; -+ unsigned char verbose; -+ struct iattr ia; -+ struct path h_path; -+ struct inode *h_isrc, *h_idst; -+ struct kstat *h_st; -+ struct au_branch *br; -+ -+ h_path.dentry = au_h_dptr(dst, bindex); -+ h_idst = d_inode(h_path.dentry); -+ br = au_sbr(dst->d_sb, bindex); -+ h_path.mnt = au_br_mnt(br); -+ h_isrc = d_inode(h_src); -+ ia.ia_valid = ATTR_FORCE | ATTR_UID | ATTR_GID -+ | ATTR_ATIME | ATTR_MTIME -+ | ATTR_ATIME_SET | ATTR_MTIME_SET; -+ if (h_src_attr && h_src_attr->valid) { -+ h_st = &h_src_attr->st; -+ ia.ia_uid = h_st->uid; -+ ia.ia_gid = h_st->gid; -+ ia.ia_atime = h_st->atime; -+ ia.ia_mtime = h_st->mtime; -+ if (h_idst->i_mode != h_st->mode -+ && !S_ISLNK(h_idst->i_mode)) { -+ ia.ia_valid |= ATTR_MODE; -+ ia.ia_mode = h_st->mode; -+ } -+ sbits = !!(h_st->mode & (S_ISUID | S_ISGID)); -+ au_cpup_attr_flags(h_idst, h_src_attr->iflags); -+ } else { -+ ia.ia_uid = h_isrc->i_uid; -+ ia.ia_gid = h_isrc->i_gid; -+ ia.ia_atime = h_isrc->i_atime; -+ ia.ia_mtime = h_isrc->i_mtime; -+ if (h_idst->i_mode != h_isrc->i_mode -+ && !S_ISLNK(h_idst->i_mode)) { -+ ia.ia_valid |= ATTR_MODE; -+ ia.ia_mode = h_isrc->i_mode; -+ } -+ sbits = !!(h_isrc->i_mode & (S_ISUID | S_ISGID)); -+ au_cpup_attr_flags(h_idst, h_isrc->i_flags); -+ } -+ /* no delegation since it is just created */ -+ err = vfsub_notify_change(&h_path, &ia, /*delegated*/NULL); ++ int err; + -+ /* 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); -+ } ++ /* ++ * This function is a dynamic '__init' function actually, ++ * so the tiny check for si_rwsem is unnecessary. ++ */ ++ /* AuRwMustWriteLock(&sbinfo->si_rwsem); */ + -+ icex = br->br_perm & AuBrAttr_ICEX; -+ if (!err) { -+ mnt_flags = au_mntflags(dst->d_sb); -+ verbose = !!au_opt_test(mnt_flags, VERBOSE); -+ err = au_cpup_xattr(h_path.dentry, h_src, icex, verbose); -+ } ++ err = -EIO; ++ sbinfo->si_dbgaufs_xigen = debugfs_create_file ++ ("xigen", dbgaufs_mode, sbinfo->si_dbgaufs, sbinfo, ++ &dbgaufs_xigen_fop); ++ if (sbinfo->si_dbgaufs_xigen) ++ err = 0; + + return err; +} ++#else ++static int dbgaufs_xigen_init(struct au_sbinfo *sbinfo) ++{ ++ return 0; ++} ++#endif /* CONFIG_AUFS_EXPORT */ + +/* ---------------------------------------------------------------------- */ + -+static int au_do_copy_file(struct file *dst, struct file *src, loff_t len, -+ char *buf, unsigned long blksize) ++void dbgaufs_si_fin(struct au_sbinfo *sbinfo) +{ -+ int err; -+ size_t sz, rbytes, wbytes; -+ unsigned char all_zero; -+ char *p, *zp; -+ struct inode *h_inode; -+ /* reduce stack usage */ -+ struct iattr *ia; -+ -+ zp = page_address(ZERO_PAGE(0)); -+ if (unlikely(!zp)) -+ return -ENOMEM; /* possible? */ -+ -+ err = 0; -+ all_zero = 0; -+ while (len) { -+ AuDbg("len %lld\n", len); -+ sz = blksize; -+ if (len < blksize) -+ sz = len; ++ /* ++ * This function is a dynamic '__fin' function actually, ++ * so the tiny check for si_rwsem is unnecessary. ++ */ ++ /* AuRwMustWriteLock(&sbinfo->si_rwsem); */ + -+ 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; ++ debugfs_remove_recursive(sbinfo->si_dbgaufs); ++ sbinfo->si_dbgaufs = NULL; ++ kobject_put(&sbinfo->si_kobj); ++} + -+ 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; ++int dbgaufs_si_init(struct au_sbinfo *sbinfo) ++{ ++ int err; ++ char name[SysaufsSiNameLen]; + -+ 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; ++ /* ++ * This function is a dynamic '__init' function actually, ++ * so the tiny check for si_rwsem is unnecessary. ++ */ ++ /* AuRwMustWriteLock(&sbinfo->si_rwsem); */ + -+ AuLabel(hole); -+ res = vfsub_llseek(dst, rbytes, SEEK_CUR); -+ err = res; -+ if (unlikely(res < 0)) -+ break; -+ } -+ len -= rbytes; -+ err = 0; ++ err = -ENOENT; ++ if (!dbgaufs) { ++ AuErr1("/debug/aufs is uninitialized\n"); ++ goto out; + } + -+ /* the last block may be a hole */ -+ if (!err && all_zero) { -+ AuLabel(last hole); ++ err = -EIO; ++ sysaufs_name(sbinfo, name); ++ sbinfo->si_dbgaufs = debugfs_create_dir(name, dbgaufs); ++ if (unlikely(!sbinfo->si_dbgaufs)) ++ goto out; ++ kobject_get(&sbinfo->si_kobj); + -+ 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--; -+ } ++ 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 (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); -+ } -+ } ++ 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; ++ ++ err = dbgaufs_xigen_init(sbinfo); ++ if (!err) ++ goto out; /* success */ + ++out_dir: ++ dbgaufs_si_fin(sbinfo); ++out: + return err; +} + -+int au_copy_file(struct file *dst, struct file *src, loff_t len) -+{ -+ int err; -+ unsigned long blksize; -+ unsigned char do_kfree; -+ char *buf; -+ -+ err = -ENOMEM; -+ blksize = dst->f_path.dentry->d_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); ++void dbgaufs_fin(void) ++{ ++ debugfs_remove(dbgaufs); ++} + -+ src->f_pos = 0; -+ dst->f_pos = 0; -+ err = au_do_copy_file(dst, src, len, buf, blksize); -+ if (do_kfree) -+ au_delayed_kfree(buf); -+ else -+ au_delayed_free_page((unsigned long)buf); ++int __init dbgaufs_init(void) ++{ ++ int err; + -+out: ++ err = -EIO; ++ dbgaufs = debugfs_create_dir(AUFS_NAME, NULL); ++ if (dbgaufs) ++ err = 0; + return err; +} +diff -urNp -x '*.orig' linux-4.9/fs/aufs/dbgaufs.h linux-4.9/fs/aufs/dbgaufs.h +--- linux-4.9/fs/aufs/dbgaufs.h 1970-01-01 01:00:00.000000000 +0100 ++++ linux-4.9/fs/aufs/dbgaufs.h 2021-02-24 16:15:09.524906971 +0100 +@@ -0,0 +1,48 @@ ++/* ++ * Copyright (C) 2005-2018 Junjiro R. Okajima ++ * ++ * This program, aufs is free software; you can redistribute it and/or modify ++ * it under the terms of the GNU General Public License as published by ++ * the Free Software Foundation; either version 2 of the License, or ++ * (at your option) any later version. ++ * ++ * This program is distributed in the hope that it will be useful, ++ * but WITHOUT ANY WARRANTY; without even the implied warranty of ++ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the ++ * GNU General Public License for more details. ++ * ++ * You should have received a copy of the GNU General Public License ++ * along with this program. If not, see . ++ */ + +/* -+ * to support a sparse file which is opened with O_APPEND, -+ * we need to close the file. ++ * debugfs interface + */ -+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; -+ void *label; -+ } *f, file[] = { -+ { -+ .bindex = cpg->bsrc, -+ .flags = O_RDONLY | O_NOATIME | O_LARGEFILE, -+ .label = &&out -+ }, -+ { -+ .bindex = cpg->bdst, -+ .flags = O_WRONLY | O_NOATIME | O_LARGEFILE, -+ .force_wr = !!au_ftest_cpup(cpg->flags, RWDST), -+ .label = &&out_src -+ } -+ }; -+ struct super_block *sb; -+ struct inode *h_src_inode; -+ struct task_struct *tsk = current; + -+ /* bsrc branch can be ro/rw. */ -+ sb = cpg->dentry->d_sb; -+ f = file; -+ for (i = 0; i < 2; i++, f++) { -+ f->dentry = au_h_dptr(cpg->dentry, f->bindex); -+ f->file = au_h_open(cpg->dentry, f->bindex, f->flags, -+ /*file*/NULL, f->force_wr); -+ err = PTR_ERR(f->file); -+ if (IS_ERR(f->file)) -+ goto *f->label; -+ } ++#ifndef __DBGAUFS_H__ ++#define __DBGAUFS_H__ + -+ /* try stopping to update while we copyup */ -+ h_src_inode = d_inode(file[SRC].dentry); -+ if (!au_test_nfs(h_src_inode->i_sb)) -+ IMustLock(h_src_inode); -+ err = au_copy_file(file[DST].file, file[SRC].file, cpg->len); ++#ifdef __KERNEL__ + -+ /* i wonder if we had O_NO_DELAY_FPUT flag */ -+ if (tsk->flags & PF_KTHREAD) -+ __fput_sync(file[DST].file); -+ else { -+ WARN(1, "%pD\nPlease report this warning to aufs-users ML", -+ file[DST].file); -+ 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_sbr_put(sb, file[DST].bindex); ++struct super_block; ++struct au_sbinfo; + -+out_src: -+ fput(file[SRC].file); -+ au_sbr_put(sb, file[SRC].bindex); -+out: -+ return err; -+} ++#ifdef CONFIG_DEBUG_FS ++/* dbgaufs.c */ ++void dbgaufs_brs_del(struct super_block *sb, aufs_bindex_t bindex); ++void dbgaufs_brs_add(struct super_block *sb, aufs_bindex_t bindex); ++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_brs_del, struct super_block *sb, aufs_bindex_t bindex) ++AuStubVoid(dbgaufs_brs_add, struct super_block *sb, aufs_bindex_t bindex) ++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 */ + -+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; ++#endif /* __KERNEL__ */ ++#endif /* __DBGAUFS_H__ */ +diff -urNp -x '*.orig' linux-4.9/fs/aufs/dcsub.c linux-4.9/fs/aufs/dcsub.c +--- linux-4.9/fs/aufs/dcsub.c 1970-01-01 01:00:00.000000000 +0100 ++++ linux-4.9/fs/aufs/dcsub.c 2021-02-24 16:15:09.524906971 +0100 +@@ -0,0 +1,225 @@ ++/* ++ * Copyright (C) 2005-2018 Junjiro R. Okajima ++ * ++ * This program, aufs is free software; you can redistribute it and/or modify ++ * it under the terms of the GNU General Public License as published by ++ * the Free Software Foundation; either version 2 of the License, or ++ * (at your option) any later version. ++ * ++ * This program is distributed in the hope that it will be useful, ++ * but WITHOUT ANY WARRANTY; without even the implied warranty of ++ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the ++ * GNU General Public License for more details. ++ * ++ * You should have received a copy of the GNU General Public License ++ * along with this program. If not, see . ++ */ + -+ 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_nested(h_src_inode, AuLsc_I_CHILD); -+ au_pin_hdir_unlock(cpg->pin); ++/* ++ * sub-routines for dentry cache ++ */ ++ ++#include "aufs.h" + -+ 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 = vfs_getattr(&h_path, &h_src_attr->st); -+ else { -+ inode_unlock(h_src_inode); -+ err = vfs_getattr(&h_path, &h_src_attr->st); -+ inode_lock_nested(h_src_inode, AuLsc_I_CHILD); -+ } -+ if (unlikely(err)) { -+ inode_unlock(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(h_src_inode); -+ } else { -+ inode_unlock(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); -+ } ++static void au_dpage_free(struct au_dpage *dpage) ++{ ++ int i; ++ struct dentry **p; + -+out: -+ return err; ++ p = dpage->dentries; ++ for (i = 0; i < dpage->ndentry; i++) ++ dput(*p++); ++ free_page((unsigned long)dpage->dentries); +} + -+static int au_do_cpup_symlink(struct path *h_path, struct dentry *h_src, -+ struct inode *h_dir) ++int au_dpages_init(struct au_dcsub_pages *dpages, gfp_t gfp) +{ -+ int err, symlen; -+ mm_segment_t old_fs; -+ union { -+ char *k; -+ char __user *u; -+ } sym; -+ struct inode *h_inode = d_inode(h_src); -+ const struct inode_operations *h_iop = h_inode->i_op; -+ -+ err = -ENOSYS; -+ if (unlikely(!h_iop->readlink)) -+ goto out; ++ int err; ++ void *p; + + err = -ENOMEM; -+ sym.k = (void *)__get_free_page(GFP_NOFS); -+ if (unlikely(!sym.k)) ++ dpages->dpages = kmalloc(sizeof(*dpages->dpages), gfp); ++ if (unlikely(!dpages->dpages)) + goto out; + -+ /* unnecessary to support mmap_sem since symlink is not mmap-able */ -+ old_fs = get_fs(); -+ set_fs(KERNEL_DS); -+ symlen = h_iop->readlink(h_src, sym.u, PATH_MAX); -+ err = symlen; -+ set_fs(old_fs); ++ p = (void *)__get_free_page(gfp); ++ if (unlikely(!p)) ++ goto out_dpages; + -+ if (symlen > 0) { -+ sym.k[symlen] = 0; -+ err = vfsub_symlink(h_dir, h_path, sym.k); -+ } -+ au_delayed_free_page((unsigned long)sym.k); ++ dpages->dpages[0].ndentry = 0; ++ dpages->dpages[0].dentries = p; ++ dpages->ndpage = 1; ++ return 0; /* success */ + ++out_dpages: ++ kfree(dpages->dpages); +out: + return err; +} + -+/* -+ * regardless 'acl' option, reset all ACL. -+ * All ACL will be copied up later from the original entry on the lower branch. -+ */ -+static int au_reset_acl(struct inode *h_dir, struct path *h_path, umode_t mode) ++void au_dpages_free(struct au_dcsub_pages *dpages) +{ -+ int err; -+ struct dentry *h_dentry; -+ struct inode *h_inode; -+ -+ h_dentry = h_path->dentry; -+ h_inode = d_inode(h_dentry); -+ /* forget_all_cached_acls(h_inode)); */ -+ err = vfsub_removexattr(h_dentry, XATTR_NAME_POSIX_ACL_ACCESS); -+ AuTraceErr(err); -+ if (err == -EOPNOTSUPP) -+ err = 0; -+ if (!err) -+ err = vfsub_acl_chmod(h_inode, mode); ++ int i; ++ struct au_dpage *p; + -+ AuTraceErr(err); -+ return err; ++ p = dpages->dpages; ++ for (i = 0; i < dpages->ndpage; i++) ++ au_dpage_free(p++); ++ kfree(dpages->dpages); +} + -+static int au_do_cpup_dir(struct au_cp_generic *cpg, struct dentry *dst_parent, -+ struct inode *h_dir, struct path *h_path) ++static int au_dpages_append(struct au_dcsub_pages *dpages, ++ struct dentry *dentry, gfp_t gfp) +{ -+ int err; -+ struct inode *dir, *inode; ++ int err, sz; ++ struct au_dpage *dpage; ++ void *p; + -+ err = vfsub_removexattr(h_path->dentry, XATTR_NAME_POSIX_ACL_DEFAULT); -+ AuTraceErr(err); -+ if (err == -EOPNOTSUPP) -+ err = 0; -+ if (unlikely(err)) -+ goto out; ++ 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; + -+ /* -+ * strange behaviour from the users view, -+ * particularry 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); ++ 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; +} + -+static noinline_for_stack -+int cpup_entry(struct au_cp_generic *cpg, struct dentry *dst_parent, -+ struct au_cpup_reg_attr *h_src_attr) -+{ ++/* 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 *), ++ void (*finish)(void *)); ++ ++struct ac_dpages_arg { + 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 au_dcsub_pages *dpages; + struct super_block *sb; ++ au_dpages_test test; ++ void *arg; ++}; + -+ /* 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); ++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; + -+ 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); ++ 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; + } -+ h_path.dentry = h_dst; + -+ isreg = 0; -+ isdir = 0; -+ mode = h_inode->i_mode; -+ switch (mode & S_IFMT) { -+ case S_IFREG: -+ isreg = 1; -+ err = vfsub_create(h_dir, &h_path, S_IRUSR | S_IWUSR, -+ /*want_excl*/true); -+ if (!err) -+ err = au_do_cpup_regular(cpg, h_src_attr); -+ break; -+ case S_IFDIR: -+ isdir = 1; -+ err = vfsub_mkdir(h_dir, &h_path, mode); -+ if (!err) -+ err = au_do_cpup_dir(cpg, dst_parent, h_dir, &h_path); -+ break; -+ case S_IFLNK: -+ err = au_do_cpup_symlink(&h_path, h_src, h_dir); -+ break; -+ case S_IFCHR: -+ case S_IFBLK: -+ AuDebugOn(!capable(CAP_MKNOD)); -+ /*FALLTHROUGH*/ -+ case S_IFIFO: -+ case S_IFSOCK: -+ err = vfsub_mknod(h_dir, &h_path, mode, h_inode->i_rdev); -+ break; -+ default: -+ AuIOErr("Unknown inode type 0%o\n", mode); -+ err = -EIO; -+ } -+ if (!err) -+ err = au_reset_acl(h_dir, &h_path, mode); ++ return ret; ++} + -+ 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 */ ++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 ++ }; + -+ 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); -+ } ++ d_walk(root, &args, au_call_dpages_append, NULL); + -+ if (do_dt) -+ au_dtime_revert(&dt); -+ return err; ++ return args.err; +} + -+static int au_do_ren_after_cpup(struct au_cp_generic *cpg, struct path *h_path) ++int au_dcsub_pages_rev(struct au_dcsub_pages *dpages, struct dentry *dentry, ++ int do_include, au_dpages_test test, void *arg) +{ + int err; -+ struct dentry *dentry, *h_dentry, *h_parent, *parent; -+ struct inode *h_dir; -+ aufs_bindex_t bdst; + -+ dentry = cpg->dentry; -+ bdst = cpg->bdst; -+ h_dentry = au_h_dptr(dentry, bdst); -+ if (!au_ftest_cpup(cpg->flags, OVERWRITE)) { -+ dget(h_dentry); -+ au_set_h_dptr(dentry, bdst, NULL); -+ err = au_lkup_neg(dentry, bdst, /*wh*/0); -+ if (!err) -+ h_path->dentry = dget(au_h_dptr(dentry, bdst)); -+ au_set_h_dptr(dentry, bdst, h_dentry); -+ } else { -+ err = 0; -+ parent = dget_parent(dentry); -+ h_parent = au_h_dptr(parent, bdst); -+ dput(parent); -+ h_path->dentry = vfsub_lkup_one(&dentry->d_name, h_parent); -+ if (IS_ERR(h_path->dentry)) -+ err = PTR_ERR(h_path->dentry); -+ } ++ 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; + -+ 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); ++ /* ++ * 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; +} + -+/* -+ * 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 unnecrssary. -+ */ -+static int au_cpup_single(struct au_cp_generic *cpg, struct dentry *dst_parent) ++static inline int au_dcsub_dpages_aufs(struct dentry *dentry, void *arg) +{ -+ int err, rerr; -+ aufs_bindex_t old_ibtop; -+ unsigned char isdir, plink; -+ struct dentry *h_src, *h_dst, *h_parent; -+ struct inode *dst_inode, *h_dir, *inode, *delegated, *src_inode; -+ struct super_block *sb; -+ struct au_branch *br; -+ /* to reuduce stack size */ -+ struct { -+ struct au_dtime dt; -+ struct path h_path; -+ struct au_cpup_reg_attr h_src_attr; -+ } *a; -+ -+ err = -ENOMEM; -+ a = kmalloc(sizeof(*a), GFP_NOFS); -+ if (unlikely(!a)) -+ goto out; -+ a->h_src_attr.valid = 0; -+ -+ sb = cpg->dentry->d_sb; -+ br = au_sbr(sb, cpg->bdst); -+ a->h_path.mnt = au_br_mnt(br); -+ h_dst = au_h_dptr(cpg->dentry, cpg->bdst); -+ h_parent = h_dst->d_parent; /* dir inode is locked */ -+ h_dir = d_inode(h_parent); -+ IMustLock(h_dir); -+ -+ h_src = au_h_dptr(cpg->dentry, cpg->bsrc); -+ inode = d_inode(cpg->dentry); ++ return au_di(dentry) && dentry->d_sb == arg; ++} + -+ if (!dst_parent) -+ dst_parent = dget_parent(cpg->dentry); -+ else -+ dget(dst_parent); ++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); ++} + -+ 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; ++int au_test_subdir(struct dentry *d1, struct dentry *d2) ++{ ++ struct path path[2] = { ++ { ++ .dentry = d1 ++ }, ++ { ++ .dentry = d2 + } ++ }; + -+ if (dst_inode->i_nlink) { -+ const int do_dt = au_ftest_cpup(cpg->flags, DTIME); -+ -+ h_src = au_plink_lkup(inode, cpg->bdst); -+ err = PTR_ERR(h_src); -+ if (IS_ERR(h_src)) -+ goto out_parent; -+ if (unlikely(d_is_negative(h_src))) { -+ err = -EIO; -+ AuIOErr("i%lu exists on b%d " -+ "but not pseudo-linked\n", -+ inode->i_ino, cpg->bdst); -+ dput(h_src); -+ goto out_parent; -+ } -+ -+ if (do_dt) { -+ a->h_path.dentry = h_parent; -+ au_dtime_store(&a->dt, dst_parent, &a->h_path); -+ } -+ -+ a->h_path.dentry = h_dst; -+ delegated = NULL; -+ err = vfsub_link(h_src, h_dir, &a->h_path, &delegated); -+ if (!err && au_ftest_cpup(cpg->flags, RENAME)) -+ err = au_do_ren_after_cpup(cpg, &a->h_path); -+ if (do_dt) -+ au_dtime_revert(&a->dt); -+ if (unlikely(err == -EWOULDBLOCK)) { -+ pr_warn("cannot retry for NFSv4 delegation" -+ " for an internal link\n"); -+ iput(delegated); -+ } -+ dput(h_src); -+ goto out_parent; -+ } else -+ /* todo: cpup_wh_file? */ -+ /* udba work */ -+ au_update_ibrange(inode, /*do_put_zero*/1); -+ } -+ -+ isdir = S_ISDIR(inode->i_mode); -+ old_ibtop = au_ibtop(inode); -+ err = cpup_entry(cpg, dst_parent, &a->h_src_attr); -+ if (unlikely(err)) -+ goto out_rev; -+ dst_inode = d_inode(h_dst); -+ inode_lock_nested(dst_inode, AuLsc_I_CHILD2); -+ /* todo: necessary? */ -+ /* au_pin_hdir_unlock(cpg->pin); */ -+ -+ err = cpup_iattr(cpg->dentry, cpg->bdst, h_src, &a->h_src_attr); -+ if (unlikely(err)) { -+ /* todo: necessary? */ -+ /* au_pin_hdir_relock(cpg->pin); */ /* ignore an error */ -+ inode_unlock(dst_inode); -+ goto out_rev; -+ } -+ -+ if (cpg->bdst < old_ibtop) { -+ if (S_ISREG(inode->i_mode)) { -+ err = au_dy_iaop(inode, cpg->bdst, dst_inode); -+ if (unlikely(err)) { -+ /* ignore an error */ -+ /* au_pin_hdir_relock(cpg->pin); */ -+ inode_unlock(dst_inode); -+ goto out_rev; -+ } -+ } -+ au_set_ibtop(inode, cpg->bdst); -+ } else -+ au_set_ibbot(inode, cpg->bdst); -+ au_set_h_iptr(inode, cpg->bdst, au_igrab(dst_inode), -+ au_hi_flags(inode, isdir)); ++ return path_is_under(path + 0, path + 1); ++} +diff -urNp -x '*.orig' linux-4.9/fs/aufs/dcsub.h linux-4.9/fs/aufs/dcsub.h +--- linux-4.9/fs/aufs/dcsub.h 1970-01-01 01:00:00.000000000 +0100 ++++ linux-4.9/fs/aufs/dcsub.h 2021-02-24 16:15:09.524906971 +0100 +@@ -0,0 +1,136 @@ ++/* ++ * Copyright (C) 2005-2018 Junjiro R. Okajima ++ * ++ * This program, aufs is free software; you can redistribute it and/or modify ++ * it under the terms of the GNU General Public License as published by ++ * the Free Software Foundation; either version 2 of the License, or ++ * (at your option) any later version. ++ * ++ * This program is distributed in the hope that it will be useful, ++ * but WITHOUT ANY WARRANTY; without even the implied warranty of ++ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the ++ * GNU General Public License for more details. ++ * ++ * You should have received a copy of the GNU General Public License ++ * along with this program. If not, see . ++ */ + -+ /* todo: necessary? */ -+ /* err = au_pin_hdir_relock(cpg->pin); */ -+ inode_unlock(dst_inode); -+ if (unlikely(err)) -+ goto out_rev; ++/* ++ * sub-routines for dentry cache ++ */ + -+ 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); ++#ifndef __AUFS_DCSUB_H__ ++#define __AUFS_DCSUB_H__ + -+ 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 */ ++#ifdef __KERNEL__ + -+ /* 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_delayed_kfree(a); -+out: -+ return err; -+} ++#include ++#include + -+#if 0 /* reserved */ -+struct au_cpup_single_args { -+ int *errp; -+ struct au_cp_generic *cpg; -+ struct dentry *dst_parent; ++struct au_dpage { ++ int ndentry; ++ struct dentry **dentries; +}; + -+static void au_call_cpup_single(void *args) -+{ -+ struct au_cpup_single_args *a = args; ++struct au_dcsub_pages { ++ int ndpage; ++ struct au_dpage *dpages; ++}; + -+ 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 ++/* ---------------------------------------------------------------------- */ ++ ++/* 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); ++ ++/* ---------------------------------------------------------------------- */ + +/* -+ * prevent SIGXFSZ in copy-up. -+ * testing CAP_MKNOD is for generic fs, -+ * but CAP_FSETID is for xfs only, currently. ++ * todo: in linux-3.13, several similar (but faster) helpers are added to ++ * include/linux/dcache.h. Try them (in the future). + */ -+static int au_cpup_sio_test(struct au_pin *pin, umode_t mode) ++ ++static inline int au_d_hashed_positive(struct dentry *d) +{ -+ int do_sio; -+ struct super_block *sb; -+ struct inode *h_dir; ++ int err; ++ struct inode *inode = d_inode(d); + -+ 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; -+ } -+ } ++ err = 0; ++ if (unlikely(d_unhashed(d) ++ || d_is_negative(d) ++ || !inode->i_nlink)) ++ err = -ENOENT; ++ return err; ++} + -+ return do_sio; ++static inline int au_d_linkable(struct dentry *d) ++{ ++ int err; ++ struct inode *inode = d_inode(d); ++ ++ err = au_d_hashed_positive(d); ++ if (err ++ && d_is_positive(d) ++ && (inode->i_state & I_LINKABLE)) ++ err = 0; ++ return err; +} + -+#if 0 /* reserved */ -+int au_sio_cpup_single(struct au_cp_generic *cpg, struct dentry *dst_parent) ++static inline int au_d_alive(struct dentry *d) +{ -+ int err, wkq_err; -+ struct dentry *h_dentry; ++ int err; ++ struct inode *inode; + -+ 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); ++ err = 0; ++ if (!IS_ROOT(d)) ++ err = au_d_hashed_positive(d); + 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(d); ++ if (unlikely(d_unlinked(d) ++ || d_is_negative(d) ++ || !inode->i_nlink)) ++ err = -ENOENT; + } ++ return err; ++} ++ ++static inline int au_alive_dir(struct dentry *d) ++{ ++ int err; + ++ err = au_d_alive(d); ++ if (unlikely(err || IS_DEADDIR(d_inode(d)))) ++ err = -ENOENT; + return err; +} -+#endif ++ ++static inline int au_qstreq(struct qstr *a, struct qstr *b) ++{ ++ return a->len == b->len ++ && !memcmp(a->name, b->name, a->len); ++} + +/* -+ * copyup the @dentry from the first active lower branch to @bdst, -+ * using au_cpup_single(). ++ * 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 int au_cpup_simple(struct au_cp_generic *cpg) ++static inline int au_dcount(struct dentry *d) +{ -+ int err; -+ unsigned int flags_orig; -+ struct dentry *dentry; ++ return (int)d_count(d); ++} + -+ AuDebugOn(cpg->bsrc < 0); ++#endif /* __KERNEL__ */ ++#endif /* __AUFS_DCSUB_H__ */ +diff -urNp -x '*.orig' linux-4.9/fs/aufs/debug.c linux-4.9/fs/aufs/debug.c +--- linux-4.9/fs/aufs/debug.c 1970-01-01 01:00:00.000000000 +0100 ++++ linux-4.9/fs/aufs/debug.c 2021-02-24 16:15:09.524906971 +0100 +@@ -0,0 +1,440 @@ ++/* ++ * Copyright (C) 2005-2018 Junjiro R. Okajima ++ * ++ * This program, aufs is free software; you can redistribute it and/or modify ++ * it under the terms of the GNU General Public License as published by ++ * the Free Software Foundation; either version 2 of the License, or ++ * (at your option) any later version. ++ * ++ * This program is distributed in the hope that it will be useful, ++ * but WITHOUT ANY WARRANTY; without even the implied warranty of ++ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the ++ * GNU General Public License for more details. ++ * ++ * You should have received a copy of the GNU General Public License ++ * along with this program. If not, see . ++ */ + -+ dentry = cpg->dentry; -+ DiMustWriteLock(dentry); ++/* ++ * debug print functions ++ */ + -+ 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 */ ++#include "aufs.h" + -+ /* revert */ -+ au_set_h_dptr(dentry, cpg->bdst, NULL); -+ au_set_dbtop(dentry, cpg->bsrc); -+ } ++/* Returns 0, or -errno. arg is in kp->arg. */ ++static int param_atomic_t_set(const char *val, const struct kernel_param *kp) ++{ ++ int err, n; + ++ err = kstrtoint(val, 0, &n); ++ if (!err) { ++ if (n > 0) ++ au_debug_on(); ++ else ++ au_debug_off(); ++ } + return err; +} + -+struct au_cpup_simple_args { -+ int *errp; -+ struct au_cp_generic *cpg; ++/* Returns length written or -errno. Buffer is 4k (ie. be short!) */ ++static int param_atomic_t_get(char *buffer, const struct kernel_param *kp) ++{ ++ atomic_t *a; ++ ++ a = kp->arg; ++ return sprintf(buffer, "%d", atomic_read(a)); ++} ++ ++static struct kernel_param_ops param_ops_atomic_t = { ++ .set = param_atomic_t_set, ++ .get = param_atomic_t_get ++ /* void (*free)(void *arg) */ +}; + -+static void au_call_cpup_simple(void *args) ++atomic_t aufs_debug = ATOMIC_INIT(0); ++MODULE_PARM_DESC(debug, "debug print"); ++module_param_named(debug, aufs_debug, atomic_t, S_IRUGO | S_IWUSR | S_IWGRP); ++ ++DEFINE_MUTEX(au_dbg_mtx); /* just to serialize the dbg msgs */ ++char *au_plevel = KERN_DEBUG; ++#define dpri(fmt, ...) do { \ ++ if ((au_plevel \ ++ && strcmp(au_plevel, KERN_DEBUG)) \ ++ || au_debug_test()) \ ++ printk("%s" fmt, au_plevel, ##__VA_ARGS__); \ ++} while (0) ++ ++/* ---------------------------------------------------------------------- */ ++ ++void au_dpri_whlist(struct au_nhash *whlist) +{ -+ struct au_cpup_simple_args *a = args; ++ unsigned long ul, n; ++ struct hlist_head *head; ++ struct au_vdir_wh *pos; + -+ au_pin_hdir_acquire_nest(a->cpg->pin); -+ *a->errp = au_cpup_simple(a->cpg); -+ au_pin_hdir_release(a->cpg->pin); ++ 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++; ++ } +} + -+static int au_do_sio_cpup_simple(struct au_cp_generic *cpg) ++void au_dpri_vdir(struct au_vdir *vdir) +{ -+ int err, wkq_err; -+ struct dentry *dentry, *parent; -+ struct file *h_file; -+ struct inode *h_dir; ++ unsigned long ul; ++ union au_vdir_deblk_p p; ++ unsigned char *o; + -+ 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; ++ if (!vdir || IS_ERR(vdir)) { ++ dpri("err %ld\n", PTR_ERR(vdir)); ++ return; + } + -+ parent = dget_parent(dentry); -+ h_dir = au_h_iptr(d_inode(parent), cpg->bdst); -+ if (!au_test_h_perm_sio(h_dir, MAY_EXEC | MAY_WRITE) -+ && !au_cpup_sio_test(cpg->pin, d_inode(dentry)->i_mode)) -+ err = au_cpup_simple(cpg); -+ else { -+ struct au_cpup_simple_args args = { -+ .errp = &err, -+ .cpg = cpg -+ }; -+ wkq_err = au_wkq_wait(au_call_cpup_simple, &args); -+ if (unlikely(wkq_err)) -+ err = wkq_err; ++ dpri("deblk %u, nblk %lu, deblk %p, last{%lu, %p}, ver %lu\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); + } -+ -+ dput(parent); -+ if (h_file) -+ au_h_open_post(dentry, cpg->bsrc, h_file); -+ -+out: -+ return err; +} + -+int au_sio_cpup_simple(struct au_cp_generic *cpg) ++static int do_pri_inode(aufs_bindex_t bindex, struct inode *inode, int hn, ++ struct dentry *wh) +{ -+ aufs_bindex_t bsrc, bbot; -+ struct dentry *dentry, *h_dentry; ++ char *n = NULL; ++ int l = 0; + -+ 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; ++ if (!inode || IS_ERR(inode)) { ++ dpri("i%d: err %ld\n", bindex, PTR_ERR(inode)); ++ return -1; + } -+ AuDebugOn(cpg->bsrc <= cpg->bdst); -+ return au_do_sio_cpup_simple(cpg); -+} + -+int au_sio_cpdown_simple(struct au_cp_generic *cpg) -+{ -+ AuDebugOn(cpg->bdst <= cpg->bsrc); -+ return au_do_sio_cpup_simple(cpg); -+} ++ /* the type of i_blocks depends upon CONFIG_LBDAF */ ++ BUILD_BUG_ON(sizeof(inode->i_blocks) != sizeof(unsigned long) ++ && sizeof(inode->i_blocks) != sizeof(u64)); ++ if (wh) { ++ n = (void *)wh->d_name.name; ++ l = wh->d_name.len; ++ } + -+/* ---------------------------------------------------------------------- */ ++ dpri("i%d: %p, i%lu, %s, cnt %d, nl %u, 0%o, sz %llu, blk %llu," ++ " hn %d, ct %lld, np %lu, st 0x%lx, f 0x%x, v %llu, g %x%s%.*s\n", ++ bindex, inode, ++ inode->i_ino, inode->i_sb ? au_sbtype(inode->i_sb) : "??", ++ atomic_read(&inode->i_count), inode->i_nlink, inode->i_mode, ++ i_size_read(inode), (unsigned long long)inode->i_blocks, ++ hn, (long long)timespec_to_ns(&inode->i_ctime) & 0x0ffff, ++ inode->i_mapping ? inode->i_mapping->nrpages : 0, ++ inode->i_state, inode->i_flags, inode->i_version, ++ inode->i_generation, ++ l ? ", wh " : "", l, n); ++ return 0; ++} + -+/* -+ * copyup the deleted file for writing. -+ */ -+static int au_do_cpup_wh(struct au_cp_generic *cpg, struct dentry *wh_dentry, -+ struct file *file) ++void au_dpri_inode(struct inode *inode) +{ -+ int err; -+ unsigned int flags_orig; -+ aufs_bindex_t bsrc_orig; -+ struct au_dinfo *dinfo; -+ struct { -+ struct au_hdentry *hd; -+ struct dentry *h_dentry; -+ } hdst, hsrc; -+ -+ dinfo = au_di(cpg->dentry); -+ AuRwMustWriteLock(&dinfo->di_rwsem); ++ struct au_iinfo *iinfo; ++ struct au_hinode *hi; ++ aufs_bindex_t bindex; ++ int err, hn; + -+ 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; ++ err = do_pri_inode(-1, inode, -1, NULL); ++ if (err || !au_test_aufs(inode->i_sb) || au_is_bad_inode(inode)) ++ return; + -+ 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; ++ 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); + } -+ 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) ++void au_dpri_dalias(struct inode *inode) +{ -+ 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; ++ struct dentry *d; + -+ dentry = cpg->dentry; -+ bdst = cpg->bdst; -+ br = au_sbr(dentry->d_sb, bdst); -+ parent = dget_parent(dentry); -+ h_parent = au_h_dptr(parent, bdst); -+ wh_dentry = au_whtmp_lkup(h_parent, br, &dentry->d_name); -+ err = PTR_ERR(wh_dentry); -+ if (IS_ERR(wh_dentry)) -+ goto out; ++ 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); ++} + -+ 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; ++static int do_pri_dentry(aufs_bindex_t bindex, struct dentry *dentry) ++{ ++ struct dentry *wh = NULL; ++ int hn; ++ struct inode *inode; ++ struct au_iinfo *iinfo; ++ struct au_hinode *hi; + -+ 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; ++ if (!dentry || IS_ERR(dentry)) { ++ dpri("d%d: err %ld\n", bindex, PTR_ERR(dentry)); ++ return -1; ++ } ++ /* do not call dget_parent() here */ ++ /* note: access d_xxx without d_lock */ ++ dpri("d%d: %p, %pd2?, %s, cnt %d, flags 0x%x, %shashed\n", ++ bindex, dentry, dentry, ++ dentry->d_sb ? au_sbtype(dentry->d_sb) : "??", ++ au_dcount(dentry), dentry->d_flags, ++ d_unhashed(dentry) ? "un" : ""); ++ hn = -1; ++ inode = NULL; ++ if (d_is_positive(dentry)) ++ inode = d_inode(dentry); ++ if (inode ++ && au_test_aufs(dentry->d_sb) ++ && bindex >= 0 ++ && !au_is_bad_inode(inode)) { ++ iinfo = au_ii(inode); ++ hi = au_hinode(iinfo, bindex); ++ hn = !!au_hn(hi); ++ wh = hi->hi_whdentry; + } -+ au_dtime_revert(&dt); -+ au_set_hi_wh(d_inode(dentry), bdst, wh_dentry); -+ -+out_wh: -+ dput(wh_dentry); -+out: -+ dput(parent); -+ return err; ++ do_pri_inode(bindex, inode, hn, wh); ++ return 0; +} + -+struct au_cpup_wh_args { -+ int *errp; -+ struct au_cp_generic *cpg; -+ struct file *file; -+}; -+ -+static void au_call_cpup_wh(void *args) ++void au_dpri_dentry(struct dentry *dentry) +{ -+ struct au_cpup_wh_args *a = args; ++ struct au_dinfo *dinfo; ++ aufs_bindex_t bindex; ++ int err; + -+ au_pin_hdir_acquire_nest(a->cpg->pin); -+ *a->errp = au_cpup_wh(a->cpg, a->file); -+ au_pin_hdir_release(a->cpg->pin); ++ err = do_pri_dentry(-1, dentry); ++ if (err || !au_test_aufs(dentry->d_sb)) ++ return; ++ ++ dinfo = au_di(dentry); ++ if (!dinfo) ++ return; ++ dpri("d-1: btop %d, bbot %d, bwh %d, bdiropq %d, gen %d, tmp %d\n", ++ dinfo->di_btop, dinfo->di_bbot, ++ dinfo->di_bwh, dinfo->di_bdiropq, au_digen(dentry), ++ dinfo->di_tmpfile); ++ if (dinfo->di_btop < 0) ++ return; ++ for (bindex = dinfo->di_btop; bindex <= dinfo->di_bbot; bindex++) ++ do_pri_dentry(bindex, au_hdentry(dinfo, bindex)->hd_dentry); +} + -+int au_sio_cpup_wh(struct au_cp_generic *cpg, struct file *file) ++static int do_pri_file(aufs_bindex_t bindex, struct file *file) +{ -+ int err, wkq_err; -+ aufs_bindex_t bdst; -+ struct dentry *dentry, *parent, *h_orph, *h_parent; -+ struct inode *dir, *h_dir, *h_tmpdir; -+ struct au_wbr *wbr; -+ struct au_pin wh_pin, *pin_orig; ++ char a[32]; + -+ 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; ++ if (!file || IS_ERR(file)) { ++ dpri("f%d: err %ld\n", bindex, PTR_ERR(file)); ++ return -1; ++ } ++ a[0] = 0; ++ if (bindex < 0 ++ && !IS_ERR_OR_NULL(file->f_path.dentry) ++ && au_test_aufs(file->f_path.dentry->d_sb) ++ && au_fi(file)) ++ snprintf(a, sizeof(a), ", gen %d, mmapped %d", ++ au_figen(file), atomic_read(&au_fi(file)->fi_mmapped)); ++ dpri("f%d: mode 0x%x, flags 0%o, cnt %ld, v %llu, pos %llu%s\n", ++ bindex, file->f_mode, file->f_flags, (long)file_count(file), ++ file->f_version, file->f_pos, a); ++ if (!IS_ERR_OR_NULL(file->f_path.dentry)) ++ do_pri_dentry(bindex, file->f_path.dentry); ++ return 0; ++} + -+ 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); ++void au_dpri_file(struct file *file) ++{ ++ struct au_finfo *finfo; ++ struct au_fidir *fidir; ++ struct au_hfile *hfile; ++ aufs_bindex_t bindex; ++ int err; + -+ inode_lock_nested(h_tmpdir, AuLsc_I_PARENT3); -+ /* todo: au_h_open_pre()? */ ++ 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; + -+ 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; -+ } ++ 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); ++ } ++} + -+ if (!au_test_h_perm_sio(h_tmpdir, MAY_EXEC | MAY_WRITE) -+ && !au_cpup_sio_test(cpg->pin, d_inode(dentry)->i_mode)) -+ err = au_cpup_wh(cpg, file); -+ else { -+ struct au_cpup_wh_args args = { -+ .errp = &err, -+ .cpg = cpg, -+ .file = file -+ }; -+ wkq_err = au_wkq_wait(au_call_cpup_wh, &args); -+ if (unlikely(wkq_err)) -+ err = wkq_err; -+ } ++static int do_pri_br(aufs_bindex_t bindex, struct au_branch *br) ++{ ++ struct vfsmount *mnt; ++ struct super_block *sb; + -+ 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); ++ 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; + -+ return err; -+} ++ dpri("s%d: {perm 0x%x, id %d, cnt %lld, wbr %p}, " ++ "%s, dev 0x%02x%02x, flags 0x%lx, cnt %d, active %d, " ++ "xino %d\n", ++ bindex, br->br_perm, br->br_id, au_br_count(br), ++ 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), !!br->br_xino.xi_file); ++ return 0; + -+/* ---------------------------------------------------------------------- */ ++out: ++ dpri("s%d: err %ld\n", bindex, PTR_ERR(br)); ++ return -1; ++} + -+/* -+ * 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) ++void au_dpri_sb(struct super_block *sb) +{ ++ struct au_sbinfo *sbinfo; ++ aufs_bindex_t bindex; + int err; -+ struct au_pin pin; -+ struct dentry *d, *parent, *h_parent, *real_parent, *h_dentry; ++ /* to reuduce stack size */ ++ struct { ++ struct vfsmount mnt; ++ struct au_branch fake; ++ } *a; + -+ err = 0; -+ parent = dget_parent(dentry); -+ if (IS_ROOT(parent)) -+ goto out; ++ /* this function can be called from magic sysrq */ ++ a = kzalloc(sizeof(*a), GFP_ATOMIC); ++ if (unlikely(!a)) { ++ dpri("no memory\n"); ++ return; ++ } + -+ au_pin_init(&pin, dentry, bdst, AuLsc_DI_PARENT2, AuLsc_I_PARENT2, -+ au_opt_udba(dentry->d_sb), AuPin_MNT_WRITE); ++ a->mnt.mnt_sb = sb; ++ a->fake.br_path.mnt = &a->mnt; ++ au_br_count_init(&a->fake); ++ err = do_pri_br(-1, &a->fake); ++ au_br_count_fin(&a->fake); ++ kfree(a); ++ dpri("dev 0x%x\n", sb->s_dev); ++ if (err || !au_test_aufs(sb)) ++ return; + -+ /* 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 */ ++ 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, ++ atomic_read(&sbinfo->si_kobj.kref.refcount)); ++ for (bindex = 0; bindex <= sbinfo->si_bbot; bindex++) ++ do_pri_br(bindex, sbinfo->si_branch[0 + bindex]); ++} + -+ /* 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); ++void __au_dbg_verify_dinode(struct dentry *dentry, const char *func, int line) ++{ ++ struct inode *h_inode, *inode = d_inode(dentry); ++ struct dentry *h_dentry; ++ aufs_bindex_t bindex, bbot, bi; + -+ /* 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); ++ if (!inode /* || au_di(dentry)->di_lsc == AuLsc_DI_TMP */) ++ return; + -+ au_pin_set_dentry(&pin, d); -+ err = au_do_pin(&pin); -+ if (!err) { -+ err = cp(d, bdst, &pin, h_parent, arg); -+ au_unpin(&pin); -+ } -+ } ++ 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; + -+ if (d != real_parent) -+ di_write_unlock(d); -+ if (unlikely(err)) -+ break; ++ for (; bindex <= bbot; bindex++) { ++ h_dentry = au_h_dptr(dentry, bindex); ++ if (!h_dentry) ++ continue; ++ h_inode = au_h_iptr(inode, bindex); ++ if (unlikely(h_inode != d_inode(h_dentry))) { ++ au_debug_on(); ++ AuDbg("b%d, %s:%d\n", bindex, func, line); ++ AuDbgDentry(dentry); ++ AuDbgInode(inode); ++ au_debug_off(); ++ BUG(); ++ } + } -+ -+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) ++void au_dbg_verify_gen(struct dentry *parent, unsigned int sigen) +{ -+ 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 err, i, j; ++ struct au_dcsub_pages dpages; ++ struct au_dpage *dpage; ++ struct dentry **dentries; ++ ++ err = au_dpages_init(&dpages, GFP_NOFS); ++ AuDebugOn(err); ++ err = au_dcsub_pages_rev_aufs(&dpages, parent, /*do_include*/1); ++ AuDebugOn(err); ++ for (i = dpages.ndpage - 1; !err && i >= 0; i--) { ++ dpage = dpages.dpages + i; ++ dentries = dpage->dentries; ++ for (j = dpage->ndentry - 1; !err && j >= 0; j--) ++ AuDebugOn(au_digen_test(dentries[j], sigen)); ++ } ++ au_dpages_free(&dpages); +} + -+int au_cpup_dirs(struct dentry *dentry, aufs_bindex_t bdst) ++void au_dbg_verify_kthread(void) +{ -+ return au_cp_dirs(dentry, bdst, au_cpup_dir, NULL); ++ 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 au_test_and_cpup_dirs(struct dentry *dentry, aufs_bindex_t bdst) ++/* ---------------------------------------------------------------------- */ ++ ++int __init au_debug_init(void) +{ -+ int err; -+ struct dentry *parent; -+ struct inode *dir; ++ aufs_bindex_t bindex; ++ struct au_vdir_destr destr; + -+ parent = dget_parent(dentry); -+ dir = d_inode(parent); -+ err = 0; -+ if (au_h_iptr(dir, bdst)) -+ goto out; ++ bindex = -1; ++ AuDebugOn(bindex >= 0); + -+ 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); ++ destr.len = -1; ++ AuDebugOn(destr.len < NAME_MAX); + -+out: -+ dput(parent); -+ return err; ++#ifdef CONFIG_4KSTACKS ++ pr_warn("CONFIG_4KSTACKS is defined.\n"); ++#endif ++ ++ return 0; +} -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 2016-10-09 16:55:36.486034798 +0200 -@@ -0,0 +1,94 @@ +diff -urNp -x '*.orig' linux-4.9/fs/aufs/debug.h linux-4.9/fs/aufs/debug.h +--- linux-4.9/fs/aufs/debug.h 1970-01-01 01:00:00.000000000 +0100 ++++ linux-4.9/fs/aufs/debug.h 2021-02-24 16:15:09.524906971 +0100 +@@ -0,0 +1,225 @@ +/* -+ * Copyright (C) 2005-2016 Junjiro R. Okajima ++ * Copyright (C) 2005-2018 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by @@ -6062,88 +7099,219 @@ diff -urN /usr/share/empty/fs/aufs/cpup.h linux/fs/aufs/cpup.h + */ + +/* -+ * copy-up/down functions ++ * debug print functions + */ + -+#ifndef __AUFS_CPUP_H__ -+#define __AUFS_CPUP_H__ ++#ifndef __AUFS_DEBUG_H__ ++#define __AUFS_DEBUG_H__ + +#ifdef __KERNEL__ + -+#include ++#include ++#include ++#include ++#include ++ ++#ifdef CONFIG_AUFS_DEBUG ++#define AuDebugOn(a) BUG_ON(a) ++ ++/* module parameter */ ++extern atomic_t aufs_debug; ++static inline void au_debug_on(void) ++{ ++ atomic_inc(&aufs_debug); ++} ++static inline void au_debug_off(void) ++{ ++ atomic_dec_if_positive(&aufs_debug); ++} ++ ++static inline int au_debug_test(void) ++{ ++ return atomic_read(&aufs_debug) > 0; ++} ++#else ++#define AuDebugOn(a) do {} while (0) ++AuStubVoid(au_debug_on, void) ++AuStubVoid(au_debug_off, void) ++AuStubInt0(au_debug_test, void) ++#endif /* CONFIG_AUFS_DEBUG */ ++ ++#define param_check_atomic_t(name, p) __param_check(name, p, atomic_t) ++ ++/* ---------------------------------------------------------------------- */ ++ ++/* debug print */ ++ ++#define AuDbg(fmt, ...) do { \ ++ if (au_debug_test()) \ ++ pr_debug("DEBUG: " fmt, ##__VA_ARGS__); \ ++} while (0) ++#define AuLabel(l) AuDbg(#l "\n") ++#define AuIOErr(fmt, ...) pr_err("I/O Error, " fmt, ##__VA_ARGS__) ++#define AuWarn1(fmt, ...) do { \ ++ static unsigned char _c; \ ++ if (!_c++) \ ++ pr_warn(fmt, ##__VA_ARGS__); \ ++} while (0) ++ ++#define AuErr1(fmt, ...) do { \ ++ static unsigned char _c; \ ++ if (!_c++) \ ++ pr_err(fmt, ##__VA_ARGS__); \ ++} while (0) ++ ++#define AuIOErr1(fmt, ...) do { \ ++ static unsigned char _c; \ ++ if (!_c++) \ ++ AuIOErr(fmt, ##__VA_ARGS__); \ ++} while (0) ++ ++#define AuUnsupportMsg "This operation is not supported." \ ++ " Please report this application to aufs-users ML." ++#define AuUnsupport(fmt, ...) do { \ ++ pr_err(AuUnsupportMsg "\n" fmt, ##__VA_ARGS__); \ ++ dump_stack(); \ ++} while (0) ++ ++#define AuTraceErr(e) do { \ ++ if (unlikely((e) < 0)) \ ++ AuDbg("err %d\n", (int)(e)); \ ++} while (0) ++ ++#define AuTraceErrPtr(p) do { \ ++ if (IS_ERR(p)) \ ++ AuDbg("err %ld\n", PTR_ERR(p)); \ ++} while (0) ++ ++/* dirty macros for debug print, use with "%.*s" and caution */ ++#define AuLNPair(qstr) (qstr)->len, (qstr)->name ++ ++/* ---------------------------------------------------------------------- */ + ++struct dentry; ++#ifdef CONFIG_AUFS_DEBUG ++extern struct mutex au_dbg_mtx; ++extern char *au_plevel; ++struct au_nhash; ++void au_dpri_whlist(struct au_nhash *whlist); ++struct au_vdir; ++void au_dpri_vdir(struct au_vdir *vdir); +struct inode; ++void au_dpri_inode(struct inode *inode); ++void au_dpri_dalias(struct inode *inode); ++void au_dpri_dentry(struct dentry *dentry); +struct file; -+struct au_pin; ++void au_dpri_file(struct file *filp); ++struct super_block; ++void au_dpri_sb(struct super_block *sb); + -+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); ++#define au_dbg_verify_dinode(d) __au_dbg_verify_dinode(d, __func__, __LINE__) ++void __au_dbg_verify_dinode(struct dentry *dentry, const char *func, int line); ++void au_dbg_verify_gen(struct dentry *parent, unsigned int sigen); ++void au_dbg_verify_kthread(void); ++ ++int __init au_debug_init(void); ++ ++#define AuDbgWhlist(w) do { \ ++ mutex_lock(&au_dbg_mtx); \ ++ AuDbg(#w "\n"); \ ++ au_dpri_whlist(w); \ ++ mutex_unlock(&au_dbg_mtx); \ ++} while (0) ++ ++#define AuDbgVdir(v) do { \ ++ mutex_lock(&au_dbg_mtx); \ ++ AuDbg(#v "\n"); \ ++ au_dpri_vdir(v); \ ++ mutex_unlock(&au_dbg_mtx); \ ++} while (0) ++ ++#define AuDbgInode(i) do { \ ++ mutex_lock(&au_dbg_mtx); \ ++ AuDbg(#i "\n"); \ ++ au_dpri_inode(i); \ ++ mutex_unlock(&au_dbg_mtx); \ ++} while (0) ++ ++#define AuDbgDAlias(i) do { \ ++ mutex_lock(&au_dbg_mtx); \ ++ AuDbg(#i "\n"); \ ++ au_dpri_dalias(i); \ ++ mutex_unlock(&au_dbg_mtx); \ ++} while (0) ++ ++#define AuDbgDentry(d) do { \ ++ mutex_lock(&au_dbg_mtx); \ ++ AuDbg(#d "\n"); \ ++ au_dpri_dentry(d); \ ++ mutex_unlock(&au_dbg_mtx); \ ++} while (0) + -+/* ---------------------------------------------------------------------- */ ++#define AuDbgFile(f) do { \ ++ mutex_lock(&au_dbg_mtx); \ ++ AuDbg(#f "\n"); \ ++ au_dpri_file(f); \ ++ mutex_unlock(&au_dbg_mtx); \ ++} while (0) + -+struct au_cp_generic { -+ struct dentry *dentry; -+ aufs_bindex_t bdst, bsrc; -+ loff_t len; -+ struct au_pin *pin; -+ unsigned int flags; -+}; ++#define AuDbgSb(sb) do { \ ++ mutex_lock(&au_dbg_mtx); \ ++ AuDbg(#sb "\n"); \ ++ au_dpri_sb(sb); \ ++ mutex_unlock(&au_dbg_mtx); \ ++} while (0) + -+/* 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 */ ++#define AuDbgSym(addr) do { \ ++ char sym[KSYM_SYMBOL_LEN]; \ ++ sprint_symbol(sym, (unsigned long)addr); \ ++ AuDbg("%s\n", sym); \ ++} while (0) ++#else ++AuStubVoid(au_dbg_verify_dinode, struct dentry *dentry) ++AuStubVoid(au_dbg_verify_gen, struct dentry *parent, unsigned int sigen) ++AuStubVoid(au_dbg_verify_kthread, void) ++AuStubInt0(__init au_debug_init, void) + -+#define 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) ++#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 */ + -+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); ++#ifdef CONFIG_AUFS_MAGIC_SYSRQ ++int __init au_sysrq_init(void); ++void au_sysrq_fin(void); + -+/* ---------------------------------------------------------------------- */ ++#ifdef CONFIG_HW_CONSOLE ++#define au_dbg_blocked() do { \ ++ WARN_ON(1); \ ++ handle_sysrq('w'); \ ++} while (0) ++#else ++AuStubVoid(au_dbg_blocked, void) ++#endif + -+/* keep timestamps when copyup */ -+struct au_dtime { -+ struct dentry *dt_dentry; -+ struct path dt_h_path; -+ struct timespec 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); ++#else ++AuStubInt0(__init au_sysrq_init, void) ++AuStubVoid(au_sysrq_fin, void) ++AuStubVoid(au_dbg_blocked, void) ++#endif /* CONFIG_AUFS_MAGIC_SYSRQ */ + +#endif /* __KERNEL__ */ -+#endif /* __AUFS_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 2016-10-09 16:55:38.886097714 +0200 -@@ -0,0 +1,438 @@ ++#endif /* __AUFS_DEBUG_H__ */ +diff -urNp -x '*.orig' linux-4.9/fs/aufs/dentry.c linux-4.9/fs/aufs/dentry.c +--- linux-4.9/fs/aufs/dentry.c 1970-01-01 01:00:00.000000000 +0100 ++++ linux-4.9/fs/aufs/dentry.c 2021-02-24 16:15:09.524906971 +0100 +@@ -0,0 +1,1152 @@ +/* -+ * Copyright (C) 2005-2016 Junjiro R. Okajima ++ * Copyright (C) 2005-2018 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by @@ -6160,853 +7328,1146 @@ diff -urN /usr/share/empty/fs/aufs/dbgaufs.c linux/fs/aufs/dbgaufs.c + */ + +/* -+ * debugfs interface ++ * lookup and dentry operations + */ + -+#include ++#include +#include "aufs.h" + -+#ifndef CONFIG_SYSFS -+#error DEBUG_FS depends upon SYSFS -+#endif -+ -+static struct dentry *dbgaufs; -+static const mode_t dbgaufs_mode = S_IRUSR | S_IRGRP | S_IROTH; -+ -+/* 20 is max digits length of ulong 64 */ -+struct dbgaufs_arg { -+ int n; -+ char a[20 * 4]; -+}; -+ +/* -+ * common function for all XINO files ++ * returns positive/negative dentry, NULL or an error. ++ * NULL means whiteout-ed or not-found. + */ -+static int dbgaufs_xi_release(struct inode *inode __maybe_unused, -+ struct file *file) -+{ -+ au_delayed_kfree(file->private_data); -+ return 0; -+} -+ -+static int dbgaufs_xi_open(struct file *xf, struct file *file, int do_fcnt) ++static struct dentry* ++au_do_lookup(struct dentry *h_parent, struct dentry *dentry, ++ aufs_bindex_t bindex, struct au_do_lookup_args *args) +{ -+ int err; -+ struct kstat st; -+ struct dbgaufs_arg *p; ++ struct dentry *h_dentry; ++ struct inode *h_inode; ++ struct au_branch *br; ++ int wh_found, opq; ++ unsigned char wh_able; ++ const unsigned char allow_neg = !!au_ftest_lkup(args->flags, ALLOW_NEG); ++ const unsigned char ignore_perm = !!au_ftest_lkup(args->flags, ++ IGNORE_PERM); + -+ err = -ENOMEM; -+ p = kmalloc(sizeof(*p), GFP_NOFS); -+ if (unlikely(!p)) ++ wh_found = 0; ++ br = au_sbr(dentry->d_sb, bindex); ++ wh_able = !!au_br_whable(br->br_perm); ++ if (wh_able) ++ wh_found = au_wh_test(h_parent, &args->whname, ignore_perm); ++ h_dentry = ERR_PTR(wh_found); ++ if (!wh_found) ++ goto real_lookup; ++ if (unlikely(wh_found < 0)) + goto out; + -+ err = 0; -+ p->n = 0; -+ file->private_data = p; -+ if (!xf) ++ /* We found a whiteout */ ++ /* au_set_dbbot(dentry, bindex); */ ++ au_set_dbwh(dentry, bindex); ++ if (!allow_neg) ++ return NULL; /* success */ ++ ++real_lookup: ++ if (!ignore_perm) ++ h_dentry = vfsub_lkup_one(args->name, h_parent); ++ else ++ h_dentry = au_sio_lkup_one(args->name, h_parent); ++ if (IS_ERR(h_dentry)) { ++ if (PTR_ERR(h_dentry) == -ENAMETOOLONG ++ && !allow_neg) ++ h_dentry = NULL; + goto out; ++ } + -+ err = vfs_getattr(&xf->f_path, &st); -+ if (!err) { -+ if (do_fcnt) -+ p->n = snprintf -+ (p->a, sizeof(p->a), "%ld, %llux%lu %lld\n", -+ (long)file_count(xf), st.blocks, st.blksize, -+ (long long)st.size); -+ else -+ p->n = snprintf(p->a, sizeof(p->a), "%llux%lu %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; ++ 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; + } + -+out: -+ return err; ++ 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 */ + -+static ssize_t dbgaufs_xi_read(struct file *file, char __user *buf, -+ size_t count, loff_t *ppos) -+{ -+ struct dbgaufs_arg *p; ++ vfsub_inode_lock_shared_nested(h_inode, AuLsc_I_CHILD); ++ opq = au_diropq_test(h_dentry); ++ inode_unlock_shared(h_inode); ++ if (opq > 0) ++ au_set_dbdiropq(dentry, bindex); ++ else if (unlikely(opq < 0)) { ++ au_set_h_dptr(dentry, bindex, NULL); ++ h_dentry = ERR_PTR(opq); ++ } ++ goto out; + -+ p = file->private_data; -+ return simple_read_from_buffer(buf, count, ppos, p->a, p->n); ++out_neg: ++ dput(h_dentry); ++ h_dentry = NULL; ++out: ++ return h_dentry; +} + -+/* ---------------------------------------------------------------------- */ -+ -+struct dbgaufs_plink_arg { -+ int n; -+ char a[]; -+}; -+ -+static int dbgaufs_plink_release(struct inode *inode __maybe_unused, -+ struct file *file) ++static int au_test_shwh(struct super_block *sb, const struct qstr *name) +{ -+ au_delayed_free_page((unsigned long)file->private_data); ++ if (unlikely(!au_opt_test(au_mntflags(sb), SHWH) ++ && !strncmp(name->name, AUFS_WH_PFX, AUFS_WH_PFX_LEN))) ++ return -EPERM; + return 0; +} + -+static int dbgaufs_plink_open(struct inode *inode, struct file *file) ++/* ++ * 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 err, i, limit; -+ unsigned long n, sum; -+ struct dbgaufs_plink_arg *p; -+ struct au_sbinfo *sbinfo; ++ 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; -+ struct au_sphlhead *sphl; + -+ err = -ENOMEM; -+ p = (void *)get_zeroed_page(GFP_NOFS); -+ if (unlikely(!p)) ++ sb = dentry->d_sb; ++ err = au_test_shwh(sb, args.name); ++ if (unlikely(err)) + goto out; + -+ err = -EFBIG; -+ sbinfo = inode->i_private; -+ sb = sbinfo->si_sb; -+ si_noflush_read_lock(sb); -+ if (au_opt_test(au_mntflags(sb), PLINK)) { -+ limit = PAGE_SIZE - sizeof(p->n); ++ err = au_wh_name_alloc(&args.whname, args.name); ++ if (unlikely(err)) ++ goto out; + -+ /* the number of buckets */ -+ n = snprintf(p->a + p->n, limit, "%d\n", AuPlink_NHASH); -+ p->n += n; -+ limit -= n; ++ 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); + -+ sum = 0; -+ for (i = 0, sphl = sbinfo->si_plink; -+ i < AuPlink_NHASH; -+ i++, sphl++) { -+ n = au_sphl_count(sphl); -+ sum += n; ++ 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; + -+ n = snprintf(p->a + p->n, limit, "%lu ", n); -+ p->n += n; -+ limit -= n; -+ if (unlikely(limit <= 0)) -+ goto out_free; ++ h_dentry = au_h_dptr(dentry, bindex); ++ if (h_dentry) { ++ if (d_is_positive(h_dentry)) ++ npositive++; ++ break; + } -+ p->a[p->n - 1] = '\n'; ++ h_parent = au_h_dptr(parent, bindex); ++ if (!h_parent || !d_is_dir(h_parent)) ++ continue; + -+ /* the sum of plinks */ -+ n = snprintf(p->a + p->n, limit, "%lu\n", sum); -+ p->n += n; -+ limit -= n; -+ if (unlikely(limit <= 0)) -+ goto out_free; -+ } else { -+#define str "1\n0\n0\n" -+ p->n = sizeof(str) - 1; -+ strcpy(p->a, str); -+#undef str ++ 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); ++ vfsub_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; ++ } + } -+ si_read_unlock(sb); + -+ err = 0; -+ file->private_data = p; -+ goto out; /* success */ ++ if (npositive) { ++ AuLabel(positive); ++ au_update_dbtop(dentry); ++ } ++ err = npositive; ++ if (unlikely(!au_opt_test(au_mntflags(sb), UDBA_NONE) ++ && au_dbtop(dentry) < 0)) { ++ err = -EIO; ++ AuIOErr("both of real entry and whiteout found, %pd, err %d\n", ++ dentry, err); ++ } + -+out_free: -+ au_delayed_free_page((unsigned long)p); ++out_parent: ++ dput(parent); ++ kfree(args.whname.name); ++ if (dirren) ++ au_dr_lkup_fin(&args); +out: + return err; +} + -+static ssize_t dbgaufs_plink_read(struct file *file, char __user *buf, -+ size_t count, loff_t *ppos) ++struct dentry *au_sio_lkup_one(struct qstr *name, struct dentry *parent) +{ -+ struct dbgaufs_plink_arg *p; -+ -+ p = file->private_data; -+ return simple_read_from_buffer(buf, count, ppos, p->a, p->n); -+} -+ -+static const struct file_operations dbgaufs_plink_fop = { -+ .owner = THIS_MODULE, -+ .open = dbgaufs_plink_open, -+ .release = dbgaufs_plink_release, -+ .read = dbgaufs_plink_read -+}; ++ struct dentry *dentry; ++ int wkq_err; + -+/* ---------------------------------------------------------------------- */ ++ if (!au_test_h_perm_sio(d_inode(parent), MAY_EXEC)) ++ dentry = vfsub_lkup_one(name, parent); ++ else { ++ struct vfsub_lkup_one_args args = { ++ .errp = &dentry, ++ .name = name, ++ .parent = parent ++ }; + -+static int dbgaufs_xib_open(struct inode *inode, struct file *file) -+{ -+ int err; -+ struct au_sbinfo *sbinfo; -+ struct super_block *sb; ++ wkq_err = au_wkq_wait(vfsub_call_lkup_one, &args); ++ if (unlikely(wkq_err)) ++ dentry = ERR_PTR(wkq_err); ++ } + -+ sbinfo = inode->i_private; -+ sb = sbinfo->si_sb; -+ si_noflush_read_lock(sb); -+ err = dbgaufs_xi_open(sbinfo->si_xib, file, /*do_fcnt*/0); -+ si_read_unlock(sb); -+ return err; ++ return dentry; +} + -+static const struct file_operations dbgaufs_xib_fop = { -+ .owner = THIS_MODULE, -+ .open = dbgaufs_xib_open, -+ .release = dbgaufs_xi_release, -+ .read = dbgaufs_xi_read -+}; -+ -+/* ---------------------------------------------------------------------- */ -+ -+#define DbgaufsXi_PREFIX "xi" -+ -+static int dbgaufs_xino_open(struct inode *inode, struct file *file) ++/* ++ * lookup @dentry on @bindex which should be negative. ++ */ ++int au_lkup_neg(struct dentry *dentry, aufs_bindex_t bindex, int wh) +{ + int err; -+ long l; -+ struct au_sbinfo *sbinfo; -+ struct super_block *sb; -+ struct file *xf; -+ struct qstr *name; ++ struct dentry *parent, *h_parent, *h_dentry; ++ struct au_branch *br; + -+ err = -ENOENT; -+ xf = NULL; -+ name = &file->f_path.dentry->d_name; -+ if (unlikely(name->len < sizeof(DbgaufsXi_PREFIX) -+ || memcmp(name->name, DbgaufsXi_PREFIX, -+ sizeof(DbgaufsXi_PREFIX) - 1))) ++ parent = dget_parent(dentry); ++ h_parent = au_h_dptr(parent, bindex); ++ br = au_sbr(dentry->d_sb, bindex); ++ if (wh) ++ h_dentry = au_whtmp_lkup(h_parent, br, &dentry->d_name); ++ else ++ h_dentry = au_sio_lkup_one(&dentry->d_name, h_parent); ++ err = PTR_ERR(h_dentry); ++ if (IS_ERR(h_dentry)) + goto out; -+ err = kstrtol(name->name + sizeof(DbgaufsXi_PREFIX) - 1, 10, &l); -+ if (unlikely(err)) ++ 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; ++ } + -+ sbinfo = inode->i_private; -+ sb = sbinfo->si_sb; -+ si_noflush_read_lock(sb); -+ if (l <= au_sbbot(sb)) { -+ xf = au_sbr(sb, (aufs_bindex_t)l)->br_xino.xi_file; -+ err = dbgaufs_xi_open(xf, file, /*do_fcnt*/1); -+ } else -+ err = -ENOENT; -+ si_read_unlock(sb); ++ err = 0; ++ if (bindex < au_dbtop(dentry)) ++ au_set_dbtop(dentry, bindex); ++ if (au_dbbot(dentry) < bindex) ++ au_set_dbbot(dentry, bindex); ++ au_set_h_dptr(dentry, bindex, h_dentry); + +out: ++ dput(parent); + return err; +} + -+static const struct file_operations dbgaufs_xino_fop = { -+ .owner = THIS_MODULE, -+ .open = dbgaufs_xino_open, -+ .release = dbgaufs_xi_release, -+ .read = dbgaufs_xi_read ++/* ---------------------------------------------------------------------- */ ++ ++/* 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; +}; + -+void dbgaufs_brs_del(struct super_block *sb, aufs_bindex_t bindex) ++static void au_iattr_save(struct au_iattr *ia, struct inode *h_inode) +{ -+ aufs_bindex_t bbot; -+ struct au_branch *br; -+ struct au_xino_file *xi; -+ -+ if (!au_sbi(sb)->si_dbgaufs) -+ return; ++ 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 = h_inode->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); ++} + -+ bbot = au_sbbot(sb); -+ for (; bindex <= bbot; bindex++) { -+ br = au_sbr(sb, bindex); -+ xi = &br->br_xino; -+ /* debugfs acquires the parent i_mutex */ -+ lockdep_off(); -+ debugfs_remove(xi->xi_dbgaufs); -+ lockdep_on(); -+ xi->xi_dbgaufs = NULL; -+ } ++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) ++ || ia->i_version != h_inode->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 dbgaufs_brs_add(struct super_block *sb, aufs_bindex_t bindex) ++static int au_h_verify_dentry(struct dentry *h_dentry, struct dentry *h_parent, ++ struct au_branch *br) +{ -+ struct au_sbinfo *sbinfo; -+ struct dentry *parent; -+ struct au_branch *br; -+ struct au_xino_file *xi; -+ aufs_bindex_t bbot; -+ char name[sizeof(DbgaufsXi_PREFIX) + 5]; /* "xi" bindex NULL */ -+ -+ sbinfo = au_sbi(sb); -+ parent = sbinfo->si_dbgaufs; -+ if (!parent) -+ return; ++ int err; ++ struct au_iattr ia; ++ struct inode *h_inode; ++ struct dentry *h_d; ++ struct super_block *h_sb; + -+ bbot = au_sbbot(sb); -+ for (; bindex <= bbot; bindex++) { -+ snprintf(name, sizeof(name), DbgaufsXi_PREFIX "%d", bindex); -+ br = au_sbr(sb, bindex); -+ xi = &br->br_xino; -+ AuDebugOn(xi->xi_dbgaufs); -+ /* debugfs acquires the parent i_mutex */ -+ lockdep_off(); -+ xi->xi_dbgaufs = debugfs_create_file(name, dbgaufs_mode, parent, -+ sbinfo, &dbgaufs_xino_fop); -+ lockdep_on(); -+ /* ignore an error */ -+ if (unlikely(!xi->xi_dbgaufs)) -+ AuWarn1("failed %s under debugfs\n", name); -+ } -+} ++ err = 0; ++ memset(&ia, -1, sizeof(ia)); ++ h_sb = h_dentry->d_sb; ++ h_inode = NULL; ++ if (d_is_positive(h_dentry)) { ++ h_inode = d_inode(h_dentry); ++ au_iattr_save(&ia, h_inode); ++ } else if (au_test_nfs(h_sb) || au_test_fuse(h_sb)) ++ /* nfs d_revalidate may return 0 for negative dentry */ ++ /* fuse d_revalidate always return 0 for negative dentry */ ++ goto out; + -+/* ---------------------------------------------------------------------- */ ++ /* main purpose is namei.c:cached_lookup() and d_revalidate */ ++ h_d = vfsub_lkup_one(&h_dentry->d_name, h_parent); ++ err = PTR_ERR(h_d); ++ if (IS_ERR(h_d)) ++ goto out; + -+#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; ++ 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); + -+ sbinfo = inode->i_private; -+ sb = sbinfo->si_sb; -+ si_noflush_read_lock(sb); -+ err = dbgaufs_xi_open(sbinfo->si_xigen, file, /*do_fcnt*/0); -+ si_read_unlock(sb); ++out: ++ AuTraceErr(err); + return err; +} + -+static const struct file_operations dbgaufs_xigen_fop = { -+ .owner = THIS_MODULE, -+ .open = dbgaufs_xigen_open, -+ .release = dbgaufs_xi_release, -+ .read = dbgaufs_xi_read -+}; -+ -+static int dbgaufs_xigen_init(struct au_sbinfo *sbinfo) ++int au_h_verify(struct dentry *h_dentry, unsigned int udba, struct inode *h_dir, ++ struct dentry *h_parent, struct au_branch *br) +{ + int err; + -+ /* -+ * This function is a dynamic '__init' function actually, -+ * so the tiny check for si_rwsem is unnecessary. -+ */ -+ /* AuRwMustWriteLock(&sbinfo->si_rwsem); */ -+ -+ err = -EIO; -+ sbinfo->si_dbgaufs_xigen = debugfs_create_file -+ ("xigen", dbgaufs_mode, sbinfo->si_dbgaufs, sbinfo, -+ &dbgaufs_xigen_fop); -+ if (sbinfo->si_dbgaufs_xigen) -+ err = 0; ++ 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; +} -+#else -+static int dbgaufs_xigen_init(struct au_sbinfo *sbinfo) -+{ -+ return 0; -+} -+#endif /* CONFIG_AUFS_EXPORT */ + +/* ---------------------------------------------------------------------- */ + -+void dbgaufs_si_fin(struct au_sbinfo *sbinfo) ++static int au_do_refresh_hdentry(struct dentry *dentry, struct dentry *parent) +{ -+ /* -+ * This function is a dynamic '__fin' function actually, -+ * so the tiny check for si_rwsem is unnecessary. -+ */ -+ /* AuRwMustWriteLock(&sbinfo->si_rwsem); */ ++ 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; + -+ debugfs_remove_recursive(sbinfo->si_dbgaufs); -+ sbinfo->si_dbgaufs = NULL; -+ kobject_put(&sbinfo->si_kobj); -+} ++ DiMustWriteLock(dentry); + -+int dbgaufs_si_init(struct au_sbinfo *sbinfo) -+{ -+ int err; -+ char name[SysaufsSiNameLen]; ++ 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; + -+ /* -+ * This function is a dynamic '__init' function actually, -+ * so the tiny check for si_rwsem is unnecessary. -+ */ -+ /* AuRwMustWriteLock(&sbinfo->si_rwsem); */ ++ new_bindex = au_br_index(sb, p->hd_id); ++ if (new_bindex == bindex) ++ continue; + -+ err = -ENOENT; -+ if (!dbgaufs) { -+ AuErr1("/debug/aufs is uninitialized\n"); -+ goto out; ++ if (dinfo->di_bwh == bindex) ++ bwh = new_bindex; ++ if (dinfo->di_bdiropq == bindex) ++ bdiropq = new_bindex; ++ if (new_bindex < 0) { ++ au_hdput(p); ++ p->hd_dentry = NULL; ++ continue; ++ } ++ ++ /* swap two lower dentries, and loop again */ ++ q = au_hdentry(dinfo, new_bindex); ++ tmp = *q; ++ *q = *p; ++ *p = tmp; ++ if (tmp.hd_dentry) { ++ bindex--; ++ p--; ++ } + } + -+ err = -EIO; -+ sysaufs_name(sbinfo, name); -+ sbinfo->si_dbgaufs = debugfs_create_dir(name, dbgaufs); -+ if (unlikely(!sbinfo->si_dbgaufs)) -+ goto out; -+ kobject_get(&sbinfo->si_kobj); ++ dinfo->di_bwh = -1; ++ if (bwh >= 0 && bwh <= au_sbbot(sb) && au_sbr_whable(sb, bwh)) ++ dinfo->di_bwh = bwh; + -+ 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; ++ dinfo->di_bdiropq = -1; ++ if (bdiropq >= 0 ++ && bdiropq <= au_sbbot(sb) ++ && au_sbr_whable(sb, bdiropq)) ++ dinfo->di_bdiropq = bdiropq; + -+ 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; ++ 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; ++ } + -+ err = dbgaufs_xigen_init(sbinfo); -+ if (!err) -+ goto out; /* success */ ++ 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; ++ } ++ } + -+out_dir: -+ dbgaufs_si_fin(sbinfo); -+out: + return err; +} + -+/* ---------------------------------------------------------------------- */ -+ -+void dbgaufs_fin(void) ++static void au_do_hide(struct dentry *dentry) +{ -+ debugfs_remove(dbgaufs); ++ struct inode *inode; ++ ++ if (d_really_is_positive(dentry)) { ++ inode = d_inode(dentry); ++ if (!d_is_dir(dentry)) { ++ if (inode->i_nlink && !d_unhashed(dentry)) ++ drop_nlink(inode); ++ } else { ++ clear_nlink(inode); ++ /* stop next lookup */ ++ inode->i_flags |= S_DEAD; ++ } ++ smp_mb(); /* necessary? */ ++ } ++ d_drop(dentry); +} + -+int __init dbgaufs_init(void) ++static int au_hide_children(struct dentry *parent) +{ -+ int err; -+ -+ 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 2016-10-09 16:55:36.486034798 +0200 -@@ -0,0 +1,48 @@ -+/* -+ * Copyright (C) 2005-2016 Junjiro R. Okajima -+ * -+ * This program, aufs is free software; you can redistribute it and/or modify -+ * it under the terms of the GNU General Public License as published by -+ * the Free Software Foundation; either version 2 of the License, or -+ * (at your option) any later version. -+ * -+ * This program is distributed in the hope that it will be useful, -+ * but WITHOUT ANY WARRANTY; without even the implied warranty of -+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the -+ * GNU General Public License for more details. -+ * -+ * You should have received a copy of the GNU General Public License -+ * along with this program. If not, see . -+ */ ++ int err, i, j, ndentry; ++ struct au_dcsub_pages dpages; ++ struct au_dpage *dpage; ++ struct dentry *dentry; + -+/* -+ * debugfs interface -+ */ ++ 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; + -+#ifndef __DBGAUFS_H__ -+#define __DBGAUFS_H__ ++ /* 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); ++ } ++ } + -+#ifdef __KERNEL__ ++out_dpages: ++ au_dpages_free(&dpages); ++out: ++ return err; ++} + -+struct super_block; -+struct au_sbinfo; ++static void au_hide(struct dentry *dentry) ++{ ++ int err; + -+#ifdef CONFIG_DEBUG_FS -+/* dbgaufs.c */ -+void dbgaufs_brs_del(struct super_block *sb, aufs_bindex_t bindex); -+void dbgaufs_brs_add(struct super_block *sb, aufs_bindex_t bindex); -+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_brs_del, struct super_block *sb, aufs_bindex_t bindex) -+AuStubVoid(dbgaufs_brs_add, struct super_block *sb, aufs_bindex_t bindex) -+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 */ ++ 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); ++} + -+#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 2016-10-09 16:55:38.886097714 +0200 -@@ -0,0 +1,225 @@ +/* -+ * Copyright (C) 2005-2016 Junjiro R. Okajima -+ * -+ * This program, aufs is free software; you can redistribute it and/or modify -+ * it under the terms of the GNU General Public License as published by -+ * the Free Software Foundation; either version 2 of the License, or -+ * (at your option) any later version. ++ * By adding a dirty branch, a cached dentry may be affected in various ways. + * -+ * 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. ++ * a dirty branch is added ++ * - on the top of layers ++ * - in the middle of layers ++ * - to the bottom of layers + * -+ * You should have received a copy of the GNU General Public License -+ * along with this program. If not, see . -+ */ -+ -+/* -+ * sub-routines for dentry cache ++ * 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 + */ -+ -+#include "aufs.h" -+ -+static void au_dpage_free(struct au_dpage *dpage) -+{ -+ int i; -+ struct dentry **p; -+ -+ p = dpage->dentries; -+ for (i = 0; i < dpage->ndentry; i++) -+ dput(*p++); -+ au_delayed_free_page((unsigned long)dpage->dentries); -+} -+ -+int au_dpages_init(struct au_dcsub_pages *dpages, gfp_t gfp) ++static int au_refresh_by_dinfo(struct dentry *dentry, struct au_dinfo *dinfo, ++ struct au_dinfo *tmp) +{ + int err; -+ void *p; ++ aufs_bindex_t bindex, bbot; ++ struct { ++ struct dentry *dentry; ++ struct inode *inode; ++ mode_t mode; ++ } orig_h, tmp_h = { ++ .dentry = NULL ++ }; ++ struct au_hdentry *hd; ++ struct inode *inode, *h_inode; ++ struct dentry *h_dentry; + -+ err = -ENOMEM; -+ dpages->dpages = kmalloc(sizeof(*dpages->dpages), gfp); -+ if (unlikely(!dpages->dpages)) -+ goto out; ++ 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; ++ } ++ } + -+ p = (void *)__get_free_page(gfp); -+ if (unlikely(!p)) -+ goto out_dpages; ++ inode = NULL; ++ if (d_really_is_positive(dentry)) ++ inode = d_inode(dentry); ++ if (!orig_h.inode) { ++ AuDbg("nagative originally\n"); ++ if (inode) { ++ au_hide(dentry); ++ goto out; ++ } ++ AuDebugOn(inode); ++ AuDebugOn(dinfo->di_btop != dinfo->di_bbot); ++ AuDebugOn(dinfo->di_bdiropq != -1); + -+ dpages->dpages[0].ndentry = 0; -+ dpages->dpages[0].dentries = p; -+ dpages->ndpage = 1; -+ return 0; /* success */ ++ if (!tmp_h.inode) { ++ AuDbg("negative --> negative\n"); ++ /* should have only one negative lower */ ++ if (tmp->di_btop >= 0 ++ && tmp->di_btop < dinfo->di_btop) { ++ AuDebugOn(tmp->di_btop != tmp->di_bbot); ++ AuDebugOn(dinfo->di_btop != dinfo->di_bbot); ++ au_set_h_dptr(dentry, dinfo->di_btop, NULL); ++ au_di_cp(dinfo, tmp); ++ hd = au_hdentry(tmp, tmp->di_btop); ++ au_set_h_dptr(dentry, tmp->di_btop, ++ dget(hd->hd_dentry)); ++ } ++ au_dbg_verify_dinode(dentry); ++ } else { ++ AuDbg("negative --> positive\n"); ++ /* ++ * similar to the behaviour of creating with bypassing ++ * aufs. ++ * unhash it in order to force an error in the ++ * succeeding create operation. ++ * we should not set S_DEAD here. ++ */ ++ d_drop(dentry); ++ /* au_di_swap(tmp, dinfo); */ ++ au_dbg_verify_dinode(dentry); ++ } ++ } else { ++ AuDbg("positive originally\n"); ++ /* inode may be NULL */ ++ AuDebugOn(inode && (inode->i_mode & S_IFMT) != orig_h.mode); ++ if (!tmp_h.inode) { ++ AuDbg("positive --> negative\n"); ++ /* or bypassing aufs */ ++ au_hide(dentry); ++ if (tmp->di_bwh >= 0 && tmp->di_bwh <= dinfo->di_btop) ++ dinfo->di_bwh = tmp->di_bwh; ++ if (inode) ++ err = au_refresh_hinode_self(inode); ++ au_dbg_verify_dinode(dentry); ++ } else if (orig_h.mode == tmp_h.mode) { ++ AuDbg("positive --> positive, same type\n"); ++ if (!S_ISDIR(orig_h.mode) ++ && dinfo->di_btop > tmp->di_btop) { ++ /* ++ * similar to the behaviour of removing and ++ * creating. ++ */ ++ au_hide(dentry); ++ if (inode) ++ err = au_refresh_hinode_self(inode); ++ au_dbg_verify_dinode(dentry); ++ } else { ++ /* fill empty slots */ ++ if (dinfo->di_btop > tmp->di_btop) ++ dinfo->di_btop = tmp->di_btop; ++ if (dinfo->di_bbot < tmp->di_bbot) ++ dinfo->di_bbot = tmp->di_bbot; ++ dinfo->di_bwh = tmp->di_bwh; ++ dinfo->di_bdiropq = tmp->di_bdiropq; ++ bbot = dinfo->di_bbot; ++ bindex = tmp->di_btop; ++ hd = au_hdentry(tmp, bindex); ++ for (; bindex <= bbot; bindex++, hd++) { ++ if (au_h_dptr(dentry, bindex)) ++ continue; ++ h_dentry = hd->hd_dentry; ++ if (!h_dentry) ++ continue; ++ AuDebugOn(d_is_negative(h_dentry)); ++ h_inode = d_inode(h_dentry); ++ AuDebugOn(orig_h.mode ++ != (h_inode->i_mode ++ & S_IFMT)); ++ au_set_h_dptr(dentry, bindex, ++ dget(h_dentry)); ++ } ++ if (inode) ++ err = au_refresh_hinode(inode, dentry); ++ au_dbg_verify_dinode(dentry); ++ } ++ } else { ++ AuDbg("positive --> positive, different type\n"); ++ /* similar to the behaviour of removing and creating */ ++ au_hide(dentry); ++ if (inode) ++ err = au_refresh_hinode_self(inode); ++ au_dbg_verify_dinode(dentry); ++ } ++ } + -+out_dpages: -+ au_delayed_kfree(dpages->dpages); +out: + return err; +} + -+void au_dpages_free(struct au_dcsub_pages *dpages) ++void au_refresh_dop(struct dentry *dentry, int force_reval) +{ -+ int i; -+ struct au_dpage *p; ++ 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; + -+ p = dpages->dpages; -+ for (i = 0; i < dpages->ndpage; i++) -+ au_dpage_free(p++); -+ au_delayed_kfree(dpages->dpages); ++ BUILD_BUG_ON(sizeof(mask) != sizeof(dentry->d_flags)); ++ ++ if (dentry->d_op == dop) ++ return; ++ ++ AuDbg("%pd\n", dentry); ++ spin_lock(&dentry->d_lock); ++ if (dop == &aufs_dop) ++ dentry->d_flags |= mask; ++ else ++ dentry->d_flags &= ~mask; ++ dentry->d_op = dop; ++ spin_unlock(&dentry->d_lock); +} + -+static int au_dpages_append(struct au_dcsub_pages *dpages, -+ struct dentry *dentry, gfp_t gfp) ++int au_refresh_dentry(struct dentry *dentry, struct dentry *parent) +{ -+ int err, sz; -+ struct au_dpage *dpage; -+ void *p; ++ int err, ebrange, nbr; ++ unsigned int sigen; ++ struct au_dinfo *dinfo, *tmp; ++ struct super_block *sb; ++ struct inode *inode; + -+ 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; ++ DiMustWriteLock(dentry); ++ AuDebugOn(IS_ROOT(dentry)); ++ AuDebugOn(d_really_is_negative(parent)); + -+ dpages->dpages = p; -+ dpage = dpages->dpages + dpages->ndpage; -+ p = (void *)__get_free_page(gfp); -+ if (unlikely(!p)) -+ goto out; ++ sb = dentry->d_sb; ++ sigen = au_sigen(sb); ++ err = au_digen_test(parent, sigen); ++ if (unlikely(err)) ++ goto out; + -+ dpage->ndentry = 0; -+ dpage->dentries = p; -+ dpages->ndpage++; ++ 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; + } + -+ AuDebugOn(au_dcount(dentry) <= 0); -+ dpage->dentries[dpage->ndentry++] = dget_dlock(dentry); -+ return 0; /* success */ ++ /* 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; +} + -+/* 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 *), -+ void (*finish)(void *)); -+ -+struct ac_dpages_arg { -+ int err; -+ struct au_dcsub_pages *dpages; -+ struct super_block *sb; -+ au_dpages_test test; -+ void *arg; -+}; -+ -+static enum d_walk_ret au_call_dpages_append(void *_arg, struct dentry *dentry) ++static int au_do_h_d_reval(struct dentry *h_dentry, unsigned int flags, ++ struct dentry *dentry, aufs_bindex_t bindex) +{ -+ enum d_walk_ret ret; -+ struct ac_dpages_arg *arg = _arg; -+ -+ ret = D_WALK_CONTINUE; -+ if (dentry->d_sb == arg->sb -+ && !IS_ROOT(dentry) -+ && au_dcount(dentry) > 0 -+ && au_di(dentry) -+ && (!arg->test || arg->test(dentry, arg->arg))) { -+ arg->err = au_dpages_append(arg->dpages, dentry, GFP_ATOMIC); -+ if (unlikely(arg->err)) -+ ret = D_WALK_QUIT; -+ } ++ int err, valid; + -+ return ret; -+} ++ err = 0; ++ if (!