diff options
Diffstat (limited to 'patches')
| -rw-r--r-- | patches/aufs2-20090406.patch | 25650 |
1 files changed, 25650 insertions, 0 deletions
diff --git a/patches/aufs2-20090406.patch b/patches/aufs2-20090406.patch new file mode 100644 index 0000000..c91d799 --- /dev/null +++ b/patches/aufs2-20090406.patch @@ -0,0 +1,25650 @@ +diff -urN ./Documentation/ABI/testing/debugfs-aufs ./Documentation/ABI/testing/debugfs-aufs +--- ./Documentation/ABI/testing/debugfs-aufs 1970-01-01 01:00:00.000000000 +0100 ++++ ./Documentation/ABI/testing/debugfs-aufs 2009-04-06 10:26:45.000000000 +0200 +@@ -0,0 +1,40 @@ ++What: /debug/aufs/si_<id>/ ++Date: March 2009 ++Contact: J. R. Okajima <hooanon05@yahoo.co.jp> ++Description: ++ Under /debug/aufs, a directory named si_<id> is created ++ per aufs mount, where <id> is a unique id generated ++ internally. ++ ++What: /debug/aufs/si_<id>/xib ++Date: March 2009 ++Contact: J. R. Okajima <hooanon05@yahoo.co.jp> ++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 ++ Documentation/filesystems/aufs/aufs.5 in detail. ++ ++What: /debug/aufs/si_<id>/xino0, xino1 ... xinoN ++Date: March 2009 ++Contact: J. R. Okajima <hooanon05@yahoo.co.jp> ++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 ++ Documentation/filesystems/aufs/aufs.5 in detail. ++ ++What: /debug/aufs/si_<id>/xigen ++Date: March 2009 ++Contact: J. R. Okajima <hooanon05@yahoo.co.jp> ++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 ++ Documentation/filesystems/aufs/aufs.5 in detail. +diff -urN ./Documentation/ABI/testing/sysfs-aufs ./Documentation/ABI/testing/sysfs-aufs +--- ./Documentation/ABI/testing/sysfs-aufs 1970-01-01 01:00:00.000000000 +0100 ++++ ./Documentation/ABI/testing/sysfs-aufs 2009-04-06 10:26:45.000000000 +0200 +@@ -0,0 +1,25 @@ ++What: /sys/fs/aufs/si_<id>/ ++Date: March 2009 ++Contact: J. R. Okajima <hooanon05@yahoo.co.jp> ++Description: ++ Under /sys/fs/aufs, a directory named si_<id> is created ++ per aufs mount, where <id> is a unique id generated ++ internally. ++ ++What: /sys/fs/aufs/si_<id>/br0, br1 ... brN ++Date: March 2009 ++Contact: J. R. Okajima <hooanon05@yahoo.co.jp> ++Description: ++ It shows the abolute path of a member directory (which ++ is called branch) in aufs, and its permission. ++ ++What: /sys/fs/aufs/si_<id>/xi_path ++Date: March 2009 ++Contact: J. R. Okajima <hooanon05@yahoo.co.jp> ++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 ++ Documentation/filesystems/aufs/aufs.5 in detail. +diff -urN ./Documentation/filesystems/aufs/README ./Documentation/filesystems/aufs/README +--- ./Documentation/filesystems/aufs/README 1970-01-01 01:00:00.000000000 +0100 ++++ ./Documentation/filesystems/aufs/README 2009-04-06 10:26:45.000000000 +0200 +@@ -0,0 +1,253 @@ ++ ++Aufs2 -- advanced multi layered unification filesystem version 2 ++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. After 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. ++ ++This version of AUFS, aufs2 has several purposes. ++- to be reviewed easily and widely. ++- to make the source files simpler and smaller by dropping several ++ original features. ++ ++Through this work, I found some bad things in aufs1 source code and ++fixed them. Some of the dropped features will be reverted in the future, ++but not all I'm afraid. ++Aufs2 supports linux-2.6.27 and later. If you want older kernel version ++support, try aufs1 from CVS on SourceForge. ++ ++ ++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 aufs1, such as: ++- keep inode number by external inode number table ++- keep the timestamps of file/dir in internal copyup operation ++- seekable directory, supporting NFS readdir. ++- support mmap(2) including /proc/PID/exe symlink, without page-copy ++- 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 shell script, /sbin/mount.aufs. ++- loopback mounted filesystem as a branch ++- kernel thread for removing the dir who has a plenty of whiteouts ++- support copyup sparse file (a file which has a 'hole' in it) ++- default permission flags for branches ++- selectable permission flags for ro branch, whether whiteout can ++ exist or not ++- export via NFS. ++- support <sysfs>/fs/aufs. ++- 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. ++- a delegation of the internal branch access to support task I/O ++ accounting, which also supports Linux Security Modules (LSM) mainly ++ for Suse AppArmor. ++- nested mount, i.e. aufs as readonly no-whiteout branch of another aufs. ++- copyup-on-open or copyup-on-write ++- show-whiteout mode ++- show configuration even out of kernel tree ++- 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. ++- and more... ++ ++Currently these features are dropped temporary from this version, aufs2. ++See design/08plan.txt in detail. ++- test only the highest one for the directory permission (dirperm1) ++- show whiteout mode (shwh) ++- copyup on open (coo=) ++- being another aufs's readonly branch (robr) ++- statistics of aufs thread (/sys/fs/aufs/stat) ++- delegation mode (dlgt) ++- intent.open/create (file open in a single lookup) ++ ++Features or just an idea in the future (see also design/*.txt), ++- reorder the branch index without del/re-add. ++- permanent xino files ++- an option for refreshing the opened files after add/del branches ++- 'move' policy for copy-up between two writable branches, after ++ checking free space. ++- remount option copy/move between two branches. (almost done) ++- O_DIRECT ++- light version, without branch manipulation. (unnecessary?) ++- copyup in userspace ++- inotify in userspace ++- xattr, acl ++ ++ ++2. Download ++---------------------------------------- ++Kindly one of aufs user, the Center for Scientific Computing and Free ++Software (C3SL), Federal University of Parana offered me a public GIT ++tree space. ++ ++There are three GIT trees, aufs2-2.6, aufs2-standalone and aufs2-util. ++While the aufs2-util is always necessary, you need either of aufs2-2.6 ++or aufs2-standalone. ++ ++The aufs2-2.6 tree includes the whole linux-2.6 GIT tree, ++git://git.kernel.org/.../torvalds/linux-2.6.git. ++And you cannot select CONFIG_AUFS_FS=m for this version, eg. you cannot ++build aufs2 as an externel kernel module. ++If you already have linux-2.6 GIT tree, you may want to pull and merge ++the "aufs2" branch from this tree. ++ ++On the other hand, the aufs2-standalone tree has only aufs2 source files ++and a necessary patch, and you can select CONFIG_AUFS_FS=m. In other ++words, the aufs2-standalone tree is generated from aufs2-2.6 tree by, ++- extract new files and modifications. ++- generate a single patch file from modifications. ++- generate a ChangeLog file from git-log. ++- commit the files newly and no log messages. this is not git-pull. ++ ++Both of aufs2-2.6 and aufs2-standalone trees have a branch whose name is ++in form of "aufs2-xx" where "xx" represents the linux kernel version, ++"linux-2.6.xx". ++ ++o aufs2-2.6 tree ++$ git clone --reference /your/linux-2.6/git/tree \ ++ http://git.c3sl.ufpr.br/pub/scm/aufs/aufs2-2.6.git \ ++ aufs2-2.6.git ++- if you don't have linux-2.6 GIT tree, then remove "--reference ..." ++$ cd aufs2-2.6.git ++$ git checkout origin/aufs2-xx # for instance, aufs2-27 for linux-2.6.27 ++ # aufs2 (no -xx) for the latest -rc version. ++ ++o aufs2-standalone tree ++$ git clone http://git.c3sl.ufpr.br/pub/scm/aufs/aufs2-standalone.git \ ++ aufs2-standalone.git ++$ cd aufs2-standalone.git ++$ git checkout origin/aufs2-xx # for instance, aufs2-27 for linux-2.6.27 ++- apply "aufs2-standalone.patch" to your kernel source files. ++ ++o aufs2-util tree ++$ git clone http://git.c3sl.ufpr.br/pub/scm/aufs/aufs2-util.git \ ++ aufs2-util.git ++$ cd aufs2-util.git ++- no particular tag/branch currently. ++ ++ ++3. Configuration and Compilation ++---------------------------------------- ++For aufs2-2.6 tree, ++- enable CONFIG_EXPERIMENTAL and CONFIG_AUFS_FS. ++- set other aufs configurations if necessary. ++ ++For aufs2-standalone tree, ++- enable CONFIG_EXPERIMENTAL and CONFIG_AUFS_FS, you can select =m. ++- edit fs/aufs/config.mk and set other aufs configurations if necessary. ++ ++And then, ++- build your kernel (or a module) by "make" ++- install it and reboot your system ++- read README in aufs2-util, build and install it ++ ++ ++4. Usage ++---------------------------------------- ++At first, make sure aufs2-util are installed, and please read the aufs ++manual, ./Documentation/filesystems/aufs/aufs.5. ++$ man -l aufs.5 ++ ++And then, ++$ mkdir /tmp/rw /tmp/aufs ++# mount -t aufs -o br=/tmp/rw:${HOME}=ro none /tmp/aufs ++ ++Here is another example. The result is equivalent. ++# mount -t aufs -o br=/tmp/rw:${HOME} 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. ++ ++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 donors: ++Tomas Matejicek(slax.org) made a donation (much more than once). ++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 GIT ++tree (2009/2). ++William Grant made a donation (2009/3). ++ ++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 -urN ./Documentation/filesystems/aufs/aufs.5 ./Documentation/filesystems/aufs/aufs.5 +--- ./Documentation/filesystems/aufs/aufs.5 1970-01-01 01:00:00.000000000 +0100 ++++ ./Documentation/filesystems/aufs/aufs.5 2009-04-06 10:26:45.000000000 +0200 +@@ -0,0 +1,1581 @@ ++.ds AUFS_VERSION aufs2 ++.ds AUFS_XINO_FNAME .aufs.xino ++.ds AUFS_XINO_DEFPATH /tmp/.aufs.xino ++.ds AUFS_DIRWH_DEF 3 ++.ds AUFS_WH_PFX .wh. ++.ds AUFS_WH_PFX_LEN 4 ++.ds AUFS_WKQ_NAME aufsd ++.ds AUFS_NWKQ_DEF 4 ++.ds AUFS_WH_DIROPQ .wh..wh..opq ++.ds AUFS_WH_BASE .wh..wh.aufs ++.ds AUFS_WH_PLINKDIR .wh..wh.plnk ++.ds AUFS_BRANCH_MAX 127 ++.ds AUFS_MFS_SECOND_DEF 30 ++.\".so aufs.tmac ++. ++.eo ++.de TQ ++.br ++.ns ++.TP \$1 ++.. ++.de Bu ++.IP \(bu 4 ++.. ++.ec ++.\" end of macro definitions ++. ++.\" ---------------------------------------------------------------------- ++.TH aufs 5 \*[AUFS_VERSION] Linux "Linux Aufs User\[aq]s Manual" ++.SH NAME ++aufs \- another unionfs. version \*[AUFS_VERSION] ++ ++.\" ---------------------------------------------------------------------- ++.SH DESCRIPTION ++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. After ++many original ideas, approaches and improvements, it ++becomes totally different from Unionfs while keeping the basic features. ++See Unionfs Version 1.x series for the basic features. ++Recently, Unionfs Version 2.x series begin taking some of same ++approaches to aufs\[aq]s. ++ ++.\" ---------------------------------------------------------------------- ++.SH MOUNT OPTIONS ++At mount-time, the order of interpreting options is, ++.RS ++.Bu ++simple flags, except xino/noxino and udba=inotify ++.Bu ++branches ++.Bu ++xino/noxino ++.Bu ++udba=inotify ++.RE ++ ++At remount-time, ++the options are interpreted in the given order, ++e.g. left to right. ++.RS ++.Bu ++create or remove ++whiteout-base(\*[AUFS_WH_BASE]) and ++whplink-dir(\*[AUFS_WH_PLINKDIR]) if necessary ++.RE ++. ++.TP ++.B br:BRANCH[:BRANCH ...] (dirs=BRANCH[:BRANCH ...]) ++Adds new branches. ++(cf. Branch Syntax). ++ ++Aufs rejects the branch which is an ancestor or a descendant of another ++branch. It is called overlapped. When the branch is loopback-mounted ++directory, aufs also checks the source fs-image file of loopback ++device. If the source file is a descendant of another branch, it will ++be rejected too. ++ ++After mounting aufs or adding a branch, if you move a branch under ++another branch and make it descendant of another branch, aufs will not ++work correctly. ++. ++.TP ++.B [ add | ins ]:index:BRANCH ++Adds a new branch. ++The index begins with 0. ++Aufs creates ++whiteout-base(\*[AUFS_WH_BASE]) and ++whplink-dir(\*[AUFS_WH_PLINKDIR]) if necessary. ++ ++If there is the same named file on the lower branch (larger index), ++aufs will hide the lower file. ++You can only see the highest file. ++You will be confused if the added branch has whiteouts (including ++diropq), they may or may not hide the lower entries. ++.\" It is recommended to make sure that the added branch has no whiteout. ++ ++If a process have once mapped a file by mmap(2) with MAP_SHARED ++and the same named file exists on the lower branch, ++the process still refers the file on the lower(hidden) ++branch after adding the branch. ++If you want to update the contents of a process address space after ++adding, you need to restart your process or open/mmap the file again. ++.\" Usually, such files are executables or shared libraries. ++(cf. Branch Syntax). ++. ++.TP ++.B del:dir ++Removes a branch. ++Aufs does not remove ++whiteout-base(\*[AUFS_WH_BASE]) and ++whplink-dir(\*[AUFS_WH_PLINKDIR]) automatically. ++For example, when you add a RO branch which was unified as RW, you ++will see whiteout-base or whplink-dir on the added RO branch. ++ ++If a process is referencing the file/directory on the deleting branch ++(by open, mmap, current working directory, etc.), aufs will return an ++error EBUSY. ++. ++.TP ++.B mod:BRANCH ++Modifies the permission flags of the branch. ++Aufs creates or removes ++whiteout-base(\*[AUFS_WH_BASE]) and/or ++whplink-dir(\*[AUFS_WH_PLINKDIR]) if necessary. ++ ++If the branch permission is been changing \[oq]rw\[cq] to \[oq]ro\[cq], and a process ++is mapping a file by mmap(2) ++.\" with MAP_SHARED ++on the branch, the process may or may not ++be able to modify its mapped memory region after modifying branch ++permission flags. ++(cf. Branch Syntax). ++. ++.TP ++.B append:BRANCH ++equivalent to \[oq]add:(last index + 1):BRANCH\[cq]. ++(cf. Branch Syntax). ++. ++.TP ++.B prepend:BRANCH ++equivalent to \[oq]add:0:BRANCH.\[cq] ++(cf. Branch Syntax). ++. ++.TP ++.B xino=filename ++Use external inode number bitmap and translation table. ++When CONFIG_AUFS_EXPORT is enabled, external inode generation table too. ++It is set to ++<FirstWritableBranch>/\*[AUFS_XINO_FNAME] by default, or ++\*[AUFS_XINO_DEFPATH]. ++Comma character in filename is not allowed. ++ ++The files are created per an aufs and per a branch filesystem, and ++unlinked. So you ++cannot find this file, but it exists and is read/written frequently by ++aufs. ++(cf. External Inode Number Bitmap, Translation Table and Generation Table). ++ ++If you enable CONFIG_SYSFS, the path of xino files are not shown in ++/proc/mounts (and /etc/mtab), instead it is shown in ++<sysfs>/fs/aufs/si_<id>/xi_path. ++Otherwise, it is shown in /proc/mounts unless it is not the default ++path. ++. ++.TP ++.B noxino ++Stop using external inode number bitmap and translation table. ++ ++If you use this option, ++Some applications will not work correctly. ++.\" And pseudo link feature will not work after the inode cache is ++.\" shrunk. ++(cf. External Inode Number Bitmap, Translation Table and Generation Table). ++. ++.TP ++.B trunc_xib ++Truncate the external inode number bitmap file. The truncation is done ++automatically when you delete a branch unless you do not specify ++\[oq]notrunc_xib\[cq] option. ++(cf. External Inode Number Bitmap, Translation Table and Generation Table). ++. ++.TP ++.B notrunc_xib ++Stop truncating the external inode number bitmap file when you delete ++a branch. ++(cf. External Inode Number Bitmap, Translation Table and Generation Table). ++. ++.TP ++.B create_policy | create=CREATE_POLICY ++.TQ ++.B copyup_policy | copyup | cpup=COPYUP_POLICY ++Policies to select one among multiple writable branches. The default ++values are \[oq]create=tdp\[cq] and \[oq]cpup=tdp\[cq]. ++link(2) and rename(2) systemcalls have an exception. In aufs, they ++try keeping their operations in the branch where the source exists. ++(cf. Policies to Select One among Multiple Writable Branches). ++. ++.TP ++.B verbose | v ++Print some information. ++Currently, it is only busy file (or inode) at deleting a branch. ++. ++.TP ++.B noverbose | quiet | q | silent ++Disable \[oq]verbose\[cq] option. ++This is default value. ++. ++.TP ++.B sum ++df(1)/statfs(2) returns the total number of blocks and inodes of ++all branches. ++Note that there are cases that systemcalls may return ENOSPC, even if ++df(1)/statfs(2) shows that aufs has some free space/inode. ++. ++.TP ++.B nosum ++Disable \[oq]sum\[cq] option. ++This is default value. ++. ++.TP ++.B dirwh=N ++Watermark to remove a dir actually at rmdir(2) and rename(2). ++ ++If the target dir which is being removed or renamed (destination dir) ++has a huge number of whiteouts, i.e. the dir is empty logically but ++physically, the cost to remove/rename the single ++dir may be very high. ++It is ++required to unlink all of whiteouts internally before issuing ++rmdir/rename to the branch. ++To reduce the cost of single systemcall, ++aufs renames the target dir to a whiteout-ed temporary name and ++invokes a pre-created ++kernel thread to remove whiteout-ed children and the target dir. ++The rmdir/rename systemcall returns just after kicking the thread. ++ ++When the number of whiteout-ed children is less than the value of ++dirwh, aufs remove them in a single systemcall instead of passing ++another thread. ++This value is ignored when the branch is NFS. ++The default value is \*[AUFS_DIRWH_DEF]. ++. ++.TP ++.B plink ++.TQ ++.B noplink ++Specifies to use \[oq]pseudo link\[cq] feature or not. ++The default is \[oq]plink\[cq] which means use this feature. ++(cf. Pseudo Link) ++. ++.TP ++.B clean_plink ++Removes all pseudo-links in memory. ++In order to make pseudo-link permanent, use ++\[oq]auplink\[cq] utility just before one of these operations, ++unmounting aufs, ++using \[oq]ro\[cq] or \[oq]noplink\[cq] mount option, ++deleting a branch from aufs, ++adding a branch into aufs, ++or changing your writable branch as readonly. ++If you installed both of /sbin/mount.aufs and /sbin/umount.aufs, and your ++mount(8) and umount(8) support them, ++\[oq]auplink\[cq] utility will be executed automatically and flush pseudo-links. ++(cf. Pseudo Link) ++. ++.TP ++.B udba=none | reval | inotify ++Specifies the level of UDBA (User\[aq]s Direct Branch Access) test. ++(cf. User\[aq]s Direct Branch Access and Inotify Limitation). ++. ++.TP ++.B diropq=whiteouted | w | always | a ++Specifies whether mkdir(2) and rename(2) dir case make the created directory ++\[oq]opaque\[cq] or not. ++In other words, to create \[oq]\*[AUFS_WH_DIROPQ]\[cq] under the created or renamed ++directory, or not to create. ++When you specify diropq=w or diropq=whiteouted, aufs will not create ++it if the ++directory was not whiteouted or opaqued. If the directory was whiteouted ++or opaqued, the created or renamed directory will be opaque. ++When you specify diropq=a or diropq==always, aufs will always create ++it regardless ++the directory was whiteouted/opaqued or not. ++The default value is diropq=w, it means not to create when it is unnecessary. ++If you define CONFIG_AUFS_COMPAT at aufs compiling time, the default will be ++diropq=a. ++You need to consider this option if you are planning to add a branch later ++since \[oq]diropq\[cq] affects the same named directory on the added branch. ++. ++.TP ++.B warn_perm ++.TQ ++.B nowarn_perm ++Adding a branch, aufs will issue a warning about uid/gid/permission of ++the adding branch directory, ++when they differ from the existing branch\[aq]s. This difference may or ++may not impose a security risk. ++If you are sure that there is no problem and want to stop the warning, ++use \[oq]nowarn_perm\[cq] option. ++The default is \[oq]warn_perm\[cq] (cf. DIAGNOSTICS). ++ ++.\" ---------------------------------------------------------------------- ++.SH Module Parameters ++.TP ++.B nwkq=N ++The number of kernel thread named \*[AUFS_WKQ_NAME]. ++ ++Those threads stay in the system while the aufs module is loaded, ++and handle the special I/O requests from aufs. ++The default value is \*[AUFS_NWKQ_DEF]. ++ ++The special I/O requests from aufs include a part of copy-up, lookup, ++directory handling, pseudo-link, xino file operations and the ++delegated access to branches. ++For example, Unix filesystems allow you to rmdir(2) which has no write ++permission bit, if its parent directory has write permission bit. In aufs, the ++removing directory may or may not have whiteout or \[oq]dir opaque\[cq] mark as its ++child. And aufs needs to unlink(2) them before rmdir(2). ++Therefore aufs delegates the actual unlink(2) and rmdir(2) to another kernel ++thread which has been created already and has a superuser privilege. ++ ++If you enable CONFIG_SYSFS, you can check this value through ++<sysfs>/module/aufs/parameters/nwkq. ++ ++. ++.TP ++.B brs=1 | 0 ++Specifies to use the branch path data file under sysfs or not. ++ ++If the number of your branches is large or their path is long ++and you meet the limitation of mount(8) ro /etc/mtab, you need to ++enable CONFIG_SYSFS and set aufs module parameter brs=1. ++ ++When this parameter is set as 1, aufs does not show \[oq]br:\[cq] (or dirs=) ++mount option through /proc/mounts (and /etc/mtab). So you can ++keep yourself from the page limitation of ++mount(8) or /etc/mtab. ++Aufs shows branch paths through <sysfs>/fs/aufs/si_XXX/brNNN. ++Actually the file under sysfs has also a size limitation, but I don\[aq]t ++think it is harmful. ++ ++There is one more side effect in setting 1 to this parameter. ++If you rename your branch, the branch path written in /etc/mtab will be ++obsoleted and the future remount will meet some error due to the ++unmatched parameters (Remember that mount(8) may take the options from ++/etc/mtab and pass them to the systemcall). ++If you set 1, /etc/mtab will not hold the branch path and you will not ++meet such trouble. On the other hand, the entires for the ++branch path under sysfs are generated dynamically. So it must not be obsoleted. ++But I don\[aq]t think users want to rename branches so often. ++ ++If CONFIG_SYSFS is disable, this paramater is always set to 0. ++. ++.TP ++.B sysrq=key ++Specifies MagicSysRq key for debugging aufs. ++You need to enable both of CONFIG_MAGIC_SYSRQ and CONFIG_AUFS_DEBUG. ++Currently this is for developers only. ++The default is \[oq]a\[cq]. ++. ++.TP ++.B debug= 0 | 1 ++Specifies disable(0) or enable(1) debug print in aufs. ++This parameter can be changed dynamically. ++You need to enable CONFIG_AUFS_DEBUG. ++Currently this is for developers only. ++The default is \[oq]0\[cq] (disable). ++ ++.\" ---------------------------------------------------------------------- ++.SH Entries under Sysfs and Debugfs ++See linux/Documentation/ABI/*/{sys,debug}fs-aufs. ++ ++.\" ---------------------------------------------------------------------- ++.SH Branch Syntax ++.TP ++.B dir_path[ =permission [ + attribute ] ] ++.TQ ++.B permission := rw | ro | rr ++.TQ ++.B attribute := wh | nolwh ++dir_path is a directory path. ++The keyword after \[oq]dir_path=\[cq] is a ++permission flags for that branch. ++Comma, colon and the permission flags string (including \[oq]=\[cq])in the path ++are not allowed. ++ ++Any filesystem can be a branch, But some are not accepted such like ++sysfs, procfs and unionfs. ++If you specify such filesystems as an aufs branch, aufs will return an error ++saying it is unsupported. ++ ++Cramfs in linux stable release has strange inodes and it makes aufs ++confused. For example, ++.nf ++$ mkdir -p w/d1 w/d2 ++$ > w/z1 ++$ > w/z2 ++$ mkcramfs w cramfs ++$ sudo mount -t cramfs -o ro,loop cramfs /mnt ++$ find /mnt -ls ++ 76 1 drwxr-xr-x 1 jro 232 64 Jan 1 1970 /mnt ++ 1 1 drwxr-xr-x 1 jro 232 0 Jan 1 1970 /mnt/d1 ++ 1 1 drwxr-xr-x 1 jro 232 0 Jan 1 1970 /mnt/d2 ++ 1 1 -rw-r--r-- 1 jro 232 0 Jan 1 1970 /mnt/z1 ++ 1 1 -rw-r--r-- 1 jro 232 0 Jan 1 1970 /mnt/z2 ++.fi ++ ++All these two directories and two files have the same inode with one ++as their link count. Aufs cannot handle such inode correctly. ++Currently, aufs involves a tiny workaround for such inodes. But some ++applications may not work correctly since aufs inode number for such ++inode will change silently. ++If you do not have any empty files, empty directories or special files, ++inodes on cramfs will be all fine. ++ ++A branch should not be shared as the writable branch between multiple ++aufs. A readonly branch can be shared. ++ ++The maximum number of branches is configurable at compile time. ++The current value is \*[AUFS_BRANCH_MAX] which depends upon ++configuration. ++ ++When an unknown permission or attribute is given, aufs sets ro to that ++branch silently. ++ ++.SS Permission ++. ++.TP ++.B rw ++Readable and writable branch. Set as default for the first branch. ++If the branch filesystem is mounted as readonly, you cannot set it \[oq]rw.\[cq] ++.\" A filesystem which does not support link(2) and i_op\->setattr(), for ++.\" example FAT, will not be used as the writable branch. ++. ++.TP ++.B ro ++Readonly branch and it has no whiteouts on it. ++Set as default for all branches except the first one. Aufs never issue ++both of write operation and lookup operation for whiteout to this branch. ++. ++.TP ++.B rr ++Real readonly branch, special case of \[oq]ro\[cq], for natively readonly ++branch. Assuming the branch is natively readonly, aufs can optimize ++some internal operation. For example, if you specify \[oq]udba=inotify\[cq] ++option, aufs does not set inotify for the things on rr branch. ++Set by default for a branch whose fs-type is either \[oq]iso9660\[cq], ++\[oq]cramfs\[cq] or \[oq]romfs\[cq]. ++ ++When your branch exists on slower device and you have some ++capacity on your hdd, you may want to try ulobdev tool in ULOOP sample. ++It can cache the contents of the real devices on another faster device, ++so you will be able to get the better access performance. ++The ulobdev tool is for a generic block device, and the ulohttp is for a ++filesystem image on http server. ++If you want to spin down your hdd to save the ++battery life or something, then you may want to use ulobdev to save the ++access to the hdd, too. ++See $AufsCVS/sample/uloop in detail. ++ ++.SS Attribute ++. ++.TP ++.B wh ++Readonly branch and it has/might have whiteouts on it. ++Aufs never issue write operation to this branch, but lookup for whiteout. ++Use this as \[oq]<branch_dir>=ro+wh\[cq]. ++. ++.TP ++.B nolwh ++Usually, aufs creates a whiteout as a hardlink on a writable ++branch. This attributes prohibits aufs to create the hardlinked ++whiteout, including the source file of all hardlinked whiteout ++(\*[AUFS_WH_BASE].) ++If you do not like a hardlink, or your writable branch does not support ++link(2), then use this attribute. ++But I am afraid a filesystem which does not support link(2) natively ++will fail in other place such as copy-up. ++Use this as \[oq]<branch_dir>=rw+nolwh\[cq]. ++Also you may want to try \[oq]noplink\[cq] mount option, while it is not recommended. ++ ++.\" .SS FUSE as a branch ++.\" A FUSE branch needs special attention. ++.\" The struct fuse_operations has a statfs operation. It is OK, but the ++.\" parameter is struct statvfs* instead of struct statfs*. So almost ++.\" all user\-space implementaion will call statvfs(3)/fstatvfs(3) instead of ++.\" statfs(2)/fstatfs(2). ++.\" In glibc, [f]statvfs(3) issues [f]statfs(2), open(2)/read(2) for ++.\" /proc/mounts, ++.\" and stat(2) for the mountpoint. With this situation, a FUSE branch will ++.\" cause a deadlock in creating something in aufs. Here is a sample ++.\" scenario, ++.\" .\" .RS ++.\" .\" .IN -10 ++.\" .Bu ++.\" create/modify a file just under the aufs root dir. ++.\" .Bu ++.\" aufs aquires a write\-lock for the parent directory, ie. the root dir. ++.\" .Bu ++.\" A library function or fuse internal may call statfs for a fuse branch. ++.\" The create=mfs mode in aufs will surely call statfs for each writable ++.\" branches. ++.\" .Bu ++.\" FUSE in kernel\-space converts and redirects the statfs request to the ++.\" user\-space. ++.\" .Bu ++.\" the user\-space statfs handler will call [f]statvfs(3). ++.\" .Bu ++.\" the [f]statvfs(3) in glibc will access /proc/mounts and issue ++.\" stat(2) for the mountpoint. But those require a read\-lock for the aufs ++.\" root directory. ++.\" .Bu ++.\" Then a deadlock occurs. ++.\" .\" .RE 1 ++.\" .\" .IN ++.\" ++.\" In order to avoid this deadlock, I would suggest not to call ++.\" [f]statvfs(3) from fuse. Here is a sample code to do this. ++.\" .nf ++.\" struct statvfs stvfs; ++.\" ++.\" main() ++.\" { ++.\" statvfs(..., &stvfs) ++.\" or ++.\" fstatvfs(..., &stvfs) ++.\" stvfs.f_fsid = 0 ++.\" } ++.\" ++.\" statfs_handler(const char *path, struct statvfs *arg) ++.\" { ++.\" struct statfs stfs ++.\" ++.\" memcpy(arg, &stvfs, sizeof(stvfs)) ++.\" ++.\" statfs(..., &stfs) ++.\" or ++.\" fstatfs(..., &stfs) ++.\" ++.\" arg->f_bfree = stfs.f_bfree ++.\" arg->f_bavail = stfs.f_bavail ++.\" arg->f_ffree = stfs.f_ffree ++.\" arg->f_favail = /* any value */ ++.\" } ++.\" .fi ++ ++.\" ---------------------------------------------------------------------- ++.SH External Inode Number Bitmap, Translation Table and Generation Table (xino) ++Aufs uses one external bitmap file and one external inode number ++translation table files per an aufs and per a branch ++filesystem by default. ++Additionally when CONFIG_AUFS_EXPORT is enabled, one external inode ++generation table is added. ++The bitmap (and the generation table) is for recycling aufs inode number ++and the others ++are a table for converting an inode number on a branch to ++an aufs inode number. The default path ++is \[oq]first writable branch\[cq]/\*[AUFS_XINO_FNAME]. ++If there is no writable branch, the ++default path ++will be \*[AUFS_XINO_DEFPATH]. ++.\" A user who executes mount(8) needs the privilege to create xino ++.\" file. ++ ++If you enable CONFIG_SYSFS, the path of xino files are not shown in ++/proc/mounts (and /etc/mtab), instead it is shown in ++<sysfs>/fs/aufs/si_<id>/xi_path. ++Otherwise, it is shown in /proc/mounts unless it is not the default ++path. ++ ++Those files are always opened and read/write by aufs frequently. ++If your writable branch is on flash memory device, it is recommended ++to put xino files on other than flash memory by specifying \[oq]xino=\[cq] ++mount option. ++ ++The ++maximum file size of the bitmap is, basically, the amount of the ++number of all the files on all branches divided by 8 (the number of ++bits in a byte). ++For example, on a 4KB page size system, if you have 32,768 (or ++2,599,968) files in aufs world, ++then the maximum file size of the bitmap is 4KB (or 320KB). ++ ++The ++maximum file size of the table will ++be \[oq]max inode number on the branch x size of an inode number\[cq]. ++For example in 32bit environment, ++ ++.nf ++$ df -i /branch_fs ++/dev/hda14 2599968 203127 2396841 8% /branch_fs ++.fi ++ ++and /branch_fs is an branch of the aufs. When the inode number is ++assigned contiguously (without \[oq]hole\[cq]), the maximum xino file size for ++/branch_fs will be 2,599,968 x 4 bytes = about 10 MB. But it might not be ++allocated all of disk blocks. ++When the inode number is assigned discontinuously, the maximum size of ++xino file will be the largest inode number on a branch x 4 bytes. ++Additionally, the file size is limited to LLONG_MAX or the s_maxbytes ++in filesystem\[aq]s superblock (s_maxbytes may be smaller than ++LLONG_MAX). So the ++support-able largest inode number on a branch is less than ++2305843009213693950 (LLONG_MAX/4\-1). ++This is the current limitation of aufs. ++On 64bit environment, this limitation becomes more strict and the ++supported largest inode number is less than LLONG_MAX/8\-1. ++ ++The xino files are always hidden, i.e. removed. So you cannot ++do \[oq]ls \-l xino_file\[cq]. ++If you enable CONFIG_DEBUG_FS, you can check these information through ++<debugfs>/aufs/<si_id>/{xib,xi[0-9]*,xigen}. xib is for the bitmap file, ++xi0 ix for the first branch, and xi1 is for the next. xigen is for the ++generation table. ++xib and xigen are in the format of, ++ ++.nf ++<blocks>x<block size> <file size> ++.fi ++ ++Note that a filesystem usually has a ++feature called pre-allocation, which means a number of ++blocks are allocated automatically, and then deallocated ++silently when the filesystem thinks they are unnecessary. ++You do not have to be surprised the sudden changes of the number of ++blocks, when your filesystem which xino files are placed supports the ++pre-allocation feature. ++ ++The rests are hidden xino file information in the format of, ++ ++.nf ++<file count>, <blocks>x<block size> <file size> ++.fi ++ ++If the file count is larger than 1, it means some of your branches are ++on the same filesystem and the xino file is shared by them. ++Note that the file size may not be equal to the actual consuming blocks ++since xino file is a sparse file, i.e. a hole in a file which does not ++consume any disk blocks. ++ ++Once you unmount aufs, the xino files for that aufs are totally gone. ++It means that the inode number is not permanent across umount or ++shutdown. ++ ++The xino files should be created on the filesystem except NFS. ++If your first writable branch is NFS, you will need to specify xino ++file path other than NFS. ++Also if you are going to remove the branch where xino files exist or ++change the branch permission to readonly, you need to use xino option ++before del/mod the branch. ++ ++The bitmap file can be truncated. ++For example, if you delete a branch which has huge number of files, ++many inode numbers will be recycled and the bitmap will be truncated ++to smaller size. Aufs does this automatically when a branch is ++deleted. ++You can truncate it anytime you like if you specify \[oq]trunc_xib\[cq] mount ++option. But when the accessed inode number was not deleted, nothing ++will be truncated. ++If you do not want to truncate it (it may be slow) when you delete a ++branch, specify \[oq]notrunc_xib\[cq] after \[oq]del\[cq] mount option. ++ ++If you do not want to use xino, use noxino mount option. Use this ++option with care, since the inode number may be changed silently and ++unexpectedly anytime. ++For example, ++rmdir failure, recursive chmod/chown/etc to a large and deep directory ++or anything else. ++And some applications will not work correctly. ++.\" When the inode number has been changed, your system ++.\" can be crazy. ++If you want to change the xino default path, use xino mount option. ++ ++After you add branches, the persistence of inode number may not be ++guaranteed. ++At remount time, cached but unused inodes are discarded. ++And the newly appeared inode may have different inode number at the ++next access time. The inodes in use have the persistent inode number. ++ ++When aufs assigned an inode number to a file, and if you create the ++same named file on the upper branch directly, then the next time you ++access the file, aufs may assign another inode number to the file even ++if you use xino option. ++Some applications may treat the file whose inode number has been ++changed as totally different file. ++ ++.\" ---------------------------------------------------------------------- ++.SH Pseudo Link (hardlink over branches) ++Aufs supports \[oq]pseudo link\[cq] which is a logical hard-link over ++branches (cf. ln(1) and link(2)). ++In other words, a copied-up file by link(2) and a copied-up file which was ++hard-linked on a readonly branch filesystem. ++ ++When you have files named fileA and fileB which are ++hardlinked on a readonly branch, if you write something into fileA, ++aufs copies-up fileA to a writable branch, and write(2) the originally ++requested thing to the copied-up fileA. On the writable branch, ++fileA is not hardlinked. ++But aufs remembers it was hardlinked, and handles fileB as if it existed ++on the writable branch, by referencing fileA\[aq]s inode on the writable ++branch as fileB\[aq]s inode. ++ ++Once you unmount aufs, the plink info for that aufs kept in memory are totally ++gone. ++It means that the pseudo-link is not permanent. ++If you want to make plink permanent, try \[oq]auplink\[cq] utility just before ++one of these operations, ++unmounting your aufs, ++using \[oq]ro\[cq] or \[oq]noplink\[cq] mount option, ++deleting a branch from aufs, ++adding a branch into aufs, ++or changing your writable branch to readonly. ++ ++This utility will reproduces all real hardlinks on a writable branch by linking ++them, and removes pseudo-link info in memory and temporary link on the ++writable branch. ++Since this utility access your branches directly, you cannot hide them by ++\[oq]mount \-\-bind /tmp /branch\[cq] or something. ++ ++If you are willing to rebuild your aufs with the same branches later, you ++should use auplink utility before you umount your aufs. ++If you installed both of /sbin/mount.aufs and /sbin/umount.aufs, and your ++mount(8) and umount(8) support them, ++\[oq]auplink\[cq] utility will be executed automatically and flush pseudo-links. ++ ++.nf ++# auplink /your/aufs/root flush ++# umount /your/aufs/root ++or ++# auplink /your/aufs/root flush ++# mount -o remount,mod:/your/writable/branch=ro /your/aufs/root ++or ++# auplink /your/aufs/root flush ++# mount -o remount,noplink /your/aufs/root ++or ++# auplink /your/aufs/root flush ++# mount -o remount,del:/your/aufs/branch /your/aufs/root ++or ++# auplink /your/aufs/root flush ++# mount -o remount,append:/your/aufs/branch /your/aufs/root ++.fi ++ ++The plinks are kept both in memory and on disk. When they consumes too much ++resources on your system, you can use the \[oq]auplink\[cq] utility at anytime and ++throw away the unnecessary pseudo-links in safe. ++ ++Additionally, the \[oq]auplink\[cq] utility is very useful for some security reasons. ++For example, when you have a directory whose permission flags ++are 0700, and a file who is 0644 under the 0700 directory. Usually, ++all files under the 0700 directory are private and no one else can see ++the file. But when the directory is 0711 and someone else knows the 0644 ++filename, he can read the file. ++ ++Basically, aufs pseudo-link feature creates a temporary link under the ++directory whose owner is root and the permission flags are 0700. ++But when the writable branch is NFS, aufs sets 0711 to the directory. ++When the 0644 file is pseudo-linked, the temporary link, of course the ++contents of the file is totally equivalent, will be created under the ++0711 directory. The filename will be generated by its inode number. ++While it is hard to know the generated filename, someone else may try peeping ++the temporary pseudo-linked file by his software tool which may try the name ++from one to MAX_INT or something. ++In this case, the 0644 file will be read unexpectedly. ++I am afraid that leaving the temporary pseudo-links can be a security hole. ++It makes sense to execute \[oq]auplink /your/aufs/root flush\[cq] ++periodically, when your writable branch is NFS. ++ ++When your writable branch is not NFS, or all users are careful enough to set 0600 ++to their private files, you do not have to worry about this issue. ++ ++If you do not want this feature, use \[oq]noplink\[cq] mount option. ++ ++.SS The behaviours of plink and noplink ++This sample shows that the \[oq]f_src_linked2\[cq] with \[oq]noplink\[cq] option cannot follow ++the link. ++ ++.nf ++none on /dev/shm/u type aufs (rw,xino=/dev/shm/rw/.aufs.xino,br:/dev/shm/rw=rw:/dev/shm/ro=ro) ++$ ls -li ../r?/f_src_linked* ./f_src_linked* ./copied ++ls: ./copied: No such file or directory ++15 -rw-r--r-- 2 jro jro 2 Dec 22 11:03 ../ro/f_src_linked ++15 -rw-r--r-- 2 jro jro 2 Dec 22 11:03 ../ro/f_src_linked2 ++22 -rw-r--r-- 2 jro jro 2 Dec 22 11:03 ./f_src_linked ++22 -rw-r--r-- 2 jro jro 2 Dec 22 11:03 ./f_src_linked2 ++$ echo abc >> f_src_linked ++$ cp f_src_linked copied ++$ ls -li ../r?/f_src_linked* ./f_src_linked* ./copied ++15 -rw-r--r-- 2 jro jro 2 Dec 22 11:03 ../ro/f_src_linked ++15 -rw-r--r-- 2 jro jro 2 Dec 22 11:03 ../ro/f_src_linked2 ++36 -rw-r--r-- 2 jro jro 6 Dec 22 11:03 ../rw/f_src_linked ++53 -rw-r--r-- 1 jro jro 6 Dec 22 11:03 ./copied ++22 -rw-r--r-- 2 jro jro 6 Dec 22 11:03 ./f_src_linked ++22 -rw-r--r-- 2 jro jro 6 Dec 22 11:03 ./f_src_linked2 ++$ cmp copied f_src_linked2 ++$ ++ ++none on /dev/shm/u type aufs (rw,xino=/dev/shm/rw/.aufs.xino,noplink,br:/dev/shm/rw=rw:/dev/shm/ro=ro) ++$ ls -li ../r?/f_src_linked* ./f_src_linked* ./copied ++ls: ./copied: No such file or directory ++17 -rw-r--r-- 2 jro jro 2 Dec 22 11:03 ../ro/f_src_linked ++17 -rw-r--r-- 2 jro jro 2 Dec 22 11:03 ../ro/f_src_linked2 ++23 -rw-r--r-- 2 jro jro 2 Dec 22 11:03 ./f_src_linked ++23 -rw-r--r-- 2 jro jro 2 Dec 22 11:03 ./f_src_linked2 ++$ echo abc >> f_src_linked ++$ cp f_src_linked copied ++$ ls -li ../r?/f_src_linked* ./f_src_linked* ./copied ++17 -rw-r--r-- 2 jro jro 2 Dec 22 11:03 ../ro/f_src_linked ++17 -rw-r--r-- 2 jro jro 2 Dec 22 11:03 ../ro/f_src_linked2 ++36 -rw-r--r-- 1 jro jro 6 Dec 22 11:03 ../rw/f_src_linked ++53 -rw-r--r-- 1 jro jro 6 Dec 22 11:03 ./copied ++23 -rw-r--r-- 2 jro jro 6 Dec 22 11:03 ./f_src_linked ++23 -rw-r--r-- 2 jro jro 6 Dec 22 11:03 ./f_src_linked2 ++$ cmp copied f_src_linked2 ++cmp: EOF on f_src_linked2 ++$ ++.fi ++ ++.\" ++.\" If you add/del a branch, or link/unlink the pseudo-linked ++.\" file on a branch ++.\" directly, aufs cannot keep the correct link count, but the status of ++.\" \[oq]pseudo-linked.\[cq] ++.\" Those files may or may not keep the file data after you unlink the ++.\" file on the branch directly, especially the case of your branch is ++.\" NFS. ++ ++If you add a branch which has fileA or fileB, aufs does not follow the ++pseudo link. The file on the added branch has no relation to the same ++named file(s) on the lower branch(es). ++If you use noxino mount option, pseudo link will not work after the ++kernel shrinks the inode cache. ++ ++This feature will not work for squashfs before version 3.2 since its ++inode is tricky. ++When the inode is hardlinked, squashfs inodes has the same inode ++number and correct link count, but the inode memory object is ++different. Squashfs inodes (before v3.2) are generated for each, even ++they are hardlinked. ++ ++.\" ---------------------------------------------------------------------- ++.SH User\[aq]s Direct Branch Access (UDBA) ++UDBA means a modification to a branch filesystem manually or directly, ++e.g. bypassing aufs. ++While aufs is designed and implemented to be safe after UDBA, ++it can make yourself and your aufs confused. And some information like ++aufs inode will be incorrect. ++For example, if you rename a file on a branch directly, the file on ++aufs may ++or may not be accessible through both of old and new name. ++Because aufs caches various information about the files on ++branches. And the cache still remains after UDBA. ++ ++Aufs has a mount option named \[oq]udba\[cq] which specifies the test level at ++access time whether UDBA was happened or not. ++. ++.TP ++.B udba=none ++Aufs trusts the dentry and the inode cache on the system, and never ++test about UDBA. With this option, aufs runs fastest, but it may show ++you incorrect data. ++Additionally, if you often modify a branch ++directly, aufs will not be able to trace the changes of inodes on the ++branch. It can be a cause of wrong behaviour, deadlock or anything else. ++ ++It is recommended to use this option only when you are sure that ++nobody access a file on a branch. ++It might be difficult for you to achieve real \[oq]no UDBA\[cq] world when you ++cannot stop your users doing \[oq]find / \-ls\[cq] or something. ++If you really want to forbid all of your users to UDBA, here is a trick ++for it. ++With this trick, users cannot see the ++branches directly and aufs runs with no problem, except \[oq]auplink\[cq] utility. ++But if you are not familiar with aufs, this trick may make ++yourself confused. ++ ++.nf ++# d=/tmp/.aufs.hide ++# mkdir $d ++# for i in $branches_you_want_to_hide ++> do ++> mount -n --bind $d $i ++> done ++.fi ++ ++When you unmount the aufs, delete/modify the branch by remount, or you ++want to show the hidden branches again, unmount the bound ++/tmp/.aufs.hide. ++ ++.nf ++# umount -n $branches_you_want_to_unbound ++.fi ++ ++If you use FUSE filesystem as an aufs branch which supports hardlink, ++you should not set this option, since FUSE makes inode objects for ++each hardlinks (at least in linux\-2.6.23). When your FUSE filesystem ++maintains them at link/unlinking, it is equivalent ++to \[oq]direct branch access\[cq] for aufs. ++ ++. ++.TP ++.B udba=reval ++Aufs tests only the existence of the file which existed. If ++the existed file was removed on the branch directly, aufs ++discard the cache about the file and ++re-lookup it. So the data will be updated. ++This test is at minimum level to keep the performance and ensure the ++existence of a file. ++This is default and aufs runs still fast. ++ ++This rule leads to some unexpected situation, but I hope it is ++harmless. Those are totally depends upon cache. Here are just a few ++examples. ++. ++.RS ++.Bu ++If the file is cached as negative or ++not-existed, aufs does not test it. And the file is still handled as ++negative after a user created the file on a branch directly. If the ++file is not cached, aufs will lookup normally and find the file. ++. ++.Bu ++When the file is cached as positive or existed, and a user created the ++same named file directly on the upper branch. Aufs detects the cached ++inode of the file is still existing and will show you the old (cached) ++file which is on the lower branch. ++. ++.Bu ++When the file is cached as positive or existed, and a user renamed the ++file by rename(2) directly. Aufs detects the inode of the file is ++still existing. You may or may not see both of the old and new files. ++Todo: If aufs also tests the name, we can detect this case. ++.RE ++ ++If your outer modification (UDBA) is rare and you can ignore the ++temporary and minor differences between virtual aufs world and real ++branch filesystem, then try this mount option. ++. ++.TP ++.B udba=inotify ++Aufs sets `inotify' to all the accessed directories on its branches ++and receives the event about the dir and its children. It consumes ++resources, cpu and memory. And I am afraid that the performance will be ++hurt, but it is most strict test level. ++There are some limitations of linux inotify, see also Inotify ++Limitation. ++So it is recommended to leave udba default option usually, and set it ++to inotify by remount when you need it. ++ ++When a user accesses the file which was notified UDBA before, the cached data ++about the file will be discarded and aufs re-lookup it. So the data will ++be updated. ++When an error condition occurs between UDBA and aufs operation, aufs ++will return an error, including EIO. ++To use this option, you need to enable CONFIG_INOTIFY and ++CONFIG_AUFS_UDBA_INOTIFY. ++ ++To rename/rmdir a directory on a branch directory may reveal the same named ++directory on the lower branch. Aufs tries re-lookuping the renamed ++directory and the revealed directory and assigning different inode ++number to them. But the inode number including their children can be a ++problem. The inode numbers will be changed silently, and ++aufs may produce a warning. If you rename a directory repeatedly and ++reveal/hide the lower directory, then aufs may confuse their inode ++numbers too. It depends upon the system cache. ++ ++When you make a directory in aufs and mount other filesystem on it, ++the directory in aufs cannot be removed expectedly because it is a ++mount point. But the same named directory on the writable branch can ++be removed, if someone wants. It is just an empty directory, instead ++of a mount point. ++Aufs cannot stop such direct rmdir, but produces a warning about it. ++ ++If the pseudo-linked file is hardlinked or unlinked on the branch ++directly, its inode link count in aufs may be incorrect. It is ++recommended to flush the psuedo-links by auplink script. ++ ++.\" ---------------------------------------------------------------------- ++.SH Linux Inotify Limitation ++Unfortunately, current inotify (linux\-2.6.18) has some limitations, ++and aufs must derive it. ++ ++.SS IN_ATTRIB, updating atime ++When a file/dir on a branch is accessed directly, the inode atime (access ++time, cf. stat(2)) may or may not be updated. In some cases, inotify ++does not fire this event. So the aufs inode atime may remain old. ++ ++.SS IN_ATTRIB, updating nlink ++When the link count of a file on a branch is incremented by link(2) ++directly, ++inotify fires IN_CREATE to the parent ++directory, but IN_ATTRIB to the file. So the aufs inode nlink may ++remain old. ++ ++.SS IN_DELETE, removing file on NFS ++When a file on a NFS branch is deleted directly, inotify may or may ++not fire ++IN_DELETE event. It depends upon the status of dentry ++(DCACHE_NFSFS_RENAMED flag). ++In this case, the file on aufs seems still exists. Aufs and any user can see ++the file. ++ ++.SS IN_IGNORED, deleted rename target ++When a file/dir on a branch is unlinked by rename(2) directly, inotify ++fires IN_IGNORED which means the inode is deleted. Actually, in some ++cases, the inode survives. For example, the rename target is linked or ++opened. In this case, inotify watch set by aufs is removed by VFS and ++inotify. ++And aufs cannot receive the events anymore. So aufs may show you ++incorrect data about the file/dir. ++ ++.\" ---------------------------------------------------------------------- ++.SH Copy On Write, or aufs internal copyup and copydown ++Every stackable filesystem which implements copy\-on\-write supports the ++copyup feature. The feature is to copy a file/dir from the lower branch ++to the upper internally. When you have one readonly branch and one ++upper writable branch, and you append a string to a file which exists on ++the readonly branch, then aufs will copy the file from the readonly ++branch to the writable branch with its directory hierarchy. It means one ++write(2) involves several logical/internal mkdir(2), creat(2), read(2), ++write(2) and close(2) systemcalls ++before the actual expected write(2) is performed. Sometimes it may take ++a long time, particulary when the file is very large. ++If CONFIG_AUFS_DEBUG is enabled, aufs produces a message saying `copying ++a large file.\[aq] ++ ++You may see the message when you change the xino file path or ++truncate the xino/xib files. Sometimes those files can be large and may ++take a long time to handle them. ++ ++.\" ---------------------------------------------------------------------- ++.SH Policies to Select One among Multiple Writable Branches ++Aufs has some policies to select one among multiple writable branches ++when you are going to write/modify something. There are two kinds of ++policies, one is for newly create something and the other is for ++internal copy-up. ++You can select them by specifying mount option \[oq]create=CREATE_POLICY\[cq] ++or \[oq]cpup=COPYUP_POLICY.\[cq] ++These policies have no meaning when you have only one writable ++branch. If there is some meaning, it must hurt the performance. ++ ++.SS Exceptions for Policies ++In every cases below, even if the policy says that the branch where a ++new file should be created is /rw2, the file will be created on /rw1. ++. ++.Bu ++If there is a readonly branch with \[oq]wh\[cq] attribute above the ++policy-selected branch and the parent dir is marked as opaque, ++or the target (creating) file is whiteouted on the ro+wh branch, then ++the policy will be ignored and the target file will be created on the ++nearest upper writable branch than the ro+wh branch. ++.RS ++.nf ++/aufs = /rw1 + /ro+wh/diropq + /rw2 ++/aufs = /rw1 + /ro+wh/wh.tgt + /rw2 ++.fi ++.RE ++. ++.Bu ++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 policy will be 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. ++.RS ++.nf ++/aufs = /rw1/diropq + /rw2 ++/aufs = /rw1/wh.tgt + /rw2 ++.fi ++.RE ++. ++.Bu ++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\[aq]t be, ie. the ++branch where the source exists is readonly, then they will follow the ++copyup policy. ++. ++.Bu ++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 are existing and selects the higher ++one. If the selected branch is readonly, then aufs follows the copyup ++policy. ++ ++.SS Policies for Creating ++. ++.TP ++.B create=tdp | top\-down\-parent ++Selects the highest writable branch where the parent dir exists. If ++the parent dir does not exist on a writable branch, then the internal ++copyup will happen. The policy for this copyup is always \[oq]bottom-up.\[cq] ++This is the default policy. ++. ++.TP ++.B create=rr | round\-robin ++Selects a writable branch in round robin. 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 are created on the same branch. ++. ++.TP ++.B create=mfs[:second] | most\-free\-space[:second] ++Selects a writable branch which has most free space. In order to keep ++the performance, you can specify the duration (\[oq]second\[cq]) which makes ++aufs hold the index of last selected writable branch until the ++specified seconds expires. The first time you create something in aufs ++after the specified seconds expired, aufs checks the amount of free ++space of all writable branches by internal statfs call ++and the held branch index will be updated. ++The default value is \*[AUFS_MFS_SECOND_DEF] seconds. ++. ++.TP ++.B create=mfsrr:low[:second] ++Selects a writable branch in most-free-space mode first, and then ++round-robin mode. If the selected branch has less free space than the ++specified value \[oq]low\[cq] in bytes, then aufs re-tries in round-robin mode. ++.\" \[oq]G\[cq], \[oq]M\[cq] and \[oq]K\[cq] (case insensitive) can be followed after \[oq]low.\[cq] Or ++Try an arithmetic expansion of shell which is defined by POSIX. ++For example, $((10 * 1024 * 1024)) for 10M. ++You can also specify the duration (\[oq]second\[cq]) which is equivalent to ++the \[oq]mfs\[cq] mode. ++. ++.TP ++.B create=pmfs[:second] ++Selects a writable branch where the parent dir exists, such as tdp ++mode. When the parent dir exists on multiple writable branches, aufs ++selects the one which has most free space, such as mfs mode. ++ ++.SS Policies for Copy-Up ++. ++.TP ++.B cpup=tdp | top\-down\-parent ++Equivalent to the same named policy for create. ++This is the default policy. ++. ++.TP ++.B cpup=bup | bottom\-up\-parent ++Selects the writable branch where the parent dir exists and the branch ++is nearest upper one from the copyup-source. ++. ++.TP ++.B cpup=bu | bottom\-up ++Selects the nearest upper writable branch from the copyup-source, ++regardless the existence of the parent dir. ++ ++.\" ---------------------------------------------------------------------- ++.SH Exporting Aufs via NFS ++Aufs is supporting NFS-exporting. ++Since aufs has no actual block device, you need to add NFS \[oq]fsid\[cq] option at ++exporting. Refer to the manual of NFS about the detail of this option. ++ ++There are some limitations or requirements. ++.RS ++.Bu ++The branch filesystem must support NFS-exporting. ++.Bu ++NFSv2 is not supported. When you mount the exported aufs from your NFS ++client, you will need to some NFS options like v3 or nfsvers=3, ++especially if it is nfsroot. ++.Bu ++If the size of the NFS file handle on your branch filesystem is large, ++aufs will ++not be able to handle it. The maximum size of NFSv3 file ++handle for a filesystem is 64 bytes. Aufs uses 24 bytes for 32bit ++system, plus 12 bytes for 64bit system. The rest is a room for a file ++handle of a branch filesystem. ++.Bu ++The External Inode Number Bitmap, Translation Table and Generation Table ++(xino) is ++required since NFS file ++handle is based upon inode number. The mount option \[oq]xino\[cq] is enabled ++by default. ++The external inode generation table and its debugfs entry ++(<debugfs>/aufs/si_*/xigen) is created when CONFIG_AUFS_EXPORT is ++enabled even if you don\[aq]t export aufs actually. ++The size of the external inode generation table grows only, never be ++truncated. You might need to pay attention to the free space of the ++filesystem where xino files are placed. By default, it is the first ++writable branch. ++.Bu ++The branch filesystems must be accessible, which means \[oq]not hidden.\[cq] ++It means you need to \[oq]mount \-\-move\[cq] when you use initramfs and ++switch_root(8), or chroot(8). ++.RE ++ ++.\" ---------------------------------------------------------------------- ++.SH Dentry and Inode Caches ++If you want to clear caches on your system, there are several tricks ++for that. If your system ram is low, ++try \[oq]find /large/dir \-ls > /dev/null\[cq]. ++It will read many inodes and dentries and cache them. Then old caches will be ++discarded. ++But when you have large ram or you do not have such large ++directory, it is not effective. ++ ++If you want to discard cache within a certain filesystem, ++try \[oq]mount \-o remount /your/mntpnt\[cq]. Some filesystem may return an error of ++EINVAL or something, but VFS discards the unused dentry/inode caches on the ++specified filesystem. ++ ++.\" ---------------------------------------------------------------------- ++.SH Compatible/Incompatible with Unionfs Version 1.x Series ++If you compile aufs with \-DCONFIG_AUFS_COMPAT, dirs= option and =nfsro ++branch permission flag are available. They are interpreted as ++br: option and =ro flags respectively. ++ \[oq]debug\[cq], \[oq]delete\[cq], \[oq]imap\[cq] options are ignored silently. When you ++compile aufs without \-DCONFIG_AUFS_COMPAT, these three options are ++also ignored, but a warning message is issued. ++ ++Ignoring \[oq]delete\[cq] option, and to keep filesystem consistency, aufs tries ++writing something to only one branch in a single systemcall. It means ++aufs may copyup even if the copyup-src branch is specified as writable. ++For example, you have two writable branches and a large regular file ++on the lower writable branch. When you issue rename(2) to the file on aufs, ++aufs may copyup it to the upper writable branch. ++If this behaviour is not what you want, then you should rename(2) it ++on the lower branch directly. ++ ++And there is a simple shell ++script \[oq]unionctl\[cq] under sample subdirectory, which is compatible with ++unionctl(8) in ++Unionfs Version 1.x series, except \-\-query action. ++This script executes mount(8) with \[oq]remount\[cq] option and uses ++add/del/mod aufs mount options. ++If you are familiar with Unionfs Version 1.x series and want to use unionctl(8), you can ++try this script instead of using mount \-o remount,... directly. ++Aufs does not support ioctl(2) interface. ++This script is highly depending upon mount(8) in ++util\-linux\-2.12p package, and you need to mount /proc to use this script. ++If your mount(8) version differs, you can try modifying this ++script. It is very easy. ++The unionctl script is just for a sample usage of aufs remount ++interface. ++ ++Aufs uses the external inode number bitmap and translation table by ++default. ++ ++The default branch permission for the first branch is \[oq]rw\[cq], and the ++rest is \[oq]ro.\[cq] ++ ++The whiteout is for hiding files on lower branches. Also it is applied ++to stop readdir going lower branches. ++The latter case is called \[oq]opaque directory.\[cq] Any ++whiteout is an empty file, it means whiteout is just an mark. ++In the case of hiding lower files, the name of whiteout is ++\[oq]\*[AUFS_WH_PFX]<filename>.\[cq] ++And in the case of stopping readdir, the name is ++\[oq]\*[AUFS_WH_PFX]\*[AUFS_WH_PFX].opq\[cq] or ++\[oq]\*[AUFS_WH_PFX]__dir_opaque.\[cq] The name depends upon your compile ++configuration ++CONFIG_AUFS_COMPAT. ++.\" All of newly created or renamed directory will be opaque. ++All whiteouts are hardlinked, ++including \[oq]<writable branch top dir>/\*[AUFS_WH_BASE].\[cq] ++ ++The hardlink on an ordinary (disk based) filesystem does not ++consume inode resource newly. But in linux tmpfs, the number of free ++inodes will be decremented by link(2). It is recommended to specify ++nr_inodes option to your tmpfs if you meet ENOSPC. Use this option ++after checking by \[oq]df \-i.\[cq] ++ ++When you rmdir or rename-to the dir who has a number of whiteouts, ++aufs rename the dir to the temporary whiteouted-name like ++\[oq]\*[AUFS_WH_PFX]<dir>.<random hex>.\[cq] Then remove it after actual operation. ++cf. mount option \[oq]dirwh.\[cq] ++ ++.\" ---------------------------------------------------------------------- ++.SH Incompatible with an Ordinary Filesystem ++stat(2) returns the inode info from the first existence inode among ++the branches, except the directory link count. ++Aufs computes the directory link count larger than the exact value usually, in ++order to keep UNIX filesystem semantics, or in order to shut find(1) mouth up. ++The size of a directory may be wrong too, but it has to do no harm. ++The timestamp of a directory will not be updated when a file is ++created or removed under it, and it was done on a lower branch. ++ ++The test for permission bits has two cases. One is for a directory, ++and the other is for a non-directory. In the case of a directory, aufs ++checks the permission bits of all existing directories. It means you ++need the correct privilege for the directories including the lower ++branches. ++The test for a non-directory is more simple. It checks only the ++topmost inode. ++ ++statfs(2) returns the information of the first branch info except ++namelen when \[oq]nosum\[cq] is specified (the default). The namelen is ++decreased by the whiteout prefix length. And the block size may differ ++from st_blksize which is obtained by stat(2). ++ ++Remember, seekdir(3) and telldir(3) are not defined in POSIX. They may ++not work as you expect. Try rewinddir(3) or re-open the dir. ++ ++The whiteout prefix (\*[AUFS_WH_PFX]) is reserved on all branches. Users should ++not handle the filename begins with this prefix. ++In order to future whiteout, the maxmum filename length is limited by ++the longest value \- \*[AUFS_WH_PFX_LEN]. It may be a violation of POSIX. ++ ++If you dislike the difference between the aufs entries in /etc/mtab ++and /proc/mounts, and if you are using mount(8) in util\-linux package, ++then try ./mount.aufs utility. Copy the script to /sbin/mount.aufs. ++This simple utility tries updating ++/etc/mtab. If you do not care about /etc/mtab, you can ignore this ++utility. ++Remember this utility is highly depending upon mount(8) in ++util\-linux\-2.12p package, and you need to mount /proc. ++ ++Since aufs uses its own inode and dentry, your system may cache huge ++number of inodes and dentries. It can be as twice as all of the files ++in your union. ++It means that unmounting or remounting readonly at shutdown time may ++take a long time, since mount(2) in VFS tries freeing all of the cache ++on the target filesystem. ++ ++When you open a directory, aufs will open several directories ++internally. ++It means you may reach the limit of the number of file descriptor. ++And when the lower directory cannot be opened, aufs will close all the ++opened upper directories and return an error. ++ ++The sub-mount under the branch ++of local filesystem ++is ignored. ++For example, if you have mount another filesystem on ++/branch/another/mntpnt, the files under \[oq]mntpnt\[cq] will be ignored by aufs. ++It is recommended to mount the sub-mount under the mounted aufs. ++For example, ++ ++.nf ++# sudo mount /dev/sdaXX /ro_branch ++# d=another/mntpnt ++# sudo mount /dev/sdbXX /ro_branch/$d ++# mkdir -p /rw_branch/$d ++# sudo mount -t aufs -o br:/rw_branch:/ro_branch none /aufs ++# sudo mount -t aufs -o br:/rw_branch/${d}:/ro_branch/${d} none /aufs/another/$d ++.fi ++ ++There are several characters which are not allowed to use in a branch ++directory path and xino filename. See detail in Branch Syntax and Mount ++Option. ++ ++The file-lock which means fcntl(2) with F_SETLK, F_SETLKW or F_GETLK, flock(2) ++and lockf(3), is applied to virtual aufs file only, not to the file on a ++branch. It means you can break the lock by accessing a branch directly. ++TODO: check \[oq]security\[cq] to hook locks, as inotify does. ++ ++The I/O to the named pipe or local socket are not handled by aufs, even ++if it exists in aufs. After the reader and the writer established their ++connection if the pipe/socket are copied-up, they keep using the old one ++instead of the copied-up one. ++ ++The fsync(2) and fdatasync(2) systemcalls return 0 which means success, even ++if the given file descriptor is not opened for writing. ++I am afraid this behaviour may violate some standards. Checking the ++behaviour of fsync(2) on ext2, aufs decided to return success. ++ ++If you want to use disk-quota, you should set it up to your writable ++branch since aufs does not have its own block device. ++ ++When your aufs is the root directory of your system, and your system ++tells you some of the filesystem were not unmounted cleanly, try these ++procedure when you shutdown your system. ++.nf ++# mount -no remount,ro / ++# for i in $writable_branches ++# do mount -no remount,ro $i ++# done ++.fi ++If your xino file is on a hard drive, you also need to specify ++\[oq]noxino\[cq] option or \[oq]xino=/your/tmpfs/xino\[cq] at remounting root ++directory. ++ ++To rename(2) directory may return EXDEV even if both of src and tgt ++are on the same aufs. When the rename-src dir exists on multiple ++branches and the lower dir has child(ren), aufs has to copyup all his ++children. It can be recursive copyup. Current aufs does not support ++such huge copyup operation at one time in kernel space, instead ++produces a warning and returns EXDEV. ++Generally, mv(1) detects this error and tries mkdir(2) and ++rename(2) or copy/unlink recursively. So the result is harmless. ++If your application which issues rename(2) for a directory does not ++support EXDEV, it will not work on aufs. ++Also this specification is applied to the case when the src directroy ++exists on the lower readonly branch and it has child(ren). ++ ++If a sudden accident such like a power failure happens during aufs is ++performing, and regular fsck for branch filesystems is completed after ++the disaster, you need to extra fsck for aufs writable branches. It is ++necessary to check whether the whiteout remains incorrectly or not, ++eg. the real filename and the whiteout for it under the same parent ++directory. If such whiteout remains, aufs cannot handle the file ++correctly. ++To check the consistency from the aufs\[aq] point of view, you can use a ++simple shell script called /sbin/auchk. Its purpose is a fsck tool for ++aufs, and it checks the illegal whiteout, the remained ++pseudo-links and the remained aufs-temp files. If they are found, the ++utility reports you and asks whether to delete or not. ++It is recommended to execute /sbin/auchk for every writable branch ++filesystem before mouting aufs if the system experienced crash. ++ ++ ++.\" ---------------------------------------------------------------------- ++.SH EXAMPLES ++The mount options are interpreted from left to right at remount-time. ++These examples ++shows how the options are handled. (assuming /sbin/mount.aufs was ++installed) ++ ++.nf ++# mount -v -t aufs br:/day0:/base none /u ++none on /u type aufs (rw,xino=/day0/.aufs.xino,br:/day0=rw:/base=ro) ++# mount -v -o remount,\\ ++ prepend:/day1,\\ ++ xino=/day1/xino,\\ ++ mod:/day0=ro,\\ ++ del:/day0 \\ ++ /u ++none on /u type aufs (rw,xino=/day1/xino,br:/day1=rw:/base=ro) ++.fi ++ ++.nf ++# mount -t aufs br:/rw none /u ++# mount -o remount,append:/ro /u ++different uid/gid/permission, /ro ++# mount -o remount,del:/ro /u ++# mount -o remount,nowarn_perm,append:/ro /u ++# ++(there is no warning) ++.fi ++ ++.\" If you want to expand your filesystem size, aufs may help you by ++.\" adding an writable branch. Since aufs supports multiple writable ++.\" branches, the old writable branch can be being writable, if you want. ++.\" In this example, any modifications to the files under /ro branch will ++.\" be copied-up to /new, but modifications to the files under /rw branch ++.\" will not. ++.\" And the next example shows the modifications to the files under /rw branch ++.\" will be copied-up to /new/a. ++.\" ++.\" Todo: test multiple writable branches policy. cpup=nearest, cpup=exist_parent. ++.\" ++.\" .nf ++.\" # mount -v -t aufs br:/rw:/ro none /u ++.\" none on /u type aufs (rw,xino=/rw/.aufs.xino,br:/rw=rw:/ro=ro) ++.\" # mkfs /new ++.\" # mount -v -o remount,add:1:/new=rw /u ++.\" none on /u type aufs (rw,xino=/rw/.aufs.xino,br:/rw=rw:/new=rw:/ro=ro) ++.\" .fi ++.\" ++.\" .nf ++.\" # mount -v -t aufs br:/rw:/ro none /u ++.\" none on /u type aufs (rw,xino=/rw/.aufs.xino,br:/rw=rw:/ro=ro) ++.\" # mkfs /new ++.\" # mkdir /new/a new/b ++.\" # mount -v -o remount,add:1:/new/b=rw,prepend:/new/a,mod:/rw=ro /u ++.\" none on /u type aufs (rw,xino=/rw/.aufs.xino,br:/new/a=rw:/rw=ro:/new/b=rw:/ro=ro) ++.\" .fi ++ ++When you use aufs as root filesystem, it is recommended to consider to ++exclude some directories. For example, /tmp and /var/log are not need ++to stack in many cases. They do not usually need to copyup or to whiteout. ++Also the swapfile on aufs (a regular file, not a block device) is not ++supported. ++In order to exclude the specific dir from aufs, try bind mounting. ++ ++And there is a good sample which is for network booted diskless machines. See ++sample/ in detail. ++ ++.\" ---------------------------------------------------------------------- ++.SH DIAGNOSTICS ++When you add a branch to your union, aufs may warn you about the ++privilege or security of the branch, which is the permission bits, ++owner and group of the top directory of the branch. ++For example, when your upper writable branch has a world writable top ++directory, ++a malicious user can create any files on the writable branch directly, ++like copyup and modify manually. I am afraid it can be a security ++issue. ++ ++When you mount or remount your union without \-o ro common mount option ++and without writable branch, aufs will warn you that the first branch ++should be writable. ++ ++.\" It is discouraged to set both of \[oq]udba\[cq] and \[oq]noxino\[cq] mount options. In ++.\" this case the inode number under aufs will always be changed and may ++.\" reach the end of inode number which is a maximum of unsigned long. If ++.\" the inode number reaches the end, aufs will return EIO repeatedly. ++ ++When you set udba other than inotify and change something on your ++branch filesystem directly, later aufs may detect some mismatches to ++its cache. If it is a critical mismatch, aufs returns EIO. ++ ++When an error occurs in aufs, aufs prints the kernel message with ++\[oq]errno.\[cq] The priority of the message (log level) is ERR or WARNING which ++depends upon the message itself. ++You can convert the \[oq]errno\[cq] into the error message by perror(3), ++strerror(3) or something. ++For example, the \[oq]errno\[cq] in the message \[oq]I/O Error, write failed (\-28)\[cq] ++is 28 which means ENOSPC or \[oq]No space left on device.\[cq] ++ ++When CONFIG_AUFS_BR_RAMFS is enabled, you can specify ramfs as an aufs ++branch. Since ramfs is simple, it doesn't set the maximum link count ++originally. In aufs, it is very dangerous, particulary for ++whiteouts. Finally aufs sets the maxmimum link count for ramfs. Tha ++value is 32000 which is borrowed from ext2. ++ ++ ++.\" .SH Current Limitation ++. ++.\" ---------------------------------------------------------------------- ++.\" SYNOPSIS ++.\" briefly describes the command or function\[aq]s interface. For commands, this ++.\" shows the syntax of the command and its arguments (including options); bold- ++.\" face is used for as-is text and italics are used to indicate replaceable ++.\" arguments. Brackets ([]) surround optional arguments, vertical bars (|) sep- ++.\" arate choices, and ellipses (...) can be repeated. For functions, it shows ++.\" any required data declarations or #include directives, followed by the func- ++.\" tion declaration. ++. ++.\" DESCRIPTION ++.\" gives an explanation of what the command, function, or format does. Discuss ++.\" how it interacts with files and standard input, and what it produces on ++.\" standard output or standard error. Omit internals and implementation ++.\" details unless they\[aq]re critical for understanding the interface. Describe ++.\" the usual case; for information on options use the OPTIONS section. If ++.\" there is some kind of input grammar or complex set of subcommands, consider ++.\" describing them in a separate USAGE section (and just place an overview in ++.\" the DESCRIPTION section). ++. ++.\" RETURN VALUE ++.\" gives a list of the values the library routine will return to the caller and ++.\" the conditions that cause these values to be returned. ++. ++.\" EXIT STATUS ++.\" lists the possible exit status values or a program and the conditions that ++.\" cause these values to be returned. ++. ++.\" USAGE ++.\" describes the grammar of any sublanguage this implements. ++. ++.\" FILES ++.\" lists the files the program or function uses, such as configuration files, ++.\" startup files, and files the program directly operates on. Give the full ++.\" pathname of these files, and use the installation process to modify the ++.\" directory part to match user preferences. For many programs, the default ++.\" installation location is in /usr/local, so your base manual page should use ++.\" /usr/local as the base. ++. ++.\" ENVIRONMENT ++.\" lists all environment variables that affect your program or function and how ++.\" they affect it. ++. ++.\" SECURITY ++.\" discusses security issues and implications. Warn about configurations or ++.\" environments that should be avoided, commands that may have security impli- ++.\" cations, and so on, especially if they aren\[aq]t obvious. Discussing security ++.\" in a separate section isn\[aq]t necessary; if it\[aq]s easier to understand, place ++.\" security information in the other sections (such as the DESCRIPTION or USAGE ++.\" section). However, please include security information somewhere! ++. ++.\" CONFORMING TO ++.\" describes any standards or conventions this implements. ++. ++.\" NOTES ++.\" provides miscellaneous notes. ++. ++.\" BUGS ++.\" lists limitations, known defects or inconveniences, and other questionable ++.\" activities. ++ ++.SH COPYRIGHT ++Copyright \(co 2005\-2009 Junjiro R. Okajima ++ ++.SH AUTHOR ++Junjiro R. Okajima ++ ++.\" SEE ALSO ++.\" lists related man pages in alphabetical order, possibly followed by other ++.\" related pages or documents. Conventionally this is the last section. +diff -urN ./Documentation/filesystems/aufs/design/01intro.txt ./Documentation/filesystems/aufs/design/01intro.txt +--- ./Documentation/filesystems/aufs/design/01intro.txt 1970-01-01 01:00:00.000000000 +0100 ++++ ./Documentation/filesystems/aufs/design/01intro.txt 2009-04-06 10:26:45.000000000 +0200 +@@ -0,0 +1,128 @@ ++ ++# Copyright (C) 2005-2009 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. ++ ++Introduction ++---------------------------------------- ++ ++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. ++ ++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' 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 and ++Bharata B Rao) 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. ++Unionfs has a longer history. When I started implementing a stacking 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. ++ ++ ++Several characters/aspects of aufs ++---------------------------------------------------------------------- ++ ++Aufs has several characters or aspects. ++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. Caller 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 ++maintain inode number. 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 -urN ./Documentation/filesystems/aufs/design/02struct.txt ./Documentation/filesystems/aufs/design/02struct.txt +--- ./Documentation/filesystems/aufs/design/02struct.txt 1970-01-01 01:00:00.000000000 +0100 ++++ ./Documentation/filesystems/aufs/design/02struct.txt 2009-04-06 10:26:46.000000000 +0200 +@@ -0,0 +1,205 @@ ++ ++# Copyright (C) 2005-2009 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. ++ ++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 ++- [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 ++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 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. ++ ++Also a writable branch has three kinds of "whiteout bases". All these ++are existed when the branch is joined to aufs and the names are ++whiteout-ed doubly, so that users will never see their names in aufs ++hierarchy. ++1. a regular file which will be linked 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 important. ++ ++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. ++ ++ ++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 a 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. ++ ++Aufs implements a feature to truncate/refresh both of xino and xib to ++reduce the number of consumed disk blocks for these files. ++ ++ ++Virtual or Vertical Dir ++---------------------------------------------------------------------- ++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 ++old. 