(h_dentry->d_flags & DCACHE_OP_REVALIDATE)) ++ goto out; + -+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 -+ }; ++ 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); + -+ d_walk(root, &args, au_call_dpages_append, NULL); ++ if (unlikely(valid < 0)) ++ err = valid; ++ else if (!valid) ++ err = -EINVAL; + -+ return args.err; ++out: ++ AuTraceErr(err); ++ return err; +} + -+int au_dcsub_pages_rev(struct au_dcsub_pages *dpages, struct dentry *dentry, -+ int do_include, au_dpages_test test, void *arg) ++/* todo: remove this */ ++static int h_d_revalidate(struct dentry *dentry, struct inode *inode, ++ unsigned int flags, int do_udba, int dirren) +{ + int err; ++ umode_t mode, h_mode; ++ aufs_bindex_t bindex, btail, btop, ibs, ibe; ++ unsigned char plus, unhashed, is_root, h_plus, h_nfs, tmpfile; ++ struct inode *h_inode, *h_cached_inode; ++ struct dentry *h_dentry; ++ struct qstr *name, *h_name; + + err = 0; -+ 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; ++ 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; + + /* -+ * RCU for vfsmount is unnecessary since this is a traverse in a single -+ * mount ++ * 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. + */ -+ 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 (do_udba && inode) { ++ mode = (inode->i_mode & S_IFMT); ++ plus = (inode->i_nlink > 0); ++ ibs = au_ibtop(inode); ++ ibe = au_ibbot(inode); + } + -+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; -+} ++ 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; + -+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); -+} ++ 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; + -+int au_test_subdir(struct dentry *d1, struct dentry *d2) -+{ -+ struct path path[2] = { -+ { -+ .dentry = d1 -+ }, -+ { -+ .dentry = d2 ++ 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; + } -+ }; -+ -+ 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 2016-10-09 16:55:36.486034798 +0200 -@@ -0,0 +1,136 @@ -+/* -+ * Copyright (C) 2005-2016 Junjiro R. Okajima -+ * -+ * This program, aufs is free software; you can redistribute it and/or modify -+ * it under the terms of the GNU General Public License as published by -+ * the Free Software Foundation; either version 2 of the License, or -+ * (at your option) any later version. -+ * -+ * This program is distributed in the hope that it will be useful, -+ * but WITHOUT ANY WARRANTY; without even the implied warranty of -+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the -+ * GNU General Public License for more details. -+ * -+ * You should have received a copy of the GNU General Public License -+ * along with this program. If not, see . -+ */ ++ spin_unlock(&h_dentry->d_lock); + -+/* -+ * sub-routines for dentry cache -+ */ ++ err = au_do_h_d_reval(h_dentry, flags, dentry, bindex); ++ if (unlikely(err)) ++ /* do not goto err, to keep the errno */ ++ break; + -+#ifndef __AUFS_DCSUB_H__ -+#define __AUFS_DCSUB_H__ ++ /* todo: plink too? */ ++ if (!do_udba) ++ continue; + -+#ifdef __KERNEL__ ++ /* UDBA tests */ ++ if (unlikely(!!inode != d_is_positive(h_dentry))) ++ goto err; + -+#include -+#include ++ 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); + -+struct au_dpage { -+ int ndentry; -+ struct dentry **dentries; -+}; ++ 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; + -+struct au_dcsub_pages { -+ int ndpage; -+ struct au_dpage *dpages; -+}; ++err: ++ err = -EINVAL; ++ break; ++ } + -+/* ---------------------------------------------------------------------- */ ++ AuTraceErr(err); ++ return err; ++} + -+/* dcsub.c */ -+int au_dpages_init(struct au_dcsub_pages *dpages, gfp_t gfp); -+void au_dpages_free(struct au_dcsub_pages *dpages); -+typedef int (*au_dpages_test)(struct dentry *dentry, void *arg); -+int au_dcsub_pages(struct au_dcsub_pages *dpages, struct dentry *root, -+ au_dpages_test test, void *arg); -+int au_dcsub_pages_rev(struct au_dcsub_pages *dpages, struct dentry *dentry, -+ int do_include, au_dpages_test test, void *arg); -+int au_dcsub_pages_rev_aufs(struct au_dcsub_pages *dpages, -+ struct dentry *dentry, int do_include); -+int au_test_subdir(struct dentry *d1, struct dentry *d2); ++/* todo: consolidate with do_refresh() and au_reval_for_attr() */ ++static int simple_reval_dpath(struct dentry *dentry, unsigned int sigen) ++{ ++ int err; ++ struct dentry *parent; + -+/* ---------------------------------------------------------------------- */ ++ if (!au_digen_test(dentry, sigen)) ++ return 0; + -+/* -+ * todo: in linux-3.13, several similar (but faster) helpers are added to -+ * include/linux/dcache.h. Try them (in the future). -+ */ ++ 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; ++} + -+static inline int au_d_hashed_positive(struct dentry *d) ++int au_reval_dpath(struct dentry *dentry, unsigned int sigen) +{ + int err; -+ struct inode *inode = d_inode(d); ++ struct dentry *d, *parent; + ++ if (!au_ftest_si(au_sbi(dentry->d_sb), FAILED_REFRESH_DIR)) ++ return simple_reval_dpath(dentry, sigen); ++ ++ /* slow loop, keep it simple and stupid */ ++ /* cf: au_cpup_dirs() */ + err = 0; -+ if (unlikely(d_unhashed(d) -+ || d_is_negative(d) -+ || !inode->i_nlink)) -+ err = -ENOENT; ++ parent = NULL; ++ while (au_digen_test(dentry, sigen)) { ++ d = dentry; ++ while (1) { ++ dput(parent); ++ parent = dget_parent(d); ++ if (!au_digen_test(parent, sigen)) ++ break; ++ d = parent; ++ } ++ ++ if (d != dentry) ++ di_write_lock_child2(d); ++ ++ /* someone might update our dentry while we were sleeping */ ++ if (au_digen_test(d, sigen)) { ++ /* ++ * todo: consolidate with simple_reval_dpath(), ++ * do_refresh() and au_reval_for_attr(). ++ */ ++ di_read_lock_parent(parent, AuLock_IR); ++ err = au_refresh_dentry(d, parent); ++ di_read_unlock(parent, AuLock_IR); ++ } ++ ++ if (d != dentry) ++ di_write_unlock(d); ++ dput(parent); ++ if (unlikely(err)) ++ break; ++ } ++ + return err; +} + -+static inline int au_d_linkable(struct dentry *d) ++/* ++ * if valid returns 1, otherwise 0. ++ */ ++static int aufs_d_revalidate(struct dentry *dentry, unsigned int flags) +{ -+ int err; -+ struct inode *inode = d_inode(d); ++ int valid, err; ++ unsigned int sigen; ++ unsigned char do_udba, dirren; ++ struct super_block *sb; ++ struct inode *inode; ++ ++ /* todo: support rcu-walk? */ ++ if (flags & LOOKUP_RCU) ++ return -ECHILD; ++ ++ valid = 0; ++ if (unlikely(!au_di(dentry))) ++ goto out; ++ ++ valid = 1; ++ sb = dentry->d_sb; ++ /* ++ * todo: very ugly ++ * i_mutex of parent dir may be held, ++ * but we should not return 'invalid' due to busy. ++ */ ++ err = aufs_read_lock(dentry, AuLock_FLUSH | AuLock_DW | AuLock_NOPLM); ++ if (unlikely(err)) { ++ valid = err; ++ AuTraceErr(err); ++ goto out; ++ } ++ inode = NULL; ++ if (d_really_is_positive(dentry)) ++ inode = d_inode(dentry); ++ if (unlikely(inode && au_is_bad_inode(inode))) { ++ err = -EINVAL; ++ AuTraceErr(err); ++ goto out_dgrade; ++ } ++ if (unlikely(au_dbrange_test(dentry))) { ++ err = -EINVAL; ++ AuTraceErr(err); ++ goto out_dgrade; ++ } ++ ++ sigen = au_sigen(sb); ++ if (au_digen_test(dentry, sigen)) { ++ AuDebugOn(IS_ROOT(dentry)); ++ err = au_reval_dpath(dentry, sigen); ++ if (unlikely(err)) { ++ AuTraceErr(err); ++ goto out_dgrade; ++ } ++ } ++ di_downgrade_lock(dentry, AuLock_IR); + -+ err = au_d_hashed_positive(d); -+ if (err -+ && d_is_positive(d) -+ && (inode->i_state & I_LINKABLE)) -+ err = 0; -+ return err; -+} ++ 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; ++ } + -+static inline int au_d_alive(struct dentry *d) -+{ -+ int err; -+ struct inode *inode; ++ 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; + -+ 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; ++ if (btop >= 0) { ++ h_inode = au_h_iptr(inode, btop); ++ if (h_inode && au_test_higen(inode, h_inode)) { ++ AuTraceErr(err); ++ goto out_inval; ++ } ++ } + } -+ return err; -+} + -+static inline int au_alive_dir(struct dentry *d) -+{ -+ int err; ++ 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 = au_d_alive(d); -+ if (unlikely(err || IS_DEADDIR(d_inode(d)))) -+ err = -ENOENT; -+ return err; ++out_dgrade: ++ di_downgrade_lock(dentry, AuLock_IR); ++out_inval: ++ aufs_read_unlock(dentry, AuLock_IR); ++ AuTraceErr(err); ++ valid = !err; ++out: ++ if (!valid) { ++ AuDbg("%pd invalid, %d\n", dentry, valid); ++ d_drop(dentry); ++ } ++ return valid; +} + -+static inline int au_qstreq(struct qstr *a, struct qstr *b) ++static void aufs_d_release(struct dentry *dentry) +{ -+ return a->len == b->len -+ && !memcmp(a->name, b->name, a->len); ++ if (au_di(dentry)) { ++ au_di_fin(dentry); ++ au_hn_di_reinit(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) -+{ -+ return (int)d_count(d); -+} ++const struct dentry_operations aufs_dop = { ++ .d_revalidate = aufs_d_revalidate, ++ .d_weak_revalidate = aufs_d_revalidate, ++ .d_release = aufs_d_release ++}; + -+#endif /* __KERNEL__ */ -+#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 2016-10-09 16:55:36.486034798 +0200 -@@ -0,0 +1,440 @@ ++/* aufs_dop without d_revalidate */ ++const struct dentry_operations aufs_dop_noreval = { ++ .d_release = aufs_d_release ++}; +diff -urNp -x '*.orig' linux-4.9/fs/aufs/dentry.h linux-4.9/fs/aufs/dentry.h +--- linux-4.9/fs/aufs/dentry.h 1970-01-01 01:00:00.000000000 +0100 ++++ linux-4.9/fs/aufs/dentry.h 2021-02-24 16:15:09.524906971 +0100 +@@ -0,0 +1,266 @@ +/* -+ * Copyright (C) 2005-2016 Junjiro R. Okajima ++ * Copyright (C) 2005-2018 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by @@ -7023,434 +8484,260 @@ diff -urN /usr/share/empty/fs/aufs/debug.c linux/fs/aufs/debug.c + */ + +/* -+ * debug print functions ++ * lookup and dentry operations + */ + -+#include "aufs.h" -+ -+/* Returns 0, or -errno. arg is in kp->arg. */ -+static int param_atomic_t_set(const char *val, const struct kernel_param *kp) -+{ -+ int err, n; -+ -+ err = kstrtoint(val, 0, &n); -+ if (!err) { -+ if (n > 0) -+ au_debug_on(); -+ else -+ au_debug_off(); -+ } -+ return err; -+} ++#ifndef __AUFS_DENTRY_H__ ++#define __AUFS_DENTRY_H__ + -+/* Returns length written or -errno. Buffer is 4k (ie. be short!) */ -+static int param_atomic_t_get(char *buffer, const struct kernel_param *kp) -+{ -+ atomic_t *a; ++#ifdef __KERNEL__ + -+ a = kp->arg; -+ return sprintf(buffer, "%d", atomic_read(a)); -+} ++#include ++#include "dirren.h" ++#include "rwsem.h" + -+static struct kernel_param_ops param_ops_atomic_t = { -+ .set = param_atomic_t_set, -+ .get = param_atomic_t_get -+ /* void (*free)(void *arg) */ ++struct au_hdentry { ++ struct dentry *hd_dentry; ++ aufs_bindex_t hd_id; +}; + -+atomic_t aufs_debug = ATOMIC_INIT(0); -+MODULE_PARM_DESC(debug, "debug print"); -+module_param_named(debug, aufs_debug, atomic_t, S_IRUGO | S_IWUSR | S_IWGRP); ++struct au_dinfo { ++ atomic_t di_generation; + -+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) ++ 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; ++} ____cacheline_aligned_in_smp; + +/* ---------------------------------------------------------------------- */ + -+void au_dpri_whlist(struct au_nhash *whlist) -+{ -+ unsigned long ul, n; -+ struct hlist_head *head; -+ struct au_vdir_wh *pos; -+ -+ n = whlist->nh_num; -+ head = whlist->nh_head; -+ for (ul = 0; ul < n; ul++) { -+ hlist_for_each_entry(pos, head, wh_hash) -+ dpri("b%d, %.*s, %d\n", -+ pos->wh_bindex, -+ pos->wh_str.len, pos->wh_str.name, -+ pos->wh_str.len); -+ head++; -+ } -+} -+ -+void au_dpri_vdir(struct au_vdir *vdir) -+{ -+ unsigned long ul; -+ union au_vdir_deblk_p p; -+ unsigned char *o; -+ -+ if (!vdir || IS_ERR(vdir)) { -+ dpri("err %ld\n", PTR_ERR(vdir)); -+ return; -+ } -+ -+ dpri("deblk %u, nblk %lu, deblk %p, last{%lu, %p}, ver %lu\n", -+ vdir->vd_deblk_sz, vdir->vd_nblk, vdir->vd_deblk, -+ vdir->vd_last.ul, vdir->vd_last.p.deblk, vdir->vd_version); -+ for (ul = 0; ul < vdir->vd_nblk; ul++) { -+ p.deblk = vdir->vd_deblk[ul]; -+ o = p.deblk; -+ dpri("[%lu]: %p\n", ul, o); -+ } -+} -+ -+static int do_pri_inode(aufs_bindex_t bindex, struct inode *inode, int hn, -+ struct dentry *wh) -+{ -+ char *n = NULL; -+ int l = 0; -+ -+ if (!inode || IS_ERR(inode)) { -+ dpri("i%d: err %ld\n", bindex, PTR_ERR(inode)); -+ return -1; -+ } -+ -+ /* the type of i_blocks depends upon CONFIG_LBDAF */ -+ BUILD_BUG_ON(sizeof(inode->i_blocks) != sizeof(unsigned long) -+ && sizeof(inode->i_blocks) != sizeof(u64)); -+ if (wh) { -+ n = (void *)wh->d_name.name; -+ l = wh->d_name.len; -+ } -+ -+ dpri("i%d: %p, i%lu, %s, cnt %d, nl %u, 0%o, sz %llu, blk %llu," -+ " hn %d, ct %lld, np %lu, st 0x%lx, f 0x%x, v %llu, g %x%s%.*s\n", -+ bindex, inode, -+ inode->i_ino, inode->i_sb ? au_sbtype(inode->i_sb) : "??", -+ atomic_read(&inode->i_count), inode->i_nlink, inode->i_mode, -+ i_size_read(inode), (unsigned long long)inode->i_blocks, -+ hn, (long long)timespec_to_ns(&inode->i_ctime) & 0x0ffff, -+ inode->i_mapping ? inode->i_mapping->nrpages : 0, -+ inode->i_state, inode->i_flags, inode->i_version, -+ inode->i_generation, -+ l ? ", wh " : "", l, n); -+ return 0; -+} -+ -+void au_dpri_inode(struct inode *inode) -+{ -+ struct au_iinfo *iinfo; -+ struct au_hinode *hi; -+ aufs_bindex_t bindex; -+ int err, hn; -+ -+ err = do_pri_inode(-1, inode, -1, NULL); -+ if (err || !au_test_aufs(inode->i_sb) || au_is_bad_inode(inode)) -+ return; ++/* 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) + -+ 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); -+ } -+} ++#ifndef CONFIG_AUFS_DIRREN ++#undef AuLkup_DIRREN ++#define AuLkup_DIRREN 0 ++#endif + -+void au_dpri_dalias(struct inode *inode) -+{ -+ struct dentry *d; ++struct au_do_lookup_args { ++ unsigned int flags; ++ mode_t type; ++ struct qstr whname, *name; ++ struct au_dr_lookup dirren; ++}; + -+ spin_lock(&inode->i_lock); -+ hlist_for_each_entry(d, &inode->i_dentry, d_u.d_alias) -+ au_dpri_dentry(d); -+ spin_unlock(&inode->i_lock); -+} ++/* ---------------------------------------------------------------------- */ + -+static int do_pri_dentry(aufs_bindex_t bindex, struct dentry *dentry) -+{ -+ struct dentry *wh = NULL; -+ int hn; -+ struct inode *inode; -+ struct au_iinfo *iinfo; -+ struct au_hinode *hi; ++/* dentry.c */ ++extern const struct dentry_operations aufs_dop, aufs_dop_noreval; ++struct au_branch; ++struct dentry *au_sio_lkup_one(struct qstr *name, struct dentry *parent); ++int au_h_verify(struct dentry *h_dentry, unsigned int udba, struct inode *h_dir, ++ struct dentry *h_parent, struct au_branch *br); + -+ if (!dentry || IS_ERR(dentry)) { -+ dpri("d%d: err %ld\n", bindex, PTR_ERR(dentry)); -+ return -1; -+ } -+ /* do not call dget_parent() here */ -+ /* note: access d_xxx without d_lock */ -+ dpri("d%d: %p, %pd2?, %s, cnt %d, flags 0x%x, %shashed\n", -+ bindex, dentry, dentry, -+ dentry->d_sb ? au_sbtype(dentry->d_sb) : "??", -+ au_dcount(dentry), dentry->d_flags, -+ d_unhashed(dentry) ? "un" : ""); -+ hn = -1; -+ inode = NULL; -+ if (d_is_positive(dentry)) -+ inode = d_inode(dentry); -+ if (inode -+ && au_test_aufs(dentry->d_sb) -+ && bindex >= 0 -+ && !au_is_bad_inode(inode)) { -+ iinfo = au_ii(inode); -+ hi = au_hinode(iinfo, bindex); -+ hn = !!au_hn(hi); -+ wh = hi->hi_whdentry; -+ } -+ do_pri_inode(bindex, inode, hn, wh); -+ return 0; -+} ++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); + -+void au_dpri_dentry(struct dentry *dentry) -+{ -+ struct au_dinfo *dinfo; -+ aufs_bindex_t bindex; -+ int err; ++/* 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); + -+ err = do_pri_dentry(-1, dentry); -+ if (err || !au_test_aufs(dentry->d_sb)) -+ return; ++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); + -+ 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); -+} ++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); + -+static int do_pri_file(aufs_bindex_t bindex, struct file *file) -+{ -+ char a[32]; ++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); + -+ if (!file || IS_ERR(file)) { -+ dpri("f%d: err %ld\n", bindex, PTR_ERR(file)); -+ return -1; -+ } -+ a[0] = 0; -+ if (bindex < 0 -+ && !IS_ERR_OR_NULL(file->f_path.dentry) -+ && au_test_aufs(file->f_path.dentry->d_sb) -+ && au_fi(file)) -+ snprintf(a, sizeof(a), ", gen %d, mmapped %d", -+ au_figen(file), atomic_read(&au_fi(file)->fi_mmapped)); -+ dpri("f%d: mode 0x%x, flags 0%o, cnt %ld, v %llu, pos %llu%s\n", -+ bindex, file->f_mode, file->f_flags, (long)file_count(file), -+ file->f_version, file->f_pos, a); -+ if (!IS_ERR_OR_NULL(file->f_path.dentry)) -+ do_pri_dentry(bindex, file->f_path.dentry); -+ return 0; -+} ++/* ---------------------------------------------------------------------- */ + -+void au_dpri_file(struct file *file) ++static inline struct au_dinfo *au_di(struct dentry *dentry) +{ -+ 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); -+ } ++ return dentry->d_fsdata; +} + -+static int do_pri_br(aufs_bindex_t bindex, struct au_branch *br) -+{ -+ struct vfsmount *mnt; -+ struct super_block *sb; ++/* ---------------------------------------------------------------------- */ + -+ if (!br || IS_ERR(br)) -+ goto out; -+ mnt = au_br_mnt(br); -+ if (!mnt || IS_ERR(mnt)) -+ goto out; -+ sb = mnt->mnt_sb; -+ if (!sb || IS_ERR(sb)) -+ goto out; ++/* 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 */ ++}; + -+ dpri("s%d: {perm 0x%x, id %d, cnt %lld, wbr %p}, " -+ "%s, dev 0x%02x%02x, flags 0x%lx, cnt %d, active %d, " -+ "xino %d\n", -+ bindex, br->br_perm, br->br_id, au_br_count(br), -+ 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), !!br->br_xino.xi_file); -+ return 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, ++ */ ++#define AuReadLockFunc(name, lsc) \ ++static inline void di_read_lock_##name(struct dentry *d, int flags) \ ++{ di_read_lock(d, flags, AuLsc_DI_##lsc); } + -+out: -+ dpri("s%d: err %ld\n", bindex, PTR_ERR(br)); -+ return -1; -+} ++#define AuWriteLockFunc(name, lsc) \ ++static inline void di_write_lock_##name(struct dentry *d) \ ++{ di_write_lock(d, AuLsc_DI_##lsc); } + -+void au_dpri_sb(struct super_block *sb) -+{ -+ struct au_sbinfo *sbinfo; -+ aufs_bindex_t bindex; -+ int err; -+ /* to reuduce stack size */ -+ struct { -+ struct vfsmount mnt; -+ struct au_branch fake; -+ } *a; ++#define AuRWLockFuncs(name, lsc) \ ++ AuReadLockFunc(name, lsc) \ ++ AuWriteLockFunc(name, lsc) + -+ /* this function can be called from magic sysrq */ -+ a = kzalloc(sizeof(*a), GFP_ATOMIC); -+ if (unlikely(!a)) { -+ dpri("no memory\n"); -+ return; -+ } ++AuRWLockFuncs(child, CHILD); ++AuRWLockFuncs(child2, CHILD2); ++AuRWLockFuncs(child3, CHILD3); ++AuRWLockFuncs(parent, PARENT); ++AuRWLockFuncs(parent2, PARENT2); ++AuRWLockFuncs(parent3, PARENT3); + -+ a->mnt.mnt_sb = sb; -+ a->fake.br_path.mnt = &a->mnt; -+ au_br_count_init(&a->fake); -+ err = do_pri_br(-1, &a->fake); -+ au_br_count_fin(&a->fake); -+ au_delayed_kfree(a); -+ dpri("dev 0x%x\n", sb->s_dev); -+ if (err || !au_test_aufs(sb)) -+ return; ++#undef AuReadLockFunc ++#undef AuWriteLockFunc ++#undef AuRWLockFuncs + -+ 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, -+ atomic_read(&sbinfo->si_kobj.kref.refcount)); -+ for (bindex = 0; bindex <= sbinfo->si_bbot; bindex++) -+ do_pri_br(bindex, sbinfo->si_branch[0 + bindex]); -+} ++#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) + +/* ---------------------------------------------------------------------- */ + -+void __au_dbg_verify_dinode(struct dentry *dentry, const char *func, int line) ++/* todo: memory barrier? */ ++static inline unsigned int au_digen(struct dentry *d) +{ -+ struct inode *h_inode, *inode = d_inode(dentry); -+ struct dentry *h_dentry; -+ aufs_bindex_t bindex, bbot, bi; ++ return atomic_read(&au_di(d)->di_generation); ++} + -+ if (!inode /* || au_di(dentry)->di_lsc == AuLsc_DI_TMP */) -+ return; ++static inline void au_h_dentry_init(struct au_hdentry *hdentry) ++{ ++ hdentry->hd_dentry = NULL; ++} + -+ 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; ++static inline struct au_hdentry *au_hdentry(struct au_dinfo *di, ++ aufs_bindex_t bindex) ++{ ++ return di->di_hdentry + bindex; ++} + -+ for (; bindex <= bbot; bindex++) { -+ h_dentry = au_h_dptr(dentry, bindex); -+ if (!h_dentry) -+ continue; -+ h_inode = au_h_iptr(inode, bindex); -+ if (unlikely(h_inode != d_inode(h_dentry))) { -+ au_debug_on(); -+ AuDbg("b%d, %s:%d\n", bindex, func, line); -+ AuDbgDentry(dentry); -+ AuDbgInode(inode); -+ au_debug_off(); -+ BUG(); -+ } -+ } ++static inline void au_hdput(struct au_hdentry *hd) ++{ ++ if (hd) ++ dput(hd->hd_dentry); +} + -+void au_dbg_verify_gen(struct dentry *parent, unsigned int sigen) ++static inline aufs_bindex_t au_dbtop(struct dentry *dentry) +{ -+ int err, i, j; -+ struct au_dcsub_pages dpages; -+ struct au_dpage *dpage; -+ struct dentry **dentries; ++ DiMustAnyLock(dentry); ++ return au_di(dentry)->di_btop; ++} + -+ 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); ++static inline aufs_bindex_t au_dbbot(struct dentry *dentry) ++{ ++ DiMustAnyLock(dentry); ++ return au_di(dentry)->di_bbot; +} + -+void au_dbg_verify_kthread(void) ++static inline aufs_bindex_t au_dbwh(struct dentry *dentry) +{ -+ 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); */ -+ } ++ 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; ++} + -+int __init au_debug_init(void) ++/* todo: hard/soft set? */ ++static inline void au_set_dbtop(struct dentry *dentry, aufs_bindex_t bindex) +{ -+ aufs_bindex_t bindex; -+ struct au_vdir_destr destr; ++ DiMustWriteLock(dentry); ++ au_di(dentry)->di_btop = bindex; ++} + -+ bindex = -1; -+ AuDebugOn(bindex >= 0); ++static inline void au_set_dbbot(struct dentry *dentry, aufs_bindex_t bindex) ++{ ++ DiMustWriteLock(dentry); ++ au_di(dentry)->di_bbot = bindex; ++} + -+ destr.len = -1; -+ AuDebugOn(destr.len < NAME_MAX); ++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; ++} + -+#ifdef CONFIG_4KSTACKS -+ pr_warn("CONFIG_4KSTACKS is defined.\n"); -+#endif ++static inline void au_set_dbdiropq(struct dentry *dentry, aufs_bindex_t bindex) ++{ ++ DiMustWriteLock(dentry); ++ au_di(dentry)->di_bdiropq = bindex; ++} + -+ return 0; ++/* ---------------------------------------------------------------------- */ ++ ++#ifdef CONFIG_AUFS_HNOTIFY ++static inline void au_digen_dec(struct dentry *d) ++{ ++ atomic_dec(&au_di(d)->di_generation); +} -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 2016-10-09 16:55:36.486034798 +0200 -@@ -0,0 +1,225 @@ ++ ++static inline void au_hn_di_reinit(struct dentry *dentry) ++{ ++ dentry->d_fsdata = NULL; ++} ++#else ++AuStubVoid(au_hn_di_reinit, struct dentry *dentry __maybe_unused) ++#endif /* CONFIG_AUFS_HNOTIFY */ ++ ++#endif /* __KERNEL__ */ ++#endif /* __AUFS_DENTRY_H__ */ +diff -urNp -x '*.orig' linux-4.9/fs/aufs/dinfo.c linux-4.9/fs/aufs/dinfo.c +--- linux-4.9/fs/aufs/dinfo.c 1970-01-01 01:00:00.000000000 +0100 ++++ linux-4.9/fs/aufs/dinfo.c 2021-02-24 16:15:09.524906971 +0100 +@@ -0,0 +1,553 @@ +/* -+ * Copyright (C) 2005-2016 Junjiro R. Okajima ++ * Copyright (C) 2005-2018 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by @@ -7467,1353 +8754,1310 @@ diff -urN /usr/share/empty/fs/aufs/debug.h linux/fs/aufs/debug.h + */ + +/* -+ * debug print functions ++ * dentry private data + */ + -+#ifndef __AUFS_DEBUG_H__ -+#define __AUFS_DEBUG_H__ -+ -+#ifdef __KERNEL__ ++#include "aufs.h" + -+#include -+#include -+#include -+#include ++void au_di_init_once(void *_dinfo) ++{ ++ struct au_dinfo *dinfo = _dinfo; + -+#ifdef CONFIG_AUFS_DEBUG -+#define AuDebugOn(a) BUG_ON(a) ++ au_rw_init(&dinfo->di_rwsem); ++} + -+/* module parameter */ -+extern atomic_t aufs_debug; -+static inline void au_debug_on(void) ++struct au_dinfo *au_di_alloc(struct super_block *sb, unsigned int lsc) +{ -+ atomic_inc(&aufs_debug); ++ struct au_dinfo *dinfo; ++ int nbr, i; ++ ++ dinfo = au_cache_alloc_dinfo(); ++ if (unlikely(!dinfo)) ++ goto out; ++ ++ nbr = au_sbbot(sb) + 1; ++ if (nbr <= 0) ++ nbr = 1; ++ dinfo->di_hdentry = kcalloc(nbr, sizeof(*dinfo->di_hdentry), GFP_NOFS); ++ if (dinfo->di_hdentry) { ++ au_rw_write_lock_nested(&dinfo->di_rwsem, lsc); ++ dinfo->di_btop = -1; ++ dinfo->di_bbot = -1; ++ dinfo->di_bwh = -1; ++ dinfo->di_bdiropq = -1; ++ dinfo->di_tmpfile = 0; ++ for (i = 0; i < nbr; i++) ++ dinfo->di_hdentry[i].hd_id = -1; ++ goto out; ++ } ++ ++ au_cache_free_dinfo(dinfo); ++ dinfo = NULL; ++ ++out: ++ return dinfo; +} -+static inline void au_debug_off(void) ++ ++void au_di_free(struct au_dinfo *dinfo) +{ -+ atomic_dec_if_positive(&aufs_debug); ++ 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++); ++ } ++ kfree(dinfo->di_hdentry); ++ au_cache_free_dinfo(dinfo); +} + -+static inline int au_debug_test(void) ++void au_di_swap(struct au_dinfo *a, struct au_dinfo *b) +{ -+ 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 */ ++ struct au_hdentry *p; ++ aufs_bindex_t bi; + -+#define param_check_atomic_t(name, p) __param_check(name, p, atomic_t) ++ 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) + -+/* debug print */ ++ DiSwap(p, hdentry); ++ DiSwap(bi, btop); ++ DiSwap(bi, bbot); ++ DiSwap(bi, bwh); ++ DiSwap(bi, bdiropq); ++ /* smp_mb(); */ + -+#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) ++#undef DiSwap ++} + -+#define AuErr1(fmt, ...) do { \ -+ static unsigned char _c; \ -+ if (!_c++) \ -+ pr_err(fmt, ##__VA_ARGS__); \ -+} while (0) ++void au_di_cp(struct au_dinfo *dst, struct au_dinfo *src) ++{ ++ AuRwMustWriteLock(&dst->di_rwsem); ++ AuRwMustWriteLock(&src->di_rwsem); + -+#define AuIOErr1(fmt, ...) do { \ -+ static unsigned char _c; \ -+ if (!_c++) \ -+ AuIOErr(fmt, ##__VA_ARGS__); \ -+} while (0) ++ 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(); */ ++} + -+#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) ++int au_di_init(struct dentry *dentry) ++{ ++ int err; ++ struct super_block *sb; ++ struct au_dinfo *dinfo; + -+#define AuTraceErr(e) do { \ -+ if (unlikely((e) < 0)) \ -+ AuDbg("err %d\n", (int)(e)); \ -+} while (0) ++ 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; + -+#define AuTraceErrPtr(p) do { \ -+ if (IS_ERR(p)) \ -+ AuDbg("err %ld\n", PTR_ERR(p)); \ -+} while (0) ++ return err; ++} + -+/* dirty macros for debug print, use with "%.*s" and caution */ -+#define AuLNPair(qstr) (qstr)->len, (qstr)->name ++void au_di_fin(struct dentry *dentry) ++{ ++ struct au_dinfo *dinfo; + -+/* ---------------------------------------------------------------------- */ ++ dinfo = au_di(dentry); ++ AuRwDestroy(&dinfo->di_rwsem); ++ au_di_free(dinfo); ++} + -+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); ++int au_di_realloc(struct au_dinfo *dinfo, int nbr, int may_shrink) ++{ ++ int err, sz; ++ struct au_hdentry *hdp; + -+#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); ++ AuRwMustWriteLock(&dinfo->di_rwsem); + -+int __init au_debug_init(void); ++ 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; ++ } + -+#define AuDbgWhlist(w) do { \ -+ mutex_lock(&au_dbg_mtx); \ -+ AuDbg(#w "\n"); \ -+ au_dpri_whlist(w); \ -+ mutex_unlock(&au_dbg_mtx); \ -+} while (0) ++ return err; ++} + -+#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) ++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(); ++ } ++} + -+#define AuDbgDAlias(i) do { \ -+ mutex_lock(&au_dbg_mtx); \ -+ AuDbg(#i "\n"); \ -+ au_dpri_dalias(i); \ -+ mutex_unlock(&au_dbg_mtx); \ -+} while (0) ++static void do_ii_read_lock(struct inode *inode, unsigned int lsc) ++{ ++ switch (lsc) { ++ case AuLsc_DI_CHILD: ++ ii_read_lock_child(inode); ++ break; ++ case AuLsc_DI_CHILD2: ++ ii_read_lock_child2(inode); ++ break; ++ case AuLsc_DI_CHILD3: ++ ii_read_lock_child3(inode); ++ break; ++ case AuLsc_DI_PARENT: ++ ii_read_lock_parent(inode); ++ break; ++ case AuLsc_DI_PARENT2: ++ ii_read_lock_parent2(inode); ++ break; ++ case AuLsc_DI_PARENT3: ++ ii_read_lock_parent3(inode); ++ break; ++ default: ++ BUG(); ++ } ++} + -+#define AuDbgDentry(d) do { \ -+ mutex_lock(&au_dbg_mtx); \ -+ AuDbg(#d "\n"); \ -+ au_dpri_dentry(d); \ -+ mutex_unlock(&au_dbg_mtx); \ -+} while (0) ++void di_read_lock(struct dentry *d, int flags, unsigned int lsc) ++{ ++ struct inode *inode; + -+#define AuDbgFile(f) do { \ -+ mutex_lock(&au_dbg_mtx); \ -+ AuDbg(#f "\n"); \ -+ au_dpri_file(f); \ -+ mutex_unlock(&au_dbg_mtx); \ -+} while (0) ++ 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); ++ } ++} + -+#define AuDbgSb(sb) do { \ -+ mutex_lock(&au_dbg_mtx); \ -+ AuDbg(#sb "\n"); \ -+ au_dpri_sb(sb); \ -+ mutex_unlock(&au_dbg_mtx); \ -+} while (0) ++void di_read_unlock(struct dentry *d, int flags) ++{ ++ struct inode *inode; + -+#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) ++ 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); ++} + -+#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 */ ++void di_downgrade_lock(struct dentry *d, int flags) ++{ ++ if (d_really_is_positive(d) && au_ftest_lock(flags, IR)) ++ ii_downgrade_lock(d_inode(d)); ++ au_rw_dgrade_lock(&au_di(d)->di_rwsem); ++} ++ ++void di_write_lock(struct dentry *d, unsigned int lsc) ++{ ++ au_rw_write_lock_nested(&au_di(d)->di_rwsem, lsc); ++ if (d_really_is_positive(d)) ++ do_ii_write_lock(d_inode(d), lsc); ++} ++ ++void di_write_unlock(struct dentry *d) ++{ ++ au_dbg_verify_dinode(d); ++ if (d_really_is_positive(d)) ++ ii_write_unlock(d_inode(d)); ++ au_rw_write_unlock(&au_di(d)->di_rwsem); ++} + -+/* ---------------------------------------------------------------------- */ ++void di_write_lock2_child(struct dentry *d1, struct dentry *d2, int isdir) ++{ ++ AuDebugOn(d1 == d2 ++ || d_inode(d1) == d_inode(d2) ++ || d1->d_sb != d2->d_sb); + -+#ifdef CONFIG_AUFS_MAGIC_SYSRQ -+int __init au_sysrq_init(void); -+void au_sysrq_fin(void); ++ 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); ++ } ++} + -+#ifdef CONFIG_HW_CONSOLE -+#define au_dbg_blocked() do { \ -+ WARN_ON(1); \ -+ handle_sysrq('w'); \ -+} while (0) -+#else -+AuStubVoid(au_dbg_blocked, void) -+#endif ++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); + -+#else -+AuStubInt0(__init au_sysrq_init, void) -+AuStubVoid(au_sysrq_fin, void) -+AuStubVoid(au_dbg_blocked, void) -+#endif /* CONFIG_AUFS_MAGIC_SYSRQ */ ++ 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); ++ } ++} + -+#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 2016-10-09 16:55:38.889431135 +0200 -@@ -0,0 +1,1130 @@ -+/* -+ * Copyright (C) 2005-2016 Junjiro R. Okajima -+ * -+ * This program, aufs is free software; you can redistribute it and/or modify -+ * it under the terms of the GNU General Public License as published by -+ * the Free Software Foundation; either version 2 of the License, or -+ * (at your option) any later version. -+ * -+ * This program is distributed in the hope that it will be useful, -+ * but WITHOUT ANY WARRANTY; without even the implied warranty of -+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the -+ * GNU General Public License for more details. -+ * -+ * You should have received a copy of the GNU General Public License -+ * along with this program. If not, see . -+ */ ++void di_write_unlock2(struct dentry *d1, struct dentry *d2) ++{ ++ di_write_unlock(d1); ++ if (d_inode(d1) == d_inode(d2)) ++ au_rw_write_unlock(&au_di(d2)->di_rwsem); ++ else ++ di_write_unlock(d2); ++} + -+/* -+ * lookup and dentry operations -+ */ ++/* ---------------------------------------------------------------------- */ + -+#include -+#include "aufs.h" ++struct dentry *au_h_dptr(struct dentry *dentry, aufs_bindex_t bindex) ++{ ++ struct dentry *d; + -+struct au_do_lookup_args { -+ unsigned int flags; -+ mode_t type; -+}; ++ 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; ++} + +/* -+ * returns positive/negative dentry, NULL or an error. -+ * NULL means whiteout-ed or not-found. ++ * extended version of au_h_dptr(). ++ * returns a hashed and positive (or linkable) h_dentry in bindex, NULL, or ++ * error. + */ -+static struct dentry* -+au_do_lookup(struct dentry *h_parent, struct dentry *dentry, -+ aufs_bindex_t bindex, struct qstr *wh_name, -+ struct au_do_lookup_args *args) ++struct dentry *au_h_d_alias(struct dentry *dentry, aufs_bindex_t bindex) +{ + struct dentry *h_dentry; -+ struct inode *h_inode; -+ struct au_branch *br; -+ int wh_found, opq; -+ unsigned char wh_able; -+ const unsigned char allow_neg = !!au_ftest_lkup(args->flags, ALLOW_NEG); -+ const unsigned char ignore_perm = !!au_ftest_lkup(args->flags, -+ IGNORE_PERM); -+ -+ wh_found = 0; -+ br = au_sbr(dentry->d_sb, bindex); -+ wh_able = !!au_br_whable(br->br_perm); -+ if (wh_able) -+ wh_found = au_wh_test(h_parent, wh_name, ignore_perm); -+ h_dentry = ERR_PTR(wh_found); -+ if (!wh_found) -+ goto real_lookup; -+ if (unlikely(wh_found < 0)) -+ goto out; ++ struct inode *inode, *h_inode; + -+ /* We found a whiteout */ -+ /* au_set_dbbot(dentry, bindex); */ -+ au_set_dbwh(dentry, bindex); -+ if (!allow_neg) -+ return NULL; /* success */ ++ AuDebugOn(d_really_is_negative(dentry)); + -+real_lookup: -+ if (!ignore_perm) -+ h_dentry = vfsub_lkup_one(&dentry->d_name, h_parent); -+ else -+ h_dentry = au_sio_lkup_one(&dentry->d_name, h_parent); -+ if (IS_ERR(h_dentry)) { -+ if (PTR_ERR(h_dentry) == -ENAMETOOLONG -+ && !allow_neg) -+ h_dentry = NULL; -+ 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 */ + } + -+ 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; -+ -+ if (au_dbbot(dentry) <= bindex) -+ au_set_dbbot(dentry, bindex); -+ if (au_dbtop(dentry) < 0 || bindex < au_dbtop(dentry)) -+ au_set_dbtop(dentry, bindex); -+ au_set_h_dptr(dentry, bindex, h_dentry); -+ -+ if (!d_is_dir(h_dentry) -+ || !wh_able -+ || (d_really_is_positive(dentry) && !d_is_dir(dentry))) -+ goto out; /* success */ ++ inode = 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; ++ } + -+ inode_lock_nested(h_inode, AuLsc_I_CHILD); -+ opq = au_diropq_test(h_dentry); -+ inode_unlock(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); ++ 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; ++ } + } -+ goto out; + -+out_neg: -+ dput(h_dentry); -+ h_dentry = NULL; +out: ++ AuDbgDentry(h_dentry); + return h_dentry; +} + -+static int au_test_shwh(struct super_block *sb, const struct qstr *name) ++aufs_bindex_t au_dbtail(struct dentry *dentry) +{ -+ if (unlikely(!au_opt_test(au_mntflags(sb), SHWH) -+ && !strncmp(name->name, AUFS_WH_PFX, AUFS_WH_PFX_LEN))) -+ return -EPERM; -+ return 0; ++ 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; +} + -+/* -+ * 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) ++aufs_bindex_t au_dbtaildir(struct dentry *dentry) +{ -+ int npositive, err; -+ aufs_bindex_t bindex, btail, bdiropq; -+ unsigned char isdir, dirperm1; -+ struct qstr whname; -+ struct au_do_lookup_args args = { -+ .flags = flags -+ }; -+ const struct qstr *name = &dentry->d_name; -+ struct dentry *parent; -+ struct super_block *sb; -+ -+ sb = dentry->d_sb; -+ err = au_test_shwh(sb, name); -+ if (unlikely(err)) -+ goto out; -+ -+ err = au_wh_name_alloc(&whname, name); -+ if (unlikely(err)) -+ goto out; ++ aufs_bindex_t bbot, bopq; + -+ isdir = !!d_is_dir(dentry); -+ dirperm1 = !!au_opt_test(au_mntflags(sb), DIRPERM1); ++ bbot = au_dbtail(dentry); ++ if (0 <= bbot) { ++ bopq = au_dbdiropq(dentry); ++ if (0 <= bopq && bopq < bbot) ++ bbot = bopq; ++ } ++ return bbot; ++} + -+ 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; ++/* ---------------------------------------------------------------------- */ + -+ 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; ++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; + -+ h_dir = d_inode(h_parent); -+ inode_lock_nested(h_dir, AuLsc_I_PARENT); -+ h_dentry = au_do_lookup(h_parent, dentry, bindex, &whname, -+ &args); -+ inode_unlock(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); ++ DiMustWriteLock(dentry); + -+ 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; -+ } ++ 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; + } ++} + -+ if (npositive) { -+ AuLabel(positive); -+ au_update_dbtop(dentry); -+ } -+ err = npositive; -+ if (unlikely(!au_opt_test(au_mntflags(sb), UDBA_NONE) -+ && au_dbtop(dentry) < 0)) { ++int au_dbrange_test(struct dentry *dentry) ++{ ++ int err; ++ aufs_bindex_t btop, bbot; ++ ++ err = 0; ++ btop = au_dbtop(dentry); ++ bbot = au_dbbot(dentry); ++ if (btop >= 0) ++ AuDebugOn(bbot < 0 && btop > bbot); ++ else { + err = -EIO; -+ AuIOErr("both of real entry and whiteout found, %pd, err %d\n", -+ dentry, err); ++ AuDebugOn(bbot >= 0); + } + -+out_parent: -+ dput(parent); -+ au_delayed_kfree(whname.name); -+out: + return err; +} + -+struct dentry *au_sio_lkup_one(struct qstr *name, struct dentry *parent) ++int au_digen_test(struct dentry *dentry, unsigned int sigen) +{ -+ struct dentry *dentry; -+ int wkq_err; ++ int err; + -+ if (!au_test_h_perm_sio(d_inode(parent), MAY_EXEC)) -+ dentry = vfsub_lkup_one(name, parent); -+ else { -+ struct vfsub_lkup_one_args args = { -+ .errp = &dentry, -+ .name = name, -+ .parent = parent -+ }; ++ err = 0; ++ if (unlikely(au_digen(dentry) != sigen ++ || au_iigen_test(d_inode(dentry), sigen))) ++ err = -EIO; + -+ wkq_err = au_wkq_wait(vfsub_call_lkup_one, &args); -+ if (unlikely(wkq_err)) -+ dentry = ERR_PTR(wkq_err); -+ } ++ return err; ++} + -+ return dentry; ++void au_update_digen(struct dentry *dentry) ++{ ++ atomic_set(&au_di(dentry)->di_generation, au_sigen(dentry->d_sb)); ++ /* smp_mb(); */ /* atomic_set */ +} + -+/* -+ * lookup @dentry on @bindex which should be negative. -+ */ -+int au_lkup_neg(struct dentry *dentry, aufs_bindex_t bindex, int wh) ++void au_update_dbrange(struct dentry *dentry, int do_put_zero) +{ -+ int err; -+ struct dentry *parent, *h_parent, *h_dentry; -+ struct au_branch *br; ++ struct au_dinfo *dinfo; ++ struct dentry *h_d; ++ struct au_hdentry *hdp; ++ aufs_bindex_t bindex, bbot; + -+ parent = dget_parent(dentry); -+ h_parent = au_h_dptr(parent, bindex); -+ br = au_sbr(dentry->d_sb, bindex); -+ if (wh) -+ h_dentry = au_whtmp_lkup(h_parent, br, &dentry->d_name); -+ else -+ h_dentry = au_sio_lkup_one(&dentry->d_name, h_parent); -+ err = PTR_ERR(h_dentry); -+ if (IS_ERR(h_dentry)) -+ goto out; -+ if (unlikely(d_is_positive(h_dentry))) { -+ err = -EIO; -+ AuIOErr("%pd should be negative on b%d.\n", h_dentry, bindex); -+ dput(h_dentry); -+ goto out; -+ } ++ DiMustWriteLock(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); ++ dinfo = au_di(dentry); ++ if (!dinfo || dinfo->di_btop < 0) ++ return; + -+out: -+ dput(parent); -+ return err; -+} ++ if (do_put_zero) { ++ bbot = dinfo->di_bbot; ++ bindex = dinfo->di_btop; ++ hdp = au_hdentry(dinfo, bindex); ++ for (; bindex <= bbot; bindex++, hdp++) { ++ h_d = hdp->hd_dentry; ++ if (h_d && d_is_negative(h_d)) ++ au_set_h_dptr(dentry, bindex, NULL); ++ } ++ } + -+/* ---------------------------------------------------------------------- */ ++ dinfo->di_btop = 0; ++ hdp = au_hdentry(dinfo, dinfo->di_btop); ++ for (; dinfo->di_btop <= dinfo->di_bbot; dinfo->di_btop++, hdp++) ++ if (hdp->hd_dentry) ++ break; ++ if (dinfo->di_btop > dinfo->di_bbot) { ++ dinfo->di_btop = -1; ++ dinfo->di_bbot = -1; ++ return; ++ } + -+/* 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; -+}; ++ 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 void au_iattr_save(struct au_iattr *ia, struct inode *h_inode) ++void au_update_dbtop(struct dentry *dentry) +{ -+ 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 = h_inode->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); ++ aufs_bindex_t bindex, bbot; ++ struct dentry *h_dentry; ++ ++ bbot = au_dbbot(dentry); ++ for (bindex = au_dbtop(dentry); bindex <= bbot; bindex++) { ++ h_dentry = au_h_dptr(dentry, bindex); ++ if (!h_dentry) ++ continue; ++ if (d_is_positive(h_dentry)) { ++ au_set_dbtop(dentry, bindex); ++ return; ++ } ++ au_set_h_dptr(dentry, bindex, NULL); ++ } +} + -+static int au_iattr_test(struct au_iattr *ia, struct inode *h_inode) ++void au_update_dbbot(struct dentry *dentry) +{ -+ 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) -+ || ia->i_version != h_inode->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); ++ 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); ++ } +} + -+static int au_h_verify_dentry(struct dentry *h_dentry, struct dentry *h_parent, -+ struct au_branch *br) ++int au_find_dbindex(struct dentry *dentry, struct dentry *h_dentry) +{ -+ int err; -+ struct au_iattr ia; -+ struct inode *h_inode; -+ struct dentry *h_d; -+ struct super_block *h_sb; ++ 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 -urNp -x '*.orig' linux-4.9/fs/aufs/dir.c linux-4.9/fs/aufs/dir.c +--- linux-4.9/fs/aufs/dir.c 1970-01-01 01:00:00.000000000 +0100 ++++ linux-4.9/fs/aufs/dir.c 2021-02-24 16:15:09.524906971 +0100 +@@ -0,0 +1,759 @@ ++/* ++ * Copyright (C) 2005-2018 Junjiro R. Okajima ++ * ++ * This program, aufs is free software; you can redistribute it and/or modify ++ * it under the terms of the GNU General Public License as published by ++ * the Free Software Foundation; either version 2 of the License, or ++ * (at your option) any later version. ++ * ++ * This program is distributed in the hope that it will be useful, ++ * but WITHOUT ANY WARRANTY; without even the implied warranty of ++ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the ++ * GNU General Public License for more details. ++ * ++ * You should have received a copy of the GNU General Public License ++ * along with this program. If not, see . ++ */ + -+ 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; ++/* ++ * directory operations ++ */ + -+ /* main purpose is namei.c:cached_lookup() and d_revalidate */ -+ h_d = vfsub_lkup_one(&h_dentry->d_name, h_parent); -+ err = PTR_ERR(h_d); -+ if (IS_ERR(h_d)) -+ goto out; ++#include ++#include "aufs.h" + -+ 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); ++void au_add_nlink(struct inode *dir, struct inode *h_dir) ++{ ++ unsigned int nlink; + -+out: -+ AuTraceErr(err); -+ return err; ++ 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); +} + -+int au_h_verify(struct dentry *h_dentry, unsigned int udba, struct inode *h_dir, -+ struct dentry *h_parent, struct au_branch *br) ++void au_sub_nlink(struct inode *dir, struct inode *h_dir) +{ -+ int err; ++ unsigned int nlink; + -+ 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); ++ AuDebugOn(!S_ISDIR(dir->i_mode) || !S_ISDIR(h_dir->i_mode)); + -+ return err; ++ 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); +} + -+/* ---------------------------------------------------------------------- */ -+ -+static int au_do_refresh_hdentry(struct dentry *dentry, struct dentry *parent) ++loff_t au_dir_size(struct file *file, struct dentry *dentry) +{ -+ int err; -+ aufs_bindex_t new_bindex, bindex, bbot, bwh, bdiropq; -+ struct au_hdentry tmp, *p, *q; -+ struct au_dinfo *dinfo; -+ struct super_block *sb; -+ -+ DiMustWriteLock(dentry); -+ -+ sb = dentry->d_sb; -+ dinfo = au_di(dentry); -+ bbot = dinfo->di_bbot; -+ bwh = dinfo->di_bwh; -+ bdiropq = dinfo->di_bdiropq; -+ bindex = dinfo->di_btop; -+ p = au_hdentry(dinfo, bindex); -+ for (; bindex <= bbot; bindex++, p++) { -+ if (!p->hd_dentry) -+ continue; ++ loff_t sz; ++ aufs_bindex_t bindex, bbot; ++ struct file *h_file; ++ struct dentry *h_dentry; + -+ new_bindex = au_br_index(sb, p->hd_id); -+ if (new_bindex == bindex) -+ continue; ++ sz = 0; ++ if (file) { ++ AuDebugOn(!d_is_dir(file->f_path.dentry)); + -+ 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; ++ 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)); + -+ /* 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--; ++ bbot = au_dbtaildir(dentry); ++ for (bindex = au_dbtop(dentry); ++ bindex <= bbot && sz < KMALLOC_MAX_SIZE; ++ bindex++) { ++ h_dentry = au_h_dptr(dentry, bindex); ++ if (h_dentry && d_is_positive(h_dentry)) ++ sz += i_size_read(d_inode(h_dentry)); + } + } ++ if (sz < KMALLOC_MAX_SIZE) ++ sz = roundup_pow_of_two(sz); ++ if (sz > KMALLOC_MAX_SIZE) ++ sz = KMALLOC_MAX_SIZE; ++ else if (sz < NAME_MAX) { ++ BUILD_BUG_ON(AUFS_RDBLK_DEF < NAME_MAX); ++ sz = AUFS_RDBLK_DEF; ++ } ++ return sz; ++} + -+ dinfo->di_bwh = -1; -+ if (bwh >= 0 && bwh <= au_sbbot(sb) && au_sbr_whable(sb, bwh)) -+ dinfo->di_bwh = bwh; ++struct au_dir_ts_arg { ++ struct dentry *dentry; ++ aufs_bindex_t brid; ++}; + -+ dinfo->di_bdiropq = -1; -+ if (bdiropq >= 0 -+ && bdiropq <= au_sbbot(sb) -+ && au_sbr_whable(sb, bdiropq)) -+ dinfo->di_bdiropq = bdiropq; ++static void au_do_dir_ts(void *arg) ++{ ++ struct au_dir_ts_arg *a = arg; ++ struct au_dtime dt; ++ struct path h_path; ++ struct inode *dir, *h_dir; ++ struct super_block *sb; ++ struct au_branch *br; ++ struct au_hinode *hdir; ++ int err; ++ aufs_bindex_t btop, bindex; + -+ 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; -+ } ++ 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 */ + -+ 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; -+ } ++ dir = d_inode(a->dentry); ++ btop = au_ibtop(dir); ++ bindex = au_br_index(sb, a->brid); ++ if (bindex < btop) ++ goto out_unlock; ++ ++ br = au_sbr(sb, bindex); ++ h_path.dentry = au_h_dptr(a->dentry, bindex); ++ if (!h_path.dentry) ++ goto out_unlock; ++ h_path.mnt = au_br_mnt(br); ++ au_dtime_store(&dt, a->dentry, &h_path); ++ ++ br = au_sbr(sb, btop); ++ if (!au_br_writable(br->br_perm)) ++ goto out_unlock; ++ h_path.dentry = au_h_dptr(a->dentry, btop); ++ h_path.mnt = au_br_mnt(br); ++ err = vfsub_mnt_want_write(h_path.mnt); ++ if (err) ++ goto out_unlock; ++ hdir = au_hi(dir, btop); ++ au_hn_inode_lock_nested(hdir, AuLsc_I_PARENT); ++ h_dir = au_h_iptr(dir, btop); ++ if (h_dir->i_nlink ++ && timespec_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); + -+ return err; ++out_unlock: ++ aufs_read_unlock(a->dentry, AuLock_DW); ++out: ++ dput(a->dentry); ++ au_nwt_done(&au_sbi(sb)->si_nowait); ++ kfree(arg); +} + -+static void au_do_hide(struct dentry *dentry) ++void au_dir_ts(struct inode *dir, aufs_bindex_t bindex) +{ -+ struct inode *inode; ++ int perm, wkq_err; ++ aufs_bindex_t btop; ++ struct au_dir_ts_arg *arg; ++ struct dentry *dentry; ++ struct super_block *sb; + -+ 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? */ ++ 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; + } -+ d_drop(dentry); -+} + -+static int au_hide_children(struct dentry *parent) -+{ -+ int err, i, j, ndentry; -+ struct au_dcsub_pages dpages; -+ struct au_dpage *dpage; -+ struct dentry *dentry; ++ perm = au_sbr_perm(sb, btop); ++ if (!au_br_writable(perm)) ++ goto out; + -+ err = au_dpages_init(&dpages, GFP_NOFS); -+ if (unlikely(err)) ++ arg = kmalloc(sizeof(*arg), GFP_NOFS); ++ if (!arg) + 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); -+ } ++ 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); ++ kfree(arg); + } + -+out_dpages: -+ au_dpages_free(&dpages); +out: -+ return err; ++ dput(dentry); +} + -+static void au_hide(struct dentry *dentry) ++/* ---------------------------------------------------------------------- */ ++ ++static int reopen_dir(struct file *file) +{ + int err; ++ unsigned int flags; ++ aufs_bindex_t bindex, btail, btop; ++ struct dentry *dentry, *h_dentry; ++ struct file *h_file; + -+ 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); ++ /* open all lower dirs */ ++ dentry = file->f_path.dentry; ++ btop = au_dbtop(dentry); ++ for (bindex = au_fbtop(file); bindex < btop; bindex++) ++ au_set_h_fptr(file, bindex, NULL); ++ au_set_fbtop(file, btop); ++ ++ btail = au_dbtaildir(dentry); ++ for (bindex = au_fbbot_dir(file); btail < bindex; bindex--) ++ au_set_h_fptr(file, bindex, NULL); ++ au_set_fbbot_dir(file, btail); ++ ++ flags = vfsub_file_flags(file); ++ for (bindex = btop; bindex <= btail; bindex++) { ++ h_dentry = au_h_dptr(dentry, bindex); ++ if (!h_dentry) ++ continue; ++ h_file = au_hf_dir(file, bindex); ++ if (h_file) ++ continue; ++ ++ h_file = au_h_open(dentry, bindex, flags, file, /*force_wr*/0); ++ err = PTR_ERR(h_file); ++ if (IS_ERR(h_file)) ++ goto out; /* close all? */ ++ au_set_h_fptr(file, bindex, h_file); + } -+ au_do_hide(dentry); ++ au_update_figen(file); ++ /* todo: necessary? */ ++ /* file->f_ra = h_file->f_ra; */ ++ err = 0; ++ ++out: ++ return err; +} + -+/* -+ * 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) ++static int do_open_dir(struct file *file, int flags, struct file *h_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; -+ -+ 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; -+ } -+ } ++ aufs_bindex_t bindex, btail; ++ struct dentry *dentry, *h_dentry; ++ struct vfsmount *mnt; + -+ inode = NULL; -+ if (d_really_is_positive(dentry)) -+ inode = d_inode(dentry); -+ if (!orig_h.inode) { -+ AuDbg("nagative originally\n"); -+ if (inode) { -+ au_hide(dentry); -+ goto out; -+ } -+ AuDebugOn(inode); -+ AuDebugOn(dinfo->di_btop != dinfo->di_bbot); -+ AuDebugOn(dinfo->di_bdiropq != -1); ++ FiMustWriteLock(file); ++ AuDebugOn(h_file); + -+ 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 = 0; ++ mnt = file->f_path.mnt; ++ dentry = file->f_path.dentry; ++ file->f_version = d_inode(dentry)->i_version; ++ bindex = au_dbtop(dentry); ++ au_set_fbtop(file, bindex); ++ btail = au_dbtaildir(dentry); ++ au_set_fbbot_dir(file, btail); ++ for (; !err && bindex <= btail; bindex++) { ++ h_dentry = au_h_dptr(dentry, bindex); ++ if (!h_dentry) ++ continue; ++ ++ err = vfsub_test_mntns(mnt, h_dentry->d_sb); ++ if (unlikely(err)) ++ break; ++ h_file = au_h_open(dentry, bindex, flags, file, /*force_wr*/0); ++ if (IS_ERR(h_file)) { ++ err = PTR_ERR(h_file); ++ break; + } ++ au_set_h_fptr(file, bindex, h_file); + } ++ au_update_figen(file); ++ /* todo: necessary? */ ++ /* file->f_ra = h_file->f_ra; */ ++ if (!err) ++ return 0; /* success */ ++ ++ /* close all */ ++ for (bindex = au_fbtop(file); bindex <= btail; bindex++) ++ au_set_h_fptr(file, bindex, NULL); ++ au_set_fbtop(file, -1); ++ au_set_fbbot_dir(file, -1); + -+out: + return err; +} + -+void au_refresh_dop(struct dentry *dentry, int force_reval) ++static int aufs_open_dir(struct inode *inode __maybe_unused, ++ struct file *file) +{ -+ 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; ++ int err; ++ struct super_block *sb; ++ struct au_fidir *fidir; + -+ BUILD_BUG_ON(sizeof(mask) != sizeof(dentry->d_flags)); ++ 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)) ++ kfree(fidir); ++ } ++ si_read_unlock(sb); ++ return err; ++} + -+ if (dentry->d_op == dop) -+ return; ++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; + -+ 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); ++ 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); ++ } ++ kfree(fidir); ++ finfo->fi_hdir = NULL; ++ } ++ au_finfo_fin(file); ++ return 0; +} + -+int au_refresh_dentry(struct dentry *dentry, struct dentry *parent) ++/* ---------------------------------------------------------------------- */ ++ ++static int au_do_flush_dir(struct file *file, fl_owner_t id) +{ -+ int err, ebrange, nbr; -+ unsigned int sigen; -+ struct au_dinfo *dinfo, *tmp; -+ struct super_block *sb; -+ struct inode *inode; ++ int err; ++ aufs_bindex_t bindex, bbot; ++ struct file *h_file; + -+ DiMustWriteLock(dentry); -+ AuDebugOn(IS_ROOT(dentry)); -+ AuDebugOn(d_really_is_negative(parent)); ++ 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; ++} + -+ sb = dentry->d_sb; -+ sigen = au_sigen(sb); -+ err = au_digen_test(parent, sigen); -+ if (unlikely(err)) -+ goto out; ++static int aufs_flush_dir(struct file *file, fl_owner_t id) ++{ ++ return au_do_flush(file, id, au_do_flush_dir); ++} + -+ 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; -+ } ++static int au_do_fsync_dir_no_file(struct dentry *dentry, int datasync) ++{ ++ int err; ++ aufs_bindex_t bbot, bindex; ++ struct inode *inode; ++ struct super_block *sb; + -+ /* 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; ++ 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; + -+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); ++ 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_do_h_d_reval(struct dentry *h_dentry, unsigned int flags, -+ struct dentry *dentry, aufs_bindex_t bindex) ++static int au_do_fsync_dir(struct file *file, int datasync) +{ -+ int err, valid; ++ int err; ++ aufs_bindex_t bbot, bindex; ++ struct file *h_file; ++ struct super_block *sb; ++ struct inode *inode; + -+ err = 0; -+ if (!(h_dentry->d_flags & DCACHE_OP_REVALIDATE)) ++ err = au_reval_and_lock_fdi(file, reopen_dir, /*wlock*/1, /*fi_lsc*/0); ++ if (unlikely(err)) + goto out; + -+ AuDbg("b%d\n", bindex); -+ /* -+ * gave up supporting LOOKUP_CREATE/OPEN for lower fs, -+ * due to whiteout and branch permission. -+ */ -+ flags &= ~(/*LOOKUP_PARENT |*/ LOOKUP_OPEN | LOOKUP_CREATE -+ | LOOKUP_FOLLOW | LOOKUP_EXCL); -+ /* it may return tri-state */ -+ valid = h_dentry->d_op->d_revalidate(h_dentry, flags); ++ 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; + -+ if (unlikely(valid < 0)) -+ err = valid; -+ else if (!valid) -+ err = -EINVAL; ++ err = vfsub_fsync(h_file, &h_file->f_path, datasync); ++ } + +out: -+ AuTraceErr(err); + return err; +} + -+/* todo: remove this */ -+static int h_d_revalidate(struct dentry *dentry, struct inode *inode, -+ unsigned int flags, int do_udba) ++/* ++ * @file may be NULL ++ */ ++static int aufs_fsync_dir(struct file *file, loff_t start, loff_t end, ++ int datasync) +{ + 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; ++ struct dentry *dentry; ++ struct inode *inode; ++ struct super_block *sb; + + err = 0; -+ plus = 0; -+ mode = 0; -+ ibs = -1; -+ ibe = -1; -+ unhashed = !!d_unhashed(dentry); -+ is_root = !!IS_ROOT(dentry); -+ name = &dentry->d_name; -+ tmpfile = au_di(dentry)->di_tmpfile; -+ -+ /* -+ * Theoretically, REVAL test should be unnecessary in case of -+ * {FS,I}NOTIFY. -+ * But {fs,i}notify doesn't fire some necessary events, -+ * IN_ATTRIB for atime/nlink/pageio -+ * Let's do REVAL test too. -+ */ -+ if (do_udba && inode) { -+ mode = (inode->i_mode & S_IFMT); -+ plus = (inode->i_nlink > 0); -+ ibs = au_ibtop(inode); -+ ibe = au_ibbot(inode); ++ 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); + -+ 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 -+ && !au_qstreq(name, h_name)) -+ )) -+ || (h_nfs -+ && !(flags & LOOKUP_OPEN) -+ && (h_dentry->d_flags -+ & DCACHE_NFSFS_RENAMED))) -+ )) { -+ int h_unhashed; ++ si_read_unlock(sb); ++ inode_unlock(inode); ++ return err; ++} + -+ h_unhashed = d_unhashed(h_dentry); -+ spin_unlock(&h_dentry->d_lock); -+ AuDbg("unhash 0x%x 0x%x, %pd %pd\n", -+ unhashed, h_unhashed, dentry, h_dentry); -+ goto err; -+ } -+ spin_unlock(&h_dentry->d_lock); ++/* ---------------------------------------------------------------------- */ + -+ err = au_do_h_d_reval(h_dentry, flags, dentry, bindex); -+ if (unlikely(err)) -+ /* do not goto err, to keep the errno */ -+ break; ++static int aufs_iterate_shared(struct file *file, struct dir_context *ctx) ++{ ++ int err; ++ struct dentry *dentry; ++ struct inode *inode, *h_inode; ++ struct super_block *sb; + -+ /* todo: plink too? */ -+ if (!do_udba) -+ continue; ++ AuDbg("%pD, ctx{%pf, %llu}\n", file, ctx->actor, ctx->pos); + -+ /* UDBA tests */ -+ if (unlikely(!!inode != d_is_positive(h_dentry))) -+ goto err; ++ dentry = file->f_path.dentry; ++ inode = d_inode(dentry); ++ IMustLock(inode); + -+ 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); ++ 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; + -+ 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; ++ 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: -+ err = -EINVAL; -+ break; ++ AuTraceErr(err); ++ return err; + } + -+ AuTraceErr(err); ++out_unlock: ++ di_read_unlock(dentry, AuLock_IR); ++ fi_write_unlock(file); ++out: ++ si_read_unlock(sb); + return err; +} + -+/* todo: consolidate with do_refresh() and au_reval_for_attr() */ -+static int simple_reval_dpath(struct dentry *dentry, unsigned int sigen) ++/* ---------------------------------------------------------------------- */ ++ ++#define AuTestEmpty_WHONLY 1 ++#define AuTestEmpty_CALLED (1 << 1) ++#define AuTestEmpty_SHWH (1 << 2) ++#define au_ftest_testempty(flags, name) ((flags) & AuTestEmpty_##name) ++#define au_fset_testempty(flags, name) \ ++ do { (flags) |= AuTestEmpty_##name; } while (0) ++#define au_fclr_testempty(flags, name) \ ++ do { (flags) &= ~AuTestEmpty_##name; } while (0) ++ ++#ifndef CONFIG_AUFS_SHWH ++#undef AuTestEmpty_SHWH ++#define AuTestEmpty_SHWH 0 ++#endif ++ ++struct test_empty_arg { ++ struct dir_context ctx; ++ struct au_nhash *whlist; ++ unsigned int flags; ++ int err; ++ aufs_bindex_t bindex; ++}; ++ ++static int test_empty_cb(struct dir_context *ctx, const char *__name, ++ int namelen, loff_t offset __maybe_unused, u64 ino, ++ unsigned int d_type) ++{ ++ struct test_empty_arg *arg = container_of(ctx, struct test_empty_arg, ++ ctx); ++ char *name = (void *)__name; ++ ++ arg->err = 0; ++ au_fset_testempty(arg->flags, CALLED); ++ /* smp_mb(); */ ++ if (name[0] == '.' ++ && (namelen == 1 || (name[1] == '.' && namelen == 2))) ++ goto out; /* success */ ++ ++ if (namelen <= AUFS_WH_PFX_LEN ++ || memcmp(name, AUFS_WH_PFX, AUFS_WH_PFX_LEN)) { ++ if (au_ftest_testempty(arg->flags, WHONLY) ++ && !au_nhash_test_known_wh(arg->whlist, name, namelen)) ++ arg->err = -ENOTEMPTY; ++ goto out; ++ } ++ ++ name += AUFS_WH_PFX_LEN; ++ namelen -= AUFS_WH_PFX_LEN; ++ if (!au_nhash_test_known_wh(arg->whlist, name, namelen)) ++ arg->err = au_nhash_append_wh ++ (arg->whlist, name, namelen, ino, d_type, arg->bindex, ++ au_ftest_testempty(arg->flags, SHWH)); ++ ++out: ++ /* smp_mb(); */ ++ AuTraceErr(arg->err); ++ return arg->err; ++} ++ ++static int do_test_empty(struct dentry *dentry, struct test_empty_arg *arg) +{ + int err; -+ struct dentry *parent; ++ struct file *h_file; + -+ if (!au_digen_test(dentry, sigen)) -+ return 0; ++ 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; + -+ 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); ++ err = 0; ++ if (!au_opt_test(au_mntflags(dentry->d_sb), UDBA_NONE) ++ && !file_inode(h_file)->i_nlink) ++ goto out_put; ++ ++ do { ++ arg->err = 0; ++ au_fclr_testempty(arg->flags, CALLED); ++ /* smp_mb(); */ ++ err = vfsub_iterate_dir(h_file, &arg->ctx); ++ if (err >= 0) ++ err = arg->err; ++ } while (!err && au_ftest_testempty(arg->flags, CALLED)); ++ ++out_put: ++ fput(h_file); ++ au_sbr_put(dentry->d_sb, arg->bindex); ++out: + return err; +} + -+int au_reval_dpath(struct dentry *dentry, unsigned int sigen) ++struct do_test_empty_args { ++ int *errp; ++ struct dentry *dentry; ++ struct test_empty_arg *arg; ++}; ++ ++static void call_do_test_empty(void *args) ++{ ++ struct do_test_empty_args *a = args; ++ *a->errp = do_test_empty(a->dentry, a->arg); ++} ++ ++static int sio_test_empty(struct dentry *dentry, struct test_empty_arg *arg) +{ -+ int err; -+ struct dentry *d, *parent; -+ -+ if (!au_ftest_si(au_sbi(dentry->d_sb), FAILED_REFRESH_DIR)) -+ return simple_reval_dpath(dentry, sigen); -+ -+ /* slow loop, keep it simple and stupid */ -+ /* cf: au_cpup_dirs() */ -+ err = 0; -+ parent = NULL; -+ while (au_digen_test(dentry, sigen)) { -+ d = dentry; -+ while (1) { -+ dput(parent); -+ parent = dget_parent(d); -+ if (!au_digen_test(parent, sigen)) -+ break; -+ d = parent; -+ } -+ -+ if (d != dentry) -+ di_write_lock_child2(d); ++ int err, wkq_err; ++ struct dentry *h_dentry; ++ struct inode *h_inode; + -+ /* 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); -+ } ++ h_dentry = au_h_dptr(dentry, arg->bindex); ++ h_inode = d_inode(h_dentry); ++ /* todo: i_mode changes anytime? */ ++ vfsub_inode_lock_shared_nested(h_inode, AuLsc_I_CHILD); ++ err = au_test_h_perm_sio(h_inode, MAY_EXEC | MAY_READ); ++ inode_unlock_shared(h_inode); ++ if (!err) ++ err = do_test_empty(dentry, arg); ++ else { ++ struct do_test_empty_args args = { ++ .errp = &err, ++ .dentry = dentry, ++ .arg = arg ++ }; ++ unsigned int flags = arg->flags; + -+ if (d != dentry) -+ di_write_unlock(d); -+ dput(parent); -+ if (unlikely(err)) -+ break; ++ wkq_err = au_wkq_wait(call_do_test_empty, &args); ++ if (unlikely(wkq_err)) ++ err = wkq_err; ++ arg->flags = flags; + } + + return err; +} + -+/* -+ * if valid returns 1, otherwise 0. -+ */ -+static int aufs_d_revalidate(struct dentry *dentry, unsigned int flags) ++int au_test_empty_lower(struct dentry *dentry) +{ -+ int valid, err; -+ unsigned int sigen; -+ unsigned char do_udba; -+ struct super_block *sb; -+ struct inode *inode; -+ -+ /* todo: support rcu-walk? */ -+ if (flags & LOOKUP_RCU) -+ return -ECHILD; ++ 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); + -+ valid = 0; -+ if (unlikely(!au_di(dentry))) -+ goto out; ++ SiMustAnyLock(dentry->d_sb); + -+ 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); ++ 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; -+ } -+ inode = NULL; -+ if (d_really_is_positive(dentry)) -+ inode = d_inode(dentry); -+ if (unlikely(inode && au_is_bad_inode(inode))) { -+ err = -EINVAL; -+ AuTraceErr(err); -+ goto out_dgrade; -+ } -+ if (unlikely(au_dbrange_test(dentry))) { -+ err = -EINVAL; -+ AuTraceErr(err); -+ goto out_dgrade; -+ } -+ -+ sigen = au_sigen(sb); -+ if (au_digen_test(dentry, sigen)) { -+ AuDebugOn(IS_ROOT(dentry)); -+ err = au_reval_dpath(dentry, sigen); -+ if (unlikely(err)) { -+ AuTraceErr(err); -+ goto out_dgrade; -+ } -+ } -+ di_downgrade_lock(dentry, AuLock_IR); + -+ err = -EINVAL; -+ if (!(flags & (LOOKUP_OPEN | LOOKUP_EMPTY)) -+ && inode -+ && !(inode->i_state && I_LINKABLE) -+ && (IS_DEADDIR(inode) || !inode->i_nlink)) { -+ AuTraceErr(err); -+ goto out_inval; -+ } ++ 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; + -+ 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; ++ au_fset_testempty(arg.flags, WHONLY); ++ btail = au_dbtaildir(dentry); ++ for (bindex = btop + 1; !err && bindex <= btail; bindex++) { ++ struct dentry *h_dentry; + -+ if (btop >= 0) { -+ h_inode = au_h_iptr(inode, btop); -+ if (h_inode && au_test_higen(inode, h_inode)) { -+ AuTraceErr(err); -+ goto out_inval; -+ } ++ h_dentry = au_h_dptr(dentry, bindex); ++ if (h_dentry && d_is_positive(h_dentry)) { ++ arg.bindex = bindex; ++ err = test_empty(dentry, &arg); + } + } + -+ err = h_d_revalidate(dentry, inode, flags, do_udba); -+ 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_whlist: ++ au_nhash_wh_free(&whlist); +out: -+ if (!valid) { -+ AuDbg("%pd invalid, %d\n", dentry, valid); -+ d_drop(dentry); -+ } -+ return valid; ++ return err; +} + -+static void aufs_d_release(struct dentry *dentry) ++int au_test_empty(struct dentry *dentry, struct au_nhash *whlist) +{ -+ if (au_di(dentry)) { -+ au_di_fin(dentry); -+ au_hn_di_reinit(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); ++ } + } ++ ++ return err; +} + -+const struct dentry_operations aufs_dop = { -+ .d_revalidate = aufs_d_revalidate, -+ .d_weak_revalidate = aufs_d_revalidate, -+ .d_release = aufs_d_release -+}; ++/* ---------------------------------------------------------------------- */ + -+/* aufs_dop without d_revalidate */ -+const struct dentry_operations aufs_dop_noreval = { -+ .d_release = aufs_d_release ++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/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 2016-10-09 16:55:38.889431135 +0200 -@@ -0,0 +1,255 @@ +diff -urNp -x '*.orig' linux-4.9/fs/aufs/dir.h linux-4.9/fs/aufs/dir.h +--- linux-4.9/fs/aufs/dir.h 1970-01-01 01:00:00.000000000 +0100 ++++ linux-4.9/fs/aufs/dir.h 2021-02-24 16:15:09.524906971 +0100 +@@ -0,0 +1,131 @@ +/* -+ * Copyright (C) 2005-2016 Junjiro R. Okajima ++ * Copyright (C) 2005-2018 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by @@ -8830,249 +10074,125 @@ diff -urN /usr/share/empty/fs/aufs/dentry.h linux/fs/aufs/dentry.h + */ + +/* -+ * lookup and dentry operations ++ * directory operations + */ + -+#ifndef __AUFS_DENTRY_H__ -+#define __AUFS_DENTRY_H__ ++#ifndef __AUFS_DIR_H__ ++#define __AUFS_DIR_H__ + +#ifdef __KERNEL__ + -+#include -+#include "rwsem.h" -+ -+struct au_hdentry { -+ struct dentry *hd_dentry; -+ aufs_bindex_t hd_id; -+}; -+ -+struct au_dinfo { -+ atomic_t di_generation; -+ -+ struct au_rwsem di_rwsem; -+ aufs_bindex_t di_btop, di_bbot, di_bwh, di_bdiropq; -+ unsigned char di_tmpfile; /* to allow the different name */ -+ union { -+ struct au_hdentry *di_hdentry; -+ struct llist_node di_lnode; /* delayed free */ -+ }; -+} ____cacheline_aligned_in_smp; -+ -+/* ---------------------------------------------------------------------- */ -+ -+/* flags for au_lkup_dentry() */ -+#define AuLkup_ALLOW_NEG 1 -+#define AuLkup_IGNORE_PERM (1 << 1) -+#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) ++#include + +/* ---------------------------------------------------------------------- */ + -+/* dentry.c */ -+extern const struct dentry_operations aufs_dop, aufs_dop_noreval; -+struct au_branch; -+struct dentry *au_sio_lkup_one(struct qstr *name, struct dentry *parent); -+int au_h_verify(struct dentry *h_dentry, unsigned int udba, struct inode *h_dir, -+ struct dentry *h_parent, struct au_branch *br); -+ -+int au_lkup_dentry(struct dentry *dentry, aufs_bindex_t btop, -+ unsigned int flags); -+int au_lkup_neg(struct dentry *dentry, aufs_bindex_t bindex, int wh); -+int au_refresh_dentry(struct dentry *dentry, struct dentry *parent); -+int au_reval_dpath(struct dentry *dentry, unsigned int sigen); -+void au_refresh_dop(struct dentry *dentry, int force_reval); -+ -+/* dinfo.c */ -+void au_di_init_once(void *_di); -+struct au_dinfo *au_di_alloc(struct super_block *sb, unsigned int lsc); -+void au_di_free(struct au_dinfo *dinfo); -+void au_di_swap(struct au_dinfo *a, struct au_dinfo *b); -+void au_di_cp(struct au_dinfo *dst, struct au_dinfo *src); -+int au_di_init(struct dentry *dentry); -+void au_di_fin(struct dentry *dentry); -+int au_di_realloc(struct au_dinfo *dinfo, int nbr, int may_shrink); -+ -+void di_read_lock(struct dentry *d, int flags, unsigned int lsc); -+void di_read_unlock(struct dentry *d, int flags); -+void di_downgrade_lock(struct dentry *d, int flags); -+void di_write_lock(struct dentry *d, unsigned int lsc); -+void di_write_unlock(struct dentry *d); -+void di_write_lock2_child(struct dentry *d1, struct dentry *d2, int isdir); -+void di_write_lock2_parent(struct dentry *d1, struct dentry *d2, int isdir); -+void di_write_unlock2(struct dentry *d1, struct dentry *d2); ++/* need to be faster and smaller */ + -+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); ++struct au_nhash { ++ unsigned int nh_num; ++ struct hlist_head *nh_head; ++}; + -+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); ++struct au_vdir_destr { ++ unsigned char len; ++ unsigned char name[0]; ++} __packed; + -+/* ---------------------------------------------------------------------- */ ++struct au_vdir_dehstr { ++ struct hlist_node hash; ++ struct au_vdir_destr *str; ++} ____cacheline_aligned_in_smp; + -+static inline struct au_dinfo *au_di(struct dentry *dentry) -+{ -+ return dentry->d_fsdata; -+} ++struct au_vdir_de { ++ ino_t de_ino; ++ unsigned char de_type; ++ /* caution: packed */ ++ struct au_vdir_destr de_str; ++} __packed; + -+/* ---------------------------------------------------------------------- */ ++struct au_vdir_wh { ++ struct hlist_node wh_hash; ++#ifdef CONFIG_AUFS_SHWH ++ ino_t wh_ino; ++ aufs_bindex_t wh_bindex; ++ unsigned char wh_type; ++#else ++ aufs_bindex_t wh_bindex; ++#endif ++ /* caution: packed */ ++ struct au_vdir_destr wh_str; ++} __packed; + -+/* 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 */ ++union au_vdir_deblk_p { ++ unsigned char *deblk; ++ struct au_vdir_de *de; +}; + -+/* -+ * 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 ++struct au_vdir { ++ unsigned char **vd_deblk; ++ unsigned long vd_nblk; ++ struct { ++ unsigned long ul; ++ union au_vdir_deblk_p p; ++ } vd_last; + -+#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) ++ unsigned long vd_version; ++ unsigned int vd_deblk_sz; ++ unsigned long vd_jiffy; ++} ____cacheline_aligned_in_smp; + +/* ---------------------------------------------------------------------- */ + -+/* 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; -+} -+ -+/* ---------------------------------------------------------------------- */ ++/* 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); + -+#ifdef CONFIG_AUFS_HNOTIFY -+static inline void au_digen_dec(struct dentry *d) -+{ -+ atomic_dec(&au_di(d)->di_generation); -+} ++/* 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); + -+static inline void au_hn_di_reinit(struct dentry *dentry) -+{ -+ dentry->d_fsdata = NULL; -+} ++/* 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 -+AuStubVoid(au_hn_di_reinit, struct dentry *dentry __maybe_unused) -+#endif /* CONFIG_AUFS_HNOTIFY */ ++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_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 2016-10-09 16:55:38.889431135 +0200 -@@ -0,0 +1,553 @@ ++#endif /* __AUFS_DIR_H__ */ +diff -urNp -x '*.orig' linux-4.9/fs/aufs/dirren.c linux-4.9/fs/aufs/dirren.c +--- linux-4.9/fs/aufs/dirren.c 1970-01-01 01:00:00.000000000 +0100 ++++ linux-4.9/fs/aufs/dirren.c 2021-02-24 16:15:09.524906971 +0100 +@@ -0,0 +1,1314 @@ +/* -+ * Copyright (C) 2005-2016 Junjiro R. Okajima ++ * Copyright (C) 2017-2018 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by @@ -9089,547 +10209,1308 @@ diff -urN /usr/share/empty/fs/aufs/dinfo.c linux/fs/aufs/dinfo.c + */ + +/* -+ * dentry private data ++ * special handling in renaming a directoy ++ * in order to support looking-up the before-renamed name on the lower readonly ++ * branches + */ + ++#include +#include "aufs.h" + -+void au_di_init_once(void *_dinfo) ++static void au_dr_hino_del(struct au_dr_br *dr, struct au_dr_hino *ent) +{ -+ struct au_dinfo *dinfo = _dinfo; ++ int idx; + -+ au_rw_init(&dinfo->di_rwsem); ++ idx = au_dr_ihash(ent->dr_h_ino); ++ au_hbl_del(&ent->dr_hnode, dr->dr_h_ino + idx); +} + -+struct au_dinfo *au_di_alloc(struct super_block *sb, unsigned int lsc) ++static int au_dr_hino_test_empty(struct au_dr_br *dr) +{ -+ struct au_dinfo *dinfo; -+ int nbr, i; ++ int ret, i; ++ struct hlist_bl_head *hbl; + -+ dinfo = au_cache_alloc_dinfo(); -+ if (unlikely(!dinfo)) -+ goto out; ++ 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); ++ } + -+ nbr = au_sbbot(sb) + 1; -+ if (nbr <= 0) -+ nbr = 1; -+ dinfo->di_hdentry = kcalloc(nbr, sizeof(*dinfo->di_hdentry), GFP_NOFS); -+ if (dinfo->di_hdentry) { -+ au_rw_write_lock_nested(&dinfo->di_rwsem, lsc); -+ dinfo->di_btop = -1; -+ dinfo->di_bbot = -1; -+ dinfo->di_bwh = -1; -+ dinfo->di_bdiropq = -1; -+ dinfo->di_tmpfile = 0; -+ for (i = 0; i < nbr; i++) -+ dinfo->di_hdentry[i].hd_id = -1; -+ goto out; ++ return ret; ++} ++ ++static struct au_dr_hino *au_dr_hino_find(struct au_dr_br *dr, ino_t ino) ++{ ++ struct au_dr_hino *found, *ent; ++ struct hlist_bl_head *hbl; ++ struct hlist_bl_node *pos; ++ int idx; ++ ++ found = NULL; ++ idx = au_dr_ihash(ino); ++ hbl = dr->dr_h_ino + idx; ++ hlist_bl_lock(hbl); ++ hlist_bl_for_each_entry(ent, pos, hbl, dr_hnode) ++ if (ent->dr_h_ino == ino) { ++ found = ent; ++ break; ++ } ++ hlist_bl_unlock(hbl); ++ ++ return found; ++} ++ ++int au_dr_hino_test_add(struct au_dr_br *dr, ino_t ino, ++ struct au_dr_hino *add_ent) ++{ ++ int found, idx; ++ struct hlist_bl_head *hbl; ++ struct hlist_bl_node *pos; ++ struct au_dr_hino *ent; ++ ++ found = 0; ++ idx = au_dr_ihash(ino); ++ hbl = dr->dr_h_ino + idx; ++#if 0 ++ { ++ struct hlist_bl_node *tmp; ++ ++ hlist_bl_for_each_entry_safe(ent, pos, tmp, hbl, dr_hnode) ++ AuDbg("hi%llu\n", (unsigned long long)ent->dr_h_ino); + } ++#endif ++ hlist_bl_lock(hbl); ++ hlist_bl_for_each_entry(ent, pos, hbl, dr_hnode) ++ if (ent->dr_h_ino == ino) { ++ found = 1; ++ break; ++ } ++ if (!found && add_ent) ++ hlist_bl_add_head(&add_ent->dr_hnode, hbl); ++ hlist_bl_unlock(hbl); + -+ au_cache_dfree_dinfo(dinfo); -+ dinfo = NULL; ++ if (!found && add_ent) ++ AuDbg("i%llu added\n", (unsigned long long)add_ent->dr_h_ino); + -+out: -+ return dinfo; ++ return found; +} + -+void au_di_free(struct au_dinfo *dinfo) ++void au_dr_hino_free(struct au_dr_br *dr) +{ -+ struct au_hdentry *p; -+ aufs_bindex_t bbot, bindex; ++ int i; ++ struct hlist_bl_head *hbl; ++ struct hlist_bl_node *pos, *tmp; ++ struct au_dr_hino *ent; + -+ /* 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++); ++ /* SiMustWriteLock(sb); */ ++ ++ for (i = 0; i < AuDirren_NHASH; i++) { ++ hbl = dr->dr_h_ino + i; ++ /* no spinlock since sbinfo must be write-locked */ ++ hlist_bl_for_each_entry_safe(ent, pos, tmp, hbl, dr_hnode) ++ kfree(ent); ++ INIT_HLIST_BL_HEAD(hbl); + } -+ au_delayed_kfree(dinfo->di_hdentry); -+ au_cache_dfree_dinfo(dinfo); +} + -+void au_di_swap(struct au_dinfo *a, struct au_dinfo *b) ++/* 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) +{ -+ struct au_hdentry *p; -+ aufs_bindex_t bi; ++ int err, i; ++ ssize_t ssz; ++ loff_t pos, oldsize; ++ uint64_t u64; ++ struct inode *hinoinode; ++ struct hlist_bl_head *hbl; ++ struct hlist_bl_node *n1, *n2; ++ struct au_dr_hino *ent; + -+ AuRwMustWriteLock(&a->di_rwsem); -+ AuRwMustWriteLock(&b->di_rwsem); ++ SiMustWriteLock(sb); ++ AuDebugOn(!au_br_writable(br->br_perm)); + -+#define DiSwap(v, name) \ -+ do { \ -+ v = a->di_##name; \ -+ a->di_##name = b->di_##name; \ -+ b->di_##name = v; \ -+ } while (0) ++ hinoinode = file_inode(hinofile); ++ oldsize = i_size_read(hinoinode); + -+ DiSwap(p, hdentry); -+ DiSwap(bi, btop); -+ DiSwap(bi, bbot); -+ DiSwap(bi, bwh); -+ DiSwap(bi, bdiropq); -+ /* smp_mb(); */ ++ 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; + -+#undef DiSwap ++ /* 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; +} + -+void au_di_cp(struct au_dinfo *dst, struct au_dinfo *src) ++static int au_dr_hino_load(struct au_dr_br *dr, struct file *hinofile) +{ -+ AuRwMustWriteLock(&dst->di_rwsem); -+ AuRwMustWriteLock(&src->di_rwsem); ++ 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; + -+ 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(); */ ++ 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(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; +} + -+int au_di_init(struct dentry *dentry) ++/* ++ * @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; -+ struct super_block *sb; -+ struct au_dinfo *dinfo; ++ int err, flags; ++ unsigned char load, suspend; ++ struct file *hinofile; ++ struct au_hinode *hdir; ++ struct inode *dir, *delegated; ++ struct path hinopath; ++ struct qstr hinoname = QSTR_INIT(AUFS_WH_DR_BRHINO, ++ sizeof(AUFS_WH_DR_BRHINO) - 1); ++ ++ AuDebugOn(bindex < 0 && !br); ++ AuDebugOn(bindex >= 0 && br); ++ ++ err = -EINVAL; ++ suspend = !br; ++ if (suspend) ++ br = au_sbr(sb, bindex); ++ load = !!path; ++ if (!load) { ++ path = &br->br_path; ++ AuDebugOn(!au_br_writable(br->br_perm)); ++ if (unlikely(!au_br_writable(br->br_perm))) ++ goto out; ++ } ++ ++ hdir = NULL; ++ if (suspend) { ++ dir = d_inode(sb->s_root); ++ hdir = au_hinode(au_ii(dir), bindex); ++ dir = hdir->hi_inode; ++ au_hn_inode_lock_nested(hdir, AuLsc_I_CHILD); ++ } else { ++ dir = d_inode(path->dentry); ++ inode_lock_nested(dir, AuLsc_I_CHILD); ++ } ++ hinopath.dentry = vfsub_lkup_one(&hinoname, path->dentry); ++ err = PTR_ERR(hinopath.dentry); ++ if (IS_ERR(hinopath.dentry)) ++ goto out_unlock; + + err = 0; -+ 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; ++ flags = O_RDONLY; ++ if (load) { ++ if (d_is_negative(hinopath.dentry)) ++ goto out_dput; /* success */ ++ } else { ++ if (au_dr_hino_test_empty(&br->br_dirren)) { ++ if (d_is_positive(hinopath.dentry)) { ++ delegated = NULL; ++ err = vfsub_unlink(dir, &hinopath, &delegated, ++ /*force*/0); ++ AuTraceErr(err); ++ if (unlikely(err)) ++ pr_err("ignored err %d, %pd2\n", ++ err, hinopath.dentry); ++ if (unlikely(err == -EWOULDBLOCK)) ++ iput(delegated); ++ err = 0; ++ } ++ goto out_dput; ++ } else if (!d_is_positive(hinopath.dentry)) { ++ err = vfsub_create(dir, &hinopath, 0600, ++ /*want_excl*/false); ++ AuTraceErr(err); ++ if (unlikely(err)) ++ goto out_dput; ++ } ++ flags = O_WRONLY; ++ } ++ hinopath.mnt = path->mnt; ++ hinofile = vfsub_dentry_open(&hinopath, flags); ++ if (suspend) ++ au_hn_inode_unlock(hdir); ++ else ++ inode_unlock(dir); ++ dput(hinopath.dentry); ++ AuTraceErrPtr(hinofile); ++ if (IS_ERR(hinofile)) { ++ err = PTR_ERR(hinofile); ++ goto out; ++ } ++ ++ if (load) ++ err = au_dr_hino_load(&br->br_dirren, hinofile); ++ else ++ err = au_dr_hino_store(sb, br, hinofile); ++ fput(hinofile); ++ goto out; + ++out_dput: ++ dput(hinopath.dentry); ++out_unlock: ++ if (suspend) ++ au_hn_inode_unlock(hdir); ++ else ++ inode_unlock(dir); ++out: ++ AuTraceErr(err); + return err; +} + -+void au_di_fin(struct dentry *dentry) ++/* ---------------------------------------------------------------------- */ ++ ++static int au_dr_brid_init(struct au_dr_brid *brid, const struct path *path) +{ -+ struct au_dinfo *dinfo; ++ int err; ++ struct kstatfs kstfs; ++ dev_t dev; ++ struct dentry *dentry; ++ struct super_block *sb; + -+ dinfo = au_di(dentry); -+ AuRwDestroy(&dinfo->di_rwsem); -+ au_di_free(dinfo); ++ err = vfs_statfs((void *)path, &kstfs); ++ AuTraceErr(err); ++ if (unlikely(err)) ++ goto out; ++ ++ /* todo: support for UUID */ ++ ++ if (kstfs.f_fsid.val[0] || kstfs.f_fsid.val[1]) { ++ brid->type = AuBrid_FSID; ++ brid->fsid = kstfs.f_fsid; ++ } else { ++ dentry = path->dentry; ++ sb = dentry->d_sb; ++ dev = sb->s_dev; ++ if (dev) { ++ brid->type = AuBrid_DEV; ++ brid->dev = dev; ++ } ++ } ++ ++out: ++ return err; +} + -+int au_di_realloc(struct au_dinfo *dinfo, int nbr, int may_shrink) ++int au_dr_br_init(struct super_block *sb, struct au_branch *br, ++ const struct path *path) +{ -+ int err, sz; -+ struct au_hdentry *hdp; ++ int err, i; ++ struct au_dr_br *dr; ++ struct hlist_bl_head *hbl; + -+ AuRwMustWriteLock(&dinfo->di_rwsem); ++ dr = &br->br_dirren; ++ hbl = dr->dr_h_ino; ++ for (i = 0; i < AuDirren_NHASH; i++, hbl++) ++ INIT_HLIST_BL_HEAD(hbl); + -+ 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; -+ } ++ err = au_dr_brid_init(&dr->dr_brid, path); ++ if (unlikely(err)) ++ goto out; ++ ++ if (au_opt_test(au_mntflags(sb), DIRREN)) ++ err = au_dr_hino(sb, /*bindex*/-1, br, path); ++ ++out: ++ AuTraceErr(err); ++ return err; ++} ++ ++int au_dr_br_fin(struct super_block *sb, struct au_branch *br) ++{ ++ int err; ++ ++ err = 0; ++ if (au_br_writable(br->br_perm)) ++ err = au_dr_hino(sb, /*bindex*/-1, br, /*path*/NULL); ++ if (!err) ++ au_dr_hino_free(&br->br_dirren); + + return err; +} + +/* ---------------------------------------------------------------------- */ + -+static void do_ii_write_lock(struct inode *inode, unsigned int lsc) ++static int au_brid_str(struct au_dr_brid *brid, struct inode *h_inode, ++ char *buf, size_t sz) +{ -+ 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); ++ int err; ++ unsigned int major, minor; ++ char *p; ++ ++ p = buf; ++ err = snprintf(p, sz, "%d_", brid->type); ++ AuDebugOn(err > sz); ++ p += err; ++ sz -= err; ++ switch (brid->type) { ++ case AuBrid_Unset: ++ return -EINVAL; ++ case AuBrid_UUID: ++ err = snprintf(p, sz, "%pU", brid->uuid.__u_bits); + break; -+ case AuLsc_DI_PARENT2: -+ ii_write_lock_parent2(inode); ++ case AuBrid_FSID: ++ err = snprintf(p, sz, "%08x-%08x", ++ brid->fsid.val[0], brid->fsid.val[1]); + break; -+ case AuLsc_DI_PARENT3: -+ ii_write_lock_parent3(inode); ++ 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; -+ default: -+ BUG(); + } ++ AuDebugOn(err > sz); ++ p += err; ++ sz -= err; ++ err = snprintf(p, sz, "_%llu", (unsigned long long)h_inode->i_ino); ++ AuDebugOn(err > sz); ++ p += err; ++ sz -= err; ++ ++ return p - buf; +} + -+static void do_ii_read_lock(struct inode *inode, unsigned int lsc) ++static int au_drinfo_name(struct au_branch *br, char *name, int len) +{ -+ 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); ++ int rlen; ++ struct dentry *br_dentry; ++ struct inode *br_inode; ++ ++ br_dentry = au_br_dentry(br); ++ br_inode = d_inode(br_dentry); ++ rlen = au_brid_str(&br->br_dirren.dr_brid, br_inode, name, len); ++ AuDebugOn(rlen >= AUFS_DIRREN_ENV_VAL_SZ); ++ AuDebugOn(rlen > len); ++ ++ return rlen; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++/* ++ * from the given @h_dentry, construct drinfo at @*fdata. ++ * when the size of @*fdata is not enough, reallocate and return new @fdata and ++ * @allocated. ++ */ ++static int au_drinfo_construct(struct au_drinfo_fdata **fdata, ++ struct dentry *h_dentry, ++ unsigned char *allocated) ++{ ++ int err, v; ++ struct au_drinfo_fdata *f, *p; ++ struct au_drinfo *drinfo; ++ struct inode *h_inode; ++ struct qstr *qname; ++ ++ err = 0; ++ f = *fdata; ++ h_inode = d_inode(h_dentry); ++ qname = &h_dentry->d_name; ++ drinfo = &f->drinfo; ++ drinfo->ino = 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(drinfo->ino), drinfo->oldnamelen, drinfo->oldname); ++ ++out: ++ AuTraceErr(err); ++ return err; ++} ++ ++/* callers have to free the return value */ ++static struct au_drinfo *au_drinfo_read_k(struct file *file, ino_t h_ino) ++{ ++ struct au_drinfo *ret, *drinfo; ++ struct au_drinfo_fdata fdata; ++ int len; ++ loff_t pos; ++ ssize_t ssz; ++ ++ ret = ERR_PTR(-EIO); ++ pos = 0; ++ ssz = vfsub_read_k(file, &fdata, sizeof(fdata), &pos); ++ if (unlikely(ssz != sizeof(fdata))) { ++ AuIOErr("ssz %zd, %u, %pD2\n", ++ ssz, (unsigned int)sizeof(fdata), file); ++ goto out; ++ } ++ ++ fdata.magic = ntohl(fdata.magic); ++ switch (fdata.magic) { ++ case AUFS_DRINFO_MAGIC_V1: + break; + default: -+ BUG(); ++ 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(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)) { ++ kfree(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; +} + -+void di_read_lock(struct dentry *d, int flags, unsigned int lsc) ++/* ---------------------------------------------------------------------- */ ++ ++/* in order to be revertible */ ++struct au_drinfo_rev_elm { ++ int created; ++ struct dentry *info_dentry; ++ struct au_drinfo *info_last; ++}; ++ ++struct au_drinfo_rev { ++ unsigned char already; ++ aufs_bindex_t nelm; ++ struct au_drinfo_rev_elm elm[0]; ++}; ++ ++/* todo: isn't it too large? */ ++struct au_drinfo_store { ++ struct path h_ppath; ++ struct dentry *h_dentry; ++ struct au_drinfo_fdata *fdata; ++ char *infoname; /* inside of whname, just after PFX */ ++ char whname[sizeof(AUFS_WH_DR_INFO_PFX) + AUFS_DIRREN_ENV_VAL_SZ]; ++ aufs_bindex_t btgt, btail; ++ unsigned char no_sio, ++ allocated, /* current size of *fdata */ ++ infonamelen, /* room size for p */ ++ whnamelen, /* length of the genarated name */ ++ renameback; /* renamed back */ ++}; ++ ++/* on rename(2) error, the caller should revert it using @elm */ ++static int au_drinfo_do_store(struct au_drinfo_store *w, ++ struct au_drinfo_rev_elm *elm) +{ -+ struct inode *inode; ++ 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; + -+ 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); ++ AuDebugOn(elm ++ && memcmp(elm, page_address(ZERO_PAGE(0)), sizeof(*elm))); ++ ++ infopath.dentry = vfsub_lookup_one_len(w->whname, w->h_ppath.dentry, ++ w->whnamelen); ++ AuTraceErrPtr(infopath.dentry); ++ if (IS_ERR(infopath.dentry)) { ++ err = PTR_ERR(infopath.dentry); ++ goto out; ++ } ++ ++ err = 0; ++ h_dir = d_inode(w->h_ppath.dentry); ++ if (elm && d_is_negative(infopath.dentry)) { ++ err = vfsub_create(h_dir, &infopath, 0600, /*want_excl*/true); ++ AuTraceErr(err); ++ if (unlikely(err)) ++ goto out_dput; ++ elm->created = 1; ++ elm->info_dentry = dget(infopath.dentry); ++ } ++ ++ infofile = vfsub_dentry_open(&infopath, O_RDWR); ++ AuTraceErrPtr(infofile); ++ if (IS_ERR(infofile)) { ++ err = PTR_ERR(infofile); ++ goto out_dput; ++ } ++ ++ h_inode = d_inode(infopath.dentry); ++ if (elm && i_size_read(h_inode)) { ++ h_inode = d_inode(w->h_dentry); ++ elm->info_last = au_drinfo_read_k(infofile, h_inode->i_ino); ++ AuTraceErrPtr(elm->info_last); ++ if (IS_ERR(elm->info_last)) { ++ err = PTR_ERR(elm->info_last); ++ elm->info_last = NULL; ++ AuDebugOn(elm->info_dentry); ++ goto out_fput; ++ } ++ } ++ ++ if (elm && w->renameback) { ++ delegated = NULL; ++ err = vfsub_unlink(h_dir, &infopath, &delegated, /*force*/0); ++ AuTraceErr(err); ++ if (unlikely(err == -EWOULDBLOCK)) ++ iput(delegated); ++ goto out_fput; ++ } ++ ++ pos = 0; ++ qname = &w->h_dentry->d_name; ++ len = sizeof(*w->fdata) + qname->len; ++ if (!elm) ++ len = sizeof(*w->fdata) + w->fdata->drinfo.oldnamelen; ++ ssz = vfsub_write_k(infofile, w->fdata, len, &pos); ++ if (ssz == len) { ++ AuDbg("hi%llu, %.*s\n", w->fdata->drinfo.ino, ++ w->fdata->drinfo.oldnamelen, w->fdata->drinfo.oldname); ++ goto out_fput; /* success */ ++ } else { ++ err = -EIO; ++ if (ssz < 0) ++ err = ssz; ++ /* the caller should revert it using @elm */ + } ++ ++out_fput: ++ fput(infofile); ++out_dput: ++ dput(infopath.dentry); ++out: ++ AuTraceErr(err); ++ return err; +} + -+void di_read_unlock(struct dentry *d, int flags) ++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 inode *inode; ++ struct au_call_drinfo_do_store_args *a = args; + -+ 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); -+ } ++ *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; + } -+ au_rw_read_unlock(&au_di(d)->di_rwsem); ++ AuTraceErr(err); ++ ++ return err; +} + -+void di_downgrade_lock(struct dentry *d, int flags) ++static int au_drinfo_store_work_init(struct au_drinfo_store *w, ++ aufs_bindex_t btgt) +{ -+ 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); ++ int err; ++ ++ memset(w, 0, sizeof(*w)); ++ w->allocated = roundup_pow_of_two(sizeof(*w->fdata) + 40); ++ strcpy(w->whname, AUFS_WH_DR_INFO_PFX); ++ w->infoname = w->whname + sizeof(AUFS_WH_DR_INFO_PFX) - 1; ++ w->infonamelen = sizeof(w->whname) - sizeof(AUFS_WH_DR_INFO_PFX); ++ w->btgt = btgt; ++ w->no_sio = !!uid_eq(current_fsuid(), GLOBAL_ROOT_UID); ++ ++ err = -ENOMEM; ++ w->fdata = kcalloc(1, w->allocated, GFP_NOFS); ++ if (unlikely(!w->fdata)) { ++ AuTraceErr(err); ++ goto out; ++ } ++ w->fdata->magic = htonl(AUFS_DRINFO_MAGIC_V1); ++ err = 0; ++ ++out: ++ return err; +} + -+void di_write_lock(struct dentry *d, unsigned int lsc) ++static void au_drinfo_store_work_fin(struct au_drinfo_store *w) +{ -+ 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); ++ kfree(w->fdata); +} + -+void di_write_unlock(struct dentry *d) ++static void au_drinfo_store_rev(struct au_drinfo_rev *rev, ++ struct au_drinfo_store *w) +{ -+ 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_drinfo_rev_elm *elm; ++ struct inode *h_dir, *delegated; ++ int err, nelm; ++ struct path infopath = { ++ .mnt = w->h_ppath.mnt ++ }; ++ ++ h_dir = d_inode(w->h_ppath.dentry); ++ IMustLock(h_dir); ++ ++ err = 0; ++ elm = rev->elm; ++ for (nelm = rev->nelm; nelm > 0; nelm--, elm++) { ++ AuDebugOn(elm->created && elm->info_last); ++ if (elm->created) { ++ AuDbg("here\n"); ++ delegated = NULL; ++ infopath.dentry = elm->info_dentry; ++ err = vfsub_unlink(h_dir, &infopath, &delegated, ++ !w->no_sio); ++ AuTraceErr(err); ++ if (unlikely(err == -EWOULDBLOCK)) ++ iput(delegated); ++ dput(elm->info_dentry); ++ } else if (elm->info_last) { ++ AuDbg("here\n"); ++ w->fdata->drinfo = *elm->info_last; ++ memcpy(w->fdata->drinfo.oldname, ++ elm->info_last->oldname, ++ elm->info_last->oldnamelen); ++ err = au_drinfo_store_sio(w, /*elm*/NULL); ++ kfree(elm->info_last); ++ } ++ if (unlikely(err)) ++ AuIOErr("%d, %s\n", err, w->whname); ++ /* go on even if err */ ++ } +} + -+void di_write_lock2_child(struct dentry *d1, struct dentry *d2, int isdir) ++/* 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) +{ -+ AuDebugOn(d1 == d2 -+ || d_inode(d1) == d_inode(d2) -+ || d1->d_sb != d2->d_sb); ++ int err, sz, nelm; ++ aufs_bindex_t bindex, btail; ++ struct au_drinfo_store work; ++ struct au_drinfo_rev *rev, **p; ++ struct au_drinfo_rev_elm *elm; ++ struct super_block *sb; ++ struct au_branch *br; ++ struct au_hinode *hdir; ++ ++ err = au_drinfo_store_work_init(&work, btgt); ++ AuTraceErr(err); ++ if (unlikely(err)) ++ goto out; ++ ++ err = -ENOMEM; ++ btail = au_dbtaildir(dentry); ++ nelm = btail - btgt; ++ sz = sizeof(*rev) + sizeof(*elm) * nelm; ++ rev = kcalloc(1, sz, GFP_NOFS); ++ if (unlikely(!rev)) { ++ AuTraceErr(err); ++ goto out_args; ++ } ++ rev->nelm = nelm; ++ elm = rev->elm; ++ p = _rev; ++ *p = rev; ++ ++ err = 0; ++ sb = dentry->d_sb; ++ work.h_ppath.dentry = au_h_dptr(dentry, btgt); ++ work.h_ppath.mnt = au_sbr_mnt(sb, btgt); ++ hdir = au_hi(d_inode(dentry), btgt); ++ au_hn_inode_lock_nested(hdir, AuLsc_I_CHILD); ++ for (bindex = btgt + 1; bindex <= btail; bindex++, elm++) { ++ work.h_dentry = au_h_dptr(dentry, bindex); ++ if (!work.h_dentry) ++ continue; ++ ++ err = au_drinfo_construct(&work.fdata, work.h_dentry, ++ &work.allocated); ++ AuTraceErr(err); ++ if (unlikely(err)) ++ break; ++ ++ work.renameback = au_qstreq(&work.h_dentry->d_name, dst_name); ++ br = au_sbr(sb, bindex); ++ work.whnamelen = sizeof(AUFS_WH_DR_INFO_PFX) - 1; ++ work.whnamelen += au_drinfo_name(br, work.infoname, ++ work.infonamelen); ++ AuDbg("whname %.*s, i%llu, %.*s\n", ++ work.whnamelen, work.whname, ++ be64_to_cpu(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); ++ kfree(rev); ++ *p = NULL; ++ } ++ au_hn_inode_unlock(hdir); ++ ++out_args: ++ au_drinfo_store_work_fin(&work); ++out: ++ return err; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++int au_dr_rename(struct dentry *src, aufs_bindex_t bindex, ++ struct qstr *dst_name, void *_rev) ++{ ++ int err, already; ++ ino_t ino; ++ struct super_block *sb; ++ struct au_branch *br; ++ struct au_dr_br *dr; ++ struct dentry *h_dentry; ++ struct inode *h_inode; ++ struct au_dr_hino *ent; ++ struct au_drinfo_rev *rev, **p; ++ ++ AuDbg("bindex %d\n", bindex); + -+ if (isdir && au_test_subdir(d1, d2)) { -+ di_write_lock_child(d1); -+ di_write_lock_child2(d2); -+ } else { -+ /* there should be no races */ -+ di_write_lock_child(d2); -+ di_write_lock_child2(d1); ++ err = -ENOMEM; ++ ent = kmalloc(sizeof(*ent), GFP_NOFS); ++ if (unlikely(!ent)) ++ goto out; ++ ++ sb = src->d_sb; ++ br = au_sbr(sb, bindex); ++ dr = &br->br_dirren; ++ h_dentry = au_h_dptr(src, bindex); ++ h_inode = d_inode(h_dentry); ++ ino = h_inode->i_ino; ++ ent->dr_h_ino = ino; ++ already = au_dr_hino_test_add(dr, ino, ent); ++ AuDbg("b%d, hi%llu, already %d\n", ++ bindex, (unsigned long long)ino, already); ++ ++ err = au_drinfo_store(src, bindex, dst_name, _rev); ++ AuTraceErr(err); ++ if (!err) { ++ p = _rev; ++ rev = *p; ++ rev->already = already; ++ goto out; /* success */ + } ++ ++ /* revert */ ++ if (!already) ++ au_dr_hino_del(dr, ent); ++ kfree(ent); ++ ++out: ++ AuTraceErr(err); ++ return err; +} + -+void di_write_lock2_parent(struct dentry *d1, struct dentry *d2, int isdir) ++void au_dr_rename_fin(struct dentry *src, aufs_bindex_t btgt, void *_rev) +{ -+ AuDebugOn(d1 == d2 -+ || d_inode(d1) == d_inode(d2) -+ || d1->d_sb != d2->d_sb); ++ struct au_drinfo_rev *rev; ++ struct au_drinfo_rev_elm *elm; ++ int nelm; + -+ if (isdir && au_test_subdir(d1, d2)) { -+ di_write_lock_parent(d1); -+ di_write_lock_parent2(d2); -+ } else { -+ /* there should be no races */ -+ di_write_lock_parent(d2); -+ di_write_lock_parent2(d1); ++ rev = _rev; ++ elm = rev->elm; ++ for (nelm = rev->nelm; nelm > 0; nelm--, elm++) { ++ dput(elm->info_dentry); ++ kfree(elm->info_last); + } ++ kfree(rev); +} + -+void di_write_unlock2(struct dentry *d1, struct dentry *d2) ++void au_dr_rename_rev(struct dentry *src, aufs_bindex_t btgt, void *_rev) +{ -+ 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); -+} ++ int err; ++ struct au_drinfo_store work; ++ struct au_drinfo_rev *rev = _rev; ++ struct super_block *sb; ++ struct au_branch *br; ++ struct inode *h_inode; ++ struct au_dr_br *dr; ++ struct au_dr_hino *ent; + -+/* ---------------------------------------------------------------------- */ ++ err = au_drinfo_store_work_init(&work, btgt); ++ if (unlikely(err)) ++ goto out; + -+struct dentry *au_h_dptr(struct dentry *dentry, aufs_bindex_t bindex) -+{ -+ struct dentry *d; ++ 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; + -+ DiMustAnyLock(dentry); ++ 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); ++ kfree(ent); + -+ 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; ++out: ++ kfree(rev); ++ if (unlikely(err)) ++ pr_err("failed to remove dirren info\n"); +} + -+/* -+ * extended version of au_h_dptr(). -+ * returns a hashed and positive (or linkable) h_dentry in bindex, NULL, or -+ * error. -+ */ -+struct dentry *au_h_d_alias(struct dentry *dentry, aufs_bindex_t bindex) ++/* ---------------------------------------------------------------------- */ ++ ++static struct au_drinfo *au_drinfo_do_load(struct path *h_ppath, ++ char *whname, int whnamelen, ++ struct dentry **info_dentry) +{ -+ struct dentry *h_dentry; -+ struct inode *inode, *h_inode; ++ struct au_drinfo *drinfo; ++ struct file *f; ++ struct inode *h_dir; ++ struct path infopath; ++ int unlocked; + -+ AuDebugOn(d_really_is_negative(dentry)); ++ AuDbg("%pd/%.*s\n", h_ppath->dentry, whnamelen, whname); + -+ 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 */ ++ *info_dentry = NULL; ++ drinfo = NULL; ++ unlocked = 0; ++ h_dir = d_inode(h_ppath->dentry); ++ vfsub_inode_lock_shared_nested(h_dir, AuLsc_I_PARENT); ++ infopath.dentry = vfsub_lookup_one_len(whname, h_ppath->dentry, ++ whnamelen); ++ if (IS_ERR(infopath.dentry)) { ++ drinfo = (void *)infopath.dentry; ++ goto out; + } + -+ inode = d_inode(dentry); -+ AuDebugOn(bindex < au_ibtop(inode)); -+ AuDebugOn(au_ibbot(inode) < bindex); -+ h_inode = au_h_iptr(inode, bindex); -+ h_dentry = d_find_alias(h_inode); -+ if (h_dentry) { -+ if (!IS_ERR(h_dentry)) { -+ if (!au_d_linkable(h_dentry)) -+ goto out; /* success */ -+ dput(h_dentry); -+ } else -+ goto out; -+ } ++ if (d_is_negative(infopath.dentry)) ++ goto out_dput; /* success */ + -+ 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; -+ } ++ infopath.mnt = h_ppath->mnt; ++ f = vfsub_dentry_open(&infopath, O_RDONLY); ++ inode_unlock_shared(h_dir); ++ unlocked = 1; ++ if (IS_ERR(f)) { ++ drinfo = (void *)f; ++ goto out_dput; + } + ++ drinfo = au_drinfo_read_k(f, /*h_ino*/0); ++ if (IS_ERR_OR_NULL(drinfo)) ++ goto out_fput; ++ ++ AuDbg("oldname %.*s\n", drinfo->oldnamelen, drinfo->oldname); ++ *info_dentry = dget(infopath.dentry); /* keep it alive */ ++ ++out_fput: ++ fput(f); ++out_dput: ++ dput(infopath.dentry); +out: -+ AuDbgDentry(h_dentry); -+ return h_dentry; ++ if (!unlocked) ++ inode_unlock_shared(h_dir); ++ AuTraceErrPtr(drinfo); ++ return drinfo; +} + -+aufs_bindex_t au_dbtail(struct dentry *dentry) ++struct au_drinfo_do_load_args { ++ struct au_drinfo **drinfop; ++ struct path *h_ppath; ++ char *whname; ++ int whnamelen; ++ struct dentry **info_dentry; ++}; ++ ++static void au_call_drinfo_do_load(void *args) +{ -+ aufs_bindex_t bbot, bwh; ++ struct au_drinfo_do_load_args *a = args; + -+ 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; ++ *a->drinfop = au_drinfo_do_load(a->h_ppath, a->whname, a->whnamelen, ++ a->info_dentry); +} + -+aufs_bindex_t au_dbtaildir(struct dentry *dentry) ++struct au_drinfo_load { ++ struct path h_ppath; ++ struct qstr *qname; ++ unsigned char no_sio; ++ ++ aufs_bindex_t ninfo; ++ struct au_drinfo **drinfo; ++}; ++ ++static int au_drinfo_load(struct au_drinfo_load *w, aufs_bindex_t bindex, ++ struct au_branch *br) +{ -+ aufs_bindex_t bbot, bopq; ++ int err, wkq_err, whnamelen, e; ++ char whname[sizeof(AUFS_WH_DR_INFO_PFX) + AUFS_DIRREN_ENV_VAL_SZ] ++ = AUFS_WH_DR_INFO_PFX; ++ struct au_drinfo *drinfo; ++ struct qstr oldname; ++ struct inode *h_dir, *delegated; ++ struct dentry *info_dentry; ++ struct path infopath; ++ ++ whnamelen = sizeof(AUFS_WH_DR_INFO_PFX) - 1; ++ whnamelen += au_drinfo_name(br, whname + whnamelen, ++ sizeof(whname) - whnamelen); ++ if (w->no_sio) ++ drinfo = au_drinfo_do_load(&w->h_ppath, whname, whnamelen, ++ &info_dentry); ++ else { ++ struct au_drinfo_do_load_args args = { ++ .drinfop = &drinfo, ++ .h_ppath = &w->h_ppath, ++ .whname = whname, ++ .whnamelen = whnamelen, ++ .info_dentry = &info_dentry ++ }; ++ wkq_err = au_wkq_wait(au_call_drinfo_do_load, &args); ++ if (unlikely(wkq_err)) ++ drinfo = ERR_PTR(wkq_err); ++ } ++ err = PTR_ERR(drinfo); ++ if (IS_ERR_OR_NULL(drinfo)) ++ goto out; + -+ bbot = au_dbtail(dentry); -+ if (0 <= bbot) { -+ bopq = au_dbdiropq(dentry); -+ if (0 <= bopq && bopq < bbot) -+ bbot = bopq; ++ err = 0; ++ oldname.len = drinfo->oldnamelen; ++ oldname.name = drinfo->oldname; ++ if (au_qstreq(w->qname, &oldname)) { ++ /* the name is renamed back */ ++ kfree(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); + } -+ return bbot; ++ kfree(w->drinfo[bindex]); ++ w->drinfo[bindex] = drinfo; ++ dput(info_dentry); ++ ++out: ++ AuTraceErr(err); ++ return err; +} + +/* ---------------------------------------------------------------------- */ + -+void au_set_h_dptr(struct dentry *dentry, aufs_bindex_t bindex, -+ struct dentry *h_dentry) ++static void au_dr_lkup_free(struct au_drinfo **drinfo, int n) +{ -+ struct au_dinfo *dinfo; -+ struct au_hdentry *hd; -+ struct au_branch *br; -+ -+ DiMustWriteLock(dentry); ++ struct au_drinfo **p = drinfo; + -+ 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; -+ } ++ while (n-- > 0) ++ kfree(*drinfo++); ++ kfree(p); +} + -+int au_dbrange_test(struct dentry *dentry) ++int au_dr_lkup(struct au_do_lookup_args *lkup, struct dentry *dentry, ++ aufs_bindex_t btgt) +{ -+ int err; -+ aufs_bindex_t btop, bbot; ++ 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; + -+ err = 0; -+ btop = au_dbtop(dentry); -+ bbot = au_dbbot(dentry); -+ if (btop >= 0) -+ AuDebugOn(bbot < 0 && btop > bbot); -+ else { -+ err = -EIO; -+ AuDebugOn(bbot >= 0); ++ AuDbg("%.*s, name %.*s, whname %.*s, b%d\n", ++ AuLNPair(&dentry->d_name), AuLNPair(&lkup->dirren.dr_name), ++ AuLNPair(&lkup->whname), btgt); ++ ++ sb = dentry->d_sb; ++ bbot = au_sbbot(sb); ++ w.ninfo = bbot + 1; ++ if (!lkup->dirren.drinfo) { ++ lkup->dirren.drinfo = kcalloc(w.ninfo, ++ sizeof(*lkup->dirren.drinfo), ++ GFP_NOFS); ++ if (unlikely(!lkup->dirren.drinfo)) { ++ err = -ENOMEM; ++ goto out; ++ } ++ lkup->dirren.ninfo = w.ninfo; ++ } ++ w.drinfo = lkup->dirren.drinfo; ++ w.no_sio = !!uid_eq(current_fsuid(), GLOBAL_ROOT_UID); ++ w.h_ppath.dentry = au_h_dptr(dentry, btgt); ++ AuDebugOn(!w.h_ppath.dentry); ++ w.h_ppath.mnt = au_sbr_mnt(sb, btgt); ++ w.qname = &dentry->d_name; ++ ++ ninfo = 0; ++ for (bindex = btgt + 1; bindex <= bbot; bindex++) { ++ br = au_sbr(sb, bindex); ++ err = au_drinfo_load(&w, bindex, br); ++ if (unlikely(err)) ++ goto out_free; ++ if (w.drinfo[bindex]) ++ ninfo++; + } ++ if (!ninfo) { ++ br = au_sbr(sb, btgt); ++ h_dir = d_inode(w.h_ppath.dentry); ++ ent = au_dr_hino_find(&br->br_dirren, h_dir->i_ino); ++ AuDebugOn(!ent); ++ au_dr_hino_del(&br->br_dirren, ent); ++ kfree(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_digen_test(struct dentry *dentry, unsigned int sigen) ++void au_dr_lkup_fin(struct au_do_lookup_args *lkup) ++{ ++ au_dr_lkup_free(lkup->dirren.drinfo, lkup->dirren.ninfo); ++} ++ ++int au_dr_lkup_name(struct au_do_lookup_args *lkup, aufs_bindex_t btgt) +{ + int err; ++ struct au_drinfo *drinfo; + + err = 0; -+ if (unlikely(au_digen(dentry) != sigen -+ || au_iigen_test(d_inode(dentry), sigen))) -+ err = -EIO; ++ if (!lkup->dirren.drinfo) ++ goto out; ++ AuDebugOn(lkup->dirren.ninfo < btgt + 1); ++ drinfo = lkup->dirren.drinfo[btgt + 1]; ++ if (!drinfo) ++ goto out; + ++ kfree(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_update_digen(struct dentry *dentry) ++int au_dr_lkup_h_ino(struct au_do_lookup_args *lkup, aufs_bindex_t bindex, ++ ino_t h_ino) +{ -+ atomic_set(&au_di(dentry)->di_generation, au_sigen(dentry->d_sb)); -+ /* smp_mb(); */ /* atomic_set */ -+} ++ int match; ++ struct au_drinfo *drinfo; + -+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; ++ match = 1; ++ if (!lkup->dirren.drinfo) ++ goto out; ++ AuDebugOn(lkup->dirren.ninfo < bindex + 1); ++ drinfo = lkup->dirren.drinfo[bindex + 1]; ++ if (!drinfo) ++ goto out; + -+ DiMustWriteLock(dentry); ++ match = (drinfo->ino == h_ino); ++ AuDbg("match %d\n", match); + -+ dinfo = au_di(dentry); -+ if (!dinfo || dinfo->di_btop < 0) -+ return; ++out: ++ return match; ++} + -+ if (do_put_zero) { -+ bbot = dinfo->di_bbot; -+ bindex = dinfo->di_btop; -+ hdp = au_hdentry(dinfo, bindex); -+ for (; bindex <= bbot; bindex++, hdp++) { -+ h_d = hdp->hd_dentry; -+ if (h_d && d_is_negative(h_d)) -+ au_set_h_dptr(dentry, bindex, NULL); -+ } -+ } ++/* ---------------------------------------------------------------------- */ + -+ dinfo->di_btop = 0; -+ hdp = au_hdentry(dinfo, dinfo->di_btop); -+ for (; dinfo->di_btop <= dinfo->di_bbot; dinfo->di_btop++, hdp++) -+ if (hdp->hd_dentry) -+ break; -+ if (dinfo->di_btop > dinfo->di_bbot) { -+ dinfo->di_btop = -1; -+ dinfo->di_bbot = -1; -+ return; ++int au_dr_opt_set(struct super_block *sb) ++{ ++ int err; ++ aufs_bindex_t bindex, bbot; ++ struct au_branch *br; ++ ++ err = 0; ++ bbot = au_sbbot(sb); ++ for (bindex = 0; !err && bindex <= bbot; bindex++) { ++ br = au_sbr(sb, bindex); ++ err = au_dr_hino(sb, bindex, /*br*/NULL, &br->br_path); + } + -+ 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); ++ return err; +} + -+void au_update_dbtop(struct dentry *dentry) ++int au_dr_opt_flush(struct super_block *sb) +{ ++ int err; + aufs_bindex_t bindex, bbot; -+ struct dentry *h_dentry; ++ struct au_branch *br; + -+ 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); ++ err = 0; ++ bbot = au_sbbot(sb); ++ for (bindex = 0; !err && bindex <= bbot; bindex++) { ++ br = au_sbr(sb, bindex); ++ if (au_br_writable(br->br_perm)) ++ err = au_dr_hino(sb, bindex, /*br*/NULL, /*path*/NULL); + } ++ ++ return err; +} + -+void au_update_dbbot(struct dentry *dentry) ++int au_dr_opt_clr(struct super_block *sb, int no_flush) +{ -+ aufs_bindex_t bindex, btop; -+ struct dentry *h_dentry; ++ int err; ++ aufs_bindex_t bindex, bbot; ++ struct au_branch *br; + -+ 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); ++ err = 0; ++ if (!no_flush) { ++ err = au_dr_opt_flush(sb); ++ if (unlikely(err)) ++ goto out; + } -+} + -+int au_find_dbindex(struct dentry *dentry, struct dentry *h_dentry) -+{ -+ aufs_bindex_t bindex, bbot; ++ bbot = au_sbbot(sb); ++ for (bindex = 0; bindex <= bbot; bindex++) { ++ br = au_sbr(sb, bindex); ++ au_dr_hino_free(&br->br_dirren); ++ } + -+ bbot = au_dbbot(dentry); -+ for (bindex = au_dbtop(dentry); bindex <= bbot; bindex++) -+ if (au_h_dptr(dentry, bindex) == h_dentry) -+ return bindex; -+ return -1; ++out: ++ return err; +} -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 2016-10-09 16:55:36.489368218 +0200 -@@ -0,0 +1,762 @@ +diff -urNp -x '*.orig' linux-4.9/fs/aufs/dirren.h linux-4.9/fs/aufs/dirren.h +--- linux-4.9/fs/aufs/dirren.h 1970-01-01 01:00:00.000000000 +0100 ++++ linux-4.9/fs/aufs/dirren.h 2021-02-24 16:15:09.524906971 +0100 +@@ -0,0 +1,145 @@ +/* -+ * Copyright (C) 2005-2016 Junjiro R. Okajima ++ * Copyright (C) 2017-2018 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by @@ -9646,1272 +11527,1430 @@ diff -urN /usr/share/empty/fs/aufs/dir.c linux/fs/aufs/dir.c + */ + +/* -+ * directory operations ++ * renamed dir info + */ + -+#include -+#include "aufs.h" -+ -+void au_add_nlink(struct inode *dir, struct inode *h_dir) -+{ -+ unsigned int nlink; -+ -+ AuDebugOn(!S_ISDIR(dir->i_mode) || !S_ISDIR(h_dir->i_mode)); ++#ifndef __AUFS_DIRREN_H__ ++#define __AUFS_DIRREN_H__ + -+ 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); -+} ++#ifdef __KERNEL__ + -+void au_sub_nlink(struct inode *dir, struct inode *h_dir) -+{ -+ unsigned int nlink; ++#include ++#include ++#include "hbl.h" + -+ AuDebugOn(!S_ISDIR(dir->i_mode) || !S_ISDIR(h_dir->i_mode)); ++#define AuDirren_NHASH 100 + -+ 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); -+} ++#ifdef CONFIG_AUFS_DIRREN ++/* copied from linux/fs/xfs/uuid.h */ ++typedef struct { ++ unsigned char __u_bits[16]; ++} uuid_t; + -+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; ++#define __UUID_TMPLT "01234567-0123-4567-0123-456701234567" + -+ sz = 0; -+ if (file) { -+ AuDebugOn(!d_is_dir(file->f_path.dentry)); ++enum au_brid_type { ++ AuBrid_Unset, ++ AuBrid_UUID, ++ AuBrid_FSID, ++ AuBrid_DEV ++}; + -+ 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)); ++struct au_dr_brid { ++ enum au_brid_type type; ++ union { ++ uuid_t uuid; /* unimplemented yet */ ++ fsid_t fsid; ++ dev_t dev; ++ }; ++}; + -+ bbot = au_dbtaildir(dentry); -+ for (bindex = au_dbtop(dentry); -+ bindex <= bbot && sz < KMALLOC_MAX_SIZE; -+ bindex++) { -+ h_dentry = au_h_dptr(dentry, bindex); -+ if (h_dentry && d_is_positive(h_dentry)) -+ sz += i_size_read(d_inode(h_dentry)); -+ } -+ } -+ if (sz < KMALLOC_MAX_SIZE) -+ sz = roundup_pow_of_two(sz); -+ if (sz > KMALLOC_MAX_SIZE) -+ sz = KMALLOC_MAX_SIZE; -+ else if (sz < NAME_MAX) { -+ BUILD_BUG_ON(AUFS_RDBLK_DEF < NAME_MAX); -+ sz = AUFS_RDBLK_DEF; -+ } -+ return sz; -+} ++/* 20 is the max digits length of ulong 64 */ ++/* brid-type "_" uuid "_" inum */ ++#define AUFS_DIRREN_FNAME_SZ (1 + 1 + sizeof(__UUID_TMPLT) + 20) ++#define AUFS_DIRREN_ENV_VAL_SZ (AUFS_DIRREN_FNAME_SZ + 1 + 20) + -+struct au_dir_ts_arg { -+ struct dentry *dentry; -+ aufs_bindex_t brid; ++struct au_dr_hino { ++ struct hlist_bl_node dr_hnode; ++ ino_t dr_h_ino; +}; + -+static void au_do_dir_ts(void *arg) -+{ -+ struct au_dir_ts_arg *a = arg; -+ struct au_dtime dt; -+ struct path h_path; -+ struct inode *dir, *h_dir; -+ struct super_block *sb; -+ struct au_branch *br; -+ struct au_hinode *hdir; -+ int err; -+ aufs_bindex_t btop, bindex; -+ -+ sb = a->dentry->d_sb; -+ if (d_really_is_negative(a->dentry)) -+ goto out; -+ /* no dir->i_mutex lock */ -+ aufs_read_lock(a->dentry, AuLock_DW); /* noflush */ ++struct au_dr_br { ++ struct hlist_bl_head dr_h_ino[AuDirren_NHASH]; ++ struct au_dr_brid dr_brid; ++}; + -+ dir = d_inode(a->dentry); -+ btop = au_ibtop(dir); -+ bindex = au_br_index(sb, a->brid); -+ if (bindex < btop) -+ goto out_unlock; ++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 + -+ br = au_sbr(sb, bindex); -+ h_path.dentry = au_h_dptr(a->dentry, bindex); -+ if (!h_path.dentry) -+ goto out_unlock; -+ h_path.mnt = au_br_mnt(br); -+ au_dtime_store(&dt, a->dentry, &h_path); ++/* ---------------------------------------------------------------------- */ + -+ br = au_sbr(sb, btop); -+ if (!au_br_writable(br->br_perm)) -+ goto out_unlock; -+ h_path.dentry = au_h_dptr(a->dentry, btop); -+ h_path.mnt = au_br_mnt(br); -+ err = vfsub_mnt_want_write(h_path.mnt); -+ if (err) -+ goto out_unlock; -+ hdir = au_hi(dir, btop); -+ au_hn_inode_lock_nested(hdir, AuLsc_I_PARENT); -+ h_dir = au_h_iptr(dir, btop); -+ if (h_dir->i_nlink -+ && timespec_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); ++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 + -+out_unlock: -+ aufs_read_unlock(a->dentry, AuLock_DW); -+out: -+ dput(a->dentry); -+ au_nwt_done(&au_sbi(sb)->si_nowait); -+ au_delayed_kfree(arg); -+} ++/* ---------------------------------------------------------------------- */ + -+void au_dir_ts(struct inode *dir, aufs_bindex_t bindex) ++#ifdef CONFIG_AUFS_DIRREN ++static inline int au_dr_ihash(ino_t h_ino) +{ -+ int perm, wkq_err; -+ aufs_bindex_t btop; -+ struct au_dir_ts_arg *arg; -+ struct dentry *dentry; -+ struct super_block *sb; -+ -+ IMustLock(dir); -+ -+ dentry = d_find_any_alias(dir); -+ AuDebugOn(!dentry); -+ sb = dentry->d_sb; -+ btop = au_ibtop(dir); -+ if (btop == bindex) { -+ au_cpup_attr_timesizes(dir); -+ goto out; -+ } -+ -+ perm = au_sbr_perm(sb, btop); -+ if (!au_br_writable(perm)) -+ goto out; -+ -+ arg = kmalloc(sizeof(*arg), GFP_NOFS); -+ if (!arg) -+ goto out; ++ return h_ino % AuDirren_NHASH; ++} ++#else ++AuStubInt0(au_dr_ihash, ino_t h_ino); ++#endif + -+ 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_delayed_kfree(arg); -+ } ++#endif /* __KERNEL__ */ ++#endif /* __AUFS_DIRREN_H__ */ +diff -urNp -x '*.orig' linux-4.9/fs/aufs/dynop.c linux-4.9/fs/aufs/dynop.c +--- linux-4.9/fs/aufs/dynop.c 1970-01-01 01:00:00.000000000 +0100 ++++ linux-4.9/fs/aufs/dynop.c 2021-02-24 16:15:09.524906971 +0100 +@@ -0,0 +1,369 @@ ++/* ++ * Copyright (C) 2010-2018 Junjiro R. Okajima ++ * ++ * This program, aufs is free software; you can redistribute it and/or modify ++ * it under the terms of the GNU General Public License as published by ++ * the Free Software Foundation; either version 2 of the License, or ++ * (at your option) any later version. ++ * ++ * This program is distributed in the hope that it will be useful, ++ * but WITHOUT ANY WARRANTY; without even the implied warranty of ++ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the ++ * GNU General Public License for more details. ++ * ++ * You should have received a copy of the GNU General Public License ++ * along with this program. If not, see . ++ */ + -+out: -+ dput(dentry); -+} ++/* ++ * dynamically customizable operations for regular files ++ */ + -+/* ---------------------------------------------------------------------- */ ++#include "aufs.h" + -+static int reopen_dir(struct file *file) ++#define DyPrSym(key) AuDbgSym(key->dk_op.dy_hop) ++ ++/* ++ * How large will these lists be? ++ * Usually just a few elements, 20-30 at most for each, I guess. ++ */ ++static struct hlist_bl_head dynop[AuDyLast]; ++ ++static struct au_dykey *dy_gfind_get(struct hlist_bl_head *hbl, ++ const void *h_op) +{ -+ int err; -+ unsigned int flags; -+ aufs_bindex_t bindex, btail, btop; -+ struct dentry *dentry, *h_dentry; -+ struct file *h_file; ++ struct au_dykey *key, *tmp; ++ struct hlist_bl_node *pos; + -+ /* 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); ++ key = NULL; ++ hlist_bl_lock(hbl); ++ hlist_bl_for_each_entry(tmp, pos, hbl, dk_hnode) ++ if (tmp->dk_op.dy_hop == h_op) { ++ key = tmp; ++ kref_get(&key->dk_kref); ++ break; ++ } ++ hlist_bl_unlock(hbl); + -+ 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); ++ return key; ++} + -+ 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; ++static struct au_dykey *dy_bradd(struct au_branch *br, struct au_dykey *key) ++{ ++ struct au_dykey **k, *found; ++ const void *h_op = key->dk_op.dy_hop; ++ int i; + -+ 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); ++ 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 */ + } -+ au_update_figen(file); -+ /* todo: necessary? */ -+ /* file->f_ra = h_file->f_ra; */ -+ err = 0; + -+out: -+ return err; ++ return found; +} + -+static int do_open_dir(struct file *file, int flags, struct file *h_file) ++/* kref_get() if @key is already added */ ++static struct au_dykey *dy_gadd(struct hlist_bl_head *hbl, struct au_dykey *key) +{ -+ int err; -+ aufs_bindex_t bindex, btail; -+ struct dentry *dentry, *h_dentry; -+ struct vfsmount *mnt; -+ -+ FiMustWriteLock(file); -+ AuDebugOn(h_file); -+ -+ err = 0; -+ mnt = file->f_path.mnt; -+ dentry = file->f_path.dentry; -+ file->f_version = d_inode(dentry)->i_version; -+ 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; ++ struct au_dykey *tmp, *found; ++ struct hlist_bl_node *pos; ++ const void *h_op = key->dk_op.dy_hop; + -+ 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); ++ found = NULL; ++ hlist_bl_lock(hbl); ++ hlist_bl_for_each_entry(tmp, pos, hbl, dk_hnode) ++ if (tmp->dk_op.dy_hop == h_op) { ++ kref_get(&tmp->dk_kref); ++ found = tmp; + break; + } -+ au_set_h_fptr(file, bindex, h_file); -+ } -+ au_update_figen(file); -+ /* todo: necessary? */ -+ /* file->f_ra = h_file->f_ra; */ -+ if (!err) -+ return 0; /* success */ -+ -+ /* close all */ -+ for (bindex = au_fbtop(file); bindex <= btail; bindex++) -+ au_set_h_fptr(file, bindex, NULL); -+ au_set_fbtop(file, -1); -+ au_set_fbbot_dir(file, -1); ++ if (!found) ++ hlist_bl_add_head(&key->dk_hnode, hbl); ++ hlist_bl_unlock(hbl); + -+ return err; ++ if (!found) ++ DyPrSym(key); ++ return found; +} + -+static int aufs_open_dir(struct inode *inode __maybe_unused, -+ struct file *file) ++static void dy_free_rcu(struct rcu_head *rcu) +{ -+ int err; -+ struct super_block *sb; -+ struct au_fidir *fidir; ++ struct au_dykey *key; + -+ err = -ENOMEM; -+ sb = file->f_path.dentry->d_sb; -+ si_read_lock(sb, AuLock_FLUSH); -+ fidir = au_fidir_alloc(sb); -+ if (fidir) { -+ struct au_do_open_args args = { -+ .open = do_open_dir, -+ .fidir = fidir -+ }; -+ err = au_do_open(file, &args); -+ if (unlikely(err)) -+ au_delayed_kfree(fidir); -+ } -+ si_read_unlock(sb); -+ return err; ++ key = container_of(rcu, struct au_dykey, dk_rcu); ++ DyPrSym(key); ++ kfree(key); +} + -+static int aufs_release_dir(struct inode *inode __maybe_unused, -+ struct file *file) ++static void dy_free(struct kref *kref) +{ -+ struct au_vdir *vdir_cache; -+ struct au_finfo *finfo; -+ struct au_fidir *fidir; -+ struct au_hfile *hf; -+ aufs_bindex_t bindex, bbot; -+ int execed, delayed; ++ struct au_dykey *key; ++ struct hlist_bl_head *hbl; + -+ delayed = (current->flags & PF_KTHREAD) || in_interrupt(); -+ finfo = au_fi(file); -+ fidir = finfo->fi_hdir; -+ if (fidir) { -+ au_sphl_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, delayed); ++ 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); ++} + -+ bindex = finfo->fi_btop; -+ if (bindex >= 0) { -+ execed = vfsub_file_execed(file); -+ 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); -+ } -+ au_delayed_kfree(fidir); -+ finfo->fi_hdir = NULL; -+ } -+ au_finfo_fin(file, delayed); -+ return 0; ++void au_dy_put(struct au_dykey *key) ++{ ++ kref_put(&key->dk_kref, dy_free); +} + +/* ---------------------------------------------------------------------- */ + -+static int au_do_flush_dir(struct file *file, fl_owner_t id) -+{ -+ int err; -+ aufs_bindex_t bindex, bbot; -+ struct file *h_file; ++#define DyDbgSize(cnt, op) AuDebugOn(cnt != sizeof(op)/sizeof(void *)) + -+ 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; -+} ++#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 + -+static int aufs_flush_dir(struct file *file, fl_owner_t id) ++#define DySet(func, dst, src, h_op, h_sb) do { \ ++ DyDbgInc(cnt); \ ++ if (h_op->func) { \ ++ if (src.func) \ ++ dst.func = src.func; \ ++ else \ ++ AuDbg("%s %s\n", au_sbtype(h_sb), #func); \ ++ } \ ++} while (0) ++ ++#define DySetForce(func, dst, src) do { \ ++ AuDebugOn(!src.func); \ ++ DyDbgInc(cnt); \ ++ dst.func = src.func; \ ++} while (0) ++ ++#define DySetAop(func) \ ++ DySet(func, dyaop->da_op, aufs_aop, h_aop, h_sb) ++#define DySetAopForce(func) \ ++ DySetForce(func, dyaop->da_op, aufs_aop) ++ ++static void dy_aop(struct au_dykey *key, const void *h_op, ++ struct super_block *h_sb __maybe_unused) +{ -+ return au_do_flush(file, id, au_do_flush_dir); ++ struct au_dyaop *dyaop = (void *)key; ++ const struct address_space_operations *h_aop = h_op; ++ DyDbgDeclare(cnt); ++ ++ AuDbg("%s\n", au_sbtype(h_sb)); ++ ++ DySetAop(writepage); ++ DySetAopForce(readpage); /* force */ ++ DySetAop(writepages); ++ DySetAop(set_page_dirty); ++ DySetAop(readpages); ++ DySetAop(write_begin); ++ DySetAop(write_end); ++ DySetAop(bmap); ++ DySetAop(invalidatepage); ++ DySetAop(releasepage); ++ DySetAop(freepage); ++ /* this one will be changed according to an aufs mount option */ ++ DySetAop(direct_IO); ++ DySetAop(migratepage); ++ DySetAop(isolate_page); ++ DySetAop(putback_page); ++ DySetAop(launder_page); ++ DySetAop(is_partially_uptodate); ++ DySetAop(is_dirty_writeback); ++ DySetAop(error_remove_page); ++ DySetAop(swap_activate); ++ DySetAop(swap_deactivate); ++ ++ DyDbgSize(cnt, *h_aop); +} + +/* ---------------------------------------------------------------------- */ + -+static int au_do_fsync_dir_no_file(struct dentry *dentry, int datasync) ++static void dy_bug(struct kref *kref) +{ -+ int err; -+ aufs_bindex_t bbot, bindex; -+ struct inode *inode; -+ struct super_block *sb; ++ BUG(); ++} + -+ 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; ++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; + -+ if (au_test_ro(sb, bindex, inode)) -+ continue; -+ h_path.dentry = au_h_dptr(dentry, bindex); -+ if (!h_path.dentry) -+ continue; ++ hbl = dynop + op->dy_type; ++ key = dy_gfind_get(hbl, op->dy_hop); ++ if (key) ++ goto out_add; /* success */ + -+ h_path.mnt = au_sbr_mnt(sb, bindex); -+ err = vfsub_fsync(NULL, &h_path, datasync); ++ p = a + op->dy_type; ++ key = kzalloc(p->sz, GFP_NOFS); ++ if (unlikely(!key)) { ++ key = ERR_PTR(-ENOMEM); ++ goto out; + } + -+ return err; ++ 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) { ++ kfree(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; +} + -+static int au_do_fsync_dir(struct file *file, int datasync) ++/* ---------------------------------------------------------------------- */ ++/* ++ * Aufs prohibits O_DIRECT by defaut 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) +{ -+ int err; -+ aufs_bindex_t bbot, bindex; -+ struct file *h_file; -+ struct super_block *sb; -+ struct inode *inode; ++ if (!do_dx) ++ dyaop->da_op.direct_IO = NULL; ++ else ++ dyaop->da_op.direct_IO = aufs_aop.direct_IO; ++} + -+ err = au_reval_and_lock_fdi(file, reopen_dir, /*wlock*/1); -+ if (unlikely(err)) ++static struct au_dyaop *dy_aget(struct au_branch *br, ++ const struct address_space_operations *h_aop, ++ int do_dx) ++{ ++ struct au_dyaop *dyaop; ++ struct au_dynop op; ++ ++ op.dy_type = AuDy_AOP; ++ op.dy_haop = h_aop; ++ dyaop = (void *)dy_get(&op, br); ++ if (IS_ERR(dyaop)) + goto out; ++ dy_adx(dyaop, do_dx); ++ ++out: ++ return dyaop; ++} ++ ++int au_dy_iaop(struct inode *inode, aufs_bindex_t bindex, ++ struct inode *h_inode) ++{ ++ int err, do_dx; ++ struct super_block *sb; ++ struct au_branch *br; ++ struct au_dyaop *dyaop; ++ ++ AuDebugOn(!S_ISREG(h_inode->i_mode)); ++ IiMustWriteLock(inode); + -+ 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; ++ br = au_sbr(sb, bindex); ++ do_dx = !!au_opt_test(au_mntflags(sb), DIO); ++ dyaop = dy_aget(br, h_inode->i_mapping->a_ops, do_dx); ++ err = PTR_ERR(dyaop); ++ if (IS_ERR(dyaop)) ++ /* unnecessary to call dy_fput() */ ++ goto out; + -+ err = vfsub_fsync(h_file, &h_file->f_path, datasync); -+ } ++ err = 0; ++ inode->i_mapping->a_ops = &dyaop->da_op; + +out: + return err; +} + +/* -+ * @file may be NULL ++ * Is it safe to replace a_ops during the inode/file is in operation? ++ * Yes, I hope so. + */ -+static int aufs_fsync_dir(struct file *file, loff_t start, loff_t end, -+ int datasync) ++int au_dy_irefresh(struct inode *inode) +{ + int err; -+ struct dentry *dentry; -+ struct inode *inode; -+ struct super_block *sb; ++ aufs_bindex_t btop; ++ struct inode *h_inode; + + 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); ++ 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); + } -+ au_cpup_attr_timesizes(inode); -+ di_write_unlock(dentry); -+ if (file) -+ fi_write_unlock(file); -+ -+ si_read_unlock(sb); -+ inode_unlock(inode); + return err; +} + ++void au_dy_arefresh(int do_dx) ++{ ++ struct hlist_bl_head *hbl; ++ struct hlist_bl_node *pos; ++ struct au_dykey *key; ++ ++ hbl = dynop + AuDy_AOP; ++ hlist_bl_lock(hbl); ++ hlist_bl_for_each_entry(key, pos, hbl, dk_hnode) ++ dy_adx((void *)key, do_dx); ++ hlist_bl_unlock(hbl); ++} ++ +/* ---------------------------------------------------------------------- */ + -+static int aufs_iterate_shared(struct file *file, struct dir_context *ctx) ++void __init au_dy_init(void) +{ -+ int err; -+ struct dentry *dentry; -+ struct inode *inode, *h_inode; -+ struct super_block *sb; ++ int i; + -+ AuDbg("%pD, ctx{%pf, %llu}\n", file, ctx->actor, ctx->pos); ++ /* make sure that 'struct au_dykey *' can be any type */ ++ BUILD_BUG_ON(offsetof(struct au_dyaop, da_key)); + -+ dentry = file->f_path.dentry; -+ inode = d_inode(dentry); -+ IMustLock(inode); ++ for (i = 0; i < AuDyLast; i++) ++ INIT_HLIST_BL_HEAD(dynop + i); ++} + -+ sb = dentry->d_sb; -+ si_read_lock(sb, AuLock_FLUSH); -+ err = au_reval_and_lock_fdi(file, reopen_dir, /*wlock*/1); -+ 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; ++void au_dy_fin(void) ++{ ++ int i; + -+ 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); ++ for (i = 0; i < AuDyLast; i++) ++ WARN_ON(!hlist_bl_empty(dynop + i)); ++} +diff -urNp -x '*.orig' linux-4.9/fs/aufs/dynop.h linux-4.9/fs/aufs/dynop.h +--- linux-4.9/fs/aufs/dynop.h 1970-01-01 01:00:00.000000000 +0100 ++++ linux-4.9/fs/aufs/dynop.h 2021-02-24 16:15:09.524906971 +0100 +@@ -0,0 +1,74 @@ ++/* ++ * Copyright (C) 2010-2018 Junjiro R. Okajima ++ * ++ * This program, aufs is free software; you can redistribute it and/or modify ++ * it under the terms of the GNU General Public License as published by ++ * the Free Software Foundation; either version 2 of the License, or ++ * (at your option) any later version. ++ * ++ * This program is distributed in the hope that it will be useful, ++ * but WITHOUT ANY WARRANTY; without even the implied warranty of ++ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the ++ * GNU General Public License for more details. ++ * ++ * You should have received a copy of the GNU General Public License ++ * along with this program. If not, see . ++ */ ++ ++/* ++ * dynamically customizable operations (for regular files only) ++ */ ++ ++#ifndef __AUFS_DYNOP_H__ ++#define __AUFS_DYNOP_H__ ++ ++#ifdef __KERNEL__ ++ ++#include ++#include + -+ AuTraceErr(err); -+ return err; -+ } ++enum {AuDy_AOP, AuDyLast}; + -+out_unlock: -+ di_read_unlock(dentry, AuLock_IR); -+ fi_write_unlock(file); -+out: -+ si_read_unlock(sb); -+ return err; -+} ++struct au_dynop { ++ int dy_type; ++ union { ++ const void *dy_hop; ++ const struct address_space_operations *dy_haop; ++ }; ++}; ++ ++struct au_dykey { ++ union { ++ struct hlist_bl_node dk_hnode; ++ struct rcu_head dk_rcu; ++ }; ++ struct au_dynop dk_op; ++ ++ /* ++ * during I am in the branch local array, kref is gotten. when the ++ * branch is removed, kref is put. ++ */ ++ struct kref dk_kref; ++}; ++ ++/* stop unioning since their sizes are very different from each other */ ++struct au_dyaop { ++ struct au_dykey da_key; ++ struct address_space_operations da_op; /* not const */ ++}; + +/* ---------------------------------------------------------------------- */ + -+#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) ++/* 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); + -+#ifndef CONFIG_AUFS_SHWH -+#undef AuTestEmpty_SHWH -+#define AuTestEmpty_SHWH 0 -+#endif ++void __init au_dy_init(void); ++void au_dy_fin(void); + -+struct test_empty_arg { -+ struct dir_context ctx; -+ struct au_nhash *whlist; -+ unsigned int flags; -+ int err; -+ aufs_bindex_t bindex; -+}; ++#endif /* __KERNEL__ */ ++#endif /* __AUFS_DYNOP_H__ */ +diff -urNp -x '*.orig' linux-4.9/fs/aufs/export.c linux-4.9/fs/aufs/export.c +--- linux-4.9/fs/aufs/export.c 1970-01-01 01:00:00.000000000 +0100 ++++ linux-4.9/fs/aufs/export.c 2021-02-24 16:15:09.528240413 +0100 +@@ -0,0 +1,836 @@ ++/* ++ * Copyright (C) 2005-2018 Junjiro R. Okajima ++ * ++ * This program, aufs is free software; you can redistribute it and/or modify ++ * it under the terms of the GNU General Public License as published by ++ * the Free Software Foundation; either version 2 of the License, or ++ * (at your option) any later version. ++ * ++ * This program is distributed in the hope that it will be useful, ++ * but WITHOUT ANY WARRANTY; without even the implied warranty of ++ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the ++ * GNU General Public License for more details. ++ * ++ * You should have received a copy of the GNU General Public License ++ * along with this program. If not, see . ++ */ + -+static int test_empty_cb(struct dir_context *ctx, const char *__name, -+ int namelen, loff_t offset __maybe_unused, u64 ino, -+ unsigned int d_type) -+{ -+ struct test_empty_arg *arg = container_of(ctx, struct test_empty_arg, -+ ctx); -+ char *name = (void *)__name; ++/* ++ * export via nfs ++ */ + -+ arg->err = 0; -+ au_fset_testempty(arg->flags, CALLED); -+ /* smp_mb(); */ -+ if (name[0] == '.' -+ && (namelen == 1 || (name[1] == '.' && namelen == 2))) -+ goto out; /* success */ ++#include ++#include ++#include ++#include ++#include ++#include ++#include "aufs.h" + -+ 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; -+ } ++union conv { ++#ifdef CONFIG_AUFS_INO_T_64 ++ __u32 a[2]; ++#else ++ __u32 a[1]; ++#endif ++ ino_t ino; ++}; + -+ 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)); ++static ino_t decode_ino(__u32 *a) ++{ ++ union conv u; + -+out: -+ /* smp_mb(); */ -+ AuTraceErr(arg->err); -+ return arg->err; ++ BUILD_BUG_ON(sizeof(u.ino) != sizeof(u.a)); ++ u.a[0] = a[0]; ++#ifdef CONFIG_AUFS_INO_T_64 ++ u.a[1] = a[1]; ++#endif ++ return u.ino; +} + -+static int do_test_empty(struct dentry *dentry, struct test_empty_arg *arg) ++static void encode_ino(__u32 *a, ino_t ino) +{ -+ int err; -+ struct file *h_file; ++ union conv u; + -+ 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; ++ u.ino = ino; ++ a[0] = u.a[0]; ++#ifdef CONFIG_AUFS_INO_T_64 ++ a[1] = u.a[1]; ++#endif ++} + -+ err = 0; -+ if (!au_opt_test(au_mntflags(dentry->d_sb), UDBA_NONE) -+ && !file_inode(h_file)->i_nlink) -+ goto out_put; ++/* 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, + -+ 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)); ++ Fh_ino = Fh_ino1, ++ Fh_dir_ino = Fh_dir_ino1 ++}; + -+out_put: -+ fput(h_file); -+ au_sbr_put(dentry->d_sb, arg->bindex); -+out: -+ return err; ++static int au_test_anon(struct dentry *dentry) ++{ ++ /* note: read d_flags without d_lock */ ++ return !!(dentry->d_flags & DCACHE_DISCONNECTED); +} + -+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_test_nfsd(void) +{ -+ struct do_test_empty_args *a = args; -+ *a->errp = do_test_empty(a->dentry, a->arg); ++ int ret; ++ struct task_struct *tsk = current; ++ char comm[sizeof(tsk->comm)]; ++ ++ ret = 0; ++ if (tsk->flags & PF_KTHREAD) { ++ get_task_comm(comm, tsk); ++ ret = !strcmp(comm, "nfsd"); ++ } ++ ++ return ret; +} + -+static int sio_test_empty(struct dentry *dentry, struct test_empty_arg *arg) ++/* ---------------------------------------------------------------------- */ ++/* inode generation external table */ ++ ++void au_xigen_inc(struct inode *inode) +{ -+ int err, wkq_err; -+ struct dentry *h_dentry; -+ struct inode *h_inode; ++ loff_t pos; ++ ssize_t sz; ++ __u32 igen; ++ struct super_block *sb; ++ struct au_sbinfo *sbinfo; + -+ h_dentry = au_h_dptr(dentry, arg->bindex); -+ h_inode = d_inode(h_dentry); -+ /* todo: i_mode changes anytime? */ -+ inode_lock_nested(h_inode, AuLsc_I_CHILD); -+ err = au_test_h_perm_sio(h_inode, MAY_EXEC | MAY_READ); -+ inode_unlock(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; ++ sb = inode->i_sb; ++ AuDebugOn(!au_opt_test(au_mntflags(sb), XINO)); + -+ wkq_err = au_wkq_wait(call_do_test_empty, &args); -+ if (unlikely(wkq_err)) -+ err = wkq_err; -+ arg->flags = flags; -+ } ++ sbinfo = au_sbi(sb); ++ pos = inode->i_ino; ++ pos *= sizeof(igen); ++ igen = inode->i_generation + 1; ++ sz = xino_fwrite(sbinfo->si_xwrite, sbinfo->si_xigen, &igen, ++ sizeof(igen), &pos); ++ if (sz == sizeof(igen)) ++ return; /* success */ + -+ return err; ++ if (unlikely(sz >= 0)) ++ AuIOErr("xigen error (%zd)\n", sz); +} + -+int au_test_empty_lower(struct dentry *dentry) ++int au_xigen_new(struct inode *inode) +{ + 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); ++ loff_t pos; ++ ssize_t sz; ++ struct super_block *sb; ++ struct au_sbinfo *sbinfo; ++ struct file *file; + -+ SiMustAnyLock(dentry->d_sb); ++ 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; + -+ 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)) ++ err = -EFBIG; ++ pos = inode->i_ino; ++ if (unlikely(au_loff_max / sizeof(inode->i_generation) - 1 < pos)) { ++ AuIOErr1("too large i%lld\n", pos); + goto out; ++ } ++ pos *= sizeof(inode->i_generation); + -+ 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 = 0; ++ sbinfo = au_sbi(sb); ++ file = sbinfo->si_xigen; ++ BUG_ON(!file); + -+ au_fset_testempty(arg.flags, WHONLY); -+ btail = au_dbtaildir(dentry); -+ for (bindex = btop + 1; !err && bindex <= btail; bindex++) { -+ struct dentry *h_dentry; ++ if (vfsub_f_size_read(file) ++ < pos + sizeof(inode->i_generation)) { ++ inode->i_generation = atomic_inc_return(&sbinfo->si_xigen_next); ++ sz = xino_fwrite(sbinfo->si_xwrite, file, &inode->i_generation, ++ sizeof(inode->i_generation), &pos); ++ } else ++ sz = xino_fread(sbinfo->si_xread, file, &inode->i_generation, ++ sizeof(inode->i_generation), &pos); ++ if (sz == sizeof(inode->i_generation)) ++ goto out; /* success */ + -+ h_dentry = au_h_dptr(dentry, bindex); -+ if (h_dentry && d_is_positive(h_dentry)) { -+ arg.bindex = bindex; -+ err = test_empty(dentry, &arg); -+ } ++ err = sz; ++ if (unlikely(sz >= 0)) { ++ err = -EIO; ++ AuIOErr("xigen error (%zd)\n", sz); + } + -+out_whlist: -+ au_nhash_wh_free(&whlist); +out: + return err; +} + -+int au_test_empty(struct dentry *dentry, struct au_nhash *whlist) ++int au_xigen_set(struct super_block *sb, struct file *base) +{ + int err; -+ struct test_empty_arg arg = { -+ .ctx = { -+ .actor = test_empty_cb -+ } -+ }; -+ aufs_bindex_t bindex, btail; ++ struct au_sbinfo *sbinfo; ++ struct file *file; + -+ 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; ++ SiMustWriteLock(sb); + -+ h_dentry = au_h_dptr(dentry, bindex); -+ if (h_dentry && d_is_positive(h_dentry)) { -+ arg.bindex = bindex; -+ err = sio_test_empty(dentry, &arg); -+ } -+ } ++ sbinfo = au_sbi(sb); ++ file = au_xino_create2(base, sbinfo->si_xigen); ++ err = PTR_ERR(file); ++ if (IS_ERR(file)) ++ goto out; ++ err = 0; ++ if (sbinfo->si_xigen) ++ fput(sbinfo->si_xigen); ++ sbinfo->si_xigen = file; + ++out: + return err; +} + -+/* ---------------------------------------------------------------------- */ -+ -+const struct file_operations aufs_dir_fop = { -+ .owner = THIS_MODULE, -+ .llseek = default_llseek, -+ .read = generic_read_dir, -+ .iterate_shared = aufs_iterate_shared, -+ .unlocked_ioctl = aufs_ioctl_dir, -+#ifdef CONFIG_COMPAT -+ .compat_ioctl = aufs_compat_ioctl_dir, -+#endif -+ .open = aufs_open_dir, -+ .release = aufs_release_dir, -+ .flush = aufs_flush_dir, -+ .fsync = aufs_fsync_dir -+}; -diff -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 2016-10-09 16:55:36.489368218 +0200 -@@ -0,0 +1,137 @@ -+/* -+ * Copyright (C) 2005-2016 Junjiro R. Okajima -+ * -+ * This program, aufs is free software; you can redistribute it and/or modify -+ * it under the terms of the GNU General Public License as published by -+ * the Free Software Foundation; either version 2 of the License, or -+ * (at your option) any later version. -+ * -+ * This program is distributed in the hope that it will be useful, -+ * but WITHOUT ANY WARRANTY; without even the implied warranty of -+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the -+ * GNU General Public License for more details. -+ * -+ * You should have received a copy of the GNU General Public License -+ * along with this program. If not, see . -+ */ -+ -+/* -+ * directory operations -+ */ -+ -+#ifndef __AUFS_DIR_H__ -+#define __AUFS_DIR_H__ ++void au_xigen_clr(struct super_block *sb) ++{ ++ struct au_sbinfo *sbinfo; + -+#ifdef __KERNEL__ ++ SiMustWriteLock(sb); + -+#include ++ sbinfo = au_sbi(sb); ++ if (sbinfo->si_xigen) { ++ fput(sbinfo->si_xigen); ++ sbinfo->si_xigen = NULL; ++ } ++} + +/* ---------------------------------------------------------------------- */ + -+/* need to be faster and smaller */ ++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; + -+struct au_nhash { -+ unsigned int nh_num; -+ struct hlist_head *nh_head; -+}; ++ dentry = NULL; ++ inode = ilookup(sb, ino); ++ if (!inode) ++ goto out; + -+struct au_vdir_destr { -+ unsigned char len; -+ unsigned char name[0]; -+} __packed; ++ 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; + -+struct au_vdir_dehstr { -+ struct hlist_node hash; -+ union { -+ struct au_vdir_destr *str; -+ struct llist_node lnode; /* delayed free */ -+ }; -+} ____cacheline_aligned_in_smp; ++ 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; ++ } + -+struct au_vdir_de { -+ ino_t de_ino; -+ unsigned char de_type; -+ /* caution: packed */ -+ struct au_vdir_destr de_str; -+} __packed; ++out_iput: ++ iput(inode); ++out: ++ AuTraceErrPtr(dentry); ++ return 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; ++/* ---------------------------------------------------------------------- */ + -+union au_vdir_deblk_p { -+ unsigned char *deblk; -+ struct au_vdir_de *de; -+}; ++/* todo: dirty? */ ++/* if exportfs_decode_fh() passed vfsmount*, we could be happy */ ++ ++struct au_compare_mnt_args { ++ /* input */ ++ struct super_block *sb; + -+struct au_vdir { -+ unsigned char **vd_deblk; -+ unsigned long vd_nblk; -+ struct { -+ unsigned long ul; -+ union au_vdir_deblk_p p; -+ } vd_last; ++ /* output */ ++ struct vfsmount *mnt; ++}; + -+ unsigned long vd_version; -+ unsigned int vd_deblk_sz; -+ union { -+ unsigned long vd_jiffy; -+ struct llist_node vd_lnode; /* delayed free */ -+ }; -+} ____cacheline_aligned_in_smp; ++static int au_compare_mnt(struct vfsmount *mnt, void *arg) ++{ ++ struct au_compare_mnt_args *a = arg; + -+/* ---------------------------------------------------------------------- */ ++ if (mnt->mnt_sb != a->sb) ++ return 0; ++ a->mnt = mntget(mnt); ++ return 1; ++} + -+/* 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 struct vfsmount *au_mnt_get(struct super_block *sb) ++{ ++ int err; ++ struct path root; ++ struct au_compare_mnt_args args = { ++ .sb = sb ++ }; + -+/* 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 atonce); -+int au_vdir_init(struct file *file); -+int au_vdir_fill_de(struct file *file, struct dir_context *ctx); ++ 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; ++} + -+/* ioctl.c */ -+long aufs_ioctl_dir(struct file *file, unsigned int cmd, unsigned long arg); ++struct au_nfsd_si_lock { ++ unsigned int sigen; ++ aufs_bindex_t bindex, br_id; ++ unsigned char force_lock; ++}; + -+#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 ++static int si_nfsd_read_lock(struct super_block *sb, ++ struct au_nfsd_si_lock *nsi_lock) ++{ ++ int err; ++ aufs_bindex_t bindex; + -+#endif /* __KERNEL__ */ -+#endif /* __AUFS_DIR_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 2016-10-09 16:55:36.489368218 +0200 -@@ -0,0 +1,371 @@ -+/* -+ * Copyright (C) 2010-2016 Junjiro R. Okajima -+ * -+ * This program, aufs is free software; you can redistribute it and/or modify -+ * it under the terms of the GNU General Public License as published by -+ * the Free Software Foundation; either version 2 of the License, or -+ * (at your option) any later version. -+ * -+ * This program is distributed in the hope that it will be useful, -+ * but WITHOUT ANY WARRANTY; without even the implied warranty of -+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the -+ * GNU General Public License for more details. -+ * -+ * You should have received a copy of the GNU General Public License -+ * along with this program. If not, see . -+ */ ++ si_read_lock(sb, AuLock_FLUSH); + -+/* -+ * dynamically customizable operations for regular files -+ */ ++ /* 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 */ + -+#include "aufs.h" ++ err = -ESTALE; ++ bindex = -1; ++ if (!nsi_lock->force_lock) ++ si_read_unlock(sb); + -+#define DyPrSym(key) AuDbgSym(key->dk_op.dy_hop) ++out: ++ nsi_lock->bindex = bindex; ++ return err; ++} + -+/* -+ * How large will these lists be? -+ * Usually just a few elements, 20-30 at most for each, I guess. -+ */ -+static struct au_sphlhead dynop[AuDyLast]; ++struct find_name_by_ino { ++ struct dir_context ctx; ++ int called, found; ++ ino_t ino; ++ char *name; ++ int namelen; ++}; + -+static struct au_dykey *dy_gfind_get(struct au_sphlhead *sphl, const void *h_op) ++static int ++find_name_by_ino(struct dir_context *ctx, const char *name, int namelen, ++ loff_t offset, u64 ino, unsigned int d_type) +{ -+ struct au_dykey *key, *tmp; -+ struct hlist_head *head; ++ struct find_name_by_ino *a = container_of(ctx, struct find_name_by_ino, ++ ctx); + -+ key = NULL; -+ head = &sphl->head; -+ rcu_read_lock(); -+ hlist_for_each_entry_rcu(tmp, head, dk_hnode) -+ if (tmp->dk_op.dy_hop == h_op) { -+ key = tmp; -+ kref_get(&key->dk_kref); -+ break; -+ } -+ rcu_read_unlock(); ++ a->called++; ++ if (a->ino != ino) ++ return 0; + -+ return key; ++ memcpy(a->name, name, namelen); ++ a->namelen = namelen; ++ a->found = 1; ++ return 1; +} + -+static struct au_dykey *dy_bradd(struct au_branch *br, struct au_dykey *key) ++static struct dentry *au_lkup_by_ino(struct path *path, ino_t ino, ++ struct au_nfsd_si_lock *nsi_lock) +{ -+ struct au_dykey **k, *found; -+ const void *h_op = key->dk_op.dy_hop; -+ int i; ++ struct dentry *dentry, *parent; ++ struct file *file; ++ struct inode *dir; ++ struct find_name_by_ino arg = { ++ .ctx = { ++ .actor = find_name_by_ino ++ } ++ }; ++ int err; + -+ 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 */ ++ parent = path->dentry; ++ if (nsi_lock) ++ si_read_unlock(parent->d_sb); ++ file = vfsub_dentry_open(path, au_dir_roflags); ++ dentry = (void *)file; ++ if (IS_ERR(file)) ++ goto out; ++ ++ dentry = ERR_PTR(-ENOMEM); ++ arg.name = (void *)__get_free_page(GFP_NOFS); ++ if (unlikely(!arg.name)) ++ goto out_file; ++ arg.ino = ino; ++ arg.found = 0; ++ do { ++ arg.called = 0; ++ /* smp_mb(); */ ++ err = vfsub_iterate_dir(file, &arg.ctx); ++ } while (!err && !arg.found && arg.called); ++ dentry = ERR_PTR(err); ++ if (unlikely(err)) ++ goto out_name; ++ /* instead of ENOENT */ ++ dentry = ERR_PTR(-ESTALE); ++ if (!arg.found) ++ goto out_name; ++ ++ /* do not call vfsub_lkup_one() */ ++ dir = d_inode(parent); ++ dentry = vfsub_lookup_one_len_unlocked(arg.name, parent, arg.namelen); ++ AuTraceErrPtr(dentry); ++ if (IS_ERR(dentry)) ++ goto out_name; ++ AuDebugOn(au_test_anon(dentry)); ++ if (unlikely(d_really_is_negative(dentry))) { ++ dput(dentry); ++ dentry = ERR_PTR(-ENOENT); + } + -+ return found; ++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; +} + -+/* kref_get() if @key is already added */ -+static struct au_dykey *dy_gadd(struct au_sphlhead *sphl, struct au_dykey *key) ++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 au_dykey *tmp, *found; -+ struct hlist_head *head; -+ const void *h_op = key->dk_op.dy_hop; ++ struct dentry *dentry; ++ struct path path; + -+ found = NULL; -+ head = &sphl->head; -+ spin_lock(&sphl->spin); -+ hlist_for_each_entry(tmp, head, dk_hnode) -+ if (tmp->dk_op.dy_hop == h_op) { -+ kref_get(&tmp->dk_kref); -+ found = tmp; -+ break; -+ } -+ if (!found) -+ hlist_add_head_rcu(&key->dk_hnode, head); -+ spin_unlock(&sphl->spin); ++ 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); + -+ if (!found) -+ DyPrSym(key); -+ return found; ++ path.mnt = au_mnt_get(sb); ++ dentry = au_lkup_by_ino(&path, ino, nsi_lock); ++ path_put(&path); ++ ++out: ++ AuTraceErrPtr(dentry); ++ return dentry; +} + -+static void dy_free_rcu(struct rcu_head *rcu) -+{ -+ struct au_dykey *key; ++/* ---------------------------------------------------------------------- */ + -+ key = container_of(rcu, struct au_dykey, dk_rcu); -+ DyPrSym(key); -+ kfree(key); /* not delayed */ ++static int h_acceptable(void *expv, struct dentry *dentry) ++{ ++ return 1; +} + -+static void dy_free(struct kref *kref) ++static char *au_build_path(struct dentry *h_parent, struct path *h_rootpath, ++ char *buf, int len, struct super_block *sb) +{ -+ struct au_dykey *key; -+ struct au_sphlhead *sphl; ++ char *p; ++ int n; ++ struct path path; + -+ key = container_of(kref, struct au_dykey, dk_kref); -+ sphl = dynop + key->dk_op.dy_type; -+ au_sphl_del_rcu(&key->dk_hnode, sphl); -+ call_rcu(&key->dk_rcu, dy_free_rcu); -+} ++ p = d_path(h_rootpath, buf, len); ++ if (IS_ERR(p)) ++ goto out; ++ n = strlen(p); + -+void au_dy_put(struct au_dykey *key) -+{ -+ kref_put(&key->dk_kref, dy_free); -+} ++ 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)] = '/'; + -+#define DyDbgSize(cnt, op) AuDebugOn(cnt != sizeof(op)/sizeof(void *)) ++out: ++ AuTraceErrPtr(p); ++ return p; ++} + -+#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 ++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; + -+#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) ++ 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 DySetForce(func, dst, src) do { \ -+ AuDebugOn(!src.func); \ -+ DyDbgInc(cnt); \ -+ dst.func = src.func; \ -+} while (0) ++ dentry = ERR_PTR(-ENOMEM); ++ pathname = (void *)__get_free_page(GFP_NOFS); ++ if (unlikely(!pathname)) ++ goto out_h_parent; + -+#define DySetAop(func) \ -+ DySet(func, dyaop->da_op, aufs_aop, h_aop, h_sb) -+#define DySetAopForce(func) \ -+ DySetForce(func, dyaop->da_op, aufs_aop) ++ 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; + -+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); ++ si_read_unlock(sb); ++ err = vfsub_kern_path(p, LOOKUP_FOLLOW | LOOKUP_DIRECTORY, &path); ++ dentry = ERR_PTR(err); ++ if (unlikely(err)) ++ goto out_relock; + -+ AuDbg("%s\n", au_sbtype(h_sb)); ++ dentry = ERR_PTR(-ENOENT); ++ AuDebugOn(au_test_anon(path.dentry)); ++ if (unlikely(d_really_is_negative(path.dentry))) ++ goto out_path; + -+ DySetAop(writepage); -+ DySetAopForce(readpage); /* force */ -+ DySetAop(writepages); -+ DySetAop(set_page_dirty); -+ DySetAop(readpages); -+ DySetAop(write_begin); -+ DySetAop(write_end); -+ DySetAop(bmap); -+ DySetAop(invalidatepage); -+ DySetAop(releasepage); -+ DySetAop(freepage); -+ /* this one will be changed according to an aufs mount option */ -+ DySetAop(direct_IO); -+ DySetAop(migratepage); -+ DySetAop(isolate_page); -+ DySetAop(putback_page); -+ DySetAop(launder_page); -+ DySetAop(is_partially_uptodate); -+ DySetAop(is_dirty_writeback); -+ DySetAop(error_remove_page); -+ DySetAop(swap_activate); -+ DySetAop(swap_deactivate); ++ if (ino != d_inode(path.dentry)->i_ino) ++ dentry = au_lkup_by_ino(&path, ino, /*nsi_lock*/NULL); ++ else ++ dentry = dget(path.dentry); + -+ DyDbgSize(cnt, *h_aop); ++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 void dy_bug(struct kref *kref) -+{ -+ BUG(); -+} -+ -+static struct au_dykey *dy_get(struct au_dynop *op, struct au_branch *br) ++static struct dentry * ++aufs_fh_to_dentry(struct super_block *sb, struct fid *fid, int fh_len, ++ int fh_type) +{ -+ struct au_dykey *key, *old; -+ struct au_sphlhead *sphl; -+ 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 -+ } ++ 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 + }; -+ const struct op *p; + -+ sphl = dynop + op->dy_type; -+ key = dy_gfind_get(sphl, op->dy_hop); -+ if (key) -+ goto out_add; /* success */ ++ dentry = ERR_PTR(-ESTALE); ++ /* it should never happen, but the file handle is unreliable */ ++ if (unlikely(fh_len < Fh_tail)) ++ goto out; ++ nsi_lock.sigen = fh[Fh_sigen]; ++ nsi_lock.br_id = fh[Fh_br_id]; ++ ++ /* branch id may be wrapped around */ ++ br = NULL; ++ if (unlikely(si_nfsd_read_lock(sb, &nsi_lock))) ++ goto out; ++ nsi_lock.force_lock = 1; ++ ++ /* is this inode still cached? */ ++ ino = decode_ino(fh + Fh_ino); ++ /* it should never happen */ ++ if (unlikely(ino == AUFS_ROOT_INO)) ++ goto out_unlock; ++ ++ dir_ino = decode_ino(fh + Fh_dir_ino); ++ dentry = decode_by_ino(sb, ino, dir_ino); ++ if (IS_ERR(dentry)) ++ goto out_unlock; ++ if (dentry) ++ goto accept; ++ ++ /* is the parent dir cached? */ ++ br = au_sbr(sb, nsi_lock.bindex); ++ au_br_get(br); ++ dentry = decode_by_dir_ino(sb, ino, dir_ino, &nsi_lock); ++ if (IS_ERR(dentry)) ++ goto out_unlock; ++ if (dentry) ++ goto accept; + -+ p = a + op->dy_type; -+ key = kzalloc(p->sz, GFP_NOFS); -+ if (unlikely(!key)) { -+ key = ERR_PTR(-ENOMEM); -+ goto out; -+ } ++ /* 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; + -+ 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(sphl, key); -+ if (old) { -+ au_delayed_kfree(key); -+ key = old; -+ } ++accept: ++ if (!au_digen_test(dentry, au_sigen(sb)) ++ && d_inode(dentry)->i_generation == fh[Fh_igen]) ++ goto out_unlock; /* success */ + -+out_add: -+ old = dy_bradd(br, key); -+ if (old) -+ /* its ref-count should never be zero here */ -+ kref_put(&key->dk_kref, dy_bug); ++ dput(dentry); ++ dentry = ERR_PTR(-ESTALE); ++out_unlock: ++ if (br) ++ au_br_put(br); ++ si_read_unlock(sb); +out: -+ return key; -+} -+ -+/* ---------------------------------------------------------------------- */ -+/* -+ * Aufs prohibits O_DIRECT by defaut 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; ++ AuTraceErrPtr(dentry); ++ return dentry; +} + -+static struct au_dyaop *dy_aget(struct au_branch *br, -+ const struct address_space_operations *h_aop, -+ int do_dx) ++#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 au_dyaop *dyaop; -+ struct au_dynop op; ++ struct dentry *parent; ++ __u32 *fh = fid->raw; ++ ino_t dir_ino; + -+ op.dy_type = AuDy_AOP; -+ op.dy_haop = h_aop; -+ dyaop = (void *)dy_get(&op, br); -+ if (IS_ERR(dyaop)) ++ dir_ino = decode_ino(fh + Fh_dir_ino); ++ parent = decode_by_ino(sb, dir_ino, 0); ++ if (IS_ERR(parent)) + goto out; -+ dy_adx(dyaop, do_dx); ++ if (!parent) ++ parent = decode_by_path(sb, au_br_index(sb, fh[Fh_br_id]), ++ dir_ino, fh, fh_len); + +out: -+ return dyaop; ++ AuTraceErrPtr(parent); ++ return parent; +} ++#endif + -+int au_dy_iaop(struct inode *inode, aufs_bindex_t bindex, -+ struct inode *h_inode) ++/* ---------------------------------------------------------------------- */ ++ ++static int aufs_encode_fh(struct inode *inode, __u32 *fh, int *max_len, ++ struct inode *dir) +{ -+ int err, do_dx; -+ struct super_block *sb; ++ int err; ++ aufs_bindex_t bindex; ++ struct super_block *sb, *h_sb; ++ struct dentry *dentry, *parent, *h_parent; ++ struct inode *h_dir; + struct au_branch *br; -+ struct au_dyaop *dyaop; + -+ AuDebugOn(!S_ISREG(h_inode->i_mode)); -+ IiMustWriteLock(inode); ++ err = -ENOSPC; ++ if (unlikely(*max_len <= Fh_tail)) { ++ AuWarn1("NFSv2 client (max_len %d)?