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. ++ ++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. ++ ++ ++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, and if the mkdir/write call arises SIGXFSZ or other signal, ++then the user process might gain a privilege or the generated core file ++was owned by a superuser. But I have a plan to switch to a new ++credential approach which will be introduced in linux-2.6.29. ++ ++Also aufs uses the system global workqueue ("events" kernel thread) too ++for asynchronous tasks, such like handling inotify, 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 ++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. +diff -urN ./Documentation/filesystems/aufs/design/03lookup.txt ./Documentation/filesystems/aufs/design/03lookup.txt +--- ./Documentation/filesystems/aufs/design/03lookup.txt 1970-01-01 01:00:00.000000000 +0100 ++++ ./Documentation/filesystems/aufs/design/03lookup.txt 2009-04-06 10:26:46.000000000 +0200 +@@ -0,0 +1,95 @@ ++ ++# Copyright (C) 2005-2009 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. ++ ++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. Generally ++speaking struct nameidata is a bigger structure and includes many ++information. 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, but it is not usable ++for a branch filesystem which requires struct nameidata. So aufs ++implements a simple lookup wrapper function. When a branch filesystem ++allows NULL as nameidata, it calls lookup_one_len(). Otherwise it builds ++a simplest nameidata and calls lookup_hash(). ++Here aufs applies "a principle in NFSD", ie. if the filesystem supports ++NFS-export, then it has to support NULL as a nameidata parameter for ++->create(), ->lookup() and ->d_revalidate(). So the lookup wrapper in ++aufs tests if ->s_export_op in the branch is NULL or not. ++ ++When a branch is a remote filesystem, aufs trusts its ->d_revalidate(). ++For d_revalidate, aufs implements three levels of revalidate tests. See ++"Revalidate Dentry and UDBA" in detail. ++ ++ ++Loopback Mount ++---------------------------------------------------------------------- ++Basically aufs supports any type of filesystem and block device for a ++branch (actually there are some exceptions). But it is prohibited to add ++a loopback mounted one whose backend file exists in a filesystem which is ++already added to aufs. The reason is to protect aufs from a recursive ++lookup. If it was allowed, the aufs lookup operation might re-enter a ++lookup for the loopback mounted branch in the same context, and will ++cause a deadlock. ++ ++ ++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 ++ 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 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 therevalidatin 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 ./Documentation/filesystems/aufs/design/04branch.txt ./Documentation/filesystems/aufs/design/04branch.txt +--- ./Documentation/filesystems/aufs/design/04branch.txt 1970-01-01 01:00:00.000000000 +0100 ++++ ./Documentation/filesystems/aufs/design/04branch.txt 2009-04-06 10:26:46.000000000 +0200 +@@ -0,0 +1,67 @@ ++ ++# Copyright (C) 2005-2009 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. ++ ++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 other 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 nothing to do 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 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 -urN ./Documentation/filesystems/aufs/design/05wbr_policy.txt ./Documentation/filesystems/aufs/design/05wbr_policy.txt +--- ./Documentation/filesystems/aufs/design/05wbr_policy.txt 1970-01-01 01:00:00.000000000 +0100 ++++ ./Documentation/filesystems/aufs/design/05wbr_policy.txt 2009-04-06 10:26:46.000000000 +0200 +@@ -0,0 +1,57 @@ ++ ++# Copyright (C) 2005-2009 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. ++ ++ ++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 two policies, round-robin and ++most-free-space policies. For copy-up three policies, top-down-parent, ++bottom-up-parent and bottom-up policies. ++ ++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 -urN ./Documentation/filesystems/aufs/design/06fmode_exec.txt ./Documentation/filesystems/aufs/design/06fmode_exec.txt +--- ./Documentation/filesystems/aufs/design/06fmode_exec.txt 1970-01-01 01:00:00.000000000 +0100 ++++ ./Documentation/filesystems/aufs/design/06fmode_exec.txt 2009-04-06 10:26:46.000000000 +0200 +@@ -0,0 +1,24 @@ ++ ++# Copyright (C) 2005-2009 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. ++ ++FMODE_EXEC and deny_write() ++---------------------------------------------------------------------- ++Generally Unix prevents an executing file from writing its filedata. ++In linux it is implemented by deny_write() and allow_write(). ++When a file is executed by exec() family, open_exec() (and sys_uselib()) ++they opens the file and calls deny_write(). If the file is aufs's virtual ++one, it has no meaning. The file which deny_write() is really necessary ++is the file on a branch. But the FMODE_EXEC flag is not passed to ++->open() operation. So aufs adopt a dirty trick. ++ ++- in order to get FMODE_EXEC, aufs ->lookup() and ->d_revalidate() set ++ nd->intent.open.file->private_data to nd->intent.open.flags temporary. ++- in aufs ->open(), when FMODE_EXEC is set in file->private_data, it ++ calls deny_write() for the file on a branch. ++- when the aufs file is released, allow_write() for the file on a branch ++ is called. +diff -urN ./Documentation/filesystems/aufs/design/07mmap.txt ./Documentation/filesystems/aufs/design/07mmap.txt +--- ./Documentation/filesystems/aufs/design/07mmap.txt 1970-01-01 01:00:00.000000000 +0100 ++++ ./Documentation/filesystems/aufs/design/07mmap.txt 2009-04-06 10:26:46.000000000 +0200 +@@ -0,0 +1,44 @@ ++ ++# Copyright (C) 2005-2009 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. ++ ++mmap(2) -- File Memory Mapping ++---------------------------------------------------------------------- ++In aufs, the file-mapped pages are shared between the file on a branch ++and the virtual one in aufs by overriding vm_operation, particularly ++->fault(). ++ ++In aufs_mmap(), ++- get and store vm_ops of the real file on a branch. ++- map the file of aufs by generic_file_mmap() and set aufs's vm ++ operations. ++ ++In aufs_fault(), ++- get the file of aufs from the passed vma, sleep if needed. ++- get the real file on a branch from the aufs file. ++- a race may happen. for instance a multithreaded library. so some lock ++ is implemented. ++- call ->fault() in the previously stored vm_ops with setting the ++ real file on a branch to vm_file. ++- restore vm_file and wake_up if someone else got sleep. ++ ++When a branch is added to or deleted from aufs, the same-named file may ++unveil and its contents will be replaced by the new one when a process ++read(2) through previously opened file. ++(Some users may not want to refresh the filedata. For such users, I ++have a plan to implement a mount option 'refrof' which decides to ++refresh the opened files or not. See plan.txt too.) ++In this case, an already mapped file will not be updated since the ++contents are a part of a process already and it should not be changed by ++aufs branch manipulation. (Even if MAP_SHARED is specified, currently). ++Of course, in case of the deleting branch has a busy file, it cannot be ++deleted from the union. ++ ++In Unionfs, it took an approach which the memory pages mapped to ++filedata are copied from the lower (real) file into the Unionfs's ++virtual one and handles it by address_space operations. Recently Unionfs ++changed it to this approach which aufs adopted since Jul 2006. +diff -urN ./Documentation/filesystems/aufs/design/08export.txt ./Documentation/filesystems/aufs/design/08export.txt +--- ./Documentation/filesystems/aufs/design/08export.txt 1970-01-01 01:00:00.000000000 +0100 ++++ ./Documentation/filesystems/aufs/design/08export.txt 2009-04-06 10:26:46.000000000 +0200 +@@ -0,0 +1,51 @@ ++ ++# Copyright (C) 2005-2009 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. ++ ++ ++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, get the parent inode number from handle and ++ search it in cache. and then open the 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 ./Documentation/filesystems/aufs/design/99plan.txt ./Documentation/filesystems/aufs/design/99plan.txt +--- ./Documentation/filesystems/aufs/design/99plan.txt 1970-01-01 01:00:00.000000000 +0100 ++++ ./Documentation/filesystems/aufs/design/99plan.txt 2009-04-06 10:26:46.000000000 +0200 +@@ -0,0 +1,125 @@ ++ ++# Copyright (C) 2005-2009 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. ++ ++Plan ++ ++Restoring some features which was implemented in aufs1. ++They were dropped in aufs2 in order to make source files simpler and ++easier to be reviewed. ++ ++ ++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" ++- then "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 best solution for this case. So I ++implemented 'dirperm1' and 'nodirperm1' option in aufs1, 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. ++ ++ ++Show Whiteout Mode (shwh) ++---------------------------------------------------------------------- ++Generally aufs hides the name of whiteouts. But in some cases, to show ++them is very useful for users. For instance, creating a new middle layer ++(branch) by merging existing layers. ++ ++(borrowing aufs1 HOW-TO from a user, Michael Towers) ++When you have three branches, ++- Bottom: 'system', squashfs (underlying base system), read-only ++- Middle: 'mods', squashfs, read-only ++- Top: 'overlay', ram (tmpfs), read-write ++ ++The top layer is loaded at boot time and saved at shutdown, to preserve ++the changes made to the system during the session. ++When larger changes have been made, or smaller changes have accumulated, ++the size of the saved top layer data grows. At this point, it would be ++nice to be able to merge the two overlay branches ('mods' and 'overlay') ++and rewrite the 'mods' squashfs, clearing the top layer and thus ++restoring save and load speed. ++ ++This merging is simplified by the use of another aufs mount, of just the ++two overlay branches using the 'shwh' option. ++# mount -t aufs -o ro,shwh,br:/livesys/overlay=ro+wh:/livesys/mods=rr+wh \ ++ aufs /livesys/merge_union ++ ++A merged view of these two branches is then available at ++/livesys/merge_union, and the new feature is that the whiteouts are ++visible! ++Note that in 'shwh' mode the aufs mount must be 'ro', which will disable ++writing to all branches. Also the default mode for all branches is 'ro'. ++It is now possible to save the combined contents of the two overlay ++branches to a new squashfs, e.g.: ++# mksquashfs /livesys/merge_union /path/to/newmods.squash ++ ++This new squashfs archive can be stored on the boot device and the ++initramfs will use it to replace the old one at the next boot. ++ ++ ++Being Another Aufs's Readonly Branch (robr) ++---------------------------------------------------------------------- ++Aufs1 allows aufs to be another aufs's readonly branch. ++This feature was developed by a user's request. But it may not be used ++currecnly. ++ ++ ++Copy-up on Open (coo=) ++---------------------------------------------------------------------- ++By default the internal copy-up is executed when it is really necessary. ++It is not done when a file is opened for writing, but when write(2) is ++done. Users who have many (over 100) branches want to know and analyse ++when and what file is copied-up. To insert a new upper branch which ++contains such files only may improve the performance of aufs. ++ ++Aufs1 implemented "coo=none | leaf | all" option. ++ ++ ++Refresh the Opened File (refrof) ++---------------------------------------------------------------------- ++This option is implemented in aufs1 but incomplete. ++ ++When user reads from a file, he expects to get its latest filedata ++generally. If the file is removed and a new same named file is created, ++the content he gets is unchanged, ie. the unlinked filedata. ++ ++Let's try case study again. ++- aufs has two branches. ++ /au = /rw + /ro ++- "fileA" exists under /ro, but /rw. ++- user opened "/au/fileA". ++- he or someone else inserts a branch (/new) between /rw and /ro. ++ /au = /rw + /new + /ro ++- the new branch has "fileA". ++- user reads from the opened "fileA" ++- which filedata should aufs return, from /ro or /new? ++ ++Some people says it has to be "from /ro" and it is a semantics of Unix. ++The others say it should be "from /new" because the file is not removed ++and it is equivalent to the case of someone else modifies the file. ++ ++Here again I don't have a best and final answer. I got an idea to ++implement 'refrof' and 'norefrof' option. When 'refrof' (REFResh the ++Opened File) is specified (by default), aufs returns the filedata from ++/new. ++Otherwise from /new. +diff -urN ./fs/aufs/Kconfig ./fs/aufs/Kconfig +--- ./fs/aufs/Kconfig 1970-01-01 01:00:00.000000000 +0100 ++++ ./fs/aufs/Kconfig 2009-04-06 10:26:46.000000000 +0200 +@@ -0,0 +1,108 @@ ++config AUFS_FS ++ tristate "Aufs (Advanced multi layered unification filesystem) support" ++ depends on EXPERIMENTAL ++ 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_HINOTIFY ++ bool "Use inotify to detect actions on a branch" ++ depends on INOTIFY ++ 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=inotify' mount option. ++ It will have a negative impact to the performance. ++ See detail in aufs.5. ++ ++config AUFS_EXPORT ++ bool "NFS-exportable aufs" ++ depends on (AUFS_FS = y && EXPORTFS = y) || (AUFS_FS = m && EXPORTFS) ++ help ++ If you want to export your mounted aufs via NFS, then enable this ++ option. There are several requirements for this configuration. ++ See detail in aufs.5. ++ ++config AUFS_BR_RAMFS ++ bool "Ramfs (initramfs/rootfs) as an aufs branch" ++ help ++ If you want to use ramfs as an aufs branch fs, then enable this ++ option. Generally tmpfs is recommended. ++ Aufs prohibited them to be a branch fs by default, because ++ initramfs becomes unusable after switch_root or something ++ generally. If you sets initramfs as an aufs branch and boot your ++ system by switch_root, you will meet a problem easily since the ++ files in initramfs may be inaccessible. ++ Unless you are going to use ramfs as an aufs branch fs without ++ switch_root or something, leave it N. ++ ++config AUFS_DEBUG ++ bool "Debug aufs" ++ help ++ Enable this to compile aufs internal debug code. ++ It will have a negative impact to the performance. ++ ++config AUFS_MAGIC_SYSRQ ++ bool ++ depends on AUFS_DEBUG && MAGIC_SYSRQ ++ default y ++ help ++ Automatic configuration for internal use. ++ When aufs supports Magic SysRq, enabled automatically. ++ ++config AUFS_BDEV_LOOP ++ bool ++ depends on BLK_DEV_LOOP ++ default y ++ help ++ Automatic configuration for internal use. ++ Convert =[ym] into =y. ++ ++config AUFS_INO_T_64 ++ bool ++ 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 */ ++endif +diff -urN ./fs/aufs/Makefile ./fs/aufs/Makefile +--- ./fs/aufs/Makefile 1970-01-01 01:00:00.000000000 +0100 ++++ ./fs/aufs/Makefile 2009-04-06 10:26:46.000000000 +0200 +@@ -0,0 +1,22 @@ ++ ++include ${src}/magic.mk ++-include ${src}/priv_def.mk ++ ++obj-$(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 plink.o wbr_policy.o \ ++ dinfo.o dentry.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 \ ++ ioctl.o ++ ++# all are boolean ++aufs-$(CONFIG_SYSFS) += sysfs.o ++aufs-$(CONFIG_DEBUG_FS) += dbgaufs.o ++aufs-$(CONFIG_AUFS_BDEV_LOOP) += loop.o ++aufs-$(CONFIG_AUFS_HINOTIFY) += hinotify.o ++aufs-$(CONFIG_AUFS_EXPORT) += export.o ++aufs-$(CONFIG_AUFS_DEBUG) += debug.o ++aufs-$(CONFIG_AUFS_MAGIC_SYSRQ) += sysrq.o +diff -urN ./fs/aufs/aufs.h ./fs/aufs/aufs.h +--- ./fs/aufs/aufs.h 1970-01-01 01:00:00.000000000 +0100 ++++ ./fs/aufs/aufs.h 2009-04-06 10:26:46.000000000 +0200 +@@ -0,0 +1,44 @@ ++/* ++ * Copyright (C) 2005-2009 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. ++ */ ++ ++/* ++ * all header files ++ */ ++ ++#ifndef __AUFS_H__ ++#define __AUFS_H__ ++ ++#ifdef __KERNEL__ ++ ++#include <linux/bug.h> ++ ++#include "debug.h" ++ ++#include "branch.h" ++#include "cpup.h" ++#include "dcsub.h" ++#include "dbgaufs.h" ++#include "dentry.h" ++#include "dir.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 ./fs/aufs/branch.c ./fs/aufs/branch.c +--- ./fs/aufs/branch.c 1970-01-01 01:00:00.000000000 +0100 ++++ ./fs/aufs/branch.c 2009-04-06 10:26:46.000000000 +0200 +@@ -0,0 +1,946 @@ ++/* ++ * Copyright (C) 2005-2009 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. ++ */ ++ ++/* ++ * branch management ++ */ ++ ++#include "aufs.h" ++ ++/* ++ * free a single branch ++ */ ++static void au_br_do_free(struct au_branch *br) ++{ ++ int i; ++ struct au_wbr *wbr; ++ ++ if (br->br_xino.xi_file) ++ fput(br->br_xino.xi_file); ++ mutex_destroy(&br->br_xino.xi_nondir_mtx); ++ ++ AuDebugOn(atomic_read(&br->br_count)); ++ ++ 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)); ++ au_rwsem_destroy(&wbr->wbr_wh_rwsem); ++ } ++ ++ /* some filesystems acquire extra lock */ ++ lockdep_off(); ++ mntput(br->br_mnt); ++ lockdep_on(); ++ ++ kfree(wbr); ++ kfree(br); ++} ++ ++/* ++ * frees all branches ++ */ ++void au_br_free(struct au_sbinfo *sbinfo) ++{ ++ aufs_bindex_t bmax; ++ struct au_branch **br; ++ ++ bmax = sbinfo->si_bend + 1; ++ br = sbinfo->si_branch; ++ while (bmax--) ++ au_br_do_free(*br++); ++} ++ ++/* ++ * find the index of a branch which is specified by @br_id. ++ */ ++int au_br_index(struct super_block *sb, aufs_bindex_t br_id) ++{ ++ aufs_bindex_t bindex, bend; ++ ++ bend = au_sbend(sb); ++ for (bindex = 0; bindex <= bend; bindex++) ++ if (au_sbr_id(sb, bindex) == br_id) ++ return bindex; ++ return -1; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++/* ++ * add a branch ++ */ ++ ++static int test_overlap(struct super_block *sb, struct dentry *h_d1, ++ struct dentry *h_d2) ++{ ++ if (unlikely(h_d1 == h_d2)) ++ return 1; ++ return !!au_test_subdir(h_d1, h_d2) ++ || !!au_test_subdir(h_d2, h_d1) ++ || au_test_loopback_overlap(sb, h_d1, h_d2) ++ || au_test_loopback_overlap(sb, h_d2, h_d1); ++} ++ ++/* ++ * 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; ++ ++ root = sb->s_root; ++ add_branch = kmalloc(sizeof(*add_branch), GFP_NOFS); ++ if (unlikely(!add_branch)) ++ goto out; ++ ++ add_branch->br_wbr = NULL; ++ if (au_br_writable(perm)) { ++ /* may be freed separately at changing the branch permission */ ++ add_branch->br_wbr = kmalloc(sizeof(*add_branch->br_wbr), ++ GFP_NOFS); ++ if (unlikely(!add_branch->br_wbr)) ++ goto out_br; ++ } ++ ++ if (unlikely(au_sbr_realloc(au_sbi(sb), new_nbranch) ++ || au_di_realloc(au_di(root), new_nbranch) ++ || au_ii_realloc(au_ii(root->d_inode), new_nbranch))) ++ goto out_wbr; ++ return add_branch; /* success */ ++ ++ out_wbr: ++ kfree(add_branch->br_wbr); ++ out_br: ++ kfree(add_branch); ++ out: ++ return ERR_PTR(-ENOMEM); ++} ++ ++/* ++ * test if the branch permission is legal or not. ++ */ ++static int test_br(struct inode *inode, int brperm, char *path) ++{ ++ int err; ++ ++ err = 0; ++ if (unlikely(au_br_writable(brperm) && IS_RDONLY(inode))) { ++ AuErr("write permission for readonly mount or inode, %s\n", ++ path); ++ err = -EINVAL; ++ } ++ ++ 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 bend, bindex; ++ struct dentry *root; ++ struct inode *inode, *h_inode; ++ ++ root = sb->s_root; ++ bend = au_sbend(sb); ++ if (unlikely(bend >= 0 ++ && au_find_dbindex(root, add->path.dentry) >= 0)) { ++ err = 1; ++ if (!remount) { ++ err = -EINVAL; ++ AuErr("%s duplicated\n", add->pathname); ++ } ++ goto out; ++ } ++ ++ err = -ENOSPC; /* -E2BIG; */ ++ if (unlikely(AUFS_BRANCH_MAX <= add->bindex ++ || AUFS_BRANCH_MAX - 1 <= bend)) { ++ AuErr("number of branches exceeded %s\n", add->pathname); ++ goto out; ++ } ++ ++ err = -EDOM; ++ if (unlikely(add->bindex < 0 || bend + 1 < add->bindex)) { ++ AuErr("bad index %d\n", add->bindex); ++ goto out; ++ } ++ ++ inode = add->path.dentry->d_inode; ++ err = -ENOENT; ++ if (unlikely(!inode->i_nlink)) { ++ AuErr("no existence %s\n", add->pathname); ++ goto out; ++ } ++ ++ err = -EINVAL; ++ if (unlikely(inode->i_sb == sb)) { ++ AuErr("%s must be outside\n", add->pathname); ++ goto out; ++ } ++ ++ if (unlikely(au_test_fs_unsuppoted(inode->i_sb))) { ++ AuErr("unsupported filesystem, %s (%s)\n", ++ add->pathname, au_sbtype(inode->i_sb)); ++ goto out; ++ } ++ ++ err = test_br(add->path.dentry->d_inode, add->perm, add->pathname); ++ if (unlikely(err)) ++ goto out; ++ ++ if (bend < 0) ++ return 0; /* success */ ++ ++ err = -EINVAL; ++ for (bindex = 0; bindex <= bend; bindex++) ++ if (unlikely(test_overlap(sb, add->path.dentry, ++ au_h_dptr(root, bindex)))) { ++ AuErr("%s is overlapped\n", add->pathname); ++ goto out; ++ } ++ ++ err = 0; ++ if (au_opt_test(au_mntflags(sb), WARN_PERM)) { ++ h_inode = au_h_dptr(root, 0)->d_inode; ++ if ((h_inode->i_mode & S_IALLUGO) != (inode->i_mode & S_IALLUGO) ++ || h_inode->i_uid != inode->i_uid ++ || h_inode->i_gid != inode->i_gid) ++ AuWarn("uid/gid/perm %s %u/%u/0%o, %u/%u/0%o\n", ++ add->pathname, ++ inode->i_uid, inode->i_gid, ++ (inode->i_mode & S_IALLUGO), ++ h_inode->i_uid, h_inode->i_gid, ++ (h_inode->i_mode & S_IALLUGO)); ++ } ++ ++ out: ++ return err; ++} ++ ++/* ++ * initialize or clean the whiteouts for an adding branch ++ */ ++static int au_br_init_wh(struct super_block *sb, struct au_branch *br, ++ int new_perm, struct dentry *h_root) ++{ ++ int err, old_perm; ++ aufs_bindex_t bindex; ++ struct mutex *h_mtx; ++ struct au_wbr *wbr; ++ struct au_hinode *hdir; ++ ++ wbr = br->br_wbr; ++ old_perm = br->br_perm; ++ br->br_perm = new_perm; ++ hdir = NULL; ++ h_mtx = NULL; ++ bindex = au_br_index(sb, br->br_id); ++ if (0 <= bindex) { ++ hdir = au_hi(sb->s_root->d_inode, bindex); ++ au_hin_imtx_lock_nested(hdir, AuLsc_I_PARENT); ++ } else { ++ h_mtx = &h_root->d_inode->i_mutex; ++ mutex_lock_nested(h_mtx, AuLsc_I_PARENT); ++ } ++ if (!wbr) ++ err = au_wh_init(h_root, br, sb); ++ else { ++ wbr_wh_write_lock(wbr); ++ err = au_wh_init(h_root, br, sb); ++ wbr_wh_write_unlock(wbr); ++ } ++ if (hdir) ++ au_hin_imtx_unlock(hdir); ++ else ++ mutex_unlock(h_mtx); ++ br->br_perm = old_perm; ++ ++ if (!err && wbr && !au_br_writable(new_perm)) { ++ kfree(wbr); ++ br->br_wbr = NULL; ++ } ++ ++ return err; ++} ++ ++static int au_wbr_init(struct au_branch *br, struct super_block *sb, ++ int perm, struct path *path) ++{ ++ int err; ++ struct au_wbr *wbr; ++ ++ wbr = br->br_wbr; ++ init_rwsem(&wbr->wbr_wh_rwsem); ++ memset(wbr->wbr_wh, 0, sizeof(wbr->wbr_wh)); ++ atomic_set(&wbr->wbr_wh_running, 0); ++ wbr->wbr_bytes = 0; ++ ++ err = au_br_init_wh(sb, br, perm, path->dentry); ++ ++ return err; ++} ++ ++/* intialize a new branch */ ++static int au_br_init(struct au_branch *br, struct super_block *sb, ++ struct au_opt_add *add) ++{ ++ int err; ++ ++ err = 0; ++ memset(&br->br_xino, 0, sizeof(br->br_xino)); ++ mutex_init(&br->br_xino.xi_nondir_mtx); ++ br->br_perm = add->perm; ++ br->br_mnt = add->path.mnt; /* set first, mntget() later */ ++ atomic_set(&br->br_count, 0); ++ br->br_xino_upper = AUFS_XINO_TRUNC_INIT; ++ atomic_set(&br->br_xino_running, 0); ++ br->br_id = au_new_br_id(sb); ++ ++ if (au_br_writable(add->perm)) { ++ err = au_wbr_init(br, sb, add->perm, &add->path); ++ if (unlikely(err)) ++ goto out; ++ } ++ ++ if (au_opt_test(au_mntflags(sb), XINO)) { ++ err = au_xino_br(sb, br, add->path.dentry->d_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; ++ } ++ } ++ ++ sysaufs_br_init(br); ++ mntget(add->path.mnt); ++ ++ 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 bend, ++ aufs_bindex_t amount) ++{ ++ struct au_branch **brp; ++ ++ brp = sbinfo->si_branch + bindex; ++ memmove(brp + 1, brp, sizeof(*brp) * amount); ++ *brp = br; ++ sbinfo->si_bend++; ++ if (unlikely(bend < 0)) ++ sbinfo->si_bend = 0; ++} ++ ++static void au_br_do_add_hdp(struct au_dinfo *dinfo, aufs_bindex_t bindex, ++ aufs_bindex_t bend, aufs_bindex_t amount) ++{ ++ struct au_hdentry *hdp; ++ ++ hdp = dinfo->di_hdentry + bindex; ++ memmove(hdp + 1, hdp, sizeof(*hdp) * amount); ++ au_h_dentry_init(hdp); ++ dinfo->di_bend++; ++ if (unlikely(bend < 0)) ++ dinfo->di_bstart = 0; ++} ++ ++static void au_br_do_add_hip(struct au_iinfo *iinfo, aufs_bindex_t bindex, ++ aufs_bindex_t bend, aufs_bindex_t amount) ++{ ++ struct au_hinode *hip; ++ ++ hip = iinfo->ii_hinode + bindex; ++ memmove(hip + 1, hip, sizeof(*hip) * amount); ++ hip->hi_inode = NULL; ++ au_hin_init(hip, NULL); ++ iinfo->ii_bend++; ++ if (unlikely(bend < 0)) ++ iinfo->ii_bstart = 0; ++} ++ ++static void au_br_do_add(struct super_block *sb, struct dentry *h_dentry, ++ struct au_branch *br, aufs_bindex_t bindex) ++{ ++ struct dentry *root; ++ struct inode *root_inode; ++ aufs_bindex_t bend, amount; ++ ++ root = sb->s_root; ++ root_inode = root->d_inode; ++ au_plink_block_maintain(sb); ++ bend = au_sbend(sb); ++ amount = bend + 1 - bindex; ++ au_br_do_add_brp(au_sbi(sb), bindex, br, bend, amount); ++ au_br_do_add_hdp(au_di(root), bindex, bend, amount); ++ au_br_do_add_hip(au_ii(root_inode), bindex, bend, amount); ++ au_set_h_dptr(root, bindex, dget(h_dentry)); ++ au_set_h_iptr(root_inode, bindex, au_igrab(h_dentry->d_inode), ++ /*flags*/0); ++} ++ ++int au_br_add(struct super_block *sb, struct au_opt_add *add, int remount) ++{ ++ int err; ++ unsigned long long maxb; ++ aufs_bindex_t bend, add_bindex; ++ struct dentry *root, *h_dentry; ++ struct inode *root_inode; ++ struct au_branch *add_branch; ++ ++ root = sb->s_root; ++ root_inode = root->d_inode; ++ IMustLock(root_inode); ++ err = test_add(sb, add, remount); ++ if (unlikely(err < 0)) ++ goto out; ++ if (err) { ++ err = 0; ++ goto out; /* success */ ++ } ++ ++ bend = au_sbend(sb); ++ add_branch = au_br_alloc(sb, bend + 2, add->perm); ++ err = PTR_ERR(add_branch); ++ if (IS_ERR(add_branch)) ++ goto out; ++ ++ err = au_br_init(add_branch, sb, add); ++ if (unlikely(err)) { ++ au_br_do_free(add_branch); ++ goto out; ++ } ++ ++ add_bindex = add->bindex; ++ h_dentry = add->path.dentry; ++ if (!remount) ++ au_br_do_add(sb, h_dentry, add_branch, add_bindex); ++ else { ++ sysaufs_brs_del(sb, add_bindex); ++ au_br_do_add(sb, h_dentry, add_branch, add_bindex); ++ sysaufs_brs_add(sb, add_bindex); ++ } ++ ++ if (!add_bindex) ++ au_cpup_attr_all(root_inode, /*force*/1); ++ else ++ au_add_nlink(root_inode, h_dentry->d_inode); ++ maxb = h_dentry->d_sb->s_maxbytes; ++ if (sb->s_maxbytes < maxb) ++ sb->s_maxbytes = maxb; ++ ++ /* ++ * this test/set prevents aufs from handling unnecesary inotify events ++ * of xino files, in a 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_dentry->d_parent == h_dentry) ++ au_xino_brid_set(sb, add_branch->br_id); ++ ++ out: ++ return err; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++/* ++ * delete a branch ++ */ ++ ++/* to show the line number, do not make it inlined function */ ++#define AuVerbose(do_info, fmt, args...) do { \ ++ if (do_info) \ ++ AuInfo(fmt, ##args); \ ++} while (0) ++ ++/* ++ * test if the branch is deletable or not. ++ */ ++static int test_dentry_busy(struct dentry *root, aufs_bindex_t bindex, ++ unsigned int sigen) ++{ ++ int err, i, j, ndentry; ++ aufs_bindex_t bstart, bend; ++ unsigned char verbose; ++ struct au_dcsub_pages dpages; ++ struct au_dpage *dpage; ++ struct dentry *d; ++ struct inode *inode; ++ ++ 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; ++ ++ verbose = !!au_opt_test(au_mntflags(root->d_sb), VERBOSE); ++ 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(!atomic_read(&d->d_count)); ++ inode = d->d_inode; ++ if (au_digen(d) == sigen && au_iigen(inode) == sigen) ++ di_read_lock_child(d, AuLock_IR); ++ else { ++ di_write_lock_child(d); ++ err = au_reval_dpath(d, sigen); ++ if (!err) ++ di_downgrade_lock(d, AuLock_IR); ++ else { ++ di_write_unlock(d); ++ break; ++ } ++ } ++ ++ bstart = au_dbstart(d); ++ bend = au_dbend(d); ++ if (bstart <= bindex ++ && bindex <= bend ++ && au_h_dptr(d, bindex) ++ && (!S_ISDIR(inode->i_mode) || bstart == bend)) { ++ err = -EBUSY; ++ AuVerbose(verbose, "busy %.*s\n", AuDLNPair(d)); ++ } ++ di_read_unlock(d, AuLock_IR); ++ } ++ } ++ ++ out_dpages: ++ au_dpages_free(&dpages); ++ out: ++ return err; ++} ++ ++static int test_inode_busy(struct super_block *sb, aufs_bindex_t bindex, ++ unsigned int sigen) ++{ ++ int err; ++ struct inode *i; ++ aufs_bindex_t bstart, bend; ++ unsigned char verbose; ++ ++ err = 0; ++ verbose = !!au_opt_test(au_mntflags(sb), VERBOSE); ++ list_for_each_entry(i, &sb->s_inodes, i_sb_list) { ++ AuDebugOn(!atomic_read(&i->i_count)); ++ if (!list_empty(&i->i_dentry)) ++ continue; ++ ++ if (au_iigen(i) == sigen) ++ ii_read_lock_child(i); ++ else { ++ ii_write_lock_child(i); ++ err = au_refresh_hinode_self(i, /*do_attr*/1); ++ if (!err) ++ ii_downgrade_lock(i); ++ else { ++ ii_write_unlock(i); ++ break; ++ } ++ } ++ ++ bstart = au_ibstart(i); ++ bend = au_ibend(i); ++ if (bstart <= bindex ++ && bindex <= bend ++ && au_h_iptr(i, bindex) ++ && (!S_ISDIR(i->i_mode) || bstart == bend)) { ++ err = -EBUSY; ++ AuVerbose(verbose, "busy i%lu\n", i->i_ino); ++ ii_read_unlock(i); ++ break; ++ } ++ ii_read_unlock(i); ++ } ++ ++ return err; ++} ++ ++static int test_children_busy(struct dentry *root, aufs_bindex_t bindex) ++{ ++ int err; ++ unsigned int sigen; ++ ++ sigen = au_sigen(root->d_sb); ++ DiMustNoWaiters(root); ++ IiMustNoWaiters(root->d_inode); ++ di_write_unlock(root); ++ err = test_dentry_busy(root, bindex, sigen); ++ if (!err) ++ err = test_inode_busy(root->d_sb, bindex, sigen); ++ di_write_lock_child(root); /* aufs_write_lock() calls ..._child() */ ++ ++ return err; ++} ++ ++static void au_br_do_del_brp(struct au_sbinfo *sbinfo, ++ const aufs_bindex_t bindex, ++ const aufs_bindex_t bend) ++{ ++ struct au_branch **brp, **p; ++ ++ brp = sbinfo->si_branch + bindex; ++ if (bindex < bend) ++ memmove(brp, brp + 1, sizeof(*brp) * (bend - bindex)); ++ sbinfo->si_branch[0 + bend] = NULL; ++ sbinfo->si_bend--; ++ ++ p = krealloc(sbinfo->si_branch, sizeof(*p) * bend, GFP_NOFS); ++ if (p) ++ sbinfo->si_branch = p; ++} ++ ++static void au_br_do_del_hdp(struct au_dinfo *dinfo, const aufs_bindex_t bindex, ++ const aufs_bindex_t bend) ++{ ++ struct au_hdentry *hdp, *p; ++ ++ hdp = dinfo->di_hdentry + bindex; ++ if (bindex < bend) ++ memmove(hdp, hdp + 1, sizeof(*hdp) * (bend - bindex)); ++ dinfo->di_hdentry[0 + bend].hd_dentry = NULL; ++ dinfo->di_bend--; ++ ++ p = krealloc(dinfo->di_hdentry, sizeof(*p) * bend, GFP_NOFS); ++ if (p) ++ dinfo->di_hdentry = p; ++} ++ ++static void au_br_do_del_hip(struct au_iinfo *iinfo, const aufs_bindex_t bindex, ++ const aufs_bindex_t bend) ++{ ++ struct au_hinode *hip, *p; ++ ++ hip = iinfo->ii_hinode + bindex; ++ if (bindex < bend) ++ memmove(hip, hip + 1, sizeof(*hip) * (bend - bindex)); ++ iinfo->ii_hinode[0 + bend].hi_inode = NULL; ++ au_hin_init(iinfo->ii_hinode + bend, NULL); ++ iinfo->ii_bend--; ++ ++ p = krealloc(iinfo->ii_hinode, sizeof(*p) * bend, GFP_NOFS); ++ if (p) ++ iinfo->ii_hinode = p; ++} ++ ++static void au_br_do_del(struct super_block *sb, aufs_bindex_t bindex, ++ struct au_branch *br) ++{ ++ aufs_bindex_t bend; ++ struct au_sbinfo *sbinfo; ++ struct dentry *root; ++ struct inode *inode; ++ ++ root = sb->s_root; ++ inode = root->d_inode; ++ au_plink_block_maintain(sb); ++ sbinfo = au_sbi(sb); ++ bend = sbinfo->si_bend; ++ ++ dput(au_h_dptr(root, bindex)); ++ au_hiput(au_hi(inode, bindex)); ++ au_br_do_free(br); ++ ++ au_br_do_del_brp(sbinfo, bindex, bend); ++ au_br_do_del_hdp(au_di(root), bindex, bend); ++ au_br_do_del_hip(au_ii(inode), bindex, bend); ++} ++ ++int au_br_del(struct super_block *sb, struct au_opt_del *del, int remount) ++{ ++ int err, rerr, i; ++ unsigned int mnt_flags; ++ aufs_bindex_t bindex, bend, br_id; ++ unsigned char do_wh, verbose; ++ struct au_branch *br; ++ struct au_wbr *wbr; ++ ++ err = 0; ++ bindex = au_find_dbindex(sb->s_root, del->h_path.dentry); ++ if (bindex < 0) { ++ if (remount) ++ goto out; /* success */ ++ err = -ENOENT; ++ AuErr("%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); ++ bend = au_sbend(sb); ++ if (unlikely(!bend)) { ++ AuVerbose(verbose, "no more branches left\n"); ++ goto out; ++ } ++ br = au_sbr(sb, bindex); ++ i = atomic_read(&br->br_count); ++ if (unlikely(i)) { ++ AuVerbose(verbose, "%d file(s) opened\n", i); ++ goto out; ++ } ++ ++ wbr = br->br_wbr; ++ do_wh = wbr && (wbr->wbr_whbase || wbr->wbr_plink || wbr->wbr_orph); ++ if (do_wh) { ++ for (i = 0; i < AuBrWh_Last; i++) { ++ dput(wbr->wbr_wh[i]); ++ wbr->wbr_wh[i] = NULL; ++ } ++ } ++ ++ err = test_children_busy(sb->s_root, bindex); ++ if (unlikely(err)) { ++ if (do_wh) ++ goto out_wh; ++ goto out; ++ } ++ ++ err = 0; ++ br_id = br->br_id; ++ 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(sb->s_root->d_inode, /*force*/1); ++ else ++ au_sub_nlink(sb->s_root->d_inode, del->h_path.dentry->d_inode); ++ if (au_opt_test(mnt_flags, PLINK)) ++ au_plink_half_refresh(sb, br_id); ++ ++ if (sb->s_maxbytes == del->h_path.dentry->d_sb->s_maxbytes) { ++ bend--; ++ sb->s_maxbytes = 0; ++ for (bindex = 0; bindex <= bend; bindex++) { ++ unsigned long long maxb; ++ ++ maxb = au_sbr_sb(sb, bindex)->s_maxbytes; ++ if (sb->s_maxbytes < maxb) ++ sb->s_maxbytes = maxb; ++ } ++ } ++ ++ if (au_xino_brid(sb) == br->br_id) ++ au_xino_brid_set(sb, -1); ++ goto out; /* success */ ++ ++ out_wh: ++ /* revert */ ++ rerr = au_br_init_wh(sb, br, br->br_perm, del->h_path.dentry); ++ if (rerr) ++ AuWarn("failed re-creating base whiteout, %s. (%d)\n", ++ del->pathname, rerr); ++ out: ++ return err; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++/* ++ * change a branch permission ++ */ ++ ++static int do_need_sigen_inc(int a, int b) ++{ ++ return au_br_whable(a) && !au_br_whable(b); ++} ++ ++static int need_sigen_inc(int old, int new) ++{ ++ return do_need_sigen_inc(old, new) ++ || do_need_sigen_inc(new, old); ++} ++ ++static int au_br_mod_files_ro(struct super_block *sb, aufs_bindex_t bindex) ++{ ++ int err; ++ unsigned long n, ul, bytes, files; ++ aufs_bindex_t bstart; ++ struct file *file, *hf, **a; ++ const int step_bytes = 1024, /* memory allocation unit */ ++ step_files = step_bytes / sizeof(*a); ++ ++ err = -ENOMEM; ++ n = 0; ++ bytes = step_bytes; ++ files = step_files; ++ a = kmalloc(bytes, GFP_NOFS); ++ if (unlikely(!a)) ++ goto out; ++ ++ /* no need file_list_lock() since sbinfo is locked? defered? */ ++ list_for_each_entry(file, &sb->s_files, f_u.fu_list) { ++ if (special_file(file->f_dentry->d_inode->i_mode)) ++ continue; ++ ++ AuDbg("%.*s\n", AuDLNPair(file->f_dentry)); ++ fi_read_lock(file); ++ if (unlikely(au_test_mmapped(file))) { ++ err = -EBUSY; ++ FiMustNoWaiters(file); ++ fi_read_unlock(file); ++ goto out_free; ++ } ++ ++ bstart = au_fbstart(file); ++ if (!S_ISREG(file->f_dentry->d_inode->i_mode) ++ || !(file->f_mode & FMODE_WRITE) ++ || bstart != bindex) { ++ FiMustNoWaiters(file); ++ fi_read_unlock(file); ++ continue; ++ } ++ ++ hf = au_h_fptr(file, bstart); ++ FiMustNoWaiters(file); ++ fi_read_unlock(file); ++ ++ if (n < files) ++ a[n++] = hf; ++ else { ++ void *p; ++ ++ err = -ENOMEM; ++ bytes += step_bytes; ++ files += step_files; ++ p = krealloc(a, bytes, GFP_NOFS); ++ if (p) { ++ a = p; ++ a[n++] = hf; ++ } else ++ goto out_free; ++ } ++ } ++ ++ err = 0; ++ for (ul = 0; ul < n; ul++) { ++ /* todo: already flushed? */ ++ /* cf. fs/super.c:mark_files_ro() */ ++ hf = a[ul]; ++ hf->f_mode &= ~FMODE_WRITE; ++ if (!file_check_writeable(hf)) { ++ file_release_write(hf); ++ mnt_drop_write(hf->f_vfsmnt); ++ } ++ } ++ ++ out_free: ++ kfree(a); ++ out: ++ return err; ++} ++ ++int au_br_mod(struct super_block *sb, struct au_opt_mod *mod, int remount, ++ int *do_update) ++{ ++ int err, rerr; ++ aufs_bindex_t bindex; ++ struct dentry *root; ++ struct au_branch *br; ++ ++ root = sb->s_root; ++ au_plink_block_maintain(sb); ++ bindex = au_find_dbindex(root, mod->h_root); ++ if (bindex < 0) { ++ if (remount) ++ return 0; /* success */ ++ err = -ENOENT; ++ AuErr("%s no such branch\n", mod->path); ++ goto out; ++ } ++ AuDbg("bindex b%d\n", bindex); ++ ++ err = test_br(mod->h_root->d_inode, mod->perm, mod->path); ++ if (unlikely(err)) ++ goto out; ++ ++ br = au_sbr(sb, bindex); ++ if (br->br_perm == mod->perm) ++ return 0; /* success */ ++ ++ if (au_br_writable(br->br_perm)) { ++ /* remove whiteout base */ ++ err = au_br_init_wh(sb, br, mod->perm, mod->h_root); ++ if (unlikely(err)) ++ goto out; ++ ++ if (!au_br_writable(mod->perm)) { ++ /* rw --> ro, file might be mmapped */ ++ DiMustNoWaiters(root); ++ IiMustNoWaiters(root->d_inode); ++ di_write_unlock(root); ++ err = au_br_mod_files_ro(sb, bindex); ++ /* aufs_write_lock() calls ..._child() */ ++ di_write_lock_child(root); ++ ++ if (unlikely(err)) { ++ rerr = -ENOMEM; ++ br->br_wbr = kmalloc(sizeof(*br->br_wbr), ++ GFP_NOFS); ++ if (br->br_wbr) ++ rerr = au_br_init_wh ++ (sb, br, br->br_perm, ++ mod->h_root); ++ 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 = kmalloc(sizeof(*br->br_wbr), GFP_NOFS); ++ if (br->br_wbr) { ++ struct path path = { ++ .mnt = br->br_mnt, ++ .dentry = mod->h_root ++ }; ++ ++ err = au_wbr_init(br, sb, mod->perm, &path); ++ if (unlikely(err)) { ++ kfree(br->br_wbr); ++ br->br_wbr = NULL; ++ } ++ } ++ } ++ ++ if (!err) { ++ *do_update |= need_sigen_inc(br->br_perm, mod->perm); ++ br->br_perm = mod->perm; ++ } ++ ++ out: ++ return err; ++} +diff -urN ./fs/aufs/branch.h ./fs/aufs/branch.h +--- ./fs/aufs/branch.h 1970-01-01 01:00:00.000000000 +0100 ++++ ./fs/aufs/branch.h 2009-04-06 10:26:46.000000000 +0200 +@@ -0,0 +1,207 @@ ++/* ++ * Copyright (C) 2005-2009 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. ++ */ ++ ++/* ++ * branch filesystems and xino for them ++ */ ++ ++#ifndef __AUFS_BRANCH_H__ ++#define __AUFS_BRANCH_H__ ++ ++#ifdef __KERNEL__ ++ ++#include <linux/fs.h> ++#include <linux/mount.h> ++#include <linux/sysfs.h> ++#include <linux/aufs_type.h> ++#include "rwsem.h" ++#include "super.h" ++ ++/* ---------------------------------------------------------------------- */ ++ ++/* a xino file */ ++struct au_xino_file { ++ struct file *xi_file; ++ struct mutex xi_nondir_mtx; ++ ++ /* todo: make xino files an array to support huge inode number */ ++ ++#ifdef CONFIG_DEBUG_FS ++ struct dentry *xi_dbgaufs; ++#endif ++}; ++ ++/* members for writable branch only */ ++enum {AuBrWh_BASE, AuBrWh_PLINK, AuBrWh_ORPH, AuBrWh_Last}; ++struct au_wbr { ++ struct rw_semaphore wbr_wh_rwsem; ++ struct dentry *wbr_wh[AuBrWh_Last]; ++ atomic_t wbr_wh_running; ++#define wbr_whbase wbr_wh[AuBrWh_BASE] /* whiteout base */ ++#define wbr_plink wbr_wh[AuBrWh_PLINK] /* pseudo-link dir */ ++#define wbr_orph wbr_wh[AuBrWh_ORPH] /* dir for orphans */ ++ ++ /* mfs mode */ ++ unsigned long long wbr_bytes; ++}; ++ ++/* protected by superblock rwsem */ ++struct au_branch { ++ struct au_xino_file br_xino; ++ ++ aufs_bindex_t br_id; ++ ++ int br_perm; ++ struct vfsmount *br_mnt; ++ atomic_t br_count; ++ ++ struct au_wbr *br_wbr; ++ ++ /* xino truncation */ ++ blkcnt_t br_xino_upper; /* watermark in blocks */ ++ atomic_t br_xino_running; ++ ++#ifdef CONFIG_SYSFS ++ /* an entry under sysfs per mount-point */ ++ char br_name[8]; ++ struct attribute br_attr; ++#endif ++}; ++ ++/* ---------------------------------------------------------------------- */ ++ ++/* branch permission and attribute */ ++enum { ++ AuBrPerm_RW, /* writable, linkable wh */ ++ AuBrPerm_RO, /* readonly, no wh */ ++ AuBrPerm_RR, /* natively readonly, no wh */ ++ ++ AuBrPerm_RWNoLinkWH, /* un-linkable whiteouts */ ++ ++ AuBrPerm_ROWH, /* whiteout-able */ ++ AuBrPerm_RRWH, /* whiteout-able */ ++ ++ AuBrPerm_Last ++}; ++ ++static inline int au_br_writable(int brperm) ++{ ++ return brperm == AuBrPerm_RW || brperm == AuBrPerm_RWNoLinkWH; ++} ++ ++static inline int au_br_whable(int brperm) ++{ ++ return brperm == AuBrPerm_RW ++ || brperm == AuBrPerm_ROWH ++ || brperm == AuBrPerm_RRWH; ++} ++ ++static inline int au_br_rdonly(struct au_branch *br) ++{ ++ return ((br->br_mnt->mnt_sb->s_flags & MS_RDONLY) ++ || !au_br_writable(br->br_perm)) ++ ? -EROFS : 0; ++} ++ ++static inline int au_br_hinotifyable(int brperm __maybe_unused) ++{ ++#ifdef CONFIG_AUFS_HINOTIFY ++ return brperm != AuBrPerm_RR && brperm != AuBrPerm_RRWH; ++#else ++ return 0; ++#endif ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++/* 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); ++struct au_opt_mod; ++int au_br_mod(struct super_block *sb, struct au_opt_mod *mod, int remount, ++ int *do_update); ++ ++/* xino.c */ ++static const loff_t au_loff_max = LLONG_MAX; ++ ++int au_xib_trunc(struct super_block *sb); ++ssize_t xino_fread(au_readf_t func, struct file *file, void *buf, size_t size, ++ loff_t *pos); ++ssize_t xino_fwrite(au_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); ++int au_xino_write0(struct super_block *sb, aufs_bindex_t bindex, ino_t h_ino, ++ ino_t ino); ++int au_xino_write(struct super_block *sb, aufs_bindex_t bindex, ino_t h_ino, ++ ino_t ino); ++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); ++ ++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); ++ ++/* ---------------------------------------------------------------------- */ ++ ++/* Superblock to branch */ ++static inline ++aufs_bindex_t au_sbr_id(struct super_block *sb, aufs_bindex_t bindex) ++{ ++ return au_sbr(sb, bindex)->br_id; ++} ++ ++static inline ++struct vfsmount *au_sbr_mnt(struct super_block *sb, aufs_bindex_t bindex) ++{ ++ return au_sbr(sb, bindex)->br_mnt; ++} ++ ++static inline ++struct super_block *au_sbr_sb(struct super_block *sb, aufs_bindex_t bindex) ++{ ++ return au_sbr_mnt(sb, bindex)->mnt_sb; ++} ++ ++static inline void au_sbr_put(struct super_block *sb, aufs_bindex_t bindex) ++{ ++ atomic_dec(&au_sbr(sb, bindex)->br_count); ++} ++ ++static inline int au_sbr_perm(struct super_block *sb, aufs_bindex_t bindex) ++{ ++ return au_sbr(sb, bindex)->br_perm; ++} ++ ++static inline int au_sbr_whable(struct super_block *sb, aufs_bindex_t bindex) ++{ ++ return au_br_whable(au_sbr_perm(sb, bindex)); ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++/* ++ * 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); ++ ++#endif /* __KERNEL__ */ ++#endif /* __AUFS_BRANCH_H__ */ +diff -urN ./fs/aufs/cpup.c ./fs/aufs/cpup.c +--- ./fs/aufs/cpup.c 1970-01-01 01:00:00.000000000 +0100 ++++ ./fs/aufs/cpup.c 2009-04-06 10:26:46.000000000 +0200 +@@ -0,0 +1,1023 @@ ++/* ++ * Copyright (C) 2005-2009 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. ++ */ ++ ++/* ++ * copy-up functions, see wbr_policy.c for copy-down ++ */ ++ ++#include <linux/fs_stack.h> ++#include <linux/uaccess.h> ++#include "aufs.h" ++ ++void au_cpup_attr_flags(struct inode *dst, struct inode *src) ++{ ++ const unsigned int mask = S_DEAD | S_SWAPFILE | S_PRIVATE ++ | S_NOATIME | S_NOCMTIME; ++ ++ dst->i_flags |= src->i_flags & ~mask; ++ if (au_test_fs_notime(dst->i_sb)) ++ dst->i_flags |= S_NOATIME | S_NOCMTIME; ++} ++ ++void au_cpup_attr_timesizes(struct inode *inode) ++{ ++ struct inode *h_inode; ++ ++ h_inode = au_h_iptr(inode, au_ibstart(inode)); ++ fsstack_copy_attr_times(inode, h_inode); ++ vfsub_copy_inode_size(inode, h_inode); ++} ++ ++void au_cpup_attr_nlink(struct inode *inode, int force) ++{ ++ struct inode *h_inode; ++ struct super_block *sb; ++ aufs_bindex_t bindex, bend; ++ ++ sb = inode->i_sb; ++ bindex = au_ibstart(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; ++ ++ inode->i_nlink = 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)) { ++ bend = au_ibend(inode); ++ for (bindex++; bindex <= bend; bindex++) { ++ h_inode = au_h_iptr(inode, bindex); ++ if (h_inode) ++ au_add_nlink(inode, h_inode); ++ } ++ } ++} ++ ++void au_cpup_attr_changeable(struct inode *inode) ++{ ++ struct inode *h_inode; ++ ++ h_inode = au_h_iptr(inode, au_ibstart(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); ++} ++ ++void au_cpup_igen(struct inode *inode, struct inode *h_inode) ++{ ++ struct au_iinfo *iinfo = au_ii(inode); ++ ++ iinfo->ii_higen = h_inode->i_generation; ++ iinfo->ii_hsb1 = h_inode->i_sb; ++} ++ ++void au_cpup_attr_all(struct inode *inode, int force) ++{ ++ struct inode *h_inode; ++ ++ h_inode = au_h_iptr(inode, au_ibstart(inode)); ++ au_cpup_attr_changeable(inode); ++ if (inode->i_nlink > 0) ++ au_cpup_attr_nlink(inode, force); ++ inode->i_rdev = h_inode->i_rdev; ++ inode->i_blkbits = h_inode->i_blkbits; ++ au_cpup_igen(inode, h_inode); ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++/* Note: dt_dentry and dt_h_dentry are not dget/dput-ed */ ++ ++/* keep the timestamps of the parent dir when cpup */ ++void au_dtime_store(struct au_dtime *dt, struct dentry *dentry, ++ struct path *h_path) ++{ ++ struct inode *h_inode; ++ ++ dt->dt_dentry = dentry; ++ dt->dt_h_path = *h_path; ++ h_inode = h_path->dentry->d_inode; ++ dt->dt_atime = h_inode->i_atime; ++ dt->dt_mtime = h_inode->i_mtime; ++ /* smp_mb(); */ ++} ++ ++void au_dtime_revert(struct au_dtime *dt) ++{ ++ struct iattr attr; ++ int err; ++ ++ attr.ia_atime = dt->dt_atime; ++ attr.ia_mtime = dt->dt_mtime; ++ attr.ia_valid = ATTR_FORCE | ATTR_MTIME | ATTR_MTIME_SET ++ | ATTR_ATIME | ATTR_ATIME_SET; ++ ++ err = vfsub_notify_change(&dt->dt_h_path, &attr); ++ if (unlikely(err)) ++ AuWarn("restoring timestamps failed(%d). ignored\n", err); ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++static noinline_for_stack ++int cpup_iattr(struct dentry *dst, aufs_bindex_t bindex, struct dentry *h_src) ++{ ++ int err, sbits; ++ struct iattr ia; ++ struct path h_path; ++ struct inode *h_isrc; ++ ++ h_path.dentry = au_h_dptr(dst, bindex); ++ h_path.mnt = au_sbr_mnt(dst->d_sb, bindex); ++ h_isrc = h_src->d_inode; ++ ia.ia_valid = ATTR_FORCE | ATTR_MODE | ATTR_UID | ATTR_GID ++ | ATTR_ATIME | ATTR_MTIME ++ | ATTR_ATIME_SET | ATTR_MTIME_SET; ++ ia.ia_mode = h_isrc->i_mode; ++ 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; ++ sbits = !!(ia.ia_mode & (S_ISUID | S_ISGID)); ++ au_cpup_attr_flags(h_path.dentry->d_inode, h_isrc); ++ err = vfsub_notify_change(&h_path, &ia); ++ ++ /* 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); ++ } ++ ++ return err; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++static int au_do_copy_file(struct file *dst, struct file *src, loff_t len, ++ char *buf, unsigned long blksize) ++{ ++ int err; ++ size_t sz, rbytes, wbytes; ++ unsigned char all_zero; ++ char *p, *zp; ++ struct mutex *h_mtx; ++ /* reduce stack usage */ ++ struct iattr *ia; ++ ++ zp = page_address(ZERO_PAGE(0)); ++ if (unlikely(!zp)) ++ return -ENOMEM; /* possible? */ ++ ++ err = 0; ++ all_zero = 0; ++ while (len) { ++ AuDbg("len %lld\n", len); ++ sz = blksize; ++ if (len < blksize) ++ sz = len; ++ ++ rbytes = 0; ++ /* todo: signal_pending? */ ++ while (!rbytes || err == -EAGAIN || err == -EINTR) { ++ rbytes = vfsub_read_k(src, buf, sz, &src->f_pos); ++ err = rbytes; ++ } ++ if (unlikely(err < 0)) ++ break; ++ ++ all_zero = 0; ++ if (len >= rbytes && rbytes == blksize) ++ all_zero = !memcmp(buf, zp, rbytes); ++ if (!all_zero) { ++ wbytes = rbytes; ++ p = buf; ++ while (wbytes) { ++ size_t b; ++ ++ b = vfsub_write_k(dst, p, wbytes, &dst->f_pos); ++ err = b; ++ /* todo: signal_pending? */ ++ if (unlikely(err == -EAGAIN || err == -EINTR)) ++ continue; ++ if (unlikely(err < 0)) ++ break; ++ wbytes -= b; ++ p += b; ++ } ++ } else { ++ loff_t res; ++ ++ AuLabel(hole); ++ res = vfsub_llseek(dst, rbytes, SEEK_CUR); ++ err = res; ++ if (unlikely(res < 0)) ++ break; ++ } ++ len -= rbytes; ++ err = 0; ++ } ++ ++ /* the last block may be a hole */ ++ if (!err && all_zero) { ++ AuLabel(last hole); ++ ++ err = 1; ++ if (au_test_nfs(dst->f_dentry->d_sb)) { ++ /* nfs requires this step to make last hole */ ++ /* is this only nfs? */ ++ do { ++ /* todo: signal_pending? */ ++ err = vfsub_write_k(dst, "\0", 1, &dst->f_pos); ++ } while (err == -EAGAIN || err == -EINTR); ++ if (err == 1) ++ dst->f_pos--; ++ } ++ ++ if (err == 1) { ++ ia = (void *)buf; ++ ia->ia_size = dst->f_pos; ++ ia->ia_valid = ATTR_SIZE | ATTR_FILE; ++ ia->ia_file = dst; ++ h_mtx = &dst->f_dentry->d_inode->i_mutex; ++ mutex_lock_nested(h_mtx, AuLsc_I_CHILD2); ++ err = vfsub_notify_change(&dst->f_path, ia); ++ mutex_unlock(h_mtx); ++ } ++ } ++ ++ 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_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); ++ ++ 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; ++} ++ ++/* ++ * to support a sparse file which is opened with O_APPEND, ++ * we need to close the file. ++ */ ++static int au_cp_regular(struct dentry *dentry, aufs_bindex_t bdst, ++ aufs_bindex_t bsrc, loff_t len) ++{ ++ int err, i; ++ enum { SRC, DST }; ++ struct { ++ aufs_bindex_t bindex; ++ unsigned int flags; ++ struct dentry *dentry; ++ struct file *file; ++ void *label; ++ } *f, file[] = { ++ { ++ .bindex = bsrc, ++ .flags = O_RDONLY | O_NOATIME | O_LARGEFILE, ++ .file = NULL, ++ .label = &&out, ++ }, ++ { ++ .bindex = bdst, ++ .flags = O_WRONLY | O_NOATIME | O_LARGEFILE, ++ .file = NULL, ++ .label = &&out_src, ++ } ++ }; ++ struct super_block *sb; ++ ++ /* bsrc branch can be ro/rw. */ ++ sb = dentry->d_sb; ++ f = file; ++ for (i = 0; i < 2; i++, f++) { ++ f->dentry = au_h_dptr(dentry, f->bindex); ++ f->file = au_h_open(dentry, f->bindex, f->flags, /*file*/NULL); ++ err = PTR_ERR(f->file); ++ if (IS_ERR(f->file)) ++ goto *f->label; ++ } ++ ++ /* try stopping to update while we copyup */ ++ IMustLock(file[SRC].dentry->d_inode); ++ err = au_copy_file(file[DST].file, file[SRC].file, len); ++ ++ fput(file[DST].file); ++ au_sbr_put(sb, file[DST].bindex); ++ ++ out_src: ++ fput(file[SRC].file); ++ au_sbr_put(sb, file[SRC].bindex); ++ out: ++ return err; ++} ++ ++static int au_do_cpup_regular(struct dentry *dentry, aufs_bindex_t bdst, ++ aufs_bindex_t bsrc, loff_t len, ++ struct inode *h_dir, struct path *h_path) ++{ ++ int err, rerr; ++ loff_t l; ++ ++ err = 0; ++ l = i_size_read(au_h_iptr(dentry->d_inode, bsrc)); ++ if (len == -1 || l < len) ++ len = l; ++ if (len) ++ err = au_cp_regular(dentry, bdst, bsrc, len); ++ if (!err) ++ goto out; /* success */ ++ ++ rerr = vfsub_unlink(h_dir, h_path, /*force*/0); ++ if (rerr) { ++ AuIOErr("failed unlinking cpup-ed %.*s(%d, %d)\n", ++ AuDLNPair(h_path->dentry), err, rerr); ++ err = -EIO; ++ } ++ ++ out: ++ return err; ++} ++ ++static int au_do_cpup_symlink(struct path *h_path, struct dentry *h_src, ++ struct inode *h_dir) ++{ ++ int err, symlen; ++ mm_segment_t old_fs; ++ char *sym; ++ ++ err = -ENOSYS; ++ if (unlikely(!h_src->d_inode->i_op->readlink)) ++ goto out; ++ ++ err = -ENOMEM; ++ sym = __getname(); ++ if (unlikely(!sym)) ++ goto out; ++ ++ old_fs = get_fs(); ++ set_fs(KERNEL_DS); ++ symlen = h_src->d_inode->i_op->readlink(h_src, (char __user *)sym, ++ PATH_MAX); ++ err = symlen; ++ set_fs(old_fs); ++ ++ if (symlen > 0) { ++ sym[symlen] = 0; ++ err = vfsub_symlink(h_dir, h_path, sym); ++ } ++ __putname(sym); ++ ++ out: ++ return err; ++} ++ ++/* return with the lower dst inode is locked */ ++static noinline_for_stack ++int cpup_entry(struct dentry *dentry, aufs_bindex_t bdst, ++ aufs_bindex_t bsrc, loff_t len, unsigned int flags, ++ struct dentry *dst_parent) ++{ ++ int err; ++ umode_t mode; ++ unsigned int mnt_flags; ++ unsigned char isdir; ++ const unsigned char do_dt = !!au_ftest_cpup(flags, DTIME); ++ struct au_dtime dt; ++ struct path h_path; ++ struct dentry *h_src, *h_dst, *h_parent; ++ struct inode *h_inode, *h_dir; ++ struct super_block *sb; ++ ++ /* bsrc branch can be ro/rw. */ ++ h_src = au_h_dptr(dentry, bsrc); ++ h_inode = h_src->d_inode; ++ AuDebugOn(h_inode != au_h_iptr(dentry->d_inode, bsrc)); ++ ++ /* try stopping to be referenced while we are creating */ ++ h_dst = au_h_dptr(dentry, bdst); ++ h_parent = h_dst->d_parent; /* dir inode is locked */ ++ h_dir = h_parent->d_inode; ++ IMustLock(h_dir); ++ AuDebugOn(h_parent != h_dst->d_parent); ++ ++ sb = dentry->d_sb; ++ h_path.mnt = au_sbr_mnt(sb, bdst); ++ if (do_dt) { ++ h_path.dentry = h_parent; ++ au_dtime_store(&dt, dst_parent, &h_path); ++ } ++ h_path.dentry = h_dst; ++ ++ isdir = 0; ++ mode = h_inode->i_mode; ++ switch (mode & S_IFMT) { ++ case S_IFREG: ++ /* try stopping to update while we are referencing */ ++ IMustLock(h_inode); ++ err = vfsub_create(h_dir, &h_path, mode | S_IWUSR); ++ if (!err) ++ err = au_do_cpup_regular ++ (dentry, bdst, bsrc, len, ++ au_h_iptr(dst_parent->d_inode, bdst), &h_path); ++ break; ++ case S_IFDIR: ++ isdir = 1; ++ err = vfsub_mkdir(h_dir, &h_path, mode); ++ if (!err) { ++ /* ++ * strange behaviour from the users view, ++ * particularry setattr case ++ */ ++ if (au_ibstart(dst_parent->d_inode) == bdst) ++ au_cpup_attr_nlink(dst_parent->d_inode, ++ /*force*/1); ++ au_cpup_attr_nlink(dentry->d_inode, /*force*/1); ++ } ++ 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; ++ } ++ ++ 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 ++ /* todo: unnecessary? */ ++ /* && dentry->d_inode->i_nlink == 1 */ ++ && bdst < bsrc ++ && !au_ftest_cpup(flags, KEEPLINO)) ++ au_xino_write0(sb, bsrc, h_inode->i_ino, /*ino*/0); ++ /* ignore this error */ ++ ++ if (do_dt) ++ au_dtime_revert(&dt); ++ 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. ++ */ ++static int au_cpup_single(struct dentry *dentry, aufs_bindex_t bdst, ++ aufs_bindex_t bsrc, loff_t len, unsigned int flags, ++ struct dentry *dst_parent) ++{ ++ int err, rerr; ++ aufs_bindex_t old_ibstart; ++ unsigned char isdir, plink; ++ struct au_dtime dt; ++ struct path h_path; ++ struct dentry *h_src, *h_dst, *h_parent; ++ struct inode *dst_inode, *h_dir, *inode; ++ struct super_block *sb; ++ ++ AuDebugOn(bsrc <= bdst); ++ ++ sb = dentry->d_sb; ++ h_path.mnt = au_sbr_mnt(sb, bdst); ++ h_dst = au_h_dptr(dentry, bdst); ++ h_parent = h_dst->d_parent; /* dir inode is locked */ ++ h_dir = h_parent->d_inode; ++ IMustLock(h_dir); ++ ++ h_src = au_h_dptr(dentry, bsrc); ++ inode = dentry->d_inode; ++ ++ if (!dst_parent) ++ dst_parent = dget_parent(dentry); ++ else ++ dget(dst_parent); ++ ++ plink = !!au_opt_test(au_mntflags(sb), PLINK); ++ dst_inode = au_h_iptr(inode, bdst); ++ if (dst_inode) { ++ if (unlikely(!plink)) { ++ err = -EIO; ++ AuIOErr("i%lu exists on a upper branch " ++ "but plink is disabled\n", inode->i_ino); ++ goto out; ++ } ++ ++ if (dst_inode->i_nlink) { ++ const int do_dt = au_ftest_cpup(flags, DTIME); ++ ++ h_src = au_plink_lkup(inode, bdst); ++ err = PTR_ERR(h_src); ++ if (IS_ERR(h_src)) ++ goto out; ++ if (unlikely(!h_src->d_inode)) { ++ err = -EIO; ++ AuIOErr("i%lu exists on a upper branch " ++ "but plink is broken\n", inode->i_ino); ++ dput(h_src); ++ goto out; ++ } ++ ++ if (do_dt) { ++ h_path.dentry = h_parent; ++ au_dtime_store(&dt, dst_parent, &h_path); ++ } ++ h_path.dentry = h_dst; ++ err = vfsub_link(h_src, h_dir, &h_path); ++ if (do_dt) ++ au_dtime_revert(&dt); ++ dput(h_src); ++ goto out; ++ } else ++ /* todo: cpup_wh_file? */ ++ /* udba work */ ++ au_update_brange(inode, 1); ++ } ++ ++ old_ibstart = au_ibstart(inode); ++ err = cpup_entry(dentry, bdst, bsrc, len, flags, dst_parent); ++ if (unlikely(err)) ++ goto out; ++ dst_inode = h_dst->d_inode; ++ mutex_lock_nested(&dst_inode->i_mutex, AuLsc_I_CHILD2); ++ ++ err = cpup_iattr(dentry, bdst, h_src); ++ isdir = S_ISDIR(dst_inode->i_mode); ++ if (!err) { ++ if (bdst < old_ibstart) ++ au_set_ibstart(inode, bdst); ++ au_set_h_iptr(inode, bdst, au_igrab(dst_inode), ++ au_hi_flags(inode, isdir)); ++ mutex_unlock(&dst_inode->i_mutex); ++ if (!isdir ++ && h_src->d_inode->i_nlink > 1 ++ && plink) ++ au_plink_append(inode, bdst, h_dst); ++ goto out; /* success */ ++ } ++ ++ /* revert */ ++ h_path.dentry = h_parent; ++ mutex_unlock(&dst_inode->i_mutex); ++ au_dtime_store(&dt, dst_parent, &h_path); ++ h_path.dentry = h_dst; ++ if (!isdir) ++ rerr = vfsub_unlink(h_dir, &h_path, /*force*/0); ++ else ++ rerr = vfsub_rmdir(h_dir, &h_path); ++ au_dtime_revert(&dt); ++ if (rerr) { ++ AuIOErr("failed removing broken entry(%d, %d)\n", err, rerr); ++ err = -EIO; ++ } ++ ++ out: ++ dput(dst_parent); ++ return err; ++} ++ ++struct au_cpup_single_args { ++ int *errp; ++ struct dentry *dentry; ++ aufs_bindex_t bdst, bsrc; ++ loff_t len; ++ unsigned int flags; ++ struct dentry *dst_parent; ++}; ++ ++static void au_call_cpup_single(void *args) ++{ ++ struct au_cpup_single_args *a = args; ++ *a->errp = au_cpup_single(a->dentry, a->bdst, a->bsrc, a->len, ++ a->flags, a->dst_parent); ++} ++ ++int au_sio_cpup_single(struct dentry *dentry, aufs_bindex_t bdst, ++ aufs_bindex_t bsrc, loff_t len, unsigned int flags, ++ struct dentry *dst_parent) ++{ ++ int err, wkq_err; ++ umode_t mode; ++ struct dentry *h_dentry; ++ ++ h_dentry = au_h_dptr(dentry, bsrc); ++ mode = h_dentry->d_inode->i_mode & S_IFMT; ++ if ((mode != S_IFCHR && mode != S_IFBLK) ++ || capable(CAP_MKNOD)) ++ err = au_cpup_single(dentry, bdst, bsrc, len, flags, ++ dst_parent); ++ else { ++ struct au_cpup_single_args args = { ++ .errp = &err, ++ .dentry = dentry, ++ .bdst = bdst, ++ .bsrc = bsrc, ++ .len = len, ++ .flags = flags, ++ .dst_parent = dst_parent ++ }; ++ wkq_err = au_wkq_wait(au_call_cpup_single, &args); ++ if (unlikely(wkq_err)) ++ err = wkq_err; ++ } ++ ++ return err; ++} ++ ++/* ++ * copyup the @dentry from the first active lower branch to @bdst, ++ * using au_cpup_single(). ++ */ ++static int au_cpup_simple(struct dentry *dentry, aufs_bindex_t bdst, loff_t len, ++ unsigned int flags) ++{ ++ int err; ++ aufs_bindex_t bsrc, bend; ++ ++ bend = au_dbend(dentry); ++ for (bsrc = bdst + 1; bsrc <= bend; bsrc++) ++ if (au_h_dptr(dentry, bsrc)) ++ break; ++ ++ err = au_lkup_neg(dentry, bdst); ++ if (!err) { ++ err = au_cpup_single(dentry, bdst, bsrc, len, flags, NULL); ++ if (!err) ++ return 0; /* success */ ++ ++ /* revert */ ++ au_set_h_dptr(dentry, bdst, NULL); ++ au_set_dbstart(dentry, bsrc); ++ } ++ ++ return err; ++} ++ ++struct au_cpup_simple_args { ++ int *errp; ++ struct dentry *dentry; ++ aufs_bindex_t bdst; ++ loff_t len; ++ unsigned int flags; ++}; ++ ++static void au_call_cpup_simple(void *args) ++{ ++ struct au_cpup_simple_args *a = args; ++ *a->errp = au_cpup_simple(a->dentry, a->bdst, a->len, a->flags); ++} ++ ++int au_sio_cpup_simple(struct dentry *dentry, aufs_bindex_t bdst, loff_t len, ++ unsigned int flags) ++{ ++ int err, wkq_err; ++ unsigned char do_sio; ++ struct dentry *parent; ++ struct inode *h_dir; ++ ++ parent = dget_parent(dentry); ++ h_dir = au_h_iptr(parent->d_inode, bdst); ++ do_sio = !!au_test_h_perm_sio(h_dir, MAY_EXEC | MAY_WRITE); ++ if (!do_sio) { ++ /* ++ * testing CAP_MKNOD is for generic fs, ++ * but CAP_FSETID is for xfs only, currently. ++ */ ++ umode_t mode = dentry->d_inode->i_mode; ++ do_sio = (((mode & (S_IFCHR | S_IFBLK)) ++ && !capable(CAP_MKNOD)) ++ || ((mode & (S_ISUID | S_ISGID)) ++ && !capable(CAP_FSETID))); ++ } ++ if (!do_sio) ++ err = au_cpup_simple(dentry, bdst, len, flags); ++ else { ++ struct au_cpup_simple_args args = { ++ .errp = &err, ++ .dentry = dentry, ++ .bdst = bdst, ++ .len = len, ++ .flags = flags ++ }; ++ wkq_err = au_wkq_wait(au_call_cpup_simple, &args); ++ if (unlikely(wkq_err)) ++ err = wkq_err; ++ } ++ ++ dput(parent); ++ return err; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++/* ++ * copyup the deleted file for writing. ++ */ ++static int au_do_cpup_wh(struct dentry *dentry, aufs_bindex_t bdst, ++ struct dentry *wh_dentry, struct file *file, ++ loff_t len) ++{ ++ int err; ++ aufs_bindex_t bstart; ++ struct au_dinfo *dinfo; ++ struct dentry *h_d_dst, *h_d_start; ++ ++ dinfo = au_di(dentry); ++ bstart = dinfo->di_bstart; ++ h_d_dst = dinfo->di_hdentry[0 + bdst].hd_dentry; ++ dinfo->di_bstart = bdst; ++ dinfo->di_hdentry[0 + bdst].hd_dentry = wh_dentry; ++ h_d_start = dinfo->di_hdentry[0 + bstart].hd_dentry; ++ if (file) ++ dinfo->di_hdentry[0 + bstart].hd_dentry ++ = au_h_fptr(file, au_fbstart(file))->f_dentry; ++ err = au_cpup_single(dentry, bdst, bstart, len, !AuCpup_DTIME, ++ /*h_parent*/NULL); ++ if (!err && file) { ++ err = au_reopen_nondir(file); ++ dinfo->di_hdentry[0 + bstart].hd_dentry = h_d_start; ++ } ++ dinfo->di_hdentry[0 + bdst].hd_dentry = h_d_dst; ++ dinfo->di_bstart = bstart; ++ ++ return err; ++} ++ ++static int au_cpup_wh(struct dentry *dentry, aufs_bindex_t bdst, loff_t len, ++ struct file *file) ++{ ++ int err; ++ struct au_dtime dt; ++ struct dentry *parent, *h_parent, *wh_dentry; ++ struct au_branch *br; ++ struct path h_path; ++ ++ br = au_sbr(dentry->d_sb, bdst); ++ parent = dget_parent(dentry); ++ h_parent = au_h_dptr(parent, bdst); ++ wh_dentry = au_whtmp_lkup(h_parent, br, &dentry->d_name); ++ err = PTR_ERR(wh_dentry); ++ if (IS_ERR(wh_dentry)) ++ goto out; ++ ++ h_path.dentry = h_parent; ++ h_path.mnt = br->br_mnt; ++ au_dtime_store(&dt, parent, &h_path); ++ err = au_do_cpup_wh(dentry, bdst, wh_dentry, file, len); ++ if (unlikely(err)) ++ goto out_wh; ++ ++ dget(wh_dentry); ++ h_path.dentry = wh_dentry; ++ err = vfsub_unlink(h_parent->d_inode, &h_path, /*force*/0); ++ if (unlikely(err)) { ++ AuIOErr("failed remove copied-up tmp file %.*s(%d)\n", ++ AuDLNPair(wh_dentry), err); ++ err = -EIO; ++ } ++ au_dtime_revert(&dt); ++ au_set_hi_wh(dentry->d_inode, bdst, wh_dentry); ++ ++ out_wh: ++ dput(wh_dentry); ++ out: ++ dput(parent); ++ return err; ++} ++ ++struct au_cpup_wh_args { ++ int *errp; ++ struct dentry *dentry; ++ aufs_bindex_t bdst; ++ loff_t len; ++ struct file *file; ++}; ++ ++static void au_call_cpup_wh(void *args) ++{ ++ struct au_cpup_wh_args *a = args; ++ *a->errp = au_cpup_wh(a->dentry, a->bdst, a->len, a->file); ++} ++ ++int au_sio_cpup_wh(struct dentry *dentry, aufs_bindex_t bdst, loff_t len, ++ struct file *file) ++{ ++ int err, wkq_err; ++ struct dentry *parent, *h_orph, *h_parent, *h_dentry; ++ struct inode *dir, *h_dir, *h_tmpdir, *h_inode; ++ struct au_wbr *wbr; ++ ++ parent = dget_parent(dentry); ++ dir = parent->d_inode; ++ h_orph = NULL; ++ h_parent = NULL; ++ h_dir = au_igrab(au_h_iptr(dir, bdst)); ++ h_tmpdir = h_dir; ++ if (!h_dir->i_nlink) { ++ wbr = au_sbr(dentry->d_sb, bdst)->br_wbr; ++ h_orph = wbr->wbr_orph; ++ ++ h_parent = dget(au_h_dptr(parent, bdst)); ++ au_set_h_dptr(parent, bdst, NULL); ++ au_set_h_dptr(parent, bdst, dget(h_orph)); ++ h_tmpdir = h_orph->d_inode; ++ au_set_h_iptr(dir, bdst, NULL, 0); ++ au_set_h_iptr(dir, bdst, au_igrab(h_tmpdir), /*flags*/0); ++ ++ /* this temporary unlock is safe */ ++ if (file) ++ h_dentry = au_h_fptr(file, au_fbstart(file))->f_dentry; ++ else ++ h_dentry = au_h_dptr(dentry, au_dbstart(dentry)); ++ h_inode = h_dentry->d_inode; ++ IMustLock(h_inode); ++ mutex_unlock(&h_inode->i_mutex); ++ mutex_lock_nested(&h_tmpdir->i_mutex, AuLsc_I_PARENT2); ++ mutex_lock_nested(&h_inode->i_mutex, AuLsc_I_CHILD); ++ } ++ ++ if (!au_test_h_perm_sio(h_tmpdir, MAY_EXEC | MAY_WRITE)) ++ err = au_cpup_wh(dentry, bdst, len, file); ++ else { ++ struct au_cpup_wh_args args = { ++ .errp = &err, ++ .dentry = dentry, ++ .bdst = bdst, ++ .len = len, ++ .file = file ++ }; ++ wkq_err = au_wkq_wait(au_call_cpup_wh, &args); ++ if (unlikely(wkq_err)) ++ err = wkq_err; ++ } ++ ++ if (h_orph) { ++ mutex_unlock(&h_tmpdir->i_mutex); ++ au_set_h_iptr(dir, bdst, NULL, 0); ++ au_set_h_iptr(dir, bdst, au_igrab(h_dir), /*flags*/0); ++ au_set_h_dptr(parent, bdst, NULL); ++ au_set_h_dptr(parent, bdst, h_parent); ++ } ++ iput(h_dir); ++ dput(parent); ++ ++ return err; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++/* ++ * generic routine for both of copy-up and copy-down. ++ */ ++/* cf. revalidate function in file.c */ ++int au_cp_dirs(struct dentry *dentry, aufs_bindex_t bdst, ++ int (*cp)(struct dentry *dentry, aufs_bindex_t bdst, ++ struct dentry *h_parent, void *arg), ++ void *arg) ++{ ++ int err; ++ struct au_pin pin; ++ struct dentry *d, *parent, *h_parent, *real_parent; ++ ++ err = 0; ++ parent = dget_parent(dentry); ++ if (IS_ROOT(parent)) ++ goto out; ++ ++ au_pin_init(&pin, dentry, bdst, AuLsc_DI_PARENT2, AuLsc_I_PARENT2, ++ au_opt_udba(dentry->d_sb), AuPin_MNT_WRITE); ++ ++ /* do not use au_dpage */ ++ real_parent = parent; ++ while (1) { ++ dput(parent); ++ parent = dget_parent(dentry); ++ h_parent = au_h_dptr(parent, bdst); ++ if (h_parent) ++ goto out; /* success */ ++ ++ /* find top dir which is necessary to cpup */ ++ do { ++ d = parent; ++ dput(parent); ++ parent = dget_parent(d); ++ di_read_lock_parent3(parent, !AuLock_IR); ++ h_parent = au_h_dptr(parent, bdst); ++ di_read_unlock(parent, !AuLock_IR); ++ } while (!h_parent); ++ ++ if (d != real_parent) ++ di_write_lock_child3(d); ++ ++ /* somebody else might create while we were sleeping */ ++ if (!au_h_dptr(d, bdst) || !au_h_dptr(d, bdst)->d_inode) { ++ if (au_h_dptr(d, bdst)) ++ au_update_dbstart(d); ++ ++ au_pin_set_dentry(&pin, d); ++ err = au_do_pin(&pin); ++ if (!err) { ++ err = cp(d, bdst, h_parent, arg); ++ au_unpin(&pin); ++ } ++ } ++ ++ if (d != real_parent) ++ di_write_unlock(d); ++ if (unlikely(err)) ++ break; ++ } ++ ++ out: ++ dput(parent); ++ return err; ++} ++ ++static int au_cpup_dir(struct dentry *dentry, aufs_bindex_t bdst, ++ struct dentry *h_parent __maybe_unused , ++ void *arg __maybe_unused) ++{ ++ return au_sio_cpup_simple(dentry, bdst, -1, AuCpup_DTIME); ++} ++ ++int au_cpup_dirs(struct dentry *dentry, aufs_bindex_t bdst) ++{ ++ return au_cp_dirs(dentry, bdst, au_cpup_dir, NULL); ++} ++ ++int au_test_and_cpup_dirs(struct dentry *dentry, aufs_bindex_t bdst) ++{ ++ int err; ++ struct dentry *parent; ++ struct inode *dir; ++ ++ parent = dget_parent(dentry); ++ dir = parent->d_inode; ++ err = 0; ++ if (au_h_iptr(dir, bdst)) ++ goto out; ++ ++ di_read_unlock(parent, AuLock_IR); ++ di_write_lock_parent(parent); ++ /* someone else might change our inode while we were sleeping */ ++ if (!au_h_iptr(dir, bdst)) ++ err = au_cpup_dirs(dentry, bdst); ++ di_downgrade_lock(parent, AuLock_IR); ++ ++ out: ++ dput(parent); ++ return err; ++} +diff -urN ./fs/aufs/cpup.h ./fs/aufs/cpup.h +--- ./fs/aufs/cpup.h 1970-01-01 01:00:00.000000000 +0100 ++++ ./fs/aufs/cpup.h 2009-04-06 10:26:46.000000000 +0200 +@@ -0,0 +1,68 @@ ++/* ++ * Copyright (C) 2005-2009 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. ++ */ ++ ++/* ++ * copy-up/down functions ++ */ ++ ++#ifndef __AUFS_CPUP_H__ ++#define __AUFS_CPUP_H__ ++ ++#ifdef __KERNEL__ ++ ++#include <linux/fs.h> ++#include <linux/aufs_type.h> ++ ++void au_cpup_attr_flags(struct inode *dst, struct inode *src); ++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); ++ ++/* ---------------------------------------------------------------------- */ ++ ++/* 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 au_ftest_cpup(flags, name) ((flags) & AuCpup_##name) ++#define au_fset_cpup(flags, name) { (flags) |= AuCpup_##name; } ++#define au_fclr_cpup(flags, name) { (flags) &= ~AuCpup_##name; } ++ ++int au_copy_file(struct file *dst, struct file *src, loff_t len); ++int au_sio_cpup_single(struct dentry *dentry, aufs_bindex_t bdst, ++ aufs_bindex_t bsrc, loff_t len, unsigned int flags, ++ struct dentry *dst_parent); ++int au_sio_cpup_simple(struct dentry *dentry, aufs_bindex_t bdst, loff_t len, ++ unsigned int flags); ++int au_sio_cpup_wh(struct dentry *dentry, aufs_bindex_t bdst, loff_t len, ++ struct file *file); ++ ++int au_cp_dirs(struct dentry *dentry, aufs_bindex_t bdst, ++ int (*cp)(struct dentry *dentry, aufs_bindex_t bdst, ++ struct dentry *h_parent, void *arg), ++ void *arg); ++int au_cpup_dirs(struct dentry *dentry, aufs_bindex_t bdst); ++int au_test_and_cpup_dirs(struct dentry *dentry, aufs_bindex_t bdst); ++ ++/* ---------------------------------------------------------------------- */ ++ ++/* keep timestamps when copyup */ ++struct au_dtime { ++ struct dentry *dt_dentry; ++ struct path dt_h_path; ++ struct 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); ++ ++#endif /* __KERNEL__ */ ++#endif /* __AUFS_CPUP_H__ */ +diff -urN ./fs/aufs/dbgaufs.c ./fs/aufs/dbgaufs.c +--- ./fs/aufs/dbgaufs.c 1970-01-01 01:00:00.000000000 +0100 ++++ ./fs/aufs/dbgaufs.c 2009-04-06 10:26:46.000000000 +0200 +@@ -0,0 +1,304 @@ ++/* ++ * Copyright (C) 2005-2009 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. ++ */ ++ ++/* ++ * debugfs interface ++ */ ++ ++#include <linux/debugfs.h> ++#include "aufs.h" ++ ++#ifndef CONFIG_SYSFS ++#error DEBUG_FS depends upon SYSFS ++#endif ++ ++static struct dentry *dbgaufs; ++static const mode_t dbgaufs_mode = 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) ++{ ++ kfree(file->private_data); ++ return 0; ++} ++ ++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_vfsmnt, xf->f_dentry, &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; ++ ++} ++ ++static ssize_t dbgaufs_xi_read(struct file *file, char __user *buf, ++ size_t count, loff_t *ppos) ++{ ++ struct dbgaufs_arg *p; ++ ++ p = file->private_data; ++ return simple_read_from_buffer(buf, count, ppos, p->a, p->n); ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++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 = { ++ .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_dentry->d_name; ++ if (unlikely(name->len < sizeof(DbgaufsXi_PREFIX) ++ || memcmp(name->name, DbgaufsXi_PREFIX, ++ sizeof(DbgaufsXi_PREFIX) - 1))) ++ goto out; ++ err = strict_strtol(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_sbend(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); ++ ++ out: ++ return err; ++} ++ ++static const struct file_operations dbgaufs_xino_fop = { ++ .open = dbgaufs_xino_open, ++ .release = dbgaufs_xi_release, ++ .read = dbgaufs_xi_read ++}; ++ ++void dbgaufs_brs_del(struct super_block *sb, aufs_bindex_t bindex) ++{ ++ aufs_bindex_t bend; ++ struct au_branch *br; ++ struct au_xino_file *xi; ++ ++ if (!au_sbi(sb)->si_dbgaufs) ++ return; ++ ++ bend = au_sbend(sb); ++ for (; bindex <= bend; bindex++) { ++ br = au_sbr(sb, bindex); ++ xi = &br->br_xino; ++ if (xi->xi_dbgaufs) { ++ debugfs_remove(xi->xi_dbgaufs); ++ xi->xi_dbgaufs = NULL; ++ } ++ } ++} ++ ++void dbgaufs_brs_add(struct super_block *sb, aufs_bindex_t bindex) ++{ ++ struct au_sbinfo *sbinfo; ++ struct dentry *parent; ++ struct au_branch *br; ++ struct au_xino_file *xi; ++ aufs_bindex_t bend; ++ char name[sizeof(DbgaufsXi_PREFIX) + 5]; /* "xi" bindex NULL */ ++ ++ sbinfo = au_sbi(sb); ++ parent = sbinfo->si_dbgaufs; ++ if (!parent) ++ return; ++ ++ bend = au_sbend(sb); ++ for (; bindex <= bend; bindex++) { ++ snprintf(name, sizeof(name), DbgaufsXi_PREFIX "%d", bindex); ++ br = au_sbr(sb, bindex); ++ xi = &br->br_xino; ++ AuDebugOn(xi->xi_dbgaufs); ++ xi->xi_dbgaufs = debugfs_create_file(name, dbgaufs_mode, parent, ++ sbinfo, &dbgaufs_xino_fop); ++ /* ignore an error */ ++ if (unlikely(!xi->xi_dbgaufs)) ++ AuWarn1("failed %s under debugfs\n", name); ++ } ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++#ifdef CONFIG_AUFS_EXPORT ++static int dbgaufs_xigen_open(struct inode *inode, struct file *file) ++{ ++ int err; ++ struct au_sbinfo *sbinfo; ++ struct super_block *sb; ++ ++ sbinfo = inode->i_private; ++ sb = sbinfo->si_sb; ++ si_noflush_read_lock(sb); ++ err = dbgaufs_xi_open(sbinfo->si_xigen, file, /*do_fcnt*/0); ++ si_read_unlock(sb); ++ return err; ++} ++ ++static const struct file_operations dbgaufs_xigen_fop = { ++ .open = dbgaufs_xigen_open, ++ .release = dbgaufs_xi_release, ++ .read = dbgaufs_xi_read ++}; ++ ++static int dbgaufs_xigen_init(struct au_sbinfo *sbinfo) ++{ ++ int err; ++ ++ err = -EIO; ++ sbinfo->si_dbgaufs_xigen = debugfs_create_file ++ ("xigen", dbgaufs_mode, sbinfo->si_dbgaufs, sbinfo, ++ &dbgaufs_xigen_fop); ++ if (sbinfo->si_dbgaufs_xigen) ++ err = 0; ++ ++ return err; ++} ++#else ++static int dbgaufs_xigen_init(struct au_sbinfo *sbinfo) ++{ ++ return 0; ++} ++#endif /* CONFIG_AUFS_EXPORT */ ++ ++/* ---------------------------------------------------------------------- */ ++ ++void dbgaufs_si_fin(struct au_sbinfo *sbinfo) ++{ ++ debugfs_remove_recursive(sbinfo->si_dbgaufs); ++ sbinfo->si_dbgaufs = NULL; ++ kobject_put(&sbinfo->si_kobj); ++} ++ ++int dbgaufs_si_init(struct au_sbinfo *sbinfo) ++{ ++ int err; ++ char name[SysaufsSiNameLen]; ++ ++ err = -ENOENT; ++ if (!dbgaufs) { ++ AuErr1("/debug/aufs is uninitialized\n"); ++ goto out; ++ } ++ ++ err = -EIO; ++ sysaufs_name(sbinfo, name); ++ sbinfo->si_dbgaufs = debugfs_create_dir(name, dbgaufs); ++ if (unlikely(!sbinfo->si_dbgaufs)) ++ goto out; ++ kobject_get(&sbinfo->si_kobj); ++ ++ sbinfo->si_dbgaufs_xib = debugfs_create_file ++ ("xib", dbgaufs_mode, sbinfo->si_dbgaufs, sbinfo, ++ &dbgaufs_xib_fop); ++ if (unlikely(!sbinfo->si_dbgaufs_xib)) ++ goto out_dir; ++ ++ err = dbgaufs_xigen_init(sbinfo); ++ if (!err) ++ goto out; /* success */ ++ ++ out_dir: ++ dbgaufs_si_fin(sbinfo); ++ out: ++ return err; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++void dbgaufs_fin(void) ++{ ++ debugfs_remove(dbgaufs); ++} ++ ++int __init dbgaufs_init(void) ++{ ++ int err; ++ ++ err = -EIO; ++ dbgaufs = debugfs_create_dir(AUFS_NAME, NULL); ++ if (dbgaufs) ++ err = 0; ++ return err; ++} +diff -urN ./fs/aufs/dbgaufs.h ./fs/aufs/dbgaufs.h +--- ./fs/aufs/dbgaufs.h 1970-01-01 01:00:00.000000000 +0100 ++++ ./fs/aufs/dbgaufs.h 2009-04-06 10:26:46.000000000 +0200 +@@ -0,0 +1,68 @@ ++/* ++ * Copyright (C) 2005-2009 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. ++ */ ++ ++/* ++ * debugfs interface ++ */ ++ ++#ifndef __DBGAUFS_H__ ++#define __DBGAUFS_H__ ++ ++#ifdef __KERNEL__ ++ ++#include <linux/fs.h> ++#include <linux/aufs_type.h> ++ ++struct au_sbinfo; ++#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 ++ ++static inline ++void dbgaufs_brs_del(struct super_block *sb, aufs_bindex_t bindex) ++{ ++ /* empty */ ++} ++ ++static inline ++void dbgaufs_brs_add(struct super_block *sb, aufs_bindex_t bindex) ++{ ++ /* empty */ ++} ++ ++static inline ++void dbgaufs_si_fin(struct au_sbinfo *sbinfo) ++{ ++ /* empty */ ++} ++ ++static inline ++int dbgaufs_si_init(struct au_sbinfo *sbinfo) ++{ ++ return 0; ++} ++ ++#define dbgaufs_fin() do {} while (0) ++ ++static inline ++int __init dbgaufs_init(void) ++{ ++ return 0; ++} ++#endif /* CONFIG_DEBUG_FS */ ++ ++#endif /* __KERNEL__ */ ++#endif /* __DBGAUFS_H__ */ +diff -urN ./fs/aufs/dcsub.c ./fs/aufs/dcsub.c +--- ./fs/aufs/dcsub.c 1970-01-01 01:00:00.000000000 +0100 ++++ ./fs/aufs/dcsub.c 2009-04-06 10:26:46.000000000 +0200 +@@ -0,0 +1,214 @@ ++/* ++ * Copyright (C) 2005-2009 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. ++ */ ++ ++/* ++ * sub-routines for dentry cache ++ */ ++ ++#include "aufs.h" ++ ++static void au_dpage_free(struct au_dpage *dpage) ++{ ++ int i; ++ struct dentry **p; ++ ++ p = dpage->dentries; ++ for (i = 0; i < dpage->ndentry; i++) ++ dput(*p++); ++ free_page((unsigned long)dpage->dentries); ++} ++ ++int au_dpages_init(struct au_dcsub_pages *dpages, gfp_t gfp) ++{ ++ int err; ++ void *p; ++ ++ err = -ENOMEM; ++ dpages->dpages = kmalloc(sizeof(*dpages->dpages), gfp); ++ if (unlikely(!dpages->dpages)) ++ goto out; ++ ++ p = (void *)__get_free_page(gfp); ++ if (unlikely(!p)) ++ goto out_dpages; ++ ++ dpages->dpages[0].ndentry = 0; ++ dpages->dpages[0].dentries = p; ++ dpages->ndpage = 1; ++ return 0; /* success */ ++ ++ out_dpages: ++ kfree(dpages->dpages); ++ out: ++ return err; ++} ++ ++void au_dpages_free(struct au_dcsub_pages *dpages) ++{ ++ int i; ++ struct au_dpage *p; ++ ++ p = dpages->dpages; ++ for (i = 0; i < dpages->ndpage; i++) ++ au_dpage_free(p++); ++ kfree(dpages->dpages); ++} ++ ++static int au_dpages_append(struct au_dcsub_pages *dpages, ++ struct dentry *dentry, gfp_t gfp) ++{ ++ int err, sz; ++ struct au_dpage *dpage; ++ void *p; ++ ++ dpage = dpages->dpages + dpages->ndpage - 1; ++ sz = PAGE_SIZE / sizeof(dentry); ++ if (unlikely(dpage->ndentry >= sz)) { ++ AuLabel(new dpage); ++ err = -ENOMEM; ++ sz = dpages->ndpage * sizeof(*dpages->dpages); ++ p = au_kzrealloc(dpages->dpages, sz, ++ sz + sizeof(*dpages->dpages), gfp); ++ if (unlikely(!p)) ++ goto out; ++ ++ dpages->dpages = p; ++ dpage = dpages->dpages + dpages->ndpage; ++ p = (void *)__get_free_page(gfp); ++ if (unlikely(!p)) ++ goto out; ++ ++ dpage->ndentry = 0; ++ dpage->dentries = p; ++ dpages->ndpage++; ++ } ++ ++ dpage->dentries[dpage->ndentry++] = dget(dentry); ++ return 0; /* success */ ++ ++ out: ++ return err; ++} ++ ++int au_dcsub_pages(struct au_dcsub_pages *dpages, struct dentry *root, ++ au_dpages_test test, void *arg) ++{ ++ int err; ++ struct dentry *this_parent = root; ++ struct list_head *next; ++ struct super_block *sb = root->d_sb; ++ ++ err = 0; ++ spin_lock(&dcache_lock); ++ repeat: ++ next = this_parent->d_subdirs.next; ++ resume: ++ if (this_parent->d_sb == sb ++ && !IS_ROOT(this_parent) ++ && atomic_read(&this_parent->d_count) ++ && this_parent->d_inode ++ && (!test || test(this_parent, arg))) { ++ err = au_dpages_append(dpages, this_parent, GFP_ATOMIC); ++ if (unlikely(err)) ++ goto out; ++ } ++ ++ while (next != &this_parent->d_subdirs) { ++ struct list_head *tmp = next; ++ struct dentry *dentry = list_entry(tmp, struct dentry, ++ d_u.d_child); ++ next = tmp->next; ++ if (/*d_unhashed(dentry) || */!dentry->d_inode) ++ continue; ++ if (!list_empty(&dentry->d_subdirs)) { ++ this_parent = dentry; ++ goto repeat; ++ } ++ if (dentry->d_sb == sb ++ && atomic_read(&dentry->d_count) ++ && (!test || test(dentry, arg))) { ++ err = au_dpages_append(dpages, dentry, GFP_ATOMIC); ++ if (unlikely(err)) ++ goto out; ++ } ++ } ++ ++ if (this_parent != root) { ++ next = this_parent->d_u.d_child.next; ++ this_parent = this_parent->d_parent; /* dcache_lock is locked */ ++ goto resume; ++ } ++ out: ++ spin_unlock(&dcache_lock); ++ return err; ++} ++ ++int au_dcsub_pages_rev(struct au_dcsub_pages *dpages, struct dentry *dentry, ++ int do_include, au_dpages_test test, void *arg) ++{ ++ int err; ++ ++ err = 0; ++ spin_lock(&dcache_lock); ++ if (do_include && (!test || test(dentry, arg))) { ++ err = au_dpages_append(dpages, dentry, GFP_ATOMIC); ++ if (unlikely(err)) ++ goto out; ++ } ++ while (!IS_ROOT(dentry)) { ++ dentry = dentry->d_parent; /* dcache_lock is locked */ ++ if (!test || test(dentry, arg)) { ++ err = au_dpages_append(dpages, dentry, GFP_ATOMIC); ++ if (unlikely(err)) ++ break; ++ } ++ } ++ ++ out: ++ spin_unlock(&dcache_lock); ++ ++ return err; ++} ++ ++struct dentry *au_test_subdir(struct dentry *d1, struct dentry *d2) ++{ ++ struct dentry *trap, **dentries; ++ int err, i, j; ++ struct au_dcsub_pages dpages; ++ struct au_dpage *dpage; ++ ++ trap = ERR_PTR(-ENOMEM); ++ err = au_dpages_init(&dpages, GFP_NOFS); ++ if (unlikely(err)) ++ goto out; ++ err = au_dcsub_pages_rev(&dpages, d1, /*do_include*/1, NULL, NULL); ++ if (unlikely(err)) ++ goto out_dpages; ++ ++ trap = d1; ++ for (i = 0; !err && i < dpages.ndpage; i++) { ++ dpage = dpages.dpages + i; ++ dentries = dpage->dentries; ++ for (j = 0; !err && j < dpage->ndentry; j++) { ++ struct dentry *d; ++ ++ d = dentries[j]; ++ err = (d == d2); ++ if (!err) ++ trap = d; ++ } ++ } ++ if (!err) ++ trap = NULL; ++ ++ out_dpages: ++ au_dpages_free(&dpages); ++ out: ++ return trap; ++} +diff -urN ./fs/aufs/dcsub.h ./fs/aufs/dcsub.h +--- ./fs/aufs/dcsub.h 1970-01-01 01:00:00.000000000 +0100 ++++ ./fs/aufs/dcsub.h 2009-04-06 10:26:46.000000000 +0200 +@@ -0,0 +1,43 @@ ++/* ++ * Copyright (C) 2005-2009 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. ++ */ ++ ++/* ++ * sub-routines for dentry cache ++ */ ++ ++#ifndef __AUFS_DCSUB_H__ ++#define __AUFS_DCSUB_H__ ++ ++#ifdef __KERNEL__ ++ ++#include <linux/dcache.h> ++ ++struct au_dpage { ++ int ndentry; ++ struct dentry **dentries; ++}; ++ ++struct au_dcsub_pages { ++ int ndpage; ++ struct au_dpage *dpages; ++}; ++ ++/* ---------------------------------------------------------------------- */ ++ ++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); ++struct dentry *au_test_subdir(struct dentry *d1, struct dentry *d2); ++ ++#endif /* __KERNEL__ */ ++#endif /* __AUFS_DCSUB_H__ */ +diff -urN ./fs/aufs/debug.c ./fs/aufs/debug.c +--- ./fs/aufs/debug.c 1970-01-01 01:00:00.000000000 +0100 ++++ ./fs/aufs/debug.c 2009-04-06 10:26:46.000000000 +0200 +@@ -0,0 +1,414 @@ ++/* ++ * Copyright (C) 2005-2009 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. ++ */ ++ ++/* ++ * debug print functions ++ */ ++ ++#include "aufs.h" ++ ++int aufs_debug; ++MODULE_PARM_DESC(debug, "debug print"); ++module_param_named(debug, aufs_debug, int, S_IRUGO | S_IWUSR | S_IWGRP); ++ ++char *au_plevel = KERN_DEBUG; ++#define dpri(fmt, arg...) do { \ ++ if (au_debug_test()) \ ++ printk("%s" fmt, au_plevel, ##arg); \ ++} while (0) ++ ++/* ---------------------------------------------------------------------- */ ++ ++void au_dpri_whlist(struct au_nhash *whlist) ++{ ++ int i; ++ struct hlist_head *head; ++ struct au_vdir_wh *tpos; ++ struct hlist_node *pos; ++ ++ for (i = 0; i < AuSize_NHASH; i++) { ++ head = whlist->heads + i; ++ hlist_for_each_entry(tpos, pos, head, wh_hash) ++ dpri("b%d, %.*s, %d\n", ++ tpos->wh_bindex, ++ tpos->wh_str.len, tpos->wh_str.name, ++ tpos->wh_str.len); ++ } ++} ++ ++void au_dpri_vdir(struct au_vdir *vdir) ++{ ++ int i; ++ union au_vdir_deblk_p p; ++ unsigned char *o; ++ ++ if (!vdir || IS_ERR(vdir)) { ++ dpri("err %ld\n", PTR_ERR(vdir)); ++ return; ++ } ++ ++ dpri("nblk %d, deblk %p, last{%d, %p}, ver %lu\n", ++ vdir->vd_nblk, vdir->vd_deblk, ++ vdir->vd_last.i, vdir->vd_last.p.p, vdir->vd_version); ++ for (i = 0; i < vdir->vd_nblk; i++) { ++ p.deblk = vdir->vd_deblk[i]; ++ o = p.p; ++ dpri("[%d]: %p\n", i, o); ++ } ++} ++ ++static int do_pri_inode(aufs_bindex_t bindex, struct inode *inode, ++ 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_LSF */ ++ 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: i%lu, %s, cnt %d, nl %u, 0%o, sz %llu, blk %llu," ++ " ct %lld, np %lu, st 0x%lx, f 0x%x, g %x%s%.*s\n", ++ bindex, ++ 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, ++ (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_generation, ++ l ? ", wh " : "", l, n); ++ return 0; ++} ++ ++void au_dpri_inode(struct inode *inode) ++{ ++ struct au_iinfo *iinfo; ++ aufs_bindex_t bindex; ++ int err; ++ ++ err = do_pri_inode(-1, inode, NULL); ++ if (err || !au_test_aufs(inode->i_sb)) ++ return; ++ ++ iinfo = au_ii(inode); ++ if (!iinfo) ++ return; ++ dpri("i-1: bstart %d, bend %d, gen %d\n", ++ iinfo->ii_bstart, iinfo->ii_bend, au_iigen(inode)); ++ if (iinfo->ii_bstart < 0) ++ return; ++ for (bindex = iinfo->ii_bstart; bindex <= iinfo->ii_bend; bindex++) ++ do_pri_inode(bindex, iinfo->ii_hinode[0 + bindex].hi_inode, ++ iinfo->ii_hinode[0 + bindex].hi_whdentry); ++} ++ ++static int do_pri_dentry(aufs_bindex_t bindex, struct dentry *dentry) ++{ ++ struct dentry *wh = NULL; ++ ++ if (!dentry || IS_ERR(dentry)) { ++ dpri("d%d: err %ld\n", bindex, PTR_ERR(dentry)); ++ return -1; ++ } ++ /* do not call dget_parent() here */ ++ dpri("d%d: %.*s?/%.*s, %s, cnt %d, flags 0x%x\n", ++ bindex, ++ AuDLNPair(dentry->d_parent), AuDLNPair(dentry), ++ dentry->d_sb ? au_sbtype(dentry->d_sb) : "??", ++ atomic_read(&dentry->d_count), dentry->d_flags); ++ if (bindex >= 0 && dentry->d_inode && au_test_aufs(dentry->d_sb)) { ++ struct au_iinfo *iinfo = au_ii(dentry->d_inode); ++ if (iinfo) ++ wh = iinfo->ii_hinode[0 + bindex].hi_whdentry; ++ } ++ do_pri_inode(bindex, dentry->d_inode, wh); ++ return 0; ++} ++ ++void au_dpri_dentry(struct dentry *dentry) ++{ ++ struct au_dinfo *dinfo; ++ aufs_bindex_t bindex; ++ int err; ++ ++ err = do_pri_dentry(-1, dentry); ++ if (err || !au_test_aufs(dentry->d_sb)) ++ return; ++ ++ dinfo = au_di(dentry); ++ if (!dinfo) ++ return; ++ dpri("d-1: bstart %d, bend %d, bwh %d, bdiropq %d, gen %d\n", ++ dinfo->di_bstart, dinfo->di_bend, ++ dinfo->di_bwh, dinfo->di_bdiropq, au_digen(dentry)); ++ if (dinfo->di_bstart < 0) ++ return; ++ for (bindex = dinfo->di_bstart; bindex <= dinfo->di_bend; bindex++) ++ do_pri_dentry(bindex, dinfo->di_hdentry[0 + bindex].hd_dentry); ++} ++ ++static int do_pri_file(aufs_bindex_t bindex, struct file *file) ++{ ++ char a[32]; ++ ++ if (!file || IS_ERR(file)) { ++ dpri("f%d: err %ld\n", bindex, PTR_ERR(file)); ++ return -1; ++ } ++ a[0] = 0; ++ if (bindex < 0 ++ && file->f_dentry ++ && au_test_aufs(file->f_dentry->d_sb) ++ && au_fi(file)) ++ snprintf(a, sizeof(a), ", mmapped %d", au_test_mmapped(file)); ++ dpri("f%d: mode 0x%x, flags 0%o, cnt %ld, pos %llu%s\n", ++ bindex, file->f_mode, file->f_flags, (long)file_count(file), ++ file->f_pos, a); ++ if (file->f_dentry) ++ do_pri_dentry(bindex, file->f_dentry); ++ return 0; ++} ++ ++void au_dpri_file(struct file *file) ++{ ++ struct au_finfo *finfo; ++ aufs_bindex_t bindex; ++ int err; ++ ++ err = do_pri_file(-1, file); ++ if (err || !file->f_dentry || !au_test_aufs(file->f_dentry->d_sb)) ++ return; ++ ++ finfo = au_fi(file); ++ if (!finfo) ++ return; ++ if (finfo->fi_bstart < 0) ++ return; ++ for (bindex = finfo->fi_bstart; bindex <= finfo->fi_bend; bindex++) { ++ struct au_hfile *hf; ++ ++ hf = finfo->fi_hfile + bindex; ++ do_pri_file(bindex, hf ? hf->hf_file : NULL); ++ } ++} ++ ++static int do_pri_br(aufs_bindex_t bindex, struct au_branch *br) ++{ ++ struct vfsmount *mnt; ++ struct super_block *sb; ++ ++ if (!br || IS_ERR(br)) ++ goto out; ++ mnt = br->br_mnt; ++ if (!mnt || IS_ERR(mnt)) ++ goto out; ++ sb = mnt->mnt_sb; ++ if (!sb || IS_ERR(sb)) ++ goto out; ++ ++ dpri("s%d: {perm 0x%x, cnt %d, wbr %p}, " ++ "%s, dev 0x%02x%02x, flags 0x%lx, cnt(BIAS) %d, active %d, " ++ "xino %d\n", ++ bindex, br->br_perm, atomic_read(&br->br_count), br->br_wbr, ++ au_sbtype(sb), MAJOR(sb->s_dev), MINOR(sb->s_dev), ++ sb->s_flags, sb->s_count - S_BIAS, ++ 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; ++} ++ ++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; ++ ++ /* this function can be called from magic sysrq */ ++ a = kzalloc(sizeof(*a), GFP_ATOMIC); ++ if (unlikely(!a)) { ++ dpri("no memory\n"); ++ return; ++ } ++ ++ a->mnt.mnt_sb = sb; ++ a->fake.br_perm = 0; ++ a->fake.br_mnt = &a->mnt; ++ a->fake.br_xino.xi_file = NULL; ++ atomic_set(&a->fake.br_count, 0); ++ smp_mb(); /* atomic_set */ ++ err = do_pri_br(-1, &a->fake); ++ kfree(a); ++ dpri("dev 0x%x\n", sb->s_dev); ++ if (err || !au_test_aufs(sb)) ++ return; ++ ++ sbinfo = au_sbi(sb); ++ if (!sbinfo) ++ return; ++ dpri("nw %d, gen %u, kobj %d\n", ++ atomic_read(&sbinfo->si_nowait.nw_len), sbinfo->si_generation, ++ atomic_read(&sbinfo->si_kobj.kref.refcount)); ++ for (bindex = 0; bindex <= sbinfo->si_bend; bindex++) ++ do_pri_br(bindex, sbinfo->si_branch[0 + bindex]); ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++void au_dbg_sleep_jiffy(int jiffy) ++{ ++ while (jiffy) ++ jiffy = schedule_timeout_uninterruptible(jiffy); ++} ++ ++void au_dbg_iattr(struct iattr *ia) ++{ ++#define AuBit(name) if (ia->ia_valid & ATTR_ ## name) \ ++ dpri(#name "\n") ++ AuBit(MODE); ++ AuBit(UID); ++ AuBit(GID); ++ AuBit(SIZE); ++ AuBit(ATIME); ++ AuBit(MTIME); ++ AuBit(CTIME); ++ AuBit(ATIME_SET); ++ AuBit(MTIME_SET); ++ AuBit(FORCE); ++ AuBit(ATTR_FLAG); ++ AuBit(KILL_SUID); ++ AuBit(KILL_SGID); ++ AuBit(FILE); ++ AuBit(KILL_PRIV); ++ AuBit(OPEN); ++ AuBit(TIMES_SET); ++#undef AuBit ++ dpri("ia_file %p\n", ia->ia_file); ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++void au_dbg_verify_dir_parent(struct dentry *dentry, unsigned int sigen) ++{ ++ struct dentry *parent; ++ ++ parent = dget_parent(dentry); ++ AuDebugOn(!S_ISDIR(dentry->d_inode->i_mode) ++ || IS_ROOT(dentry) ++ || au_digen(parent) != sigen); ++ dput(parent); ++} ++ ++void au_dbg_verify_nondir_parent(struct dentry *dentry, unsigned int sigen) ++{ ++ struct dentry *parent; ++ ++ parent = dget_parent(dentry); ++ AuDebugOn(S_ISDIR(dentry->d_inode->i_mode) ++ || au_digen(parent) != sigen); ++ dput(parent); ++} ++ ++void au_dbg_verify_gen(struct dentry *parent, unsigned int sigen) ++{ ++ int err, i, j; ++ struct au_dcsub_pages dpages; ++ struct au_dpage *dpage; ++ struct dentry **dentries; ++ ++ err = au_dpages_init(&dpages, GFP_NOFS); ++ AuDebugOn(err); ++ err = au_dcsub_pages_rev(&dpages, parent, /*do_include*/1, NULL, NULL); ++ 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(dentries[j]) != sigen); ++ } ++ au_dpages_free(&dpages); ++} ++ ++void au_dbg_verify_hf(struct au_finfo *finfo) ++{ ++ struct au_hfile *hf; ++ aufs_bindex_t bend, bindex; ++ ++ if (finfo->fi_bstart >= 0) { ++ bend = finfo->fi_bend; ++ for (bindex = finfo->fi_bstart; bindex <= bend; bindex++) { ++ hf = finfo->fi_hfile + bindex; ++ AuDebugOn(hf->hf_file || hf->hf_br); ++ } ++ } ++} ++ ++void au_dbg_verify_kthread(void) ++{ ++ if (au_test_wkq(current)) { ++ au_dbg_blocked(); ++ BUG(); ++ } ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++void au_debug_sbinfo_init(struct au_sbinfo *sbinfo __maybe_unused) ++{ ++#ifdef AuForceNoPlink ++ au_opt_clr(sbinfo->si_mntflags, PLINK); ++#endif ++#ifdef AuForceNoXino ++ au_opt_clr(sbinfo->si_mntflags, XINO); ++#endif ++#ifdef AuForceNoRefrof ++ au_opt_clr(sbinfo->si_mntflags, REFROF); ++#endif ++#ifdef AuForceHinotify ++ au_opt_set_udba(sbinfo->si_mntflags, UDBA_HINOTIFY); ++#endif ++} ++ ++int __init au_debug_init(void) ++{ ++ aufs_bindex_t bindex; ++ struct au_vdir_destr destr; ++ ++ bindex = -1; ++ AuDebugOn(bindex >= 0); ++ ++ destr.len = -1; ++ AuDebugOn(destr.len < NAME_MAX); ++ ++#ifdef CONFIG_4KSTACKS ++ AuWarn("CONFIG_4KSTACKS is defined.\n"); ++#endif ++ ++#ifdef AuForceNoBrs ++ sysaufs_brs = 0; ++#endif ++ ++ return 0; ++} +diff -urN ./fs/aufs/debug.h ./fs/aufs/debug.h +--- ./fs/aufs/debug.h 1970-01-01 01:00:00.000000000 +0100 ++++ ./fs/aufs/debug.h 2009-04-06 10:26:46.000000000 +0200 +@@ -0,0 +1,243 @@ ++/* ++ * Copyright (C) 2005-2009 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. ++ */ ++ ++/* ++ * debug print functions ++ */ ++ ++#ifndef __AUFS_DEBUG_H__ ++#define __AUFS_DEBUG_H__ ++ ++#ifdef __KERNEL__ ++ ++#include <linux/delay.h> ++#include <linux/fs.h> ++#include <linux/kd.h> ++#include <linux/vt_kern.h> ++#include <linux/sysrq.h> ++#include <linux/aufs_type.h> ++ ++#ifdef CONFIG_AUFS_DEBUG ++#define AuDebugOn(a) BUG_ON(a) ++ ++/* module parameter */ ++extern int aufs_debug; ++static inline void au_debug(int n) ++{ ++ aufs_debug = n; ++ smp_mb(); ++} ++ ++static inline int au_debug_test(void) ++{ ++ return aufs_debug; ++} ++#else ++#define AuDebugOn(a) do {} while (0) ++#define au_debug() do {} while (0) ++static inline int au_debug_test(void) ++{ ++ return 0; ++} ++#endif /* CONFIG_AUFS_DEBUG */ ++ ++/* ---------------------------------------------------------------------- */ ++ ++/* debug print */ ++ ++#define AuDpri(lvl, fmt, arg...) \ ++ printk(lvl AUFS_NAME " %s:%d:%s[%d]: " fmt, \ ++ __func__, __LINE__, current->comm, current->pid, ##arg) ++#define AuDbg(fmt, arg...) do { \ ++ if (au_debug_test()) \ ++ AuDpri(KERN_DEBUG, fmt, ##arg); \ ++} while (0) ++#define AuLabel(l) AuDbg(#l "\n") ++#define AuInfo(fmt, arg...) AuDpri(KERN_INFO, fmt, ##arg) ++#define AuWarn(fmt, arg...) AuDpri(KERN_WARNING, fmt, ##arg) ++#define AuErr(fmt, arg...) AuDpri(KERN_ERR, fmt, ##arg) ++#define AuIOErr(fmt, arg...) AuErr("I/O Error, " fmt, ##arg) ++#define AuWarn1(fmt, arg...) do { \ ++ static unsigned char _c; \ ++ if (!_c++) \ ++ AuWarn(fmt, ##arg); \ ++} while (0) ++ ++#define AuErr1(fmt, arg...) do { \ ++ static unsigned char _c; \ ++ if (!_c++) \ ++ AuErr(fmt, ##arg); \ ++} while (0) ++ ++#define AuIOErr1(fmt, arg...) do { \ ++ static unsigned char _c; \ ++ if (!_c++) \ ++ AuIOErr(fmt, ##arg); \ ++} while (0) ++ ++#define AuUnsupportMsg "This operation is not supported." \ ++ " Please report this application to aufs-users ML." ++#define AuUnsupport(fmt, args...) do { \ ++ AuErr(AuUnsupportMsg "\n" fmt, ##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 ++#define AuDLNPair(d) AuLNPair(&(d)->d_name) ++ ++/* ---------------------------------------------------------------------- */ ++ ++struct au_sbinfo; ++struct au_finfo; ++#ifdef CONFIG_AUFS_DEBUG ++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); ++void au_dpri_inode(struct inode *inode); ++void au_dpri_dentry(struct dentry *dentry); ++void au_dpri_file(struct file *filp); ++void au_dpri_sb(struct super_block *sb); ++ ++void au_dbg_sleep_jiffy(int jiffy); ++void au_dbg_iattr(struct iattr *ia); ++ ++void au_dbg_verify_dir_parent(struct dentry *dentry, unsigned int sigen); ++void au_dbg_verify_nondir_parent(struct dentry *dentry, unsigned int sigen); ++void au_dbg_verify_gen(struct dentry *parent, unsigned int sigen); ++void au_dbg_verify_hf(struct au_finfo *finfo); ++void au_dbg_verify_kthread(void); ++ ++int __init au_debug_init(void); ++void au_debug_sbinfo_init(struct au_sbinfo *sbinfo); ++#define AuDbgWhlist(w) do { \ ++ AuDbg(#w "\n"); \ ++ au_dpri_whlist(w); \ ++} while (0) ++ ++#define AuDbgVdir(v) do { \ ++ AuDbg(#v "\n"); \ ++ au_dpri_vdir(v); \ ++} while (0) ++ ++#define AuDbgInode(i) do { \ ++ AuDbg(#i "\n"); \ ++ au_dpri_inode(i); \ ++} while (0) ++ ++#define AuDbgDentry(d) do { \ ++ AuDbg(#d "\n"); \ ++ au_dpri_dentry(d); \ ++} while (0) ++ ++#define AuDbgFile(f) do { \ ++ AuDbg(#f "\n"); \ ++ au_dpri_file(f); \ ++} while (0) ++ ++#define AuDbgSb(sb) do { \ ++ AuDbg(#sb "\n"); \ ++ au_dpri_sb(sb); \ ++} while (0) ++ ++#define AuDbgSleep(sec) do { \ ++ AuDbg("sleep %d sec\n", sec); \ ++ ssleep(sec); \ ++} while (0) ++ ++#define AuDbgSleepJiffy(jiffy) do { \ ++ AuDbg("sleep %d jiffies\n", jiffy); \ ++ au_dbg_sleep_jiffy(jiffy); \ ++} while (0) ++ ++#define AuDbgIAttr(ia) do { \ ++ AuDbg("ia_valid 0x%x\n", (ia)->ia_valid); \ ++ au_dbg_iattr(ia); \ ++} while (0) ++#else ++static inline void au_dbg_verify_dir_parent(struct dentry *dentry, ++ unsigned int sigen) ++{ ++ /* empty */ ++} ++static inline void au_dbg_verify_nondir_parent(struct dentry *dentry, ++ unsigned int sigen) ++{ ++ /* empty */ ++} ++static inline void au_dbg_verify_gen(struct dentry *parent, unsigned int sigen) ++{ ++ /* empty */ ++} ++static inline void au_dbg_verify_hf(struct au_finfo *finfo) ++{ ++ /* empty */ ++} ++static inline void au_dbg_verify_kthread(void) ++{ ++ /* empty */ ++} ++ ++static inline int au_debug_init(void) ++{ ++ return 0; ++} ++static inline void au_debug_sbinfo_init(struct au_sbinfo *sbinfo) ++{ ++ /* empty */ ++} ++#define AuDbgWhlist(w) do {} while (0) ++#define AuDbgVdir(v) do {} while (0) ++#define AuDbgInode(i) do {} while (0) ++#define AuDbgDentry(d) do {} while (0) ++#define AuDbgFile(f) do {} while (0) ++#define AuDbgSb(sb) do {} while (0) ++#define AuDbgSleep(sec) do {} while (0) ++#define AuDbgSleepJiffy(jiffy) do {} while (0) ++#define AuDbgIAttr(ia) do {} while (0) ++#endif /* CONFIG_AUFS_DEBUG */ ++ ++/* ---------------------------------------------------------------------- */ ++ ++#ifdef CONFIG_AUFS_MAGIC_SYSRQ ++int __init au_sysrq_init(void); ++void au_sysrq_fin(void); ++ ++#ifdef CONFIG_HW_CONSOLE ++#define au_dbg_blocked() do { \ ++ WARN_ON(1); \ ++ handle_sysrq('w', vc_cons[fg_console].d->vc_tty); \ ++} while (0) ++#else ++#define au_dbg_blocked() do {} while (0) ++#endif ++ ++#else ++static inline int au_sysrq_init(void) ++{ ++ return 0; ++} ++#define au_sysrq_fin() do {} while (0) ++#define au_dbg_blocked() do {} while (0) ++#endif /* CONFIG_AUFS_MAGIC_SYSRQ */ ++ ++#endif /* __KERNEL__ */ ++#endif /* __AUFS_DEBUG_H__ */ +diff -urN ./fs/aufs/dentry.c ./fs/aufs/dentry.c +--- ./fs/aufs/dentry.c 1970-01-01 01:00:00.000000000 +0100 ++++ ./fs/aufs/dentry.c 2009-04-06 10:26:46.000000000 +0200 +@@ -0,0 +1,858 @@ ++/* ++ * Copyright (C) 2005-2009 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. ++ */ ++ ++/* ++ * lookup and dentry operations ++ */ ++ ++#include "aufs.h" ++ ++static void au_h_nd(struct nameidata *h_nd, struct nameidata *nd) ++{ ++ if (nd) { ++ *h_nd = *nd; ++ ++ /* ++ * gave up supporting LOOKUP_CREATE/OPEN for lower fs, ++ * due to whiteout and branch permission. ++ */ ++ h_nd->flags &= ~(/*LOOKUP_PARENT |*/ LOOKUP_OPEN | LOOKUP_CREATE ++ | LOOKUP_FOLLOW); ++ /* unnecessary? */ ++ h_nd->intent.open.file = NULL; ++ } else ++ memset(h_nd, 0, sizeof(*h_nd)); ++} ++ ++struct au_lkup_one_args { ++ struct dentry **errp; ++ struct qstr *name; ++ struct dentry *h_parent; ++ struct au_branch *br; ++ struct nameidata *nd; ++}; ++ ++struct dentry *au_lkup_one(struct qstr *name, struct dentry *h_parent, ++ struct au_branch *br, struct nameidata *nd) ++{ ++ struct dentry *h_dentry; ++ int err; ++ struct nameidata h_nd; ++ ++ if (au_test_fs_null_nd(h_parent->d_sb)) ++ return vfsub_lookup_one_len(name->name, h_parent, name->len); ++ ++ au_h_nd(&h_nd, nd); ++ h_nd.path.dentry = h_parent; ++ h_nd.path.mnt = br->br_mnt; ++ ++ err = __lookup_one_len(name->name, &h_nd.last, NULL, name->len); ++ h_dentry = ERR_PTR(err); ++ if (!err) { ++ path_get(&h_nd.path); ++ h_dentry = vfsub_lookup_hash(&h_nd); ++ path_put(&h_nd.path); ++ } ++ ++ return h_dentry; ++} ++ ++static void au_call_lkup_one(void *args) ++{ ++ struct au_lkup_one_args *a = args; ++ *a->errp = au_lkup_one(a->name, a->h_parent, a->br, a->nd); ++} ++ ++#define AuLkup_ALLOW_NEG 1 ++#define au_ftest_lkup(flags, name) ((flags) & AuLkup_##name) ++#define au_fset_lkup(flags, name) { (flags) |= AuLkup_##name; } ++#define au_fclr_lkup(flags, name) { (flags) &= ~AuLkup_##name; } ++ ++struct au_do_lookup_args { ++ unsigned int flags; ++ mode_t type; ++ struct nameidata *nd; ++}; ++ ++/* ++ * returns positive/negative dentry, NULL or an error. ++ * NULL means whiteout-ed or not-found. ++ */ ++static struct dentry* ++au_do_lookup(struct dentry *h_parent, struct dentry *dentry, ++ aufs_bindex_t bindex, struct qstr *wh_name, ++ struct au_do_lookup_args *args) ++{ ++ struct dentry *h_dentry; ++ struct inode *h_inode, *inode; ++ struct qstr *name; ++ struct au_branch *br; ++ int wh_found, opq; ++ unsigned char wh_able; ++ const unsigned char allow_neg = !!au_ftest_lkup(args->flags, ALLOW_NEG); ++ ++ name = &dentry->d_name; ++ 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, br, /*try_sio*/0); ++ h_dentry = ERR_PTR(wh_found); ++ if (!wh_found) ++ goto real_lookup; ++ if (unlikely(wh_found < 0)) ++ goto out; ++ ++ /* We found a whiteout */ ++ /* au_set_dbend(dentry, bindex); */ ++ au_set_dbwh(dentry, bindex); ++ if (!allow_neg) ++ return NULL; /* success */ ++ ++ real_lookup: ++ h_dentry = au_lkup_one(name, h_parent, br, args->nd); ++ if (IS_ERR(h_dentry)) ++ goto out; ++ ++ h_inode = h_dentry->d_inode; ++ if (!h_inode) { ++ 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_dbend(dentry) <= bindex) ++ au_set_dbend(dentry, bindex); ++ if (au_dbstart(dentry) < 0 || bindex < au_dbstart(dentry)) ++ au_set_dbstart(dentry, bindex); ++ au_set_h_dptr(dentry, bindex, h_dentry); ++ ++ inode = dentry->d_inode; ++ if (!h_inode || !S_ISDIR(h_inode->i_mode) || !wh_able ++ || (inode && !S_ISDIR(inode->i_mode))) ++ goto out; /* success */ ++ ++ mutex_lock_nested(&h_inode->i_mutex, AuLsc_I_CHILD); ++ opq = au_diropq_test(h_dentry, br); ++ mutex_unlock(&h_inode->i_mutex); ++ if (opq > 0) ++ au_set_dbdiropq(dentry, bindex); ++ else if (unlikely(opq < 0)) { ++ au_set_h_dptr(dentry, bindex, NULL); ++ h_dentry = ERR_PTR(opq); ++ } ++ goto out; ++ ++ out_neg: ++ dput(h_dentry); ++ h_dentry = NULL; ++ out: ++ return h_dentry; ++} ++ ++/* ++ * 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 bstart, mode_t type, ++ struct nameidata *nd) ++{ ++ int npositive, err; ++ aufs_bindex_t bindex, btail, bdiropq; ++ unsigned char isdir; ++ struct qstr whname; ++ struct au_do_lookup_args args = { ++ .flags = 0, ++ .type = type, ++ .nd = nd ++ }; ++ const struct qstr *name = &dentry->d_name; ++ struct dentry *parent; ++ struct inode *inode; ++ ++ err = -EPERM; ++ parent = dget_parent(dentry); ++ if (unlikely(!strncmp(name->name, AUFS_WH_PFX, AUFS_WH_PFX_LEN))) ++ goto out; ++ ++ err = au_wh_name_alloc(&whname, name); ++ if (unlikely(err)) ++ goto out; ++ ++ inode = dentry->d_inode; ++ isdir = !!(inode && S_ISDIR(inode->i_mode)); ++ if (!type) ++ au_fset_lkup(args.flags, ALLOW_NEG); ++ ++ npositive = 0; ++ btail = au_dbtaildir(parent); ++ for (bindex = bstart; 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 (h_dentry->d_inode) ++ npositive++; ++ if (type != S_IFDIR) ++ break; ++ continue; ++ } ++ h_parent = au_h_dptr(parent, bindex); ++ if (!h_parent) ++ continue; ++ h_dir = h_parent->d_inode; ++ if (!h_dir || !S_ISDIR(h_dir->i_mode)) ++ continue; ++ ++ mutex_lock_nested(&h_dir->i_mutex, AuLsc_I_PARENT); ++ h_dentry = au_do_lookup(h_parent, dentry, bindex, &whname, ++ &args); ++ mutex_unlock(&h_dir->i_mutex); ++ err = PTR_ERR(h_dentry); ++ if (IS_ERR(h_dentry)) ++ goto out_wh; ++ au_fclr_lkup(args.flags, ALLOW_NEG); ++ ++ if (au_dbwh(dentry) >= 0) ++ break; ++ if (!h_dentry) ++ continue; ++ h_inode = h_dentry->d_inode; ++ if (!h_inode) ++ continue; ++ 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; ++ } ++ } ++ ++ if (npositive) { ++ AuLabel(positive); ++ au_update_dbstart(dentry); ++ } ++ err = npositive; ++ if (unlikely(!au_opt_test(au_mntflags(dentry->d_sb), UDBA_NONE) ++ && au_dbstart(dentry) < 0)) ++ /* both of real entry and whiteout found */ ++ err = -EIO; ++ ++ out_wh: ++ kfree(whname.name); ++ out: ++ dput(parent); ++ return err; ++} ++ ++struct dentry *au_sio_lkup_one(struct qstr *name, struct dentry *parent, ++ struct au_branch *br) ++{ ++ struct dentry *dentry; ++ int wkq_err; ++ ++ if (!au_test_h_perm_sio(parent->d_inode, MAY_EXEC)) ++ dentry = au_lkup_one(name, parent, br, /*nd*/NULL); ++ else { ++ struct au_lkup_one_args args = { ++ .errp = &dentry, ++ .name = name, ++ .h_parent = parent, ++ .br = br, ++ .nd = NULL ++ }; ++ ++ wkq_err = au_wkq_wait(au_call_lkup_one, &args); ++ if (unlikely(wkq_err)) ++ dentry = ERR_PTR(wkq_err); ++ } ++ ++ return dentry; ++} ++ ++/* ++ * lookup @dentry on @bindex which should be negative. ++ */ ++int au_lkup_neg(struct dentry *dentry, aufs_bindex_t bindex) ++{ ++ int err; ++ struct dentry *parent, *h_parent, *h_dentry; ++ struct qstr *name; ++ ++ name = &dentry->d_name; ++ parent = dget_parent(dentry); ++ h_parent = au_h_dptr(parent, bindex); ++ h_dentry = au_sio_lkup_one(name, h_parent, ++ au_sbr(dentry->d_sb, bindex)); ++ err = PTR_ERR(h_dentry); ++ if (IS_ERR(h_dentry)) ++ goto out; ++ if (unlikely(h_dentry->d_inode)) { ++ err = -EIO; ++ AuIOErr("b%d %.*s should be negative.\n", ++ bindex, AuDLNPair(h_dentry)); ++ dput(h_dentry); ++ goto out; ++ } ++ ++ if (bindex < au_dbstart(dentry)) ++ au_set_dbstart(dentry, bindex); ++ if (au_dbend(dentry) < bindex) ++ au_set_dbend(dentry, bindex); ++ au_set_h_dptr(dentry, bindex, h_dentry); ++ err = 0; ++ ++ out: ++ dput(parent); ++ return err; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++/* subset of struct inode */ ++struct au_iattr { ++ unsigned long i_ino; ++ /* unsigned int i_nlink; */ ++ uid_t i_uid; ++ gid_t i_gid; ++ u64 i_version; ++/* ++ loff_t i_size; ++ blkcnt_t i_blocks; ++*/ ++ umode_t i_mode; ++}; ++ ++static void au_iattr_save(struct au_iattr *ia, struct inode *h_inode) ++{ ++ ia->i_ino = h_inode->i_ino; ++ /* ia->i_nlink = h_inode->i_nlink; */ ++ ia->i_uid = h_inode->i_uid; ++ ia->i_gid = h_inode->i_gid; ++ ia->i_version = 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); ++} ++ ++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 */ ++ || 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); ++} ++ ++static int au_h_verify_dentry(struct dentry *h_dentry, struct dentry *h_parent, ++ struct au_branch *br) ++{ ++ int err; ++ struct au_iattr ia; ++ struct inode *h_inode; ++ struct dentry *h_d; ++ struct super_block *h_sb; ++ ++ err = 0; ++ memset(&ia, -1, sizeof(ia)); ++ h_sb = h_dentry->d_sb; ++ h_inode = h_dentry->d_inode; ++ if (h_inode) ++ 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 = au_lkup_one(&h_dentry->d_name, h_parent, br, /*nd*/NULL); ++ err = PTR_ERR(h_d); ++ if (IS_ERR(h_d)) ++ goto out; ++ ++ err = 0; ++ if (unlikely(h_d != h_dentry ++ || h_d->d_inode != h_inode ++ || (h_inode && au_iattr_test(&ia, h_inode)))) ++ err = au_busy_or_stale(); ++ dput(h_d); ++ ++ out: ++ AuTraceErr(err); ++ return err; ++} ++ ++int au_h_verify(struct dentry *h_dentry, unsigned int udba, struct inode *h_dir, ++ struct dentry *h_parent, struct au_branch *br) ++{ ++ int err; ++ ++ err = 0; ++ if (udba == AuOpt_UDBA_REVAL) { ++ IMustLock(h_dir); ++ err = (h_dentry->d_parent->d_inode != h_dir); ++ } else if (udba == AuOpt_UDBA_HINOTIFY) ++ err = au_h_verify_dentry(h_dentry, h_parent, br); ++ ++ return err; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++static void au_do_refresh_hdentry(struct au_hdentry *p, struct au_dinfo *dinfo, ++ struct dentry *parent) ++{ ++ struct dentry *h_d, *h_dp; ++ struct au_hdentry tmp, *q; ++ struct super_block *sb; ++ aufs_bindex_t new_bindex, bindex, bend, bwh, bdiropq; ++ ++ bend = dinfo->di_bend; ++ bwh = dinfo->di_bwh; ++ bdiropq = dinfo->di_bdiropq; ++ for (bindex = dinfo->di_bstart; bindex <= bend; bindex++, p++) { ++ h_d = p->hd_dentry; ++ if (!h_d) ++ continue; ++ ++ h_dp = dget_parent(h_d); ++ if (h_dp == au_h_dptr(parent, bindex)) { ++ dput(h_dp); ++ continue; ++ } ++ ++ new_bindex = au_find_dbindex(parent, h_dp); ++ dput(h_dp); ++ 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 = dinfo->di_hdentry + new_bindex; ++ tmp = *q; ++ *q = *p; ++ *p = tmp; ++ if (tmp.hd_dentry) { ++ bindex--; ++ p--; ++ } ++ } ++ ++ sb = parent->d_sb; ++ dinfo->di_bwh = -1; ++ if (bwh >= 0 && bwh <= au_sbend(sb) && au_sbr_whable(sb, bwh)) ++ dinfo->di_bwh = bwh; ++ ++ dinfo->di_bdiropq = -1; ++ if (bdiropq >= 0 ++ && bdiropq <= au_sbend(sb) ++ && au_sbr_whable(sb, bdiropq)) ++ dinfo->di_bdiropq = bdiropq; ++ ++ bend = au_dbend(parent); ++ p = dinfo->di_hdentry; ++ for (bindex = 0; bindex <= bend; bindex++, p++) ++ if (p->hd_dentry) { ++ dinfo->di_bstart = bindex; ++ break; ++ } ++ ++ p = dinfo->di_hdentry + bend; ++ for (bindex = bend; bindex >= 0; bindex--, p--) ++ if (p->hd_dentry) { ++ dinfo->di_bend = bindex; ++ break; ++ } ++} ++ ++/* ++ * returns the number of found lower positive dentries, ++ * otherwise an error. ++ */ ++int au_refresh_hdentry(struct dentry *dentry, mode_t type) ++{ ++ int npositive, err; ++ unsigned int sigen; ++ aufs_bindex_t bstart; ++ struct au_dinfo *dinfo; ++ struct super_block *sb; ++ struct dentry *parent; ++ ++ sb = dentry->d_sb; ++ AuDebugOn(IS_ROOT(dentry)); ++ sigen = au_sigen(sb); ++ parent = dget_parent(dentry); ++ AuDebugOn(au_digen(parent) != sigen ++ || au_iigen(parent->d_inode) != sigen); ++ ++ dinfo = au_di(dentry); ++ err = au_di_realloc(dinfo, au_sbend(sb) + 1); ++ npositive = err; ++ if (unlikely(err)) ++ goto out; ++ au_do_refresh_hdentry(dinfo->di_hdentry + dinfo->di_bstart, dinfo, ++ parent); ++ ++ npositive = 0; ++ bstart = au_dbstart(parent); ++ if (type != S_IFDIR && dinfo->di_bstart == bstart) ++ goto out_dgen; /* success */ ++ ++ npositive = au_lkup_dentry(dentry, bstart, type, /*nd*/NULL); ++ if (npositive < 0) ++ goto out; ++ if (dinfo->di_bwh >= 0 && dinfo->di_bwh <= dinfo->di_bstart) ++ d_drop(dentry); ++ ++ out_dgen: ++ au_update_digen(dentry); ++ out: ++ dput(parent); ++ AuTraceErr(npositive); ++ return npositive; ++} ++ ++static noinline_for_stack ++int au_do_h_d_reval(struct dentry *h_dentry, struct nameidata *nd, ++ struct dentry *dentry, aufs_bindex_t bindex) ++{ ++ int err, valid; ++ int (*reval)(struct dentry *, struct nameidata *); ++ ++ err = 0; ++ reval = NULL; ++ if (h_dentry->d_op) ++ reval = h_dentry->d_op->d_revalidate; ++ if (!reval) ++ goto out; ++ ++ AuDbg("b%d\n", bindex); ++ if (au_test_fs_null_nd(h_dentry->d_sb)) ++ /* it may return tri-state */ ++ valid = reval(h_dentry, NULL); ++ else { ++ struct nameidata h_nd; ++ int locked; ++ struct dentry *parent; ++ ++ au_h_nd(&h_nd, nd); ++ parent = nd->path.dentry; ++ locked = (nd && nd->path.dentry != dentry); ++ if (locked) ++ di_read_lock_parent(parent, AuLock_IR); ++ BUG_ON(bindex > au_dbend(parent)); ++ h_nd.path.dentry = au_h_dptr(parent, bindex); ++ BUG_ON(!h_nd.path.dentry); ++ h_nd.path.mnt = au_sbr(parent->d_sb, bindex)->br_mnt; ++ path_get(&h_nd.path); ++ valid = reval(h_dentry, &h_nd); ++ path_put(&h_nd.path); ++ if (locked) ++ di_read_unlock(parent, AuLock_IR); ++ } ++ ++ if (unlikely(valid < 0)) ++ err = valid; ++ else if (!valid) ++ err = -EINVAL; ++ ++ out: ++ AuTraceErr(err); ++ return err; ++} ++ ++/* todo: remove this */ ++static int h_d_revalidate(struct dentry *dentry, struct inode *inode, ++ struct nameidata *nd, int do_udba) ++{ ++ int err; ++ umode_t mode, h_mode; ++ aufs_bindex_t bindex, btail, bstart, ibs, ibe; ++ unsigned char plus, unhashed, is_root, h_plus; ++ struct inode *first, *h_inode, *h_cached_inode; ++ struct dentry *h_dentry; ++ struct qstr *name, *h_name; ++ ++ err = 0; ++ plus = 0; ++ mode = 0; ++ first = NULL; ++ ibs = -1; ++ ibe = -1; ++ unhashed = !!d_unhashed(dentry); ++ is_root = !!IS_ROOT(dentry); ++ name = &dentry->d_name; ++ ++ /* ++ * Theoretically, REVAL test should be unnecessary in case of INOTIFY. ++ * But inotify doesn't fire some necessary events, ++ * IN_ATTRIB for atime/nlink/pageio ++ * IN_DELETE for NFS dentry ++ * Let's do REVAL test too. ++ */ ++ if (do_udba && inode) { ++ mode = (inode->i_mode & S_IFMT); ++ plus = (inode->i_nlink > 0); ++ first = au_h_iptr(inode, au_ibstart(inode)); ++ ibs = au_ibstart(inode); ++ ibe = au_ibend(inode); ++ } ++ ++ bstart = au_dbstart(dentry); ++ btail = bstart; ++ if (inode && S_ISDIR(inode->i_mode)) ++ btail = au_dbtaildir(dentry); ++ for (bindex = bstart; bindex <= btail; bindex++) { ++ h_dentry = au_h_dptr(dentry, bindex); ++ if (!h_dentry) ++ continue; ++ ++ AuDbg("b%d, %.*s\n", bindex, AuDLNPair(h_dentry)); ++ h_name = &h_dentry->d_name; ++ if (unlikely(do_udba ++ && !is_root ++ && (unhashed != !!d_unhashed(h_dentry) ++ || name->len != h_name->len ++ || memcmp(name->name, h_name->name, name->len)) ++ )) { ++ AuDbg("unhash 0x%x 0x%x, %.*s %.*s\n", ++ unhashed, d_unhashed(h_dentry), ++ AuDLNPair(dentry), AuDLNPair(h_dentry)); ++ goto err; ++ } ++ ++ err = au_do_h_d_reval(h_dentry, nd, dentry, bindex); ++ if (unlikely(err)) ++ /* do not goto err, to keep the errno */ ++ break; ++ ++ /* todo: plink too? */ ++ if (!do_udba) ++ continue; ++ ++ /* UDBA tests */ ++ h_inode = h_dentry->d_inode; ++ if (unlikely(!!inode != !!h_inode)) ++ goto err; ++ ++ h_plus = plus; ++ h_mode = mode; ++ h_cached_inode = h_inode; ++ if (h_inode) { ++ h_mode = (h_inode->i_mode & S_IFMT); ++ h_plus = (h_inode->i_nlink > 0); ++ } ++ if (inode && ibs <= bindex && bindex <= ibe) ++ h_cached_inode = au_h_iptr(inode, bindex); ++ ++ if (unlikely(plus != h_plus ++ || mode != h_mode ++ || h_cached_inode != h_inode)) ++ goto err; ++ continue; ++ ++ err: ++ err = -EINVAL; ++ break; ++ } ++ ++ return err; ++} ++ ++static int simple_reval_dpath(struct dentry *dentry, unsigned int sigen) ++{ ++ int err; ++ struct dentry *parent; ++ struct inode *inode; ++ ++ inode = dentry->d_inode; ++ if (au_digen(dentry) == sigen && au_iigen(inode) == sigen) ++ return 0; ++ ++ parent = dget_parent(dentry); ++ di_read_lock_parent(parent, AuLock_IR); ++ AuDebugOn(au_digen(parent) != sigen ++ || au_iigen(parent->d_inode) != sigen); ++ au_dbg_verify_gen(parent, sigen); ++ ++ /* returns a number of positive dentries */ ++ err = au_refresh_hdentry(dentry, inode->i_mode & S_IFMT); ++ if (err >= 0) ++ err = au_refresh_hinode(inode, dentry); ++ ++ di_read_unlock(parent, AuLock_IR); ++ dput(parent); ++ return err; ++} ++ ++int au_reval_dpath(struct dentry *dentry, unsigned int sigen) ++{ ++ int err; ++ struct dentry *d, *parent; ++ struct inode *inode; ++ ++ if (!au_ftest_si(au_sbi(dentry->d_sb), FAILED_REFRESH_DIRS)) ++ return simple_reval_dpath(dentry, sigen); ++ ++ /* slow loop, keep it simple and stupid */ ++ /* cf: au_cpup_dirs() */ ++ err = 0; ++ parent = NULL; ++ while (au_digen(dentry) != sigen ++ || au_iigen(dentry->d_inode) != sigen) { ++ d = dentry; ++ while (1) { ++ dput(parent); ++ parent = dget_parent(d); ++ if (au_digen(parent) == sigen ++ && au_iigen(parent->d_inode) == sigen) ++ break; ++ d = parent; ++ } ++ ++ inode = d->d_inode; ++ if (d != dentry) ++ di_write_lock_child(d); ++ ++ /* someone might update our dentry while we were sleeping */ ++ if (au_digen(d) != sigen || au_iigen(d->d_inode) != sigen) { ++ di_read_lock_parent(parent, AuLock_IR); ++ /* returns a number of positive dentries */ ++ err = au_refresh_hdentry(d, inode->i_mode & S_IFMT); ++ if (err >= 0) ++ err = au_refresh_hinode(inode, d); ++ di_read_unlock(parent, AuLock_IR); ++ } ++ ++ if (d != dentry) ++ di_write_unlock(d); ++ dput(parent); ++ if (unlikely(err)) ++ break; ++ } ++ ++ return err; ++} ++ ++/* ++ * if valid returns 1, otherwise 0. ++ */ ++static int aufs_d_revalidate(struct dentry *dentry, struct nameidata *nd) ++{ ++ int valid, err; ++ unsigned int sigen; ++ unsigned char do_udba; ++ struct super_block *sb; ++ struct inode *inode; ++ ++ err = -EINVAL; ++ sb = dentry->d_sb; ++ inode = dentry->d_inode; ++ aufs_read_lock(dentry, AuLock_FLUSH | AuLock_DW); ++ sigen = au_sigen(sb); ++ if (au_digen(dentry) != sigen) { ++ AuDebugOn(IS_ROOT(dentry)); ++ if (inode) ++ err = au_reval_dpath(dentry, sigen); ++ if (unlikely(err)) ++ goto out_dgrade; ++ AuDebugOn(au_digen(dentry) != sigen); ++ } ++ if (inode && au_iigen(inode) != sigen) { ++ AuDebugOn(IS_ROOT(dentry)); ++ err = au_refresh_hinode(inode, dentry); ++ if (unlikely(err)) ++ goto out_dgrade; ++ AuDebugOn(au_iigen(inode) != sigen); ++ } ++ di_downgrade_lock(dentry, AuLock_IR); ++ ++ AuDebugOn(au_digen(dentry) != sigen); ++ AuDebugOn(inode && au_iigen(inode) != sigen); ++ err = -EINVAL; ++ do_udba = !au_opt_test(au_mntflags(sb), UDBA_NONE); ++ if (do_udba && inode) { ++ aufs_bindex_t bstart = au_ibstart(inode); ++ ++ if (bstart >= 0 ++ && au_test_higen(inode, au_h_iptr(inode, bstart))) ++ goto out; ++ } ++ ++ err = h_d_revalidate(dentry, inode, nd, do_udba); ++ if (unlikely(!err && do_udba && au_dbstart(dentry) < 0)) ++ /* both of real entry and whiteout found */ ++ err = -EIO; ++ goto out; ++ ++ out_dgrade: ++ di_downgrade_lock(dentry, AuLock_IR); ++ out: ++ au_store_oflag(nd, inode); ++ aufs_read_unlock(dentry, AuLock_IR); ++ AuTraceErr(err); ++ valid = !err; ++ if (!valid) ++ AuDbg("%.*s invalid\n", AuDLNPair(dentry)); ++ return valid; ++} ++ ++static void aufs_d_release(struct dentry *dentry) ++{ ++ struct au_dinfo *dinfo; ++ aufs_bindex_t bend, bindex; ++ ++ dinfo = dentry->d_fsdata; ++ if (!dinfo) ++ return; ++ ++ /* dentry may not be revalidated */ ++ bindex = dinfo->di_bstart; ++ if (bindex >= 0) { ++ struct au_hdentry *p; ++ ++ bend = dinfo->di_bend; ++ p = dinfo->di_hdentry + bindex; ++ while (bindex++ <= bend) { ++ if (p->hd_dentry) ++ au_hdput(p); ++ p++; ++ } ++ } ++ kfree(dinfo->di_hdentry); ++ au_rwsem_destroy(&dinfo->di_rwsem); ++ au_cache_free_dinfo(dinfo); ++ au_hin_di_reinit(dentry); ++} ++ ++struct dentry_operations aufs_dop = { ++ .d_revalidate = aufs_d_revalidate, ++ .d_release = aufs_d_release ++}; +diff -urN ./fs/aufs/dentry.h ./fs/aufs/dentry.h +--- ./fs/aufs/dentry.h 1970-01-01 01:00:00.000000000 +0100 ++++ ./fs/aufs/dentry.h 2009-04-06 10:26:46.000000000 +0200 +@@ -0,0 +1,213 @@ ++/* ++ * Copyright (C) 2005-2009 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. ++ */ ++ ++/* ++ * lookup and dentry operations ++ */ ++ ++#ifndef __AUFS_DENTRY_H__ ++#define __AUFS_DENTRY_H__ ++ ++#ifdef __KERNEL__ ++ ++#include <linux/fs.h> ++#include <linux/namei.h> ++#include <linux/aufs_type.h> ++#include "rwsem.h" ++ ++/* make a single member structure for future use */ ++/* todo: remove this structure */ ++struct au_hdentry { ++ struct dentry *hd_dentry; ++}; ++ ++struct au_dinfo { ++ atomic_t di_generation; ++ ++ struct rw_semaphore di_rwsem; ++ aufs_bindex_t di_bstart, di_bend, di_bwh, di_bdiropq; ++ struct au_hdentry *di_hdentry; ++}; ++ ++/* ---------------------------------------------------------------------- */ ++ ++/* dentry.c */ ++extern struct dentry_operations aufs_dop; ++struct au_branch; ++struct dentry *au_lkup_one(struct qstr *name, struct dentry *h_parent, ++ struct au_branch *br, struct nameidata *nd); ++struct dentry *au_sio_lkup_one(struct qstr *name, struct dentry *parent, ++ struct au_branch *br); ++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 bstart, mode_t type, ++ struct nameidata *nd); ++int au_lkup_neg(struct dentry *dentry, aufs_bindex_t bindex); ++int au_refresh_hdentry(struct dentry *dentry, mode_t type); ++int au_reval_dpath(struct dentry *dentry, unsigned int sigen); ++ ++/* dinfo.c */ ++int au_alloc_dinfo(struct dentry *dentry); ++int au_di_realloc(struct au_dinfo *dinfo, int nbr); ++ ++void di_read_lock(struct dentry *d, int flags, unsigned int lsc); ++void di_read_unlock(struct dentry *d, int flags); ++void di_downgrade_lock(struct dentry *d, int flags); ++void di_write_lock(struct dentry *d, unsigned int lsc); ++void di_write_unlock(struct dentry *d); ++void di_write_lock2_child(struct dentry *d1, struct dentry *d2, int isdir); ++void di_write_lock2_parent(struct dentry *d1, struct dentry *d2, int isdir); ++void di_write_unlock2(struct dentry *d1, struct dentry *d2); ++ ++struct dentry *au_h_dptr(struct dentry *dentry, aufs_bindex_t bindex); ++aufs_bindex_t au_dbtail(struct dentry *dentry); ++aufs_bindex_t au_dbtaildir(struct dentry *dentry); ++ ++void au_set_h_dptr(struct dentry *dentry, aufs_bindex_t bindex, ++ struct dentry *h_dentry); ++void au_update_digen(struct dentry *dentry); ++void au_update_dbrange(struct dentry *dentry, int do_put_zero); ++void au_update_dbstart(struct dentry *dentry); ++void au_update_dbend(struct dentry *dentry); ++int au_find_dbindex(struct dentry *dentry, struct dentry *h_dentry); ++ ++/* ---------------------------------------------------------------------- */ ++ ++static inline struct au_dinfo *au_di(struct dentry *dentry) ++{ ++ return dentry->d_fsdata; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++/* lock subclass for dinfo */ ++enum { ++ AuLsc_DI_CHILD, /* child first */ ++ AuLsc_DI_CHILD2, /* rename(2), link(2), and cpup at hinotify */ ++ AuLsc_DI_CHILD3, /* copyup dirs */ ++ AuLsc_DI_PARENT, ++ AuLsc_DI_PARENT2, ++ AuLsc_DI_PARENT3 ++}; ++ ++/* ++ * di_read_lock_child, di_write_lock_child, ++ * di_read_lock_child2, di_write_lock_child2, ++ * di_read_lock_child3, di_write_lock_child3, ++ * di_read_lock_parent, di_write_lock_parent, ++ * di_read_lock_parent2, di_write_lock_parent2, ++ * di_read_lock_parent3, di_write_lock_parent3, ++ */ ++#define AuReadLockFunc(name, lsc) \ ++static inline void di_read_lock_##name(struct dentry *d, int flags) \ ++{ di_read_lock(d, flags, AuLsc_DI_##lsc); } ++ ++#define AuWriteLockFunc(name, lsc) \ ++static inline void di_write_lock_##name(struct dentry *d) \ ++{ di_write_lock(d, AuLsc_DI_##lsc); } ++ ++#define AuRWLockFuncs(name, lsc) \ ++ AuReadLockFunc(name, lsc) \ ++ AuWriteLockFunc(name, lsc) ++ ++AuRWLockFuncs(child, CHILD); ++AuRWLockFuncs(child2, CHILD2); ++AuRWLockFuncs(child3, CHILD3); ++AuRWLockFuncs(parent, PARENT); ++AuRWLockFuncs(parent2, PARENT2); ++AuRWLockFuncs(parent3, PARENT3); ++ ++#undef AuReadLockFunc ++#undef AuWriteLockFunc ++#undef AuRWLockFuncs ++ ++#define DiMustNoWaiters(d) AuRwMustNoWaiters(&au_di(d)->di_rwsem) ++ ++/* ---------------------------------------------------------------------- */ ++ ++/* 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 void au_hdput(struct au_hdentry *hd) ++{ ++ dput(hd->hd_dentry); ++} ++ ++static inline aufs_bindex_t au_dbstart(struct dentry *dentry) ++{ ++ return au_di(dentry)->di_bstart; ++} ++ ++static inline aufs_bindex_t au_dbend(struct dentry *dentry) ++{ ++ return au_di(dentry)->di_bend; ++} ++ ++static inline aufs_bindex_t au_dbwh(struct dentry *dentry) ++{ ++ return au_di(dentry)->di_bwh; ++} ++ ++static inline aufs_bindex_t au_dbdiropq(struct dentry *dentry) ++{ ++ return au_di(dentry)->di_bdiropq; ++} ++ ++/* todo: hard/soft set? */ ++static inline void au_set_dbstart(struct dentry *dentry, aufs_bindex_t bindex) ++{ ++ au_di(dentry)->di_bstart = bindex; ++} ++ ++static inline void au_set_dbend(struct dentry *dentry, aufs_bindex_t bindex) ++{ ++ au_di(dentry)->di_bend = bindex; ++} ++ ++static inline void au_set_dbwh(struct dentry *dentry, aufs_bindex_t bindex) ++{ ++ /* dbwh can be outside of bstart - bend range */ ++ au_di(dentry)->di_bwh = bindex; ++} ++ ++static inline void au_set_dbdiropq(struct dentry *dentry, aufs_bindex_t bindex) ++{ ++ au_di(dentry)->di_bdiropq = bindex; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++#ifdef CONFIG_AUFS_HINOTIFY ++static inline void au_digen_dec(struct dentry *d) ++{ ++ atomic_dec(&au_di(d)->di_generation); ++} ++ ++static inline void au_hin_di_reinit(struct dentry *dentry) ++{ ++ dentry->d_fsdata = NULL; ++} ++#else ++static inline void au_hin_di_reinit(struct dentry *dentry __maybe_unused) ++{ ++ /* empty */ ++} ++#endif /* CONFIG_AUFS_HINOTIFY */ ++ ++#endif /* __KERNEL__ */ ++#endif /* __AUFS_DENTRY_H__ */ +diff -urN ./fs/aufs/dinfo.c ./fs/aufs/dinfo.c +--- ./fs/aufs/dinfo.c 1970-01-01 01:00:00.000000000 +0100 ++++ ./fs/aufs/dinfo.c 2009-04-06 10:26:46.000000000 +0200 +@@ -0,0 +1,351 @@ ++/* ++ * Copyright (C) 2005-2009 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. ++ */ ++ ++/* ++ * dentry private data ++ */ ++ ++#include "aufs.h" ++ ++int au_alloc_dinfo(struct dentry *dentry) ++{ ++ struct au_dinfo *dinfo; ++ struct super_block *sb; ++ int nbr; ++ ++ dinfo = au_cache_alloc_dinfo(); ++ if (unlikely(!dinfo)) ++ goto out; ++ ++ sb = dentry->d_sb; ++ nbr = au_sbend(sb) + 1; ++ if (nbr <= 0) ++ nbr = 1; ++ dinfo->di_hdentry = kcalloc(nbr, sizeof(*dinfo->di_hdentry), GFP_NOFS); ++ if (unlikely(!dinfo->di_hdentry)) ++ goto out_dinfo; ++ ++ atomic_set(&dinfo->di_generation, au_sigen(sb)); ++ /* smp_mb(); */ /* atomic_set */ ++ init_rwsem(&dinfo->di_rwsem); ++ down_write_nested(&dinfo->di_rwsem, AuLsc_DI_CHILD); ++ dinfo->di_bstart = -1; ++ dinfo->di_bend = -1; ++ dinfo->di_bwh = -1; ++ dinfo->di_bdiropq = -1; ++ ++ dentry->d_fsdata = dinfo; ++ dentry->d_op = &aufs_dop; ++ return 0; /* success */ ++ ++ out_dinfo: ++ au_cache_free_dinfo(dinfo); ++ out: ++ return -ENOMEM; ++} ++ ++int au_di_realloc(struct au_dinfo *dinfo, int nbr) ++{ ++ int err, sz; ++ struct au_hdentry *hdp; ++ ++ err = -ENOMEM; ++ sz = sizeof(*hdp) * (dinfo->di_bend + 1); ++ if (!sz) ++ sz = sizeof(*hdp); ++ hdp = au_kzrealloc(dinfo->di_hdentry, sz, sizeof(*hdp) * nbr, GFP_NOFS); ++ if (hdp) { ++ dinfo->di_hdentry = hdp; ++ err = 0; ++ } ++ ++ return err; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++static void do_ii_write_lock(struct inode *inode, unsigned int lsc) ++{ ++ switch (lsc) { ++ case AuLsc_DI_CHILD: ++ ii_write_lock_child(inode); ++ break; ++ case AuLsc_DI_CHILD2: ++ ii_write_lock_child2(inode); ++ break; ++ case AuLsc_DI_CHILD3: ++ ii_write_lock_child3(inode); ++ break; ++ case AuLsc_DI_PARENT: ++ ii_write_lock_parent(inode); ++ break; ++ case AuLsc_DI_PARENT2: ++ ii_write_lock_parent2(inode); ++ break; ++ case AuLsc_DI_PARENT3: ++ ii_write_lock_parent3(inode); ++ break; ++ default: ++ BUG(); ++ } ++} ++ ++static void do_ii_read_lock(struct inode *inode, unsigned int lsc) ++{ ++ switch (lsc) { ++ case AuLsc_DI_CHILD: ++ ii_read_lock_child(inode); ++ break; ++ case AuLsc_DI_CHILD2: ++ ii_read_lock_child2(inode); ++ break; ++ case AuLsc_DI_CHILD3: ++ ii_read_lock_child3(inode); ++ break; ++ case AuLsc_DI_PARENT: ++ ii_read_lock_parent(inode); ++ break; ++ case AuLsc_DI_PARENT2: ++ ii_read_lock_parent2(inode); ++ break; ++ case AuLsc_DI_PARENT3: ++ ii_read_lock_parent3(inode); ++ break; ++ default: ++ BUG(); ++ } ++} ++ ++void di_read_lock(struct dentry *d, int flags, unsigned int lsc) ++{ ++ down_read_nested(&au_di(d)->di_rwsem, lsc); ++ if (d->d_inode) { ++ if (au_ftest_lock(flags, IW)) ++ do_ii_write_lock(d->d_inode, lsc); ++ else if (au_ftest_lock(flags, IR)) ++ do_ii_read_lock(d->d_inode, lsc); ++ } ++} ++ ++void di_read_unlock(struct dentry *d, int flags) ++{ ++ if (d->d_inode) { ++ if (au_ftest_lock(flags, IW)) ++ ii_write_unlock(d->d_inode); ++ else if (au_ftest_lock(flags, IR)) ++ ii_read_unlock(d->d_inode); ++ } ++ up_read(&au_di(d)->di_rwsem); ++} ++ ++void di_downgrade_lock(struct dentry *d, int flags) ++{ ++ downgrade_write(&au_di(d)->di_rwsem); ++ if (d->d_inode && au_ftest_lock(flags, IR)) ++ ii_downgrade_lock(d->d_inode); ++} ++ ++void di_write_lock(struct dentry *d, unsigned int lsc) ++{ ++ down_write_nested(&au_di(d)->di_rwsem, lsc); ++ if (d->d_inode) ++ do_ii_write_lock(d->d_inode, lsc); ++} ++ ++void di_write_unlock(struct dentry *d) ++{ ++ if (d->d_inode) ++ ii_write_unlock(d->d_inode); ++ up_write(&au_di(d)->di_rwsem); ++} ++ ++void di_write_lock2_child(struct dentry *d1, struct dentry *d2, int isdir) ++{ ++ AuDebugOn(d1 == d2 ++ || d1->d_inode == d2->d_inode ++ || d1->d_sb != d2->d_sb); ++ ++ 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); ++ } ++} ++ ++void di_write_lock2_parent(struct dentry *d1, struct dentry *d2, int isdir) ++{ ++ AuDebugOn(d1 == d2 ++ || d1->d_inode == d2->d_inode ++ || d1->d_sb != d2->d_sb); ++ ++ 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); ++ } ++} ++ ++void di_write_unlock2(struct dentry *d1, struct dentry *d2) ++{ ++ di_write_unlock(d1); ++ if (d1->d_inode == d2->d_inode) ++ up_write(&au_di(d2)->di_rwsem); ++ else ++ di_write_unlock(d2); ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++struct dentry *au_h_dptr(struct dentry *dentry, aufs_bindex_t bindex) ++{ ++ struct dentry *d; ++ ++ if (au_dbstart(dentry) < 0 || bindex < au_dbstart(dentry)) ++ return NULL; ++ AuDebugOn(bindex < 0); ++ d = au_di(dentry)->di_hdentry[0 + bindex].hd_dentry; ++ AuDebugOn(d && (atomic_read(&d->d_count) <= 0)); ++ return d; ++} ++ ++aufs_bindex_t au_dbtail(struct dentry *dentry) ++{ ++ aufs_bindex_t bend, bwh; ++ ++ bend = au_dbend(dentry); ++ if (0 <= bend) { ++ bwh = au_dbwh(dentry); ++ if (!bwh) ++ return bwh; ++ if (0 < bwh && bwh < bend) ++ return bwh - 1; ++ } ++ return bend; ++} ++ ++aufs_bindex_t au_dbtaildir(struct dentry *dentry) ++{ ++ aufs_bindex_t bend, bopq; ++ ++ bend = au_dbtail(dentry); ++ if (0 <= bend) { ++ bopq = au_dbdiropq(dentry); ++ if (0 <= bopq && bopq < bend) ++ bend = bopq; ++ } ++ return bend; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++void au_set_h_dptr(struct dentry *dentry, aufs_bindex_t bindex, ++ struct dentry *h_dentry) ++{ ++ struct au_hdentry *hd = au_di(dentry)->di_hdentry + bindex; ++ ++ if (hd->hd_dentry) ++ au_hdput(hd); ++ hd->hd_dentry = h_dentry; ++} ++ ++void au_update_digen(struct dentry *dentry) ++{ ++ atomic_set(&au_di(dentry)->di_generation, au_sigen(dentry->d_sb)); ++ /* smp_mb(); */ /* atomic_set */ ++} ++ ++void au_update_dbrange(struct dentry *dentry, int do_put_zero) ++{ ++ struct au_dinfo *dinfo; ++ struct dentry *h_d; ++ ++ dinfo = au_di(dentry); ++ if (!dinfo || dinfo->di_bstart < 0) ++ return; ++ ++ if (do_put_zero) { ++ aufs_bindex_t bindex, bend; ++ ++ bend = dinfo->di_bend; ++ for (bindex = dinfo->di_bstart; bindex <= bend; bindex++) { ++ h_d = dinfo->di_hdentry[0 + bindex].hd_dentry; ++ if (h_d && !h_d->d_inode) ++ au_set_h_dptr(dentry, bindex, NULL); ++ } ++ } ++ ++ dinfo->di_bstart = -1; ++ while (++dinfo->di_bstart <= dinfo->di_bend) ++ if (dinfo->di_hdentry[0 + dinfo->di_bstart].hd_dentry) ++ break; ++ if (dinfo->di_bstart > dinfo->di_bend) { ++ dinfo->di_bstart = -1; ++ dinfo->di_bend = -1; ++ return; ++ } ++ ++ dinfo->di_bend++; ++ while (0 <= --dinfo->di_bend) ++ if (dinfo->di_hdentry[0 + dinfo->di_bend].hd_dentry) ++ break; ++ AuDebugOn(dinfo->di_bstart > dinfo->di_bend || dinfo->di_bend < 0); ++} ++ ++void au_update_dbstart(struct dentry *dentry) ++{ ++ aufs_bindex_t bindex, bend; ++ struct dentry *h_dentry; ++ ++ bend = au_dbend(dentry); ++ for (bindex = au_dbstart(dentry); bindex <= bend; bindex++) { ++ h_dentry = au_h_dptr(dentry, bindex); ++ if (!h_dentry) ++ continue; ++ if (h_dentry->d_inode) { ++ au_set_dbstart(dentry, bindex); ++ return; ++ } ++ au_set_h_dptr(dentry, bindex, NULL); ++ } ++} ++ ++void au_update_dbend(struct dentry *dentry) ++{ ++ aufs_bindex_t bindex, bstart; ++ struct dentry *h_dentry; ++ ++ bstart = au_dbstart(dentry); ++ for (bindex = au_dbend(dentry); bindex <= bstart; bindex--) { ++ h_dentry = au_h_dptr(dentry, bindex); ++ if (!h_dentry) ++ continue; ++ if (h_dentry->d_inode) { ++ au_set_dbend(dentry, bindex); ++ return; ++ } ++ au_set_h_dptr(dentry, bindex, NULL); ++ } ++} ++ ++int au_find_dbindex(struct dentry *dentry, struct dentry *h_dentry) ++{ ++ aufs_bindex_t bindex, bend; ++ ++ bend = au_dbend(dentry); ++ for (bindex = au_dbstart(dentry); bindex <= bend; bindex++) ++ if (au_h_dptr(dentry, bindex) == h_dentry) ++ return bindex; ++ return -1; ++} +diff -urN ./fs/aufs/dir.c ./fs/aufs/dir.c +--- ./fs/aufs/dir.c 1970-01-01 01:00:00.000000000 +0100 ++++ ./fs/aufs/dir.c 2009-04-06 10:26:46.000000000 +0200 +@@ -0,0 +1,513 @@ ++/* ++ * Copyright (C) 2005-2009 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. ++ */ ++ ++/* ++ * directory operations ++ */ ++ ++#include <linux/fs_stack.h> ++#include "aufs.h" ++ ++void au_add_nlink(struct inode *dir, struct inode *h_dir) ++{ ++ AuDebugOn(!S_ISDIR(dir->i_mode) || !S_ISDIR(h_dir->i_mode)); ++ ++ dir->i_nlink += h_dir->i_nlink - 2; ++ if (h_dir->i_nlink < 2) ++ dir->i_nlink += 2; ++} ++ ++void au_sub_nlink(struct inode *dir, struct inode *h_dir) ++{ ++ AuDebugOn(!S_ISDIR(dir->i_mode) || !S_ISDIR(h_dir->i_mode)); ++ ++ dir->i_nlink -= h_dir->i_nlink - 2; ++ if (h_dir->i_nlink < 2) ++ dir->i_nlink -= 2; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++static int reopen_dir(struct file *file) ++{ ++ int err; ++ unsigned int flags; ++ aufs_bindex_t bindex, btail, bstart; ++ struct dentry *dentry, *h_dentry; ++ struct file *h_file; ++ ++ /* open all lower dirs */ ++ dentry = file->f_dentry; ++ bstart = au_dbstart(dentry); ++ for (bindex = au_fbstart(file); bindex < bstart; bindex++) ++ au_set_h_fptr(file, bindex, NULL); ++ au_set_fbstart(file, bstart); ++ ++ btail = au_dbtaildir(dentry); ++ for (bindex = au_fbend(file); btail < bindex; bindex--) ++ au_set_h_fptr(file, bindex, NULL); ++ au_set_fbend(file, btail); ++ ++ flags = file->f_flags; ++ for (bindex = bstart; bindex <= btail; bindex++) { ++ h_dentry = au_h_dptr(dentry, bindex); ++ if (!h_dentry) ++ continue; ++ h_file = au_h_fptr(file, bindex); ++ if (h_file) ++ continue; ++ ++ h_file = au_h_open(dentry, bindex, flags, file); ++ err = PTR_ERR(h_file); ++ if (IS_ERR(h_file)) ++ goto out; /* close all? */ ++ au_set_h_fptr(file, bindex, h_file); ++ } ++ au_update_figen(file); ++ /* todo: necessary? */ ++ /* file->f_ra = h_file->f_ra; */ ++ err = 0; ++ ++ out: ++ return err; ++} ++ ++static int do_open_dir(struct file *file, int flags) ++{ ++ int err; ++ aufs_bindex_t bindex, btail; ++ struct dentry *dentry, *h_dentry; ++ struct file *h_file; ++ ++ err = 0; ++ dentry = file->f_dentry; ++ au_set_fvdir_cache(file, NULL); ++ au_fi(file)->fi_maintain_plink = 0; ++ file->f_version = dentry->d_inode->i_version; ++ bindex = au_dbstart(dentry); ++ au_set_fbstart(file, bindex); ++ btail = au_dbtaildir(dentry); ++ au_set_fbend(file, btail); ++ for (; !err && bindex <= btail; bindex++) { ++ h_dentry = au_h_dptr(dentry, bindex); ++ if (!h_dentry) ++ continue; ++ ++ h_file = au_h_open(dentry, bindex, flags, file); ++ 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_fbstart(file); bindex <= btail; bindex++) ++ au_set_h_fptr(file, bindex, NULL); ++ au_set_fbstart(file, -1); ++ au_set_fbend(file, -1); ++ return err; ++} ++ ++static int aufs_open_dir(struct inode *inode __maybe_unused, ++ struct file *file) ++{ ++ return au_do_open(file, do_open_dir); ++} ++ ++static int aufs_release_dir(struct inode *inode __maybe_unused, ++ struct file *file) ++{ ++ struct au_vdir *vdir_cache; ++ struct super_block *sb; ++ struct au_sbinfo *sbinfo; ++ ++ sb = file->f_dentry->d_sb; ++ si_noflush_read_lock(sb); ++ fi_write_lock(file); ++ vdir_cache = au_fvdir_cache(file); ++ if (vdir_cache) ++ au_vdir_free(vdir_cache); ++ if (au_fi(file)->fi_maintain_plink) { ++ sbinfo = au_sbi(sb); ++ au_fclr_si(sbinfo, MAINTAIN_PLINK); ++ wake_up_all(&sbinfo->si_plink_wq); ++ } ++ fi_write_unlock(file); ++ au_finfo_fin(file); ++ si_read_unlock(sb); ++ return 0; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++static int au_do_fsync_dir_no_file(struct dentry *dentry, int datasync) ++{ ++ int err; ++ aufs_bindex_t bend, bindex; ++ struct inode *inode; ++ struct super_block *sb; ++ ++ err = 0; ++ sb = dentry->d_sb; ++ inode = dentry->d_inode; ++ IMustLock(inode); ++ bend = au_dbend(dentry); ++ for (bindex = au_dbstart(dentry); !err && bindex <= bend; bindex++) { ++ struct path h_path; ++ struct inode *h_inode; ++ ++ if (au_test_ro(sb, bindex, inode)) ++ continue; ++ h_path.dentry = au_h_dptr(dentry, bindex); ++ if (!h_path.dentry) ++ continue; ++ h_inode = h_path.dentry->d_inode; ++ if (!h_inode) ++ continue; ++ ++ /* no mnt_want_write() */ ++ /* cf. fs/nsfd/vfs.c and fs/nfsd/nfs4recover.c */ ++ /* todo: inotiry fired? */ ++ h_path.mnt = au_sbr_mnt(sb, bindex); ++ mutex_lock(&h_inode->i_mutex); ++ err = filemap_fdatawrite(h_inode->i_mapping); ++ AuDebugOn(!h_inode->i_fop); ++ if (!err && h_inode->i_fop->fsync) ++ err = h_inode->i_fop->fsync(NULL, h_path.dentry, ++ datasync); ++ if (!err) ++ err = filemap_fdatawrite(h_inode->i_mapping); ++ if (!err) ++ vfsub_update_h_iattr(&h_path, /*did*/NULL); /*ignore*/ ++ mutex_unlock(&h_inode->i_mutex); ++ } ++ ++ return err; ++} ++ ++static int au_do_fsync_dir(struct file *file, int datasync) ++{ ++ int err; ++ aufs_bindex_t bend, bindex; ++ struct file *h_file; ++ struct super_block *sb; ++ struct inode *inode; ++ struct mutex *h_mtx; ++ ++ err = au_reval_and_lock_fdi(file, reopen_dir, /*wlock*/1); ++ if (unlikely(err)) ++ goto out; ++ ++ sb = file->f_dentry->d_sb; ++ inode = file->f_dentry->d_inode; ++ bend = au_fbend(file); ++ for (bindex = au_fbstart(file); !err && bindex <= bend; bindex++) { ++ h_file = au_h_fptr(file, bindex); ++ if (!h_file || au_test_ro(sb, bindex, inode)) ++ continue; ++ ++ err = vfs_fsync(h_file, h_file->f_dentry, datasync); ++ if (!err) { ++ h_mtx = &h_file->f_dentry->d_inode->i_mutex; ++ mutex_lock(h_mtx); ++ vfsub_update_h_iattr(&h_file->f_path, /*did*/NULL); ++ /*ignore*/ ++ mutex_unlock(h_mtx); ++ } ++ } ++ ++ out: ++ return err; ++} ++ ++/* ++ * @file may be NULL ++ */ ++static int aufs_fsync_dir(struct file *file, struct dentry *dentry, ++ int datasync) ++{ ++ int err; ++ struct super_block *sb; ++ ++ IMustLock(dentry->d_inode); ++ ++ err = 0; ++ 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(dentry->d_inode); ++ di_write_unlock(dentry); ++ if (file) ++ fi_write_unlock(file); ++ ++ si_read_unlock(sb); ++ return err; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++static int aufs_readdir(struct file *file, void *dirent, filldir_t filldir) ++{ ++ int err; ++ struct dentry *dentry; ++ struct inode *inode; ++ struct super_block *sb; ++ ++ dentry = file->f_dentry; ++ inode = dentry->d_inode; ++ IMustLock(inode); ++ ++ 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_vdir_init(file); ++ di_downgrade_lock(dentry, AuLock_IR); ++ if (unlikely(err)) ++ goto out_unlock; ++ ++ if (!au_test_nfsd(current)) { ++ err = au_vdir_fill_de(file, dirent, filldir); ++ fsstack_copy_attr_atime(inode, ++ au_h_iptr(inode, au_ibstart(inode))); ++ } else { ++ /* ++ * nfsd filldir may call lookup_one_len(), vfs_getattr(), ++ * encode_fh() and others. ++ */ ++ struct inode *h_inode = au_h_iptr(inode, au_ibstart(inode)); ++ ++ di_read_unlock(dentry, AuLock_IR); ++ si_read_unlock(sb); ++ lockdep_off(); ++ err = au_vdir_fill_de(file, dirent, filldir); ++ lockdep_on(); ++ fsstack_copy_attr_atime(inode, h_inode); ++ fi_write_unlock(file); ++ ++ AuTraceErr(err); ++ return err; ++ } ++ ++ out_unlock: ++ di_read_unlock(dentry, AuLock_IR); ++ fi_write_unlock(file); ++ out: ++ si_read_unlock(sb); ++ return err; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++#define AuTestEmpty_WHONLY 1 ++#define AuTestEmpty_CALLED (1 << 2) ++#define au_ftest_testempty(flags, name) ((flags) & AuTestEmpty_##name) ++#define au_fset_testempty(flags, name) { (flags) |= AuTestEmpty_##name; } ++#define au_fclr_testempty(flags, name) { (flags) &= ~AuTestEmpty_##name; } ++ ++struct test_empty_arg { ++ struct au_nhash *whlist; ++ unsigned int flags; ++ int err; ++ aufs_bindex_t bindex; ++}; ++ ++static int test_empty_cb(void *__arg, const char *__name, int namelen, ++ loff_t offset __maybe_unused, u64 ino __maybe_unused, ++ unsigned int d_type __maybe_unused) ++{ ++ struct test_empty_arg *arg = __arg; ++ 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, arg->bindex); ++ ++ out: ++ /* smp_mb(); */ ++ AuTraceErr(arg->err); ++ return arg->err; ++} ++ ++static int do_test_empty(struct dentry *dentry, struct test_empty_arg *arg) ++{ ++ int err; ++ struct file *h_file; ++ ++ h_file = au_h_open(dentry, arg->bindex, ++ O_RDONLY | O_NONBLOCK | O_DIRECTORY | O_LARGEFILE, ++ /*file*/NULL); ++ err = PTR_ERR(h_file); ++ if (IS_ERR(h_file)) ++ goto out; ++ ++ err = 0; ++ if (!au_opt_test(au_mntflags(dentry->d_sb), UDBA_NONE) ++ && !h_file->f_dentry->d_inode->i_nlink) ++ goto out_put; ++ ++ do { ++ arg->err = 0; ++ au_fclr_testempty(arg->flags, CALLED); ++ /* smp_mb(); */ ++ err = vfsub_readdir(h_file, test_empty_cb, arg); ++ 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; ++} ++ ++struct do_test_empty_args { ++ int *errp; ++ struct dentry *dentry; ++ struct test_empty_arg *arg; ++}; ++ ++static void call_do_test_empty(void *args) ++{ ++ struct do_test_empty_args *a = args; ++ *a->errp = do_test_empty(a->dentry, a->arg); ++} ++ ++static int sio_test_empty(struct dentry *dentry, struct test_empty_arg *arg) ++{ ++ int err, wkq_err; ++ struct dentry *h_dentry; ++ struct inode *h_inode; ++ ++ h_dentry = au_h_dptr(dentry, arg->bindex); ++ h_inode = h_dentry->d_inode; ++ mutex_lock_nested(&h_inode->i_mutex, AuLsc_I_CHILD); ++ err = au_test_h_perm_sio(h_inode, MAY_EXEC | MAY_READ); ++ mutex_unlock(&h_inode->i_mutex); ++ if (!err) ++ err = do_test_empty(dentry, arg); ++ else { ++ struct do_test_empty_args args = { ++ .errp = &err, ++ .dentry = dentry, ++ .arg = arg ++ }; ++ unsigned int flags = arg->flags; ++ ++ wkq_err = au_wkq_wait(call_do_test_empty, &args); ++ if (unlikely(wkq_err)) ++ err = wkq_err; ++ arg->flags = flags; ++ } ++ ++ return err; ++} ++ ++int au_test_empty_lower(struct dentry *dentry) ++{ ++ int err; ++ aufs_bindex_t bindex, bstart, btail; ++ struct test_empty_arg arg; ++ struct au_nhash *whlist; ++ ++ whlist = au_nhash_new(GFP_NOFS); ++ err = PTR_ERR(whlist); ++ if (IS_ERR(whlist)) ++ goto out; ++ ++ bstart = au_dbstart(dentry); ++ arg.whlist = whlist; ++ arg.flags = 0; ++ arg.bindex = bstart; ++ err = do_test_empty(dentry, &arg); ++ if (unlikely(err)) ++ goto out_whlist; ++ ++ au_fset_testempty(arg.flags, WHONLY); ++ btail = au_dbtaildir(dentry); ++ for (bindex = bstart + 1; !err && bindex <= btail; bindex++) { ++ struct dentry *h_dentry; ++ ++ h_dentry = au_h_dptr(dentry, bindex); ++ if (h_dentry && h_dentry->d_inode) { ++ arg.bindex = bindex; ++ err = do_test_empty(dentry, &arg); ++ } ++ } ++ ++ out_whlist: ++ au_nhash_del(whlist); ++ out: ++ return err; ++} ++ ++int au_test_empty(struct dentry *dentry, struct au_nhash *whlist) ++{ ++ int err; ++ struct test_empty_arg arg; ++ aufs_bindex_t bindex, btail; ++ ++ err = 0; ++ arg.whlist = whlist; ++ arg.flags = AuTestEmpty_WHONLY; ++ btail = au_dbtaildir(dentry); ++ for (bindex = au_dbstart(dentry); !err && bindex <= btail; bindex++) { ++ struct dentry *h_dentry; ++ ++ h_dentry = au_h_dptr(dentry, bindex); ++ if (h_dentry && h_dentry->d_inode) { ++ arg.bindex = bindex; ++ err = sio_test_empty(dentry, &arg); ++ } ++ } ++ ++ return err; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++const struct file_operations aufs_dir_fop = { ++ .read = generic_read_dir, ++ .readdir = aufs_readdir, ++ .unlocked_ioctl = aufs_ioctl_dir, ++ .open = aufs_open_dir, ++ .release = aufs_release_dir, ++ .flush = aufs_flush, ++ .fsync = aufs_fsync_dir ++}; +diff -urN ./fs/aufs/dir.h ./fs/aufs/dir.h +--- ./fs/aufs/dir.h 1970-01-01 01:00:00.000000000 +0100 ++++ ./fs/aufs/dir.h 2009-04-06 10:26:46.000000000 +0200 +@@ -0,0 +1,104 @@ ++/* ++ * Copyright (C) 2005-2009 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. ++ */ ++ ++/* ++ * directory operations ++ */ ++ ++#ifndef __AUFS_DIR_H__ ++#define __AUFS_DIR_H__ ++ ++#ifdef __KERNEL__ ++ ++#include <linux/fs.h> ++#include <linux/aufs_type.h> ++ ++/* ---------------------------------------------------------------------- */ ++ ++/* need to be faster and smaller */ ++ ++#define AuSize_DEBLK 512 ++#define AuSize_NHASH 32 ++ ++typedef char au_vdir_deblk_t[AuSize_DEBLK]; ++ ++struct au_nhash { ++ struct hlist_head heads[AuSize_NHASH]; ++}; ++ ++struct au_vdir_destr { ++ unsigned char len; ++ char name[0]; ++} __packed; ++ ++struct au_vdir_dehstr { ++ struct hlist_node hash; ++ struct au_vdir_destr *str; ++}; ++ ++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; ++ aufs_bindex_t wh_bindex; ++ struct au_vdir_destr wh_str; ++} __packed; ++ ++union au_vdir_deblk_p { ++ unsigned char *p; ++ au_vdir_deblk_t *deblk; ++ struct au_vdir_de *de; ++}; ++ ++struct au_vdir { ++ au_vdir_deblk_t **vd_deblk; ++ int vd_nblk; ++ struct { ++ int i; ++ union au_vdir_deblk_p p; ++ } vd_last; ++ ++ unsigned long vd_version; ++ unsigned long vd_jiffy; ++}; ++ ++/* ---------------------------------------------------------------------- */ ++ ++/* 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); ++int au_test_empty_lower(struct dentry *dentry); ++int au_test_empty(struct dentry *dentry, struct au_nhash *whlist); ++ ++/* vdir.c */ ++struct au_nhash *au_nhash_new(gfp_t gfp); ++void au_nhash_del(struct au_nhash *nhash); ++void au_nhash_init(struct au_nhash *nhash); ++void au_nhash_move(struct au_nhash *dst, struct au_nhash *src); ++void au_nhash_fin(struct au_nhash *nhash); ++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 namelen); ++int au_nhash_append_wh(struct au_nhash *whlist, char *name, int namelen, ++ aufs_bindex_t bindex); ++void au_vdir_free(struct au_vdir *vdir); ++int au_vdir_init(struct file *file); ++int au_vdir_fill_de(struct file *file, void *dirent, filldir_t filldir); ++ ++/* ioctl.c */ ++long aufs_ioctl_dir(struct file *file, unsigned int cmd, unsigned long arg); ++ ++#endif /* __KERNEL__ */ ++#endif /* __AUFS_DIR_H__ */ +diff -urN ./fs/aufs/export.c ./fs/aufs/export.c +--- ./fs/aufs/export.c 1970-01-01 01:00:00.000000000 +0100 ++++ ./fs/aufs/export.c 2009-04-06 10:26:46.000000000 +0200 +@@ -0,0 +1,725 @@ ++/* ++ * Copyright (C) 2005-2009 Junjiro 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. ++ */ ++ ++/* ++ * export via nfs ++ */ ++ ++#include <linux/exportfs.h> ++#include <linux/mnt_namespace.h> ++#include <linux/random.h> ++#include "aufs.h" ++ ++union conv { ++#ifdef CONFIG_AUFS_INO_T_64 ++ __u32 a[2]; ++#else ++ __u32 a[1]; ++#endif ++ ino_t ino; ++}; ++ ++static ino_t decode_ino(__u32 *a) ++{ ++ union conv u; ++ ++ BUILD_BUG_ON(sizeof(u.ino) != sizeof(u.a)); ++ u.a[0] = a[0]; ++#ifdef CONFIG_AUFS_INO_T_64 ++ u.a[1] = a[1]; ++#endif ++ return u.ino; ++} ++ ++static void encode_ino(__u32 *a, ino_t ino) ++{ ++ union conv u; ++ ++ u.ino = ino; ++ a[0] = u.a[0]; ++#ifdef CONFIG_AUFS_INO_T_64 ++ a[1] = u.a[1]; ++#endif ++} ++ ++/* NFS file handle */ ++enum { ++ Fh_br_id, ++ Fh_sigen, ++#ifdef CONFIG_AUFS_INO_T_64 ++ /* support 64bit inode number */ ++ Fh_ino1, ++ Fh_ino2, ++ Fh_dir_ino1, ++ Fh_dir_ino2, ++#else ++ Fh_ino1, ++ Fh_dir_ino1, ++#endif ++ Fh_igen, ++ Fh_h_type, ++ Fh_tail, ++ ++ Fh_ino = Fh_ino1, ++ Fh_dir_ino = Fh_dir_ino1 ++}; ++ ++static int au_test_anon(struct dentry *dentry) ++{ ++ return !!(dentry->d_flags & DCACHE_DISCONNECTED); ++} ++ ++/* ---------------------------------------------------------------------- */ ++/* inode generation external table */ ++ ++int au_xigen_inc(struct inode *inode) ++{ ++ int err; ++ loff_t pos; ++ ssize_t sz; ++ __u32 igen; ++ struct super_block *sb; ++ struct au_sbinfo *sbinfo; ++ ++ err = 0; ++ sb = inode->i_sb; ++ if (unlikely(!au_opt_test(au_mntflags(sb), XINO))) ++ goto out; ++ ++ pos = inode->i_ino; ++ pos *= sizeof(igen); ++ igen = inode->i_generation + 1; ++ sbinfo = au_sbi(sb); ++ sz = xino_fwrite(sbinfo->si_xwrite, sbinfo->si_xigen, &igen, ++ sizeof(igen), &pos); ++ if (sz == sizeof(igen)) ++ goto out; /* success */ ++ ++ err = sz; ++ if (unlikely(sz >= 0)) { ++ err = -EIO; ++ AuIOErr("xigen error (%zd)\n", sz); ++ } ++ ++ out: ++ return err; ++} ++ ++int au_xigen_new(struct inode *inode) ++{ ++ int err; ++ loff_t pos; ++ ssize_t sz; ++ struct super_block *sb; ++ struct au_sbinfo *sbinfo; ++ struct file *file; ++ ++ err = 0; ++ /* todo: dirty, at mount time */ ++ if (inode->i_ino == AUFS_ROOT_INO) ++ goto out; ++ sb = inode->i_sb; ++ if (unlikely(!au_opt_test(au_mntflags(sb), XINO))) ++ goto out; ++ ++ err = -EFBIG; ++ pos = inode->i_ino; ++ if (unlikely(au_loff_max / sizeof(inode->i_generation) - 1 < pos)) { ++ AuIOErr1("too large i%lld\n", pos); ++ goto out; ++ } ++ pos *= sizeof(inode->i_generation); ++ ++ err = 0; ++ sbinfo = au_sbi(sb); ++ file = sbinfo->si_xigen; ++ BUG_ON(!file); ++ ++ if (i_size_read(file->f_dentry->d_inode) ++ < pos + sizeof(inode->i_generation)) { ++ inode->i_generation = atomic_inc_return(&sbinfo->si_xigen_next); ++ sz = xino_fwrite(sbinfo->si_xwrite, file, &inode->i_generation, ++ sizeof(inode->i_generation), &pos); ++ } else ++ sz = xino_fread(sbinfo->si_xread, file, &inode->i_generation, ++ sizeof(inode->i_generation), &pos); ++ if (sz == sizeof(inode->i_generation)) ++ goto out; /* success */ ++ ++ err = sz; ++ if (unlikely(sz >= 0)) { ++ err = -EIO; ++ AuIOErr("xigen error (%zd)\n", sz); ++ } ++ ++ out: ++ return err; ++} ++ ++int au_xigen_set(struct super_block *sb, struct file *base) ++{ ++ int err; ++ struct au_sbinfo *sbinfo; ++ struct file *file; ++ ++ 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; ++} ++ ++void au_xigen_clr(struct super_block *sb) ++{ ++ struct au_sbinfo *sbinfo; ++ ++ sbinfo = au_sbi(sb); ++ if (sbinfo->si_xigen) { ++ fput(sbinfo->si_xigen); ++ sbinfo->si_xigen = NULL; ++ } ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++static struct dentry *decode_by_ino(struct super_block *sb, ino_t ino, ++ ino_t dir_ino) ++{ ++ struct dentry *dentry, *d; ++ struct inode *inode; ++ unsigned int sigen; ++ ++ dentry = NULL; ++ inode = ilookup(sb, ino); ++ if (!inode) ++ goto out; ++ ++ dentry = ERR_PTR(-ESTALE); ++ sigen = au_sigen(sb); ++ if (unlikely(is_bad_inode(inode) ++ || IS_DEADDIR(inode) ++ || sigen != au_iigen(inode))) ++ goto out_iput; ++ ++ dentry = NULL; ++ if (!dir_ino || S_ISDIR(inode->i_mode)) ++ dentry = d_find_alias(inode); ++ else { ++ spin_lock(&dcache_lock); ++ list_for_each_entry(d, &inode->i_dentry, d_alias) ++ if (!au_test_anon(d) ++ && d->d_parent->d_inode->i_ino == dir_ino) { ++ dentry = dget_locked(d); ++ break; ++ } ++ spin_unlock(&dcache_lock); ++ } ++ if (unlikely(dentry && sigen != au_digen(dentry))) { ++ dput(dentry); ++ dentry = ERR_PTR(-ESTALE); ++ } ++ ++ out_iput: ++ iput(inode); ++ out: ++ return dentry; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++/* todo: dirty? */ ++/* if exportfs_decode_fh() passed vfsmount*, we could be happy */ ++static struct vfsmount *au_mnt_get(struct super_block *sb) ++{ ++ struct mnt_namespace *ns; ++ struct vfsmount *pos, *mnt; ++ ++ spin_lock(&vfsmount_lock); ++ /* no get/put ?? */ ++ AuDebugOn(!current->nsproxy); ++ ns = current->nsproxy->mnt_ns; ++ AuDebugOn(!ns); ++ mnt = NULL; ++ /* the order (reverse) will not be a problem */ ++ list_for_each_entry(pos, &ns->list, mnt_list) ++ if (pos->mnt_sb == sb) { ++ mnt = mntget(pos); ++ break; ++ } ++ spin_unlock(&vfsmount_lock); ++ AuDebugOn(!mnt); ++ ++ return mnt; ++} ++ ++struct au_nfsd_si_lock { ++ const unsigned int sigen; ++ const aufs_bindex_t br_id; ++ unsigned char force_lock; ++}; ++ ++static aufs_bindex_t si_nfsd_read_lock(struct super_block *sb, ++ struct au_nfsd_si_lock *nsi_lock) ++{ ++ aufs_bindex_t bindex; ++ ++ si_read_lock(sb, AuLock_FLUSH); ++ ++ /* branch id may be wrapped around */ ++ 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 (!nsi_lock->force_lock) ++ si_read_unlock(sb); ++ bindex = -1; ++ ++ out: ++ return bindex; ++} ++ ++struct find_name_by_ino { ++ int called, found; ++ ino_t ino; ++ char *name; ++ int namelen; ++}; ++ ++static int ++find_name_by_ino(void *arg, const char *name, int namelen, loff_t offset, ++ u64 ino, unsigned int d_type) ++{ ++ struct find_name_by_ino *a = arg; ++ ++ a->called++; ++ if (a->ino != ino) ++ return 0; ++ ++ memcpy(a->name, name, namelen); ++ a->namelen = namelen; ++ a->found = 1; ++ return 1; ++} ++ ++static struct dentry *au_lkup_by_ino(struct path *path, ino_t ino, ++ struct au_nfsd_si_lock *nsi_lock) ++{ ++ struct dentry *dentry, *parent; ++ struct file *file; ++ struct inode *dir; ++ struct find_name_by_ino arg; ++ int err; ++ ++ parent = path->dentry; ++ if (nsi_lock) ++ si_read_unlock(parent->d_sb); ++ path_get(path); ++ file = dentry_open(parent, path->mnt, au_dir_roflags, current_cred()); ++ dentry = (void *)file; ++ if (IS_ERR(file)) ++ goto out; ++ ++ dentry = ERR_PTR(-ENOMEM); ++ arg.name = __getname(); ++ if (unlikely(!arg.name)) ++ goto out_file; ++ arg.ino = ino; ++ arg.found = 0; ++ do { ++ arg.called = 0; ++ /* smp_mb(); */ ++ err = vfsub_readdir(file, find_name_by_ino, &arg); ++ } while (!err && !arg.found && arg.called); ++ dentry = ERR_PTR(err); ++ if (unlikely(err)) ++ goto out_name; ++ dentry = ERR_PTR(-ENOENT); ++ if (!arg.found) ++ goto out_name; ++ ++ /* do not call au_lkup_one() */ ++ dir = parent->d_inode; ++ mutex_lock(&dir->i_mutex); ++ dentry = vfsub_lookup_one_len(arg.name, parent, arg.namelen); ++ mutex_unlock(&dir->i_mutex); ++ AuTraceErrPtr(dentry); ++ if (IS_ERR(dentry)) ++ goto out_name; ++ AuDebugOn(au_test_anon(dentry)); ++ if (unlikely(!dentry->d_inode)) { ++ dput(dentry); ++ dentry = ERR_PTR(-ENOENT); ++ } ++ ++ out_name: ++ __putname(arg.name); ++ out_file: ++ fput(file); ++ out: ++ if (unlikely(nsi_lock ++ && si_nfsd_read_lock(parent->d_sb, nsi_lock) < 0)) ++ if (!IS_ERR(dentry)) { ++ dput(dentry); ++ dentry = ERR_PTR(-ESTALE); ++ } ++ AuTraceErrPtr(dentry); ++ return dentry; ++} ++ ++static struct dentry *decode_by_dir_ino(struct super_block *sb, ino_t ino, ++ ino_t dir_ino, ++ struct au_nfsd_si_lock *nsi_lock) ++{ ++ struct dentry *dentry; ++ struct path path; ++ ++ if (dir_ino != AUFS_ROOT_INO) { ++ path.dentry = decode_by_ino(sb, dir_ino, 0); ++ dentry = path.dentry; ++ if (!path.dentry || IS_ERR(path.dentry)) ++ goto out; ++ AuDebugOn(au_test_anon(path.dentry)); ++ } else ++ path.dentry = dget(sb->s_root); ++ ++ path.mnt = au_mnt_get(sb); ++ dentry = au_lkup_by_ino(&path, ino, nsi_lock); ++ path_put(&path); ++ ++ out: ++ AuTraceErrPtr(dentry); ++ return dentry; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++static int h_acceptable(void *expv, struct dentry *dentry) ++{ ++ return 1; ++} ++ ++static char *au_build_path(struct dentry *h_parent, struct path *h_rootpath, ++ char *buf, int len, struct super_block *sb) ++{ ++ char *p; ++ int n; ++ struct path path; ++ ++ p = d_path(h_rootpath, buf, len); ++ if (IS_ERR(p)) ++ goto out; ++ n = strlen(p); ++ ++ path.mnt = h_rootpath->mnt; ++ path.dentry = h_parent; ++ p = d_path(&path, buf, len); ++ if (IS_ERR(p)) ++ goto out; ++ if (n != 1) ++ p += n; ++ ++ path.mnt = au_mnt_get(sb); ++ path.dentry = sb->s_root; ++ p = d_path(&path, buf, len - strlen(p)); ++ mntput(path.mnt); ++ if (IS_ERR(p)) ++ goto out; ++ if (n != 1) ++ p[strlen(p)] = '/'; ++ ++ out: ++ AuTraceErrPtr(p); ++ return p; ++} ++ ++static ++struct dentry *decode_by_path(struct super_block *sb, aufs_bindex_t bindex, ++ ino_t ino, __u32 *fh, int fh_len, ++ struct au_nfsd_si_lock *nsi_lock) ++{ ++ struct dentry *dentry, *h_parent, *root; ++ struct super_block *h_sb; ++ char *pathname, *p; ++ struct vfsmount *h_mnt; ++ struct au_branch *br; ++ int err; ++ struct path path; ++ ++ br = au_sbr(sb, bindex); ++ /* au_br_get(br); */ ++ h_mnt = br->br_mnt; ++ h_sb = h_mnt->mnt_sb; ++ /* todo: call lower fh_to_dentry()? fh_to_parent()? */ ++ h_parent = exportfs_decode_fh(h_mnt, (void *)(fh + Fh_tail), ++ fh_len - Fh_tail, fh[Fh_h_type], ++ h_acceptable, /*context*/NULL); ++ dentry = h_parent; ++ if (unlikely(!h_parent || IS_ERR(h_parent))) { ++ AuWarn1("%s decode_fh failed, %ld\n", ++ au_sbtype(h_sb), PTR_ERR(h_parent)); ++ goto out; ++ } ++ dentry = NULL; ++ if (unlikely(au_test_anon(h_parent))) { ++ AuWarn1("%s decode_fh returned a disconnected dentry\n", ++ au_sbtype(h_sb)); ++ goto out_h_parent; ++ } ++ ++ dentry = ERR_PTR(-ENOMEM); ++ pathname = (void *)__get_free_page(GFP_NOFS); ++ if (unlikely(!pathname)) ++ goto out_h_parent; ++ ++ root = sb->s_root; ++ path.mnt = h_mnt; ++ di_read_lock_parent(root, !AuLock_IR); ++ path.dentry = au_h_dptr(root, bindex); ++ di_read_unlock(root, !AuLock_IR); ++ p = au_build_path(h_parent, &path, pathname, PAGE_SIZE, sb); ++ dentry = (void *)p; ++ if (IS_ERR(p)) ++ goto out_pathname; ++ ++ si_read_unlock(sb); ++ err = vfsub_kern_path(p, LOOKUP_FOLLOW | LOOKUP_DIRECTORY, &path); ++ dentry = ERR_PTR(err); ++ if (unlikely(err)) ++ goto out_relock; ++ ++ dentry = ERR_PTR(-ENOENT); ++ AuDebugOn(au_test_anon(path.dentry)); ++ if (unlikely(!path.dentry->d_inode)) ++ goto out_path; ++ ++ if (ino != path.dentry->d_inode->i_ino) ++ dentry = au_lkup_by_ino(&path, ino, /*nsi_lock*/NULL); ++ else ++ dentry = dget(path.dentry); ++ ++ out_path: ++ path_put(&path); ++ out_relock: ++ if (unlikely(si_nfsd_read_lock(sb, nsi_lock) < 0)) ++ if (!IS_ERR(dentry)) { ++ dput(dentry); ++ dentry = ERR_PTR(-ESTALE); ++ } ++ out_pathname: ++ free_page((unsigned long)pathname); ++ out_h_parent: ++ dput(h_parent); ++ out: ++ /* au_br_put(br); */ ++ AuTraceErrPtr(dentry); ++ return dentry; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++static struct dentry * ++aufs_fh_to_dentry(struct super_block *sb, struct fid *fid, int fh_len, ++ int fh_type) ++{ ++ struct dentry *dentry; ++ __u32 *fh = fid->raw; ++ ino_t ino, dir_ino; ++ aufs_bindex_t bindex; ++ struct au_nfsd_si_lock nsi_lock = { ++ .sigen = fh[Fh_sigen], ++ .br_id = fh[Fh_br_id], ++ .force_lock = 0 ++ }; ++ ++ AuDebugOn(fh_len < Fh_tail); ++ ++ dentry = ERR_PTR(-ESTALE); ++ /* branch id may be wrapped around */ ++ bindex = si_nfsd_read_lock(sb, &nsi_lock); ++ if (unlikely(bindex < 0)) ++ goto out; ++ nsi_lock.force_lock = 1; ++ ++ /* is this inode still cached? */ ++ ino = decode_ino(fh + Fh_ino); ++ AuDebugOn(ino == AUFS_ROOT_INO); ++ 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? */ ++ dentry = decode_by_dir_ino(sb, ino, dir_ino, &nsi_lock); ++ if (IS_ERR(dentry)) ++ goto out_unlock; ++ if (dentry) ++ goto accept; ++ ++ /* lookup path */ ++ dentry = decode_by_path(sb, bindex, ino, fh, fh_len, &nsi_lock); ++ if (IS_ERR(dentry)) ++ goto out_unlock; ++ if (unlikely(!dentry)) ++ /* todo?: make it ESTALE */ ++ goto out_unlock; ++ ++ accept: ++ if (dentry->d_inode->i_generation == fh[Fh_igen]) ++ goto out_unlock; /* success */ ++ ++ dput(dentry); ++ dentry = ERR_PTR(-ESTALE); ++ out_unlock: ++ si_read_unlock(sb); ++ out: ++ AuTraceErrPtr(dentry); ++ return dentry; ++} ++ ++#if 0 /* reserved for future use */ ++/* support subtreecheck option */ ++static struct dentry *aufs_fh_to_parent(struct super_block *sb, struct fid *fid, ++ int fh_len, int fh_type) ++{ ++ struct dentry *parent; ++ __u32 *fh = fid->raw; ++ ino_t dir_ino; ++ ++ dir_ino = decode_ino(fh + Fh_dir_ino); ++ parent = decode_by_ino(sb, dir_ino, 0); ++ if (IS_ERR(parent)) ++ goto out; ++ if (!parent) ++ parent = decode_by_path(sb, au_br_index(sb, fh[Fh_br_id]), ++ dir_ino, fh, fh_len); ++ ++ out: ++ AuTraceErrPtr(parent); ++ return parent; ++} ++#endif ++ ++/* ---------------------------------------------------------------------- */ ++ ++static int aufs_encode_fh(struct dentry *dentry, __u32 *fh, int *max_len, ++ int connectable) ++{ ++ int err; ++ aufs_bindex_t bindex, bend; ++ struct super_block *sb, *h_sb; ++ struct inode *inode; ++ struct dentry *parent, *h_parent; ++ struct au_branch *br; ++ ++ AuDebugOn(au_test_anon(dentry)); ++ ++ parent = NULL; ++ err = -ENOSPC; ++ if (unlikely(*max_len <= Fh_tail)) { ++ AuWarn1("NFSv2 client (max_len %d)?