\n", *max_len); ++ goto out; ++ } ++ ++ err = FILEID_ROOT; ++ if (inode->i_ino == AUFS_ROOT_INO) { ++ AuDebugOn(inode->i_ino != AUFS_ROOT_INO); ++ goto out; ++ } + ++ h_parent = NULL; + sb = inode->i_sb; -+ 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 = si_read_lock(sb, AuLock_FLUSH); ++ if (unlikely(err)) + goto out; + -+ err = 0; -+ inode->i_mapping->a_ops = &dyaop->da_op; ++#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; +} + -+/* -+ * 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) ++/* ---------------------------------------------------------------------- */ ++ ++static int aufs_commit_metadata(struct inode *inode) +{ + int err; -+ aufs_bindex_t btop; ++ aufs_bindex_t bindex; ++ struct super_block *sb; + struct inode *h_inode; ++ int (*f)(struct inode *inode); + -+ err = 0; -+ if (S_ISREG(inode->i_mode)) { -+ btop = au_ibtop(inode); -+ h_inode = au_h_iptr(inode, btop); -+ err = au_dy_iaop(inode, btop, h_inode); -+ } -+ return err; -+} ++ 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); + -+void au_dy_arefresh(int do_dx) -+{ -+ struct au_sphlhead *sphl; -+ struct hlist_head *head; -+ struct au_dykey *key; ++ f = h_inode->i_sb->s_export_op->commit_metadata; ++ if (f) ++ err = f(h_inode); ++ else { ++ struct writeback_control wbc = { ++ .sync_mode = WB_SYNC_ALL, ++ .nr_to_write = 0 /* metadata only */ ++ }; + -+ sphl = dynop + AuDy_AOP; -+ head = &sphl->head; -+ spin_lock(&sphl->spin); -+ hlist_for_each_entry(key, head, dk_hnode) -+ dy_adx((void *)key, do_dx); -+ spin_unlock(&sphl->spin); ++ err = sync_inode(h_inode, &wbc); ++ } ++ ++ au_cpup_attr_timesizes(inode); ++ ii_write_unlock(inode); ++ si_read_unlock(sb); ++ return err; +} + +/* ---------------------------------------------------------------------- */ + -+void __init au_dy_init(void) -+{ -+ int i; -+ -+ /* make sure that 'struct au_dykey *' can be any type */ -+ BUILD_BUG_ON(offsetof(struct au_dyaop, da_key)); -+ -+ for (i = 0; i < AuDyLast; i++) -+ au_sphl_init(dynop + i); -+} ++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_dy_fin(void) ++void au_export_init(struct super_block *sb) +{ -+ int i; ++ struct au_sbinfo *sbinfo; ++ __u32 u; + -+ for (i = 0; i < AuDyLast; i++) -+ WARN_ON(!hlist_empty(&dynop[i].head)); ++ BUILD_BUG_ON_MSG(IS_BUILTIN(CONFIG_AUFS_FS) ++ && IS_MODULE(CONFIG_EXPORTFS), ++ AUFS_NAME ": unsupported configuration " ++ "CONFIG_EXPORTFS=m and CONFIG_AUFS_FS=y"); ++ ++ sb->s_export_op = &aufs_export_op; ++ sbinfo = au_sbi(sb); ++ sbinfo->si_xigen = NULL; ++ get_random_bytes(&u, sizeof(u)); ++ BUILD_BUG_ON(sizeof(u) != sizeof(int)); ++ atomic_set(&sbinfo->si_xigen_next, u); +} -diff -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 2016-10-09 16:55:36.489368218 +0200 -@@ -0,0 +1,74 @@ +diff -urNp -x '*.orig' linux-4.9/fs/aufs/f_op.c linux-4.9/fs/aufs/f_op.c +--- linux-4.9/fs/aufs/f_op.c 1970-01-01 01:00:00.000000000 +0100 ++++ linux-4.9/fs/aufs/f_op.c 2021-02-24 16:15:09.541574180 +0100 +@@ -0,0 +1,817 @@ +/* -+ * Copyright (C) 2010-2016 Junjiro R. Okajima ++ * Copyright (C) 2005-2018 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by @@ -10928,908 +12967,811 @@ diff -urN /usr/share/empty/fs/aufs/dynop.h linux/fs/aufs/dynop.h + */ + +/* -+ * dynamically customizable operations (for regular files only) ++ * file and vm operations + */ + -+#ifndef __AUFS_DYNOP_H__ -+#define __AUFS_DYNOP_H__ ++#include ++#include ++#include ++#include ++#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 -+#include ++ FiMustWriteLock(file); + -+enum {AuDy_AOP, AuDyLast}; ++ 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); ++ } 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; ++ get_file(h_file); ++ } ++ if (IS_ERR(h_file)) ++ err = PTR_ERR(h_file); ++ else { ++ if ((flags & __O_TMPFILE) ++ && !(flags & O_EXCL)) { ++ h_inode = file_inode(h_file); ++ spin_lock(&h_inode->i_lock); ++ h_inode->i_state |= I_LINKABLE; ++ spin_unlock(&h_inode->i_lock); ++ } ++ au_set_fbtop(file, bindex); ++ au_set_h_fptr(file, bindex, h_file); ++ au_update_figen(file); ++ /* todo: necessary? */ ++ /* file->f_ra = h_file->f_ra; */ ++ } + -+struct au_dynop { -+ int dy_type; -+ union { -+ const void *dy_hop; -+ const struct address_space_operations *dy_haop; -+ }; -+}; ++out: ++ return err; ++} + -+struct au_dykey { -+ union { -+ struct hlist_node dk_hnode; -+ struct rcu_head dk_rcu; ++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 dk_op; -+ -+ /* -+ * during I am in the branch local array, kref is gotten. when the -+ * branch is removed, kref is put. -+ */ -+ struct kref dk_kref; -+}; -+ -+/* stop unioning since their sizes are very different from each other */ -+struct au_dyaop { -+ struct au_dykey da_key; -+ struct address_space_operations da_op; /* not const */ -+}; + -+/* ---------------------------------------------------------------------- */ -+ -+/* 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); ++ AuDbg("%pD, f_flags 0x%x, f_mode 0x%x\n", ++ file, vfsub_file_flags(file), file->f_mode); + -+void __init au_dy_init(void); -+void au_dy_fin(void); ++ 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; ++} + -+#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 2016-12-17 12:28:17.595211562 +0100 -@@ -0,0 +1,836 @@ -+/* -+ * Copyright (C) 2005-2016 Junjiro R. Okajima -+ * -+ * This program, aufs is free software; you can redistribute it and/or modify -+ * it under the terms of the GNU General Public License as published by -+ * the Free Software Foundation; either version 2 of the License, or -+ * (at your option) any later version. -+ * -+ * This program is distributed in the hope that it will be useful, -+ * but WITHOUT ANY WARRANTY; without even the implied warranty of -+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the -+ * GNU General Public License for more details. -+ * -+ * You should have received a copy of the GNU General Public License -+ * along with this program. If not, see . -+ */ ++int aufs_release_nondir(struct inode *inode __maybe_unused, struct file *file) ++{ ++ struct au_finfo *finfo; ++ aufs_bindex_t bindex; + -+/* -+ * export via nfs -+ */ ++ 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); + -+#include -+#include -+#include -+#include -+#include -+#include -+#include "aufs.h" ++ au_finfo_fin(file); ++ return 0; ++} + -+union conv { -+#ifdef CONFIG_AUFS_INO_T_64 -+ __u32 a[2]; -+#else -+ __u32 a[1]; -+#endif -+ ino_t ino; -+}; ++/* ---------------------------------------------------------------------- */ + -+static ino_t decode_ino(__u32 *a) ++static int au_do_flush_nondir(struct file *file, fl_owner_t id) +{ -+ union conv u; ++ int err; ++ struct file *h_file; + -+ 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; ++ err = 0; ++ h_file = au_hf_top(file); ++ if (h_file) ++ err = vfsub_flush(h_file, id); ++ return err; +} + -+static void encode_ino(__u32 *a, ino_t ino) ++static int aufs_flush_nondir(struct file *file, fl_owner_t id) +{ -+ union conv u; -+ -+ u.ino = ino; -+ a[0] = u.a[0]; -+#ifdef CONFIG_AUFS_INO_T_64 -+ a[1] = u.a[1]; -+#endif ++ return au_do_flush(file, id, au_do_flush_nondir); +} + -+/* NFS file handle */ -+enum { -+ Fh_br_id, -+ Fh_sigen, -+#ifdef CONFIG_AUFS_INO_T_64 -+ /* support 64bit inode number */ -+ Fh_ino1, -+ Fh_ino2, -+ Fh_dir_ino1, -+ Fh_dir_ino2, -+#else -+ Fh_ino1, -+ Fh_dir_ino1, -+#endif -+ Fh_igen, -+ Fh_h_type, -+ Fh_tail, -+ -+ Fh_ino = Fh_ino1, -+ Fh_dir_ino = Fh_dir_ino1 -+}; -+ -+static int au_test_anon(struct dentry *dentry) -+{ -+ /* note: read d_flags without d_lock */ -+ return !!(dentry->d_flags & DCACHE_DISCONNECTED); -+} ++/* ---------------------------------------------------------------------- */ ++/* ++ * 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-mamagement (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. ++ */ + -+int au_test_nfsd(void) ++/* 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) +{ -+ int ret; -+ struct task_struct *tsk = current; -+ char comm[sizeof(tsk->comm)]; ++ struct file *h_file; ++ int err; + -+ ret = 0; -+ if (tsk->flags & PF_KTHREAD) { -+ get_task_comm(comm, tsk); -+ ret = !strcmp(comm, "nfsd"); -+ } ++ 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 ret; ++ return h_file; +} + -+/* ---------------------------------------------------------------------- */ -+/* inode generation external table */ -+ -+void au_xigen_inc(struct inode *inode) ++static void au_read_post(struct inode *inode, struct file *h_file) +{ -+ 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)); ++ /* update without lock, I don't think it a problem */ ++ fsstack_copy_attr_atime(inode, file_inode(h_file)); ++ fput(h_file); ++} + -+ sbinfo = au_sbi(sb); -+ pos = inode->i_ino; -+ pos *= sizeof(igen); -+ igen = inode->i_generation + 1; -+ sz = xino_fwrite(sbinfo->si_xwrite, sbinfo->si_xigen, &igen, -+ sizeof(igen), &pos); -+ if (sz == sizeof(igen)) -+ return; /* success */ ++struct au_write_pre { ++ /* input */ ++ unsigned int lsc; + -+ if (unlikely(sz >= 0)) -+ AuIOErr("xigen error (%zd)\n", sz); -+} ++ /* output */ ++ blkcnt_t blks; ++ aufs_bindex_t btop; ++}; + -+int au_xigen_new(struct inode *inode) ++/* ++ * 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; -+ loff_t pos; -+ ssize_t sz; -+ struct super_block *sb; -+ struct au_sbinfo *sbinfo; -+ struct file *file; ++ unsigned int lsc; ++ struct au_pin pin; + -+ 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))) ++ 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; + -+ 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; ++ 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; ++ } + } -+ pos *= sizeof(inode->i_generation); + -+ err = 0; -+ sbinfo = au_sbi(sb); -+ file = sbinfo->si_xigen; -+ BUG_ON(!file); ++ 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); + -+ if (vfsub_f_size_read(file) -+ < pos + sizeof(inode->i_generation)) { -+ inode->i_generation = atomic_inc_return(&sbinfo->si_xigen_next); -+ sz = xino_fwrite(sbinfo->si_xwrite, file, &inode->i_generation, -+ sizeof(inode->i_generation), &pos); -+ } else -+ sz = xino_fread(sbinfo->si_xread, file, &inode->i_generation, -+ sizeof(inode->i_generation), &pos); -+ if (sz == sizeof(inode->i_generation)) -+ goto out; /* success */ ++out_fi: ++ fi_write_unlock(file); ++out: ++ return h_file; ++} + -+ err = sz; -+ if (unlikely(sz >= 0)) { -+ err = -EIO; -+ AuIOErr("xigen error (%zd)\n", sz); -+ } ++static void au_write_post(struct inode *inode, struct file *h_file, ++ struct au_write_pre *wpre, ssize_t written) ++{ ++ struct inode *h_inode; + -+out: -+ return err; ++ 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); +} + -+int au_xigen_set(struct super_block *sb, struct file *base) ++static ssize_t aufs_read(struct file *file, char __user *buf, size_t count, ++ loff_t *ppos) +{ -+ int err; -+ struct au_sbinfo *sbinfo; -+ struct file *file; ++ ssize_t err; ++ struct inode *inode; ++ struct file *h_file; ++ struct super_block *sb; + -+ SiMustWriteLock(sb); ++ inode = file_inode(file); ++ sb = inode->i_sb; ++ si_read_lock(sb, AuLock_FLUSH | AuLock_NOPLMW); + -+ sbinfo = au_sbi(sb); -+ file = au_xino_create2(base, sbinfo->si_xigen); -+ err = PTR_ERR(file); -+ if (IS_ERR(file)) ++ h_file = au_read_pre(file, /*keep_fi*/0, /*lsc*/0); ++ err = PTR_ERR(h_file); ++ if (IS_ERR(h_file)) + goto out; -+ err = 0; -+ if (sbinfo->si_xigen) -+ fput(sbinfo->si_xigen); -+ sbinfo->si_xigen = file; ++ ++ /* filedata may be obsoleted by concurrent copyup, but no problem */ ++ err = vfsub_read_u(h_file, buf, count, ppos); ++ /* todo: necessary? */ ++ /* file->f_ra = h_file->f_ra; */ ++ au_read_post(inode, h_file); + +out: ++ si_read_unlock(sb); + return err; +} + -+void au_xigen_clr(struct super_block *sb) ++/* ++ * 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) +{ -+ struct au_sbinfo *sbinfo; -+ -+ SiMustWriteLock(sb); ++ int err; ++ struct super_block *sb = inode->i_sb; + -+ sbinfo = au_sbi(sb); -+ if (sbinfo->si_xigen) { -+ fput(sbinfo->si_xigen); -+ sbinfo->si_xigen = NULL; ++ while (1) { ++ inode_lock(inode); ++ err = si_read_lock(sb, AuLock_FLUSH | AuLock_NOPLM); ++ if (!err) ++ break; ++ inode_unlock(inode); ++ si_read_lock(sb, AuLock_NOPLMW); ++ si_read_unlock(sb); + } +} + -+/* ---------------------------------------------------------------------- */ -+ -+static struct dentry *decode_by_ino(struct super_block *sb, ino_t ino, -+ ino_t dir_ino) ++static ssize_t aufs_write(struct file *file, const char __user *ubuf, ++ size_t count, loff_t *ppos) +{ -+ struct dentry *dentry, *d; ++ ssize_t err; ++ struct au_write_pre wpre; + struct inode *inode; -+ unsigned int sigen; ++ struct file *h_file; ++ char __user *buf = (char __user *)ubuf; + -+ dentry = NULL; -+ inode = ilookup(sb, ino); -+ if (!inode) -+ goto out; ++ inode = file_inode(file); ++ au_mtx_and_read_lock(inode); + -+ 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; ++ 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; + -+ 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; -+ } ++ err = vfsub_write_u(h_file, buf, count, ppos); ++ au_write_post(inode, h_file, &wpre, err); + -+out_iput: -+ iput(inode); +out: -+ AuTraceErrPtr(dentry); -+ return dentry; ++ si_read_unlock(inode->i_sb); ++ inode_unlock(inode); ++ return err; +} + -+/* ---------------------------------------------------------------------- */ -+ -+/* todo: dirty? */ -+/* if exportfs_decode_fh() passed vfsmount*, we could be happy */ ++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 *); + -+struct au_compare_mnt_args { -+ /* input */ -+ struct super_block *sb; ++ err = security_file_permission(h_file, rw); ++ if (unlikely(err)) ++ goto out; + -+ /* output */ -+ struct vfsmount *mnt; -+}; ++ err = -ENOSYS; ++ iter = NULL; ++ if (rw == MAY_READ) ++ iter = h_file->f_op->read_iter; ++ else if (rw == MAY_WRITE) ++ iter = h_file->f_op->write_iter; + -+static int au_compare_mnt(struct vfsmount *mnt, void *arg) -+{ -+ struct au_compare_mnt_args *a = arg; ++ 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; + -+ if (mnt->mnt_sb != a->sb) -+ return 0; -+ a->mnt = mntget(mnt); -+ return 1; ++out: ++ return err; +} + -+static struct vfsmount *au_mnt_get(struct super_block *sb) ++static ssize_t aufs_read_iter(struct kiocb *kio, struct iov_iter *iov_iter) +{ -+ int err; -+ struct path root; -+ struct au_compare_mnt_args args = { -+ .sb = sb -+ }; -+ -+ get_fs_root(current->fs, &root); -+ rcu_read_lock(); -+ err = iterate_mounts(au_compare_mnt, &args, root.mnt); -+ rcu_read_unlock(); -+ path_put(&root); -+ AuDebugOn(!err); -+ AuDebugOn(!args.mnt); -+ return args.mnt; -+} -+ -+struct au_nfsd_si_lock { -+ unsigned int sigen; -+ aufs_bindex_t bindex, br_id; -+ unsigned char force_lock; -+}; ++ ssize_t err; ++ struct file *file, *h_file; ++ struct inode *inode; ++ struct super_block *sb; + -+static int si_nfsd_read_lock(struct super_block *sb, -+ struct au_nfsd_si_lock *nsi_lock) -+{ -+ int err; -+ aufs_bindex_t bindex; ++ file = kio->ki_filp; ++ inode = file_inode(file); ++ sb = inode->i_sb; ++ si_read_lock(sb, AuLock_FLUSH | AuLock_NOPLMW); + -+ si_read_lock(sb, AuLock_FLUSH); ++ h_file = au_read_pre(file, /*keep_fi*/1, /*lsc*/0); ++ 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 */ ++ 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; ++ smp_mb(); /* unnecessary? */ ++ } ++ } ++ fi_read_unlock(file); + -+ err = -ESTALE; -+ bindex = -1; -+ if (!nsi_lock->force_lock) -+ si_read_unlock(sb); ++ 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: -+ nsi_lock->bindex = bindex; ++ si_read_unlock(sb); + return err; +} + -+struct find_name_by_ino { -+ struct dir_context ctx; -+ int called, found; -+ ino_t ino; -+ char *name; -+ int namelen; -+}; -+ -+static int -+find_name_by_ino(struct dir_context *ctx, const char *name, int namelen, -+ loff_t offset, u64 ino, unsigned int d_type) ++static ssize_t aufs_write_iter(struct kiocb *kio, struct iov_iter *iov_iter) +{ -+ struct find_name_by_ino *a = container_of(ctx, struct find_name_by_ino, -+ ctx); ++ ssize_t err; ++ struct au_write_pre wpre; ++ struct inode *inode; ++ struct file *file, *h_file; + -+ a->called++; -+ if (a->ino != ino) -+ return 0; ++ file = kio->ki_filp; ++ inode = file_inode(file); ++ au_mtx_and_read_lock(inode); + -+ memcpy(a->name, name, namelen); -+ a->namelen = namelen; -+ a->found = 1; -+ 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)) ++ goto out; ++ ++ err = au_do_iter(h_file, MAY_WRITE, kio, iov_iter); ++ au_write_post(inode, h_file, &wpre, err); ++ ++out: ++ si_read_unlock(inode->i_sb); ++ inode_unlock(inode); ++ return err; +} + -+static struct dentry *au_lkup_by_ino(struct path *path, ino_t ino, -+ struct au_nfsd_si_lock *nsi_lock) ++static ssize_t aufs_splice_read(struct file *file, loff_t *ppos, ++ struct pipe_inode_info *pipe, size_t len, ++ unsigned int flags) +{ -+ struct dentry *dentry, *parent; -+ struct file *file; -+ struct inode *dir; -+ struct find_name_by_ino arg = { -+ .ctx = { -+ .actor = find_name_by_ino -+ } -+ }; -+ int err; ++ ssize_t err; ++ struct file *h_file; ++ struct inode *inode; ++ struct super_block *sb; + -+ 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; ++ inode = file_inode(file); ++ sb = inode->i_sb; ++ si_read_lock(sb, AuLock_FLUSH | AuLock_NOPLMW); + -+ 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; ++ h_file = au_read_pre(file, /*keep_fi*/0, /*lsc*/0); ++ err = PTR_ERR(h_file); ++ if (IS_ERR(h_file)) ++ goto out; + -+ /* do not call vfsub_lkup_one() */ -+ dir = d_inode(parent); -+ dentry = vfsub_lookup_one_len_unlocked(arg.name, parent, arg.namelen); -+ AuTraceErrPtr(dentry); -+ if (IS_ERR(dentry)) -+ goto out_name; -+ AuDebugOn(au_test_anon(dentry)); -+ if (unlikely(d_really_is_negative(dentry))) { -+ dput(dentry); -+ dentry = ERR_PTR(-ENOENT); -+ } ++ err = vfsub_splice_to(h_file, ppos, pipe, len, flags); ++ /* todo: necessasry? */ ++ /* file->f_ra = h_file->f_ra; */ ++ au_read_post(inode, h_file); + -+out_name: -+ au_delayed_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; ++ si_read_unlock(sb); ++ return err; +} + -+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) ++static ssize_t ++aufs_splice_write(struct pipe_inode_info *pipe, struct file *file, loff_t *ppos, ++ size_t len, unsigned int flags) +{ -+ 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); ++ ssize_t err; ++ struct au_write_pre wpre; ++ struct inode *inode; ++ struct file *h_file; + -+ path.mnt = au_mnt_get(sb); -+ dentry = au_lkup_by_ino(&path, ino, nsi_lock); -+ path_put(&path); ++ inode = file_inode(file); ++ au_mtx_and_read_lock(inode); + -+out: -+ AuTraceErrPtr(dentry); -+ return dentry; -+} ++ wpre.lsc = 0; ++ h_file = au_write_pre(file, /*do_ready*/1, &wpre); ++ err = PTR_ERR(h_file); ++ if (IS_ERR(h_file)) ++ goto out; + -+/* ---------------------------------------------------------------------- */ ++ err = vfsub_splice_from(pipe, h_file, ppos, len, flags); ++ au_write_post(inode, h_file, &wpre, err); + -+static int h_acceptable(void *expv, struct dentry *dentry) -+{ -+ return 1; ++out: ++ si_read_unlock(inode->i_sb); ++ inode_unlock(inode); ++ return err; +} + -+static char *au_build_path(struct dentry *h_parent, struct path *h_rootpath, -+ char *buf, int len, struct super_block *sb) ++static long aufs_fallocate(struct file *file, int mode, loff_t offset, ++ loff_t len) +{ -+ char *p; -+ int n; -+ struct path path; ++ long err; ++ struct au_write_pre wpre; ++ struct inode *inode; ++ struct file *h_file; + -+ p = d_path(h_rootpath, buf, len); -+ if (IS_ERR(p)) -+ goto out; -+ n = strlen(p); ++ inode = file_inode(file); ++ au_mtx_and_read_lock(inode); + -+ path.mnt = h_rootpath->mnt; -+ path.dentry = h_parent; -+ p = d_path(&path, buf, len); -+ if (IS_ERR(p)) ++ 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; -+ 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)] = '/'; ++ lockdep_off(); ++ err = vfs_fallocate(h_file, mode, offset, len); ++ lockdep_on(); ++ au_write_post(inode, h_file, &wpre, /*written*/1); + +out: -+ AuTraceErrPtr(p); -+ return p; ++ si_read_unlock(inode->i_sb); ++ inode_unlock(inode); ++ return err; +} + -+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) ++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 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; ++ 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] + -+ 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)); ++ 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; -+ } -+ 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; ++ 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 comparision. ++ */ ++ 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; + -+ 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; ++ 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; + -+ si_read_unlock(sb); -+ err = vfsub_kern_path(p, LOOKUP_FOLLOW | LOOKUP_DIRECTORY, &path); -+ dentry = ERR_PTR(err); -+ if (unlikely(err)) -+ goto out_relock; ++ 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; ++ } ++ } + -+ dentry = ERR_PTR(-ENOENT); -+ AuDebugOn(au_test_anon(path.dentry)); -+ if (unlikely(d_really_is_negative(path.dentry))) -+ goto out_path; ++ 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; ++ } + -+ if (ino != d_inode(path.dentry)->i_ino) -+ dentry = au_lkup_by_ino(&path, ino, /*nsi_lock*/NULL); -+ else -+ dentry = dget(path.dentry); ++ err = vfsub_copy_file_range(a_src.h_file, src_pos, a_dst.h_file, ++ dst_pos, len, flags); + -+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: -+ au_delayed_free_page((unsigned long)pathname); -+out_h_parent: -+ dput(h_parent); ++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: -+ AuTraceErrPtr(dentry); -+ return dentry; ++ return err; ++#undef a_src ++#undef a_dst +} + +/* ---------------------------------------------------------------------- */ + -+static struct dentry * -+aufs_fh_to_dentry(struct super_block *sb, struct fid *fid, int fh_len, -+ int fh_type) -+{ -+ struct dentry *dentry; -+ __u32 *fh = fid->raw; -+ struct au_branch *br; -+ ino_t ino, dir_ino; -+ struct au_nfsd_si_lock nsi_lock = { -+ .force_lock = 0 -+ }; -+ -+ dentry = ERR_PTR(-ESTALE); -+ /* it should never happen, but the file handle is unreliable */ -+ if (unlikely(fh_len < Fh_tail)) -+ goto out; -+ nsi_lock.sigen = fh[Fh_sigen]; -+ nsi_lock.br_id = fh[Fh_br_id]; -+ -+ /* branch id may be wrapped around */ -+ br = NULL; -+ if (unlikely(si_nfsd_read_lock(sb, &nsi_lock))) -+ goto out; -+ nsi_lock.force_lock = 1; -+ -+ /* is this inode still cached? */ -+ ino = decode_ino(fh + Fh_ino); -+ /* it should never happen */ -+ if (unlikely(ino == AUFS_ROOT_INO)) -+ goto out_unlock; ++/* ++ * 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 definitly bad, but is not a problem since "si_rwsem for ++ * read" allows muliple 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. ++ */ + -+ 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; ++#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) + -+ /* is the parent dir cached? */ -+ br = au_sbr(sb, nsi_lock.bindex); -+ au_br_get(br); -+ dentry = decode_by_dir_ino(sb, ino, dir_ino, &nsi_lock); -+ if (IS_ERR(dentry)) -+ goto out_unlock; -+ if (dentry) -+ goto accept; ++static unsigned long au_arch_prot_conv(unsigned long flags) ++{ ++ /* currently ppc64 only */ ++#ifdef CONFIG_PPC64 ++ /* cf. linux/arch/powerpc/include/asm/mman.h */ ++ AuDebugOn(arch_calc_vm_prot_bits(-1) != VM_SAO); ++ return AuConv_VM_PROT(flags, SAO); ++#else ++ AuDebugOn(arch_calc_vm_prot_bits(-1)); ++ return 0; ++#endif ++} + -+ /* 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; ++static unsigned long au_prot_conv(unsigned long flags) ++{ ++ return AuConv_VM_PROT(flags, READ) ++ | AuConv_VM_PROT(flags, WRITE) ++ | AuConv_VM_PROT(flags, EXEC) ++ | au_arch_prot_conv(flags); ++} + -+accept: -+ if (!au_digen_test(dentry, au_sigen(sb)) -+ && d_inode(dentry)->i_generation == fh[Fh_igen]) -+ goto out_unlock; /* success */ ++/* cf. linux/include/linux/mman.h: calc_vm_flag_bits() */ ++#define AuConv_VM_MAP(f, b) _calc_vm_trans(f, VM_##b, MAP_##b) + -+ dput(dentry); -+ dentry = ERR_PTR(-ESTALE); -+out_unlock: -+ if (br) -+ au_br_put(br); -+ si_read_unlock(sb); -+out: -+ AuTraceErrPtr(dentry); -+ return dentry; ++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 + -+#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 int aufs_mmap(struct file *file, struct vm_area_struct *vma) +{ -+ struct dentry *parent; -+ __u32 *fh = fid->raw; -+ ino_t dir_ino; ++ 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; + -+ dir_ino = decode_ino(fh + Fh_dir_ino); -+ parent = decode_by_ino(sb, dir_ino, 0); -+ if (IS_ERR(parent)) ++ AuDbgVmRegion(file, vma); ++ ++ inode = file_inode(file); ++ sb = inode->i_sb; ++ lockdep_off(); ++ si_read_lock(sb, AuLock_NOPLMW); ++ ++ h_file = au_write_pre(file, wlock, /*wpre*/NULL); ++ lockdep_on(); ++ err = PTR_ERR(h_file); ++ if (IS_ERR(h_file)) + goto out; -+ if (!parent) -+ parent = decode_by_path(sb, au_br_index(sb, fh[Fh_br_id]), -+ dir_ino, fh, fh_len); + ++ 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 = h_file->f_op->mmap(h_file, vma); ++ if (!err) { ++ au_vm_prfile_set(vma, file); ++ fsstack_copy_attr_atime(inode, file_inode(h_file)); ++ goto out_fput; /* success */ ++ } ++ au_unset_mmapped(file); ++ au_vm_file_reset(vma, file); ++ ++out_fput: ++ lockdep_off(); ++ ii_write_unlock(inode); ++ lockdep_on(); ++ fput(h_file); +out: -+ AuTraceErrPtr(parent); -+ return parent; ++ lockdep_off(); ++ si_read_unlock(sb); ++ lockdep_on(); ++ AuTraceErr(err); ++ return err; +} -+#endif + +/* ---------------------------------------------------------------------- */ + -+static int aufs_encode_fh(struct inode *inode, __u32 *fh, int *max_len, -+ struct inode *dir) ++static int aufs_fsync_nondir(struct file *file, loff_t start, loff_t end, ++ int datasync) +{ + int err; -+ aufs_bindex_t bindex; -+ struct super_block *sb, *h_sb; -+ struct dentry *dentry, *parent, *h_parent; -+ struct inode *h_dir; -+ struct au_branch *br; ++ struct au_write_pre wpre; ++ struct inode *inode; ++ struct file *h_file; + -+ err = -ENOSPC; -+ if (unlikely(*max_len <= Fh_tail)) { -+ AuWarn1("NFSv2 client (max_len %d)?\n", *max_len); ++ err = 0; /* -EBADF; */ /* posix? */ ++ if (unlikely(!(file->f_mode & FMODE_WRITE))) + goto out; -+ } + -+ err = FILEID_ROOT; -+ if (inode->i_ino == AUFS_ROOT_INO) { -+ AuDebugOn(inode->i_ino != AUFS_ROOT_INO); -+ goto out; -+ } ++ inode = file_inode(file); ++ au_mtx_and_read_lock(inode); + -+ h_parent = NULL; -+ sb = inode->i_sb; -+ err = si_read_lock(sb, AuLock_FLUSH); -+ if (unlikely(err)) -+ goto out; ++ 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; + -+#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); -+ } ++ err = vfsub_fsync(h_file, &h_file->f_path, datasync); ++ au_write_post(inode, h_file, &wpre, /*written*/0); + -+ 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; ++out_unlock: ++ si_read_unlock(inode->i_sb); ++ inode_unlock(inode); ++out: ++ return err; ++} + -+ 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; -+ } ++static int aufs_fasync(int fd, struct file *file, int flag) ++{ ++ int err; ++ struct file *h_file; ++ struct super_block *sb; + -+ 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; ++ sb = file->f_path.dentry->d_sb; ++ si_read_lock(sb, AuLock_FLUSH | AuLock_NOPLMW); + -+ *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)); ++ h_file = au_read_pre(file, /*keep_fi*/0, /*lsc*/0); ++ err = PTR_ERR(h_file); ++ if (IS_ERR(h_file)) ++ goto out; ++ ++ if (h_file->f_op->fasync) ++ err = h_file->f_op->fasync(fd, h_file, flag); ++ fput(h_file); /* instead of au_read_post() */ + -+out_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; ++ si_read_unlock(sb); + return err; +} + -+/* ---------------------------------------------------------------------- */ -+ -+static int aufs_commit_metadata(struct inode *inode) ++static int aufs_setfl(struct file *file, unsigned long arg) +{ + int err; -+ aufs_bindex_t bindex; ++ struct file *h_file; + struct super_block *sb; -+ struct inode *h_inode; -+ int (*f)(struct inode *inode); + -+ sb = inode->i_sb; ++ sb = file->f_path.dentry->d_sb; + si_read_lock(sb, AuLock_FLUSH | AuLock_NOPLMW); -+ ii_write_lock_child(inode); -+ bindex = au_ibtop(inode); -+ AuDebugOn(bindex < 0); -+ h_inode = au_h_iptr(inode, bindex); + -+ f = h_inode->i_sb->s_export_op->commit_metadata; -+ if (f) -+ err = f(h_inode); -+ else { -+ struct writeback_control wbc = { -+ .sync_mode = WB_SYNC_ALL, -+ .nr_to_write = 0 /* metadata only */ -+ }; ++ h_file = au_read_pre(file, /*keep_fi*/0, /*lsc*/0); ++ err = PTR_ERR(h_file); ++ if (IS_ERR(h_file)) ++ goto out; + -+ err = sync_inode(h_inode, &wbc); -+ } ++ /* 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() */ + -+ au_cpup_attr_timesizes(inode); -+ ii_write_unlock(inode); ++out: + si_read_unlock(sb); + return err; +} + +/* ---------------------------------------------------------------------- */ + -+static struct export_operations aufs_export_op = { -+ .fh_to_dentry = aufs_fh_to_dentry, -+ /* .fh_to_parent = aufs_fh_to_parent, */ -+ .encode_fh = aufs_encode_fh, -+ .commit_metadata = aufs_commit_metadata -+}; -+ -+void au_export_init(struct super_block *sb) ++/* no one supports this operation, currently */ ++#if 0 ++static ssize_t aufs_sendpage(struct file *file, struct page *page, int offset, ++ size_t len, loff_t *pos, int more) +{ -+ struct au_sbinfo *sbinfo; -+ __u32 u; ++} ++#endif + -+ BUILD_BUG_ON_MSG(IS_BUILTIN(CONFIG_AUFS_FS) -+ && IS_MODULE(CONFIG_EXPORTFS), -+ AUFS_NAME ": unsupported configuration " -+ "CONFIG_EXPORTFS=m and CONFIG_AUFS_FS=y"); ++/* ---------------------------------------------------------------------- */ + -+ sb->s_export_op = &aufs_export_op; -+ sbinfo = au_sbi(sb); -+ sbinfo->si_xigen = NULL; -+ get_random_bytes(&u, sizeof(u)); -+ BUILD_BUG_ON(sizeof(u) != sizeof(int)); -+ atomic_set(&sbinfo->si_xigen_next, u); -+} -diff -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 2016-10-09 16:55:36.489368218 +0200 -@@ -0,0 +1,426 @@ ++const struct file_operations aufs_file_fop = { ++ .owner = THIS_MODULE, ++ ++ .llseek = default_llseek, ++ ++ .read = aufs_read, ++ .write = aufs_write, ++ .read_iter = aufs_read_iter, ++ .write_iter = aufs_write_iter, ++ ++#ifdef CONFIG_AUFS_POLL ++ .poll = aufs_poll, ++#endif ++ .unlocked_ioctl = aufs_ioctl_nondir, ++#ifdef CONFIG_COMPAT ++ .compat_ioctl = aufs_compat_ioctl_nondir, ++#endif ++ .mmap = aufs_mmap, ++ .open = aufs_open_nondir, ++ .flush = aufs_flush_nondir, ++ .release = aufs_release_nondir, ++ .fsync = aufs_fsync_nondir, ++ .fasync = aufs_fasync, ++ /* .sendpage = aufs_sendpage, */ ++ .setfl = aufs_setfl, ++ .splice_write = aufs_splice_write, ++ .splice_read = aufs_splice_read, ++#if 0 ++ .aio_splice_write = aufs_aio_splice_write, ++ .aio_splice_read = aufs_aio_splice_read, ++#endif ++ .fallocate = aufs_fallocate, ++ .copy_file_range = aufs_copy_file_range ++}; +diff -urNp -x '*.orig' linux-4.9/fs/aufs/fhsm.c linux-4.9/fs/aufs/fhsm.c +--- linux-4.9/fs/aufs/fhsm.c 1970-01-01 01:00:00.000000000 +0100 ++++ linux-4.9/fs/aufs/fhsm.c 2021-02-24 16:15:09.528240413 +0100 +@@ -0,0 +1,427 @@ +/* -+ * Copyright (C) 2011-2016 Junjiro R. Okajima ++ * Copyright (C) 2011-2018 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by @@ -12013,7 +13955,8 @@ diff -urN /usr/share/empty/fs/aufs/fhsm.c linux/fs/aufs/fhsm.c + if (atomic_read(&fhsm->fhsm_readable)) + mask = POLLIN /* | POLLRDNORM */; + -+ AuTraceErr((int)mask); ++ if (!mask) ++ AuDbg("mask 0x%x\n", mask); + return mask; +} + @@ -12254,12 +14197,12 @@ diff -urN /usr/share/empty/fs/aufs/fhsm.c linux/fs/aufs/fhsm.c + if (u != AUFS_FHSM_CACHE_DEF_SEC) + seq_printf(seq, ",fhsm_sec=%u", u); +} -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 2016-10-09 16:55:38.889431135 +0200 -@@ -0,0 +1,857 @@ +diff -urNp -x '*.orig' linux-4.9/fs/aufs/file.c linux-4.9/fs/aufs/file.c +--- linux-4.9/fs/aufs/file.c 1970-01-01 01:00:00.000000000 +0100 ++++ linux-4.9/fs/aufs/file.c 2021-02-24 16:15:09.528240413 +0100 +@@ -0,0 +1,848 @@ +/* -+ * Copyright (C) 2005-2016 Junjiro R. Okajima ++ * Copyright (C) 2005-2018 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by @@ -12368,7 +14311,7 @@ diff -urN /usr/share/empty/fs/aufs/file.c linux/fs/aufs/file.c + +static int au_cmoo(struct dentry *dentry) +{ -+ int err, cmoo; ++ int err, cmoo, matched; + unsigned int udba; + struct path h_path; + struct au_pin pin; @@ -12403,9 +14346,12 @@ diff -urN /usr/share/empty/fs/aufs/file.c linux/fs/aufs/file.c + sbinfo = au_sbi(sb); + fhsm = &sbinfo->si_fhsm; + pid = au_fhsm_pid(fhsm); -+ if (pid -+ && (current->pid == pid -+ || current->real_parent->pid == pid)) ++ rcu_read_lock(); ++ matched = (pid ++ && (current->pid == pid ++ || rcu_dereference(current->real_parent)->pid == pid)); ++ rcu_read_unlock(); ++ if (matched) + goto out; + + br = au_sbr(sb, cpg.bsrc); @@ -12482,11 +14428,11 @@ diff -urN /usr/share/empty/fs/aufs/file.c linux/fs/aufs/file.c + +int au_do_open(struct file *file, struct au_do_open_args *args) +{ -+ int err, no_lock = args->no_lock; ++ int err, aopen = args->aopen; + struct dentry *dentry; + struct au_finfo *finfo; + -+ if (!no_lock) ++ if (!aopen) + err = au_finfo_init(file, args->fidir); + else { + lockdep_off(); @@ -12498,33 +14444,20 @@ diff -urN /usr/share/empty/fs/aufs/file.c linux/fs/aufs/file.c + + dentry = file->f_path.dentry; + AuDebugOn(IS_ERR_OR_NULL(dentry)); -+ if (!no_lock) { -+ di_write_lock_child(dentry); -+ err = au_cmoo(dentry); -+ di_downgrade_lock(dentry, AuLock_IR); -+ if (!err) -+ err = args->open(file, vfsub_file_flags(file), NULL); -+ di_read_unlock(dentry, AuLock_IR); -+ } else { -+ err = au_cmoo(dentry); -+ if (!err) -+ err = args->open(file, vfsub_file_flags(file), -+ args->h_file); -+ if (!err && au_fbtop(file) != au_dbtop(dentry)) -+ /* -+ * cmoo happens after h_file was opened. -+ * need to refresh file later. -+ */ -+ atomic_dec(&au_fi(file)->fi_generation); -+ } ++ di_write_lock_child(dentry); ++ err = au_cmoo(dentry); ++ di_downgrade_lock(dentry, AuLock_IR); ++ if (!err) ++ err = args->open(file, vfsub_file_flags(file), NULL); ++ di_read_unlock(dentry, AuLock_IR); + + finfo = au_fi(file); + if (!err) { + finfo->fi_file = file; -+ au_sphl_add(&finfo->fi_hlist, -+ &au_sbi(file->f_path.dentry->d_sb)->si_files); ++ au_hbl_add(&finfo->fi_hlist, ++ &au_sbi(file->f_path.dentry->d_sb)->si_files); + } -+ if (!no_lock) ++ if (!aopen) + fi_write_unlock(file); + else { + lockdep_off(); @@ -12533,7 +14466,7 @@ diff -urN /usr/share/empty/fs/aufs/file.c linux/fs/aufs/file.c + } + if (unlikely(err)) { + finfo->fi_hdir = NULL; -+ au_finfo_fin(file, /*atonce*/0); ++ au_finfo_fin(file); + } + +out: @@ -12853,7 +14786,6 @@ diff -urN /usr/share/empty/fs/aufs/file.c linux/fs/aufs/file.c + +static void au_do_refresh_dir(struct file *file) +{ -+ int execed; + aufs_bindex_t bindex, bbot, new_bindex, brid; + struct au_hfile *p, tmp, *q; + struct au_finfo *finfo; @@ -12892,7 +14824,6 @@ diff -urN /usr/share/empty/fs/aufs/file.c linux/fs/aufs/file.c + } + } + -+ execed = vfsub_file_execed(file); + p = fidir->fd_hfile; + if (!au_test_mmapped(file) && !d_unlinked(file->f_path.dentry)) { + bbot = au_sbbot(sb); @@ -12901,14 +14832,14 @@ diff -urN /usr/share/empty/fs/aufs/file.c linux/fs/aufs/file.c + if (p->hf_file) { + if (file_inode(p->hf_file)) + break; -+ au_hfput(p, execed); ++ au_hfput(p, /*execed*/0); + } + } else { + bbot = au_br_index(sb, brid); + for (finfo->fi_btop = 0; finfo->fi_btop < bbot; + finfo->fi_btop++, p++) + if (p->hf_file) -+ au_hfput(p, execed); ++ au_hfput(p, /*execed*/0); + bbot = au_sbbot(sb); + } + @@ -12918,7 +14849,7 @@ diff -urN /usr/share/empty/fs/aufs/file.c linux/fs/aufs/file.c + if (p->hf_file) { + if (file_inode(p->hf_file)) + break; -+ au_hfput(p, execed); ++ au_hfput(p, /*execed*/0); + } + AuDebugOn(fidir->fd_bbot < finfo->fi_btop); +} @@ -12980,7 +14911,7 @@ diff -urN /usr/share/empty/fs/aufs/file.c linux/fs/aufs/file.c + +/* common function to regular file and dir */ +int au_reval_and_lock_fdi(struct file *file, int (*reopen)(struct file *file), -+ int wlock) ++ int wlock, unsigned int fi_lsc) +{ + int err; + unsigned int sigen, figen; @@ -12993,9 +14924,12 @@ diff -urN /usr/share/empty/fs/aufs/file.c linux/fs/aufs/file.c + dentry = file->f_path.dentry; + inode = d_inode(dentry); + sigen = au_sigen(dentry->d_sb); -+ fi_write_lock(file); ++ fi_write_lock_nested(file, fi_lsc); + figen = au_figen(file); -+ di_write_lock_child(dentry); ++ if (!fi_lsc) ++ di_write_lock_child(dentry); ++ else ++ di_write_lock_child2(dentry); + btop = au_dbtop(dentry); + pseudo_link = (btop != au_ibtop(inode)); + if (sigen == figen && !pseudo_link && au_fbtop(file) == btop) { @@ -13034,546 +14968,93 @@ diff -urN /usr/share/empty/fs/aufs/file.c linux/fs/aufs/file.c +/* for madvise(2) */ +static int aufs_readpage(struct file *file __maybe_unused, struct page *page) +{ -+ unlock_page(page); -+ return 0; -+} -+ -+/* it will never be called, but necessary to support O_DIRECT */ -+static ssize_t aufs_direct_IO(struct kiocb *iocb, struct iov_iter *iter) -+{ BUG(); return 0; } -+ -+/* they will never be called. */ -+#ifdef CONFIG_AUFS_DEBUG -+static int aufs_write_begin(struct file *file, struct address_space *mapping, -+ loff_t pos, unsigned len, unsigned flags, -+ struct page **pagep, void **fsdata) -+{ AuUnsupport(); return 0; } -+static int aufs_write_end(struct file *file, struct address_space *mapping, -+ loff_t pos, unsigned len, unsigned copied, -+ struct page *page, void *fsdata) -+{ AuUnsupport(); return 0; } -+static int aufs_writepage(struct page *page, struct writeback_control *wbc) -+{ AuUnsupport(); return 0; } -+ -+static int aufs_set_page_dirty(struct page *page) -+{ AuUnsupport(); return 0; } -+static void aufs_invalidatepage(struct page *page, unsigned int offset, -+ unsigned int length) -+{ AuUnsupport(); } -+static int aufs_releasepage(struct page *page, gfp_t gfp) -+{ AuUnsupport(); return 0; } -+#if 0 /* called by memory compaction regardless file */ -+static int aufs_migratepage(struct address_space *mapping, struct page *newpage, -+ struct page *page, enum migrate_mode mode) -+{ AuUnsupport(); return 0; } -+#endif -+static bool aufs_isolate_page(struct page *page, isolate_mode_t mode) -+{ AuUnsupport(); return true; } -+static void aufs_putback_page(struct page *page) -+{ AuUnsupport(); } -+static int aufs_launder_page(struct page *page) -+{ AuUnsupport(); return 0; } -+static int aufs_is_partially_uptodate(struct page *page, -+ unsigned long from, -+ unsigned long count) -+{ AuUnsupport(); return 0; } -+static void aufs_is_dirty_writeback(struct page *page, bool *dirty, -+ bool *writeback) -+{ AuUnsupport(); } -+static int aufs_error_remove_page(struct address_space *mapping, -+ struct page *page) -+{ AuUnsupport(); return 0; } -+static int aufs_swap_activate(struct swap_info_struct *sis, struct file *file, -+ sector_t *span) -+{ AuUnsupport(); return 0; } -+static void aufs_swap_deactivate(struct file *file) -+{ AuUnsupport(); } -+#endif /* CONFIG_AUFS_DEBUG */ -+ -+const struct address_space_operations aufs_aop = { -+ .readpage = aufs_readpage, -+ .direct_IO = aufs_direct_IO, -+#ifdef CONFIG_AUFS_DEBUG -+ .writepage = aufs_writepage, -+ /* no writepages, because of writepage */ -+ .set_page_dirty = aufs_set_page_dirty, -+ /* no readpages, because of readpage */ -+ .write_begin = aufs_write_begin, -+ .write_end = aufs_write_end, -+ /* no bmap, no block device */ -+ .invalidatepage = aufs_invalidatepage, -+ .releasepage = aufs_releasepage, -+ /* is fallback_migrate_page ok? */ -+ /* .migratepage = aufs_migratepage, */ -+ .isolate_page = aufs_isolate_page, -+ .putback_page = aufs_putback_page, -+ .launder_page = aufs_launder_page, -+ .is_partially_uptodate = aufs_is_partially_uptodate, -+ .is_dirty_writeback = aufs_is_dirty_writeback, -+ .error_remove_page = aufs_error_remove_page, -+ .swap_activate = aufs_swap_activate, -+ .swap_deactivate = aufs_swap_deactivate -+#endif /* CONFIG_AUFS_DEBUG */ -+}; -diff -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 2016-10-09 16:55:38.889431135 +0200 -@@ -0,0 +1,294 @@ -+/* -+ * Copyright (C) 2005-2016 Junjiro R. Okajima -+ * -+ * This program, aufs is free software; you can redistribute it and/or modify -+ * it under the terms of the GNU General Public License as published by -+ * the Free Software Foundation; either version 2 of the License, or -+ * (at your option) any later version. -+ * -+ * This program is distributed in the hope that it will be useful, -+ * but WITHOUT ANY WARRANTY; without even the implied warranty of -+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the -+ * GNU General Public License for more details. -+ * -+ * You should have received a copy of the GNU General Public License -+ * along with this program. If not, see . -+ */ -+ -+/* -+ * file operations -+ */ -+ -+#ifndef __AUFS_FILE_H__ -+#define __AUFS_FILE_H__ -+ -+#ifdef __KERNEL__ -+ -+#include -+#include -+#include -+#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_node fi_hlist; -+ union { -+ struct file *fi_file; /* very ugly */ -+ struct llist_node fi_lnode; /* delayed free */ -+ }; -+} ____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 no_lock; -+ 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); -+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 -+unsigned int aufs_poll(struct file *file, poll_table *wait); -+#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); -+ -+/* 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 atonce); -+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; -+} -+ -+/* ---------------------------------------------------------------------- */ -+ -+/* -+ * fi_read_lock, fi_write_lock, -+ * fi_read_unlock, fi_write_unlock, fi_downgrade_lock -+ */ -+AuSimpleRwsemFuncs(fi, struct file *f, &au_fi(f)->fi_rwsem); -+ -+#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 2016-10-09 16:55:38.889431135 +0200 -@@ -0,0 +1,151 @@ -+/* -+ * Copyright (C) 2005-2016 Junjiro R. Okajima -+ * -+ * This program, aufs is free software; you can redistribute it and/or modify -+ * it under the terms of the GNU General Public License as published by -+ * the Free Software Foundation; either version 2 of the License, or -+ * (at your option) any later version. -+ * -+ * This program is distributed in the hope that it will be useful, -+ * but WITHOUT ANY WARRANTY; without even the implied warranty of -+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the -+ * GNU General Public License for more details. -+ * -+ * You should have received a copy of the GNU General Public License -+ * along with this program. If not, see . -+ */ -+ -+/* -+ * 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_br_put(hf->hf_br); -+ 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, int atonce) -+{ -+ struct au_finfo *finfo; -+ -+ au_nfiles_dec(file->f_path.dentry->d_sb); -+ -+ finfo = au_fi(file); -+ AuDebugOn(finfo->fi_hdir); -+ AuRwDestroy(&finfo->fi_rwsem); -+ if (!atonce) -+ au_cache_dfree_finfo(finfo); -+ else -+ 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; ++ unlock_page(page); ++ return 0; ++} + -+ err = -ENOMEM; -+ dentry = file->f_path.dentry; -+ finfo = au_cache_alloc_finfo(); -+ if (unlikely(!finfo)) -+ goto out; ++/* it will never be called, but necessary to support O_DIRECT */ ++static ssize_t aufs_direct_IO(struct kiocb *iocb, struct iov_iter *iter) ++{ BUG(); return 0; } + -+ err = 0; -+ au_nfiles_inc(dentry->d_sb); -+ 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 */ ++/* they will never be called. */ ++#ifdef CONFIG_AUFS_DEBUG ++static int aufs_write_begin(struct file *file, struct address_space *mapping, ++ loff_t pos, unsigned len, unsigned flags, ++ struct page **pagep, void **fsdata) ++{ AuUnsupport(); return 0; } ++static int aufs_write_end(struct file *file, struct address_space *mapping, ++ loff_t pos, unsigned len, unsigned copied, ++ struct page *page, void *fsdata) ++{ AuUnsupport(); return 0; } ++static int aufs_writepage(struct page *page, struct writeback_control *wbc) ++{ AuUnsupport(); return 0; } + -+ file->private_data = finfo; ++static int aufs_set_page_dirty(struct page *page) ++{ AuUnsupport(); return 0; } ++static void aufs_invalidatepage(struct page *page, unsigned int offset, ++ unsigned int length) ++{ AuUnsupport(); } ++static int aufs_releasepage(struct page *page, gfp_t gfp) ++{ AuUnsupport(); return 0; } ++#if 0 /* called by memory compaction regardless file */ ++static int aufs_migratepage(struct address_space *mapping, struct page *newpage, ++ struct page *page, enum migrate_mode mode) ++{ AuUnsupport(); return 0; } ++#endif ++static bool aufs_isolate_page(struct page *page, isolate_mode_t mode) ++{ AuUnsupport(); return true; } ++static void aufs_putback_page(struct page *page) ++{ AuUnsupport(); } ++static int aufs_launder_page(struct page *page) ++{ AuUnsupport(); return 0; } ++static int aufs_is_partially_uptodate(struct page *page, ++ unsigned long from, ++ unsigned long count) ++{ AuUnsupport(); return 0; } ++static void aufs_is_dirty_writeback(struct page *page, bool *dirty, ++ bool *writeback) ++{ AuUnsupport(); } ++static int aufs_error_remove_page(struct address_space *mapping, ++ struct page *page) ++{ AuUnsupport(); return 0; } ++static int aufs_swap_activate(struct swap_info_struct *sis, struct file *file, ++ sector_t *span) ++{ AuUnsupport(); return 0; } ++static void aufs_swap_deactivate(struct file *file) ++{ AuUnsupport(); } ++#endif /* CONFIG_AUFS_DEBUG */ + -+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 2016-12-17 12:28:17.595211562 +0100 -@@ -0,0 +1,723 @@ ++const struct address_space_operations aufs_aop = { ++ .readpage = aufs_readpage, ++ .direct_IO = aufs_direct_IO, ++#ifdef CONFIG_AUFS_DEBUG ++ .writepage = aufs_writepage, ++ /* no writepages, because of writepage */ ++ .set_page_dirty = aufs_set_page_dirty, ++ /* no readpages, because of readpage */ ++ .write_begin = aufs_write_begin, ++ .write_end = aufs_write_end, ++ /* no bmap, no block device */ ++ .invalidatepage = aufs_invalidatepage, ++ .releasepage = aufs_releasepage, ++ /* is fallback_migrate_page ok? */ ++ /* .migratepage = aufs_migratepage, */ ++ .isolate_page = aufs_isolate_page, ++ .putback_page = aufs_putback_page, ++ .launder_page = aufs_launder_page, ++ .is_partially_uptodate = aufs_is_partially_uptodate, ++ .is_dirty_writeback = aufs_is_dirty_writeback, ++ .error_remove_page = aufs_error_remove_page, ++ .swap_activate = aufs_swap_activate, ++ .swap_deactivate = aufs_swap_deactivate ++#endif /* CONFIG_AUFS_DEBUG */ ++}; +diff -urNp -x '*.orig' linux-4.9/fs/aufs/file.h linux-4.9/fs/aufs/file.h +--- linux-4.9/fs/aufs/file.h 1970-01-01 01:00:00.000000000 +0100 ++++ linux-4.9/fs/aufs/file.h 2021-02-24 16:15:09.528240413 +0100 +@@ -0,0 +1,330 @@ +/* -+ * Copyright (C) 2005-2016 Junjiro R. Okajima ++ * Copyright (C) 2005-2018 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by @@ -13590,717 +15071,476 @@ diff -urN /usr/share/empty/fs/aufs/f_op.c linux/fs/aufs/f_op.c + */ + +/* -+ * file and vm operations ++ * file operations + */ + -+#include -+#include -+#include -+#include -+#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); -+ } 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; -+ get_file(h_file); -+ } -+ if (IS_ERR(h_file)) -+ err = PTR_ERR(h_file); -+ else { -+ if ((flags & __O_TMPFILE) -+ && !(flags & O_EXCL)) { -+ h_inode = file_inode(h_file); -+ spin_lock(&h_inode->i_lock); -+ h_inode->i_state |= I_LINKABLE; -+ spin_unlock(&h_inode->i_lock); -+ } -+ au_set_fbtop(file, bindex); -+ au_set_h_fptr(file, bindex, h_file); -+ au_update_figen(file); -+ /* todo: necessary? */ -+ /* file->f_ra = h_file->f_ra; */ -+ } ++#ifndef __AUFS_FILE_H__ ++#define __AUFS_FILE_H__ + -+out: -+ return err; -+} ++#ifdef __KERNEL__ + -+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 -+ }; ++#include ++#include ++#include ++#include "rwsem.h" + -+ AuDbg("%pD, f_flags 0x%x, f_mode 0x%x\n", -+ file, vfsub_file_flags(file), file->f_mode); ++struct au_branch; ++struct au_hfile { ++ struct file *hf_file; ++ struct au_branch *hf_br; ++}; + -+ 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 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[]; ++}; + -+int aufs_release_nondir(struct inode *inode __maybe_unused, struct file *file) ++static inline int au_fidir_sz(int nent) +{ -+ struct au_finfo *finfo; -+ aufs_bindex_t bindex; -+ int delayed; -+ -+ finfo = au_fi(file); -+ au_sphl_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); -+ -+ delayed = (current->flags & PF_KTHREAD) || in_interrupt(); -+ au_finfo_fin(file, delayed); -+ return 0; ++ AuDebugOn(nent < 0); ++ return sizeof(struct au_fidir) + sizeof(struct au_hfile) * nent; +} + -+/* ---------------------------------------------------------------------- */ ++struct au_finfo { ++ atomic_t fi_generation; + -+static int au_do_flush_nondir(struct file *file, fl_owner_t id) -+{ -+ int err; -+ struct file *h_file; ++ struct au_rwsem fi_rwsem; ++ aufs_bindex_t fi_btop; + -+ err = 0; -+ h_file = au_hf_top(file); -+ if (h_file) -+ err = vfsub_flush(h_file, id); -+ return err; -+} ++ /* 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 */ + -+static int aufs_flush_nondir(struct file *file, fl_owner_t id) -+{ -+ return au_do_flush(file, id, au_do_flush_nondir); -+} ++ struct hlist_bl_node fi_hlist; ++ struct file *fi_file; /* very ugly */ ++} ____cacheline_aligned_in_smp; + +/* ---------------------------------------------------------------------- */ -+/* -+ * 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-mamagement (by keeping -+ * si_rwsem), no harmful copy-up should happen. Actually copy-up may happen in -+ * read functions after [fdi]_rwsem are released, but it should be harmless. -+ */ -+ -+/* Callers should call au_read_post() or fput() in the end */ -+struct file *au_read_pre(struct file *file, int keep_fi) -+{ -+ struct file *h_file; -+ int err; -+ -+ err = au_reval_and_lock_fdi(file, au_reopen_nondir, /*wlock*/0); -+ if (!err) { -+ di_read_unlock(file->f_path.dentry, AuLock_IR); -+ h_file = au_hf_top(file); -+ get_file(h_file); -+ if (!keep_fi) -+ fi_read_unlock(file); -+ } else -+ h_file = ERR_PTR(err); -+ -+ return h_file; -+} -+ -+static void au_read_post(struct inode *inode, struct file *h_file) -+{ -+ /* update without lock, I don't think it a problem */ -+ fsstack_copy_attr_atime(inode, file_inode(h_file)); -+ fput(h_file); -+} + -+struct au_write_pre { -+ blkcnt_t blks; -+ aufs_bindex_t btop; ++/* 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)); + -+/* -+ * 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; -+ struct au_pin pin; ++/* poll.c */ ++#ifdef CONFIG_AUFS_POLL ++unsigned int aufs_poll(struct file *file, poll_table *wait); ++#endif + -+ err = au_reval_and_lock_fdi(file, au_reopen_nondir, /*wlock*/1); -+ h_file = ERR_PTR(err); -+ if (unlikely(err)) -+ goto out; ++#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 + -+ 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; -+ } -+ } ++/* 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); + -+ 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); ++/* 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); + -+out_fi: -+ fi_write_unlock(file); -+out: -+ return 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); + -+static void au_write_post(struct inode *inode, struct file *h_file, -+ struct au_write_pre *wpre, ssize_t written) -+{ -+ struct inode *h_inode; ++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); + -+ 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); -+ fput(h_file); ++/* 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 + -+ /* 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); -+} ++/* ---------------------------------------------------------------------- */ + -+static ssize_t aufs_read(struct file *file, char __user *buf, size_t count, -+ loff_t *ppos) ++static inline struct au_finfo *au_fi(struct file *file) +{ -+ ssize_t err; -+ struct inode *inode; -+ struct file *h_file; -+ struct super_block *sb; -+ -+ inode = file_inode(file); -+ sb = inode->i_sb; -+ si_read_lock(sb, AuLock_FLUSH | AuLock_NOPLMW); -+ -+ h_file = au_read_pre(file, /*keep_fi*/0); -+ err = PTR_ERR(h_file); -+ if (IS_ERR(h_file)) -+ goto out; -+ -+ /* filedata may be obsoleted by concurrent copyup, but no problem */ -+ err = vfsub_read_u(h_file, buf, count, ppos); -+ /* todo: necessary? */ -+ /* file->f_ra = h_file->f_ra; */ -+ au_read_post(inode, h_file); -+ -+out: -+ si_read_unlock(sb); -+ return err; ++ return file->private_data; +} + ++/* ---------------------------------------------------------------------- */ ++ +/* -+ * 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. ++ * fi_read_lock, fi_write_lock, ++ * fi_read_unlock, fi_write_unlock, fi_downgrade_lock + */ -+static void au_mtx_and_read_lock(struct inode *inode) -+{ -+ int err; -+ struct super_block *sb = inode->i_sb; ++AuSimpleRwsemFuncs(fi, struct file *f, &au_fi(f)->fi_rwsem); + -+ 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); -+ } -+} ++/* lock subclass for finfo */ ++enum { ++ AuLsc_FI_1, ++ AuLsc_FI_2 ++}; + -+static ssize_t aufs_write(struct file *file, const char __user *ubuf, -+ size_t count, loff_t *ppos) ++static inline void fi_read_lock_nested(struct file *f, unsigned int lsc) +{ -+ ssize_t err; -+ struct au_write_pre wpre; -+ struct inode *inode; -+ struct file *h_file; -+ char __user *buf = (char __user *)ubuf; -+ -+ inode = file_inode(file); -+ au_mtx_and_read_lock(inode); -+ -+ h_file = au_write_pre(file, /*do_ready*/1, &wpre); -+ err = PTR_ERR(h_file); -+ if (IS_ERR(h_file)) -+ goto out; -+ -+ err = vfsub_write_u(h_file, buf, count, ppos); -+ au_write_post(inode, h_file, &wpre, err); -+ -+out: -+ si_read_unlock(inode->i_sb); -+ inode_unlock(inode); -+ return err; ++ au_rw_read_lock_nested(&au_fi(f)->fi_rwsem, lsc); +} + -+static ssize_t au_do_iter(struct file *h_file, int rw, struct kiocb *kio, -+ struct iov_iter *iov_iter) ++static inline void fi_write_lock_nested(struct file *f, unsigned int lsc) +{ -+ ssize_t err; -+ struct file *file; -+ ssize_t (*iter)(struct kiocb *, struct iov_iter *); -+ -+ err = security_file_permission(h_file, rw); -+ if (unlikely(err)) -+ goto out; -+ -+ err = -ENOSYS; -+ iter = NULL; -+ if (rw == MAY_READ) -+ iter = h_file->f_op->read_iter; -+ else if (rw == MAY_WRITE) -+ iter = h_file->f_op->write_iter; -+ -+ file = kio->ki_filp; -+ kio->ki_filp = h_file; -+ if (iter) { -+ lockdep_off(); -+ err = iter(kio, iov_iter); -+ lockdep_on(); -+ } else -+ /* currently there is no such fs */ -+ WARN_ON_ONCE(1); -+ kio->ki_filp = file; -+ -+out: -+ return err; ++ au_rw_write_lock_nested(&au_fi(f)->fi_rwsem, lsc); +} + -+static ssize_t aufs_read_iter(struct kiocb *kio, struct iov_iter *iov_iter) -+{ -+ ssize_t err; -+ struct file *file, *h_file; -+ struct inode *inode; -+ struct super_block *sb; -+ -+ file = kio->ki_filp; -+ inode = file_inode(file); -+ sb = inode->i_sb; -+ si_read_lock(sb, AuLock_FLUSH | AuLock_NOPLMW); -+ -+ h_file = au_read_pre(file, /*keep_fi*/1); -+ err = PTR_ERR(h_file); -+ if (IS_ERR(h_file)) -+ goto out; ++/* ++ * 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); } + -+ 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); ++#define AuWriteLockFunc(name) \ ++static inline void fi_write_lock_##name(struct file *f) \ ++{ fi_write_lock_nested(f, AuLsc_FI_##name); } + -+ 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); ++#define AuRWLockFuncs(name) \ ++ AuReadLockFunc(name) \ ++ AuWriteLockFunc(name) + -+out: -+ si_read_unlock(sb); -+ return err; -+} ++AuRWLockFuncs(1); ++AuRWLockFuncs(2); + -+static ssize_t aufs_write_iter(struct kiocb *kio, struct iov_iter *iov_iter) -+{ -+ ssize_t err; -+ struct au_write_pre wpre; -+ struct inode *inode; -+ struct file *file, *h_file; ++#undef AuReadLockFunc ++#undef AuWriteLockFunc ++#undef AuRWLockFuncs + -+ file = kio->ki_filp; -+ inode = file_inode(file); -+ au_mtx_and_read_lock(inode); ++#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) + -+ 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); ++/* todo: hard/soft set? */ ++static inline aufs_bindex_t au_fbtop(struct file *file) ++{ ++ FiMustAnyLock(file); ++ return au_fi(file)->fi_btop; ++} + -+out: -+ si_read_unlock(inode->i_sb); -+ inode_unlock(inode); -+ return err; ++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 ssize_t aufs_splice_read(struct file *file, loff_t *ppos, -+ struct pipe_inode_info *pipe, size_t len, -+ unsigned int flags) ++static inline struct au_vdir *au_fvdir_cache(struct file *file) +{ -+ ssize_t err; -+ struct file *h_file; -+ struct inode *inode; -+ struct super_block *sb; ++ FiMustAnyLock(file); ++ AuDebugOn(!au_fi(file)->fi_hdir); ++ return au_fi(file)->fi_hdir->fd_vdir_cache; ++} + -+ inode = file_inode(file); -+ sb = inode->i_sb; -+ si_read_lock(sb, AuLock_FLUSH | AuLock_NOPLMW); ++static inline void au_set_fbtop(struct file *file, aufs_bindex_t bindex) ++{ ++ FiMustWriteLock(file); ++ au_fi(file)->fi_btop = bindex; ++} + -+ h_file = au_read_pre(file, /*keep_fi*/0); -+ err = PTR_ERR(h_file); -+ if (IS_ERR(h_file)) -+ goto out; ++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; ++} + -+ err = vfsub_splice_to(h_file, ppos, pipe, len, flags); -+ /* todo: necessasry? */ -+ /* file->f_ra = h_file->f_ra; */ -+ au_read_post(inode, h_file); ++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; ++} + -+out: -+ si_read_unlock(sb); -+ return 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; +} + -+static ssize_t -+aufs_splice_write(struct pipe_inode_info *pipe, struct file *file, loff_t *ppos, -+ size_t len, unsigned int flags) ++static inline struct file *au_hf_dir(struct file *file, aufs_bindex_t bindex) +{ -+ ssize_t err; -+ struct au_write_pre wpre; -+ struct inode *inode; -+ struct file *h_file; ++ FiMustAnyLock(file); ++ AuDebugOn(!au_fi(file)->fi_hdir); ++ return au_fi(file)->fi_hdir->fd_hfile[0 + bindex].hf_file; ++} + -+ inode = file_inode(file); -+ au_mtx_and_read_lock(inode); ++/* todo: memory barrier? */ ++static inline unsigned int au_figen(struct file *f) ++{ ++ return atomic_read(&au_fi(f)->fi_generation); ++} + -+ 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_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)) ++ ; ++} + -+ err = vfsub_splice_from(pipe, h_file, ppos, len, flags); -+ au_write_post(inode, h_file, &wpre, err); ++static inline void au_unset_mmapped(struct file *f) ++{ ++ atomic_dec(&au_fi(f)->fi_mmapped); ++} + -+out: -+ si_read_unlock(inode->i_sb); -+ inode_unlock(inode); -+ return err; ++static inline int au_test_mmapped(struct file *f) ++{ ++ return atomic_read(&au_fi(f)->fi_mmapped); +} + -+static long aufs_fallocate(struct file *file, int mode, loff_t offset, -+ loff_t len) ++/* customize vma->vm_file */ ++ ++static inline void au_do_vm_file_reset(struct vm_area_struct *vma, ++ struct file *file) +{ -+ long err; -+ struct au_write_pre wpre; -+ struct inode *inode; -+ struct file *h_file; ++ struct file *f; + -+ inode = file_inode(file); -+ au_mtx_and_read_lock(inode); ++ f = vma->vm_file; ++ get_file(file); ++ vma->vm_file = file; ++ fput(f); ++} + -+ h_file = au_write_pre(file, /*do_ready*/1, &wpre); -+ err = PTR_ERR(h_file); -+ if (IS_ERR(h_file)) -+ goto out; ++#ifdef CONFIG_MMU ++#define AuDbgVmRegion(file, vma) do {} while (0) + -+ lockdep_off(); -+ err = vfs_fallocate(h_file, mode, offset, len); -+ lockdep_on(); -+ au_write_post(inode, h_file, &wpre, /*written*/1); ++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)) + -+out: -+ si_read_unlock(inode->i_sb); -+ inode_unlock(inode); -+ return err; ++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 -urNp -x '*.orig' linux-4.9/fs/aufs/finfo.c linux-4.9/fs/aufs/finfo.c +--- linux-4.9/fs/aufs/finfo.c 1970-01-01 01:00:00.000000000 +0100 ++++ linux-4.9/fs/aufs/finfo.c 2021-02-24 16:15:09.528240413 +0100 +@@ -0,0 +1,148 @@ +/* -+ * 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 definitly bad, but is not a problem since "si_rwsem for -+ * read" allows muliple 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. ++ * Copyright (C) 2005-2018 Junjiro R. Okajima + * -+ * 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. ++ * This program, aufs is free software; you can redistribute it and/or modify ++ * it under the terms of the GNU General Public License as published by ++ * the Free Software Foundation; either version 2 of the License, or ++ * (at your option) any later version. ++ * ++ * This program is distributed in the hope that it will be useful, ++ * but WITHOUT ANY WARRANTY; without even the implied warranty of ++ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the ++ * GNU General Public License for more details. ++ * ++ * You should have received a copy of the GNU General Public License ++ * along with this program. If not, see . + */ + -+#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) ++/* ++ * file private data ++ */ + -+static unsigned long au_arch_prot_conv(unsigned long flags) ++#include "aufs.h" ++ ++void au_hfput(struct au_hfile *hf, int execed) +{ -+ /* 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 ++ if (execed) ++ allow_write_access(hf->hf_file); ++ fput(hf->hf_file); ++ hf->hf_file = NULL; ++ au_br_put(hf->hf_br); ++ hf->hf_br = NULL; +} + -+static unsigned long au_prot_conv(unsigned long flags) ++void au_set_h_fptr(struct file *file, aufs_bindex_t bindex, struct file *val) +{ -+ return AuConv_VM_PROT(flags, READ) -+ | AuConv_VM_PROT(flags, WRITE) -+ | AuConv_VM_PROT(flags, EXEC) -+ | au_arch_prot_conv(flags); -+} ++ struct au_finfo *finfo = au_fi(file); ++ struct au_hfile *hf; ++ struct au_fidir *fidir; + -+/* cf. linux/include/linux/mman.h: calc_vm_flag_bits() */ -+#define AuConv_VM_MAP(f, b) _calc_vm_trans(f, VM_##b, MAP_##b) ++ fidir = finfo->fi_hdir; ++ if (!fidir) { ++ AuDebugOn(finfo->fi_btop != bindex); ++ hf = &finfo->fi_htop; ++ } else ++ hf = fidir->fd_hfile + 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); ++ 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); ++ } +} -+#endif + -+static int aufs_mmap(struct file *file, struct vm_area_struct *vma) ++void au_update_figen(struct file *file) +{ -+ 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); ++ atomic_set(&au_fi(file)->fi_generation, au_digen(file->f_path.dentry)); ++ /* smp_mb(); */ /* atomic_set */ ++} + -+ inode = file_inode(file); -+ sb = inode->i_sb; -+ lockdep_off(); -+ si_read_lock(sb, AuLock_NOPLMW); ++/* ---------------------------------------------------------------------- */ + -+ h_file = au_write_pre(file, wlock, /*wpre*/NULL); -+ lockdep_on(); -+ err = PTR_ERR(h_file); -+ if (IS_ERR(h_file)) -+ goto out; ++struct au_fidir *au_fidir_alloc(struct super_block *sb) ++{ ++ struct au_fidir *fidir; ++ int nbr; + -+ 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 = h_file->f_op->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 */ ++ 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; + } -+ au_unset_mmapped(file); -+ au_vm_file_reset(vma, file); + -+out_fput: -+ lockdep_off(); -+ ii_write_unlock(inode); -+ lockdep_on(); -+ fput(h_file); -+out: -+ lockdep_off(); -+ si_read_unlock(sb); -+ lockdep_on(); -+ AuTraceErr(err); -+ return err; ++ return fidir; +} + -+/* ---------------------------------------------------------------------- */ -+ -+static int aufs_fsync_nondir(struct file *file, loff_t start, loff_t end, -+ int datasync) ++int au_fidir_realloc(struct au_finfo *finfo, int nbr, int may_shrink) +{ + int err; -+ struct au_write_pre wpre; -+ struct inode *inode; -+ struct file *h_file; -+ -+ err = 0; /* -EBADF; */ /* posix? */ -+ if (unlikely(!(file->f_mode & FMODE_WRITE))) -+ goto out; -+ -+ inode = file_inode(file); -+ au_mtx_and_read_lock(inode); ++ struct au_fidir *fidir, *p; + -+ h_file = au_write_pre(file, /*do_ready*/1, &wpre); -+ err = PTR_ERR(h_file); -+ if (IS_ERR(h_file)) -+ goto out_unlock; ++ AuRwMustWriteLock(&finfo->fi_rwsem); ++ fidir = finfo->fi_hdir; ++ AuDebugOn(!fidir); + -+ err = vfsub_fsync(h_file, &h_file->f_path, datasync); -+ au_write_post(inode, h_file, &wpre, /*written*/0); ++ 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; ++ } + -+out_unlock: -+ si_read_unlock(inode->i_sb); -+ inode_unlock(inode); -+out: + return err; +} + -+static int aufs_fasync(int fd, struct file *file, int flag) ++/* ---------------------------------------------------------------------- */ ++ ++void au_finfo_fin(struct file *file) +{ -+ int err; -+ struct file *h_file; -+ struct super_block *sb; ++ struct au_finfo *finfo; + -+ sb = file->f_path.dentry->d_sb; -+ si_read_lock(sb, AuLock_FLUSH | AuLock_NOPLMW); ++ au_nfiles_dec(file->f_path.dentry->d_sb); + -+ h_file = au_read_pre(file, /*keep_fi*/0); -+ err = PTR_ERR(h_file); -+ if (IS_ERR(h_file)) -+ goto out; ++ finfo = au_fi(file); ++ AuDebugOn(finfo->fi_hdir); ++ AuRwDestroy(&finfo->fi_rwsem); ++ au_cache_free_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() */ ++void au_fi_init_once(void *_finfo) ++{ ++ struct au_finfo *finfo = _finfo; + -+out: -+ si_read_unlock(sb); -+ return err; ++ au_rw_init(&finfo->fi_rwsem); +} + -+static int aufs_setfl(struct file *file, unsigned long arg) ++int au_finfo_init(struct file *file, struct au_fidir *fidir) +{ + int err; -+ struct file *h_file; -+ struct super_block *sb; -+ -+ sb = file->f_path.dentry->d_sb; -+ si_read_lock(sb, AuLock_FLUSH | AuLock_NOPLMW); ++ struct au_finfo *finfo; ++ struct dentry *dentry; + -+ h_file = au_read_pre(file, /*keep_fi*/0); -+ err = PTR_ERR(h_file); -+ if (IS_ERR(h_file)) ++ err = -ENOMEM; ++ dentry = file->f_path.dentry; ++ finfo = au_cache_alloc_finfo(); ++ if (unlikely(!finfo)) + goto out; + -+ arg |= vfsub_file_flags(file) & FASYNC; /* stop calling h_file->fasync */ -+ err = setfl(/*unused fd*/-1, h_file, arg); -+ fput(h_file); /* instead of au_read_post() */ ++ err = 0; ++ au_nfiles_inc(dentry->d_sb); ++ 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: -+ si_read_unlock(sb); + return err; +} -+ -+/* ---------------------------------------------------------------------- */ -+ -+/* no one supports this operation, currently */ -+#if 0 -+static ssize_t aufs_sendpage(struct file *file, struct page *page, int offset, -+ size_t len, loff_t *pos, int more) -+{ -+} -+#endif -+ -+/* ---------------------------------------------------------------------- */ -+ -+const struct file_operations aufs_file_fop = { -+ .owner = THIS_MODULE, -+ -+ .llseek = default_llseek, -+ -+ .read = aufs_read, -+ .write = aufs_write, -+ .read_iter = aufs_read_iter, -+ .write_iter = aufs_write_iter, -+ -+#ifdef CONFIG_AUFS_POLL -+ .poll = aufs_poll, -+#endif -+ .unlocked_ioctl = aufs_ioctl_nondir, -+#ifdef CONFIG_COMPAT -+ .compat_ioctl = aufs_compat_ioctl_nondir, -+#endif -+ .mmap = aufs_mmap, -+ .open = aufs_open_nondir, -+ .flush = aufs_flush_nondir, -+ .release = aufs_release_nondir, -+ .fsync = aufs_fsync_nondir, -+ .fasync = aufs_fasync, -+ /* .sendpage = aufs_sendpage, */ -+ .setfl = aufs_setfl, -+ .splice_write = aufs_splice_write, -+ .splice_read = aufs_splice_read, -+#if 0 -+ .aio_splice_write = aufs_aio_splice_write, -+ .aio_splice_read = aufs_aio_splice_read, -+#endif -+ .fallocate = aufs_fallocate -+}; -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 2016-10-09 16:55:36.492701639 +0200 +diff -urNp -x '*.orig' linux-4.9/fs/aufs/fstype.h linux-4.9/fs/aufs/fstype.h +--- linux-4.9/fs/aufs/fstype.h 1970-01-01 01:00:00.000000000 +0100 ++++ linux-4.9/fs/aufs/fstype.h 2021-02-24 16:15:09.528240413 +0100 @@ -0,0 +1,400 @@ +/* -+ * Copyright (C) 2005-2016 Junjiro R. Okajima ++ * Copyright (C) 2005-2018 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by @@ -14699,12 +15939,80 @@ diff -urN /usr/share/empty/fs/aufs/fstype.h linux/fs/aufs/fstype.h + +#endif /* __KERNEL__ */ +#endif /* __AUFS_FSTYPE_H__ */ -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 2016-10-09 16:55:36.492701639 +0200 +diff -urNp -x '*.orig' linux-4.9/fs/aufs/hbl.h linux-4.9/fs/aufs/hbl.h +--- linux-4.9/fs/aufs/hbl.h 1970-01-01 01:00:00.000000000 +0100 ++++ linux-4.9/fs/aufs/hbl.h 2021-02-24 16:15:09.528240413 +0100 +@@ -0,0 +1,64 @@ ++/* ++ * Copyright (C) 2017-2018 Junjiro R. Okajima ++ * ++ * This program, aufs is free software; you can redistribute it and/or modify ++ * it under the terms of the GNU General Public License as published by ++ * the Free Software Foundation; either version 2 of the License, or ++ * (at your option) any later version. ++ * ++ * This program is distributed in the hope that it will be useful, ++ * but WITHOUT ANY WARRANTY; without even the implied warranty of ++ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the ++ * GNU General Public License for more details. ++ * ++ * You should have received a copy of the GNU General Public License ++ * along with this program. If not, see . ++ */ ++ ++/* ++ * helpers for hlist_bl.h ++ */ ++ ++#ifndef __AUFS_HBL_H__ ++#define __AUFS_HBL_H__ ++ ++#ifdef __KERNEL__ ++ ++#include ++ ++static inline void au_hbl_add(struct hlist_bl_node *node, ++ struct hlist_bl_head *hbl) ++{ ++ hlist_bl_lock(hbl); ++ hlist_bl_add_head(node, hbl); ++ hlist_bl_unlock(hbl); ++} ++ ++static inline void au_hbl_del(struct hlist_bl_node *node, ++ struct hlist_bl_head *hbl) ++{ ++ hlist_bl_lock(hbl); ++ hlist_bl_del(node); ++ hlist_bl_unlock(hbl); ++} ++ ++#define au_hbl_for_each(pos, head) \ ++ for (pos = hlist_bl_first(head); \ ++ pos; \ ++ pos = pos->next) ++ ++static inline unsigned long au_hbl_count(struct hlist_bl_head *hbl) ++{ ++ unsigned long cnt; ++ struct hlist_bl_node *pos; ++ ++ cnt = 0; ++ hlist_bl_lock(hbl); ++ au_hbl_for_each(pos, hbl) ++ cnt++; ++ hlist_bl_unlock(hbl); ++ return cnt; ++} ++ ++#endif /* __KERNEL__ */ ++#endif /* __AUFS_HBL_H__ */ +diff -urNp -x '*.orig' linux-4.9/fs/aufs/hfsnotify.c linux-4.9/fs/aufs/hfsnotify.c +--- linux-4.9/fs/aufs/hfsnotify.c 1970-01-01 01:00:00.000000000 +0100 ++++ linux-4.9/fs/aufs/hfsnotify.c 2021-02-24 16:15:09.528240413 +0100 @@ -0,0 +1,287 @@ +/* -+ * Copyright (C) 2005-2016 Junjiro R. Okajima ++ * Copyright (C) 2005-2018 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by @@ -14737,8 +16045,8 @@ diff -urN /usr/share/empty/fs/aufs/hfsnotify.c linux/fs/aufs/hfsnotify.c + struct au_hnotify *hn = container_of(mark, struct au_hnotify, + hn_mark); + /* AuDbg("here\n"); */ -+ au_cache_dfree_hnotify(hn); -+ smp_mb__before_atomic(); ++ au_cache_free_hnotify(hn); ++ smp_mb__before_atomic(); /* for atomic64_dec */ + if (atomic64_dec_and_test(&au_hfsn_ifree)) + wake_up(&au_hfsn_wq); +} @@ -14861,7 +16169,7 @@ diff -urN /usr/share/empty/fs/aufs/hfsnotify.c linux/fs/aufs/hfsnotify.c + struct au_br_hfsnotify *hfsn = group->private; + + /* AuDbg("here\n"); */ -+ au_delayed_kfree(hfsn); ++ kfree(hfsn); +} + +static int au_hfsn_handle_event(struct fsnotify_group *group, @@ -14955,7 +16263,7 @@ diff -urN /usr/share/empty/fs/aufs/hfsnotify.c linux/fs/aufs/hfsnotify.c + goto out; /* success */ + +out_hfsn: -+ au_delayed_kfree(hfsn); ++ kfree(hfsn); +out: + return err; +} @@ -14990,12 +16298,12 @@ diff -urN /usr/share/empty/fs/aufs/hfsnotify.c linux/fs/aufs/hfsnotify.c + .fin_br = au_hfsn_fin_br, + .init_br = au_hfsn_init_br +}; -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 2016-10-09 16:55:36.492701639 +0200 +diff -urNp -x '*.orig' linux-4.9/fs/aufs/hfsplus.c linux-4.9/fs/aufs/hfsplus.c +--- linux-4.9/fs/aufs/hfsplus.c 1970-01-01 01:00:00.000000000 +0100 ++++ linux-4.9/fs/aufs/hfsplus.c 2021-02-24 16:15:09.528240413 +0100 @@ -0,0 +1,56 @@ +/* -+ * Copyright (C) 2010-2016 Junjiro R. Okajima ++ * Copyright (C) 2010-2018 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by @@ -15050,12 +16358,12 @@ diff -urN /usr/share/empty/fs/aufs/hfsplus.c linux/fs/aufs/hfsplus.c + au_sbr_put(dentry->d_sb, bindex); + } +} -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 2016-10-09 16:55:36.492701639 +0200 -@@ -0,0 +1,723 @@ +diff -urNp -x '*.orig' linux-4.9/fs/aufs/hnotify.c linux-4.9/fs/aufs/hnotify.c +--- linux-4.9/fs/aufs/hnotify.c 1970-01-01 01:00:00.000000000 +0100 ++++ linux-4.9/fs/aufs/hnotify.c 2021-02-24 16:15:09.528240413 +0100 +@@ -0,0 +1,719 @@ +/* -+ * Copyright (C) 2005-2016 Junjiro R. Okajima ++ * Copyright (C) 2005-2018 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by @@ -15091,7 +16399,7 @@ diff -urN /usr/share/empty/fs/aufs/hnotify.c linux/fs/aufs/hnotify.c + AuTraceErr(err); + if (unlikely(err)) { + hinode->hi_notify = NULL; -+ au_cache_dfree_hnotify(hn); ++ au_cache_free_hnotify(hn); + /* + * The upper dir was removed by udba, but the same named + * dir left. In this case, aufs assignes a new inode @@ -15115,7 +16423,7 @@ diff -urN /usr/share/empty/fs/aufs/hnotify.c linux/fs/aufs/hnotify.c + if (hn) { + hinode->hi_notify = NULL; + if (au_hnotify_op.free(hinode, hn)) -+ au_cache_dfree_hnotify(hn); ++ au_cache_free_hnotify(hn); + } +} + @@ -15378,11 +16686,11 @@ diff -urN /usr/share/empty/fs/aufs/hnotify.c linux/fs/aufs/hnotify.c + if (au_ftest_hnjob(a->flags, TRYXINO0) + && a->inode + && a->h_inode) { -+ inode_lock_nested(a->h_inode, AuLsc_I_CHILD); ++ vfsub_inode_lock_shared_nested(a->h_inode, AuLsc_I_CHILD); + if (!a->h_inode->i_nlink + && !