\n", *max_len); ++ goto out; ++ } ++ ++ err = FILEID_ROOT; ++ if (IS_ROOT(dentry)) { ++ AuDebugOn(dentry->d_inode->i_ino != AUFS_ROOT_INO); ++ goto out; ++ } ++ ++ err = -EIO; ++ h_parent = NULL; ++ sb = dentry->d_sb; ++ aufs_read_lock(dentry, AuLock_FLUSH | AuLock_IR); ++ parent = dget_parent(dentry); ++ di_read_lock_parent(parent, !AuLock_IR); ++ inode = dentry->d_inode; ++ AuDebugOn(!inode); ++#ifdef CONFIG_AUFS_DEBUG ++ if (unlikely(!au_opt_test(au_mntflags(sb), XINO))) ++ AuWarn1("NFS-exporting requires xino\n"); ++#endif ++ ++ bend = au_dbtaildir(parent); ++ for (bindex = au_dbstart(parent); bindex <= bend; bindex++) { ++ h_parent = au_h_dptr(parent, bindex); ++ if (h_parent) { ++ dget(h_parent); ++ break; ++ } ++ } ++ if (unlikely(!h_parent)) ++ goto out_unlock; ++ ++ err = -EPERM; ++ br = au_sbr(sb, bindex); ++ h_sb = br->br_mnt->mnt_sb; ++ if (unlikely(!h_sb->s_export_op)) { ++ AuErr1("%s branch is not exportable\n", au_sbtype(h_sb)); ++ goto out_dput; ++ } ++ ++ 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, parent->d_inode->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 != 255) ++ err = 99; ++ else ++ AuWarn1("%s encode_fh failed\n", au_sbtype(h_sb)); ++ ++ out_dput: ++ dput(h_parent); ++ out_unlock: ++ di_read_unlock(parent, !AuLock_IR); ++ dput(parent); ++ aufs_read_unlock(dentry, AuLock_IR); ++ out: ++ if (unlikely(err < 0)) ++ err = 255; ++ 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 ++}; ++ ++void au_export_init(struct super_block *sb) ++{ ++ struct au_sbinfo *sbinfo; ++ __u32 u; ++ ++ 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 ./fs/aufs/f_op.c ./fs/aufs/f_op.c +--- ./fs/aufs/f_op.c 1970-01-01 01:00:00.000000000 +0100 ++++ ./fs/aufs/f_op.c 2009-04-06 10:26:46.000000000 +0200 +@@ -0,0 +1,551 @@ ++/* ++ * Copyright (C) 2005-2009 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. ++ */ ++ ++/* ++ * file and vm operations ++ */ ++ ++#include <linux/fs_stack.h> ++#include <linux/poll.h> ++#include "aufs.h" ++ ++/* common function to regular file and dir */ ++int aufs_flush(struct file *file, fl_owner_t id) ++{ ++ int err; ++ aufs_bindex_t bindex, bend; ++ struct dentry *dentry; ++ struct file *h_file; ++ ++ dentry = file->f_dentry; ++ si_noflush_read_lock(dentry->d_sb); ++ fi_read_lock(file); ++ di_read_lock_child(dentry, AuLock_IW); ++ ++ err = 0; ++ bend = au_fbend(file); ++ for (bindex = au_fbstart(file); !err && bindex <= bend; bindex++) { ++ h_file = au_h_fptr(file, bindex); ++ if (!h_file || !h_file->f_op->flush) ++ continue; ++ ++ err = h_file->f_op->flush(h_file, id); ++ if (!err) ++ vfsub_update_h_iattr(&h_file->f_path, /*did*/NULL); ++ /*ignore*/ ++ } ++ au_cpup_attr_timesizes(dentry->d_inode); ++ ++ di_read_unlock(dentry, AuLock_IW); ++ fi_read_unlock(file); ++ si_read_unlock(dentry->d_sb); ++ return err; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++static int do_open_nondir(struct file *file, int flags) ++{ ++ int err; ++ aufs_bindex_t bindex; ++ struct file *h_file; ++ struct dentry *dentry; ++ ++ err = 0; ++ dentry = file->f_dentry; ++ au_fi(file)->fi_h_vm_ops = NULL; ++ bindex = au_dbstart(dentry); ++ /* O_TRUNC is processed already */ ++ BUG_ON(au_test_ro(dentry->d_sb, bindex, dentry->d_inode) ++ && (flags & O_TRUNC)); ++ ++ h_file = au_h_open(dentry, bindex, flags, file); ++ if (IS_ERR(h_file)) ++ err = PTR_ERR(h_file); ++ else { ++ au_set_fbstart(file, bindex); ++ au_set_fbend(file, bindex); ++ au_set_h_fptr(file, bindex, h_file); ++ au_update_figen(file); ++ /* todo: necessary? */ ++ /* file->f_ra = h_file->f_ra; */ ++ } ++ return err; ++} ++ ++static int aufs_open_nondir(struct inode *inode __maybe_unused, ++ struct file *file) ++{ ++ return au_do_open(file, do_open_nondir); ++} ++ ++static int aufs_release_nondir(struct inode *inode __maybe_unused, ++ struct file *file) ++{ ++ struct super_block *sb = file->f_dentry->d_sb; ++ ++ si_noflush_read_lock(sb); ++ au_finfo_fin(file); ++ si_read_unlock(sb); ++ return 0; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++static ssize_t aufs_read(struct file *file, char __user *buf, size_t count, ++ loff_t *ppos) ++{ ++ ssize_t err; ++ struct dentry *dentry; ++ struct file *h_file; ++ struct super_block *sb; ++ ++ dentry = file->f_dentry; ++ sb = dentry->d_sb; ++ si_read_lock(sb, AuLock_FLUSH); ++ err = au_reval_and_lock_fdi(file, au_reopen_nondir, /*wlock*/0); ++ if (unlikely(err)) ++ goto out; ++ ++ h_file = au_h_fptr(file, au_fbstart(file)); ++ err = vfsub_read_u(h_file, buf, count, ppos); ++ /* todo: necessary? */ ++ /* file->f_ra = h_file->f_ra; */ ++ fsstack_copy_attr_atime(dentry->d_inode, h_file->f_dentry->d_inode); ++ ++ di_read_unlock(dentry, AuLock_IR); ++ fi_read_unlock(file); ++ out: ++ si_read_unlock(sb); ++ return err; ++} ++ ++static ssize_t aufs_write(struct file *file, const char __user *ubuf, ++ size_t count, loff_t *ppos) ++{ ++ ssize_t err; ++ aufs_bindex_t bstart; ++ struct au_pin pin; ++ struct dentry *dentry; ++ struct inode *inode; ++ struct super_block *sb; ++ struct file *h_file; ++ char __user *buf = (char __user *)ubuf; ++ ++ dentry = file->f_dentry; ++ sb = dentry->d_sb; ++ inode = dentry->d_inode; ++ mutex_lock(&inode->i_mutex); ++ si_read_lock(sb, AuLock_FLUSH); ++ ++ err = au_reval_and_lock_fdi(file, au_reopen_nondir, /*wlock*/1); ++ if (unlikely(err)) ++ goto out; ++ ++ err = au_ready_to_write(file, -1, &pin); ++ di_downgrade_lock(dentry, AuLock_IR); ++ if (unlikely(err)) ++ goto out_unlock; ++ ++ bstart = au_fbstart(file); ++ h_file = au_h_fptr(file, bstart); ++ au_unpin(&pin); ++ err = vfsub_write_u(h_file, buf, count, ppos); ++ au_cpup_attr_timesizes(inode); ++ inode->i_mode = h_file->f_dentry->d_inode->i_mode; ++ ++ out_unlock: ++ di_read_unlock(dentry, AuLock_IR); ++ fi_write_unlock(file); ++ out: ++ si_read_unlock(sb); ++ mutex_unlock(&inode->i_mutex); ++ return err; ++} ++ ++static ssize_t aufs_splice_read(struct file *file, loff_t *ppos, ++ struct pipe_inode_info *pipe, size_t len, ++ unsigned int flags) ++{ ++ ssize_t err; ++ struct file *h_file; ++ struct dentry *dentry; ++ struct super_block *sb; ++ ++ dentry = file->f_dentry; ++ sb = dentry->d_sb; ++ si_read_lock(sb, AuLock_FLUSH); ++ err = au_reval_and_lock_fdi(file, au_reopen_nondir, /*wlock*/0); ++ if (unlikely(err)) ++ goto out; ++ ++ err = -EINVAL; ++ h_file = au_h_fptr(file, au_fbstart(file)); ++ if (au_test_loopback_kthread()) { ++ file->f_mapping = h_file->f_mapping; ++ smp_mb(); /* unnecessary? */ ++ } ++ err = vfsub_splice_to(h_file, ppos, pipe, len, flags); ++ /* todo: necessasry? */ ++ /* file->f_ra = h_file->f_ra; */ ++ fsstack_copy_attr_atime(dentry->d_inode, h_file->f_dentry->d_inode); ++ ++ di_read_unlock(dentry, AuLock_IR); ++ fi_read_unlock(file); ++ ++ out: ++ si_read_unlock(sb); ++ return err; ++} ++ ++static ssize_t ++aufs_splice_write(struct pipe_inode_info *pipe, struct file *file, loff_t *ppos, ++ size_t len, unsigned int flags) ++{ ++ ssize_t err; ++ struct au_pin pin; ++ struct dentry *dentry; ++ struct inode *inode; ++ struct super_block *sb; ++ struct file *h_file; ++ ++ dentry = file->f_dentry; ++ inode = dentry->d_inode; ++ mutex_lock(&inode->i_mutex); ++ sb = dentry->d_sb; ++ si_read_lock(sb, AuLock_FLUSH); ++ ++ err = au_reval_and_lock_fdi(file, au_reopen_nondir, /*wlock*/1); ++ if (unlikely(err)) ++ goto out; ++ ++ err = au_ready_to_write(file, -1, &pin); ++ di_downgrade_lock(dentry, AuLock_IR); ++ if (unlikely(err)) ++ goto out_unlock; ++ ++ h_file = au_h_fptr(file, au_fbstart(file)); ++ au_unpin(&pin); ++ err = vfsub_splice_from(pipe, h_file, ppos, len, flags); ++ au_cpup_attr_timesizes(inode); ++ inode->i_mode = h_file->f_dentry->d_inode->i_mode; ++ ++ out_unlock: ++ di_read_unlock(dentry, AuLock_IR); ++ fi_write_unlock(file); ++ out: ++ si_read_unlock(sb); ++ mutex_unlock(&inode->i_mutex); ++ return err; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++static struct file *au_safe_file(struct vm_area_struct *vma) ++{ ++ struct file *file; ++ ++ file = vma->vm_file; ++ if (file->private_data && au_test_aufs(file->f_dentry->d_sb)) ++ return file; ++ return NULL; ++} ++ ++static void au_reset_file(struct vm_area_struct *vma, struct file *file) ++{ ++ vma->vm_file = file; ++ /* smp_mb(); */ /* flush vm_file */ ++} ++ ++static int aufs_fault(struct vm_area_struct *vma, struct vm_fault *vmf) ++{ ++ int err; ++ static DECLARE_WAIT_QUEUE_HEAD(wq); ++ struct file *file, *h_file; ++ struct au_finfo *finfo; ++ ++ /* todo: non-robr mode, user vm_file as it is? */ ++ wait_event(wq, (file = au_safe_file(vma))); ++ ++ /* do not revalidate, no si lock */ ++ finfo = au_fi(file); ++ h_file = finfo->fi_hfile[0 + finfo->fi_bstart].hf_file; ++ AuDebugOn(!h_file || !au_test_mmapped(file)); ++ ++ fi_write_lock(file); ++ vma->vm_file = h_file; ++ err = finfo->fi_h_vm_ops->fault(vma, vmf); ++ /* todo: necessary? */ ++ /* file->f_ra = h_file->f_ra; */ ++ au_reset_file(vma, file); ++ fi_write_unlock(file); ++#if 0 /* def CONFIG_SMP */ ++ /* wake_up_nr(&wq, online_cpu - 1); */ ++ wake_up_all(&wq); ++#else ++ wake_up(&wq); ++#endif ++ ++ return err; ++} ++ ++static struct vm_operations_struct aufs_vm_ops = { ++ .fault = aufs_fault ++}; ++ ++/* ---------------------------------------------------------------------- */ ++ ++static struct vm_operations_struct *au_vm_ops(struct file *h_file, ++ struct vm_area_struct *vma) ++{ ++ struct vm_operations_struct *vm_ops; ++ int err; ++ ++ err = h_file->f_op->mmap(h_file, vma); ++ vm_ops = ERR_PTR(err); ++ if (unlikely(err)) ++ goto out; ++ vm_ops = vma->vm_ops; ++ err = do_munmap(current->mm, vma->vm_start, ++ vma->vm_end - vma->vm_start); ++ if (unlikely(err)) { ++ AuIOErr("failed internal unmapping %.*s, %d\n", ++ AuDLNPair(h_file->f_dentry), err); ++ vm_ops = ERR_PTR(-EIO); ++ } ++ ++ out: ++ return vm_ops; ++} ++ ++static int aufs_mmap(struct file *file, struct vm_area_struct *vma) ++{ ++ int err; ++ unsigned char wlock, mmapped; ++ struct dentry *dentry; ++ struct super_block *sb; ++ struct file *h_file; ++ struct vm_operations_struct *vm_ops; ++ ++ dentry = file->f_dentry; ++ mmapped = !!au_test_mmapped(file); /* can be harmless race condition */ ++ wlock = !!(file->f_mode & FMODE_WRITE); ++ sb = dentry->d_sb; ++ si_read_lock(sb, AuLock_FLUSH); ++ err = au_reval_and_lock_fdi(file, au_reopen_nondir, wlock | !mmapped); ++ if (unlikely(err)) ++ goto out; ++ ++ if (wlock) { ++ struct au_pin pin; ++ ++ err = au_ready_to_write(file, -1, &pin); ++ di_downgrade_lock(dentry, AuLock_IR); ++ if (unlikely(err)) ++ goto out_unlock; ++ au_unpin(&pin); ++ } else if (!mmapped) ++ di_downgrade_lock(dentry, AuLock_IR); ++ ++ h_file = au_h_fptr(file, au_fbstart(file)); ++ if (au_test_fs_bad_mapping(h_file->f_dentry->d_sb)) { ++ /* ++ * by this assignment, f_mapping will differs from aufs inode ++ * i_mapping. ++ * if someone else mixes the use of f_dentry->d_inode and ++ * f_mapping->host, then a problem may arise. ++ */ ++ file->f_mapping = h_file->f_mapping; ++ } ++ ++ vm_ops = NULL; ++ if (!mmapped) { ++ vm_ops = au_vm_ops(h_file, vma); ++ err = PTR_ERR(vm_ops); ++ if (IS_ERR(vm_ops)) ++ goto out_unlock; ++ } ++ ++ /* ++ * unnecessary to handle MAP_DENYWRITE and deny_write_access()? ++ * currently MAP_DENYWRITE from userspace is ignored, but elf loader ++ * sets it. when FMODE_EXEC is set (by open_exec() or sys_uselib()), ++ * both of the aufs file and the lower file is deny_write_access()-ed. ++ * finally I hope we can skip handlling MAP_DENYWRITE here. ++ */ ++ err = generic_file_mmap(file, vma); ++ if (unlikely(err)) ++ goto out_unlock; ++ vma->vm_ops = &aufs_vm_ops; ++ /* test again */ ++ if (!au_test_mmapped(file)) ++ au_fi(file)->fi_h_vm_ops = vm_ops; ++ ++ vfsub_file_accessed(h_file); ++ fsstack_copy_attr_atime(dentry->d_inode, h_file->f_dentry->d_inode); ++ ++ out_unlock: ++ di_read_unlock(dentry, AuLock_IR); ++ if (!wlock && mmapped) ++ fi_read_unlock(file); ++ else ++ fi_write_unlock(file); ++ out: ++ si_read_unlock(sb); ++ return err; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++static unsigned int aufs_poll(struct file *file, poll_table *wait) ++{ ++ unsigned int mask; ++ int err; ++ struct file *h_file; ++ struct dentry *dentry; ++ struct super_block *sb; ++ ++ /* We should pretend an error happened. */ ++ mask = POLLERR /* | POLLIN | POLLOUT */; ++ dentry = file->f_dentry; ++ sb = dentry->d_sb; ++ si_read_lock(sb, AuLock_FLUSH); ++ err = au_reval_and_lock_fdi(file, au_reopen_nondir, /*wlock*/0); ++ if (unlikely(err)) ++ goto out; ++ ++ /* it is not an error if h_file has no operation */ ++ mask = DEFAULT_POLLMASK; ++ h_file = au_h_fptr(file, au_fbstart(file)); ++ if (h_file->f_op->poll) ++ mask = h_file->f_op->poll(h_file, wait); ++ ++ di_read_unlock(dentry, AuLock_IR); ++ fi_read_unlock(file); ++ ++ out: ++ si_read_unlock(sb); ++ AuTraceErr((int)mask); ++ return mask; ++} ++ ++static int aufs_fsync_nondir(struct file *file, struct dentry *dentry, ++ int datasync) ++{ ++ int err; ++ struct au_pin pin; ++ struct inode *inode; ++ struct file *h_file; ++ struct super_block *sb; ++ ++ inode = dentry->d_inode; ++ IMustLock(file->f_mapping->host); ++ if (inode != file->f_mapping->host) { ++ mutex_unlock(&file->f_mapping->host->i_mutex); ++ mutex_lock(&inode->i_mutex); ++ } ++ IMustLock(inode); ++ ++ sb = dentry->d_sb; ++ si_read_lock(sb, AuLock_FLUSH); ++ ++ err = 0; /* -EBADF; */ /* posix? */ ++ if (unlikely(!(file->f_mode & FMODE_WRITE))) ++ goto out; ++ err = au_reval_and_lock_fdi(file, au_reopen_nondir, /*wlock*/1); ++ if (unlikely(err)) ++ goto out; ++ ++ err = au_ready_to_write(file, -1, &pin); ++ di_downgrade_lock(dentry, AuLock_IR); ++ if (unlikely(err)) ++ goto out_unlock; ++ au_unpin(&pin); ++ ++ err = -EINVAL; ++ h_file = au_h_fptr(file, au_fbstart(file)); ++ if (h_file->f_op->fsync) { ++ struct dentry *h_d; ++ struct mutex *h_mtx; ++ ++ /* ++ * no filemap_fdatawrite() since aufs file has no its own ++ * mapping, but dir. ++ */ ++ h_d = h_file->f_dentry; ++ h_mtx = &h_d->d_inode->i_mutex; ++ mutex_lock_nested(h_mtx, AuLsc_I_CHILD); ++ err = h_file->f_op->fsync(h_file, h_d, datasync); ++ if (!err) ++ vfsub_update_h_iattr(&h_file->f_path, /*did*/NULL); ++ /*ignore*/ ++ au_cpup_attr_timesizes(inode); ++ mutex_unlock(h_mtx); ++ } ++ ++ out_unlock: ++ di_read_unlock(dentry, AuLock_IR); ++ fi_write_unlock(file); ++ out: ++ si_read_unlock(sb); ++ if (inode != file->f_mapping->host) { ++ mutex_unlock(&inode->i_mutex); ++ mutex_lock(&file->f_mapping->host->i_mutex); ++ } ++ return err; ++} ++ ++static int aufs_fasync(int fd, struct file *file, int flag) ++{ ++ int err; ++ struct file *h_file; ++ struct dentry *dentry; ++ struct super_block *sb; ++ ++ dentry = file->f_dentry; ++ sb = dentry->d_sb; ++ si_read_lock(sb, AuLock_FLUSH); ++ err = au_reval_and_lock_fdi(file, au_reopen_nondir, /*wlock*/0); ++ if (unlikely(err)) ++ goto out; ++ ++ h_file = au_h_fptr(file, au_fbstart(file)); ++ if (h_file->f_op->fasync) ++ err = h_file->f_op->fasync(fd, h_file, flag); ++ ++ di_read_unlock(dentry, AuLock_IR); ++ fi_read_unlock(file); ++ ++ out: ++ si_read_unlock(sb); ++ return err; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++const struct file_operations aufs_file_fop = { ++ /* ++ * while generic_file_llseek/_unlocked() don't use BKL, ++ * don't use it since it operates file->f_mapping->host. ++ * in aufs, it may be a real file and may confuse users by UDBA. ++ */ ++ /* .llseek = generic_file_llseek, */ ++ ++ .read = aufs_read, ++ .write = aufs_write, ++ .poll = aufs_poll, ++ .mmap = aufs_mmap, ++ .open = aufs_open_nondir, ++ .flush = aufs_flush, ++ .release = aufs_release_nondir, ++ .fsync = aufs_fsync_nondir, ++ .fasync = aufs_fasync, ++ .splice_write = aufs_splice_write, ++ .splice_read = aufs_splice_read ++}; +diff -urN ./fs/aufs/file.c ./fs/aufs/file.c +--- ./fs/aufs/file.c 1970-01-01 01:00:00.000000000 +0100 ++++ ./fs/aufs/file.c 2009-04-06 10:26:46.000000000 +0200 +@@ -0,0 +1,558 @@ ++/* ++ * Copyright (C) 2005-2009 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. ++ */ ++ ++/* ++ * handling file/dir, and address_space operation ++ */ ++ ++#include <linux/fsnotify.h> ++#include <linux/pagemap.h> ++#include "aufs.h" ++ ++/* ++ * a dirty trick for handling deny_write_access(). ++ * because FMODE_EXEC flag is not passed to f_op->open(), ++ * set it to file->private_data temporary. ++ */ ++void au_store_oflag(struct nameidata *nd, struct inode *inode) ++{ ++ if (nd ++ /* && !(nd->flags & LOOKUP_CONTINUE) */ ++ && (nd->flags & LOOKUP_OPEN) ++ && (nd->intent.open.flags & vfsub_fmode_to_uint(FMODE_EXEC)) ++ && inode ++ && S_ISREG(inode->i_mode)) { ++ /* suppress a warning in lp64 */ ++ unsigned long flags = nd->intent.open.flags; ++ nd->intent.open.file->private_data = (void *)flags; ++ /* smp_mb(); */ ++ } ++} ++ ++/* drop flags for writing */ ++unsigned int au_file_roflags(unsigned int flags) ++{ ++ flags &= ~(O_WRONLY | O_RDWR | O_APPEND | O_CREAT | O_TRUNC); ++ flags |= O_RDONLY | O_NOATIME; ++ return flags; ++} ++ ++/* common functions to regular file and dir */ ++struct file *au_h_open(struct dentry *dentry, aufs_bindex_t bindex, int flags, ++ struct file *file) ++{ ++ struct file *h_file; ++ struct dentry *h_dentry; ++ struct inode *h_inode; ++ struct super_block *sb; ++ struct au_branch *br; ++ int err; ++ ++ h_dentry = au_h_dptr(dentry, bindex); ++ h_inode = h_dentry->d_inode; ++ /* a race condition can happen between open and unlink/rmdir */ ++ h_file = ERR_PTR(-ENOENT); ++ if (unlikely((!d_unhashed(dentry) && d_unhashed(h_dentry)) ++ || !h_inode)) ++ goto out; ++ ++ sb = dentry->d_sb; ++ br = au_sbr(sb, bindex); ++ h_file = ERR_PTR(-EACCES); ++ if (file && (file->f_mode & FMODE_EXEC) ++ && (br->br_mnt->mnt_flags & MNT_NOEXEC)) ++ goto out; ++ ++ /* drop flags for writing */ ++ if (au_test_ro(sb, bindex, dentry->d_inode)) ++ flags = au_file_roflags(flags); ++ flags &= ~O_CREAT; ++ atomic_inc(&br->br_count); ++ h_file = dentry_open(dget(h_dentry), mntget(br->br_mnt), flags, ++ current_cred()); ++ if (IS_ERR(h_file)) ++ goto out_br; ++ AuDebugOn(!h_file->f_op); ++ ++ if (file && (file->f_mode & FMODE_EXEC)) { ++ h_file->f_mode |= FMODE_EXEC; ++ err = deny_write_access(h_file); ++ if (unlikely(err)) { ++ fput(h_file); ++ h_file = ERR_PTR(err); ++ goto out_br; ++ } ++ } ++ fsnotify_open(h_dentry); ++ goto out; /* success */ ++ ++ out_br: ++ atomic_dec(&br->br_count); ++ out: ++ return h_file; ++} ++ ++int au_do_open(struct file *file, int (*open)(struct file *file, int flags)) ++{ ++ int err; ++ struct dentry *dentry; ++ struct super_block *sb; ++ ++ dentry = file->f_dentry; ++ sb = dentry->d_sb; ++ si_read_lock(sb, AuLock_FLUSH); ++ err = au_finfo_init(file); ++ if (unlikely(err)) ++ goto out; ++ ++ di_read_lock_child(dentry, AuLock_IR); ++ err = open(file, file->f_flags); ++ di_read_unlock(dentry, AuLock_IR); ++ ++ fi_write_unlock(file); ++ if (unlikely(err)) ++ au_finfo_fin(file); ++ out: ++ si_read_unlock(sb); ++ return err; ++} ++ ++int au_reopen_nondir(struct file *file) ++{ ++ int err; ++ aufs_bindex_t bstart, bindex, bend; ++ struct dentry *dentry; ++ struct file *h_file, *h_file_tmp; ++ ++ dentry = file->f_dentry; ++ bstart = au_dbstart(dentry); ++ h_file_tmp = NULL; ++ if (au_fbstart(file) == bstart) { ++ h_file = au_h_fptr(file, bstart); ++ if (file->f_mode == h_file->f_mode) ++ return 0; /* success */ ++ h_file_tmp = h_file; ++ get_file(h_file_tmp); ++ au_set_h_fptr(file, bstart, NULL); ++ } ++ AuDebugOn(au_fbstart(file) < bstart ++ || au_fi(file)->fi_hfile[0 + bstart].hf_file); ++ ++ h_file = au_h_open(dentry, bstart, file->f_flags & ~O_TRUNC, file); ++ err = PTR_ERR(h_file); ++ if (IS_ERR(h_file)) ++ goto out; /* todo: close all? */ ++ ++ err = 0; ++ au_set_fbstart(file, bstart); ++ au_set_h_fptr(file, bstart, h_file); ++ au_update_figen(file); ++ /* todo: necessary? */ ++ /* file->f_ra = h_file->f_ra; */ ++ ++ /* close lower files */ ++ bend = au_fbend(file); ++ for (bindex = bstart + 1; bindex <= bend; bindex++) ++ au_set_h_fptr(file, bindex, NULL); ++ au_set_fbend(file, bstart); ++ ++ out: ++ if (h_file_tmp) ++ fput(h_file_tmp); ++ return err; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++static int au_reopen_wh(struct file *file, aufs_bindex_t btgt, ++ struct dentry *hi_wh) ++{ ++ int err; ++ aufs_bindex_t bstart; ++ struct au_dinfo *dinfo; ++ struct dentry *h_dentry; ++ ++ dinfo = au_di(file->f_dentry); ++ bstart = dinfo->di_bstart; ++ dinfo->di_bstart = btgt; ++ h_dentry = dinfo->di_hdentry[0 + btgt].hd_dentry; ++ dinfo->di_hdentry[0 + btgt].hd_dentry = hi_wh; ++ err = au_reopen_nondir(file); ++ dinfo->di_hdentry[0 + btgt].hd_dentry = h_dentry; ++ dinfo->di_bstart = bstart; ++ ++ return err; ++} ++ ++static int au_ready_to_write_wh(struct file *file, loff_t len, ++ aufs_bindex_t bcpup) ++{ ++ int err; ++ struct inode *inode; ++ struct dentry *dentry, *hi_wh; ++ struct super_block *sb; ++ ++ dentry = file->f_dentry; ++ inode = dentry->d_inode; ++ hi_wh = au_hi_wh(inode, bcpup); ++ if (!hi_wh) ++ err = au_sio_cpup_wh(dentry, bcpup, len, file); ++ else ++ /* already copied-up after unlink */ ++ err = au_reopen_wh(file, bcpup, hi_wh); ++ ++ sb = dentry->d_sb; ++ if (!err && inode->i_nlink > 1 && au_opt_test(au_mntflags(sb), PLINK)) ++ au_plink_append(inode, bcpup, au_h_dptr(dentry, bcpup)); ++ ++ return err; ++} ++ ++/* ++ * prepare the @file for writing. ++ */ ++int au_ready_to_write(struct file *file, loff_t len, struct au_pin *pin) ++{ ++ int err; ++ aufs_bindex_t bstart, bcpup; ++ struct dentry *dentry, *parent, *h_dentry; ++ struct inode *h_inode, *inode; ++ struct super_block *sb; ++ ++ dentry = file->f_dentry; ++ sb = dentry->d_sb; ++ bstart = au_fbstart(file); ++ inode = dentry->d_inode; ++ err = au_test_ro(sb, bstart, inode); ++ if (!err && (au_h_fptr(file, bstart)->f_mode & FMODE_WRITE)) { ++ err = au_pin(pin, dentry, bstart, AuOpt_UDBA_NONE, /*flags*/0); ++ goto out; ++ } ++ ++ /* need to cpup */ ++ parent = dget_parent(dentry); ++ di_write_lock_parent(parent); ++ err = AuWbrCopyup(au_sbi(sb), dentry); ++ bcpup = err; ++ if (unlikely(err < 0)) ++ goto out_dgrade; ++ err = 0; ++ ++ if (!au_h_dptr(parent, bcpup)) { ++ err = au_cpup_dirs(dentry, bcpup); ++ if (unlikely(err)) ++ goto out_dgrade; ++ } ++ ++ err = au_pin(pin, dentry, bcpup, AuOpt_UDBA_NONE, ++ AuPin_DI_LOCKED | AuPin_MNT_WRITE); ++ if (unlikely(err)) ++ goto out_dgrade; ++ ++ h_dentry = au_h_fptr(file, bstart)->f_dentry; ++ h_inode = h_dentry->d_inode; ++ mutex_lock_nested(&h_inode->i_mutex, AuLsc_I_CHILD); ++ if (d_unhashed(dentry) /* || d_unhashed(h_dentry) */ ++ /* || !h_inode->i_nlink */) { ++ err = au_ready_to_write_wh(file, len, bcpup); ++ di_downgrade_lock(parent, AuLock_IR); ++ } else { ++ di_downgrade_lock(parent, AuLock_IR); ++ if (!au_h_dptr(dentry, bcpup)) ++ err = au_sio_cpup_simple(dentry, bcpup, len, ++ AuCpup_DTIME); ++ if (!err) ++ err = au_reopen_nondir(file); ++ } ++ mutex_unlock(&h_inode->i_mutex); ++ ++ if (!err) { ++ au_pin_set_parent_lflag(pin, /*lflag*/0); ++ goto out_dput; /* success */ ++ } ++ au_unpin(pin); ++ goto out_unlock; ++ ++ out_dgrade: ++ di_downgrade_lock(parent, AuLock_IR); ++ out_unlock: ++ di_read_unlock(parent, AuLock_IR); ++ out_dput: ++ dput(parent); ++ out: ++ return err; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++static int au_file_refresh_by_inode(struct file *file, int *need_reopen) ++{ ++ int err; ++ aufs_bindex_t bstart; ++ struct au_pin pin; ++ struct au_finfo *finfo; ++ struct dentry *dentry, *parent, *hi_wh; ++ struct inode *inode; ++ struct super_block *sb; ++ ++ err = 0; ++ finfo = au_fi(file); ++ dentry = file->f_dentry; ++ sb = dentry->d_sb; ++ inode = dentry->d_inode; ++ bstart = au_ibstart(inode); ++ if (bstart == finfo->fi_bstart) ++ goto out; ++ ++ parent = dget_parent(dentry); ++ if (au_test_ro(sb, bstart, inode)) { ++ di_read_lock_parent(parent, !AuLock_IR); ++ err = AuWbrCopyup(au_sbi(sb), dentry); ++ bstart = err; ++ di_read_unlock(parent, !AuLock_IR); ++ if (unlikely(err < 0)) ++ goto out_parent; ++ err = 0; ++ } ++ ++ di_read_lock_parent(parent, AuLock_IR); ++ hi_wh = au_hi_wh(inode, bstart); ++ if (au_opt_test(au_mntflags(sb), PLINK) ++ && au_plink_test(inode) ++ && !d_unhashed(dentry)) { ++ err = au_test_and_cpup_dirs(dentry, bstart); ++ if (unlikely(err)) ++ goto out_unlock; ++ ++ /* always superio. */ ++ err = au_pin(&pin, dentry, bstart, AuOpt_UDBA_NONE, ++ AuPin_DI_LOCKED | AuPin_MNT_WRITE); ++ if (!err) ++ err = au_sio_cpup_simple(dentry, bstart, -1, ++ AuCpup_DTIME); ++ au_unpin(&pin); ++ } else if (hi_wh) { ++ /* already copied-up after unlink */ ++ err = au_reopen_wh(file, bstart, hi_wh); ++ *need_reopen = 0; ++ } ++ ++ out_unlock: ++ di_read_unlock(parent, AuLock_IR); ++ out_parent: ++ dput(parent); ++ out: ++ return err; ++} ++ ++static void au_do_refresh_file(struct file *file) ++{ ++ aufs_bindex_t bindex, bend, new_bindex, brid; ++ struct au_hfile *p, tmp, *q; ++ struct au_finfo *finfo; ++ struct super_block *sb; ++ ++ sb = file->f_dentry->d_sb; ++ finfo = au_fi(file); ++ p = finfo->fi_hfile + finfo->fi_bstart; ++ brid = p->hf_br->br_id; ++ bend = finfo->fi_bend; ++ for (bindex = finfo->fi_bstart; bindex <= bend; bindex++, p++) { ++ if (!p->hf_file) ++ continue; ++ ++ new_bindex = au_br_index(sb, p->hf_br->br_id); ++ if (new_bindex == bindex) ++ continue; ++ if (new_bindex < 0) { ++ au_set_h_fptr(file, bindex, NULL); ++ continue; ++ } ++ ++ /* swap two lower inode, and loop again */ ++ q = finfo->fi_hfile + new_bindex; ++ tmp = *q; ++ *q = *p; ++ *p = tmp; ++ if (tmp.hf_file) { ++ bindex--; ++ p--; ++ } ++ } ++ ++ p = finfo->fi_hfile; ++ if (!au_test_mmapped(file) && !d_unhashed(file->f_dentry)) { ++ bend = au_sbend(sb); ++ for (finfo->fi_bstart = 0; finfo->fi_bstart <= bend; ++ finfo->fi_bstart++, p++) ++ if (p->hf_file) { ++ if (p->hf_file->f_dentry ++ && p->hf_file->f_dentry->d_inode) ++ break; ++ else ++ au_hfput(p, file); ++ } ++ } else { ++ bend = au_br_index(sb, brid); ++ for (finfo->fi_bstart = 0; finfo->fi_bstart < bend; ++ finfo->fi_bstart++, p++) ++ if (p->hf_file) ++ au_hfput(p, file); ++ bend = au_sbend(sb); ++ } ++ ++ p = finfo->fi_hfile + bend; ++ for (finfo->fi_bend = bend; finfo->fi_bend >= finfo->fi_bstart; ++ finfo->fi_bend--, p--) ++ if (p->hf_file) { ++ if (p->hf_file->f_dentry ++ && p->hf_file->f_dentry->d_inode) ++ break; ++ else ++ au_hfput(p, file); ++ } ++ AuDebugOn(finfo->fi_bend < finfo->fi_bstart); ++} ++ ++/* ++ * after branch manipulating, refresh the file. ++ */ ++static int refresh_file(struct file *file, int (*reopen)(struct file *file)) ++{ ++ int err, need_reopen; ++ struct dentry *dentry; ++ aufs_bindex_t bend, bindex; ++ ++ dentry = file->f_dentry; ++ err = au_fi_realloc(au_fi(file), au_sbend(dentry->d_sb) + 1); ++ if (unlikely(err)) ++ goto out; ++ au_do_refresh_file(file); ++ ++ err = 0; ++ need_reopen = 1; ++ if (!au_test_mmapped(file)) ++ err = au_file_refresh_by_inode(file, &need_reopen); ++ if (!err && need_reopen && !d_unhashed(dentry)) ++ err = reopen(file); ++ if (!err) { ++ au_update_figen(file); ++ return 0; /* success */ ++ } ++ ++ /* error, close all lower files */ ++ bend = au_fbend(file); ++ for (bindex = au_fbstart(file); bindex <= bend; bindex++) ++ au_set_h_fptr(file, bindex, NULL); ++ ++ out: ++ return err; ++} ++ ++/* common function to regular file and dir */ ++int au_reval_and_lock_fdi(struct file *file, int (*reopen)(struct file *file), ++ int wlock) ++{ ++ int err; ++ unsigned int sigen, figen; ++ aufs_bindex_t bstart; ++ unsigned char pseudo_link; ++ struct dentry *dentry; ++ ++ err = 0; ++ dentry = file->f_dentry; ++ sigen = au_sigen(dentry->d_sb); ++ fi_write_lock(file); ++ figen = au_figen(file); ++ di_write_lock_child(dentry); ++ bstart = au_dbstart(dentry); ++ pseudo_link = (bstart != au_ibstart(dentry->d_inode)); ++ if (sigen == figen && !pseudo_link && au_fbstart(file) == bstart) { ++ if (!wlock) { ++ di_downgrade_lock(dentry, AuLock_IR); ++ fi_downgrade_lock(file); ++ } ++ goto out; /* success */ ++ } ++ ++ AuDbg("sigen %d, figen %d\n", sigen, figen); ++ if (sigen != au_digen(dentry) ++ || sigen != au_iigen(dentry->d_inode)) { ++ err = au_reval_dpath(dentry, sigen); ++ if (unlikely(err < 0)) ++ goto out; ++ AuDebugOn(au_digen(dentry) != sigen ++ || au_iigen(dentry->d_inode) != sigen); ++ } ++ ++ err = refresh_file(file, reopen); ++ if (!err) { ++ if (!wlock) { ++ di_downgrade_lock(dentry, AuLock_IR); ++ fi_downgrade_lock(file); ++ } ++ } else { ++ di_write_unlock(dentry); ++ fi_write_unlock(file); ++ } ++ ++ out: ++ return err; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++/* cf. aufs_nopage() */ ++/* for madvise(2) */ ++static int aufs_readpage(struct file *file __maybe_unused, struct page *page) ++{ ++ unlock_page(page); ++ return 0; ++} ++ ++/* 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 void aufs_sync_page(struct page *page) ++{ AuUnsupport(); } ++ ++static int aufs_set_page_dirty(struct page *page) ++{ AuUnsupport(); return 0; } ++static void aufs_invalidatepage(struct page *page, unsigned long offset) ++{ AuUnsupport(); } ++static int aufs_releasepage(struct page *page, gfp_t gfp) ++{ AuUnsupport(); return 0; } ++static ssize_t aufs_direct_IO(int rw, struct kiocb *iocb, ++ const struct iovec *iov, loff_t offset, ++ unsigned long nr_segs) ++{ AuUnsupport(); return 0; } ++#endif /* CONFIG_AUFS_DEBUG */ ++ ++struct address_space_operations aufs_aop = { ++ .readpage = aufs_readpage, ++#ifdef CONFIG_AUFS_DEBUG ++ .writepage = aufs_writepage, ++ .sync_page = aufs_sync_page, ++ .set_page_dirty = aufs_set_page_dirty, ++ .write_begin = aufs_write_begin, ++ .write_end = aufs_write_end, ++ .invalidatepage = aufs_invalidatepage, ++ .releasepage = aufs_releasepage, ++ .direct_IO = aufs_direct_IO, ++#endif /* CONFIG_AUFS_DEBUG */ ++}; +diff -urN ./fs/aufs/file.h ./fs/aufs/file.h +--- ./fs/aufs/file.h 1970-01-01 01:00:00.000000000 +0100 ++++ ./fs/aufs/file.h 2009-04-06 10:26:46.000000000 +0200 +@@ -0,0 +1,148 @@ ++/* ++ * Copyright (C) 2005-2009 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. ++ */ ++ ++/* ++ * file operations ++ */ ++ ++#ifndef __AUFS_FILE_H__ ++#define __AUFS_FILE_H__ ++ ++#ifdef __KERNEL__ ++ ++#include <linux/file.h> ++#include <linux/fs.h> ++#include <linux/aufs_type.h> ++#include "rwsem.h" ++ ++struct au_branch; ++struct au_hfile { ++ struct file *hf_file; ++ struct au_branch *hf_br; ++}; ++ ++struct au_vdir; ++struct au_finfo { ++ atomic_t fi_generation; ++ ++ struct rw_semaphore fi_rwsem; ++ struct au_hfile *fi_hfile; ++ aufs_bindex_t fi_bstart, fi_bend; ++ ++ union { ++ /* non-dir only */ ++ struct vm_operations_struct *fi_h_vm_ops; ++ ++ /* dir only */ ++ struct { ++ struct au_vdir *fi_vdir_cache; ++ int fi_maintain_plink; ++ }; ++ }; ++}; ++ ++/* ---------------------------------------------------------------------- */ ++ ++/* file.c */ ++extern struct address_space_operations aufs_aop; ++void au_store_oflag(struct nameidata *nd, struct inode *inode); ++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 au_do_open(struct file *file, int (*open)(struct file *file, int flags)); ++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); ++ ++/* f_op.c */ ++extern const struct file_operations aufs_file_fop; ++int aufs_flush(struct file *file, fl_owner_t id); ++ ++/* finfo.c */ ++void au_hfput(struct au_hfile *hf, struct file *file); ++void au_set_h_fptr(struct file *file, aufs_bindex_t bindex, ++ struct file *h_file); ++ ++void au_update_figen(struct file *file); ++ ++void au_finfo_fin(struct file *file); ++int au_finfo_init(struct file *file); ++int au_fi_realloc(struct au_finfo *finfo, int nbr); ++ ++/* ---------------------------------------------------------------------- */ ++ ++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) ++ ++/* ---------------------------------------------------------------------- */ ++ ++/* todo: hard/soft set? */ ++static inline aufs_bindex_t au_fbstart(struct file *file) ++{ ++ return au_fi(file)->fi_bstart; ++} ++ ++static inline aufs_bindex_t au_fbend(struct file *file) ++{ ++ return au_fi(file)->fi_bend; ++} ++ ++static inline struct au_vdir *au_fvdir_cache(struct file *file) ++{ ++ return au_fi(file)->fi_vdir_cache; ++} ++ ++static inline void au_set_fbstart(struct file *file, aufs_bindex_t bindex) ++{ ++ au_fi(file)->fi_bstart = bindex; ++} ++ ++static inline void au_set_fbend(struct file *file, aufs_bindex_t bindex) ++{ ++ au_fi(file)->fi_bend = bindex; ++} ++ ++static inline void au_set_fvdir_cache(struct file *file, ++ struct au_vdir *vdir_cache) ++{ ++ au_fi(file)->fi_vdir_cache = vdir_cache; ++} ++ ++static inline struct file *au_h_fptr(struct file *file, aufs_bindex_t bindex) ++{ ++ return au_fi(file)->fi_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 int au_test_mmapped(struct file *f) ++{ ++ return !!(au_fi(f)->fi_h_vm_ops); ++} ++ ++#endif /* __KERNEL__ */ ++#endif /* __AUFS_FILE_H__ */ +diff -urN ./fs/aufs/finfo.c ./fs/aufs/finfo.c +--- ./fs/aufs/finfo.c 1970-01-01 01:00:00.000000000 +0100 ++++ ./fs/aufs/finfo.c 2009-04-06 10:26:46.000000000 +0200 +@@ -0,0 +1,124 @@ ++/* ++ * Copyright (C) 2005-2009 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. ++ */ ++ ++/* ++ * file private data ++ */ ++ ++#include "aufs.h" ++ ++void au_hfput(struct au_hfile *hf, struct file *file) ++{ ++ if (file->f_mode & FMODE_EXEC) ++ allow_write_access(hf->hf_file); ++ fput(hf->hf_file); ++ hf->hf_file = NULL; ++ atomic_dec(&hf->hf_br->br_count); ++ 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; ++ ++ hf = finfo->fi_hfile + bindex; ++ if (hf->hf_file) ++ au_hfput(hf, file); ++ if (val) { ++ hf->hf_file = val; ++ hf->hf_br = au_sbr(file->f_dentry->d_sb, bindex); ++ } ++} ++ ++void au_update_figen(struct file *file) ++{ ++ atomic_set(&au_fi(file)->fi_generation, au_digen(file->f_dentry)); ++ /* smp_mb(); */ /* atomic_set */ ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++void au_finfo_fin(struct file *file) ++{ ++ struct au_finfo *finfo; ++ aufs_bindex_t bindex, bend; ++ ++ fi_write_lock(file); ++ bend = au_fbend(file); ++ bindex = au_fbstart(file); ++ if (bindex >= 0) ++ /* ++ * calls fput() instead of filp_close(), ++ * since no dnotify or lock for the lower file. ++ */ ++ for (; bindex <= bend; bindex++) ++ au_set_h_fptr(file, bindex, NULL); ++ ++ finfo = au_fi(file); ++ au_dbg_verify_hf(finfo); ++ kfree(finfo->fi_hfile); ++ fi_write_unlock(file); ++ au_rwsem_destroy(&finfo->fi_rwsem); ++ au_cache_free_finfo(finfo); ++} ++ ++int au_finfo_init(struct file *file) ++{ ++ struct au_finfo *finfo; ++ struct dentry *dentry; ++ unsigned long ul; ++ ++ dentry = file->f_dentry; ++ finfo = au_cache_alloc_finfo(); ++ if (unlikely(!finfo)) ++ goto out; ++ ++ finfo->fi_hfile = kcalloc(au_sbend(dentry->d_sb) + 1, ++ sizeof(*finfo->fi_hfile), GFP_NOFS); ++ if (unlikely(!finfo->fi_hfile)) ++ goto out_finfo; ++ ++ init_rwsem(&finfo->fi_rwsem); ++ down_write(&finfo->fi_rwsem); ++ finfo->fi_bstart = -1; ++ finfo->fi_bend = -1; ++ atomic_set(&finfo->fi_generation, au_digen(dentry)); ++ /* smp_mb(); */ /* atomic_set */ ++ ++ /* cf. au_store_oflag() */ ++ /* suppress a warning in lp64 */ ++ ul = (unsigned long)file->private_data; ++ file->f_mode |= (vfsub_uint_to_fmode(ul) & FMODE_EXEC); ++ file->private_data = finfo; ++ return 0; /* success */ ++ ++ out_finfo: ++ au_cache_free_finfo(finfo); ++ out: ++ return -ENOMEM; ++} ++ ++int au_fi_realloc(struct au_finfo *finfo, int nbr) ++{ ++ int err, sz; ++ struct au_hfile *hfp; ++ ++ err = -ENOMEM; ++ sz = sizeof(*hfp) * (finfo->fi_bend + 1); ++ if (!sz) ++ sz = sizeof(*hfp); ++ hfp = au_kzrealloc(finfo->fi_hfile, sz, sizeof(*hfp) * nbr, GFP_NOFS); ++ if (hfp) { ++ finfo->fi_hfile = hfp; ++ err = 0; ++ } ++ ++ return err; ++} +diff -urN ./fs/aufs/fstype.h ./fs/aufs/fstype.h +--- ./fs/aufs/fstype.h 1970-01-01 01:00:00.000000000 +0100 ++++ ./fs/aufs/fstype.h 2009-04-06 10:26:46.000000000 +0200 +@@ -0,0 +1,454 @@ ++/* ++ * Copyright (C) 2005-2009 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. ++ */ ++ ++/* ++ * judging filesystem type ++ */ ++ ++#ifndef __AUFS_FSTYPE_H__ ++#define __AUFS_FSTYPE_H__ ++ ++#ifdef __KERNEL__ ++ ++#include <linux/fs.h> ++#include <linux/cramfs_fs.h> ++#include <linux/magic.h> ++#include <linux/romfs_fs.h> ++#include <linux/aufs_type.h> ++ ++static inline int au_test_aufs(struct super_block *sb) ++{ ++ return sb->s_magic == AUFS_SUPER_MAGIC; ++} ++ ++static inline const char *au_sbtype(struct super_block *sb) ++{ ++ return sb->s_type->name; ++} ++ ++static inline int au_test_iso9660(struct super_block *sb __maybe_unused) ++{ ++#if defined(CONFIG_ROMFS_FS) || defined(CONFIG_ROMFS_FS_MODULE) ++ return sb->s_magic == ROMFS_MAGIC; ++#else ++ return 0; ++#endif ++} ++ ++static inline int au_test_romfs(struct super_block *sb __maybe_unused) ++{ ++#if defined(CONFIG_ISO9660_FS) || defined(CONFIG_ISO9660_FS_MODULE) ++ return sb->s_magic == ISOFS_SUPER_MAGIC; ++#else ++ return 0; ++#endif ++} ++ ++static inline int au_test_cramfs(struct super_block *sb __maybe_unused) ++{ ++#if defined(CONFIG_CRAMFS) || defined(CONFIG_CRAMFS_MODULE) ++ return sb->s_magic == CRAMFS_MAGIC; ++#endif ++ return 0; ++} ++ ++static inline int au_test_nfs(struct super_block *sb __maybe_unused) ++{ ++#if defined(CONFIG_NFS_FS) || defined(CONFIG_NFS_FS_MODULE) ++ return sb->s_magic == NFS_SUPER_MAGIC; ++#else ++ return 0; ++#endif ++} ++ ++static inline int au_test_fuse(struct super_block *sb __maybe_unused) ++{ ++#if defined(CONFIG_FUSE_FS) || defined(CONFIG_FUSE_FS_MODULE) ++ return sb->s_magic == FUSE_SUPER_MAGIC; ++#else ++ return 0; ++#endif ++} ++ ++static inline int au_test_xfs(struct super_block *sb __maybe_unused) ++{ ++#if defined(CONFIG_XFS_FS) || defined(CONFIG_XFS_FS_MODULE) ++ return sb->s_magic == XFS_SB_MAGIC; ++#else ++ return 0; ++#endif ++} ++ ++static inline int au_test_tmpfs(struct super_block *sb __maybe_unused) ++{ ++#ifdef CONFIG_TMPFS ++ return sb->s_magic == TMPFS_MAGIC; ++#else ++ return 0; ++#endif ++} ++ ++static inline int au_test_ecryptfs(struct super_block *sb __maybe_unused) ++{ ++#if defined(CONFIG_ECRYPT_FS) || defined(CONFIG_ECRYPT_FS_MODULE) ++ return !strcmp(au_sbtype(sb), "ecryptfs"); ++#else ++ return 0; ++#endif ++} ++ ++static inline int au_test_smbfs(struct super_block *sb __maybe_unused) ++{ ++#if defined(CONFIG_SMB_FS) || defined(CONFIG_SMB_FS_MODULE) ++ return sb->s_magic == SMB_SUPER_MAGIC; ++#else ++ return 0; ++#endif ++} ++ ++static inline int au_test_ocfs2(struct super_block *sb __maybe_unused) ++{ ++#if defined(CONFIG_OCFS2_FS) || defined(CONFIG_OCFS2_FS_MODULE) ++ return sb->s_magic == OCFS2_SUPER_MAGIC; ++#else ++ return 0; ++#endif ++} ++ ++static inline int au_test_ocfs2_dlmfs(struct super_block *sb __maybe_unused) ++{ ++#if defined(CONFIG_OCFS2_FS_O2CB) || defined(CONFIG_OCFS2_FS_O2CB_MODULE) ++ return sb->s_magic == DLMFS_MAGIC; ++#else ++ return 0; ++#endif ++} ++ ++static inline int au_test_coda(struct super_block *sb __maybe_unused) ++{ ++#if defined(CONFIG_CODA_FS) || defined(CONFIG_CODA_FS_MODULE) ++ return sb->s_magic == CODA_SUPER_MAGIC; ++#else ++ return 0; ++#endif ++} ++ ++static inline int au_test_v9fs(struct super_block *sb __maybe_unused) ++{ ++#if defined(CONFIG_9P_FS) || defined(CONFIG_9P_FS_MODULE) ++ return sb->s_magic == V9FS_MAGIC; ++#else ++ return 0; ++#endif ++} ++ ++static inline int au_test_ext4(struct super_block *sb __maybe_unused) ++{ ++#if defined(CONFIG_EXT4DEV_FS) || defined(CONFIG_EXT4DEV_FS_MODULE) ++ return sb->s_magic == EXT4_SUPER_MAGIC; ++#else ++ return 0; ++#endif ++} ++ ++static inline int au_test_sysv(struct super_block *sb __maybe_unused) ++{ ++#if defined(CONFIG_SYSV_FS) || defined(CONFIG_SYSV_FS_MODULE) ++ return !strcmp(au_sbtype(sb), "sysv"); ++#else ++ return 0; ++#endif ++} ++ ++static inline int au_test_ramfs(struct super_block *sb) ++{ ++ return sb->s_magic == RAMFS_MAGIC; ++} ++ ++static inline int au_test_ubifs(struct super_block *sb __maybe_unused) ++{ ++#if defined(CONFIG_UBIFS_FS) || defined(CONFIG_UBIFS_FS_MODULE) ++ return sb->s_magic == UBIFS_SUPER_MAGIC; ++#else ++ return 0; ++#endif ++} ++ ++static inline int au_test_procfs(struct super_block *sb __maybe_unused) ++{ ++#ifdef CONFIG_PROC_FS ++ return sb->s_magic == PROC_SUPER_MAGIC; ++#else ++ return 0; ++#endif ++} ++ ++static inline int au_test_sysfs(struct super_block *sb __maybe_unused) ++{ ++#ifdef CONFIG_SYSFS ++ return sb->s_magic == SYSFS_MAGIC; ++#else ++ return 0; ++#endif ++} ++ ++static inline int au_test_configfs(struct super_block *sb __maybe_unused) ++{ ++#if defined(CONFIG_CONFIGFS_FS) || defined(CONFIG_CONFIGFS_FS_MODULE) ++ return sb->s_magic == CONFIGFS_MAGIC; ++#else ++ return 0; ++#endif ++} ++ ++static inline int au_test_minix(struct super_block *sb __maybe_unused) ++{ ++#if defined(CONFIG_MINIX_FS) || defined(CONFIG_MINIX_FS_MODULE) ++ return sb->s_magic == MINIX3_SUPER_MAGIC ++ || sb->s_magic == MINIX2_SUPER_MAGIC ++ || sb->s_magic == MINIX2_SUPER_MAGIC2 ++ || sb->s_magic == MINIX_SUPER_MAGIC ++ || sb->s_magic == MINIX_SUPER_MAGIC2; ++#else ++ return 0; ++#endif ++} ++ ++static inline int au_test_cifs(struct super_block *sb __maybe_unused) ++{ ++#if defined(CONFIG_CIFS_FS) || defined(CONFIGCIFS_FS_MODULE) ++ return sb->s_magic == CIFS_MAGIC_NUMBER; ++#else ++ return 0; ++#endif ++} ++ ++static inline int au_test_fat(struct super_block *sb __maybe_unused) ++{ ++#if defined(CONFIG_FAT_FS) || defined(CONFIG_FAT_FS_MODULE) ++ return sb->s_magic == MSDOS_SUPER_MAGIC; ++#else ++ return 0; ++#endif ++} ++ ++static inline int au_test_msdos(struct super_block *sb) ++{ ++ return au_test_fat(sb); ++} ++ ++static inline int au_test_vfat(struct super_block *sb) ++{ ++ return au_test_fat(sb); ++} ++ ++static inline int au_test_securityfs(struct super_block *sb __maybe_unused) ++{ ++#ifdef CONFIG_SECURITYFS ++ return sb->s_magic == SECURITYFS_MAGIC; ++#else ++ return 0; ++#endif ++} ++ ++static inline int au_test_squashfs(struct super_block *sb __maybe_unused) ++{ ++#if defined(CONFIG_SQUASHFS) || defined(CONFIG_SQUASHFS_MODULE) ++ return sb->s_magic == SQUASHFS_MAGIC; ++#else ++ return 0; ++#endif ++} ++ ++static inline int au_test_btrfs(struct super_block *sb __maybe_unused) ++{ ++#if defined(CONFIG_BTRFS_FS) || defined(CONFIG_BTRFS_FS_MODULE) ++ return sb->s_magic == BTRFS_SUPER_MAGIC; ++#else ++ return 0; ++#endif ++} ++ ++static inline int au_test_xenfs(struct super_block *sb __maybe_unused) ++{ ++#if defined(CONFIG_XENFS) || defined(CONFIG_XENFS_MODULE) ++ return sb->s_magic == XENFS_SUPER_MAGIC; ++#else ++ return 0; ++#endif ++} ++ ++static inline int au_test_debugfs(struct super_block *sb __maybe_unused) ++{ ++#ifdef CONFIG_DEBUG_FS ++ return sb->s_magic == DEBUGFS_MAGIC; ++#else ++ return 0; ++#endif ++} ++ ++/* ---------------------------------------------------------------------- */ ++/* ++ * they can't be an aufs branch. ++ */ ++static inline int au_test_fs_unsuppoted(struct super_block *sb) ++{ ++ return ++#ifndef CONFIG_AUFS_BR_RAMFS ++ au_test_ramfs(sb) || ++#endif ++ au_test_procfs(sb) ++ || au_test_sysfs(sb) ++ || au_test_configfs(sb) ++ || au_test_debugfs(sb) ++ || au_test_securityfs(sb) ++ || au_test_xenfs(sb) ++ /* || !strcmp(au_sbtype(sb), "unionfs") */ ++ || au_test_aufs(sb); /* will be supported in next version */ ++} ++ ++/* ++ * If the filesystem supports NFS-export, then it has to support NULL as ++ * a nameidata parameter for ->create(), ->lookup() and ->d_revalidate(). ++ * We can apply this principle when we handle a lower filesystem. ++ */ ++static inline int au_test_fs_null_nd(struct super_block *sb) ++{ ++ return !!sb->s_export_op; ++} ++ ++static inline int au_test_fs_remote(struct super_block *sb) ++{ ++ return !au_test_tmpfs(sb) ++#ifdef CONFIG_AUFS_BR_RAMFS ++ && !au_test_ramfs(sb) ++#endif ++ && !(sb->s_type->fs_flags & FS_REQUIRES_DEV); ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++/* ++ * Note: these functions (below) are created after reading ->getattr() in all ++ * filesystems under linux/fs. it means we have to do so in every update... ++ */ ++ ++/* ++ * some filesystems require getattr to refresh the inode attributes before ++ * referencing. ++ * in most cases, we can rely on the inode attribute in NFS (or every remote fs) ++ * and leave the work for d_revalidate() ++ */ ++static inline int au_test_fs_refresh_iattr(struct super_block *sb) ++{ ++ return au_test_nfs(sb) ++ || au_test_fuse(sb) ++ /* || au_test_smbfs(sb) */ /* untested */ ++ /* || au_test_ocfs2(sb) */ /* untested */ ++ /* || au_test_btrfs(sb) */ /* untested */ ++ /* || au_test_coda(sb) */ /* untested */ ++ /* || au_test_v9fs(sb) */ /* untested */ ++ ; ++} ++ ++/* ++ * filesystems which don't maintain i_size or i_blocks. ++ */ ++static inline int au_test_fs_bad_iattr_size(struct super_block *sb) ++{ ++ return au_test_xfs(sb) ++ /* || au_test_ext4(sb) */ /* untested */ ++ /* || au_test_ocfs2(sb) */ /* untested */ ++ /* || au_test_ocfs2_dlmfs(sb) */ /* untested */ ++ /* || au_test_sysv(sb) */ /* untested */ ++ /* || au_test_ubifs(sb) */ /* untested */ ++ /* || au_test_minix(sb) */ /* untested */ ++ ; ++} ++ ++/* ++ * filesystems which don't store the correct value in some of their inode ++ * attributes. ++ */ ++static inline int au_test_fs_bad_iattr(struct super_block *sb) ++{ ++ return au_test_fs_bad_iattr_size(sb) ++ /* || au_test_cifs(sb) */ /* untested */ ++ || au_test_fat(sb) ++ || au_test_msdos(sb) ++ || au_test_vfat(sb); ++} ++ ++/* ++ * filesystems which sets S_NOATIME and S_NOCMTIME. ++ */ ++static inline int au_test_fs_notime(struct super_block *sb) ++{ ++ return au_test_nfs(sb) ++ || au_test_fuse(sb) ++ /* || au_test_cifs(sb) */ /* untested */ ++ /* || au_test_ubifs(sb) */ /* untested */ ++ ; ++} ++ ++/* ++ * filesystems which requires replacing i_mapping. ++ */ ++static inline int au_test_fs_bad_mapping(struct super_block *sb) ++{ ++ return au_test_fuse(sb); ++} ++ ++/* temporary support for i#1 in cramfs */ ++static inline int au_test_fs_unique_ino(struct inode *inode) ++{ ++ if (au_test_cramfs(inode->i_sb)) ++ return inode->i_ino != 1; ++ return 1; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++/* ++ * the filesystem where the xino files placed must support i/o after unlink and ++ * maintain i_size and i_blocks. ++ */ ++static inline int au_test_fs_bad_xino(struct super_block *sb) ++{ ++ return au_test_fs_remote(sb) ++ || au_test_fs_bad_iattr_size(sb) ++#ifdef CONFIG_AUFS_BR_RAMFS ++ || !(au_test_ramfs(sb) || au_test_fs_null_nd(sb)) ++#else ++ || !au_test_fs_null_nd(sb) /* to keep xino code simple */ ++#endif ++ /* don't want unnecessary work for xino */ ++ || au_test_aufs(sb) ++ || au_test_ecryptfs(sb); ++} ++ ++static inline int au_test_fs_trunc_xino(struct super_block *sb) ++{ ++ return au_test_tmpfs(sb) ++ || au_test_ramfs(sb); ++} ++ ++/* ++ * test if the @sb is real-readonly. ++ */ ++static inline int au_test_fs_rr(struct super_block *sb) ++{ ++ return au_test_squashfs(sb) ++ || au_test_iso9660(sb) ++ || au_test_cramfs(sb) ++ || au_test_romfs(sb); ++} ++ ++#endif /* __KERNEL__ */ ++#endif /* __AUFS_FSTYPE_H__ */ +diff -urN ./fs/aufs/hinotify.c ./fs/aufs/hinotify.c +--- ./fs/aufs/hinotify.c 1970-01-01 01:00:00.000000000 +0100 ++++ ./fs/aufs/hinotify.c 2009-04-06 10:26:46.000000000 +0200 +@@ -0,0 +1,746 @@ ++/* ++ * Copyright (C) 2005-2009 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. ++ */ ++ ++/* ++ * inotify for the lower directories ++ */ ++ ++#include "aufs.h" ++ ++static const __u32 AuHinMask = (IN_MOVE | IN_DELETE | IN_CREATE); ++static struct inotify_handle *au_hin_handle; ++ ++AuCacheFuncs(hinotify, HINOTIFY); ++ ++int au_hin_alloc(struct au_hinode *hinode, struct inode *inode, ++ struct inode *h_inode) ++{ ++ int err; ++ struct au_hinotify *hin; ++ s32 wd; ++ ++ err = -ENOMEM; ++ hin = au_cache_alloc_hinotify(); ++ if (hin) { ++ AuDebugOn(hinode->hi_notify); ++ hinode->hi_notify = hin; ++ hin->hin_aufs_inode = inode; ++ ++ inotify_init_watch(&hin->hin_watch); ++ wd = inotify_add_watch(au_hin_handle, &hin->hin_watch, h_inode, ++ AuHinMask); ++ if (wd >= 0) ++ return 0; /* success */ ++ ++ err = wd; ++ put_inotify_watch(&hin->hin_watch); ++ au_cache_free_hinotify(hin); ++ hinode->hi_notify = NULL; ++ } ++ ++ return err; ++} ++ ++void au_hin_free(struct au_hinode *hinode) ++{ ++ int err; ++ struct au_hinotify *hin; ++ ++ hin = hinode->hi_notify; ++ if (hin) { ++ err = 0; ++ if (atomic_read(&hin->hin_watch.count)) ++ err = inotify_rm_watch(au_hin_handle, &hin->hin_watch); ++ if (unlikely(err)) ++ /* it means the watch is already removed */ ++ AuWarn("failed inotify_rm_watch() %d\n", err); ++ au_cache_free_hinotify(hin); ++ hinode->hi_notify = NULL; ++ } ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++void au_hin_ctl(struct au_hinode *hinode, int do_set) ++{ ++ struct inode *h_inode; ++ struct inotify_watch *watch; ++ ++ if (!hinode->hi_notify) ++ return; ++ ++ h_inode = hinode->hi_inode; ++ IMustLock(h_inode); ++ ++ /* todo: try inotify_find_update_watch()? */ ++ watch = &hinode->hi_notify->hin_watch; ++ mutex_lock(&h_inode->inotify_mutex); ++ /* mutex_lock(&watch->ih->mutex); */ ++ if (do_set) { ++ AuDebugOn(watch->mask & AuHinMask); ++ watch->mask |= AuHinMask; ++ } else { ++ AuDebugOn(!(watch->mask & AuHinMask)); ++ watch->mask &= ~AuHinMask; ++ } ++ /* mutex_unlock(&watch->ih->mutex); */ ++ mutex_unlock(&h_inode->inotify_mutex); ++} ++ ++void au_reset_hinotify(struct inode *inode, unsigned int flags) ++{ ++ aufs_bindex_t bindex, bend; ++ struct inode *hi; ++ struct dentry *iwhdentry; ++ ++ bend = au_ibend(inode); ++ for (bindex = au_ibstart(inode); bindex <= bend; bindex++) { ++ hi = au_h_iptr(inode, bindex); ++ if (!hi) ++ continue; ++ ++ /* mutex_lock_nested(&hi->i_mutex, AuLsc_I_CHILD); */ ++ iwhdentry = au_hi_wh(inode, bindex); ++ if (iwhdentry) ++ dget(iwhdentry); ++ au_igrab(hi); ++ au_set_h_iptr(inode, bindex, NULL, 0); ++ au_set_h_iptr(inode, bindex, au_igrab(hi), ++ flags & ~AuHi_XINO); ++ iput(hi); ++ dput(iwhdentry); ++ /* mutex_unlock(&hi->i_mutex); */ ++ } ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++static int hin_xino(struct inode *inode, struct inode *h_inode) ++{ ++ int err; ++ aufs_bindex_t bindex, bend, bfound, bstart; ++ struct inode *h_i; ++ ++ err = 0; ++ if (unlikely(inode->i_ino == AUFS_ROOT_INO)) { ++ AuWarn("branch root dir was changed\n"); ++ goto out; ++ } ++ ++ bfound = -1; ++ bend = au_ibend(inode); ++ bstart = au_ibstart(inode); ++#if 0 /* reserved for future use */ ++ if (bindex == bend) { ++ /* keep this ino in rename case */ ++ goto out; ++ } ++#endif ++ for (bindex = bstart; bindex <= bend; bindex++) { ++ if (au_h_iptr(inode, bindex) == h_inode) { ++ bfound = bindex; ++ break; ++ } ++ } ++ if (bfound < 0) ++ goto out; ++ ++ for (bindex = bstart; bindex <= bend; bindex++) { ++ h_i = au_h_iptr(inode, bindex); ++ if (!h_i) ++ continue; ++ ++ err = au_xino_write0(inode->i_sb, bindex, h_i->i_ino, 0); ++ /* ignore this error */ ++ /* bad action? */ ++ } ++ ++ /* children inode number will be broken */ ++ ++ out: ++ AuTraceErr(err); ++ return err; ++} ++ ++static int hin_gen_tree(struct dentry *dentry) ++{ ++ int err, i, j, ndentry; ++ struct au_dcsub_pages dpages; ++ struct au_dpage *dpage; ++ struct dentry **dentries; ++ ++ err = au_dpages_init(&dpages, GFP_NOFS); ++ if (unlikely(err)) ++ goto out; ++ err = au_dcsub_pages(&dpages, dentry, NULL, NULL); ++ if (unlikely(err)) ++ goto out_dpages; ++ ++ for (i = 0; i < dpages.ndpage; i++) { ++ dpage = dpages.dpages + i; ++ dentries = dpage->dentries; ++ ndentry = dpage->ndentry; ++ for (j = 0; j < ndentry; j++) { ++ struct dentry *d; ++ ++ d = dentries[j]; ++ if (IS_ROOT(d)) ++ continue; ++ ++ d_drop(d); ++ au_digen_dec(d); ++ if (d->d_inode) ++ /* todo: reset children xino? ++ cached children only? */ ++ au_iigen_dec(d->d_inode); ++ } ++ } ++ ++ out_dpages: ++ au_dpages_free(&dpages); ++ ++ /* discard children */ ++ dentry_unhash(dentry); ++ dput(dentry); ++ out: ++ return err; ++} ++ ++/* ++ * return 0 if processed. ++ */ ++static int hin_gen_by_inode(char *name, unsigned int nlen, struct inode *inode, ++ const unsigned int isdir) ++{ ++ int err; ++ struct dentry *d; ++ struct qstr *dname; ++ ++ err = 1; ++ if (unlikely(inode->i_ino == AUFS_ROOT_INO)) { ++ AuWarn("branch root dir was changed\n"); ++ err = 0; ++ goto out; ++ } ++ ++ if (!isdir) { ++ AuDebugOn(!name); ++ au_iigen_dec(inode); ++ spin_lock(&dcache_lock); ++ list_for_each_entry(d, &inode->i_dentry, d_alias) { ++ dname = &d->d_name; ++ if (dname->len != nlen ++ && memcmp(dname->name, name, nlen)) ++ continue; ++ err = 0; ++ spin_lock(&d->d_lock); ++ __d_drop(d); ++ au_digen_dec(d); ++ spin_unlock(&d->d_lock); ++ break; ++ } ++ spin_unlock(&dcache_lock); ++ } else { ++ au_fset_si(au_sbi(inode->i_sb), FAILED_REFRESH_DIRS); ++ d = d_find_alias(inode); ++ if (!d) { ++ au_iigen_dec(inode); ++ goto out; ++ } ++ ++ dname = &d->d_name; ++ if (dname->len == nlen && !memcmp(dname->name, name, nlen)) ++ err = hin_gen_tree(d); ++ dput(d); ++ } ++ ++ out: ++ AuTraceErr(err); ++ return err; ++} ++ ++static int hin_gen_by_name(struct dentry *dentry, const unsigned int isdir) ++{ ++ int err; ++ struct inode *inode; ++ ++ inode = dentry->d_inode; ++ if (IS_ROOT(dentry) ++ /* || (inode && inode->i_ino == AUFS_ROOT_INO) */ ++ ) { ++ AuWarn("branch root dir was changed\n"); ++ return 0; ++ } ++ ++ err = 0; ++ if (!isdir) { ++ d_drop(dentry); ++ au_digen_dec(dentry); ++ if (inode) ++ au_iigen_dec(inode); ++ } else { ++ au_fset_si(au_sbi(dentry->d_sb), FAILED_REFRESH_DIRS); ++ if (inode) ++ err = hin_gen_tree(dentry); ++ } ++ ++ AuTraceErr(err); ++ return err; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++/* hinotify job flags */ ++#define AuHinJob_XINO0 1 ++#define AuHinJob_GEN (1 << 1) ++#define AuHinJob_DIRENT (1 << 2) ++#define AuHinJob_ISDIR (1 << 3) ++#define AuHinJob_TRYXINO0 (1 << 4) ++#define AuHinJob_MNTPNT (1 << 5) ++#define au_ftest_hinjob(flags, name) ((flags) & AuHinJob_##name) ++#define au_fset_hinjob(flags, name) { (flags) |= AuHinJob_##name; } ++#define au_fclr_hinjob(flags, name) { (flags) &= ~AuHinJob_##name; } ++ ++struct hin_job_args { ++ unsigned int flags; ++ struct inode *inode, *h_inode, *dir, *h_dir; ++ struct dentry *dentry; ++ char *h_name; ++ int h_nlen; ++}; ++ ++static int hin_job(struct hin_job_args *a) ++{ ++ const unsigned int isdir = au_ftest_hinjob(a->flags, ISDIR); ++ ++ /* reset xino */ ++ if (au_ftest_hinjob(a->flags, XINO0) && a->inode) ++ hin_xino(a->inode, a->h_inode); /* ignore this error */ ++ ++ if (au_ftest_hinjob(a->flags, TRYXINO0) ++ && a->inode ++ && a->h_inode) { ++ mutex_lock_nested(&a->h_inode->i_mutex, AuLsc_I_CHILD); ++ if (!a->h_inode->i_nlink) ++ hin_xino(a->inode, a->h_inode); /* ignore this error */ ++ mutex_unlock(&a->h_inode->i_mutex); ++ } ++ ++ /* make the generation obsolete */ ++ if (au_ftest_hinjob(a->flags, GEN)) { ++ int err = -1; ++ if (a->inode) ++ err = hin_gen_by_inode(a->h_name, a->h_nlen, a->inode, ++ isdir); ++ if (err && a->dentry) ++ hin_gen_by_name(a->dentry, isdir); ++ /* ignore this error */ ++ } ++ ++ /* make dir entries obsolete */ ++ if (au_ftest_hinjob(a->flags, DIRENT) && a->inode) { ++ struct au_vdir *vdir; ++ ++ vdir = au_ivdir(a->inode); ++ if (vdir) ++ vdir->vd_jiffy = 0; ++ /* IMustLock(a->inode); */ ++ /* a->inode->i_version++; */ ++ } ++ ++ /* can do nothing but warn */ ++ if (au_ftest_hinjob(a->flags, MNTPNT) ++ && a->dentry ++ && d_mountpoint(a->dentry)) ++ AuWarn("mount-point %.*s is removed or renamed\n", ++ AuDLNPair(a->dentry)); ++ ++ return 0; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++static char *in_name(u32 mask) ++{ ++#ifdef CONFIG_AUFS_DEBUG ++#define test_ret(flag) if (mask & flag) \ ++ return #flag; ++ test_ret(IN_ACCESS); ++ test_ret(IN_MODIFY); ++ test_ret(IN_ATTRIB); ++ test_ret(IN_CLOSE_WRITE); ++ test_ret(IN_CLOSE_NOWRITE); ++ test_ret(IN_OPEN); ++ test_ret(IN_MOVED_FROM); ++ test_ret(IN_MOVED_TO); ++ test_ret(IN_CREATE); ++ test_ret(IN_DELETE); ++ test_ret(IN_DELETE_SELF); ++ test_ret(IN_MOVE_SELF); ++ test_ret(IN_UNMOUNT); ++ test_ret(IN_Q_OVERFLOW); ++ test_ret(IN_IGNORED); ++ return ""; ++#undef test_ret ++#else ++ return "??"; ++#endif ++} ++ ++static struct dentry *lookup_wlock_by_name(char *name, unsigned int nlen, ++ struct inode *dir) ++{ ++ struct dentry *dentry, *d, *parent; ++ struct qstr *dname; ++ ++ parent = d_find_alias(dir); ++ if (!parent) ++ return NULL; ++ ++ dentry = NULL; ++ spin_lock(&dcache_lock); ++ list_for_each_entry(d, &parent->d_subdirs, d_u.d_child) { ++ /* AuDbg("%.*s\n", AuDLNPair(d)); */ ++ dname = &d->d_name; ++ if (dname->len != nlen || memcmp(dname->name, name, nlen)) ++ continue; ++ if (!atomic_read(&d->d_count) || !d->d_fsdata) { ++ spin_lock(&d->d_lock); ++ __d_drop(d); ++ spin_unlock(&d->d_lock); ++ continue; ++ } ++ ++ dentry = dget(d); ++ break; ++ } ++ spin_unlock(&dcache_lock); ++ dput(parent); ++ ++ if (dentry) ++ di_write_lock_child(dentry); ++ ++ return dentry; ++} ++ ++static struct inode *lookup_wlock_by_ino(struct super_block *sb, ++ aufs_bindex_t bindex, ino_t h_ino) ++{ ++ struct inode *inode; ++ ino_t ino; ++ int err; ++ ++ inode = NULL; ++ err = au_xino_read(sb, bindex, h_ino, &ino); ++ if (!err && ino) ++ inode = ilookup(sb, ino); ++ if (!inode) ++ goto out; ++ ++ if (unlikely(inode->i_ino == AUFS_ROOT_INO)) { ++ AuWarn("wrong root branch\n"); ++ iput(inode); ++ inode = NULL; ++ goto out; ++ } ++ ++ ii_write_lock_child(inode); ++ ++ out: ++ return inode; ++} ++ ++enum { CHILD, PARENT }; ++struct postproc_args { ++ struct inode *h_dir, *dir, *h_child_inode; ++ u32 mask; ++ unsigned int flags[2]; ++ unsigned int h_child_nlen; ++ char h_child_name[]; ++}; ++ ++static void postproc(void *_args) ++{ ++ struct postproc_args *a = _args; ++ struct super_block *sb; ++ aufs_bindex_t bindex, bend, bfound; ++ unsigned char xino, try_iput; ++ int err; ++ struct inode *inode; ++ ino_t h_ino; ++ struct hin_job_args args; ++ struct dentry *dentry; ++ struct au_sbinfo *sbinfo; ++ ++ AuDebugOn(!_args); ++ AuDebugOn(!a->h_dir); ++ AuDebugOn(!a->dir); ++ AuDebugOn(!a->mask); ++ AuDbg("mask 0x%x %s, i%lu, hi%lu, hci%lu\n", ++ a->mask, in_name(a->mask), a->dir->i_ino, a->h_dir->i_ino, ++ a->h_child_inode ? a->h_child_inode->i_ino : 0); ++ ++ inode = NULL; ++ dentry = NULL; ++ /* ++ * do not lock a->dir->i_mutex here ++ * because of d_revalidate() may cause a deadlock. ++ */ ++ sb = a->dir->i_sb; ++ AuDebugOn(!sb); ++ sbinfo = au_sbi(sb); ++ AuDebugOn(!sbinfo); ++ /* big aufs lock */ ++ si_noflush_write_lock(sb); ++ ++ ii_read_lock_parent(a->dir); ++ bfound = -1; ++ bend = au_ibend(a->dir); ++ for (bindex = au_ibstart(a->dir); bindex <= bend; bindex++) ++ if (au_h_iptr(a->dir, bindex) == a->h_dir) { ++ bfound = bindex; ++ break; ++ } ++ ii_read_unlock(a->dir); ++ if (unlikely(bfound < 0)) ++ goto out; ++ ++ xino = !!au_opt_test(au_mntflags(sb), XINO); ++ h_ino = 0; ++ if (a->h_child_inode) ++ h_ino = a->h_child_inode->i_ino; ++ ++ if (a->h_child_nlen ++ && (au_ftest_hinjob(a->flags[CHILD], GEN) ++ || au_ftest_hinjob(a->flags[CHILD], MNTPNT))) ++ dentry = lookup_wlock_by_name(a->h_child_name, a->h_child_nlen, ++ a->dir); ++ try_iput = 0; ++ if (dentry) ++ inode = dentry->d_inode; ++ if (xino && !inode && h_ino ++ && (au_ftest_hinjob(a->flags[CHILD], XINO0) ++ || au_ftest_hinjob(a->flags[CHILD], TRYXINO0) ++ || au_ftest_hinjob(a->flags[CHILD], GEN))) { ++ inode = lookup_wlock_by_ino(sb, bfound, h_ino); ++ try_iput = 1; ++ } ++ ++ args.flags = a->flags[CHILD]; ++ args.dentry = dentry; ++ args.inode = inode; ++ args.h_inode = a->h_child_inode; ++ args.dir = a->dir; ++ args.h_dir = a->h_dir; ++ args.h_name = a->h_child_name; ++ args.h_nlen = a->h_child_nlen; ++ err = hin_job(&args); ++ if (dentry) { ++ if (dentry->d_fsdata) ++ di_write_unlock(dentry); ++ dput(dentry); ++ } ++ if (inode && try_iput) { ++ ii_write_unlock(inode); ++ iput(inode); ++ } ++ ++ ii_write_lock_parent(a->dir); ++ args.flags = a->flags[PARENT]; ++ args.dentry = NULL; ++ args.inode = a->dir; ++ args.h_inode = a->h_dir; ++ args.dir = NULL; ++ args.h_dir = NULL; ++ args.h_name = NULL; ++ args.h_nlen = 0; ++ err = hin_job(&args); ++ ii_write_unlock(a->dir); ++ ++ out: ++ au_nwt_done(&sbinfo->si_nowait); ++ si_write_unlock(sb); ++ ++ iput(a->h_child_inode); ++ iput(a->h_dir); ++ iput(a->dir); ++ kfree(a); ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++static void aufs_inotify(struct inotify_watch *watch, u32 wd __maybe_unused, ++ u32 mask, u32 cookie __maybe_unused, ++ const char *h_child_name, struct inode *h_child_inode) ++{ ++ struct au_hinotify *hinotify; ++ struct postproc_args *args; ++ int len, wkq_err; ++ unsigned char isdir, isroot, wh; ++ char *p; ++ struct inode *dir; ++ unsigned int flags[2]; ++ ++ /* if IN_UNMOUNT happens, there must be another bug */ ++ AuDebugOn(mask & IN_UNMOUNT); ++ if (mask & (IN_IGNORED | IN_UNMOUNT)) { ++ put_inotify_watch(watch); ++ return; ++ } ++#ifdef AuDbgHinotify ++ au_debug(1); ++ if (1 || !h_child_name || strcmp(h_child_name, AUFS_XINO_FNAME)) { ++ AuDbg("i%lu, wd %d, mask 0x%x %s, cookie 0x%x, hcname %s," ++ " hi%lu\n", ++ watch->inode->i_ino, wd, mask, in_name(mask), cookie, ++ h_child_name ? h_child_name : "", ++ h_child_inode ? h_child_inode->i_ino : 0); ++ WARN_ON(1); ++ } ++ au_debug(0); ++#endif ++ ++ hinotify = container_of(watch, struct au_hinotify, hin_watch); ++ AuDebugOn(!hinotify || !hinotify->hin_aufs_inode); ++ dir = igrab(hinotify->hin_aufs_inode); ++ if (!dir) ++ return; ++ ++ isroot = (dir->i_ino == AUFS_ROOT_INO); ++ len = 0; ++ wh = 0; ++ if (h_child_name) { ++ len = strlen(h_child_name); ++ if (!memcmp(h_child_name, AUFS_WH_PFX, AUFS_WH_PFX_LEN)) { ++ h_child_name += AUFS_WH_PFX_LEN; ++ len -= AUFS_WH_PFX_LEN; ++ wh = 1; ++ } ++ } ++ ++ isdir = 0; ++ if (h_child_inode) ++ isdir = !!S_ISDIR(h_child_inode->i_mode); ++ flags[PARENT] = AuHinJob_ISDIR; ++ flags[CHILD] = 0; ++ if (isdir) ++ flags[CHILD] = AuHinJob_ISDIR; ++ switch (mask & IN_ALL_EVENTS) { ++ case IN_MOVED_FROM: ++ case IN_MOVED_TO: ++ AuDebugOn(!h_child_name || !h_child_inode); ++ au_fset_hinjob(flags[CHILD], GEN); ++ au_fset_hinjob(flags[CHILD], XINO0); ++ au_fset_hinjob(flags[CHILD], MNTPNT); ++ au_fset_hinjob(flags[PARENT], DIRENT); ++ break; ++ ++ case IN_CREATE: ++ AuDebugOn(!h_child_name || !h_child_inode); ++ au_fset_hinjob(flags[PARENT], DIRENT); ++ au_fset_hinjob(flags[CHILD], GEN); ++ break; ++ ++ case IN_DELETE: ++ /* ++ * aufs never be able to get this child inode. ++ * revalidation should be in d_revalidate() ++ * by checking i_nlink, i_generation or d_unhashed(). ++ */ ++ AuDebugOn(!h_child_name); ++ au_fset_hinjob(flags[PARENT], DIRENT); ++ au_fset_hinjob(flags[CHILD], GEN); ++ au_fset_hinjob(flags[CHILD], TRYXINO0); ++ au_fset_hinjob(flags[CHILD], MNTPNT); ++ break; ++ ++ default: ++ AuDebugOn(1); ++ } ++ ++ if (wh) ++ h_child_inode = NULL; ++ ++ /* iput() and kfree() will be called in postproc() */ ++ /* ++ * inotify_mutex is already acquired and kmalloc/prune_icache may lock ++ * iprune_mutex. strange. ++ */ ++ lockdep_off(); ++ args = kmalloc(sizeof(*args) + len + 1, GFP_NOFS); ++ lockdep_on(); ++ if (unlikely(!args)) { ++ AuErr1("no memory\n"); ++ iput(dir); ++ return; ++ } ++ args->flags[PARENT] = flags[PARENT]; ++ args->flags[CHILD] = flags[CHILD]; ++ args->mask = mask; ++ args->dir = dir; ++ args->h_dir = igrab(watch->inode); ++ if (h_child_inode) ++ h_child_inode = igrab(h_child_inode); /* can be NULL */ ++ args->h_child_inode = h_child_inode; ++ args->h_child_nlen = len; ++ if (len) { ++ p = (void *)args; ++ p += sizeof(*args); ++ memcpy(p, h_child_name, len + 1); ++ } ++ ++ lockdep_off(); ++ wkq_err = au_wkq_nowait(postproc, args, dir->i_sb); ++ lockdep_on(); ++ if (unlikely(wkq_err)) ++ AuErr("wkq %d\n", wkq_err); ++} ++ ++static void aufs_inotify_destroy(struct inotify_watch *watch __maybe_unused) ++{ ++ return; ++} ++ ++static struct inotify_operations aufs_inotify_ops = { ++ .handle_event = aufs_inotify, ++ .destroy_watch = aufs_inotify_destroy ++}; ++ ++/* ---------------------------------------------------------------------- */ ++ ++static void au_hin_destroy_cache(void) ++{ ++ kmem_cache_destroy(au_cachep[AuCache_HINOTIFY]); ++ au_cachep[AuCache_HINOTIFY] = NULL; ++} ++ ++int __init au_hinotify_init(void) ++{ ++ int err; ++ ++ err = -ENOMEM; ++ au_cachep[AuCache_HINOTIFY] = AuCache(au_hinotify); ++ if (au_cachep[AuCache_HINOTIFY]) { ++ err = 0; ++ au_hin_handle = inotify_init(&aufs_inotify_ops); ++ if (IS_ERR(au_hin_handle)) { ++ err = PTR_ERR(au_hin_handle); ++ au_hin_destroy_cache(); ++ } ++ } ++ AuTraceErr(err); ++ return err; ++} ++ ++void au_hinotify_fin(void) ++{ ++ inotify_destroy(au_hin_handle); ++ if (au_cachep[AuCache_HINOTIFY]) ++ au_hin_destroy_cache(); ++} +diff -urN ./fs/aufs/i_op.c ./fs/aufs/i_op.c +--- ./fs/aufs/i_op.c 1970-01-01 01:00:00.000000000 +0100 ++++ ./fs/aufs/i_op.c 2009-04-06 10:26:46.000000000 +0200 +@@ -0,0 +1,862 @@ ++/* ++ * Copyright (C) 2005-2009 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. ++ */ ++ ++/* ++ * inode operations (except add/del/rename) ++ */ ++ ++#include <linux/device_cgroup.h> ++#include <linux/fs_stack.h> ++#include <linux/uaccess.h> ++#include "aufs.h" ++ ++static int h_permission(struct inode *h_inode, int mask, ++ struct vfsmount *h_mnt, int brperm) ++{ ++ int err; ++ const unsigned char write_mask = !!(mask & (MAY_WRITE | MAY_APPEND)); ++ ++ err = -EACCES; ++ if ((write_mask && IS_IMMUTABLE(h_inode)) ++ || ((mask & MAY_EXEC) ++ && S_ISREG(h_inode->i_mode) ++ && ((h_mnt->mnt_flags & MNT_NOEXEC) ++ || !(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. ++ */ ++ 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); */ ++ err = generic_permission(h_inode, mask, NULL); ++ } 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 & (MAY_READ | MAY_WRITE | MAY_EXEC ++ | MAY_APPEND)); ++ ++ out: ++ return err; ++} ++ ++static int aufs_permission(struct inode *inode, int mask) ++{ ++ int err; ++ aufs_bindex_t bindex, bend; ++ const unsigned char isdir = !!S_ISDIR(inode->i_mode); ++ const unsigned char write_mask = !!(mask & (MAY_WRITE | MAY_APPEND)); ++ struct inode *h_inode; ++ struct super_block *sb; ++ struct au_branch *br; ++ ++ sb = inode->i_sb; ++ si_read_lock(sb, AuLock_FLUSH); ++ ii_read_lock_child(inode); ++ ++ if (!isdir || write_mask) { ++ h_inode = au_h_iptr(inode, au_ibstart(inode)); ++ AuDebugOn(!h_inode ++ || ((h_inode->i_mode & S_IFMT) ++ != (inode->i_mode & S_IFMT))); ++ err = 0; ++ bindex = au_ibstart(inode); ++ br = au_sbr(sb, bindex); ++ err = h_permission(h_inode, mask, br->br_mnt, br->br_perm); ++ ++ if (write_mask && !err) { ++ /* 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; ++ bend = au_ibend(inode); ++ for (bindex = au_ibstart(inode); !err && bindex <= bend; bindex++) { ++ h_inode = au_h_iptr(inode, bindex); ++ if (h_inode) { ++ AuDebugOn(!S_ISDIR(h_inode->i_mode)); ++ br = au_sbr(sb, bindex); ++ err = h_permission(h_inode, mask, br->br_mnt, ++ 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, ++ struct nameidata *nd) ++{ ++ struct dentry *ret, *parent; ++ struct inode *inode, *h_inode; ++ struct mutex *mtx; ++ struct super_block *sb; ++ int err, npositive; ++ aufs_bindex_t bstart; ++ ++ /* temporary workaround for a bug in NFSD readdir */ ++ if (!au_test_nfsd(current)) ++ IMustLock(dir); ++ else ++ WARN_ONCE(!mutex_is_locked(&dir->i_mutex), ++ "a known problem of NFSD readdir since 2.6.28\n"); ++ ++ sb = dir->i_sb; ++ si_read_lock(sb, AuLock_FLUSH); ++ err = au_alloc_dinfo(dentry); ++ ret = ERR_PTR(err); ++ if (unlikely(err)) ++ goto out; ++ ++ parent = dentry->d_parent; /* dir inode is locked */ ++ di_read_lock_parent(parent, AuLock_IR); ++ npositive = au_lkup_dentry(dentry, au_dbstart(parent), /*type*/0, nd); ++ di_read_unlock(parent, AuLock_IR); ++ err = npositive; ++ ret = ERR_PTR(err); ++ if (unlikely(err < 0)) ++ goto out_unlock; ++ ++ inode = NULL; ++ if (npositive) { ++ bstart = au_dbstart(dentry); ++ h_inode = au_h_dptr(dentry, bstart)->d_inode; ++ if (!S_ISDIR(h_inode->i_mode)) { ++ /* ++ * stop 'race'-ing between hardlinks under different ++ * parents. ++ */ ++ mtx = &au_sbr(sb, bstart)->br_xino.xi_nondir_mtx; ++ mutex_lock(mtx); ++ inode = au_new_inode(dentry, /*must_new*/0); ++ mutex_unlock(mtx); ++ } else ++ inode = au_new_inode(dentry, /*must_new*/0); ++ ret = (void *)inode; ++ } ++ if (IS_ERR(inode)) ++ goto out_unlock; ++ ++ ret = d_splice_alias(inode, dentry); ++ if (unlikely(IS_ERR(ret) && inode)) ++ ii_write_unlock(inode); ++ au_store_oflag(nd, inode); ++ ++ out_unlock: ++ di_write_unlock(dentry); ++ out: ++ si_read_unlock(sb); ++ return ret; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++static int au_wr_dir_cpup(struct dentry *dentry, struct dentry *parent, ++ const unsigned char add_entry, aufs_bindex_t bcpup, ++ aufs_bindex_t bstart) ++{ ++ int err; ++ struct dentry *h_parent; ++ struct inode *h_dir; ++ ++ if (add_entry) { ++ au_update_dbstart(dentry); ++ IMustLock(parent->d_inode); ++ } else ++ di_write_lock_parent(parent); ++ ++ err = 0; ++ if (!au_h_dptr(parent, bcpup)) { ++ if (bstart < bcpup) ++ err = au_cpdown_dirs(dentry, bcpup); ++ else ++ err = au_cpup_dirs(dentry, bcpup); ++ } ++ if (!err && add_entry) { ++ h_parent = au_h_dptr(parent, bcpup); ++ h_dir = h_parent->d_inode; ++ mutex_lock_nested(&h_dir->i_mutex, AuLsc_I_PARENT); ++ err = au_lkup_neg(dentry, bcpup); ++ /* todo: no unlock here */ ++ mutex_unlock(&h_dir->i_mutex); ++ if (bstart < bcpup && au_dbstart(dentry) < 0) { ++ au_set_dbstart(dentry, 0); ++ au_update_dbrange(dentry, /*do_put_zero*/0); ++ } ++ } ++ ++ if (!add_entry) ++ di_write_unlock(parent); ++ if (!err) ++ err = bcpup; /* success */ ++ ++ return err; ++} ++ ++/* ++ * decide the branch and the parent dir where we will create a new entry. ++ * returns new bindex or an error. ++ * copyup the parent dir if needed. ++ */ ++int au_wr_dir(struct dentry *dentry, struct dentry *src_dentry, ++ struct au_wr_dir_args *args) ++{ ++ int err; ++ aufs_bindex_t bcpup, bstart, src_bstart; ++ const unsigned char add_entry = !!au_ftest_wrdir(args->flags, ++ ADD_ENTRY); ++ struct super_block *sb; ++ struct dentry *parent; ++ struct au_sbinfo *sbinfo; ++ ++ sb = dentry->d_sb; ++ sbinfo = au_sbi(sb); ++ parent = dget_parent(dentry); ++ bstart = au_dbstart(dentry); ++ bcpup = bstart; ++ if (args->force_btgt < 0) { ++ if (src_dentry) { ++ src_bstart = au_dbstart(src_dentry); ++ if (src_bstart < bstart) ++ bcpup = src_bstart; ++ } else if (add_entry) { ++ err = AuWbrCreate(sbinfo, dentry, ++ au_ftest_wrdir(args->flags, ISDIR)); ++ bcpup = err; ++ } ++ ++ if (bcpup < 0 || au_test_ro(sb, bcpup, dentry->d_inode)) { ++ 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, dentry->d_inode)); ++ } ++ AuDbg("bstart %d, bcpup %d\n", bstart, bcpup); ++ if (bstart < bcpup) ++ au_update_dbrange(dentry, /*do_put_zero*/1); ++ ++ err = bcpup; ++ if (bcpup == bstart) ++ goto out; /* success */ ++ ++ /* copyup the new parent into the branch we process */ ++ err = au_wr_dir_cpup(dentry, parent, add_entry, bcpup, bstart); ++ ++ out: ++ dput(parent); ++ return err; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++struct dentry *au_pinned_h_parent(struct au_pin *pin) ++{ ++ if (pin && pin->parent) ++ return au_h_dptr(pin->parent, pin->bindex); ++ return NULL; ++} ++ ++void au_unpin(struct au_pin *p) ++{ ++ if (au_ftest_pin(p->flags, MNT_WRITE)) ++ mnt_drop_write(p->h_mnt); ++ if (!p->hdir) ++ return; ++ ++ au_hin_imtx_unlock(p->hdir); ++ 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; ++} ++ ++int au_do_pin(struct au_pin *p) ++{ ++ int err; ++ struct super_block *sb; ++ struct dentry *h_dentry, *h_parent; ++ struct au_branch *br; ++ struct inode *h_dir; ++ ++ err = 0; ++ sb = p->dentry->d_sb; ++ br = au_sbr(sb, p->bindex); ++ if (IS_ROOT(p->dentry)) { ++ if (au_ftest_pin(p->flags, MNT_WRITE)) { ++ p->h_mnt = br->br_mnt; ++ err = mnt_want_write(p->h_mnt); ++ if (unlikely(err)) { ++ au_fclr_pin(p->flags, MNT_WRITE); ++ goto out_err; ++ } ++ } ++ goto out; ++ } ++ ++ h_dentry = NULL; ++ if (p->bindex <= au_dbend(p->dentry)) ++ 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; ++ h_parent = au_h_dptr(p->parent, p->bindex); ++ p->hdir = au_hi(p->parent->d_inode, p->bindex); ++ if (p->hdir) ++ h_dir = p->hdir->hi_inode; ++ ++ /* udba case */ ++ if (unlikely(!p->hdir || !h_dir)) { ++ err = au_busy_or_stale(); ++ if (!au_ftest_pin(p->flags, DI_LOCKED)) ++ di_read_unlock(p->parent, AuLock_IR); ++ dput(p->parent); ++ p->parent = NULL; ++ goto out_err; ++ } ++ ++ au_igrab(h_dir); ++ au_hin_imtx_lock_nested(p->hdir, p->lsc_hi); ++ ++ if (h_dentry) { ++ err = au_h_verify(h_dentry, p->udba, h_dir, h_parent, br); ++ if (unlikely(err)) { ++ au_fclr_pin(p->flags, MNT_WRITE); ++ goto out_unpin; ++ } ++ } ++ ++ if (au_ftest_pin(p->flags, MNT_WRITE)) { ++ p->h_mnt = br->br_mnt; ++ err = mnt_want_write(p->h_mnt); ++ if (unlikely(err)) { ++ au_fclr_pin(p->flags, MNT_WRITE); ++ goto out_unpin; ++ } ++ } ++ goto out; /* success */ ++ ++ out_unpin: ++ au_unpin(p); ++ out_err: ++ AuErr("err %d\n", err); ++ err = au_busy_or_stale(); ++ out: ++ return err; ++} ++ ++void au_pin_init(struct au_pin *p, struct dentry *dentry, ++ aufs_bindex_t bindex, int lsc_di, int lsc_hi, ++ unsigned int udba, unsigned char flags) ++{ ++ p->dentry = dentry; ++ p->udba = udba; ++ p->lsc_di = lsc_di; ++ p->lsc_hi = lsc_hi; ++ p->flags = flags; ++ p->bindex = bindex; ++ ++ p->parent = NULL; ++ p->hdir = NULL; ++ p->h_mnt = NULL; ++} ++ ++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); ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++#define AuIcpup_DID_CPUP 1 ++#define au_ftest_icpup(flags, name) ((flags) & AuIcpup_##name) ++#define au_fset_icpup(flags, name) { (flags) |= AuIcpup_##name; } ++#define au_fclr_icpup(flags, name) { (flags) &= ~AuIcpup_##name; } ++ ++struct au_icpup_args { ++ unsigned char flags; ++ unsigned char pin_flags; ++ aufs_bindex_t btgt; ++ struct au_pin pin; ++ struct path h_path; ++ struct inode *h_inode; ++}; ++ ++static int au_lock_and_icpup(struct dentry *dentry, struct iattr *ia, ++ struct au_icpup_args *a) ++{ ++ int err; ++ unsigned int udba; ++ loff_t sz; ++ aufs_bindex_t bstart; ++ struct dentry *hi_wh, *parent; ++ struct inode *inode; ++ struct au_wr_dir_args wr_dir_args = { ++ .force_btgt = -1, ++ .flags = 0 ++ }; ++ ++ di_write_lock_child(dentry); ++ bstart = au_dbstart(dentry); ++ inode = dentry->d_inode; ++ if (S_ISDIR(inode->i_mode)) ++ au_fset_wrdir(wr_dir_args.flags, ISDIR); ++ /* plink or hi_wh() case */ ++ if (bstart != au_ibstart(inode)) ++ wr_dir_args.force_btgt = au_ibstart(inode); ++ err = au_wr_dir(dentry, /*src_dentry*/NULL, &wr_dir_args); ++ if (unlikely(err < 0)) ++ goto out_dentry; ++ a->btgt = err; ++ if (err != bstart) ++ au_fset_icpup(a->flags, DID_CPUP); ++ ++ err = 0; ++ a->pin_flags = AuPin_MNT_WRITE; ++ parent = NULL; ++ if (!IS_ROOT(dentry)) { ++ au_fset_pin(a->pin_flags, DI_LOCKED); ++ parent = dget_parent(dentry); ++ di_write_lock_parent(parent); ++ } ++ ++ udba = au_opt_udba(dentry->d_sb); ++ if (d_unhashed(dentry) || (ia->ia_valid & ATTR_FILE)) ++ udba = AuOpt_UDBA_NONE; ++ err = au_pin(&a->pin, dentry, a->btgt, udba, a->pin_flags); ++ if (unlikely(err)) { ++ if (parent) { ++ di_write_unlock(parent); ++ dput(parent); ++ } ++ goto out_dentry; ++ } ++ a->h_path.dentry = au_h_dptr(dentry, bstart); ++ a->h_inode = a->h_path.dentry->d_inode; ++ mutex_lock_nested(&a->h_inode->i_mutex, AuLsc_I_CHILD); ++ sz = -1; ++ if ((ia->ia_valid & ATTR_SIZE) && ia->ia_size < i_size_read(a->h_inode)) ++ sz = ia->ia_size; ++ ++ hi_wh = NULL; ++ if (au_ftest_icpup(a->flags, DID_CPUP) && d_unhashed(dentry)) { ++ hi_wh = au_hi_wh(inode, a->btgt); ++ if (!hi_wh) { ++ err = au_sio_cpup_wh(dentry, a->btgt, sz, /*file*/NULL); ++ if (unlikely(err)) ++ goto out_unlock; ++ hi_wh = au_hi_wh(inode, a->btgt); ++ /* todo: revalidate hi_wh? */ ++ } ++ } ++ ++ if (parent) { ++ au_pin_set_parent_lflag(&a->pin, /*lflag*/0); ++ di_downgrade_lock(parent, AuLock_IR); ++ dput(parent); ++ } ++ if (!au_ftest_icpup(a->flags, DID_CPUP)) ++ goto out; /* success */ ++ ++ if (!d_unhashed(dentry)) { ++ err = au_sio_cpup_simple(dentry, a->btgt, sz, AuCpup_DTIME); ++ 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: ++ mutex_unlock(&a->h_inode->i_mutex); ++ a->h_inode = a->h_path.dentry->d_inode; ++ if (!err) { ++ mutex_lock_nested(&a->h_inode->i_mutex, AuLsc_I_CHILD); ++ goto out; /* success */ ++ } ++ ++ au_unpin(&a->pin); ++ ++ out_dentry: ++ di_write_unlock(dentry); ++ out: ++ return err; ++} ++ ++static int aufs_setattr(struct dentry *dentry, struct iattr *ia) ++{ ++ int err; ++ struct inode *inode; ++ struct super_block *sb; ++ struct file *file; ++ struct au_icpup_args *a; ++ ++ err = -ENOMEM; ++ a = kzalloc(sizeof(*a), GFP_NOFS); ++ if (unlikely(!a)) ++ goto out; ++ ++ inode = dentry->d_inode; ++ IMustLock(inode); ++ sb = dentry->d_sb; ++ si_read_lock(sb, AuLock_FLUSH); ++ ++ file = NULL; ++ if (ia->ia_valid & ATTR_FILE) { ++ /* currently ftruncate(2) only */ ++ file = ia->ia_file; ++ fi_write_lock(file); ++ ia->ia_file = au_h_fptr(file, au_fbstart(file)); ++ } ++ ++ if (ia->ia_valid & (ATTR_KILL_SUID | ATTR_KILL_SGID)) ++ ia->ia_valid &= ~ATTR_MODE; ++ ++ err = au_lock_and_icpup(dentry, ia, a); ++ if (unlikely(err < 0)) ++ goto out_si; ++ 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_SIZE) { ++ struct file *f; ++ ++ if (ia->ia_size < i_size_read(inode)) { ++ /* unmap only */ ++ err = vmtruncate(inode, ia->ia_size); ++ if (unlikely(err)) ++ goto out_unlock; ++ } ++ ++ f = NULL; ++ if (ia->ia_valid & ATTR_FILE) ++ f = ia->ia_file; ++ mutex_unlock(&a->h_inode->i_mutex); ++ err = vfsub_trunc(&a->h_path, ia->ia_size, ia->ia_valid, f); ++ mutex_lock_nested(&a->h_inode->i_mutex, AuLsc_I_CHILD); ++ } else ++ err = vfsub_notify_change(&a->h_path, ia); ++ if (!err) ++ au_cpup_attr_changeable(inode); ++ ++ out_unlock: ++ mutex_unlock(&a->h_inode->i_mutex); ++ au_unpin(&a->pin); ++ di_write_unlock(dentry); ++ out_si: ++ if (file) { ++ fi_write_unlock(file); ++ ia->ia_file = file; ++ ia->ia_valid |= ATTR_FILE; ++ } ++ si_read_unlock(sb); ++ kfree(a); ++ out: ++ return err; ++} ++ ++static int au_getattr_lock_reval(struct dentry *dentry, unsigned int sigen) ++{ ++ int err; ++ struct inode *inode; ++ struct dentry *parent; ++ ++ err = 0; ++ inode = dentry->d_inode; ++ di_write_lock_child(dentry); ++ if (au_digen(dentry) != sigen || au_iigen(inode) != sigen) { ++ parent = dget_parent(dentry); ++ di_read_lock_parent(parent, AuLock_IR); ++ /* returns a number of positive dentries */ ++ err = au_refresh_hdentry(dentry, inode->i_mode & S_IFMT); ++ if (err > 0) ++ err = au_refresh_hinode(inode, dentry); ++ di_read_unlock(parent, AuLock_IR); ++ dput(parent); ++ if (unlikely(!err)) ++ err = -EIO; ++ } ++ di_downgrade_lock(dentry, AuLock_IR); ++ ++ return err; ++} ++ ++static void au_refresh_iattr(struct inode *inode, struct kstat *st, ++ unsigned int nlink) ++{ ++ inode->i_mode = st->mode; ++ inode->i_uid = st->uid; ++ inode->i_gid = st->gid; ++ inode->i_atime = st->atime; ++ inode->i_mtime = st->mtime; ++ inode->i_ctime = st->ctime; ++ ++ au_cpup_attr_nlink(inode, /*force*/0); ++ if (S_ISDIR(inode->i_mode)) { ++ inode->i_nlink -= nlink; ++ inode->i_nlink += st->nlink; ++ } ++ ++ spin_lock(&inode->i_lock); ++ inode->i_blocks = st->blocks; ++ i_size_write(inode, st->size); ++ spin_unlock(&inode->i_lock); ++} ++ ++static int aufs_getattr(struct vfsmount *mnt __maybe_unused, ++ struct dentry *dentry, struct kstat *st) ++{ ++ int err; ++ unsigned int mnt_flags; ++ aufs_bindex_t bindex; ++ unsigned char udba_none, positive, did_lock; ++ struct super_block *sb, *h_sb; ++ struct inode *inode; ++ struct vfsmount *h_mnt; ++ struct dentry *h_dentry; ++ ++ err = 0; ++ did_lock = 0; ++ sb = dentry->d_sb; ++ inode = dentry->d_inode; ++ si_read_lock(sb, AuLock_FLUSH); ++ if (IS_ROOT(dentry)) { ++ /* lock free root dinfo */ ++ h_dentry = dget(au_di(dentry)->di_hdentry->hd_dentry); ++ h_mnt = au_sbr_mnt(sb, 0); ++ goto getattr; ++ } ++ ++ did_lock = 1; ++ mnt_flags = au_mntflags(sb); ++ udba_none = !!au_opt_test(mnt_flags, UDBA_NONE); ++ ++ /* support fstat(2) */ ++ if (!d_unhashed(dentry) && !udba_none) { ++ unsigned int sigen = au_sigen(sb); ++ if (au_digen(dentry) == sigen && au_iigen(inode) == sigen) ++ di_read_lock_child(dentry, AuLock_IR); ++ else { ++ err = au_getattr_lock_reval(dentry, sigen); ++ if (unlikely(err)) ++ goto out; ++ } ++ } else ++ di_read_lock_child(dentry, AuLock_IR); ++ ++ bindex = au_ibstart(inode); ++ h_mnt = au_sbr_mnt(sb, bindex); ++ h_sb = h_mnt->mnt_sb; ++ if (!au_test_fs_bad_iattr(h_sb) && udba_none) ++ goto out_fill; /* success */ ++ ++ if (au_dbstart(dentry) == bindex) ++ h_dentry = dget(au_h_dptr(dentry, bindex)); ++ else if (au_opt_test(mnt_flags, PLINK) && au_plink_test(inode)) { ++ h_dentry = au_plink_lkup(inode, bindex); ++ if (IS_ERR(h_dentry)) ++ goto out_fill; /* pretending success */ ++ } else ++ /* illegally overlapped or something */ ++ goto out_fill; /* pretending success */ ++ ++ getattr: ++ positive = !!h_dentry->d_inode; ++ if (positive) ++ err = vfs_getattr(h_mnt, h_dentry, st); ++ dput(h_dentry); ++ if (!err) { ++ if (positive) ++ au_refresh_iattr(inode, st, h_dentry->d_inode->i_nlink); ++ goto out_fill; /* success */ ++ } ++ goto out; ++ ++ out_fill: ++ generic_fillattr(inode, st); ++ out: ++ if (did_lock) ++ di_read_unlock(dentry, AuLock_IR); ++ si_read_unlock(sb); ++ return err; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++static int h_readlink(struct dentry *dentry, int bindex, char __user *buf, ++ int bufsiz) ++{ ++ int err; ++ struct super_block *sb; ++ struct dentry *h_dentry; ++ ++ err = -EINVAL; ++ h_dentry = au_h_dptr(dentry, bindex); ++ if (unlikely(/* !h_dentry ++ || !h_dentry->d_inode ++ || !h_dentry->d_inode->i_op ++ || */ !h_dentry->d_inode->i_op->readlink)) ++ goto out; ++ ++ err = security_inode_readlink(h_dentry); ++ if (unlikely(err)) ++ goto out; ++ ++ sb = dentry->d_sb; ++ if (!au_test_ro(sb, bindex, dentry->d_inode)) { ++ vfsub_touch_atime(au_sbr_mnt(sb, bindex), h_dentry); ++ fsstack_copy_attr_atime(dentry->d_inode, h_dentry->d_inode); ++ } ++ err = h_dentry->d_inode->i_op->readlink(h_dentry, buf, bufsiz); ++ ++ out: ++ return err; ++} ++ ++static int aufs_readlink(struct dentry *dentry, char __user *buf, int bufsiz) ++{ ++ int err; ++ ++ aufs_read_lock(dentry, AuLock_IR); ++ err = h_readlink(dentry, au_dbstart(dentry), buf, bufsiz); ++ aufs_read_unlock(dentry, AuLock_IR); ++ ++ return err; ++} ++ ++static void *aufs_follow_link(struct dentry *dentry, struct nameidata *nd) ++{ ++ int err; ++ char *buf; ++ mm_segment_t old_fs; ++ ++ err = -ENOMEM; ++ buf = __getname(); ++ if (unlikely(!buf)) ++ goto out; ++ ++ aufs_read_lock(dentry, AuLock_IR); ++ old_fs = get_fs(); ++ set_fs(KERNEL_DS); ++ err = h_readlink(dentry, au_dbstart(dentry), (char __user *)buf, ++ PATH_MAX); ++ set_fs(old_fs); ++ aufs_read_unlock(dentry, AuLock_IR); ++ ++ if (err >= 0) { ++ buf[err] = 0; ++ /* will be freed by put_link */ ++ nd_set_link(nd, buf); ++ return NULL; /* success */ ++ } ++ __putname(buf); ++ ++ out: ++ path_put(&nd->path); ++ AuTraceErr(err); ++ return ERR_PTR(err); ++} ++ ++static void aufs_put_link(struct dentry *dentry __maybe_unused, ++ struct nameidata *nd, void *cookie __maybe_unused) ++{ ++ __putname(nd_get_link(nd)); ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++static void aufs_truncate_range(struct inode *inode __maybe_unused, ++ loff_t start __maybe_unused, ++ loff_t end __maybe_unused) ++{ ++ AuUnsupport(); ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++struct inode_operations aufs_symlink_iop = { ++ .permission = aufs_permission, ++ .setattr = aufs_setattr, ++ .getattr = aufs_getattr, ++ .readlink = aufs_readlink, ++ .follow_link = aufs_follow_link, ++ .put_link = aufs_put_link ++}; ++ ++struct inode_operations aufs_dir_iop = { ++ .