(a->h_inode->i_state & I_LINKABLE)) + hn_xino(a->inode, a->h_inode); /* ignore this error */ -+ inode_unlock(a->h_inode); ++ inode_unlock_shared(a->h_inode); + } + + /* make the generation obsolete */ @@ -15518,6 +16826,14 @@ diff -urN /usr/share/empty/fs/aufs/hnotify.c linux/fs/aufs/hnotify.c + AuDebugOn(!sbinfo); + si_write_lock(sb, AuLock_NOPLMW); + ++ if (au_opt_test(sbinfo->si_mntflags, DIRREN)) ++ switch (a->mask & FS_EVENTS_POSS_ON_CHILD) { ++ case FS_MOVED_FROM: ++ case FS_MOVED_TO: ++ AuWarn1("DIRREN with UDBA may not work correctly " ++ "for the direct rename(2)\n"); ++ } ++ + ii_read_lock_parent(a->dir); + bfound = -1; + bbot = au_ibbot(a->dir); @@ -15588,7 +16904,7 @@ diff -urN /usr/share/empty/fs/aufs/hnotify.c linux/fs/aufs/hnotify.c + iput(a->dir); + si_write_unlock(sb); + au_nwt_done(&sbinfo->si_nowait); -+ au_delayed_kfree(a); ++ kfree(a); +} + +/* ---------------------------------------------------------------------- */ @@ -15683,1836 +16999,2489 @@ diff -urN /usr/share/empty/fs/aufs/hnotify.c linux/fs/aufs/hnotify.c + p[len] = 0; + } + -+ /* NFS fires the event for silly-renamed one from kworker */ -+ f = 0; -+ if (!dir->i_nlink -+ || (au_test_nfs(h_dir->i_sb) && (mask & FS_DELETE))) -+ f = AuWkq_NEST; -+ err = au_wkq_nowait(au_hn_bh, args, dir->i_sb, f); -+ if (unlikely(err)) { -+ pr_err("wkq %d\n", err); -+ iput(args->h_child_inode); -+ iput(args->h_dir); -+ iput(args->dir); -+ au_delayed_kfree(args); ++ /* NFS fires the event for silly-renamed one from kworker */ ++ f = 0; ++ if (!dir->i_nlink ++ || (au_test_nfs(h_dir->i_sb) && (mask & FS_DELETE))) ++ f = AuWkq_NEST; ++ err = au_wkq_nowait(au_hn_bh, args, dir->i_sb, f); ++ if (unlikely(err)) { ++ pr_err("wkq %d\n", err); ++ iput(args->h_child_inode); ++ iput(args->h_dir); ++ iput(args->dir); ++ kfree(args); ++ } ++ ++out: ++ return err; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++int au_hnotify_reset_br(unsigned int udba, struct au_branch *br, int perm) ++{ ++ int err; ++ ++ AuDebugOn(!(udba & AuOptMask_UDBA)); ++ ++ err = 0; ++ if (au_hnotify_op.reset_br) ++ err = au_hnotify_op.reset_br(udba, br, perm); ++ ++ return err; ++} ++ ++int au_hnotify_init_br(struct au_branch *br, int perm) ++{ ++ int err; ++ ++ err = 0; ++ if (au_hnotify_op.init_br) ++ err = au_hnotify_op.init_br(br, perm); ++ ++ return err; ++} ++ ++void au_hnotify_fin_br(struct au_branch *br) ++{ ++ if (au_hnotify_op.fin_br) ++ au_hnotify_op.fin_br(br); ++} ++ ++static void au_hn_destroy_cache(void) ++{ ++ kmem_cache_destroy(au_cache[AuCache_HNOTIFY]); ++ au_cache[AuCache_HNOTIFY] = NULL; ++} ++ ++int __init au_hnotify_init(void) ++{ ++ int err; ++ ++ err = -ENOMEM; ++ au_cache[AuCache_HNOTIFY] = AuCache(au_hnotify); ++ if (au_cache[AuCache_HNOTIFY]) { ++ err = 0; ++ if (au_hnotify_op.init) ++ err = au_hnotify_op.init(); ++ if (unlikely(err)) ++ au_hn_destroy_cache(); ++ } ++ AuTraceErr(err); ++ return err; ++} ++ ++void au_hnotify_fin(void) ++{ ++ if (au_hnotify_op.fin) ++ au_hnotify_op.fin(); ++ ++ /* cf. au_cache_fin() */ ++ if (au_cache[AuCache_HNOTIFY]) ++ au_hn_destroy_cache(); ++} +diff -urNp -x '*.orig' linux-4.9/fs/aufs/i_op.c linux-4.9/fs/aufs/i_op.c +--- linux-4.9/fs/aufs/i_op.c 1970-01-01 01:00:00.000000000 +0100 ++++ linux-4.9/fs/aufs/i_op.c 2021-02-24 16:15:09.531573855 +0100 +@@ -0,0 +1,1459 @@ ++/* ++ * Copyright (C) 2005-2018 Junjiro R. Okajima ++ * ++ * This program, aufs is free software; you can redistribute it and/or modify ++ * it under the terms of the GNU General Public License as published by ++ * the Free Software Foundation; either version 2 of the License, or ++ * (at your option) any later version. ++ * ++ * This program is distributed in the hope that it will be useful, ++ * but WITHOUT ANY WARRANTY; without even the implied warranty of ++ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the ++ * GNU General Public License for more details. ++ * ++ * You should have received a copy of the GNU General Public License ++ * along with this program. If not, see . ++ */ ++ ++/* ++ * inode operations (except add/del/rename) ++ */ ++ ++#include ++#include ++#include ++#include ++#include "aufs.h" ++ ++static int h_permission(struct inode *h_inode, int mask, ++ struct path *h_path, int brperm) ++{ ++ int err; ++ const unsigned char write_mask = !!(mask & (MAY_WRITE | MAY_APPEND)); ++ ++ err = -EPERM; ++ if (write_mask && IS_IMMUTABLE(h_inode)) ++ goto out; ++ ++ err = -EACCES; ++ if (((mask & MAY_EXEC) ++ && S_ISREG(h_inode->i_mode) ++ && (path_noexec(h_path) ++ || !(h_inode->i_mode & S_IXUGO)))) ++ goto out; ++ ++ /* ++ * - skip the lower fs test in the case of write to ro branch. ++ * - nfs dir permission write check is optimized, but a policy for ++ * link/rename requires a real check. ++ * - nfs always sets MS_POSIXACL regardless its mount option 'noacl.' ++ * in this case, generic_permission() returns -EOPNOTSUPP. ++ */ ++ if ((write_mask && !au_br_writable(brperm)) ++ || (au_test_nfs(h_inode->i_sb) && S_ISDIR(h_inode->i_mode) ++ && write_mask && !(mask & MAY_READ)) ++ || !h_inode->i_op->permission) { ++ /* AuLabel(generic_permission); */ ++ /* AuDbg("get_acl %pf\n", h_inode->i_op->get_acl); */ ++ err = generic_permission(h_inode, mask); ++ if (err == -EOPNOTSUPP && au_test_nfs_noacl(h_inode)) ++ err = h_inode->i_op->permission(h_inode, mask); ++ AuTraceErr(err); ++ } else { ++ /* AuLabel(h_inode->permission); */ ++ err = h_inode->i_op->permission(h_inode, mask); ++ AuTraceErr(err); ++ } ++ ++ if (!err) ++ err = devcgroup_inode_permission(h_inode, mask); ++ if (!err) ++ err = security_inode_permission(h_inode, mask); ++ ++#if 0 ++ if (!err) { ++ /* todo: do we need to call ima_path_check()? */ ++ struct path h_path = { ++ .dentry = ++ .mnt = h_mnt ++ }; ++ err = ima_path_check(&h_path, ++ mask & (MAY_READ | MAY_WRITE | MAY_EXEC), ++ IMA_COUNT_LEAVE); ++ } ++#endif ++ ++out: ++ return err; ++} ++ ++static int aufs_permission(struct inode *inode, int mask) ++{ ++ int err; ++ aufs_bindex_t bindex, bbot; ++ const unsigned char isdir = !!S_ISDIR(inode->i_mode), ++ write_mask = !!(mask & (MAY_WRITE | MAY_APPEND)); ++ struct inode *h_inode; ++ struct super_block *sb; ++ struct au_branch *br; ++ ++ /* todo: support rcu-walk? */ ++ if (mask & MAY_NOT_BLOCK) ++ return -ECHILD; ++ ++ sb = inode->i_sb; ++ si_read_lock(sb, AuLock_FLUSH); ++ ii_read_lock_child(inode); ++#if 0 ++ err = au_iigen_test(inode, au_sigen(sb)); ++ if (unlikely(err)) ++ goto out; ++#endif ++ ++ if (!isdir ++ || write_mask ++ || au_opt_test(au_mntflags(sb), DIRPERM1)) { ++ err = au_busy_or_stale(); ++ h_inode = au_h_iptr(inode, au_ibtop(inode)); ++ if (unlikely(!h_inode ++ || (h_inode->i_mode & S_IFMT) ++ != (inode->i_mode & S_IFMT))) ++ goto out; ++ ++ err = 0; ++ bindex = au_ibtop(inode); ++ br = au_sbr(sb, bindex); ++ err = h_permission(h_inode, mask, &br->br_path, br->br_perm); ++ if (write_mask ++ && !err ++ && !special_file(h_inode->i_mode)) { ++ /* test whether the upper writable branch exists */ ++ err = -EROFS; ++ for (; bindex >= 0; bindex--) ++ if (!au_br_rdonly(au_sbr(sb, bindex))) { ++ err = 0; ++ break; ++ } ++ } ++ goto out; ++ } ++ ++ /* non-write to dir */ ++ err = 0; ++ bbot = au_ibbot(inode); ++ for (bindex = au_ibtop(inode); !err && bindex <= bbot; bindex++) { ++ h_inode = au_h_iptr(inode, bindex); ++ if (h_inode) { ++ err = au_busy_or_stale(); ++ if (unlikely(!S_ISDIR(h_inode->i_mode))) ++ break; ++ ++ br = au_sbr(sb, bindex); ++ err = h_permission(h_inode, mask, &br->br_path, ++ br->br_perm); ++ } ++ } ++ ++out: ++ ii_read_unlock(inode); ++ si_read_unlock(sb); ++ return err; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++static struct dentry *aufs_lookup(struct inode *dir, struct dentry *dentry, ++ unsigned int flags) ++{ ++ struct dentry *ret, *parent; ++ struct inode *inode; ++ struct super_block *sb; ++ int err, npositive; ++ ++ IMustLock(dir); ++ ++ /* todo: support rcu-walk? */ ++ ret = ERR_PTR(-ECHILD); ++ if (flags & LOOKUP_RCU) ++ goto out; ++ ++ ret = ERR_PTR(-ENAMETOOLONG); ++ if (unlikely(dentry->d_name.len > AUFS_MAX_NAMELEN)) ++ goto out; ++ ++ sb = dir->i_sb; ++ err = si_read_lock(sb, AuLock_FLUSH | AuLock_NOPLM); ++ ret = ERR_PTR(err); ++ if (unlikely(err)) ++ goto out; ++ ++ err = au_di_init(dentry); ++ ret = ERR_PTR(err); ++ if (unlikely(err)) ++ goto out_si; ++ ++ inode = NULL; ++ npositive = 0; /* suppress a warning */ ++ parent = dentry->d_parent; /* dir inode is locked */ ++ di_read_lock_parent(parent, AuLock_IR); ++ err = au_alive_dir(parent); ++ if (!err) ++ err = au_digen_test(parent, au_sigen(sb)); ++ if (!err) { ++ /* regardless LOOKUP_CREATE, always ALLOW_NEG */ ++ npositive = au_lkup_dentry(dentry, au_dbtop(parent), ++ AuLkup_ALLOW_NEG); ++ err = npositive; ++ } ++ di_read_unlock(parent, AuLock_IR); ++ ret = ERR_PTR(err); ++ if (unlikely(err < 0)) ++ goto out_unlock; ++ ++ if (npositive) { ++ inode = au_new_inode(dentry, /*must_new*/0); ++ if (IS_ERR(inode)) { ++ ret = (void *)inode; ++ inode = NULL; ++ goto out_unlock; ++ } ++ } ++ ++ if (inode) ++ atomic_inc(&inode->i_count); ++ ret = d_splice_alias(inode, dentry); ++#if 0 ++ if (unlikely(d_need_lookup(dentry))) { ++ spin_lock(&dentry->d_lock); ++ dentry->d_flags &= ~DCACHE_NEED_LOOKUP; ++ spin_unlock(&dentry->d_lock); ++ } else ++#endif ++ if (inode) { ++ if (!IS_ERR(ret)) { ++ iput(inode); ++ if (ret && ret != dentry) ++ ii_write_unlock(inode); ++ } else { ++ ii_write_unlock(inode); ++ iput(inode); ++ inode = NULL; ++ } ++ } ++ ++out_unlock: ++ di_write_unlock(dentry); ++out_si: ++ si_read_unlock(sb); ++out: ++ return ret; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++struct aopen_node { ++ struct hlist_bl_node hblist; ++ struct file *file, *h_file; ++}; ++ ++static int au_do_aopen(struct inode *inode, struct file *file) ++{ ++ struct hlist_bl_head *aopen; ++ struct hlist_bl_node *pos; ++ struct aopen_node *node; ++ struct au_do_open_args args = { ++ .aopen = 1, ++ .open = au_do_open_nondir ++ }; ++ ++ aopen = &au_sbi(inode->i_sb)->si_aopen; ++ hlist_bl_lock(aopen); ++ hlist_bl_for_each_entry(node, pos, aopen, hblist) ++ if (node->file == file) { ++ args.h_file = node->h_file; ++ break; ++ } ++ hlist_bl_unlock(aopen); ++ /* AuDebugOn(!args.h_file); */ ++ ++ return au_do_open(file, &args); ++} ++ ++static int aufs_atomic_open(struct inode *dir, struct dentry *dentry, ++ struct file *file, unsigned int open_flag, ++ umode_t create_mode, int *opened) ++{ ++ int err, unlocked, h_opened = *opened; ++ unsigned int lkup_flags; ++ struct dentry *parent, *d; ++ struct hlist_bl_head *aopen; ++ struct vfsub_aopen_args args = { ++ .open_flag = open_flag, ++ .create_mode = create_mode, ++ .opened = &h_opened ++ }; ++ struct aopen_node aopen_node = { ++ .file = file ++ }; ++ ++ IMustLock(dir); ++ AuDbg("open_flag 0%o\n", open_flag); ++ AuDbgDentry(dentry); ++ ++ err = 0; ++ if (!au_di(dentry)) { ++ lkup_flags = LOOKUP_OPEN; ++ if (open_flag & O_CREAT) ++ lkup_flags |= LOOKUP_CREATE; ++ d = aufs_lookup(dir, dentry, lkup_flags); ++ if (IS_ERR(d)) { ++ err = PTR_ERR(d); ++ AuTraceErr(err); ++ goto out; ++ } else if (d) { ++ /* ++ * obsoleted dentry found. ++ * another error will be returned later. ++ */ ++ d_drop(d); ++ AuDbgDentry(d); ++ dput(d); ++ } ++ AuDbgDentry(dentry); ++ } ++ ++ if (d_is_positive(dentry) ++ || d_unhashed(dentry) ++ || d_unlinked(dentry) ++ || !(open_flag & O_CREAT)) ++ goto out_no_open; ++ ++ unlocked = 0; ++ err = aufs_read_lock(dentry, AuLock_DW | AuLock_FLUSH | AuLock_GEN); ++ if (unlikely(err)) ++ goto out; ++ ++ 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)) ++ goto out_unlock; ++ ++ AuDbgDentry(dentry); ++ if (d_is_positive(dentry)) ++ goto out_unlock; ++ ++ args.file = get_empty_filp(); ++ err = PTR_ERR(args.file); ++ if (IS_ERR(args.file)) ++ goto out_unlock; ++ ++ args.file->f_flags = file->f_flags; ++ err = au_aopen_or_create(dir, dentry, &args); ++ AuTraceErr(err); ++ AuDbgFile(args.file); ++ if (unlikely(err < 0)) { ++ if (h_opened & FILE_OPENED) ++ fput(args.file); ++ else ++ put_filp(args.file); ++ goto out_unlock; ++ } ++ di_write_unlock(parent); ++ di_write_unlock(dentry); ++ unlocked = 1; ++ ++ /* some filesystems don't set FILE_CREATED while succeeded? */ ++ *opened |= FILE_CREATED; ++ if (h_opened & FILE_OPENED) ++ aopen_node.h_file = args.file; ++ else { ++ put_filp(args.file); ++ args.file = NULL; + } ++ aopen = &au_sbi(dir->i_sb)->si_aopen; ++ au_hbl_add(&aopen_node.hblist, aopen); ++ err = finish_open(file, dentry, au_do_aopen, opened); ++ au_hbl_del(&aopen_node.hblist, aopen); ++ AuTraceErr(err); ++ AuDbgFile(file); ++ if (aopen_node.h_file) ++ fput(aopen_node.h_file); + ++out_unlock: ++ if (unlocked) ++ si_read_unlock(dentry->d_sb); ++ else { ++ di_write_unlock(parent); ++ aufs_read_unlock(dentry, AuLock_DW); ++ } ++ AuDbgDentry(dentry); ++ if (unlikely(err < 0)) ++ goto out; ++out_no_open: ++ if (err >= 0 && !(*opened & FILE_CREATED)) { ++ AuLabel(out_no_open); ++ dget(dentry); ++ err = finish_no_open(file, dentry); ++ } +out: ++ AuDbg("%pd%s%s\n", dentry, ++ (*opened & FILE_CREATED) ? " created" : "", ++ (*opened & FILE_OPENED) ? " opened" : ""); ++ AuTraceErr(err); + return err; +} + ++ +/* ---------------------------------------------------------------------- */ + -+int au_hnotify_reset_br(unsigned int udba, struct au_branch *br, int perm) ++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; + -+ AuDebugOn(!(udba & AuOptMask_UDBA)); -+ -+ err = 0; -+ if (au_hnotify_op.reset_br) -+ err = au_hnotify_op.reset_br(udba, br, perm); -+ -+ return err; -+} -+ -+int au_hnotify_init_br(struct au_branch *br, int perm) -+{ -+ int err; ++ if (add_entry) ++ IMustLock(d_inode(parent)); ++ else ++ di_write_lock_parent(parent); + + err = 0; -+ if (au_hnotify_op.init_br) -+ err = au_hnotify_op.init_br(br, perm); -+ -+ return err; -+} -+ -+void au_hnotify_fin_br(struct au_branch *br) -+{ -+ if (au_hnotify_op.fin_br) -+ au_hnotify_op.fin_br(br); -+} -+ -+static void au_hn_destroy_cache(void) -+{ -+ struct au_cache *cp; -+ -+ flush_delayed_work(&au_dfree.dwork); -+ cp = au_dfree.cache + AuCache_HNOTIFY; -+ AuDebugOn(!llist_empty(&cp->llist)); -+ kmem_cache_destroy(cp->cache); -+ cp->cache = NULL; -+} ++ 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); ++ vfsub_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); + -+AU_CACHE_DFREE_FUNC(hnotify, HNOTIFY, hn_lnode); ++ 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); ++ } ++ } + -+int __init au_hnotify_init(void) -+{ -+ int err; -+ struct au_cache *cp; ++ if (!add_entry) ++ di_write_unlock(parent); ++ if (!err) ++ err = bcpup; /* success */ + -+ err = -ENOMEM; -+ cp = au_dfree.cache + AuCache_HNOTIFY; -+ cp->cache = AuCache(au_hnotify); -+ if (cp->cache) { -+ err = 0; -+ if (au_hnotify_op.init) -+ err = au_hnotify_op.init(); -+ if (unlikely(err)) -+ au_hn_destroy_cache(); -+ } + AuTraceErr(err); + return err; +} + -+void au_hnotify_fin(void) -+{ -+ struct au_cache *cp; -+ -+ if (au_hnotify_op.fin) -+ au_hnotify_op.fin(); -+ -+ /* cf. au_cache_fin() */ -+ cp = au_dfree.cache + AuCache_HNOTIFY; -+ if (cp->cache) -+ au_hn_destroy_cache(); -+} -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 2016-10-09 16:55:38.889431135 +0200 -@@ -0,0 +1,285 @@ -+/* -+ * Copyright (C) 2005-2016 Junjiro R. Okajima -+ * -+ * This program, aufs is free software; you can redistribute it and/or modify -+ * it under the terms of the GNU General Public License as published by -+ * the Free Software Foundation; either version 2 of the License, or -+ * (at your option) any later version. -+ * -+ * This program is distributed in the hope that it will be useful, -+ * but WITHOUT ANY WARRANTY; without even the implied warranty of -+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the -+ * GNU General Public License for more details. -+ * -+ * You should have received a copy of the GNU General Public License -+ * along with this program. If not, see . -+ */ -+ +/* -+ * inode private data ++ * 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. + */ -+ -+#include "aufs.h" -+ -+struct inode *au_h_iptr(struct inode *inode, aufs_bindex_t bindex) -+{ -+ struct inode *h_inode; -+ struct au_hinode *hinode; -+ -+ IiMustAnyLock(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; -+} -+ -+/* todo: hard/soft set? */ -+void au_hiput(struct au_hinode *hinode) -+{ -+ au_hn_free(hinode); -+ dput(hinode->hi_whdentry); -+ iput(hinode->hi_inode); -+} -+ -+unsigned int au_hi_flags(struct inode *inode, int isdir) ++int au_wr_dir(struct dentry *dentry, struct dentry *src_dentry, ++ struct au_wr_dir_args *args) +{ ++ int err; + unsigned int flags; -+ const unsigned int mnt_flags = au_mntflags(inode->i_sb); -+ -+ 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; -+} -+ -+void au_set_h_iptr(struct inode *inode, aufs_bindex_t bindex, -+ struct inode *h_inode, unsigned int flags) -+{ -+ struct au_hinode *hinode; -+ struct inode *hi; -+ struct au_iinfo *iinfo = au_ii(inode); -+ -+ IiMustWriteLock(inode); -+ -+ hinode = au_hinode(iinfo, bindex); -+ hi = hinode->hi_inode; -+ AuDebugOn(h_inode && atomic_read(&h_inode->i_count) <= 0); -+ -+ 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; ++ 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; + -+ 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); ++ 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 (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); ++ 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))); + } -+} -+ -+void au_set_hi_wh(struct inode *inode, aufs_bindex_t bindex, -+ struct dentry *h_wh) -+{ -+ struct au_hinode *hinode; -+ -+ 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; ++ AuDbg("btop %d, bcpup %d\n", btop, bcpup); ++ err = bcpup; ++ if (bcpup == btop) ++ goto out; /* success */ + -+ 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); ++ /* 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)); + } + -+ 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); ++out: ++ dput(parent); ++ return err; +} + +/* ---------------------------------------------------------------------- */ + -+void au_icntnr_init_once(void *_c) ++void au_pin_hdir_unlock(struct au_pin *p) +{ -+ 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); ++ if (p->hdir) ++ au_hn_inode_unlock(p->hdir); +} + -+void au_hinode_init(struct au_hinode *hinode) ++int au_pin_hdir_lock(struct au_pin *p) +{ -+ hinode->hi_inode = NULL; -+ hinode->hi_id = -1; -+ au_hn_init(hinode); -+ hinode->hi_whdentry = NULL; -+} ++ int err; + -+int au_iinfo_init(struct inode *inode) -+{ -+ struct au_iinfo *iinfo; -+ struct super_block *sb; -+ struct au_hinode *hi; -+ int nbr, i; ++ err = 0; ++ if (!p->hdir) ++ goto out; + -+ 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_ninodes_inc(sb); ++ /* even if an error happens later, keep this lock */ ++ au_hn_inode_lock_nested(p->hdir, p->lsc_hi); + -+ iinfo->ii_hinode = hi; -+ for (i = 0; i < nbr; i++, hi++) -+ au_hinode_init(hi); ++ err = -EBUSY; ++ if (unlikely(p->hdir->hi_inode != d_inode(p->h_parent))) ++ goto out; + -+ iinfo->ii_generation.ig_generation = au_sigen(sb); -+ iinfo->ii_btop = -1; -+ iinfo->ii_bbot = -1; -+ iinfo->ii_vdir = NULL; -+ return 0; -+ } -+ return -ENOMEM; ++ err = 0; ++ if (p->h_dentry) ++ err = au_h_verify(p->h_dentry, p->udba, p->hdir->hi_inode, ++ p->h_parent, p->br); ++ ++out: ++ return err; +} + -+int au_hinode_realloc(struct au_iinfo *iinfo, int nbr, int may_shrink) ++int au_pin_hdir_relock(struct au_pin *p) +{ + int err, i; -+ struct au_hinode *hip; ++ struct inode *h_i; ++ struct dentry *h_d[] = { ++ p->h_dentry, ++ p->h_parent ++ }; + -+ AuRwMustWriteLock(&iinfo->ii_rwsem); ++ err = au_pin_hdir_lock(p); ++ if (unlikely(err)) ++ 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; ++ 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; +} + -+void au_iinfo_fin(struct inode *inode) ++static void au_pin_hdir_set_owner(struct au_pin *p, struct task_struct *task) +{ -+ struct au_iinfo *iinfo; -+ struct au_hinode *hi; -+ struct super_block *sb; -+ aufs_bindex_t bindex, bbot; -+ const unsigned char unlinked = !inode->i_nlink; -+ -+ AuDebugOn(au_is_bad_inode(inode)); -+ -+ sb = inode->i_sb; -+ au_ninodes_dec(sb); -+ 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(); -+ } -+ -+ iinfo = au_ii(inode); -+ if (iinfo->ii_vdir) -+ au_vdir_free(iinfo->ii_vdir, /*atonce*/0); ++#if !defined(CONFIG_RWSEM_GENERIC_SPINLOCK) && defined(CONFIG_RWSEM_SPIN_ON_OWNER) ++ p->hdir->hi_inode->i_rwsem.owner = task; ++#endif ++} + -+ 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++; -+ } ++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); + } -+ au_delayed_kfree(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 2016-10-09 16:55:38.889431135 +0200 -@@ -0,0 +1,519 @@ -+/* -+ * Copyright (C) 2005-2016 Junjiro R. Okajima -+ * -+ * This program, aufs is free software; you can redistribute it and/or modify -+ * it under the terms of the GNU General Public License as published by -+ * the Free Software Foundation; either version 2 of the License, or -+ * (at your option) any later version. -+ * -+ * This program is distributed in the hope that it will be useful, -+ * but WITHOUT ANY WARRANTY; without even the implied warranty of -+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the -+ * GNU General Public License for more details. -+ * -+ * You should have received a copy of the GNU General Public License -+ * along with this program. If not, see . -+ */ -+ -+/* -+ * inode functions -+ */ -+ -+#include "aufs.h" + -+struct inode *au_igrab(struct inode *inode) ++void au_pin_hdir_release(struct au_pin *p) +{ -+ if (inode) { -+ AuDebugOn(!atomic_read(&inode->i_count)); -+ ihold(inode); ++ if (p->hdir) { ++ au_pin_hdir_set_owner(p, p->task); ++ rwsem_release(&p->hdir->hi_inode->i_rwsem.dep_map, 1, _RET_IP_); + } -+ return inode; +} + -+static void au_refresh_hinode_attr(struct inode *inode, int do_version) ++struct dentry *au_pinned_h_parent(struct au_pin *pin) +{ -+ au_cpup_attr_all(inode, /*force*/0); -+ au_update_iigen(inode, /*half*/1); -+ if (do_version) -+ inode->i_version++; ++ if (pin && pin->parent) ++ return au_h_dptr(pin->parent, pin->bindex); ++ return NULL; +} + -+static int au_ii_refresh(struct inode *inode, int *update) ++void au_unpin(struct au_pin *p) +{ -+ 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; ++ 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; + -+ AuDebugOn(au_is_bad_inode(inode)); -+ IiMustWriteLock(inode); ++ 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 */ ++} + -+ *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)) ++int au_do_pin(struct au_pin *p) ++{ ++ int err; ++ struct super_block *sb; ++ struct inode *h_dir; ++ ++ err = 0; ++ sb = p->dentry->d_sb; ++ p->br = au_sbr(sb, p->bindex); ++ if (IS_ROOT(p->dentry)) { ++ if (au_ftest_pin(p->flags, MNT_WRITE)) { ++ p->h_mnt = au_br_mnt(p->br); ++ err = vfsub_mnt_want_write(p->h_mnt); ++ if (unlikely(err)) { ++ au_fclr_pin(p->flags, MNT_WRITE); ++ goto out_err; ++ } ++ } + goto out; ++ } + -+ 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; ++ p->h_dentry = NULL; ++ if (p->bindex <= au_dbbot(p->dentry)) ++ p->h_dentry = au_h_dptr(p->dentry, p->bindex); + -+ AuDebugOn(type != (p->hi_inode->i_mode & S_IFMT)); -+ new_bindex = au_br_index(sb, p->hi_id); -+ if (new_bindex == bindex) -+ continue; ++ p->parent = dget_parent(p->dentry); ++ if (!au_ftest_pin(p->flags, DI_LOCKED)) ++ di_read_lock(p->parent, AuLock_IR, p->lsc_di); + -+ if (new_bindex < 0) { -+ *update = 1; -+ au_hiput(p); -+ p->hi_inode = NULL; -+ continue; -+ } ++ 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; + -+ 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--; ++ /* ++ * udba case, or ++ * if DI_LOCKED is not set, then p->parent may be different ++ * and h_parent can be NULL. ++ */ ++ if (unlikely(!p->hdir || !h_dir || !p->h_parent)) { ++ err = -EBUSY; ++ if (!au_ftest_pin(p->flags, DI_LOCKED)) ++ di_read_unlock(p->parent, AuLock_IR); ++ dput(p->parent); ++ p->parent = NULL; ++ goto out_err; ++ } ++ ++ if (au_ftest_pin(p->flags, MNT_WRITE)) { ++ p->h_mnt = au_br_mnt(p->br); ++ err = vfsub_mnt_want_write(p->h_mnt); ++ if (unlikely(err)) { ++ au_fclr_pin(p->flags, MNT_WRITE); ++ if (!au_ftest_pin(p->flags, DI_LOCKED)) ++ di_read_unlock(p->parent, AuLock_IR); ++ dput(p->parent); ++ p->parent = NULL; ++ goto out_err; + } + } -+ au_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; + ++ au_igrab(h_dir); ++ err = au_pin_hdir_lock(p); ++ if (!err) ++ goto out; /* success */ ++ ++ au_unpin(p); ++ ++out_err: ++ pr_err("err %d\n", err); ++ err = au_busy_or_stale(); +out: -+ AuTraceErr(err); + return err; +} + -+void au_refresh_iop(struct inode *inode, int force_getattr) ++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) +{ -+ int type; -+ struct au_sbinfo *sbi = au_sbi(inode->i_sb); -+ const struct inode_operations *iop -+ = force_getattr ? aufs_iop : sbi->si_iop_array; ++ p->dentry = dentry; ++ p->udba = udba; ++ p->lsc_di = lsc_di; ++ p->lsc_hi = lsc_hi; ++ p->flags = flags; ++ p->bindex = bindex; + -+ if (inode->i_op == iop) -+ return; ++ p->parent = NULL; ++ p->hdir = NULL; ++ p->h_mnt = NULL; + -+ 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; -+ } ++ p->h_dentry = NULL; ++ p->h_parent = NULL; ++ p->br = NULL; ++ p->task = current; ++} + -+ inode->i_op = iop + type; -+ /* unnecessary smp_wmb() */ ++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); +} + -+int au_refresh_hinode_self(struct inode *inode) ++/* ---------------------------------------------------------------------- */ ++ ++/* ++ * ->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, update; ++ int err; ++ struct dentry *parent; + -+ err = au_ii_refresh(inode, &update); -+ if (!err) -+ au_refresh_hinode_attr(inode, update && S_ISDIR(inode->i_mode)); ++ err = 0; ++ if (au_digen_test(dentry, sigen)) { ++ parent = dget_parent(dentry); ++ di_read_lock_parent(parent, AuLock_IR); ++ err = au_refresh_dentry(dentry, parent); ++ di_read_unlock(parent, AuLock_IR); ++ dput(parent); ++ } + + AuTraceErr(err); + return err; +} + -+int au_refresh_hinode(struct inode *inode, struct dentry *dentry) ++int au_pin_and_icpup(struct dentry *dentry, struct iattr *ia, ++ struct au_icpup_args *a) +{ -+ 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; ++ 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 ++ }; + -+ err = au_ii_refresh(inode, &update); -+ if (unlikely(err)) ++ 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); + -+ 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; ++ 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); ++ } + -+ h_d = au_h_dptr(dentry, bindex); -+ if (!h_d || d_is_negative(h_d)) -+ continue; ++ err = au_pin(&a->pin, dentry, a->btgt, a->udba, a->pin_flags); ++ if (unlikely(err)) ++ goto out_parent; + -+ 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; -+ } ++ 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)) { ++ vfsub_inode_lock_shared_nested(a->h_inode, AuLsc_I_CHILD); ++ if (ia->ia_size < i_size_read(a->h_inode)) ++ sz = ia->ia_size; ++ inode_unlock_shared(a->h_inode); ++ } ++ ++ hi_wh = NULL; ++ if (au_ftest_icpup(a->flags, DID_CPUP) && d_unlinked(dentry)) { ++ hi_wh = au_hi_wh(inode, a->btgt); ++ if (!hi_wh) { ++ struct au_cp_generic cpg = { ++ .dentry = dentry, ++ .bdst = a->btgt, ++ .bsrc = -1, ++ .len = sz, ++ .pin = &a->pin ++ }; ++ err = au_sio_cpup_wh(&cpg, /*file*/NULL); ++ if (unlikely(err)) ++ goto out_unlock; ++ hi_wh = au_hi_wh(inode, a->btgt); ++ /* todo: revalidate hi_wh? */ + } -+ if (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); + ++ if (parent) { ++ au_pin_set_parent_lflag(&a->pin, /*lflag*/0); ++ di_downgrade_lock(parent, AuLock_IR); ++ dput(parent); ++ parent = NULL; ++ } ++ if (!au_ftest_icpup(a->flags, DID_CPUP)) ++ goto out; /* success */ ++ ++ if (!d_unhashed(dentry)) { ++ struct au_cp_generic cpg = { ++ .dentry = dentry, ++ .bdst = a->btgt, ++ .bsrc = btop, ++ .len = sz, ++ .pin = &a->pin, ++ .flags = AuCpup_DTIME | AuCpup_HOPEN ++ }; ++ err = au_sio_cpup_simple(&cpg); ++ if (!err) ++ a->h_path.dentry = au_h_dptr(dentry, a->btgt); ++ } else if (!hi_wh) ++ a->h_path.dentry = au_h_dptr(dentry, a->btgt); ++ else ++ a->h_path.dentry = hi_wh; /* do not dget here */ ++ ++out_unlock: ++ a->h_inode = d_inode(a->h_path.dentry); ++ if (!err) ++ goto out; /* success */ ++ au_unpin(&a->pin); ++out_parent: ++ if (parent) { ++ di_write_unlock(parent); ++ dput(parent); ++ } +out: -+ AuTraceErr(err); ++ if (!err) ++ inode_lock_nested(a->h_inode, AuLsc_I_CHILD); + return err; +} + -+static int set_inode(struct inode *inode, struct dentry *dentry) ++static int aufs_setattr(struct dentry *dentry, struct iattr *ia) +{ + int err; -+ 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; -+ struct inode_operations *iop; ++ struct inode *inode, *delegated; ++ struct super_block *sb; ++ struct file *file; ++ struct au_icpup_args *a; + -+ IiMustWriteLock(inode); ++ inode = d_inode(dentry); ++ IMustLock(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; ++ err = setattr_prepare(dentry, ia); ++ if (unlikely(err)) + goto out; -+ } + -+ /* 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_acl() every time, -+ * do not call cache_no_acl() for aufs inode. -+ */ ++ err = -ENOMEM; ++ a = kzalloc(sizeof(*a), GFP_NOFS); ++ if (unlikely(!a)) ++ goto out; + -+out: -+ return err; -+} ++ if (ia->ia_valid & (ATTR_KILL_SUID | ATTR_KILL_SGID)) ++ ia->ia_valid &= ~ATTR_MODE; + -+/* -+ * successful returns with iinfo write_locked -+ * minus: errno -+ * zero: success, matched -+ * plus: no error, but unmatched -+ */ -+static int reval_inode(struct inode *inode, struct dentry *dentry) -+{ -+ int err; -+ unsigned int gen, igflags; -+ aufs_bindex_t bindex, bbot; -+ struct inode *h_inode, *h_dinode; -+ struct dentry *h_dentry; ++ file = NULL; ++ sb = dentry->d_sb; ++ err = si_read_lock(sb, AuLock_FLUSH | AuLock_NOPLM); ++ if (unlikely(err)) ++ goto out_kfree; + -+ /* -+ * 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 (ia->ia_valid & ATTR_FILE) { ++ /* currently ftruncate(2) only */ ++ AuDebugOn(!d_is_reg(dentry)); ++ file = ia->ia_file; ++ err = au_reval_and_lock_fdi(file, au_reopen_nondir, /*wlock*/1, ++ /*fi_lsc*/0); ++ if (unlikely(err)) ++ goto out_si; ++ ia->ia_file = au_hf_top(file); ++ a->udba = AuOpt_UDBA_NONE; ++ } else { ++ /* fchmod() doesn't pass ia_file */ ++ a->udba = au_opt_udba(sb); ++ di_write_lock_child(dentry); ++ /* no d_unlinked(), to set UDBA_NONE for root */ ++ if (d_unhashed(dentry)) ++ a->udba = AuOpt_UDBA_NONE; ++ if (a->udba != AuOpt_UDBA_NONE) { ++ AuDebugOn(IS_ROOT(dentry)); ++ err = au_reval_for_attr(dentry, au_sigen(sb)); ++ if (unlikely(err)) ++ goto out_dentry; ++ } ++ } + -+ err = 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; ++ err = au_pin_and_icpup(dentry, ia, a); ++ if (unlikely(err < 0)) ++ goto out_dentry; ++ if (au_ftest_icpup(a->flags, DID_CPUP)) { ++ ia->ia_file = NULL; ++ ia->ia_valid &= ~ATTR_FILE; ++ } ++ ++ a->h_path.mnt = au_sbr_mnt(sb, a->btgt); ++ if ((ia->ia_valid & (ATTR_MODE | ATTR_CTIME)) ++ == (ATTR_MODE | ATTR_CTIME)) { ++ err = security_path_chmod(&a->h_path, ia->ia_mode); ++ if (unlikely(err)) ++ goto out_unlock; ++ } else if ((ia->ia_valid & (ATTR_UID | ATTR_GID)) ++ && (ia->ia_valid & ATTR_CTIME)) { ++ err = security_path_chown(&a->h_path, ia->ia_uid, ia->ia_gid); ++ if (unlikely(err)) ++ goto out_unlock; ++ } + -+ err = 0; -+ gen = au_iigen(inode, &igflags); -+ if (gen == au_digen(dentry) -+ && !au_ig_ftest(igflags, HALF_REFRESHED)) -+ break; ++ if (ia->ia_valid & ATTR_SIZE) { ++ struct file *f; + -+ /* fully refresh inode using dentry */ -+ err = au_refresh_hinode(inode, dentry); -+ if (!err) -+ au_update_iigen(inode, /*half*/0); -+ break; ++ if (ia->ia_size < i_size_read(inode)) ++ /* unmap only */ ++ truncate_setsize(inode, ia->ia_size); ++ ++ f = NULL; ++ if (ia->ia_valid & ATTR_FILE) ++ f = ia->ia_file; ++ inode_unlock(a->h_inode); ++ err = vfsub_trunc(&a->h_path, ia->ia_size, ia->ia_valid, f); ++ inode_lock_nested(a->h_inode, AuLsc_I_CHILD); ++ } else { ++ delegated = NULL; ++ while (1) { ++ err = vfsub_notify_change(&a->h_path, ia, &delegated); ++ if (delegated) { ++ err = break_deleg_wait(&delegated); ++ if (!err) ++ continue; ++ } ++ break; ++ } + } ++ /* ++ * regardless aufs 'acl' option setting. ++ * why don't all acl-aware fs call this func from their ->setattr()? ++ */ ++ if (!err && (ia->ia_valid & ATTR_MODE)) ++ err = vfsub_acl_chmod(a->h_inode, ia->ia_mode); ++ if (!err) ++ au_cpup_attr_changeable(inode); + ++out_unlock: ++ inode_unlock(a->h_inode); ++ au_unpin(&a->pin); + if (unlikely(err)) -+ ii_write_unlock(inode); ++ 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: ++ kfree(a); +out: ++ AuTraceErr(err); + return err; +} + -+int au_ino(struct super_block *sb, aufs_bindex_t bindex, ino_t h_ino, -+ unsigned int d_type, ino_t *ino) ++#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 mutex *mtx; -+ -+ /* prevent hardlinked inode number from race condition */ -+ mtx = NULL; -+ if (d_type != DT_DIR) { -+ mtx = &au_sbr(sb, bindex)->br_xino.xi_nondir_mtx; -+ mutex_lock(mtx); -+ } -+ err = au_xino_read(sb, bindex, h_ino, ino); -+ if (unlikely(err)) -+ goto out; ++ struct super_block *sb; + -+ if (!*ino) { -+ err = -EIO; -+ *ino = au_xino_new_ino(sb); -+ if (unlikely(!*ino)) -+ goto out; -+ err = au_xino_write(sb, bindex, h_ino, *ino); ++ sb = dentry->d_sb; ++ a->udba = au_opt_udba(sb); ++ /* no d_unlinked(), to set UDBA_NONE for root */ ++ if (d_unhashed(dentry)) ++ a->udba = AuOpt_UDBA_NONE; ++ if (a->udba != AuOpt_UDBA_NONE) { ++ AuDebugOn(IS_ROOT(dentry)); ++ err = au_reval_for_attr(dentry, au_sigen(sb)); + if (unlikely(err)) + goto out; + } ++ err = au_pin_and_icpup(dentry, /*ia*/NULL, a); ++ if (unlikely(err < 0)) ++ goto out; ++ ++ h_path->dentry = a->h_path.dentry; ++ h_path->mnt = au_sbr_mnt(sb, a->btgt); + +out: -+ if (mtx) -+ mutex_unlock(mtx); + return err; +} + -+/* successful returns with iinfo write_locked */ -+/* todo: return with unlocked? */ -+struct inode *au_new_inode(struct dentry *dentry, int must_new) ++ssize_t au_sxattr(struct dentry *dentry, struct inode *inode, ++ struct au_sxattr *arg) +{ -+ struct inode *inode, *h_inode; -+ struct dentry *h_dentry; -+ struct super_block *sb; -+ struct mutex *mtx; -+ ino_t h_ino, ino; + int err; -+ aufs_bindex_t btop; -+ -+ 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; -+ -+ /* -+ * stop 'race'-ing between hardlinks under different -+ * parents. -+ */ -+ mtx = NULL; -+ if (!d_is_dir(h_dentry)) -+ mtx = &au_sbr(sb, btop)->br_xino.xi_nondir_mtx; -+ -+new_ino: -+ if (mtx) -+ mutex_lock(mtx); -+ err = au_xino_read(sb, btop, h_ino, &ino); -+ inode = ERR_PTR(err); -+ if (unlikely(err)) -+ goto out; ++ struct path h_path; ++ struct super_block *sb; ++ struct au_icpup_args *a; ++ struct inode *h_inode; + -+ if (!ino) { -+ ino = au_xino_new_ino(sb); -+ if (unlikely(!ino)) { -+ inode = ERR_PTR(-EIO); -+ goto out; -+ } -+ } ++ IMustLock(inode); + -+ AuDbg("i%lu\n", (unsigned long)ino); -+ inode = au_iget_locked(sb, ino); -+ err = PTR_ERR(inode); -+ if (IS_ERR(inode)) ++ err = -ENOMEM; ++ a = kzalloc(sizeof(*a), GFP_NOFS); ++ if (unlikely(!a)) + goto out; + -+ 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; /* success */ -+ } ++ sb = dentry->d_sb; ++ err = si_read_lock(sb, AuLock_FLUSH | AuLock_NOPLM); ++ if (unlikely(err)) ++ goto out_kfree; + -+ /* -+ * 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 (mtx) -+ mutex_unlock(mtx); -+ err = reval_inode(inode, dentry); -+ if (unlikely(err < 0)) { -+ mtx = NULL; -+ goto out_iput; -+ } ++ 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; + -+ if (!err) { -+ mtx = NULL; -+ goto out; /* success */ -+ } else if (mtx) -+ mutex_lock(mtx); ++ inode_unlock(a->h_inode); ++ switch (arg->type) { ++ case AU_XATTR_SET: ++ AuDebugOn(d_is_negative(h_path.dentry)); ++ err = vfsub_setxattr(h_path.dentry, ++ arg->u.set.name, arg->u.set.value, ++ arg->u.set.size, arg->u.set.flags); ++ break; ++ case AU_ACL_SET: ++ err = -EOPNOTSUPP; ++ h_inode = d_inode(h_path.dentry); ++ if (h_inode->i_op->set_acl) ++ /* this will call posix_acl_update_mode */ ++ err = h_inode->i_op->set_acl(h_inode, ++ arg->u.acl_set.acl, ++ arg->u.acl_set.type); ++ break; + } ++ if (!err) ++ au_cpup_attr_timesizes(inode); + -+ 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 (mtx) -+ mutex_unlock(mtx); -+ goto new_ino; -+ } ++ au_unpin(&a->pin); ++ if (unlikely(err)) ++ au_update_dbtop(dentry); + -+out_iput: -+ iput(inode); -+ inode = ERR_PTR(err); ++out_di: ++ di_write_unlock(dentry); ++ si_read_unlock(sb); ++out_kfree: ++ kfree(a); +out: -+ if (mtx) -+ mutex_unlock(mtx); -+ return inode; ++ AuTraceErr(err); ++ return err; +} ++#endif + -+/* ---------------------------------------------------------------------- */ -+ -+int au_test_ro(struct super_block *sb, aufs_bindex_t bindex, -+ struct inode *inode) ++static void au_refresh_iattr(struct inode *inode, struct kstat *st, ++ unsigned int nlink) +{ -+ int err; -+ struct inode *hi; ++ unsigned int n; + -+ err = au_br_rdonly(au_sbr(sb, bindex)); ++ inode->i_mode = st->mode; ++ /* don't i_[ug]id_write() here */ ++ inode->i_uid = st->uid; ++ inode->i_gid = st->gid; ++ inode->i_atime = st->atime; ++ inode->i_mtime = st->mtime; ++ inode->i_ctime = st->ctime; + -+ /* 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; ++ 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); + } + -+ return err; -+} -+ -+int au_test_h_perm(struct inode *h_inode, int mask) -+{ -+ if (uid_eq(current_fsuid(), GLOBAL_ROOT_UID)) -+ return 0; -+ return inode_permission(h_inode, mask); ++ spin_lock(&inode->i_lock); ++ inode->i_blocks = st->blocks; ++ i_size_write(inode, st->size); ++ spin_unlock(&inode->i_lock); +} + -+int au_test_h_perm_sio(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_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 2016-12-17 12:28:17.595211562 +0100 -@@ -0,0 +1,691 @@ +/* -+ * Copyright (C) 2005-2016 Junjiro R. Okajima -+ * -+ * This program, aufs is free software; you can redistribute it and/or modify -+ * it under the terms of the GNU General Public License as published by -+ * the Free Software Foundation; either version 2 of the License, or -+ * (at your option) any later version. -+ * -+ * This program is distributed in the hope that it will be useful, -+ * but WITHOUT ANY WARRANTY; without even the implied warranty of -+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the -+ * GNU General Public License for more details. -+ * -+ * You should have received a copy of the GNU General Public License -+ * along with this program. If not, see . ++ * common routine for aufs_getattr() and au_getxattr(). ++ * returns zero or negative (an error). ++ * @dentry will be read-locked in success. + */ ++int au_h_path_getattr(struct dentry *dentry, int force, struct path *h_path, ++ int locked) ++{ ++ int err; ++ unsigned int mnt_flags, sigen; ++ unsigned char udba_none; ++ aufs_bindex_t bindex; ++ struct super_block *sb, *h_sb; ++ struct inode *inode; + -+/* -+ * inode operations -+ */ ++ h_path->mnt = NULL; ++ h_path->dentry = NULL; + -+#ifndef __AUFS_INODE_H__ -+#define __AUFS_INODE_H__ ++ err = 0; ++ sb = dentry->d_sb; ++ mnt_flags = au_mntflags(sb); ++ udba_none = !!au_opt_test(mnt_flags, UDBA_NONE); + -+#ifdef __KERNEL__ ++ if (unlikely(locked)) ++ goto body; /* skip locking dinfo */ + -+#include -+#include "rwsem.h" ++ /* 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); + -+struct vfsmount; ++body: ++ inode = d_inode(dentry); ++ bindex = au_ibtop(inode); ++ h_path->mnt = au_sbr_mnt(sb, bindex); ++ h_sb = h_path->mnt->mnt_sb; ++ if (!force ++ && !au_test_fs_bad_iattr(h_sb) ++ && udba_none) ++ goto out; /* success */ + -+struct au_hnotify { -+#ifdef CONFIG_AUFS_HNOTIFY -+#ifdef CONFIG_AUFS_HFSNOTIFY -+ /* never use fsnotify_add_vfsmount_mark() */ -+ struct fsnotify_mark hn_mark; -+#endif -+ union { -+ struct inode *hn_aufs_inode; /* no get/put */ -+ struct llist_node hn_lnode; /* delayed free */ -+ }; -+#endif -+} ____cacheline_aligned_in_smp; ++ 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); ++ } + -+struct au_hinode { -+ struct inode *hi_inode; -+ aufs_bindex_t hi_id; -+#ifdef CONFIG_AUFS_HNOTIFY -+ struct au_hnotify *hi_notify; -+#endif ++out: ++ return err; ++} + -+ /* reference to the copied-up whiteout with get/put */ -+ struct dentry *hi_whdentry; -+}; ++static int aufs_getattr(struct vfsmount *mnt __maybe_unused, ++ struct dentry *dentry, struct kstat *st) ++{ ++ int err; ++ unsigned char positive; ++ struct path h_path; ++ struct inode *inode; ++ struct super_block *sb; + -+/* 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) ++ inode = d_inode(dentry); ++ sb = dentry->d_sb; ++ err = si_read_lock(sb, AuLock_FLUSH | AuLock_NOPLM); ++ if (unlikely(err)) ++ goto out; ++ err = au_h_path_getattr(dentry, /*force*/0, &h_path, /*locked*/0); ++ if (unlikely(err)) ++ goto out_si; ++ if (unlikely(!h_path.dentry)) ++ /* illegally overlapped or something */ ++ goto out_fill; /* pretending success */ + -+struct au_iigen { -+ spinlock_t ig_spin; -+ __u32 ig_generation, ig_flags; -+}; ++ positive = d_is_positive(h_path.dentry); ++ if (positive) ++ err = vfs_getattr(&h_path, st); ++ 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; + -+struct au_vdir; -+struct au_iinfo { -+ struct au_iigen ii_generation; -+ struct super_block *ii_hsb1; /* no get/put */ ++out_fill: ++ generic_fillattr(inode, st); ++out_di: ++ di_read_unlock(dentry, AuLock_IR); ++out_si: ++ si_read_unlock(sb); ++out: ++ AuTraceErr(err); ++ return err; ++} + -+ 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; -+}; ++/* ---------------------------------------------------------------------- */ + -+struct au_icntnr { -+ struct au_iinfo iinfo; -+ struct inode vfs_inode; -+ union { -+ struct hlist_node plink; -+ struct llist_node lnode; /* delayed free */ -+ }; -+} ____cacheline_aligned_in_smp; ++static const char *aufs_get_link(struct dentry *dentry, struct inode *inode, ++ struct delayed_call *done) ++{ ++ const char *ret; ++ struct dentry *h_dentry; ++ struct inode *h_inode; ++ int err; ++ aufs_bindex_t bindex; + -+/* 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) ++ ret = NULL; /* suppress a warning */ ++ err = -ECHILD; ++ if (!dentry) ++ goto out; + -+struct au_pin { -+ /* input */ -+ struct dentry *dentry; -+ unsigned int udba; -+ unsigned char lsc_di, lsc_hi, flags; -+ aufs_bindex_t bindex; ++ err = aufs_read_lock(dentry, AuLock_IR | AuLock_GEN); ++ if (unlikely(err)) ++ goto out; + -+ /* output */ -+ struct dentry *parent; -+ struct au_hinode *hdir; -+ struct vfsmount *h_mnt; ++ err = au_d_hashed_positive(dentry); ++ if (unlikely(err)) ++ goto out_unlock; + -+ /* temporary unlock/relock for copyup */ -+ struct dentry *h_dentry, *h_parent; -+ struct au_branch *br; -+ struct task_struct *task; -+}; ++ 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; + -+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); ++ err = -EBUSY; ++ h_dentry = NULL; ++ if (au_dbtop(dentry) <= bindex) { ++ h_dentry = au_h_dptr(dentry, bindex); ++ if (h_dentry) ++ dget(h_dentry); ++ } ++ if (!h_dentry) { ++ h_dentry = d_find_any_alias(h_inode); ++ if (IS_ERR(h_dentry)) { ++ err = PTR_ERR(h_dentry); ++ goto out_unlock; ++ } ++ } ++ if (unlikely(!h_dentry)) ++ goto out_unlock; + -+/* ---------------------------------------------------------------------- */ ++ err = 0; ++ AuDbg("%pf\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 au_iinfo *au_ii(struct inode *inode) -+{ -+ BUG_ON(is_bad_inode(inode)); -+ return &(container_of(inode, struct au_icntnr, vfs_inode)->iinfo); ++out_unlock: ++ aufs_read_unlock(dentry, AuLock_IR); ++out: ++ if (unlikely(err)) ++ ret = ERR_PTR(err); ++ AuTraceErrPtr(ret); ++ return ret; +} + +/* ---------------------------------------------------------------------- */ + -+/* 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 inode *h_inode, int mask); -+int au_test_h_perm_sio(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) ++static int au_is_special(struct inode *inode) +{ -+#ifdef CONFIG_AUFS_SHWH -+ return au_ino(sb, bindex, h_ino, d_type, ino); -+#else -+ return 0; -+#endif ++ return (inode->i_mode & (S_IFBLK | S_IFCHR | S_IFIFO | S_IFSOCK)); +} + -+/* i_op.c */ -+enum { -+ AuIop_SYMLINK, -+ AuIop_DIR, -+ AuIop_OTHER, -+ AuIop_Last -+}; -+extern struct inode_operations aufs_iop[AuIop_Last], -+ aufs_iop_nogetattr[AuIop_Last]; -+ -+/* 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) -+ -+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); -+ -+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); -+ -+#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) -+ -+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; ++static int aufs_update_time(struct inode *inode, struct timespec *ts, int flags) ++{ ++ int err; ++ aufs_bindex_t bindex; ++ struct super_block *sb; + struct inode *h_inode; -+}; ++ struct vfsmount *h_mnt; + -+int au_pin_and_icpup(struct dentry *dentry, struct iattr *ia, -+ struct au_icpup_args *a); ++ sb = inode->i_sb; ++ WARN_ONCE((flags & S_ATIME) && !IS_NOATIME(inode), ++ "unexpected s_flags 0x%lx", sb->s_flags); + -+int au_h_path_getattr(struct dentry *dentry, int force, struct path *h_path); ++ /* mmap_sem might be acquired already, cf. aufs_mmap() */ ++ lockdep_off(); ++ si_read_lock(sb, AuLock_FLUSH); ++ ii_write_lock_child(inode); ++ lockdep_on(); + -+/* 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 inode *dir, struct dentry *dentry, umode_t mode, -+ dev_t dev); -+int aufs_symlink(struct inode *dir, struct dentry *dentry, const char *symname); -+int aufs_create(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 inode *dir, struct dentry *dentry, umode_t mode); -+int aufs_link(struct dentry *src_dentry, struct inode *dir, -+ struct dentry *dentry); -+int aufs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode); ++ err = 0; ++ bindex = au_ibtop(inode); ++ h_inode = au_h_iptr(inode, bindex); ++ if (!au_test_ro(sb, bindex, inode)) { ++ h_mnt = au_sbr_mnt(sb, bindex); ++ err = vfsub_mnt_want_write(h_mnt); ++ if (!err) { ++ err = vfsub_update_time(h_inode, ts, flags); ++ vfsub_mnt_drop_write(h_mnt); ++ } ++ } else if (au_is_special(h_inode)) { ++ /* ++ * Never copy-up here. ++ * These special files may already be opened and used for ++ * communicating. If we copied it up, then the communication ++ * would be corrupted. ++ */ ++ AuWarn1("timestamps for i%lu are ignored " ++ "since it is on readonly branch (hi%lu).\n", ++ inode->i_ino, h_inode->i_ino); ++ } else if (flags & ~S_ATIME) { ++ err = -EIO; ++ AuIOErr1("unexpected flags 0x%x\n", flags); ++ AuDebugOn(1); ++ } + -+/* 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); ++ lockdep_off(); ++ if (!err) ++ au_cpup_attr_timesizes(inode); ++ ii_write_unlock(inode); ++ si_read_unlock(sb); ++ lockdep_on(); + -+/* i_op_ren.c */ -+int au_wbr(struct dentry *dentry, aufs_bindex_t btgt); -+int aufs_rename(struct inode *src_dir, struct dentry *src_dentry, -+ struct inode *dir, struct dentry *dentry, -+ unsigned int flags); ++ if (!err && (flags & S_VERSION)) ++ inode_inc_iversion(inode); + -+/* 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); ++ return err; ++} + -+/* 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) ++/* ---------------------------------------------------------------------- */ + -+#ifndef CONFIG_AUFS_HNOTIFY -+#undef AuHi_HNOTIFY -+#define AuHi_HNOTIFY 0 ++/* no getattr version will be set by module.c:aufs_init() */ ++struct inode_operations aufs_iop_nogetattr[AuIop_Last], ++ aufs_iop[] = { ++ [AuIop_SYMLINK] = { ++ .permission = aufs_permission, ++#ifdef CONFIG_FS_POSIX_ACL ++ .get_acl = aufs_get_acl, ++ .set_acl = aufs_set_acl, /* unsupport for symlink? */ +#endif + -+void au_set_h_iptr(struct inode *inode, aufs_bindex_t bindex, -+ struct inode *h_inode, unsigned int flags); ++ .setattr = aufs_setattr, ++ .getattr = aufs_getattr, + -+void au_update_iigen(struct inode *inode, int half); -+void au_update_ibrange(struct inode *inode, int do_put_zero); ++#ifdef CONFIG_AUFS_XATTR ++ .listxattr = aufs_listxattr, ++#endif + -+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); ++ .readlink = generic_readlink, ++ .get_link = aufs_get_link, + -+#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) ++ /* .update_time = aufs_update_time */ ++ }, ++ [AuIop_DIR] = { ++ .create = aufs_create, ++ .lookup = aufs_lookup, ++ .link = aufs_link, ++ .unlink = aufs_unlink, ++ .symlink = aufs_symlink, ++ .mkdir = aufs_mkdir, ++ .rmdir = aufs_rmdir, ++ .mknod = aufs_mknod, ++ .rename = aufs_rename, ++ ++ .permission = aufs_permission, ++#ifdef CONFIG_FS_POSIX_ACL ++ .get_acl = aufs_get_acl, ++ .set_acl = aufs_set_acl, +#endif -+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 */ ++ ++ .setattr = aufs_setattr, ++ .getattr = aufs_getattr, + +#ifdef CONFIG_AUFS_XATTR -+/* xattr.c */ -+int au_cpup_xattr(struct dentry *h_dst, struct dentry *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 dentry *h_dst, struct dentry *h_src, -+ int ignore_flags, unsigned int verbose); -+AuStubVoid(au_xattr_init, struct super_block *sb); ++ .listxattr = aufs_listxattr, +#endif + ++ .update_time = aufs_update_time, ++ .atomic_open = aufs_atomic_open, ++ .tmpfile = aufs_tmpfile ++ }, ++ [AuIop_OTHER] = { ++ .permission = aufs_permission, +#ifdef CONFIG_FS_POSIX_ACL -+struct posix_acl *aufs_get_acl(struct inode *inode, int type); -+int aufs_set_acl(struct inode *inode, struct posix_acl *acl, int type); ++ .get_acl = aufs_get_acl, ++ .set_acl = aufs_set_acl, +#endif + -+#if IS_ENABLED(CONFIG_AUFS_XATTR) || IS_ENABLED(CONFIG_FS_POSIX_ACL) -+enum { -+ AU_XATTR_SET, -+ AU_ACL_SET -+}; ++ .setattr = aufs_setattr, ++ .getattr = aufs_getattr, + -+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); ++#ifdef CONFIG_AUFS_XATTR ++ .listxattr = aufs_listxattr, +#endif + -+/* ---------------------------------------------------------------------- */ -+ -+/* 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 ++ .update_time = aufs_update_time ++ } +}; -+ +diff -urNp -x '*.orig' linux-4.9/fs/aufs/i_op_add.c linux-4.9/fs/aufs/i_op_add.c +--- linux-4.9/fs/aufs/i_op_add.c 1970-01-01 01:00:00.000000000 +0100 ++++ linux-4.9/fs/aufs/i_op_add.c 2021-02-24 16:15:09.531573855 +0100 +@@ -0,0 +1,928 @@ +/* -+ * 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, ++ * Copyright (C) 2005-2018 Junjiro R. Okajima ++ * ++ * This program, aufs is free software; you can redistribute it and/or modify ++ * it under the terms of the GNU General Public License as published by ++ * the Free Software Foundation; either version 2 of the License, or ++ * (at your option) any later version. ++ * ++ * This program is distributed in the hope that it will be useful, ++ * but WITHOUT ANY WARRANTY; without even the implied warranty of ++ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the ++ * GNU General Public License for more details. ++ * ++ * You should have received a copy of the GNU General Public License ++ * along with this program. If not, see . + */ -+#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); \ -+} -+ -+#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); \ -+} -+ -+#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); -+AuRWLockFuncs(new_child, NEW_CHILD); ++/* ++ * inode operations (add entry) ++ */ + -+#undef AuReadLockFunc -+#undef AuWriteLockFunc -+#undef AuRWLockFuncs ++#include "aufs.h" + +/* -+ * ii_read_unlock, ii_write_unlock, ii_downgrade_lock ++ * 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. + */ -+AuSimpleUnlockRwsemFuncs(ii, struct inode *i, &au_ii(i)->ii_rwsem); ++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; + -+#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) ++ 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); ++ dir->i_version++; ++ au_fhsm_wrote(sb, bindex, /*force*/0); ++ return 0; /* success */ ++ } + -+static inline void au_icntnr_init(struct au_icntnr *c) -+{ -+#ifdef CONFIG_AUFS_DEBUG -+ c->vfs_inode.i_mode = 0; -+#endif ++ 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 inline unsigned int au_iigen(struct inode *inode, unsigned int *igflags) ++static int au_d_may_add(struct dentry *dentry) +{ -+ unsigned int gen; -+ struct au_iinfo *iinfo; -+ struct au_iigen *iigen; -+ -+ 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); ++ int err; + -+ return gen; ++ err = 0; ++ if (unlikely(d_unhashed(dentry))) ++ err = -ENOENT; ++ if (unlikely(d_really_is_positive(dentry))) ++ err = -EEXIST; ++ 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 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) +{ -+ struct au_iinfo *iinfo; ++ int err; ++ umode_t h_mode; ++ struct dentry *h_dentry; ++ 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); -+} ++ err = -ENAMETOOLONG; ++ if (unlikely(dentry->d_name.len > AUFS_MAX_NAMELEN)) ++ goto out; ++ ++ h_dentry = au_h_dptr(dentry, bindex); ++ if (d_really_is_negative(dentry)) { ++ err = -EEXIST; ++ if (unlikely(d_is_positive(h_dentry))) ++ goto out; ++ } else { ++ /* rename(2) case */ ++ err = -EIO; ++ if (unlikely(d_is_negative(h_dentry))) ++ goto out; ++ h_inode = d_inode(h_dentry); ++ if (unlikely(!h_inode->i_nlink)) ++ goto out; ++ ++ h_mode = h_inode->i_mode; ++ if (!isdir) { ++ err = -EISDIR; ++ if (unlikely(S_ISDIR(h_mode))) ++ goto out; ++ } else if (unlikely(!S_ISDIR(h_mode))) { ++ err = -ENOTDIR; ++ goto out; ++ } ++ } + -+static inline void au_iigen_dec(struct inode *inode) -+{ -+ struct au_iinfo *iinfo; -+ struct au_iigen *iigen; ++ err = 0; ++ /* expected parent dir is locked */ ++ if (unlikely(h_parent != h_dentry->d_parent)) ++ err = -EIO; + -+ iinfo = au_ii(inode); -+ iigen = &iinfo->ii_generation; -+ spin_lock(&iigen->ig_spin); -+ iigen->ig_generation--; -+ spin_unlock(&iigen->ig_spin); ++out: ++ AuTraceErr(err); ++ return err; +} + -+static inline int au_iigen_test(struct inode *inode, unsigned int sigen) ++/* ++ * 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; + -+ err = 0; -+ if (unlikely(inode && au_iigen(inode, NULL) != sigen)) -+ err = -EIO; ++ AuDbg("%pd\n", dentry); + -+ return err; -+} ++ err = au_wr_dir(dentry, src_dentry, wr_dir_args); ++ bcpup = err; ++ wh_dentry = ERR_PTR(err); ++ if (unlikely(err < 0)) ++ goto out; + -+/* ---------------------------------------------------------------------- */ ++ sb = dentry->d_sb; ++ udba = au_opt_udba(sb); ++ err = au_pin(pin, dentry, bcpup, udba, ++ AuPin_DI_LOCKED | AuPin_MNT_WRITE); ++ wh_dentry = ERR_PTR(err); ++ if (unlikely(err)) ++ goto out; + -+static inline struct au_hinode *au_hinode(struct au_iinfo *iinfo, -+ aufs_bindex_t bindex) -+{ -+ return iinfo->ii_hinode + bindex; -+} ++ 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; + -+static inline int au_is_bad_inode(struct inode *inode) -+{ -+ return !!(is_bad_inode(inode) || !au_hinode(au_ii(inode), 0)); -+} ++ 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); ++ } + -+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; -+} ++ wh_dentry = NULL; ++ if (bcpup != au_dbwh(dentry)) ++ goto out; /* success */ + -+static inline aufs_bindex_t au_ibtop(struct inode *inode) -+{ -+ IiMustAnyLock(inode); -+ return au_ii(inode)->ii_btop; -+} ++ /* ++ * 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); + -+static inline aufs_bindex_t au_ibbot(struct inode *inode) -+{ -+ IiMustAnyLock(inode); -+ return au_ii(inode)->ii_bbot; ++out_unpin: ++ if (IS_ERR(wh_dentry)) ++ au_unpin(pin); ++out: ++ return wh_dentry; +} + -+static inline struct au_vdir *au_ivdir(struct inode *inode) -+{ -+ IiMustAnyLock(inode); -+ return au_ii(inode)->ii_vdir; -+} ++/* ---------------------------------------------------------------------- */ + -+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; -+} ++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 inline void au_set_ibtop(struct inode *inode, aufs_bindex_t bindex) ++static int add_simple(struct inode *dir, struct dentry *dentry, ++ struct simple_arg *arg) +{ -+ IiMustWriteLock(inode); -+ au_ii(inode)->ii_btop = bindex; -+} ++ int err, rerr; ++ aufs_bindex_t btop; ++ unsigned char created; ++ const unsigned char try_aopen ++ = (arg->type == Creat && arg->u.c.try_aopen); ++ struct dentry *wh_dentry, *parent; ++ struct inode *h_dir; ++ struct super_block *sb; ++ struct au_branch *br; ++ /* to reuduce stack size */ ++ struct { ++ struct au_dtime dt; ++ struct au_pin pin; ++ struct path h_path; ++ struct au_wr_dir_args wr_dir_args; ++ } *a; + -+static inline void au_set_ibbot(struct inode *inode, aufs_bindex_t bindex) -+{ -+ IiMustWriteLock(inode); -+ au_ii(inode)->ii_bbot = bindex; -+} ++ AuDbg("%pd\n", dentry); ++ IMustLock(dir); + -+static inline void au_set_ivdir(struct inode *inode, struct au_vdir *vdir) -+{ -+ IiMustWriteLock(inode); -+ au_ii(inode)->ii_vdir = vdir; -+} ++ 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; + -+static inline struct au_hinode *au_hi(struct inode *inode, aufs_bindex_t bindex) -+{ -+ IiMustAnyLock(inode); -+ return au_hinode(au_ii(inode), bindex); -+} ++ parent = dentry->d_parent; /* dir inode is locked */ ++ if (!try_aopen) { ++ err = aufs_read_lock(dentry, AuLock_DW | AuLock_GEN); ++ if (unlikely(err)) ++ goto out_free; ++ } ++ err = au_d_may_add(dentry); ++ if (unlikely(err)) ++ goto out_unlock; ++ if (!try_aopen) ++ di_write_lock_parent(parent); ++ wh_dentry = lock_hdir_lkup_wh(dentry, &a->dt, /*src_dentry*/NULL, ++ &a->pin, &a->wr_dir_args); ++ err = PTR_ERR(wh_dentry); ++ if (IS_ERR(wh_dentry)) ++ goto out_parent; + -+/* ---------------------------------------------------------------------- */ ++ btop = au_dbtop(dentry); ++ sb = dentry->d_sb; ++ br = au_sbr(sb, btop); ++ a->h_path.dentry = au_h_dptr(dentry, btop); ++ a->h_path.mnt = au_br_mnt(br); ++ h_dir = au_pinned_h_dir(&a->pin); ++ switch (arg->type) { ++ case Creat: ++ err = 0; ++ 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); ++ else ++ err = vfsub_atomic_open(h_dir, a->h_path.dentry, ++ arg->u.c.aopen, br); ++ break; ++ case Symlink: ++ err = vfsub_symlink(h_dir, &a->h_path, arg->u.s.symname); ++ break; ++ case Mknod: ++ err = vfsub_mknod(h_dir, &a->h_path, arg->u.m.mode, ++ arg->u.m.dev); ++ break; ++ default: ++ BUG(); ++ } ++ created = !err; ++ if (!err) ++ err = epilog(dir, btop, wh_dentry, dentry); + -+static inline struct dentry *au_pinned_parent(struct au_pin *pin) -+{ -+ if (pin) -+ return pin->parent; -+ return NULL; -+} ++ /* revert */ ++ if (unlikely(created && err && 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); ++ } + -+static inline struct inode *au_pinned_h_dir(struct au_pin *pin) -+{ -+ if (pin && pin->hdir) -+ return pin->hdir->hi_inode; -+ return NULL; ++ if (!err && try_aopen && !h_dir->i_op->atomic_open) ++ *arg->u.c.aopen->opened |= FILE_CREATED; ++ ++ au_unpin(&a->pin); ++ dput(wh_dentry); ++ ++out_parent: ++ if (!try_aopen) ++ di_write_unlock(parent); ++out_unlock: ++ if (unlikely(err)) { ++ au_update_dbtop(dentry); ++ d_drop(dentry); ++ } ++ if (!try_aopen) ++ aufs_read_unlock(dentry, AuLock_DW); ++out_free: ++ kfree(a); ++out: ++ return err; +} + -+static inline struct au_hinode *au_pinned_hdir(struct au_pin *pin) ++int aufs_mknod(struct inode *dir, struct dentry *dentry, umode_t mode, ++ dev_t dev) +{ -+ if (pin) -+ return pin->hdir; -+ return NULL; ++ struct simple_arg arg = { ++ .type = Mknod, ++ .u.m = { ++ .mode = mode, ++ .dev = dev ++ } ++ }; ++ return add_simple(dir, dentry, &arg); +} + -+static inline void au_pin_set_dentry(struct au_pin *pin, struct dentry *dentry) ++int aufs_symlink(struct inode *dir, struct dentry *dentry, const char *symname) +{ -+ if (pin) -+ pin->dentry = dentry; ++ struct simple_arg arg = { ++ .type = Symlink, ++ .u.s.symname = symname ++ }; ++ return add_simple(dir, dentry, &arg); +} + -+static inline void au_pin_set_parent_lflag(struct au_pin *pin, -+ unsigned char lflag) ++int aufs_create(struct inode *dir, struct dentry *dentry, umode_t mode, ++ bool want_excl) +{ -+ if (pin) { -+ if (lflag) -+ au_fset_pin(pin->flags, DI_LOCKED); -+ else -+ au_fclr_pin(pin->flags, DI_LOCKED); -+ } ++ struct simple_arg arg = { ++ .type = Creat, ++ .u.c = { ++ .mode = mode, ++ .want_excl = want_excl ++ } ++ }; ++ return add_simple(dir, dentry, &arg); +} + -+#if 0 /* reserved */ -+static inline void au_pin_set_parent(struct au_pin *pin, struct dentry *parent) ++int au_aopen_or_create(struct inode *dir, struct dentry *dentry, ++ struct vfsub_aopen_args *aopen_args) +{ -+ if (pin) { -+ dput(pin->parent); -+ pin->parent = dget(parent); -+ } ++ 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); +} -+#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); ++int aufs_tmpfile(struct inode *dir, struct dentry *dentry, umode_t mode) ++{ ++ int err; ++ aufs_bindex_t bindex; ++ struct super_block *sb; ++ struct dentry *parent, *h_parent, *h_dentry; ++ struct inode *h_dir, *inode; ++ struct vfsmount *h_mnt; ++ struct au_wr_dir_args wr_dir_args = { ++ .force_btgt = -1, ++ .flags = AuWrDir_TMPFILE ++ }; + -+ /* -+ * if it returns true, the the caller should free hinode->hi_notify, -+ * otherwise ->free() frees it. -+ */ -+ int (*free)(struct au_hinode *hinode, -+ struct au_hnotify *hn) __must_check; ++ /* copy-up may happen */ ++ inode_lock(dir); + -+ void (*fin)(void); -+ int (*init)(void); ++ sb = dir->i_sb; ++ err = si_read_lock(sb, AuLock_FLUSH | AuLock_NOPLM); ++ if (unlikely(err)) ++ goto out; + -+ 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); -+}; ++ err = au_di_init(dentry); ++ if (unlikely(err)) ++ goto out_si; + -+/* 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, -+ 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); ++ err = -EBUSY; ++ parent = d_find_any_alias(dir); ++ AuDebugOn(!parent); ++ di_write_lock_parent(parent); ++ if (unlikely(d_inode(parent) != dir)) ++ goto out_parent; + -+/* hfsnotify.c */ -+extern const struct au_hnotify_op au_hnotify_op; ++ err = au_digen_test(parent, au_sigen(sb)); ++ if (unlikely(err)) ++ goto out_parent; + -+static inline -+void au_hn_init(struct au_hinode *hinode) -+{ -+ hinode->hi_notify = NULL; -+} ++ 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; + -+static inline struct au_hnotify *au_hn(struct au_hinode *hinode) -+{ -+ return hinode->hi_notify; -+} ++ err = -EOPNOTSUPP; ++ h_dir = au_h_iptr(dir, bindex); ++ if (unlikely(!h_dir->i_op->tmpfile)) ++ goto out_parent; + -+#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 */ ++ h_mnt = au_sbr_mnt(sb, bindex); ++ err = vfsub_mnt_want_write(h_mnt); ++ if (unlikely(err)) ++ goto out_parent; + -+static inline void au_hn_suspend(struct au_hinode *hdir) -+{ -+ au_hn_ctl(hdir, /*do_set*/0); -+} ++ h_parent = au_h_dptr(parent, bindex); ++ err = inode_permission(d_inode(h_parent), MAY_WRITE | MAY_EXEC); ++ if (unlikely(err)) ++ goto out_mnt; + -+static inline void au_hn_resume(struct au_hinode *hdir) -+{ -+ au_hn_ctl(hdir, /*do_set*/1); -+} ++ err = -ENOMEM; ++ h_dentry = d_alloc(h_parent, &dentry->d_name); ++ if (unlikely(!h_dentry)) ++ goto out_mnt; + -+static inline void au_hn_inode_lock(struct au_hinode *hdir) -+{ -+ inode_lock(hdir->hi_inode); -+ au_hn_suspend(hdir); -+} ++ err = h_dir->i_op->tmpfile(h_dir, h_dentry, mode); ++ if (unlikely(err)) ++ goto out_dentry; + -+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); -+} ++ au_set_dbtop(dentry, bindex); ++ au_set_dbbot(dentry, bindex); ++ au_set_h_dptr(dentry, bindex, dget(h_dentry)); ++ inode = au_new_inode(dentry, /*must_new*/1); ++ if (IS_ERR(inode)) { ++ err = PTR_ERR(inode); ++ au_set_h_dptr(dentry, bindex, NULL); ++ au_set_dbtop(dentry, -1); ++ au_set_dbbot(dentry, -1); ++ } else { ++ if (!inode->i_nlink) ++ set_nlink(inode, 1); ++ d_tmpfile(dentry, inode); ++ au_di(dentry)->di_tmpfile = 1; + -+static inline void au_hn_inode_unlock(struct au_hinode *hdir) -+{ -+ au_hn_resume(hdir); -+ inode_unlock(hdir->hi_inode); -+} ++ /* update without i_mutex */ ++ if (au_ibtop(dir) == au_dbtop(dentry)) ++ au_cpup_attr_timesizes(dir); ++ } + -+#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 2016-10-09 16:55:36.492701639 +0200 -@@ -0,0 +1,219 @@ -+/* -+ * Copyright (C) 2005-2016 Junjiro R. Okajima -+ * -+ * This program, aufs is free software; you can redistribute it and/or modify -+ * it under the terms of the GNU General Public License as published by -+ * the Free Software Foundation; either version 2 of the License, or -+ * (at your option) any later version. -+ * -+ * This program is distributed in the hope that it will be useful, -+ * but WITHOUT ANY WARRANTY; without even the implied warranty of -+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the -+ * GNU General Public License for more details. -+ * -+ * You should have received a copy of the GNU General Public License -+ * along with this program. If not, see . -+ */ ++out_dentry: ++ dput(h_dentry); ++out_mnt: ++ vfsub_mnt_drop_write(h_mnt); ++out_parent: ++ di_write_unlock(parent); ++ dput(parent); ++ di_write_unlock(dentry); ++ if (unlikely(err)) { ++ au_di_fin(dentry); ++ dentry->d_fsdata = NULL; ++ } ++out_si: ++ si_read_unlock(sb); ++out: ++ inode_unlock(dir); ++ return err; ++} + -+/* -+ * ioctl -+ * plink-management and readdir in userspace. -+ * assist the pathconf(3) wrapper library. -+ * move-down -+ * File-based Hierarchical Storage Management. -+ */ ++/* ---------------------------------------------------------------------- */ + -+#include -+#include -+#include "aufs.h" ++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_wbr_fd(struct path *path, struct aufs_wbr_fd __user *arg) ++static int au_cpup_before_link(struct dentry *src_dentry, ++ struct au_link_args *a) +{ -+ 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 ++ 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 */ + }; -+ const int valid = O_RDONLY | O_NONBLOCK | O_LARGEFILE | O_DIRECTORY -+ | O_NOATIME | O_CLOEXEC; + -+ AuDebugOn(wbrfd.oflags & ~valid); ++ di_read_lock_parent(a->src_parent, AuLock_IR); ++ err = au_test_and_cpup_dirs(src_dentry, a->bdst); ++ if (unlikely(err)) ++ goto out; + -+ if (arg) { -+ err = copy_from_user(&wbrfd, arg, sizeof(wbrfd)); -+ if (unlikely(err)) { -+ err = -EFAULT; -+ 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 = -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 = au_sio_cpup_simple(&cpg); ++ au_unpin(&a->pin); + -+ fd = get_unused_fd_flags(0); -+ err = fd; -+ if (unlikely(fd < 0)) -+ goto out; ++out: ++ di_read_unlock(a->src_parent, AuLock_IR); ++ return err; ++} + -+ 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; -+ } ++static int au_cpup_or_link(struct dentry *src_dentry, struct dentry *dentry, ++ struct au_link_args *a) ++{ ++ int err; ++ unsigned char plink; ++ aufs_bindex_t bbot; ++ struct dentry *h_src_dentry; ++ struct inode *h_inode, *inode, *delegated; ++ struct super_block *sb; ++ struct file *h_file; + -+ h_file = ERR_PTR(-ENOENT); -+ br = au_sbr(sb, wbi); -+ if (!au_br_writable(br->br_perm)) { -+ if (arg) -+ goto out_unlock; ++ 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; + -+ 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; ++ if (unlikely(d_is_negative(h_src_dentry))) { ++ dput(h_src_dentry); ++ h_src_dentry = NULL; ++ } ++ ++ } ++ if (h_src_dentry) { ++ delegated = NULL; ++ err = vfsub_link(h_src_dentry, au_pinned_h_dir(&a->pin), ++ &a->h_path, &delegated); ++ if (unlikely(err == -EWOULDBLOCK)) { ++ pr_warn("cannot retry for NFSv4 delegation" ++ " for an internal link\n"); ++ iput(delegated); + } ++ dput(h_src_dentry); ++ } else { ++ AuIOErr("no dentry found for hi%lu on b%d\n", ++ h_inode->i_ino, a->bdst); ++ err = -EIO; + } + } -+ AuDbg("wbi %d\n", wbi); -+ if (wbi >= 0) -+ h_file = au_h_open(root, wbi, wbrfd.oflags, NULL, -+ /*force_wr*/0); + -+out_unlock: -+ aufs_read_unlock(root, AuLock_IR); -+ err = PTR_ERR(h_file); -+ if (IS_ERR(h_file)) -+ goto out_fd; -+ -+ au_br_put(br); /* cf. au_h_open() */ -+ fd_install(fd, h_file); -+ err = fd; -+ goto out; /* success */ ++ if (!err && !plink) ++ au_plink_append(inode, a->bdst, a->h_path.dentry); + -+out_fd: -+ put_unused_fd(fd); +out: + AuTraceErr(err); + return err; +} + -+/* ---------------------------------------------------------------------- */ -+ -+long aufs_ioctl_dir(struct file *file, unsigned int cmd, unsigned long arg) ++int aufs_link(struct dentry *src_dentry, struct inode *dir, ++ struct dentry *dentry) +{ -+ long err; -+ struct dentry *dentry; ++ int err, rerr; ++ struct au_dtime dt; ++ struct au_link_args *a; ++ struct dentry *wh_dentry, *h_src_dentry; ++ struct inode *inode, *delegated; ++ struct super_block *sb; ++ struct au_wr_dir_args wr_dir_args = { ++ /* .force_btgt = -1, */ ++ .flags = AuWrDir_ADD_ENTRY ++ }; + -+ switch (cmd) { -+ case AUFS_CTL_RDU: -+ case AUFS_CTL_RDU_INO: -+ err = au_rdu_ioctl(file, cmd, arg); -+ break; ++ IMustLock(dir); ++ inode = d_inode(src_dentry); ++ IMustLock(inode); + -+ case AUFS_CTL_WBR_FD: -+ err = au_wbr_fd(&file->f_path, (void __user *)arg); -+ break; ++ err = -ENOMEM; ++ a = kzalloc(sizeof(*a), GFP_NOFS); ++ if (unlikely(!a)) ++ goto out; + -+ case AUFS_CTL_IBUSY: -+ err = au_ibusy_ioctl(file, arg); -+ break; ++ 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; + -+ case AUFS_CTL_BRINFO: -+ err = au_brinfo_ioctl(file, arg); -+ break; ++ a->src_parent = dget_parent(src_dentry); ++ wr_dir_args.force_btgt = au_ibtop(inode); + -+ 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; ++ 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; + -+ default: -+ /* do not call the lower */ -+ AuDbg("0x%x\n", cmd); -+ err = -ENOTTY; ++ 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 unnecrssary. ++ */ ++ if (au_opt_test(au_mntflags(sb), PLINK)) { ++ if (a->bdst < a->bsrc ++ /* && h_src_dentry->d_sb != a->h_path.dentry->d_sb */) ++ err = au_cpup_or_link(src_dentry, dentry, a); ++ else { ++ delegated = NULL; ++ err = vfsub_link(h_src_dentry, au_pinned_h_dir(&a->pin), ++ &a->h_path, &delegated); ++ if (unlikely(err == -EWOULDBLOCK)) { ++ pr_warn("cannot retry for NFSv4 delegation" ++ " for an internal link\n"); ++ iput(delegated); ++ } ++ } ++ dput(h_src_dentry); ++ } else { ++ /* ++ * copyup src_dentry to the branch we process, ++ * and then link(2) to it. ++ */ ++ dput(h_src_dentry); ++ if (a->bdst < a->bsrc ++ /* && h_src_dentry->d_sb != a->h_path.dentry->d_sb */) { ++ au_unpin(&a->pin); ++ di_write_unlock(a->parent); ++ err = au_cpup_before_link(src_dentry, a); ++ di_write_lock_parent(a->parent); ++ if (!err) ++ err = au_pin(&a->pin, dentry, a->bdst, ++ au_opt_udba(sb), ++ AuPin_DI_LOCKED | AuPin_MNT_WRITE); ++ if (unlikely(err)) ++ goto out_wh; ++ } ++ if (!err) { ++ h_src_dentry = au_h_dptr(src_dentry, a->bdst); ++ err = -ENOENT; ++ if (h_src_dentry && d_is_positive(h_src_dentry)) { ++ delegated = NULL; ++ err = vfsub_link(h_src_dentry, ++ au_pinned_h_dir(&a->pin), ++ &a->h_path, &delegated); ++ if (unlikely(err == -EWOULDBLOCK)) { ++ pr_warn("cannot retry" ++ " for NFSv4 delegation" ++ " for an internal link\n"); ++ iput(delegated); ++ } ++ } ++ } ++ } ++ if (unlikely(err)) ++ goto out_unpin; ++ ++ if (wh_dentry) { ++ a->h_path.dentry = wh_dentry; ++ err = au_wh_unlink_dentry(au_pinned_h_dir(&a->pin), &a->h_path, ++ dentry); ++ if (unlikely(err)) ++ goto out_revert; + } + ++ au_dir_ts(dir, a->bdst); ++ dir->i_version++; ++ inc_nlink(inode); ++ inode->i_ctime = dir->i_ctime; ++ d_instantiate(dentry, au_igrab(inode)); ++ if (d_unhashed(a->h_path.dentry)) ++ /* some filesystem calls d_drop() */ ++ d_drop(dentry); ++ /* some filesystems consume an inode even hardlink */ ++ au_fhsm_wrote(sb, a->bdst, /*force*/0); ++ goto out_unpin; /* success */ ++ ++out_revert: ++ /* no delegation since it is just created */ ++ rerr = vfsub_unlink(au_pinned_h_dir(&a->pin), &a->h_path, ++ /*delegated*/NULL, /*force*/0); ++ if (unlikely(rerr)) { ++ AuIOErr("%pd reverting failed(%d, %d)\n", dentry, err, rerr); ++ err = -EIO; ++ } ++ au_dtime_revert(&dt); ++out_unpin: ++ au_unpin(&a->pin); ++out_wh: ++ dput(wh_dentry); ++out_parent: ++ di_write_unlock(a->parent); ++ dput(a->src_parent); ++out_unlock: ++ if (unlikely(err)) { ++ au_update_dbtop(dentry); ++ d_drop(dentry); ++ } ++ aufs_read_and_write_unlock2(dentry, src_dentry); ++out_kfree: ++ kfree(a); ++out: + AuTraceErr(err); + return err; +} + -+long aufs_ioctl_nondir(struct file *file, unsigned int cmd, unsigned long arg) ++int aufs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) +{ -+ long err; ++ int err, rerr; ++ aufs_bindex_t bindex; ++ unsigned char diropq; ++ struct path h_path; ++ struct dentry *wh_dentry, *parent, *opq_dentry; ++ struct inode *h_inode; ++ struct super_block *sb; ++ struct { ++ struct au_pin pin; ++ struct au_dtime dt; ++ } *a; /* reduce the stack usage */ ++ struct au_wr_dir_args wr_dir_args = { ++ .force_btgt = -1, ++ .flags = AuWrDir_ADD_ENTRY | AuWrDir_ISDIR ++ }; + -+ switch (cmd) { -+ case AUFS_CTL_MVDOWN: -+ err = au_mvdown(file->f_path.dentry, (void __user *)arg); -+ break; ++ IMustLock(dir); + -+ case AUFS_CTL_WBR_FD: -+ err = au_wbr_fd(&file->f_path, (void __user *)arg); -+ break; ++ err = -ENOMEM; ++ a = kmalloc(sizeof(*a), GFP_NOFS); ++ if (unlikely(!a)) ++ goto out; + -+ default: -+ /* do not call the lower */ -+ AuDbg("0x%x\n", cmd); -+ err = -ENOTTY; -+ } ++ 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; + -+ AuTraceErr(err); -+ return err; -+} ++ parent = dentry->d_parent; /* dir inode is locked */ ++ di_write_lock_parent(parent); ++ wh_dentry = lock_hdir_lkup_wh(dentry, &a->dt, /*src_dentry*/NULL, ++ &a->pin, &wr_dir_args); ++ err = PTR_ERR(wh_dentry); ++ if (IS_ERR(wh_dentry)) ++ goto out_parent; + -+#ifdef CONFIG_COMPAT -+long aufs_compat_ioctl_dir(struct file *file, unsigned int cmd, -+ unsigned long arg) -+{ -+ long err; ++ 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; + -+ switch (cmd) { -+ case AUFS_CTL_RDU: -+ case AUFS_CTL_RDU_INO: -+ err = au_rdu_compat_ioctl(file, cmd, arg); -+ break; ++ /* 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; ++ } + -+ case AUFS_CTL_IBUSY: -+ err = au_ibusy_compat_ioctl(file, arg); -+ break; ++ err = epilog(dir, bindex, wh_dentry, dentry); ++ if (!err) { ++ inc_nlink(dir); ++ goto out_unpin; /* success */ ++ } + -+ case AUFS_CTL_BRINFO: -+ err = au_brinfo_compat_ioctl(file, arg); -+ break; ++ /* 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 (rerr) { ++ AuIOErr("%pd reverting diropq failed(%d, %d)\n", ++ dentry, err, rerr); ++ err = -EIO; ++ } ++ } + -+ default: -+ err = aufs_ioctl_dir(file, cmd, arg); ++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; + } -+ -+ AuTraceErr(err); ++ au_dtime_revert(&a->dt); ++out_unpin: ++ au_unpin(&a->pin); ++ dput(wh_dentry); ++out_parent: ++ di_write_unlock(parent); ++out_unlock: ++ if (unlikely(err)) { ++ au_update_dbtop(dentry); ++ d_drop(dentry); ++ } ++ aufs_read_unlock(dentry, AuLock_DW); ++out_free: ++ kfree(a); ++out: + return err; +} -+ -+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 2016-12-17 12:28:17.595211562 +0100 -@@ -0,0 +1,928 @@ +diff -urNp -x '*.orig' linux-4.9/fs/aufs/i_op_del.c linux-4.9/fs/aufs/i_op_del.c +--- linux-4.9/fs/aufs/i_op_del.c 1970-01-01 01:00:00.000000000 +0100 ++++ linux-4.9/fs/aufs/i_op_del.c 2021-02-24 16:15:09.531573855 +0100 +@@ -0,0 +1,511 @@ +/* -+ * Copyright (C) 2005-2016 Junjiro R. Okajima ++ * Copyright (C) 2005-2018 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by @@ -17529,108 +19498,86 @@ diff -urN /usr/share/empty/fs/aufs/i_op_add.c linux/fs/aufs/i_op_add.c + */ + +/* -+ * inode operations (add entry) ++ * inode operations (del entry) + */ + +#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. ++ * 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 + */ -+static int epilog(struct inode *dir, aufs_bindex_t bindex, -+ struct dentry *wh_dentry, struct dentry *dentry) ++int au_wr_dir_need_wh(struct dentry *dentry, int isdir, aufs_bindex_t *bcpup) +{ -+ int err, rerr; -+ aufs_bindex_t bwh; -+ struct path h_path; ++ int need_wh, err; ++ aufs_bindex_t btop; + 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); ++ 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 (*bcpup != btop) { ++ err = au_cpup_dirs(dentry, *bcpup); + if (unlikely(err)) + goto out; -+ } ++ need_wh = 1; ++ } else { ++ struct au_dinfo *dinfo, *tmp; + -+ 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); -+ dir->i_version++; -+ au_fhsm_wrote(sb, bindex, /*force*/0); -+ return 0; /* success */ ++ 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); ++ } + } -+ -+ 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); ++ AuDbg("need_wh %d\n", need_wh); ++ err = need_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. ++ * simple tests for the del-entry operations. + * following the checks in vfs, plus the parent-child relationship. + */ -+int au_may_add(struct dentry *dentry, aufs_bindex_t bindex, ++int au_may_del(struct dentry *dentry, aufs_bindex_t bindex, + struct dentry *h_parent, int isdir) +{ + int err; + umode_t h_mode; -+ struct dentry *h_dentry; ++ struct dentry *h_dentry, *h_latest; + struct inode *h_inode; + -+ err = -ENAMETOOLONG; -+ if (unlikely(dentry->d_name.len > AUFS_MAX_NAMELEN)) -+ goto out; -+ + h_dentry = au_h_dptr(dentry, bindex); -+ if (d_really_is_negative(dentry)) { -+ err = -EEXIST; -+ if (unlikely(d_is_positive(h_dentry))) -+ goto out; -+ } else { -+ /* rename(2) case */ -+ err = -EIO; ++ if (d_really_is_positive(dentry)) { ++ err = -ENOENT; + if (unlikely(d_is_negative(h_dentry))) + goto out; + h_inode = d_inode(h_dentry); @@ -17646,709 +19593,306 @@ diff -urN /usr/share/empty/fs/aufs/i_op_add.c linux/fs/aufs/i_op_add.c + err = -ENOTDIR; + goto out; + } ++ } else { ++ /* rename(2) case */ ++ err = -EIO; ++ if (unlikely(d_is_positive(h_dentry))) ++ goto out; + } + -+ err = 0; ++ err = -ENOENT; + /* expected parent dir is locked */ + if (unlikely(h_parent != h_dentry->d_parent)) -+ err = -EIO; -+ -+out: -+ AuTraceErr(err); -+ return err; -+} -+ -+/* -+ * initial procedure of adding a new entry. -+ * prepare writable branch and the parent dir, lock it, -+ * and lookup whiteout for the new entry. -+ */ -+static struct dentry* -+lock_hdir_lkup_wh(struct dentry *dentry, struct au_dtime *dt, -+ struct dentry *src_dentry, struct au_pin *pin, -+ struct au_wr_dir_args *wr_dir_args) -+{ -+ struct dentry *wh_dentry, *h_parent; -+ struct super_block *sb; -+ struct au_branch *br; -+ int err; -+ unsigned int udba; -+ aufs_bindex_t bcpup; -+ -+ AuDbg("%pd\n", dentry); -+ -+ err = au_wr_dir(dentry, src_dentry, wr_dir_args); -+ bcpup = err; -+ wh_dentry = ERR_PTR(err); -+ if (unlikely(err < 0)) -+ goto out; -+ -+ sb = dentry->d_sb; -+ udba = au_opt_udba(sb); -+ err = au_pin(pin, dentry, bcpup, udba, -+ AuPin_DI_LOCKED | AuPin_MNT_WRITE); -+ wh_dentry = ERR_PTR(err); -+ if (unlikely(err)) + goto out; -+ -+ h_parent = au_pinned_h_parent(pin); -+ if (udba != AuOpt_UDBA_NONE -+ && au_dbtop(dentry) == bcpup) -+ err = au_may_add(dentry, bcpup, h_parent, -+ au_ftest_wrdir(wr_dir_args->flags, ISDIR)); -+ else if (unlikely(dentry->d_name.len > AUFS_MAX_NAMELEN)) -+ err = -ENAMETOOLONG; -+ wh_dentry = ERR_PTR(err); -+ if (unlikely(err)) -+ goto out_unpin; -+ -+ br = au_sbr(sb, bcpup); -+ if (dt) { -+ struct path tmp = { -+ .dentry = h_parent, -+ .mnt = au_br_mnt(br) -+ }; -+ au_dtime_store(dt, au_pinned_parent(pin), &tmp); -+ } -+ -+ wh_dentry = NULL; -+ if (bcpup != au_dbwh(dentry)) -+ goto out; /* success */ ++ err = 0; + + /* -+ * 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. ++ * rmdir a dir may break the consistency on some filesystem. ++ * let's try heavy test. + */ -+ wh_dentry = au_wh_lkup(h_parent, &dentry->d_name, br); -+ -+out_unpin: -+ if (IS_ERR(wh_dentry)) -+ au_unpin(pin); -+out: -+ return wh_dentry; -+} -+ -+/* ---------------------------------------------------------------------- */ -+ -+enum { Mknod, Symlink, Creat }; -+struct simple_arg { -+ int type; -+ union { -+ struct { -+ umode_t mode; -+ bool want_excl; -+ bool try_aopen; -+ struct vfsub_aopen_args *aopen; -+ } c; -+ struct { -+ const char *symname; -+ } s; -+ struct { -+ umode_t mode; -+ dev_t dev; -+ } m; -+ } u; -+}; -+ -+static int add_simple(struct inode *dir, struct dentry *dentry, -+ struct simple_arg *arg) -+{ -+ int err, rerr; -+ aufs_bindex_t btop; -+ unsigned char created; -+ const unsigned char try_aopen -+ = (arg->type == Creat && arg->u.c.try_aopen); -+ struct dentry *wh_dentry, *parent; -+ struct inode *h_dir; -+ struct super_block *sb; -+ struct au_branch *br; -+ /* to reuduce stack size */ -+ struct { -+ struct au_dtime dt; -+ struct au_pin pin; -+ struct path h_path; -+ struct au_wr_dir_args wr_dir_args; -+ } *a; -+ -+ AuDbg("%pd\n", dentry); -+ IMustLock(dir); -+ -+ err = -ENOMEM; -+ a = kmalloc(sizeof(*a), GFP_NOFS); -+ if (unlikely(!a)) -+ goto out; -+ a->wr_dir_args.force_btgt = -1; -+ a->wr_dir_args.flags = AuWrDir_ADD_ENTRY; -+ -+ parent = dentry->d_parent; /* dir inode is locked */ -+ if (!try_aopen) { -+ err = aufs_read_lock(dentry, AuLock_DW | AuLock_GEN); -+ if (unlikely(err)) -+ goto out_free; -+ } -+ err = au_d_may_add(dentry); -+ if (unlikely(err)) -+ goto out_unlock; -+ if (!try_aopen) -+ di_write_lock_parent(parent); -+ wh_dentry = lock_hdir_lkup_wh(dentry, &a->dt, /*src_dentry*/NULL, -+ &a->pin, &a->wr_dir_args); -+ err = PTR_ERR(wh_dentry); -+ if (IS_ERR(wh_dentry)) -+ goto out_parent; -+ -+ btop = au_dbtop(dentry); -+ sb = dentry->d_sb; -+ br = au_sbr(sb, btop); -+ a->h_path.dentry = au_h_dptr(dentry, btop); -+ a->h_path.mnt = au_br_mnt(br); -+ h_dir = au_pinned_h_dir(&a->pin); -+ switch (arg->type) { -+ case Creat: -+ err = 0; -+ 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); -+ else -+ err = vfsub_atomic_open(h_dir, a->h_path.dentry, -+ arg->u.c.aopen, br); -+ break; -+ case Symlink: -+ err = vfsub_symlink(h_dir, &a->h_path, arg->u.s.symname); -+ break; -+ case Mknod: -+ err = vfsub_mknod(h_dir, &a->h_path, arg->u.m.mode, -+ arg->u.m.dev); -+ break; -+ default: -+ BUG(); -+ } -+ created = !err; -+ if (!err) -+ err = epilog(dir, btop, wh_dentry, dentry); -+ -+ /* revert */ -+ if (unlikely(created && err && 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 (!err && try_aopen && !h_dir->i_op->atomic_open) -+ *arg->u.c.aopen->opened |= FILE_CREATED; -+ -+ au_unpin(&a->pin); -+ dput(wh_dentry); -+ -+out_parent: -+ if (!try_aopen) -+ di_write_unlock(parent); -+out_unlock: -+ if (unlikely(err)) { -+ au_update_dbtop(dentry); -+ d_drop(dentry); -+ } -+ if (!try_aopen) -+ aufs_read_unlock(dentry, AuLock_DW); -+out_free: -+ au_delayed_kfree(a); -+out: -+ return err; -+} -+ -+int aufs_mknod(struct inode *dir, struct dentry *dentry, umode_t mode, -+ dev_t dev) -+{ -+ struct simple_arg arg = { -+ .type = Mknod, -+ .u.m = { -+ .mode = mode, -+ .dev = dev -+ } -+ }; -+ return add_simple(dir, dentry, &arg); -+} -+ -+int aufs_symlink(struct inode *dir, struct dentry *dentry, const char *symname) -+{ -+ struct simple_arg arg = { -+ .type = Symlink, -+ .u.s.symname = symname -+ }; -+ return add_simple(dir, dentry, &arg); -+} -+ -+int aufs_create(struct inode *dir, struct dentry *dentry, umode_t mode, -+ bool want_excl) -+{ -+ struct simple_arg arg = { -+ .type = Creat, -+ .u.c = { -+ .mode = mode, -+ .want_excl = want_excl -+ } -+ }; -+ return add_simple(dir, dentry, &arg); -+} -+ -+int au_aopen_or_create(struct inode *dir, struct dentry *dentry, -+ struct vfsub_aopen_args *aopen_args) -+{ -+ struct simple_arg arg = { -+ .type = Creat, -+ .u.c = { -+ .mode = aopen_args->create_mode, -+ .want_excl = aopen_args->open_flag & O_EXCL, -+ .try_aopen = true, -+ .aopen = aopen_args -+ } -+ }; -+ return add_simple(dir, dentry, &arg); -+} -+ -+int aufs_tmpfile(struct inode *dir, struct dentry *dentry, umode_t mode) -+{ -+ int err; -+ aufs_bindex_t bindex; -+ struct super_block *sb; -+ struct dentry *parent, *h_parent, *h_dentry; -+ struct inode *h_dir, *inode; -+ struct vfsmount *h_mnt; -+ struct au_wr_dir_args wr_dir_args = { -+ .force_btgt = -1, -+ .flags = AuWrDir_TMPFILE -+ }; -+ -+ /* copy-up may happen */ -+ inode_lock(dir); -+ -+ sb = dir->i_sb; -+ err = si_read_lock(sb, AuLock_FLUSH | AuLock_NOPLM); -+ if (unlikely(err)) -+ goto out; -+ -+ err = au_di_init(dentry); -+ if (unlikely(err)) -+ goto out_si; -+ -+ err = -EBUSY; -+ parent = d_find_any_alias(dir); -+ AuDebugOn(!parent); -+ di_write_lock_parent(parent); -+ if (unlikely(d_inode(parent) != dir)) -+ goto out_parent; -+ -+ err = au_digen_test(parent, au_sigen(sb)); -+ if (unlikely(err)) -+ goto out_parent; -+ -+ bindex = au_dbtop(parent); -+ au_set_dbtop(dentry, bindex); -+ au_set_dbbot(dentry, bindex); -+ err = au_wr_dir(dentry, /*src_dentry*/NULL, &wr_dir_args); -+ bindex = err; -+ if (unlikely(err < 0)) -+ goto out_parent; -+ -+ err = -EOPNOTSUPP; -+ h_dir = au_h_iptr(dir, bindex); -+ if (unlikely(!h_dir->i_op->tmpfile)) -+ goto out_parent; -+ -+ h_mnt = au_sbr_mnt(sb, bindex); -+ err = vfsub_mnt_want_write(h_mnt); -+ if (unlikely(err)) -+ goto out_parent; -+ -+ h_parent = au_h_dptr(parent, bindex); -+ err = inode_permission(d_inode(h_parent), MAY_WRITE | MAY_EXEC); -+ if (unlikely(err)) -+ goto out_mnt; -+ -+ err = -ENOMEM; -+ h_dentry = d_alloc(h_parent, &dentry->d_name); -+ if (unlikely(!h_dentry)) -+ goto out_mnt; -+ -+ err = h_dir->i_op->tmpfile(h_dir, h_dentry, mode); -+ if (unlikely(err)) -+ goto out_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); -+ } else { -+ if (!inode->i_nlink) -+ set_nlink(inode, 1); -+ d_tmpfile(dentry, inode); -+ au_di(dentry)->di_tmpfile = 1; -+ -+ /* update without i_mutex */ -+ if (au_ibtop(dir) == au_dbtop(dentry)) -+ au_cpup_attr_timesizes(dir); -+ } ++ err = -EACCES; ++ if (unlikely(!au_opt_test(au_mntflags(dentry->d_sb), DIRPERM1) ++ && au_test_h_perm(d_inode(h_parent), ++ MAY_EXEC | MAY_WRITE))) ++ goto out; ++ ++ h_latest = au_sio_lkup_one(&dentry->d_name, h_parent); ++ err = -EIO; ++ if (IS_ERR(h_latest)) ++ goto out; ++ if (h_latest == h_dentry) ++ err = 0; ++ dput(h_latest); + -+out_dentry: -+ dput(h_dentry); -+out_mnt: -+ vfsub_mnt_drop_write(h_mnt); -+out_parent: -+ di_write_unlock(parent); -+ dput(parent); -+ di_write_unlock(dentry); -+ if (unlikely(err)) { -+ au_di_fin(dentry); -+ dentry->d_fsdata = NULL; -+ } -+out_si: -+ si_read_unlock(sb); +out: -+ inode_unlock(dir); + return err; +} + -+/* ---------------------------------------------------------------------- */ -+ -+struct au_link_args { -+ aufs_bindex_t bdst, bsrc; -+ struct au_pin pin; -+ struct path h_path; -+ struct dentry *src_parent, *parent; -+}; -+ -+static int au_cpup_before_link(struct dentry *src_dentry, -+ struct au_link_args *a) ++/* ++ * decide the branch where we operate for @dentry. the branch index will be set ++ * @rbcpup. after diciding 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; -+ 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 */ -+ }; ++ struct dentry *wh_dentry; ++ struct super_block *sb; ++ struct path h_path; ++ int err, need_wh; ++ unsigned int udba; ++ aufs_bindex_t bcpup; + -+ di_read_lock_parent(a->src_parent, AuLock_IR); -+ err = au_test_and_cpup_dirs(src_dentry, a->bdst); -+ if (unlikely(err)) ++ need_wh = au_wr_dir_need_wh(dentry, isdir, rbcpup); ++ wh_dentry = ERR_PTR(need_wh); ++ if (unlikely(need_wh < 0)) + 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), ++ 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; + -+ err = au_sio_cpup_simple(&cpg); -+ au_unpin(&a->pin); ++ 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 */ + ++out_unpin: ++ au_unpin(pin); +out: -+ di_read_unlock(a->src_parent, AuLock_IR); -+ return err; ++ return wh_dentry; +} + -+static int au_cpup_or_link(struct dentry *src_dentry, struct dentry *dentry, -+ struct au_link_args *a) ++/* ++ * 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 char plink; -+ aufs_bindex_t bbot; -+ struct dentry *h_src_dentry; -+ struct inode *h_inode, *inode, *delegated; ++ int rmdir_later, err, dirwh; ++ struct dentry *h_dentry; + struct super_block *sb; -+ struct file *h_file; ++ struct inode *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; ++ 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; + -+ if (unlikely(d_is_negative(h_src_dentry))) { -+ dput(h_src_dentry); -+ h_src_dentry = NULL; -+ } ++ /* stop monitoring */ ++ inode = d_inode(dentry); ++ au_hn_free(au_hi(inode, bindex)); + -+ } -+ if (h_src_dentry) { -+ delegated = NULL; -+ err = vfsub_link(h_src_dentry, au_pinned_h_dir(&a->pin), -+ &a->h_path, &delegated); -+ if (unlikely(err == -EWOULDBLOCK)) { -+ pr_warn("cannot retry for NFSv4 delegation" -+ " for an internal link\n"); -+ iput(delegated); -+ } -+ dput(h_src_dentry); -+ } else { -+ AuIOErr("no dentry found for hi%lu on b%d\n", -+ h_inode->i_ino, a->bdst); -+ err = -EIO; -+ } ++ if (!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 (!err && !plink) -+ au_plink_append(inode, a->bdst, a->h_path.dentry); ++ 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; ++ } + +out: + AuTraceErr(err); + return err; +} + -+int aufs_link(struct dentry *src_dentry, struct inode *dir, -+ struct dentry *dentry) ++/* ++ * final procedure for deleting a entry. ++ * maintain dentry and iattr. ++ */ ++static void epilog(struct inode *dir, struct dentry *dentry, ++ aufs_bindex_t 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 ++ struct inode *inode; ++ ++ inode = d_inode(dentry); ++ d_drop(dentry); ++ inode->i_ctime = dir->i_ctime; ++ ++ au_dir_ts(dir, bindex); ++ dir->i_version++; ++} ++ ++/* ++ * 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) + }; + ++ 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; ++ struct dentry *parent, *wh_dentry; ++ /* to reuduce 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 = kzalloc(sizeof(*a), GFP_NOFS); ++ a = kmalloc(sizeof(*a), GFP_NOFS); + if (unlikely(!a)) + goto out; + -+ a->parent = dentry->d_parent; /* dir inode is locked */ -+ err = aufs_read_and_write_lock2(dentry, src_dentry, -+ AuLock_NOPLM | AuLock_GEN); -+ if (unlikely(err)) -+ goto out_kfree; -+ err = au_d_linkable(src_dentry); ++ err = aufs_read_lock(dentry, AuLock_DW | AuLock_GEN); + if (unlikely(err)) -+ goto out_unlock; -+ err = au_d_may_add(dentry); ++ 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? */ + -+ 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); ++ 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; + -+ 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 unnecrssary. -+ */ -+ 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); -+ } ++ 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); + } -+ 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); -+ } -+ } -+ } ++ /* dir inode is locked */ ++ h_dir = d_inode(wh_dentry->d_parent); ++ IMustLock(h_dir); ++ err = 0; + } -+ 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; ++ 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*/ ++ inode->i_ctime = d_inode(a->h_path.dentry)->i_ctime; ++ } else ++ /* todo: this timestamp may be reverted later */ ++ inode->i_ctime = h_dir->i_ctime; ++ goto out_unpin; /* success */ + } + -+ au_dir_ts(dir, a->bdst); -+ dir->i_version++; -+ inc_nlink(inode); -+ inode->i_ctime = dir->i_ctime; -+ d_instantiate(dentry, au_igrab(inode)); -+ if (d_unhashed(a->h_path.dentry)) -+ /* some filesystem calls d_drop() */ -+ d_drop(dentry); -+ /* some filesystems consume an inode even hardlink */ -+ au_fhsm_wrote(sb, a->bdst, /*force*/0); -+ goto out_unpin; /* success */ ++ /* revert */ ++ if (wh_dentry) { ++ int 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; ++ rerr = do_revert(err, dir, bindex, bwh, wh_dentry, dentry, ++ &a->dt); ++ if (rerr) ++ err = rerr; + } -+ 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(a->parent); -+ dput(a->src_parent); ++ di_write_unlock(parent); +out_unlock: -+ if (unlikely(err)) { -+ au_update_dbtop(dentry); -+ d_drop(dentry); -+ } -+ aufs_read_and_write_unlock2(dentry, src_dentry); -+out_kfree: -+ au_delayed_kfree(a); ++ aufs_read_unlock(dentry, AuLock_DW); ++out_free: ++ kfree(a); +out: -+ AuTraceErr(err); + return err; +} + -+int aufs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) ++int aufs_rmdir(struct inode *dir, struct dentry *dentry) +{ -+ 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; ++ 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 reuduce 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; ++ } *a; + + IMustLock(dir); + @@ -18357,94 +19901,102 @@ diff -urN /usr/share/empty/fs/aufs/i_op_add.c linux/fs/aufs/i_op_add.c + if (unlikely(!a)) + goto out; + -+ err = aufs_read_lock(dentry, AuLock_DW | AuLock_GEN); ++ err = aufs_read_lock(dentry, AuLock_DW | AuLock_FLUSH | AuLock_GEN); + if (unlikely(err)) + goto out_free; -+ err = au_d_may_add(dentry); ++ 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? */ ++ ++ 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); -+ wh_dentry = lock_hdir_lkup_wh(dentry, &a->dt, /*src_dentry*/NULL, -+ &a->pin, &wr_dir_args); ++ 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); + err = PTR_ERR(wh_dentry); + if (IS_ERR(wh_dentry)) + goto out_parent; + -+ sb = dentry->d_sb; -+ bindex = au_dbtop(dentry); -+ h_path.dentry = au_h_dptr(dentry, bindex); -+ h_path.mnt = au_sbr_mnt(sb, bindex); -+ err = vfsub_mkdir(au_pinned_h_dir(&a->pin), &h_path, mode); -+ if (unlikely(err)) -+ goto out_unpin; ++ 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)); + -+ /* 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; ++ /* dir inode is locked */ ++ IMustLock(d_inode(wh_dentry->d_parent)); ++ err = 0; + } + -+ err = epilog(dir, bindex, wh_dentry, dentry); + if (!err) { -+ inc_nlink(dir); ++ 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; ++ } ++ + 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 (rerr) { -+ AuIOErr("%pd reverting diropq failed(%d, %d)\n", -+ dentry, err, rerr); -+ err = -EIO; -+ } -+ } ++ AuLabel(revert); ++ if (wh_dentry) { ++ int rerr; + -+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; ++ rerr = do_revert(err, dir, bindex, bwh, wh_dentry, dentry, ++ &a->dt); ++ if (rerr) ++ err = rerr; + } -+ 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_delayed_kfree(a); ++ kfree(a); +out: ++ AuTraceErr(err); + return err; +} -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 2016-12-17 12:28:17.595211562 +0100 -@@ -0,0 +1,1444 @@ +diff -urNp -x '*.orig' linux-4.9/fs/aufs/i_op_ren.c linux-4.9/fs/aufs/i_op_ren.c +--- linux-4.9/fs/aufs/i_op_ren.c 1970-01-01 01:00:00.000000000 +0100 ++++ linux-4.9/fs/aufs/i_op_ren.c 2021-02-24 16:15:09.531573855 +0100 +@@ -0,0 +1,1246 @@ +/* -+ * Copyright (C) 2005-2016 Junjiro R. Okajima ++ * Copyright (C) 2005-2018 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by @@ -18461,1438 +20013,1529 @@ diff -urN /usr/share/empty/fs/aufs/i_op.c linux/fs/aufs/i_op.c + */ + +/* -+ * inode operations (except add/del/rename) ++ * inode operation (rename entry) ++ * todo: this is crazy monster + */ + -+#include -+#include -+#include -+#include +#include "aufs.h" + -+static int h_permission(struct inode *h_inode, int mask, -+ struct path *h_path, int brperm) ++enum { AuSRC, AuDST, AuSrcDst }; ++enum { AuPARENT, AuCHILD, AuParentChild }; ++ ++#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) ++ ++#ifndef CONFIG_AUFS_DIRREN ++#undef AuRen_DIRREN ++#define AuRen_DIRREN 0 ++#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; ++ ++ struct au_whtmp_rmdir *thargs; ++ struct dentry *h_dst; ++ struct au_hinode *h_root; ++}; ++ ++/* ---------------------------------------------------------------------- */ ++ ++/* ++ * 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. ++ */ ++ ++#define RevertFailure(fmt, ...) do { \ ++ AuIOErr("revert failure: " fmt " (%d, %d)\n", \ ++ ##__VA_ARGS__, err, rerr); \ ++ err = -EIO; \ ++} while (0) ++ ++static void au_ren_do_rev_diropq(int err, struct au_ren_args *a, int idx) +{ -+ int err; -+ const unsigned char write_mask = !!(mask & (MAY_WRITE | MAY_APPEND)); ++ int rerr; ++ struct dentry *d; ++#define src_or_dst(member) a->sd[idx].member + -+ err = -EPERM; -+ if (write_mask && IS_IMMUTABLE(h_inode)) -+ goto out; ++ 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); + -+ err = -EACCES; -+ if (((mask & MAY_EXEC) -+ && S_ISREG(h_inode->i_mode) -+ && (path_noexec(h_path) -+ || !(h_inode->i_mode & S_IXUGO)))) -+ goto out; ++#undef src_or_dst_ ++} + -+ /* -+ * - 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 MS_POSIXACL regardless its mount option 'noacl.' -+ * in this case, generic_permission() returns -EOPNOTSUPP. -+ */ -+ if ((write_mask && !au_br_writable(brperm)) -+ || (au_test_nfs(h_inode->i_sb) && S_ISDIR(h_inode->i_mode) -+ && write_mask && !(mask & MAY_READ)) -+ || !h_inode->i_op->permission) { -+ /* AuLabel(generic_permission); */ -+ /* AuDbg("get_acl %pf\n", h_inode->i_op->get_acl); */ -+ err = generic_permission(h_inode, mask); -+ if (err == -EOPNOTSUPP && au_test_nfs_noacl(h_inode)) -+ err = h_inode->i_op->permission(h_inode, mask); -+ AuTraceErr(err); -+ } else { -+ /* AuLabel(h_inode->permission); */ -+ err = h_inode->i_op->permission(h_inode, mask); -+ AuTraceErr(err); ++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) ++{ ++ int rerr; ++ struct inode *delegated; ++ ++ a->h_path.dentry = vfsub_lkup_one(&a->src_dentry->d_name, ++ a->src_h_parent); ++ rerr = PTR_ERR(a->h_path.dentry); ++ if (IS_ERR(a->h_path.dentry)) { ++ RevertFailure("lkup one %pd", a->src_dentry); ++ return; + } + -+ if (!err) -+ err = devcgroup_inode_permission(h_inode, mask); -+ if (!err) -+ err = security_inode_permission(h_inode, mask); ++ 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); ++} + -+#if 0 -+ if (!err) { -+ /* todo: do we need to call ima_path_check()? */ -+ struct path h_path = { -+ .dentry = -+ .mnt = h_mnt -+ }; -+ err = ima_path_check(&h_path, -+ mask & (MAY_READ | MAY_WRITE | MAY_EXEC), -+ IMA_COUNT_LEAVE); ++static void au_ren_rev_whtmp(int err, struct au_ren_args *a) ++{ ++ int rerr; ++ struct inode *delegated; ++ ++ a->h_path.dentry = vfsub_lkup_one(&a->dst_dentry->d_name, ++ a->dst_h_parent); ++ 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; + } -+#endif + -+out: ++ 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) ++{ ++ 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 ++ ++/* ---------------------------------------------------------------------- */ ++ ++/* ++ * 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) ++{ ++ int err; ++ struct dentry *d; ++ struct inode *delegated; ++ ++ 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(); ++ ++ if (!err && a->h_dst) ++ /* it will be set to dinfo later */ ++ dget(a->h_dst); ++ + return err; +} + -+static int aufs_permission(struct inode *inode, int mask) ++/* cf. aufs_rmdir() */ ++static int au_ren_del_whtmp(struct au_ren_args *a) +{ + 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 inode *dir; + -+ /* todo: support rcu-walk? */ -+ if (mask & MAY_NOT_BLOCK) -+ return -ECHILD; ++ 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; ++ } + -+ sb = inode->i_sb; -+ si_read_lock(sb, AuLock_FLUSH); -+ ii_read_lock_child(inode); -+#if 0 -+ err = au_iigen_test(inode, au_sigen(sb)); -+ if (unlikely(err)) -+ goto out; -+#endif ++ return 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))) ++/* 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 ++ ++ 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); ++ ++#undef src_or_dst_ ++ return err; ++} ++ ++static int au_ren_diropq(struct au_ren_args *a) ++{ ++ int err; ++ unsigned char always; ++ struct dentry *d; ++ ++ 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 */ + -+ 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; ++ 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 */ + -+ /* 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; ++out_rev_src: ++ AuDbg("err %d, reverting src\n", err); ++ au_ren_rev_diropq(err, a); ++out: ++ return err; ++} + -+ br = au_sbr(sb, bindex); -+ err = h_permission(h_inode, mask, &br->br_path, -+ br->br_perm); ++static int do_rename(struct au_ren_args *a) ++{ ++ int err; ++ struct dentry *d, *h_d; ++ ++ 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); + } -+ } -+ -+out: -+ ii_read_unlock(inode); -+ si_read_unlock(sb); -+ return err; -+} + -+/* ---------------------------------------------------------------------- */ ++ /* 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 struct dentry *aufs_lookup(struct inode *dir, struct dentry *dentry, -+ unsigned int flags) -+{ -+ struct dentry *ret, *parent; -+ struct inode *inode; -+ struct super_block *sb; -+ int err, npositive; ++ /* 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; ++ } + -+ IMustLock(dir); ++ /* rename dentry to tmpwh */ ++ if (a->thargs) { ++ err = au_whtmp_ren(a->dst_h_dentry, a->br); ++ if (unlikely(err)) ++ goto out_whdst; + -+ /* todo: support rcu-walk? */ -+ ret = ERR_PTR(-ECHILD); -+ if (flags & LOOKUP_RCU) -+ goto out; ++ 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); ++ } ++ } + -+ ret = ERR_PTR(-ENAMETOOLONG); -+ if (unlikely(dentry->d_name.len > AUFS_MAX_NAMELEN)) -+ goto out; ++ BUG_ON(d_is_positive(a->dst_h_dentry) && a->src_btop != a->btgt); ++#if 0 ++ BUG_ON(!au_ftest_ren(a->auren_flags, DIRREN) ++ && d_is_positive(a->dst_h_dentry) ++ && a->src_btop != a->btgt); ++#endif + -+ sb = dir->i_sb; -+ err = si_read_lock(sb, AuLock_FLUSH | AuLock_NOPLM); -+ ret = ERR_PTR(err); ++ /* rename by vfs_rename or cpup */ ++ err = au_ren_or_cpup(a); + if (unlikely(err)) -+ goto out; ++ /* leave the copied-up one */ ++ goto out_whtmp; + -+ err = au_di_init(dentry); -+ ret = ERR_PTR(err); ++ /* make dir opaque */ ++ err = au_ren_diropq(a); + if (unlikely(err)) -+ goto out_si; ++ goto out_rename; + -+ 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; ++ /* 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*/ ++ a->dst_inode->i_ctime = d_inode(a->h_path.dentry)->i_ctime; + } -+ di_read_unlock(parent, AuLock_IR); -+ ret = ERR_PTR(err); -+ if (unlikely(err < 0)) -+ goto out_unlock; ++ 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*/ ++ a->src_inode->i_ctime = d_inode(a->h_path.dentry)->i_ctime; + -+ if (npositive) { -+ inode = au_new_inode(dentry, /*must_new*/0); -+ if (IS_ERR(inode)) { -+ ret = (void *)inode; -+ inode = NULL; -+ goto out_unlock; ++ 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 (inode) -+ atomic_inc(&inode->i_count); -+ ret = d_splice_alias(inode, dentry); -+#if 0 -+ if (unlikely(d_need_lookup(dentry))) { -+ spin_lock(&dentry->d_lock); -+ dentry->d_flags &= ~DCACHE_NEED_LOOKUP; -+ spin_unlock(&dentry->d_lock); -+ } else -+#endif -+ if (inode) { -+ if (!IS_ERR(ret)) { -+ iput(inode); -+ if (ret && ret != dentry) -+ ii_write_unlock(inode); -+ } else { -+ ii_write_unlock(inode); -+ iput(inode); -+ inode = NULL; -+ } ++ /* 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_unlock: -+ di_write_unlock(dentry); -+out_si: -+ si_read_unlock(sb); ++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 ret; ++ return err; +} + +/* ---------------------------------------------------------------------- */ + -+struct aopen_node { -+ struct hlist_node hlist; -+ struct file *file, *h_file; -+}; -+ -+static int au_do_aopen(struct inode *inode, struct file *file) ++/* ++ * 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) +{ -+ struct au_sphlhead *aopen; -+ struct aopen_node *node; -+ struct au_do_open_args args = { -+ .no_lock = 1, -+ .open = au_do_open_nondir -+ }; -+ -+ aopen = &au_sbi(inode->i_sb)->si_aopen; -+ spin_lock(&aopen->spin); -+ hlist_for_each_entry(node, &aopen->head, hlist) -+ if (node->file == file) { -+ args.h_file = node->h_file; -+ break; -+ } -+ spin_unlock(&aopen->spin); -+ /* AuDebugOn(!args.h_file); */ -+ -+ return au_do_open(file, &args); ++ return au_test_empty(dentry, whlist); +} + -+static int aufs_atomic_open(struct inode *dir, struct dentry *dentry, -+ struct file *file, unsigned int open_flag, -+ umode_t create_mode, int *opened) ++/* ++ * 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, h_opened = *opened; -+ unsigned int lkup_flags; -+ struct dentry *parent, *d; -+ struct au_sphlhead *aopen; -+ struct vfsub_aopen_args args = { -+ .open_flag = open_flag, -+ .create_mode = create_mode, -+ .opened = &h_opened -+ }; -+ struct aopen_node aopen_node = { -+ .file = file -+ }; -+ -+ IMustLock(dir); -+ AuDbg("open_flag 0%o\n", open_flag); -+ AuDbgDentry(dentry); ++ int err; ++ unsigned int rdhash; ++ aufs_bindex_t btop, btgt; ++ struct dentry *dentry; ++ struct super_block *sb; ++ struct au_sbinfo *sbinfo; + -+ 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); -+ } ++ 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); + -+ if (d_is_positive(dentry) -+ || d_unhashed(dentry) -+ || d_unlinked(dentry) -+ || !(open_flag & O_CREAT)) -+ goto out_no_open; ++ btgt = a->btgt; ++ btop = au_dbtop(dentry); ++ if (btop != btgt) { ++ struct au_nhash whlist; + -+ err = aufs_read_lock(dentry, AuLock_DW | AuLock_FLUSH | AuLock_GEN); -+ if (unlikely(err)) ++ 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; -+ -+ 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)) -+ goto out_unlock; -+ -+ AuDbgDentry(dentry); -+ if (d_is_positive(dentry)) -+ goto out_unlock; -+ -+ args.file = get_empty_filp(); -+ err = PTR_ERR(args.file); -+ if (IS_ERR(args.file)) -+ goto out_unlock; -+ -+ args.file->f_flags = file->f_flags; -+ err = au_aopen_or_create(dir, dentry, &args); -+ AuTraceErr(err); -+ AuDbgFile(args.file); -+ if (unlikely(err < 0)) { -+ if (h_opened & FILE_OPENED) -+ fput(args.file); -+ else -+ put_filp(args.file); -+ goto out_unlock; + } + -+ /* some filesystems don't set FILE_CREATED while succeeded? */ -+ *opened |= FILE_CREATED; -+ if (h_opened & FILE_OPENED) -+ aopen_node.h_file = args.file; -+ else { -+ put_filp(args.file); -+ args.file = NULL; -+ } -+ aopen = &au_sbi(dir->i_sb)->si_aopen; -+ au_sphl_add(&aopen_node.hlist, aopen); -+ err = finish_open(file, dentry, au_do_aopen, opened); -+ au_sphl_del(&aopen_node.hlist, aopen); -+ AuTraceErr(err); -+ AuDbgFile(file); -+ if (aopen_node.h_file) -+ fput(aopen_node.h_file); ++ if (btop == au_dbtaildir(dentry)) ++ return 0; /* success */ ++ ++ err = au_test_empty_lower(dentry); + -+out_unlock: -+ di_write_unlock(parent); -+ aufs_read_unlock(dentry, AuLock_DW); -+ AuDbgDentry(dentry); -+ if (unlikely(err < 0)) -+ goto out; -+out_no_open: -+ if (err >= 0 && !(*opened & FILE_CREATED)) { -+ AuLabel(out_no_open); -+ dget(dentry); -+ err = finish_no_open(file, dentry); -+ } +out: -+ AuDbg("%pd%s%s\n", dentry, -+ (*opened & FILE_CREATED) ? " created" : "", -+ (*opened & FILE_OPENED) ? " opened" : ""); -+ AuTraceErr(err); ++ 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 int au_wr_dir_cpup(struct dentry *dentry, struct dentry *parent, -+ const unsigned char add_entry, aufs_bindex_t bcpup, -+ aufs_bindex_t btop) ++/* side effect: sets whlist and h_dentry */ ++static int au_ren_may_dir(struct au_ren_args *a) +{ + int err; -+ struct dentry *h_parent; -+ struct inode *h_dir; ++ unsigned int rdhash; ++ struct dentry *d; + -+ if (add_entry) -+ IMustLock(d_inode(parent)); -+ else -+ di_write_lock_parent(parent); ++ d = a->dst_dentry; ++ SiMustAnyLock(d->d_sb); + + 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 (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); + } -+ 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_nested(h_dir, AuLsc_I_PARENT); -+ err = au_lkup_neg(dentry, bcpup, /*wh*/0); -+ /* todo: no unlock here */ -+ inode_unlock(h_dir); ++ a->dst_h_dentry = au_h_dptr(d, au_dbtop(d)); ++ if (unlikely(err)) ++ goto out; + -+ 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); ++ 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; + } + } -+ -+ 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. ++ * simple tests for rename. ++ * following the checks in vfs, plus the parent-child relationship. + */ -+int au_wr_dir(struct dentry *dentry, struct dentry *src_dentry, -+ struct au_wr_dir_args *args) ++static int au_may_ren(struct au_ren_args *a) +{ -+ int err; -+ unsigned int flags; -+ aufs_bindex_t bcpup, btop, src_btop; -+ const unsigned char add_entry -+ = au_ftest_wrdir(args->flags, ADD_ENTRY) -+ | au_ftest_wrdir(args->flags, TMPFILE); -+ struct super_block *sb; -+ struct dentry *parent; -+ struct au_sbinfo *sbinfo; -+ -+ sb = dentry->d_sb; -+ sbinfo = au_sbi(sb); -+ parent = dget_parent(dentry); -+ btop = au_dbtop(dentry); -+ bcpup = btop; -+ if (args->force_btgt < 0) { -+ if (src_dentry) { -+ src_btop = au_dbtop(src_dentry); -+ if (src_btop < btop) -+ bcpup = src_btop; -+ } else if (add_entry) { -+ flags = 0; -+ if (au_ftest_wrdir(args->flags, ISDIR)) -+ au_fset_wbr(flags, DIR); -+ err = AuWbrCreate(sbinfo, dentry, flags); -+ bcpup = err; -+ } ++ int err, isdir; ++ struct inode *h_inode; + -+ 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))); ++ 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; + } + -+ AuDbg("btop %d, bcpup %d\n", btop, bcpup); -+ err = bcpup; -+ if (bcpup == btop) -+ goto out; /* success */ ++ err = 0; ++ if (a->dst_btop != a->btgt) ++ goto out; + -+ /* 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 = -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: -+ dput(parent); ++ if (unlikely(err == -ENOENT || err == -EEXIST)) ++ err = -EIO; ++ AuTraceErr(err); + return err; +} + +/* ---------------------------------------------------------------------- */ + -+void au_pin_hdir_unlock(struct au_pin *p) ++/* ++ * locking order ++ * (VFS) ++ * - src_dir and dir by lock_rename() ++ * - inode if exitsts ++ * (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) +{ -+ if (p->hdir) -+ au_hn_inode_unlock(p->hdir); ++ 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)); +} + -+int au_pin_hdir_lock(struct au_pin *p) ++static int au_ren_lock(struct au_ren_args *a) +{ + int err; ++ unsigned int udba; + + err = 0; -+ if (!p->hdir) -+ goto out; -+ -+ /* even if an error happens later, keep this lock */ -+ au_hn_inode_lock_nested(p->hdir, p->lsc_hi); -+ -+ err = -EBUSY; -+ if (unlikely(p->hdir->hi_inode != d_inode(p->h_parent))) -+ goto out; -+ -+ err = 0; -+ if (p->h_dentry) -+ err = au_h_verify(p->h_dentry, p->udba, p->hdir->hi_inode, -+ p->h_parent, p->br); -+ -+out: -+ return err; -+} -+ -+int au_pin_hdir_relock(struct au_pin *p) -+{ -+ int err, i; -+ struct inode *h_i; -+ struct dentry *h_d[] = { -+ p->h_dentry, -+ p->h_parent -+ }; ++ 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 = au_pin_hdir_lock(p); ++ 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; + -+ 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; ++ /* ++ * 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); ++ 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 void au_pin_hdir_set_owner(struct au_pin *p, struct task_struct *task) -+{ -+#if !defined(CONFIG_RWSEM_GENERIC_SPINLOCK) && defined(CONFIG_RWSEM_SPIN_ON_OWNER) -+ p->hdir->hi_inode->i_rwsem.owner = task; -+#endif -+} ++/* ---------------------------------------------------------------------- */ + -+void au_pin_hdir_acquire_nest(struct au_pin *p) ++static void au_ren_refresh_dir(struct au_ren_args *a) +{ -+ 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); -+ } -+} ++ struct inode *dir; + -+void au_pin_hdir_release(struct au_pin *p) -+{ -+ if (p->hdir) { -+ au_pin_hdir_set_owner(p, p->task); -+ rwsem_release(&p->hdir->hi_inode->i_rwsem.dep_map, 1, _RET_IP_); ++ dir = a->dst_dir; ++ dir->i_version++; ++ 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); + -+struct dentry *au_pinned_h_parent(struct au_pin *pin) -+{ -+ if (pin && pin->parent) -+ return au_h_dptr(pin->parent, pin->bindex); -+ return NULL; -+} ++ if (a->exchange) { ++ dir = a->src_dir; ++ dir->i_version++; ++ 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); ++ } + -+void au_unpin(struct au_pin *p) -+{ -+ if (p->hdir) -+ au_pin_hdir_unlock(p); -+ if (p->h_mnt && au_ftest_pin(p->flags, MNT_WRITE)) -+ vfsub_mnt_drop_write(p->h_mnt); -+ if (!p->hdir) ++ if (au_ftest_ren(a->auren_flags, ISSAMEDIR)) + 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 */ ++ dir = a->src_dir; ++ dir->i_version++; ++ if (au_ftest_ren(a->auren_flags, ISDIR_SRC)) ++ au_cpup_attr_nlink(dir, /*force*/1); ++ au_dir_ts(dir, a->btgt); +} + -+int au_do_pin(struct au_pin *p) ++static void au_ren_refresh(struct au_ren_args *a) +{ -+ int err; ++ aufs_bindex_t bbot, bindex; ++ struct dentry *d, *h_d; ++ struct inode *i, *h_i; + struct super_block *sb; -+ struct inode *h_dir; + -+ err = 0; -+ sb = p->dentry->d_sb; -+ p->br = au_sbr(sb, p->bindex); -+ if (IS_ROOT(p->dentry)) { -+ if (au_ftest_pin(p->flags, MNT_WRITE)) { -+ p->h_mnt = au_br_mnt(p->br); -+ err = vfsub_mnt_want_write(p->h_mnt); -+ if (unlikely(err)) { -+ au_fclr_pin(p->flags, MNT_WRITE); -+ goto out_err; ++ 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); + } -+ } -+ goto out; ++ 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); + } + -+ p->h_dentry = NULL; -+ if (p->bindex <= au_dbbot(p->dentry)) -+ p->h_dentry = au_h_dptr(p->dentry, p->bindex); -+ -+ p->parent = dget_parent(p->dentry); -+ if (!au_ftest_pin(p->flags, DI_LOCKED)) -+ di_read_lock(p->parent, AuLock_IR, p->lsc_di); -+ -+ h_dir = NULL; -+ p->h_parent = au_h_dptr(p->parent, p->bindex); -+ p->hdir = au_hi(d_inode(p->parent), p->bindex); -+ if (p->hdir) -+ h_dir = p->hdir->hi_inode; ++ 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; ++ } + -+ /* -+ * 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; ++ 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); + -+ 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; ++ 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); ++} + -+ au_igrab(h_dir); -+ err = au_pin_hdir_lock(p); -+ if (!err) -+ goto out; /* success */ ++/* ---------------------------------------------------------------------- */ + -+ au_unpin(p); ++/* mainly for link(2) and rename(2) */ ++int au_wbr(struct dentry *dentry, aufs_bindex_t btgt) ++{ ++ aufs_bindex_t bdiropq, bwh; ++ 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; ++ ++ AuDbg("btgt %d\n", btgt); ++ return btgt; ++} ++ ++/* sets src_btop, dst_btop and btgt */ ++static int au_ren_wbr(struct au_ren_args *a) ++{ ++ int err; ++ struct au_wr_dir_args wr_dir_args = { ++ /* .force_btgt = -1, */ ++ .flags = AuWrDir_ADD_ENTRY ++ }; ++ ++ 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); + -+out_err: -+ pr_err("err %d\n", err); -+ err = au_busy_or_stale(); -+out: + return err; +} + -+void au_pin_init(struct au_pin *p, struct dentry *dentry, -+ aufs_bindex_t bindex, int lsc_di, int lsc_hi, -+ unsigned int udba, unsigned char flags) ++static void au_ren_dt(struct au_ren_args *a) +{ -+ p->dentry = dentry; -+ p->udba = udba; -+ p->lsc_di = lsc_di; -+ p->lsc_hi = lsc_hi; -+ p->flags = flags; -+ p->bindex = 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); ++ } + -+ p->parent = NULL; -+ p->hdir = NULL; -+ p->h_mnt = NULL; ++ au_fclr_ren(a->auren_flags, DT_DSTDIR); ++ if (!au_ftest_ren(a->auren_flags, ISDIR_SRC) ++ && !a->exchange) ++ return; + -+ p->h_dentry = NULL; -+ p->h_parent = NULL; -+ p->br = NULL; -+ p->task = current; ++ 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); ++ } +} + -+int au_pin(struct au_pin *pin, struct dentry *dentry, aufs_bindex_t bindex, -+ unsigned int udba, unsigned char flags) ++static void au_ren_rev_dt(int err, struct au_ren_args *a) +{ -+ au_pin_init(pin, dentry, bindex, AuLsc_DI_PARENT, AuLsc_I_PARENT2, -+ udba, flags); -+ return au_do_pin(pin); ++ struct dentry *h_d; ++ struct inode *h_inode; ++ ++ au_dtime_revert(a->src_dt + AuPARENT); ++ if (!au_ftest_ren(a->auren_flags, ISSAMEDIR)) ++ au_dtime_revert(a->dst_dt + AuPARENT); ++ ++ 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 (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); ++ } ++ } +} + +/* ---------------------------------------------------------------------- */ + -+/* -+ * ->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 aufs_rename(struct inode *_src_dir, struct dentry *_src_dentry, ++ struct inode *_dst_dir, struct dentry *_dst_dentry, ++ unsigned int _flags) +{ -+ int err; -+ struct dentry *parent; ++ int err, lock_flags; ++ void *rev; ++ /* reduce stack space */ ++ struct au_ren_args *a; ++ struct au_pin pin; + -+ 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("%pd, %pd, 0x%x\n", _src_dentry, _dst_dentry, _flags); ++ IMustLock(_src_dir); ++ IMustLock(_dst_dir); ++ ++ err = -EINVAL; ++ if (unlikely(_flags & RENAME_WHITEOUT)) ++ 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; ++ 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); + } + -+ AuTraceErr(err); -+ return err; -+} ++ 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; + -+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 -+ }; ++ 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 (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); ++ /* ++ * 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; -+ a->btgt = err; -+ if (err != btop) -+ au_fset_icpup(a->flags, DID_CPUP); ++ goto out_parent; ++ a->br = au_sbr(a->dst_dentry->d_sb, a->btgt); ++ a->h_path.mnt = au_br_mnt(a->br); + -+ 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); ++ /* are they available to be renamed */ ++ err = au_ren_may_dir(a); ++ if (unlikely(err)) ++ goto out_children; ++ ++ /* 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; + } + -+ err = au_pin(&a->pin, dentry, a->btgt, a->udba, a->pin_flags); -+ if (unlikely(err)) -+ goto out_parent; -+ -+ sz = -1; -+ a->h_path.dentry = au_h_dptr(dentry, btop); -+ a->h_inode = d_inode(a->h_path.dentry); -+ if (ia && (ia->ia_valid & ATTR_SIZE)) { -+ inode_lock_nested(a->h_inode, AuLsc_I_CHILD); -+ if (ia->ia_size < i_size_read(a->h_inode)) -+ sz = ia->ia_size; -+ inode_unlock(a->h_inode); ++ 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); + -+ 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) { ++ /* 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 = dentry, ++ .dentry = a->src_dentry, + .bdst = a->btgt, -+ .bsrc = -1, -+ .len = sz, -+ .pin = &a->pin ++ .bsrc = a->src_btop, ++ .len = -1, ++ .pin = &pin, ++ .flags = AuCpup_DTIME | AuCpup_HOPEN + }; -+ 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? */ ++ 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 (parent) { -+ au_pin_set_parent_lflag(&a->pin, /*lflag*/0); -+ di_downgrade_lock(parent, AuLock_IR); -+ dput(parent); -+ parent = NULL; ++ /* 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); + } -+ if (!au_ftest_icpup(a->flags, DID_CPUP)) -+ goto out; /* success */ + -+ if (!d_unhashed(dentry)) { -+ struct au_cp_generic cpg = { -+ .dentry = dentry, -+ .bdst = a->btgt, -+ .bsrc = btop, -+ .len = sz, -+ .pin = &a->pin, -+ .flags = AuCpup_DTIME | AuCpup_HOPEN -+ }; -+ err = au_sio_cpup_simple(&cpg); -+ if (!err) -+ a->h_path.dentry = au_h_dptr(dentry, a->btgt); -+ } else if (!hi_wh) -+ a->h_path.dentry = au_h_dptr(dentry, a->btgt); -+ else -+ a->h_path.dentry = hi_wh; /* do not dget here */ ++ /* lock them all */ ++ err = au_ren_lock(a); ++ if (unlikely(err)) ++ /* leave the copied-up one */ ++ goto out_children; + -+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); ++ 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; + } -+out: -+ if (!err) -+ inode_lock_nested(a->h_inode, AuLsc_I_CHILD); -+ return err; -+} + -+static int aufs_setattr(struct dentry *dentry, struct iattr *ia) -+{ -+ int err; -+ struct inode *inode, *delegated; -+ struct super_block *sb; -+ struct file *file; -+ struct au_icpup_args *a; ++ /* store timestamps to be revertible */ ++ au_ren_dt(a); + -+ inode = d_inode(dentry); -+ IMustLock(inode); ++ /* 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; ++ } + -+ err = setattr_prepare(dentry, ia); ++ /* here we go */ ++ err = do_rename(a); + if (unlikely(err)) -+ goto out; -+ -+ err = -ENOMEM; -+ a = kzalloc(sizeof(*a), GFP_NOFS); -+ if (unlikely(!a)) -+ goto out; ++ goto out_dirren; + -+ if (ia->ia_valid & (ATTR_KILL_SUID | ATTR_KILL_SGID)) -+ ia->ia_valid &= ~ATTR_MODE; ++ if (au_ftest_ren(a->auren_flags, DIRREN)) ++ au_dr_rename_fin(a->src_dentry, a->btgt, rev); + -+ file = NULL; -+ sb = dentry->d_sb; -+ err = si_read_lock(sb, AuLock_FLUSH | AuLock_NOPLM); -+ if (unlikely(err)) -+ goto out_kfree; ++ /* update dir attributes */ ++ au_ren_refresh_dir(a); + -+ 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); -+ 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; -+ } -+ } ++ /* dput/iput all lower dentries */ ++ au_ren_refresh(a); + -+ 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; -+ } ++ goto out_hdir; /* success */ + -+ 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; ++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); + } -+ -+ if (ia->ia_valid & ATTR_SIZE) { -+ struct file *f; -+ -+ if (ia->ia_size < i_size_read(inode)) -+ /* unmap only */ -+ truncate_setsize(inode, ia->ia_size); -+ -+ f = NULL; -+ if (ia->ia_valid & ATTR_FILE) -+ f = ia->ia_file; -+ inode_unlock(a->h_inode); -+ err = vfsub_trunc(&a->h_path, ia->ia_size, ia->ia_valid, f); -+ inode_lock_nested(a->h_inode, AuLsc_I_CHILD); -+ } else { -+ delegated = NULL; -+ while (1) { -+ err = vfsub_notify_change(&a->h_path, ia, &delegated); -+ if (delegated) { -+ err = break_deleg_wait(&delegated); -+ if (!err) -+ continue; -+ } -+ break; ++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); + } -+ /* -+ * regardless aufs 'acl' option setting. -+ * why don't all acl-aware fs call this func from their ->setattr()? -+ */ -+ if (!err && (ia->ia_valid & ATTR_MODE)) -+ err = vfsub_acl_chmod(a->h_inode, ia->ia_mode); -+ if (!err) -+ au_cpup_attr_changeable(inode); -+ ++ 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: -+ 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_delayed_kfree(a); ++ 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); ++ kfree(a); +out: + AuTraceErr(err); + return err; +} +diff -urNp -x '*.orig' linux-4.9/fs/aufs/iinfo.c linux-4.9/fs/aufs/iinfo.c +--- linux-4.9/fs/aufs/iinfo.c 1970-01-01 01:00:00.000000000 +0100 ++++ linux-4.9/fs/aufs/iinfo.c 2021-02-24 16:15:09.528240413 +0100 +@@ -0,0 +1,285 @@ ++/* ++ * Copyright (C) 2005-2018 Junjiro R. Okajima ++ * ++ * This program, aufs is free software; you can redistribute it and/or modify ++ * it under the terms of the GNU General Public License as published by ++ * the Free Software Foundation; either version 2 of the License, or ++ * (at your option) any later version. ++ * ++ * This program is distributed in the hope that it will be useful, ++ * but WITHOUT ANY WARRANTY; without even the implied warranty of ++ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the ++ * GNU General Public License for more details. ++ * ++ * You should have received a copy of the GNU General Public License ++ * along with this program. If not, see . ++ */ + -+#if IS_ENABLED(CONFIG_AUFS_XATTR) || IS_ENABLED(CONFIG_FS_POSIX_ACL) -+static int au_h_path_to_set_attr(struct dentry *dentry, -+ struct au_icpup_args *a, struct path *h_path) -+{ -+ int err; -+ struct super_block *sb; -+ -+ sb = dentry->d_sb; -+ a->udba = au_opt_udba(sb); -+ /* no d_unlinked(), to set UDBA_NONE for root */ -+ if (d_unhashed(dentry)) -+ a->udba = AuOpt_UDBA_NONE; -+ if (a->udba != AuOpt_UDBA_NONE) { -+ AuDebugOn(IS_ROOT(dentry)); -+ err = au_reval_for_attr(dentry, au_sigen(sb)); -+ if (unlikely(err)) -+ goto out; -+ } -+ err = au_pin_and_icpup(dentry, /*ia*/NULL, a); -+ if (unlikely(err < 0)) -+ goto out; -+ -+ h_path->dentry = a->h_path.dentry; -+ h_path->mnt = au_sbr_mnt(sb, a->btgt); ++/* ++ * inode private data ++ */ + -+out: -+ return err; -+} ++#include "aufs.h" + -+ssize_t au_sxattr(struct dentry *dentry, struct inode *inode, -+ struct au_sxattr *arg) ++struct inode *au_h_iptr(struct inode *inode, aufs_bindex_t bindex) +{ -+ int err; -+ struct path h_path; -+ struct super_block *sb; -+ struct au_icpup_args *a; + struct inode *h_inode; ++ struct au_hinode *hinode; + -+ IMustLock(inode); -+ -+ err = -ENOMEM; -+ a = kzalloc(sizeof(*a), GFP_NOFS); -+ if (unlikely(!a)) -+ goto out; -+ -+ sb = dentry->d_sb; -+ err = si_read_lock(sb, AuLock_FLUSH | AuLock_NOPLM); -+ if (unlikely(err)) -+ goto out_kfree; -+ -+ h_path.dentry = NULL; /* silence gcc */ -+ di_write_lock_child(dentry); -+ err = au_h_path_to_set_attr(dentry, a, &h_path); -+ if (unlikely(err)) -+ goto out_di; -+ -+ inode_unlock(a->h_inode); -+ switch (arg->type) { -+ case AU_XATTR_SET: -+ AuDebugOn(d_is_negative(h_path.dentry)); -+ err = vfsub_setxattr(h_path.dentry, -+ arg->u.set.name, arg->u.set.value, -+ arg->u.set.size, arg->u.set.flags); -+ break; -+ case AU_ACL_SET: -+ err = -EOPNOTSUPP; -+ h_inode = d_inode(h_path.dentry); -+ if (h_inode->i_op->set_acl) -+ /* this will call posix_acl_update_mode */ -+ err = h_inode->i_op->set_acl(h_inode, -+ arg->u.acl_set.acl, -+ arg->u.acl_set.type); -+ break; -+ } -+ if (!err) -+ au_cpup_attr_timesizes(inode); -+ -+ au_unpin(&a->pin); -+ if (unlikely(err)) -+ au_update_dbtop(dentry); ++ IiMustAnyLock(inode); + -+out_di: -+ di_write_unlock(dentry); -+ si_read_unlock(sb); -+out_kfree: -+ au_delayed_kfree(a); -+out: -+ AuTraceErr(err); -+ return err; ++ 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; +} -+#endif + -+static void au_refresh_iattr(struct inode *inode, struct kstat *st, -+ unsigned int nlink) ++/* todo: hard/soft set? */ ++void au_hiput(struct au_hinode *hinode) +{ -+ unsigned int n; -+ -+ inode->i_mode = st->mode; -+ /* don't i_[ug]id_write() here */ -+ inode->i_uid = st->uid; -+ inode->i_gid = st->gid; -+ inode->i_atime = st->atime; -+ inode->i_mtime = st->mtime; -+ inode->i_ctime = st->ctime; ++ au_hn_free(hinode); ++ dput(hinode->hi_whdentry); ++ iput(hinode->hi_inode); ++} + -+ 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); -+ } ++unsigned int au_hi_flags(struct inode *inode, int isdir) ++{ ++ unsigned int flags; ++ const unsigned int mnt_flags = au_mntflags(inode->i_sb); + -+ spin_lock(&inode->i_lock); -+ inode->i_blocks = st->blocks; -+ i_size_write(inode, st->size); -+ spin_unlock(&inode->i_lock); ++ 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; +} + -+/* -+ * common routine for aufs_getattr() and au_getxattr(). -+ * returns zero or negative (an error). -+ * @dentry will be read-locked in success. -+ */ -+int au_h_path_getattr(struct dentry *dentry, int force, struct path *h_path) ++void au_set_h_iptr(struct inode *inode, aufs_bindex_t bindex, ++ struct inode *h_inode, unsigned int flags) +{ -+ int err; -+ unsigned int mnt_flags, sigen; -+ unsigned char udba_none; -+ aufs_bindex_t bindex; -+ struct super_block *sb, *h_sb; -+ struct inode *inode; ++ struct au_hinode *hinode; ++ struct inode *hi; ++ struct au_iinfo *iinfo = au_ii(inode); + -+ h_path->mnt = NULL; -+ h_path->dentry = NULL; ++ IiMustWriteLock(inode); + -+ err = 0; -+ sb = dentry->d_sb; -+ mnt_flags = au_mntflags(sb); -+ udba_none = !!au_opt_test(mnt_flags, UDBA_NONE); ++ hinode = au_hinode(iinfo, bindex); ++ hi = hinode->hi_inode; ++ AuDebugOn(h_inode && atomic_read(&h_inode->i_count) <= 0); + -+ /* 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; -+ } ++ 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; ++ ++ 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); + } -+ } else -+ di_read_lock_child(dentry, AuLock_IR); -+ -+ inode = d_inode(dentry); -+ bindex = au_ibtop(inode); -+ h_path->mnt = au_sbr_mnt(sb, bindex); -+ h_sb = h_path->mnt->mnt_sb; -+ if (!force -+ && !au_test_fs_bad_iattr(h_sb) -+ && udba_none) -+ goto out; /* success */ + -+ if (au_dbtop(dentry) == bindex) -+ h_path->dentry = au_h_dptr(dentry, bindex); -+ else if (au_opt_test(mnt_flags, PLINK) && au_plink_test(inode)) { -+ h_path->dentry = au_plink_lkup(inode, bindex); -+ if (IS_ERR(h_path->dentry)) -+ /* pretending success */ -+ h_path->dentry = NULL; -+ else -+ dput(h_path->dentry); ++ 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); ++ } + } -+ -+out: -+ return err; +} + -+static int aufs_getattr(struct vfsmount *mnt __maybe_unused, -+ struct dentry *dentry, struct kstat *st) ++void au_set_hi_wh(struct inode *inode, aufs_bindex_t bindex, ++ struct dentry *h_wh) +{ -+ int err; -+ unsigned char positive; -+ struct path h_path; -+ struct inode *inode; -+ struct super_block *sb; -+ -+ inode = d_inode(dentry); -+ sb = dentry->d_sb; -+ err = si_read_lock(sb, AuLock_FLUSH | AuLock_NOPLM); -+ if (unlikely(err)) -+ goto out; -+ err = au_h_path_getattr(dentry, /*force*/0, &h_path); -+ if (unlikely(err)) -+ goto out_si; -+ if (unlikely(!h_path.dentry)) -+ /* illegally overlapped or something */ -+ goto out_fill; /* pretending success */ ++ struct au_hinode *hinode; + -+ positive = d_is_positive(h_path.dentry); -+ if (positive) -+ err = vfs_getattr(&h_path, st); -+ 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; ++ IiMustWriteLock(inode); + -+out_fill: -+ generic_fillattr(inode, st); -+out_di: -+ di_read_unlock(dentry, AuLock_IR); -+out_si: -+ si_read_unlock(sb); -+out: -+ AuTraceErr(err); -+ return err; ++ hinode = au_hinode(au_ii(inode), bindex); ++ AuDebugOn(hinode->hi_whdentry); ++ hinode->hi_whdentry = h_wh; +} + -+/* ---------------------------------------------------------------------- */ -+ -+static const char *aufs_get_link(struct dentry *dentry, struct inode *inode, -+ struct delayed_call *done) ++void au_update_iigen(struct inode *inode, int half) +{ -+ const char *ret; -+ struct dentry *h_dentry; -+ struct inode *h_inode; -+ int err; -+ aufs_bindex_t bindex; ++ struct au_iinfo *iinfo; ++ struct au_iigen *iigen; ++ unsigned int sigen; + -+ ret = NULL; /* suppress a warning */ -+ err = -ECHILD; -+ if (!dentry) -+ goto out; ++ 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); ++} + -+ err = aufs_read_lock(dentry, AuLock_IR | AuLock_GEN); -+ if (unlikely(err)) -+ 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 = au_d_hashed_positive(dentry); -+ if (unlikely(err)) -+ goto out_unlock; ++ AuDebugOn(au_is_bad_inode(inode)); ++ IiMustWriteLock(inode); + -+ 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; ++ 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 = -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; ++ 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); + } + } -+ if (unlikely(!h_dentry)) -+ goto out_unlock; -+ -+ err = 0; -+ AuDbg("%pf\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; ++ 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); +} + +/* ---------------------------------------------------------------------- */ + -+static int au_is_special(struct inode *inode) ++void au_icntnr_init_once(void *_c) +{ -+ return (inode->i_mode & (S_IFBLK | S_IFCHR | S_IFIFO | S_IFSOCK)); ++ 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); +} + -+static int aufs_update_time(struct inode *inode, struct timespec *ts, int flags) ++void au_hinode_init(struct au_hinode *hinode) +{ -+ int err; -+ aufs_bindex_t bindex; ++ 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 inode *h_inode; -+ struct vfsmount *h_mnt; ++ struct au_hinode *hi; ++ int nbr, i; + + sb = inode->i_sb; -+ WARN_ONCE((flags & S_ATIME) && !IS_NOATIME(inode), -+ "unexpected s_flags 0x%lx", sb->s_flags); ++ 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_ninodes_inc(sb); + -+ /* mmap_sem might be acquired already, cf. aufs_mmap() */ -+ lockdep_off(); -+ si_read_lock(sb, AuLock_FLUSH); -+ ii_write_lock_child(inode); -+ lockdep_on(); ++ iinfo->ii_hinode = hi; ++ for (i = 0; i < nbr; i++, hi++) ++ au_hinode_init(hi); + -+ err = 0; -+ bindex = au_ibtop(inode); -+ h_inode = au_h_iptr(inode, bindex); -+ if (!au_test_ro(sb, bindex, inode)) { -+ h_mnt = au_sbr_mnt(sb, bindex); -+ err = vfsub_mnt_want_write(h_mnt); -+ if (!err) { -+ err = vfsub_update_time(h_inode, ts, flags); -+ vfsub_mnt_drop_write(h_mnt); -+ } -+ } else if (au_is_special(h_inode)) { -+ /* -+ * Never copy-up here. -+ * These special files may already be opened and used for -+ * communicating. If we copied it up, then the communication -+ * would be corrupted. -+ */ -+ AuWarn1("timestamps for i%lu are ignored " -+ "since it is on readonly branch (hi%lu).\n", -+ inode->i_ino, h_inode->i_ino); -+ } else if (flags & ~S_ATIME) { -+ err = -EIO; -+ AuIOErr1("unexpected flags 0x%x\n", flags); -+ AuDebugOn(1); ++ iinfo->ii_generation.ig_generation = au_sigen(sb); ++ iinfo->ii_btop = -1; ++ iinfo->ii_bbot = -1; ++ iinfo->ii_vdir = NULL; ++ return 0; + } -+ -+ lockdep_off(); -+ 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; ++ return -ENOMEM; +} + -+/* ---------------------------------------------------------------------- */ -+ -+/* no getattr version will be set by module.c:aufs_init() */ -+struct inode_operations aufs_iop_nogetattr[AuIop_Last], -+ aufs_iop[] = { -+ [AuIop_SYMLINK] = { -+ .permission = aufs_permission, -+#ifdef CONFIG_FS_POSIX_ACL -+ .get_acl = aufs_get_acl, -+ .set_acl = aufs_set_acl, /* unsupport for symlink? */ -+#endif -+ -+ .setattr = aufs_setattr, -+ .getattr = aufs_getattr, -+ -+#ifdef CONFIG_AUFS_XATTR -+ .listxattr = aufs_listxattr, -+#endif -+ -+ .readlink = generic_readlink, -+ .get_link = aufs_get_link, ++int au_hinode_realloc(struct au_iinfo *iinfo, int nbr, int may_shrink) ++{ ++ int err, i; ++ struct au_hinode *hip; + -+ /* .