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, ++ .setattr = aufs_setattr, ++ .getattr = aufs_getattr ++}; ++ ++struct inode_operations aufs_iop = { ++ .permission = aufs_permission, ++ .setattr = aufs_setattr, ++ .getattr = aufs_getattr, ++ .truncate_range = aufs_truncate_range ++}; +diff -urN ./fs/aufs/i_op_add.c ./fs/aufs/i_op_add.c +--- ./fs/aufs/i_op_add.c 1970-01-01 01:00:00.000000000 +0100 ++++ ./fs/aufs/i_op_add.c 2009-04-06 10:26:46.000000000 +0200 +@@ -0,0 +1,625 @@ ++/* ++ * Copyright (C) 2005-2009 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. ++ */ ++ ++/* ++ * inode operations (add 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. ++ */ ++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 inode *inode, *h_dir; ++ struct dentry *wh; ++ ++ bwh = -1; ++ if (wh_dentry) { ++ h_dir = wh_dentry->d_parent->d_inode; /* 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(dir->i_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 = dentry->d_parent->d_inode; /* dir inode is locked */ ++ IMustLock(dir); ++ if (au_ibstart(dir) == au_dbstart(dentry)) ++ au_cpup_attr_timesizes(dir); ++ dir->i_version++; ++ return 0; /* success */ ++ } ++ ++ err = PTR_ERR(inode); ++ if (!wh_dentry) ++ goto out; ++ ++ /* revert */ ++ /* dir inode is locked */ ++ wh = au_wh_create(dentry, bwh, wh_dentry->d_parent); ++ rerr = PTR_ERR(wh); ++ if (IS_ERR(wh)) { ++ AuIOErr("%.*s reverting whiteout failed(%d, %d)\n", ++ AuDLNPair(dentry), err, rerr); ++ err = -EIO; ++ } else ++ dput(wh); ++ ++ out: ++ return err; ++} ++ ++/* ++ * simple tests for the adding inode operations. ++ * following the checks in vfs, plus the parent-child relationship. ++ */ ++int au_may_add(struct dentry *dentry, aufs_bindex_t bindex, ++ struct dentry *h_parent, int isdir) ++{ ++ int err; ++ umode_t h_mode; ++ struct dentry *h_dentry; ++ struct inode *h_inode; ++ ++ h_dentry = au_h_dptr(dentry, bindex); ++ h_inode = h_dentry->d_inode; ++ if (!dentry->d_inode) { ++ err = -EEXIST; ++ if (unlikely(h_inode)) ++ goto out; ++ } else { ++ /* rename(2) case */ ++ err = -EIO; ++ if (unlikely(!h_inode || !h_inode->i_nlink)) ++ goto out; ++ ++ h_mode = h_inode->i_mode; ++ if (!isdir) { ++ err = -EISDIR; ++ if (unlikely(S_ISDIR(h_mode))) ++ goto out; ++ } else if (unlikely(!S_ISDIR(h_mode))) { ++ err = -ENOTDIR; ++ goto out; ++ } ++ } ++ ++ err = -EIO; ++ /* expected parent dir is locked */ ++ if (unlikely(h_parent != h_dentry->d_parent)) ++ goto out; ++ err = 0; ++ ++ out: ++ 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; ++ ++ 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_dbstart(dentry) == bcpup) { ++ err = au_may_add(dentry, bcpup, h_parent, ++ au_ftest_wrdir(wr_dir_args->flags, ISDIR)); ++ 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 = br->br_mnt ++ }; ++ au_dtime_store(dt, au_pinned_parent(pin), &tmp); ++ } ++ ++ wh_dentry = NULL; ++ if (bcpup != au_dbwh(dentry)) ++ goto out; /* success */ ++ ++ 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 { ++ int mode; ++ struct nameidata *nd; ++ } c; ++ struct { ++ const char *symname; ++ } s; ++ struct { ++ int mode; ++ dev_t dev; ++ } m; ++ } u; ++}; ++ ++static int add_simple(struct inode *dir, struct dentry *dentry, ++ struct simple_arg *arg) ++{ ++ int err; ++ aufs_bindex_t bstart; ++ unsigned char created; ++ struct au_dtime dt; ++ struct au_pin pin; ++ struct path h_path; ++ struct dentry *wh_dentry, *parent; ++ struct inode *h_dir; ++ struct au_wr_dir_args wr_dir_args = { ++ .force_btgt = -1, ++ .flags = AuWrDir_ADD_ENTRY ++ }; ++ ++ IMustLock(dir); ++ ++ parent = dentry->d_parent; /* dir inode is locked */ ++ aufs_read_lock(dentry, AuLock_DW); ++ di_write_lock_parent(parent); ++ wh_dentry = lock_hdir_lkup_wh(dentry, &dt, /*src_dentry*/NULL, &pin, ++ &wr_dir_args); ++ err = PTR_ERR(wh_dentry); ++ if (IS_ERR(wh_dentry)) ++ goto out; ++ ++ bstart = au_dbstart(dentry); ++ h_path.dentry = au_h_dptr(dentry, bstart); ++ h_path.mnt = au_sbr_mnt(dentry->d_sb, bstart); ++ h_dir = au_pinned_h_dir(&pin); ++ switch (arg->type) { ++ case Creat: ++ err = vfsub_create(h_dir, &h_path, arg->u.c.mode); ++ break; ++ case Symlink: ++ err = vfsub_symlink(h_dir, &h_path, arg->u.s.symname); ++ break; ++ case Mknod: ++ err = vfsub_mknod(h_dir, &h_path, arg->u.m.mode, arg->u.m.dev); ++ break; ++ default: ++ BUG(); ++ } ++ created = !err; ++ if (!err) ++ err = epilog(dir, bstart, wh_dentry, dentry); ++ ++ /* revert */ ++ if (unlikely(created && err && h_path.dentry->d_inode)) { ++ int rerr; ++ rerr = vfsub_unlink(h_dir, &h_path, /*force*/0); ++ if (rerr) { ++ AuIOErr("%.*s revert failure(%d, %d)\n", ++ AuDLNPair(dentry), err, rerr); ++ err = -EIO; ++ } ++ au_dtime_revert(&dt); ++ d_drop(dentry); ++ } ++ ++ au_unpin(&pin); ++ dput(wh_dentry); ++ ++ out: ++ if (unlikely(err)) { ++ au_update_dbstart(dentry); ++ d_drop(dentry); ++ } ++ di_write_unlock(parent); ++ aufs_read_unlock(dentry, AuLock_DW); ++ return err; ++} ++ ++int aufs_mknod(struct inode *dir, struct dentry *dentry, int 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, int mode, ++ struct nameidata *nd) ++{ ++ struct simple_arg arg = { ++ .type = Creat, ++ .u.c = { ++ .mode = mode, ++ .nd = nd ++ } ++ }; ++ return add_simple(dir, dentry, &arg); ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++struct au_link_args { ++ aufs_bindex_t bdst, bsrc; ++ struct au_pin pin; ++ struct path h_path; ++ struct dentry *src_parent, *parent; ++}; ++ ++static int au_cpup_before_link(struct dentry *src_dentry, ++ struct au_link_args *a) ++{ ++ int err; ++ struct dentry *h_src_dentry; ++ struct mutex *h_mtx; ++ ++ di_read_lock_parent(a->src_parent, AuLock_IR); ++ err = au_test_and_cpup_dirs(src_dentry, a->bdst); ++ if (unlikely(err)) ++ goto out; ++ ++ h_src_dentry = au_h_dptr(src_dentry, a->bsrc); ++ h_mtx = &h_src_dentry->d_inode->i_mutex; ++ 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; ++ mutex_lock_nested(h_mtx, AuLsc_I_CHILD); ++ err = au_sio_cpup_simple(src_dentry, a->bdst, -1, ++ AuCpup_DTIME /* | AuCpup_KEEPLINO */); ++ mutex_unlock(h_mtx); ++ au_unpin(&a->pin); ++ ++ out: ++ di_read_unlock(a->src_parent, AuLock_IR); ++ return err; ++} ++ ++static int au_cpup_or_link(struct dentry *src_dentry, struct au_link_args *a) ++{ ++ int err; ++ unsigned char plink; ++ struct inode *h_inode, *inode; ++ struct dentry *h_src_dentry; ++ struct super_block *sb; ++ ++ plink = 0; ++ h_inode = NULL; ++ sb = src_dentry->d_sb; ++ inode = src_dentry->d_inode; ++ if (au_ibstart(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. */ ++ au_set_dbstart(src_dentry, a->bdst); ++ au_set_h_dptr(src_dentry, a->bdst, dget(a->h_path.dentry)); ++ h_inode = au_h_dptr(src_dentry, a->bsrc)->d_inode; ++ mutex_lock_nested(&h_inode->i_mutex, AuLsc_I_CHILD); ++ err = au_sio_cpup_single(src_dentry, a->bdst, a->bsrc, -1, ++ AuCpup_KEEPLINO, a->parent); ++ mutex_unlock(&h_inode->i_mutex); ++ au_set_h_dptr(src_dentry, a->bdst, NULL); ++ au_set_dbstart(src_dentry, a->bsrc); ++ } else { ++ /* the inode of src_dentry already exists on a.bdst branch */ ++ h_src_dentry = d_find_alias(h_inode); ++ if (!h_src_dentry && au_plink_test(inode)) { ++ plink = 1; ++ h_src_dentry = au_plink_lkup(inode, a->bdst); ++ err = PTR_ERR(h_src_dentry); ++ if (IS_ERR(h_src_dentry)) ++ goto out; ++ ++ if (unlikely(!h_src_dentry->d_inode)) { ++ dput(h_src_dentry); ++ h_src_dentry = NULL; ++ } ++ ++ } ++ if (h_src_dentry) { ++ err = vfsub_link(h_src_dentry, au_pinned_h_dir(&a->pin), ++ &a->h_path); ++ dput(h_src_dentry); ++ } else { ++ AuIOErr("no dentry found for hi%lu on b%d\n", ++ h_inode->i_ino, a->bdst); ++ err = -EIO; ++ } ++ } ++ ++ if (!err && !plink) ++ au_plink_append(inode, a->bdst, a->h_path.dentry); ++ ++out: ++ return err; ++} ++ ++int aufs_link(struct dentry *src_dentry, struct inode *dir, ++ struct dentry *dentry) ++{ ++ int err, rerr; ++ struct au_dtime dt; ++ struct au_link_args *a; ++ struct dentry *wh_dentry, *h_src_dentry; ++ struct inode *inode; ++ struct super_block *sb; ++ struct au_wr_dir_args wr_dir_args = { ++ /* .force_btgt = -1, */ ++ .flags = AuWrDir_ADD_ENTRY ++ }; ++ ++ IMustLock(dir); ++ inode = src_dentry->d_inode; ++ IMustLock(inode); ++ ++ err = -ENOMEM; ++ a = kzalloc(sizeof(*a), GFP_NOFS); ++ if (unlikely(!a)) ++ goto out; ++ ++ a->parent = dentry->d_parent; /* dir inode is locked */ ++ aufs_read_and_write_lock2(dentry, src_dentry, /*AuLock_FLUSH*/0); ++ a->src_parent = dget_parent(src_dentry); ++ wr_dir_args.force_btgt = au_dbstart(src_dentry); ++ ++ 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_unlock; ++ ++ err = 0; ++ sb = dentry->d_sb; ++ a->bdst = au_dbstart(dentry); ++ a->h_path.dentry = au_h_dptr(dentry, a->bdst); ++ a->h_path.mnt = au_sbr_mnt(sb, a->bdst); ++ a->bsrc = au_dbstart(src_dentry); ++ 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, a); ++ else { ++ h_src_dentry = au_h_dptr(src_dentry, a->bdst); ++ err = vfsub_link(h_src_dentry, au_pinned_h_dir(&a->pin), ++ &a->h_path); ++ } ++ } else { ++ /* ++ * copyup src_dentry to the branch we process, ++ * and then link(2) to it. ++ */ ++ 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); ++ if (!err) { ++ di_write_lock_parent(a->parent); ++ 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 = vfsub_link(h_src_dentry, au_pinned_h_dir(&a->pin), ++ &a->h_path); ++ } ++ } ++ 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; ++ } ++ ++ dir->i_version++; ++ if (au_ibstart(dir) == au_dbstart(dentry)) ++ au_cpup_attr_timesizes(dir); ++ inc_nlink(inode); ++ inode->i_ctime = dir->i_ctime; ++ if (!d_unhashed(a->h_path.dentry)) ++ d_instantiate(dentry, au_igrab(inode)); ++ else ++ /* some filesystem calls d_drop() */ ++ d_drop(dentry); ++ goto out_unpin; /* success */ ++ ++ out_revert: ++ rerr = vfsub_unlink(au_pinned_h_dir(&a->pin), &a->h_path, /*force*/0); ++ if (!rerr) ++ goto out_dt; ++ AuIOErr("%.*s reverting failed(%d, %d)\n", ++ AuDLNPair(dentry), err, rerr); ++ err = -EIO; ++ out_dt: ++ d_drop(dentry); ++ au_dtime_revert(&dt); ++ out_unpin: ++ au_unpin(&a->pin); ++ out_wh: ++ dput(wh_dentry); ++ out_unlock: ++ if (unlikely(err)) { ++ au_update_dbstart(dentry); ++ d_drop(dentry); ++ } ++ di_write_unlock(a->parent); ++ dput(a->src_parent); ++ aufs_read_and_write_unlock2(dentry, src_dentry); ++ kfree(a); ++ out: ++ return err; ++} ++ ++int aufs_mkdir(struct inode *dir, struct dentry *dentry, int mode) ++{ ++ int err, rerr; ++ aufs_bindex_t bindex; ++ unsigned char diropq; ++ struct au_pin pin; ++ struct path h_path; ++ struct dentry *wh_dentry, *parent, *opq_dentry; ++ struct mutex *h_mtx; ++ struct super_block *sb; ++ struct au_dtime dt; ++ struct au_wr_dir_args wr_dir_args = { ++ .force_btgt = -1, ++ .flags = AuWrDir_ADD_ENTRY | AuWrDir_ISDIR ++ }; ++ ++ IMustLock(dir); ++ ++ aufs_read_lock(dentry, AuLock_DW); ++ parent = dentry->d_parent; /* dir inode is locked */ ++ di_write_lock_parent(parent); ++ wh_dentry = lock_hdir_lkup_wh(dentry, &dt, /*src_dentry*/NULL, &pin, ++ &wr_dir_args); ++ err = PTR_ERR(wh_dentry); ++ if (IS_ERR(wh_dentry)) ++ goto out; ++ ++ sb = dentry->d_sb; ++ bindex = au_dbstart(dentry); ++ h_path.dentry = au_h_dptr(dentry, bindex); ++ h_path.mnt = au_sbr_mnt(sb, bindex); ++ err = vfsub_mkdir(au_pinned_h_dir(&pin), &h_path, mode); ++ if (unlikely(err)) ++ goto out_unlock; ++ ++ /* make the dir opaque */ ++ diropq = 0; ++ h_mtx = &h_path.dentry->d_inode->i_mutex; ++ if (wh_dentry ++ || au_opt_test(au_mntflags(sb), ALWAYS_DIROPQ)) { ++ mutex_lock_nested(h_mtx, AuLsc_I_CHILD); ++ opq_dentry = au_diropq_create(dentry, bindex); ++ mutex_unlock(h_mtx); ++ err = PTR_ERR(opq_dentry); ++ if (IS_ERR(opq_dentry)) ++ goto out_dir; ++ dput(opq_dentry); ++ diropq = 1; ++ } ++ ++ err = epilog(dir, bindex, wh_dentry, dentry); ++ if (!err) { ++ inc_nlink(dir); ++ goto out_unlock; /* success */ ++ } ++ ++ /* revert */ ++ if (diropq) { ++ AuLabel(revert opq); ++ mutex_lock_nested(h_mtx, AuLsc_I_CHILD); ++ rerr = au_diropq_remove(dentry, bindex); ++ mutex_unlock(h_mtx); ++ if (rerr) { ++ AuIOErr("%.*s reverting diropq failed(%d, %d)\n", ++ AuDLNPair(dentry), err, rerr); ++ err = -EIO; ++ } ++ } ++ ++ out_dir: ++ AuLabel(revert dir); ++ rerr = vfsub_rmdir(au_pinned_h_dir(&pin), &h_path); ++ if (rerr) { ++ AuIOErr("%.*s reverting dir failed(%d, %d)\n", ++ AuDLNPair(dentry), err, rerr); ++ err = -EIO; ++ } ++ d_drop(dentry); ++ au_dtime_revert(&dt); ++ out_unlock: ++ au_unpin(&pin); ++ dput(wh_dentry); ++ out: ++ if (unlikely(err)) { ++ au_update_dbstart(dentry); ++ d_drop(dentry); ++ } ++ di_write_unlock(parent); ++ aufs_read_unlock(dentry, AuLock_DW); ++ return err; ++} +diff -urN ./fs/aufs/i_op_del.c ./fs/aufs/i_op_del.c +--- ./fs/aufs/i_op_del.c 1970-01-01 01:00:00.000000000 +0100 ++++ ./fs/aufs/i_op_del.c 2009-04-06 10:26:46.000000000 +0200 +@@ -0,0 +1,471 @@ ++/* ++ * Copyright (C) 2005-2009 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. ++ */ ++ ++/* ++ * inode operations (del entry) ++ */ ++ ++#include "aufs.h" ++ ++/* ++ * decide if a new whiteout for @dentry is necessary or not. ++ * when it is necessary, prepare the parent dir for the upper branch whose ++ * branch index is @bcpup for creation. the actual creation of the whiteout will ++ * be done by caller. ++ * return value: ++ * 0: wh is unnecessary ++ * plus: wh is necessary ++ * minus: error ++ */ ++int au_wr_dir_need_wh(struct dentry *dentry, int isdir, aufs_bindex_t *bcpup) ++{ ++ int need_wh, err; ++ aufs_bindex_t bstart; ++ struct super_block *sb; ++ ++ sb = dentry->d_sb; ++ bstart = au_dbstart(dentry); ++ if (*bcpup < 0) { ++ *bcpup = bstart; ++ if (au_test_ro(sb, bstart, dentry->d_inode)) { ++ err = AuWbrCopyup(au_sbi(sb), dentry); ++ *bcpup = err; ++ if (unlikely(err < 0)) ++ goto out; ++ } ++ } else ++ AuDebugOn(bstart < *bcpup ++ || au_test_ro(sb, *bcpup, dentry->d_inode)); ++ AuDbg("bcpup %d, bstart %d\n", *bcpup, bstart); ++ ++ if (*bcpup != bstart) { ++ err = au_cpup_dirs(dentry, *bcpup); ++ if (unlikely(err)) ++ goto out; ++ need_wh = 1; ++ } else { ++ aufs_bindex_t old_bend, new_bend, bdiropq = -1; ++ ++ old_bend = au_dbend(dentry); ++ if (isdir) { ++ bdiropq = au_dbdiropq(dentry); ++ au_set_dbdiropq(dentry, -1); ++ } ++ need_wh = au_lkup_dentry(dentry, bstart + 1, /*type*/0, ++ /*nd*/NULL); ++ err = need_wh; ++ if (isdir) ++ au_set_dbdiropq(dentry, bdiropq); ++ if (unlikely(err < 0)) ++ goto out; ++ new_bend = au_dbend(dentry); ++ if (!need_wh && old_bend != new_bend) { ++ au_set_h_dptr(dentry, new_bend, NULL); ++ au_set_dbend(dentry, old_bend); ++ } ++ } ++ AuDbg("need_wh %d\n", need_wh); ++ err = need_wh; ++ ++ out: ++ return err; ++} ++ ++/* ++ * simple tests for the del-entry operations. ++ * following the checks in vfs, plus the parent-child relationship. ++ */ ++int au_may_del(struct dentry *dentry, aufs_bindex_t bindex, ++ struct dentry *h_parent, int isdir) ++{ ++ int err; ++ umode_t h_mode; ++ struct dentry *h_dentry, *h_latest; ++ struct inode *h_inode; ++ ++ h_dentry = au_h_dptr(dentry, bindex); ++ h_inode = h_dentry->d_inode; ++ if (dentry->d_inode) { ++ err = -ENOENT; ++ if (unlikely(!h_inode || !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; ++ } ++ } else { ++ /* rename(2) case */ ++ err = -EIO; ++ if (unlikely(h_inode)) ++ goto out; ++ } ++ ++ err = -ENOENT; ++ /* expected parent dir is locked */ ++ if (unlikely(h_parent != h_dentry->d_parent)) ++ goto out; ++ err = 0; ++ ++ /* ++ * rmdir a dir may break the consistency on some filesystem. ++ * let's try heavy test. ++ */ ++ err = -EACCES; ++ if (unlikely(au_test_h_perm(h_parent->d_inode, MAY_EXEC | MAY_WRITE))) ++ goto out; ++ ++ h_latest = au_sio_lkup_one(&dentry->d_name, h_parent, ++ au_sbr(dentry->d_sb, bindex)); ++ err = -EIO; ++ if (IS_ERR(h_latest)) ++ goto out; ++ if (h_latest == h_dentry) ++ err = 0; ++ dput(h_latest); ++ ++ out: ++ 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) ++{ ++ 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; ++ ++ 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; ++ ++ h_path.dentry = au_pinned_h_parent(pin); ++ if (udba != AuOpt_UDBA_NONE ++ && au_dbstart(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; /* success */ ++ /* returns with the parent is locked and wh_dentry is dget-ed */ ++ ++ out_unpin: ++ au_unpin(pin); ++ out: ++ return wh_dentry; ++} ++ ++/* ++ * when removing a dir, rename it to a unique temporary whiteout-ed name first ++ * in order to be revertible and save time for removing many child whiteouts ++ * under the dir. ++ * returns 1 when there are too many child whiteout and caller should remove ++ * them asynchronously. returns 0 when the number of children is enough small to ++ * remove now or the branch fs is a remote fs. ++ * otherwise return an error. ++ */ ++static int renwh_and_rmdir(struct dentry *dentry, aufs_bindex_t bindex, ++ struct au_nhash *whlist, struct inode *dir) ++{ ++ int rmdir_later, err, dirwh; ++ struct dentry *h_dentry; ++ struct super_block *sb; ++ ++ sb = dentry->d_sb; ++ h_dentry = au_h_dptr(dentry, bindex); ++ err = au_whtmp_ren(h_dentry, au_sbr(sb, bindex)); ++ if (unlikely(err)) ++ goto out; ++ ++ /* stop monitoring */ ++ au_hin_free(au_hi(dentry->d_inode, bindex)); ++ ++ if (!au_test_fs_remote(h_dentry->d_sb)) { ++ dirwh = au_sbi(sb)->si_dirwh; ++ rmdir_later = (dirwh <= 1); ++ if (!rmdir_later) ++ rmdir_later = au_nhash_test_longer_wh(whlist, bindex, ++ dirwh); ++ if (rmdir_later) ++ return rmdir_later; ++ } ++ ++ err = au_whtmp_rmdir(dir, bindex, h_dentry, whlist); ++ if (unlikely(err)) { ++ AuIOErr("rmdir %.*s, b%d failed, %d. ignored\n", ++ AuDLNPair(h_dentry), bindex, err); ++ err = 0; ++ } ++ ++ out: ++ return err; ++} ++ ++/* ++ * final procedure for deleting a entry. ++ * maintain dentry and iattr. ++ */ ++static void epilog(struct inode *dir, struct dentry *dentry, ++ aufs_bindex_t bindex) ++{ ++ struct inode *inode; ++ ++ /* ++ * even if this is not a dir, ++ * set S_DEAD here since we need to detect the dead inode. ++ */ ++ inode = dentry->d_inode; ++ if (!inode->i_nlink) ++ inode->i_flags |= S_DEAD; ++ d_drop(dentry); ++ inode->i_ctime = dir->i_ctime; ++ ++ if (atomic_read(&dentry->d_count) == 1) { ++ au_set_h_dptr(dentry, au_dbstart(dentry), NULL); ++ au_update_dbstart(dentry); ++ } ++ if (au_ibstart(dir) == bindex) ++ au_cpup_attr_timesizes(dir); ++ 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 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, bwh) ++ }; ++ ++ rerr = au_wh_unlink_dentry(au_h_iptr(dir, bwh), &h_path, dentry); ++ if (!rerr) { ++ au_set_dbwh(dentry, bwh); ++ au_dtime_revert(dt); ++ return 0; ++ } ++ ++ AuIOErr("%.*s reverting whiteout failed(%d, %d)\n", ++ AuDLNPair(dentry), err, rerr); ++ return -EIO; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++int aufs_unlink(struct inode *dir, struct dentry *dentry) ++{ ++ int err; ++ aufs_bindex_t bwh, bindex, bstart; ++ struct au_dtime dt; ++ struct au_pin pin; ++ struct path h_path; ++ struct inode *inode, *h_dir; ++ struct dentry *parent, *wh_dentry; ++ ++ IMustLock(dir); ++ inode = dentry->d_inode; ++ if (unlikely(!inode)) ++ return -ENOENT; /* possible? */ ++ IMustLock(inode); ++ ++ aufs_read_lock(dentry, AuLock_DW); ++ parent = dentry->d_parent; /* dir inode is locked */ ++ di_write_lock_parent(parent); ++ ++ bstart = au_dbstart(dentry); ++ bwh = au_dbwh(dentry); ++ bindex = -1; ++ wh_dentry = lock_hdir_create_wh(dentry, /*isdir*/0, &bindex, &dt, &pin); ++ err = PTR_ERR(wh_dentry); ++ if (IS_ERR(wh_dentry)) ++ goto out; ++ ++ h_path.mnt = au_sbr_mnt(dentry->d_sb, bstart); ++ h_path.dentry = au_h_dptr(dentry, bstart); ++ dget(h_path.dentry); ++ if (bindex == bstart) { ++ h_dir = au_pinned_h_dir(&pin); ++ err = vfsub_unlink(h_dir, &h_path, /*force*/0); ++ } else { ++ /* dir inode is locked */ ++ h_dir = wh_dentry->d_parent->d_inode; ++ IMustLock(h_dir); ++ err = 0; ++ } ++ ++ if (!err) { ++ drop_nlink(inode); ++ epilog(dir, dentry, bindex); ++ ++ /* update target timestamps */ ++ if (bindex == bstart) { ++ vfsub_update_h_iattr(&h_path, /*did*/NULL); /*ignore*/ ++ inode->i_ctime = h_path.dentry->d_inode->i_ctime; ++ } else ++ /* todo: this timestamp may be reverted later */ ++ inode->i_ctime = h_dir->i_ctime; ++ goto out_unlock; /* success */ ++ } ++ ++ /* revert */ ++ if (wh_dentry) { ++ int rerr; ++ ++ rerr = do_revert(err, dir, bwh, wh_dentry, dentry, &dt); ++ if (rerr) ++ err = rerr; ++ } ++ ++ out_unlock: ++ au_unpin(&pin); ++ dput(wh_dentry); ++ dput(h_path.dentry); ++ out: ++ di_write_unlock(parent); ++ aufs_read_unlock(dentry, AuLock_DW); ++ return err; ++} ++ ++int aufs_rmdir(struct inode *dir, struct dentry *dentry) ++{ ++ int err, rmdir_later; ++ aufs_bindex_t bwh, bindex, bstart; ++ struct au_dtime dt; ++ struct au_pin pin; ++ struct inode *inode; ++ struct dentry *parent, *wh_dentry, *h_dentry; ++ struct au_whtmp_rmdir_args *args; ++ struct au_nhash *whlist; ++ ++ IMustLock(dir); ++ inode = dentry->d_inode; ++ err = -ENOENT; /* possible? */ ++ if (unlikely(!inode)) ++ goto out; ++ IMustLock(inode); ++ ++ whlist = au_nhash_new(GFP_NOFS); ++ err = PTR_ERR(whlist); ++ if (IS_ERR(whlist)) ++ goto out; ++ ++ err = -ENOMEM; ++ args = kmalloc(sizeof(*args), GFP_NOFS); ++ if (unlikely(!args)) ++ goto out_whlist; ++ ++ aufs_read_lock(dentry, AuLock_DW | AuLock_FLUSH); ++ parent = dentry->d_parent; /* dir inode is locked */ ++ di_write_lock_parent(parent); ++ err = au_test_empty(dentry, whlist); ++ if (unlikely(err)) ++ goto out_args; ++ ++ bstart = au_dbstart(dentry); ++ bwh = au_dbwh(dentry); ++ bindex = -1; ++ wh_dentry = lock_hdir_create_wh(dentry, /*isdir*/1, &bindex, &dt, &pin); ++ err = PTR_ERR(wh_dentry); ++ if (IS_ERR(wh_dentry)) ++ goto out_args; ++ ++ h_dentry = au_h_dptr(dentry, bstart); ++ dget(h_dentry); ++ rmdir_later = 0; ++ if (bindex == bstart) { ++ err = renwh_and_rmdir(dentry, bstart, whlist, dir); ++ if (err > 0) { ++ rmdir_later = err; ++ err = 0; ++ } ++ } else { ++ /* stop monitoring */ ++ au_hin_free(au_hi(inode, bstart)); ++ ++ /* dir inode is locked */ ++ IMustLock(wh_dentry->d_parent->d_inode); ++ err = 0; ++ } ++ ++ if (!err) { ++ clear_nlink(inode); ++ au_set_dbdiropq(dentry, -1); ++ epilog(dir, dentry, bindex); ++ ++ if (rmdir_later) { ++ au_whtmp_kick_rmdir(dir, bstart, h_dentry, whlist, ++ args); ++ args = NULL; ++ } ++ ++ goto out_unlock; /* success */ ++ } ++ ++ /* revert */ ++ AuLabel(revert); ++ if (wh_dentry) { ++ int rerr; ++ ++ rerr = do_revert(err, dir, bwh, wh_dentry, dentry, &dt); ++ if (rerr) ++ err = rerr; ++ } ++ ++ out_unlock: ++ au_unpin(&pin); ++ dput(wh_dentry); ++ dput(h_dentry); ++ out_args: ++ di_write_unlock(parent); ++ aufs_read_unlock(dentry, AuLock_DW); ++ kfree(args); ++ out_whlist: ++ au_nhash_del(whlist); ++ out: ++ return err; ++} +diff -urN ./fs/aufs/i_op_ren.c ./fs/aufs/i_op_ren.c +--- ./fs/aufs/i_op_ren.c 1970-01-01 01:00:00.000000000 +0100 ++++ ./fs/aufs/i_op_ren.c 2009-04-06 10:26:46.000000000 +0200 +@@ -0,0 +1,929 @@ ++/* ++ * Copyright (C) 2005-2009 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. ++ */ ++ ++/* ++ * inode operation (rename entry) ++ * todo: this is crazy monster ++ */ ++ ++#include "aufs.h" ++ ++enum { AuSRC, AuDST, AuSrcDst }; ++enum { AuPARENT, AuCHILD, AuParentChild }; ++ ++#define AuRen_ISDIR 1 ++#define AuRen_ISSAMEDIR (1 << 1) ++#define AuRen_WHSRC (1 << 2) ++#define AuRen_WHDST (1 << 3) ++#define AuRen_MNT_WRITE (1 << 4) ++#define AuRen_DT_DSTDIR (1 << 5) ++#define AuRen_DIROPQ (1 << 6) ++#define AuRen_CPUP (1 << 7) ++#define au_ftest_ren(flags, name) ((flags) & AuRen_##name) ++#define au_fset_ren(flags, name) { (flags) |= AuRen_##name; } ++#define au_fclr_ren(flags, name) { (flags) &= ~AuRen_##name; } ++ ++struct au_ren_args { ++ struct { ++ struct dentry *dentry, *h_dentry, *parent, *h_parent, ++ *wh_dentry; ++ struct inode *dir, *inode; ++ struct au_hinode *hdir; ++ struct au_dtime dt[AuParentChild]; ++ aufs_bindex_t bstart; ++ } 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_h_dir sd[AuSRC].hdir->hi_inode ++#define src_dt sd[AuSRC].dt ++#define src_bstart sd[AuSRC].bstart ++ ++#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_h_dir sd[AuDST].hdir->hi_inode ++#define dst_dt sd[AuDST].dt ++#define dst_bstart sd[AuDST].bstart ++ ++ struct dentry *h_trap; ++ struct au_branch *br; ++ struct au_hinode *src_hinode; ++ struct path h_path; ++ struct au_nhash whlist; ++ aufs_bindex_t btgt; ++ ++ unsigned int flags; ++ ++ struct au_whtmp_rmdir_args *thargs; ++ struct dentry *h_dst; ++}; ++ ++/* ---------------------------------------------------------------------- */ ++ ++/* ++ * functions for reverting. ++ * when an error happened in a single rename systemcall, we should revert ++ * everything as if nothing happend. ++ * we don't need to revert the copied-up/down the parent dir since they are ++ * harmless. ++ */ ++ ++#define RevertFailure(fmt, args...) do { \ ++ AuIOErr("revert failure: " fmt " (%d, %d)\n", \ ++ ##args, err, rerr); \ ++ err = -EIO; \ ++} while (0) ++ ++static void au_ren_rev_diropq(int err, struct au_ren_args *a) ++{ ++ int rerr; ++ ++ au_hin_imtx_lock_nested(a->src_hinode, AuLsc_I_CHILD); ++ rerr = au_diropq_remove(a->src_dentry, a->btgt); ++ au_hin_imtx_unlock(a->src_hinode); ++ if (rerr) ++ RevertFailure("remove diropq %.*s", AuDLNPair(a->src_dentry)); ++} ++ ++ ++static void au_ren_rev_rename(int err, struct au_ren_args *a) ++{ ++ int rerr; ++ ++ a->h_path.dentry = au_lkup_one(&a->src_dentry->d_name, a->src_h_parent, ++ a->br, /*nd*/NULL); ++ rerr = PTR_ERR(a->h_path.dentry); ++ if (IS_ERR(a->h_path.dentry)) { ++ RevertFailure("au_lkup_one %.*s", AuDLNPair(a->src_dentry)); ++ return; ++ } ++ ++ rerr = vfsub_rename(a->dst_h_dir, ++ au_h_dptr(a->src_dentry, a->btgt), ++ a->src_h_dir, &a->h_path); ++ 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 %.*s", AuDLNPair(a->src_dentry)); ++} ++ ++static void au_ren_rev_cpup(int err, struct au_ren_args *a) ++{ ++ int rerr; ++ ++ a->h_path.dentry = a->dst_h_dentry; ++ rerr = vfsub_unlink(a->dst_h_dir, &a->h_path, /*force*/0); ++ au_set_h_dptr(a->src_dentry, a->btgt, NULL); ++ au_set_dbstart(a->src_dentry, a->src_bstart); ++ if (rerr) ++ RevertFailure("unlink %.*s", AuDLNPair(a->dst_h_dentry)); ++} ++ ++ ++static void au_ren_rev_whtmp(int err, struct au_ren_args *a) ++{ ++ int rerr; ++ ++ a->h_path.dentry = au_lkup_one(&a->dst_dentry->d_name, a->dst_h_parent, ++ a->br, /*nd*/NULL); ++ rerr = PTR_ERR(a->h_path.dentry); ++ if (IS_ERR(a->h_path.dentry)) { ++ RevertFailure("lookup %.*s", AuDLNPair(a->dst_dentry)); ++ return; ++ } ++ if (a->h_path.dentry->d_inode) { ++ d_drop(a->h_path.dentry); ++ dput(a->h_path.dentry); ++ return; ++ } ++ ++ rerr = vfsub_rename(a->dst_h_dir, a->h_dst, a->dst_h_dir, &a->h_path); ++ d_drop(a->h_path.dentry); ++ dput(a->h_path.dentry); ++ if (!rerr) { ++ au_set_h_dptr(a->dst_dentry, a->btgt, NULL); ++ au_set_h_dptr(a->dst_dentry, a->btgt, dget(a->h_dst)); ++ } else ++ RevertFailure("rename %.*s", AuDLNPair(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); ++ if (rerr) ++ RevertFailure("unlink %.*s", AuDLNPair(a->src_wh_dentry)); ++} ++ ++static void au_ren_rev_drop(struct au_ren_args *a) ++{ ++ struct dentry *d, *h_d; ++ int i; ++ aufs_bindex_t bend, bindex; ++ ++ for (i = 0; i < AuSrcDst; i++) { ++ d = a->sd[i].dentry; ++ d_drop(d); ++ bend = au_dbend(d); ++ for (bindex = au_dbstart(d); bindex <= bend; bindex++) { ++ h_d = au_h_dptr(d, bindex); ++ if (h_d) ++ d_drop(h_d); ++ } ++ } ++ ++ au_update_dbstart(a->dst_dentry); ++ if (a->thargs) ++ d_drop(a->h_dst); ++} ++#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; ++ ++ d = a->src_dentry; ++ if (au_dbstart(d) == a->btgt) { ++ a->h_path.dentry = a->dst_h_dentry; ++ if (au_ftest_ren(a->flags, DIROPQ) ++ && au_dbdiropq(d) == a->btgt) ++ au_fclr_ren(a->flags, DIROPQ); ++ AuDebugOn(au_dbstart(d) != a->btgt); ++ err = vfsub_rename(a->src_h_dir, au_h_dptr(d, a->btgt), ++ a->dst_h_dir, &a->h_path); ++ } else { ++ struct mutex *h_mtx = &a->src_h_dentry->d_inode->i_mutex; ++ ++ au_fset_ren(a->flags, CPUP); ++ mutex_lock_nested(h_mtx, AuLsc_I_CHILD); ++ au_set_dbstart(d, a->btgt); ++ au_set_h_dptr(d, a->btgt, dget(a->dst_h_dentry)); ++ err = au_sio_cpup_single(d, a->btgt, a->src_bstart, -1, ++ !AuCpup_DTIME, a->dst_parent); ++ if (unlikely(err)) { ++ au_set_h_dptr(d, a->btgt, NULL); ++ au_set_dbstart(d, a->src_bstart); ++ } ++ mutex_unlock(h_mtx); ++ } ++ ++ return err; ++} ++ ++/* cf. aufs_rmdir() */ ++static int au_ren_del_whtmp(struct au_ren_args *a) ++{ ++ int err; ++ struct inode *dir; ++ ++ dir = a->dst_dir; ++ 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)) ++ AuWarn("failed removing whtmp dir %.*s (%d), " ++ "ignored.\n", AuDLNPair(a->h_dst), err); ++ } else { ++ au_whtmp_kick_rmdir(dir, a->btgt, a->h_dst, &a->whlist, ++ a->thargs); ++ dput(a->h_dst); ++ a->thargs = NULL; ++ } ++ ++ return 0; ++} ++ ++/* make it 'opaque' dir. */ ++static int au_ren_diropq(struct au_ren_args *a) ++{ ++ int err; ++ struct dentry *diropq; ++ ++ err = 0; ++ a->src_hinode = au_hi(a->src_inode, a->btgt); ++ au_hin_imtx_lock_nested(a->src_hinode, AuLsc_I_CHILD); ++ diropq = au_diropq_create(a->src_dentry, a->btgt); ++ au_hin_imtx_unlock(a->src_hinode); ++ if (IS_ERR(diropq)) ++ err = PTR_ERR(diropq); ++ dput(diropq); ++ ++ return err; ++} ++ ++static int do_rename(struct au_ren_args *a) ++{ ++ int err; ++ struct dentry *d, *h_d; ++ ++ /* prepare workqueue args for asynchronous rmdir */ ++ h_d = a->dst_h_dentry; ++ if (au_ftest_ren(a->flags, ISDIR) && h_d->d_inode) { ++ err = -ENOMEM; ++ a->thargs = kmalloc(sizeof(*a->thargs), GFP_NOFS); ++ if (unlikely(!a->thargs)) ++ goto out; ++ a->h_dst = dget(h_d); ++ } ++ ++ /* create whiteout for src_dentry */ ++ if (au_ftest_ren(a->flags, WHSRC)) { ++ 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; ++ } ++ ++ /* lookup whiteout for dentry */ ++ if (au_ftest_ren(a->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 (!h_d->d_inode) ++ dput(h_d); ++ else ++ a->dst_wh_dentry = h_d; ++ } ++ ++ /* rename dentry to tmpwh */ ++ if (a->thargs) { ++ err = au_whtmp_ren(a->dst_h_dentry, a->br); ++ if (unlikely(err)) ++ goto out_whdst; ++ ++ d = a->dst_dentry; ++ au_set_h_dptr(d, a->btgt, NULL); ++ err = au_lkup_neg(d, a->btgt); ++ if (unlikely(err)) ++ goto out_whtmp; ++ a->dst_h_dentry = au_h_dptr(d, a->btgt); ++ } ++ ++ /* cpup src */ ++ if (a->dst_h_dentry->d_inode && a->src_bstart != a->btgt) { ++ struct mutex *h_mtx = &a->src_h_dentry->d_inode->i_mutex; ++ ++ mutex_lock_nested(h_mtx, AuLsc_I_CHILD); ++ err = au_sio_cpup_simple(a->src_dentry, a->btgt, -1, ++ !AuCpup_DTIME); ++ mutex_unlock(h_mtx); ++ if (unlikely(err)) ++ goto out_whtmp; ++ } ++ ++ /* rename by vfs_rename or cpup */ ++ d = a->dst_dentry; ++ if (au_ftest_ren(a->flags, ISDIR) ++ && (a->dst_wh_dentry ++ || au_dbdiropq(d) == a->btgt ++ /* hide the lower to keep xino */ ++ || a->btgt < au_dbend(d) ++ || au_opt_test(au_mntflags(d->d_sb), ALWAYS_DIROPQ))) ++ au_fset_ren(a->flags, DIROPQ); ++ err = au_ren_or_cpup(a); ++ if (unlikely(err)) ++ /* leave the copied-up one */ ++ goto out_whtmp; ++ ++ /* make dir opaque */ ++ if (au_ftest_ren(a->flags, DIROPQ)) { ++ err = au_ren_diropq(a); ++ if (unlikely(err)) ++ goto out_rename; ++ } ++ ++ /* update target timestamps */ ++ AuDebugOn(au_dbstart(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 = a->h_path.dentry->d_inode->i_ctime; ++ ++ /* 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; ++ } ++ ++ /* remove whtmp */ ++ if (a->thargs) ++ au_ren_del_whtmp(a); /* ignore this error */ ++ ++ err = 0; ++ goto out_success; ++ ++ out_diropq: ++ if (au_ftest_ren(a->flags, DIROPQ)) ++ au_ren_rev_diropq(err, a); ++ out_rename: ++ if (!au_ftest_ren(a->flags, CPUP)) ++ au_ren_rev_rename(err, a); ++ else ++ au_ren_rev_cpup(err, a); ++ 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); ++ au_ren_rev_drop(a); ++ out_success: ++ dput(a->src_wh_dentry); ++ dput(a->dst_wh_dentry); ++ out_thargs: ++ if (a->thargs) { ++ dput(a->h_dst); ++ kfree(a->thargs); ++ } ++ out: ++ return err; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++/* ++ * test if @dentry dir can be rename destination or not. ++ * success means, it is a logically empty dir. ++ */ ++static int may_rename_dstdir(struct dentry *dentry, struct au_nhash *whlist) ++{ ++ return au_test_empty(dentry, whlist); ++} ++ ++/* ++ * 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; ++ aufs_bindex_t bstart; ++ ++ bstart = au_dbstart(dentry); ++ if (bstart != btgt) { ++ struct au_nhash *whlist; ++ ++ whlist = au_nhash_new(GFP_NOFS); ++ err = PTR_ERR(whlist); ++ if (IS_ERR(whlist)) ++ goto out; ++ err = au_test_empty(dentry, whlist); ++ au_nhash_del(whlist); ++ goto out; ++ } ++ ++ if (bstart == au_dbtaildir(dentry)) ++ return 0; /* success */ ++ ++ err = au_test_empty_lower(dentry); ++ ++ out: ++ if (err == -ENOTEMPTY) { ++ AuWarn1("renaming dir who has child(ren) on multiple branches," ++ " is not supported\n"); ++ err = -EXDEV; ++ } ++ return err; ++} ++ ++/* side effect: sets whlist and h_dentry */ ++static int au_ren_may_dir(struct au_ren_args *a) ++{ ++ int err; ++ struct dentry *d; ++ ++ err = 0; ++ au_nhash_init(&a->whlist); ++ d = a->dst_dentry; ++ if (au_ftest_ren(a->flags, ISDIR) && a->dst_inode) { ++ au_set_dbstart(d, a->dst_bstart); ++ err = may_rename_dstdir(d, &a->whlist); ++ au_set_dbstart(d, a->btgt); ++ } ++ a->dst_h_dentry = au_h_dptr(d, au_dbstart(d)); ++ if (unlikely(err)) ++ goto out; ++ ++ d = a->src_dentry; ++ a->src_h_dentry = au_h_dptr(d, au_dbstart(d)); ++ if (au_ftest_ren(a->flags, ISDIR)) { ++ err = may_rename_srcdir(d, a->btgt); ++ if (unlikely(err)) ++ au_nhash_fin(&a->whlist); ++ } ++ ++ out: ++ return err; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++/* ++ * simple tests for rename. ++ * following the checks in vfs, plus the parent-child relationship. ++ */ ++static int au_may_ren(struct au_ren_args *a) ++{ ++ int err, isdir; ++ struct inode *h_inode; ++ ++ if (a->src_bstart == a->btgt) { ++ err = au_may_del(a->src_dentry, a->btgt, a->src_h_parent, ++ au_ftest_ren(a->flags, ISDIR)); ++ if (unlikely(err)) ++ goto out; ++ err = -EINVAL; ++ if (unlikely(a->src_h_dentry == a->h_trap)) ++ goto out; ++ } ++ ++ err = 0; ++ if (a->dst_bstart != a->btgt) ++ goto out; ++ ++ err = -EIO; ++ h_inode = a->dst_h_dentry->d_inode; ++ isdir = !!au_ftest_ren(a->flags, ISDIR); ++ if (!a->dst_dentry->d_inode) { ++ if (unlikely(h_inode)) ++ goto out; ++ err = au_may_add(a->dst_dentry, a->btgt, a->dst_h_parent, ++ isdir); ++ } else { ++ if (unlikely(!h_inode || !h_inode->i_nlink)) ++ goto out; ++ err = au_may_del(a->dst_dentry, a->btgt, a->dst_h_parent, ++ isdir); ++ if (unlikely(err)) ++ goto out; ++ err = -ENOTEMPTY; ++ if (unlikely(a->dst_h_dentry == a->h_trap)) ++ goto out; ++ err = 0; ++ } ++ ++ out: ++ if (unlikely(err == -ENOENT || err == -EEXIST)) ++ err = -EIO; ++ return err; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++/* ++ * 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) ++{ ++ struct super_block *sb; ++ ++ sb = a->dst_dentry->d_sb; ++ if (au_ftest_ren(a->flags, MNT_WRITE)) ++ mnt_drop_write(a->br->br_mnt); ++ vfsub_unlock_rename(a->src_h_parent, a->src_hdir, ++ a->dst_h_parent, a->dst_hdir); ++} ++ ++static int au_ren_lock(struct au_ren_args *a) ++{ ++ 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); ++ 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 (au_dbstart(a->src_dentry) == a->btgt) ++ err = au_h_verify(a->src_h_dentry, udba, ++ a->src_h_parent->d_inode, a->src_h_parent, ++ a->br); ++ if (!err && au_dbstart(a->dst_dentry) == a->btgt) ++ err = au_h_verify(a->dst_h_dentry, udba, ++ a->dst_h_parent->d_inode, a->dst_h_parent, ++ a->br); ++ if (!err) { ++ err = mnt_want_write(a->br->br_mnt); ++ if (unlikely(err)) ++ goto out_unlock; ++ au_fset_ren(a->flags, MNT_WRITE); ++ goto out; /* success */ ++ } ++ ++ err = au_busy_or_stale(); ++ ++ out_unlock: ++ au_ren_unlock(a); ++ out: ++ return err; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++static void au_ren_refresh_dir(struct au_ren_args *a) ++{ ++ struct inode *dir; ++ ++ dir = a->dst_dir; ++ dir->i_version++; ++ if (au_ftest_ren(a->flags, ISDIR)) { ++ /* is this updating defined in POSIX? */ ++ au_cpup_attr_timesizes(a->src_inode); ++ au_cpup_attr_nlink(dir, /*force*/1); ++ if (a->dst_inode) { ++ clear_nlink(a->dst_inode); ++ au_cpup_attr_timesizes(a->dst_inode); ++ } ++ } ++ if (au_ibstart(dir) == a->btgt) ++ au_cpup_attr_timesizes(dir); ++ ++ if (au_ftest_ren(a->flags, ISSAMEDIR)) ++ return; ++ ++ dir = a->src_dir; ++ dir->i_version++; ++ if (au_ftest_ren(a->flags, ISDIR)) ++ au_cpup_attr_nlink(dir, /*force*/1); ++ if (au_ibstart(dir) == a->btgt) ++ au_cpup_attr_timesizes(dir); ++} ++ ++static void au_ren_refresh(struct au_ren_args *a) ++{ ++ aufs_bindex_t bend, bindex; ++ struct dentry *d, *h_d; ++ struct inode *i, *h_i; ++ struct super_block *sb; ++ ++ d = a->src_dentry; ++ au_set_dbwh(d, -1); ++ bend = au_dbend(d); ++ for (bindex = a->btgt + 1; bindex <= bend; bindex++) { ++ h_d = au_h_dptr(d, bindex); ++ if (h_d) ++ au_set_h_dptr(d, bindex, NULL); ++ } ++ au_set_dbend(d, a->btgt); ++ ++ sb = d->d_sb; ++ i = a->src_inode; ++ if (au_opt_test(au_mntflags(sb), PLINK) && au_plink_test(i)) ++ return; /* success */ ++ ++ bend = au_ibend(i); ++ for (bindex = a->btgt + 1; bindex <= bend; bindex++) { ++ h_i = au_h_iptr(i, bindex); ++ if (h_i) { ++ au_xino_write0(sb, bindex, h_i->i_ino, 0); ++ /* ignore this error */ ++ au_set_h_iptr(i, bindex, NULL, 0); ++ } ++ } ++ au_set_ibend(i, a->btgt); ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++/* 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(parent->d_inode); /* 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_bstart, dst_bstart 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_bstart = au_dbstart(a->src_dentry); ++ a->dst_bstart = au_dbstart(a->dst_dentry); ++ if (au_ftest_ren(a->flags, ISDIR)) ++ au_fset_wrdir(wr_dir_args.flags, ISDIR); ++ wr_dir_args.force_btgt = a->src_bstart; ++ if (a->dst_inode && a->dst_bstart < a->src_bstart) ++ wr_dir_args.force_btgt = a->dst_bstart; ++ 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; ++ ++ return err; ++} ++ ++static void au_ren_dt(struct au_ren_args *a) ++{ ++ a->h_path.dentry = a->src_h_parent; ++ au_dtime_store(a->src_dt + AuPARENT, a->src_parent, &a->h_path); ++ if (!au_ftest_ren(a->flags, ISSAMEDIR)) { ++ a->h_path.dentry = a->dst_h_parent; ++ au_dtime_store(a->dst_dt + AuPARENT, a->dst_parent, &a->h_path); ++ } ++ ++ au_fclr_ren(a->flags, DT_DSTDIR); ++ if (!au_ftest_ren(a->flags, ISDIR)) ++ return; ++ ++ a->h_path.dentry = a->src_h_dentry; ++ au_dtime_store(a->src_dt + AuCHILD, a->src_dentry, &a->h_path); ++ if (a->dst_h_dentry->d_inode) { ++ au_fset_ren(a->flags, DT_DSTDIR); ++ a->h_path.dentry = a->dst_h_dentry; ++ au_dtime_store(a->dst_dt + AuCHILD, a->dst_dentry, &a->h_path); ++ } ++} ++ ++static void au_ren_rev_dt(int err, struct au_ren_args *a) ++{ ++ struct dentry *h_d; ++ struct mutex *h_mtx; ++ ++ au_dtime_revert(a->src_dt + AuPARENT); ++ if (!au_ftest_ren(a->flags, ISSAMEDIR)) ++ au_dtime_revert(a->dst_dt + AuPARENT); ++ ++ if (au_ftest_ren(a->flags, ISDIR) && err != -EIO) { ++ h_d = a->src_dt[AuCHILD].dt_h_path.dentry; ++ h_mtx = &h_d->d_inode->i_mutex; ++ mutex_lock_nested(h_mtx, AuLsc_I_CHILD); ++ au_dtime_revert(a->src_dt + AuCHILD); ++ mutex_unlock(h_mtx); ++ ++ if (au_ftest_ren(a->flags, DT_DSTDIR)) { ++ h_d = a->dst_dt[AuCHILD].dt_h_path.dentry; ++ h_mtx = &h_d->d_inode->i_mutex; ++ mutex_lock_nested(h_mtx, AuLsc_I_CHILD); ++ au_dtime_revert(a->dst_dt + AuCHILD); ++ mutex_unlock(h_mtx); ++ } ++ } ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++int aufs_rename(struct inode *_src_dir, struct dentry *_src_dentry, ++ struct inode *_dst_dir, struct dentry *_dst_dentry) ++{ ++ int err; ++ /* reduce stack space */ ++ struct au_ren_args *a; ++ ++ IMustLock(_src_dir); ++ IMustLock(_dst_dir); ++ ++ err = -ENOMEM; ++ BUILD_BUG_ON(sizeof(*a) > PAGE_SIZE); ++ a = kzalloc(sizeof(*a), GFP_NOFS); ++ if (unlikely(!a)) ++ goto out; ++ ++ a->src_dir = _src_dir; ++ a->src_dentry = _src_dentry; ++ a->src_inode = a->src_dentry->d_inode; ++ 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 = a->dst_dentry->d_inode; ++ a->dst_parent = a->dst_dentry->d_parent; /* dir inode is locked */ ++ if (a->dst_inode) { ++ IMustLock(a->dst_inode); ++ au_igrab(a->dst_inode); ++ } ++ ++ err = -ENOTDIR; ++ if (S_ISDIR(a->src_inode->i_mode)) { ++ au_fset_ren(a->flags, ISDIR); ++ if (unlikely(a->dst_inode && !S_ISDIR(a->dst_inode->i_mode))) ++ goto out_free; ++ aufs_read_and_write_lock2(a->dst_dentry, a->src_dentry, ++ AuLock_DIR | AuLock_FLUSH); ++ } else ++ aufs_read_and_write_lock2(a->dst_dentry, a->src_dentry, ++ AuLock_FLUSH); ++ ++ au_fset_ren(a->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_unlock; ++ a->br = au_sbr(a->dst_dentry->d_sb, a->btgt); ++ a->h_path.mnt = a->br->br_mnt; ++ ++ /* are they available to be renamed */ ++ err = au_ren_may_dir(a); ++ if (unlikely(err)) ++ goto out_unlock; ++ ++ /* prepare the writable parent dir on the same branch */ ++ if (a->dst_bstart == a->btgt) { ++ au_fset_ren(a->flags, WHDST); ++ } else { ++ err = au_cpup_dirs(a->dst_dentry, a->btgt); ++ if (unlikely(err)) ++ goto out_children; ++ } ++ ++ 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->flags, ISDIR), ++ &a->btgt); ++ di_write_unlock(a->src_parent); ++ di_write_lock2_parent(a->src_parent, a->dst_parent, /*isdir*/1); ++ au_fclr_ren(a->flags, ISSAMEDIR); ++ } else ++ err = au_wr_dir_need_wh(a->src_dentry, ++ au_ftest_ren(a->flags, ISDIR), ++ &a->btgt); ++ if (unlikely(err < 0)) ++ goto out_children; ++ if (err) ++ au_fset_ren(a->flags, WHSRC); ++ ++ /* lock them all */ ++ err = au_ren_lock(a); ++ if (unlikely(err)) ++ goto out_children; ++ ++ if (!au_opt_test(au_mntflags(a->dst_dir->i_sb), UDBA_NONE)) { ++ err = au_may_ren(a); ++ if (unlikely(err)) ++ goto out_hdir; ++ } ++ ++ /* store timestamps to be revertible */ ++ au_ren_dt(a); ++ ++ /* here we go */ ++ err = do_rename(a); ++ if (unlikely(err)) ++ goto out_dt; ++ ++ /* update dir attributes */ ++ au_ren_refresh_dir(a); ++ ++ /* dput/iput all lower dentries */ ++ au_ren_refresh(a); ++ ++ goto out_hdir; /* success */ ++ ++ out_dt: ++ au_ren_rev_dt(err, a); ++ out_hdir: ++ au_ren_unlock(a); ++ out_children: ++ au_nhash_fin(&a->whlist); ++ out_unlock: ++ if (unlikely(err && au_ftest_ren(a->flags, ISDIR))) { ++ au_update_dbstart(a->dst_dentry); ++ d_drop(a->dst_dentry); ++ } ++ if (!err) { ++ d_move(a->src_dentry, a->dst_dentry); ++ if (a->dst_inode ++ && (a->dst_inode->i_nlink <= 1 ++ || au_ftest_ren(a->flags, ISDIR))) ++ a->dst_inode->i_flags |= S_DEAD; ++ } ++ if (au_ftest_ren(a->flags, ISSAMEDIR)) ++ di_write_unlock(a->dst_parent); ++ else ++ di_write_unlock2(a->src_parent, a->dst_parent); ++ aufs_read_and_write_unlock2(a->dst_dentry, a->src_dentry); ++ out_free: ++ iput(a->dst_inode); ++ kfree(a); ++ out: ++ return err; ++} +diff -urN ./fs/aufs/iinfo.c ./fs/aufs/iinfo.c +--- ./fs/aufs/iinfo.c 1970-01-01 01:00:00.000000000 +0100 ++++ ./fs/aufs/iinfo.c 2009-04-06 10:26:46.000000000 +0200 +@@ -0,0 +1,262 @@ ++/* ++ * Copyright (C) 2005-2009 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. ++ */ ++ ++/* ++ * inode private data ++ */ ++ ++#include "aufs.h" ++ ++struct inode *au_h_iptr(struct inode *inode, aufs_bindex_t bindex) ++{ ++ struct inode *h_inode; ++ ++ h_inode = au_ii(inode)->ii_hinode[0 + bindex].hi_inode; ++ AuDebugOn(h_inode && atomic_read(&h_inode->i_count) <= 0); ++ return h_inode; ++} ++ ++/* todo: hard/soft set? */ ++void au_set_ibstart(struct inode *inode, aufs_bindex_t bindex) ++{ ++ struct au_iinfo *iinfo = au_ii(inode); ++ struct inode *h_inode; ++ ++ iinfo->ii_bstart = bindex; ++ h_inode = iinfo->ii_hinode[bindex + 0].hi_inode; ++ if (h_inode) ++ au_cpup_igen(inode, h_inode); ++} ++ ++void au_hiput(struct au_hinode *hinode) ++{ ++ au_hin_free(hinode); ++ dput(hinode->hi_whdentry); ++ iput(hinode->hi_inode); ++} ++ ++unsigned int au_hi_flags(struct inode *inode, int isdir) ++{ ++ 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_HINOTIFY)) ++ au_fset_hi(flags, HINOTIFY); ++ 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); ++ ++ hinode = iinfo->ii_hinode + bindex; ++ hi = hinode->hi_inode; ++ AuDebugOn(h_inode && atomic_read(&h_inode->i_count) <= 0); ++ AuDebugOn(h_inode && hi); ++ ++ if (hi) ++ au_hiput(hinode); ++ hinode->hi_inode = h_inode; ++ if (h_inode) { ++ int err; ++ struct super_block *sb = inode->i_sb; ++ struct au_branch *br; ++ ++ if (bindex == iinfo->ii_bstart) ++ 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); ++ } ++ ++ if (au_ftest_hi(flags, HINOTIFY) ++ && au_br_hinotifyable(br->br_perm)) { ++ err = au_hin_alloc(hinode, inode, h_inode); ++ if (unlikely(err)) ++ AuIOErr1("au_hin_alloc() %d\n", err); ++ } ++ } ++} ++ ++void au_set_hi_wh(struct inode *inode, aufs_bindex_t bindex, ++ struct dentry *h_wh) ++{ ++ struct au_hinode *hinode; ++ ++ hinode = au_ii(inode)->ii_hinode + bindex; ++ AuDebugOn(hinode->hi_whdentry); ++ hinode->hi_whdentry = h_wh; ++} ++ ++void au_update_iigen(struct inode *inode) ++{ ++ atomic_set(&au_ii(inode)->ii_generation, au_sigen(inode->i_sb)); ++ /* smp_mb(); */ /* atomic_set */ ++} ++ ++/* it may be called at remount time, too */ ++void au_update_brange(struct inode *inode, int do_put_zero) ++{ ++ struct au_iinfo *iinfo; ++ ++ iinfo = au_ii(inode); ++ if (!iinfo || iinfo->ii_bstart < 0) ++ return; ++ ++ if (do_put_zero) { ++ aufs_bindex_t bindex; ++ ++ for (bindex = iinfo->ii_bstart; bindex <= iinfo->ii_bend; ++ bindex++) { ++ struct inode *h_i; ++ ++ h_i = iinfo->ii_hinode[0 + bindex].hi_inode; ++ if (h_i && !h_i->i_nlink) ++ au_set_h_iptr(inode, bindex, NULL, 0); ++ } ++ } ++ ++ iinfo->ii_bstart = -1; ++ while (++iinfo->ii_bstart <= iinfo->ii_bend) ++ if (iinfo->ii_hinode[0 + iinfo->ii_bstart].hi_inode) ++ break; ++ if (iinfo->ii_bstart > iinfo->ii_bend) { ++ iinfo->ii_bstart = -1; ++ iinfo->ii_bend = -1; ++ return; ++ } ++ ++ iinfo->ii_bend++; ++ while (0 <= --iinfo->ii_bend) ++ if (iinfo->ii_hinode[0 + iinfo->ii_bend].hi_inode) ++ break; ++ AuDebugOn(iinfo->ii_bstart > iinfo->ii_bend || iinfo->ii_bend < 0); ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++int au_iinfo_init(struct inode *inode) ++{ ++ struct au_iinfo *iinfo; ++ struct super_block *sb; ++ int nbr, i; ++ ++ sb = inode->i_sb; ++ iinfo = &(container_of(inode, struct au_icntnr, vfs_inode)->iinfo); ++ nbr = au_sbend(sb) + 1; ++ if (unlikely(nbr <= 0)) ++ nbr = 1; ++ iinfo->ii_hinode = kcalloc(nbr, sizeof(*iinfo->ii_hinode), GFP_NOFS); ++ if (iinfo->ii_hinode) { ++ for (i = 0; i < nbr; i++) ++ iinfo->ii_hinode[i].hi_id = -1; ++ ++ atomic_set(&iinfo->ii_generation, au_sigen(sb)); ++ /* smp_mb(); */ /* atomic_set */ ++ init_rwsem(&iinfo->ii_rwsem); ++ iinfo->ii_bstart = -1; ++ iinfo->ii_bend = -1; ++ iinfo->ii_vdir = NULL; ++ return 0; ++ } ++ return -ENOMEM; ++} ++ ++int au_ii_realloc(struct au_iinfo *iinfo, int nbr) ++{ ++ int err, sz; ++ struct au_hinode *hip; ++ ++ err = -ENOMEM; ++ sz = sizeof(*hip) * (iinfo->ii_bend + 1); ++ if (!sz) ++ sz = sizeof(*hip); ++ hip = au_kzrealloc(iinfo->ii_hinode, sz, sizeof(*hip) * nbr, GFP_NOFS); ++ if (hip) { ++ iinfo->ii_hinode = hip; ++ err = 0; ++ } ++ ++ return err; ++} ++ ++static int au_iinfo_write0(struct super_block *sb, struct au_hinode *hinode, ++ ino_t ino) ++{ ++ int err; ++ aufs_bindex_t bindex; ++ unsigned char locked; ++ ++ err = 0; ++ locked = !!si_noflush_read_trylock(sb); ++ bindex = au_br_index(sb, hinode->hi_id); ++ if (bindex >= 0) ++ err = au_xino_write0(sb, bindex, hinode->hi_inode->i_ino, ino); ++ /* error action? */ ++ if (locked) ++ si_read_unlock(sb); ++ return err; ++} ++ ++void au_iinfo_fin(struct inode *inode) ++{ ++ ino_t ino; ++ aufs_bindex_t bend; ++ unsigned char unlinked = !inode->i_nlink || IS_DEADDIR(inode); ++ struct au_iinfo *iinfo; ++ struct au_hinode *hi; ++ struct super_block *sb; ++ ++ if (unlinked) { ++ int err = au_xigen_inc(inode); ++ if (unlikely(err)) ++ AuWarn1("failed resetting i_generation, %d\n", err); ++ } ++ ++ iinfo = au_ii(inode); ++ /* bad_inode case */ ++ if (!iinfo) ++ return; ++ ++ if (iinfo->ii_vdir) ++ au_vdir_free(iinfo->ii_vdir); ++ ++ if (iinfo->ii_bstart >= 0) { ++ sb = inode->i_sb; ++ ino = 0; ++ if (unlinked) ++ ino = inode->i_ino; ++ hi = iinfo->ii_hinode + iinfo->ii_bstart; ++ bend = iinfo->ii_bend; ++ while (iinfo->ii_bstart++ <= bend) { ++ if (hi->hi_inode) { ++ if (unlinked || !hi->hi_inode->i_nlink) { ++ au_iinfo_write0(sb, hi, ino); ++ /* ignore this error */ ++ ino = 0; ++ } ++ au_hiput(hi); ++ } ++ hi++; ++ } ++ } ++ ++ kfree(iinfo->ii_hinode); ++ au_rwsem_destroy(&iinfo->ii_rwsem); ++} +diff -urN ./fs/aufs/inode.c ./fs/aufs/inode.c +--- ./fs/aufs/inode.c 1970-01-01 01:00:00.000000000 +0100 ++++ ./fs/aufs/inode.c 2009-04-06 10:26:46.000000000 +0200 +@@ -0,0 +1,356 @@ ++/* ++ * Copyright (C) 2005-2009 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. ++ */ ++ ++/* ++ * inode functions ++ */ ++ ++#include "aufs.h" ++ ++static void au_refresh_hinode_attr(struct inode *inode, int do_version) ++{ ++ au_cpup_attr_all(inode, /*force*/0); ++ au_update_iigen(inode); ++ if (do_version) ++ inode->i_version++; ++} ++ ++int au_refresh_hinode_self(struct inode *inode, int do_attr) ++{ ++ int err; ++ aufs_bindex_t bindex, new_bindex; ++ unsigned char update; ++ struct inode *first; ++ struct au_hinode *p, *q, tmp; ++ struct super_block *sb; ++ struct au_iinfo *iinfo; ++ ++ update = 0; ++ sb = inode->i_sb; ++ iinfo = au_ii(inode); ++ err = au_ii_realloc(iinfo, au_sbend(sb) + 1); ++ if (unlikely(err)) ++ goto out; ++ ++ p = iinfo->ii_hinode + iinfo->ii_bstart; ++ first = p->hi_inode; ++ err = 0; ++ for (bindex = iinfo->ii_bstart; bindex <= iinfo->ii_bend; ++ bindex++, p++) { ++ if (!p->hi_inode) ++ continue; ++ ++ new_bindex = au_br_index(sb, p->hi_id); ++ if (new_bindex == bindex) ++ continue; ++ ++ if (new_bindex < 0) { ++ update++; ++ au_hiput(p); ++ p->hi_inode = NULL; ++ continue; ++ } ++ ++ if (new_bindex < iinfo->ii_bstart) ++ iinfo->ii_bstart = new_bindex; ++ if (iinfo->ii_bend < new_bindex) ++ iinfo->ii_bend = new_bindex; ++ /* swap two lower inode, and loop again */ ++ q = iinfo->ii_hinode + new_bindex; ++ tmp = *q; ++ *q = *p; ++ *p = tmp; ++ if (tmp.hi_inode) { ++ bindex--; ++ p--; ++ } ++ } ++ au_update_brange(inode, /*do_put_zero*/0); ++ if (do_attr) ++ au_refresh_hinode_attr(inode, update && S_ISDIR(inode->i_mode)); ++ ++ out: ++ return err; ++} ++ ++int au_refresh_hinode(struct inode *inode, struct dentry *dentry) ++{ ++ int err, update; ++ unsigned int flags; ++ aufs_bindex_t bindex, bend; ++ unsigned char isdir; ++ struct inode *first; ++ struct au_hinode *p; ++ struct au_iinfo *iinfo; ++ ++ err = au_refresh_hinode_self(inode, /*do_attr*/0); ++ if (unlikely(err)) ++ goto out; ++ ++ update = 0; ++ iinfo = au_ii(inode); ++ p = iinfo->ii_hinode + iinfo->ii_bstart; ++ first = p->hi_inode; ++ isdir = S_ISDIR(inode->i_mode); ++ flags = au_hi_flags(inode, isdir); ++ bend = au_dbend(dentry); ++ for (bindex = au_dbstart(dentry); bindex <= bend; bindex++) { ++ struct inode *h_i; ++ struct dentry *h_d; ++ ++ h_d = au_h_dptr(dentry, bindex); ++ if (!h_d || !h_d->d_inode) ++ continue; ++ ++ if (iinfo->ii_bstart <= bindex && bindex <= iinfo->ii_bend) { ++ h_i = au_h_iptr(inode, bindex); ++ if (h_i) { ++ if (h_i == h_d->d_inode) ++ continue; ++ err = -EIO; ++ break; ++ } ++ } ++ if (bindex < iinfo->ii_bstart) ++ iinfo->ii_bstart = bindex; ++ if (iinfo->ii_bend < bindex) ++ iinfo->ii_bend = bindex; ++ au_set_h_iptr(inode, bindex, au_igrab(h_d->d_inode), flags); ++ update = 1; ++ } ++ au_update_brange(inode, /*do_put_zero*/0); ++ ++ if (unlikely(err)) ++ goto out; ++ ++ au_refresh_hinode_attr(inode, update && isdir); ++ ++ out: ++ return err; ++} ++ ++static int set_inode(struct inode *inode, struct dentry *dentry) ++{ ++ int err; ++ unsigned int flags; ++ umode_t mode; ++ aufs_bindex_t bindex, bstart, btail; ++ unsigned char isdir; ++ struct dentry *h_dentry; ++ struct inode *h_inode; ++ struct au_iinfo *iinfo; ++ ++ err = 0; ++ isdir = 0; ++ bstart = au_dbstart(dentry); ++ h_inode = au_h_dptr(dentry, bstart)->d_inode; ++ mode = h_inode->i_mode; ++ switch (mode & S_IFMT) { ++ case S_IFREG: ++ btail = au_dbtail(dentry); ++ inode->i_op = &aufs_iop; ++ inode->i_fop = &aufs_file_fop; ++ inode->i_mapping->a_ops = &aufs_aop; ++ break; ++ case S_IFDIR: ++ isdir = 1; ++ btail = au_dbtaildir(dentry); ++ inode->i_op = &aufs_dir_iop; ++ inode->i_fop = &aufs_dir_fop; ++ break; ++ case S_IFLNK: ++ btail = au_dbtail(dentry); ++ inode->i_op = &aufs_symlink_iop; ++ break; ++ case S_IFBLK: ++ case S_IFCHR: ++ case S_IFIFO: ++ case S_IFSOCK: ++ btail = au_dbtail(dentry); ++ inode->i_op = &aufs_iop; ++ init_special_inode(inode, mode, h_inode->i_rdev); ++ break; ++ default: ++ AuIOErr("Unknown file type 0%o\n", mode); ++ err = -EIO; ++ goto out; ++ } ++ ++ flags = au_hi_flags(inode, isdir); ++ iinfo = au_ii(inode); ++ iinfo->ii_bstart = bstart; ++ iinfo->ii_bend = btail; ++ for (bindex = bstart; bindex <= btail; bindex++) { ++ h_dentry = au_h_dptr(dentry, bindex); ++ if (h_dentry) ++ au_set_h_iptr(inode, bindex, ++ au_igrab(h_dentry->d_inode), flags); ++ } ++ au_cpup_attr_all(inode, /*force*/1); ++ ++ out: ++ return err; ++} ++ ++/* successful returns with iinfo write_locked */ ++static int reval_inode(struct inode *inode, struct dentry *dentry, int *matched) ++{ ++ int err; ++ aufs_bindex_t bindex, bend; ++ struct inode *h_inode, *h_dinode; ++ ++ *matched = 0; ++ ++ /* ++ * 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; ++ ++ ii_write_lock_new_child(inode); ++ if (unlikely(IS_DEADDIR(inode))) ++ goto out_unlock; ++ ++ err = 0; ++ h_dinode = au_h_dptr(dentry, au_dbstart(dentry))->d_inode; ++ bend = au_ibend(inode); ++ for (bindex = au_ibstart(inode); bindex <= bend; bindex++) { ++ h_inode = au_h_iptr(inode, bindex); ++ if (h_inode && h_inode == h_dinode) { ++ *matched = 1; ++ err = 0; ++ if (au_iigen(inode) != au_digen(dentry)) ++ err = au_refresh_hinode(inode, dentry); ++ break; ++ } ++ } ++ ++ out_unlock: ++ if (unlikely(err)) ++ ii_write_unlock(inode); ++ out: ++ return err; ++} ++ ++/* successful returns with iinfo write_locked */ ++/* todo: return with unlocked? */ ++struct inode *au_new_inode(struct dentry *dentry, int must_new) ++{ ++ struct inode *inode; ++ struct dentry *h_dentry; ++ struct super_block *sb; ++ ino_t h_ino, ino; ++ int err, match; ++ aufs_bindex_t bstart; ++ ++ sb = dentry->d_sb; ++ bstart = au_dbstart(dentry); ++ h_dentry = au_h_dptr(dentry, bstart); ++ h_ino = h_dentry->d_inode->i_ino; ++ err = au_xino_read(sb, bstart, h_ino, &ino); ++ inode = ERR_PTR(err); ++ if (unlikely(err)) ++ goto out; ++ new_ino: ++ if (!ino) { ++ ino = au_xino_new_ino(sb); ++ if (unlikely(!ino)) { ++ inode = ERR_PTR(-EIO); ++ goto out; ++ } ++ } ++ ++ AuDbg("i%lu\n", (unsigned long)ino); ++ inode = au_iget_locked(sb, ino); ++ err = PTR_ERR(inode); ++ if (IS_ERR(inode)) ++ 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); ++ unlock_new_inode(inode); ++ if (!err) ++ goto out; /* success */ ++ ++ iget_failed(inode); ++ ii_write_unlock(inode); ++ goto out_iput; ++ } else if (!must_new) { ++ err = reval_inode(inode, dentry, &match); ++ if (!err) ++ goto out; /* success */ ++ else if (match) ++ goto out_iput; ++ } ++ ++ if (unlikely(au_test_fs_unique_ino(h_dentry->d_inode))) ++ AuWarn1("Un-notified UDBA or repeatedly renamed dir," ++ " b%d, %s, %.*s, hi%lu, i%lu.\n", ++ bstart, au_sbtype(h_dentry->d_sb), AuDLNPair(dentry), ++ (unsigned long)h_ino, (unsigned long)ino); ++ ino = 0; ++ err = au_xino_write0(sb, bstart, h_ino, 0); ++ if (!err) { ++ iput(inode); ++ goto new_ino; ++ } ++ ++ out_iput: ++ iput(inode); ++ inode = ERR_PTR(err); ++ out: ++ return inode; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++int au_test_ro(struct super_block *sb, aufs_bindex_t bindex, ++ struct inode *inode) ++{ ++ int err; ++ ++ err = au_br_rdonly(au_sbr(sb, bindex)); ++ ++ /* pseudo-link after flushed may happen out of bounds */ ++ if (!err ++ && inode ++ && au_ibstart(inode) <= bindex ++ && bindex <= au_ibend(inode)) { ++ /* ++ * permission check is unnecessary since vfsub routine ++ * will be called later ++ */ ++ struct inode *hi = au_h_iptr(inode, bindex); ++ if (hi) ++ err = IS_IMMUTABLE(hi) ? -EROFS : 0; ++ } ++ ++ return err; ++} ++ ++int au_test_h_perm(struct inode *h_inode, int mask) ++{ ++ if (!current_fsuid()) ++ 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 -urN ./fs/aufs/inode.h ./fs/aufs/inode.h +--- ./fs/aufs/inode.h 1970-01-01 01:00:00.000000000 +0100 ++++ ./fs/aufs/inode.h 2009-04-06 10:26:46.000000000 +0200 +@@ -0,0 +1,471 @@ ++/* ++ * Copyright (C) 2005-2009 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. ++ */ ++ ++/* ++ * inode operations ++ */ ++ ++#ifndef __AUFS_INODE_H__ ++#define __AUFS_INODE_H__ ++ ++#ifdef __KERNEL__ ++ ++#include <linux/fs.h> ++#include <linux/inotify.h> ++#include <linux/namei.h> ++#include <linux/aufs_type.h> ++#include "rwsem.h" ++ ++struct au_hinotify { ++#ifdef CONFIG_AUFS_HINOTIFY ++ struct inotify_watch hin_watch; ++ struct inode *hin_aufs_inode; /* no get/put */ ++#endif ++}; ++ ++struct au_hinode { ++ struct inode *hi_inode; ++ aufs_bindex_t hi_id; ++#ifdef CONFIG_AUFS_HINOTIFY ++ struct au_hinotify *hi_notify; ++#endif ++ ++ /* reference to the copied-up whiteout with get/put */ ++ struct dentry *hi_whdentry; ++}; ++ ++struct au_vdir; ++struct au_iinfo { ++ atomic_t ii_generation; ++ struct super_block *ii_hsb1; /* no get/put */ ++ ++ struct rw_semaphore ii_rwsem; ++ aufs_bindex_t ii_bstart, ii_bend; ++ __u32 ii_higen; ++ struct au_hinode *ii_hinode; ++ struct au_vdir *ii_vdir; ++}; ++ ++struct au_icntnr { ++ struct au_iinfo iinfo; ++ struct inode vfs_inode; ++}; ++ ++/* 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) { (flags) |= AuPin_##name; } ++#define au_fclr_pin(flags, name) { (flags) &= ~AuPin_##name; } ++ ++struct au_pin { ++ /* input */ ++ struct dentry *dentry; ++ unsigned int udba; ++ unsigned char lsc_di, lsc_hi, flags; ++ aufs_bindex_t bindex; ++ ++ /* output */ ++ struct dentry *parent; ++ struct au_hinode *hdir; ++ struct vfsmount *h_mnt; ++}; ++ ++/* ---------------------------------------------------------------------- */ ++ ++static inline struct au_iinfo *au_ii(struct inode *inode) ++{ ++ struct au_iinfo *iinfo; ++ ++ iinfo = &(container_of(inode, struct au_icntnr, vfs_inode)->iinfo); ++ if (iinfo->ii_hinode) ++ return iinfo; ++ return NULL; /* debugging bad_inode case */ ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++/* inode.c */ ++int au_refresh_hinode_self(struct inode *inode, int do_attr); ++int au_refresh_hinode(struct inode *inode, struct dentry *dentry); ++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); ++ ++/* i_op.c */ ++extern struct inode_operations aufs_iop, aufs_symlink_iop, aufs_dir_iop; ++ ++/* au_wr_dir flags */ ++#define AuWrDir_ADD_ENTRY 1 ++#define AuWrDir_ISDIR (1 << 1) ++#define au_ftest_wrdir(flags, name) ((flags) & AuWrDir_##name) ++#define au_fset_wrdir(flags, name) { (flags) |= AuWrDir_##name; } ++#define au_fclr_wrdir(flags, name) { (flags) &= ~AuWrDir_##name; } ++ ++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); ++ ++/* 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, int 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, int mode, ++ struct nameidata *nd); ++int aufs_link(struct dentry *src_dentry, struct inode *dir, ++ struct dentry *dentry); ++int aufs_mkdir(struct inode *dir, struct dentry *dentry, int mode); ++ ++/* 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); ++ ++/* 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); ++ ++/* iinfo.c */ ++struct inode *au_h_iptr(struct inode *inode, aufs_bindex_t bindex); ++void au_hiput(struct au_hinode *hinode); ++void au_set_ibstart(struct inode *inode, aufs_bindex_t bindex); ++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); ++ ++/* hinode flags */ ++#define AuHi_XINO 1 ++#define AuHi_HINOTIFY (1 << 1) ++#define au_ftest_hi(flags, name) ((flags) & AuHi_##name) ++#define au_fset_hi(flags, name) { (flags) |= AuHi_##name; } ++#define au_fclr_hi(flags, name) { (flags) &= ~AuHi_##name; } ++ ++#ifndef CONFIG_AUFS_HINOTIFY ++#undef AuHi_HINOTIFY ++#define AuHi_HINOTIFY 0 ++#endif ++ ++void au_set_h_iptr(struct inode *inode, aufs_bindex_t bindex, ++ struct inode *h_inode, unsigned int flags); ++ ++void au_update_iigen(struct inode *inode); ++void au_update_brange(struct inode *inode, int do_put_zero); ++ ++int au_iinfo_init(struct inode *inode); ++void au_iinfo_fin(struct inode *inode); ++int au_ii_realloc(struct au_iinfo *iinfo, int nbr); ++ ++/* plink.c */ ++void au_plink_block_maintain(struct super_block *sb); ++#ifdef CONFIG_AUFS_DEBUG ++void au_plink_list(struct super_block *sb); ++#else ++static inline void au_plink_list(struct super_block *sb) ++{ ++ /* nothing */ ++} ++#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); ++void au_plink_half_refresh(struct super_block *sb, aufs_bindex_t br_id); ++ ++/* ---------------------------------------------------------------------- */ ++ ++/* lock subclass for iinfo */ ++enum { ++ AuLsc_II_CHILD, /* child first */ ++ AuLsc_II_CHILD2, /* rename(2), link(2), and cpup at hinotify */ ++ 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 ++}; ++ ++/* ++ * 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) \ ++{ \ ++ down_read_nested(&au_ii(i)->ii_rwsem, AuLsc_II_##lsc); \ ++} ++ ++#define AuWriteLockFunc(name, lsc) \ ++static inline void ii_write_lock_##name(struct inode *i) \ ++{ \ ++ down_write_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 ++ ++/* ++ * ii_read_unlock, ii_write_unlock, ii_downgrade_lock ++ */ ++AuSimpleUnlockRwsemFuncs(ii, struct inode *i, &au_ii(i)->ii_rwsem); ++ ++#define IiMustNoWaiters(i) AuRwMustNoWaiters(&au_ii(i)->ii_rwsem) ++ ++/* ---------------------------------------------------------------------- */ ++ ++static inline unsigned int au_iigen(struct inode *inode) ++{ ++ return atomic_read(&au_ii(inode)->ii_generation); ++} ++ ++/* 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; ++ ++ iinfo = au_ii(inode); ++ return !(iinfo->ii_hsb1 == h_inode->i_sb ++ && iinfo->ii_higen == h_inode->i_generation); ++} ++ ++static inline struct inode *au_igrab(struct inode *inode) ++{ ++ if (inode) { ++ AuDebugOn(!atomic_read(&inode->i_count)); ++ atomic_inc(&inode->i_count); ++ } ++ return inode; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++static inline aufs_bindex_t au_ii_br_id(struct inode *inode, ++ aufs_bindex_t bindex) ++{ ++ return au_ii(inode)->ii_hinode[0 + bindex].hi_id; ++} ++ ++static inline aufs_bindex_t au_ibstart(struct inode *inode) ++{ ++ return au_ii(inode)->ii_bstart; ++} ++ ++static inline aufs_bindex_t au_ibend(struct inode *inode) ++{ ++ return au_ii(inode)->ii_bend; ++} ++ ++static inline struct au_vdir *au_ivdir(struct inode *inode) ++{ ++ return au_ii(inode)->ii_vdir; ++} ++ ++static inline struct dentry *au_hi_wh(struct inode *inode, aufs_bindex_t bindex) ++{ ++ return au_ii(inode)->ii_hinode[0 + bindex].hi_whdentry; ++} ++ ++static inline void au_set_ibend(struct inode *inode, aufs_bindex_t bindex) ++{ ++ au_ii(inode)->ii_bend = bindex; ++} ++ ++static inline void au_set_ivdir(struct inode *inode, struct au_vdir *vdir) ++{ ++ au_ii(inode)->ii_vdir = vdir; ++} ++ ++static inline struct au_hinode *au_hi(struct inode *inode, aufs_bindex_t bindex) ++{ ++ return au_ii(inode)->ii_hinode + bindex; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++static inline struct dentry *au_pinned_parent(struct au_pin *pin) ++{ ++ if (pin) ++ return pin->parent; ++ return NULL; ++} ++ ++static inline struct inode *au_pinned_h_dir(struct au_pin *pin) ++{ ++ if (pin && pin->hdir) ++ return pin->hdir->hi_inode; ++ return NULL; ++} ++ ++static inline struct au_hinode *au_pinned_hdir(struct au_pin *pin) ++{ ++ if (pin) ++ return pin->hdir; ++ return NULL; ++} ++ ++static inline void au_pin_set_dentry(struct au_pin *pin, struct dentry *dentry) ++{ ++ if (pin) ++ pin->dentry = dentry; ++} ++ ++static inline void au_pin_set_parent_lflag(struct au_pin *pin, ++ unsigned char lflag) ++{ ++ if (pin) { ++ /* dirty macros require brackets */ ++ if (lflag) { ++ au_fset_pin(pin->flags, DI_LOCKED); ++ } else { ++ au_fclr_pin(pin->flags, DI_LOCKED); ++ } ++ } ++} ++ ++static inline void au_pin_set_parent(struct au_pin *pin, struct dentry *parent) ++{ ++ if (pin) { ++ dput(pin->parent); ++ pin->parent = dget(parent); ++ } ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++#ifdef CONFIG_AUFS_HINOTIFY ++/* hinotify.c */ ++int au_hin_alloc(struct au_hinode *hinode, struct inode *inode, ++ struct inode *h_inode); ++void au_hin_free(struct au_hinode *hinode); ++void au_hin_ctl(struct au_hinode *hinode, int do_set); ++void au_reset_hinotify(struct inode *inode, unsigned int flags); ++ ++int __init au_hinotify_init(void); ++void au_hinotify_fin(void); ++ ++static inline ++void au_hin_init(struct au_hinode *hinode, struct au_hinotify *val) ++{ ++ hinode->hi_notify = val; ++} ++ ++static inline void au_iigen_dec(struct inode *inode) ++{ ++ atomic_dec(&au_ii(inode)->ii_generation); ++} ++ ++#else ++static inline ++int au_hin_alloc(struct au_hinode *hinode __maybe_unused, ++ struct inode *inode __maybe_unused, ++ struct inode *h_inode __maybe_unused) ++{ ++ return -EOPNOTSUPP; ++} ++ ++static inline void au_hin_free(struct au_hinode *hinode __maybe_unused) ++{ ++ /* nothing */ ++} ++ ++static inline void au_hin_ctl(struct au_hinode *hinode __maybe_unused, ++ int do_set __maybe_unused) ++{ ++ /* nothing */ ++} ++ ++static inline void au_reset_hinotify(struct inode *inode __maybe_unused, ++ unsigned int flags __maybe_unused) ++{ ++ /* nothing */ ++} ++ ++static inline int au_hinotify_init(void) ++{ ++ return 0; ++} ++ ++#define au_hinotify_fin() do {} while (0) ++ ++static inline ++void au_hin_init(struct au_hinode *hinode __maybe_unused, ++ struct au_hinotify *val __maybe_unused) ++{ ++ /* empty */ ++} ++#endif /* CONFIG_AUFS_HINOTIFY */ ++ ++static inline void au_hin_suspend(struct au_hinode *hdir) ++{ ++ au_hin_ctl(hdir, /*do_set*/0); ++} ++ ++static inline void au_hin_resume(struct au_hinode *hdir) ++{ ++ au_hin_ctl(hdir, /*do_set*/1); ++} ++ ++static inline void au_hin_imtx_lock(struct au_hinode *hdir) ++{ ++ mutex_lock(&hdir->hi_inode->i_mutex); ++ au_hin_suspend(hdir); ++} ++ ++static inline void au_hin_imtx_lock_nested(struct au_hinode *hdir, ++ unsigned int sc __maybe_unused) ++{ ++ mutex_lock_nested(&hdir->hi_inode->i_mutex, sc); ++ au_hin_suspend(hdir); ++} ++ ++static inline void au_hin_imtx_unlock(struct au_hinode *hdir) ++{ ++ au_hin_resume(hdir); ++ mutex_unlock(&hdir->hi_inode->i_mutex); ++} ++ ++#endif /* __KERNEL__ */ ++#endif /* __AUFS_INODE_H__ */ +diff -urN ./fs/aufs/ioctl.c ./fs/aufs/ioctl.c +--- ./fs/aufs/ioctl.c 1970-01-01 01:00:00.000000000 +0100 ++++ ./fs/aufs/ioctl.c 2009-04-06 10:26:46.000000000 +0200 +@@ -0,0 +1,54 @@ ++/* ++ * Copyright (C) 2005-2009 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. ++ */ ++ ++#include <linux/uaccess.h> ++#include "aufs.h" ++ ++long aufs_ioctl_dir(struct file *file, unsigned int cmd, ++ unsigned long arg __maybe_unused) ++{ ++ long err; ++ struct super_block *sb; ++ struct au_sbinfo *sbinfo; ++ ++ err = -EACCES; ++ if (!capable(CAP_SYS_ADMIN)) ++ goto out; ++ ++ err = 0; ++ sb = file->f_dentry->d_sb; ++ sbinfo = au_sbi(sb); ++ switch (cmd) { ++ case AUFS_CTL_PLINK_MAINT: ++ /* ++ * pseudo-link maintenance mode, ++ * cleared by aufs_release_dir() ++ */ ++ si_write_lock(sb); ++ if (!au_ftest_si(sbinfo, MAINTAIN_PLINK)) { ++ au_fset_si(sbinfo, MAINTAIN_PLINK); ++ au_fi(file)->fi_maintain_plink = 1; ++ } else ++ err = -EBUSY; ++ si_write_unlock(sb); ++ break; ++ case AUFS_CTL_PLINK_CLEAN: ++ if (au_opt_test(sbinfo->si_mntflags, PLINK)) { ++ aufs_write_lock(sb->s_root); ++ au_plink_put(sb); ++ aufs_write_unlock(sb->s_root); ++ } ++ break; ++ default: ++ err = -EINVAL; ++ } ++ ++ out: ++ return err; ++} +diff -urN ./fs/aufs/loop.c ./fs/aufs/loop.c +--- ./fs/aufs/loop.c 1970-01-01 01:00:00.000000000 +0100 ++++ ./fs/aufs/loop.c 2009-04-06 10:26:46.000000000 +0200 +@@ -0,0 +1,46 @@ ++/* ++ * Copyright (C) 2005-2009 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. ++ */ ++ ++/* ++ * support for loopback block device as a branch ++ */ ++ ++#include <linux/loop.h> ++#include "aufs.h" ++ ++/* ++ * test if two lower dentries have overlapping branches. ++ */ ++int au_test_loopback_overlap(struct super_block *sb, struct dentry *h_d1, ++ struct dentry *h_d2) ++{ ++ struct inode *h_inode; ++ struct loop_device *l; ++ ++ h_inode = h_d1->d_inode; ++ if (MAJOR(h_inode->i_sb->s_dev) != LOOP_MAJOR) ++ return 0; ++ ++ l = h_inode->i_sb->s_bdev->bd_disk->private_data; ++ h_d1 = l->lo_backing_file->f_dentry; ++ /* h_d1 can be local NFS. in this case aufs cannot detect the loop */ ++ if (unlikely(h_d1->d_sb == sb)) ++ return 1; ++ return !!au_test_subdir(h_d1, h_d2); ++} ++ ++/* true if a kernel thread named 'loop[0-9].