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, ++ AuRwMustWriteLock(&iinfo->ii_rwsem); + -+ .permission = aufs_permission, -+#ifdef CONFIG_FS_POSIX_ACL -+ .get_acl = aufs_get_acl, -+ .set_acl = aufs_set_acl, -+#endif ++ 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; ++ } + -+ .setattr = aufs_setattr, -+ .getattr = aufs_getattr, ++ return err; ++} + -+#ifdef CONFIG_AUFS_XATTR -+ .listxattr = aufs_listxattr, -+#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; + -+ .update_time = aufs_update_time, -+ .atomic_open = aufs_atomic_open, -+ .tmpfile = aufs_tmpfile -+ }, -+ [AuIop_OTHER] = { -+ .permission = aufs_permission, -+#ifdef CONFIG_FS_POSIX_ACL -+ .get_acl = aufs_get_acl, -+ .set_acl = aufs_set_acl, -+#endif ++ AuDebugOn(au_is_bad_inode(inode)); + -+ .setattr = aufs_setattr, -+ .getattr = aufs_getattr, ++ sb = inode->i_sb; ++ au_ninodes_dec(sb); ++ 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(); ++ } + -+#ifdef CONFIG_AUFS_XATTR -+ .listxattr = aufs_listxattr, -+#endif ++ iinfo = au_ii(inode); ++ if (iinfo->ii_vdir) ++ au_vdir_free(iinfo->ii_vdir); + -+ .update_time = aufs_update_time ++ 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++; ++ } + } -+}; -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 2016-10-09 16:55:36.492701639 +0200 -@@ -0,0 +1,511 @@ ++ kfree(iinfo->ii_hinode); ++ AuRwDestroy(&iinfo->ii_rwsem); ++} +diff -urNp -x '*.orig' linux-4.9/fs/aufs/inode.c linux-4.9/fs/aufs/inode.c +--- linux-4.9/fs/aufs/inode.c 1970-01-01 01:00:00.000000000 +0100 ++++ linux-4.9/fs/aufs/inode.c 2021-02-24 16:15:09.528240413 +0100 +@@ -0,0 +1,527 @@ +/* -+ * Copyright (C) 2005-2016 Junjiro R. Okajima ++ * Copyright (C) 2005-2018 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by @@ -19909,505 +21552,521 @@ diff -urN /usr/share/empty/fs/aufs/i_op_del.c linux/fs/aufs/i_op_del.c + */ + +/* -+ * inode operations (del entry) ++ * inode functions + */ + +#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) ++struct inode *au_igrab(struct inode *inode) +{ -+ 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; -+ } -+ } else -+ AuDebugOn(btop < *bcpup -+ || au_test_ro(sb, *bcpup, d_inode(dentry))); -+ AuDbg("bcpup %d, btop %d\n", *bcpup, btop); -+ -+ 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); -+ } ++ if (inode) { ++ AuDebugOn(!atomic_read(&inode->i_count)); ++ ihold(inode); + } -+ AuDbg("need_wh %d\n", need_wh); -+ err = need_wh; -+ -+out: -+ return err; ++ return inode; +} + -+/* -+ * 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) ++static void au_refresh_hinode_attr(struct inode *inode, int do_version) +{ -+ int err; -+ umode_t h_mode; -+ struct dentry *h_dentry, *h_latest; -+ struct inode *h_inode; ++ au_cpup_attr_all(inode, /*force*/0); ++ au_update_iigen(inode, /*half*/1); ++ if (do_version) ++ inode->i_version++; ++} + -+ 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; ++static int au_ii_refresh(struct inode *inode, int *update) ++{ ++ 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; + -+ 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; -+ } ++ AuDebugOn(au_is_bad_inode(inode)); ++ IiMustWriteLock(inode); + -+ err = -ENOENT; -+ /* expected parent dir is locked */ -+ if (unlikely(h_parent != h_dentry->d_parent)) ++ *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; -+ err = 0; + -+ /* -+ * rmdir a dir may break the consistency on some filesystem. -+ * let's try heavy test. -+ */ -+ err = -EACCES; -+ if (unlikely(!au_opt_test(au_mntflags(dentry->d_sb), DIRPERM1) -+ && au_test_h_perm(d_inode(h_parent), -+ MAY_EXEC | MAY_WRITE))) -+ 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; ++ } + -+ h_latest = au_sio_lkup_one(&dentry->d_name, h_parent); -+ err = -EIO; -+ if (IS_ERR(h_latest)) -+ goto out; -+ if (h_latest == h_dentry) -+ err = 0; -+ dput(h_latest); ++ 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; +} + -+/* -+ * decide the branch where we operate for @dentry. the branch index will be set -+ * @rbcpup. after diciding 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) ++void au_refresh_iop(struct inode *inode, int force_getattr) +{ -+ struct dentry *wh_dentry; -+ struct super_block *sb; -+ struct path h_path; -+ int err, need_wh; -+ unsigned int udba; -+ aufs_bindex_t bcpup; -+ -+ need_wh = au_wr_dir_need_wh(dentry, isdir, rbcpup); -+ wh_dentry = ERR_PTR(need_wh); -+ if (unlikely(need_wh < 0)) -+ goto out; ++ int type; ++ struct au_sbinfo *sbi = au_sbi(inode->i_sb); ++ const struct inode_operations *iop ++ = force_getattr ? aufs_iop : sbi->si_iop_array; + -+ 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; ++ if (inode->i_op == iop) ++ return; + -+ 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; ++ 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_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 */ ++ inode->i_op = iop + type; ++ /* unnecessary smp_wmb() */ ++} + -+ wh_dentry = au_wh_create(dentry, bcpup, h_path.dentry); -+ if (IS_ERR(wh_dentry)) -+ goto out_unpin; ++int au_refresh_hinode_self(struct inode *inode) ++{ ++ int err, update; + -+ /* returns with the parent is locked and wh_dentry is dget-ed */ -+ goto out; /* success */ ++ err = au_ii_refresh(inode, &update); ++ if (!err) ++ au_refresh_hinode_attr(inode, update && S_ISDIR(inode->i_mode)); + -+out_unpin: -+ au_unpin(pin); -+out: -+ return wh_dentry; ++ AuTraceErr(err); ++ 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) ++int au_refresh_hinode(struct inode *inode, struct dentry *dentry) +{ -+ int rmdir_later, err, dirwh; -+ struct dentry *h_dentry; -+ struct super_block *sb; -+ struct inode *inode; ++ 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; + -+ sb = dentry->d_sb; -+ SiMustAnyLock(sb); -+ h_dentry = au_h_dptr(dentry, bindex); -+ err = au_whtmp_ren(h_dentry, au_sbr(sb, bindex)); ++ err = au_ii_refresh(inode, &update); + if (unlikely(err)) + goto out; + -+ /* stop monitoring */ -+ inode = d_inode(dentry); -+ au_hn_free(au_hi(inode, bindex)); ++ 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; + -+ 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; -+ } ++ h_d = au_h_dptr(dentry, bindex); ++ if (!h_d || d_is_negative(h_d)) ++ continue; + -+ 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; ++ 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); + +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) ++static int set_inode(struct inode *inode, struct dentry *dentry) +{ -+ struct inode *inode; -+ -+ inode = d_inode(dentry); -+ d_drop(dentry); -+ inode->i_ctime = dir->i_ctime; ++ int err; ++ 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; ++ struct inode_operations *iop; + -+ au_dir_ts(dir, bindex); -+ dir->i_version++; -+} ++ IiMustWriteLock(inode); + -+/* -+ * 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) -+ }; ++ 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; ++ goto out; ++ } + -+ 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; ++ /* 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_acl() every time, ++ * do not call cache_no_acl() for aufs inode. ++ */ + -+ AuIOErr("%pd reverting whiteout failed(%d, %d)\n", dentry, err, rerr); -+ return -EIO; ++out: ++ return err; +} + -+/* ---------------------------------------------------------------------- */ -+ -+int aufs_unlink(struct inode *dir, struct dentry *dentry) ++/* ++ * successful returns with iinfo write_locked ++ * minus: errno ++ * zero: success, matched ++ * plus: no error, but unmatched ++ */ ++static int reval_inode(struct inode *inode, struct dentry *dentry) +{ + int err; -+ aufs_bindex_t bwh, bindex, btop; -+ struct inode *inode, *h_dir, *delegated; -+ struct dentry *parent, *wh_dentry; -+ /* to reuduce stack size */ -+ struct { -+ struct au_dtime dt; -+ struct au_pin pin; -+ struct path h_path; -+ } *a; -+ -+ IMustLock(dir); ++ unsigned int gen, igflags; ++ aufs_bindex_t bindex, bbot; ++ struct inode *h_inode, *h_dinode; ++ struct dentry *h_dentry; + -+ err = -ENOMEM; -+ a = kmalloc(sizeof(*a), GFP_NOFS); -+ if (unlikely(!a)) ++ /* ++ * 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; + -+ err = aufs_read_lock(dentry, AuLock_DW | AuLock_GEN); -+ if (unlikely(err)) -+ 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? */ -+ -+ 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; ++ 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; + -+ 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; ++ gen = au_iigen(inode, &igflags); ++ if (gen == au_digen(dentry) ++ && !au_ig_ftest(igflags, HALF_REFRESHED)) ++ break; ++ ++ /* fully refresh inode using dentry */ ++ err = au_refresh_hinode(inode, dentry); ++ if (!err) ++ au_update_iigen(inode, /*half*/0); ++ break; + } + -+ if (!err) { -+ vfsub_drop_nlink(inode); -+ epilog(dir, dentry, bindex); ++ if (unlikely(err)) ++ ii_write_unlock(inode); ++out: ++ return err; ++} + -+ /* update target timestamps */ -+ if (bindex == btop) { -+ vfsub_update_h_iattr(&a->h_path, /*did*/NULL); -+ /*ignore*/ -+ inode->i_ctime = d_inode(a->h_path.dentry)->i_ctime; -+ } else -+ /* todo: this timestamp may be reverted later */ -+ inode->i_ctime = h_dir->i_ctime; -+ goto out_unpin; /* success */ ++int au_ino(struct super_block *sb, aufs_bindex_t bindex, ino_t h_ino, ++ unsigned int d_type, ino_t *ino) ++{ ++ int err, idx; ++ const int isnondir = d_type != DT_DIR; ++ ++ /* prevent hardlinked inode number from race condition */ ++ if (isnondir) { ++ err = au_xinondir_enter(sb, bindex, h_ino, &idx); ++ if (unlikely(err)) ++ goto out; + } + -+ /* revert */ -+ if (wh_dentry) { -+ int rerr; ++ err = au_xino_read(sb, bindex, h_ino, ino); ++ if (unlikely(err)) ++ goto out_xinondir; + -+ rerr = do_revert(err, dir, bindex, bwh, wh_dentry, dentry, -+ &a->dt); -+ if (rerr) -+ err = rerr; ++ 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_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_delayed_kfree(a); ++out_xinondir: ++ if (isnondir && idx >= 0) ++ au_xinondir_leave(sb, bindex, h_ino, idx); +out: + return err; +} + -+int aufs_rmdir(struct inode *dir, struct dentry *dentry) ++/* successful returns with iinfo write_locked */ ++/* todo: return with unlocked? */ ++struct inode *au_new_inode(struct dentry *dentry, int must_new) +{ -+ 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 reuduce stack size */ -+ struct { -+ struct au_dtime dt; -+ struct au_pin pin; -+ } *a; ++ 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; + -+ IMustLock(dir); ++ 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; + -+ err = -ENOMEM; -+ a = kmalloc(sizeof(*a), GFP_NOFS); -+ if (unlikely(!a)) -+ goto out; ++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 = aufs_read_lock(dentry, AuLock_DW | AuLock_FLUSH | AuLock_GEN); -+ if (unlikely(err)) -+ goto out_free; -+ err = au_alive_dir(dentry); ++ err = au_xino_read(sb, btop, h_ino, &ino); ++ inode = ERR_PTR(err); + 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; ++ 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; ++ if (!ino) { ++ ino = au_xino_new_ino(sb); ++ if (unlikely(!ino)) { ++ inode = ERR_PTR(-EIO); ++ goto out_xinondir; ++ } ++ } + -+ 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; ++ AuDbg("i%lu\n", (unsigned long)ino); ++ inode = au_iget_locked(sb, ino); ++ err = PTR_ERR(inode); ++ if (IS_ERR(inode)) ++ goto out_xinondir; + -+ 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; ++ 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 */ + } -+ } else { -+ /* stop monitoring */ -+ au_hn_free(au_hi(inode, btop)); + -+ /* dir inode is locked */ -+ IMustLock(d_inode(wh_dentry->d_parent)); -+ err = 0; ++ /* ++ * 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) { -+ vfsub_dead_dir(inode); -+ au_set_dbdiropq(dentry, -1); -+ epilog(dir, dentry, bindex); ++ iput(inode); ++ if (hlinked && idx >= 0) ++ au_xinondir_leave(sb, btop, h_ino, idx); ++ goto new_ino; ++ } + -+ if (rmdir_later) { -+ au_whtmp_kick_rmdir(dir, btop, h_dentry, args); -+ args = NULL; -+ } ++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; ++} + -+ goto out_unpin; /* success */ -+ } ++/* ---------------------------------------------------------------------- */ + -+ /* revert */ -+ AuLabel(revert); -+ if (wh_dentry) { -+ int rerr; ++int au_test_ro(struct super_block *sb, aufs_bindex_t bindex, ++ struct inode *inode) ++{ ++ int err; ++ struct inode *hi; + -+ rerr = do_revert(err, dir, bindex, bwh, wh_dentry, dentry, -+ &a->dt); -+ if (rerr) -+ err = rerr; ++ 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; + } + -+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_delayed_kfree(a); -+out: -+ AuTraceErr(err); + return err; +} -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 2016-12-17 12:28:17.595211562 +0100 -@@ -0,0 +1,1165 @@ ++ ++int au_test_h_perm(struct inode *h_inode, int mask) ++{ ++ if (uid_eq(current_fsuid(), GLOBAL_ROOT_UID)) ++ return 0; ++ return inode_permission(h_inode, mask); ++} ++ ++int au_test_h_perm_sio(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_inode, mask); ++} +diff -urNp -x '*.orig' linux-4.9/fs/aufs/inode.h linux-4.9/fs/aufs/inode.h +--- linux-4.9/fs/aufs/inode.h 1970-01-01 01:00:00.000000000 +0100 ++++ linux-4.9/fs/aufs/inode.h 2021-02-24 16:15:09.528240413 +0100 +@@ -0,0 +1,696 @@ +/* -+ * Copyright (C) 2005-2016 Junjiro R. Okajima ++ * Copyright (C) 2005-2018 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by @@ -20424,1348 +22083,913 @@ diff -urN /usr/share/empty/fs/aufs/i_op_ren.c linux/fs/aufs/i_op_ren.c + */ + +/* -+ * inode operation (rename entry) -+ * todo: this is crazy monster ++ * inode operations + */ + -+#include "aufs.h" -+ -+enum { AuSRC, AuDST, AuSrcDst }; -+enum { AuPARENT, AuCHILD, AuParentChild }; -+ -+#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 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) ++#ifndef __AUFS_INODE_H__ ++#define __AUFS_INODE_H__ + -+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]; ++#ifdef __KERNEL__ + -+#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 ++#include ++#include "rwsem.h" + -+#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 vfsmount; + -+ struct dentry *h_trap; -+ struct au_branch *br; -+ struct path h_path; -+ struct au_nhash whlist; -+ aufs_bindex_t btgt, src_bwh; ++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 */ ++#endif ++} ____cacheline_aligned_in_smp; + -+ struct { -+ unsigned short auren_flags; -+ unsigned char flags; /* syscall parameter */ -+ unsigned char exchange; -+ } __packed; ++struct au_hinode { ++ struct inode *hi_inode; ++ aufs_bindex_t hi_id; ++#ifdef CONFIG_AUFS_HNOTIFY ++ struct au_hnotify *hi_notify; ++#endif + -+ struct au_whtmp_rmdir *thargs; -+ struct dentry *h_dst; ++ /* reference to the copied-up whiteout with get/put */ ++ struct dentry *hi_whdentry; +}; + -+/* ---------------------------------------------------------------------- */ -+ -+/* -+ * 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. -+ */ -+ -+#define RevertFailure(fmt, ...) do { \ -+ AuIOErr("revert failure: " fmt " (%d, %d)\n", \ -+ ##__VA_ARGS__, err, rerr); \ -+ err = -EIO; \ -+} while (0) -+ -+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 -+ -+ 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); -+ -+#undef src_or_dst_ -+} -+ -+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) -+{ -+ int rerr; -+ struct inode *delegated; -+ -+ a->h_path.dentry = vfsub_lkup_one(&a->src_dentry->d_name, -+ a->src_h_parent); -+ rerr = PTR_ERR(a->h_path.dentry); -+ if (IS_ERR(a->h_path.dentry)) { -+ RevertFailure("lkup one %pd", a->src_dentry); -+ return; -+ } -+ -+ 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; -+ -+ a->h_path.dentry = vfsub_lkup_one(&a->dst_dentry->d_name, -+ a->dst_h_parent); -+ 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) -+{ -+ 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 -+ -+/* ---------------------------------------------------------------------- */ -+ -+/* -+ * 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) -+{ -+ int err; -+ struct dentry *d; -+ struct inode *delegated; -+ -+ 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(); -+ -+ if (!err && a->h_dst) -+ /* it will be set to dinfo later */ -+ dget(a->h_dst); -+ -+ return err; -+} -+ -+/* cf. aufs_rmdir() */ -+static int au_ren_del_whtmp(struct au_ren_args *a) -+{ -+ int err; -+ struct inode *dir; ++/* 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) + -+ 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_iigen { ++ spinlock_t ig_spin; ++ __u32 ig_generation, ig_flags; ++}; + -+ return 0; -+} ++struct au_vdir; ++struct au_iinfo { ++ struct au_iigen ii_generation; ++ struct super_block *ii_hsb1; /* no get/put */ + -+/* 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 ++ 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; ++}; + -+ 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); ++struct au_icntnr { ++ struct au_iinfo iinfo; ++ struct inode vfs_inode; ++ struct hlist_bl_node plink; ++} ____cacheline_aligned_in_smp; + -+#undef src_or_dst_ -+ return err; -+} ++/* 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) + -+static int au_ren_diropq(struct au_ren_args *a) -+{ -+ int err; -+ unsigned char always; -+ struct dentry *d; ++struct au_pin { ++ /* input */ ++ struct dentry *dentry; ++ unsigned int udba; ++ unsigned char lsc_di, lsc_hi, flags; ++ aufs_bindex_t bindex; + -+ 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) -+ && 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 */ ++ /* output */ ++ struct dentry *parent; ++ struct au_hinode *hdir; ++ struct vfsmount *h_mnt; + -+ 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 */ ++ /* temporary unlock/relock for copyup */ ++ struct dentry *h_dentry, *h_parent; ++ struct au_branch *br; ++ struct task_struct *task; ++}; + -+out_rev_src: -+ AuDbg("err %d, reverting src\n", err); -+ au_ren_rev_diropq(err, a); -+out: -+ 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); ++ ++/* ---------------------------------------------------------------------- */ ++ ++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); +} + -+static int do_rename(struct au_ren_args *a) ++/* ---------------------------------------------------------------------- */ ++ ++/* 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 inode *h_inode, int mask); ++int au_test_h_perm_sio(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) +{ -+ int err; -+ struct dentry *d, *h_d; ++#ifdef CONFIG_AUFS_SHWH ++ return au_ino(sb, bindex, h_ino, d_type, ino); ++#else ++ return 0; ++#endif ++} + -+ if (!a->exchange) { -+ /* prepare workqueue args for asynchronous rmdir */ -+ h_d = a->dst_h_dentry; -+ if (au_ftest_ren(a->auren_flags, ISDIR_DST) -+ && 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); -+ } ++/* i_op.c */ ++enum { ++ AuIop_SYMLINK, ++ AuIop_DIR, ++ AuIop_OTHER, ++ AuIop_Last ++}; ++extern struct inode_operations aufs_iop[AuIop_Last], ++ aufs_iop_nogetattr[AuIop_Last]; + -+ /* 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; -+ } ++/* 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) + -+ /* 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; -+ } ++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); + -+ /* rename dentry to tmpwh */ -+ if (a->thargs) { -+ err = au_whtmp_ren(a->dst_h_dentry, a->br); -+ if (unlikely(err)) -+ goto out_whdst; ++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); + -+ 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); -+ } -+ } ++#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) + -+ BUG_ON(d_is_positive(a->dst_h_dentry) && a->src_btop != a->btgt); ++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; ++}; + -+ /* rename by vfs_rename or cpup */ -+ err = au_ren_or_cpup(a); -+ if (unlikely(err)) -+ /* leave the copied-up one */ -+ goto out_whtmp; ++int au_pin_and_icpup(struct dentry *dentry, struct iattr *ia, ++ struct au_icpup_args *a); + -+ /* make dir opaque */ -+ err = au_ren_diropq(a); -+ if (unlikely(err)) -+ goto out_rename; ++int au_h_path_getattr(struct dentry *dentry, int force, struct path *h_path, ++ int locked); + -+ /* 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*/ -+ a->dst_inode->i_ctime = d_inode(a->h_path.dentry)->i_ctime; -+ } -+ 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*/ -+ a->src_inode->i_ctime = d_inode(a->h_path.dentry)->i_ctime; ++/* 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 inode *dir, struct dentry *dentry, umode_t mode, ++ dev_t dev); ++int aufs_symlink(struct inode *dir, struct dentry *dentry, const char *symname); ++int aufs_create(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 inode *dir, struct dentry *dentry, umode_t mode); ++int aufs_link(struct dentry *src_dentry, struct inode *dir, ++ struct dentry *dentry); ++int aufs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode); + -+ 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; -+ } ++/* 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); + -+ /* remove whtmp */ -+ if (a->thargs) -+ au_ren_del_whtmp(a); /* ignore this error */ ++/* i_op_ren.c */ ++int au_wbr(struct dentry *dentry, aufs_bindex_t btgt); ++int aufs_rename(struct inode *src_dir, struct dentry *src_dentry, ++ struct inode *dir, struct dentry *dentry, ++ unsigned int flags); + -+ au_fhsm_wrote(a->src_dentry->d_sb, a->btgt, /*force*/0); -+ } -+ err = 0; -+ 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); + -+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; -+} ++/* 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) + -+/* ---------------------------------------------------------------------- */ ++#ifndef CONFIG_AUFS_HNOTIFY ++#undef AuHi_HNOTIFY ++#define AuHi_HNOTIFY 0 ++#endif + -+/* -+ * 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); -+} ++void au_set_h_iptr(struct inode *inode, aufs_bindex_t bindex, ++ struct inode *h_inode, unsigned int flags); + -+/* -+ * test if @dentry dir can be rename source or not. -+ * if it can, return 0 and @children is filled. -+ * success means, -+ * - it is a logically empty dir. -+ * - or, it exists on writable branch and has no children including whiteouts -+ * on the lower branch. -+ */ -+static int may_rename_srcdir(struct dentry *dentry, aufs_bindex_t btgt) -+{ -+ int err; -+ unsigned int rdhash; -+ aufs_bindex_t btop; ++void au_update_iigen(struct inode *inode, int half); ++void au_update_ibrange(struct inode *inode, int do_put_zero); + -+ btop = au_dbtop(dentry); -+ if (btop != btgt) { -+ struct au_nhash whlist; ++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); + -+ 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; -+ err = au_test_empty(dentry, &whlist); -+ au_nhash_wh_free(&whlist); -+ goto out; -+ } ++#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 */ + -+ if (btop == au_dbtaildir(dentry)) -+ return 0; /* success */ ++#ifdef CONFIG_AUFS_XATTR ++/* xattr.c */ ++int au_cpup_xattr(struct dentry *h_dst, struct dentry *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 dentry *h_dst, struct dentry *h_src, ++ int ignore_flags, unsigned int verbose); ++AuStubVoid(au_xattr_init, struct super_block *sb); ++#endif + -+ err = au_test_empty_lower(dentry); ++#ifdef CONFIG_FS_POSIX_ACL ++struct posix_acl *aufs_get_acl(struct inode *inode, int type); ++int aufs_set_acl(struct inode *inode, struct posix_acl *acl, int type); ++#endif + -+out: -+ if (err == -ENOTEMPTY) { -+ AuWarn1("renaming dir who has child(ren) on multiple branches," -+ " is not supported\n"); -+ err = -EXDEV; -+ } -+ return err; -+} ++#if IS_ENABLED(CONFIG_AUFS_XATTR) || IS_ENABLED(CONFIG_FS_POSIX_ACL) ++enum { ++ AU_XATTR_SET, ++ AU_ACL_SET ++}; + -+/* side effect: sets whlist and h_dentry */ -+static int au_ren_may_dir(struct au_ren_args *a) -+{ -+ int err; -+ unsigned int rdhash; -+ struct dentry *d; ++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 + -+ 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; ++/* 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) { -+ 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(d, a->btgt); -+ } -+ a->dst_h_dentry = au_h_dptr(d, au_dbtop(d)); -+ if (unlikely(err)) -+ goto out; ++/* ++ * 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); \ ++} + -+ 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(d, a->btgt); -+ if (unlikely(err)) { -+ au_nhash_wh_free(&a->whlist); -+ a->whlist.nh_num = 0; -+ } -+ } -+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); \ +} + -+/* ---------------------------------------------------------------------- */ ++#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); ++AuRWLockFuncs(new_child, NEW_CHILD); ++ ++#undef AuReadLockFunc ++#undef AuWriteLockFunc ++#undef AuRWLockFuncs + +/* -+ * simple tests for rename. -+ * following the checks in vfs, plus the parent-child relationship. ++ * ii_read_unlock, ii_write_unlock, ii_downgrade_lock + */ -+static int au_may_ren(struct au_ren_args *a) -+{ -+ int err, isdir; -+ struct inode *h_inode; ++AuSimpleUnlockRwsemFuncs(ii, struct inode *i, &au_ii(i)->ii_rwsem); + -+ 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; -+ } ++#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) + -+ err = 0; -+ if (a->dst_btop != a->btgt) -+ goto out; ++/* ---------------------------------------------------------------------- */ + -+ err = -ENOTEMPTY; -+ if (unlikely(a->dst_h_dentry == a->h_trap)) -+ goto out; ++static inline void au_icntnr_init(struct au_icntnr *c) ++{ ++#ifdef CONFIG_AUFS_DEBUG ++ c->vfs_inode.i_mode = 0; ++#endif ++} + -+ 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); -+ } ++static inline unsigned int au_iigen(struct inode *inode, unsigned int *igflags) ++{ ++ unsigned int gen; ++ struct au_iinfo *iinfo; ++ struct au_iigen *iigen; + -+out: -+ if (unlikely(err == -ENOENT || err == -EEXIST)) -+ err = -EIO; -+ AuTraceErr(err); -+ return err; ++ 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); ++ ++ return gen; +} + -+/* ---------------------------------------------------------------------- */ ++/* 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; + -+/* -+ * locking order -+ * (VFS) -+ * - src_dir and dir by lock_rename() -+ * - inode if exitsts -+ * (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) ++ iinfo = au_ii(inode); ++ AuRwMustAnyLock(&iinfo->ii_rwsem); ++ return !(iinfo->ii_hsb1 == h_inode->i_sb ++ && iinfo->ii_higen == h_inode->i_generation); ++} ++ ++static inline void au_iigen_dec(struct inode *inode) +{ -+ vfsub_unlock_rename(a->src_h_parent, a->src_hdir, -+ a->dst_h_parent, a->dst_hdir); -+ if (au_ftest_ren(a->auren_flags, MNT_WRITE)) -+ vfsub_mnt_drop_write(au_br_mnt(a->br)); ++ 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); +} + -+static int au_ren_lock(struct au_ren_args *a) ++static inline int au_iigen_test(struct inode *inode, unsigned int sigen) +{ + int err; -+ unsigned int udba; + + 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); -+ 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); ++ if (unlikely(inode && au_iigen(inode, NULL) != sigen)) ++ err = -EIO; + -+out: + return err; +} + +/* ---------------------------------------------------------------------- */ + -+static void au_ren_refresh_dir(struct au_ren_args *a) ++static inline struct au_hinode *au_hinode(struct au_iinfo *iinfo, ++ aufs_bindex_t bindex) +{ -+ struct inode *dir; ++ return iinfo->ii_hinode + bindex; ++} + -+ dir = a->dst_dir; -+ dir->i_version++; -+ 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); ++static inline int au_is_bad_inode(struct inode *inode) ++{ ++ return !!(is_bad_inode(inode) || !au_hinode(au_ii(inode), 0)); ++} + -+ if (a->exchange) { -+ dir = a->src_dir; -+ dir->i_version++; -+ 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); -+ } ++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; ++} + -+ if (au_ftest_ren(a->auren_flags, ISSAMEDIR)) -+ return; ++static inline aufs_bindex_t au_ibtop(struct inode *inode) ++{ ++ IiMustAnyLock(inode); ++ return au_ii(inode)->ii_btop; ++} + -+ dir = a->src_dir; -+ dir->i_version++; -+ if (au_ftest_ren(a->auren_flags, ISDIR_SRC)) -+ au_cpup_attr_nlink(dir, /*force*/1); -+ au_dir_ts(dir, a->btgt); ++static inline aufs_bindex_t au_ibbot(struct inode *inode) ++{ ++ IiMustAnyLock(inode); ++ return au_ii(inode)->ii_bbot; +} + -+static void au_ren_refresh(struct au_ren_args *a) ++static inline struct au_vdir *au_ivdir(struct inode *inode) +{ -+ aufs_bindex_t bbot, bindex; -+ struct dentry *d, *h_d; -+ struct inode *i, *h_i; -+ struct super_block *sb; ++ IiMustAnyLock(inode); ++ return au_ii(inode)->ii_vdir; ++} + -+ 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); ++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; ++} + -+ 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); -+ } ++static inline void au_set_ibtop(struct inode *inode, aufs_bindex_t bindex) ++{ ++ IiMustWriteLock(inode); ++ au_ii(inode)->ii_btop = bindex; ++} + -+ d = a->src_dentry; -+ if (!a->exchange) { -+ 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); ++static inline void au_set_ibbot(struct inode *inode, aufs_bindex_t bindex) ++{ ++ IiMustWriteLock(inode); ++ au_ii(inode)->ii_bbot = bindex; ++} + -+ sb = d->d_sb; -+ i = a->src_inode; -+ if (au_opt_test(au_mntflags(sb), PLINK) && au_plink_test(i)) -+ return; /* success */ ++static inline void au_set_ivdir(struct inode *inode, struct au_vdir *vdir) ++{ ++ IiMustWriteLock(inode); ++ au_ii(inode)->ii_vdir = vdir; ++} + -+ 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); -+ } -+ d_drop(a->src_dentry); ++static inline struct au_hinode *au_hi(struct inode *inode, aufs_bindex_t bindex) ++{ ++ IiMustAnyLock(inode); ++ return au_hinode(au_ii(inode), bindex); +} + +/* ---------------------------------------------------------------------- */ + -+/* mainly for link(2) and rename(2) */ -+int au_wbr(struct dentry *dentry, aufs_bindex_t btgt) ++static inline struct dentry *au_pinned_parent(struct au_pin *pin) +{ -+ aufs_bindex_t bdiropq, bwh; -+ 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; -+ -+ AuDbg("btgt %d\n", btgt); -+ return btgt; ++ if (pin) ++ return pin->parent; ++ return NULL; +} + -+/* sets src_btop, dst_btop and btgt */ -+static int au_ren_wbr(struct au_ren_args *a) ++static inline struct inode *au_pinned_h_dir(struct au_pin *pin) +{ -+ int err; -+ struct au_wr_dir_args wr_dir_args = { -+ /* .force_btgt = -1, */ -+ .flags = AuWrDir_ADD_ENTRY -+ }; ++ if (pin && pin->hdir) ++ return pin->hdir->hi_inode; ++ return NULL; ++} + -+ 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 struct au_hinode *au_pinned_hdir(struct au_pin *pin) ++{ ++ if (pin) ++ return pin->hdir; ++ return NULL; ++} + -+ return err; ++static inline void au_pin_set_dentry(struct au_pin *pin, struct dentry *dentry) ++{ ++ if (pin) ++ pin->dentry = dentry; +} + -+static void au_ren_dt(struct au_ren_args *a) ++static inline void au_pin_set_parent_lflag(struct au_pin *pin, ++ unsigned char lflag) +{ -+ 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); ++ if (pin) { ++ if (lflag) ++ au_fset_pin(pin->flags, DI_LOCKED); ++ else ++ au_fclr_pin(pin->flags, DI_LOCKED); + } ++} + -+ au_fclr_ren(a->auren_flags, DT_DSTDIR); -+ if (!au_ftest_ren(a->auren_flags, ISDIR_SRC) -+ && !a->exchange) -+ return; -+ -+ 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); ++#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 + -+static void au_ren_rev_dt(int err, struct au_ren_args *a) -+{ -+ struct dentry *h_d; -+ struct inode *h_inode; ++/* ---------------------------------------------------------------------- */ + -+ au_dtime_revert(a->src_dt + AuPARENT); -+ if (!au_ftest_ren(a->auren_flags, ISSAMEDIR)) -+ au_dtime_revert(a->dst_dt + AuPARENT); ++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 (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 it returns true, the the caller should free hinode->hi_notify, ++ * otherwise ->free() frees it. ++ */ ++ int (*free)(struct au_hinode *hinode, ++ struct au_hnotify *hn) __must_check; + -+ 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); -+ } -+ } -+} ++ 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); ++}; + -+int aufs_rename(struct inode *_src_dir, struct dentry *_src_dentry, -+ struct inode *_dst_dir, struct dentry *_dst_dentry, -+ unsigned int _flags) ++/* 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, ++ 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 err, lock_flags; -+ /* reduce stack space */ -+ struct au_ren_args *a; -+ struct au_pin pin; ++ hinode->hi_notify = NULL; ++} + -+ AuDbg("%pd, %pd, 0x%x\n", _src_dentry, _dst_dentry, _flags); -+ IMustLock(_src_dir); -+ IMustLock(_dst_dir); ++static inline struct au_hnotify *au_hn(struct au_hinode *hinode) ++{ ++ return hinode->hi_notify; ++} + -+ err = -EINVAL; -+ if (unlikely(_flags & RENAME_WHITEOUT)) -+ goto out; ++#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 = -ENOMEM; -+ BUILD_BUG_ON(sizeof(*a) > PAGE_SIZE); -+ a = kzalloc(sizeof(*a), GFP_NOFS); -+ if (unlikely(!a)) -+ goto out; ++static inline void au_hn_suspend(struct au_hinode *hdir) ++{ ++ au_hn_ctl(hdir, /*do_set*/0); ++} + -+ a->flags = _flags; -+ 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_resume(struct au_hinode *hdir) ++{ ++ au_hn_ctl(hdir, /*do_set*/1); ++} + -+ 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(struct au_hinode *hdir) ++{ ++ inode_lock(hdir->hi_inode); ++ 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; ++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); ++} + -+ /* -+ * 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; ++#if 0 /* unused */ ++#include "vfsub.h" ++static inline void au_hn_inode_lock_shared_nested(struct au_hinode *hdir, ++ unsigned int sc) ++{ ++ vfsub_inode_lock_shared_nested(hdir->hi_inode, sc); ++ au_hn_suspend(hdir); ++} ++#endif + -+ au_fset_ren(a->auren_flags, ISSAMEDIR); /* temporary */ -+ di_write_lock_parent(a->dst_parent); ++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 -urNp -x '*.orig' linux-4.9/fs/aufs/ioctl.c linux-4.9/fs/aufs/ioctl.c +--- linux-4.9/fs/aufs/ioctl.c 1970-01-01 01:00:00.000000000 +0100 ++++ linux-4.9/fs/aufs/ioctl.c 2021-02-24 16:15:09.531573855 +0100 +@@ -0,0 +1,219 @@ ++/* ++ * Copyright (C) 2005-2018 Junjiro R. Okajima ++ * ++ * This program, aufs is free software; you can redistribute it and/or modify ++ * it under the terms of the GNU General Public License as published by ++ * the Free Software Foundation; either version 2 of the License, or ++ * (at your option) any later version. ++ * ++ * This program is distributed in the hope that it will be useful, ++ * but WITHOUT ANY WARRANTY; without even the implied warranty of ++ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the ++ * GNU General Public License for more details. ++ * ++ * You should have received a copy of the GNU General Public License ++ * along with this program. If not, see . ++ */ + -+ /* 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 ++#include ++#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 (arg) { ++ err = copy_from_user(&wbrfd, arg, sizeof(wbrfd)); ++ if (unlikely(err)) { ++ err = -EFAULT; ++ goto out; + } -+ 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 = -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; ++ fd = get_unused_fd_flags(0); ++ err = fd; ++ if (unlikely(fd < 0)) ++ goto out; + -+ 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; ++ 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 timestamps to be revertible */ -+ au_ren_dt(a); -+ -+ /* here we go */ -+ err = do_rename(a); -+ 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; + -+ /* update dir attributes */ -+ au_ren_refresh_dir(a); ++ 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); + -+ /* dput/iput all lower dentries */ -+ au_ren_refresh(a); ++out_unlock: ++ aufs_read_unlock(root, AuLock_IR); ++ err = PTR_ERR(h_file); ++ if (IS_ERR(h_file)) ++ goto out_fd; + -+ goto out_hdir; /* success */ ++ au_br_put(br); /* cf. au_h_open() */ ++ fd_install(fd, h_file); ++ err = fd; ++ goto out; /* success */ + -+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 (!a->exchange) -+ d_move(a->src_dentry, a->dst_dentry); -+ else -+ d_exchange(a->src_dentry, a->dst_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_delayed_kfree(a); ++out_fd: ++ put_unused_fd(fd); +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 2016-10-09 16:55:36.482701377 +0200 -@@ -0,0 +1,185 @@ -+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. ++long aufs_ioctl_dir(struct file *file, unsigned int cmd, unsigned long arg) ++{ ++ long err; ++ struct dentry *dentry; + -+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. ++ switch (cmd) { ++ case AUFS_CTL_RDU: ++ case AUFS_CTL_RDU_INO: ++ err = au_rdu_ioctl(file, cmd, arg); ++ break; + -+choice -+ prompt "method" if AUFS_HNOTIFY -+ default AUFS_HFSNOTIFY -+config AUFS_HFSNOTIFY -+ bool "fsnotify" -+ select FSNOTIFY -+endchoice ++ case AUFS_CTL_WBR_FD: ++ err = au_wbr_fd(&file->f_path, (void __user *)arg); ++ break; + -+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. ++ case AUFS_CTL_IBUSY: ++ err = au_ibusy_ioctl(file, arg); ++ break; + -+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 */ ++ case AUFS_CTL_BRINFO: ++ err = au_brinfo_ioctl(file, arg); ++ break; + -+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. ++ 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; + -+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. ++ default: ++ /* do not call the lower */ ++ AuDbg("0x%x\n", cmd); ++ err = -ENOTTY; ++ } + -+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. ++ 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. ++long aufs_ioctl_nondir(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_MVDOWN: ++ err = au_mvdown(file->f_path.dentry, (void __user *)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_WBR_FD: ++ err = au_wbr_fd(&file->f_path, (void __user *)arg); ++ break; + -+config AUFS_POLL -+ bool -+ help -+ Automatic configuration for internal use. ++ default: ++ /* do not call the lower */ ++ AuDbg("0x%x\n", cmd); ++ err = -ENOTTY; ++ } + -+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. ++ AuTraceErr(err); ++ return err; ++} + -+config AUFS_BDEV_LOOP -+ bool -+ depends on BLK_DEV_LOOP -+ default y -+ help -+ Automatic configuration for internal use. -+ Convert =[ym] into =y. ++#ifdef CONFIG_COMPAT ++long aufs_compat_ioctl_dir(struct file *file, unsigned int cmd, ++ unsigned long arg) ++{ ++ long 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. ++ switch (cmd) { ++ case AUFS_CTL_RDU: ++ case AUFS_CTL_RDU_INO: ++ err = au_rdu_compat_ioctl(file, cmd, arg); ++ break; + -+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/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 2016-10-09 16:55:38.889431135 +0200 -@@ -0,0 +1,147 @@ ++ case AUFS_CTL_IBUSY: ++ err = au_ibusy_compat_ioctl(file, arg); ++ break; ++ ++ case AUFS_CTL_BRINFO: ++ err = au_brinfo_compat_ioctl(file, arg); ++ break; ++ ++ default: ++ err = aufs_ioctl_dir(file, cmd, arg); ++ } ++ ++ AuTraceErr(err); ++ return err; ++} ++ ++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 -urNp -x '*.orig' linux-4.9/fs/aufs/loop.c linux-4.9/fs/aufs/loop.c +--- linux-4.9/fs/aufs/loop.c 1970-01-01 01:00:00.000000000 +0100 ++++ linux-4.9/fs/aufs/loop.c 2021-02-24 16:15:09.541574180 +0100 +@@ -0,0 +1,163 @@ +/* -+ * Copyright (C) 2005-2016 Junjiro R. Okajima ++ * Copyright (C) 2005-2018 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by @@ -21909,14 +23133,30 @@ diff -urN /usr/share/empty/fs/aufs/loop.c linux/fs/aufs/loop.c +{ + if (backing_file_func) + symbol_put(loop_backing_file); -+ au_delayed_kfree(au_warn_loopback_array); ++ kfree(au_warn_loopback_array); +} -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 2016-10-09 16:55:36.492701639 +0200 -@@ -0,0 +1,52 @@ ++ ++/* ---------------------------------------------------------------------- */ ++ ++/* support the loopback block device insude aufs */ ++ ++struct file *aufs_real_loop(struct file *file) ++{ ++ struct file *f; ++ ++ 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; ++} +diff -urNp -x '*.orig' linux-4.9/fs/aufs/loop.h linux-4.9/fs/aufs/loop.h +--- linux-4.9/fs/aufs/loop.h 1970-01-01 01:00:00.000000000 +0100 ++++ linux-4.9/fs/aufs/loop.h 2021-02-24 16:15:09.541574180 +0100 +@@ -0,0 +1,58 @@ +/* -+ * Copyright (C) 2005-2016 Junjiro R. Okajima ++ * Copyright (C) 2005-2018 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by @@ -21955,7 +23195,11 @@ diff -urN /usr/share/empty/fs/aufs/loop.h linux/fs/aufs/loop.h + +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) ++ +AuStubInt0(au_test_loopback_overlap, struct super_block *sb, + struct dentry *h_adding) +AuStubInt0(au_test_loopback_kthread, void) @@ -21963,13 +23207,15 @@ diff -urN /usr/share/empty/fs/aufs/loop.h linux/fs/aufs/loop.h + +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 */ + +#endif /* __KERNEL__ */ +#endif /* __AUFS_LOOP_H__ */ -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 2016-10-09 16:55:36.492701639 +0200 +diff -urNp -x '*.orig' linux-4.9/fs/aufs/magic.mk linux-4.9/fs/aufs/magic.mk +--- linux-4.9/fs/aufs/magic.mk 1970-01-01 01:00:00.000000000 +0100 ++++ linux-4.9/fs/aufs/magic.mk 2021-02-24 16:15:09.531573855 +0100 @@ -0,0 +1,30 @@ + +# defined in ${srctree}/fs/fuse/inode.c @@ -22001,60 +23247,12 @@ diff -urN /usr/share/empty/fs/aufs/magic.mk linux/fs/aufs/magic.mk +ifdef CONFIG_HFSPLUS_FS +ccflags-y += -DHFSPLUS_SUPER_MAGIC=0x482b +endif -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 2016-10-09 16:55:36.486034798 +0200 -@@ -0,0 +1,44 @@ -+ -+include ${src}/magic.mk -+ifeq (${CONFIG_AUFS_FS},m) -+include ${src}/conf.mk -+endif -+-include ${src}/priv_def.mk -+ -+# cf. include/linux/kernel.h -+# enable pr_debug -+ccflags-y += -DDEBUG -+# sparse requires the full pathname -+ifdef M -+ccflags-y += -include ${M}/../../include/uapi/linux/aufs_type.h -+else -+ccflags-y += -include ${srctree}/include/uapi/linux/aufs_type.h -+endif -+ -+obj-$(CONFIG_AUFS_FS) += aufs.o -+aufs-y := module.o sbinfo.o super.o branch.o xino.o sysaufs.o opts.o \ -+ wkq.o vfsub.o dcsub.o \ -+ cpup.o whout.o wbr_policy.o \ -+ dinfo.o dentry.o \ -+ dynop.o \ -+ finfo.o file.o f_op.o \ -+ dir.o vdir.o \ -+ iinfo.o inode.o i_op.o i_op_add.o i_op_del.o i_op_ren.o \ -+ mvdown.o ioctl.o -+ -+# all are boolean -+aufs-$(CONFIG_PROC_FS) += procfs.o plink.o -+aufs-$(CONFIG_SYSFS) += sysfs.o -+aufs-$(CONFIG_DEBUG_FS) += dbgaufs.o -+aufs-$(CONFIG_AUFS_BDEV_LOOP) += loop.o -+aufs-$(CONFIG_AUFS_HNOTIFY) += hnotify.o -+aufs-$(CONFIG_AUFS_HFSNOTIFY) += hfsnotify.o -+aufs-$(CONFIG_AUFS_EXPORT) += export.o -+aufs-$(CONFIG_AUFS_XATTR) += xattr.o -+aufs-$(CONFIG_FS_POSIX_ACL) += posix_acl.o -+aufs-$(CONFIG_AUFS_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 2016-10-09 16:55:38.889431135 +0200 -@@ -0,0 +1,333 @@ +diff -urNp -x '*.orig' linux-4.9/fs/aufs/module.c linux-4.9/fs/aufs/module.c +--- linux-4.9/fs/aufs/module.c 1970-01-01 01:00:00.000000000 +0100 ++++ linux-4.9/fs/aufs/module.c 2021-02-24 16:15:09.531573855 +0100 +@@ -0,0 +1,266 @@ +/* -+ * Copyright (C) 2005-2016 Junjiro R. Okajima ++ * Copyright (C) 2005-2018 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by @@ -22089,7 +23287,7 @@ diff -urN /usr/share/empty/fs/aufs/module.c linux/fs/aufs/module.c + if (p) { +#if 0 /* unused */ + if (!new_sz) { -+ au_delayed_kfree(p); ++ kfree(p); + p = NULL; + goto out; + } @@ -22113,7 +23311,7 @@ diff -urN /usr/share/empty/fs/aufs/module.c linux/fs/aufs/module.c + if (q) { + if (p) { + memcpy(q, p, new_sz); -+ au_delayed_kfree(p); ++ kfree(p); + } + p = q; + } else @@ -22137,61 +23335,11 @@ diff -urN /usr/share/empty/fs/aufs/module.c linux/fs/aufs/module.c +/* + * aufs caches + */ -+ -+struct au_dfree au_dfree; -+ -+/* delayed free */ -+static void au_do_dfree(struct work_struct *work __maybe_unused) -+{ -+ struct llist_head *head; -+ struct llist_node *node, *next; -+ -+#define AU_CACHE_DFREE_DO_BODY(name, idx, lnode) do { \ -+ head = &au_dfree.cache[AuCache_##idx].llist; \ -+ node = llist_del_all(head); \ -+ for (; node; node = next) { \ -+ struct au_##name *p \ -+ = llist_entry(node, struct au_##name, \ -+ lnode); \ -+ next = llist_next(node); \ -+ au_cache_free_##name(p); \ -+ } \ -+ } while (0) -+ -+ AU_CACHE_DFREE_DO_BODY(dinfo, DINFO, di_lnode); -+ AU_CACHE_DFREE_DO_BODY(icntnr, ICNTNR, lnode); -+ AU_CACHE_DFREE_DO_BODY(finfo, FINFO, fi_lnode); -+ AU_CACHE_DFREE_DO_BODY(vdir, VDIR, vd_lnode); -+ AU_CACHE_DFREE_DO_BODY(vdir_dehstr, DEHSTR, lnode); -+#ifdef CONFIG_AUFS_HNOTIFY -+ AU_CACHE_DFREE_DO_BODY(hnotify, HNOTIFY, hn_lnode); -+#endif -+ -+#define AU_DFREE_DO_BODY(llist, func) do { \ -+ node = llist_del_all(llist); \ -+ for (; node; node = next) { \ -+ next = llist_next(node); \ -+ func(node); \ -+ } \ -+ } while (0) -+ -+ AU_DFREE_DO_BODY(au_dfree.llist + AU_DFREE_KFREE, kfree); -+ AU_DFREE_DO_BODY(au_dfree.llist + AU_DFREE_FREE_PAGE, au_free_page); -+ -+#undef AU_CACHE_DFREE_DO_BODY -+#undef AU_DFREE_DO_BODY -+} -+ -+AU_CACHE_DFREE_FUNC(dinfo, DINFO, di_lnode); -+AU_CACHE_DFREE_FUNC(icntnr, ICNTNR, lnode); -+AU_CACHE_DFREE_FUNC(finfo, FINFO, fi_lnode); -+AU_CACHE_DFREE_FUNC(vdir, VDIR, vd_lnode); -+AU_CACHE_DFREE_FUNC(vdir_dehstr, DEHSTR, lnode); ++struct kmem_cache *au_cache[AuCache_Last]; + +static void au_cache_fin(void) +{ + int i; -+ struct au_cache *cp; + + /* + * Make sure all delayed rcu free inodes are flushed before we @@ -22201,33 +23349,27 @@ diff -urN /usr/share/empty/fs/aufs/module.c linux/fs/aufs/module.c + + /* excluding AuCache_HNOTIFY */ + BUILD_BUG_ON(AuCache_HNOTIFY + 1 != AuCache_Last); -+ flush_delayed_work(&au_dfree.dwork); + for (i = 0; i < AuCache_HNOTIFY; i++) { -+ cp = au_dfree.cache + i; -+ AuDebugOn(!llist_empty(&cp->llist)); -+ kmem_cache_destroy(cp->cache); -+ cp->cache = NULL; ++ kmem_cache_destroy(au_cache[i]); ++ au_cache[i] = NULL; + } +} + +static int __init au_cache_init(void) +{ -+ struct au_cache *cp; -+ -+ cp = au_dfree.cache; -+ cp[AuCache_DINFO].cache = AuCacheCtor(au_dinfo, au_di_init_once); -+ if (cp[AuCache_DINFO].cache) ++ au_cache[AuCache_DINFO] = AuCacheCtor(au_dinfo, au_di_init_once); ++ if (au_cache[AuCache_DINFO]) + /* SLAB_DESTROY_BY_RCU */ -+ cp[AuCache_ICNTNR].cache = AuCacheCtor(au_icntnr, ++ au_cache[AuCache_ICNTNR] = AuCacheCtor(au_icntnr, + au_icntnr_init_once); -+ if (cp[AuCache_ICNTNR].cache) -+ cp[AuCache_FINFO].cache = AuCacheCtor(au_finfo, ++ if (au_cache[AuCache_ICNTNR]) ++ au_cache[AuCache_FINFO] = AuCacheCtor(au_finfo, + au_fi_init_once); -+ if (cp[AuCache_FINFO].cache) -+ cp[AuCache_VDIR].cache = AuCache(au_vdir); -+ if (cp[AuCache_VDIR].cache) -+ cp[AuCache_DEHSTR].cache = AuCache(au_vdir_dehstr); -+ if (cp[AuCache_DEHSTR].cache) ++ if (au_cache[AuCache_FINFO]) ++ au_cache[AuCache_VDIR] = AuCache(au_vdir); ++ if (au_cache[AuCache_VDIR]) ++ au_cache[AuCache_DEHSTR] = AuCache(au_vdir_dehstr); ++ if (au_cache[AuCache_DEHSTR]) + return 0; + + au_cache_fin(); @@ -22243,7 +23385,7 @@ diff -urN /usr/share/empty/fs/aufs/module.c linux/fs/aufs/module.c + * iterate_supers_type() doesn't protect us from + * remounting (branch management) + */ -+struct au_sphlhead au_sbilist; ++struct hlist_bl_head au_sbilist; +#endif + +/* @@ -22276,9 +23418,9 @@ diff -urN /usr/share/empty/fs/aufs/module.c linux/fs/aufs/module.c + int err; + + err = seq_path(seq, path, au_esc_chars); -+ if (err > 0) ++ if (err >= 0) + err = 0; -+ else if (err < 0) ++ else + err = -ENOMEM; + + return err; @@ -22290,7 +23432,6 @@ diff -urN /usr/share/empty/fs/aufs/module.c linux/fs/aufs/module.c +{ + int err, i; + char *p; -+ struct au_cache *cp; + + p = au_esc_chars; + for (i = 1; i <= ' '; i++) @@ -22305,15 +23446,7 @@ diff -urN /usr/share/empty/fs/aufs/module.c linux/fs/aufs/module.c + for (i = 0; i < AuIop_Last; i++) + aufs_iop_nogetattr[i].getattr = NULL; + -+ /* First, initialize au_dfree */ -+ for (i = 0; i < AuCache_Last; i++) { /* including hnotify */ -+ cp = au_dfree.cache + i; -+ cp->cache = NULL; -+ init_llist_head(&cp->llist); -+ } -+ for (i = 0; i < AU_DFREE_Last; i++) -+ init_llist_head(au_dfree.llist + i); -+ INIT_DELAYED_WORK(&au_dfree.dwork, au_do_dfree); ++ memset(au_cache, 0, sizeof(au_cache)); /* including hnotify */ + + au_sbilist_init(); + sysaufs_brs_init(); @@ -22365,7 +23498,6 @@ diff -urN /usr/share/empty/fs/aufs/module.c linux/fs/aufs/module.c +out_sysaufs: + sysaufs_fin(); + au_dy_fin(); -+ flush_delayed_work(&au_dfree.dwork); +out: + return err; +} @@ -22381,17 +23513,16 @@ diff -urN /usr/share/empty/fs/aufs/module.c linux/fs/aufs/module.c + au_procfs_fin(); + sysaufs_fin(); + au_dy_fin(); -+ flush_delayed_work(&au_dfree.dwork); +} + +module_init(aufs_init); +module_exit(aufs_exit); -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 2016-10-09 16:55:38.889431135 +0200 -@@ -0,0 +1,156 @@ +diff -urNp -x '*.orig' linux-4.9/fs/aufs/module.h linux-4.9/fs/aufs/module.h +--- linux-4.9/fs/aufs/module.h 1970-01-01 01:00:00.000000000 +0100 ++++ linux-4.9/fs/aufs/module.h 2021-02-24 16:15:09.531573855 +0100 +@@ -0,0 +1,101 @@ +/* -+ * Copyright (C) 2005-2016 Junjiro R. Okajima ++ * Copyright (C) 2005-2018 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by @@ -22417,7 +23548,6 @@ diff -urN /usr/share/empty/fs/aufs/module.h linux/fs/aufs/module.h +#ifdef __KERNEL__ + +#include -+#include "debug.h" + +struct path; +struct seq_file; @@ -22456,7 +23586,7 @@ diff -urN /usr/share/empty/fs/aufs/module.h linux/fs/aufs/module.h + +/* ---------------------------------------------------------------------- */ + -+/* kmem cache and delayed free */ ++/* kmem cache */ +enum { + AuCache_DINFO, + AuCache_ICNTNR, @@ -22467,28 +23597,7 @@ diff -urN /usr/share/empty/fs/aufs/module.h linux/fs/aufs/module.h + AuCache_Last +}; + -+enum { -+ AU_DFREE_KFREE, -+ AU_DFREE_FREE_PAGE, -+ AU_DFREE_Last -+}; -+ -+struct au_cache { -+ struct kmem_cache *cache; -+ struct llist_head llist; /* delayed free */ -+}; -+ -+/* -+ * in order to reduce the cost of the internal timer, consolidate all the -+ * delayed free works into a single delayed_work. -+ */ -+struct au_dfree { -+ struct au_cache cache[AuCache_Last]; -+ struct llist_head llist[AU_DFREE_Last]; -+ struct delayed_work dwork; -+}; -+ -+extern struct au_dfree au_dfree; ++extern struct kmem_cache *au_cache[AuCache_Last]; + +#define AuCacheFlags (SLAB_RECLAIM_ACCOUNT | SLAB_MEM_SPREAD) +#define AuCache(type) KMEM_CACHE(type, AuCacheFlags) @@ -22496,25 +23605,11 @@ diff -urN /usr/share/empty/fs/aufs/module.h linux/fs/aufs/module.h + kmem_cache_create(#type, sizeof(struct type), \ + __alignof__(struct type), AuCacheFlags, ctor) + -+#define AU_DFREE_DELAY msecs_to_jiffies(10) -+#define AU_DFREE_BODY(lnode, llist) do { \ -+ if (llist_add(lnode, llist)) \ -+ schedule_delayed_work(&au_dfree.dwork, \ -+ AU_DFREE_DELAY); \ -+ } while (0) -+#define AU_CACHE_DFREE_FUNC(name, idx, lnode) \ -+ void au_cache_dfree_##name(struct au_##name *p) \ -+ { \ -+ struct au_cache *cp = au_dfree.cache + AuCache_##idx; \ -+ AU_DFREE_BODY(&p->lnode, &cp->llist); \ -+ } -+ +#define AuCacheFuncs(name, index) \ +static inline struct au_##name *au_cache_alloc_##name(void) \ -+{ return kmem_cache_alloc(au_dfree.cache[AuCache_##index].cache, GFP_NOFS); } \ ++{ return kmem_cache_alloc(au_cache[AuCache_##index], GFP_NOFS); } \ +static inline void au_cache_free_##name(struct au_##name *p) \ -+{ kmem_cache_free(au_dfree.cache[AuCache_##index].cache, p); } \ -+void au_cache_dfree_##name(struct au_##name *p) ++{ kmem_cache_free(au_cache[AuCache_##index], p); } + +AuCacheFuncs(dinfo, DINFO); +AuCacheFuncs(icntnr, ICNTNR); @@ -22525,33 +23620,14 @@ diff -urN /usr/share/empty/fs/aufs/module.h linux/fs/aufs/module.h +AuCacheFuncs(hnotify, HNOTIFY); +#endif + -+static inline void au_delayed_kfree(const void *p) -+{ -+ AuDebugOn(!p); -+ AuDebugOn(ksize(p) < sizeof(struct llist_node)); -+ -+ AU_DFREE_BODY((void *)p, au_dfree.llist + AU_DFREE_KFREE); -+} -+ -+/* cast only */ -+static inline void au_free_page(void *p) -+{ -+ free_page((unsigned long)p); -+} -+ -+static inline void au_delayed_free_page(unsigned long addr) -+{ -+ AU_DFREE_BODY((void *)addr, au_dfree.llist + AU_DFREE_FREE_PAGE); -+} -+ +#endif /* __KERNEL__ */ +#endif /* __AUFS_MODULE_H__ */ -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 2016-10-09 16:55:36.492701639 +0200 +diff -urNp -x '*.orig' linux-4.9/fs/aufs/mvdown.c linux-4.9/fs/aufs/mvdown.c +--- linux-4.9/fs/aufs/mvdown.c 1970-01-01 01:00:00.000000000 +0100 ++++ linux-4.9/fs/aufs/mvdown.c 2021-02-24 16:15:09.531573855 +0100 @@ -0,0 +1,704 @@ +/* -+ * Copyright (C) 2011-2016 Junjiro R. Okajima ++ * Copyright (C) 2011-2018 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by @@ -23249,17 +24325,17 @@ diff -urN /usr/share/empty/fs/aufs/mvdown.c linux/fs/aufs/mvdown.c + e = copy_to_user(uarg, &args->mvdown, sizeof(args->mvdown)); + if (unlikely(e)) + err = -EFAULT; -+ au_delayed_kfree(args); ++ kfree(args); +out: + AuTraceErr(err); + return err; +} -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 2016-12-17 12:28:17.598545045 +0100 -@@ -0,0 +1,1870 @@ +diff -urNp -x '*.orig' linux-4.9/fs/aufs/opts.c linux-4.9/fs/aufs/opts.c +--- linux-4.9/fs/aufs/opts.c 1970-01-01 01:00:00.000000000 +0100 ++++ linux-4.9/fs/aufs/opts.c 2021-02-24 16:15:09.534907296 +0100 +@@ -0,0 +1,1913 @@ +/* -+ * Copyright (C) 2005-2016 Junjiro R. Okajima ++ * Copyright (C) 2005-2018 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by @@ -23307,6 +24383,7 @@ diff -urN /usr/share/empty/fs/aufs/opts.c linux/fs/aufs/opts.c + Opt_verbose, Opt_noverbose, + Opt_sum, Opt_nosum, Opt_wsum, + Opt_dirperm1, Opt_nodirperm1, ++ Opt_dirren, Opt_nodirren, + Opt_acl, Opt_noacl, + Opt_tail, Opt_ignore, Opt_ignore_silent, Opt_err +}; @@ -23361,10 +24438,18 @@ diff -urN /usr/share/empty/fs/aufs/opts.c linux/fs/aufs/opts.c + {Opt_dio, "dio"}, + {Opt_nodio, "nodio"}, + ++#ifdef CONFIG_AUFS_DIRREN ++ {Opt_dirren, "dirren"}, ++ {Opt_nodirren, "nodirren"}, ++#else ++ {Opt_ignore, "dirren"}, ++ {Opt_ignore_silent, "nodirren"}, ++#endif ++ +#ifdef CONFIG_AUFS_FHSM + {Opt_fhsm_sec, "fhsm_sec=%d"}, +#else -+ {Opt_ignore_silent, "fhsm_sec=%d"}, ++ {Opt_ignore, "fhsm_sec=%d"}, +#endif + + {Opt_diropq_a, "diropq=always"}, @@ -23377,7 +24462,7 @@ diff -urN /usr/share/empty/fs/aufs/opts.c linux/fs/aufs/opts.c + + /* keep them temporary */ + {Opt_ignore_silent, "nodlgt"}, -+ {Opt_ignore_silent, "clean_plink"}, ++ {Opt_ignore, "clean_plink"}, + +#ifdef CONFIG_AUFS_SHWH + {Opt_shwh, "shwh"}, @@ -23415,7 +24500,7 @@ diff -urN /usr/share/empty/fs/aufs/opts.c linux/fs/aufs/opts.c + {Opt_acl, "acl"}, + {Opt_noacl, "noacl"}, +#else -+ {Opt_ignore_silent, "acl"}, ++ {Opt_ignore, "acl"}, + {Opt_ignore_silent, "noacl"}, +#endif + @@ -24003,6 +25088,12 @@ diff -urN /usr/share/empty/fs/aufs/opts.c linux/fs/aufs/opts.c + case Opt_fhsm_sec: + AuDbg("fhsm_sec %u\n", opt->fhsm_second); + break; ++ case Opt_dirren: ++ AuLabel(dirren); ++ break; ++ case Opt_nodirren: ++ AuLabel(nodirren); ++ break; + case Opt_acl: + AuLabel(acl); + break; @@ -24453,6 +25544,8 @@ diff -urN /usr/share/empty/fs/aufs/opts.c linux/fs/aufs/opts.c + case Opt_wsum: + case Opt_rdblk_def: + case Opt_rdhash_def: ++ case Opt_dirren: ++ case Opt_nodirren: + case Opt_acl: + case Opt_noacl: + err = 0; @@ -24524,7 +25617,7 @@ diff -urN /usr/share/empty/fs/aufs/opts.c linux/fs/aufs/opts.c + } + } + -+ au_delayed_kfree(a); ++ kfree(a); + dump_opts(opts); + if (unlikely(err)) + au_opts_free(opts); @@ -24719,6 +25812,28 @@ diff -urN /usr/share/empty/fs/aufs/opts.c linux/fs/aufs/opts.c + au_fclr_opts(opts->flags, TRUNC_XIB); + break; + ++ case Opt_dirren: ++ err = 1; ++ if (!au_opt_test(sbinfo->si_mntflags, DIRREN)) { ++ err = au_dr_opt_set(sb); ++ if (!err) ++ err = 1; ++ } ++ if (err == 1) ++ au_opt_set(sbinfo->si_mntflags, DIRREN); ++ break; ++ case Opt_nodirren: ++ err = 1; ++ if (au_opt_test(sbinfo->si_mntflags, DIRREN)) { ++ err = au_dr_opt_clr(sb, au_ftest_opts(opts->flags, ++ DR_FLUSHED)); ++ if (!err) ++ err = 1; ++ } ++ if (err == 1) ++ au_opt_clr(sbinfo->si_mntflags, DIRREN); ++ break; ++ + case Opt_acl: + sb->s_flags |= MS_POSIXACL; + break; @@ -24787,7 +25902,6 @@ diff -urN /usr/share/empty/fs/aufs/opts.c linux/fs/aufs/opts.c + } + break; + } -+ + return err; +} + @@ -24948,8 +26062,7 @@ diff -urN /usr/share/empty/fs/aufs/opts.c linux/fs/aufs/opts.c + au_hn_inode_unlock(hdir); + + if (!err && do_free) { -+ if (wbr) -+ au_delayed_kfree(wbr); ++ kfree(wbr); + br->br_wbr = NULL; + } + } @@ -25078,7 +26191,11 @@ diff -urN /usr/share/empty/fs/aufs/opts.c linux/fs/aufs/opts.c + + SiMustWriteLock(sb); + -+ err = 0; ++ err = au_dr_opt_flush(sb); ++ if (unlikely(err)) ++ goto out; ++ au_fset_opts(opts->flags, DR_FLUSHED); ++ + dir = d_inode(sb->s_root); + sbinfo = au_sbi(sb); + opt_xino = NULL; @@ -25119,6 +26236,8 @@ diff -urN /usr/share/empty/fs/aufs/opts.c linux/fs/aufs/opts.c + au_fset_opts(opts->flags, REFRESH); + + AuDbg("status 0x%x\n", opts->flags); ++ ++out: + return err; +} + @@ -25128,12 +26247,12 @@ diff -urN /usr/share/empty/fs/aufs/opts.c linux/fs/aufs/opts.c +{ + return au_mntflags(sb) & AuOptMask_UDBA; +} -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 2016-12-17 12:28:17.598545045 +0100 -@@ -0,0 +1,213 @@ +diff -urNp -x '*.orig' linux-4.9/fs/aufs/opts.h linux-4.9/fs/aufs/opts.h +--- linux-4.9/fs/aufs/opts.h 1970-01-01 01:00:00.000000000 +0100 ++++ linux-4.9/fs/aufs/opts.h 2021-02-24 16:15:09.534907296 +0100 +@@ -0,0 +1,224 @@ +/* -+ * Copyright (C) 2005-2016 Junjiro R. Okajima ++ * Copyright (C) 2005-2018 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by @@ -25161,7 +26280,6 @@ diff -urN /usr/share/empty/fs/aufs/opts.h linux/fs/aufs/opts.h +#include + +struct file; -+struct super_block; + +/* ---------------------------------------------------------------------- */ + @@ -25182,11 +26300,16 @@ diff -urN /usr/share/empty/fs/aufs/opts.h linux/fs/aufs/opts.h +#define AuOpt_WARN_PERM (1 << 12) /* warn when add-branch */ +#define AuOpt_VERBOSE (1 << 13) /* busy inode when del-branch */ +#define AuOpt_DIO (1 << 14) /* direct io */ ++#define AuOpt_DIRREN (1 << 15) /* directory rename */ + +#ifndef CONFIG_AUFS_HNOTIFY +#undef AuOpt_UDBA_HNOTIFY +#define AuOpt_UDBA_HNOTIFY 0 +#endif ++#ifndef CONFIG_AUFS_DIRREN ++#undef AuOpt_DIRREN ++#define AuOpt_DIRREN 0 ++#endif +#ifndef CONFIG_AUFS_SHWH +#undef AuOpt_SHWH +#define AuOpt_SHWH 0 @@ -25311,12 +26434,18 @@ diff -urN /usr/share/empty/fs/aufs/opts.h linux/fs/aufs/opts.h +#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 au_ftest_opts(flags, name) ((flags) & AuOpts_##name) +#define au_fset_opts(flags, name) \ + do { (flags) |= AuOpts_##name; } while (0) +#define au_fclr_opts(flags, name) \ + do { (flags) &= ~AuOpts_##name; } while (0) + ++#ifndef CONFIG_AUFS_DIRREN ++#undef AuOpts_DR_FLUSHED ++#define AuOpts_DR_FLUSHED 0 ++#endif ++ +struct au_opts { + struct au_opt *opt; + int max_opt; @@ -25335,6 +26464,7 @@ diff -urN /usr/share/empty/fs/aufs/opts.h linux/fs/aufs/opts.h +const char *au_optstr_wbr_create(int wbr_create); + +void au_opts_free(struct au_opts *opts); ++struct super_block; +int au_opts_parse(struct super_block *sb, char *str, struct au_opts *opts); +int au_opts_verify(struct super_block *sb, unsigned long sb_flags, + unsigned int pending); @@ -25345,12 +26475,12 @@ diff -urN /usr/share/empty/fs/aufs/opts.h linux/fs/aufs/opts.h + +#endif /* __KERNEL__ */ +#endif /* __AUFS_OPTS_H__ */ -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 2016-10-09 16:55:36.496035060 +0200 -@@ -0,0 +1,514 @@ +diff -urNp -x '*.orig' linux-4.9/fs/aufs/plink.c linux-4.9/fs/aufs/plink.c +--- linux-4.9/fs/aufs/plink.c 1970-01-01 01:00:00.000000000 +0100 ++++ linux-4.9/fs/aufs/plink.c 2021-02-24 16:15:09.534907296 +0100 +@@ -0,0 +1,515 @@ +/* -+ * Copyright (C) 2005-2016 Junjiro R. Okajima ++ * Copyright (C) 2005-2018 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by @@ -25486,7 +26616,8 @@ diff -urN /usr/share/empty/fs/aufs/plink.c linux/fs/aufs/plink.c +{ + int i; + struct au_sbinfo *sbinfo; -+ struct hlist_head *plink_hlist; ++ struct hlist_bl_head *hbl; ++ struct hlist_bl_node *pos; + struct au_icntnr *icntnr; + + SiMustAnyLock(sb); @@ -25496,11 +26627,11 @@ diff -urN /usr/share/empty/fs/aufs/plink.c linux/fs/aufs/plink.c + AuDebugOn(au_plink_maint(sb, AuLock_NOPLM)); + + for (i = 0; i < AuPlink_NHASH; i++) { -+ plink_hlist = &sbinfo->si_plink[i].head; -+ rcu_read_lock(); -+ hlist_for_each_entry_rcu(icntnr, plink_hlist, plink) ++ hbl = sbinfo->si_plink + i; ++ hlist_bl_lock(hbl); ++ hlist_bl_for_each_entry(icntnr, pos, hbl, plink) + AuDbg("%lu\n", icntnr->vfs_inode.i_ino); -+ rcu_read_unlock(); ++ hlist_bl_unlock(hbl); + } +} +#endif @@ -25510,7 +26641,8 @@ diff -urN /usr/share/empty/fs/aufs/plink.c linux/fs/aufs/plink.c +{ + int found, i; + struct au_sbinfo *sbinfo; -+ struct hlist_head *plink_hlist; ++ struct hlist_bl_head *hbl; ++ struct hlist_bl_node *pos; + struct au_icntnr *icntnr; + + sbinfo = au_sbi(inode->i_sb); @@ -25520,14 +26652,14 @@ diff -urN /usr/share/empty/fs/aufs/plink.c linux/fs/aufs/plink.c + + found = 0; + i = au_plink_hash(inode->i_ino); -+ plink_hlist = &sbinfo->si_plink[i].head; -+ rcu_read_lock(); -+ hlist_for_each_entry_rcu(icntnr, plink_hlist, plink) ++ hbl = sbinfo->si_plink + i; ++ hlist_bl_lock(hbl); ++ hlist_bl_for_each_entry(icntnr, pos, hbl, plink) + if (&icntnr->vfs_inode == inode) { + found = 1; + break; + } -+ rcu_read_unlock(); ++ hlist_bl_unlock(hbl); + return found; +} + @@ -25566,9 +26698,9 @@ diff -urN /usr/share/empty/fs/aufs/plink.c linux/fs/aufs/plink.c + struct inode *h_inode; + + h_inode = d_inode(h_parent); -+ inode_lock_nested(h_inode, AuLsc_I_CHILD2); ++ vfsub_inode_lock_shared_nested(h_inode, AuLsc_I_CHILD2); + h_dentry = vfsub_lkup_one(tgtname, h_parent); -+ inode_unlock(h_inode); ++ inode_unlock_shared(h_inode); + return h_dentry; +} + @@ -25715,9 +26847,9 @@ diff -urN /usr/share/empty/fs/aufs/plink.c linux/fs/aufs/plink.c +{ + struct super_block *sb; + struct au_sbinfo *sbinfo; -+ struct hlist_head *plink_hlist; ++ struct hlist_bl_head *hbl; ++ struct hlist_bl_node *pos; + struct au_icntnr *icntnr; -+ struct au_sphlhead *sphl; + int found, err, cnt, i; + + sb = inode->i_sb; @@ -25730,12 +26862,11 @@ diff -urN /usr/share/empty/fs/aufs/plink.c linux/fs/aufs/plink.c + return; + + i = au_plink_hash(inode->i_ino); -+ sphl = sbinfo->si_plink + i; -+ plink_hlist = &sphl->head; ++ hbl = sbinfo->si_plink + i; + au_igrab(inode); + -+ spin_lock(&sphl->spin); -+ hlist_for_each_entry(icntnr, plink_hlist, plink) { ++ hlist_bl_lock(hbl); ++ hlist_bl_for_each_entry(icntnr, pos, hbl, plink) { + if (&icntnr->vfs_inode == inode) { + found = 1; + break; @@ -25743,11 +26874,11 @@ diff -urN /usr/share/empty/fs/aufs/plink.c linux/fs/aufs/plink.c + } + if (!found) { + icntnr = container_of(inode, struct au_icntnr, vfs_inode); -+ hlist_add_head_rcu(&icntnr->plink, plink_hlist); ++ hlist_bl_add_head(&icntnr->plink, hbl); + } -+ spin_unlock(&sphl->spin); ++ hlist_bl_unlock(hbl); + if (!found) { -+ cnt = au_sphl_count(sphl); ++ cnt = au_hbl_count(hbl); +#define msg "unexpectedly unblanced or too many pseudo-links" + if (cnt > AUFS_PLINK_WARN) + AuWarn1(msg ", %d\n", cnt); @@ -25755,7 +26886,7 @@ diff -urN /usr/share/empty/fs/aufs/plink.c linux/fs/aufs/plink.c + err = whplink(h_dentry, inode, bindex, au_sbr(sb, bindex)); + if (unlikely(err)) { + pr_warn("err %d, damaged pseudo link.\n", err); -+ au_sphl_del_rcu(&icntnr->plink, sphl); ++ au_hbl_del(&icntnr->plink, hbl); + iput(&icntnr->vfs_inode); + } + } else @@ -25767,8 +26898,8 @@ diff -urN /usr/share/empty/fs/aufs/plink.c linux/fs/aufs/plink.c +{ + int i, warned; + struct au_sbinfo *sbinfo; -+ struct hlist_head *plink_hlist; -+ struct hlist_node *tmp; ++ struct hlist_bl_head *hbl; ++ struct hlist_bl_node *pos, *tmp; + struct au_icntnr *icntnr; + + SiMustWriteLock(sb); @@ -25780,14 +26911,14 @@ diff -urN /usr/share/empty/fs/aufs/plink.c linux/fs/aufs/plink.c + /* no spin_lock since sbinfo is write-locked */ + warned = 0; + for (i = 0; i < AuPlink_NHASH; i++) { -+ plink_hlist = &sbinfo->si_plink[i].head; -+ if (!warned && verbose && !hlist_empty(plink_hlist)) { ++ hbl = sbinfo->si_plink + i; ++ if (!warned && verbose && !hlist_bl_empty(hbl)) { + pr_warn("pseudo-link is not flushed"); + warned = 1; + } -+ hlist_for_each_entry_safe(icntnr, tmp, plink_hlist, plink) ++ hlist_bl_for_each_entry_safe(icntnr, pos, tmp, hbl, plink) + iput(&icntnr->vfs_inode); -+ INIT_HLIST_HEAD(plink_hlist); ++ INIT_HLIST_BL_HEAD(hbl); + } +} + @@ -25835,8 +26966,8 @@ diff -urN /usr/share/empty/fs/aufs/plink.c linux/fs/aufs/plink.c +void au_plink_half_refresh(struct super_block *sb, aufs_bindex_t br_id) +{ + struct au_sbinfo *sbinfo; -+ struct hlist_head *plink_hlist; -+ struct hlist_node *tmp; ++ struct hlist_bl_head *hbl; ++ struct hlist_bl_node *pos, *tmp; + struct au_icntnr *icntnr; + struct inode *inode; + int i, do_put; @@ -25847,15 +26978,15 @@ diff -urN /usr/share/empty/fs/aufs/plink.c linux/fs/aufs/plink.c + AuDebugOn(!au_opt_test(au_mntflags(sb), PLINK)); + AuDebugOn(au_plink_maint(sb, AuLock_NOPLM)); + -+ /* no spin_lock since sbinfo is write-locked */ ++ /* no bit_lock since sbinfo is write-locked */ + for (i = 0; i < AuPlink_NHASH; i++) { -+ plink_hlist = &sbinfo->si_plink[i].head; -+ hlist_for_each_entry_safe(icntnr, tmp, plink_hlist, plink) { ++ hbl = sbinfo->si_plink + i; ++ hlist_bl_for_each_entry_safe(icntnr, pos, tmp, hbl, plink) { + inode = au_igrab(&icntnr->vfs_inode); + ii_write_lock_child(inode); + do_put = au_plink_do_half_refresh(inode, br_id); + if (do_put) { -+ hlist_del(&icntnr->plink); ++ hlist_bl_del(&icntnr->plink); + iput(inode); + } + ii_write_unlock(inode); @@ -25863,12 +26994,12 @@ diff -urN /usr/share/empty/fs/aufs/plink.c linux/fs/aufs/plink.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 2016-10-09 16:55:36.496035060 +0200 -@@ -0,0 +1,52 @@ +diff -urNp -x '*.orig' linux-4.9/fs/aufs/poll.c linux-4.9/fs/aufs/poll.c +--- linux-4.9/fs/aufs/poll.c 1970-01-01 01:00:00.000000000 +0100 ++++ linux-4.9/fs/aufs/poll.c 2021-02-24 16:15:09.534907296 +0100 +@@ -0,0 +1,53 @@ +/* -+ * Copyright (C) 2005-2016 Junjiro R. Okajima ++ * Copyright (C) 2005-2018 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by @@ -25903,7 +27034,7 @@ diff -urN /usr/share/empty/fs/aufs/poll.c linux/fs/aufs/poll.c + sb = file->f_path.dentry->d_sb; + si_read_lock(sb, AuLock_FLUSH | AuLock_NOPLMW); + -+ h_file = au_read_pre(file, /*keep_fi*/0); ++ h_file = au_read_pre(file, /*keep_fi*/0, /*lsc*/0); + err = PTR_ERR(h_file); + if (IS_ERR(h_file)) + goto out; @@ -25916,15 +27047,16 @@ diff -urN /usr/share/empty/fs/aufs/poll.c linux/fs/aufs/poll.c + +out: + si_read_unlock(sb); -+ AuTraceErr((int)mask); ++ if (mask & POLLERR) ++ AuDbg("mask 0x%x\n", mask); + return mask; +} -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 2016-12-17 12:28:17.598545045 +0100 -@@ -0,0 +1,98 @@ +diff -urNp -x '*.orig' linux-4.9/fs/aufs/posix_acl.c linux-4.9/fs/aufs/posix_acl.c +--- linux-4.9/fs/aufs/posix_acl.c 1970-01-01 01:00:00.000000000 +0100 ++++ linux-4.9/fs/aufs/posix_acl.c 2021-02-24 16:15:09.534907296 +0100 +@@ -0,0 +1,102 @@ +/* -+ * Copyright (C) 2014-2016 Junjiro R. Okajima ++ * Copyright (C) 2014-2018 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by @@ -25974,6 +27106,8 @@ diff -urN /usr/share/empty/fs/aufs/posix_acl.c linux/fs/aufs/posix_acl.c + + /* always topmost only */ + acl = get_acl(h_inode, type); ++ if (!IS_ERR_OR_NULL(acl)) ++ set_cached_acl(inode, type, acl); + +out: + ii_read_unlock(inode); @@ -26015,18 +27149,20 @@ diff -urN /usr/share/empty/fs/aufs/posix_acl.c linux/fs/aufs/posix_acl.c + ssz = au_sxattr(dentry, inode, &arg); + dput(dentry); + err = ssz; -+ if (ssz >= 0) ++ if (ssz >= 0) { + err = 0; ++ set_cached_acl(inode, type, acl); ++ } + +out: + return err; +} -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 2016-10-09 16:55:36.496035060 +0200 -@@ -0,0 +1,169 @@ +diff -urNp -x '*.orig' linux-4.9/fs/aufs/procfs.c linux-4.9/fs/aufs/procfs.c +--- linux-4.9/fs/aufs/procfs.c 1970-01-01 01:00:00.000000000 +0100 ++++ linux-4.9/fs/aufs/procfs.c 2021-02-24 16:15:09.534907296 +0100 +@@ -0,0 +1,170 @@ +/* -+ * Copyright (C) 2010-2016 Junjiro R. Okajima ++ * Copyright (C) 2010-2018 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by @@ -26076,6 +27212,7 @@ diff -urN /usr/share/empty/fs/aufs/procfs.c linux/fs/aufs/procfs.c + int err; + struct super_block *sb; + struct au_sbinfo *sbinfo; ++ struct hlist_bl_node *pos; + + err = -EBUSY; + if (unlikely(file->private_data)) @@ -26083,14 +27220,14 @@ diff -urN /usr/share/empty/fs/aufs/procfs.c linux/fs/aufs/procfs.c + + sb = NULL; + /* don't use au_sbilist_lock() here */ -+ spin_lock(&au_sbilist.spin); -+ hlist_for_each_entry(sbinfo, &au_sbilist.head, si_list) ++ hlist_bl_lock(&au_sbilist); ++ hlist_bl_for_each_entry(sbinfo, pos, &au_sbilist, si_list) + if (id == sysaufs_si_id(sbinfo)) { + kobject_get(&sbinfo->si_kobj); + sb = sbinfo->si_sb; + break; + } -+ spin_unlock(&au_sbilist.spin); ++ hlist_bl_unlock(&au_sbilist); + + err = -EINVAL; + if (unlikely(!sb)) @@ -26194,12 +27331,12 @@ diff -urN /usr/share/empty/fs/aufs/procfs.c linux/fs/aufs/procfs.c +out: + return err; +} -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 2016-10-09 16:55:36.496035060 +0200 +diff -urNp -x '*.orig' linux-4.9/fs/aufs/rdu.c linux-4.9/fs/aufs/rdu.c +--- linux-4.9/fs/aufs/rdu.c 1970-01-01 01:00:00.000000000 +0100 ++++ linux-4.9/fs/aufs/rdu.c 2021-02-24 16:15:09.534907296 +0100 @@ -0,0 +1,381 @@ +/* -+ * Copyright (C) 2005-2016 Junjiro R. Okajima ++ * Copyright (C) 2005-2018 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by @@ -26579,12 +27716,12 @@ diff -urN /usr/share/empty/fs/aufs/rdu.c linux/fs/aufs/rdu.c + return err; +} +#endif -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 2016-10-09 16:55:36.496035060 +0200 +diff -urNp -x '*.orig' linux-4.9/fs/aufs/rwsem.h linux-4.9/fs/aufs/rwsem.h +--- linux-4.9/fs/aufs/rwsem.h 1970-01-01 01:00:00.000000000 +0100 ++++ linux-4.9/fs/aufs/rwsem.h 2021-02-24 16:15:09.534907296 +0100 @@ -0,0 +1,198 @@ +/* -+ * Copyright (C) 2005-2016 Junjiro R. Okajima ++ * Copyright (C) 2005-2018 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by @@ -26781,12 +27918,12 @@ diff -urN /usr/share/empty/fs/aufs/rwsem.h linux/fs/aufs/rwsem.h + +#endif /* __KERNEL__ */ +#endif /* __AUFS_RWSEM_H__ */ -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 2016-10-09 16:55:38.889431135 +0200 -@@ -0,0 +1,355 @@ +diff -urNp -x '*.orig' linux-4.9/fs/aufs/sbinfo.c linux-4.9/fs/aufs/sbinfo.c +--- linux-4.9/fs/aufs/sbinfo.c 1970-01-01 01:00:00.000000000 +0100 ++++ linux-4.9/fs/aufs/sbinfo.c 2021-02-24 16:15:09.534907296 +0100 +@@ -0,0 +1,304 @@ +/* -+ * Copyright (C) 2005-2016 Junjiro R. Okajima ++ * Copyright (C) 2005-2018 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by @@ -26819,7 +27956,7 @@ diff -urN /usr/share/empty/fs/aufs/sbinfo.c linux/fs/aufs/sbinfo.c + + sbinfo = container_of(kobj, struct au_sbinfo, si_kobj); + for (i = 0; i < AuPlink_NHASH; i++) -+ AuDebugOn(!hlist_empty(&sbinfo->si_plink[i].head)); ++ AuDebugOn(!hlist_bl_empty(sbinfo->si_plink + i)); + AuDebugOn(atomic_read(&sbinfo->si_nowait.nw_len)); + + AuDebugOn(percpu_counter_sum(&sbinfo->si_ninodes)); @@ -26831,15 +27968,11 @@ diff -urN /usr/share/empty/fs/aufs/sbinfo.c linux/fs/aufs/sbinfo.c + au_br_free(sbinfo); + au_rw_write_unlock(&sbinfo->si_rwsem); + -+ au_delayed_kfree(sbinfo->si_branch); -+ for (i = 0; i < AU_NPIDMAP; i++) -+ if (sbinfo->au_si_pid.pid_bitmap[i]) -+ au_delayed_kfree(sbinfo->au_si_pid.pid_bitmap[i]); -+ mutex_destroy(&sbinfo->au_si_pid.pid_mtx); ++ kfree(sbinfo->si_branch); + mutex_destroy(&sbinfo->si_xib_mtx); + AuRwDestroy(&sbinfo->si_rwsem); + -+ au_delayed_kfree(sbinfo); ++ kfree(sbinfo); +} + +int au_si_alloc(struct super_block *sb) @@ -26863,7 +27996,6 @@ diff -urN /usr/share/empty/fs/aufs/sbinfo.c linux/fs/aufs/sbinfo.c + + au_nwt_init(&sbinfo->si_nowait); + au_rw_init_wlock(&sbinfo->si_rwsem); -+ mutex_init(&sbinfo->au_si_pid.pid_mtx); + + percpu_counter_init(&sbinfo->si_ninodes, 0, GFP_NOFS); + percpu_counter_init(&sbinfo->si_nfiles, 0, GFP_NOFS); @@ -26887,7 +28019,7 @@ diff -urN /usr/share/empty/fs/aufs/sbinfo.c linux/fs/aufs/sbinfo.c + sbinfo->si_xino_brid = -1; + /* leave si_xib_last_pindex and si_xib_next_bit */ + -+ au_sphl_init(&sbinfo->si_aopen); ++ INIT_HLIST_BL_HEAD(&sbinfo->si_aopen); + + sbinfo->si_rdcache = msecs_to_jiffies(AUFS_RDCACHE_DEF * MSEC_PER_SEC); + sbinfo->si_rdblk = AUFS_RDBLK_DEF; @@ -26895,11 +28027,11 @@ diff -urN /usr/share/empty/fs/aufs/sbinfo.c linux/fs/aufs/sbinfo.c + sbinfo->si_dirwh = AUFS_DIRWH_DEF; + + for (i = 0; i < AuPlink_NHASH; i++) -+ au_sphl_init(sbinfo->si_plink + i); ++ INIT_HLIST_BL_HEAD(sbinfo->si_plink + i); + init_waitqueue_head(&sbinfo->si_plink_wq); + spin_lock_init(&sbinfo->si_plink_maint_lock); + -+ au_sphl_init(&sbinfo->si_files); ++ INIT_HLIST_BL_HEAD(&sbinfo->si_files); + + /* with getattr by default */ + sbinfo->si_iop_array = aufs_iop; @@ -26911,9 +28043,9 @@ diff -urN /usr/share/empty/fs/aufs/sbinfo.c linux/fs/aufs/sbinfo.c + return 0; /* success */ + +out_br: -+ au_delayed_kfree(sbinfo->si_branch); ++ kfree(sbinfo->si_branch); +out_sbinfo: -+ au_delayed_kfree(sbinfo); ++ kfree(sbinfo); +out: + return err; +} @@ -27094,175 +28226,12 @@ diff -urN /usr/share/empty/fs/aufs/sbinfo.c linux/fs/aufs/sbinfo.c + di_write_unlock2(d1, d2); + si_read_unlock(d1->d_sb); +} -+ -+/* ---------------------------------------------------------------------- */ -+ -+static void si_pid_alloc(struct au_si_pid *au_si_pid, int idx) -+{ -+ unsigned long *p; -+ -+ BUILD_BUG_ON(sizeof(unsigned long) != -+ sizeof(*au_si_pid->pid_bitmap)); -+ -+ mutex_lock(&au_si_pid->pid_mtx); -+ p = au_si_pid->pid_bitmap[idx]; -+ while (!p) { -+ /* -+ * bad approach. -+ * but keeping 'si_pid_set()' void is more important. -+ */ -+ p = kcalloc(BITS_TO_LONGS(AU_PIDSTEP), -+ sizeof(*au_si_pid->pid_bitmap), -+ GFP_NOFS); -+ if (p) -+ break; -+ cond_resched(); -+ } -+ au_si_pid->pid_bitmap[idx] = p; -+ mutex_unlock(&au_si_pid->pid_mtx); -+} -+ -+void si_pid_set(struct super_block *sb) -+{ -+ pid_t bit; -+ int idx; -+ unsigned long *bitmap; -+ struct au_si_pid *au_si_pid; -+ -+ si_pid_idx_bit(&idx, &bit); -+ au_si_pid = &au_sbi(sb)->au_si_pid; -+ bitmap = au_si_pid->pid_bitmap[idx]; -+ if (!bitmap) { -+ si_pid_alloc(au_si_pid, idx); -+ bitmap = au_si_pid->pid_bitmap[idx]; -+ } -+ AuDebugOn(test_bit(bit, bitmap)); -+ set_bit(bit, bitmap); -+ /* smp_mb(); */ -+} -diff -urN /usr/share/empty/fs/aufs/spl.h linux/fs/aufs/spl.h ---- /usr/share/empty/fs/aufs/spl.h 1970-01-01 01:00:00.000000000 +0100 -+++ linux/fs/aufs/spl.h 2016-10-09 16:55:36.496035060 +0200 -@@ -0,0 +1,113 @@ -+/* -+ * Copyright (C) 2005-2016 Junjiro R. Okajima -+ * -+ * This program, aufs is free software; you can redistribute it and/or modify -+ * it under the terms of the GNU General Public License as published by -+ * the Free Software Foundation; either version 2 of the License, or -+ * (at your option) any later version. -+ * -+ * This program is distributed in the hope that it will be useful, -+ * but WITHOUT ANY WARRANTY; without even the implied warranty of -+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the -+ * GNU General Public License for more details. -+ * -+ * You should have received a copy of the GNU General Public License -+ * along with this program. If not, see . -+ */ -+ -+/* -+ * simple list protected by a spinlock -+ */ -+ -+#ifndef __AUFS_SPL_H__ -+#define __AUFS_SPL_H__ -+ -+#ifdef __KERNEL__ -+ -+#if 0 -+struct au_splhead { -+ spinlock_t spin; -+ struct list_head head; -+}; -+ -+static inline void au_spl_init(struct au_splhead *spl) -+{ -+ spin_lock_init(&spl->spin); -+ INIT_LIST_HEAD(&spl->head); -+} -+ -+static inline void au_spl_add(struct list_head *list, struct au_splhead *spl) -+{ -+ spin_lock(&spl->spin); -+ list_add(list, &spl->head); -+ spin_unlock(&spl->spin); -+} -+ -+static inline void au_spl_del(struct list_head *list, struct au_splhead *spl) -+{ -+ spin_lock(&spl->spin); -+ list_del(list); -+ spin_unlock(&spl->spin); -+} -+ -+static inline void au_spl_del_rcu(struct list_head *list, -+ struct au_splhead *spl) -+{ -+ spin_lock(&spl->spin); -+ list_del_rcu(list); -+ spin_unlock(&spl->spin); -+} -+#endif -+ -+/* ---------------------------------------------------------------------- */ -+ -+struct au_sphlhead { -+ spinlock_t spin; -+ struct hlist_head head; -+}; -+ -+static inline void au_sphl_init(struct au_sphlhead *sphl) -+{ -+ spin_lock_init(&sphl->spin); -+ INIT_HLIST_HEAD(&sphl->head); -+} -+ -+static inline void au_sphl_add(struct hlist_node *hlist, -+ struct au_sphlhead *sphl) -+{ -+ spin_lock(&sphl->spin); -+ hlist_add_head(hlist, &sphl->head); -+ spin_unlock(&sphl->spin); -+} -+ -+static inline void au_sphl_del(struct hlist_node *hlist, -+ struct au_sphlhead *sphl) -+{ -+ spin_lock(&sphl->spin); -+ hlist_del(hlist); -+ spin_unlock(&sphl->spin); -+} -+ -+static inline void au_sphl_del_rcu(struct hlist_node *hlist, -+ struct au_sphlhead *sphl) -+{ -+ spin_lock(&sphl->spin); -+ hlist_del_rcu(hlist); -+ spin_unlock(&sphl->spin); -+} -+ -+static inline unsigned long au_sphl_count(struct au_sphlhead *sphl) -+{ -+ unsigned long cnt; -+ struct hlist_node *pos; -+ -+ cnt = 0; -+ spin_lock(&sphl->spin); -+ hlist_for_each(pos, &sphl->head) -+ cnt++; -+ spin_unlock(&sphl->spin); -+ return cnt; -+} -+ -+#endif /* __KERNEL__ */ -+#endif /* __AUFS_SPL_H__ */ -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 2016-12-17 12:28:17.598545045 +0100 -@@ -0,0 +1,1046 @@ +diff -urNp -x '*.orig' linux-4.9/fs/aufs/super.c linux-4.9/fs/aufs/super.c +--- linux-4.9/fs/aufs/super.c 1970-01-01 01:00:00.000000000 +0100 ++++ linux-4.9/fs/aufs/super.c 2021-02-24 16:15:09.541574180 +0100 +@@ -0,0 +1,1049 @@ +/* -+ * Copyright (C) 2005-2016 Junjiro R. Okajima ++ * Copyright (C) 2005-2018 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by @@ -27309,7 +28278,7 @@ diff -urN /usr/share/empty/fs/aufs/super.c linux/fs/aufs/super.c +{ + struct inode *inode = container_of(head, struct inode, i_rcu); + -+ au_cache_dfree_icntnr(container_of(inode, struct au_icntnr, vfs_inode)); ++ au_cache_free_icntnr(container_of(inode, struct au_icntnr, vfs_inode)); +} + +static void aufs_destroy_inode(struct inode *inode) @@ -27551,6 +28520,7 @@ diff -urN /usr/share/empty/fs/aufs/super.c linux/fs/aufs/super.c + + au_fhsm_show(m, sbinfo); + ++ AuBool(DIRREN, dirren); + AuBool(SUM, sum); + /* AuBool(SUM_W, wsum); */ + AuBool(WARN_PERM, warn_perm); @@ -27710,12 +28680,10 @@ diff -urN /usr/share/empty/fs/aufs/super.c linux/fs/aufs/super.c + continue; + + h_sb = au_sbr_sb(sb, bindex); -+ if (h_sb->s_op->sync_fs) { -+ e = h_sb->s_op->sync_fs(h_sb, wait); -+ if (unlikely(e && !err)) -+ err = e; -+ /* go on even if an error happens */ -+ } ++ e = vfsub_sync_filesystem(h_sb, wait); ++ if (unlikely(e && !err)) ++ err = e; ++ /* go on even if an error happens */ + } + si_read_unlock(sb); + @@ -28099,7 +29067,7 @@ diff -urN /usr/share/empty/fs/aufs/super.c linux/fs/aufs/super.c +out_mtx: + inode_unlock(inode); +out_opts: -+ au_delayed_free_page((unsigned long)opts.opt); ++ free_page((unsigned long)opts.opt); +out: + err = cvt_err(err); + AuTraceErr(err); @@ -28115,7 +29083,10 @@ diff -urN /usr/share/empty/fs/aufs/super.c linux/fs/aufs/super.c + .statfs = aufs_statfs, + .put_super = aufs_put_super, + .sync_fs = aufs_sync_fs, -+ .remount_fs = aufs_remount_fs ++ .remount_fs = aufs_remount_fs, ++#ifdef CONFIG_AUFS_BDEV_LOOP ++ .real_loop = aufs_real_loop ++#endif +}; + +/* ---------------------------------------------------------------------- */ @@ -28240,7 +29211,7 @@ diff -urN /usr/share/empty/fs/aufs/super.c linux/fs/aufs/super.c + kobject_put(&sbinfo->si_kobj); + sb->s_fs_info = NULL; +out_opts: -+ au_delayed_free_page((unsigned long)opts.opt); ++ free_page((unsigned long)opts.opt); +out: + AuTraceErr(err); + err = cvt_err(err); @@ -28291,6 +29262,7 @@ diff -urN /usr/share/empty/fs/aufs/super.c linux/fs/aufs/super.c + if (au_opt_test(sbinfo->si_mntflags, PLINK)) + au_plink_put(sb, /*verbose*/1); + au_xino_clr(sb); ++ au_dr_opt_flush(sb); + sbinfo->si_sb = NULL; + aufs_write_unlock(sb->s_root); + au_nwt_flush(&sbinfo->si_nowait); @@ -28307,12 +29279,12 @@ diff -urN /usr/share/empty/fs/aufs/super.c linux/fs/aufs/super.c + /* no need to __module_get() and module_put(). */ + .owner = THIS_MODULE, +}; -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 2016-12-17 12:28:17.598545045 +0100 -@@ -0,0 +1,639 @@ +diff -urNp -x '*.orig' linux-4.9/fs/aufs/super.h linux-4.9/fs/aufs/super.h +--- linux-4.9/fs/aufs/super.h 1970-01-01 01:00:00.000000000 +0100 ++++ linux-4.9/fs/aufs/super.h 2021-02-24 16:15:09.534907296 +0100 +@@ -0,0 +1,617 @@ +/* -+ * Copyright (C) 2005-2016 Junjiro R. Okajima ++ * Copyright (C) 2005-2018 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by @@ -28339,8 +29311,8 @@ diff -urN /usr/share/empty/fs/aufs/super.h linux/fs/aufs/super.h + +#include +#include ++#include "hbl.h" +#include "rwsem.h" -+#include "spl.h" +#include "wkq.h" + +/* policies to select one among multiple writable branches */ @@ -28392,13 +29364,6 @@ diff -urN /usr/share/empty/fs/aufs/super.h linux/fs/aufs/super.h +#endif +}; + -+#define AU_PIDSTEP (int)(BITS_TO_LONGS(PID_MAX_DEFAULT) * BITS_PER_LONG) -+#define AU_NPIDMAP (int)DIV_ROUND_UP(PID_MAX_LIMIT, AU_PIDSTEP) -+struct au_si_pid { -+ unsigned long *pid_bitmap[AU_NPIDMAP]; -+ struct mutex pid_mtx; -+}; -+ +struct au_branch; +struct au_sbinfo { + /* nowait tasks in the system-wide workqueue */ @@ -28410,9 +29375,6 @@ diff -urN /usr/share/empty/fs/aufs/super.h linux/fs/aufs/super.h + */ + struct au_rwsem si_rwsem; + -+ /* prevent recursive locking in deleting inode */ -+ struct au_si_pid au_si_pid; -+ + /* + * dirty approach to protect sb->sb_inodes and ->s_files (gone) from + * remount. @@ -28472,7 +29434,7 @@ diff -urN /usr/share/empty/fs/aufs/super.h linux/fs/aufs/super.h +#endif + + /* dirty trick to suppoer atomic_open */ -+ struct au_sphlhead si_aopen; ++ struct hlist_bl_head si_aopen; + + /* vdir parameters */ + unsigned long si_rdcache; /* max cache time in jiffies */ @@ -28488,13 +29450,13 @@ diff -urN /usr/share/empty/fs/aufs/super.h linux/fs/aufs/super.h + unsigned int si_dirwh; + + /* pseudo_link list */ -+ struct au_sphlhead si_plink[AuPlink_NHASH]; ++ struct hlist_bl_head si_plink[AuPlink_NHASH]; + wait_queue_head_t si_plink_wq; + spinlock_t si_plink_maint_lock; + pid_t si_plink_maint_pid; + + /* file list */ -+ struct au_sphlhead si_files; ++ struct hlist_bl_head si_files; + + /* with/without getattr, brother of sb->s_d_op */ + struct inode_operations *si_iop_array; @@ -28516,7 +29478,7 @@ diff -urN /usr/share/empty/fs/aufs/super.h linux/fs/aufs/super.h +#endif + +#ifdef CONFIG_AUFS_SBILIST -+ struct hlist_node si_list; ++ struct hlist_bl_node si_list; +#endif + + /* dirty, necessary for unmounting, sysfs and sysrq */ @@ -28691,32 +29653,32 @@ diff -urN /usr/share/empty/fs/aufs/super.h linux/fs/aufs/super.h + +#ifdef CONFIG_AUFS_SBILIST +/* module.c */ -+extern struct au_sphlhead au_sbilist; ++extern struct hlist_bl_head au_sbilist; + +static inline void au_sbilist_init(void) +{ -+ au_sphl_init(&au_sbilist); ++ INIT_HLIST_BL_HEAD(&au_sbilist); +} + +static inline void au_sbilist_add(struct super_block *sb) +{ -+ au_sphl_add(&au_sbi(sb)->si_list, &au_sbilist); ++ au_hbl_add(&au_sbi(sb)->si_list, &au_sbilist); +} + +static inline void au_sbilist_del(struct super_block *sb) +{ -+ au_sphl_del(&au_sbi(sb)->si_list, &au_sbilist); ++ au_hbl_del(&au_sbi(sb)->si_list, &au_sbilist); +} + +#ifdef CONFIG_AUFS_MAGIC_SYSRQ +static inline void au_sbilist_lock(void) +{ -+ spin_lock(&au_sbilist.spin); ++ hlist_bl_lock(&au_sbilist); +} + +static inline void au_sbilist_unlock(void) +{ -+ spin_unlock(&au_sbilist.spin); ++ hlist_bl_unlock(&au_sbilist); +} +#define AuGFP_SBILIST GFP_ATOMIC +#else @@ -28754,42 +29716,30 @@ diff -urN /usr/share/empty/fs/aufs/super.h linux/fs/aufs/super.h + +/* ---------------------------------------------------------------------- */ + -+static inline void si_pid_idx_bit(int *idx, pid_t *bit) -+{ -+ /* the origin of pid is 1, but the bitmap's is 0 */ -+ *bit = current->pid - 1; -+ *idx = *bit / AU_PIDSTEP; -+ *bit %= AU_PIDSTEP; -+} ++/* current->atomic_flags */ ++/* this value should never corrupt the ones defined in linux/sched.h */ ++#define PFA_AUFS 7 ++ ++TASK_PFA_TEST(AUFS, test_aufs) /* task_test_aufs */ ++TASK_PFA_SET(AUFS, aufs) /* task_set_aufs */ ++TASK_PFA_CLEAR(AUFS, aufs) /* task_clear_aufs */ + +static inline int si_pid_test(struct super_block *sb) +{ -+ pid_t bit; -+ int idx; -+ unsigned long *bitmap; -+ -+ si_pid_idx_bit(&idx, &bit); -+ bitmap = au_sbi(sb)->au_si_pid.pid_bitmap[idx]; -+ if (bitmap) -+ return test_bit(bit, bitmap); -+ return 0; ++ return !!task_test_aufs(current); +} + +static inline void si_pid_clr(struct super_block *sb) +{ -+ pid_t bit; -+ int idx; -+ unsigned long *bitmap; -+ -+ si_pid_idx_bit(&idx, &bit); -+ bitmap = au_sbi(sb)->au_si_pid.pid_bitmap[idx]; -+ BUG_ON(!bitmap); -+ AuDebugOn(!test_bit(bit, bitmap)); -+ clear_bit(bit, bitmap); -+ /* smp_mb(); */ ++ AuDebugOn(!task_test_aufs(current)); ++ task_clear_aufs(current); +} + -+void si_pid_set(struct super_block *sb); ++static inline void si_pid_set(struct super_block *sb) ++{ ++ AuDebugOn(task_test_aufs(current)); ++ task_set_aufs(current); ++} + +/* ---------------------------------------------------------------------- */ + @@ -28950,12 +29900,12 @@ diff -urN /usr/share/empty/fs/aufs/super.h linux/fs/aufs/super.h + +#endif /* __KERNEL__ */ +#endif /* __AUFS_SUPER_H__ */ -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 2016-10-09 16:55:36.496035060 +0200 +diff -urNp -x '*.orig' linux-4.9/fs/aufs/sysaufs.c linux-4.9/fs/aufs/sysaufs.c +--- linux-4.9/fs/aufs/sysaufs.c 1970-01-01 01:00:00.000000000 +0100 ++++ linux-4.9/fs/aufs/sysaufs.c 2021-02-24 16:15:09.534907296 +0100 @@ -0,0 +1,104 @@ +/* -+ * Copyright (C) 2005-2016 Junjiro R. Okajima ++ * Copyright (C) 2005-2018 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by @@ -29058,12 +30008,12 @@ diff -urN /usr/share/empty/fs/aufs/sysaufs.c linux/fs/aufs/sysaufs.c +out: + return err; +} -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 2016-10-09 16:55:36.496035060 +0200 +diff -urNp -x '*.orig' linux-4.9/fs/aufs/sysaufs.h linux-4.9/fs/aufs/sysaufs.h +--- linux-4.9/fs/aufs/sysaufs.h 1970-01-01 01:00:00.000000000 +0100 ++++ linux-4.9/fs/aufs/sysaufs.h 2021-02-24 16:15:09.534907296 +0100 @@ -0,0 +1,101 @@ +/* -+ * Copyright (C) 2005-2016 Junjiro R. Okajima ++ * Copyright (C) 2005-2018 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by @@ -29163,12 +30113,12 @@ diff -urN /usr/share/empty/fs/aufs/sysaufs.h linux/fs/aufs/sysaufs.h + +#endif /* __KERNEL__ */ +#endif /* __SYSAUFS_H__ */ -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 2016-10-09 16:55:36.496035060 +0200 +diff -urNp -x '*.orig' linux-4.9/fs/aufs/sysfs.c linux-4.9/fs/aufs/sysfs.c +--- linux-4.9/fs/aufs/sysfs.c 1970-01-01 01:00:00.000000000 +0100 ++++ linux-4.9/fs/aufs/sysfs.c 2021-02-24 16:15:09.534907296 +0100 @@ -0,0 +1,376 @@ +/* -+ * Copyright (C) 2005-2016 Junjiro R. Okajima ++ * Copyright (C) 2005-2018 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by @@ -29378,7 +30328,7 @@ diff -urN /usr/share/empty/fs/aufs/sysfs.c linux/fs/aufs/sysfs.c + if (unlikely(err == PAGE_SIZE)) + err = -EFBIG; + } -+ au_delayed_kfree(seq); ++ kfree(seq); +out_unlock: + si_read_unlock(sb); +out: @@ -29449,9 +30399,9 @@ diff -urN /usr/share/empty/fs/aufs/sysfs.c linux/fs/aufs/sysfs.c + err = -EFAULT; + +out_seq: -+ au_delayed_kfree(seq); ++ kfree(seq); +out_buf: -+ au_delayed_free_page((unsigned long)buf); ++ free_page((unsigned long)buf); +out: + si_read_unlock(sb); + return err; @@ -29543,12 +30493,12 @@ diff -urN /usr/share/empty/fs/aufs/sysfs.c linux/fs/aufs/sysfs.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 2016-10-09 16:55:36.496035060 +0200 -@@ -0,0 +1,157 @@ +diff -urNp -x '*.orig' linux-4.9/fs/aufs/sysrq.c linux-4.9/fs/aufs/sysrq.c +--- linux-4.9/fs/aufs/sysrq.c 1970-01-01 01:00:00.000000000 +0100 ++++ linux-4.9/fs/aufs/sysrq.c 2021-02-24 16:15:09.534907296 +0100 +@@ -0,0 +1,159 @@ +/* -+ * Copyright (C) 2005-2016 Junjiro R. Okajima ++ * Copyright (C) 2005-2018 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by @@ -29579,7 +30529,8 @@ diff -urN /usr/share/empty/fs/aufs/sysrq.c linux/fs/aufs/sysrq.c + char *plevel; + struct au_sbinfo *sbinfo; + struct file *file; -+ struct au_sphlhead *files; ++ struct hlist_bl_head *files; ++ struct hlist_bl_node *pos; + struct au_finfo *finfo; + + plevel = au_plevel; @@ -29638,8 +30589,8 @@ diff -urN /usr/share/empty/fs/aufs/sysrq.c linux/fs/aufs/sysrq.c +#endif + pr("files\n"); + files = &au_sbi(sb)->si_files; -+ spin_lock(&files->spin); -+ hlist_for_each_entry(finfo, &files->head, fi_hlist) { ++ hlist_bl_lock(files); ++ hlist_bl_for_each_entry(finfo, pos, files, fi_hlist) { + umode_t mode; + + file = finfo->fi_file; @@ -29647,7 +30598,7 @@ diff -urN /usr/share/empty/fs/aufs/sysrq.c linux/fs/aufs/sysrq.c + if (!special_file(mode)) + au_dpri_file(file); + } -+ spin_unlock(&files->spin); ++ hlist_bl_unlock(files); + pr("done\n"); + +#undef pr @@ -29664,10 +30615,11 @@ diff -urN /usr/share/empty/fs/aufs/sysrq.c linux/fs/aufs/sysrq.c +static void au_sysrq(int key __maybe_unused) +{ + struct au_sbinfo *sbinfo; ++ struct hlist_bl_node *pos; + + lockdep_off(); + au_sbilist_lock(); -+ hlist_for_each_entry(sbinfo, &au_sbilist.head, si_list) ++ hlist_bl_for_each_entry(sbinfo, pos, &au_sbilist, si_list) + sysrq_sb(sbinfo->si_sb); + au_sbilist_unlock(); + lockdep_on(); @@ -29704,12 +30656,12 @@ diff -urN /usr/share/empty/fs/aufs/sysrq.c linux/fs/aufs/sysrq.c + if (unlikely(err)) + pr_err("err %d (ignored)\n", err); +} -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 2016-10-09 16:55:38.889431135 +0200 -@@ -0,0 +1,900 @@ +diff -urNp -x '*.orig' linux-4.9/fs/aufs/vdir.c linux-4.9/fs/aufs/vdir.c +--- linux-4.9/fs/aufs/vdir.c 1970-01-01 01:00:00.000000000 +0100 ++++ linux-4.9/fs/aufs/vdir.c 2021-02-24 16:15:09.538240738 +0100 +@@ -0,0 +1,893 @@ +/* -+ * Copyright (C) 2005-2016 Junjiro R. Okajima ++ * Copyright (C) 2005-2018 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by @@ -29820,7 +30772,7 @@ diff -urN /usr/share/empty/fs/aufs/vdir.c linux/fs/aufs/vdir.c + struct hlist_node *node; + + hlist_for_each_entry_safe(pos, node, head, wh_hash) -+ au_delayed_kfree(pos); ++ kfree(pos); +} + +static void au_nhash_de_do_free(struct hlist_head *head) @@ -29829,7 +30781,7 @@ diff -urN /usr/share/empty/fs/aufs/vdir.c linux/fs/aufs/vdir.c + struct hlist_node *node; + + hlist_for_each_entry_safe(pos, node, head, hash) -+ au_cache_dfree_vdir_dehstr(pos); ++ au_cache_free_vdir_dehstr(pos); +} + +static void au_nhash_do_free(struct au_nhash *nhash, @@ -29847,7 +30799,7 @@ diff -urN /usr/share/empty/fs/aufs/vdir.c linux/fs/aufs/vdir.c + nhash_count(head); + free(head++); + } -+ au_delayed_kfree(nhash->nh_head); ++ kfree(nhash->nh_head); +} + +void au_nhash_wh_free(struct au_nhash *whlist) @@ -30060,23 +31012,15 @@ diff -urN /usr/share/empty/fs/aufs/vdir.c linux/fs/aufs/vdir.c + +/* ---------------------------------------------------------------------- */ + -+void au_vdir_free(struct au_vdir *vdir, int atonce) ++void au_vdir_free(struct au_vdir *vdir) +{ + unsigned char **deblk; + + deblk = vdir->vd_deblk; -+ if (!atonce) { -+ while (vdir->vd_nblk--) -+ au_delayed_kfree(*deblk++); -+ au_delayed_kfree(vdir->vd_deblk); -+ au_cache_dfree_vdir(vdir); -+ } else { -+ /* not delayed */ -+ while (vdir->vd_nblk--) -+ kfree(*deblk++); -+ kfree(vdir->vd_deblk); -+ au_cache_free_vdir(vdir); -+ } ++ while (vdir->vd_nblk--) ++ kfree(*deblk++); ++ kfree(vdir->vd_deblk); ++ au_cache_free_vdir(vdir); +} + +static struct au_vdir *alloc_vdir(struct file *file) @@ -30110,10 +31054,10 @@ diff -urN /usr/share/empty/fs/aufs/vdir.c linux/fs/aufs/vdir.c + if (!err) + return vdir; /* success */ + -+ au_delayed_kfree(vdir->vd_deblk); ++ kfree(vdir->vd_deblk); + +out_free: -+ au_cache_dfree_vdir(vdir); ++ au_cache_free_vdir(vdir); +out: + vdir = ERR_PTR(err); + return vdir; @@ -30125,7 +31069,7 @@ diff -urN /usr/share/empty/fs/aufs/vdir.c linux/fs/aufs/vdir.c + union au_vdir_deblk_p p, deblk_end; + + while (vdir->vd_nblk > 1) { -+ au_delayed_kfree(vdir->vd_deblk[vdir->vd_nblk - 1]); ++ kfree(vdir->vd_deblk[vdir->vd_nblk - 1]); + /* vdir->vd_deblk[vdir->vd_nblk - 1] = NULL; */ + vdir->vd_nblk--; + } @@ -30256,7 +31200,7 @@ diff -urN /usr/share/empty/fs/aufs/vdir.c linux/fs/aufs/vdir.c + } + } + -+ au_delayed_free_page((unsigned long)o); ++ free_page((unsigned long)o); + +out: + AuTraceErr(err); @@ -30395,7 +31339,7 @@ diff -urN /usr/share/empty/fs/aufs/vdir.c linux/fs/aufs/vdir.c + if (allocated) + au_set_ivdir(inode, allocated); + } else if (allocated) -+ au_vdir_free(allocated, /*atonce*/0); ++ au_vdir_free(allocated); + +out: + return err; @@ -30490,7 +31434,7 @@ diff -urN /usr/share/empty/fs/aufs/vdir.c linux/fs/aufs/vdir.c + if (allocated) + au_set_fvdir_cache(file, allocated); + } else if (allocated) -+ au_vdir_free(allocated, /*atonce*/0); ++ au_vdir_free(allocated); + +out: + return err; @@ -30559,7 +31503,8 @@ diff -urN /usr/share/empty/fs/aufs/vdir.c linux/fs/aufs/vdir.c + +out: + /* smp_mb(); */ -+ AuTraceErr(!valid); ++ if (!valid) ++ AuDbg("valid %d\n", !valid); + return valid; +} + @@ -30608,12 +31553,12 @@ diff -urN /usr/share/empty/fs/aufs/vdir.c linux/fs/aufs/vdir.c + /* smp_mb(); */ + return 0; +} -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 2016-12-17 12:28:17.598545045 +0100 -@@ -0,0 +1,886 @@ +diff -urNp -x '*.orig' linux-4.9/fs/aufs/vfsub.c linux-4.9/fs/aufs/vfsub.c +--- linux-4.9/fs/aufs/vfsub.c 1970-01-01 01:00:00.000000000 +0100 ++++ linux-4.9/fs/aufs/vfsub.c 2021-02-24 16:15:09.538240738 +0100 +@@ -0,0 +1,894 @@ +/* -+ * Copyright (C) 2005-2016 Junjiro R. Okajima ++ * Copyright (C) 2005-2018 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by @@ -30633,29 +31578,36 @@ diff -urN /usr/share/empty/fs/aufs/vfsub.c linux/fs/aufs/vfsub.c + * sub-routines for VFS + */ + ++#include +#include +#include +#include +#include -+#ifdef CONFIG_AUFS_BR_FUSE -+#include "../fs/mount.h" -+#endif +#include "aufs.h" + +#ifdef CONFIG_AUFS_BR_FUSE +int vfsub_test_mntns(struct vfsmount *mnt, struct super_block *h_sb) +{ -+ struct nsproxy *ns; -+ + if (!au_test_fuse(h_sb) || !au_userns) + return 0; + -+ ns = current->nsproxy; -+ /* no {get,put}_nsproxy(ns) */ -+ return real_mount(mnt)->mnt_ns == ns->mnt_ns ? 0 : -EACCES; ++ return is_current_mnt_ns(mnt) ? 0 : -EACCES; +} +#endif + ++int vfsub_sync_filesystem(struct super_block *h_sb, int wait) ++{ ++ int err; ++ ++ lockdep_off(); ++ down_read(&h_sb->s_umount); ++ err = __sync_filesystem(h_sb, wait); ++ up_read(&h_sb->s_umount); ++ lockdep_on(); ++ ++ return err; ++} ++ +/* ---------------------------------------------------------------------- */ + +int vfsub_update_h_iattr(struct path *h_path, int *did) @@ -31199,6 +32151,7 @@ diff -urN /usr/share/empty/fs/aufs/vfsub.c linux/fs/aufs/vfsub.c + lockdep_on(); + if (err >= 0) + vfsub_update_h_iattr(&file->f_path, /*did*/NULL); /*ignore*/ ++ + return err; +} + @@ -31498,12 +32451,12 @@ diff -urN /usr/share/empty/fs/aufs/vfsub.c linux/fs/aufs/vfsub.c + + return err; +} -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 2016-12-17 12:28:17.598545045 +0100 -@@ -0,0 +1,316 @@ +diff -urNp -x '*.orig' linux-4.9/fs/aufs/vfsub.h linux-4.9/fs/aufs/vfsub.h +--- linux-4.9/fs/aufs/vfsub.h 1970-01-01 01:00:00.000000000 +0100 ++++ linux-4.9/fs/aufs/vfsub.h 2021-02-24 16:15:09.538240738 +0100 +@@ -0,0 +1,355 @@ +/* -+ * Copyright (C) 2005-2016 Junjiro R. Okajima ++ * Copyright (C) 2005-2018 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by @@ -31558,6 +32511,13 @@ diff -urN /usr/share/empty/fs/aufs/vfsub.h linux/fs/aufs/vfsub.h +#define MtxMustLock(mtx) AuDebugOn(!mutex_is_locked(mtx)) +#define IMustLock(i) AuDebugOn(!inode_is_locked(i)) + ++/* why VFS doesn't define it? */ ++static inline ++void vfsub_inode_lock_shared_nested(struct inode *inode, unsigned int sc) ++{ ++ down_read_nested(&inode->i_rwsem, sc); ++} ++ +/* ---------------------------------------------------------------------- */ + +static inline void vfsub_drop_nlink(struct inode *inode) @@ -31587,6 +32547,8 @@ diff -urN /usr/share/empty/fs/aufs/vfsub.h linux/fs/aufs/vfsub.h +AuStubInt0(vfsub_test_mntns, struct vfsmount *mnt, struct super_block *h_sb); +#endif + ++int vfsub_sync_filesystem(struct super_block *h_sb, int wait); ++ +/* ---------------------------------------------------------------------- */ + +int vfsub_update_h_iattr(struct path *h_path, int *did); @@ -31768,6 +32730,36 @@ diff -urN /usr/share/empty/fs/aufs/vfsub.h linux/fs/aufs/vfsub.h + struct file *h_file); +int vfsub_fsync(struct file *file, struct path *path, int datasync); + ++/* ++ * re-use branch fs's ioctl(FICLONE) while aufs itself doesn't support such ++ * ioctl. ++ */ ++static inline int vfsub_clone_file_range(struct file *src, struct file *dst, ++ u64 len) ++{ ++ int err; ++ ++ lockdep_off(); ++ err = vfs_clone_file_range(src, 0, dst, 0, len); ++ lockdep_on(); ++ ++ return err; ++} ++ ++/* copy_file_range(2) is a systemcall */ ++static inline ssize_t vfsub_copy_file_range(struct file *src, loff_t src_pos, ++ struct file *dst, loff_t dst_pos, ++ size_t len, unsigned int flags) ++{ ++ ssize_t ssz; ++ ++ lockdep_off(); ++ ssz = vfs_copy_file_range(src, src_pos, dst, dst_pos, len, flags); ++ lockdep_on(); ++ ++ return ssz; ++} ++ +/* ---------------------------------------------------------------------- */ + +static inline loff_t vfsub_llseek(struct file *file, loff_t offset, int origin) @@ -31818,12 +32810,12 @@ diff -urN /usr/share/empty/fs/aufs/vfsub.h linux/fs/aufs/vfsub.h + +#endif /* __KERNEL__ */ +#endif /* __AUFS_VFSUB_H__ */ -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 2016-12-17 12:28:17.598545045 +0100 +diff -urNp -x '*.orig' linux-4.9/fs/aufs/wbr_policy.c linux-4.9/fs/aufs/wbr_policy.c +--- linux-4.9/fs/aufs/wbr_policy.c 1970-01-01 01:00:00.000000000 +0100 ++++ linux-4.9/fs/aufs/wbr_policy.c 2021-02-24 16:15:09.538240738 +0100 @@ -0,0 +1,830 @@ +/* -+ * Copyright (C) 2005-2016 Junjiro R. Okajima ++ * Copyright (C) 2005-2018 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by @@ -32285,7 +33277,7 @@ diff -urN /usr/share/empty/fs/aufs/wbr_policy.c linux/fs/aufs/wbr_policy.c + + mfs->mfsrr_bytes = bavail; + AuDbg("b%d\n", mfs->mfs_bindex); -+ au_delayed_kfree(st); ++ kfree(st); +} + +static int au_wbr_create_mfs(struct dentry *dentry, unsigned int flags) @@ -32652,12 +33644,12 @@ diff -urN /usr/share/empty/fs/aufs/wbr_policy.c linux/fs/aufs/wbr_policy.c + .fin = au_wbr_create_fin_mfs + } +}; -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 2016-12-17 12:28:17.598545045 +0100 +diff -urNp -x '*.orig' linux-4.9/fs/aufs/whout.c linux-4.9/fs/aufs/whout.c +--- linux-4.9/fs/aufs/whout.c 1970-01-01 01:00:00.000000000 +0100 ++++ linux-4.9/fs/aufs/whout.c 2021-02-24 16:15:09.538240738 +0100 @@ -0,0 +1,1061 @@ +/* -+ * Copyright (C) 2005-2016 Junjiro R. Okajima ++ * Copyright (C) 2005-2018 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by @@ -32820,7 +33812,7 @@ diff -urN /usr/share/empty/fs/aufs/whout.c linux/fs/aufs/whout.c + +out_name: + if (name != defname) -+ au_delayed_kfree(name); ++ kfree(name); +out: + AuTraceErrPtr(dentry); + return dentry; @@ -33260,7 +34252,7 @@ diff -urN /usr/share/empty/fs/aufs/whout.c linux/fs/aufs/whout.c + au_br_put(a->br); + si_write_unlock(a->sb); + au_nwt_done(&au_sbi(a->sb)->si_nowait); -+ au_delayed_kfree(arg); ++ kfree(arg); + if (unlikely(err)) + AuIOErr("err %d\n", err); +} @@ -33288,7 +34280,7 @@ diff -urN /usr/share/empty/fs/aufs/whout.c linux/fs/aufs/whout.c + if (unlikely(wkq_err)) { + atomic_dec(&br->br_wbr->wbr_wh_running); + au_br_put(br); -+ au_delayed_kfree(arg); ++ kfree(arg); + } + do_dec = 0; + } @@ -33447,7 +34439,7 @@ diff -urN /usr/share/empty/fs/aufs/whout.c linux/fs/aufs/whout.c + wh_dentry = ERR_PTR(err); + if (!err) { + wh_dentry = vfsub_lkup_one(&wh_name, h_parent); -+ au_delayed_kfree(wh_name.name); ++ kfree(wh_name.name); + } + return wh_dentry; +} @@ -33523,7 +34515,7 @@ diff -urN /usr/share/empty/fs/aufs/whout.c linux/fs/aufs/whout.c + break; + } + } -+ au_delayed_free_page((unsigned long)wh_name.name); ++ free_page((unsigned long)wh_name.name); + +out: + return err; @@ -33565,7 +34557,7 @@ diff -urN /usr/share/empty/fs/aufs/whout.c linux/fs/aufs/whout.c + rdhash = AUFS_RDHASH_DEF; + err = au_nhash_alloc(&whtmp->whlist, rdhash, gfp); + if (unlikely(err)) { -+ au_delayed_kfree(whtmp); ++ kfree(whtmp); + whtmp = ERR_PTR(err); + } + @@ -33580,7 +34572,7 @@ diff -urN /usr/share/empty/fs/aufs/whout.c linux/fs/aufs/whout.c + dput(whtmp->wh_dentry); + iput(whtmp->dir); + au_nhash_wh_free(&whtmp->whlist); -+ au_delayed_kfree(whtmp); ++ kfree(whtmp); +} + +/* @@ -33717,12 +34709,12 @@ diff -urN /usr/share/empty/fs/aufs/whout.c linux/fs/aufs/whout.c + au_whtmp_rmdir_free(args); + } +} -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 2016-10-09 16:55:36.496035060 +0200 +diff -urNp -x '*.orig' linux-4.9/fs/aufs/whout.h linux-4.9/fs/aufs/whout.h +--- linux-4.9/fs/aufs/whout.h 1970-01-01 01:00:00.000000000 +0100 ++++ linux-4.9/fs/aufs/whout.h 2021-02-24 16:15:09.538240738 +0100 @@ -0,0 +1,85 @@ +/* -+ * Copyright (C) 2005-2016 Junjiro R. Okajima ++ * Copyright (C) 2005-2018 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by @@ -33806,12 +34798,12 @@ diff -urN /usr/share/empty/fs/aufs/whout.h linux/fs/aufs/whout.h + +#endif /* __KERNEL__ */ +#endif /* __AUFS_WHOUT_H__ */ -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 2016-10-09 16:55:36.496035060 +0200 -@@ -0,0 +1,213 @@ +diff -urNp -x '*.orig' linux-4.9/fs/aufs/wkq.c linux-4.9/fs/aufs/wkq.c +--- linux-4.9/fs/aufs/wkq.c 1970-01-01 01:00:00.000000000 +0100 ++++ linux-4.9/fs/aufs/wkq.c 2021-02-24 16:15:09.538240738 +0100 +@@ -0,0 +1,212 @@ +/* -+ * Copyright (C) 2005-2016 Junjiro R. Okajima ++ * Copyright (C) 2005-2018 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by @@ -33866,7 +34858,7 @@ diff -urN /usr/share/empty/fs/aufs/wkq.c linux/fs/aufs/wkq.c + else { + kobject_put(wkinfo->kobj); + module_put(THIS_MODULE); /* todo: ?? */ -+ au_delayed_kfree(wkinfo); ++ kfree(wkinfo); + } +} + @@ -33889,7 +34881,7 @@ diff -urN /usr/share/empty/fs/aufs/wkq.c linux/fs/aufs/wkq.c + +static void au_wkq_comp_free(struct completion *comp) +{ -+ au_delayed_kfree(comp); ++ kfree(comp); +} + +#else @@ -33953,11 +34945,10 @@ diff -urN /usr/share/empty/fs/aufs/wkq.c linux/fs/aufs/wkq.c + /* no timeout, no interrupt */ + wait_for_completion(wkinfo.comp); + au_wkq_comp_free(comp); -+ destroy_work_on_stack(&wkinfo.wk); + } + ++ destroy_work_on_stack(&wkinfo.wk); + return err; -+ +} + +/* @@ -34023,12 +35014,12 @@ diff -urN /usr/share/empty/fs/aufs/wkq.c linux/fs/aufs/wkq.c + + return err; +} -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 2016-10-09 16:55:36.496035060 +0200 +diff -urNp -x '*.orig' linux-4.9/fs/aufs/wkq.h linux-4.9/fs/aufs/wkq.h +--- linux-4.9/fs/aufs/wkq.h 1970-01-01 01:00:00.000000000 +0100 ++++ linux-4.9/fs/aufs/wkq.h 2021-02-24 16:15:09.538240738 +0100 @@ -0,0 +1,93 @@ +/* -+ * Copyright (C) 2005-2016 Junjiro R. Okajima ++ * Copyright (C) 2005-2018 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by @@ -34054,7 +35045,7 @@ diff -urN /usr/share/empty/fs/aufs/wkq.h linux/fs/aufs/wkq.h + +#ifdef __KERNEL__ + -+#include ++#include + +struct super_block; + @@ -34120,12 +35111,12 @@ diff -urN /usr/share/empty/fs/aufs/wkq.h linux/fs/aufs/wkq.h + +#endif /* __KERNEL__ */ +#endif /* __AUFS_WKQ_H__ */ -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 2016-12-17 12:28:17.598545045 +0100 -@@ -0,0 +1,332 @@ +diff -urNp -x '*.orig' linux-4.9/fs/aufs/xattr.c linux-4.9/fs/aufs/xattr.c +--- linux-4.9/fs/aufs/xattr.c 1970-01-01 01:00:00.000000000 +0100 ++++ linux-4.9/fs/aufs/xattr.c 2021-02-24 16:15:09.538240738 +0100 +@@ -0,0 +1,355 @@ +/* -+ * Copyright (C) 2014-2016 Junjiro R. Okajima ++ * Copyright (C) 2014-2018 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by @@ -34145,6 +35136,8 @@ diff -urN /usr/share/empty/fs/aufs/xattr.c linux/fs/aufs/xattr.c + * handling xattr functions + */ + ++#include ++#include +#include +#include "aufs.h" + @@ -34240,7 +35233,7 @@ diff -urN /usr/share/empty/fs/aufs/xattr.c linux/fs/aufs/xattr.c + h_isrc = d_inode(h_src); + h_idst = d_inode(h_dst); + inode_unlock(h_idst); -+ inode_lock_nested(h_isrc, AuLsc_I_CHILD); ++ vfsub_inode_lock_shared_nested(h_isrc, AuLsc_I_CHILD); + inode_lock_nested(h_idst, AuLsc_I_CHILD2); + unlocked = 0; + @@ -34266,7 +35259,7 @@ diff -urN /usr/share/empty/fs/aufs/xattr.c linux/fs/aufs/xattr.c + goto out; + err = vfs_listxattr(h_src, p, ssz); + } -+ inode_unlock(h_isrc); ++ inode_unlock_shared(h_isrc); + unlocked = 1; + AuDbg("err %d, ssz %zd\n", err, ssz); + if (unlikely(err < 0)) @@ -34302,21 +35295,32 @@ diff -urN /usr/share/empty/fs/aufs/xattr.c linux/fs/aufs/xattr.c + AuTraceErr(err); + } + -+ if (value) -+ au_delayed_kfree(value); ++ kfree(value); + +out_free: -+ if (o) -+ au_delayed_kfree(o); ++ kfree(o); +out: + if (!unlocked) -+ inode_unlock(h_isrc); ++ inode_unlock_shared(h_isrc); + AuTraceErr(err); + return err; +} + +/* ---------------------------------------------------------------------- */ + ++static int au_smack_reentering(struct super_block *sb) ++{ ++#if IS_ENABLED(CONFIG_SECURITY_SMACK) ++ /* ++ * as a part of lookup, smack_d_instantiate() is called, and it calls ++ * i_op->getxattr(). ouch. ++ */ ++ return si_pid_test(sb); ++#else ++ return 0; ++#endif ++} ++ +enum { + AU_XATTR_LIST, + AU_XATTR_GET @@ -34340,14 +35344,18 @@ diff -urN /usr/share/empty/fs/aufs/xattr.c linux/fs/aufs/xattr.c +static ssize_t au_lgxattr(struct dentry *dentry, struct au_lgxattr *arg) +{ + ssize_t err; ++ int reenter; + struct path h_path; + struct super_block *sb; + + sb = dentry->d_sb; -+ err = si_read_lock(sb, AuLock_FLUSH | AuLock_NOPLM); -+ if (unlikely(err)) -+ goto out; -+ err = au_h_path_getattr(dentry, /*force*/1, &h_path); ++ reenter = au_smack_reentering(sb); ++ if (!reenter) { ++ err = si_read_lock(sb, AuLock_FLUSH | AuLock_NOPLM); ++ if (unlikely(err)) ++ goto out; ++ } ++ err = au_h_path_getattr(dentry, /*force*/1, &h_path, reenter); + if (unlikely(err)) + goto out_si; + if (unlikely(!h_path.dentry)) @@ -34369,9 +35377,11 @@ diff -urN /usr/share/empty/fs/aufs/xattr.c linux/fs/aufs/xattr.c + } + +out_di: -+ di_read_unlock(dentry, AuLock_IR); ++ if (!reenter) ++ di_read_unlock(dentry, AuLock_IR); +out_si: -+ si_read_unlock(sb); ++ if (!reenter) ++ si_read_unlock(sb); +out: + AuTraceErr(err); + return err; @@ -34448,7 +35458,11 @@ diff -urN /usr/share/empty/fs/aufs/xattr.c linux/fs/aufs/xattr.c +}; + +static const struct xattr_handler *au_xattr_handlers[] = { -+ &au_xattr_handler, ++#ifdef CONFIG_FS_POSIX_ACL ++ &posix_acl_access_xattr_handler, ++ &posix_acl_default_xattr_handler, ++#endif ++ &au_xattr_handler, /* must be last */ + NULL +}; + @@ -34456,12 +35470,12 @@ diff -urN /usr/share/empty/fs/aufs/xattr.c linux/fs/aufs/xattr.c +{ + sb->s_xattr = au_xattr_handlers; +} -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 2016-10-09 16:55:36.496035060 +0200 -@@ -0,0 +1,1318 @@ +diff -urNp -x '*.orig' linux-4.9/fs/aufs/xino.c linux-4.9/fs/aufs/xino.c +--- linux-4.9/fs/aufs/xino.c 1970-01-01 01:00:00.000000000 +0100 ++++ linux-4.9/fs/aufs/xino.c 2021-02-24 16:15:09.538240738 +0100 +@@ -0,0 +1,1415 @@ +/* -+ * Copyright (C) 2005-2016 Junjiro R. Okajima ++ * Copyright (C) 2005-2018 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by @@ -34800,7 +35814,7 @@ diff -urN /usr/share/empty/fs/aufs/xino.c linux/fs/aufs/xino.c + AuErr1("statfs err %d, ignored\n", err); + +out_st: -+ au_delayed_kfree(st); ++ kfree(st); +out: + return err; +} @@ -34835,7 +35849,7 @@ diff -urN /usr/share/empty/fs/aufs/xino.c linux/fs/aufs/xino.c + au_br_put(br); + si_write_unlock(sb); + au_nwt_done(&au_sbi(sb)->si_nowait); -+ au_delayed_kfree(args); ++ kfree(args); +} + +static int xino_trunc_test(struct super_block *sb, struct au_branch *br) @@ -34889,7 +35903,7 @@ diff -urN /usr/share/empty/fs/aufs/xino.c linux/fs/aufs/xino.c + + pr_err("wkq %d\n", wkq_err); + au_br_put(br); -+ au_delayed_kfree(args); ++ kfree(args); + +out: + atomic_dec(&br->br_xino_running); @@ -35413,7 +36427,7 @@ diff -urN /usr/share/empty/fs/aufs/xino.c linux/fs/aufs/xino.c + (sb, au_sbr(sb, bindex)->br_xino.xi_file, page); + else + AuDbg("b%d\n", bindex); -+ au_delayed_free_page((unsigned long)page); ++ free_page((unsigned long)page); + +out: + return err; @@ -35491,7 +36505,7 @@ diff -urN /usr/share/empty/fs/aufs/xino.c linux/fs/aufs/xino.c + fput(sbinfo->si_xib); + sbinfo->si_xib = NULL; + if (sbinfo->si_xib_buf) -+ au_delayed_free_page((unsigned long)sbinfo->si_xib_buf); ++ free_page((unsigned long)sbinfo->si_xib_buf); + sbinfo->si_xib_buf = NULL; +} + @@ -35535,7 +36549,7 @@ diff -urN /usr/share/empty/fs/aufs/xino.c linux/fs/aufs/xino.c + +out_free: + if (sbinfo->si_xib_buf) -+ au_delayed_free_page((unsigned long)sbinfo->si_xib_buf); ++ free_page((unsigned long)sbinfo->si_xib_buf); + sbinfo->si_xib_buf = NULL; + if (err >= 0) + err = -EIO; @@ -35628,7 +36642,7 @@ diff -urN /usr/share/empty/fs/aufs/xino.c linux/fs/aufs/xino.c + fput(p->new); + else + break; -+ au_delayed_kfree(fpair); ++ kfree(fpair); +out: + return err; +} @@ -35739,7 +36753,7 @@ diff -urN /usr/share/empty/fs/aufs/xino.c linux/fs/aufs/xino.c + if (!IS_ERR(file)) + au_xino_brid_set(sb, br->br_id); + } -+ au_delayed_free_page((unsigned long)page); ++ free_page((unsigned long)page); + } else { + file = au_xino_create(sb, AUFS_XINO_DEFPATH, /*silent*/0); + if (IS_ERR(file)) @@ -35775,15 +36789,692 @@ diff -urN /usr/share/empty/fs/aufs/xino.c linux/fs/aufs/xino.c + 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 2016-12-17 12:28:38.769494865 +0100 -@@ -0,0 +1,419 @@ ++out: ++ return err; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++void au_xinondir_leave(struct super_block *sb, aufs_bindex_t bindex, ++ ino_t h_ino, int idx) ++{ ++ struct au_xino_file *xino; ++ ++ AuDebugOn(!au_opt_test(au_mntflags(sb), XINO)); ++ xino = &au_sbr(sb, bindex)->br_xino; ++ AuDebugOn(idx < 0 || xino->xi_nondir.total <= idx); ++ ++ spin_lock(&xino->xi_nondir.spin); ++ AuDebugOn(xino->xi_nondir.array[idx] != h_ino); ++ xino->xi_nondir.array[idx] = 0; ++ spin_unlock(&xino->xi_nondir.spin); ++ wake_up_all(&xino->xi_nondir.wqh); ++} ++ ++static int au_xinondir_find(struct au_xino_file *xino, ino_t h_ino) ++{ ++ int found, total, i; ++ ++ found = -1; ++ total = xino->xi_nondir.total; ++ for (i = 0; i < total; i++) { ++ if (xino->xi_nondir.array[i] != h_ino) ++ continue; ++ found = i; ++ break; ++ } ++ ++ return found; ++} ++ ++static int au_xinondir_expand(struct au_xino_file *xino) ++{ ++ int err, sz; ++ ino_t *p; ++ ++ BUILD_BUG_ON(KMALLOC_MAX_SIZE > INT_MAX); ++ ++ err = -ENOMEM; ++ sz = xino->xi_nondir.total * sizeof(ino_t); ++ if (unlikely(sz > KMALLOC_MAX_SIZE / 2)) ++ goto out; ++ p = au_kzrealloc(xino->xi_nondir.array, sz, sz << 1, GFP_ATOMIC, ++ /*may_shrink*/0); ++ if (p) { ++ xino->xi_nondir.array = p; ++ xino->xi_nondir.total <<= 1; ++ AuDbg("xi_nondir.total %d\n", xino->xi_nondir.total); ++ err = 0; ++ } ++ ++out: ++ return err; ++} ++ ++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_file *xino; ++ ++ err = 0; ++ *idx = -1; ++ if (!au_opt_test(au_mntflags(sb), XINO)) ++ goto out; /* no xino */ ++ ++ xino = &au_sbr(sb, bindex)->br_xino; ++ ++again: ++ spin_lock(&xino->xi_nondir.spin); ++ found = au_xinondir_find(xino, h_ino); ++ if (found == -1) { ++ empty = au_xinondir_find(xino, /*h_ino*/0); ++ if (empty == -1) { ++ empty = xino->xi_nondir.total; ++ err = au_xinondir_expand(xino); ++ if (unlikely(err)) ++ goto out_unlock; ++ } ++ xino->xi_nondir.array[empty] = h_ino; ++ *idx = empty; ++ } else { ++ spin_unlock(&xino->xi_nondir.spin); ++ wait_event(xino->xi_nondir.wqh, ++ xino->xi_nondir.array[found] != h_ino); ++ goto again; ++ } ++ ++out_unlock: ++ spin_unlock(&xino->xi_nondir.spin); ++out: ++ return err; ++} +diff -urNp -x '*.orig' linux-4.9/fs/dcache.c linux-4.9/fs/dcache.c +--- linux-4.9/fs/dcache.c 2021-02-24 16:14:57.291175760 +0100 ++++ linux-4.9/fs/dcache.c 2021-02-24 16:15:09.514906646 +0100 +@@ -1206,7 +1206,7 @@ enum d_walk_ret { + * + * The @enter() and @finish() 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 *), + void (*finish)(void *)) + { +@@ -1314,6 +1314,7 @@ rename_retry: + seq = 1; + goto again; + } ++EXPORT_SYMBOL_GPL(d_walk); + + /* + * Search for at least 1 mount point in the dentry's subdirs. +@@ -2935,6 +2936,7 @@ void d_exchange(struct dentry *dentry1, + + write_sequnlock(&rename_lock); + } ++EXPORT_SYMBOL_GPL(d_exchange); + + /** + * d_ancestor - search for an ancestor +diff -urNp -x '*.orig' linux-4.9/fs/exec.c linux-4.9/fs/exec.c +--- linux-4.9/fs/exec.c 2021-02-24 16:14:56.427814341 +0100 ++++ linux-4.9/fs/exec.c 2021-02-24 16:15:09.514906646 +0100 +@@ -104,6 +104,7 @@ 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 -urNp -x '*.orig' linux-4.9/fs/fcntl.c linux-4.9/fs/fcntl.c +--- linux-4.9/fs/fcntl.c 2021-02-24 16:14:57.297842644 +0100 ++++ linux-4.9/fs/fcntl.c 2021-02-24 16:15:09.514906646 +0100 +@@ -30,7 +30,7 @@ + + #define SETFL_MASK (O_APPEND | O_NONBLOCK | O_NDELAY | O_DIRECT | O_NOATIME) + +-static int setfl(int fd, struct file * filp, unsigned long arg) ++int setfl(int fd, struct file * filp, unsigned long arg) + { + struct inode * inode = file_inode(filp); + int error = 0; +@@ -61,6 +61,8 @@ static int setfl(int fd, struct file * f + + 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; + +@@ -81,6 +83,7 @@ static int setfl(int fd, struct file * f + out: + return error; + } ++EXPORT_SYMBOL_GPL(setfl); + + static void f_modown(struct file *filp, struct pid *pid, enum pid_type type, + int force) +diff -urNp -x '*.orig' linux-4.9/fs/file_table.c linux-4.9/fs/file_table.c +--- linux-4.9/fs/file_table.c 2021-02-24 16:14:57.297842644 +0100 ++++ linux-4.9/fs/file_table.c 2021-02-24 16:15:09.514906646 +0100 +@@ -151,6 +151,7 @@ over: + } + return ERR_PTR(-ENFILE); + } ++EXPORT_SYMBOL_GPL(get_empty_filp); + + /** + * alloc_file - allocate and initialize a 'struct file' +@@ -264,6 +265,7 @@ void flush_delayed_fput(void) + { + delayed_fput(NULL); + } ++EXPORT_SYMBOL_GPL(flush_delayed_fput); + + static DECLARE_DELAYED_WORK(delayed_fput_work, delayed_fput); + +@@ -306,6 +308,7 @@ void __fput_sync(struct file *file) + } + + EXPORT_SYMBOL(fput); ++EXPORT_SYMBOL_GPL(__fput_sync); + + void put_filp(struct file *file) + { +@@ -316,6 +319,7 @@ void put_filp(struct file *file) + file_free(file); + } + } ++EXPORT_SYMBOL_GPL(put_filp); + + void __init files_init(void) + { +diff -urNp -x '*.orig' linux-4.9/fs/inode.c linux-4.9/fs/inode.c +--- linux-4.9/fs/inode.c 2021-02-24 16:14:57.301176086 +0100 ++++ linux-4.9/fs/inode.c 2021-02-24 16:15:09.514906646 +0100 +@@ -1651,7 +1651,7 @@ EXPORT_SYMBOL(generic_update_time); + * This does the actual work of updating an inodes time or version. Must have + * had called mnt_want_write() before calling this. + */ +-static int update_time(struct inode *inode, struct timespec *time, int flags) ++int update_time(struct inode *inode, struct timespec *time, int flags) + { + int (*update_time)(struct inode *, struct timespec *, int); + +@@ -1660,6 +1660,7 @@ static int update_time(struct inode *ino + + return update_time(inode, time, flags); + } ++EXPORT_SYMBOL_GPL(update_time); + + /** + * touch_atime - update the access time +diff -urNp -x '*.orig' linux-4.9/fs/namespace.c linux-4.9/fs/namespace.c +--- linux-4.9/fs/namespace.c 2021-02-24 16:14:57.304509527 +0100 ++++ linux-4.9/fs/namespace.c 2021-02-24 16:15:09.514906646 +0100 +@@ -472,6 +472,7 @@ void __mnt_drop_write(struct vfsmount *m + mnt_dec_writers(real_mount(mnt)); + preempt_enable(); + } ++EXPORT_SYMBOL_GPL(__mnt_drop_write); + + /** + * mnt_drop_write - give up write access to a mount +@@ -804,6 +805,13 @@ static inline int check_mnt(struct mount + 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 + */ +@@ -1905,6 +1913,7 @@ int iterate_mounts(int (*f)(struct vfsmo + } + return 0; + } ++EXPORT_SYMBOL_GPL(iterate_mounts); + + static void cleanup_group_ids(struct mount *mnt, struct mount *end) + { +diff -urNp -x '*.orig' linux-4.9/fs/notify/group.c linux-4.9/fs/notify/group.c +--- linux-4.9/fs/notify/group.c 2016-12-11 20:17:54.000000000 +0100 ++++ linux-4.9/fs/notify/group.c 2021-02-24 16:15:09.514906646 +0100 +@@ -22,6 +22,7 @@ + #include + #include + #include ++#include + + #include + #include "fsnotify.h" +@@ -100,6 +101,7 @@ void fsnotify_get_group(struct fsnotify_ + { + atomic_inc(&group->refcnt); + } ++EXPORT_SYMBOL_GPL(fsnotify_get_group); + + /* + * Drop a reference to a group. Free it if it's through. +@@ -109,6 +111,7 @@ void fsnotify_put_group(struct fsnotify_ + if (atomic_dec_and_test(&group->refcnt)) + fsnotify_final_destroy_group(group); + } ++EXPORT_SYMBOL_GPL(fsnotify_put_group); + + /* + * Create a new fsnotify_group and hold a reference for the group returned. +@@ -137,6 +140,7 @@ struct fsnotify_group *fsnotify_alloc_gr + + return group; + } ++EXPORT_SYMBOL_GPL(fsnotify_alloc_group); + + int fsnotify_fasync(int fd, struct file *file, int on) + { +diff -urNp -x '*.orig' linux-4.9/fs/notify/mark.c linux-4.9/fs/notify/mark.c +--- linux-4.9/fs/notify/mark.c 2016-12-11 20:17:54.000000000 +0100 ++++ linux-4.9/fs/notify/mark.c 2021-02-24 16:15:09.514906646 +0100 +@@ -113,6 +113,7 @@ void fsnotify_put_mark(struct fsnotify_m + mark->free_mark(mark); + } + } ++EXPORT_SYMBOL_GPL(fsnotify_put_mark); + + /* Calculate mask of events for a list of marks */ + u32 fsnotify_recalc_mask(struct hlist_head *head) +@@ -230,6 +231,7 @@ void fsnotify_destroy_mark(struct fsnoti + mutex_unlock(&group->mark_mutex); + fsnotify_free_mark(mark); + } ++EXPORT_SYMBOL_GPL(fsnotify_destroy_mark); + + void fsnotify_destroy_marks(struct hlist_head *head, spinlock_t *lock) + { +@@ -415,6 +417,7 @@ err: + + return ret; + } ++EXPORT_SYMBOL_GPL(fsnotify_add_mark); + + int fsnotify_add_mark(struct fsnotify_mark *mark, struct fsnotify_group *group, + struct inode *inode, struct vfsmount *mnt, int allow_dups) +@@ -533,6 +536,7 @@ void fsnotify_init_mark(struct fsnotify_ + atomic_set(&mark->refcnt, 1); + mark->free_mark = free_mark; + } ++EXPORT_SYMBOL_GPL(fsnotify_init_mark); + + /* + * Destroy all marks in destroy_list, waits for SRCU period to finish before +diff -urNp -x '*.orig' linux-4.9/fs/open.c linux-4.9/fs/open.c +--- linux-4.9/fs/open.c 2021-02-24 16:14:57.311176411 +0100 ++++ linux-4.9/fs/open.c 2021-02-24 16:15:09.514906646 +0100 +@@ -69,6 +69,7 @@ int do_truncate(struct dentry *dentry, l + inode_unlock(dentry->d_inode); + return ret; + } ++EXPORT_SYMBOL_GPL(do_truncate); + + long vfs_truncate(struct path *path, loff_t length) + { +@@ -737,6 +738,7 @@ int open_check_o_direct(struct file *f) + } + return 0; + } ++EXPORT_SYMBOL_GPL(open_check_o_direct); + + static int do_dentry_open(struct file *f, + struct inode *inode, +diff -urNp -x '*.orig' linux-4.9/fs/proc/base.c linux-4.9/fs/proc/base.c +--- linux-4.9/fs/proc/base.c 2021-02-24 16:14:57.374511804 +0100 ++++ linux-4.9/fs/proc/base.c 2021-02-24 16:15:09.508239763 +0100 +@@ -2016,7 +2016,7 @@ static int map_files_get_link(struct den + down_read(&mm->mmap_sem); + vma = find_exact_vma(mm, vm_start, vm_end); + if (vma && vma->vm_file) { +- *path = vma->vm_file->f_path; ++ *path = vma_pr_or_file(vma)->f_path; + path_get(path); + rc = 0; + } +diff -urNp -x '*.orig' linux-4.9/fs/proc/nommu.c linux-4.9/fs/proc/nommu.c +--- linux-4.9/fs/proc/nommu.c 2016-12-11 20:17:54.000000000 +0100 ++++ linux-4.9/fs/proc/nommu.c 2021-02-24 16:15:09.508239763 +0100 +@@ -45,7 +45,10 @@ static int nommu_region_show(struct seq_ + 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 -urNp -x '*.orig' linux-4.9/fs/proc/task_mmu.c linux-4.9/fs/proc/task_mmu.c +--- linux-4.9/fs/proc/task_mmu.c 2021-02-24 16:14:56.501150059 +0100 ++++ linux-4.9/fs/proc/task_mmu.c 2021-02-24 16:15:09.508239763 +0100 +@@ -291,7 +291,10 @@ show_map_vma(struct seq_file *m, struct + 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; +@@ -1648,7 +1651,7 @@ static int show_numa_map(struct seq_file + 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; + struct mm_walk walk = { + .hugetlb_entry = gather_hugetlb_stats, +diff -urNp -x '*.orig' linux-4.9/fs/proc/task_nommu.c linux-4.9/fs/proc/task_nommu.c +--- linux-4.9/fs/proc/task_nommu.c 2016-12-11 20:17:54.000000000 +0100 ++++ linux-4.9/fs/proc/task_nommu.c 2021-02-24 16:15:09.508239763 +0100 +@@ -155,7 +155,10 @@ static int nommu_vma_show(struct seq_fil + 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 -urNp -x '*.orig' linux-4.9/fs/read_write.c linux-4.9/fs/read_write.c +--- linux-4.9/fs/read_write.c 2021-02-24 16:14:56.504483501 +0100 ++++ linux-4.9/fs/read_write.c 2021-02-24 16:15:09.514906646 +0100 +@@ -517,6 +517,30 @@ ssize_t __vfs_write(struct file *file, c + } + EXPORT_SYMBOL(__vfs_write); + ++vfs_readf_t vfs_readf(struct file *file) ++{ ++ const struct file_operations *fop = file->f_op; ++ ++ if (fop->read) ++ return fop->read; ++ if (fop->read_iter) ++ return new_sync_read; ++ return ERR_PTR(-ENOSYS); ++} ++EXPORT_SYMBOL_GPL(vfs_readf); ++ ++vfs_writef_t vfs_writef(struct file *file) ++{ ++ const struct file_operations *fop = file->f_op; ++ ++ if (fop->write) ++ return fop->write; ++ if (fop->write_iter) ++ return new_sync_write; ++ return ERR_PTR(-ENOSYS); ++} ++EXPORT_SYMBOL_GPL(vfs_writef); ++ + ssize_t __kernel_write(struct file *file, const char *buf, size_t count, loff_t *pos) + { + mm_segment_t old_fs; +diff -urNp -x '*.orig' linux-4.9/fs/splice.c linux-4.9/fs/splice.c +--- linux-4.9/fs/splice.c 2021-02-24 16:14:56.507816943 +0100 ++++ linux-4.9/fs/splice.c 2021-02-24 16:15:09.518240088 +0100 +@@ -856,8 +856,8 @@ EXPORT_SYMBOL(generic_splice_sendpage); + /* + * Attempt to initiate a splice from pipe to file. + */ +-static long do_splice_from(struct pipe_inode_info *pipe, struct file *out, +- loff_t *ppos, size_t len, unsigned int flags) ++long do_splice_from(struct pipe_inode_info *pipe, struct file *out, ++ loff_t *ppos, size_t len, unsigned int flags) + { + ssize_t (*splice_write)(struct pipe_inode_info *, struct file *, + loff_t *, size_t, unsigned int); +@@ -869,13 +869,14 @@ static long do_splice_from(struct pipe_i + + return splice_write(pipe, out, ppos, len, flags); + } ++EXPORT_SYMBOL_GPL(do_splice_from); + + /* + * Attempt to initiate a splice from a file to a pipe. + */ +-static long do_splice_to(struct file *in, loff_t *ppos, +- struct pipe_inode_info *pipe, size_t len, +- unsigned int flags) ++long do_splice_to(struct file *in, loff_t *ppos, ++ struct pipe_inode_info *pipe, size_t len, ++ unsigned int flags) + { + ssize_t (*splice_read)(struct file *, loff_t *, + struct pipe_inode_info *, size_t, unsigned int); +@@ -898,6 +899,7 @@ static long do_splice_to(struct file *in + + return splice_read(in, ppos, pipe, len, flags); + } ++EXPORT_SYMBOL_GPL(do_splice_to); + + /** + * splice_direct_to_actor - splices data directly between two non-pipes +diff -urNp -x '*.orig' linux-4.9/fs/sync.c linux-4.9/fs/sync.c +--- linux-4.9/fs/sync.c 2016-12-11 20:17:54.000000000 +0100 ++++ linux-4.9/fs/sync.c 2021-02-24 16:15:09.518240088 +0100 +@@ -27,7 +27,7 @@ + * wait == 1 case since in that case write_inode() functions do + * sync_dirty_buffer() and thus effectively write one block at a time. + */ +-static int __sync_filesystem(struct super_block *sb, int wait) ++int __sync_filesystem(struct super_block *sb, int wait) + { + if (wait) + sync_inodes_sb(sb); +@@ -38,6 +38,7 @@ static int __sync_filesystem(struct supe + sb->s_op->sync_fs(sb, wait); + return __sync_blockdev(sb->s_bdev, wait); + } ++EXPORT_SYMBOL_GPL(__sync_filesystem); + + /* + * Write out and wait upon all dirty data associated with this +diff -urNp -x '*.orig' linux-4.9/fs/xattr.c linux-4.9/fs/xattr.c +--- linux-4.9/fs/xattr.c 2021-02-24 16:14:57.317843295 +0100 ++++ linux-4.9/fs/xattr.c 2021-02-24 16:15:09.518240088 +0100 +@@ -334,6 +334,7 @@ vfs_getxattr_alloc(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 -urNp -x '*.orig' linux-4.9/include/linux/file.h linux-4.9/include/linux/file.h +--- linux-4.9/include/linux/file.h 2016-12-11 20:17:54.000000000 +0100 ++++ linux-4.9/include/linux/file.h 2021-02-24 16:15:09.508239763 +0100 +@@ -19,6 +19,7 @@ struct dentry; + struct path; + extern struct file *alloc_file(struct path *, fmode_t mode, + const struct file_operations *fop); ++extern struct file *get_empty_filp(void); + + static inline void fput_light(struct file *file, int fput_needed) + { +diff -urNp -x '*.orig' linux-4.9/include/linux/fs.h linux-4.9/include/linux/fs.h +--- linux-4.9/include/linux/fs.h 2021-02-24 16:14:57.317843295 +0100 ++++ linux-4.9/include/linux/fs.h 2021-02-24 16:15:09.541574180 +0100 +@@ -1315,6 +1315,7 @@ extern void fasync_free(struct fasync_st + /* can be called from interrupts */ + extern void kill_fasync(struct fasync_struct **, int, int); + ++extern int setfl(int fd, struct file * filp, unsigned long arg); + extern void __f_setown(struct file *filp, struct pid *, enum pid_type, int force); + extern void f_setown(struct file *filp, unsigned long arg, int force); + extern void f_delown(struct file *filp); +@@ -1745,6 +1746,7 @@ struct file_operations { + ssize_t (*sendpage) (struct file *, struct page *, int, size_t, loff_t *, int); + unsigned long (*get_unmapped_area)(struct file *, unsigned long, unsigned long, unsigned long, unsigned long); + int (*check_flags)(int); ++ int (*setfl)(struct file *, unsigned long); + int (*flock) (struct file *, int, struct file_lock *); + ssize_t (*splice_write)(struct pipe_inode_info *, struct file *, loff_t *, size_t, unsigned int); + ssize_t (*splice_read)(struct file *, loff_t *, struct pipe_inode_info *, size_t, unsigned int); +@@ -1800,6 +1802,12 @@ ssize_t rw_copy_check_uvector(int type, + struct iovec **ret_pointer); + ssize_t vfs_sendfile(struct file *, struct file *, loff_t *, size_t, loff_t); + ++typedef ssize_t (*vfs_readf_t)(struct file *, char __user *, size_t, loff_t *); ++typedef ssize_t (*vfs_writef_t)(struct file *, const char __user *, size_t, ++ loff_t *); ++vfs_readf_t vfs_readf(struct file *file); ++vfs_writef_t vfs_writef(struct file *file); ++ + extern ssize_t __vfs_read(struct file *, char __user *, size_t, loff_t *); + extern ssize_t __vfs_write(struct file *, const char __user *, size_t, loff_t *); + extern ssize_t vfs_read(struct file *, char __user *, size_t, loff_t *); +@@ -1847,6 +1855,10 @@ struct super_operations { + struct shrink_control *); + long (*free_cached_objects)(struct super_block *, + struct shrink_control *); ++#if defined(CONFIG_BLK_DEV_LOOP) || defined(CONFIG_BLK_DEV_LOOP_MODULE) ++ /* and aufs */ ++ struct file *(*real_loop)(struct file *); ++#endif + }; + + /* +@@ -2197,6 +2209,7 @@ extern int current_umask(void); + extern void ihold(struct inode * inode); + extern void iput(struct inode *); + extern int generic_update_time(struct inode *, struct timespec *, int); ++extern int update_time(struct inode *, struct timespec *, int); + + /* /sys/fs */ + extern struct kobject *fs_kobj; +@@ -2479,6 +2492,7 @@ static inline bool sb_is_blkdev_sb(struc + return false; + } + #endif ++extern int __sync_filesystem(struct super_block *, int); + extern int sync_filesystem(struct super_block *); + extern const struct file_operations def_blk_fops; + extern const struct file_operations def_chr_fops; +diff -urNp -x '*.orig' linux-4.9/include/linux/mm.h linux-4.9/include/linux/mm.h +--- linux-4.9/include/linux/mm.h 2021-02-24 16:14:56.574485779 +0100 ++++ linux-4.9/include/linux/mm.h 2021-02-24 16:15:09.508239763 +0100 +@@ -1314,6 +1314,28 @@ static inline int fixup_user_fault(struc + } + #endif + ++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); ++ ++#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__) ++ ++#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); ++ ++#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 */ ++ + 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 -urNp -x '*.orig' linux-4.9/include/linux/mm_types.h linux-4.9/include/linux/mm_types.h +--- linux-4.9/include/linux/mm_types.h 2021-02-24 16:14:56.574485779 +0100 ++++ linux-4.9/include/linux/mm_types.h 2021-02-24 16:15:09.508239763 +0100 +@@ -280,6 +280,7 @@ 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 */ ++ struct file *vm_prfile; /* the virtual backing file or NULL */ + + int vm_usage; /* region usage count (access under nommu_region_sem) */ + bool vm_icache_flushed : 1; /* true if the icache has been flushed for +@@ -354,6 +355,7 @@ 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). */ ++ struct file *vm_prfile; /* shadow of vm_file */ + void * vm_private_data; /* was vm_pte (shared mem) */ + + #ifndef CONFIG_MMU +diff -urNp -x '*.orig' linux-4.9/include/linux/mnt_namespace.h linux-4.9/include/linux/mnt_namespace.h +--- linux-4.9/include/linux/mnt_namespace.h 2016-12-11 20:17:54.000000000 +0100 ++++ linux-4.9/include/linux/mnt_namespace.h 2021-02-24 16:15:09.508239763 +0100 +@@ -5,11 +5,14 @@ + struct mnt_namespace; + struct fs_struct; + struct user_namespace; ++struct vfsmount; + + extern struct mnt_namespace *copy_mnt_ns(unsigned long, struct mnt_namespace *, + struct user_namespace *, struct fs_struct *); + extern void put_mnt_ns(struct mnt_namespace *ns); + ++extern int is_current_mnt_ns(struct vfsmount *mnt); ++ + extern const struct file_operations proc_mounts_operations; + extern const struct file_operations proc_mountinfo_operations; + extern const struct file_operations proc_mountstats_operations; +diff -urNp -x '*.orig' linux-4.9/include/linux/splice.h linux-4.9/include/linux/splice.h +--- linux-4.9/include/linux/splice.h 2016-12-11 20:17:54.000000000 +0100 ++++ linux-4.9/include/linux/splice.h 2021-02-24 16:15:09.508239763 +0100 +@@ -86,4 +86,10 @@ extern void spd_release_page(struct spli + + 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 -urNp -x '*.orig' linux-4.9/include/uapi/linux/Kbuild linux-4.9/include/uapi/linux/Kbuild +--- linux-4.9/include/uapi/linux/Kbuild 2021-02-24 16:14:56.617820522 +0100 ++++ linux-4.9/include/uapi/linux/Kbuild 2021-02-24 16:15:09.501572879 +0100 +@@ -59,6 +59,7 @@ header-y += atmsvc.h + header-y += atm_tcp.h + header-y += atm_zatm.h + header-y += audit.h ++header-y += aufs_type.h + header-y += auto_fs4.h + header-y += auto_fs.h + header-y += auxvec.h +diff -urNp -x '*.orig' linux-4.9/include/uapi/linux/aufs_type.h linux-4.9/include/uapi/linux/aufs_type.h +--- linux-4.9/include/uapi/linux/aufs_type.h 1970-01-01 01:00:00.000000000 +0100 ++++ linux-4.9/include/uapi/linux/aufs_type.h 2021-02-24 16:15:09.538240738 +0100 +@@ -0,0 +1,447 @@ +/* -+ * Copyright (C) 2005-2016 Junjiro R. Okajima ++ * Copyright (C) 2005-2018 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by @@ -35823,7 +37514,7 @@ diff -urN /usr/share/empty/include/uapi/linux/aufs_type.h linux/include/uapi/lin + +#include + -+#define AUFS_VERSION "4.9-20161219" ++#define AUFS_VERSION "4.9-20180409" + +/* todo? move this to linux-2.6.19/include/magic.h */ +#define AUFS_SUPER_MAGIC ('a' << 24 | 'u' << 16 | 'f' << 8 | 's') @@ -35885,6 +37576,13 @@ diff -urN /usr/share/empty/include/uapi/linux/aufs_type.h linux/include/uapi/lin +#define AUFS_PLINK_MAINT_DIR "fs/" AUFS_NAME +#define AUFS_PLINK_MAINT_PATH AUFS_PLINK_MAINT_DIR "/" AUFS_PLINK_MAINT_NAME + ++/* dirren, renamed dir */ ++#define AUFS_DR_INFO_PFX AUFS_WH_PFX ".dr." ++#define AUFS_DR_BRHINO_NAME AUFS_WH_PFX "hino" ++/* whiteouted doubly */ ++#define AUFS_WH_DR_INFO_PFX AUFS_WH_PFX AUFS_DR_INFO_PFX ++#define AUFS_WH_DR_BRHINO AUFS_WH_PFX AUFS_DR_BRHINO_NAME ++ +#define AUFS_DIROPQ_NAME AUFS_WH_PFX ".opq" /* whiteouted doubly */ +#define AUFS_WH_DIROPQ AUFS_WH_PFX AUFS_DIROPQ_NAME + @@ -36103,6 +37801,27 @@ diff -urN /usr/share/empty/include/uapi/linux/aufs_type.h linux/include/uapi/lin + +/* ---------------------------------------------------------------------- */ + ++/* dirren. the branch is identified by the filename who contains this */ ++struct au_drinfo { ++ uint64_t ino; ++ union { ++ uint8_t oldnamelen; ++ uint64_t _padding; ++ }; ++ uint8_t oldname[0]; ++} __aligned(8); ++ ++struct au_drinfo_fdata { ++ uint32_t magic; ++ struct au_drinfo drinfo; ++} __aligned(8); ++ ++#define AUFS_DRINFO_MAGIC_V1 ('a' << 24 | 'd' << 16 | 'r' << 8 | 0x01) ++/* future */ ++#define AUFS_DRINFO_MAGIC_V2 ('a' << 24 | 'd' << 16 | 'r' << 8 | 0x02) ++ ++/* ---------------------------------------------------------------------- */ ++ +struct aufs_wbr_fd { + uint32_t oflags; + int16_t brid; @@ -36201,277 +37920,407 @@ diff -urN /usr/share/empty/include/uapi/linux/aufs_type.h linux/include/uapi/lin +#define AUFS_CTL_FHSM_FD _IOW(AuCtlType, AuCtl_FHSM_FD, int) + +#endif /* __AUFS_TYPE_H__ */ -aufs4.9 loopback patch - -diff --git a/drivers/block/loop.c b/drivers/block/loop.c -index 6ee9235..f64161f 100644 ---- a/drivers/block/loop.c -+++ b/drivers/block/loop.c -@@ -551,7 +551,7 @@ static int do_req_filebacked(struct loop_device *lo, struct request *rq) +diff -urNp -x '*.orig' linux-4.9/kernel/fork.c linux-4.9/kernel/fork.c +--- linux-4.9/kernel/fork.c 2021-02-24 16:14:57.337843945 +0100 ++++ linux-4.9/kernel/fork.c 2021-02-24 16:15:09.508239763 +0100 +@@ -638,7 +638,7 @@ static __latent_entropy int dup_mmap(str + struct inode *inode = file_inode(file); + struct address_space *mapping = file->f_mapping; + +- get_file(file); ++ vma_get_file(tmp); + if (tmp->vm_flags & VM_DENYWRITE) + atomic_dec(&inode->i_writecount); + i_mmap_lock_write(mapping); +diff -urNp -x '*.orig' linux-4.9/kernel/task_work.c linux-4.9/kernel/task_work.c +--- linux-4.9/kernel/task_work.c 2016-12-11 20:17:54.000000000 +0100 ++++ linux-4.9/kernel/task_work.c 2021-02-24 16:15:09.518240088 +0100 +@@ -119,3 +119,4 @@ void task_work_run(void) + } while (work); + } } ++EXPORT_SYMBOL_GPL(task_work_run); +diff -urNp -x '*.orig' linux-4.9/mm/Makefile linux-4.9/mm/Makefile +--- linux-4.9/mm/Makefile 2016-12-11 20:17:54.000000000 +0100 ++++ linux-4.9/mm/Makefile 2021-02-24 16:15:09.511573204 +0100 +@@ -37,7 +37,7 @@ obj-y := filemap.o mempool.o oom_kill. + mm_init.o mmu_context.o percpu.o slab_common.o \ + compaction.o vmacache.o \ + interval_tree.o list_lru.o workingset.o \ +- debug.o $(mmu-y) ++ prfile.o debug.o $(mmu-y) - struct switch_request { + obj-y += init-mm.o + +diff -urNp -x '*.orig' linux-4.9/mm/filemap.c linux-4.9/mm/filemap.c +--- linux-4.9/mm/filemap.c 2021-02-24 16:14:56.697823124 +0100 ++++ linux-4.9/mm/filemap.c 2021-02-24 16:15:09.511573204 +0100 +@@ -2312,7 +2312,7 @@ int filemap_page_mkwrite(struct vm_area_ + int ret = VM_FAULT_LOCKED; + + sb_start_pagefault(inode->i_sb); +- file_update_time(vma->vm_file); ++ vma_file_update_time(vma); + lock_page(page); + if (page->mapping != inode->i_mapping) { + unlock_page(page); +diff -urNp -x '*.orig' linux-4.9/mm/memory.c linux-4.9/mm/memory.c +--- linux-4.9/mm/memory.c 2021-02-24 16:14:56.704490008 +0100 ++++ linux-4.9/mm/memory.c 2021-02-24 16:15:09.511573204 +0100 +@@ -2124,7 +2124,7 @@ static inline int wp_page_reuse(struct f + } + + if (!page_mkwrite) +- file_update_time(vma->vm_file); ++ vma_file_update_time(vma); + } + + return VM_FAULT_WRITE; +diff -urNp -x '*.orig' linux-4.9/mm/mmap.c linux-4.9/mm/mmap.c +--- linux-4.9/mm/mmap.c 2021-02-24 16:14:56.707823450 +0100 ++++ linux-4.9/mm/mmap.c 2021-02-24 16:15:09.511573204 +0100 +@@ -164,7 +164,7 @@ static struct vm_area_struct *remove_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); + mpol_put(vma_policy(vma)); + kmem_cache_free(vm_area_cachep, vma); + return next; +@@ -887,7 +887,7 @@ again: + if (remove_next) { + if (file) { + uprobe_munmap(next, next->vm_start, next->vm_end); +- fput(file); ++ vma_fput(vma); + } + if (next->anon_vma) + anon_vma_merge(vma, next); +@@ -1767,8 +1767,8 @@ out: + return addr; + + unmap_and_free_vma: ++ vma_fput(vma); + vma->vm_file = NULL; +- fput(file); + + /* Undo any partial mapping done by a device driver. */ + unmap_region(mm, vma, prev, vma->vm_start, vma->vm_end); +@@ -2602,7 +2602,7 @@ static int __split_vma(struct mm_struct + 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); +@@ -2621,7 +2621,7 @@ static int __split_vma(struct mm_struct + if (new->vm_ops && new->vm_ops->close) + new->vm_ops->close(new); + if (new->vm_file) +- fput(new->vm_file); ++ vma_fput(new); + unlink_anon_vmas(new); + out_free_mpol: + mpol_put(vma_policy(new)); +@@ -2772,7 +2772,7 @@ SYSCALL_DEFINE5(remap_file_pages, unsign + struct vm_area_struct *vma; + unsigned long populate = 0; + unsigned long ret = -EINVAL; - struct file *file; -+ struct file *file, *virt_file; - struct completion wait; - }; ++ struct file *file, *prfile; -@@ -577,6 +577,7 @@ static void do_loop_switch(struct loop_device *lo, struct switch_request *p) - mapping = file->f_mapping; - mapping_set_gfp_mask(old_file->f_mapping, lo->old_gfp_mask); - lo->lo_backing_file = file; -+ lo->lo_backing_virt_file = p->virt_file; - lo->lo_blocksize = S_ISBLK(mapping->host->i_mode) ? - mapping->host->i_bdev->bd_block_size : PAGE_SIZE; - lo->old_gfp_mask = mapping_gfp_mask(mapping); -@@ -589,11 +590,13 @@ static void do_loop_switch(struct loop_device *lo, struct switch_request *p) - * First it needs to flush existing IO, it does this by sending a magic - * BIO down the pipe. The completion of this BIO does the actual switch. - */ --static int loop_switch(struct loop_device *lo, struct file *file) -+static int loop_switch(struct loop_device *lo, struct file *file, -+ struct file *virt_file) - { - struct switch_request w; + pr_warn_once("%s (%d) uses deprecated remap_file_pages() syscall. See Documentation/vm/remap_file_pages.txt.\n", + current->comm, current->pid); +@@ -2847,10 +2847,27 @@ SYSCALL_DEFINE5(remap_file_pages, unsign + } + } - w.file = file; -+ w.virt_file = virt_file; +- file = get_file(vma->vm_file); ++ vma_get_file(vma); ++ file = vma->vm_file; ++ prfile = vma->vm_prfile; + ret = do_mmap_pgoff(vma->vm_file, start, size, + prot, flags, pgoff, &populate); ++ 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 (new_vma != vma) ++ get_file(prfile); ++ } ++ /* ++ * two fput()s instead of vma_fput(vma), ++ * coz vma may not be available anymore. ++ */ + fput(file); ++ if (prfile) ++ fput(prfile); + out: + up_write(&mm->mmap_sem); + if (populate) +@@ -3127,7 +3144,7 @@ struct vm_area_struct *copy_vma(struct v + 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); + vma_link(mm, new_vma, prev, rb_link, rb_parent); +diff -urNp -x '*.orig' linux-4.9/mm/nommu.c linux-4.9/mm/nommu.c +--- linux-4.9/mm/nommu.c 2021-02-24 16:14:56.707823450 +0100 ++++ linux-4.9/mm/nommu.c 2021-02-24 16:15:09.511573204 +0100 +@@ -640,7 +640,7 @@ static void __put_nommu_region(struct vm + up_write(&nommu_region_sem); - /* freeze queue and wait for completion of scheduled requests */ - blk_mq_freeze_queue(lo->lo_queue); -@@ -612,7 +615,16 @@ static int loop_switch(struct loop_device *lo, struct file *file) - */ - static int loop_flush(struct loop_device *lo) - { -- return loop_switch(lo, NULL); -+ return loop_switch(lo, NULL, NULL); + 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 */ +@@ -798,7 +798,7 @@ static void delete_vma(struct mm_struct + 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); + kmem_cache_free(vm_area_cachep, vma); + } +@@ -1324,7 +1324,7 @@ 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; +@@ -1399,10 +1399,10 @@ error_just_free: + up_write(&nommu_region_sem); + error: + 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); + kmem_cache_free(vm_area_cachep, vma); + return ret; + +diff -urNp -x '*.orig' linux-4.9/mm/prfile.c linux-4.9/mm/prfile.c +--- linux-4.9/mm/prfile.c 1970-01-01 01:00:00.000000000 +0100 ++++ linux-4.9/mm/prfile.c 2021-02-24 16:15:09.511573204 +0100 +@@ -0,0 +1,85 @@ ++/* ++ * 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) 2014-2018 Junjro R. Okajima ++ * Copyright (c) 2014 Ian Campbell ++ */ ++ ++#include ++#include ++#include ++ ++/* #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 +} + -+static struct file *loop_real_file(struct file *file) ++void vma_do_file_update_time(struct vm_area_struct *vma, const char func[], ++ int line) +{ -+ struct file *f = NULL; ++ struct file *f = vma->vm_file, *pr = vma->vm_prfile; + -+ 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; ++ 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; ++} ++ ++void vmr_do_fput(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__); ++ fput(f); ++ if (f && pr) ++ fput(pr); ++} ++#endif /* !CONFIG_MMU */ +diff -urNp -x '*.orig' linux-4.9/security/commoncap.c linux-4.9/security/commoncap.c +--- linux-4.9/security/commoncap.c 2021-02-24 16:14:57.371178363 +0100 ++++ linux-4.9/security/commoncap.c 2021-02-24 16:15:09.518240088 +0100 +@@ -1067,12 +1067,14 @@ int cap_mmap_addr(unsigned long addr) + } + return ret; } ++EXPORT_SYMBOL_GPL(cap_mmap_addr); - static void loop_reread_partitions(struct loop_device *lo, -@@ -649,6 +661,7 @@ static int loop_change_fd(struct loop_device *lo, struct block_device *bdev, - unsigned int arg) + int cap_mmap_file(struct file *file, unsigned long reqprot, + unsigned long prot, unsigned long flags) { - struct file *file, *old_file; -+ struct file *f, *virt_file = NULL, *old_virt_file; - struct inode *inode; - int error; - -@@ -665,9 +678,16 @@ static int loop_change_fd(struct loop_device *lo, struct block_device *bdev, - file = fget(arg); - if (!file) - goto out; -+ f = loop_real_file(file); -+ if (f) { -+ virt_file = file; -+ file = f; -+ get_file(file); -+ } - - inode = file->f_mapping->host; - old_file = lo->lo_backing_file; -+ old_virt_file = lo->lo_backing_virt_file; - - error = -EINVAL; - -@@ -679,17 +699,21 @@ static int loop_change_fd(struct loop_device *lo, struct block_device *bdev, - goto out_putf; - - /* and ... switch */ -- error = loop_switch(lo, file); -+ error = loop_switch(lo, file, virt_file); - if (error) - goto out_putf; - - fput(old_file); -+ if (old_virt_file) -+ fput(old_virt_file); - if (lo->lo_flags & LO_FLAGS_PARTSCAN) - loop_reread_partitions(lo, bdev); return 0; + } ++EXPORT_SYMBOL_GPL(cap_mmap_file); - out_putf: - fput(file); -+ if (virt_file) -+ fput(virt_file); - out: - return error; + #ifdef CONFIG_SECURITY + +diff -urNp -x '*.orig' linux-4.9/security/device_cgroup.c linux-4.9/security/device_cgroup.c +--- linux-4.9/security/device_cgroup.c 2021-02-24 16:14:56.891162747 +0100 ++++ linux-4.9/security/device_cgroup.c 2021-02-24 16:15:09.518240088 +0100 +@@ -7,6 +7,7 @@ + #include + #include + #include ++#include + #include + #include + #include +@@ -849,6 +850,7 @@ int __devcgroup_inode_permission(struct + return __devcgroup_check_permission(type, imajor(inode), iminor(inode), + access); } -@@ -876,7 +900,7 @@ static int loop_prepare_queue(struct loop_device *lo) - static int loop_set_fd(struct loop_device *lo, fmode_t mode, - struct block_device *bdev, unsigned int arg) - { -- struct file *file, *f; -+ struct file *file, *f, *virt_file = NULL; - struct inode *inode; - struct address_space *mapping; - unsigned lo_blocksize; -@@ -891,6 +915,12 @@ static int loop_set_fd(struct loop_device *lo, fmode_t mode, - file = fget(arg); - if (!file) - goto out; -+ f = loop_real_file(file); -+ if (f) { -+ virt_file = file; -+ file = f; -+ get_file(file); -+ } ++EXPORT_SYMBOL_GPL(__devcgroup_inode_permission); - error = -EBUSY; - if (lo->lo_state != Lo_unbound) -@@ -943,6 +973,7 @@ static int loop_set_fd(struct loop_device *lo, fmode_t mode, - lo->lo_device = bdev; - lo->lo_flags = lo_flags; - lo->lo_backing_file = file; -+ lo->lo_backing_virt_file = virt_file; - lo->transfer = NULL; - lo->ioctl = NULL; - lo->lo_sizelimit = 0; -@@ -975,6 +1006,8 @@ static int loop_set_fd(struct loop_device *lo, fmode_t mode, + int devcgroup_inode_mknod(int mode, dev_t dev) + { +diff -urNp -x '*.orig' linux-4.9/security/security.c linux-4.9/security/security.c +--- linux-4.9/security/security.c 2021-02-24 16:14:56.897829631 +0100 ++++ linux-4.9/security/security.c 2021-02-24 16:15:09.518240088 +0100 +@@ -443,6 +443,7 @@ int security_path_rmdir(const struct pat + return 0; + return call_int_hook(path_rmdir, 0, dir, dentry); + } ++EXPORT_SYMBOL_GPL(security_path_rmdir); - out_putf: - fput(file); -+ if (virt_file) -+ fput(virt_file); - out: - /* This is safe: open() is still holding a reference. */ - module_put(THIS_MODULE); -@@ -1021,6 +1054,7 @@ static int loop_set_fd(struct loop_device *lo, fmode_t mode, - static int loop_clr_fd(struct loop_device *lo) + int security_path_unlink(const struct path *dir, struct dentry *dentry) { - struct file *filp = lo->lo_backing_file; -+ struct file *virt_filp = lo->lo_backing_virt_file; - gfp_t gfp = lo->old_gfp_mask; - struct block_device *bdev = lo->lo_device; +@@ -459,6 +460,7 @@ int security_path_symlink(const struct p + return 0; + return call_int_hook(path_symlink, 0, dir, dentry, old_name); + } ++EXPORT_SYMBOL_GPL(security_path_symlink); -@@ -1052,6 +1086,7 @@ static int loop_clr_fd(struct loop_device *lo) - spin_lock_irq(&lo->lo_lock); - lo->lo_state = Lo_rundown; - lo->lo_backing_file = NULL; -+ lo->lo_backing_virt_file = NULL; - spin_unlock_irq(&lo->lo_lock); + int security_path_link(struct dentry *old_dentry, const struct path *new_dir, + struct dentry *new_dentry) +@@ -467,6 +469,7 @@ int security_path_link(struct dentry *ol + return 0; + return call_int_hook(path_link, 0, old_dentry, new_dir, new_dentry); + } ++EXPORT_SYMBOL_GPL(security_path_link); - loop_release_xfer(lo); -@@ -1096,6 +1131,8 @@ static int loop_clr_fd(struct loop_device *lo) - * bd_mutex which is usually taken before lo_ctl_mutex. - */ - fput(filp); -+ if (virt_filp) -+ fput(virt_filp); - return 0; + int security_path_rename(const struct path *old_dir, struct dentry *old_dentry, + const struct path *new_dir, struct dentry *new_dentry, +@@ -494,6 +497,7 @@ int security_path_truncate(const struct + return 0; + return call_int_hook(path_truncate, 0, path); } ++EXPORT_SYMBOL_GPL(security_path_truncate); -diff --git a/drivers/block/loop.h b/drivers/block/loop.h -index fb2237c..c3888c5 100644 ---- a/drivers/block/loop.h -+++ b/drivers/block/loop.h -@@ -46,7 +46,7 @@ struct loop_device { - int (*ioctl)(struct loop_device *, int cmd, - unsigned long arg); + int security_path_chmod(const struct path *path, umode_t mode) + { +@@ -501,6 +505,7 @@ int security_path_chmod(const struct pat + return 0; + return call_int_hook(path_chmod, 0, path, mode); + } ++EXPORT_SYMBOL_GPL(security_path_chmod); -- struct file * lo_backing_file; -+ struct file * lo_backing_file, *lo_backing_virt_file; - struct block_device *lo_device; - unsigned lo_blocksize; - void *key_data; -diff --git a/fs/aufs/f_op.c b/fs/aufs/f_op.c -index d2a9a1d..d7519d0 100644 ---- a/fs/aufs/f_op.c -+++ b/fs/aufs/f_op.c -@@ -351,7 +351,7 @@ static ssize_t aufs_read_iter(struct kiocb *kio, struct iov_iter *iov_iter) - if (IS_ERR(h_file)) - goto out; + int security_path_chown(const struct path *path, kuid_t uid, kgid_t gid) + { +@@ -508,6 +513,7 @@ int security_path_chown(const struct pat + return 0; + return call_int_hook(path_chown, 0, path, uid, gid); + } ++EXPORT_SYMBOL_GPL(security_path_chown); -- 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 c3ca50f..a3dbdaf 100644 ---- a/fs/aufs/loop.c -+++ b/fs/aufs/loop.c -@@ -132,3 +132,19 @@ void au_loopback_fin(void) - symbol_put(loop_backing_file); - au_delayed_kfree(au_warn_loopback_array); + int security_path_chroot(const struct path *path) + { +@@ -593,6 +599,7 @@ int security_inode_readlink(struct dentr + return 0; + return call_int_hook(inode_readlink, 0, dentry); } -+ -+/* ---------------------------------------------------------------------- */ -+ -+/* support the loopback block device insude aufs */ -+ -+struct file *aufs_real_loop(struct file *file) -+{ -+ struct file *f; -+ -+ 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; -+} -diff --git a/fs/aufs/loop.h b/fs/aufs/loop.h -index 48bf070..66afec7 100644 ---- a/fs/aufs/loop.h -+++ b/fs/aufs/loop.h -@@ -25,7 +25,11 @@ ++EXPORT_SYMBOL_GPL(security_inode_readlink); - 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) -+ - AuStubInt0(au_test_loopback_overlap, struct super_block *sb, - struct dentry *h_adding) - AuStubInt0(au_test_loopback_kthread, void) -@@ -33,6 +37,8 @@ + int security_inode_follow_link(struct dentry *dentry, struct inode *inode, + bool rcu) +@@ -608,6 +615,7 @@ int security_inode_permission(struct ino + return 0; + return call_int_hook(inode_permission, 0, inode, mask); + } ++EXPORT_SYMBOL_GPL(security_inode_permission); - 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 */ + int security_inode_setattr(struct dentry *dentry, struct iattr *attr) + { +@@ -779,6 +787,7 @@ int security_file_permission(struct file - #endif /* __KERNEL__ */ -diff --git a/fs/aufs/super.c b/fs/aufs/super.c -index 0082ce4..5085378 100644 ---- a/fs/aufs/super.c -+++ b/fs/aufs/super.c -@@ -839,7 +839,10 @@ static int aufs_remount_fs(struct super_block *sb, int *flags, char *data) - .statfs = aufs_statfs, - .put_super = aufs_put_super, - .sync_fs = aufs_sync_fs, -- .remount_fs = aufs_remount_fs -+ .remount_fs = aufs_remount_fs, -+#ifdef CONFIG_AUFS_BDEV_LOOP -+ .real_loop = aufs_real_loop -+#endif - }; + return fsnotify_perm(file, mask); + } ++EXPORT_SYMBOL_GPL(security_file_permission); - /* ---------------------------------------------------------------------- */ -diff --git a/include/linux/fs.h b/include/linux/fs.h -index a903bc3..db820e3 100644 ---- a/include/linux/fs.h -+++ b/include/linux/fs.h -@@ -1823,6 +1823,10 @@ struct super_operations { - struct shrink_control *); - long (*free_cached_objects)(struct super_block *, - struct shrink_control *); -+#if defined(CONFIG_BLK_DEV_LOOP) || defined(CONFIG_BLK_DEV_LOOP_MODULE) -+ /* and aufs */ -+ struct file *(*real_loop)(struct file *); -+#endif - }; + int security_file_alloc(struct file *file) + { +@@ -838,6 +847,7 @@ int security_mmap_file(struct file *file + return ret; + return ima_file_mmap(file, prot); + } ++EXPORT_SYMBOL_GPL(security_mmap_file); - /* + int security_mmap_addr(unsigned long addr) + {