*' accesses a file */ ++int au_test_loopback_kthread(void) ++{ ++ const char c = current->comm[4]; ++ ++ return current->mm == NULL ++ && '0' <= c && c <= '9' ++ && strncmp(current->comm, "loop", 4) == 0; ++} +diff -urN ./fs/aufs/loop.h ./fs/aufs/loop.h +--- ./fs/aufs/loop.h 1970-01-01 01:00:00.000000000 +0100 ++++ ./fs/aufs/loop.h 2009-04-06 10:26:46.000000000 +0200 +@@ -0,0 +1,41 @@ ++/* ++ * Copyright (C) 2005-2009 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. ++ */ ++ ++/* ++ * support for loopback mount as a branch ++ */ ++ ++#ifndef __AUFS_LOOP_H__ ++#define __AUFS_LOOP_H__ ++ ++#ifdef __KERNEL__ ++ ++#include <linux/fs.h> ++ ++#ifdef CONFIG_AUFS_BDEV_LOOP ++/* loop.c */ ++int au_test_loopback_overlap(struct super_block *sb, struct dentry *h_d1, ++ struct dentry *h_d2); ++int au_test_loopback_kthread(void); ++#else ++static inline ++int au_test_loopback_overlap(struct super_block *sb, struct dentry *h_d1, ++ struct dentry *h_d2) ++{ ++ return 0; ++} ++ ++static inline int au_test_loopback_kthread(void) ++{ ++ return 0; ++} ++#endif /* BLK_DEV_LOOP */ ++ ++#endif /* __KERNEL__ */ ++#endif /* __AUFS_LOOP_H__ */ +diff -urN ./fs/aufs/magic.mk ./fs/aufs/magic.mk +--- ./fs/aufs/magic.mk 1970-01-01 01:00:00.000000000 +0100 ++++ ./fs/aufs/magic.mk 2009-04-06 10:26:46.000000000 +0200 +@@ -0,0 +1,58 @@ ++ ++# defined in ${srctree}/fs/fuse/inode.c ++# tristate ++ifdef CONFIG_FUSE_FS ++ccflags-y += -DFUSE_SUPER_MAGIC=0x65735546 ++endif ++ ++# defined in ${srctree}/fs/ocfs2/ocfs2_fs.h ++# tristate ++ifdef CONFIG_OCFS2_FS ++ccflags-y += -DOCFS2_SUPER_MAGIC=0x7461636f ++endif ++ ++# defined in ${srctree}/fs/ocfs2/dlm/userdlm.h ++# tristate ++ifdef CONFIG_OCFS2_FS_O2CB ++ccflags-y += -DDLMFS_MAGIC=0x76a9f425 ++endif ++ ++# defined in ${srctree}/fs/ramfs/inode.c ++# always true ++ccflags-y += -DRAMFS_MAGIC=0x858458f6 ++ ++# defined in ${srctree}/fs/cifs/cifsfs.c ++# tristate ++ifdef CONFIG_CIFS_FS ++ccflags-y += -DCIFS_MAGIC_NUMBER=0xFF534D42 ++endif ++ ++# defined in ${srctree}/fs/xfs/xfs_sb.h ++# tristate ++ifdef CONFIG_XFS_FS ++ccflags-y += -DXFS_SB_MAGIC=0x58465342 ++endif ++ ++# defined in ${srctree}/fs/configfs/mount.c ++# tristate ++ifdef CONFIG_CONFIGFS_FS ++ccflags-y += -DCONFIGFS_MAGIC=0x62656570 ++endif ++ ++# defined in ${srctree}/fs/9p/v9fs.h ++# tristate ++ifdef CONFIG_9P_FS ++ccflags-y += -DV9FS_MAGIC=0x01021997 ++endif ++ ++# defined in ${srctree}/fs/ubifs/ubifs.h ++# tristate ++ifdef CONFIG_UBIFS_FS ++ccflags-y += -DUBIFS_SUPER_MAGIC=0x24051905 ++endif ++ ++# defined in ${srctree}/fs/debugfs/inode.c ++# boolean ++ifdef CONFIG_DEBUG_FS ++ccflags-y += -DDEBUGFS_MAGIC=0x64626720 ++endif +diff -urN ./fs/aufs/module.c ./fs/aufs/module.c +--- ./fs/aufs/module.c 1970-01-01 01:00:00.000000000 +0100 ++++ ./fs/aufs/module.c 2009-04-06 10:26:46.000000000 +0200 +@@ -0,0 +1,164 @@ ++/* ++ * Copyright (C) 2005-2009 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. ++ */ ++ ++/* ++ * module global variables and operations ++ */ ++ ++#include <linux/module.h> ++#include <linux/seq_file.h> ++#include "aufs.h" ++ ++void *au_kzrealloc(void *p, unsigned int nused, unsigned int new_sz, gfp_t gfp) ++{ ++ if (new_sz <= nused) ++ return p; ++ ++ p = krealloc(p, new_sz, gfp); ++ if (p) ++ memset(p + nused, 0, new_sz - nused); ++ return p; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++/* ++ * aufs caches ++ */ ++struct kmem_cache *au_cachep[AuCache_Last]; ++static int __init au_cache_init(void) ++{ ++ au_cachep[AuCache_DINFO] = AuCache(au_dinfo); ++ if (au_cachep[AuCache_DINFO]) ++ au_cachep[AuCache_ICNTNR] = AuCache(au_icntnr); ++ if (au_cachep[AuCache_ICNTNR]) ++ au_cachep[AuCache_FINFO] = AuCache(au_finfo); ++ if (au_cachep[AuCache_FINFO]) ++ au_cachep[AuCache_VDIR] = AuCache(au_vdir); ++ if (au_cachep[AuCache_VDIR]) ++ au_cachep[AuCache_DEHSTR] = AuCache(au_vdir_dehstr); ++ if (au_cachep[AuCache_DEHSTR]) ++ return 0; ++ ++ return -ENOMEM; ++} ++ ++static void au_cache_fin(void) ++{ ++ int i; ++ for (i = 0; i < AuCache_Last; i++) ++ if (au_cachep[i]) { ++ kmem_cache_destroy(au_cachep[i]); ++ au_cachep[i] = NULL; ++ } ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++int au_dir_roflags; ++ ++/* ++ * functions for module interface. ++ */ ++MODULE_LICENSE("GPL"); ++/* MODULE_LICENSE("GPL v2"); */ ++MODULE_AUTHOR("Junjiro R. Okajima"); ++MODULE_DESCRIPTION(AUFS_NAME ++ " -- Advanced multi layered unification filesystem"); ++MODULE_VERSION(AUFS_VERSION); ++ ++/* it should be 'byte', but param_set_byte() prints it by "%c" */ ++short aufs_nwkq = AUFS_NWKQ_DEF; ++MODULE_PARM_DESC(nwkq, "the number of workqueue thread, " AUFS_WKQ_NAME); ++module_param_named(nwkq, aufs_nwkq, short, S_IRUGO); ++ ++/* this module parameter has no meaning when SYSFS is disabled */ ++int sysaufs_brs = 1; ++MODULE_PARM_DESC(brs, "use <sysfs>/fs/aufs/si_*/brN"); ++module_param_named(brs, sysaufs_brs, int, S_IRUGO); ++ ++/* ---------------------------------------------------------------------- */ ++ ++static char au_esc_chars[0x20 + 3]; /* 0x01-0x20, backslash, del, and NULL */ ++ ++int au_seq_path(struct seq_file *seq, struct path *path) ++{ ++ return seq_path(seq, path, au_esc_chars); ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++static int __init aufs_init(void) ++{ ++ int err, i; ++ char *p; ++ ++ p = au_esc_chars; ++ for (i = 1; i <= ' '; i++) ++ *p++ = i; ++ *p++ = '\\'; ++ *p++ = '\x7f'; ++ *p = 0; ++ ++ au_dir_roflags = au_file_roflags(O_DIRECTORY | O_LARGEFILE); ++ ++ sysaufs_brs_init(); ++ au_debug_init(); ++ ++ err = -EINVAL; ++ if (unlikely(aufs_nwkq <= 0)) ++ goto out; ++ ++ err = sysaufs_init(); ++ if (unlikely(err)) ++ goto out; ++ err = au_wkq_init(); ++ if (unlikely(err)) ++ goto out_sysaufs; ++ err = au_hinotify_init(); ++ if (unlikely(err)) ++ goto out_wkq; ++ err = au_sysrq_init(); ++ if (unlikely(err)) ++ goto out_hin; ++ err = au_cache_init(); ++ if (unlikely(err)) ++ goto out_sysrq; ++ err = register_filesystem(&aufs_fs_type); ++ if (unlikely(err)) ++ goto out_cache; ++ pr_info(AUFS_NAME " " AUFS_VERSION "\n"); ++ goto out; /* success */ ++ ++ out_cache: ++ au_cache_fin(); ++ out_sysrq: ++ au_sysrq_fin(); ++ out_hin: ++ au_hinotify_fin(); ++ out_wkq: ++ au_wkq_fin(); ++ out_sysaufs: ++ sysaufs_fin(); ++ out: ++ return err; ++} ++ ++static void __exit aufs_exit(void) ++{ ++ unregister_filesystem(&aufs_fs_type); ++ au_cache_fin(); ++ au_sysrq_fin(); ++ au_hinotify_fin(); ++ au_wkq_fin(); ++ sysaufs_fin(); ++} ++ ++module_init(aufs_init); ++module_exit(aufs_exit); +diff -urN ./fs/aufs/module.h ./fs/aufs/module.h +--- ./fs/aufs/module.h 1970-01-01 01:00:00.000000000 +0100 ++++ ./fs/aufs/module.h 2009-04-06 10:26:46.000000000 +0200 +@@ -0,0 +1,66 @@ ++/* ++ * Copyright (C) 2005-2009 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. ++ */ ++ ++/* ++ * module initialization and module-global ++ */ ++ ++#ifndef __AUFS_MODULE_H__ ++#define __AUFS_MODULE_H__ ++ ++#ifdef __KERNEL__ ++ ++#include <linux/slab.h> ++ ++/* module parameters */ ++extern short aufs_nwkq; ++extern int sysaufs_brs; ++ ++/* ---------------------------------------------------------------------- */ ++ ++extern int au_dir_roflags; ++ ++void *au_kzrealloc(void *p, unsigned int nused, unsigned int new_sz, gfp_t gfp); ++int au_seq_path(struct seq_file *seq, struct path *path); ++ ++/* ---------------------------------------------------------------------- */ ++ ++/* kmem cache */ ++enum { ++ AuCache_DINFO, ++ AuCache_ICNTNR, ++ AuCache_FINFO, ++ AuCache_VDIR, ++ AuCache_DEHSTR, ++#ifdef CONFIG_AUFS_HINOTIFY ++ AuCache_HINOTIFY, ++#endif ++ AuCache_Last ++}; ++ ++#define AuCache(type) KMEM_CACHE(type, SLAB_RECLAIM_ACCOUNT) ++ ++extern struct kmem_cache *au_cachep[]; ++ ++#define AuCacheFuncs(name, index) \ ++static inline void *au_cache_alloc_##name(void) \ ++{ return kmem_cache_alloc(au_cachep[AuCache_##index], GFP_NOFS); } \ ++static inline void au_cache_free_##name(void *p) \ ++{ kmem_cache_free(au_cachep[AuCache_##index], p); } ++ ++AuCacheFuncs(dinfo, DINFO); ++AuCacheFuncs(icntnr, ICNTNR); ++AuCacheFuncs(finfo, FINFO); ++AuCacheFuncs(vdir, VDIR); ++AuCacheFuncs(dehstr, DEHSTR); ++ ++/* ---------------------------------------------------------------------- */ ++ ++#endif /* __KERNEL__ */ ++#endif /* __AUFS_MODULE_H__ */ +diff -urN ./fs/aufs/opts.c ./fs/aufs/opts.c +--- ./fs/aufs/opts.c 1970-01-01 01:00:00.000000000 +0100 ++++ ./fs/aufs/opts.c 2009-04-06 10:26:46.000000000 +0200 +@@ -0,0 +1,1438 @@ ++/* ++ * Copyright (C) 2005-2009 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. ++ */ ++ ++/* ++ * mount options/flags ++ */ ++ ++#include <linux/types.h> /* a distribution requires */ ++#include <linux/parser.h> ++#include "aufs.h" ++ ++/* ---------------------------------------------------------------------- */ ++ ++enum { ++ Opt_br, ++ Opt_add, Opt_del, Opt_mod, Opt_reorder, Opt_append, Opt_prepend, ++ Opt_idel, Opt_imod, Opt_ireorder, ++ Opt_dirwh, Opt_rdcache, Opt_deblk, Opt_nhash, Opt_rendir, ++ Opt_xino, Opt_zxino, Opt_noxino, ++ Opt_trunc_xino, Opt_trunc_xino_v, Opt_notrunc_xino, ++ Opt_trunc_xino_path, Opt_itrunc_xino, ++ Opt_trunc_xib, Opt_notrunc_xib, ++ Opt_plink, Opt_noplink, Opt_list_plink, ++ Opt_udba, ++ /* Opt_lock, Opt_unlock, */ ++ Opt_cmd, Opt_cmd_args, ++ Opt_diropq_a, Opt_diropq_w, ++ Opt_warn_perm, Opt_nowarn_perm, ++ Opt_wbr_copyup, Opt_wbr_create, ++ Opt_refrof, Opt_norefrof, ++ Opt_verbose, Opt_noverbose, ++ Opt_sum, Opt_nosum, Opt_wsum, ++ Opt_tail, Opt_ignore, Opt_ignore_silent, Opt_err ++}; ++ ++static match_table_t options = { ++ {Opt_br, "br=%s"}, ++ {Opt_br, "br:%s"}, ++ ++ {Opt_add, "add=%d:%s"}, ++ {Opt_add, "add:%d:%s"}, ++ {Opt_add, "ins=%d:%s"}, ++ {Opt_add, "ins:%d:%s"}, ++ {Opt_append, "append=%s"}, ++ {Opt_append, "append:%s"}, ++ {Opt_prepend, "prepend=%s"}, ++ {Opt_prepend, "prepend:%s"}, ++ ++ {Opt_del, "del=%s"}, ++ {Opt_del, "del:%s"}, ++ /* {Opt_idel, "idel:%d"}, */ ++ {Opt_mod, "mod=%s"}, ++ {Opt_mod, "mod:%s"}, ++ /* {Opt_imod, "imod:%d:%s"}, */ ++ ++ {Opt_dirwh, "dirwh=%d"}, ++ ++ {Opt_xino, "xino=%s"}, ++ {Opt_noxino, "noxino"}, ++ {Opt_trunc_xino, "trunc_xino"}, ++ {Opt_trunc_xino_v, "trunc_xino_v=%d:%d"}, ++ {Opt_notrunc_xino, "notrunc_xino"}, ++ {Opt_trunc_xino_path, "trunc_xino=%s"}, ++ {Opt_itrunc_xino, "itrunc_xino=%d"}, ++ /* {Opt_zxino, "zxino=%s"}, */ ++ {Opt_trunc_xib, "trunc_xib"}, ++ {Opt_notrunc_xib, "notrunc_xib"}, ++ ++ {Opt_plink, "plink"}, ++ {Opt_noplink, "noplink"}, ++#ifdef CONFIG_AUFS_DEBUG ++ {Opt_list_plink, "list_plink"}, ++#endif ++ ++ {Opt_udba, "udba=%s"}, ++ ++ {Opt_diropq_a, "diropq=always"}, ++ {Opt_diropq_a, "diropq=a"}, ++ {Opt_diropq_w, "diropq=whiteouted"}, ++ {Opt_diropq_w, "diropq=w"}, ++ ++ {Opt_warn_perm, "warn_perm"}, ++ {Opt_nowarn_perm, "nowarn_perm"}, ++ ++ /* keep them temporary */ ++ {Opt_ignore_silent, "coo=%s"}, ++ {Opt_ignore_silent, "nodlgt"}, ++ {Opt_ignore_silent, "nodirperm1"}, ++ {Opt_ignore_silent, "noshwh"}, ++ {Opt_ignore_silent, "noshwh"}, ++ {Opt_ignore_silent, "clean_plink"}, ++ ++ {Opt_rendir, "rendir=%d"}, ++ ++ {Opt_refrof, "refrof"}, ++ {Opt_norefrof, "norefrof"}, ++ ++ {Opt_verbose, "verbose"}, ++ {Opt_verbose, "v"}, ++ {Opt_noverbose, "noverbose"}, ++ {Opt_noverbose, "quiet"}, ++ {Opt_noverbose, "q"}, ++ {Opt_noverbose, "silent"}, ++ ++ {Opt_sum, "sum"}, ++ {Opt_nosum, "nosum"}, ++ {Opt_wsum, "wsum"}, ++ ++ {Opt_rdcache, "rdcache=%d"}, ++ {Opt_rdcache, "rdcache:%d"}, ++ ++ {Opt_wbr_create, "create=%s"}, ++ {Opt_wbr_create, "create_policy=%s"}, ++ {Opt_wbr_copyup, "cpup=%s"}, ++ {Opt_wbr_copyup, "copyup=%s"}, ++ {Opt_wbr_copyup, "copyup_policy=%s"}, ++ ++ /* internal use for the scripts */ ++ {Opt_ignore_silent, "si=%s"}, ++ ++ {Opt_br, "dirs=%s"}, ++ {Opt_ignore, "debug=%d"}, ++ {Opt_ignore, "delete=whiteout"}, ++ {Opt_ignore, "delete=all"}, ++ {Opt_ignore, "imap=%s"}, ++ ++ {Opt_err, NULL} ++}; ++ ++/* ---------------------------------------------------------------------- */ ++ ++static const char *au_parser_pattern(int val, struct match_token *token) ++{ ++ while (token->pattern) { ++ if (token->token == val) ++ return token->pattern; ++ token++; ++ } ++ BUG(); ++ return "??"; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++static match_table_t brperms = { ++ {AuBrPerm_RO, AUFS_BRPERM_RO}, ++ {AuBrPerm_RR, AUFS_BRPERM_RR}, ++ {AuBrPerm_RW, AUFS_BRPERM_RW}, ++ ++ {AuBrPerm_ROWH, AUFS_BRPERM_ROWH}, ++ {AuBrPerm_RRWH, AUFS_BRPERM_RRWH}, ++ {AuBrPerm_RWNoLinkWH, AUFS_BRPERM_RWNLWH}, ++ ++ {AuBrPerm_ROWH, "nfsro"}, ++ {AuBrPerm_RO, NULL} ++}; ++ ++static int br_perm_val(char *perm) ++{ ++ int val; ++ substring_t args[MAX_OPT_ARGS]; ++ ++ val = match_token(perm, brperms, args); ++ return val; ++} ++ ++const char *au_optstr_br_perm(int brperm) ++{ ++ return au_parser_pattern(brperm, (void *)brperms); ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++static match_table_t udbalevel = { ++ {AuOpt_UDBA_REVAL, "reval"}, ++ {AuOpt_UDBA_NONE, "none"}, ++#ifdef CONFIG_AUFS_HINOTIFY ++ {AuOpt_UDBA_HINOTIFY, "inotify"}, ++#endif ++ {-1, NULL} ++}; ++ ++static int udba_val(char *str) ++{ ++ substring_t args[MAX_OPT_ARGS]; ++ ++ return match_token(str, udbalevel, args); ++} ++ ++const char *au_optstr_udba(int udba) ++{ ++ return au_parser_pattern(udba, (void *)udbalevel); ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++static match_table_t au_wbr_create_policy = { ++ {AuWbrCreate_TDP, "tdp"}, ++ {AuWbrCreate_TDP, "top-down-parent"}, ++ {AuWbrCreate_RR, "rr"}, ++ {AuWbrCreate_RR, "round-robin"}, ++ {AuWbrCreate_MFS, "mfs"}, ++ {AuWbrCreate_MFS, "most-free-space"}, ++ {AuWbrCreate_MFSV, "mfs:%d"}, ++ {AuWbrCreate_MFSV, "most-free-space:%d"}, ++ ++ {AuWbrCreate_MFSRR, "mfsrr:%d"}, ++ {AuWbrCreate_MFSRRV, "mfsrr:%d:%d"}, ++ {AuWbrCreate_PMFS, "pmfs"}, ++ {AuWbrCreate_PMFSV, "pmfs:%d"}, ++ ++ {-1, NULL} ++}; ++ ++/* cf. linux/lib/parser.c */ ++static int au_match_ull(substring_t *s, unsigned long long *result) ++{ ++ int err; ++ unsigned int len; ++ char a[32]; ++ ++ err = -ERANGE; ++ len = s->to - s->from; ++ if (len + 1 <= sizeof(a)) { ++ memcpy(a, s->from, len); ++ a[len] = '\0'; ++ err = strict_strtoull(a, 0, result); ++ } ++ return err; ++} ++ ++static int au_wbr_mfs_wmark(substring_t *arg, char *str, ++ struct au_opt_wbr_create *create) ++{ ++ int err; ++ unsigned long long ull; ++ ++ err = 0; ++ if (!au_match_ull(arg, &ull)) ++ create->mfsrr_watermark = ull; ++ else { ++ AuErr("bad integer in %s\n", str); ++ err = -EINVAL; ++ } ++ ++ return err; ++} ++ ++static int au_wbr_mfs_sec(substring_t *arg, char *str, ++ struct au_opt_wbr_create *create) ++{ ++ int n, err; ++ ++ err = 0; ++ if (!match_int(arg, &n) && 0 <= n) ++ create->mfs_second = n; ++ else { ++ AuErr("bad integer in %s\n", str); ++ err = -EINVAL; ++ } ++ ++ return err; ++} ++ ++static int au_wbr_create_val(char *str, struct au_opt_wbr_create *create) ++{ ++ int err, e; ++ substring_t args[MAX_OPT_ARGS]; ++ ++ err = match_token(str, au_wbr_create_policy, args); ++ create->wbr_create = err; ++ switch (err) { ++ case AuWbrCreate_MFSRRV: ++ e = au_wbr_mfs_wmark(&args[0], str, create); ++ if (!e) ++ e = au_wbr_mfs_sec(&args[1], str, create); ++ if (unlikely(e)) ++ err = e; ++ break; ++ case AuWbrCreate_MFSRR: ++ e = au_wbr_mfs_wmark(&args[0], str, create); ++ if (unlikely(e)) { ++ err = e; ++ break; ++ } ++ /*FALLTHROUGH*/ ++ case AuWbrCreate_MFS: ++ case AuWbrCreate_PMFS: ++ create->mfs_second = AUFS_MFS_SECOND_DEF; ++ break; ++ case AuWbrCreate_MFSV: ++ case AuWbrCreate_PMFSV: ++ e = au_wbr_mfs_sec(&args[0], str, create); ++ if (unlikely(e)) ++ err = e; ++ break; ++ } ++ ++ return err; ++} ++ ++const char *au_optstr_wbr_create(int wbr_create) ++{ ++ return au_parser_pattern(wbr_create, (void *)au_wbr_create_policy); ++} ++ ++static match_table_t au_wbr_copyup_policy = { ++ {AuWbrCopyup_TDP, "tdp"}, ++ {AuWbrCopyup_TDP, "top-down-parent"}, ++ {AuWbrCopyup_BUP, "bup"}, ++ {AuWbrCopyup_BUP, "bottom-up-parent"}, ++ {AuWbrCopyup_BU, "bu"}, ++ {AuWbrCopyup_BU, "bottom-up"}, ++ {-1, NULL} ++}; ++ ++static int au_wbr_copyup_val(char *str) ++{ ++ substring_t args[MAX_OPT_ARGS]; ++ ++ return match_token(str, au_wbr_copyup_policy, args); ++} ++ ++const char *au_optstr_wbr_copyup(int wbr_copyup) ++{ ++ return au_parser_pattern(wbr_copyup, (void *)au_wbr_copyup_policy); ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++static const int lkup_dirflags = LOOKUP_FOLLOW | LOOKUP_DIRECTORY; ++ ++static void dump_opts(struct au_opts *opts) ++{ ++#ifdef CONFIG_AUFS_DEBUG ++ /* reduce stack space */ ++ union { ++ struct au_opt_add *add; ++ struct au_opt_del *del; ++ struct au_opt_mod *mod; ++ struct au_opt_xino *xino; ++ struct au_opt_xino_itrunc *xino_itrunc; ++ struct au_opt_wbr_create *create; ++ } u; ++ struct au_opt *opt; ++ ++ opt = opts->opt; ++ while (opt->type != Opt_tail) { ++ switch (opt->type) { ++ case Opt_add: ++ u.add = &opt->add; ++ AuDbg("add {b%d, %s, 0x%x, %p}\n", ++ u.add->bindex, u.add->pathname, u.add->perm, ++ u.add->path.dentry); ++ break; ++ case Opt_del: ++ case Opt_idel: ++ u.del = &opt->del; ++ AuDbg("del {%s, %p}\n", ++ u.del->pathname, u.del->h_path.dentry); ++ break; ++ case Opt_mod: ++ case Opt_imod: ++ u.mod = &opt->mod; ++ AuDbg("mod {%s, 0x%x, %p}\n", ++ u.mod->path, u.mod->perm, u.mod->h_root); ++ break; ++ case Opt_append: ++ u.add = &opt->add; ++ AuDbg("append {b%d, %s, 0x%x, %p}\n", ++ u.add->bindex, u.add->pathname, u.add->perm, ++ u.add->path.dentry); ++ break; ++ case Opt_prepend: ++ u.add = &opt->add; ++ AuDbg("prepend {b%d, %s, 0x%x, %p}\n", ++ u.add->bindex, u.add->pathname, u.add->perm, ++ u.add->path.dentry); ++ break; ++ case Opt_dirwh: ++ AuDbg("dirwh %d\n", opt->dirwh); ++ break; ++ case Opt_rdcache: ++ AuDbg("rdcache %d\n", opt->rdcache); ++ break; ++ case Opt_xino: ++ u.xino = &opt->xino; ++ AuDbg("xino {%s %.*s}\n", ++ u.xino->path, ++ AuDLNPair(u.xino->file->f_dentry)); ++ break; ++ case Opt_trunc_xino: ++ AuLabel(trunc_xino); ++ break; ++ case Opt_notrunc_xino: ++ AuLabel(notrunc_xino); ++ break; ++ case Opt_trunc_xino_path: ++ case Opt_itrunc_xino: ++ u.xino_itrunc = &opt->xino_itrunc; ++ AuDbg("trunc_xino %d\n", u.xino_itrunc->bindex); ++ break; ++ ++ case Opt_noxino: ++ AuLabel(noxino); ++ break; ++ case Opt_trunc_xib: ++ AuLabel(trunc_xib); ++ break; ++ case Opt_notrunc_xib: ++ AuLabel(notrunc_xib); ++ break; ++ case Opt_plink: ++ AuLabel(plink); ++ break; ++ case Opt_noplink: ++ AuLabel(noplink); ++ break; ++ case Opt_list_plink: ++ AuLabel(list_plink); ++ break; ++ case Opt_udba: ++ AuDbg("udba %d, %s\n", ++ opt->udba, au_optstr_udba(opt->udba)); ++ break; ++ case Opt_diropq_a: ++ AuLabel(diropq_a); ++ break; ++ case Opt_diropq_w: ++ AuLabel(diropq_w); ++ break; ++ case Opt_warn_perm: ++ AuLabel(warn_perm); ++ break; ++ case Opt_nowarn_perm: ++ AuLabel(nowarn_perm); ++ break; ++ case Opt_refrof: ++ AuLabel(refrof); ++ break; ++ case Opt_norefrof: ++ AuLabel(norefrof); ++ break; ++ case Opt_verbose: ++ AuLabel(verbose); ++ break; ++ case Opt_noverbose: ++ AuLabel(noverbose); ++ break; ++ case Opt_sum: ++ AuLabel(sum); ++ break; ++ case Opt_nosum: ++ AuLabel(nosum); ++ break; ++ case Opt_wsum: ++ AuLabel(wsum); ++ break; ++ case Opt_wbr_create: ++ u.create = &opt->wbr_create; ++ AuDbg("create %d, %s\n", u.create->wbr_create, ++ au_optstr_wbr_create(u.create->wbr_create)); ++ switch (u.create->wbr_create) { ++ case AuWbrCreate_MFSV: ++ case AuWbrCreate_PMFSV: ++ AuDbg("%d sec\n", u.create->mfs_second); ++ break; ++ case AuWbrCreate_MFSRR: ++ AuDbg("%llu watermark\n", ++ u.create->mfsrr_watermark); ++ break; ++ case AuWbrCreate_MFSRRV: ++ AuDbg("%llu watermark, %d sec\n", ++ u.create->mfsrr_watermark, ++ u.create->mfs_second); ++ break; ++ } ++ break; ++ case Opt_wbr_copyup: ++ AuDbg("copyup %d, %s\n", opt->wbr_copyup, ++ au_optstr_wbr_copyup(opt->wbr_copyup)); ++ break; ++ default: ++ BUG(); ++ } ++ opt++; ++ } ++#endif ++} ++ ++void au_opts_free(struct au_opts *opts) ++{ ++ struct au_opt *opt; ++ ++ opt = opts->opt; ++ while (opt->type != Opt_tail) { ++ switch (opt->type) { ++ case Opt_add: ++ case Opt_append: ++ case Opt_prepend: ++ path_put(&opt->add.path); ++ break; ++ case Opt_del: ++ case Opt_idel: ++ path_put(&opt->del.h_path); ++ break; ++ case Opt_mod: ++ case Opt_imod: ++ dput(opt->mod.h_root); ++ break; ++ case Opt_xino: ++ fput(opt->xino.file); ++ break; ++ } ++ opt++; ++ } ++} ++ ++static int opt_add(struct au_opt *opt, char *opt_str, unsigned long sb_flags, ++ aufs_bindex_t bindex) ++{ ++ int err; ++ struct au_opt_add *add = &opt->add; ++ char *p; ++ ++ add->bindex = bindex; ++ add->perm = AuBrPerm_Last; ++ add->pathname = opt_str; ++ p = strchr(opt_str, '='); ++ if (p) { ++ *p++ = 0; ++ if (*p) ++ add->perm = br_perm_val(p); ++ } ++ ++ err = vfsub_kern_path(add->pathname, lkup_dirflags, &add->path); ++ if (!err) { ++ if (!p) { ++ add->perm = AuBrPerm_RO; ++ if (au_test_fs_rr(add->path.dentry->d_sb)) ++ add->perm = AuBrPerm_RR; ++ else if (!bindex && !(sb_flags & MS_RDONLY)) ++ add->perm = AuBrPerm_RW; ++ } ++ opt->type = Opt_add; ++ goto out; ++ } ++ AuErr("lookup failed %s (%d)\n", add->pathname, err); ++ err = -EINVAL; ++ ++ out: ++ return err; ++} ++ ++static int au_opts_parse_del(struct au_opt_del *del, substring_t args[]) ++{ ++ int err; ++ ++ del->pathname = args[0].from; ++ AuDbg("del path %s\n", del->pathname); ++ ++ err = vfsub_kern_path(del->pathname, lkup_dirflags, &del->h_path); ++ if (unlikely(err)) ++ AuErr("lookup failed %s (%d)\n", del->pathname, err); ++ ++ return err; ++} ++ ++#if 0 /* reserved for future use */ ++static int au_opts_parse_idel(struct super_block *sb, aufs_bindex_t bindex, ++ struct au_opt_del *del, substring_t args[]) ++{ ++ int err; ++ struct dentry *root; ++ ++ err = -EINVAL; ++ root = sb->s_root; ++ aufs_read_lock(root, AuLock_FLUSH); ++ if (bindex < 0 || au_sbend(sb) < bindex) { ++ AuErr("out of bounds, %d\n", bindex); ++ goto out; ++ } ++ ++ err = 0; ++ del->h_path.dentry = dget(au_h_dptr(root, bindex)); ++ del->h_path.mnt = mntget(au_sbr_mnt(sb, bindex)); ++ ++ out: ++ aufs_read_unlock(root, !AuLock_IR); ++ return err; ++} ++#endif ++ ++static int au_opts_parse_mod(struct au_opt_mod *mod, substring_t args[]) ++{ ++ int err; ++ struct path path; ++ char *p; ++ ++ err = -EINVAL; ++ mod->path = args[0].from; ++ p = strchr(mod->path, '='); ++ if (unlikely(!p)) { ++ AuErr("no permssion %s\n", args[0].from); ++ goto out; ++ } ++ ++ *p++ = 0; ++ err = vfsub_kern_path(mod->path, lkup_dirflags, &path); ++ if (unlikely(err)) { ++ AuErr("lookup failed %s (%d)\n", mod->path, err); ++ goto out; ++ } ++ ++ mod->perm = br_perm_val(p); ++ AuDbg("mod path %s, perm 0x%x, %s\n", mod->path, mod->perm, p); ++ mod->h_root = dget(path.dentry); ++ path_put(&path); ++ ++ out: ++ return err; ++} ++ ++#if 0 /* reserved for future use */ ++static int au_opts_parse_imod(struct super_block *sb, aufs_bindex_t bindex, ++ struct au_opt_mod *mod, substring_t args[]) ++{ ++ int err; ++ struct dentry *root; ++ ++ err = -EINVAL; ++ root = sb->s_root; ++ aufs_read_lock(root, AuLock_FLUSH); ++ if (bindex < 0 || au_sbend(sb) < bindex) { ++ AuErr("out of bounds, %d\n", bindex); ++ goto out; ++ } ++ ++ err = 0; ++ mod->perm = br_perm_val(args[1].from); ++ AuDbg("mod path %s, perm 0x%x, %s\n", ++ mod->path, mod->perm, args[1].from); ++ mod->h_root = dget(au_h_dptr(root, bindex)); ++ ++ out: ++ aufs_read_unlock(root, !AuLock_IR); ++ return err; ++} ++#endif ++ ++static int au_opts_parse_xino(struct super_block *sb, struct au_opt_xino *xino, ++ substring_t args[]) ++{ ++ int err; ++ struct file *file; ++ ++ file = au_xino_create(sb, args[0].from, /*silent*/0); ++ err = PTR_ERR(file); ++ if (IS_ERR(file)) ++ goto out; ++ ++ err = -EINVAL; ++ if (unlikely(file->f_dentry->d_sb == sb)) { ++ fput(file); ++ AuErr("%s must be outside\n", args[0].from); ++ goto out; ++ } ++ ++ err = 0; ++ xino->file = file; ++ xino->path = args[0].from; ++ ++ out: ++ return err; ++} ++ ++static ++int au_opts_parse_xino_itrunc_path(struct super_block *sb, ++ struct au_opt_xino_itrunc *xino_itrunc, ++ substring_t args[]) ++{ ++ int err; ++ aufs_bindex_t bend, bindex; ++ struct path path; ++ struct dentry *root; ++ ++ err = vfsub_kern_path(args[0].from, lkup_dirflags, &path); ++ if (unlikely(err)) { ++ AuErr("lookup failed %s (%d)\n", args[0].from, err); ++ goto out; ++ } ++ ++ xino_itrunc->bindex = -1; ++ root = sb->s_root; ++ aufs_read_lock(root, AuLock_FLUSH); ++ bend = au_sbend(sb); ++ for (bindex = 0; bindex <= bend; bindex++) { ++ if (au_h_dptr(root, bindex) == path.dentry) { ++ xino_itrunc->bindex = bindex; ++ break; ++ } ++ } ++ aufs_read_unlock(root, !AuLock_IR); ++ path_put(&path); ++ ++ if (unlikely(xino_itrunc->bindex < 0)) { ++ AuErr("no such branch %s\n", args[0].from); ++ err = -EINVAL; ++ } ++ ++ out: ++ return err; ++} ++ ++/* called without aufs lock */ ++int au_opts_parse(struct super_block *sb, char *str, struct au_opts *opts) ++{ ++ int err, n, token; ++ aufs_bindex_t bindex; ++ unsigned char skipped; ++ struct dentry *root; ++ struct au_opt *opt, *opt_tail; ++ char *opt_str; ++ /* reduce the stack space */ ++ union { ++ struct au_opt_xino_itrunc *xino_itrunc; ++ struct au_opt_wbr_create *create; ++ } u; ++ struct { ++ substring_t args[MAX_OPT_ARGS]; ++ } *a; ++ ++ err = -ENOMEM; ++ a = kmalloc(sizeof(*a), GFP_NOFS); ++ if (unlikely(!a)) ++ goto out; ++ ++ root = sb->s_root; ++ err = 0; ++ bindex = 0; ++ opt = opts->opt; ++ opt_tail = opt + opts->max_opt - 1; ++ opt->type = Opt_tail; ++ while (!err && (opt_str = strsep(&str, ",")) && *opt_str) { ++ err = -EINVAL; ++ skipped = 0; ++ token = match_token(opt_str, options, a->args); ++ switch (token) { ++ case Opt_br: ++ err = 0; ++ while (!err && (opt_str = strsep(&a->args[0].from, ":")) ++ && *opt_str) { ++ err = opt_add(opt, opt_str, opts->sb_flags, ++ bindex++); ++ if (unlikely(!err && ++opt > opt_tail)) { ++ err = -E2BIG; ++ break; ++ } ++ opt->type = Opt_tail; ++ skipped = 1; ++ } ++ break; ++ case Opt_add: ++ if (unlikely(match_int(&a->args[0], &n))) { ++ AuErr("bad integer in %s\n", opt_str); ++ break; ++ } ++ bindex = n; ++ err = opt_add(opt, a->args[1].from, opts->sb_flags, ++ bindex); ++ if (!err) ++ opt->type = token; ++ break; ++ case Opt_append: ++ err = opt_add(opt, a->args[0].from, opts->sb_flags, ++ /*dummy bindex*/1); ++ if (!err) ++ opt->type = token; ++ break; ++ case Opt_prepend: ++ err = opt_add(opt, a->args[0].from, opts->sb_flags, ++ /*bindex*/0); ++ if (!err) ++ opt->type = token; ++ break; ++ case Opt_del: ++ err = au_opts_parse_del(&opt->del, a->args); ++ if (!err) ++ opt->type = token; ++ break; ++#if 0 /* reserved for future use */ ++ case Opt_idel: ++ del->pathname = "(indexed)"; ++ if (unlikely(match_int(&args[0], &n))) { ++ AuErr("bad integer in %s\n", opt_str); ++ break; ++ } ++ err = au_opts_parse_idel(sb, n, &opt->del, a->args); ++ if (!err) ++ opt->type = token; ++ break; ++#endif ++ case Opt_mod: ++ err = au_opts_parse_mod(&opt->mod, a->args); ++ if (!err) ++ opt->type = token; ++ break; ++#ifdef IMOD /* reserved for future use */ ++ case Opt_imod: ++ u.mod->path = "(indexed)"; ++ if (unlikely(match_int(&a->args[0], &n))) { ++ AuErr("bad integer in %s\n", opt_str); ++ break; ++ } ++ err = au_opts_parse_imod(sb, n, &opt->mod, a->args); ++ if (!err) ++ opt->type = token; ++ break; ++#endif ++ case Opt_xino: ++ err = au_opts_parse_xino(sb, &opt->xino, a->args); ++ if (!err) ++ opt->type = token; ++ break; ++ ++ case Opt_trunc_xino_path: ++ err = au_opts_parse_xino_itrunc_path ++ (sb, &opt->xino_itrunc, a->args); ++ if (!err) ++ opt->type = token; ++ break; ++ ++ case Opt_itrunc_xino: ++ u.xino_itrunc = &opt->xino_itrunc; ++ if (unlikely(match_int(&a->args[0], &n))) { ++ AuErr("bad integer in %s\n", opt_str); ++ break; ++ } ++ u.xino_itrunc->bindex = n; ++ aufs_read_lock(root, AuLock_FLUSH); ++ if (n < 0 || au_sbend(sb) < n) { ++ AuErr("out of bounds, %d\n", n); ++ aufs_read_unlock(root, !AuLock_IR); ++ break; ++ } ++ aufs_read_unlock(root, !AuLock_IR); ++ err = 0; ++ opt->type = token; ++ break; ++ ++ case Opt_dirwh: ++ if (unlikely(match_int(&a->args[0], &opt->dirwh))) ++ break; ++ err = 0; ++ opt->type = token; ++ break; ++ ++ case Opt_rdcache: ++ if (unlikely(match_int(&a->args[0], &opt->rdcache))) ++ break; ++ err = 0; ++ opt->type = token; ++ break; ++ ++ case Opt_trunc_xino: ++ case Opt_notrunc_xino: ++ case Opt_noxino: ++ case Opt_trunc_xib: ++ case Opt_notrunc_xib: ++ case Opt_plink: ++ case Opt_noplink: ++ case Opt_list_plink: ++ case Opt_diropq_a: ++ case Opt_diropq_w: ++ case Opt_warn_perm: ++ case Opt_nowarn_perm: ++ case Opt_refrof: ++ case Opt_norefrof: ++ case Opt_verbose: ++ case Opt_noverbose: ++ case Opt_sum: ++ case Opt_nosum: ++ case Opt_wsum: ++ err = 0; ++ opt->type = token; ++ break; ++ ++ case Opt_udba: ++ opt->udba = udba_val(a->args[0].from); ++ if (opt->udba >= 0) { ++ err = 0; ++ opt->type = token; ++ } else ++ AuErr("wrong value, %s\n", opt_str); ++ break; ++ ++ case Opt_wbr_create: ++ u.create = &opt->wbr_create; ++ u.create->wbr_create ++ = au_wbr_create_val(a->args[0].from, u.create); ++ if (u.create->wbr_create >= 0) { ++ err = 0; ++ opt->type = token; ++ } else ++ AuErr("wrong value, %s\n", opt_str); ++ break; ++ case Opt_wbr_copyup: ++ opt->wbr_copyup = au_wbr_copyup_val(a->args[0].from); ++ if (opt->wbr_copyup >= 0) { ++ err = 0; ++ opt->type = token; ++ } else ++ AuErr("wrong value, %s\n", opt_str); ++ break; ++ ++ case Opt_ignore: ++ AuWarn("ignored %s\n", opt_str); ++ /*FALLTHROUGH*/ ++ case Opt_ignore_silent: ++ skipped = 1; ++ err = 0; ++ break; ++ case Opt_err: ++ AuErr("unknown option %s\n", opt_str); ++ break; ++ } ++ ++ if (!err && !skipped) { ++ if (unlikely(++opt > opt_tail)) { ++ err = -E2BIG; ++ opt--; ++ opt->type = Opt_tail; ++ break; ++ } ++ opt->type = Opt_tail; ++ } ++ } ++ ++ kfree(a); ++ dump_opts(opts); ++ if (unlikely(err)) ++ au_opts_free(opts); ++ ++ out: ++ return err; ++} ++ ++static int au_opt_wbr_create(struct super_block *sb, ++ struct au_opt_wbr_create *create) ++{ ++ int err; ++ struct au_sbinfo *sbinfo; ++ ++ err = 1; /* handled */ ++ sbinfo = au_sbi(sb); ++ if (sbinfo->si_wbr_create_ops->fin) { ++ err = sbinfo->si_wbr_create_ops->fin(sb); ++ if (!err) ++ err = 1; ++ } ++ ++ sbinfo->si_wbr_create = create->wbr_create; ++ sbinfo->si_wbr_create_ops = au_wbr_create_ops + create->wbr_create; ++ switch (create->wbr_create) { ++ case AuWbrCreate_MFSRRV: ++ case AuWbrCreate_MFSRR: ++ sbinfo->si_wbr_mfs.mfsrr_watermark = create->mfsrr_watermark; ++ /*FALLTHROUGH*/ ++ case AuWbrCreate_MFS: ++ case AuWbrCreate_MFSV: ++ case AuWbrCreate_PMFS: ++ case AuWbrCreate_PMFSV: ++ sbinfo->si_wbr_mfs.mfs_expire = create->mfs_second * HZ; ++ break; ++ } ++ ++ if (sbinfo->si_wbr_create_ops->init) ++ sbinfo->si_wbr_create_ops->init(sb); /* ignore */ ++ ++ return err; ++} ++ ++/* ++ * returns, ++ * plus: processed without an error ++ * zero: unprocessed ++ */ ++static int au_opt_simple(struct super_block *sb, struct au_opt *opt, ++ struct au_opts *opts) ++{ ++ int err; ++ struct au_sbinfo *sbinfo; ++ ++ err = 1; /* handled */ ++ sbinfo = au_sbi(sb); ++ switch (opt->type) { ++ case Opt_udba: ++ sbinfo->si_mntflags &= ~AuOptMask_UDBA; ++ sbinfo->si_mntflags |= opt->udba; ++ opts->given_udba |= opt->udba; ++ break; ++ ++ case Opt_plink: ++ au_opt_set(sbinfo->si_mntflags, PLINK); ++ break; ++ case Opt_noplink: ++ if (au_opt_test(sbinfo->si_mntflags, PLINK)) ++ au_plink_put(sb); ++ au_opt_clr(sbinfo->si_mntflags, PLINK); ++ break; ++ case Opt_list_plink: ++ if (au_opt_test(sbinfo->si_mntflags, PLINK)) ++ au_plink_list(sb); ++ break; ++ ++ case Opt_diropq_a: ++ au_opt_set(sbinfo->si_mntflags, ALWAYS_DIROPQ); ++ break; ++ case Opt_diropq_w: ++ au_opt_clr(sbinfo->si_mntflags, ALWAYS_DIROPQ); ++ break; ++ ++ case Opt_warn_perm: ++ au_opt_set(sbinfo->si_mntflags, WARN_PERM); ++ break; ++ case Opt_nowarn_perm: ++ au_opt_clr(sbinfo->si_mntflags, WARN_PERM); ++ break; ++ ++ case Opt_refrof: ++ au_opt_set(sbinfo->si_mntflags, REFROF); ++ break; ++ case Opt_norefrof: ++ au_opt_clr(sbinfo->si_mntflags, REFROF); ++ break; ++ ++ case Opt_verbose: ++ au_opt_set(sbinfo->si_mntflags, VERBOSE); ++ break; ++ case Opt_noverbose: ++ au_opt_clr(sbinfo->si_mntflags, VERBOSE); ++ break; ++ ++ case Opt_sum: ++ au_opt_set(sbinfo->si_mntflags, SUM); ++ break; ++ case Opt_wsum: ++ au_opt_clr(sbinfo->si_mntflags, SUM); ++ au_opt_set(sbinfo->si_mntflags, SUM_W); ++ case Opt_nosum: ++ au_opt_clr(sbinfo->si_mntflags, SUM); ++ au_opt_clr(sbinfo->si_mntflags, SUM_W); ++ break; ++ ++ case Opt_wbr_create: ++ err = au_opt_wbr_create(sb, &opt->wbr_create); ++ break; ++ case Opt_wbr_copyup: ++ sbinfo->si_wbr_copyup = opt->wbr_copyup; ++ sbinfo->si_wbr_copyup_ops = au_wbr_copyup_ops + opt->wbr_copyup; ++ break; ++ ++ case Opt_dirwh: ++ sbinfo->si_dirwh = opt->dirwh; ++ break; ++ ++ case Opt_rdcache: ++ sbinfo->si_rdcache = opt->rdcache * HZ; ++ break; ++ ++ case Opt_trunc_xino: ++ au_opt_set(sbinfo->si_mntflags, TRUNC_XINO); ++ break; ++ case Opt_notrunc_xino: ++ au_opt_clr(sbinfo->si_mntflags, TRUNC_XINO); ++ break; ++ ++ case Opt_trunc_xino_path: ++ case Opt_itrunc_xino: ++ err = au_xino_trunc(sb, opt->xino_itrunc.bindex); ++ if (!err) ++ err = 1; ++ break; ++ ++ case Opt_trunc_xib: ++ au_fset_opts(opts->flags, TRUNC_XIB); ++ break; ++ case Opt_notrunc_xib: ++ au_fclr_opts(opts->flags, TRUNC_XIB); ++ break; ++ ++ default: ++ err = 0; ++ break; ++ } ++ ++ return err; ++} ++ ++/* ++ * returns tri-state. ++ * plus: processed without an error ++ * zero: unprocessed ++ * minus: error ++ */ ++static int au_opt_br(struct super_block *sb, struct au_opt *opt, ++ struct au_opts *opts) ++{ ++ int err, do_refresh; ++ ++ err = 0; ++ switch (opt->type) { ++ case Opt_append: ++ opt->add.bindex = au_sbend(sb) + 1; ++ if (opt->add.bindex < 0) ++ opt->add.bindex = 0; ++ goto add; ++ case Opt_prepend: ++ opt->add.bindex = 0; ++ add: ++ case Opt_add: ++ err = au_br_add(sb, &opt->add, ++ au_ftest_opts(opts->flags, REMOUNT)); ++ if (!err) { ++ err = 1; ++ au_fset_opts(opts->flags, REFRESH_DIR); ++ if (au_br_whable(opt->add.perm)) ++ au_fset_opts(opts->flags, REFRESH_NONDIR); ++ } ++ break; ++ ++ case Opt_del: ++ case Opt_idel: ++ err = au_br_del(sb, &opt->del, ++ au_ftest_opts(opts->flags, REMOUNT)); ++ if (!err) { ++ err = 1; ++ au_fset_opts(opts->flags, TRUNC_XIB); ++ au_fset_opts(opts->flags, REFRESH_DIR); ++ au_fset_opts(opts->flags, REFRESH_NONDIR); ++ } ++ break; ++ ++ case Opt_mod: ++ case Opt_imod: ++ err = au_br_mod(sb, &opt->mod, ++ au_ftest_opts(opts->flags, REMOUNT), ++ &do_refresh); ++ if (!err) { ++ err = 1; ++ if (do_refresh) { ++ au_fset_opts(opts->flags, REFRESH_DIR); ++ au_fset_opts(opts->flags, REFRESH_NONDIR); ++ } ++ } ++ break; ++ } ++ ++ return err; ++} ++ ++static int au_opt_xino(struct super_block *sb, struct au_opt *opt, ++ struct au_opt_xino **opt_xino, ++ struct au_opts *opts) ++{ ++ int err; ++ aufs_bindex_t bend, bindex; ++ struct dentry *root, *parent, *h_root; ++ ++ err = 0; ++ switch (opt->type) { ++ case Opt_xino: ++ err = au_xino_set(sb, &opt->xino, ++ !!au_ftest_opts(opts->flags, REMOUNT)); ++ if (unlikely(err)) ++ break; ++ ++ *opt_xino = &opt->xino; ++ au_xino_brid_set(sb, -1); ++ ++ /* safe d_parent access */ ++ parent = opt->xino.file->f_dentry->d_parent; ++ root = sb->s_root; ++ bend = au_sbend(sb); ++ for (bindex = 0; bindex <= bend; bindex++) { ++ h_root = au_h_dptr(root, bindex); ++ if (h_root == parent) { ++ au_xino_brid_set(sb, au_sbr_id(sb, bindex)); ++ break; ++ } ++ } ++ break; ++ ++ case Opt_noxino: ++ au_xino_clr(sb); ++ au_xino_brid_set(sb, -1); ++ *opt_xino = (void *)-1; ++ break; ++ } ++ ++ return err; ++} ++ ++int au_opts_verify(struct super_block *sb, unsigned long sb_flags, ++ unsigned int pending) ++{ ++ int err; ++ aufs_bindex_t bindex, bend; ++ unsigned char do_plink, skip, do_free; ++ struct au_branch *br; ++ struct au_wbr *wbr; ++ struct dentry *root; ++ struct inode *dir, *h_dir; ++ struct au_sbinfo *sbinfo; ++ struct au_hinode *hdir; ++ ++ sbinfo = au_sbi(sb); ++ AuDebugOn(!(sbinfo->si_mntflags & AuOptMask_UDBA)); ++ ++ if (unlikely(!(sb_flags & MS_RDONLY) ++ && !au_br_writable(au_sbr_perm(sb, 0)))) ++ AuWarn("first branch should be rw\n"); ++ ++ if (au_opt_test((sbinfo->si_mntflags | pending), UDBA_HINOTIFY) ++ && !au_opt_test(sbinfo->si_mntflags, XINO)) ++ AuWarn("udba=inotify requires xino\n"); ++ ++ err = 0; ++ root = sb->s_root; ++ dir = sb->s_root->d_inode; ++ do_plink = !!au_opt_test(sbinfo->si_mntflags, PLINK); ++ bend = au_sbend(sb); ++ for (bindex = 0; !err && bindex <= bend; bindex++) { ++ skip = 0; ++ h_dir = au_h_iptr(dir, bindex); ++ br = au_sbr(sb, bindex); ++ do_free = 0; ++ ++ wbr = br->br_wbr; ++ if (wbr) ++ wbr_wh_read_lock(wbr); ++ ++ switch (br->br_perm) { ++ case AuBrPerm_RO: ++ case AuBrPerm_ROWH: ++ case AuBrPerm_RR: ++ case AuBrPerm_RRWH: ++ do_free = !!wbr; ++ skip = (!wbr ++ || (!wbr->wbr_whbase ++ && !wbr->wbr_plink ++ && !wbr->wbr_orph)); ++ break; ++ ++ case AuBrPerm_RWNoLinkWH: ++ /* skip = (!br->br_whbase && !br->br_orph); */ ++ skip = (!wbr || !wbr->wbr_whbase); ++ if (skip && wbr) { ++ if (do_plink) ++ skip = !!wbr->wbr_plink; ++ else ++ skip = !wbr->wbr_plink; ++ } ++ break; ++ ++ case AuBrPerm_RW: ++ /* skip = (br->br_whbase && br->br_ohph); */ ++ skip = (wbr && wbr->wbr_whbase); ++ if (skip) { ++ if (do_plink) ++ skip = !!wbr->wbr_plink; ++ else ++ skip = !wbr->wbr_plink; ++ } ++ break; ++ ++ default: ++ BUG(); ++ } ++ if (wbr) ++ wbr_wh_read_unlock(wbr); ++ ++ if (skip) ++ continue; ++ ++ hdir = au_hi(dir, bindex); ++ au_hin_imtx_lock_nested(hdir, AuLsc_I_PARENT); ++ if (wbr) ++ wbr_wh_write_lock(wbr); ++ err = au_wh_init(au_h_dptr(root, bindex), br, sb); ++ if (wbr) ++ wbr_wh_write_unlock(wbr); ++ au_hin_imtx_unlock(hdir); ++ ++ if (!err && do_free) { ++ kfree(wbr); ++ br->br_wbr = NULL; ++ } ++ } ++ ++ return err; ++} ++ ++int au_opts_mount(struct super_block *sb, struct au_opts *opts) ++{ ++ int err; ++ unsigned int tmp; ++ aufs_bindex_t bend; ++ struct au_opt *opt; ++ struct au_opt_xino *opt_xino, xino; ++ struct au_sbinfo *sbinfo; ++ ++ err = 0; ++ opt_xino = NULL; ++ opt = opts->opt; ++ while (err >= 0 && opt->type != Opt_tail) ++ err = au_opt_simple(sb, opt++, opts); ++ if (err > 0) ++ err = 0; ++ else if (unlikely(err < 0)) ++ goto out; ++ ++ /* disable xino and udba temporary */ ++ sbinfo = au_sbi(sb); ++ tmp = sbinfo->si_mntflags; ++ au_opt_clr(sbinfo->si_mntflags, XINO); ++ au_opt_set_udba(sbinfo->si_mntflags, UDBA_REVAL); ++ ++ opt = opts->opt; ++ while (err >= 0 && opt->type != Opt_tail) ++ err = au_opt_br(sb, opt++, opts); ++ if (err > 0) ++ err = 0; ++ else if (unlikely(err < 0)) ++ goto out; ++ ++ bend = au_sbend(sb); ++ if (unlikely(bend < 0)) { ++ err = -EINVAL; ++ AuErr("no branches\n"); ++ goto out; ++ } ++ ++ if (au_opt_test(tmp, XINO)) ++ au_opt_set(sbinfo->si_mntflags, XINO); ++ opt = opts->opt; ++ while (!err && opt->type != Opt_tail) ++ err = au_opt_xino(sb, opt++, &opt_xino, opts); ++ if (unlikely(err)) ++ goto out; ++ ++ err = au_opts_verify(sb, sb->s_flags, tmp); ++ if (unlikely(err)) ++ goto out; ++ ++ /* restore xino */ ++ if (au_opt_test(tmp, XINO) && !opt_xino) { ++ xino.file = au_xino_def(sb); ++ err = PTR_ERR(xino.file); ++ if (IS_ERR(xino.file)) ++ goto out; ++ ++ err = au_xino_set(sb, &xino, /*remount*/0); ++ fput(xino.file); ++ if (unlikely(err)) ++ goto out; ++ } ++ ++ /* restore udba */ ++ sbinfo->si_mntflags &= ~AuOptMask_UDBA; ++ sbinfo->si_mntflags |= (tmp & AuOptMask_UDBA); ++ if (au_opt_test(tmp, UDBA_HINOTIFY)) { ++ struct inode *dir = sb->s_root->d_inode; ++ au_reset_hinotify(dir, ++ au_hi_flags(dir, /*isdir*/1) & ~AuHi_XINO); ++ } ++ ++ out: ++ return err; ++} ++ ++int au_opts_remount(struct super_block *sb, struct au_opts *opts) ++{ ++ int err, rerr; ++ struct inode *dir; ++ struct au_opt_xino *opt_xino; ++ struct au_opt *opt; ++ struct au_sbinfo *sbinfo; ++ ++ dir = sb->s_root->d_inode; ++ sbinfo = au_sbi(sb); ++ err = 0; ++ opt_xino = NULL; ++ opt = opts->opt; ++ while (err >= 0 && opt->type != Opt_tail) { ++ err = au_opt_simple(sb, opt, opts); ++ if (!err) ++ err = au_opt_br(sb, opt, opts); ++ if (!err) ++ err = au_opt_xino(sb, opt, &opt_xino, opts); ++ opt++; ++ } ++ if (err > 0) ++ err = 0; ++ AuTraceErr(err); ++ /* go on even err */ ++ ++ rerr = au_opts_verify(sb, opts->sb_flags, /*pending*/0); ++ if (unlikely(rerr && !err)) ++ err = rerr; ++ ++ if (au_ftest_opts(opts->flags, TRUNC_XIB)) { ++ rerr = au_xib_trunc(sb); ++ if (unlikely(rerr && !err)) ++ err = rerr; ++ } ++ ++ /* will be handled by the caller */ ++ if (!au_ftest_opts(opts->flags, REFRESH_DIR) ++ && (opts->given_udba || au_opt_test(sbinfo->si_mntflags, XINO))) ++ au_fset_opts(opts->flags, REFRESH_DIR); ++ ++ AuDbg("status 0x%x\n", opts->flags); ++ return err; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++unsigned int au_opt_udba(struct super_block *sb) ++{ ++ return au_mntflags(sb) & AuOptMask_UDBA; ++} +diff -urN ./fs/aufs/opts.h ./fs/aufs/opts.h +--- ./fs/aufs/opts.h 1970-01-01 01:00:00.000000000 +0100 ++++ ./fs/aufs/opts.h 2009-04-06 10:26:46.000000000 +0200 +@@ -0,0 +1,180 @@ ++/* ++ * Copyright (C) 2005-2009 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. ++ */ ++ ++/* ++ * mount options/flags ++ */ ++ ++#ifndef __AUFS_OPTS_H__ ++#define __AUFS_OPTS_H__ ++ ++#ifdef __KERNEL__ ++ ++#include <linux/fs.h> ++#include <linux/namei.h> ++#include <linux/aufs_type.h> ++ ++/* ---------------------------------------------------------------------- */ ++ ++/* mount flags */ ++#define AuOpt_XINO 1 /* external inode number bitmap ++ and translation table */ ++#define AuOpt_TRUNC_XINO (1 << 1) /* truncate xino files */ ++#define AuOpt_UDBA_NONE (1 << 2) /* users direct branch access */ ++#define AuOpt_UDBA_REVAL (1 << 3) ++#define AuOpt_UDBA_HINOTIFY (1 << 4) ++#define AuOpt_PLINK (1 << 5) /* pseudo-link */ ++#define AuOpt_DIRPERM1 (1 << 6) /* unimplemented */ ++#define AuOpt_REFROF (1 << 7) /* unimplemented */ ++#define AuOpt_ALWAYS_DIROPQ (1 << 8) /* policy to creating diropq */ ++#define AuOpt_SUM (1 << 9) /* summation for statfs(2) */ ++#define AuOpt_SUM_W (1 << 10) /* unimplemented */ ++#define AuOpt_WARN_PERM (1 << 11) /* warn when add-branch */ ++#define AuOpt_VERBOSE (1 << 12) /* busy inode when del-branch */ ++ ++#ifndef CONFIG_AUFS_HINOTIFY ++#undef AuOpt_UDBA_HINOTIFY ++#define AuOpt_UDBA_HINOTIFY 0 ++#endif ++ ++#define AuOpt_Def (AuOpt_XINO \ ++ | AuOpt_UDBA_REVAL \ ++ | AuOpt_PLINK \ ++ /* | AuOpt_DIRPERM1 */ \ ++ | AuOpt_WARN_PERM) ++#define AuOptMask_UDBA (AuOpt_UDBA_NONE \ ++ | AuOpt_UDBA_REVAL \ ++ | AuOpt_UDBA_HINOTIFY) ++ ++#define au_opt_test(flags, name) (flags & AuOpt_##name) ++#define au_opt_set(flags, name) do { \ ++ BUILD_BUG_ON(AuOpt_##name & AuOptMask_UDBA); \ ++ ((flags) |= AuOpt_##name); \ ++} while (0) ++#define au_opt_set_udba(flags, name) do { \ ++ (flags) &= ~AuOptMask_UDBA; \ ++ ((flags) |= AuOpt_##name); \ ++} while (0) ++#define au_opt_clr(flags, name) { ((flags) &= ~AuOpt_##name); } ++ ++/* ---------------------------------------------------------------------- */ ++ ++/* policies to select one among multiple writable branches */ ++enum { ++ AuWbrCreate_TDP, /* top down parent */ ++ AuWbrCreate_RR, /* round robin */ ++ AuWbrCreate_MFS, /* most free space */ ++ AuWbrCreate_MFSV, /* mfs with seconds */ ++ AuWbrCreate_MFSRR, /* mfs then rr */ ++ AuWbrCreate_MFSRRV, /* mfs then rr with seconds */ ++ AuWbrCreate_PMFS, /* parent and mfs */ ++ AuWbrCreate_PMFSV, /* parent and mfs with seconds */ ++ ++ AuWbrCreate_Def = AuWbrCreate_TDP ++}; ++ ++enum { ++ AuWbrCopyup_TDP, /* top down parent */ ++ AuWbrCopyup_BUP, /* bottom up parent */ ++ AuWbrCopyup_BU, /* bottom up */ ++ ++ AuWbrCopyup_Def = AuWbrCopyup_TDP ++}; ++ ++/* ---------------------------------------------------------------------- */ ++ ++struct au_opt_add { ++ aufs_bindex_t bindex; ++ char *pathname; ++ int perm; ++ struct path path; ++}; ++ ++struct au_opt_del { ++ char *pathname; ++ struct path h_path; ++}; ++ ++struct au_opt_mod { ++ char *path; ++ int perm; ++ struct dentry *h_root; ++}; ++ ++struct au_opt_xino { ++ char *path; ++ struct file *file; ++}; ++ ++struct au_opt_xino_itrunc { ++ aufs_bindex_t bindex; ++}; ++ ++struct au_opt_wbr_create { ++ int wbr_create; ++ int mfs_second; ++ unsigned long long mfsrr_watermark; ++}; ++ ++struct au_opt { ++ int type; ++ union { ++ struct au_opt_xino xino; ++ struct au_opt_xino_itrunc xino_itrunc; ++ struct au_opt_add add; ++ struct au_opt_del del; ++ struct au_opt_mod mod; ++ int dirwh; ++ int rdcache; ++ int deblk; ++ int nhash; ++ int udba; ++ struct au_opt_wbr_create wbr_create; ++ int wbr_copyup; ++ }; ++}; ++ ++/* opts flags */ ++#define AuOpts_REMOUNT 1 ++#define AuOpts_REFRESH_DIR (1 << 1) ++#define AuOpts_REFRESH_NONDIR (1 << 2) ++#define AuOpts_TRUNC_XIB (1 << 3) ++#define au_ftest_opts(flags, name) ((flags) & AuOpts_##name) ++#define au_fset_opts(flags, name) { (flags) |= AuOpts_##name; } ++#define au_fclr_opts(flags, name) { (flags) &= ~AuOpts_##name; } ++ ++struct au_opts { ++ struct au_opt *opt; ++ int max_opt; ++ ++ unsigned int given_udba; ++ unsigned int flags; ++ unsigned long sb_flags; ++}; ++ ++/* ---------------------------------------------------------------------- */ ++ ++const char *au_optstr_br_perm(int brperm); ++const char *au_optstr_udba(int udba); ++const char *au_optstr_wbr_copyup(int wbr_copyup); ++const char *au_optstr_wbr_create(int wbr_create); ++ ++void au_opts_free(struct au_opts *opts); ++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); ++int au_opts_mount(struct super_block *sb, struct au_opts *opts); ++int au_opts_remount(struct super_block *sb, struct au_opts *opts); ++ ++unsigned int au_opt_udba(struct super_block *sb); ++ ++/* ---------------------------------------------------------------------- */ ++ ++#endif /* __KERNEL__ */ ++#endif /* __AUFS_OPTS_H__ */ +diff -urN ./fs/aufs/plink.c ./fs/aufs/plink.c +--- ./fs/aufs/plink.c 1970-01-01 01:00:00.000000000 +0100 ++++ ./fs/aufs/plink.c 2009-04-06 10:26:46.000000000 +0200 +@@ -0,0 +1,335 @@ ++/* ++ * Copyright (C) 2005-2009 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. ++ */ ++ ++/* ++ * pseudo-link ++ */ ++ ++#include "aufs.h" ++ ++/* ++ * during a user process maintains the pseudo-links, ++ * prohibit adding a new plink and branch manipulation. ++ */ ++void au_plink_block_maintain(struct super_block *sb) ++{ ++ struct au_sbinfo *sbi = au_sbi(sb); ++ /* gave up wake_up_bit() */ ++ wait_event(sbi->si_plink_wq, !au_ftest_si(sbi, MAINTAIN_PLINK)); ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++struct pseudo_link { ++ struct list_head list; ++ struct inode *inode; ++}; ++ ++#ifdef CONFIG_AUFS_DEBUG ++void au_plink_list(struct super_block *sb) ++{ ++ struct au_sbinfo *sbinfo; ++ struct list_head *plink_list; ++ struct pseudo_link *plink; ++ ++ sbinfo = au_sbi(sb); ++ AuDebugOn(!au_opt_test(au_mntflags(sb), PLINK)); ++ ++ plink_list = &sbinfo->si_plink.head; ++ spin_lock(&sbinfo->si_plink.spin); ++ list_for_each_entry(plink, plink_list, list) ++ AuDbg("%lu\n", plink->inode->i_ino); ++ spin_unlock(&sbinfo->si_plink.spin); ++} ++#endif ++ ++/* is the inode pseudo-linked? */ ++int au_plink_test(struct inode *inode) ++{ ++ int found; ++ struct au_sbinfo *sbinfo; ++ struct list_head *plink_list; ++ struct pseudo_link *plink; ++ ++ sbinfo = au_sbi(inode->i_sb); ++ AuDebugOn(!au_opt_test(au_mntflags(inode->i_sb), PLINK)); ++ ++ found = 0; ++ plink_list = &sbinfo->si_plink.head; ++ spin_lock(&sbinfo->si_plink.spin); ++ list_for_each_entry(plink, plink_list, list) ++ if (plink->inode == inode) { ++ found = 1; ++ break; ++ } ++ spin_unlock(&sbinfo->si_plink.spin); ++ return found; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++/* ++ * generate a name for plink. ++ * the file will be stored under AUFS_WH_PLINKDIR. ++ */ ++/* 20 is max digits length of ulong 64 */ ++#define PLINK_NAME_LEN ((20 + 1) * 2) ++ ++static int plink_name(char *name, int len, struct inode *inode, ++ aufs_bindex_t bindex) ++{ ++ int rlen; ++ struct inode *h_inode; ++ ++ h_inode = au_h_iptr(inode, bindex); ++ rlen = snprintf(name, len, "%lu.%lu", inode->i_ino, h_inode->i_ino); ++ return rlen; ++} ++ ++/* lookup the plink-ed @inode under the branch at @bindex */ ++struct dentry *au_plink_lkup(struct inode *inode, aufs_bindex_t bindex) ++{ ++ struct dentry *h_dentry, *h_parent; ++ struct au_branch *br; ++ struct inode *h_dir; ++ char a[PLINK_NAME_LEN]; ++ struct qstr tgtname = { ++ .name = a ++ }; ++ ++ br = au_sbr(inode->i_sb, bindex); ++ h_parent = br->br_wbr->wbr_plink; ++ h_dir = h_parent->d_inode; ++ tgtname.len = plink_name(a, sizeof(a), inode, bindex); ++ ++ /* always superio. */ ++ mutex_lock_nested(&h_dir->i_mutex, AuLsc_I_CHILD2); ++ h_dentry = au_sio_lkup_one(&tgtname, h_parent, br); ++ mutex_unlock(&h_dir->i_mutex); ++ return h_dentry; ++} ++ ++/* create a pseudo-link */ ++static int do_whplink(struct qstr *tgt, struct dentry *h_parent, ++ struct dentry *h_dentry, struct au_branch *br) ++{ ++ int err; ++ struct path h_path = { ++ .mnt = br->br_mnt ++ }; ++ struct inode *h_dir; ++ ++ h_dir = h_parent->d_inode; ++ again: ++ h_path.dentry = au_lkup_one(tgt, h_parent, br, /*nd*/NULL); ++ err = PTR_ERR(h_path.dentry); ++ if (IS_ERR(h_path.dentry)) ++ goto out; ++ ++ err = 0; ++ /* wh.plink dir is not monitored */ ++ if (h_path.dentry->d_inode ++ && h_path.dentry->d_inode != h_dentry->d_inode) { ++ err = vfsub_unlink(h_dir, &h_path, /*force*/0); ++ dput(h_path.dentry); ++ h_path.dentry = NULL; ++ if (!err) ++ goto again; ++ } ++ if (!err && !h_path.dentry->d_inode) ++ err = vfsub_link(h_dentry, h_dir, &h_path); ++ dput(h_path.dentry); ++ ++ out: ++ return err; ++} ++ ++struct do_whplink_args { ++ int *errp; ++ struct qstr *tgt; ++ struct dentry *h_parent; ++ struct dentry *h_dentry; ++ struct au_branch *br; ++}; ++ ++static void call_do_whplink(void *args) ++{ ++ struct do_whplink_args *a = args; ++ *a->errp = do_whplink(a->tgt, a->h_parent, a->h_dentry, a->br); ++} ++ ++static int whplink(struct dentry *h_dentry, struct inode *inode, ++ aufs_bindex_t bindex, struct au_branch *br) ++{ ++ int err, wkq_err; ++ struct au_wbr *wbr; ++ struct dentry *h_parent; ++ struct inode *h_dir; ++ char a[PLINK_NAME_LEN]; ++ struct qstr tgtname = { ++ .name = a ++ }; ++ ++ wbr = au_sbr(inode->i_sb, bindex)->br_wbr; ++ h_parent = wbr->wbr_plink; ++ h_dir = h_parent->d_inode; ++ tgtname.len = plink_name(a, sizeof(a), inode, bindex); ++ ++ /* always superio. */ ++ mutex_lock_nested(&h_dir->i_mutex, AuLsc_I_CHILD2); ++ if (!au_test_wkq(current)) { ++ struct do_whplink_args args = { ++ .errp = &err, ++ .tgt = &tgtname, ++ .h_parent = h_parent, ++ .h_dentry = h_dentry, ++ .br = br ++ }; ++ wkq_err = au_wkq_wait(call_do_whplink, &args); ++ if (unlikely(wkq_err)) ++ err = wkq_err; ++ } else ++ err = do_whplink(&tgtname, h_parent, h_dentry, br); ++ mutex_unlock(&h_dir->i_mutex); ++ ++ return err; ++} ++ ++/* free a single plink */ ++static void do_put_plink(struct pseudo_link *plink, int do_del) ++{ ++ iput(plink->inode); ++ if (do_del) ++ list_del(&plink->list); ++ kfree(plink); ++} ++ ++/* ++ * create a new pseudo-link for @h_dentry on @bindex. ++ * the linked inode is held in aufs @inode. ++ */ ++void au_plink_append(struct inode *inode, aufs_bindex_t bindex, ++ struct dentry *h_dentry) ++{ ++ struct super_block *sb; ++ struct au_sbinfo *sbinfo; ++ struct list_head *plink_list; ++ struct pseudo_link *plink; ++ int found, err, cnt; ++ ++ sb = inode->i_sb; ++ sbinfo = au_sbi(sb); ++ AuDebugOn(!au_opt_test(au_mntflags(sb), PLINK)); ++ ++ err = 0; ++ cnt = 0; ++ found = 0; ++ plink_list = &sbinfo->si_plink.head; ++ spin_lock(&sbinfo->si_plink.spin); ++ list_for_each_entry(plink, plink_list, list) { ++ cnt++; ++ if (plink->inode == inode) { ++ found = 1; ++ break; ++ } ++ } ++ if (found) { ++ spin_unlock(&sbinfo->si_plink.spin); ++ return; ++ } ++ ++ plink = NULL; ++ if (!found) { ++ plink = kmalloc(sizeof(*plink), GFP_ATOMIC); ++ if (plink) { ++ plink->inode = au_igrab(inode); ++ list_add(&plink->list, plink_list); ++ cnt++; ++ } else ++ err = -ENOMEM; ++ } ++ spin_unlock(&sbinfo->si_plink.spin); ++ ++ if (!err) { ++ au_plink_block_maintain(sb); ++ err = whplink(h_dentry, inode, bindex, au_sbr(sb, bindex)); ++ } ++ ++ if (unlikely(cnt > AUFS_PLINK_WARN)) ++ AuWarn1("unexpectedly many pseudo links, %d\n", cnt); ++ if (unlikely(err)) { ++ AuWarn("err %d, damaged pseudo link.\n", err); ++ if (!found && plink) ++ do_put_plink(plink, /*do_del*/1); ++ } ++} ++ ++/* free all plinks */ ++void au_plink_put(struct super_block *sb) ++{ ++ struct au_sbinfo *sbinfo; ++ struct list_head *plink_list; ++ struct pseudo_link *plink, *tmp; ++ ++ sbinfo = au_sbi(sb); ++ AuDebugOn(!au_opt_test(au_mntflags(sb), PLINK)); ++ ++ plink_list = &sbinfo->si_plink.head; ++ /* no spin_lock since sbinfo is write-locked */ ++ list_for_each_entry_safe(plink, tmp, plink_list, list) ++ do_put_plink(plink, 0); ++ INIT_LIST_HEAD(plink_list); ++} ++ ++/* free the plinks on a branch specified by @br_id */ ++void au_plink_half_refresh(struct super_block *sb, aufs_bindex_t br_id) ++{ ++ struct au_sbinfo *sbinfo; ++ struct list_head *plink_list; ++ struct pseudo_link *plink, *tmp; ++ struct inode *inode; ++ aufs_bindex_t bstart, bend, bindex; ++ unsigned char do_put; ++ ++ sbinfo = au_sbi(sb); ++ AuDebugOn(!au_opt_test(au_mntflags(sb), PLINK)); ++ ++ plink_list = &sbinfo->si_plink.head; ++ /* no spin_lock since sbinfo is write-locked */ ++ list_for_each_entry_safe(plink, tmp, plink_list, list) { ++ do_put = 0; ++ inode = au_igrab(plink->inode); ++ ii_write_lock_child(inode); ++ bstart = au_ibstart(inode); ++ bend = au_ibend(inode); ++ if (bstart >= 0) { ++ for (bindex = bstart; bindex <= bend; bindex++) { ++ if (!au_h_iptr(inode, bindex) ++ || au_ii_br_id(inode, bindex) != br_id) ++ continue; ++ au_set_h_iptr(inode, bindex, NULL, 0); ++ do_put = 1; ++ break; ++ } ++ } else ++ do_put_plink(plink, 1); ++ ++ if (do_put) { ++ for (bindex = bstart; bindex <= bend; bindex++) ++ if (au_h_iptr(inode, bindex)) { ++ do_put = 0; ++ break; ++ } ++ if (do_put) ++ do_put_plink(plink, 1); ++ } ++ ii_write_unlock(inode); ++ iput(inode); ++ } ++} +diff -urN ./fs/aufs/rwsem.h ./fs/aufs/rwsem.h +--- ./fs/aufs/rwsem.h 1970-01-01 01:00:00.000000000 +0100 ++++ ./fs/aufs/rwsem.h 2009-04-06 10:26:46.000000000 +0200 +@@ -0,0 +1,52 @@ ++/* ++ * Copyright (C) 2005-2009 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. ++ */ ++ ++/* ++ * simple read-write semaphore wrappers ++ */ ++ ++#ifndef __AUFS_RWSEM_H__ ++#define __AUFS_RWSEM_H__ ++ ++#ifdef __KERNEL__ ++ ++#include <linux/fs.h> ++ ++#define au_rwsem_destroy(rw) AuDebugOn(rwsem_is_locked(rw)) ++#define AuRwMustNoWaiters(rw) AuDebugOn(!list_empty(&(rw)->wait_list)) ++ ++#define AuSimpleLockRwsemFuncs(prefix, param, rwsem) \ ++static inline void prefix##_read_lock(param) \ ++{ down_read(rwsem); } \ ++static inline void prefix##_write_lock(param) \ ++{ down_write(rwsem); } \ ++static inline int prefix##_read_trylock(param) \ ++{ return down_read_trylock(rwsem); } \ ++static inline int prefix##_write_trylock(param) \ ++{ return down_write_trylock(rwsem); } ++/* why is not _nested version defined */ ++/* static inline void prefix##_read_trylock_nested(param, lsc) ++{ down_write_trylock_nested(rwsem, lsc)); } ++static inline void prefix##_write_trylock_nestd(param, lsc) ++{ down_write_trylock_nested(rwsem, lsc); } */ ++ ++#define AuSimpleUnlockRwsemFuncs(prefix, param, rwsem) \ ++static inline void prefix##_read_unlock(param) \ ++{ up_read(rwsem); } \ ++static inline void prefix##_write_unlock(param) \ ++{ up_write(rwsem); } \ ++static inline void prefix##_downgrade_lock(param) \ ++{ downgrade_write(rwsem); } ++ ++#define AuSimpleRwsemFuncs(prefix, param, rwsem) \ ++ AuSimpleLockRwsemFuncs(prefix, param, rwsem) \ ++ AuSimpleUnlockRwsemFuncs(prefix, param, rwsem) ++ ++#endif /* __KERNEL__ */ ++#endif /* __AUFS_RWSEM_H__ */ +diff -urN ./fs/aufs/sbinfo.c ./fs/aufs/sbinfo.c +--- ./fs/aufs/sbinfo.c 1970-01-01 01:00:00.000000000 +0100 ++++ ./fs/aufs/sbinfo.c 2009-04-06 10:26:46.000000000 +0200 +@@ -0,0 +1,192 @@ ++/* ++ * Copyright (C) 2005-2009 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. ++ */ ++ ++/* ++ * superblock private data ++ */ ++ ++#include "aufs.h" ++ ++/* ++ * they are necessary regardless sysfs is disabled. ++ */ ++void au_si_free(struct kobject *kobj) ++{ ++ struct au_sbinfo *sbinfo; ++ struct super_block *sb; ++ ++ sbinfo = container_of(kobj, struct au_sbinfo, si_kobj); ++ AuDebugOn(!list_empty(&sbinfo->si_plink.head)); ++ ++ sb = sbinfo->si_sb; ++ si_write_lock(sb); ++ au_xino_clr(sb); ++ au_br_free(sbinfo); ++ kfree(sbinfo->si_branch); ++ mutex_destroy(&sbinfo->si_xib_mtx); ++ si_write_unlock(sb); ++ au_rwsem_destroy(&sbinfo->si_rwsem); ++ ++ kfree(sbinfo); ++} ++ ++int au_si_alloc(struct super_block *sb) ++{ ++ int err; ++ struct au_sbinfo *sbinfo; ++ ++ err = -ENOMEM; ++ sbinfo = kmalloc(sizeof(*sbinfo), GFP_NOFS); ++ if (unlikely(!sbinfo)) ++ goto out; ++ ++ /* will be reallocated separately */ ++ sbinfo->si_branch = kzalloc(sizeof(*sbinfo->si_branch), GFP_NOFS); ++ if (unlikely(!sbinfo->si_branch)) ++ goto out_sbinfo; ++ ++ memset(&sbinfo->si_kobj, 0, sizeof(sbinfo->si_kobj)); ++ err = sysaufs_si_init(sbinfo); ++ if (unlikely(err)) ++ goto out_br; ++ ++ au_nwt_init(&sbinfo->si_nowait); ++ init_rwsem(&sbinfo->si_rwsem); ++ down_write(&sbinfo->si_rwsem); ++ sbinfo->si_generation = 0; ++ sbinfo->au_si_status = 0; ++ sbinfo->si_bend = -1; ++ sbinfo->si_last_br_id = 0; ++ ++ sbinfo->si_wbr_copyup = AuWbrCopyup_Def; ++ sbinfo->si_wbr_create = AuWbrCreate_Def; ++ sbinfo->si_wbr_copyup_ops = au_wbr_copyup_ops + AuWbrCopyup_Def; ++ sbinfo->si_wbr_create_ops = au_wbr_create_ops + AuWbrCreate_Def; ++ ++ sbinfo->si_mntflags = AuOpt_Def; ++ ++ sbinfo->si_xread = NULL; ++ sbinfo->si_xwrite = NULL; ++ sbinfo->si_xib = NULL; ++ mutex_init(&sbinfo->si_xib_mtx); ++ sbinfo->si_xib_buf = NULL; ++ sbinfo->si_xino_brid = -1; ++ /* leave si_xib_last_pindex and si_xib_next_bit */ ++ ++ sbinfo->si_rdcache = AUFS_RDCACHE_DEF * HZ; ++ sbinfo->si_dirwh = AUFS_DIRWH_DEF; ++ ++ au_spl_init(&sbinfo->si_plink); ++ init_waitqueue_head(&sbinfo->si_plink_wq); ++ ++ /* leave other members for sysaufs and si_mnt. */ ++ sbinfo->si_sb = sb; ++ sb->s_fs_info = sbinfo; ++ au_debug_sbinfo_init(sbinfo); ++ return 0; /* success */ ++ ++ out_br: ++ kfree(sbinfo->si_branch); ++ out_sbinfo: ++ kfree(sbinfo); ++ out: ++ return err; ++} ++ ++int au_sbr_realloc(struct au_sbinfo *sbinfo, int nbr) ++{ ++ int err, sz; ++ struct au_branch **brp; ++ ++ err = -ENOMEM; ++ sz = sizeof(*brp) * (sbinfo->si_bend + 1); ++ if (unlikely(!sz)) ++ sz = sizeof(*brp); ++ brp = au_kzrealloc(sbinfo->si_branch, sz, sizeof(*brp) * nbr, GFP_NOFS); ++ if (brp) { ++ sbinfo->si_branch = brp; ++ err = 0; ++ } ++ ++ return err; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++unsigned int au_sigen_inc(struct super_block *sb) ++{ ++ unsigned int gen; ++ ++ gen = ++au_sbi(sb)->si_generation; ++ au_update_digen(sb->s_root); ++ au_update_iigen(sb->s_root->d_inode); ++ sb->s_root->d_inode->i_version++; ++ return gen; ++} ++ ++aufs_bindex_t au_new_br_id(struct super_block *sb) ++{ ++ aufs_bindex_t br_id; ++ int i; ++ struct au_sbinfo *sbinfo; ++ ++ sbinfo = au_sbi(sb); ++ for (i = 0; i <= AUFS_BRANCH_MAX; i++) { ++ br_id = ++sbinfo->si_last_br_id; ++ if (br_id && au_br_index(sb, br_id) < 0) ++ return br_id; ++ } ++ ++ return -1; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++/* dentry and super_block lock. call at entry point */ ++void aufs_read_lock(struct dentry *dentry, int flags) ++{ ++ si_read_lock(dentry->d_sb, flags); ++ if (au_ftest_lock(flags, DW)) ++ di_write_lock_child(dentry); ++ else ++ di_read_lock_child(dentry, flags); ++} ++ ++void aufs_read_unlock(struct dentry *dentry, int flags) ++{ ++ if (au_ftest_lock(flags, DW)) ++ di_write_unlock(dentry); ++ else ++ di_read_unlock(dentry, flags); ++ si_read_unlock(dentry->d_sb); ++} ++ ++void aufs_write_lock(struct dentry *dentry) ++{ ++ si_write_lock(dentry->d_sb); ++ di_write_lock_child(dentry); ++} ++ ++void aufs_write_unlock(struct dentry *dentry) ++{ ++ di_write_unlock(dentry); ++ si_write_unlock(dentry->d_sb); ++} ++ ++void aufs_read_and_write_lock2(struct dentry *d1, struct dentry *d2, int flags) ++{ ++ si_read_lock(d1->d_sb, flags); ++ di_write_lock2_child(d1, d2, au_ftest_lock(flags, DIR)); ++} ++ ++void aufs_read_and_write_unlock2(struct dentry *d1, struct dentry *d2) ++{ ++ di_write_unlock2(d1, d2); ++ si_read_unlock(d1->d_sb); ++} +diff -urN ./fs/aufs/spl.h ./fs/aufs/spl.h +--- ./fs/aufs/spl.h 1970-01-01 01:00:00.000000000 +0100 ++++ ./fs/aufs/spl.h 2009-04-06 10:26:46.000000000 +0200 +@@ -0,0 +1,47 @@ ++/* ++ * Copyright (C) 2005-2009 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. ++ */ ++ ++/* ++ * simple list protected by a spinlock ++ */ ++ ++#ifndef __AUFS_SPL_H__ ++#define __AUFS_SPL_H__ ++ ++#ifdef __KERNEL__ ++ ++#include <linux/fs.h> ++ ++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); ++} ++ ++#endif /* __KERNEL__ */ ++#endif /* __AUFS_SPL_H__ */ +diff -urN ./fs/aufs/super.c ./fs/aufs/super.c +--- ./fs/aufs/super.c 1970-01-01 01:00:00.000000000 +0100 ++++ ./fs/aufs/super.c 2009-04-06 10:26:46.000000000 +0200 +@@ -0,0 +1,854 @@ ++/* ++ * Copyright (C) 2005-2009 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. ++ */ ++ ++/* ++ * mount and super_block operations ++ */ ++ ++#include <linux/buffer_head.h> ++#include <linux/seq_file.h> ++#include <linux/statfs.h> ++#include "aufs.h" ++ ++/* ++ * super_operations ++ */ ++static struct inode *aufs_alloc_inode(struct super_block *sb __maybe_unused) ++{ ++ struct au_icntnr *c; ++ ++ c = au_cache_alloc_icntnr(); ++ if (c) { ++ inode_init_once(&c->vfs_inode); ++ c->vfs_inode.i_version = 1; /* sigen(sb); */ ++ c->iinfo.ii_hinode = NULL; ++ return &c->vfs_inode; ++ } ++ return NULL; ++} ++ ++static void aufs_destroy_inode(struct inode *inode) ++{ ++ au_iinfo_fin(inode); ++ au_cache_free_icntnr(container_of(inode, struct au_icntnr, vfs_inode)); ++} ++ ++struct inode *au_iget_locked(struct super_block *sb, ino_t ino) ++{ ++ struct inode *inode; ++ int err; ++ ++ inode = iget_locked(sb, ino); ++ if (unlikely(!inode)) { ++ inode = ERR_PTR(-ENOMEM); ++ goto out; ++ } ++ if (!(inode->i_state & I_NEW)) ++ goto out; ++ ++ err = au_xigen_new(inode); ++ if (!err) ++ err = au_iinfo_init(inode); ++ if (!err) ++ inode->i_version++; ++ else { ++ iget_failed(inode); ++ inode = ERR_PTR(err); ++ } ++ ++ out: ++ /* never return NULL */ ++ AuDebugOn(!inode); ++ AuTraceErrPtr(inode); ++ return inode; ++} ++ ++/* lock free root dinfo */ ++static int au_show_brs(struct seq_file *seq, struct super_block *sb) ++{ ++ int err; ++ aufs_bindex_t bindex, bend; ++ struct path path; ++ struct au_hdentry *hd; ++ struct au_branch *br; ++ ++ err = 0; ++ bend = au_sbend(sb); ++ hd = au_di(sb->s_root)->di_hdentry; ++ for (bindex = 0; !err && bindex <= bend; bindex++) { ++ br = au_sbr(sb, bindex); ++ path.mnt = br->br_mnt; ++ path.dentry = hd[bindex].hd_dentry; ++ err = au_seq_path(seq, &path); ++ if (err > 0) ++ err = seq_printf(seq, "=%s", ++ au_optstr_br_perm(br->br_perm)); ++ if (!err && bindex != bend) ++ err = seq_putc(seq, ':'); ++ } ++ ++ return err; ++} ++ ++static void au_show_wbr_create(struct seq_file *m, int v, ++ struct au_sbinfo *sbinfo) ++{ ++ const char *pat; ++ ++ seq_printf(m, ",create="); ++ pat = au_optstr_wbr_create(v); ++ switch (v) { ++ case AuWbrCreate_TDP: ++ case AuWbrCreate_RR: ++ case AuWbrCreate_MFS: ++ case AuWbrCreate_PMFS: ++ seq_printf(m, pat); ++ break; ++ case AuWbrCreate_MFSV: ++ seq_printf(m, /*pat*/"mfs:%lu", ++ sbinfo->si_wbr_mfs.mfs_expire / HZ); ++ break; ++ case AuWbrCreate_PMFSV: ++ seq_printf(m, /*pat*/"pmfs:%lu", ++ sbinfo->si_wbr_mfs.mfs_expire / HZ); ++ break; ++ case AuWbrCreate_MFSRR: ++ seq_printf(m, /*pat*/"mfsrr:%llu", ++ sbinfo->si_wbr_mfs.mfsrr_watermark); ++ break; ++ case AuWbrCreate_MFSRRV: ++ seq_printf(m, /*pat*/"mfsrr:%llu:%lu", ++ sbinfo->si_wbr_mfs.mfsrr_watermark, ++ sbinfo->si_wbr_mfs.mfs_expire / HZ); ++ break; ++ } ++} ++ ++static int au_show_xino(struct seq_file *seq, struct vfsmount *mnt) ++{ ++#ifdef CONFIG_SYSFS ++ return 0; ++#else ++ int err; ++ const int len = sizeof(AUFS_XINO_FNAME) - 1; ++ aufs_bindex_t bindex, brid; ++ struct super_block *sb; ++ struct qstr *name; ++ struct file *f; ++ struct dentry *d, *h_root; ++ ++ err = 0; ++ sb = mnt->mnt_sb; ++ f = au_sbi(sb)->si_xib; ++ if (!f) ++ goto out; ++ ++ /* stop printing the default xino path on the first writable branch */ ++ h_root = NULL; ++ brid = au_xino_brid(sb); ++ if (brid >= 0) { ++ bindex = au_br_index(sb, brid); ++ h_root = au_di(sb->s_root)->di_hdentry[0 + bindex].hd_dentry; ++ } ++ d = f->f_dentry; ++ name = &d->d_name; ++ /* safe ->d_parent because the file is unlinked */ ++ if (d->d_parent == h_root ++ && name->len == len ++ && !memcmp(name->name, AUFS_XINO_FNAME, len)) ++ goto out; ++ ++ seq_puts(seq, ",xino="); ++ err = au_xino_path(seq, f); ++ ++ out: ++ return err; ++#endif ++} ++ ++/* seq_file will re-call me in case of too long string */ ++static int aufs_show_options(struct seq_file *m, struct vfsmount *mnt) ++{ ++ int err, n; ++ unsigned int mnt_flags, v; ++ struct super_block *sb; ++ struct au_sbinfo *sbinfo; ++ ++#define AuBool(name, str) do { \ ++ v = au_opt_test(mnt_flags, name); \ ++ if (v != au_opt_test(AuOpt_Def, name)) \ ++ seq_printf(m, ",%s" #str, v ? "" : "no"); \ ++} while (0) ++ ++#define AuStr(name, str) do { \ ++ v = mnt_flags & AuOptMask_##name; \ ++ if (v != (AuOpt_Def & AuOptMask_##name)) \ ++ seq_printf(m, "," #str "=%s", au_optstr_##str(v)); \ ++} while (0) ++ ++ /* lock free root dinfo */ ++ sb = mnt->mnt_sb; ++ si_noflush_read_lock(sb); ++ sbinfo = au_sbi(sb); ++ seq_printf(m, ",si=%lx", sysaufs_si_id(sbinfo)); ++ ++ mnt_flags = au_mntflags(sb); ++ if (au_opt_test(mnt_flags, XINO)) { ++ err = au_show_xino(m, mnt); ++ if (unlikely(err)) ++ goto out; ++ } else ++ seq_puts(m, ",noxino"); ++ ++ AuBool(TRUNC_XINO, trunc_xino); ++ AuStr(UDBA, udba); ++ AuBool(PLINK, plink); ++ /* AuBool(DIRPERM1, dirperm1); */ ++ /* AuBool(REFROF, refrof); */ ++ ++ v = sbinfo->si_wbr_create; ++ if (v != AuWbrCreate_Def) ++ au_show_wbr_create(m, v, sbinfo); ++ ++ v = sbinfo->si_wbr_copyup; ++ if (v != AuWbrCopyup_Def) ++ seq_printf(m, ",cpup=%s", au_optstr_wbr_copyup(v)); ++ ++ v = au_opt_test(mnt_flags, ALWAYS_DIROPQ); ++ if (v != au_opt_test(AuOpt_Def, ALWAYS_DIROPQ)) ++ seq_printf(m, ",diropq=%c", v ? 'a' : 'w'); ++ ++ n = sbinfo->si_dirwh; ++ if (n != AUFS_DIRWH_DEF) ++ seq_printf(m, ",dirwh=%d", n); ++ ++ n = sbinfo->si_rdcache / HZ; ++ if (n != AUFS_RDCACHE_DEF) ++ seq_printf(m, ",rdcache=%d", n); ++ ++ AuBool(SUM, sum); ++ /* AuBool(SUM_W, wsum); */ ++ AuBool(WARN_PERM, warn_perm); ++ AuBool(VERBOSE, verbose); ++ ++ out: ++ /* be sure to print "br:" last */ ++ if (!sysaufs_brs) { ++ seq_puts(m, ",br:"); ++ au_show_brs(m, sb); ++ } ++ si_read_unlock(sb); ++ return 0; ++ ++#undef Deleted ++#undef AuBool ++#undef AuStr ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++/* sum mode which returns the summation for statfs(2) */ ++ ++static u64 au_add_till_max(u64 a, u64 b) ++{ ++ u64 old; ++ ++ old = a; ++ a += b; ++ if (old < a) ++ return a; ++ return ULLONG_MAX; ++} ++ ++static int au_statfs_sum(struct super_block *sb, struct kstatfs *buf) ++{ ++ int err; ++ u64 blocks, bfree, bavail, files, ffree; ++ aufs_bindex_t bend, bindex, i; ++ unsigned char shared; ++ struct vfsmount *h_mnt; ++ struct super_block *h_sb; ++ ++ blocks = 0; ++ bfree = 0; ++ bavail = 0; ++ files = 0; ++ ffree = 0; ++ ++ err = 0; ++ bend = au_sbend(sb); ++ for (bindex = bend; bindex >= 0; bindex--) { ++ h_mnt = au_sbr_mnt(sb, bindex); ++ h_sb = h_mnt->mnt_sb; ++ shared = 0; ++ for (i = bindex + 1; !shared && i <= bend; i++) ++ shared = (au_sbr_sb(sb, i) == h_sb); ++ if (shared) ++ continue; ++ ++ /* sb->s_root for NFS is unreliable */ ++ err = vfs_statfs(h_mnt->mnt_root, buf); ++ if (unlikely(err)) ++ goto out; ++ ++ blocks = au_add_till_max(blocks, buf->f_blocks); ++ bfree = au_add_till_max(bfree, buf->f_bfree); ++ bavail = au_add_till_max(bavail, buf->f_bavail); ++ files = au_add_till_max(files, buf->f_files); ++ ffree = au_add_till_max(ffree, buf->f_ffree); ++ } ++ ++ buf->f_blocks = blocks; ++ buf->f_bfree = bfree; ++ buf->f_bavail = bavail; ++ buf->f_files = files; ++ buf->f_ffree = ffree; ++ ++ out: ++ return err; ++} ++ ++static int aufs_statfs(struct dentry *dentry, struct kstatfs *buf) ++{ ++ int err; ++ struct super_block *sb; ++ ++ /* lock free root dinfo */ ++ sb = dentry->d_sb; ++ si_noflush_read_lock(sb); ++ if (!au_opt_test(au_mntflags(sb), SUM)) ++ /* sb->s_root for NFS is unreliable */ ++ err = vfs_statfs(au_sbr_mnt(sb, 0)->mnt_root, buf); ++ else ++ err = au_statfs_sum(sb, buf); ++ si_read_unlock(sb); ++ ++ if (!err) { ++ buf->f_type = AUFS_SUPER_MAGIC; ++ buf->f_namelen -= AUFS_WH_PFX_LEN; ++ memset(&buf->f_fsid, 0, sizeof(buf->f_fsid)); ++ } ++ /* buf->f_bsize = buf->f_blocks = buf->f_bfree = buf->f_bavail = -1; */ ++ ++ return err; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++/* try flushing the lower fs at aufs remount/unmount time */ ++ ++static void au_fsync_br(struct super_block *sb) ++{ ++ aufs_bindex_t bend, bindex; ++ int brperm; ++ struct au_branch *br; ++ struct super_block *h_sb; ++ ++ bend = au_sbend(sb); ++ for (bindex = 0; bindex < bend; bindex++) { ++ br = au_sbr(sb, bindex); ++ brperm = br->br_perm; ++ if (brperm == AuBrPerm_RR || brperm == AuBrPerm_RRWH) ++ continue; ++ h_sb = br->br_mnt->mnt_sb; ++ if (bdev_read_only(h_sb->s_bdev)) ++ continue; ++ ++ lockdep_off(); ++ down_write(&h_sb->s_umount); ++ shrink_dcache_sb(h_sb); ++ fsync_super(h_sb); ++ up_write(&h_sb->s_umount); ++ lockdep_on(); ++ } ++} ++ ++/* ++ * this IS NOT for super_operations. ++ * I guess it will be reverted someday. ++ */ ++static void aufs_umount_begin(struct super_block *sb) ++{ ++ struct au_sbinfo *sbinfo; ++ ++ sbinfo = au_sbi(sb); ++ if (!sbinfo) ++ return; ++ ++ si_write_lock(sb); ++ au_fsync_br(sb); ++ if (au_opt_test(au_mntflags(sb), PLINK)) ++ au_plink_put(sb); ++ if (sbinfo->si_wbr_create_ops->fin) ++ sbinfo->si_wbr_create_ops->fin(sb); ++ si_write_unlock(sb); ++} ++ ++/* final actions when unmounting a file system */ ++static void aufs_put_super(struct super_block *sb) ++{ ++ struct au_sbinfo *sbinfo; ++ ++ sbinfo = au_sbi(sb); ++ if (!sbinfo) ++ return; ++ ++ aufs_umount_begin(sb); ++ dbgaufs_si_fin(sbinfo); ++ kobject_put(&sbinfo->si_kobj); ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++/* ++ * refresh dentry and inode at remount time. ++ */ ++static int do_refresh(struct dentry *dentry, mode_t type, ++ unsigned int dir_flags) ++{ ++ int err; ++ struct dentry *parent; ++ ++ di_write_lock_child(dentry); ++ parent = dget_parent(dentry); ++ di_read_lock_parent(parent, AuLock_IR); ++ ++ /* returns the number of positive dentries */ ++ err = au_refresh_hdentry(dentry, type); ++ if (err >= 0) { ++ struct inode *inode = dentry->d_inode; ++ err = au_refresh_hinode(inode, dentry); ++ if (!err && type == S_IFDIR) ++ au_reset_hinotify(inode, dir_flags); ++ } ++ if (unlikely(err)) ++ AuErr("unrecoverable error %d, %.*s\n", err, AuDLNPair(dentry)); ++ ++ di_read_unlock(parent, AuLock_IR); ++ dput(parent); ++ di_write_unlock(dentry); ++ ++ return err; ++} ++ ++static int test_dir(struct dentry *dentry, void *arg __maybe_unused) ++{ ++ return S_ISDIR(dentry->d_inode->i_mode); ++} ++ ++/* gave up consolidating with refresh_nondir() */ ++static int refresh_dir(struct dentry *root, unsigned int sigen) ++{ ++ int err, i, j, ndentry, e; ++ struct au_dcsub_pages dpages; ++ struct au_dpage *dpage; ++ struct dentry **dentries; ++ struct inode *inode; ++ const unsigned int flags = au_hi_flags(root->d_inode, /*isdir*/1); ++ ++ err = 0; ++ list_for_each_entry(inode, &root->d_sb->s_inodes, i_sb_list) ++ if (S_ISDIR(inode->i_mode) && au_iigen(inode) != sigen) { ++ ii_write_lock_child(inode); ++ e = au_refresh_hinode_self(inode, /*do_attr*/1); ++ ii_write_unlock(inode); ++ if (unlikely(e)) { ++ AuDbg("e %d, i%lu\n", e, inode->i_ino); ++ if (!err) ++ err = e; ++ /* go on even if err */ ++ } ++ } ++ ++ e = au_dpages_init(&dpages, GFP_NOFS); ++ if (unlikely(e)) { ++ if (!err) ++ err = e; ++ goto out; ++ } ++ e = au_dcsub_pages(&dpages, root, test_dir, NULL); ++ if (unlikely(e)) { ++ if (!err) ++ err = e; ++ goto out_dpages; ++ } ++ ++ for (i = 0; !e && i < dpages.ndpage; i++) { ++ dpage = dpages.dpages + i; ++ dentries = dpage->dentries; ++ ndentry = dpage->ndentry; ++ for (j = 0; !e && j < ndentry; j++) { ++ struct dentry *d; ++ ++ d = dentries[j]; ++ au_dbg_verify_dir_parent(d, sigen); ++ if (au_digen(d) != sigen) { ++ e = do_refresh(d, S_IFDIR, flags); ++ if (unlikely(e && !err)) ++ err = e; ++ /* break on err */ ++ } ++ } ++ } ++ ++ out_dpages: ++ au_dpages_free(&dpages); ++ out: ++ return err; ++} ++ ++static int test_nondir(struct dentry *dentry, void *arg __maybe_unused) ++{ ++ return !S_ISDIR(dentry->d_inode->i_mode); ++} ++ ++static int refresh_nondir(struct dentry *root, unsigned int sigen, ++ int do_dentry) ++{ ++ int err, i, j, ndentry, e; ++ struct au_dcsub_pages dpages; ++ struct au_dpage *dpage; ++ struct dentry **dentries; ++ struct inode *inode; ++ ++ err = 0; ++ list_for_each_entry(inode, &root->d_sb->s_inodes, i_sb_list) ++ if (!S_ISDIR(inode->i_mode) && au_iigen(inode) != sigen) { ++ ii_write_lock_child(inode); ++ e = au_refresh_hinode_self(inode, /*do_attr*/1); ++ ii_write_unlock(inode); ++ if (unlikely(e)) { ++ AuDbg("e %d, i%lu\n", e, inode->i_ino); ++ if (!err) ++ err = e; ++ /* go on even if err */ ++ } ++ } ++ ++ if (!do_dentry) ++ goto out; ++ ++ e = au_dpages_init(&dpages, GFP_NOFS); ++ if (unlikely(e)) { ++ if (!err) ++ err = e; ++ goto out; ++ } ++ e = au_dcsub_pages(&dpages, root, test_nondir, NULL); ++ if (unlikely(e)) { ++ if (!err) ++ err = e; ++ goto out_dpages; ++ } ++ ++ for (i = 0; i < dpages.ndpage; i++) { ++ dpage = dpages.dpages + i; ++ dentries = dpage->dentries; ++ ndentry = dpage->ndentry; ++ for (j = 0; j < ndentry; j++) { ++ struct dentry *d; ++ ++ d = dentries[j]; ++ au_dbg_verify_nondir_parent(d, sigen); ++ inode = d->d_inode; ++ if (inode && au_digen(d) != sigen) { ++ e = do_refresh(d, inode->i_mode & S_IFMT, ++ /*dir_flags*/0); ++ if (unlikely(e && !err)) ++ err = e; ++ /* go on even err */ ++ } ++ } ++ } ++ ++ out_dpages: ++ au_dpages_free(&dpages); ++ out: ++ return err; ++} ++ ++static void au_remount_refresh(struct super_block *sb, unsigned int flags) ++{ ++ int err; ++ unsigned int sigen; ++ struct au_sbinfo *sbinfo; ++ struct dentry *root; ++ struct inode *inode; ++ ++ au_sigen_inc(sb); ++ sigen = au_sigen(sb); ++ sbinfo = au_sbi(sb); ++ au_fclr_si(sbinfo, FAILED_REFRESH_DIRS); ++ ++ root = sb->s_root; ++ DiMustNoWaiters(root); ++ inode = root->d_inode; ++ IiMustNoWaiters(inode); ++ au_reset_hinotify(inode, au_hi_flags(inode, /*isdir*/1)); ++ di_write_unlock(root); ++ ++ err = refresh_dir(root, sigen); ++ if (unlikely(err)) { ++ au_fset_si(sbinfo, FAILED_REFRESH_DIRS); ++ AuWarn("Refreshing directories failed, ignored (%d)\n", err); ++ } ++ ++ if (au_ftest_opts(flags, REFRESH_NONDIR)) { ++ err = refresh_nondir(root, sigen, !err); ++ if (unlikely(err)) ++ AuWarn("Refreshing non-directories failed, ignored" ++ "(%d)\n", err); ++ } ++ ++ /* aufs_write_lock() calls ..._child() */ ++ di_write_lock_child(root); ++ au_cpup_attr_all(root->d_inode, /*force*/1); ++} ++ ++/* stop extra interpretation of errno in mount(8), and strange error messages */ ++static int cvt_err(int err) ++{ ++ AuTraceErr(err); ++ ++ switch (err) { ++ case -ENOENT: ++ case -ENOTDIR: ++ case -EEXIST: ++ case -EIO: ++ err = -EINVAL; ++ } ++ return err; ++} ++ ++static int aufs_remount_fs(struct super_block *sb, int *flags, char *data) ++{ ++ int err; ++ struct au_opts opts; ++ struct dentry *root; ++ struct inode *inode; ++ struct au_sbinfo *sbinfo; ++ ++ err = 0; ++ root = sb->s_root; ++ if (!data || !*data) { ++ aufs_write_lock(root); ++ err = au_opts_verify(sb, *flags, /*pending*/0); ++ if (!err) ++ au_fsync_br(sb); ++ aufs_write_unlock(root); ++ goto out; ++ } ++ ++ err = -ENOMEM; ++ memset(&opts, 0, sizeof(opts)); ++ opts.opt = (void *)__get_free_page(GFP_NOFS); ++ if (unlikely(!opts.opt)) ++ goto out; ++ opts.max_opt = PAGE_SIZE / sizeof(*opts.opt); ++ opts.flags = AuOpts_REMOUNT; ++ opts.sb_flags = *flags; ++ ++ /* parse it before aufs lock */ ++ err = au_opts_parse(sb, data, &opts); ++ if (unlikely(err)) ++ goto out_opts; ++ ++ sbinfo = au_sbi(sb); ++ inode = root->d_inode; ++ mutex_lock(&inode->i_mutex); ++ aufs_write_lock(root); ++ au_fsync_br(sb); ++ ++ /* au_opts_remount() may return an error */ ++ err = au_opts_remount(sb, &opts); ++ au_opts_free(&opts); ++ ++ if (au_ftest_opts(opts.flags, REFRESH_DIR) ++ || au_ftest_opts(opts.flags, REFRESH_NONDIR)) ++ au_remount_refresh(sb, opts.flags); ++ ++ aufs_write_unlock(root); ++ mutex_unlock(&inode->i_mutex); ++ ++ out_opts: ++ free_page((unsigned long)opts.opt); ++ out: ++ err = cvt_err(err); ++ AuTraceErr(err); ++ return err; ++} ++ ++static struct super_operations aufs_sop = { ++ .alloc_inode = aufs_alloc_inode, ++ .destroy_inode = aufs_destroy_inode, ++ .drop_inode = generic_delete_inode, ++ .show_options = aufs_show_options, ++ .statfs = aufs_statfs, ++ .put_super = aufs_put_super, ++ .remount_fs = aufs_remount_fs ++}; ++ ++/* ---------------------------------------------------------------------- */ ++ ++static int alloc_root(struct super_block *sb) ++{ ++ int err; ++ struct inode *inode; ++ struct dentry *root; ++ ++ err = -ENOMEM; ++ inode = au_iget_locked(sb, AUFS_ROOT_INO); ++ err = PTR_ERR(inode); ++ if (IS_ERR(inode)) ++ goto out; ++ ++ inode->i_op = &aufs_dir_iop; ++ inode->i_fop = &aufs_dir_fop; ++ inode->i_mode = S_IFDIR; ++ inode->i_nlink = 2; ++ unlock_new_inode(inode); ++ ++ root = d_alloc_root(inode); ++ if (unlikely(!root)) ++ goto out_iput; ++ err = PTR_ERR(root); ++ if (IS_ERR(root)) ++ goto out_iput; ++ ++ err = au_alloc_dinfo(root); ++ if (!err) { ++ sb->s_root = root; ++ return 0; /* success */ ++ } ++ dput(root); ++ goto out; /* do not iput */ ++ ++ out_iput: ++ iget_failed(inode); ++ iput(inode); ++ out: ++ return err; ++ ++} ++ ++static int aufs_fill_super(struct super_block *sb, void *raw_data, ++ int silent __maybe_unused) ++{ ++ int err; ++ struct au_opts opts; ++ struct dentry *root; ++ struct inode *inode; ++ char *arg = raw_data; ++ ++ if (unlikely(!arg || !*arg)) { ++ err = -EINVAL; ++ AuErr("no arg\n"); ++ goto out; ++ } ++ ++ err = -ENOMEM; ++ memset(&opts, 0, sizeof(opts)); ++ opts.opt = (void *)__get_free_page(GFP_NOFS); ++ if (unlikely(!opts.opt)) ++ goto out; ++ opts.max_opt = PAGE_SIZE / sizeof(*opts.opt); ++ opts.sb_flags = sb->s_flags; ++ ++ err = au_si_alloc(sb); ++ if (unlikely(err)) ++ goto out_opts; ++ ++ /* all timestamps always follow the ones on the branch */ ++ sb->s_flags |= MS_NOATIME | MS_NODIRATIME; ++ sb->s_op = &aufs_sop; ++ sb->s_magic = AUFS_SUPER_MAGIC; ++ sb->s_maxbytes = 0; ++ au_export_init(sb); ++ ++ err = alloc_root(sb); ++ if (unlikely(err)) { ++ si_write_unlock(sb); ++ goto out_info; ++ } ++ root = sb->s_root; ++ inode = root->d_inode; ++ ++ /* ++ * actually we can parse options regardless aufs lock here. ++ * but at remount time, parsing must be done before aufs lock. ++ * so we follow the same rule. ++ */ ++ ii_write_lock_parent(inode); ++ aufs_write_unlock(root); ++ err = au_opts_parse(sb, arg, &opts); ++ if (unlikely(err)) ++ goto out_root; ++ ++ /* lock vfs_inode first, then aufs. */ ++ mutex_lock(&inode->i_mutex); ++ inode->i_op = &aufs_dir_iop; ++ inode->i_fop = &aufs_dir_fop; ++ aufs_write_lock(root); ++ err = au_opts_mount(sb, &opts); ++ au_opts_free(&opts); ++ if (unlikely(err)) ++ goto out_unlock; ++ aufs_write_unlock(root); ++ mutex_unlock(&inode->i_mutex); ++ goto out_opts; /* success */ ++ ++ out_unlock: ++ aufs_write_unlock(root); ++ mutex_unlock(&inode->i_mutex); ++ out_root: ++ dput(root); ++ sb->s_root = NULL; ++ out_info: ++ kobject_put(&au_sbi(sb)->si_kobj); ++ sb->s_fs_info = NULL; ++ out_opts: ++ free_page((unsigned long)opts.opt); ++ out: ++ AuTraceErr(err); ++ err = cvt_err(err); ++ AuTraceErr(err); ++ return err; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++static int aufs_get_sb(struct file_system_type *fs_type, int flags, ++ const char *dev_name __maybe_unused, void *raw_data, ++ struct vfsmount *mnt) ++{ ++ int err; ++ struct super_block *sb; ++ ++ /* all timestamps always follow the ones on the branch */ ++ /* mnt->mnt_flags |= MNT_NOATIME | MNT_NODIRATIME; */ ++ err = get_sb_nodev(fs_type, flags, raw_data, aufs_fill_super, mnt); ++ if (!err) { ++ sb = mnt->mnt_sb; ++ si_write_lock(sb); ++ sysaufs_brs_add(sb, 0); ++ si_write_unlock(sb); ++ } ++ return err; ++} ++ ++struct file_system_type aufs_fs_type = { ++ .name = AUFS_FSTYPE, ++ .fs_flags = ++ FS_RENAME_DOES_D_MOVE /* a race between rename and others */ ++ | FS_REVAL_DOT, /* for NFS branch and udba */ ++ .get_sb = aufs_get_sb, ++ .kill_sb = generic_shutdown_super, ++ /* no need to __module_get() and module_put(). */ ++ .owner = THIS_MODULE, ++}; +diff -urN ./fs/aufs/super.h ./fs/aufs/super.h +--- ./fs/aufs/super.h 1970-01-01 01:00:00.000000000 +0100 ++++ ./fs/aufs/super.h 2009-04-06 10:26:46.000000000 +0200 +@@ -0,0 +1,349 @@ ++/* ++ * Copyright (C) 2005-2009 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. ++ */ ++ ++/* ++ * super_block operations ++ */ ++ ++#ifndef __AUFS_SUPER_H__ ++#define __AUFS_SUPER_H__ ++ ++#ifdef __KERNEL__ ++ ++#include <linux/fs.h> ++#include <linux/kobject.h> ++#include <linux/aufs_type.h> ++#include "rwsem.h" ++#include "spl.h" ++#include "wkq.h" ++ ++typedef ssize_t (*au_readf_t)(struct file *, char __user *, size_t, loff_t *); ++typedef ssize_t (*au_writef_t)(struct file *, const char __user *, size_t, ++ loff_t *); ++ ++/* policies to select one among multiple writable branches */ ++struct au_wbr_copyup_operations { ++ int (*copyup)(struct dentry *dentry); ++}; ++ ++struct au_wbr_create_operations { ++ int (*create)(struct dentry *dentry, int isdir); ++ int (*init)(struct super_block *sb); ++ int (*fin)(struct super_block *sb); ++}; ++ ++struct au_wbr_mfs { ++ struct mutex mfs_lock; /* protect this structure */ ++ unsigned long mfs_jiffy; ++ unsigned long mfs_expire; ++ aufs_bindex_t mfs_bindex; ++ ++ unsigned long long mfsrr_bytes; ++ unsigned long long mfsrr_watermark; ++}; ++ ++/* sbinfo status flags */ ++/* ++ * set true when refresh_dirs() failed at remount time. ++ * then try refreshing dirs at access time again. ++ * if it is false, refreshing dirs at access time is unnecesary ++ */ ++#define AuSi_FAILED_REFRESH_DIRS 1 ++#define AuSi_MAINTAIN_PLINK (1 << 1) /* ioctl */ ++#define au_ftest_si(sbinfo, name) ((sbinfo)->au_si_status & AuSi_##name) ++#define au_fset_si(sbinfo, name) \ ++ { (sbinfo)->au_si_status |= AuSi_##name; } ++#define au_fclr_si(sbinfo, name) \ ++ { (sbinfo)->au_si_status &= ~AuSi_##name; } ++ ++struct au_branch; ++struct au_sbinfo { ++ /* nowait tasks in the system-wide workqueue */ ++ struct au_nowait_tasks si_nowait; ++ ++ struct rw_semaphore si_rwsem; ++ ++ /* branch management */ ++ unsigned int si_generation; ++ ++ /* see above flags */ ++ unsigned char au_si_status; ++ ++ aufs_bindex_t si_bend; ++ aufs_bindex_t si_last_br_id; ++ struct au_branch **si_branch; ++ ++ /* policy to select a writable branch */ ++ unsigned char si_wbr_copyup; ++ unsigned char si_wbr_create; ++ struct au_wbr_copyup_operations *si_wbr_copyup_ops; ++ struct au_wbr_create_operations *si_wbr_create_ops; ++ ++ /* round robin */ ++ atomic_t si_wbr_rr_next; ++ ++ /* most free space */ ++ struct au_wbr_mfs si_wbr_mfs; ++ ++ /* mount flags */ ++ /* include/asm-ia64/siginfo.h defines a macro named si_flags */ ++ unsigned int si_mntflags; ++ ++ /* external inode number (bitmap and translation table) */ ++ au_readf_t si_xread; ++ au_writef_t si_xwrite; ++ struct file *si_xib; ++ struct mutex si_xib_mtx; /* protect xib members */ ++ unsigned long *si_xib_buf; ++ unsigned long si_xib_last_pindex; ++ int si_xib_next_bit; ++ aufs_bindex_t si_xino_brid; ++ /* reserved for future use */ ++ /* unsigned long long si_xib_limit; */ /* Max xib file size */ ++ ++#ifdef CONFIG_AUFS_EXPORT ++ /* i_generation */ ++ struct file *si_xigen; ++ atomic_t si_xigen_next; ++#endif ++ ++ /* readdir cache time, max, in HZ */ ++ unsigned long si_rdcache; ++ ++ /* ++ * If the number of whiteouts are larger than si_dirwh, leave all of ++ * them after au_whtmp_ren to reduce the cost of rmdir(2). ++ * future fsck.aufs or kernel thread will remove them later. ++ * Otherwise, remove all whiteouts and the dir in rmdir(2). ++ */ ++ unsigned int si_dirwh; ++ ++ /* ++ * rename(2) a directory with all children. ++ */ ++ /* reserved for future use */ ++ /* int si_rendir; */ ++ ++ /* pseudo_link list */ ++ struct au_splhead si_plink; ++ wait_queue_head_t si_plink_wq; ++ ++ /* ++ * sysfs and lifetime management. ++ * this is not a small structure and it may be a waste of memory in case ++ * of sysfs is disabled, particulary when many aufs-es are mounted. ++ * but using sysfs is majority. ++ */ ++ struct kobject si_kobj; ++#ifdef CONFIG_DEBUG_FS ++ struct dentry *si_dbgaufs, *si_dbgaufs_xib; ++#ifdef CONFIG_AUFS_EXPORT ++ struct dentry *si_dbgaufs_xigen; ++#endif ++#endif ++ ++ /* dirty, necessary for unmounting, sysfs and sysrq */ ++ struct super_block *si_sb; ++}; ++ ++/* ---------------------------------------------------------------------- */ ++ ++/* policy to select one among writable branches */ ++#define AuWbrCopyup(sbinfo, args...) \ ++ ((sbinfo)->si_wbr_copyup_ops->copyup(args)) ++#define AuWbrCreate(sbinfo, args...) \ ++ ((sbinfo)->si_wbr_create_ops->create(args)) ++ ++/* flags for si_read_lock()/aufs_read_lock()/di_read_lock() */ ++#define AuLock_DW 1 /* write-lock dentry */ ++#define AuLock_IR (1 << 1) /* read-lock inode */ ++#define AuLock_IW (1 << 2) /* write-lock inode */ ++#define AuLock_FLUSH (1 << 3) /* wait for 'nowait' tasks */ ++#define AuLock_DIR (1 << 4) /* target is a dir */ ++#define au_ftest_lock(flags, name) ((flags) & AuLock_##name) ++#define au_fset_lock(flags, name) { (flags) |= AuLock_##name; } ++#define au_fclr_lock(flags, name) { (flags) &= ~AuLock_##name; } ++ ++/* ---------------------------------------------------------------------- */ ++ ++/* super.c */ ++extern struct file_system_type aufs_fs_type; ++struct inode *au_iget_locked(struct super_block *sb, ino_t ino); ++ ++/* sbinfo.c */ ++void au_si_free(struct kobject *kobj); ++int au_si_alloc(struct super_block *sb); ++int au_sbr_realloc(struct au_sbinfo *sbinfo, int nbr); ++ ++unsigned int au_sigen_inc(struct super_block *sb); ++aufs_bindex_t au_new_br_id(struct super_block *sb); ++ ++void aufs_read_lock(struct dentry *dentry, int flags); ++void aufs_read_unlock(struct dentry *dentry, int flags); ++void aufs_write_lock(struct dentry *dentry); ++void aufs_write_unlock(struct dentry *dentry); ++void aufs_read_and_write_lock2(struct dentry *d1, struct dentry *d2, int isdir); ++void aufs_read_and_write_unlock2(struct dentry *d1, struct dentry *d2); ++ ++/* wbr_policy.c */ ++extern struct au_wbr_copyup_operations au_wbr_copyup_ops[]; ++extern struct au_wbr_create_operations au_wbr_create_ops[]; ++int au_cpdown_dirs(struct dentry *dentry, aufs_bindex_t bdst); ++ ++/* ---------------------------------------------------------------------- */ ++ ++static inline struct au_sbinfo *au_sbi(struct super_block *sb) ++{ ++ return sb->s_fs_info; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++#ifdef CONFIG_AUFS_EXPORT ++void au_export_init(struct super_block *sb); ++ ++static inline int au_test_nfsd(struct task_struct *tsk) ++{ ++ return !tsk->mm && !strcmp(tsk->comm, "nfsd"); ++} ++ ++int au_xigen_inc(struct inode *inode); ++int au_xigen_new(struct inode *inode); ++int au_xigen_set(struct super_block *sb, struct file *base); ++void au_xigen_clr(struct super_block *sb); ++ ++static inline int au_busy_or_stale(void) ++{ ++ if (!au_test_nfsd(current)) ++ return -EBUSY; ++ return -ESTALE; ++} ++#else ++static inline void au_export_init(struct super_block *sb) ++{ ++ /* nothing */ ++} ++ ++static inline int au_test_nfsd(struct task_struct *tsk) ++{ ++ return 0; ++} ++ ++static inline int au_xigen_inc(struct inode *inode) ++{ ++ return 0; ++} ++ ++static inline int au_xigen_new(struct inode *inode) ++{ ++ return 0; ++} ++ ++static inline int au_xigen_set(struct super_block *sb, struct file *base) ++{ ++ return 0; ++} ++ ++static inline void au_xigen_clr(struct super_block *sb) ++{ ++ /* empty */ ++} ++ ++static inline int au_busy_or_stale(void) ++{ ++ return -EBUSY; ++} ++#endif /* CONFIG_AUFS_EXPORT */ ++ ++/* ---------------------------------------------------------------------- */ ++ ++static inline void dbgaufs_si_null(struct au_sbinfo *sbinfo) ++{ ++#ifdef CONFIG_DEBUG_FS ++ sbinfo->si_dbgaufs = NULL; ++ sbinfo->si_dbgaufs_xib = NULL; ++#ifdef CONFIG_AUFS_EXPORT ++ sbinfo->si_dbgaufs_xigen = NULL; ++#endif ++#endif ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++/* lock superblock. mainly for entry point functions */ ++/* ++ * si_noflush_read_lock, si_noflush_write_lock, ++ * si_read_unlock, si_write_unlock, si_downgrade_lock ++ */ ++AuSimpleLockRwsemFuncs(si_noflush, struct super_block *sb, ++ &au_sbi(sb)->si_rwsem); ++AuSimpleUnlockRwsemFuncs(si, struct super_block *sb, &au_sbi(sb)->si_rwsem); ++ ++static inline void si_read_lock(struct super_block *sb, int flags) ++{ ++ if (au_ftest_lock(flags, FLUSH)) ++ au_nwt_flush(&au_sbi(sb)->si_nowait); ++ si_noflush_read_lock(sb); ++} ++ ++static inline void si_write_lock(struct super_block *sb) ++{ ++ au_nwt_flush(&au_sbi(sb)->si_nowait); ++ si_noflush_write_lock(sb); ++} ++ ++static inline int si_read_trylock(struct super_block *sb, int flags) ++{ ++ if (au_ftest_lock(flags, FLUSH)) ++ au_nwt_flush(&au_sbi(sb)->si_nowait); ++ return si_noflush_read_trylock(sb); ++} ++ ++static inline int si_write_trylock(struct super_block *sb, int flags) ++{ ++ if (au_ftest_lock(flags, FLUSH)) ++ au_nwt_flush(&au_sbi(sb)->si_nowait); ++ return si_noflush_write_trylock(sb); ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++static inline aufs_bindex_t au_sbend(struct super_block *sb) ++{ ++ return au_sbi(sb)->si_bend; ++} ++ ++static inline unsigned int au_mntflags(struct super_block *sb) ++{ ++ return au_sbi(sb)->si_mntflags; ++} ++ ++static inline unsigned int au_sigen(struct super_block *sb) ++{ ++ return au_sbi(sb)->si_generation; ++} ++ ++static inline struct au_branch *au_sbr(struct super_block *sb, ++ aufs_bindex_t bindex) ++{ ++ return au_sbi(sb)->si_branch[0 + bindex]; ++} ++ ++static inline void au_xino_brid_set(struct super_block *sb, aufs_bindex_t brid) ++{ ++ au_sbi(sb)->si_xino_brid = brid; ++} ++ ++static inline aufs_bindex_t au_xino_brid(struct super_block *sb) ++{ ++ return au_sbi(sb)->si_xino_brid; ++} ++ ++#endif /* __KERNEL__ */ ++#endif /* __AUFS_SUPER_H__ */ +diff -urN ./fs/aufs/sysaufs.c ./fs/aufs/sysaufs.c +--- ./fs/aufs/sysaufs.c 1970-01-01 01:00:00.000000000 +0100 ++++ ./fs/aufs/sysaufs.c 2009-04-06 10:26:46.000000000 +0200 +@@ -0,0 +1,95 @@ ++/* ++ * Copyright (C) 2005-2009 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. ++ */ ++ ++/* ++ * sysfs interface and lifetime management ++ * they are necessary regardless sysfs is disabled. ++ */ ++ ++#include <linux/fs.h> ++#include <linux/random.h> ++#include <linux/sysfs.h> ++#include "aufs.h" ++ ++unsigned long sysaufs_si_mask; ++struct kset *sysaufs_ket; ++ ++#define AuSiAttr(_name) { \ ++ .attr = { .name = __stringify(_name), .mode = 0444 }, \ ++ .show = sysaufs_si_##_name, \ ++} ++ ++static struct sysaufs_si_attr sysaufs_si_attr_xi_path = AuSiAttr(xi_path); ++struct attribute *sysaufs_si_attrs[] = { ++ &sysaufs_si_attr_xi_path.attr, ++ NULL, ++}; ++ ++static struct sysfs_ops au_sbi_ops = { ++ .show = sysaufs_si_show ++}; ++ ++static struct kobj_type au_sbi_ktype = { ++ .release = au_si_free, ++ .sysfs_ops = &au_sbi_ops, ++ .default_attrs = sysaufs_si_attrs ++}; ++ ++/* ---------------------------------------------------------------------- */ ++ ++int sysaufs_si_init(struct au_sbinfo *sbinfo) ++{ ++ int err; ++ ++ sbinfo->si_kobj.kset = sysaufs_ket; ++ /* cf. sysaufs_name() */ ++ err = kobject_init_and_add ++ (&sbinfo->si_kobj, &au_sbi_ktype, /*&sysaufs_ket->kobj*/NULL, ++ SysaufsSiNamePrefix "%lx", sysaufs_si_id(sbinfo)); ++ ++ dbgaufs_si_null(sbinfo); ++ if (!err) { ++ err = dbgaufs_si_init(sbinfo); ++ if (unlikely(err)) ++ kobject_put(&sbinfo->si_kobj); ++ } ++ return err; ++} ++ ++void sysaufs_fin(void) ++{ ++ dbgaufs_fin(); ++ sysfs_remove_group(&sysaufs_ket->kobj, sysaufs_attr_group); ++ kset_unregister(sysaufs_ket); ++} ++ ++int __init sysaufs_init(void) ++{ ++ int err; ++ ++ do { ++ get_random_bytes(&sysaufs_si_mask, sizeof(sysaufs_si_mask)); ++ } while (!sysaufs_si_mask); ++ ++ sysaufs_ket = kset_create_and_add(AUFS_NAME, NULL, fs_kobj); ++ err = PTR_ERR(sysaufs_ket); ++ if (IS_ERR(sysaufs_ket)) ++ goto out; ++ err = sysfs_create_group(&sysaufs_ket->kobj, sysaufs_attr_group); ++ if (unlikely(err)) { ++ kset_unregister(sysaufs_ket); ++ goto out; ++ } ++ ++ err = dbgaufs_init(); ++ if (unlikely(err)) ++ sysaufs_fin(); ++ out: ++ return err; ++} +diff -urN ./fs/aufs/sysaufs.h ./fs/aufs/sysaufs.h +--- ./fs/aufs/sysaufs.h 1970-01-01 01:00:00.000000000 +0100 ++++ ./fs/aufs/sysaufs.h 2009-04-06 10:26:46.000000000 +0200 +@@ -0,0 +1,109 @@ ++/* ++ * Copyright (C) 2005-2009 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. ++ */ ++ ++/* ++ * sysfs interface and mount lifetime management ++ */ ++ ++#ifndef __SYSAUFS_H__ ++#define __SYSAUFS_H__ ++ ++#ifdef __KERNEL__ ++ ++#include <linux/fs.h> ++#include <linux/sysfs.h> ++#include <linux/aufs_type.h> ++#include "module.h" ++ ++struct sysaufs_si_attr { ++ struct attribute attr; ++ int (*show)(struct seq_file *seq, struct super_block *sb); ++}; ++ ++/* ---------------------------------------------------------------------- */ ++ ++/* sysaufs.c */ ++extern unsigned long sysaufs_si_mask; ++extern struct kset *sysaufs_ket; ++extern struct attribute *sysaufs_si_attrs[]; ++int sysaufs_si_init(struct au_sbinfo *sbinfo); ++int __init sysaufs_init(void); ++void sysaufs_fin(void); ++ ++/* ---------------------------------------------------------------------- */ ++ ++/* some people doesn't like to show a pointer in kernel */ ++static inline unsigned long sysaufs_si_id(struct au_sbinfo *sbinfo) ++{ ++ return sysaufs_si_mask ^ (unsigned long)sbinfo; ++} ++ ++#define SysaufsSiNamePrefix "si_" ++#define SysaufsSiNameLen (sizeof(SysaufsSiNamePrefix) + 16) ++static inline void sysaufs_name(struct au_sbinfo *sbinfo, char *name) ++{ ++ snprintf(name, SysaufsSiNameLen, SysaufsSiNamePrefix "%lx", ++ sysaufs_si_id(sbinfo)); ++} ++ ++struct au_branch; ++#ifdef CONFIG_SYSFS ++/* sysfs.c */ ++extern struct attribute_group *sysaufs_attr_group; ++ ++int sysaufs_si_xi_path(struct seq_file *seq, struct super_block *sb); ++ssize_t sysaufs_si_show(struct kobject *kobj, struct attribute *attr, ++ char *buf); ++ ++void sysaufs_br_init(struct au_branch *br); ++void sysaufs_brs_add(struct super_block *sb, aufs_bindex_t bindex); ++void sysaufs_brs_del(struct super_block *sb, aufs_bindex_t bindex); ++ ++#define sysaufs_brs_init() do {} while (0) ++ ++#else ++#define sysaufs_attr_group NULL ++ ++static inline ++int sysaufs_si_xi_path(struct seq_file *seq, struct super_block *sb) ++{ ++ return 0; ++} ++ ++static inline ++ssize_t sysaufs_si_show(struct kobject *kobj, struct attribute *attr, ++ char *buf) ++{ ++ return 0; ++} ++ ++static inline void sysaufs_br_init(struct au_branch *br) ++{ ++ /* empty */ ++} ++ ++static inline void sysaufs_brs_add(struct super_block *sb, aufs_bindex_t bindex) ++{ ++ /* nothing */ ++} ++ ++static inline void sysaufs_brs_del(struct super_block *sb, aufs_bindex_t bindex) ++{ ++ /* nothing */ ++} ++ ++static inline void sysaufs_brs_init(void) ++{ ++ sysaufs_brs = 0; ++} ++ ++#endif /* CONFIG_SYSFS */ ++ ++#endif /* __KERNEL__ */ ++#endif /* __SYSAUFS_H__ */ +diff -urN ./fs/aufs/sysfs.c ./fs/aufs/sysfs.c +--- ./fs/aufs/sysfs.c 1970-01-01 01:00:00.000000000 +0100 ++++ ./fs/aufs/sysfs.c 2009-04-06 10:26:46.000000000 +0200 +@@ -0,0 +1,198 @@ ++/* ++ * Copyright (C) 2005-2009 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. ++ */ ++ ++/* ++ * sysfs interface ++ */ ++ ++#include <linux/fs.h> ++#include <linux/seq_file.h> ++#include <linux/sysfs.h> ++#include "aufs.h" ++ ++static struct attribute *au_attr[] = { ++ NULL, /* need to NULL terminate the list of attributes */ ++}; ++ ++static struct attribute_group sysaufs_attr_group_body = { ++ .attrs = au_attr ++}; ++ ++struct attribute_group *sysaufs_attr_group = &sysaufs_attr_group_body; ++ ++/* ---------------------------------------------------------------------- */ ++ ++int sysaufs_si_xi_path(struct seq_file *seq, struct super_block *sb) ++{ ++ int err; ++ ++ err = 0; ++ if (au_opt_test(au_mntflags(sb), XINO)) { ++ err = au_xino_path(seq, au_sbi(sb)->si_xib); ++ seq_putc(seq, '\n'); ++ } ++ return err; ++} ++ ++/* ++ * the lifetime of branch is independent from the entry under sysfs. ++ * sysfs handles the lifetime of the entry, and never call ->show() after it is ++ * unlinked. ++ */ ++static int sysaufs_si_br(struct seq_file *seq, struct super_block *sb, ++ aufs_bindex_t bindex) ++{ ++ struct path path; ++ struct dentry *root; ++ struct au_branch *br; ++ ++ AuDbg("b%d\n", bindex); ++ ++ root = sb->s_root; ++ di_read_lock_parent(root, !AuLock_IR); ++ br = au_sbr(sb, bindex); ++ path.mnt = br->br_mnt; ++ path.dentry = au_h_dptr(root, bindex); ++ au_seq_path(seq, &path); ++ di_read_unlock(root, !AuLock_IR); ++ seq_printf(seq, "=%s\n", au_optstr_br_perm(br->br_perm)); ++ return 0; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++static struct seq_file *au_seq(char *p, ssize_t len) ++{ ++ struct seq_file *seq; ++ ++ seq = kzalloc(sizeof(*seq), GFP_NOFS); ++ if (seq) { ++ /* mutex_init(&seq.lock); */ ++ seq->buf = p; ++ seq->size = len; ++ return seq; /* success */ ++ } ++ ++ seq = ERR_PTR(-ENOMEM); ++ return seq; ++} ++ ++#define SysaufsBr_PREFIX "br" ++ ++/* todo: file size may exceed PAGE_SIZE */ ++ssize_t sysaufs_si_show(struct kobject *kobj, struct attribute *attr, ++ char *buf) ++{ ++ ssize_t err; ++ long l; ++ aufs_bindex_t bend; ++ struct au_sbinfo *sbinfo; ++ struct super_block *sb; ++ struct seq_file *seq; ++ char *name; ++ struct attribute **cattr; ++ ++ sbinfo = container_of(kobj, struct au_sbinfo, si_kobj); ++ sb = sbinfo->si_sb; ++ si_noflush_read_lock(sb); ++ ++ seq = au_seq(buf, PAGE_SIZE); ++ err = PTR_ERR(seq); ++ if (IS_ERR(seq)) ++ goto out; ++ ++ name = (void *)attr->name; ++ cattr = sysaufs_si_attrs; ++ while (*cattr) { ++ if (!strcmp(name, (*cattr)->name)) { ++ err = container_of(*cattr, struct sysaufs_si_attr, attr) ++ ->show(seq, sb); ++ goto out_seq; ++ } ++ cattr++; ++ } ++ ++ bend = au_sbend(sb); ++ if (!strncmp(name, SysaufsBr_PREFIX, sizeof(SysaufsBr_PREFIX) - 1)) { ++ name += sizeof(SysaufsBr_PREFIX) - 1; ++ err = strict_strtol(name, 10, &l); ++ if (!err) { ++ if (l <= bend) ++ err = sysaufs_si_br(seq, sb, (aufs_bindex_t)l); ++ else ++ err = -ENOENT; ++ } ++ goto out_seq; ++ } ++ BUG(); ++ ++ out_seq: ++ if (!err) { ++ err = seq->count; ++ /* sysfs limit */ ++ if (unlikely(err == PAGE_SIZE)) ++ err = -EFBIG; ++ } ++ kfree(seq); ++ out: ++ si_read_unlock(sb); ++ return err; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++void sysaufs_br_init(struct au_branch *br) ++{ ++ br->br_attr.name = br->br_name; ++ br->br_attr.mode = S_IRUGO; ++ br->br_attr.owner = THIS_MODULE; ++} ++ ++void sysaufs_brs_del(struct super_block *sb, aufs_bindex_t bindex) ++{ ++ struct au_branch *br; ++ struct kobject *kobj; ++ aufs_bindex_t bend; ++ ++ dbgaufs_brs_del(sb, bindex); ++ ++ if (!sysaufs_brs) ++ return; ++ ++ kobj = &au_sbi(sb)->si_kobj; ++ bend = au_sbend(sb); ++ for (; bindex <= bend; bindex++) { ++ br = au_sbr(sb, bindex); ++ sysfs_remove_file(kobj, &br->br_attr); ++ } ++} ++ ++void sysaufs_brs_add(struct super_block *sb, aufs_bindex_t bindex) ++{ ++ int err; ++ aufs_bindex_t bend; ++ struct kobject *kobj; ++ struct au_branch *br; ++ ++ dbgaufs_brs_add(sb, bindex); ++ ++ if (!sysaufs_brs) ++ return; ++ ++ kobj = &au_sbi(sb)->si_kobj; ++ bend = au_sbend(sb); ++ for (; bindex <= bend; bindex++) { ++ br = au_sbr(sb, bindex); ++ snprintf(br->br_name, sizeof(br->br_name), SysaufsBr_PREFIX ++ "%d", bindex); ++ err = sysfs_create_file(kobj, &br->br_attr); ++ if (unlikely(err)) ++ AuWarn("failed %s under sysfs(%d)\n", br->br_name, err); ++ } ++} +diff -urN ./fs/aufs/sysrq.c ./fs/aufs/sysrq.c +--- ./fs/aufs/sysrq.c 1970-01-01 01:00:00.000000000 +0100 ++++ ./fs/aufs/sysrq.c 2009-04-06 10:26:46.000000000 +0200 +@@ -0,0 +1,106 @@ ++/* ++ * Copyright (C) 2005-2009 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. ++ */ ++ ++/* ++ * magic sysrq hanlder ++ */ ++ ++#include <linux/fs.h> ++#include <linux/module.h> ++#include <linux/moduleparam.h> ++/* #include <linux/sysrq.h> */ ++#include "aufs.h" ++ ++/* ---------------------------------------------------------------------- */ ++ ++static void sysrq_sb(struct super_block *sb) ++{ ++ char *plevel; ++ struct au_sbinfo *sbinfo; ++ struct file *file; ++ ++ plevel = au_plevel; ++ au_plevel = KERN_WARNING; ++ au_debug(1); ++ ++ sbinfo = au_sbi(sb); ++ pr_warning("si=%lx\n", sysaufs_si_id(sbinfo)); ++ pr_warning(AUFS_NAME ": superblock\n"); ++ au_dpri_sb(sb); ++ pr_warning(AUFS_NAME ": root dentry\n"); ++ au_dpri_dentry(sb->s_root); ++ pr_warning(AUFS_NAME ": root inode\n"); ++ au_dpri_inode(sb->s_root->d_inode); ++#if 0 ++ struct inode *i; ++ pr_warning(AUFS_NAME ": isolated inode\n"); ++ list_for_each_entry(i, &sb->s_inodes, i_sb_list) ++ if (list_empty(&i->i_dentry)) ++ au_dpri_inode(i); ++#endif ++ pr_warning(AUFS_NAME ": files\n"); ++ list_for_each_entry(file, &sb->s_files, f_u.fu_list) ++ if (!special_file(file->f_dentry->d_inode->i_mode)) ++ au_dpri_file(file); ++ ++ au_plevel = plevel; ++ au_debug(0); ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++/* module parameter */ ++static char *aufs_sysrq_key = "a"; ++module_param_named(sysrq, aufs_sysrq_key, charp, S_IRUGO); ++MODULE_PARM_DESC(sysrq, "MagicSysRq key for " AUFS_NAME); ++ ++static void au_sysrq(int key __maybe_unused, ++ struct tty_struct *tty __maybe_unused) ++{ ++ struct kobject *kobj; ++ struct au_sbinfo *sbinfo; ++ ++ /* spin_lock(&sysaufs_ket->list_lock); */ ++ list_for_each_entry(kobj, &sysaufs_ket->list, entry) { ++ sbinfo = container_of(kobj, struct au_sbinfo, si_kobj); ++ sysrq_sb(sbinfo->si_sb); ++ } ++ /* spin_unlock(&sysaufs_ket->list_lock); */ ++} ++ ++static struct sysrq_key_op au_sysrq_op = { ++ .handler = au_sysrq, ++ .help_msg = "Aufs", ++ .action_msg = "Aufs", ++ .enable_mask = SYSRQ_ENABLE_DUMP ++}; ++ ++/* ---------------------------------------------------------------------- */ ++ ++int __init au_sysrq_init(void) ++{ ++ int err; ++ char key; ++ ++ err = -1; ++ key = *aufs_sysrq_key; ++ if ('a' <= key && key <= 'z') ++ err = register_sysrq_key(key, &au_sysrq_op); ++ if (unlikely(err)) ++ AuErr("err %d, sysrq=%c\n", err, key); ++ return err; ++} ++ ++void au_sysrq_fin(void) ++{ ++ int err; ++ err = unregister_sysrq_key(*aufs_sysrq_key, &au_sysrq_op); ++ if (unlikely(err)) ++ AuErr("err %d (ignored)\n", err); ++} +diff -urN ./fs/aufs/vdir.c ./fs/aufs/vdir.c +--- ./fs/aufs/vdir.c 1970-01-01 01:00:00.000000000 +0100 ++++ ./fs/aufs/vdir.c 2009-04-06 10:26:46.000000000 +0200 +@@ -0,0 +1,776 @@ ++/* ++ * Copyright (C) 2005-2009 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. ++ */ ++ ++/* ++ * virtual or vertical directory ++ */ ++ ++#include "aufs.h" ++ ++static int calc_size(int namelen) ++{ ++ int sz; ++ const int mask = sizeof(ino_t) - 1; ++ ++ BUILD_BUG_ON(sizeof(ino_t) != sizeof(long)); ++ ++ sz = sizeof(struct au_vdir_de) + namelen; ++ if (sz & mask) { ++ sz += sizeof(ino_t); ++ sz &= ~mask; ++ } ++ ++ AuDebugOn(sz % sizeof(ino_t)); ++ return sz; ++} ++ ++static int set_deblk_end(union au_vdir_deblk_p *p, ++ union au_vdir_deblk_p *deblk_end) ++{ ++ if (calc_size(0) <= deblk_end->p - p->p) { ++ p->de->de_str.len = 0; ++ /* smp_mb(); */ ++ return 0; ++ } ++ return -1; /* error */ ++} ++ ++/* returns true or false */ ++static int is_deblk_end(union au_vdir_deblk_p *p, ++ union au_vdir_deblk_p *deblk_end) ++{ ++ if (calc_size(0) <= deblk_end->p - p->p) ++ return !p->de->de_str.len; ++ return 1; ++} ++ ++static au_vdir_deblk_t *last_deblk(struct au_vdir *vdir) ++{ ++ return vdir->vd_deblk[vdir->vd_nblk - 1]; ++} ++ ++void au_nhash_init(struct au_nhash *nhash) ++{ ++ int i; ++ struct hlist_head *heads; ++ ++ heads = nhash->heads; ++ for (i = 0; i < AuSize_NHASH; i++) ++ INIT_HLIST_HEAD(heads++); ++} ++ ++struct au_nhash *au_nhash_new(gfp_t gfp) ++{ ++ struct au_nhash *nhash; ++ ++ nhash = kmalloc(sizeof(*nhash), gfp); ++ if (nhash) { ++ au_nhash_init(nhash); ++ return nhash; ++ } ++ return ERR_PTR(-ENOMEM); ++} ++ ++void au_nhash_del(struct au_nhash *nhash) ++{ ++ au_nhash_fin(nhash); ++ kfree(nhash); ++} ++ ++void au_nhash_move(struct au_nhash *dst, struct au_nhash *src) ++{ ++ int i; ++ struct hlist_head *dsth, *srch; ++ ++ *dst = *src; ++ srch = src->heads; ++ dsth = dst->heads; ++ for (i = 0; i < AuSize_NHASH; i++) { ++ if (dsth->first) ++ dsth->first->pprev = &dsth->first; ++ dsth++; ++ INIT_HLIST_HEAD(srch++); ++ } ++ /* smp_mb(); */ ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++void au_nhash_fin(struct au_nhash *whlist) ++{ ++ int i; ++ struct hlist_head *head; ++ struct au_vdir_wh *tpos; ++ struct hlist_node *pos, *n; ++ ++ head = whlist->heads; ++ for (i = 0; i < AuSize_NHASH; i++) { ++ hlist_for_each_entry_safe(tpos, pos, n, head, wh_hash) { ++ /* hlist_del(pos); */ ++ kfree(tpos); ++ } ++ head++; ++ } ++} ++ ++int au_nhash_test_longer_wh(struct au_nhash *whlist, aufs_bindex_t btgt, ++ int limit) ++{ ++ int n, i; ++ struct hlist_head *head; ++ struct au_vdir_wh *tpos; ++ struct hlist_node *pos; ++ ++ n = 0; ++ head = whlist->heads; ++ for (i = 0; i < AuSize_NHASH; i++) { ++ hlist_for_each_entry(tpos, pos, head, wh_hash) ++ if (tpos->wh_bindex == btgt && ++n > limit) ++ return 1; ++ head++; ++ } ++ return 0; ++} ++ ++static unsigned int au_name_hash(const unsigned char *name, unsigned int len) ++{ ++ return full_name_hash(name, len) % AuSize_NHASH; ++} ++ ++/* returns found or not */ ++int au_nhash_test_known_wh(struct au_nhash *whlist, char *name, int namelen) ++{ ++ struct hlist_head *head; ++ struct au_vdir_wh *tpos; ++ struct hlist_node *pos; ++ struct au_vdir_destr *str; ++ ++ head = whlist->heads + au_name_hash(name, namelen); ++ hlist_for_each_entry(tpos, pos, head, wh_hash) { ++ str = &tpos->wh_str; ++ AuDbg("%.*s\n", str->len, str->name); ++ if (str->len == namelen && !memcmp(str->name, name, namelen)) ++ return 1; ++ } ++ return 0; ++} ++ ++int au_nhash_append_wh(struct au_nhash *whlist, char *name, int namelen, ++ aufs_bindex_t bindex) ++{ ++ int err; ++ struct au_vdir_destr *str; ++ struct au_vdir_wh *wh; ++ ++ err = -ENOMEM; ++ wh = kmalloc(sizeof(*wh) + namelen, GFP_NOFS); ++ if (unlikely(!wh)) ++ goto out; ++ ++ err = 0; ++ wh->wh_bindex = bindex; ++ str = &wh->wh_str; ++ str->len = namelen; ++ memcpy(str->name, name, namelen); ++ hlist_add_head(&wh->wh_hash, ++ whlist->heads + au_name_hash(name, namelen)); ++ /* smp_mb(); */ ++ ++ out: ++ return err; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++void au_vdir_free(struct au_vdir *vdir) ++{ ++ au_vdir_deblk_t **deblk; ++ ++ deblk = vdir->vd_deblk; ++ while (vdir->vd_nblk--) ++ kfree(*deblk++); ++ kfree(vdir->vd_deblk); ++ au_cache_free_vdir(vdir); ++} ++ ++static int append_deblk(struct au_vdir *vdir) ++{ ++ int err, sz, i; ++ au_vdir_deblk_t **o; ++ union au_vdir_deblk_p p, deblk_end; ++ ++ err = -ENOMEM; ++ sz = sizeof(*o) * vdir->vd_nblk; ++ o = au_kzrealloc(vdir->vd_deblk, sz, sz + sizeof(*o), GFP_NOFS); ++ if (unlikely(!o)) ++ goto out; ++ ++ vdir->vd_deblk = o; ++ p.deblk = kmalloc(sizeof(*p.deblk), GFP_NOFS); ++ if (p.deblk) { ++ i = vdir->vd_nblk++; ++ vdir->vd_deblk[i] = p.deblk; ++ vdir->vd_last.i = i; ++ vdir->vd_last.p.p = p.p; ++ deblk_end.deblk = p.deblk + 1; ++ err = set_deblk_end(&p, &deblk_end); ++ } ++ ++ out: ++ return err; ++} ++ ++static struct au_vdir *alloc_vdir(void) ++{ ++ struct au_vdir *vdir; ++ int err; ++ ++ err = -ENOMEM; ++ vdir = au_cache_alloc_vdir(); ++ if (unlikely(!vdir)) ++ goto out; ++ ++ vdir->vd_deblk = kzalloc(sizeof(*vdir->vd_deblk), GFP_NOFS); ++ if (unlikely(!vdir->vd_deblk)) ++ goto out_free; ++ ++ vdir->vd_nblk = 0; ++ vdir->vd_version = 0; ++ vdir->vd_jiffy = 0; ++ err = append_deblk(vdir); ++ if (!err) ++ return vdir; /* success */ ++ ++ kfree(vdir->vd_deblk); ++ ++ out_free: ++ au_cache_free_vdir(vdir); ++ out: ++ vdir = ERR_PTR(err); ++ return vdir; ++} ++ ++static int reinit_vdir(struct au_vdir *vdir) ++{ ++ int err; ++ union au_vdir_deblk_p p, deblk_end; ++ ++ while (vdir->vd_nblk > 1) { ++ kfree(vdir->vd_deblk[vdir->vd_nblk - 1]); ++ vdir->vd_deblk[vdir->vd_nblk - 1] = NULL; ++ vdir->vd_nblk--; ++ } ++ p.deblk = vdir->vd_deblk[0]; ++ deblk_end.deblk = p.deblk + 1; ++ err = set_deblk_end(&p, &deblk_end); ++ vdir->vd_version = 0; ++ vdir->vd_jiffy = 0; ++ vdir->vd_last.i = 0; ++ vdir->vd_last.p.deblk = vdir->vd_deblk[0]; ++ /* smp_mb(); */ ++ return err; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++static void free_dehlist(struct au_nhash *dehlist) ++{ ++ int i; ++ struct hlist_head *head; ++ struct au_vdir_dehstr *tpos; ++ struct hlist_node *pos, *n; ++ ++ head = dehlist->heads; ++ for (i = 0; i < AuSize_NHASH; i++) { ++ hlist_for_each_entry_safe(tpos, pos, n, head, hash) { ++ /* hlist_del(pos); */ ++ au_cache_free_dehstr(tpos); ++ } ++ head++; ++ } ++} ++ ++/* returns found(true) or not */ ++static int test_known(struct au_nhash *delist, char *name, int namelen) ++{ ++ struct hlist_head *head; ++ struct au_vdir_dehstr *tpos; ++ struct hlist_node *pos; ++ struct au_vdir_destr *str; ++ ++ head = delist->heads + au_name_hash(name, namelen); ++ hlist_for_each_entry(tpos, pos, head, hash) { ++ str = tpos->str; ++ AuDbg("%.*s\n", str->len, str->name); ++ if (str->len == namelen && !memcmp(str->name, name, namelen)) ++ return 1; ++ } ++ return 0; ++ ++} ++ ++static int append_de(struct au_vdir *vdir, char *name, int namelen, ino_t ino, ++ unsigned int d_type, struct au_nhash *delist) ++{ ++ int err, sz; ++ union au_vdir_deblk_p p, *room, deblk_end; ++ struct au_vdir_dehstr *dehstr; ++ ++ p.deblk = last_deblk(vdir); ++ deblk_end.deblk = p.deblk + 1; ++ room = &vdir->vd_last.p; ++ AuDebugOn(room->p < p.p || deblk_end.p <= room->p ++ || !is_deblk_end(room, &deblk_end)); ++ ++ sz = calc_size(namelen); ++ if (unlikely(sz > deblk_end.p - room->p)) { ++ err = append_deblk(vdir); ++ if (unlikely(err)) ++ goto out; ++ ++ p.deblk = last_deblk(vdir); ++ deblk_end.deblk = p.deblk + 1; ++ /* smp_mb(); */ ++ AuDebugOn(room->p != p.p); ++ } ++ ++ err = -ENOMEM; ++ dehstr = au_cache_alloc_dehstr(); ++ if (unlikely(!dehstr)) ++ goto out; ++ ++ dehstr->str = &room->de->de_str; ++ hlist_add_head(&dehstr->hash, ++ delist->heads + au_name_hash(name, namelen)); ++ room->de->de_ino = ino; ++ room->de->de_type = d_type; ++ room->de->de_str.len = namelen; ++ memcpy(room->de->de_str.name, name, namelen); ++ ++ err = 0; ++ room->p += sz; ++ if (unlikely(set_deblk_end(room, &deblk_end))) ++ err = append_deblk(vdir); ++ /* smp_mb(); */ ++ ++ out: ++ return err; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++static int au_ino(struct super_block *sb, aufs_bindex_t bindex, ino_t h_ino, ++ unsigned int d_type, ino_t *ino) ++{ ++ int err; ++ struct mutex *mtx; ++ const int isdir = (d_type == DT_DIR); ++ ++ /* prevent hardlinks from race condition */ ++ mtx = NULL; ++ if (!isdir) { ++ 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; ++ ++ if (!*ino) { ++ err = -EIO; ++ *ino = au_xino_new_ino(sb); ++ if (unlikely(!*ino)) ++ goto out; ++ err = au_xino_write(sb, bindex, h_ino, *ino); ++ if (unlikely(err)) ++ goto out; ++ } ++ ++ out: ++ if (!isdir) ++ mutex_unlock(mtx); ++ return err; ++} ++ ++#define AuFillVdir_CALLED 1 ++#define au_ftest_fillvdir(flags, name) ((flags) & AuFillVdir_##name) ++#define au_fset_fillvdir(flags, name) { (flags) |= AuFillVdir_##name; } ++#define au_fclr_fillvdir(flags, name) { (flags) &= ~AuFillVdir_##name; } ++ ++struct fillvdir_arg { ++ struct file *file; ++ struct au_vdir *vdir; ++ struct au_nhash *delist; ++ struct au_nhash *whlist; ++ aufs_bindex_t bindex; ++ unsigned int flags; ++ int err; ++}; ++ ++static int fillvdir(void *__arg, const char *__name, int namelen, ++ loff_t offset __maybe_unused, u64 h_ino, ++ unsigned int d_type) ++{ ++ struct fillvdir_arg *arg = __arg; ++ char *name = (void *)__name; ++ struct super_block *sb; ++ struct au_nhash *delist, *whlist; ++ ino_t ino; ++ aufs_bindex_t bindex, bend; ++ ++ bend = arg->bindex; ++ arg->err = 0; ++ au_fset_fillvdir(arg->flags, CALLED); ++ /* smp_mb(); */ ++ if (namelen <= AUFS_WH_PFX_LEN ++ || memcmp(name, AUFS_WH_PFX, AUFS_WH_PFX_LEN)) { ++ delist = arg->delist; ++ for (bindex = 0; bindex < bend; bindex++) ++ if (test_known(delist++, name, namelen) ++ || au_nhash_test_known_wh(arg->whlist + bindex, ++ name, namelen)) ++ goto out; /* already exists or whiteouted */ ++ ++ ino = 1; /* why does gcc warn? */ ++ sb = arg->file->f_dentry->d_sb; ++ arg->err = au_ino(sb, bend, h_ino, d_type, &ino); ++ if (!arg->err) ++ arg->err = append_de(arg->vdir, name, namelen, ino, ++ d_type, arg->delist + bend); ++ } else { ++ name += AUFS_WH_PFX_LEN; ++ namelen -= AUFS_WH_PFX_LEN; ++ whlist = arg->whlist; ++ for (bindex = 0; bindex < bend; bindex++) ++ if (au_nhash_test_known_wh(whlist++, name, namelen)) ++ goto out; /* already whiteouted */ ++ ++ ino = 1; /* dummy */ ++ if (!arg->err) ++ arg->err = au_nhash_append_wh ++ (arg->whlist + bend, name, namelen, bend); ++ } ++ ++ out: ++ if (!arg->err) ++ arg->vdir->vd_jiffy = jiffies; ++ /* smp_mb(); */ ++ AuTraceErr(arg->err); ++ return arg->err; ++} ++ ++static int au_do_read_vdir(struct fillvdir_arg *arg) ++{ ++ int err; ++ loff_t offset; ++ aufs_bindex_t bend, bindex, bstart; ++ struct file *hf, *file; ++ struct au_nhash *delist, *whlist; ++ ++ err = -ENOMEM; ++ bend = au_fbend(arg->file); ++ arg->delist = kmalloc(sizeof(*arg->delist) * (bend + 1), GFP_NOFS); ++ if (unlikely(!arg->delist)) ++ goto out; ++ arg->whlist = kmalloc(sizeof(*arg->whlist) * (bend + 1), GFP_NOFS); ++ if (unlikely(!arg->whlist)) ++ goto out_delist; ++ ++ err = 0; ++ delist = arg->delist; ++ whlist = arg->whlist; ++ for (bindex = 0; bindex <= bend; bindex++) { ++ au_nhash_init(delist++); ++ au_nhash_init(whlist++); ++ } ++ ++ arg->flags = 0; ++ file = arg->file; ++ bstart = au_fbstart(file); ++ for (bindex = bstart; !err && bindex <= bend; bindex++) { ++ hf = au_h_fptr(file, bindex); ++ if (!hf) ++ continue; ++ ++ offset = vfsub_llseek(hf, 0, SEEK_SET); ++ err = offset; ++ if (unlikely(offset)) ++ break; ++ ++ arg->bindex = bindex; ++ do { ++ arg->err = 0; ++ au_fclr_fillvdir(arg->flags, CALLED); ++ /* smp_mb(); */ ++ err = vfsub_readdir(hf, fillvdir, arg); ++ if (err >= 0) ++ err = arg->err; ++ } while (!err && au_ftest_fillvdir(arg->flags, CALLED)); ++ } ++ ++ delist = arg->delist + bstart; ++ whlist = arg->whlist + bstart; ++ for (bindex = bstart; bindex <= bend; bindex++) { ++ free_dehlist(delist++); ++ au_nhash_fin(whlist++); ++ } ++ kfree(arg->whlist); ++ ++ out_delist: ++ kfree(arg->delist); ++ out: ++ return err; ++} ++ ++static int read_vdir(struct file *file, int may_read) ++{ ++ int err; ++ unsigned long expire; ++ unsigned char do_read; ++ struct fillvdir_arg arg; ++ struct inode *inode; ++ struct au_vdir *vdir, *allocated; ++ ++ err = 0; ++ inode = file->f_dentry->d_inode; ++ IMustLock(inode); ++ allocated = NULL; ++ do_read = 0; ++ expire = au_sbi(inode->i_sb)->si_rdcache; ++ vdir = au_ivdir(inode); ++ if (!vdir) { ++ do_read = 1; ++ vdir = alloc_vdir(); ++ err = PTR_ERR(vdir); ++ if (IS_ERR(vdir)) ++ goto out; ++ err = 0; ++ allocated = vdir; ++ } else if (may_read ++ && (inode->i_version != vdir->vd_version ++ || time_after(jiffies, vdir->vd_jiffy + expire))) { ++ do_read = 1; ++ err = reinit_vdir(vdir); ++ if (unlikely(err)) ++ goto out; ++ } ++ ++ if (!do_read) ++ return 0; /* success */ ++ ++ arg.file = file; ++ arg.vdir = vdir; ++ err = au_do_read_vdir(&arg); ++ if (!err) { ++ /* file->f_pos = 0; */ ++ vdir->vd_version = inode->i_version; ++ vdir->vd_last.i = 0; ++ vdir->vd_last.p.deblk = vdir->vd_deblk[0]; ++ if (allocated) ++ au_set_ivdir(inode, allocated); ++ } else if (allocated) ++ au_vdir_free(allocated); ++ ++ out: ++ return err; ++} ++ ++static int copy_vdir(struct au_vdir *tgt, struct au_vdir *src) ++{ ++ int err, i, rerr, n; ++ ++ AuDebugOn(tgt->vd_nblk != 1); ++ ++ err = -ENOMEM; ++ if (tgt->vd_nblk < src->vd_nblk) { ++ au_vdir_deblk_t **p; ++ ++ p = au_kzrealloc(tgt->vd_deblk, sizeof(*p) * tgt->vd_nblk, ++ sizeof(*p) * src->vd_nblk, GFP_NOFS); ++ if (unlikely(!p)) ++ goto out; ++ tgt->vd_deblk = p; ++ } ++ ++ tgt->vd_nblk = src->vd_nblk; ++ n = src->vd_nblk; ++ memcpy(tgt->vd_deblk[0], src->vd_deblk[0], AuSize_DEBLK); ++ /* tgt->vd_last.i = 0; */ ++ /* tgt->vd_last.p.deblk = tgt->vd_deblk[0]; */ ++ tgt->vd_version = src->vd_version; ++ tgt->vd_jiffy = src->vd_jiffy; ++ ++ for (i = 1; i < n; i++) { ++ tgt->vd_deblk[i] = kmalloc(AuSize_DEBLK, GFP_NOFS); ++ if (tgt->vd_deblk[i]) ++ memcpy(tgt->vd_deblk[i], src->vd_deblk[i], ++ AuSize_DEBLK); ++ else ++ goto out; ++ } ++ /* smp_mb(); */ ++ return 0; /* success */ ++ ++ out: ++ rerr = reinit_vdir(tgt); ++ BUG_ON(rerr); ++ return err; ++} ++ ++int au_vdir_init(struct file *file) ++{ ++ int err; ++ struct inode *inode; ++ struct au_vdir *vdir_cache, *allocated; ++ ++ err = read_vdir(file, !file->f_pos); ++ if (unlikely(err)) ++ goto out; ++ ++ allocated = NULL; ++ vdir_cache = au_fvdir_cache(file); ++ if (!vdir_cache) { ++ vdir_cache = alloc_vdir(); ++ err = PTR_ERR(vdir_cache); ++ if (IS_ERR(vdir_cache)) ++ goto out; ++ allocated = vdir_cache; ++ } else if (!file->f_pos && vdir_cache->vd_version != file->f_version) { ++ err = reinit_vdir(vdir_cache); ++ if (unlikely(err)) ++ goto out; ++ } else ++ return 0; /* success */ ++ ++ inode = file->f_dentry->d_inode; ++ err = copy_vdir(vdir_cache, au_ivdir(inode)); ++ if (!err) { ++ file->f_version = inode->i_version; ++ if (allocated) ++ au_set_fvdir_cache(file, allocated); ++ } else if (allocated) ++ au_vdir_free(allocated); ++ ++ out: ++ return err; ++} ++ ++static loff_t calc_offset(struct au_vdir *vdir) ++{ ++ loff_t offset; ++ union au_vdir_deblk_p p; ++ ++ p.deblk = vdir->vd_deblk[vdir->vd_last.i]; ++ offset = vdir->vd_last.p.p - p.p; ++ offset += sizeof(*p.deblk) * vdir->vd_last.i; ++ return offset; ++} ++ ++/* returns true or false */ ++static int seek_vdir(struct file *file) ++{ ++ int valid, i, n; ++ loff_t offset; ++ union au_vdir_deblk_p p, deblk_end; ++ struct au_vdir *vdir_cache; ++ ++ valid = 1; ++ vdir_cache = au_fvdir_cache(file); ++ offset = calc_offset(vdir_cache); ++ AuDbg("offset %lld\n", offset); ++ if (file->f_pos == offset) ++ goto out; ++ ++ vdir_cache->vd_last.i = 0; ++ vdir_cache->vd_last.p.deblk = vdir_cache->vd_deblk[0]; ++ if (!file->f_pos) ++ goto out; ++ ++ valid = 0; ++ i = file->f_pos / AuSize_DEBLK; ++ AuDbg("i %d\n", i); ++ if (i >= vdir_cache->vd_nblk) ++ goto out; ++ ++ n = vdir_cache->vd_nblk; ++ for (; i < n; i++) { ++ p.deblk = vdir_cache->vd_deblk[i]; ++ deblk_end.deblk = p.deblk + 1; ++ offset = i; ++ offset *= AuSize_DEBLK; ++ while (!is_deblk_end(&p, &deblk_end) && offset < file->f_pos) { ++ int l; ++ ++ l = calc_size(p.de->de_str.len); ++ offset += l; ++ p.p += l; ++ } ++ if (!is_deblk_end(&p, &deblk_end)) { ++ valid = 1; ++ vdir_cache->vd_last.i = i; ++ vdir_cache->vd_last.p = p; ++ break; ++ } ++ } ++ ++ out: ++ /* smp_mb(); */ ++ AuTraceErr(!valid); ++ return valid; ++} ++ ++int au_vdir_fill_de(struct file *file, void *dirent, filldir_t filldir) ++{ ++ int err, l; ++ union au_vdir_deblk_p deblk_end; ++ struct au_vdir *vdir_cache; ++ struct au_vdir_de *de; ++ ++ BUILD_BUG_ON(AuSize_DEBLK < NAME_MAX || PAGE_SIZE < AuSize_DEBLK); ++ ++ vdir_cache = au_fvdir_cache(file); ++ if (!seek_vdir(file)) ++ return 0; ++ ++ while (1) { ++ deblk_end.deblk ++ = vdir_cache->vd_deblk[vdir_cache->vd_last.i] + 1; ++ while (!is_deblk_end(&vdir_cache->vd_last.p, &deblk_end)) { ++ de = vdir_cache->vd_last.p.de; ++ AuDbg("%.*s, off%lld, i%lu, dt%d\n", ++ de->de_str.len, de->de_str.name, ++ file->f_pos, (unsigned long)de->de_ino, ++ de->de_type); ++ err = filldir(dirent, de->de_str.name, de->de_str.len, ++ file->f_pos, de->de_ino, de->de_type); ++ if (unlikely(err)) { ++ AuTraceErr(err); ++ /* todo: ignore the error caused by udba? */ ++ /* return err; */ ++ return 0; ++ } ++ ++ l = calc_size(de->de_str.len); ++ vdir_cache->vd_last.p.p += l; ++ file->f_pos += l; ++ } ++ if (vdir_cache->vd_last.i < vdir_cache->vd_nblk - 1) { ++ vdir_cache->vd_last.i++; ++ vdir_cache->vd_last.p.deblk ++ = vdir_cache->vd_deblk[vdir_cache->vd_last.i]; ++ file->f_pos = sizeof(*vdir_cache->vd_last.p.deblk) ++ * vdir_cache->vd_last.i; ++ continue; ++ } ++ break; ++ } ++ ++ /* smp_mb(); */ ++ return 0; ++} +diff -urN ./fs/aufs/vfsub.c ./fs/aufs/vfsub.c +--- ./fs/aufs/vfsub.c 1970-01-01 01:00:00.000000000 +0100 ++++ ./fs/aufs/vfsub.c 2009-04-06 10:26:46.000000000 +0200 +@@ -0,0 +1,731 @@ ++/* ++ * Copyright (C) 2005-2009 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. ++ */ ++ ++/* ++ * sub-routines for VFS ++ */ ++ ++#include <linux/uaccess.h> ++#include "aufs.h" ++ ++int vfsub_update_h_iattr(struct path *h_path, int *did) ++{ ++ int err; ++ struct kstat st; ++ struct super_block *h_sb; ++ ++ /* for remote fs, leave work for its getattr or d_revalidate */ ++ /* for bad i_attr fs, handle them in aufs_getattr() */ ++ /* still some fs may acquire i_mutex. we need to skip them */ ++ err = 0; ++ if (!did) ++ did = &err; ++ h_sb = h_path->dentry->d_sb; ++ *did = (!au_test_fs_remote(h_sb) && au_test_fs_refresh_iattr(h_sb)); ++ if (*did) ++ err = vfs_getattr(h_path->mnt, h_path->dentry, &st); ++ ++ return err; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++struct file *vfsub_filp_open(const char *path, int oflags, int mode) ++{ ++ struct file *file; ++ ++ lockdep_off(); ++ file = filp_open(path, oflags, mode); ++ lockdep_on(); ++ if (IS_ERR(file)) ++ goto out; ++ AuDebugOn(!file->f_op); ++ vfsub_update_h_iattr(&file->f_path, /*did*/NULL); /*ignore*/ ++ ++ out: ++ return file; ++} ++ ++int vfsub_kern_path(const char *name, unsigned int flags, struct path *path) ++{ ++ int err; ++ ++ /* lockdep_off(); */ ++ err = kern_path(name, flags, path); ++ /* lockdep_on(); */ ++ if (!err && path->dentry->d_inode) ++ vfsub_update_h_iattr(path, /*did*/NULL); /*ignore*/ ++ return err; ++} ++ ++struct dentry *vfsub_lookup_one_len(const char *name, struct dentry *parent, ++ int len) ++{ ++ struct path path = { ++ .mnt = NULL ++ }; ++ ++ IMustLock(parent->d_inode); ++ ++ path.dentry = lookup_one_len(name, parent, len); ++ if (IS_ERR(path.dentry)) ++ goto out; ++ if (path.dentry->d_inode) ++ vfsub_update_h_iattr(&path, /*did*/NULL); /*ignore*/ ++ ++ out: ++ return path.dentry; ++} ++ ++struct dentry *vfsub_lookup_hash(struct nameidata *nd) ++{ ++ struct path path = { ++ .mnt = nd->path.mnt ++ }; ++ ++ IMustLock(nd->path.dentry->d_inode); ++ ++ path.dentry = lookup_hash(nd); ++ if (!IS_ERR(path.dentry) && path.dentry->d_inode) ++ vfsub_update_h_iattr(&path, /*did*/NULL); /*ignore*/ ++ ++ return path.dentry; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++struct dentry *vfsub_lock_rename(struct dentry *d1, struct au_hinode *hdir1, ++ struct dentry *d2, struct au_hinode *hdir2) ++{ ++ struct dentry *d; ++ ++ lockdep_off(); ++ d = lock_rename(d1, d2); ++ lockdep_on(); ++ au_hin_suspend(hdir1); ++ if (hdir1 != hdir2) ++ au_hin_suspend(hdir2); ++ ++ return d; ++} ++ ++void vfsub_unlock_rename(struct dentry *d1, struct au_hinode *hdir1, ++ struct dentry *d2, struct au_hinode *hdir2) ++{ ++ au_hin_resume(hdir1); ++ if (hdir1 != hdir2) ++ au_hin_resume(hdir2); ++ lockdep_off(); ++ unlock_rename(d1, d2); ++ lockdep_on(); ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++int vfsub_create(struct inode *dir, struct path *path, int mode) ++{ ++ int err; ++ struct dentry *d; ++ ++ IMustLock(dir); ++ ++ d = path->dentry; ++ path->dentry = d->d_parent; ++ err = security_path_mknod(path, path->dentry, mode, 0); ++ path->dentry = d; ++ if (unlikely(err)) ++ goto out; ++ ++ if (au_test_fs_null_nd(dir->i_sb)) ++ err = vfs_create(dir, path->dentry, mode, NULL); ++ else { ++ struct nameidata h_nd; ++ ++ memset(&h_nd, 0, sizeof(h_nd)); ++ h_nd.flags = LOOKUP_CREATE; ++ h_nd.intent.open.flags = O_CREAT ++ | vfsub_fmode_to_uint(FMODE_READ); ++ h_nd.intent.open.create_mode = mode; ++ h_nd.path.dentry = path->dentry->d_parent; ++ h_nd.path.mnt = path->mnt; ++ path_get(&h_nd.path); ++ err = vfs_create(dir, path->dentry, mode, &h_nd); ++ path_put(&h_nd.path); ++ } ++ ++ if (!err) { ++ struct path tmp = *path; ++ int did; ++ ++ vfsub_update_h_iattr(&tmp, &did); ++ if (did) { ++ tmp.dentry = path->dentry->d_parent; ++ vfsub_update_h_iattr(&tmp, /*did*/NULL); ++ } ++ /*ignore*/ ++ } ++ ++ out: ++ return err; ++} ++ ++int vfsub_symlink(struct inode *dir, struct path *path, const char *symname) ++{ ++ int err; ++ struct dentry *d; ++ ++ IMustLock(dir); ++ ++ d = path->dentry; ++ path->dentry = d->d_parent; ++ err = security_path_symlink(path, path->dentry, symname); ++ path->dentry = d; ++ if (unlikely(err)) ++ goto out; ++ ++ err = vfs_symlink(dir, path->dentry, symname); ++ if (!err) { ++ struct path tmp = *path; ++ int did; ++ ++ vfsub_update_h_iattr(&tmp, &did); ++ if (did) { ++ tmp.dentry = path->dentry->d_parent; ++ vfsub_update_h_iattr(&tmp, /*did*/NULL); ++ } ++ /*ignore*/ ++ } ++ ++ out: ++ return err; ++} ++ ++int vfsub_mknod(struct inode *dir, struct path *path, int mode, dev_t dev) ++{ ++ int err; ++ struct dentry *d; ++ ++ IMustLock(dir); ++ ++ d = path->dentry; ++ path->dentry = d->d_parent; ++ err = security_path_mknod(path, path->dentry, mode, dev); ++ path->dentry = d; ++ if (unlikely(err)) ++ goto out; ++ ++ err = vfs_mknod(dir, path->dentry, mode, dev); ++ if (!err) { ++ struct path tmp = *path; ++ int did; ++ ++ vfsub_update_h_iattr(&tmp, &did); ++ if (did) { ++ tmp.dentry = path->dentry->d_parent; ++ vfsub_update_h_iattr(&tmp, /*did*/NULL); ++ } ++ /*ignore*/ ++ } ++ ++ out: ++ return err; ++} ++ ++/* ramfs doesn't check i_nlink in link(2), aufs sets a limit for it */ ++static int au_test_nlink(struct inode *inode) ++{ ++#ifndef CONFIG_AUFS_BR_RAMFS ++ return 0; ++#else ++ /* borrowing the upper limit from EXT2_LINK_MAX */ ++ const unsigned int ramfs_link_max = 32000; ++ ++ if (!au_test_ramfs(inode->i_sb) ++ || inode->i_nlink < ramfs_link_max) ++ return 0; ++ return -EMLINK; ++#endif ++} ++ ++int vfsub_link(struct dentry *src_dentry, struct inode *dir, struct path *path) ++{ ++ int err; ++ struct dentry *d; ++ ++ IMustLock(dir); ++ ++ err = au_test_nlink(src_dentry->d_inode); ++ if (unlikely(err)) ++ return err; ++ ++ d = path->dentry; ++ path->dentry = d->d_parent; ++ err = security_path_link(src_dentry, path, path->dentry); ++ path->dentry = d; ++ if (unlikely(err)) ++ goto out; ++ ++ lockdep_off(); ++ err = vfs_link(src_dentry, dir, path->dentry); ++ lockdep_on(); ++ if (!err) { ++ struct path tmp = *path; ++ int did; ++ ++ /* fuse has different memory inode for the same inumber */ ++ vfsub_update_h_iattr(&tmp, &did); ++ if (did) { ++ tmp.dentry = path->dentry->d_parent; ++ vfsub_update_h_iattr(&tmp, /*did*/NULL); ++ tmp.dentry = src_dentry; ++ vfsub_update_h_iattr(&tmp, /*did*/NULL); ++ } ++ /*ignore*/ ++ } ++ ++ out: ++ return err; ++} ++ ++int vfsub_rename(struct inode *src_dir, struct dentry *src_dentry, ++ struct inode *dir, struct path *path) ++{ ++ int err; ++ struct path tmp = { ++ .mnt = path->mnt ++ }; ++ struct dentry *d; ++ ++ IMustLock(dir); ++ IMustLock(src_dir); ++ ++ d = path->dentry; ++ path->dentry = d->d_parent; ++ tmp.dentry = src_dentry->d_parent; ++ err = security_path_rename(&tmp, src_dentry, path, path->dentry); ++ path->dentry = d; ++ if (unlikely(err)) ++ goto out; ++ ++ lockdep_off(); ++ err = vfs_rename(src_dir, src_dentry, dir, path->dentry); ++ lockdep_on(); ++ if (!err) { ++ int did; ++ ++ tmp.dentry = d->d_parent; ++ vfsub_update_h_iattr(&tmp, &did); ++ if (did) { ++ tmp.dentry = src_dentry; ++ vfsub_update_h_iattr(&tmp, /*did*/NULL); ++ tmp.dentry = src_dentry->d_parent; ++ vfsub_update_h_iattr(&tmp, /*did*/NULL); ++ } ++ /*ignore*/ ++ } ++ ++ out: ++ return err; ++} ++ ++int vfsub_mkdir(struct inode *dir, struct path *path, int mode) ++{ ++ int err; ++ struct dentry *d; ++ ++ IMustLock(dir); ++ ++ d = path->dentry; ++ path->dentry = d->d_parent; ++ err = security_path_mkdir(path, path->dentry, mode); ++ path->dentry = d; ++ if (unlikely(err)) ++ goto out; ++ ++ err = vfs_mkdir(dir, path->dentry, mode); ++ if (!err) { ++ struct path tmp = *path; ++ int did; ++ ++ vfsub_update_h_iattr(&tmp, &did); ++ if (did) { ++ tmp.dentry = path->dentry->d_parent; ++ vfsub_update_h_iattr(&tmp, /*did*/NULL); ++ } ++ /*ignore*/ ++ } ++ ++ out: ++ return err; ++} ++ ++int vfsub_rmdir(struct inode *dir, struct path *path) ++{ ++ int err; ++ struct dentry *d; ++ ++ IMustLock(dir); ++ ++ d = path->dentry; ++ path->dentry = d->d_parent; ++ err = security_path_rmdir(path, path->dentry); ++ path->dentry = d; ++ if (unlikely(err)) ++ goto out; ++ ++ lockdep_off(); ++ err = vfs_rmdir(dir, path->dentry); ++ lockdep_on(); ++ if (!err) { ++ struct path tmp = { ++ .dentry = path->dentry->d_parent, ++ .mnt = path->mnt ++ }; ++ ++ vfsub_update_h_iattr(&tmp, /*did*/NULL); /*ignore*/ ++ } ++ ++ out: ++ return err; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++ssize_t vfsub_read_u(struct file *file, char __user *ubuf, size_t count, ++ loff_t *ppos) ++{ ++ ssize_t err; ++ ++ err = vfs_read(file, ubuf, count, ppos); ++ if (err >= 0) ++ vfsub_update_h_iattr(&file->f_path, /*did*/NULL); /*ignore*/ ++ return err; ++} ++ ++/* todo: kernel_read()? */ ++ssize_t vfsub_read_k(struct file *file, void *kbuf, size_t count, ++ loff_t *ppos) ++{ ++ ssize_t err; ++ mm_segment_t oldfs; ++ ++ oldfs = get_fs(); ++ set_fs(KERNEL_DS); ++ err = vfsub_read_u(file, (char __user *)kbuf, count, ppos); ++ set_fs(oldfs); ++ return err; ++} ++ ++ssize_t vfsub_write_u(struct file *file, const char __user *ubuf, size_t count, ++ loff_t *ppos) ++{ ++ ssize_t err; ++ ++ lockdep_off(); ++ err = vfs_write(file, ubuf, count, ppos); ++ lockdep_on(); ++ if (err >= 0) ++ vfsub_update_h_iattr(&file->f_path, /*did*/NULL); /*ignore*/ ++ return err; ++} ++ ++ssize_t vfsub_write_k(struct file *file, void *kbuf, size_t count, loff_t *ppos) ++{ ++ ssize_t err; ++ mm_segment_t oldfs; ++ ++ oldfs = get_fs(); ++ set_fs(KERNEL_DS); ++ err = vfsub_write_u(file, (const char __user *)kbuf, count, ppos); ++ set_fs(oldfs); ++ return err; ++} ++ ++int vfsub_readdir(struct file *file, filldir_t filldir, void *arg) ++{ ++ int err; ++ ++ lockdep_off(); ++ err = vfs_readdir(file, filldir, arg); ++ lockdep_on(); ++ if (err >= 0) ++ vfsub_update_h_iattr(&file->f_path, /*did*/NULL); /*ignore*/ ++ return err; ++} ++ ++long vfsub_splice_to(struct file *in, loff_t *ppos, ++ struct pipe_inode_info *pipe, size_t len, ++ unsigned int flags) ++{ ++ long err; ++ ++ lockdep_off(); ++ err = vfs_splice_to(in, ppos, pipe, len, flags); ++ lockdep_on(); ++ if (err >= 0) ++ vfsub_update_h_iattr(&in->f_path, /*did*/NULL); /*ignore*/ ++ return err; ++} ++ ++long vfsub_splice_from(struct pipe_inode_info *pipe, struct file *out, ++ loff_t *ppos, size_t len, unsigned int flags) ++{ ++ long err; ++ ++ lockdep_off(); ++ err = vfs_splice_from(pipe, out, ppos, len, flags); ++ lockdep_on(); ++ if (err >= 0) ++ vfsub_update_h_iattr(&out->f_path, /*did*/NULL); /*ignore*/ ++ return err; ++} ++ ++/* cf. open.c:do_sys_truncate() and do_sys_ftruncate() */ ++int vfsub_trunc(struct path *h_path, loff_t length, unsigned int attr, ++ struct file *h_file) ++{ ++ int err; ++ struct inode *h_inode; ++ ++ h_inode = h_path->dentry->d_inode; ++ if (!h_file) { ++ err = mnt_want_write(h_path->mnt); ++ if (err) ++ goto out; ++ err = inode_permission(h_inode, MAY_WRITE); ++ if (err) ++ goto out_mnt; ++ err = get_write_access(h_inode); ++ if (err) ++ goto out_mnt; ++ err = break_lease(h_inode, vfsub_fmode_to_uint(FMODE_WRITE)); ++ if (err) ++ goto out_inode; ++ } ++ ++ err = locks_verify_truncate(h_inode, h_file, length); ++ if (!err) ++ err = security_path_truncate(h_path, length, attr); ++ if (!err) { ++ lockdep_off(); ++ err = do_truncate(h_path->dentry, length, attr, h_file); ++ lockdep_on(); ++ } ++ ++ out_inode: ++ if (!h_file) ++ put_write_access(h_inode); ++ out_mnt: ++ if (!h_file) ++ mnt_drop_write(h_path->mnt); ++ out: ++ return err; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++struct au_vfsub_mkdir_args { ++ int *errp; ++ struct inode *dir; ++ struct path *path; ++ int mode; ++}; ++ ++static void au_call_vfsub_mkdir(void *args) ++{ ++ struct au_vfsub_mkdir_args *a = args; ++ *a->errp = vfsub_mkdir(a->dir, a->path, a->mode); ++} ++ ++int vfsub_sio_mkdir(struct inode *dir, struct path *path, int mode) ++{ ++ int err, do_sio, wkq_err; ++ ++ do_sio = au_test_h_perm_sio(dir, MAY_EXEC | MAY_WRITE); ++ if (!do_sio) ++ err = vfsub_mkdir(dir, path, mode); ++ else { ++ struct au_vfsub_mkdir_args args = { ++ .errp = &err, ++ .dir = dir, ++ .path = path, ++ .mode = mode ++ }; ++ wkq_err = au_wkq_wait(au_call_vfsub_mkdir, &args); ++ if (unlikely(wkq_err)) ++ err = wkq_err; ++ } ++ ++ return err; ++} ++ ++struct au_vfsub_rmdir_args { ++ int *errp; ++ struct inode *dir; ++ struct path *path; ++}; ++ ++static void au_call_vfsub_rmdir(void *args) ++{ ++ struct au_vfsub_rmdir_args *a = args; ++ *a->errp = vfsub_rmdir(a->dir, a->path); ++} ++ ++int vfsub_sio_rmdir(struct inode *dir, struct path *path) ++{ ++ int err, do_sio, wkq_err; ++ ++ do_sio = au_test_h_perm_sio(dir, MAY_EXEC | MAY_WRITE); ++ if (!do_sio) ++ err = vfsub_rmdir(dir, path); ++ else { ++ struct au_vfsub_rmdir_args args = { ++ .errp = &err, ++ .dir = dir, ++ .path = path ++ }; ++ wkq_err = au_wkq_wait(au_call_vfsub_rmdir, &args); ++ if (unlikely(wkq_err)) ++ err = wkq_err; ++ } ++ ++ return err; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++struct notify_change_args { ++ int *errp; ++ struct path *path; ++ struct iattr *ia; ++}; ++ ++static void call_notify_change(void *args) ++{ ++ struct notify_change_args *a = args; ++ struct inode *h_inode; ++ ++ h_inode = a->path->dentry->d_inode; ++ IMustLock(h_inode); ++ ++ *a->errp = -EPERM; ++ if (!IS_IMMUTABLE(h_inode) && !IS_APPEND(h_inode)) { ++ lockdep_off(); ++ *a->errp = notify_change(a->path->dentry, a->ia); ++ lockdep_on(); ++ if (!*a->errp) ++ vfsub_update_h_iattr(a->path, /*did*/NULL); /*ignore*/ ++ } ++ AuTraceErr(*a->errp); ++} ++ ++int vfsub_notify_change(struct path *path, struct iattr *ia) ++{ ++ int err; ++ struct notify_change_args args = { ++ .errp = &err, ++ .path = path, ++ .ia = ia ++ }; ++ ++ call_notify_change(&args); ++ ++ return err; ++} ++ ++int vfsub_sio_notify_change(struct path *path, struct iattr *ia) ++{ ++ int err, wkq_err; ++ struct notify_change_args args = { ++ .errp = &err, ++ .path = path, ++ .ia = ia ++ }; ++ ++ wkq_err = au_wkq_wait(call_notify_change, &args); ++ if (unlikely(wkq_err)) ++ err = wkq_err; ++ ++ return err; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++struct unlink_args { ++ int *errp; ++ struct inode *dir; ++ struct path *path; ++}; ++ ++static void call_unlink(void *args) ++{ ++ struct unlink_args *a = args; ++ struct dentry *d = a->path->dentry; ++ struct inode *h_inode; ++ const int stop_sillyrename = (au_test_nfs(d->d_sb) ++ && atomic_read(&d->d_count) == 1); ++ ++ IMustLock(a->dir); ++ ++ a->path->dentry = d->d_parent; ++ *a->errp = security_path_unlink(a->path, d); ++ a->path->dentry = d; ++ if (unlikely(*a->errp)) ++ return; ++ ++ if (!stop_sillyrename) ++ dget(d); ++ h_inode = d->d_inode; ++ if (h_inode) ++ atomic_inc(&h_inode->i_count); ++ ++ lockdep_off(); ++ *a->errp = vfs_unlink(a->dir, d); ++ lockdep_on(); ++ if (!*a->errp) { ++ struct path tmp = { ++ .dentry = d->d_parent, ++ .mnt = a->path->mnt ++ }; ++ vfsub_update_h_iattr(&tmp, /*did*/NULL); /*ignore*/ ++ } ++ ++ if (!stop_sillyrename) ++ dput(d); ++ if (h_inode) ++ iput(h_inode); ++ ++ AuTraceErr(*a->errp); ++} ++ ++/* ++ * @dir: must be locked. ++ * @dentry: target dentry. ++ */ ++int vfsub_unlink(struct inode *dir, struct path *path, int force) ++{ ++ int err; ++ struct unlink_args args = { ++ .errp = &err, ++ .dir = dir, ++ .path = path ++ }; ++ ++ if (!force) ++ call_unlink(&args); ++ else { ++ int wkq_err; ++ ++ wkq_err = au_wkq_wait(call_unlink, &args); ++ if (unlikely(wkq_err)) ++ err = wkq_err; ++ } ++ ++ return err; ++} +diff -urN ./fs/aufs/vfsub.h ./fs/aufs/vfsub.h +--- ./fs/aufs/vfsub.h 1970-01-01 01:00:00.000000000 +0100 ++++ ./fs/aufs/vfsub.h 2009-04-06 10:26:46.000000000 +0200 +@@ -0,0 +1,165 @@ ++/* ++ * Copyright (C) 2005-2009 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. ++ */ ++ ++/* ++ * sub-routines for VFS ++ */ ++ ++#ifndef __AUFS_VFSUB_H__ ++#define __AUFS_VFSUB_H__ ++ ++#ifdef __KERNEL__ ++ ++#include <linux/fs.h> ++#include <linux/fs_stack.h> ++#include <linux/namei.h> ++#include <linux/security.h> ++#include <linux/splice.h> ++ ++/* ---------------------------------------------------------------------- */ ++ ++/* lock subclass for lower inode */ ++/* default MAX_LOCKDEP_SUBCLASSES(8) is not enough */ ++/* reduce? gave up. */ ++enum { ++ AuLsc_I_Begin = I_MUTEX_QUOTA, /* 4 */ ++ AuLsc_I_PARENT, /* lower inode, parent first */ ++ AuLsc_I_PARENT2, /* copyup dirs */ ++ AuLsc_I_CHILD, ++ AuLsc_I_CHILD2, ++ AuLsc_I_End ++}; ++ ++/* to debug easier, do not make them inlined functions */ ++#define MtxMustLock(mtx) AuDebugOn(!mutex_is_locked(mtx)) ++#define IMustLock(i) MtxMustLock(&(i)->i_mutex) ++ ++/* ---------------------------------------------------------------------- */ ++ ++static inline void vfsub_copy_inode_size(struct inode *inode, ++ struct inode *h_inode) ++{ ++ spin_lock(&inode->i_lock); ++ fsstack_copy_inode_size(inode, h_inode); ++ spin_unlock(&inode->i_lock); ++} ++ ++int vfsub_update_h_iattr(struct path *h_path, int *did); ++struct file *vfsub_filp_open(const char *path, int oflags, int mode); ++int vfsub_kern_path(const char *name, unsigned int flags, struct path *path); ++struct dentry *vfsub_lookup_one_len(const char *name, struct dentry *parent, ++ int len); ++struct dentry *vfsub_lookup_hash(struct nameidata *nd); ++ ++/* ---------------------------------------------------------------------- */ ++ ++struct au_hinode; ++struct dentry *vfsub_lock_rename(struct dentry *d1, struct au_hinode *hdir1, ++ struct dentry *d2, struct au_hinode *hdir2); ++void vfsub_unlock_rename(struct dentry *d1, struct au_hinode *hdir1, ++ struct dentry *d2, struct au_hinode *hdir2); ++ ++int vfsub_create(struct inode *dir, struct path *path, int mode); ++int vfsub_symlink(struct inode *dir, struct path *path, ++ const char *symname); ++int vfsub_mknod(struct inode *dir, struct path *path, int mode, dev_t dev); ++int vfsub_link(struct dentry *src_dentry, struct inode *dir, ++ struct path *path); ++int vfsub_rename(struct inode *src_hdir, struct dentry *src_dentry, ++ struct inode *hdir, struct path *path); ++int vfsub_mkdir(struct inode *dir, struct path *path, int mode); ++int vfsub_rmdir(struct inode *dir, struct path *path); ++ ++/* ---------------------------------------------------------------------- */ ++ ++ssize_t vfsub_read_u(struct file *file, char __user *ubuf, size_t count, ++ loff_t *ppos); ++ssize_t vfsub_read_k(struct file *file, void *kbuf, size_t count, ++ loff_t *ppos); ++ssize_t vfsub_write_u(struct file *file, const char __user *ubuf, size_t count, ++ loff_t *ppos); ++ssize_t vfsub_write_k(struct file *file, void *kbuf, size_t count, ++ loff_t *ppos); ++int vfsub_readdir(struct file *file, filldir_t filldir, void *arg); ++ ++static inline void vfsub_file_accessed(struct file *h_file) ++{ ++ file_accessed(h_file); ++ vfsub_update_h_iattr(&h_file->f_path, /*did*/NULL); /*ignore*/ ++} ++ ++static inline void vfsub_touch_atime(struct vfsmount *h_mnt, ++ struct dentry *h_dentry) ++{ ++ struct path h_path = { ++ .dentry = h_dentry, ++ .mnt = h_mnt ++ }; ++ touch_atime(h_mnt, h_dentry); ++ vfsub_update_h_iattr(&h_path, /*did*/NULL); /*ignore*/ ++} ++ ++long vfsub_splice_to(struct file *in, loff_t *ppos, ++ struct pipe_inode_info *pipe, size_t len, ++ unsigned int flags); ++long vfsub_splice_from(struct pipe_inode_info *pipe, struct file *out, ++ loff_t *ppos, size_t len, unsigned int flags); ++int vfsub_trunc(struct path *h_path, loff_t length, unsigned int attr, ++ struct file *h_file); ++ ++/* ---------------------------------------------------------------------- */ ++ ++static inline loff_t vfsub_llseek(struct file *file, loff_t offset, int origin) ++{ ++ loff_t err; ++ ++ lockdep_off(); ++ err = vfs_llseek(file, offset, origin); ++ lockdep_on(); ++ return err; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++/* dirty workaround for strict type of fmode_t */ ++union vfsub_fmu { ++ fmode_t fm; ++ unsigned int ui; ++}; ++ ++static inline unsigned int vfsub_fmode_to_uint(fmode_t fm) ++{ ++ union vfsub_fmu u = { ++ .fm = fm ++ }; ++ ++ BUILD_BUG_ON(sizeof(u.fm) != sizeof(u.ui)); ++ ++ return u.ui; ++} ++ ++static inline fmode_t vfsub_uint_to_fmode(unsigned int ui) ++{ ++ union vfsub_fmu u = { ++ .ui = ui ++ }; ++ ++ return u.fm; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++int vfsub_sio_mkdir(struct inode *dir, struct path *path, int mode); ++int vfsub_sio_rmdir(struct inode *dir, struct path *path); ++int vfsub_sio_notify_change(struct path *path, struct iattr *ia); ++int vfsub_notify_change(struct path *path, struct iattr *ia); ++int vfsub_unlink(struct inode *dir, struct path *path, int force); ++ ++#endif /* __KERNEL__ */ ++#endif /* __AUFS_VFSUB_H__ */ +diff -urN ./fs/aufs/wbr_policy.c ./fs/aufs/wbr_policy.c +--- ./fs/aufs/wbr_policy.c 1970-01-01 01:00:00.000000000 +0100 ++++ ./fs/aufs/wbr_policy.c 2009-04-06 10:26:46.000000000 +0200 +@@ -0,0 +1,628 @@ ++/* ++ * Copyright (C) 2005-2009 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. ++ */ ++ ++/* ++ * policies for selecting one among multiple writable branches ++ */ ++ ++#include <linux/statfs.h> ++#include "aufs.h" ++ ++/* subset of cpup_attr() */ ++static noinline_for_stack ++int au_cpdown_attr(struct path *h_path, struct dentry *h_src) ++{ ++ int err, sbits; ++ struct iattr ia; ++ struct inode *h_isrc; ++ ++ h_isrc = h_src->d_inode; ++ ia.ia_valid = ATTR_FORCE | ATTR_MODE | ATTR_UID | ATTR_GID; ++ ia.ia_mode = h_isrc->i_mode; ++ ia.ia_uid = h_isrc->i_uid; ++ ia.ia_gid = h_isrc->i_gid; ++ sbits = !!(ia.ia_mode & (S_ISUID | S_ISGID)); ++ au_cpup_attr_flags(h_path->dentry->d_inode, h_isrc); ++ err = vfsub_sio_notify_change(h_path, &ia); ++ ++ /* 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_sio_notify_change(h_path, &ia); ++ } ++ ++ return err; ++} ++ ++#define AuCpdown_PARENT_OPQ 1 ++#define AuCpdown_WHED (1 << 1) ++#define AuCpdown_MADE_DIR (1 << 2) ++#define AuCpdown_DIROPQ (1 << 3) ++#define au_ftest_cpdown(flags, name) ((flags) & AuCpdown_##name) ++#define au_fset_cpdown(flags, name) { (flags) |= AuCpdown_##name; } ++#define au_fclr_cpdown(flags, name) { (flags) &= ~AuCpdown_##name; } ++ ++struct au_cpdown_dir_args { ++ struct dentry *parent; ++ unsigned int flags; ++}; ++ ++static int au_cpdown_dir_opq(struct dentry *dentry, aufs_bindex_t bdst, ++ struct au_cpdown_dir_args *a) ++{ ++ int err; ++ struct dentry *opq_dentry; ++ ++ opq_dentry = au_diropq_create(dentry, bdst); ++ err = PTR_ERR(opq_dentry); ++ if (IS_ERR(opq_dentry)) ++ goto out; ++ dput(opq_dentry); ++ au_fset_cpdown(a->flags, DIROPQ); ++ ++ out: ++ return err; ++} ++ ++static int au_cpdown_dir_wh(struct dentry *dentry, struct dentry *h_parent, ++ struct inode *dir, aufs_bindex_t bdst) ++{ ++ int err; ++ struct path h_path; ++ struct au_branch *br; ++ ++ br = au_sbr(dentry->d_sb, bdst); ++ h_path.dentry = au_wh_lkup(h_parent, &dentry->d_name, br); ++ err = PTR_ERR(h_path.dentry); ++ if (IS_ERR(h_path.dentry)) ++ goto out; ++ ++ err = 0; ++ if (h_path.dentry->d_inode) { ++ h_path.mnt = br->br_mnt; ++ err = au_wh_unlink_dentry(au_h_iptr(dir, bdst), &h_path, ++ dentry); ++ } ++ dput(h_path.dentry); ++ ++ out: ++ return err; ++} ++ ++static int au_cpdown_dir(struct dentry *dentry, aufs_bindex_t bdst, ++ struct dentry *h_parent, void *arg) ++{ ++ int err, rerr; ++ aufs_bindex_t bend, bopq, bstart; ++ unsigned char parent_opq; ++ struct path h_path; ++ struct dentry *parent; ++ struct inode *h_dir, *h_inode, *inode, *dir; ++ struct au_cpdown_dir_args *args = arg; ++ ++ bstart = au_dbstart(dentry); ++ /* dentry is di-locked */ ++ parent = dget_parent(dentry); ++ dir = parent->d_inode; ++ h_dir = h_parent->d_inode; ++ AuDebugOn(h_dir != au_h_iptr(dir, bdst)); ++ IMustLock(h_dir); ++ ++ err = au_lkup_neg(dentry, bdst); ++ if (unlikely(err < 0)) ++ goto out; ++ h_path.dentry = au_h_dptr(dentry, bdst); ++ h_path.mnt = au_sbr_mnt(dentry->d_sb, bdst); ++ err = vfsub_sio_mkdir(au_h_iptr(dir, bdst), &h_path, ++ S_IRWXU | S_IRUGO | S_IXUGO); ++ if (unlikely(err)) ++ goto out_put; ++ au_fset_cpdown(args->flags, MADE_DIR); ++ ++ bend = au_dbend(dentry); ++ bopq = au_dbdiropq(dentry); ++ au_fclr_cpdown(args->flags, WHED); ++ au_fclr_cpdown(args->flags, DIROPQ); ++ if (au_dbwh(dentry) == bdst) ++ au_fset_cpdown(args->flags, WHED); ++ if (!au_ftest_cpdown(args->flags, PARENT_OPQ) && bopq <= bdst) ++ au_fset_cpdown(args->flags, PARENT_OPQ); ++ parent_opq = (au_ftest_cpdown(args->flags, PARENT_OPQ) ++ && args->parent == dentry); ++ h_inode = h_path.dentry->d_inode; ++ mutex_lock_nested(&h_inode->i_mutex, AuLsc_I_CHILD); ++ if (au_ftest_cpdown(args->flags, WHED)) { ++ err = au_cpdown_dir_opq(dentry, bdst, args); ++ if (unlikely(err)) { ++ mutex_unlock(&h_inode->i_mutex); ++ goto out_dir; ++ } ++ } ++ ++ err = au_cpdown_attr(&h_path, au_h_dptr(dentry, bstart)); ++ mutex_unlock(&h_inode->i_mutex); ++ if (unlikely(err)) ++ goto out_opq; ++ ++ if (au_ftest_cpdown(args->flags, WHED)) { ++ err = au_cpdown_dir_wh(dentry, h_parent, dir, bdst); ++ if (unlikely(err)) ++ goto out_opq; ++ } ++ ++ inode = dentry->d_inode; ++ if (au_ibend(inode) < bdst) ++ au_set_ibend(inode, bdst); ++ au_set_h_iptr(inode, bdst, au_igrab(h_inode), ++ au_hi_flags(inode, /*isdir*/1)); ++ goto out; /* success */ ++ ++ /* revert */ ++ out_opq: ++ if (au_ftest_cpdown(args->flags, DIROPQ)) { ++ mutex_lock_nested(&h_inode->i_mutex, AuLsc_I_CHILD); ++ rerr = au_diropq_remove(dentry, bdst); ++ mutex_unlock(&h_inode->i_mutex); ++ if (unlikely(rerr)) { ++ AuIOErr("failed removing diropq for %.*s b%d (%d)\n", ++ AuDLNPair(dentry), bdst, rerr); ++ err = -EIO; ++ goto out; ++ } ++ } ++ out_dir: ++ if (au_ftest_cpdown(args->flags, MADE_DIR)) { ++ rerr = vfsub_sio_rmdir(au_h_iptr(dir, bdst), &h_path); ++ if (unlikely(rerr)) { ++ AuIOErr("failed removing %.*s b%d (%d)\n", ++ AuDLNPair(dentry), bdst, rerr); ++ err = -EIO; ++ } ++ } ++ out_put: ++ au_set_h_dptr(dentry, bdst, NULL); ++ if (au_dbend(dentry) == bdst) ++ au_update_dbend(dentry); ++ out: ++ dput(parent); ++ return err; ++} ++ ++int au_cpdown_dirs(struct dentry *dentry, aufs_bindex_t bdst) ++{ ++ int err; ++ struct au_cpdown_dir_args args = { ++ .parent = dget_parent(dentry), ++ .flags = 0 ++ }; ++ ++ err = au_cp_dirs(dentry, bdst, au_cpdown_dir, &args); ++ dput(args.parent); ++ ++ return err; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++/* policies for create */ ++ ++static int au_wbr_bu(struct super_block *sb, aufs_bindex_t bindex) ++{ ++ for (; bindex >= 0; bindex--) ++ if (!au_br_rdonly(au_sbr(sb, bindex))) ++ return bindex; ++ return -EROFS; ++} ++ ++/* top down parent */ ++static int au_wbr_create_tdp(struct dentry *dentry, int isdir __maybe_unused) ++{ ++ int err; ++ aufs_bindex_t bstart, bindex; ++ struct super_block *sb; ++ struct dentry *parent, *h_parent; ++ ++ sb = dentry->d_sb; ++ bstart = au_dbstart(dentry); ++ err = bstart; ++ if (!au_br_rdonly(au_sbr(sb, bstart))) ++ goto out; ++ ++ err = -EROFS; ++ parent = dget_parent(dentry); ++ for (bindex = au_dbstart(parent); bindex < bstart; bindex++) { ++ h_parent = au_h_dptr(parent, bindex); ++ if (!h_parent || !h_parent->d_inode) ++ continue; ++ ++ if (!au_br_rdonly(au_sbr(sb, bindex))) { ++ err = bindex; ++ break; ++ } ++ } ++ dput(parent); ++ ++ /* bottom up here */ ++ if (unlikely(err < 0)) ++ err = au_wbr_bu(sb, bstart - 1); ++ ++ out: ++ AuDbg("b%d\n", err); ++ return err; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++/* an exception for the policy other than tdp */ ++static int au_wbr_create_exp(struct dentry *dentry) ++{ ++ int err; ++ aufs_bindex_t bwh, bdiropq; ++ struct dentry *parent; ++ ++ err = -1; ++ bwh = au_dbwh(dentry); ++ parent = dget_parent(dentry); ++ bdiropq = au_dbdiropq(parent); ++ if (bwh >= 0) { ++ if (bdiropq >= 0) ++ err = min(bdiropq, bwh); ++ else ++ err = bwh; ++ AuDbg("%d\n", err); ++ } else if (bdiropq >= 0) { ++ err = bdiropq; ++ AuDbg("%d\n", err); ++ } ++ dput(parent); ++ ++ if (err >= 0 && au_br_rdonly(au_sbr(dentry->d_sb, err))) ++ err = -1; ++ ++ AuDbg("%d\n", err); ++ return err; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++/* round robin */ ++static int au_wbr_create_init_rr(struct super_block *sb) ++{ ++ int err; ++ ++ err = au_wbr_bu(sb, au_sbend(sb)); ++ atomic_set(&au_sbi(sb)->si_wbr_rr_next, -err); /* less important */ ++ ++ AuDbg("b%d\n", err); ++ return err; ++} ++ ++static int au_wbr_create_rr(struct dentry *dentry, int isdir) ++{ ++ int err, nbr; ++ unsigned int u; ++ aufs_bindex_t bindex, bend; ++ struct super_block *sb; ++ atomic_t *next; ++ ++ err = au_wbr_create_exp(dentry); ++ if (err >= 0) ++ goto out; ++ ++ sb = dentry->d_sb; ++ next = &au_sbi(sb)->si_wbr_rr_next; ++ bend = au_sbend(sb); ++ nbr = bend + 1; ++ for (bindex = 0; bindex <= bend; bindex++) { ++ if (!isdir) { ++ err = atomic_dec_return(next) + 1; ++ /* modulo for 0 is meaningless */ ++ if (unlikely(!err)) ++ err = atomic_dec_return(next) + 1; ++ } else ++ err = atomic_read(next); ++ AuDbg("%d\n", err); ++ u = err; ++ err = u % nbr; ++ AuDbg("%d\n", err); ++ if (!au_br_rdonly(au_sbr(sb, err))) ++ break; ++ err = -EROFS; ++ } ++ ++ out: ++ AuDbg("%d\n", err); ++ return err; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++/* most free space */ ++static void au_mfs(struct dentry *dentry) ++{ ++ struct super_block *sb; ++ struct au_branch *br; ++ struct au_wbr_mfs *mfs; ++ aufs_bindex_t bindex, bend; ++ int err; ++ unsigned long long b, bavail; ++ /* reduce the stack usage */ ++ struct kstatfs *st; ++ ++ st = kmalloc(sizeof(*st), GFP_NOFS); ++ if (unlikely(!st)) { ++ AuWarn1("failed updating mfs(%d), ignored\n", -ENOMEM); ++ return; ++ } ++ ++ bavail = 0; ++ sb = dentry->d_sb; ++ mfs = &au_sbi(sb)->si_wbr_mfs; ++ mfs->mfs_bindex = -EROFS; ++ mfs->mfsrr_bytes = 0; ++ bend = au_sbend(sb); ++ for (bindex = 0; bindex <= bend; bindex++) { ++ br = au_sbr(sb, bindex); ++ if (au_br_rdonly(br)) ++ continue; ++ ++ /* sb->s_root for NFS is unreliable */ ++ err = vfs_statfs(br->br_mnt->mnt_root, st); ++ if (unlikely(err)) { ++ AuWarn1("failed statfs, b%d, %d\n", bindex, err); ++ continue; ++ } ++ ++ /* when the available size is equal, select the lower one */ ++ BUILD_BUG_ON(sizeof(b) < sizeof(st->f_bavail) ++ || sizeof(b) < sizeof(st->f_bsize)); ++ b = st->f_bavail * st->f_bsize; ++ br->br_wbr->wbr_bytes = b; ++ if (b >= bavail) { ++ bavail = b; ++ mfs->mfs_bindex = bindex; ++ mfs->mfs_jiffy = jiffies; ++ } ++ } ++ ++ mfs->mfsrr_bytes = bavail; ++ AuDbg("b%d\n", mfs->mfs_bindex); ++ kfree(st); ++} ++ ++static int au_wbr_create_mfs(struct dentry *dentry, int isdir __maybe_unused) ++{ ++ int err; ++ struct super_block *sb; ++ struct au_wbr_mfs *mfs; ++ ++ err = au_wbr_create_exp(dentry); ++ if (err >= 0) ++ goto out; ++ ++ sb = dentry->d_sb; ++ mfs = &au_sbi(sb)->si_wbr_mfs; ++ mutex_lock(&mfs->mfs_lock); ++ if (time_after(jiffies, mfs->mfs_jiffy + mfs->mfs_expire) ++ || mfs->mfs_bindex < 0 ++ || au_br_rdonly(au_sbr(sb, mfs->mfs_bindex))) ++ au_mfs(dentry); ++ mutex_unlock(&mfs->mfs_lock); ++ err = mfs->mfs_bindex; ++ ++ out: ++ AuDbg("b%d\n", err); ++ return err; ++} ++ ++static int au_wbr_create_init_mfs(struct super_block *sb) ++{ ++ struct au_wbr_mfs *mfs; ++ ++ mfs = &au_sbi(sb)->si_wbr_mfs; ++ mutex_init(&mfs->mfs_lock); ++ mfs->mfs_jiffy = 0; ++ mfs->mfs_bindex = -EROFS; ++ ++ return 0; ++} ++ ++static int au_wbr_create_fin_mfs(struct super_block *sb __maybe_unused) ++{ ++ mutex_destroy(&au_sbi(sb)->si_wbr_mfs.mfs_lock); ++ return 0; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++/* most free space and then round robin */ ++static int au_wbr_create_mfsrr(struct dentry *dentry, int isdir) ++{ ++ int err; ++ struct au_wbr_mfs *mfs; ++ ++ err = au_wbr_create_mfs(dentry, isdir); ++ if (err >= 0) { ++ mfs = &au_sbi(dentry->d_sb)->si_wbr_mfs; ++ if (mfs->mfsrr_bytes < mfs->mfsrr_watermark) ++ err = au_wbr_create_rr(dentry, isdir); ++ } ++ ++ AuDbg("b%d\n", err); ++ return err; ++} ++ ++static int au_wbr_create_init_mfsrr(struct super_block *sb) ++{ ++ int err; ++ ++ au_wbr_create_init_mfs(sb); /* ignore */ ++ err = au_wbr_create_init_rr(sb); ++ ++ return err; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++/* top down parent and most free space */ ++static int au_wbr_create_pmfs(struct dentry *dentry, int isdir) ++{ ++ int err, e2; ++ unsigned long long b; ++ aufs_bindex_t bindex, bstart, bend; ++ struct super_block *sb; ++ struct dentry *parent, *h_parent; ++ struct au_branch *br; ++ ++ err = au_wbr_create_tdp(dentry, isdir); ++ if (unlikely(err < 0)) ++ goto out; ++ parent = dget_parent(dentry); ++ bstart = au_dbstart(parent); ++ bend = au_dbtaildir(parent); ++ if (bstart == bend) ++ goto out_parent; /* success */ ++ ++ e2 = au_wbr_create_mfs(dentry, isdir); ++ if (e2 < 0) ++ goto out_parent; /* success */ ++ ++ /* when the available size is equal, select upper one */ ++ sb = dentry->d_sb; ++ br = au_sbr(sb, err); ++ b = br->br_wbr->wbr_bytes; ++ AuDbg("b%d, %llu\n", err, b); ++ ++ for (bindex = bstart; bindex <= bend; bindex++) { ++ h_parent = au_h_dptr(parent, bindex); ++ if (!h_parent || !h_parent->d_inode) ++ continue; ++ ++ br = au_sbr(sb, bindex); ++ if (!au_br_rdonly(br) && br->br_wbr->wbr_bytes > b) { ++ b = br->br_wbr->wbr_bytes; ++ err = bindex; ++ AuDbg("b%d, %llu\n", err, b); ++ } ++ } ++ ++ out_parent: ++ dput(parent); ++ out: ++ AuDbg("b%d\n", err); ++ return err; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++/* policies for copyup */ ++ ++/* top down parent */ ++static int au_wbr_copyup_tdp(struct dentry *dentry) ++{ ++ return au_wbr_create_tdp(dentry, /*isdir, anything is ok*/0); ++} ++ ++/* bottom up parent */ ++static int au_wbr_copyup_bup(struct dentry *dentry) ++{ ++ int err; ++ aufs_bindex_t bindex, bstart; ++ struct dentry *parent, *h_parent; ++ struct super_block *sb; ++ ++ err = -EROFS; ++ sb = dentry->d_sb; ++ parent = dget_parent(dentry); ++ bstart = au_dbstart(parent); ++ for (bindex = au_dbstart(dentry); bindex >= bstart; bindex--) { ++ h_parent = au_h_dptr(parent, bindex); ++ if (!h_parent || !h_parent->d_inode) ++ continue; ++ ++ if (!au_br_rdonly(au_sbr(sb, bindex))) { ++ err = bindex; ++ break; ++ } ++ } ++ dput(parent); ++ ++ /* bottom up here */ ++ if (unlikely(err < 0)) ++ err = au_wbr_bu(sb, bstart - 1); ++ ++ AuDbg("b%d\n", err); ++ return err; ++} ++ ++/* bottom up */ ++static int au_wbr_copyup_bu(struct dentry *dentry) ++{ ++ int err; ++ ++ err = au_wbr_bu(dentry->d_sb, au_dbstart(dentry)); ++ ++ AuDbg("b%d\n", err); ++ return err; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++struct au_wbr_copyup_operations au_wbr_copyup_ops[] = { ++ [AuWbrCopyup_TDP] = { ++ .copyup = au_wbr_copyup_tdp ++ }, ++ [AuWbrCopyup_BUP] = { ++ .copyup = au_wbr_copyup_bup ++ }, ++ [AuWbrCopyup_BU] = { ++ .copyup = au_wbr_copyup_bu ++ } ++}; ++ ++struct au_wbr_create_operations au_wbr_create_ops[] = { ++ [AuWbrCreate_TDP] = { ++ .create = au_wbr_create_tdp ++ }, ++ [AuWbrCreate_RR] = { ++ .create = au_wbr_create_rr, ++ .init = au_wbr_create_init_rr ++ }, ++ [AuWbrCreate_MFS] = { ++ .create = au_wbr_create_mfs, ++ .init = au_wbr_create_init_mfs, ++ .fin = au_wbr_create_fin_mfs ++ }, ++ [AuWbrCreate_MFSV] = { ++ .create = au_wbr_create_mfs, ++ .init = au_wbr_create_init_mfs, ++ .fin = au_wbr_create_fin_mfs ++ }, ++ [AuWbrCreate_MFSRR] = { ++ .create = au_wbr_create_mfsrr, ++ .init = au_wbr_create_init_mfsrr, ++ .fin = au_wbr_create_fin_mfs ++ }, ++ [AuWbrCreate_MFSRRV] = { ++ .create = au_wbr_create_mfsrr, ++ .init = au_wbr_create_init_mfsrr, ++ .fin = au_wbr_create_fin_mfs ++ }, ++ [AuWbrCreate_PMFS] = { ++ .create = au_wbr_create_pmfs, ++ .init = au_wbr_create_init_mfs, ++ .fin = au_wbr_create_fin_mfs ++ }, ++ [AuWbrCreate_PMFSV] = { ++ .create = au_wbr_create_pmfs, ++ .init = au_wbr_create_init_mfs, ++ .fin = au_wbr_create_fin_mfs ++ } ++}; +diff -urN ./fs/aufs/whout.c ./fs/aufs/whout.c +--- ./fs/aufs/whout.c 1970-01-01 01:00:00.000000000 +0100 ++++ ./fs/aufs/whout.c 2009-04-06 10:26:46.000000000 +0200 +@@ -0,0 +1,1010 @@ ++/* ++ * Copyright (C) 2005-2009 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. ++ */ ++ ++/* ++ * whiteout for logical deletion and opaque directory ++ */ ++ ++#include <linux/fs.h> ++#include "aufs.h" ++ ++#define WH_MASK S_IRUGO ++ ++/* ++ * If a directory contains this file, then it is opaque. We start with the ++ * .wh. flag so that it is blocked by lookup. ++ */ ++static struct qstr diropq_name = { ++ .name = AUFS_WH_DIROPQ, ++ .len = sizeof(AUFS_WH_DIROPQ) - 1 ++}; ++ ++/* ++ * generate whiteout name, which is NOT terminated by NULL. ++ * @name: original d_name.name ++ * @len: original d_name.len ++ * @wh: whiteout qstr ++ * returns zero when succeeds, otherwise error. ++ * succeeded value as wh->name should be freed by kfree(). ++ */ ++int au_wh_name_alloc(struct qstr *wh, const struct qstr *name) ++{ ++ char *p; ++ ++ if (unlikely(name->len > PATH_MAX - AUFS_WH_PFX_LEN)) ++ return -ENAMETOOLONG; ++ ++ wh->len = name->len + AUFS_WH_PFX_LEN; ++ p = kmalloc(wh->len, GFP_NOFS); ++ wh->name = p; ++ if (p) { ++ memcpy(p, AUFS_WH_PFX, AUFS_WH_PFX_LEN); ++ memcpy(p + AUFS_WH_PFX_LEN, name->name, name->len); ++ /* smp_mb(); */ ++ return 0; ++ } ++ return -ENOMEM; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++/* ++ * test if the @wh_name exists under @h_parent. ++ * @try_sio specifies the necessary of super-io. ++ */ ++int au_wh_test(struct dentry *h_parent, struct qstr *wh_name, ++ struct au_branch *br, int try_sio) ++{ ++ int err; ++ struct dentry *wh_dentry; ++ struct inode *h_dir; ++ ++ h_dir = h_parent->d_inode; ++ if (!try_sio) ++ wh_dentry = au_lkup_one(wh_name, h_parent, br, /*nd*/NULL); ++ else ++ wh_dentry = au_sio_lkup_one(wh_name, h_parent, br); ++ err = PTR_ERR(wh_dentry); ++ if (IS_ERR(wh_dentry)) ++ goto out; ++ ++ err = 0; ++ if (!wh_dentry->d_inode) ++ goto out_wh; /* success */ ++ ++ err = 1; ++ if (S_ISREG(wh_dentry->d_inode->i_mode)) ++ goto out_wh; /* success */ ++ ++ err = -EIO; ++ AuIOErr("%.*s Invalid whiteout entry type 0%o.\n", ++ AuDLNPair(wh_dentry), wh_dentry->d_inode->i_mode); ++ ++ out_wh: ++ dput(wh_dentry); ++ out: ++ return err; ++} ++ ++/* ++ * test if the @h_dentry sets opaque or not. ++ */ ++int au_diropq_test(struct dentry *h_dentry, struct au_branch *br) ++{ ++ int err; ++ struct inode *h_dir; ++ ++ h_dir = h_dentry->d_inode; ++ err = au_wh_test(h_dentry, &diropq_name, br, ++ au_test_h_perm_sio(h_dir, MAY_EXEC)); ++ return err; ++} ++ ++/* ++ * returns a negative dentry whose name is unique and temporary. ++ */ ++struct dentry *au_whtmp_lkup(struct dentry *h_parent, struct au_branch *br, ++ struct qstr *prefix) ++{ ++#define HEX_LEN 4 ++ struct dentry *dentry; ++ int i; ++ char defname[AUFS_WH_PFX_LEN * 2 + DNAME_INLINE_LEN_MIN + 1 ++ + HEX_LEN + 1], *name, *p; ++ static unsigned short cnt; ++ struct qstr qs; ++ ++ name = defname; ++ qs.len = sizeof(defname) - DNAME_INLINE_LEN_MIN + prefix->len - 1; ++ if (unlikely(prefix->len > DNAME_INLINE_LEN_MIN)) { ++ dentry = ERR_PTR(-ENAMETOOLONG); ++ if (unlikely(qs.len >= PATH_MAX)) ++ goto out; ++ dentry = ERR_PTR(-ENOMEM); ++ name = kmalloc(qs.len + 1, GFP_NOFS); ++ if (unlikely(!name)) ++ goto out; ++ } ++ ++ /* doubly whiteout-ed */ ++ memcpy(name, AUFS_WH_PFX AUFS_WH_PFX, AUFS_WH_PFX_LEN * 2); ++ p = name + AUFS_WH_PFX_LEN * 2; ++ memcpy(p, prefix->name, prefix->len); ++ p += prefix->len; ++ *p++ = '.'; ++ AuDebugOn(name + qs.len + 1 - p <= HEX_LEN); ++ ++ qs.name = name; ++ for (i = 0; i < 3; i++) { ++ sprintf(p, "%.*d", HEX_LEN, cnt++); ++ dentry = au_sio_lkup_one(&qs, h_parent, br); ++ if (IS_ERR(dentry) || !dentry->d_inode) ++ goto out_name; ++ dput(dentry); ++ } ++ /* AuWarn("could not get random name\n"); */ ++ dentry = ERR_PTR(-EEXIST); ++ AuDbg("%.*s\n", AuLNPair(&qs)); ++ BUG(); ++ ++ out_name: ++ if (name != defname) ++ kfree(name); ++ out: ++ return dentry; ++#undef HEX_LEN ++} ++ ++/* ++ * rename the @h_dentry on @br to the whiteouted temporary name. ++ */ ++int au_whtmp_ren(struct dentry *h_dentry, struct au_branch *br) ++{ ++ int err; ++ struct path h_path = { ++ .mnt = br->br_mnt ++ }; ++ struct inode *h_dir; ++ struct dentry *h_parent; ++ ++ h_parent = h_dentry->d_parent; /* dir inode is locked */ ++ h_dir = h_parent->d_inode; ++ IMustLock(h_dir); ++ ++ h_path.dentry = au_whtmp_lkup(h_parent, br, &h_dentry->d_name); ++ err = PTR_ERR(h_path.dentry); ++ if (IS_ERR(h_path.dentry)) ++ goto out; ++ ++ /* under the same dir, no need to lock_rename() */ ++ err = vfsub_rename(h_dir, h_dentry, h_dir, &h_path); ++ AuTraceErr(err); ++ dput(h_path.dentry); ++ ++ out: ++ return err; ++} ++ ++/* ---------------------------------------------------------------------- */ ++/* ++ * functions for removing a whiteout ++ */ ++ ++static int do_unlink_wh(struct inode *h_dir, struct path *h_path) ++{ ++ int force; ++ ++ /* ++ * forces superio when the dir has a sticky bit. ++ * this may be a violation of unix fs semantics. ++ */ ++ force = (h_dir->i_mode & S_ISVTX) ++ && h_path->dentry->d_inode->i_uid != current_fsuid(); ++ return vfsub_unlink(h_dir, h_path, force); ++} ++ ++int au_wh_unlink_dentry(struct inode *h_dir, struct path *h_path, ++ struct dentry *dentry) ++{ ++ int err; ++ ++ err = do_unlink_wh(h_dir, h_path); ++ if (!err && dentry) ++ au_set_dbwh(dentry, -1); ++ ++ return err; ++} ++ ++static int unlink_wh_name(struct dentry *h_parent, struct qstr *wh, ++ struct au_branch *br) ++{ ++ int err; ++ struct path h_path = { ++ .mnt = br->br_mnt ++ }; ++ ++ err = 0; ++ h_path.dentry = au_lkup_one(wh, h_parent, br, /*nd*/NULL); ++ if (IS_ERR(h_path.dentry)) ++ err = PTR_ERR(h_path.dentry); ++ else { ++ if (h_path.dentry->d_inode ++ && S_ISREG(h_path.dentry->d_inode->i_mode)) ++ err = do_unlink_wh(h_parent->d_inode, &h_path); ++ dput(h_path.dentry); ++ } ++ ++ return err; ++} ++ ++/* ---------------------------------------------------------------------- */ ++/* ++ * initialize/clean whiteout for a branch ++ */ ++ ++static void au_wh_clean(struct inode *h_dir, struct path *whpath, ++ const int isdir) ++{ ++ int err; ++ ++ if (!whpath->dentry->d_inode) ++ return; ++ ++ err = mnt_want_write(whpath->mnt); ++ if (!err) { ++ if (isdir) ++ err = vfsub_rmdir(h_dir, whpath); ++ else ++ err = vfsub_unlink(h_dir, whpath, /*force*/0); ++ mnt_drop_write(whpath->mnt); ++ } ++ if (unlikely(err)) ++ AuWarn("failed removing %.*s (%d), ignored.\n", ++ AuDLNPair(whpath->dentry), err); ++} ++ ++static int test_linkable(struct dentry *h_root) ++{ ++ struct inode *h_dir = h_root->d_inode; ++ ++ if (h_dir->i_op->link) ++ return 0; ++ ++ AuErr("%.*s (%s) doesn't support link(2), use noplink and rw+nolwh\n", ++ AuDLNPair(h_root), au_sbtype(h_root->d_sb)); ++ return -ENOSYS; ++} ++ ++/* todo: should this mkdir be done in /sbin/mount.aufs helper? */ ++static int au_whdir(struct inode *h_dir, struct path *path) ++{ ++ int err; ++ ++ err = -EEXIST; ++ if (!path->dentry->d_inode) { ++ int mode = S_IRWXU; ++ ++ if (au_test_nfs(path->dentry->d_sb)) ++ mode |= S_IXUGO; ++ err = mnt_want_write(path->mnt); ++ if (!err) { ++ err = vfsub_mkdir(h_dir, path, mode); ++ mnt_drop_write(path->mnt); ++ } ++ } else if (S_ISDIR(path->dentry->d_inode->i_mode)) ++ err = 0; ++ else ++ AuErr("unknown %.*s exists\n", AuDLNPair(path->dentry)); ++ ++ return err; ++} ++ ++struct au_wh_base { ++ const struct qstr *name; ++ struct dentry *dentry; ++}; ++ ++static void au_wh_init_ro(struct inode *h_dir, struct au_wh_base base[], ++ struct path *h_path) ++{ ++ h_path->dentry = base[AuBrWh_BASE].dentry; ++ au_wh_clean(h_dir, h_path, /*isdir*/0); ++ h_path->dentry = base[AuBrWh_PLINK].dentry; ++ au_wh_clean(h_dir, h_path, /*isdir*/1); ++ h_path->dentry = base[AuBrWh_ORPH].dentry; ++ au_wh_clean(h_dir, h_path, /*isdir*/1); ++} ++ ++/* ++ * returns tri-state, ++ * minus: error, caller should print the mesage ++ * zero: succuess ++ * plus: error, caller should NOT print the mesage ++ */ ++static int au_wh_init_rw_nolink(struct dentry *h_root, struct au_wbr *wbr, ++ int do_plink, struct au_wh_base base[], ++ struct path *h_path) ++{ ++ int err; ++ struct inode *h_dir; ++ ++ h_dir = h_root->d_inode; ++ h_path->dentry = base[AuBrWh_BASE].dentry; ++ au_wh_clean(h_dir, h_path, /*isdir*/0); ++ h_path->dentry = base[AuBrWh_PLINK].dentry; ++ if (do_plink) { ++ err = test_linkable(h_root); ++ if (unlikely(err)) { ++ err = 1; ++ goto out; ++ } ++ ++ err = au_whdir(h_dir, h_path); ++ if (unlikely(err)) ++ goto out; ++ wbr->wbr_plink = dget(base[AuBrWh_PLINK].dentry); ++ } else ++ au_wh_clean(h_dir, h_path, /*isdir*/1); ++ h_path->dentry = base[AuBrWh_ORPH].dentry; ++ err = au_whdir(h_dir, h_path); ++ if (unlikely(err)) ++ goto out; ++ wbr->wbr_orph = dget(base[AuBrWh_ORPH].dentry); ++ ++ out: ++ return err; ++} ++ ++/* ++ * for the moment, aufs supports the branch filesystem which does not support ++ * link(2). testing on FAT which does not support i_op->setattr() fully either, ++ * copyup failed. finally, such filesystem will not be used as the writable ++ * branch. ++ * ++ * returns tri-state, see above. ++ */ ++static int au_wh_init_rw(struct dentry *h_root, struct au_wbr *wbr, ++ int do_plink, struct au_wh_base base[], ++ struct path *h_path) ++{ ++ int err; ++ struct inode *h_dir; ++ ++ err = test_linkable(h_root); ++ if (unlikely(err)) { ++ err = 1; ++ goto out; ++ } ++ ++ /* ++ * todo: should this create be done in /sbin/mount.aufs helper? ++ */ ++ err = -EEXIST; ++ h_dir = h_root->d_inode; ++ if (!base[AuBrWh_BASE].dentry->d_inode) { ++ err = mnt_want_write(h_path->mnt); ++ if (!err) { ++ h_path->dentry = base[AuBrWh_BASE].dentry; ++ err = vfsub_create(h_dir, h_path, WH_MASK); ++ mnt_drop_write(h_path->mnt); ++ } ++ } else if (S_ISREG(base[AuBrWh_BASE].dentry->d_inode->i_mode)) ++ err = 0; ++ else ++ AuErr("unknown %.*s/%.*s exists\n", ++ AuDLNPair(h_root), AuDLNPair(base[AuBrWh_BASE].dentry)); ++ if (unlikely(err)) ++ goto out; ++ ++ h_path->dentry = base[AuBrWh_PLINK].dentry; ++ if (do_plink) { ++ err = au_whdir(h_dir, h_path); ++ if (unlikely(err)) ++ goto out; ++ wbr->wbr_plink = dget(base[AuBrWh_PLINK].dentry); ++ } else ++ au_wh_clean(h_dir, h_path, /*isdir*/1); ++ wbr->wbr_whbase = dget(base[AuBrWh_BASE].dentry); ++ ++ h_path->dentry = base[AuBrWh_ORPH].dentry; ++ err = au_whdir(h_dir, h_path); ++ if (unlikely(err)) ++ goto out; ++ wbr->wbr_orph = dget(base[AuBrWh_ORPH].dentry); ++ ++ out: ++ return err; ++} ++ ++/* ++ * initialize the whiteout base file/dir for @br. ++ */ ++int au_wh_init(struct dentry *h_root, struct au_branch *br, ++ struct super_block *sb) ++{ ++ int err, i; ++ const unsigned char do_plink ++ = !!au_opt_test(au_mntflags(sb), PLINK); ++ struct path path = { ++ .mnt = br->br_mnt ++ }; ++ struct inode *h_dir; ++ struct au_wbr *wbr = br->br_wbr; ++ static const struct qstr base_name[] = { ++ [AuBrWh_BASE] = { ++ .name = AUFS_BASE_NAME, ++ .len = sizeof(AUFS_BASE_NAME) - 1 ++ }, ++ [AuBrWh_PLINK] = { ++ .name = AUFS_PLINKDIR_NAME, ++ .len = sizeof(AUFS_PLINKDIR_NAME) - 1 ++ }, ++ [AuBrWh_ORPH] = { ++ .name = AUFS_ORPHDIR_NAME, ++ .len = sizeof(AUFS_ORPHDIR_NAME) - 1 ++ } ++ }; ++ struct au_wh_base base[] = { ++ [AuBrWh_BASE] = { ++ .name = base_name + AuBrWh_BASE, ++ .dentry = NULL ++ }, ++ [AuBrWh_PLINK] = { ++ .name = base_name + AuBrWh_PLINK, ++ .dentry = NULL ++ }, ++ [AuBrWh_ORPH] = { ++ .name = base_name + AuBrWh_ORPH, ++ .dentry = NULL ++ } ++ }; ++ ++ ++ h_dir = h_root->d_inode; ++ for (i = 0; i < AuBrWh_Last; i++) { ++ /* doubly whiteouted */ ++ struct dentry *d; ++ ++ d = au_wh_lkup(h_root, (void *)base[i].name, br); ++ err = PTR_ERR(d); ++ if (IS_ERR(d)) ++ goto out; ++ ++ base[i].dentry = d; ++ AuDebugOn(wbr ++ && wbr->wbr_wh[i] ++ && wbr->wbr_wh[i] != base[i].dentry); ++ } ++ ++ if (wbr) ++ for (i = 0; i < AuBrWh_Last; i++) { ++ dput(wbr->wbr_wh[i]); ++ wbr->wbr_wh[i] = NULL; ++ } ++ ++ err = 0; ++ ++ switch (br->br_perm) { ++ case AuBrPerm_RO: ++ case AuBrPerm_ROWH: ++ case AuBrPerm_RR: ++ case AuBrPerm_RRWH: ++ au_wh_init_ro(h_dir, base, &path); ++ break; ++ ++ case AuBrPerm_RWNoLinkWH: ++ err = au_wh_init_rw_nolink(h_root, wbr, do_plink, base, &path); ++ if (err > 0) ++ goto out; ++ else if (err) ++ goto out_err; ++ break; ++ ++ case AuBrPerm_RW: ++ err = au_wh_init_rw(h_root, wbr, do_plink, base, &path); ++ if (err > 0) ++ goto out; ++ else if (err) ++ goto out_err; ++ break; ++ ++ default: ++ BUG(); ++ } ++ goto out; /* success */ ++ ++ out_err: ++ AuErr("an error(%d) on the writable branch %.*s(%s)\n", ++ err, AuDLNPair(h_root), au_sbtype(h_root->d_sb)); ++ out: ++ for (i = 0; i < AuBrWh_Last; i++) ++ dput(base[i].dentry); ++ return err; ++} ++ ++/* ---------------------------------------------------------------------- */ ++/* ++ * whiteouts are all hard-linked usually. ++ * when its link count reaches a ceiling, we create a new whiteout base ++ * asynchronously. ++ */ ++ ++struct reinit_br_wh { ++ struct super_block *sb; ++ struct au_branch *br; ++}; ++ ++static void reinit_br_wh(void *arg) ++{ ++ int err; ++ aufs_bindex_t bindex; ++ struct path h_path; ++ struct reinit_br_wh *a = arg; ++ struct au_wbr *wbr; ++ struct inode *dir; ++ struct dentry *h_root; ++ struct au_hinode *hdir; ++ ++ err = 0; ++ wbr = a->br->br_wbr; ++ /* big aufs lock */ ++ si_noflush_write_lock(a->sb); ++ if (!au_br_writable(a->br->br_perm)) ++ goto out; ++ bindex = au_br_index(a->sb, a->br->br_id); ++ if (unlikely(bindex < 0)) ++ goto out; ++ ++ dir = a->sb->s_root->d_inode; ++ /* ii_read_lock_parent(dir); */ ++ hdir = au_hi(dir, bindex); ++ h_root = au_h_dptr(a->sb->s_root, bindex); ++ ++ au_hin_imtx_lock_nested(hdir, AuLsc_I_PARENT); ++ wbr_wh_write_lock(wbr); ++ err = au_h_verify(wbr->wbr_whbase, au_opt_udba(a->sb), hdir->hi_inode, ++ h_root, a->br); ++ if (!err) { ++ err = mnt_want_write(a->br->br_mnt); ++ if (!err) { ++ h_path.dentry = wbr->wbr_whbase; ++ h_path.mnt = a->br->br_mnt; ++ err = vfsub_unlink(hdir->hi_inode, &h_path, /*force*/0); ++ mnt_drop_write(a->br->br_mnt); ++ } ++ } else { ++ AuWarn("%.*s is moved, ignored\n", AuDLNPair(wbr->wbr_whbase)); ++ err = 0; ++ } ++ dput(wbr->wbr_whbase); ++ wbr->wbr_whbase = NULL; ++ if (!err) ++ err = au_wh_init(h_root, a->br, a->sb); ++ wbr_wh_write_unlock(wbr); ++ au_hin_imtx_unlock(hdir); ++ /* ii_read_unlock(dir); */ ++ ++ out: ++ if (wbr) ++ atomic_dec(&wbr->wbr_wh_running); ++ atomic_dec(&a->br->br_count); ++ au_nwt_done(&au_sbi(a->sb)->si_nowait); ++ si_write_unlock(a->sb); ++ kfree(arg); ++ if (unlikely(err)) ++ AuIOErr("err %d\n", err); ++} ++ ++static void kick_reinit_br_wh(struct super_block *sb, struct au_branch *br) ++{ ++ int do_dec, wkq_err; ++ struct reinit_br_wh *arg; ++ ++ do_dec = 1; ++ if (atomic_inc_return(&br->br_wbr->wbr_wh_running) != 1) ++ goto out; ++ ++ /* ignore ENOMEM */ ++ arg = kmalloc(sizeof(*arg), GFP_NOFS); ++ if (arg) { ++ /* ++ * dec(wh_running), kfree(arg) and dec(br_count) ++ * in reinit function ++ */ ++ arg->sb = sb; ++ arg->br = br; ++ atomic_inc(&br->br_count); ++ wkq_err = au_wkq_nowait(reinit_br_wh, arg, sb); ++ if (unlikely(wkq_err)) { ++ atomic_dec(&br->br_wbr->wbr_wh_running); ++ atomic_dec(&br->br_count); ++ kfree(arg); ++ } ++ do_dec = 0; ++ } ++ ++ out: ++ if (do_dec) ++ atomic_dec(&br->br_wbr->wbr_wh_running); ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++/* ++ * create the whiteout @wh. ++ */ ++static int link_or_create_wh(struct super_block *sb, aufs_bindex_t bindex, ++ struct dentry *wh) ++{ ++ int err; ++ struct path h_path = { ++ .dentry = wh ++ }; ++ struct au_branch *br; ++ struct au_wbr *wbr; ++ struct dentry *h_parent; ++ struct inode *h_dir; ++ ++ h_parent = wh->d_parent; /* dir inode is locked */ ++ h_dir = h_parent->d_inode; ++ IMustLock(h_dir); ++ ++ br = au_sbr(sb, bindex); ++ h_path.mnt = br->br_mnt; ++ wbr = br->br_wbr; ++ wbr_wh_read_lock(wbr); ++ if (wbr->wbr_whbase) { ++ err = vfsub_link(wbr->wbr_whbase, h_dir, &h_path); ++ if (!err || err != -EMLINK) ++ goto out; ++ ++ /* link count full. re-initialize br_whbase. */ ++ kick_reinit_br_wh(sb, br); ++ } ++ ++ /* return this error in this context */ ++ err = vfsub_create(h_dir, &h_path, WH_MASK); ++ ++ out: ++ wbr_wh_read_unlock(wbr); ++ return err; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++/* ++ * create or remove the diropq. ++ */ ++static struct dentry *do_diropq(struct dentry *dentry, aufs_bindex_t bindex, ++ unsigned int flags) ++{ ++ struct dentry *opq_dentry, *h_dentry; ++ struct super_block *sb; ++ struct au_branch *br; ++ int err; ++ ++ sb = dentry->d_sb; ++ br = au_sbr(sb, bindex); ++ h_dentry = au_h_dptr(dentry, bindex); ++ opq_dentry = au_lkup_one(&diropq_name, h_dentry, br, /*nd*/NULL); ++ if (IS_ERR(opq_dentry)) ++ goto out; ++ ++ if (au_ftest_diropq(flags, CREATE)) { ++ err = link_or_create_wh(sb, bindex, opq_dentry); ++ if (!err) { ++ au_set_dbdiropq(dentry, bindex); ++ goto out; /* success */ ++ } ++ } else { ++ struct path tmp = { ++ .dentry = opq_dentry, ++ .mnt = br->br_mnt ++ }; ++ err = do_unlink_wh(au_h_iptr(dentry->d_inode, bindex), &tmp); ++ if (!err) ++ au_set_dbdiropq(dentry, -1); ++ } ++ dput(opq_dentry); ++ opq_dentry = ERR_PTR(err); ++ ++ out: ++ return opq_dentry; ++} ++ ++struct do_diropq_args { ++ struct dentry **errp; ++ struct dentry *dentry; ++ aufs_bindex_t bindex; ++ unsigned int flags; ++}; ++ ++static void call_do_diropq(void *args) ++{ ++ struct do_diropq_args *a = args; ++ *a->errp = do_diropq(a->dentry, a->bindex, a->flags); ++} ++ ++struct dentry *au_diropq_sio(struct dentry *dentry, aufs_bindex_t bindex, ++ unsigned int flags) ++{ ++ struct dentry *diropq, *h_dentry; ++ ++ h_dentry = au_h_dptr(dentry, bindex); ++ if (!au_test_h_perm_sio(h_dentry->d_inode, MAY_EXEC | MAY_WRITE)) ++ diropq = do_diropq(dentry, bindex, flags); ++ else { ++ int wkq_err; ++ struct do_diropq_args args = { ++ .errp = &diropq, ++ .dentry = dentry, ++ .bindex = bindex, ++ .flags = flags ++ }; ++ ++ wkq_err = au_wkq_wait(call_do_diropq, &args); ++ if (unlikely(wkq_err)) ++ diropq = ERR_PTR(wkq_err); ++ } ++ ++ return diropq; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++/* ++ * lookup whiteout dentry. ++ * @h_parent: lower parent dentry which must exist and be locked ++ * @base_name: name of dentry which will be whiteouted ++ * returns dentry for whiteout. ++ */ ++struct dentry *au_wh_lkup(struct dentry *h_parent, struct qstr *base_name, ++ struct au_branch *br) ++{ ++ int err; ++ struct qstr wh_name; ++ struct dentry *wh_dentry; ++ ++ err = au_wh_name_alloc(&wh_name, base_name); ++ wh_dentry = ERR_PTR(err); ++ if (!err) { ++ wh_dentry = au_lkup_one(&wh_name, h_parent, br, /*nd*/NULL); ++ kfree(wh_name.name); ++ } ++ return wh_dentry; ++} ++ ++/* ++ * link/create a whiteout for @dentry on @bindex. ++ */ ++struct dentry *au_wh_create(struct dentry *dentry, aufs_bindex_t bindex, ++ struct dentry *h_parent) ++{ ++ struct dentry *wh_dentry; ++ struct super_block *sb; ++ int err; ++ ++ sb = dentry->d_sb; ++ wh_dentry = au_wh_lkup(h_parent, &dentry->d_name, au_sbr(sb, bindex)); ++ if (!IS_ERR(wh_dentry) && !wh_dentry->d_inode) { ++ err = link_or_create_wh(sb, bindex, wh_dentry); ++ if (!err) ++ au_set_dbwh(dentry, bindex); ++ else { ++ dput(wh_dentry); ++ wh_dentry = ERR_PTR(err); ++ } ++ } ++ ++ return wh_dentry; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++/* Delete all whiteouts in this directory on branch bindex. */ ++static int del_wh_children(struct dentry *h_dentry, struct au_nhash *whlist, ++ aufs_bindex_t bindex, struct au_branch *br) ++{ ++ int err, i; ++ struct qstr wh_name; ++ char *p; ++ struct hlist_head *head; ++ struct au_vdir_wh *tpos; ++ struct hlist_node *pos; ++ struct au_vdir_destr *str; ++ ++ err = -ENOMEM; ++ p = __getname(); ++ wh_name.name = p; ++ if (unlikely(!wh_name.name)) ++ goto out; ++ ++ err = 0; ++ memcpy(p, AUFS_WH_PFX, AUFS_WH_PFX_LEN); ++ p += AUFS_WH_PFX_LEN; ++ head = whlist->heads; ++ for (i = 0; !err && i < AuSize_NHASH; i++, head++) { ++ hlist_for_each_entry(tpos, pos, head, wh_hash) { ++ if (tpos->wh_bindex != bindex) ++ continue; ++ ++ str = &tpos->wh_str; ++ if (str->len + AUFS_WH_PFX_LEN <= PATH_MAX) { ++ memcpy(p, str->name, str->len); ++ wh_name.len = AUFS_WH_PFX_LEN + str->len; ++ err = unlink_wh_name(h_dentry, &wh_name, br); ++ if (!err) ++ continue; ++ break; ++ } ++ AuIOErr("whiteout name too long %.*s\n", ++ str->len, str->name); ++ err = -EIO; ++ break; ++ } ++ } ++ __putname(wh_name.name); ++ ++ out: ++ return err; ++} ++ ++struct del_wh_children_args { ++ int *errp; ++ struct dentry *h_dentry; ++ struct au_nhash *whlist; ++ aufs_bindex_t bindex; ++ struct au_branch *br; ++}; ++ ++static void call_del_wh_children(void *args) ++{ ++ struct del_wh_children_args *a = args; ++ *a->errp = del_wh_children(a->h_dentry, a->whlist, a->bindex, a->br); ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++/* ++ * rmdir the whiteouted temporary named dir @h_dentry. ++ * @whlist: whiteouted children. ++ */ ++int au_whtmp_rmdir(struct inode *dir, aufs_bindex_t bindex, ++ struct dentry *wh_dentry, struct au_nhash *whlist) ++{ ++ int err; ++ struct path h_tmp; ++ struct inode *wh_inode, *h_dir; ++ struct au_branch *br; ++ ++ h_dir = wh_dentry->d_parent->d_inode; /* dir inode is locked */ ++ IMustLock(h_dir); ++ ++ br = au_sbr(dir->i_sb, bindex); ++ wh_inode = wh_dentry->d_inode; ++ mutex_lock_nested(&wh_inode->i_mutex, AuLsc_I_CHILD); ++ ++ /* ++ * someone else might change some whiteouts while we were sleeping. ++ * it means this whlist may have an obsoleted entry. ++ */ ++ if (!au_test_h_perm_sio(wh_inode, MAY_EXEC | MAY_WRITE)) ++ err = del_wh_children(wh_dentry, whlist, bindex, br); ++ else { ++ int wkq_err; ++ struct del_wh_children_args args = { ++ .errp = &err, ++ .h_dentry = wh_dentry, ++ .whlist = whlist, ++ .bindex = bindex, ++ .br = br ++ }; ++ ++ wkq_err = au_wkq_wait(call_del_wh_children, &args); ++ if (unlikely(wkq_err)) ++ err = wkq_err; ++ } ++ mutex_unlock(&wh_inode->i_mutex); ++ ++ if (!err) { ++ h_tmp.dentry = wh_dentry; ++ h_tmp.mnt = br->br_mnt; ++ err = vfsub_rmdir(h_dir, &h_tmp); ++ /* d_drop(h_dentry); */ ++ } ++ ++ if (!err) { ++ if (au_ibstart(dir) == bindex) { ++ au_cpup_attr_timesizes(dir); ++ drop_nlink(dir); ++ } ++ return 0; /* success */ ++ } ++ ++ AuWarn("failed removing %.*s(%d), ignored\n", ++ AuDLNPair(wh_dentry), err); ++ return err; ++} ++ ++static void au_whtmp_rmdir_free_args(struct au_whtmp_rmdir_args *args) ++{ ++ au_nhash_fin(&args->whlist); ++ dput(args->wh_dentry); ++ iput(args->dir); ++ kfree(args); ++} ++ ++static void call_rmdir_whtmp(void *args) ++{ ++ int err; ++ struct au_whtmp_rmdir_args *a = args; ++ struct super_block *sb; ++ struct dentry *h_parent; ++ struct inode *h_dir; ++ struct au_branch *br; ++ struct au_hinode *hdir; ++ ++ /* rmdir by nfsd may cause deadlock with this i_mutex */ ++ /* mutex_lock(&a->dir->i_mutex); */ ++ sb = a->dir->i_sb; ++ si_noflush_read_lock(sb); ++ err = au_test_ro(sb, a->bindex, NULL); ++ if (unlikely(err)) ++ goto out; ++ ++ err = -EIO; ++ br = au_sbr(sb, a->bindex); ++ ii_write_lock_parent(a->dir); ++ h_parent = dget_parent(a->wh_dentry); ++ h_dir = h_parent->d_inode; ++ hdir = au_hi(a->dir, a->bindex); ++ au_hin_imtx_lock_nested(hdir, AuLsc_I_PARENT); ++ err = au_h_verify(a->wh_dentry, au_opt_udba(sb), h_dir, h_parent, br); ++ if (!err) { ++ err = mnt_want_write(br->br_mnt); ++ if (!err) { ++ err = au_whtmp_rmdir(a->dir, a->bindex, a->wh_dentry, ++ &a->whlist); ++ mnt_drop_write(br->br_mnt); ++ } ++ } ++ au_hin_imtx_unlock(hdir); ++ dput(h_parent); ++ ii_write_unlock(a->dir); ++ ++ out: ++ /* mutex_unlock(&a->dir->i_mutex); */ ++ au_nwt_done(&au_sbi(sb)->si_nowait); ++ si_read_unlock(sb); ++ au_whtmp_rmdir_free_args(a); ++ if (unlikely(err)) ++ AuIOErr("err %d\n", err); ++} ++ ++void au_whtmp_kick_rmdir(struct inode *dir, aufs_bindex_t bindex, ++ struct dentry *wh_dentry, struct au_nhash *whlist, ++ struct au_whtmp_rmdir_args *args) ++{ ++ int wkq_err; ++ ++ IMustLock(dir); ++ ++ /* all post-process will be done in do_rmdir_whtmp(). */ ++ args->dir = au_igrab(dir); ++ args->bindex = bindex; ++ args->wh_dentry = dget(wh_dentry); ++ au_nhash_init(&args->whlist); ++ au_nhash_move(&args->whlist, whlist); ++ wkq_err = au_wkq_nowait(call_rmdir_whtmp, args, dir->i_sb); ++ if (unlikely(wkq_err)) { ++ AuWarn("rmdir error %.*s (%d), ignored\n", ++ AuDLNPair(wh_dentry), wkq_err); ++ au_whtmp_rmdir_free_args(args); ++ } ++} +diff -urN ./fs/aufs/whout.h ./fs/aufs/whout.h +--- ./fs/aufs/whout.h 1970-01-01 01:00:00.000000000 +0100 ++++ ./fs/aufs/whout.h 2009-04-06 10:26:46.000000000 +0200 +@@ -0,0 +1,78 @@ ++/* ++ * Copyright (C) 2005-2009 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. ++ */ ++ ++/* ++ * whiteout for logical deletion and opaque directory ++ */ ++ ++#ifndef __AUFS_WHOUT_H__ ++#define __AUFS_WHOUT_H__ ++ ++#ifdef __KERNEL__ ++ ++#include <linux/fs.h> ++#include <linux/aufs_type.h> ++#include "dir.h" ++ ++/* whout.c */ ++int au_wh_name_alloc(struct qstr *wh, const struct qstr *name); ++struct au_branch; ++int au_wh_test(struct dentry *h_parent, struct qstr *wh_name, ++ struct au_branch *br, int try_sio); ++int au_diropq_test(struct dentry *h_dentry, struct au_branch *br); ++struct dentry *au_whtmp_lkup(struct dentry *h_parent, struct au_branch *br, ++ struct qstr *prefix); ++int au_whtmp_ren(struct dentry *h_dentry, struct au_branch *br); ++int au_wh_unlink_dentry(struct inode *h_dir, struct path *h_path, ++ struct dentry *dentry); ++int au_wh_init(struct dentry *h_parent, struct au_branch *br, ++ struct super_block *sb); ++ ++/* diropq flags */ ++#define AuDiropq_CREATE 1 ++#define au_ftest_diropq(flags, name) ((flags) & AuDiropq_##name) ++#define au_fset_diropq(flags, name) { (flags) |= AuDiropq_##name; } ++#define au_fclr_diropq(flags, name) { (flags) &= ~AuDiropq_##name; } ++ ++struct dentry *au_diropq_sio(struct dentry *dentry, aufs_bindex_t bindex, ++ unsigned int flags); ++struct dentry *au_wh_lkup(struct dentry *h_parent, struct qstr *base_name, ++ struct au_branch *br); ++struct dentry *au_wh_create(struct dentry *dentry, aufs_bindex_t bindex, ++ struct dentry *h_parent); ++ ++/* real rmdir for the whiteout-ed dir */ ++struct au_whtmp_rmdir_args { ++ struct inode *dir; ++ aufs_bindex_t bindex; ++ struct dentry *wh_dentry; ++ struct au_nhash whlist; ++}; ++ ++int au_whtmp_rmdir(struct inode *dir, aufs_bindex_t bindex, ++ struct dentry *wh_dentry, struct au_nhash *whlist); ++void au_whtmp_kick_rmdir(struct inode *dir, aufs_bindex_t bindex, ++ struct dentry *wh_dentry, struct au_nhash *whlist, ++ struct au_whtmp_rmdir_args *args); ++ ++/* ---------------------------------------------------------------------- */ ++ ++static inline struct dentry *au_diropq_create(struct dentry *dentry, ++ aufs_bindex_t bindex) ++{ ++ return au_diropq_sio(dentry, bindex, AuDiropq_CREATE); ++} ++ ++static inline int au_diropq_remove(struct dentry *dentry, aufs_bindex_t bindex) ++{ ++ return PTR_ERR(au_diropq_sio(dentry, bindex, !AuDiropq_CREATE)); ++} ++ ++#endif /* __KERNEL__ */ ++#endif /* __AUFS_WHOUT_H__ */ +diff -urN ./fs/aufs/wkq.c ./fs/aufs/wkq.c +--- ./fs/aufs/wkq.c 1970-01-01 01:00:00.000000000 +0100 ++++ ./fs/aufs/wkq.c 2009-04-06 10:26:46.000000000 +0200 +@@ -0,0 +1,249 @@ ++/* ++ * Copyright (C) 2005-2009 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. ++ */ ++ ++/* ++ * workqueue for asynchronous/super-io operations ++ * todo: try new dredential scheme ++ */ ++ ++#include "aufs.h" ++ ++/* internal workqueue named AUFS_WKQ_NAME */ ++static struct au_wkq { ++ struct workqueue_struct *q; ++ ++ /* balancing */ ++ atomic_t busy; ++} *au_wkq; ++ ++struct au_wkinfo { ++ struct work_struct wk; ++ struct super_block *sb; ++ ++ unsigned int flags; /* see wkq.h */ ++ ++ au_wkq_func_t func; ++ void *args; ++ ++ atomic_t *busyp; ++ struct completion *comp; ++}; ++ ++/* ---------------------------------------------------------------------- */ ++ ++static int enqueue(struct au_wkq *wkq, struct au_wkinfo *wkinfo) ++{ ++ wkinfo->busyp = &wkq->busy; ++ if (au_ftest_wkq(wkinfo->flags, WAIT)) ++ return !queue_work(wkq->q, &wkinfo->wk); ++ else ++ return !schedule_work(&wkinfo->wk); ++} ++ ++static void do_wkq(struct au_wkinfo *wkinfo) ++{ ++ unsigned int idle, n; ++ int i, idle_idx; ++ ++ while (1) { ++ if (au_ftest_wkq(wkinfo->flags, WAIT)) { ++ idle_idx = 0; ++ idle = UINT_MAX; ++ for (i = 0; i < aufs_nwkq; i++) { ++ n = atomic_inc_return(&au_wkq[i].busy); ++ if (n == 1 && !enqueue(au_wkq + i, wkinfo)) ++ return; /* success */ ++ ++ if (n < idle) { ++ idle_idx = i; ++ idle = n; ++ } ++ atomic_dec(&au_wkq[i].busy); ++ } ++ } else ++ idle_idx = aufs_nwkq; ++ ++ atomic_inc(&au_wkq[idle_idx].busy); ++ if (!enqueue(au_wkq + idle_idx, wkinfo)) ++ return; /* success */ ++ ++ /* impossible? */ ++ AuWarn1("failed to queue_work()\n"); ++ yield(); ++ } ++} ++ ++static void wkq_func(struct work_struct *wk) ++{ ++ struct au_wkinfo *wkinfo = container_of(wk, struct au_wkinfo, wk); ++ ++ wkinfo->func(wkinfo->args); ++ atomic_dec(wkinfo->busyp); ++ if (au_ftest_wkq(wkinfo->flags, WAIT)) ++ complete(wkinfo->comp); ++ else { ++ kobject_put(&au_sbi(wkinfo->sb)->si_kobj); ++ module_put(THIS_MODULE); ++ kfree(wkinfo); ++ } ++} ++ ++/* ++ * Since struct completion is large, try allocating it dynamically. ++ */ ++#if defined(CONFIG_4KSTACKS) || defined(AuTest4KSTACKS) ++#define AuWkqCompDeclare(name) struct completion *comp = NULL ++ ++static int au_wkq_comp_alloc(struct au_wkinfo *wkinfo, struct completion **comp) ++{ ++ *comp = kmalloc(sizeof(**comp), GFP_NOFS); ++ if (*comp) { ++ init_completion(*comp); ++ wkinfo->comp = *comp; ++ return 0; ++ } ++ return -ENOMEM; ++} ++ ++static void au_wkq_comp_free(struct completion *comp) ++{ ++ kfree(comp); ++} ++ ++#else ++ ++/* no braces */ ++#define AuWkqCompDeclare(name) \ ++ DECLARE_COMPLETION_ONSTACK(_ ## name); \ ++ struct completion *comp = &_ ## name ++ ++static int au_wkq_comp_alloc(struct au_wkinfo *wkinfo, struct completion **comp) ++{ ++ wkinfo->comp = *comp; ++ return 0; ++} ++ ++static void au_wkq_comp_free(struct completion *comp __maybe_unused) ++{ ++ /* empty */ ++} ++#endif /* 4KSTACKS */ ++ ++static void au_wkq_run(struct au_wkinfo *wkinfo) ++{ ++ au_dbg_verify_kthread(); ++ INIT_WORK(&wkinfo->wk, wkq_func); ++ do_wkq(wkinfo); ++} ++ ++int au_wkq_wait(au_wkq_func_t func, void *args) ++{ ++ int err; ++ AuWkqCompDeclare(comp); ++ struct au_wkinfo wkinfo = { ++ .flags = AuWkq_WAIT, ++ .func = func, ++ .args = args ++ }; ++ ++ err = au_wkq_comp_alloc(&wkinfo, &comp); ++ if (!err) { ++ au_wkq_run(&wkinfo); ++ /* no timeout, no interrupt */ ++ wait_for_completion(wkinfo.comp); ++ au_wkq_comp_free(comp); ++ } ++ ++ return err; ++ ++} ++ ++int au_wkq_nowait(au_wkq_func_t func, void *args, struct super_block *sb) ++{ ++ int err; ++ struct au_wkinfo *wkinfo; ++ ++ atomic_inc(&au_sbi(sb)->si_nowait.nw_len); ++ ++ /* ++ * wkq_func() must free this wkinfo. ++ * it highly depends upon the implementation of workqueue. ++ */ ++ err = 0; ++ wkinfo = kmalloc(sizeof(*wkinfo), GFP_NOFS); ++ if (wkinfo) { ++ wkinfo->sb = sb; ++ wkinfo->flags = !AuWkq_WAIT; ++ wkinfo->func = func; ++ wkinfo->args = args; ++ wkinfo->comp = NULL; ++ kobject_get(&au_sbi(sb)->si_kobj); ++ __module_get(THIS_MODULE); ++ ++ au_wkq_run(wkinfo); ++ } else { ++ err = -ENOMEM; ++ atomic_dec(&au_sbi(sb)->si_nowait.nw_len); ++ } ++ ++ return err; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++void au_nwt_init(struct au_nowait_tasks *nwt) ++{ ++ atomic_set(&nwt->nw_len, 0); ++ /* smp_mb();*/ /* atomic_set */ ++ init_waitqueue_head(&nwt->nw_wq); ++} ++ ++void au_wkq_fin(void) ++{ ++ int i; ++ ++ for (i = 0; i < aufs_nwkq; i++) ++ if (au_wkq[i].q && !IS_ERR(au_wkq[i].q)) ++ destroy_workqueue(au_wkq[i].q); ++ kfree(au_wkq); ++} ++ ++int __init au_wkq_init(void) ++{ ++ int err, i; ++ struct au_wkq *nowaitq; ++ ++ /* '+1' is for accounting of nowait queue */ ++ err = -ENOMEM; ++ au_wkq = kcalloc(aufs_nwkq + 1, sizeof(*au_wkq), GFP_NOFS); ++ if (unlikely(!au_wkq)) ++ goto out; ++ ++ err = 0; ++ for (i = 0; i < aufs_nwkq; i++) { ++ au_wkq[i].q = create_singlethread_workqueue(AUFS_WKQ_NAME); ++ if (au_wkq[i].q && !IS_ERR(au_wkq[i].q)) { ++ atomic_set(&au_wkq[i].busy, 0); ++ continue; ++ } ++ ++ err = PTR_ERR(au_wkq[i].q); ++ au_wkq_fin(); ++ goto out; ++ } ++ ++ /* nowait accounting */ ++ nowaitq = au_wkq + aufs_nwkq; ++ atomic_set(&nowaitq->busy, 0); ++ nowaitq->q = NULL; ++ /* smp_mb(); */ /* atomic_set */ ++ ++ out: ++ return err; ++} +diff -urN ./fs/aufs/wkq.h ./fs/aufs/wkq.h +--- ./fs/aufs/wkq.h 1970-01-01 01:00:00.000000000 +0100 ++++ ./fs/aufs/wkq.h 2009-04-06 10:26:46.000000000 +0200 +@@ -0,0 +1,72 @@ ++/* ++ * Copyright (C) 2005-2009 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. ++ */ ++ ++/* ++ * workqueue for asynchronous/super-io operations ++ * todo: try new credentials management scheme ++ */ ++ ++#ifndef __AUFS_WKQ_H__ ++#define __AUFS_WKQ_H__ ++ ++#ifdef __KERNEL__ ++ ++#include <linux/fs.h> ++#include <linux/sched.h> ++#include <linux/workqueue.h> ++#include <linux/aufs_type.h> ++ ++/* ---------------------------------------------------------------------- */ ++ ++/* ++ * in the next operation, wait for the 'nowait' tasks in system-wide workqueue ++ */ ++struct au_nowait_tasks { ++ atomic_t nw_len; ++ wait_queue_head_t nw_wq; ++}; ++ ++/* ---------------------------------------------------------------------- */ ++ ++typedef void (*au_wkq_func_t)(void *args); ++ ++/* wkq flags */ ++#define AuWkq_WAIT 1 ++#define au_ftest_wkq(flags, name) ((flags) & AuWkq_##name) ++#define au_fset_wkq(flags, name) { (flags) |= AuWkq_##name; } ++#define au_fclr_wkq(flags, name) { (flags) &= ~AuWkq_##name; } ++ ++/* wkq.c */ ++int au_wkq_wait(au_wkq_func_t func, void *args); ++int au_wkq_nowait(au_wkq_func_t func, void *args, struct super_block *sb); ++void au_nwt_init(struct au_nowait_tasks *nwt); ++int __init au_wkq_init(void); ++void au_wkq_fin(void); ++ ++/* ---------------------------------------------------------------------- */ ++ ++static inline int au_test_wkq(struct task_struct *tsk) ++{ ++ return !tsk->mm && !strcmp(tsk->comm, AUFS_WKQ_NAME); ++} ++ ++static inline void au_nwt_done(struct au_nowait_tasks *nwt) ++{ ++ if (!atomic_dec_return(&nwt->nw_len)) ++ wake_up_all(&nwt->nw_wq); ++} ++ ++static inline int au_nwt_flush(struct au_nowait_tasks *nwt) ++{ ++ wait_event(nwt->nw_wq, !atomic_read(&nwt->nw_len)); ++ return 0; ++} ++ ++#endif /* __KERNEL__ */ ++#endif /* __AUFS_WKQ_H__ */ +diff -urN ./fs/aufs/xino.c ./fs/aufs/xino.c +--- ./fs/aufs/xino.c 1970-01-01 01:00:00.000000000 +0100 ++++ ./fs/aufs/xino.c 2009-04-06 10:26:46.000000000 +0200 +@@ -0,0 +1,1178 @@ ++/* ++ * Copyright (C) 2005-2009 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. ++ */ ++ ++/* ++ * external inode number translation table and bitmap ++ */ ++ ++#include <linux/seq_file.h> ++#include <linux/uaccess.h> ++#include "aufs.h" ++ ++ssize_t xino_fread(au_readf_t func, struct file *file, void *buf, size_t size, ++ loff_t *pos) ++{ ++ ssize_t err; ++ mm_segment_t oldfs; ++ ++ oldfs = get_fs(); ++ set_fs(KERNEL_DS); ++ do { ++ /* todo: signal_pending? */ ++ err = func(file, (char __user *)buf, size, pos); ++ } while (err == -EAGAIN || err == -EINTR); ++ set_fs(oldfs); ++ ++#if 0 /* reserved for future use */ ++ if (err > 0) ++ fsnotify_access(file->f_dentry); ++#endif ++ ++ return err; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++static ssize_t do_xino_fwrite(au_writef_t func, struct file *file, void *buf, ++ size_t size, loff_t *pos) ++{ ++ ssize_t err; ++ mm_segment_t oldfs; ++ ++ oldfs = get_fs(); ++ set_fs(KERNEL_DS); ++ lockdep_off(); ++ do { ++ /* todo: signal_pending? */ ++ err = func(file, (const char __user *)buf, size, pos); ++ } while (err == -EAGAIN || err == -EINTR); ++ lockdep_on(); ++ set_fs(oldfs); ++ ++#if 0 /* reserved for future use */ ++ if (err > 0) ++ fsnotify_modify(file->f_dentry); ++#endif ++ ++ return err; ++} ++ ++struct do_xino_fwrite_args { ++ ssize_t *errp; ++ au_writef_t func; ++ struct file *file; ++ void *buf; ++ size_t size; ++ loff_t *pos; ++}; ++ ++static void call_do_xino_fwrite(void *args) ++{ ++ struct do_xino_fwrite_args *a = args; ++ *a->errp = do_xino_fwrite(a->func, a->file, a->buf, a->size, a->pos); ++} ++ ++ssize_t xino_fwrite(au_writef_t func, struct file *file, void *buf, size_t size, ++ loff_t *pos) ++{ ++ ssize_t err; ++ ++ /* todo: signal block and no wkq? */ ++ /* todo: new credential scheme */ ++ /* ++ * it breaks RLIMIT_FSIZE and normal user's limit, ++ * users should care about quota and real 'filesystem full.' ++ */ ++ if (!au_test_wkq(current)) { ++ int wkq_err; ++ struct do_xino_fwrite_args args = { ++ .errp = &err, ++ .func = func, ++ .file = file, ++ .buf = buf, ++ .size = size, ++ .pos = pos ++ }; ++ ++ wkq_err = au_wkq_wait(call_do_xino_fwrite, &args); ++ if (unlikely(wkq_err)) ++ err = wkq_err; ++ } else ++ err = do_xino_fwrite(func, file, buf, size, pos); ++ ++ return err; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++/* ++ * create a new xinofile at the same place/path as @base_file. ++ */ ++struct file *au_xino_create2(struct file *base_file, struct file *copy_src) ++{ ++ struct file *file; ++ struct dentry *base, *dentry, *parent; ++ struct inode *dir; ++ struct qstr *name; ++ int err; ++ ++ base = base_file->f_dentry; ++ parent = base->d_parent; /* dir inode is locked */ ++ dir = parent->d_inode; ++ IMustLock(dir); ++ ++ file = ERR_PTR(-EINVAL); ++ name = &base->d_name; ++ dentry = vfsub_lookup_one_len(name->name, parent, name->len); ++ if (IS_ERR(dentry)) { ++ file = (void *)dentry; ++ AuErr("%.*s lookup err %ld\n", AuLNPair(name), PTR_ERR(dentry)); ++ goto out; ++ } ++ ++ /* no need to mnt_want_write() since we call dentry_open() later */ ++ err = vfs_create(dir, dentry, S_IRUGO | S_IWUGO, NULL); ++ if (unlikely(err)) { ++ file = ERR_PTR(err); ++ AuErr("%.*s create err %d\n", AuLNPair(name), err); ++ goto out_dput; ++ } ++ ++ file = dentry_open(dget(dentry), mntget(base_file->f_vfsmnt), ++ O_RDWR | O_CREAT | O_EXCL | O_LARGEFILE, ++ current_cred()); ++ if (IS_ERR(file)) { ++ AuErr("%.*s open err %ld\n", AuLNPair(name), PTR_ERR(file)); ++ goto out_dput; ++ } ++ AuDebugOn(!file->f_op); ++ ++ err = vfsub_unlink(dir, &file->f_path, /*force*/0); ++ if (unlikely(err)) { ++ AuErr("%.*s unlink err %d\n", AuLNPair(name), err); ++ goto out_fput; ++ } ++ ++ if (copy_src) { ++ /* no one can touch copy_src xino */ ++ err = au_copy_file(file, copy_src, ++ i_size_read(copy_src->f_dentry->d_inode)); ++ if (unlikely(err)) { ++ AuErr("%.*s copy err %d\n", AuLNPair(name), err); ++ goto out_fput; ++ } ++ } ++ goto out_dput; /* success */ ++ ++ out_fput: ++ fput(file); ++ file = ERR_PTR(err); ++ out_dput: ++ dput(dentry); ++ out: ++ return file; ++} ++ ++struct au_xino_lock_dir { ++ struct au_hinode *hdir; ++ struct dentry *parent; ++ struct mutex *mtx; ++}; ++ ++static void au_xino_lock_dir(struct super_block *sb, struct file *xino, ++ struct au_xino_lock_dir *ldir) ++{ ++ aufs_bindex_t brid, bindex; ++ ++ ldir->hdir = NULL; ++ bindex = -1; ++ brid = au_xino_brid(sb); ++ if (brid >= 0) ++ bindex = au_br_index(sb, brid); ++ if (bindex >= 0) { ++ ldir->hdir = au_hi(sb->s_root->d_inode, bindex); ++ au_hin_imtx_lock_nested(ldir->hdir, AuLsc_I_PARENT); ++ } else { ++ ldir->parent = dget_parent(xino->f_dentry); ++ ldir->mtx = &ldir->parent->d_inode->i_mutex; ++ mutex_lock_nested(ldir->mtx, AuLsc_I_PARENT); ++ } ++} ++ ++static void au_xino_unlock_dir(struct au_xino_lock_dir *ldir) ++{ ++ if (ldir->hdir) ++ au_hin_imtx_unlock(ldir->hdir); ++ else { ++ mutex_unlock(ldir->mtx); ++ dput(ldir->parent); ++ } ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++/* trucate xino files asynchronously */ ++ ++int au_xino_trunc(struct super_block *sb, aufs_bindex_t bindex) ++{ ++ int err; ++ aufs_bindex_t bi, bend; ++ struct au_branch *br; ++ struct file *new_xino, *file; ++ struct super_block *h_sb; ++ struct au_xino_lock_dir ldir; ++ ++ err = -EINVAL; ++ bend = au_sbend(sb); ++ if (unlikely(bindex < 0 || bend < bindex)) ++ goto out; ++ br = au_sbr(sb, bindex); ++ file = br->br_xino.xi_file; ++ if (!file) ++ goto out; ++ ++ au_xino_lock_dir(sb, file, &ldir); ++ /* mnt_want_write() is unnecessary here */ ++ new_xino = au_xino_create2(file, file); ++ au_xino_unlock_dir(&ldir); ++ err = PTR_ERR(new_xino); ++ if (IS_ERR(new_xino)) ++ goto out; ++ err = 0; ++ fput(file); ++ br->br_xino.xi_file = new_xino; ++ ++ h_sb = br->br_mnt->mnt_sb; ++ for (bi = 0; bi <= bend; bi++) { ++ if (unlikely(bi == bindex)) ++ continue; ++ br = au_sbr(sb, bi); ++ if (br->br_mnt->mnt_sb != h_sb) ++ continue; ++ ++ fput(br->br_xino.xi_file); ++ br->br_xino.xi_file = new_xino; ++ get_file(new_xino); ++ } ++ ++ out: ++ return err; ++} ++ ++struct xino_do_trunc_args { ++ struct super_block *sb; ++ struct au_branch *br; ++}; ++ ++static void xino_do_trunc(void *_args) ++{ ++ struct xino_do_trunc_args *args = _args; ++ struct super_block *sb; ++ struct au_branch *br; ++ struct inode *dir; ++ int err; ++ aufs_bindex_t bindex; ++ ++ err = 0; ++ sb = args->sb; ++ dir = sb->s_root->d_inode; ++ br = args->br; ++ ++ si_noflush_write_lock(sb); ++ ii_read_lock_parent(dir); ++ bindex = au_br_index(sb, br->br_id); ++ err = au_xino_trunc(sb, bindex); ++ if (unlikely(err)) ++ goto out; ++ ++ if (br->br_xino.xi_file->f_dentry->d_inode->i_blocks ++ >= br->br_xino_upper) ++ br->br_xino_upper += AUFS_XINO_TRUNC_STEP; ++ ++ out: ++ ii_read_unlock(dir); ++ if (unlikely(err)) ++ AuWarn("err b%d, (%d)\n", bindex, err); ++ atomic_dec(&br->br_xino_running); ++ atomic_dec(&br->br_count); ++ au_nwt_done(&au_sbi(sb)->si_nowait); ++ si_write_unlock(sb); ++ kfree(args); ++} ++ ++static void xino_try_trunc(struct super_block *sb, struct au_branch *br) ++{ ++ struct xino_do_trunc_args *args; ++ int wkq_err; ++ ++ if (br->br_xino.xi_file->f_dentry->d_inode->i_blocks ++ < br->br_xino_upper) ++ return; ++ ++ if (atomic_inc_return(&br->br_xino_running) > 1) ++ goto out; ++ ++ /* lock and kfree() will be called in trunc_xino() */ ++ args = kmalloc(sizeof(*args), GFP_NOFS); ++ if (unlikely(!args)) { ++ AuErr1("no memory\n"); ++ goto out_args; ++ } ++ ++ atomic_inc(&br->br_count); ++ args->sb = sb; ++ args->br = br; ++ wkq_err = au_wkq_nowait(xino_do_trunc, args, sb); ++ if (!wkq_err) ++ return; /* success */ ++ ++ AuErr("wkq %d\n", wkq_err); ++ atomic_dec(&br->br_count); ++ ++ out_args: ++ kfree(args); ++ out: ++ atomic_dec(&br->br_xino_running); ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++static int au_xino_do_write(au_writef_t write, struct file *file, ++ ino_t h_ino, ino_t ino) ++{ ++ loff_t pos; ++ ssize_t sz; ++ ++ pos = h_ino; ++ if (unlikely(au_loff_max / sizeof(ino) - 1 < pos)) { ++ AuIOErr1("too large hi%lu\n", (unsigned long)h_ino); ++ return -EFBIG; ++ } ++ pos *= sizeof(ino); ++ sz = xino_fwrite(write, file, &ino, sizeof(ino), &pos); ++ if (sz == sizeof(ino)) ++ return 0; /* success */ ++ ++ AuIOErr("write failed (%zd)\n", sz); ++ return -EIO; ++} ++ ++/* ++ * write @ino to the xinofile for the specified branch{@sb, @bindex} ++ * at the position of @h_ino. ++ * even if @ino is zero, it is written to the xinofile and means no entry. ++ * if the size of the xino file on a specific filesystem exceeds the watermark, ++ * try truncating it. ++ */ ++int au_xino_write(struct super_block *sb, aufs_bindex_t bindex, ino_t h_ino, ++ ino_t ino) ++{ ++ int err; ++ unsigned int mnt_flags; ++ struct au_branch *br; ++ ++ BUILD_BUG_ON(sizeof(long long) != sizeof(au_loff_max) ++ || ((loff_t)-1) > 0); ++ ++ mnt_flags = au_mntflags(sb); ++ if (!au_opt_test(mnt_flags, XINO)) ++ return 0; ++ ++ br = au_sbr(sb, bindex); ++ err = au_xino_do_write(au_sbi(sb)->si_xwrite, br->br_xino.xi_file, ++ h_ino, ino); ++ if (!err) { ++ if (au_opt_test(mnt_flags, TRUNC_XINO) ++ && au_test_fs_trunc_xino(br->br_mnt->mnt_sb)) ++ xino_try_trunc(sb, br); ++ return 0; /* success */ ++ } ++ ++ AuIOErr("write failed (%d)\n", err); ++ return -EIO; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++/* aufs inode number bitmap */ ++ ++static const int page_bits = (int)PAGE_SIZE * BITS_PER_BYTE; ++static ino_t xib_calc_ino(unsigned long pindex, int bit) ++{ ++ ino_t ino; ++ ++ AuDebugOn(bit < 0 || page_bits <= bit); ++ ino = AUFS_FIRST_INO + pindex * page_bits + bit; ++ return ino; ++} ++ ++static void xib_calc_bit(ino_t ino, unsigned long *pindex, int *bit) ++{ ++ AuDebugOn(ino < AUFS_FIRST_INO); ++ ino -= AUFS_FIRST_INO; ++ *pindex = ino / page_bits; ++ *bit = ino % page_bits; ++} ++ ++static int xib_pindex(struct super_block *sb, unsigned long pindex) ++{ ++ int err; ++ loff_t pos; ++ ssize_t sz; ++ struct au_sbinfo *sbinfo; ++ struct file *xib; ++ unsigned long *p; ++ ++ sbinfo = au_sbi(sb); ++ MtxMustLock(&sbinfo->si_xib_mtx); ++ AuDebugOn(pindex > ULONG_MAX / PAGE_SIZE ++ || !au_opt_test(sbinfo->si_mntflags, XINO)); ++ ++ if (pindex == sbinfo->si_xib_last_pindex) ++ return 0; ++ ++ xib = sbinfo->si_xib; ++ p = sbinfo->si_xib_buf; ++ pos = sbinfo->si_xib_last_pindex; ++ pos *= PAGE_SIZE; ++ sz = xino_fwrite(sbinfo->si_xwrite, xib, p, PAGE_SIZE, &pos); ++ if (unlikely(sz != PAGE_SIZE)) ++ goto out; ++ ++ pos = pindex; ++ pos *= PAGE_SIZE; ++ if (i_size_read(xib->f_dentry->d_inode) >= pos + PAGE_SIZE) ++ sz = xino_fread(sbinfo->si_xread, xib, p, PAGE_SIZE, &pos); ++ else { ++ memset(p, 0, PAGE_SIZE); ++ sz = xino_fwrite(sbinfo->si_xwrite, xib, p, PAGE_SIZE, &pos); ++ } ++ if (sz == PAGE_SIZE) { ++ sbinfo->si_xib_last_pindex = pindex; ++ return 0; /* success */ ++ } ++ ++ out: ++ AuIOErr1("write failed (%zd)\n", sz); ++ err = sz; ++ if (sz >= 0) ++ err = -EIO; ++ return err; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++int au_xino_write0(struct super_block *sb, aufs_bindex_t bindex, ino_t h_ino, ++ ino_t ino) ++{ ++ int err, bit; ++ unsigned long pindex; ++ struct au_sbinfo *sbinfo; ++ ++ if (!au_opt_test(au_mntflags(sb), XINO)) ++ return 0; ++ ++ err = 0; ++ if (ino) { ++ sbinfo = au_sbi(sb); ++ xib_calc_bit(ino, &pindex, &bit); ++ AuDebugOn(page_bits <= bit); ++ mutex_lock(&sbinfo->si_xib_mtx); ++ err = xib_pindex(sb, pindex); ++ if (!err) { ++ clear_bit(bit, sbinfo->si_xib_buf); ++ sbinfo->si_xib_next_bit = bit; ++ } ++ mutex_unlock(&sbinfo->si_xib_mtx); ++ } ++ ++ if (!err) ++ err = au_xino_write(sb, bindex, h_ino, 0); ++ return err; ++} ++ ++/* get an unused inode number from bitmap */ ++ino_t au_xino_new_ino(struct super_block *sb) ++{ ++ ino_t ino; ++ unsigned long *p, pindex, ul, pend; ++ struct au_sbinfo *sbinfo; ++ struct file *file; ++ int free_bit, err; ++ ++ if (!au_opt_test(au_mntflags(sb), XINO)) ++ return iunique(sb, AUFS_FIRST_INO); ++ ++ sbinfo = au_sbi(sb); ++ mutex_lock(&sbinfo->si_xib_mtx); ++ p = sbinfo->si_xib_buf; ++ free_bit = sbinfo->si_xib_next_bit; ++ if (free_bit < page_bits && !test_bit(free_bit, p)) ++ goto out; /* success */ ++ free_bit = find_first_zero_bit(p, page_bits); ++ if (free_bit < page_bits) ++ goto out; /* success */ ++ ++ pindex = sbinfo->si_xib_last_pindex; ++ for (ul = pindex - 1; ul < ULONG_MAX; ul--) { ++ err = xib_pindex(sb, ul); ++ if (unlikely(err)) ++ goto out_err; ++ free_bit = find_first_zero_bit(p, page_bits); ++ if (free_bit < page_bits) ++ goto out; /* success */ ++ } ++ ++ file = sbinfo->si_xib; ++ pend = i_size_read(file->f_dentry->d_inode) / PAGE_SIZE; ++ for (ul = pindex + 1; ul <= pend; ul++) { ++ err = xib_pindex(sb, ul); ++ if (unlikely(err)) ++ goto out_err; ++ free_bit = find_first_zero_bit(p, page_bits); ++ if (free_bit < page_bits) ++ goto out; /* success */ ++ } ++ BUG(); ++ ++ out: ++ set_bit(free_bit, p); ++ sbinfo->si_xib_next_bit++; ++ pindex = sbinfo->si_xib_last_pindex; ++ mutex_unlock(&sbinfo->si_xib_mtx); ++ ino = xib_calc_ino(pindex, free_bit); ++ AuDbg("i%lu\n", (unsigned long)ino); ++ return ino; ++ out_err: ++ mutex_unlock(&sbinfo->si_xib_mtx); ++ AuDbg("i0\n"); ++ return 0; ++} ++ ++/* ++ * read @ino from xinofile for the specified branch{@sb, @bindex} ++ * at the position of @h_ino. ++ * if @ino does not exist and @do_new is true, get new one. ++ */ ++int au_xino_read(struct super_block *sb, aufs_bindex_t bindex, ino_t h_ino, ++ ino_t *ino) ++{ ++ int err; ++ ssize_t sz; ++ loff_t pos; ++ struct file *file; ++ struct au_sbinfo *sbinfo; ++ ++ *ino = 0; ++ if (!au_opt_test(au_mntflags(sb), XINO)) ++ return 0; /* no xino */ ++ ++ err = 0; ++ sbinfo = au_sbi(sb); ++ pos = h_ino; ++ if (unlikely(au_loff_max / sizeof(*ino) - 1 < pos)) { ++ AuIOErr1("too large hi%lu\n", (unsigned long)h_ino); ++ return -EFBIG; ++ } ++ pos *= sizeof(*ino); ++ ++ file = au_sbr(sb, bindex)->br_xino.xi_file; ++ if (i_size_read(file->f_dentry->d_inode) < pos + sizeof(*ino)) ++ return 0; /* no ino */ ++ ++ sz = xino_fread(sbinfo->si_xread, file, ino, sizeof(*ino), &pos); ++ if (sz == sizeof(*ino)) ++ return 0; /* success */ ++ ++ err = sz; ++ if (unlikely(sz >= 0)) { ++ err = -EIO; ++ AuIOErr("xino read error (%zd)\n", sz); ++ } ++ ++ return err; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++/* create and set a new xino file */ ++ ++struct file *au_xino_create(struct super_block *sb, char *fname, int silent) ++{ ++ struct file *file; ++ struct dentry *h_parent, *d; ++ struct inode *h_dir; ++ int err; ++ ++ /* ++ * at mount-time, and the xino file is the default path, ++ * hinotify is disabled so we have no inotify events to ignore. ++ * when a user specified the xino, we cannot get au_hdir to be ignored. ++ */ ++ file = vfsub_filp_open(fname, O_RDWR | O_CREAT | O_EXCL | O_LARGEFILE, ++ S_IRUGO | S_IWUGO); ++ if (IS_ERR(file)) { ++ if (!silent) ++ AuErr("open %s(%ld)\n", fname, PTR_ERR(file)); ++ return file; ++ } ++ ++ /* keep file count */ ++ h_parent = dget_parent(file->f_dentry); ++ h_dir = h_parent->d_inode; ++ mutex_lock_nested(&h_dir->i_mutex, AuLsc_I_PARENT); ++ /* mnt_want_write() is unnecessary here */ ++ err = vfsub_unlink(h_dir, &file->f_path, /*force*/0); ++ mutex_unlock(&h_dir->i_mutex); ++ dput(h_parent); ++ if (unlikely(err)) { ++ if (!silent) ++ AuErr("unlink %s(%d)\n", fname, err); ++ goto out; ++ } ++ ++ err = -EINVAL; ++ d = file->f_dentry; ++ if (unlikely(sb == d->d_sb)) { ++ if (!silent) ++ AuErr("%s must be outside\n", fname); ++ goto out; ++ } ++ if (unlikely(au_test_fs_bad_xino(d->d_sb))) { ++ if (!silent) ++ AuErr("xino doesn't support %s(%s)\n", ++ fname, au_sbtype(d->d_sb)); ++ goto out; ++ } ++ return file; /* success */ ++ ++ out: ++ fput(file); ++ file = ERR_PTR(err); ++ return file; ++} ++ ++/* ++ * find another branch who is on the same filesystem of the specified ++ * branch{@btgt}. search until @bend. ++ */ ++static int is_sb_shared(struct super_block *sb, aufs_bindex_t btgt, ++ aufs_bindex_t bend) ++{ ++ aufs_bindex_t bindex; ++ struct super_block *tgt_sb = au_sbr_sb(sb, btgt); ++ ++ for (bindex = 0; bindex < btgt; bindex++) ++ if (unlikely(tgt_sb == au_sbr_sb(sb, bindex))) ++ return bindex; ++ for (bindex++; bindex <= bend; bindex++) ++ if (unlikely(tgt_sb == au_sbr_sb(sb, bindex))) ++ return bindex; ++ return -1; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++/* ++ * initialize the xinofile for the specified branch @br ++ * at the place/path where @base_file indicates. ++ * test whether another branch is on the same filesystem or not, ++ * if @do_test is true. ++ */ ++int au_xino_br(struct super_block *sb, struct au_branch *br, ino_t h_ino, ++ struct file *base_file, int do_test) ++{ ++ int err; ++ ino_t ino; ++ aufs_bindex_t bend, bindex; ++ struct au_branch *shared_br, *b; ++ struct file *file; ++ struct super_block *tgt_sb; ++ ++ shared_br = NULL; ++ bend = au_sbend(sb); ++ if (do_test) { ++ tgt_sb = br->br_mnt->mnt_sb; ++ for (bindex = 0; bindex <= bend; bindex++) { ++ b = au_sbr(sb, bindex); ++ if (tgt_sb == b->br_mnt->mnt_sb) { ++ shared_br = b; ++ break; ++ } ++ } ++ } ++ ++ if (!shared_br || !shared_br->br_xino.xi_file) { ++ struct au_xino_lock_dir ldir; ++ ++ au_xino_lock_dir(sb, base_file, &ldir); ++ /* mnt_want_write() is unnecessary here */ ++ file = au_xino_create2(base_file, NULL); ++ au_xino_unlock_dir(&ldir); ++ err = PTR_ERR(file); ++ if (IS_ERR(file)) ++ goto out; ++ br->br_xino.xi_file = file; ++ } else { ++ br->br_xino.xi_file = shared_br->br_xino.xi_file; ++ get_file(br->br_xino.xi_file); ++ } ++ ++ ino = AUFS_ROOT_INO; ++ err = au_xino_do_write(au_sbi(sb)->si_xwrite, br->br_xino.xi_file, ++ h_ino, ino); ++ if (!err) ++ return 0; /* success */ ++ ++ ++ out: ++ return err; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++/* trucate a xino bitmap file */ ++ ++/* todo: slow */ ++static int do_xib_restore(struct super_block *sb, struct file *file, void *page) ++{ ++ int err, bit; ++ ssize_t sz; ++ unsigned long pindex; ++ loff_t pos, pend; ++ struct au_sbinfo *sbinfo; ++ au_readf_t func; ++ ino_t *ino; ++ unsigned long *p; ++ ++ err = 0; ++ sbinfo = au_sbi(sb); ++ p = sbinfo->si_xib_buf; ++ func = sbinfo->si_xread; ++ pend = i_size_read(file->f_dentry->d_inode); ++ pos = 0; ++ while (pos < pend) { ++ sz = xino_fread(func, file, page, PAGE_SIZE, &pos); ++ err = sz; ++ if (unlikely(sz <= 0)) ++ goto out; ++ ++ err = 0; ++ for (ino = page; sz > 0; ino++, sz -= sizeof(ino)) { ++ if (unlikely(*ino < AUFS_FIRST_INO)) ++ continue; ++ ++ xib_calc_bit(*ino, &pindex, &bit); ++ AuDebugOn(page_bits <= bit); ++ err = xib_pindex(sb, pindex); ++ if (!err) ++ set_bit(bit, p); ++ else ++ goto out; ++ } ++ } ++ ++ out: ++ return err; ++} ++ ++static int xib_restore(struct super_block *sb) ++{ ++ int err; ++ aufs_bindex_t bindex, bend; ++ void *page; ++ ++ err = -ENOMEM; ++ page = (void *)__get_free_page(GFP_NOFS); ++ if (unlikely(!page)) ++ goto out; ++ ++ err = 0; ++ bend = au_sbend(sb); ++ for (bindex = 0; !err && bindex <= bend; bindex++) ++ if (!bindex || is_sb_shared(sb, bindex, bindex - 1) < 0) ++ err = do_xib_restore ++ (sb, au_sbr(sb, bindex)->br_xino.xi_file, page); ++ else ++ AuDbg("b%d\n", bindex); ++ free_page((unsigned long)page); ++ ++ out: ++ return err; ++} ++ ++int au_xib_trunc(struct super_block *sb) ++{ ++ int err; ++ ssize_t sz; ++ loff_t pos; ++ struct au_xino_lock_dir ldir; ++ struct au_sbinfo *sbinfo; ++ unsigned long *p; ++ struct file *file; ++ ++ err = 0; ++ sbinfo = au_sbi(sb); ++ if (!au_opt_test(sbinfo->si_mntflags, XINO)) ++ goto out; ++ ++ file = sbinfo->si_xib; ++ if (i_size_read(file->f_dentry->d_inode) <= PAGE_SIZE) ++ goto out; ++ ++ au_xino_lock_dir(sb, file, &ldir); ++ /* mnt_want_write() is unnecessary here */ ++ file = au_xino_create2(sbinfo->si_xib, NULL); ++ au_xino_unlock_dir(&ldir); ++ err = PTR_ERR(file); ++ if (IS_ERR(file)) ++ goto out; ++ fput(sbinfo->si_xib); ++ sbinfo->si_xib = file; ++ ++ p = sbinfo->si_xib_buf; ++ memset(p, 0, PAGE_SIZE); ++ pos = 0; ++ sz = xino_fwrite(sbinfo->si_xwrite, sbinfo->si_xib, p, PAGE_SIZE, &pos); ++ if (unlikely(sz != PAGE_SIZE)) { ++ err = sz; ++ AuIOErr("err %d\n", err); ++ if (sz >= 0) ++ err = -EIO; ++ goto out; ++ } ++ ++ mutex_lock(&sbinfo->si_xib_mtx); ++ /* mnt_want_write() is unnecessary here */ ++ err = xib_restore(sb); ++ mutex_unlock(&sbinfo->si_xib_mtx); ++ ++out: ++ return err; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++/* ++ * xino mount option handlers ++ */ ++static au_readf_t find_readf(struct file *h_file) ++{ ++ const struct file_operations *fop = h_file->f_op; ++ ++ if (fop->read) ++ return fop->read; ++ if (fop->aio_read) ++ return do_sync_read; ++ return ERR_PTR(-ENOSYS); ++} ++ ++static au_writef_t find_writef(struct file *h_file) ++{ ++ const struct file_operations *fop = h_file->f_op; ++ ++ if (fop->write) ++ return fop->write; ++ if (fop->aio_write) ++ return do_sync_write; ++ return ERR_PTR(-ENOSYS); ++} ++ ++/* xino bitmap */ ++static void xino_clear_xib(struct super_block *sb) ++{ ++ struct au_sbinfo *sbinfo; ++ ++ sbinfo = au_sbi(sb); ++ sbinfo->si_xread = NULL; ++ sbinfo->si_xwrite = NULL; ++ if (sbinfo->si_xib) ++ fput(sbinfo->si_xib); ++ sbinfo->si_xib = NULL; ++ free_page((unsigned long)sbinfo->si_xib_buf); ++ sbinfo->si_xib_buf = NULL; ++} ++ ++static int au_xino_set_xib(struct super_block *sb, struct file *base) ++{ ++ int err; ++ loff_t pos; ++ struct au_sbinfo *sbinfo; ++ struct file *file; ++ ++ sbinfo = au_sbi(sb); ++ file = au_xino_create2(base, sbinfo->si_xib); ++ err = PTR_ERR(file); ++ if (IS_ERR(file)) ++ goto out; ++ if (sbinfo->si_xib) ++ fput(sbinfo->si_xib); ++ sbinfo->si_xib = file; ++ sbinfo->si_xread = find_readf(file); ++ sbinfo->si_xwrite = find_writef(file); ++ ++ err = -ENOMEM; ++ if (!sbinfo->si_xib_buf) ++ sbinfo->si_xib_buf = (void *)get_zeroed_page(GFP_NOFS); ++ if (unlikely(!sbinfo->si_xib_buf)) ++ goto out_unset; ++ ++ sbinfo->si_xib_last_pindex = 0; ++ sbinfo->si_xib_next_bit = 0; ++ if (i_size_read(file->f_dentry->d_inode) < PAGE_SIZE) { ++ pos = 0; ++ err = xino_fwrite(sbinfo->si_xwrite, file, sbinfo->si_xib_buf, ++ PAGE_SIZE, &pos); ++ if (unlikely(err != PAGE_SIZE)) ++ goto out_free; ++ } ++ err = 0; ++ goto out; /* success */ ++ ++ out_free: ++ free_page((unsigned long)sbinfo->si_xib_buf); ++ sbinfo->si_xib_buf = NULL; ++ if (err >= 0) ++ err = -EIO; ++ out_unset: ++ fput(sbinfo->si_xib); ++ sbinfo->si_xib = NULL; ++ sbinfo->si_xread = NULL; ++ sbinfo->si_xwrite = NULL; ++ out: ++ return err; ++} ++ ++/* xino for each branch */ ++static void xino_clear_br(struct super_block *sb) ++{ ++ aufs_bindex_t bindex, bend; ++ struct au_branch *br; ++ ++ bend = au_sbend(sb); ++ for (bindex = 0; bindex <= bend; bindex++) { ++ br = au_sbr(sb, bindex); ++ if (!br || !br->br_xino.xi_file) ++ continue; ++ ++ fput(br->br_xino.xi_file); ++ br->br_xino.xi_file = NULL; ++ } ++} ++ ++static int au_xino_set_br(struct super_block *sb, struct file *base) ++{ ++ int err; ++ ino_t ino; ++ aufs_bindex_t bindex, bend, bshared; ++ struct { ++ struct file *old, *new; ++ } *fpair, *p; ++ struct au_branch *br; ++ struct inode *inode; ++ au_writef_t writef; ++ ++ err = -ENOMEM; ++ bend = au_sbend(sb); ++ fpair = kcalloc(bend + 1, sizeof(*fpair), GFP_NOFS); ++ if (unlikely(!fpair)) ++ goto out; ++ ++ inode = sb->s_root->d_inode; ++ ino = AUFS_ROOT_INO; ++ writef = au_sbi(sb)->si_xwrite; ++ for (bindex = 0, p = fpair; bindex <= bend; bindex++, p++) { ++ br = au_sbr(sb, bindex); ++ bshared = is_sb_shared(sb, bindex, bindex - 1); ++ if (bshared >= 0) { ++ /* shared xino */ ++ *p = fpair[bshared]; ++ get_file(p->new); ++ } ++ ++ if (!p->new) { ++ /* new xino */ ++ p->old = br->br_xino.xi_file; ++ p->new = au_xino_create2(base, br->br_xino.xi_file); ++ err = PTR_ERR(p->new); ++ if (IS_ERR(p->new)) { ++ p->new = NULL; ++ goto out_pair; ++ } ++ } ++ ++ err = au_xino_do_write(writef, p->new, ++ au_h_iptr(inode, bindex)->i_ino, ino); ++ if (unlikely(err)) ++ goto out_pair; ++ } ++ ++ for (bindex = 0, p = fpair; bindex <= bend; bindex++, p++) { ++ br = au_sbr(sb, bindex); ++ if (br->br_xino.xi_file) ++ fput(br->br_xino.xi_file); ++ get_file(p->new); ++ br->br_xino.xi_file = p->new; ++ } ++ ++ out_pair: ++ for (bindex = 0, p = fpair; bindex <= bend; bindex++, p++) ++ if (p->new) ++ fput(p->new); ++ else ++ break; ++ kfree(fpair); ++ out: ++ return err; ++} ++ ++void au_xino_clr(struct super_block *sb) ++{ ++ struct au_sbinfo *sbinfo; ++ ++ au_xigen_clr(sb); ++ xino_clear_xib(sb); ++ xino_clear_br(sb); ++ sbinfo = au_sbi(sb); ++ /* lvalue, do not call au_mntflags() */ ++ au_opt_clr(sbinfo->si_mntflags, XINO); ++} ++ ++int au_xino_set(struct super_block *sb, struct au_opt_xino *xino, int remount) ++{ ++ int err, skip; ++ struct dentry *parent, *cur_parent; ++ struct qstr *dname, *cur_name; ++ struct file *cur_xino; ++ struct inode *dir; ++ struct au_sbinfo *sbinfo; ++ ++ err = 0; ++ sbinfo = au_sbi(sb); ++ parent = dget_parent(xino->file->f_dentry); ++ if (remount) { ++ skip = 0; ++ dname = &xino->file->f_dentry->d_name; ++ cur_xino = sbinfo->si_xib; ++ if (cur_xino) { ++ cur_parent = dget_parent(cur_xino->f_dentry); ++ cur_name = &cur_xino->f_dentry->d_name; ++ skip = (cur_parent == parent ++ && dname->len == cur_name->len ++ && !memcmp(dname->name, cur_name->name, ++ dname->len)); ++ dput(cur_parent); ++ } ++ if (skip) ++ goto out; ++ } ++ ++ au_opt_set(sbinfo->si_mntflags, XINO); ++ dir = parent->d_inode; ++ mutex_lock_nested(&dir->i_mutex, AuLsc_I_PARENT); ++ /* mnt_want_write() is unnecessary here */ ++ err = au_xino_set_xib(sb, xino->file); ++ if (!err) ++ err = au_xigen_set(sb, xino->file); ++ if (!err) ++ err = au_xino_set_br(sb, xino->file); ++ mutex_unlock(&dir->i_mutex); ++ if (!err) ++ goto out; /* success */ ++ ++ /* reset all */ ++ AuIOErr("failed creating xino(%d).\n", err); ++ ++ out: ++ dput(parent); ++ return err; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++/* ++ * create a xinofile at the default place/path. ++ */ ++struct file *au_xino_def(struct super_block *sb) ++{ ++ struct file *file; ++ char *page, *p; ++ struct au_branch *br; ++ struct super_block *h_sb; ++ struct path path; ++ aufs_bindex_t bend, bindex, bwr; ++ ++ br = NULL; ++ bend = au_sbend(sb); ++ bwr = -1; ++ for (bindex = 0; bindex <= bend; bindex++) { ++ br = au_sbr(sb, bindex); ++ if (au_br_writable(br->br_perm) ++ && !au_test_fs_bad_xino(br->br_mnt->mnt_sb)) { ++ bwr = bindex; ++ break; ++ } ++ } ++ ++ if (bwr >= 0) { ++ file = ERR_PTR(-ENOMEM); ++ page = __getname(); ++ if (unlikely(!page)) ++ goto out; ++ path.mnt = br->br_mnt; ++ path.dentry = au_h_dptr(sb->s_root, bwr); ++ p = d_path(&path, page, PATH_MAX - sizeof(AUFS_XINO_FNAME)); ++ file = (void *)p; ++ if (!IS_ERR(p)) { ++ strcat(p, "/" AUFS_XINO_FNAME); ++ AuDbg("%s\n", p); ++ file = au_xino_create(sb, p, /*silent*/0); ++ if (!IS_ERR(file)) ++ au_xino_brid_set(sb, br->br_id); ++ } ++ __putname(page); ++ } else { ++ file = au_xino_create(sb, AUFS_XINO_DEFPATH, /*silent*/0); ++ if (IS_ERR(file)) ++ goto out; ++ h_sb = file->f_dentry->d_sb; ++ if (unlikely(au_test_fs_bad_xino(h_sb))) { ++ AuErr("xino doesn't support %s(%s)\n", ++ AUFS_XINO_DEFPATH, au_sbtype(h_sb)); ++ fput(file); ++ file = ERR_PTR(-EINVAL); ++ } ++ if (!IS_ERR(file)) ++ au_xino_brid_set(sb, -1); ++ } ++ ++ out: ++ return file; ++} ++ ++/* ---------------------------------------------------------------------- */ ++ ++int au_xino_path(struct seq_file *seq, struct file *file) ++{ ++ int err; ++ ++ err = au_seq_path(seq, &file->f_path); ++ if (unlikely(err < 0)) ++ goto out; ++ ++ err = 0; ++#define Deleted "\\040(deleted)" ++ seq->count -= sizeof(Deleted) - 1; ++ AuDebugOn(memcmp(seq->buf + seq->count, Deleted, ++ sizeof(Deleted) - 1)); ++#undef Deleted ++ ++ out: ++ return err; ++} +diff -urN ./include/linux/aufs_type.h ./include/linux/aufs_type.h +--- ./include/linux/aufs_type.h 1970-01-01 01:00:00.000000000 +0100 ++++ ./include/linux/aufs_type.h 2009-04-06 10:26:46.000000000 +0200 +@@ -0,0 +1,98 @@ ++/* ++ * Copyright (C) 2005-2009 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. ++ */ ++ ++#ifndef __AUFS_TYPE_H__ ++#define __AUFS_TYPE_H__ ++ ++#include <linux/ioctl.h> ++ ++#define AUFS_VERSION "2-standalone.tree-29-20090406" ++ ++/* todo? move this to linux-2.6.19/include/magic.h */ ++#define AUFS_SUPER_MAGIC ('a' << 24 | 'u' << 16 | 'f' << 8 | 's') ++ ++/* ---------------------------------------------------------------------- */ ++ ++#ifdef CONFIG_AUFS_BRANCH_MAX_127 ++/* some environments treat 'char' as 'unsigned char' by default */ ++typedef signed char aufs_bindex_t; ++#define AUFS_BRANCH_MAX 127 ++#else ++typedef short aufs_bindex_t; ++#ifdef CONFIG_AUFS_BRANCH_MAX_511 ++#define AUFS_BRANCH_MAX 511 ++#elif defined(CONFIG_AUFS_BRANCH_MAX_1023) ++#define AUFS_BRANCH_MAX 1023 ++#elif defined(CONFIG_AUFS_BRANCH_MAX_32767) ++#define AUFS_BRANCH_MAX 32767 ++#endif ++#endif ++ ++#ifdef __KERNEL__ ++#ifndef AUFS_BRANCH_MAX ++#error unknown CONFIG_AUFS_BRANCH_MAX value ++#endif ++#endif /* __KERNEL__ */ ++ ++/* ---------------------------------------------------------------------- */ ++ ++#define AUFS_NAME "aufs" ++#define AUFS_FSTYPE AUFS_NAME ++ ++#define AUFS_ROOT_INO 2 ++#define AUFS_FIRST_INO 11 ++ ++#define AUFS_WH_PFX ".wh." ++#define AUFS_WH_PFX_LEN ((int)sizeof(AUFS_WH_PFX) - 1) ++#define AUFS_XINO_FNAME "." AUFS_NAME ".xino" ++#define AUFS_XINO_DEFPATH "/tmp/" AUFS_XINO_FNAME ++#define AUFS_XINO_TRUNC_INIT 64 /* blocks */ ++#define AUFS_XINO_TRUNC_STEP 4 /* blocks */ ++#define AUFS_DIRWH_DEF 3 ++#define AUFS_RDCACHE_DEF 10 /* seconds */ ++#define AUFS_WKQ_NAME AUFS_NAME "d" ++#define AUFS_NWKQ_DEF 4 ++#define AUFS_MFS_SECOND_DEF 30 /* seconds */ ++#define AUFS_PLINK_WARN 100 /* number of plinks */ ++ ++#define AUFS_DIROPQ_NAME AUFS_WH_PFX ".opq" /* whiteouted doubly */ ++#define AUFS_WH_DIROPQ AUFS_WH_PFX AUFS_DIROPQ_NAME ++ ++#define AUFS_BASE_NAME AUFS_WH_PFX AUFS_NAME ++#define AUFS_PLINKDIR_NAME AUFS_WH_PFX "plnk" ++#define AUFS_ORPHDIR_NAME AUFS_WH_PFX "orph" ++ ++/* doubly whiteouted */ ++#define AUFS_WH_BASE AUFS_WH_PFX AUFS_BASE_NAME ++#define AUFS_WH_PLINKDIR AUFS_WH_PFX AUFS_PLINKDIR_NAME ++#define AUFS_WH_ORPHDIR AUFS_WH_PFX AUFS_ORPHDIR_NAME ++ ++/* branch permission */ ++#define AUFS_BRPERM_RW "rw" ++#define AUFS_BRPERM_RO "ro" ++#define AUFS_BRPERM_RR "rr" ++#define AUFS_BRPERM_WH "wh" ++#define AUFS_BRPERM_NLWH "nolwh" ++#define AUFS_BRPERM_ROWH AUFS_BRPERM_RO "+" AUFS_BRPERM_WH ++#define AUFS_BRPERM_RRWH AUFS_BRPERM_RR "+" AUFS_BRPERM_WH ++#define AUFS_BRPERM_RWNLWH AUFS_BRPERM_RW "+" AUFS_BRPERM_NLWH ++ ++/* ---------------------------------------------------------------------- */ ++ ++/* ioctl */ ++enum { ++ AuCtl_PLINK_MAINT, ++ AuCtl_PLINK_CLEAN ++}; ++ ++#define AuCtlType 'A' ++#define AUFS_CTL_PLINK_MAINT _IO(AuCtlType, AuCtl_PLINK_MAINT) ++#define AUFS_CTL_PLINK_CLEAN _IO(AuCtlType, AuCtl_PLINK_CLEAN) ++ ++#endif /* __AUFS_TYPE_H__ */ +aufs2 standalone patch for linux-2.6.29 + +diff --git a/fs/ecryptfs/inode.c b/fs/ecryptfs/inode.c +index 55b3145..4af299a 100644 +--- a/fs/ecryptfs/inode.c ++++ b/fs/ecryptfs/inode.c +@@ -459,9 +459,6 @@ out_lock: + unlock_dir(lower_dir_dentry); + dput(lower_new_dentry); + dput(lower_old_dentry); +- d_drop(lower_old_dentry); +- d_drop(new_dentry); +- d_drop(old_dentry); + return rc; + } + +@@ -473,7 +470,10 @@ static int ecryptfs_unlink(struct inode *dir, struct dentry *dentry) + struct dentry *lower_dir_dentry; + + lower_dir_dentry = lock_parent(lower_dentry); ++ dget(lower_dentry); ++ atomic_inc(&lower_dentry->d_inode->i_count); + rc = vfs_unlink(lower_dir_inode, lower_dentry); ++ dput(lower_dentry); + if (rc) { + printk(KERN_ERR "Error in vfs_unlink; rc = [%d]\n", rc); + goto out_unlock; +@@ -484,6 +484,7 @@ static int ecryptfs_unlink(struct inode *dir, struct dentry *dentry) + dentry->d_inode->i_ctime = dir->i_ctime; + d_drop(dentry); + out_unlock: ++ iput(lower_dentry->d_inode); + unlock_dir(lower_dir_dentry); + return rc; + } +@@ -569,8 +570,12 @@ static int ecryptfs_rmdir(struct inode *dir, struct dentry *dentry) + fsstack_copy_attr_times(dir, lower_dir_dentry->d_inode); + dir->i_nlink = lower_dir_dentry->d_inode->i_nlink; + unlock_dir(lower_dir_dentry); +- if (!rc) ++ if (!rc) { ++ struct inode *inode = dentry->d_inode; ++ inode->i_nlink = ecryptfs_inode_to_lower(inode)->i_nlink; ++ inode->i_ctime = dir->i_ctime; + d_drop(dentry); ++ } + dput(dentry); + return rc; + } +aufs2 standalone patch for linux-2.6.29 + +diff --git a/fs/Kconfig b/fs/Kconfig +index 93945dd..75156dd 100644 +--- a/fs/Kconfig ++++ b/fs/Kconfig +@@ -222,6 +222,7 @@ source "fs/qnx4/Kconfig" + source "fs/romfs/Kconfig" + source "fs/sysv/Kconfig" + source "fs/ufs/Kconfig" ++source "fs/aufs/Kconfig" + + endif # MISC_FILESYSTEMS + +diff --git a/fs/Makefile b/fs/Makefile +index dc20db3..a4e9a65 100644 +--- a/fs/Makefile ++++ b/fs/Makefile +@@ -124,3 +124,4 @@ obj-$(CONFIG_DEBUG_FS) += debugfs/ + obj-$(CONFIG_OCFS2_FS) += ocfs2/ + obj-$(CONFIG_BTRFS_FS) += btrfs/ + obj-$(CONFIG_GFS2_FS) += gfs2/ ++obj-$(CONFIG_AUFS_FS) += aufs/ +diff --git a/fs/namei.c b/fs/namei.c +index bbc15c2..e54d1b2 100644 +--- a/fs/namei.c ++++ b/fs/namei.c +@@ -335,6 +335,7 @@ int deny_write_access(struct file * file) + + return 0; + } ++EXPORT_SYMBOL(deny_write_access); + + /** + * path_get - get a reference to a path +@@ -1196,7 +1197,7 @@ out: + * needs parent already locked. Doesn't follow mounts. + * SMP-safe. + */ +-static struct dentry *lookup_hash(struct nameidata *nd) ++struct dentry *lookup_hash(struct nameidata *nd) + { + int err; + +@@ -1205,8 +1206,9 @@ static struct dentry *lookup_hash(struct nameidata *nd) + return ERR_PTR(err); + return __lookup_hash(&nd->last, nd->path.dentry, nd); + } ++EXPORT_SYMBOL(lookup_hash); + +-static int __lookup_one_len(const char *name, struct qstr *this, ++int __lookup_one_len(const char *name, struct qstr *this, + struct dentry *base, int len) + { + unsigned long hash; +@@ -1227,6 +1229,7 @@ static int __lookup_one_len(const char *name, struct qstr *this, + this->hash = end_name_hash(hash); + return 0; + } ++EXPORT_SYMBOL(__lookup_one_len); + + /** + * lookup_one_len - filesystem helper to lookup single pathname component +diff --git a/fs/namespace.c b/fs/namespace.c +index 06f8e63..b002ec3 100644 +--- a/fs/namespace.c ++++ b/fs/namespace.c +@@ -37,6 +37,9 @@ + + /* spinlock for vfsmount related operations, inplace of dcache_lock */ + __cacheline_aligned_in_smp DEFINE_SPINLOCK(vfsmount_lock); ++#ifdef CONFIG_AUFS_EXPORT ++EXPORT_SYMBOL(vfsmount_lock); ++#endif + + static int event; + static DEFINE_IDA(mnt_id_ida); +diff --git a/fs/open.c b/fs/open.c +index a3a78ce..d2f61c7 100644 +--- a/fs/open.c ++++ b/fs/open.c +@@ -220,6 +220,7 @@ int do_truncate(struct dentry *dentry, loff_t length, unsigned int time_attrs, + mutex_unlock(&dentry->d_inode->i_mutex); + return err; + } ++EXPORT_SYMBOL(do_truncate); + + static long do_sys_truncate(const char __user *pathname, loff_t length) + { +diff --git a/fs/super.c b/fs/super.c +index 6ce5014..af66b69 100644 +--- a/fs/super.c ++++ b/fs/super.c +@@ -287,6 +287,7 @@ int fsync_super(struct super_block *sb) + __fsync_super(sb); + return sync_blockdev(sb->s_bdev); + } ++EXPORT_SYMBOL(fsync_super); + + /** + * generic_shutdown_super - common helper for ->kill_sb() +diff --git a/include/linux/Kbuild b/include/linux/Kbuild +index 106c3ba..d0c7262 100644 +--- a/include/linux/Kbuild ++++ b/include/linux/Kbuild +@@ -34,6 +34,7 @@ header-y += atmppp.h + header-y += atmsap.h + header-y += atmsvc.h + header-y += atm_zatm.h ++header-y += aufs_type.h + header-y += auto_fs4.h + header-y += ax25.h + header-y += b1lli.h +diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h +index 23bf02f..49e5b47 100644 +--- a/include/linux/lockdep.h ++++ b/include/linux/lockdep.h +@@ -58,7 +58,7 @@ enum lock_usage_bit + #define LOCKF_USED_IN_IRQ_READ \ + (LOCKF_USED_IN_HARDIRQ_READ | LOCKF_USED_IN_SOFTIRQ_READ) + +-#define MAX_LOCKDEP_SUBCLASSES 8UL ++#define MAX_LOCKDEP_SUBCLASSES 12UL + + /* + * Lock-classes are keyed via unique addresses, by embedding the +diff --git a/include/linux/namei.h b/include/linux/namei.h +index fc2e035..182d43b 100644 +--- a/include/linux/namei.h ++++ b/include/linux/namei.h +@@ -75,6 +75,9 @@ extern struct file *lookup_instantiate_filp(struct nameidata *nd, struct dentry + extern struct file *nameidata_to_filp(struct nameidata *nd, int flags); + extern void release_open_intent(struct nameidata *); + ++extern struct dentry *lookup_hash(struct nameidata *nd); ++extern int __lookup_one_len(const char *name, struct qstr *this, ++ struct dentry *base, int len); + extern struct dentry *lookup_one_len(const char *, struct dentry *, int); + extern struct dentry *lookup_one_noperm(const char *, struct dentry *); + +diff --git a/security/device_cgroup.c b/security/device_cgroup.c +index 3aacd0f..b900dc3 100644 +--- a/security/device_cgroup.c ++++ b/security/device_cgroup.c +@@ -507,6 +507,7 @@ acc_check: + + return -EPERM; + } ++EXPORT_SYMBOL(devcgroup_inode_permission); + + int devcgroup_inode_mknod(int mode, dev_t dev) + { +diff --git a/security/security.c b/security/security.c +index c3586c0..8b0495f 100644 +--- a/security/security.c ++++ b/security/security.c +@@ -389,6 +389,7 @@ int security_path_mkdir(struct path *path, struct dentry *dentry, int mode) + return 0; + return security_ops->path_mkdir(path, dentry, mode); + } ++EXPORT_SYMBOL(security_path_mkdir); + + int security_path_rmdir(struct path *path, struct dentry *dentry) + { +@@ -396,6 +397,7 @@ int security_path_rmdir(struct path *path, struct dentry *dentry) + return 0; + return security_ops->path_rmdir(path, dentry); + } ++EXPORT_SYMBOL(security_path_rmdir); + + int security_path_unlink(struct path *path, struct dentry *dentry) + { +@@ -403,6 +405,7 @@ int security_path_unlink(struct path *path, struct dentry *dentry) + return 0; + return security_ops->path_unlink(path, dentry); + } ++EXPORT_SYMBOL(security_path_unlink); + + int security_path_symlink(struct path *path, struct dentry *dentry, + const char *old_name) +@@ -411,6 +414,7 @@ int security_path_symlink(struct path *path, struct dentry *dentry, + return 0; + return security_ops->path_symlink(path, dentry, old_name); + } ++EXPORT_SYMBOL(security_path_symlink); + + int security_path_link(struct dentry *old_dentry, struct path *new_dir, + struct dentry *new_dentry) +@@ -419,6 +423,7 @@ int security_path_link(struct dentry *old_dentry, struct path *new_dir, + return 0; + return security_ops->path_link(old_dentry, new_dir, new_dentry); + } ++EXPORT_SYMBOL(security_path_link); + + int security_path_rename(struct path *old_dir, struct dentry *old_dentry, + struct path *new_dir, struct dentry *new_dentry) +@@ -429,6 +434,7 @@ int security_path_rename(struct path *old_dir, struct dentry *old_dentry, + return security_ops->path_rename(old_dir, old_dentry, new_dir, + new_dentry); + } ++EXPORT_SYMBOL(security_path_rename); + + int security_path_truncate(struct path *path, loff_t length, + unsigned int time_attrs) +@@ -437,6 +443,7 @@ int security_path_truncate(struct path *path, loff_t length, + return 0; + return security_ops->path_truncate(path, length, time_attrs); + } ++EXPORT_SYMBOL(security_path_truncate); + #endif + + int security_inode_create(struct inode *dir, struct dentry *dentry, int mode) +@@ -506,6 +513,7 @@ int security_inode_readlink(struct dentry *dentry) + return 0; + return security_ops->inode_readlink(dentry); + } ++EXPORT_SYMBOL(security_inode_readlink); + + int security_inode_follow_link(struct dentry *dentry, struct nameidata *nd) + { |